diff --git a/[refs] b/[refs]
index e3efa24b6c47..db3e9e42b222 100644
--- a/[refs]
+++ b/[refs]
@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 5f0b2976cb2b62668a076f54419c24b8ab677167
+refs/heads/master: 5f78e4d33945b291d12765cdd7e4304f437b9361
diff --git a/trunk/Documentation/DMA-API.txt b/trunk/Documentation/DMA-API.txt
index b939ebb62871..80d150458c80 100644
--- a/trunk/Documentation/DMA-API.txt
+++ b/trunk/Documentation/DMA-API.txt
@@ -145,7 +145,7 @@ Part Ic - DMA addressing limitations
 int
 dma_supported(struct device *dev, u64 mask)
 int
-pci_dma_supported(struct device *dev, u64 mask)
+pci_dma_supported(struct pci_dev *hwdev, u64 mask)
 
 Checks to see if the device can support DMA to the memory described by
 mask.
@@ -189,7 +189,7 @@ dma_addr_t
 dma_map_single(struct device *dev, void *cpu_addr, size_t size,
 		      enum dma_data_direction direction)
 dma_addr_t
-pci_map_single(struct device *dev, void *cpu_addr, size_t size,
+pci_map_single(struct pci_dev *hwdev, void *cpu_addr, size_t size,
 		      int direction)
 
 Maps a piece of processor virtual memory so it can be accessed by the
@@ -395,6 +395,71 @@ Notes:  You must do this:
 
 See also dma_map_single().
 
+dma_addr_t
+dma_map_single_attrs(struct device *dev, void *cpu_addr, size_t size,
+		     enum dma_data_direction dir,
+		     struct dma_attrs *attrs)
+
+void
+dma_unmap_single_attrs(struct device *dev, dma_addr_t dma_addr,
+		       size_t size, enum dma_data_direction dir,
+		       struct dma_attrs *attrs)
+
+int
+dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
+		 int nents, enum dma_data_direction dir,
+		 struct dma_attrs *attrs)
+
+void
+dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl,
+		   int nents, enum dma_data_direction dir,
+		   struct dma_attrs *attrs)
+
+The four functions above are just like the counterpart functions
+without the _attrs suffixes, except that they pass an optional
+struct dma_attrs*.
+
+struct dma_attrs encapsulates a set of "dma attributes". For the
+definition of struct dma_attrs see linux/dma-attrs.h.
+
+The interpretation of dma attributes is architecture-specific, and
+each attribute should be documented in Documentation/DMA-attributes.txt.
+
+If struct dma_attrs* is NULL, the semantics of each of these
+functions is identical to those of the corresponding function
+without the _attrs suffix. As a result dma_map_single_attrs()
+can generally replace dma_map_single(), etc.
+
+As an example of the use of the *_attrs functions, here's how
+you could pass an attribute DMA_ATTR_FOO when mapping memory
+for DMA:
+
+#include <linux/dma-attrs.h>
+/* DMA_ATTR_FOO should be defined in linux/dma-attrs.h and
+ * documented in Documentation/DMA-attributes.txt */
+...
+
+	DEFINE_DMA_ATTRS(attrs);
+	dma_set_attr(DMA_ATTR_FOO, &attrs);
+	....
+	n = dma_map_sg_attrs(dev, sg, nents, DMA_TO_DEVICE, &attr);
+	....
+
+Architectures that care about DMA_ATTR_FOO would check for its
+presence in their implementations of the mapping and unmapping
+routines, e.g.:
+
+void whizco_dma_map_sg_attrs(struct device *dev, dma_addr_t dma_addr,
+			     size_t size, enum dma_data_direction dir,
+			     struct dma_attrs *attrs)
+{
+	....
+	int foo =  dma_get_attr(DMA_ATTR_FOO, attrs);
+	....
+	if (foo)
+		/* twizzle the frobnozzle */
+	....
+
 
 Part II - Advanced dma_ usage
 -----------------------------
diff --git a/trunk/Documentation/DMA-attributes.txt b/trunk/Documentation/DMA-attributes.txt
new file mode 100644
index 000000000000..6d772f84b477
--- /dev/null
+++ b/trunk/Documentation/DMA-attributes.txt
@@ -0,0 +1,24 @@
+			DMA attributes
+			==============
+
+This document describes the semantics of the DMA attributes that are
+defined in linux/dma-attrs.h.
+
+DMA_ATTR_WRITE_BARRIER
+----------------------
+
+DMA_ATTR_WRITE_BARRIER is a (write) barrier attribute for DMA.  DMA
+to a memory region with the DMA_ATTR_WRITE_BARRIER attribute forces
+all pending DMA writes to complete, and thus provides a mechanism to
+strictly order DMA from a device across all intervening busses and
+bridges.  This barrier is not specific to a particular type of
+interconnect, it applies to the system as a whole, and so its
+implementation must account for the idiosyncracies of the system all
+the way from the DMA device to memory.
+
+As an example of a situation where DMA_ATTR_WRITE_BARRIER would be
+useful, suppose that a device does a DMA write to indicate that data is
+ready and available in memory.  The DMA of the "completion indication"
+could race with data DMA.  Mapping the memory used for completion
+indications with DMA_ATTR_WRITE_BARRIER would prevent the race.
+
diff --git a/trunk/Documentation/DocBook/kernel-api.tmpl b/trunk/Documentation/DocBook/kernel-api.tmpl
index 488dd4a4945b..b7b1482f6e04 100644
--- a/trunk/Documentation/DocBook/kernel-api.tmpl
+++ b/trunk/Documentation/DocBook/kernel-api.tmpl
@@ -119,7 +119,7 @@ X!Ilib/string.c
 !Elib/string.c
      </sect1>
      <sect1><title>Bit Operations</title>
-!Iinclude/asm-x86/bitops_32.h
+!Iinclude/asm-x86/bitops.h
      </sect1>
   </chapter>
 
@@ -645,4 +645,58 @@ X!Idrivers/video/console/fonts.c
 !Edrivers/i2c/i2c-core.c
   </chapter>
 
+  <chapter id="clk">
+     <title>Clock Framework</title>
+
+     <para>
+	The clock framework defines programming interfaces to support
+	software management of the system clock tree.
+	This framework is widely used with System-On-Chip (SOC) platforms
+	to support power management and various devices which may need
+	custom clock rates.
+	Note that these "clocks" don't relate to timekeeping or real
+	time clocks (RTCs), each of which have separate frameworks.
+	These <structname>struct clk</structname> instances may be used
+	to manage for example a 96 MHz signal that is used to shift bits
+	into and out of peripherals or busses, or otherwise trigger
+	synchronous state machine transitions in system hardware.
+     </para>
+
+     <para>
+	Power management is supported by explicit software clock gating:
+	unused clocks are disabled, so the system doesn't waste power
+	changing the state of transistors that aren't in active use.
+	On some systems this may be backed by hardware clock gating,
+	where clocks are gated without being disabled in software.
+	Sections of chips that are powered but not clocked may be able
+	to retain their last state.
+	This low power state is often called a <emphasis>retention
+	mode</emphasis>.
+	This mode still incurs leakage currents, especially with finer
+	circuit geometries, but for CMOS circuits power is mostly used
+	by clocked state changes.
+     </para>
+
+     <para>
+	Power-aware drivers only enable their clocks when the device
+	they manage is in active use.  Also, system sleep states often
+	differ according to which clock domains are active:  while a
+	"standby" state may allow wakeup from several active domains, a
+	"mem" (suspend-to-RAM) state may require a more wholesale shutdown
+	of clocks derived from higher speed PLLs and oscillators, limiting
+	the number of possible wakeup event sources.  A driver's suspend
+	method may need to be aware of system-specific clock constraints
+	on the target sleep state.
+     </para>
+
+     <para>
+        Some platforms support programmable clock generators.  These
+	can be used by external chips of various kinds, such as other
+	CPUs, multimedia codecs, and devices with strict requirements
+	for interface clocking.
+     </para>
+
+!Iinclude/linux/clk.h
+  </chapter>
+
 </book>
diff --git a/trunk/Documentation/cgroups.txt b/trunk/Documentation/cgroups.txt
index 31d12e21ff8a..c298a6690e0d 100644
--- a/trunk/Documentation/cgroups.txt
+++ b/trunk/Documentation/cgroups.txt
@@ -500,8 +500,7 @@ post-attachment activity that requires memory allocations or blocking.
 
 void fork(struct cgroup_subsy *ss, struct task_struct *task)
 
-Called when a task is forked into a cgroup. Also called during
-registration for all existing tasks.
+Called when a task is forked into a cgroup.
 
 void exit(struct cgroup_subsys *ss, struct task_struct *task)
 
diff --git a/trunk/Documentation/controllers/devices.txt b/trunk/Documentation/controllers/devices.txt
new file mode 100644
index 000000000000..4dcea42432c2
--- /dev/null
+++ b/trunk/Documentation/controllers/devices.txt
@@ -0,0 +1,48 @@
+Device Whitelist Controller
+
+1. Description:
+
+Implement a cgroup to track and enforce open and mknod restrictions
+on device files.  A device cgroup associates a device access
+whitelist with each cgroup.  A whitelist entry has 4 fields.
+'type' is a (all), c (char), or b (block).  'all' means it applies
+to all types and all major and minor numbers.  Major and minor are
+either an integer or * for all.  Access is a composition of r
+(read), w (write), and m (mknod).
+
+The root device cgroup starts with rwm to 'all'.  A child device
+cgroup gets a copy of the parent.  Administrators can then remove
+devices from the whitelist or add new entries.  A child cgroup can
+never receive a device access which is denied its parent.  However
+when a device access is removed from a parent it will not also be
+removed from the child(ren).
+
+2. User Interface
+
+An entry is added using devices.allow, and removed using
+devices.deny.  For instance
+
+	echo 'c 1:3 mr' > /cgroups/1/devices.allow
+
+allows cgroup 1 to read and mknod the device usually known as
+/dev/null.  Doing
+
+	echo a > /cgroups/1/devices.deny
+
+will remove the default 'a *:* mrw' entry.
+
+3. Security
+
+Any task can move itself between cgroups.  This clearly won't
+suffice, but we can decide the best way to adequately restrict
+movement as people get some experience with this.  We may just want
+to require CAP_SYS_ADMIN, which at least is a separate bit from
+CAP_MKNOD.  We may want to just refuse moving to a cgroup which
+isn't a descendent of the current one.  Or we may want to use
+CAP_MAC_ADMIN, since we really are trying to lock down root.
+
+CAP_SYS_ADMIN is needed to modify the whitelist or move another
+task to a new cgroup.  (Again we'll probably want to change that).
+
+A cgroup may not be granted more permissions than the cgroup's
+parent has.
diff --git a/trunk/Documentation/controllers/resource_counter.txt b/trunk/Documentation/controllers/resource_counter.txt
new file mode 100644
index 000000000000..f196ac1d7d25
--- /dev/null
+++ b/trunk/Documentation/controllers/resource_counter.txt
@@ -0,0 +1,181 @@
+
+		The Resource Counter
+
+The resource counter, declared at include/linux/res_counter.h,
+is supposed to facilitate the resource management by controllers
+by providing common stuff for accounting.
+
+This "stuff" includes the res_counter structure and routines
+to work with it.
+
+
+
+1. Crucial parts of the res_counter structure
+
+ a. unsigned long long usage
+
+ 	The usage value shows the amount of a resource that is consumed
+	by a group at a given time. The units of measurement should be
+	determined by the controller that uses this counter. E.g. it can
+	be bytes, items or any other unit the controller operates on.
+
+ b. unsigned long long max_usage
+
+ 	The maximal value of the usage over time.
+
+ 	This value is useful when gathering statistical information about
+	the particular group, as it shows the actual resource requirements
+	for a particular group, not just some usage snapshot.
+
+ c. unsigned long long limit
+
+ 	The maximal allowed amount of resource to consume by the group. In
+	case the group requests for more resources, so that the usage value
+	would exceed the limit, the resource allocation is rejected (see
+	the next section).
+
+ d. unsigned long long failcnt
+
+ 	The failcnt stands for "failures counter". This is the number of
+	resource allocation attempts that failed.
+
+ c. spinlock_t lock
+
+ 	Protects changes of the above values.
+
+
+
+2. Basic accounting routines
+
+ a. void res_counter_init(struct res_counter *rc)
+
+ 	Initializes the resource counter. As usual, should be the first
+	routine called for a new counter.
+
+ b. int res_counter_charge[_locked]
+			(struct res_counter *rc, unsigned long val)
+
+	When a resource is about to be allocated it has to be accounted
+	with the appropriate resource counter (controller should determine
+	which one to use on its own). This operation is called "charging".
+
+	This is not very important which operation - resource allocation
+	or charging - is performed first, but
+	  * if the allocation is performed first, this may create a
+	    temporary resource over-usage by the time resource counter is
+	    charged;
+	  * if the charging is performed first, then it should be uncharged
+	    on error path (if the one is called).
+
+ c. void res_counter_uncharge[_locked]
+			(struct res_counter *rc, unsigned long val)
+
+	When a resource is released (freed) it should be de-accounted
+	from the resource counter it was accounted to.  This is called
+	"uncharging".
+
+    The _locked routines imply that the res_counter->lock is taken.
+
+
+ 2.1 Other accounting routines
+
+    There are more routines that may help you with common needs, like
+    checking whether the limit is reached or resetting the max_usage
+    value. They are all declared in include/linux/res_counter.h.
+
+
+
+3. Analyzing the resource counter registrations
+
+ a. If the failcnt value constantly grows, this means that the counter's
+    limit is too tight. Either the group is misbehaving and consumes too
+    many resources, or the configuration is not suitable for the group
+    and the limit should be increased.
+
+ b. The max_usage value can be used to quickly tune the group. One may
+    set the limits to maximal values and either load the container with
+    a common pattern or leave one for a while. After this the max_usage
+    value shows the amount of memory the container would require during
+    its common activity.
+
+    Setting the limit a bit above this value gives a pretty good
+    configuration that works in most of the cases.
+
+ c. If the max_usage is much less than the limit, but the failcnt value
+    is growing, then the group tries to allocate a big chunk of resource
+    at once.
+
+ d. If the max_usage is much less than the limit, but the failcnt value
+    is 0, then this group is given too high limit, that it does not
+    require. It is better to lower the limit a bit leaving more resource
+    for other groups.
+
+
+
+4. Communication with the control groups subsystem (cgroups)
+
+All the resource controllers that are using cgroups and resource counters
+should provide files (in the cgroup filesystem) to work with the resource
+counter fields. They are recommended to adhere to the following rules:
+
+ a. File names
+
+ 	Field name	File name
+	---------------------------------------------------
+	usage		usage_in_<unit_of_measurement>
+	max_usage	max_usage_in_<unit_of_measurement>
+	limit		limit_in_<unit_of_measurement>
+	failcnt		failcnt
+	lock		no file :)
+
+ b. Reading from file should show the corresponding field value in the
+    appropriate format.
+
+ c. Writing to file
+
+ 	Field		Expected behavior
+	----------------------------------
+	usage		prohibited
+	max_usage	reset to usage
+	limit		set the limit
+	failcnt		reset to zero
+
+
+
+5. Usage example
+
+ a. Declare a task group (take a look at cgroups subsystem for this) and
+    fold a res_counter into it
+
+	struct my_group {
+		struct res_counter res;
+
+		<other fields>
+	}
+
+ b. Put hooks in resource allocation/release paths
+
+ 	int alloc_something(...)
+	{
+		if (res_counter_charge(res_counter_ptr, amount) < 0)
+			return -ENOMEM;
+
+		<allocate the resource and return to the caller>
+	}
+
+	void release_something(...)
+	{
+		res_counter_uncharge(res_counter_ptr, amount);
+
+		<release the resource>
+	}
+
+    In order to keep the usage value self-consistent, both the
+    "res_counter_ptr" and the "amount" in release_something() should be
+    the same as they were in the alloc_something() when the releasing
+    resource was allocated.
+
+ c. Provide the way to read res_counter values and set them (the cgroups
+    still can help with it).
+
+ c. Compile and run :)
diff --git a/trunk/Documentation/cpu-freq/user-guide.txt b/trunk/Documentation/cpu-freq/user-guide.txt
index af3b925ece08..6c442d8426b5 100644
--- a/trunk/Documentation/cpu-freq/user-guide.txt
+++ b/trunk/Documentation/cpu-freq/user-guide.txt
@@ -154,6 +154,11 @@ scaling_governor,		and by "echoing" the name of another
 				that some governors won't load - they only
 				work on some specific architectures or
 				processors.
+
+cpuinfo_cur_freq :		Current speed of the CPU, in KHz.
+
+scaling_available_frequencies : List of available frequencies, in KHz.
+
 scaling_min_freq and
 scaling_max_freq		show the current "policy limits" (in
 				kHz). By echoing new values into these
@@ -162,6 +167,15 @@ scaling_max_freq		show the current "policy limits" (in
 				first set scaling_max_freq, then
 				scaling_min_freq.
 
+affected_cpus :			List of CPUs that require software coordination
+				of frequency.
+
+related_cpus :			List of CPUs that need some sort of frequency
+				coordination, whether software or hardware.
+
+scaling_driver :		Hardware driver for cpufreq.
+
+scaling_cur_freq :		Current frequency of the CPU, in KHz.
 
 If you have selected the "userspace" governor which allows you to
 set the CPU operating frequency to a specific value, you can read out
diff --git a/trunk/Documentation/cpusets.txt b/trunk/Documentation/cpusets.txt
index aa854b9b18cd..fb7b361e6eea 100644
--- a/trunk/Documentation/cpusets.txt
+++ b/trunk/Documentation/cpusets.txt
@@ -171,6 +171,7 @@ files describing that cpuset:
  - memory_migrate flag: if set, move pages to cpusets nodes
  - cpu_exclusive flag: is cpu placement exclusive?
  - mem_exclusive flag: is memory placement exclusive?
+ - mem_hardwall flag:  is memory allocation hardwalled
  - memory_pressure: measure of how much paging pressure in cpuset
 
 In addition, the root cpuset only has the following file:
@@ -222,17 +223,18 @@ If a cpuset is cpu or mem exclusive, no other cpuset, other than
 a direct ancestor or descendent, may share any of the same CPUs or
 Memory Nodes.
 
-A cpuset that is mem_exclusive restricts kernel allocations for
-page, buffer and other data commonly shared by the kernel across
-multiple users.  All cpusets, whether mem_exclusive or not, restrict
-allocations of memory for user space.  This enables configuring a
-system so that several independent jobs can share common kernel data,
-such as file system pages, while isolating each jobs user allocation in
-its own cpuset.  To do this, construct a large mem_exclusive cpuset to
-hold all the jobs, and construct child, non-mem_exclusive cpusets for
-each individual job.  Only a small amount of typical kernel memory,
-such as requests from interrupt handlers, is allowed to be taken
-outside even a mem_exclusive cpuset.
+A cpuset that is mem_exclusive *or* mem_hardwall is "hardwalled",
+i.e. it restricts kernel allocations for page, buffer and other data
+commonly shared by the kernel across multiple users.  All cpusets,
+whether hardwalled or not, restrict allocations of memory for user
+space.  This enables configuring a system so that several independent
+jobs can share common kernel data, such as file system pages, while
+isolating each job's user allocation in its own cpuset.  To do this,
+construct a large mem_exclusive cpuset to hold all the jobs, and
+construct child, non-mem_exclusive cpusets for each individual job.
+Only a small amount of typical kernel memory, such as requests from
+interrupt handlers, is allowed to be taken outside even a
+mem_exclusive cpuset.
 
 
 1.5 What is memory_pressure ?
@@ -707,7 +709,7 @@ Now you want to do something with this cpuset.
 
 In this directory you can find several files:
 # ls
-cpus  cpu_exclusive  mems  mem_exclusive  tasks
+cpus  cpu_exclusive  mems  mem_exclusive mem_hardwall  tasks
 
 Reading them will give you information about the state of this cpuset:
 the CPUs and Memory Nodes it can use, the processes that are using
diff --git a/trunk/Documentation/dontdiff b/trunk/Documentation/dontdiff
index 354aec047c0e..881e6dd03aea 100644
--- a/trunk/Documentation/dontdiff
+++ b/trunk/Documentation/dontdiff
@@ -141,6 +141,7 @@ mkprep
 mktables
 mktree
 modpost
+modules.order
 modversions.h*
 offset.h
 offsets.h
@@ -171,6 +172,7 @@ sm_tbl*
 split-include
 tags
 tftpboot.img
+timeconst.h
 times.h*
 tkparse
 trix_boot.h
diff --git a/trunk/Documentation/fb/gxfb.txt b/trunk/Documentation/fb/gxfb.txt
new file mode 100644
index 000000000000..2f640903bbb2
--- /dev/null
+++ b/trunk/Documentation/fb/gxfb.txt
@@ -0,0 +1,52 @@
+[This file is cloned from VesaFB/aty128fb]
+
+What is gxfb?
+=================
+
+This is a graphics framebuffer driver for AMD Geode GX2 based processors.
+
+Advantages:
+
+ * No need to use AMD's VSA code (or other VESA emulation layer) in the
+   BIOS.
+ * It provides a nice large console (128 cols + 48 lines with 1024x768)
+   without using tiny, unreadable fonts.
+ * You can run XF68_FBDev on top of /dev/fb0
+ * Most important: boot logo :-)
+
+Disadvantages:
+
+ * graphic mode is slower than text mode...
+
+
+How to use it?
+==============
+
+Switching modes is done using  gxfb.mode_option=<resolution>... boot
+parameter or using `fbset' program.
+
+See Documentation/fb/modedb.txt for more information on modedb
+resolutions.
+
+
+X11
+===
+
+XF68_FBDev should generally work fine, but it is non-accelerated.
+
+
+Configuration
+=============
+
+You can pass kernel command line options to gxfb with gxfb.<option>.
+For example, gxfb.mode_option=800x600@75.
+Accepted options:
+
+mode_option	- specify the video mode.  Of the form
+		  <x>x<y>[-<bpp>][@<refresh>]
+vram		- size of video ram (normally auto-detected)
+vt_switch	- enable vt switching during suspend/resume.  The vt
+		  switch is slow, but harmless.
+
+--
+Andres Salomon <dilinger@debian.org>
diff --git a/trunk/Documentation/fb/intelfb.txt b/trunk/Documentation/fb/intelfb.txt
index da5ee74219e8..27a3160650a4 100644
--- a/trunk/Documentation/fb/intelfb.txt
+++ b/trunk/Documentation/fb/intelfb.txt
@@ -14,6 +14,8 @@ graphics devices.  These would include:
 	Intel 915GM
 	Intel 945G
 	Intel 945GM
+	Intel 965G
+	Intel 965GM
 
 B.  List of available options
 
diff --git a/trunk/Documentation/fb/lxfb.txt b/trunk/Documentation/fb/lxfb.txt
new file mode 100644
index 000000000000..38b3ca6f6ca7
--- /dev/null
+++ b/trunk/Documentation/fb/lxfb.txt
@@ -0,0 +1,52 @@
+[This file is cloned from VesaFB/aty128fb]
+
+What is lxfb?
+=================
+
+This is a graphics framebuffer driver for AMD Geode LX based processors.
+
+Advantages:
+
+ * No need to use AMD's VSA code (or other VESA emulation layer) in the
+   BIOS.
+ * It provides a nice large console (128 cols + 48 lines with 1024x768)
+   without using tiny, unreadable fonts.
+ * You can run XF68_FBDev on top of /dev/fb0
+ * Most important: boot logo :-)
+
+Disadvantages:
+
+ * graphic mode is slower than text mode...
+
+
+How to use it?
+==============
+
+Switching modes is done using  lxfb.mode_option=<resolution>... boot
+parameter or using `fbset' program.
+
+See Documentation/fb/modedb.txt for more information on modedb
+resolutions.
+
+
+X11
+===
+
+XF68_FBDev should generally work fine, but it is non-accelerated.
+
+
+Configuration
+=============
+
+You can pass kernel command line options to lxfb with lxfb.<option>.
+For example, lxfb.mode_option=800x600@75.
+Accepted options:
+
+mode_option	- specify the video mode.  Of the form
+		  <x>x<y>[-<bpp>][@<refresh>]
+vram		- size of video ram (normally auto-detected)
+vt_switch	- enable vt switching during suspend/resume.  The vt
+		  switch is slow, but harmless.
+
+--
+Andres Salomon <dilinger@debian.org>
diff --git a/trunk/Documentation/fb/metronomefb.txt b/trunk/Documentation/fb/metronomefb.txt
index b9a2e7b7e838..237ca412582d 100644
--- a/trunk/Documentation/fb/metronomefb.txt
+++ b/trunk/Documentation/fb/metronomefb.txt
@@ -1,7 +1,7 @@
 			Metronomefb
 			-----------
 Maintained by Jaya Kumar <jayakumar.lkml.gmail.com>
-Last revised: Nov 20, 2007
+Last revised: Mar 10, 2008
 
 Metronomefb is a driver for the Metronome display controller. The controller
 is from E-Ink Corporation. It is intended to be used to drive the E-Ink
@@ -11,20 +11,18 @@ display media here http://www.e-ink.com/products/matrix/metronome.html .
 Metronome is interfaced to the host CPU through the AMLCD interface. The
 host CPU generates the control information and the image in a framebuffer
 which is then delivered to the AMLCD interface by a host specific method.
-Currently, that's implemented for the PXA's LCDC controller. The display and
-error status are each pulled through individual GPIOs.
+The display and error status are each pulled through individual GPIOs.
 
-Metronomefb was written for the PXA255/gumstix/lyre combination and
-therefore currently has board set specific code in it. If other boards based on
-other architectures are available, then the host specific code can be separated
-and abstracted out.
+Metronomefb is platform independent and depends on a board specific driver
+to do all physical IO work. Currently, an example is implemented for the
+PXA board used in the AM-200 EPD devkit. This example is am200epd.c
 
 Metronomefb requires waveform information which is delivered via the AMLCD
 interface to the metronome controller. The waveform information is expected to
 be delivered from userspace via the firmware class interface. The waveform file
 can be compressed as long as your udev or hotplug script is aware of the need
-to uncompress it before delivering it. metronomefb will ask for waveform.wbf
-which would typically go into /lib/firmware/waveform.wbf depending on your
+to uncompress it before delivering it. metronomefb will ask for metronome.wbf
+which would typically go into /lib/firmware/metronome.wbf depending on your
 udev/hotplug setup. I have only tested with a single waveform file which was
 originally labeled 23P01201_60_WT0107_MTC. I do not know what it stands for.
 Caution should be exercised when manipulating the waveform as there may be
diff --git a/trunk/Documentation/fb/modedb.txt b/trunk/Documentation/fb/modedb.txt
index 4fcdb4cf4cca..ec4dee75a354 100644
--- a/trunk/Documentation/fb/modedb.txt
+++ b/trunk/Documentation/fb/modedb.txt
@@ -125,8 +125,12 @@ There may be more modes.
     amifb	- Amiga chipset frame buffer
     aty128fb	- ATI Rage128 / Pro frame buffer
     atyfb	- ATI Mach64 frame buffer
+    pm2fb	- Permedia 2/2V frame buffer
+    pm3fb	- Permedia 3 frame buffer
+    sstfb	- Voodoo 1/2 (SST1) chipset frame buffer
     tdfxfb	- 3D Fx frame buffer
     tridentfb	- Trident (Cyber)blade chipset frame buffer
+    vt8623fb	- VIA 8623 frame buffer
 
 BTW, only a few drivers use this at the moment. Others are to follow
 (feel free to send patches).
diff --git a/trunk/Documentation/feature-removal-schedule.txt b/trunk/Documentation/feature-removal-schedule.txt
index 448729fcaeb1..599fe55bf297 100644
--- a/trunk/Documentation/feature-removal-schedule.txt
+++ b/trunk/Documentation/feature-removal-schedule.txt
@@ -128,15 +128,6 @@ Who:	Arjan van de Ven <arjan@linux.intel.com>
 
 ---------------------------
 
-What:	vm_ops.nopage
-When:	Soon, provided in-kernel callers have been converted
-Why:	This interface is replaced by vm_ops.fault, but it has been around
-	forever, is used by a lot of drivers, and doesn't cost much to
-	maintain.
-Who:	Nick Piggin <npiggin@suse.de>
-
----------------------------
-
 What:	PHYSDEVPATH, PHYSDEVBUS, PHYSDEVDRIVER in the uevent environment
 When:	October 2008
 Why:	The stacking of class devices makes these values misleading and
diff --git a/trunk/Documentation/filesystems/Locking b/trunk/Documentation/filesystems/Locking
index 42d4b30b1045..c2992bc54f2f 100644
--- a/trunk/Documentation/filesystems/Locking
+++ b/trunk/Documentation/filesystems/Locking
@@ -511,7 +511,6 @@ prototypes:
 	void (*open)(struct vm_area_struct*);
 	void (*close)(struct vm_area_struct*);
 	int (*fault)(struct vm_area_struct*, struct vm_fault *);
-	struct page *(*nopage)(struct vm_area_struct*, unsigned long, int *);
 	int (*page_mkwrite)(struct vm_area_struct *, struct page *);
 
 locking rules:
@@ -519,7 +518,6 @@ locking rules:
 open:		no	yes
 close:		no	yes
 fault:		no	yes
-nopage:		no	yes
 page_mkwrite:	no	yes		no
 
 	->page_mkwrite() is called when a previously read-only page is
@@ -537,4 +535,3 @@ NULL.
 
 ipc/shm.c::shm_delete() - may need BKL.
 ->read() and ->write() in many drivers are (probably) missing BKL.
-drivers/sgi/char/graphics.c::sgi_graphics_nopage() - may need BKL.
diff --git a/trunk/Documentation/filesystems/tmpfs.txt b/trunk/Documentation/filesystems/tmpfs.txt
index 145e44086358..222437efd75a 100644
--- a/trunk/Documentation/filesystems/tmpfs.txt
+++ b/trunk/Documentation/filesystems/tmpfs.txt
@@ -92,6 +92,18 @@ NodeList format is a comma-separated list of decimal numbers and ranges,
 a range being two hyphen-separated decimal numbers, the smallest and
 largest node numbers in the range.  For example, mpol=bind:0-3,5,7,9-15
 
+NUMA memory allocation policies have optional flags that can be used in
+conjunction with their modes.  These optional flags can be specified
+when tmpfs is mounted by appending them to the mode before the NodeList.
+See Documentation/vm/numa_memory_policy.txt for a list of all available
+memory allocation policy mode flags.
+
+	=static		is equivalent to	MPOL_F_STATIC_NODES
+	=relative	is equivalent to	MPOL_F_RELATIVE_NODES
+
+For example, mpol=bind=static:NodeList, is the equivalent of an
+allocation policy of MPOL_BIND | MPOL_F_STATIC_NODES.
+
 Note that trying to mount a tmpfs with an mpol option will fail if the
 running kernel does not support NUMA; and will fail if its nodelist
 specifies a node which is not online.  If your system relies on that
diff --git a/trunk/Documentation/filesystems/vfat.txt b/trunk/Documentation/filesystems/vfat.txt
index fcc123ffa252..2d5e1e582e13 100644
--- a/trunk/Documentation/filesystems/vfat.txt
+++ b/trunk/Documentation/filesystems/vfat.txt
@@ -17,6 +17,21 @@ dmask=###     -- The permission mask for the directory.
 fmask=###     -- The permission mask for files.
                  The default is the umask of current process.
 
+allow_utime=### -- This option controls the permission check of mtime/atime.
+
+                  20 - If current process is in group of file's group ID,
+                       you can change timestamp.
+                   2 - Other users can change timestamp.
+
+                 The default is set from `dmask' option. (If the directory is
+                 writable, utime(2) is also allowed. I.e. ~dmask & 022)
+
+                 Normally utime(2) checks current process is owner of
+                 the file, or it has CAP_FOWNER capability.  But FAT
+                 filesystem doesn't have uid/gid on disk, so normal
+                 check is too unflexible. With this option you can
+                 relax it.
+
 codepage=###  -- Sets the codepage number for converting to shortname
 		 characters on FAT filesystem.
 		 By default, FAT_DEFAULT_CODEPAGE setting is used.
diff --git a/trunk/Documentation/gpio.txt b/trunk/Documentation/gpio.txt
index 54630095aa3c..c35ca9e40d4c 100644
--- a/trunk/Documentation/gpio.txt
+++ b/trunk/Documentation/gpio.txt
@@ -107,6 +107,16 @@ type of GPIO controller, and on one particular board 80-95 with an FPGA.
 The numbers need not be contiguous; either of those platforms could also
 use numbers 2000-2063 to identify GPIOs in a bank of I2C GPIO expanders.
 
+If you want to initialize a structure with an invalid GPIO number, use
+some negative number (perhaps "-EINVAL"); that will never be valid.  To
+test if a number could reference a GPIO, you may use this predicate:
+
+	int gpio_is_valid(int number);
+
+A number that's not valid will be rejected by calls which may request
+or free GPIOs (see below).  Other numbers may also be rejected; for
+example, a number might be valid but unused on a given board.
+
 Whether a platform supports multiple GPIO controllers is currently a
 platform-specific implementation issue.
 
diff --git a/trunk/Documentation/ia64/kvm.txt b/trunk/Documentation/ia64/kvm.txt
new file mode 100644
index 000000000000..bec9d815da33
--- /dev/null
+++ b/trunk/Documentation/ia64/kvm.txt
@@ -0,0 +1,82 @@
+Currently, kvm module in EXPERIMENTAL stage on IA64. This means that
+interfaces are not stable enough to use. So, plase had better don't run
+critical applications in virtual machine. We will try our best to make it
+strong in future versions!
+				Guide: How to boot up guests on kvm/ia64
+
+This guide is to describe how to enable kvm support for IA-64 systems.
+
+1. Get the kvm source from git.kernel.org.
+	Userspace source:
+		git clone git://git.kernel.org/pub/scm/virt/kvm/kvm-userspace.git
+	Kernel Source:
+		git clone git://git.kernel.org/pub/scm/linux/kernel/git/xiantao/kvm-ia64.git
+
+2. Compile the source code.
+	2.1 Compile userspace code:
+		(1)cd ./kvm-userspace
+		(2)./configure
+		(3)cd kernel
+		(4)make sync LINUX= $kernel_dir (kernel_dir is the directory of kernel source.)
+		(5)cd ..
+		(6)make qemu
+		(7)cd qemu; make install
+
+	2.2 Compile kernel source code:
+		(1) cd ./$kernel_dir
+		(2) Make menuconfig
+		(3) Enter into virtualization option, and choose kvm.
+		(4) make
+		(5) Once (4) done, make modules_install
+		(6) Make initrd, and use new kernel to reboot up host machine.
+		(7) Once (6) done, cd $kernel_dir/arch/ia64/kvm
+		(8) insmod kvm.ko; insmod kvm-intel.ko
+
+Note: For step 2, please make sure that host page size == TARGET_PAGE_SIZE of qemu, otherwise, may fail.
+
+3. Get Guest Firmware named as Flash.fd, and put it under right place:
+	(1) If you have the guest firmware (binary) released by Intel Corp for Xen, use it directly.
+
+	(2) If you have no firmware at hand, Please download its source from
+		hg clone http://xenbits.xensource.com/ext/efi-vfirmware.hg
+	    you can get the firmware's binary in the directory of efi-vfirmware.hg/binaries.
+
+	(3) Rename the firware you owned to Flash.fd, and copy it to /usr/local/share/qemu
+
+4. Boot up Linux or Windows guests:
+	4.1 Create or install a image for guest boot. If you have xen experience, it should be easy.
+
+	4.2 Boot up guests use the following command.
+		/usr/local/bin/qemu-system-ia64 -smp xx -m 512 -hda $your_image
+		(xx is the number of virtual processors for the guest, now the maximum value is 4)
+
+5. Known possibile issue on some platforms with old Firmware.
+
+If meet strange host crashe issues, try to solve it through either of the following ways:
+
+(1): Upgrade your Firmware to the latest one.
+
+(2): Applying the below patch to kernel source.
+diff --git a/arch/ia64/kernel/pal.S b/arch/ia64/kernel/pal.S
+index 0b53344..f02b0f7 100644
+--- a/arch/ia64/kernel/pal.S
++++ b/arch/ia64/kernel/pal.S
+@@ -84,7 +84,8 @@ GLOBAL_ENTRY(ia64_pal_call_static)
+	mov ar.pfs = loc1
+	mov rp = loc0
+	;;
+-	srlz.d				// seralize restoration of psr.l
++	srlz.i			// seralize restoration of psr.l
++	;;
+	br.ret.sptk.many b0
+ END(ia64_pal_call_static)
+
+6. Bug report:
+	If you found any issues when use kvm/ia64, Please post the bug info to kvm-ia64-devel mailing list.
+	https://lists.sourceforge.net/lists/listinfo/kvm-ia64-devel/
+
+Thanks for your interest! Let's work together, and make kvm/ia64 stronger and stronger!
+
+
+								Xiantao Zhang <xiantao.zhang@intel.com>
+											2008.3.10
diff --git a/trunk/Documentation/ide/ide-tape.txt b/trunk/Documentation/ide/ide-tape.txt
index 658f271a373f..3f348a0b21d8 100644
--- a/trunk/Documentation/ide/ide-tape.txt
+++ b/trunk/Documentation/ide/ide-tape.txt
@@ -1,146 +1,65 @@
-/*
- * IDE ATAPI streaming tape driver.
- *
- * This driver is a part of the Linux ide driver.
- *
- * The driver, in co-operation with ide.c, basically traverses the
- * request-list for the block device interface. The character device
- * interface, on the other hand, creates new requests, adds them
- * to the request-list of the block device, and waits for their completion.
- *
- * Pipelined operation mode is now supported on both reads and writes.
- *
- * The block device major and minor numbers are determined from the
- * tape's relative position in the ide interfaces, as explained in ide.c.
- *
- * The character device interface consists of the following devices:
- *
- * ht0		major 37, minor 0	first  IDE tape, rewind on close.
- * ht1		major 37, minor 1	second IDE tape, rewind on close.
- * ...
- * nht0		major 37, minor 128	first  IDE tape, no rewind on close.
- * nht1		major 37, minor 129	second IDE tape, no rewind on close.
- * ...
- *
- * The general magnetic tape commands compatible interface, as defined by
- * include/linux/mtio.h, is accessible through the character device.
- *
- * General ide driver configuration options, such as the interrupt-unmask
- * flag, can be configured by issuing an ioctl to the block device interface,
- * as any other ide device.
- *
- * Our own ide-tape ioctl's can be issued to either the block device or
- * the character device interface.
- *
- * Maximal throughput with minimal bus load will usually be achieved in the
- * following scenario:
- *
- *	1.	ide-tape is operating in the pipelined operation mode.
- *	2.	No buffering is performed by the user backup program.
- *
- * Testing was done with a 2 GB CONNER CTMA 4000 IDE ATAPI Streaming Tape Drive.
- *
- * Here are some words from the first releases of hd.c, which are quoted
- * in ide.c and apply here as well:
- *
- * | Special care is recommended.  Have Fun!
- *
- *
- * An overview of the pipelined operation mode.
- *
- * In the pipelined write mode, we will usually just add requests to our
- * pipeline and return immediately, before we even start to service them. The
- * user program will then have enough time to prepare the next request while
- * we are still busy servicing previous requests. In the pipelined read mode,
- * the situation is similar - we add read-ahead requests into the pipeline,
- * before the user even requested them.
- *
- * The pipeline can be viewed as a "safety net" which will be activated when
- * the system load is high and prevents the user backup program from keeping up
- * with the current tape speed. At this point, the pipeline will get
- * shorter and shorter but the tape will still be streaming at the same speed.
- * Assuming we have enough pipeline stages, the system load will hopefully
- * decrease before the pipeline is completely empty, and the backup program
- * will be able to "catch up" and refill the pipeline again.
- *
- * When using the pipelined mode, it would be best to disable any type of
- * buffering done by the user program, as ide-tape already provides all the
- * benefits in the kernel, where it can be done in a more efficient way.
- * As we will usually not block the user program on a request, the most
- * efficient user code will then be a simple read-write-read-... cycle.
- * Any additional logic will usually just slow down the backup process.
- *
- * Using the pipelined mode, I get a constant over 400 KBps throughput,
- * which seems to be the maximum throughput supported by my tape.
- *
- * However, there are some downfalls:
- *
- *	1.	We use memory (for data buffers) in proportional to the number
- *		of pipeline stages (each stage is about 26 KB with my tape).
- *	2.	In the pipelined write mode, we cheat and postpone error codes
- *		to the user task. In read mode, the actual tape position
- *		will be a bit further than the last requested block.
- *
- * Concerning (1):
- *
- *	1.	We allocate stages dynamically only when we need them. When
- *		we don't need them, we don't consume additional memory. In
- *		case we can't allocate stages, we just manage without them
- *		(at the expense of decreased throughput) so when Linux is
- *		tight in memory, we will not pose additional difficulties.
- *
- *	2.	The maximum number of stages (which is, in fact, the maximum
- *		amount of memory) which we allocate is limited by the compile
- *		time parameter IDETAPE_MAX_PIPELINE_STAGES.
- *
- *	3.	The maximum number of stages is a controlled parameter - We
- *		don't start from the user defined maximum number of stages
- *		but from the lower IDETAPE_MIN_PIPELINE_STAGES (again, we
- *		will not even allocate this amount of stages if the user
- *		program can't handle the speed). We then implement a feedback
- *		loop which checks if the pipeline is empty, and if it is, we
- *		increase the maximum number of stages as necessary until we
- *		reach the optimum value which just manages to keep the tape
- *		busy with minimum allocated memory or until we reach
- *		IDETAPE_MAX_PIPELINE_STAGES.
- *
- * Concerning (2):
- *
- *	In pipelined write mode, ide-tape can not return accurate error codes
- *	to the user program since we usually just add the request to the
- *      pipeline without waiting for it to be serviced. In case an error
- *      occurs, I will report it on the next user request.
- *
- *	In the pipelined read mode, subsequent read requests or forward
- *	filemark spacing will perform correctly, as we preserve all blocks
- *	and filemarks which we encountered during our excess read-ahead.
- *
- *	For accurate tape positioning and error reporting, disabling
- *	pipelined mode might be the best option.
- *
- * You can enable/disable/tune the pipelined operation mode by adjusting
- * the compile time parameters below.
- *
- *
- *	Possible improvements.
- *
- *	1.	Support for the ATAPI overlap protocol.
- *
- *		In order to maximize bus throughput, we currently use the DSC
- *		overlap method which enables ide.c to service requests from the
- *		other device while the tape is busy executing a command. The
- *		DSC overlap method involves polling the tape's status register
- *		for the DSC bit, and servicing the other device while the tape
- *		isn't ready.
- *
- *		In the current QIC development standard (December 1995),
- *		it is recommended that new tape drives will *in addition*
- *		implement the ATAPI overlap protocol, which is used for the
- *		same purpose - efficient use of the IDE bus, but is interrupt
- *		driven and thus has much less CPU overhead.
- *
- *		ATAPI overlap is likely to be supported in most new ATAPI
- *		devices, including new ATAPI cdroms, and thus provides us
- *		a method by which we can achieve higher throughput when
- *		sharing a (fast) ATA-2 disk with any (slow) new ATAPI device.
- */
+IDE ATAPI streaming tape driver.
+
+This driver is a part of the Linux ide driver.
+
+The driver, in co-operation with ide.c, basically traverses the
+request-list for the block device interface. The character device
+interface, on the other hand, creates new requests, adds them
+to the request-list of the block device, and waits for their completion.
+
+The block device major and minor numbers are determined from the
+tape's relative position in the ide interfaces, as explained in ide.c.
+
+The character device interface consists of the following devices:
+
+ht0		major 37, minor 0	first  IDE tape, rewind on close.
+ht1		major 37, minor 1	second IDE tape, rewind on close.
+...
+nht0		major 37, minor 128	first  IDE tape, no rewind on close.
+nht1		major 37, minor 129	second IDE tape, no rewind on close.
+...
+
+The general magnetic tape commands compatible interface, as defined by
+include/linux/mtio.h, is accessible through the character device.
+
+General ide driver configuration options, such as the interrupt-unmask
+flag, can be configured by issuing an ioctl to the block device interface,
+as any other ide device.
+
+Our own ide-tape ioctl's can be issued to either the block device or
+the character device interface.
+
+Maximal throughput with minimal bus load will usually be achieved in the
+following scenario:
+
+     1.	ide-tape is operating in the pipelined operation mode.
+     2.	No buffering is performed by the user backup program.
+
+Testing was done with a 2 GB CONNER CTMA 4000 IDE ATAPI Streaming Tape Drive.
+
+Here are some words from the first releases of hd.c, which are quoted
+in ide.c and apply here as well:
+
+| Special care is recommended.  Have Fun!
+
+Possible improvements:
+
+1. Support for the ATAPI overlap protocol.
+
+In order to maximize bus throughput, we currently use the DSC
+overlap method which enables ide.c to service requests from the
+other device while the tape is busy executing a command. The
+DSC overlap method involves polling the tape's status register
+for the DSC bit, and servicing the other device while the tape
+isn't ready.
+
+In the current QIC development standard (December 1995),
+it is recommended that new tape drives will *in addition*
+implement the ATAPI overlap protocol, which is used for the
+same purpose - efficient use of the IDE bus, but is interrupt
+driven and thus has much less CPU overhead.
+
+ATAPI overlap is likely to be supported in most new ATAPI
+devices, including new ATAPI cdroms, and thus provides us
+a method by which we can achieve higher throughput when
+sharing a (fast) ATA-2 disk with any (slow) new ATAPI device.
diff --git a/trunk/Documentation/ide/ide.txt b/trunk/Documentation/ide/ide.txt
index 486c699f4aea..0c78f4b1d9d9 100644
--- a/trunk/Documentation/ide/ide.txt
+++ b/trunk/Documentation/ide/ide.txt
@@ -82,27 +82,26 @@ Drives are normally found by auto-probing and/or examining the CMOS/BIOS data.
 For really weird situations, the apparent (fdisk) geometry can also be specified
 on the kernel "command line" using LILO.  The format of such lines is:
 
-	hdx=cyls,heads,sects
-or	hdx=cdrom
+	ide_core.chs=[interface_number.device_number]:cyls,heads,sects
+or	ide_core.cdrom=[interface_number.device_number]
 
-where hdx can be any of hda through hdh, Three values are required
-(cyls,heads,sects).  For example:
+For example:
 
-	hdc=1050,32,64  hdd=cdrom
+	ide_core.chs=1.0:1050,32,64  ide_core.cdrom=1.1
 
-either {hda,hdb} or {hdc,hdd}.  The results of successful auto-probing may
-override the physical geometry/irq specified, though the "original" geometry
-may be retained as the "logical" geometry for partitioning purposes (fdisk).
+The results of successful auto-probing may override the physical geometry/irq
+specified, though the "original" geometry may be retained as the "logical"
+geometry for partitioning purposes (fdisk).
 
 If the auto-probing during boot time confuses a drive (ie. the drive works
 with hd.c but not with ide.c), then an command line option may be specified
 for each drive for which you'd like the drive to skip the hardware
 probe/identification sequence.  For example:
 
-	hdb=noprobe
+	ide_core.noprobe=0.1
 or
-	hdc=768,16,32
-	hdc=noprobe
+	ide_core.chs=1.0:768,16,32
+	ide_core.noprobe=1.0
 
 Note that when only one IDE device is attached to an interface, it should be
 jumpered as "single" or "master", *not* "slave".  Many folks have had
@@ -118,9 +117,9 @@ If for some reason your cdrom drive is *not* found at boot time, you can force
 the probe to look harder by supplying a kernel command line parameter
 via LILO, such as:
 
-	hdc=cdrom	/* hdc = "master" on second interface */
+	ide_core.cdrom=1.0	/* "master" on second interface (hdc) */
 or
-	hdd=cdrom	/* hdd = "slave" on second interface */
+	ide_core.cdrom=1.1	/* "slave" on second interface (hdd) */
 
 For example, a GW2000 system might have a hard drive on the primary
 interface (/dev/hda) and an IDE cdrom drive on the secondary interface
@@ -174,9 +173,7 @@ to /etc/modprobe.conf.
 
 When ide.c is used as a module, you can pass command line parameters to the
 driver using the "options=" keyword to insmod, while replacing any ',' with
-';'.  For example:
-
-	insmod ide.o options="hda=nodma hdb=nodma"
+';'.
 
 
 ================================================================================
@@ -184,57 +181,6 @@ driver using the "options=" keyword to insmod, while replacing any ',' with
 Summary of ide driver parameters for kernel command line
 --------------------------------------------------------
 
- "hdx="  is recognized for all "x" from "a" to "u", such as "hdc".
-
- "idex=" is recognized for all "x" from "0" to "9", such as "ide1".
-
- "hdx=noprobe"		: drive may be present, but do not probe for it
-
- "hdx=none"		: drive is NOT present, ignore cmos and do not probe
-
- "hdx=nowerr"		: ignore the WRERR_STAT bit on this drive
-
- "hdx=cdrom"		: drive is present, and is a cdrom drive
-
- "hdx=cyl,head,sect"	: disk drive is present, with specified geometry
-
- "hdx=autotune"		: driver will attempt to tune interface speed
-			  to the fastest PIO mode supported,
-			  if possible for this drive only.
-			  Not fully supported by all chipset types,
-			  and quite likely to cause trouble with
-			  older/odd IDE drives.
-
- "hdx=nodma"		: disallow DMA
-
- "idebus=xx"		: inform IDE driver of VESA/PCI bus speed in MHz,
-			  where "xx" is between 20 and 66 inclusive,
-			  used when tuning chipset PIO modes.
-			  For PCI bus, 25 is correct for a P75 system,
-			  30 is correct for P90,P120,P180 systems,
-			  and 33 is used for P100,P133,P166 systems.
-			  If in doubt, use idebus=33 for PCI.
-			  As for VLB, it is safest to not specify it.
-			  Bigger values are safer than smaller ones.
-
- "idex=serialize"	: do not overlap operations on idex. Please note
-			  that you will have to specify this option for
-			  both the respective primary and secondary channel
-			  to take effect.
-
- "idex=reset"		: reset interface after probe
-
- "idex=ata66"		: informs the interface that it has an 80c cable
-			  for chipsets that are ATA-66 capable, but the
-			  ability to bit test for detection is currently
-			  unknown.
-
- "ide=doubler"		: probe/support IDE doublers on Amiga
-
-There may be more options than shown -- use the source, Luke!
-
-Everything else is rejected with a "BAD OPTION" message.
-
 For legacy IDE VLB host drivers (ali14xx/dtc2278/ht6560b/qd65xx/umc8672)
 you need to explicitly enable probing by using "probe" kernel parameter,
 i.e. to enable probing for ALI M14xx chipsets (ali14xx host driver) use:
@@ -251,6 +197,33 @@ are detected automatically).
 You also need to use "probe" kernel parameter for ide-4drives driver
 (support for IDE generic chipset with four drives on one port).
 
+To enable support for IDE doublers on Amiga use "doubler" kernel parameter
+for gayle host driver (i.e. "gayle.doubler" if the driver is built-in).
+
+To force ignoring cable detection (this should be needed only if you're using
+short 40-wires cable which cannot be automatically detected - if this is not
+a case please report it as a bug instead) use "ignore_cable" kernel parameter:
+
+* "ide_core.ignore_cable=[interface_number]" boot option if IDE is built-in
+  (i.e. "ide_core.ignore_cable=1" to force ignoring cable for "ide1")
+
+* "ignore_cable=[interface_number]" module parameter (for ide_core module)
+  if IDE is compiled as module
+
+Other kernel parameters for ide_core are:
+
+* "nodma=[interface_number.device_number]" to disallow DMA for a device
+
+* "noflush=[interface_number.device_number]" to disable flush requests
+
+* "noprobe=[interface_number.device_number]" to skip probing
+
+* "nowerr=[interface_number.device_number]" to ignore the WRERR_STAT bit
+
+* "cdrom=[interface_number.device_number]" to force device as a CD-ROM
+
+* "chs=[interface_number.device_number]" to force device as a disk (using CHS)
+
 ================================================================================
 
 Some Terminology
diff --git a/trunk/Documentation/ioctl-number.txt b/trunk/Documentation/ioctl-number.txt
index c18363bd8d11..240ce7a56c40 100644
--- a/trunk/Documentation/ioctl-number.txt
+++ b/trunk/Documentation/ioctl-number.txt
@@ -183,6 +183,8 @@ Code	Seq#	Include File		Comments
 0xAC	00-1F	linux/raw.h
 0xAD	00	Netfilter device	in development:
 					<mailto:rusty@rustcorp.com.au>	
+0xAE	all	linux/kvm.h		Kernel-based Virtual Machine
+					<mailto:kvm-devel@lists.sourceforge.net>
 0xB0	all	RATIO devices		in development:
 					<mailto:vgo@ratio.de>
 0xB1	00-1F	PPPoX			<mailto:mostrows@styx.uwaterloo.ca>
diff --git a/trunk/Documentation/kbuild/kconfig-language.txt b/trunk/Documentation/kbuild/kconfig-language.txt
index 649cb8799890..00b950d1c193 100644
--- a/trunk/Documentation/kbuild/kconfig-language.txt
+++ b/trunk/Documentation/kbuild/kconfig-language.txt
@@ -104,14 +104,15 @@ applicable everywhere (see syntax).
   Reverse dependencies can only be used with boolean or tristate
   symbols.
   Note:
-	select is evil.... select will by brute force set a symbol
-	equal to 'y' without visiting the dependencies. So abusing
-	select you are able to select a symbol FOO even if FOO depends
-	on BAR that is not set. In general use select only for
-	non-visible symbols (no prompts anywhere) and for symbols with
-	no dependencies. That will limit the usefulness but on the
-	other hand avoid the illegal configurations all over. kconfig
-	should one day warn about such things.
+	select should be used with care. select will force
+	a symbol to a value without visiting the dependencies.
+	By abusing select you are able to select a symbol FOO even
+	if FOO depends on BAR that is not set.
+	In general use select only for non-visible symbols
+	(no prompts anywhere) and for symbols with no dependencies.
+	That will limit the usefulness but on the other hand avoid
+	the illegal configurations all over.
+	kconfig should one day warn about such things.
 
 - numerical ranges: "range" <symbol> <symbol> ["if" <expr>]
   This allows to limit the range of possible input values for int
diff --git a/trunk/Documentation/kernel-parameters.txt b/trunk/Documentation/kernel-parameters.txt
index bf6303ec0bde..3ce193f86565 100644
--- a/trunk/Documentation/kernel-parameters.txt
+++ b/trunk/Documentation/kernel-parameters.txt
@@ -627,8 +627,7 @@ and is between 256 and 4096 characters. It is defined in the file
 	eata=		[HW,SCSI]
 
 	edd=		[EDD]
-			Format: {"of[f]" | "sk[ipmbr]"}
-			See comment in arch/i386/boot/edd.S
+			Format: {"off" | "on" | "skip[mbr]"}
 
 	eisa_irq_edge=	[PARISC,HW]
 			See header of drivers/parisc/eisa.c.
@@ -772,10 +771,6 @@ and is between 256 and 4096 characters. It is defined in the file
 			Format: ide=nodma or ide=doubler
 			See Documentation/ide/ide.txt.
 
-	ide?=		[HW] (E)IDE subsystem
-			Format: ide?=ata66 or chipset specific parameters.
-			See Documentation/ide/ide.txt.
-
 	idebus=		[HW] (E)IDE subsystem - VLB/PCI bus speed
 			See Documentation/ide/ide.txt.
 
@@ -1393,6 +1388,13 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	nr_uarts=	[SERIAL] maximum number of UARTs to be registered.
 
+	olpc_ec_timeout= [OLPC] ms delay when issuing EC commands
+			Rather than timing out after 20 ms if an EC
+			command is not properly ACKed, override the length
+			of the timeout.  We have interrupts disabled while
+			waiting for the ACK, so if this is set too high
+			interrupts *may* be lost!
+
 	opl3=		[HW,OSS]
 			Format: <io>
 
diff --git a/trunk/Documentation/keys-request-key.txt b/trunk/Documentation/keys-request-key.txt
index 266955d23ee6..09b55e461740 100644
--- a/trunk/Documentation/keys-request-key.txt
+++ b/trunk/Documentation/keys-request-key.txt
@@ -11,26 +11,29 @@ request_key*():
 
 	struct key *request_key(const struct key_type *type,
 				const char *description,
-				const char *callout_string);
+				const char *callout_info);
 
 or:
 
 	struct key *request_key_with_auxdata(const struct key_type *type,
 					     const char *description,
-					     const char *callout_string,
+					     const char *callout_info,
+					     size_t callout_len,
 					     void *aux);
 
 or:
 
 	struct key *request_key_async(const struct key_type *type,
 				      const char *description,
-				      const char *callout_string);
+				      const char *callout_info,
+				      size_t callout_len);
 
 or:
 
 	struct key *request_key_async_with_auxdata(const struct key_type *type,
 						   const char *description,
-						   const char *callout_string,
+						   const char *callout_info,
+					     	   size_t callout_len,
 						   void *aux);
 
 Or by userspace invoking the request_key system call:
diff --git a/trunk/Documentation/keys.txt b/trunk/Documentation/keys.txt
index 51652d39e61c..d5c7a57d1700 100644
--- a/trunk/Documentation/keys.txt
+++ b/trunk/Documentation/keys.txt
@@ -170,7 +170,8 @@ The key service provides a number of features besides keys:
      amount of description and payload space that can be consumed.
 
      The user can view information on this and other statistics through procfs
-     files.
+     files.  The root user may also alter the quota limits through sysctl files
+     (see the section "New procfs files").
 
      Process-specific and thread-specific keyrings are not counted towards a
      user's quota.
@@ -329,6 +330,27 @@ about the status of the key service:
 	<bytes>/<max>		Key size quota
 
 
+Four new sysctl files have been added also for the purpose of controlling the
+quota limits on keys:
+
+ (*) /proc/sys/kernel/keys/root_maxkeys
+     /proc/sys/kernel/keys/root_maxbytes
+
+     These files hold the maximum number of keys that root may have and the
+     maximum total number of bytes of data that root may have stored in those
+     keys.
+
+ (*) /proc/sys/kernel/keys/maxkeys
+     /proc/sys/kernel/keys/maxbytes
+
+     These files hold the maximum number of keys that each non-root user may
+     have and the maximum total number of bytes of data that each of those
+     users may have stored in their keys.
+
+Root may alter these by writing each new limit as a decimal number string to
+the appropriate file.
+
+
 ===============================
 USERSPACE SYSTEM CALL INTERFACE
 ===============================
@@ -711,6 +733,27 @@ The keyctl syscall functions are:
      The assumed authoritative key is inherited across fork and exec.
 
 
+ (*) Get the LSM security context attached to a key.
+
+	long keyctl(KEYCTL_GET_SECURITY, key_serial_t key, char *buffer,
+		    size_t buflen)
+
+     This function returns a string that represents the LSM security context
+     attached to a key in the buffer provided.
+
+     Unless there's an error, it always returns the amount of data it could
+     produce, even if that's too big for the buffer, but it won't copy more
+     than requested to userspace. If the buffer pointer is NULL then no copy
+     will take place.
+
+     A NUL character is included at the end of the string if the buffer is
+     sufficiently big.  This is included in the returned count.  If no LSM is
+     in force then an empty string will be returned.
+
+     A process must have view permission on the key for this function to be
+     successful.
+
+
 ===============
 KERNEL SERVICES
 ===============
@@ -771,7 +814,7 @@ payload contents" for more information.
 
 	struct key *request_key(const struct key_type *type,
 				const char *description,
-				const char *callout_string);
+				const char *callout_info);
 
     This is used to request a key or keyring with a description that matches
     the description specified according to the key type's match function. This
@@ -793,24 +836,28 @@ payload contents" for more information.
 
 	struct key *request_key_with_auxdata(const struct key_type *type,
 					     const char *description,
-					     const char *callout_string,
+					     const void *callout_info,
+					     size_t callout_len,
 					     void *aux);
 
     This is identical to request_key(), except that the auxiliary data is
-    passed to the key_type->request_key() op if it exists.
+    passed to the key_type->request_key() op if it exists, and the callout_info
+    is a blob of length callout_len, if given (the length may be 0).
 
 
 (*) A key can be requested asynchronously by calling one of:
 
 	struct key *request_key_async(const struct key_type *type,
 				      const char *description,
-				      const char *callout_string);
+				      const void *callout_info,
+				      size_t callout_len);
 
     or:
 
 	struct key *request_key_async_with_auxdata(const struct key_type *type,
 						   const char *description,
-						   const char *callout_string,
+						   const char *callout_info,
+					     	   size_t callout_len,
 					     	   void *aux);
 
     which are asynchronous equivalents of request_key() and
diff --git a/trunk/Documentation/kprobes.txt b/trunk/Documentation/kprobes.txt
index be89f393274f..6877e7187113 100644
--- a/trunk/Documentation/kprobes.txt
+++ b/trunk/Documentation/kprobes.txt
@@ -37,6 +37,11 @@ registration function such as register_kprobe() specifies where
 the probe is to be inserted and what handler is to be called when
 the probe is hit.
 
+There are also register_/unregister_*probes() functions for batch
+registration/unregistration of a group of *probes. These functions
+can speed up unregistration process when you have to unregister
+a lot of probes at once.
+
 The next three subsections explain how the different types of
 probes work.  They explain certain things that you'll need to
 know in order to make the best use of Kprobes -- e.g., the
@@ -190,10 +195,11 @@ code mapping.
 4. API Reference
 
 The Kprobes API includes a "register" function and an "unregister"
-function for each type of probe.  Here are terse, mini-man-page
-specifications for these functions and the associated probe handlers
-that you'll write.  See the files in the samples/kprobes/ sub-directory
-for examples.
+function for each type of probe. The API also includes "register_*probes"
+and "unregister_*probes" functions for (un)registering arrays of probes.
+Here are terse, mini-man-page specifications for these functions and
+the associated probe handlers that you'll write. See the files in the
+samples/kprobes/ sub-directory for examples.
 
 4.1 register_kprobe
 
@@ -319,6 +325,43 @@ void unregister_kretprobe(struct kretprobe *rp);
 Removes the specified probe.  The unregister function can be called
 at any time after the probe has been registered.
 
+NOTE:
+If the functions find an incorrect probe (ex. an unregistered probe),
+they clear the addr field of the probe.
+
+4.5 register_*probes
+
+#include <linux/kprobes.h>
+int register_kprobes(struct kprobe **kps, int num);
+int register_kretprobes(struct kretprobe **rps, int num);
+int register_jprobes(struct jprobe **jps, int num);
+
+Registers each of the num probes in the specified array.  If any
+error occurs during registration, all probes in the array, up to
+the bad probe, are safely unregistered before the register_*probes
+function returns.
+- kps/rps/jps: an array of pointers to *probe data structures
+- num: the number of the array entries.
+
+NOTE:
+You have to allocate(or define) an array of pointers and set all
+of the array entries before using these functions.
+
+4.6 unregister_*probes
+
+#include <linux/kprobes.h>
+void unregister_kprobes(struct kprobe **kps, int num);
+void unregister_kretprobes(struct kretprobe **rps, int num);
+void unregister_jprobes(struct jprobe **jps, int num);
+
+Removes each of the num probes in the specified array at once.
+
+NOTE:
+If the functions find some incorrect probes (ex. unregistered
+probes) in the specified array, they clear the addr field of those
+incorrect probes. However, other probes in the array are
+unregistered correctly.
+
 5. Kprobes Features and Limitations
 
 Kprobes allows multiple probes at the same address.  Currently,
diff --git a/trunk/Documentation/md.txt b/trunk/Documentation/md.txt
index 396cdd982c26..a8b430627473 100644
--- a/trunk/Documentation/md.txt
+++ b/trunk/Documentation/md.txt
@@ -450,3 +450,9 @@ These currently include
       there are upper and lower limits (32768, 16).  Default is 128.
   strip_cache_active (currently raid5 only)
       number of active entries in the stripe cache
+  preread_bypass_threshold (currently raid5 only)
+      number of times a stripe requiring preread will be bypassed by
+      a stripe that does not require preread.  For fairness defaults
+      to 1.  Setting this to 0 disables bypass accounting and
+      requires preread stripes to wait until all full-width stripe-
+      writes are complete.  Valid values are 0 to stripe_cache_size.
diff --git a/trunk/Documentation/oops-tracing.txt b/trunk/Documentation/oops-tracing.txt
index 7f60dfe642ca..b152e81da592 100644
--- a/trunk/Documentation/oops-tracing.txt
+++ b/trunk/Documentation/oops-tracing.txt
@@ -253,6 +253,10 @@ characters, each representing a particular tainted value.
 
   8: 'D' if the kernel has died recently, i.e. there was an OOPS or BUG.
 
+  9: 'A' if the ACPI table has been overridden.
+
+ 10: 'W' if a warning has previously been issued by the kernel.
+
 The primary reason for the 'Tainted: ' string is to tell kernel
 debuggers if this is a clean kernel or if anything unusual has
 occurred.  Tainting is permanent: even if an offending module is
diff --git a/trunk/Documentation/powerpc/booting-without-of.txt b/trunk/Documentation/powerpc/booting-without-of.txt
index cf89e8cfd5bf..1d2a772506cf 100644
--- a/trunk/Documentation/powerpc/booting-without-of.txt
+++ b/trunk/Documentation/powerpc/booting-without-of.txt
@@ -2836,6 +2836,39 @@ platforms are moved over to use the flattened-device-tree model.
 		   big-endian;
 	   };
 
+    r) Freescale Display Interface Unit
+
+    The Freescale DIU is a LCD controller, with proper hardware, it can also
+    drive DVI monitors.
+
+    Required properties:
+    - compatible : should be "fsl-diu".
+    - reg : should contain at least address and length of the DIU register
+      set.
+    - Interrupts : one DIU interrupt should be describe here.
+
+    Example (MPC8610HPCD)
+	display@2c000 {
+		compatible = "fsl,diu";
+		reg = <0x2c000 100>;
+		interrupts = <72 2>;
+		interrupt-parent = <&mpic>;
+	};
+
+    s) Freescale on board FPGA
+
+    This is the memory-mapped registers for on board FPGA.
+
+    Required properities:
+    - compatible : should be "fsl,fpga-pixis".
+    - reg : should contain the address and the lenght of the FPPGA register
+      set.
+
+    Example (MPC8610HPCD)
+	board-control@e8000000 {
+		compatible = "fsl,fpga-pixis";
+		reg = <0xe8000000 32>;
+	};
 
 VII - Marvell Discovery mv64[345]6x System Controller chips
 ===========================================================
diff --git a/trunk/Documentation/powerpc/kvm_440.txt b/trunk/Documentation/powerpc/kvm_440.txt
new file mode 100644
index 000000000000..c02a003fa03a
--- /dev/null
+++ b/trunk/Documentation/powerpc/kvm_440.txt
@@ -0,0 +1,41 @@
+Hollis Blanchard <hollisb@us.ibm.com>
+15 Apr 2008
+
+Various notes on the implementation of KVM for PowerPC 440:
+
+To enforce isolation, host userspace, guest kernel, and guest userspace all
+run at user privilege level. Only the host kernel runs in supervisor mode.
+Executing privileged instructions in the guest traps into KVM (in the host
+kernel), where we decode and emulate them. Through this technique, unmodified
+440 Linux kernels can be run (slowly) as guests. Future performance work will
+focus on reducing the overhead and frequency of these traps.
+
+The usual code flow is started from userspace invoking an "run" ioctl, which
+causes KVM to switch into guest context. We use IVPR to hijack the host
+interrupt vectors while running the guest, which allows us to direct all
+interrupts to kvmppc_handle_interrupt(). At this point, we could either
+- handle the interrupt completely (e.g. emulate "mtspr SPRG0"), or
+- let the host interrupt handler run (e.g. when the decrementer fires), or
+- return to host userspace (e.g. when the guest performs device MMIO)
+
+Address spaces: We take advantage of the fact that Linux doesn't use the AS=1
+address space (in host or guest), which gives us virtual address space to use
+for guest mappings. While the guest is running, the host kernel remains mapped
+in AS=0, but the guest can only use AS=1 mappings.
+
+TLB entries: The TLB entries covering the host linear mapping remain
+present while running the guest. This reduces the overhead of lightweight
+exits, which are handled by KVM running in the host kernel. We keep three
+copies of the TLB:
+ - guest TLB: contents of the TLB as the guest sees it
+ - shadow TLB: the TLB that is actually in hardware while guest is running
+ - host TLB: to restore TLB state when context switching guest -> host
+When a TLB miss occurs because a mapping was not present in the shadow TLB,
+but was present in the guest TLB, KVM handles the fault without invoking the
+guest. Large guest pages are backed by multiple 4KB shadow pages through this
+mechanism.
+
+IO: MMIO and DCR accesses are emulated by userspace. We use virtio for network
+and block IO, so those drivers must be enabled in the guest. It's possible
+that some qemu device emulation (e.g. e1000 or rtl8139) may also work with
+little effort.
diff --git a/trunk/Documentation/s390/kvm.txt b/trunk/Documentation/s390/kvm.txt
new file mode 100644
index 000000000000..6f5ceb0f09fc
--- /dev/null
+++ b/trunk/Documentation/s390/kvm.txt
@@ -0,0 +1,125 @@
+*** BIG FAT WARNING ***
+The kvm module is currently in EXPERIMENTAL state for s390. This means that
+the interface to the module is not yet considered to remain stable. Thus, be
+prepared that we keep breaking your userspace application and guest
+compatibility over and over again until we feel happy with the result. Make sure
+your guest kernel, your host kernel, and your userspace launcher are in a
+consistent state.
+
+This Documentation describes the unique ioctl calls to /dev/kvm, the resulting
+kvm-vm file descriptors, and the kvm-vcpu file descriptors that differ from x86.
+
+1. ioctl calls to /dev/kvm
+KVM does support the following ioctls on s390 that are common with other
+architectures and do behave the same:
+KVM_GET_API_VERSION
+KVM_CREATE_VM		(*) see note
+KVM_CHECK_EXTENSION
+KVM_GET_VCPU_MMAP_SIZE
+
+Notes:
+* KVM_CREATE_VM may fail on s390, if the calling process has multiple
+threads and has not called KVM_S390_ENABLE_SIE before.
+
+In addition, on s390 the following architecture specific ioctls are supported:
+ioctl:		KVM_S390_ENABLE_SIE
+args:		none
+see also:	include/linux/kvm.h
+This call causes the kernel to switch on PGSTE in the user page table. This
+operation is needed in order to run a virtual machine, and it requires the
+calling process to be single-threaded. Note that the first call to KVM_CREATE_VM
+will implicitly try to switch on PGSTE if the user process has not called
+KVM_S390_ENABLE_SIE before. User processes that want to launch multiple threads
+before creating a virtual machine have to call KVM_S390_ENABLE_SIE, or will
+observe an error calling KVM_CREATE_VM. Switching on PGSTE is a one-time
+operation, is not reversible, and will persist over the entire lifetime of
+the calling process. It does not have any user-visible effect other than a small
+performance penalty.
+
+2. ioctl calls to the kvm-vm file descriptor
+KVM does support the following ioctls on s390 that are common with other
+architectures and do behave the same:
+KVM_CREATE_VCPU
+KVM_SET_USER_MEMORY_REGION      (*) see note
+KVM_GET_DIRTY_LOG		(**) see note
+
+Notes:
+*  kvm does only allow exactly one memory slot on s390, which has to start
+   at guest absolute address zero and at a user address that is aligned on any
+   page boundary. This hardware "limitation" allows us to have a few unique
+   optimizations. The memory slot doesn't have to be filled
+   with memory actually, it may contain sparse holes. That said, with different
+   user memory layout this does still allow a large flexibility when
+   doing the guest memory setup.
+** KVM_GET_DIRTY_LOG doesn't work properly yet. The user will receive an empty
+log. This ioctl call is only needed for guest migration, and we intend to
+implement this one in the future.
+
+In addition, on s390 the following architecture specific ioctls for the kvm-vm
+file descriptor are supported:
+ioctl:		KVM_S390_INTERRUPT
+args:		struct kvm_s390_interrupt *
+see also:	include/linux/kvm.h
+This ioctl is used to submit a floating interrupt for a virtual machine.
+Floating interrupts may be delivered to any virtual cpu in the configuration.
+Only some interrupt types defined in include/linux/kvm.h make sense when
+submitted as floating interrupts. The following interrupts are not considered
+to be useful as floating interrupts, and a call to inject them will result in
+-EINVAL error code: program interrupts and interprocessor signals. Valid
+floating interrupts are:
+KVM_S390_INT_VIRTIO
+KVM_S390_INT_SERVICE
+
+3. ioctl calls to the kvm-vcpu file descriptor
+KVM does support the following ioctls on s390 that are common with other
+architectures and do behave the same:
+KVM_RUN
+KVM_GET_REGS
+KVM_SET_REGS
+KVM_GET_SREGS
+KVM_SET_SREGS
+KVM_GET_FPU
+KVM_SET_FPU
+
+In addition, on s390 the following architecture specific ioctls for the
+kvm-vcpu file descriptor are supported:
+ioctl:		KVM_S390_INTERRUPT
+args:		struct kvm_s390_interrupt *
+see also:	include/linux/kvm.h
+This ioctl is used to submit an interrupt for a specific virtual cpu.
+Only some interrupt types defined in include/linux/kvm.h make sense when
+submitted for a specific cpu. The following interrupts are not considered
+to be useful, and a call to inject them will result in -EINVAL error code:
+service processor calls and virtio interrupts. Valid interrupt types are:
+KVM_S390_PROGRAM_INT
+KVM_S390_SIGP_STOP
+KVM_S390_RESTART
+KVM_S390_SIGP_SET_PREFIX
+KVM_S390_INT_EMERGENCY
+
+ioctl:		KVM_S390_STORE_STATUS
+args:		unsigned long
+see also:	include/linux/kvm.h
+This ioctl stores the state of the cpu at the guest real address given as
+argument, unless one of the following values defined in include/linux/kvm.h
+is given as arguement:
+KVM_S390_STORE_STATUS_NOADDR - the CPU stores its status to the save area in
+absolute lowcore as defined by the principles of operation
+KVM_S390_STORE_STATUS_PREFIXED - the CPU stores its status to the save area in
+its prefix page just like the dump tool that comes with zipl. This is useful
+to create a system dump for use with lkcdutils or crash.
+
+ioctl:		KVM_S390_SET_INITIAL_PSW
+args:		struct kvm_s390_psw *
+see also:	include/linux/kvm.h
+This ioctl can be used to set the processor status word (psw) of a stopped cpu
+prior to running it with KVM_RUN. Note that this call is not required to modify
+the psw during sie intercepts that fall back to userspace because struct kvm_run
+does contain the psw, and this value is evaluated during reentry of KVM_RUN
+after the intercept exit was recognized.
+
+ioctl:		KVM_S390_INITIAL_RESET
+args:		none
+see also:	include/linux/kvm.h
+This ioctl can be used to perform an initial cpu reset as defined by the
+principles of operation. The target cpu has to be in stopped state.
diff --git a/trunk/Documentation/spi/spidev b/trunk/Documentation/spi/spidev
index 5c8e1b988a08..ed2da5e5b28a 100644
--- a/trunk/Documentation/spi/spidev
+++ b/trunk/Documentation/spi/spidev
@@ -126,8 +126,8 @@ NOTES:
 FULL DUPLEX CHARACTER DEVICE API
 ================================
 
-See the sample program below for one example showing the use of the full
-duplex programming interface.  (Although it doesn't perform a full duplex
+See the spidev_fdx.c sample program for one example showing the use of the
+full duplex programming interface.  (Although it doesn't perform a full duplex
 transfer.)  The model is the same as that used in the kernel spi_sync()
 request; the individual transfers offer the same capabilities as are
 available to kernel drivers (except that it's not asynchronous).
@@ -141,167 +141,3 @@ and bitrate for each transfer segment.)
 
 To make a full duplex request, provide both rx_buf and tx_buf for the
 same transfer.  It's even OK if those are the same buffer.
-
-
-SAMPLE PROGRAM
-==============
-
---------------------------------	CUT HERE
-#include <stdio.h>
-#include <unistd.h>
-#include <stdlib.h>
-#include <fcntl.h>
-#include <string.h>
-
-#include <sys/ioctl.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-
-#include <linux/types.h>
-#include <linux/spi/spidev.h>
-
-
-static int verbose;
-
-static void do_read(int fd, int len)
-{
-	unsigned char	buf[32], *bp;
-	int		status;
-
-	/* read at least 2 bytes, no more than 32 */
-	if (len < 2)
-		len = 2;
-	else if (len > sizeof(buf))
-		len = sizeof(buf);
-	memset(buf, 0, sizeof buf);
-
-	status = read(fd, buf, len);
-	if (status < 0) {
-		perror("read");
-		return;
-	}
-	if (status != len) {
-		fprintf(stderr, "short read\n");
-		return;
-	}
-
-	printf("read(%2d, %2d): %02x %02x,", len, status,
-		buf[0], buf[1]);
-	status -= 2;
-	bp = buf + 2;
-	while (status-- > 0)
-		printf(" %02x", *bp++);
-	printf("\n");
-}
-
-static void do_msg(int fd, int len)
-{
-	struct spi_ioc_transfer	xfer[2];
-	unsigned char		buf[32], *bp;
-	int			status;
-
-	memset(xfer, 0, sizeof xfer);
-	memset(buf, 0, sizeof buf);
-
-	if (len > sizeof buf)
-		len = sizeof buf;
-
-	buf[0] = 0xaa;
-	xfer[0].tx_buf = (__u64) buf;
-	xfer[0].len = 1;
-
-	xfer[1].rx_buf = (__u64) buf;
-	xfer[1].len = len;
-
-	status = ioctl(fd, SPI_IOC_MESSAGE(2), xfer);
-	if (status < 0) {
-		perror("SPI_IOC_MESSAGE");
-		return;
-	}
-
-	printf("response(%2d, %2d): ", len, status);
-	for (bp = buf; len; len--)
-		printf(" %02x", *bp++);
-	printf("\n");
-}
-
-static void dumpstat(const char *name, int fd)
-{
-	__u8	mode, lsb, bits;
-	__u32	speed;
-
-	if (ioctl(fd, SPI_IOC_RD_MODE, &mode) < 0) {
-		perror("SPI rd_mode");
-		return;
-	}
-	if (ioctl(fd, SPI_IOC_RD_LSB_FIRST, &lsb) < 0) {
-		perror("SPI rd_lsb_fist");
-		return;
-	}
-	if (ioctl(fd, SPI_IOC_RD_BITS_PER_WORD, &bits) < 0) {
-		perror("SPI bits_per_word");
-		return;
-	}
-	if (ioctl(fd, SPI_IOC_RD_MAX_SPEED_HZ, &speed) < 0) {
-		perror("SPI max_speed_hz");
-		return;
-	}
-
-	printf("%s: spi mode %d, %d bits %sper word, %d Hz max\n",
-		name, mode, bits, lsb ? "(lsb first) " : "", speed);
-}
-
-int main(int argc, char **argv)
-{
-	int		c;
-	int		readcount = 0;
-	int		msglen = 0;
-	int		fd;
-	const char	*name;
-
-	while ((c = getopt(argc, argv, "hm:r:v")) != EOF) {
-		switch (c) {
-		case 'm':
-			msglen = atoi(optarg);
-			if (msglen < 0)
-				goto usage;
-			continue;
-		case 'r':
-			readcount = atoi(optarg);
-			if (readcount < 0)
-				goto usage;
-			continue;
-		case 'v':
-			verbose++;
-			continue;
-		case 'h':
-		case '?':
-usage:
-			fprintf(stderr,
-				"usage: %s [-h] [-m N] [-r N] /dev/spidevB.D\n",
-				argv[0]);
-			return 1;
-		}
-	}
-
-	if ((optind + 1) != argc)
-		goto usage;
-	name = argv[optind];
-
-	fd = open(name, O_RDWR);
-	if (fd < 0) {
-		perror("open");
-		return 1;
-	}
-
-	dumpstat(name, fd);
-
-	if (msglen)
-		do_msg(fd, msglen);
-
-	if (readcount)
-		do_read(fd, readcount);
-
-	close(fd);
-	return 0;
-}
diff --git a/trunk/Documentation/spi/spidev_fdx.c b/trunk/Documentation/spi/spidev_fdx.c
new file mode 100644
index 000000000000..fc354f760384
--- /dev/null
+++ b/trunk/Documentation/spi/spidev_fdx.c
@@ -0,0 +1,158 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <string.h>
+
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include <linux/types.h>
+#include <linux/spi/spidev.h>
+
+
+static int verbose;
+
+static void do_read(int fd, int len)
+{
+	unsigned char	buf[32], *bp;
+	int		status;
+
+	/* read at least 2 bytes, no more than 32 */
+	if (len < 2)
+		len = 2;
+	else if (len > sizeof(buf))
+		len = sizeof(buf);
+	memset(buf, 0, sizeof buf);
+
+	status = read(fd, buf, len);
+	if (status < 0) {
+		perror("read");
+		return;
+	}
+	if (status != len) {
+		fprintf(stderr, "short read\n");
+		return;
+	}
+
+	printf("read(%2d, %2d): %02x %02x,", len, status,
+		buf[0], buf[1]);
+	status -= 2;
+	bp = buf + 2;
+	while (status-- > 0)
+		printf(" %02x", *bp++);
+	printf("\n");
+}
+
+static void do_msg(int fd, int len)
+{
+	struct spi_ioc_transfer	xfer[2];
+	unsigned char		buf[32], *bp;
+	int			status;
+
+	memset(xfer, 0, sizeof xfer);
+	memset(buf, 0, sizeof buf);
+
+	if (len > sizeof buf)
+		len = sizeof buf;
+
+	buf[0] = 0xaa;
+	xfer[0].tx_buf = (__u64) buf;
+	xfer[0].len = 1;
+
+	xfer[1].rx_buf = (__u64) buf;
+	xfer[1].len = len;
+
+	status = ioctl(fd, SPI_IOC_MESSAGE(2), xfer);
+	if (status < 0) {
+		perror("SPI_IOC_MESSAGE");
+		return;
+	}
+
+	printf("response(%2d, %2d): ", len, status);
+	for (bp = buf; len; len--)
+		printf(" %02x", *bp++);
+	printf("\n");
+}
+
+static void dumpstat(const char *name, int fd)
+{
+	__u8	mode, lsb, bits;
+	__u32	speed;
+
+	if (ioctl(fd, SPI_IOC_RD_MODE, &mode) < 0) {
+		perror("SPI rd_mode");
+		return;
+	}
+	if (ioctl(fd, SPI_IOC_RD_LSB_FIRST, &lsb) < 0) {
+		perror("SPI rd_lsb_fist");
+		return;
+	}
+	if (ioctl(fd, SPI_IOC_RD_BITS_PER_WORD, &bits) < 0) {
+		perror("SPI bits_per_word");
+		return;
+	}
+	if (ioctl(fd, SPI_IOC_RD_MAX_SPEED_HZ, &speed) < 0) {
+		perror("SPI max_speed_hz");
+		return;
+	}
+
+	printf("%s: spi mode %d, %d bits %sper word, %d Hz max\n",
+		name, mode, bits, lsb ? "(lsb first) " : "", speed);
+}
+
+int main(int argc, char **argv)
+{
+	int		c;
+	int		readcount = 0;
+	int		msglen = 0;
+	int		fd;
+	const char	*name;
+
+	while ((c = getopt(argc, argv, "hm:r:v")) != EOF) {
+		switch (c) {
+		case 'm':
+			msglen = atoi(optarg);
+			if (msglen < 0)
+				goto usage;
+			continue;
+		case 'r':
+			readcount = atoi(optarg);
+			if (readcount < 0)
+				goto usage;
+			continue;
+		case 'v':
+			verbose++;
+			continue;
+		case 'h':
+		case '?':
+usage:
+			fprintf(stderr,
+				"usage: %s [-h] [-m N] [-r N] /dev/spidevB.D\n",
+				argv[0]);
+			return 1;
+		}
+	}
+
+	if ((optind + 1) != argc)
+		goto usage;
+	name = argv[optind];
+
+	fd = open(name, O_RDWR);
+	if (fd < 0) {
+		perror("open");
+		return 1;
+	}
+
+	dumpstat(name, fd);
+
+	if (msglen)
+		do_msg(fd, msglen);
+
+	if (readcount)
+		do_read(fd, readcount);
+
+	close(fd);
+	return 0;
+}
diff --git a/trunk/Documentation/sysrq.txt b/trunk/Documentation/sysrq.txt
index 10c8f6922ef4..5ce0952aa065 100644
--- a/trunk/Documentation/sysrq.txt
+++ b/trunk/Documentation/sysrq.txt
@@ -85,6 +85,8 @@ On all -  write a character to /proc/sysrq-trigger.  e.g.:
 'k'     - Secure Access Key (SAK) Kills all programs on the current virtual
           console. NOTE: See important comments below in SAK section.
 
+'l'     - Shows a stack backtrace for all active CPUs.
+
 'm'     - Will dump current memory info to your console.
 
 'n'	- Used to make RT tasks nice-able
diff --git a/trunk/Documentation/vm/numa_memory_policy.txt b/trunk/Documentation/vm/numa_memory_policy.txt
index dd4986497996..bad16d3f6a47 100644
--- a/trunk/Documentation/vm/numa_memory_policy.txt
+++ b/trunk/Documentation/vm/numa_memory_policy.txt
@@ -135,77 +135,58 @@ most general to most specific:
 
 Components of Memory Policies
 
-    A Linux memory policy is a tuple consisting of a "mode" and an optional set
-    of nodes.  The mode determine the behavior of the policy, while the
-    optional set of nodes can be viewed as the arguments to the behavior.
+    A Linux memory policy consists of a "mode", optional mode flags, and an
+    optional set of nodes.  The mode determines the behavior of the policy,
+    the optional mode flags determine the behavior of the mode, and the
+    optional set of nodes can be viewed as the arguments to the policy
+    behavior.
 
    Internally, memory policies are implemented by a reference counted
    structure, struct mempolicy.  Details of this structure will be discussed
    in context, below, as required to explain the behavior.
 
-	Note:  in some functions AND in the struct mempolicy itself, the mode
-	is called "policy".  However, to avoid confusion with the policy tuple,
-	this document will continue to use the term "mode".
-
    Linux memory policy supports the following 4 behavioral modes:
 
-	Default Mode--MPOL_DEFAULT:  The behavior specified by this mode is
-	context or scope dependent.
-
-	    As mentioned in the Policy Scope section above, during normal
-	    system operation, the System Default Policy is hard coded to
-	    contain the Default mode.
-
-	    In this context, default mode means "local" allocation--that is
-	    attempt to allocate the page from the node associated with the cpu
-	    where the fault occurs.  If the "local" node has no memory, or the
-	    node's memory can be exhausted [no free pages available], local
-	    allocation will "fallback to"--attempt to allocate pages from--
-	    "nearby" nodes, in order of increasing "distance".
+	Default Mode--MPOL_DEFAULT:  This mode is only used in the memory
+	policy APIs.  Internally, MPOL_DEFAULT is converted to the NULL
+	memory policy in all policy scopes.  Any existing non-default policy
+	will simply be removed when MPOL_DEFAULT is specified.  As a result,
+	MPOL_DEFAULT means "fall back to the next most specific policy scope."
 
-		Implementation detail -- subject to change:  "Fallback" uses
-		a per node list of sibling nodes--called zonelists--built at
-		boot time, or when nodes or memory are added or removed from
-		the system [memory hotplug].  These per node zonelist are
-		constructed with nodes in order of increasing distance based
-		on information provided by the platform firmware.
+	    For example, a NULL or default task policy will fall back to the
+	    system default policy.  A NULL or default vma policy will fall
+	    back to the task policy.
 
-	    When a task/process policy or a shared policy contains the Default
-	    mode, this also means "local allocation", as described above.
+	    When specified in one of the memory policy APIs, the Default mode
+	    does not use the optional set of nodes.
 
-	    In the context of a VMA, Default mode means "fall back to task
-	    policy"--which may or may not specify Default mode.  Thus, Default
-	    mode can not be counted on to mean local allocation when used
-	    on a non-shared region of the address space.  However, see
-	    MPOL_PREFERRED below.
-
-	    The Default mode does not use the optional set of nodes.
+	    It is an error for the set of nodes specified for this policy to
+	    be non-empty.
 
 	MPOL_BIND:  This mode specifies that memory must come from the
-	set of nodes specified by the policy.
-
-	    The memory policy APIs do not specify an order in which the nodes
-	    will be searched.  However, unlike "local allocation", the Bind
-	    policy does not consider the distance between the nodes.  Rather,
-	    allocations will fallback to the nodes specified by the policy in
-	    order of numeric node id.  Like everything in Linux, this is subject
-	    to change.
+	set of nodes specified by the policy.  Memory will be allocated from
+	the node in the set with sufficient free memory that is closest to
+	the node where the allocation takes place.
 
 	MPOL_PREFERRED:  This mode specifies that the allocation should be
 	attempted from the single node specified in the policy.  If that
-	allocation fails, the kernel will search other nodes, exactly as
-	it would for a local allocation that started at the preferred node
-	in increasing distance from the preferred node.  "Local" allocation
-	policy can be viewed as a Preferred policy that starts at the node
+	allocation fails, the kernel will search other nodes, in order of
+	increasing distance from the preferred node based on information
+	provided by the platform firmware.
 	containing the cpu where the allocation takes place.
 
 	    Internally, the Preferred policy uses a single node--the
-	    preferred_node member of struct mempolicy.  A "distinguished
-	    value of this preferred_node, currently '-1', is interpreted
-	    as "the node containing the cpu where the allocation takes
-	    place"--local allocation.  This is the way to specify
-	    local allocation for a specific range of addresses--i.e. for
-	    VMA policies.
+	    preferred_node member of struct mempolicy.  When the internal
+	    mode flag MPOL_F_LOCAL is set, the preferred_node is ignored and
+	    the policy is interpreted as local allocation.  "Local" allocation
+	    policy can be viewed as a Preferred policy that starts at the node
+	    containing the cpu where the allocation takes place.
+
+	    It is possible for the user to specify that local allocation is
+	    always preferred by passing an empty nodemask with this mode.
+	    If an empty nodemask is passed, the policy cannot use the
+	    MPOL_F_STATIC_NODES or MPOL_F_RELATIVE_NODES flags described
+	    below.
 
 	MPOL_INTERLEAVED:  This mode specifies that page allocations be
 	interleaved, on a page granularity, across the nodes specified in
@@ -231,6 +212,154 @@ Components of Memory Policies
 	    the temporary interleaved system default policy works in this
 	    mode.
 
+   Linux memory policy supports the following optional mode flags:
+
+	MPOL_F_STATIC_NODES:  This flag specifies that the nodemask passed by
+	the user should not be remapped if the task or VMA's set of allowed
+	nodes changes after the memory policy has been defined.
+
+	    Without this flag, anytime a mempolicy is rebound because of a
+	    change in the set of allowed nodes, the node (Preferred) or
+	    nodemask (Bind, Interleave) is remapped to the new set of
+	    allowed nodes.  This may result in nodes being used that were
+	    previously undesired.
+
+	    With this flag, if the user-specified nodes overlap with the
+	    nodes allowed by the task's cpuset, then the memory policy is
+	    applied to their intersection.  If the two sets of nodes do not
+	    overlap, the Default policy is used.
+
+	    For example, consider a task that is attached to a cpuset with
+	    mems 1-3 that sets an Interleave policy over the same set.  If
+	    the cpuset's mems change to 3-5, the Interleave will now occur
+	    over nodes 3, 4, and 5.  With this flag, however, since only node
+	    3 is allowed from the user's nodemask, the "interleave" only
+	    occurs over that node.  If no nodes from the user's nodemask are
+	    now allowed, the Default behavior is used.
+
+	    MPOL_F_STATIC_NODES cannot be combined with the
+	    MPOL_F_RELATIVE_NODES flag.  It also cannot be used for
+	    MPOL_PREFERRED policies that were created with an empty nodemask
+	    (local allocation).
+
+	MPOL_F_RELATIVE_NODES:  This flag specifies that the nodemask passed
+	by the user will be mapped relative to the set of the task or VMA's
+	set of allowed nodes.  The kernel stores the user-passed nodemask,
+	and if the allowed nodes changes, then that original nodemask will
+	be remapped relative to the new set of allowed nodes.
+
+	    Without this flag (and without MPOL_F_STATIC_NODES), anytime a
+	    mempolicy is rebound because of a change in the set of allowed
+	    nodes, the node (Preferred) or nodemask (Bind, Interleave) is
+	    remapped to the new set of allowed nodes.  That remap may not
+	    preserve the relative nature of the user's passed nodemask to its
+	    set of allowed nodes upon successive rebinds: a nodemask of
+	    1,3,5 may be remapped to 7-9 and then to 1-3 if the set of
+	    allowed nodes is restored to its original state.
+
+	    With this flag, the remap is done so that the node numbers from
+	    the user's passed nodemask are relative to the set of allowed
+	    nodes.  In other words, if nodes 0, 2, and 4 are set in the user's
+	    nodemask, the policy will be effected over the first (and in the
+	    Bind or Interleave case, the third and fifth) nodes in the set of
+	    allowed nodes.  The nodemask passed by the user represents nodes
+	    relative to task or VMA's set of allowed nodes.
+
+	    If the user's nodemask includes nodes that are outside the range
+	    of the new set of allowed nodes (for example, node 5 is set in
+	    the user's nodemask when the set of allowed nodes is only 0-3),
+	    then the remap wraps around to the beginning of the nodemask and,
+	    if not already set, sets the node in the mempolicy nodemask.
+
+	    For example, consider a task that is attached to a cpuset with
+	    mems 2-5 that sets an Interleave policy over the same set with
+	    MPOL_F_RELATIVE_NODES.  If the cpuset's mems change to 3-7, the
+	    interleave now occurs over nodes 3,5-6.  If the cpuset's mems
+	    then change to 0,2-3,5, then the interleave occurs over nodes
+	    0,3,5.
+
+	    Thanks to the consistent remapping, applications preparing
+	    nodemasks to specify memory policies using this flag should
+	    disregard their current, actual cpuset imposed memory placement
+	    and prepare the nodemask as if they were always located on
+	    memory nodes 0 to N-1, where N is the number of memory nodes the
+	    policy is intended to manage.  Let the kernel then remap to the
+	    set of memory nodes allowed by the task's cpuset, as that may
+	    change over time.
+
+	    MPOL_F_RELATIVE_NODES cannot be combined with the
+	    MPOL_F_STATIC_NODES flag.  It also cannot be used for
+	    MPOL_PREFERRED policies that were created with an empty nodemask
+	    (local allocation).
+
+MEMORY POLICY REFERENCE COUNTING
+
+To resolve use/free races, struct mempolicy contains an atomic reference
+count field.  Internal interfaces, mpol_get()/mpol_put() increment and
+decrement this reference count, respectively.  mpol_put() will only free
+the structure back to the mempolicy kmem cache when the reference count
+goes to zero.
+
+When a new memory policy is allocated, it's reference count is initialized
+to '1', representing the reference held by the task that is installing the
+new policy.  When a pointer to a memory policy structure is stored in another
+structure, another reference is added, as the task's reference will be dropped
+on completion of the policy installation.
+
+During run-time "usage" of the policy, we attempt to minimize atomic operations
+on the reference count, as this can lead to cache lines bouncing between cpus
+and NUMA nodes.  "Usage" here means one of the following:
+
+1) querying of the policy, either by the task itself [using the get_mempolicy()
+   API discussed below] or by another task using the /proc/<pid>/numa_maps
+   interface.
+
+2) examination of the policy to determine the policy mode and associated node
+   or node lists, if any, for page allocation.  This is considered a "hot
+   path".  Note that for MPOL_BIND, the "usage" extends across the entire
+   allocation process, which may sleep during page reclaimation, because the
+   BIND policy nodemask is used, by reference, to filter ineligible nodes.
+
+We can avoid taking an extra reference during the usages listed above as
+follows:
+
+1) we never need to get/free the system default policy as this is never
+   changed nor freed, once the system is up and running.
+
+2) for querying the policy, we do not need to take an extra reference on the
+   target task's task policy nor vma policies because we always acquire the
+   task's mm's mmap_sem for read during the query.  The set_mempolicy() and
+   mbind() APIs [see below] always acquire the mmap_sem for write when
+   installing or replacing task or vma policies.  Thus, there is no possibility
+   of a task or thread freeing a policy while another task or thread is
+   querying it.
+
+3) Page allocation usage of task or vma policy occurs in the fault path where
+   we hold them mmap_sem for read.  Again, because replacing the task or vma
+   policy requires that the mmap_sem be held for write, the policy can't be
+   freed out from under us while we're using it for page allocation.
+
+4) Shared policies require special consideration.  One task can replace a
+   shared memory policy while another task, with a distinct mmap_sem, is
+   querying or allocating a page based on the policy.  To resolve this
+   potential race, the shared policy infrastructure adds an extra reference
+   to the shared policy during lookup while holding a spin lock on the shared
+   policy management structure.  This requires that we drop this extra
+   reference when we're finished "using" the policy.  We must drop the
+   extra reference on shared policies in the same query/allocation paths
+   used for non-shared policies.  For this reason, shared policies are marked
+   as such, and the extra reference is dropped "conditionally"--i.e., only
+   for shared policies.
+
+   Because of this extra reference counting, and because we must lookup
+   shared policies in a tree structure under spinlock, shared policies are
+   more expensive to use in the page allocation path.  This is expecially
+   true for shared policies on shared memory regions shared by tasks running
+   on different NUMA nodes.  This extra overhead can be avoided by always
+   falling back to task or system default policy for shared memory regions,
+   or by prefaulting the entire shared memory region into memory and locking
+   it down.  However, this might not be appropriate for all applications.
+
 MEMORY POLICY APIs
 
 Linux supports 3 system calls for controlling memory policy.  These APIS
@@ -251,7 +380,9 @@ Set [Task] Memory Policy:
 	Set's the calling task's "task/process memory policy" to mode
 	specified by the 'mode' argument and the set of nodes defined
 	by 'nmask'.  'nmask' points to a bit mask of node ids containing
-	at least 'maxnode' ids.
+	at least 'maxnode' ids.  Optional mode flags may be passed by
+	combining the 'mode' argument with the flag (for example:
+	MPOL_INTERLEAVE | MPOL_F_STATIC_NODES).
 
 	See the set_mempolicy(2) man page for more details
 
@@ -303,29 +434,19 @@ MEMORY POLICIES AND CPUSETS
 Memory policies work within cpusets as described above.  For memory policies
 that require a node or set of nodes, the nodes are restricted to the set of
 nodes whose memories are allowed by the cpuset constraints.  If the nodemask
-specified for the policy contains nodes that are not allowed by the cpuset, or
-the intersection of the set of nodes specified for the policy and the set of
-nodes with memory is the empty set, the policy is considered invalid
-and cannot be installed.
-
-The interaction of memory policies and cpusets can be problematic for a
-couple of reasons:
-
-1) the memory policy APIs take physical node id's as arguments.  As mentioned
-   above, it is illegal to specify nodes that are not allowed in the cpuset.
-   The application must query the allowed nodes using the get_mempolicy()
-   API with the MPOL_F_MEMS_ALLOWED flag to determine the allowed nodes and
-   restrict itself to those nodes.  However, the resources available to a
-   cpuset can be changed by the system administrator, or a workload manager
-   application, at any time.  So, a task may still get errors attempting to
-   specify policy nodes, and must query the allowed memories again.
-
-2) when tasks in two cpusets share access to a memory region, such as shared
-   memory segments created by shmget() of mmap() with the MAP_ANONYMOUS and
-   MAP_SHARED flags, and any of the tasks install shared policy on the region,
-   only nodes whose memories are allowed in both cpusets may be used in the
-   policies.  Obtaining this information requires "stepping outside" the
-   memory policy APIs to use the cpuset information and requires that one
-   know in what cpusets other task might be attaching to the shared region.
-   Furthermore, if the cpusets' allowed memory sets are disjoint, "local"
-   allocation is the only valid policy.
+specified for the policy contains nodes that are not allowed by the cpuset and
+MPOL_F_RELATIVE_NODES is not used, the intersection of the set of nodes
+specified for the policy and the set of nodes with memory is used.  If the
+result is the empty set, the policy is considered invalid and cannot be
+installed.  If MPOL_F_RELATIVE_NODES is used, the policy's nodes are mapped
+onto and folded into the task's set of allowed nodes as previously described.
+
+The interaction of memory policies and cpusets can be problematic when tasks
+in two cpusets share access to a memory region, such as shared memory segments
+created by shmget() of mmap() with the MAP_ANONYMOUS and MAP_SHARED flags, and
+any of the tasks install shared policy on the region, only nodes whose
+memories are allowed in both cpusets may be used in the policies.  Obtaining
+this information requires "stepping outside" the memory policy APIs to use the
+cpuset information and requires that one know in what cpusets other task might
+be attaching to the shared region.  Furthermore, if the cpusets' allowed
+memory sets are disjoint, "local" allocation is the only valid policy.
diff --git a/trunk/Documentation/vm/slabinfo.c b/trunk/Documentation/vm/slabinfo.c
index 22d7e3e4d60c..d3ce295bffac 100644
--- a/trunk/Documentation/vm/slabinfo.c
+++ b/trunk/Documentation/vm/slabinfo.c
@@ -31,7 +31,7 @@ struct slabinfo {
 	int hwcache_align, object_size, objs_per_slab;
 	int sanity_checks, slab_size, store_user, trace;
 	int order, poison, reclaim_account, red_zone;
-	unsigned long partial, objects, slabs;
+	unsigned long partial, objects, slabs, objects_partial, objects_total;
 	unsigned long alloc_fastpath, alloc_slowpath;
 	unsigned long free_fastpath, free_slowpath;
 	unsigned long free_frozen, free_add_partial, free_remove_partial;
@@ -540,7 +540,8 @@ void slabcache(struct slabinfo *s)
 		return;
 
 	store_size(size_str, slab_size(s));
-	snprintf(dist_str, 40, "%lu/%lu/%d", s->slabs, s->partial, s->cpu_slabs);
+	snprintf(dist_str, 40, "%lu/%lu/%d", s->slabs - s->cpu_slabs,
+						s->partial, s->cpu_slabs);
 
 	if (!line++)
 		first_line();
@@ -776,7 +777,6 @@ void totals(void)
 		unsigned long used;
 		unsigned long long wasted;
 		unsigned long long objwaste;
-		long long objects_in_partial_slabs;
 		unsigned long percentage_partial_slabs;
 		unsigned long percentage_partial_objs;
 
@@ -790,18 +790,11 @@ void totals(void)
 		wasted = size - used;
 		objwaste = s->slab_size - s->object_size;
 
-		objects_in_partial_slabs = s->objects -
-			(s->slabs - s->partial - s ->cpu_slabs) *
-			s->objs_per_slab;
-
-		if (objects_in_partial_slabs < 0)
-			objects_in_partial_slabs = 0;
-
 		percentage_partial_slabs = s->partial * 100 / s->slabs;
 		if (percentage_partial_slabs > 100)
 			percentage_partial_slabs = 100;
 
-		percentage_partial_objs = objects_in_partial_slabs * 100
+		percentage_partial_objs = s->objects_partial * 100
 							/ s->objects;
 
 		if (percentage_partial_objs > 100)
@@ -823,8 +816,8 @@ void totals(void)
 			min_objects = s->objects;
 		if (used < min_used)
 			min_used = used;
-		if (objects_in_partial_slabs < min_partobj)
-			min_partobj = objects_in_partial_slabs;
+		if (s->objects_partial < min_partobj)
+			min_partobj = s->objects_partial;
 		if (percentage_partial_slabs < min_ppart)
 			min_ppart = percentage_partial_slabs;
 		if (percentage_partial_objs < min_ppartobj)
@@ -848,8 +841,8 @@ void totals(void)
 			max_objects = s->objects;
 		if (used > max_used)
 			max_used = used;
-		if (objects_in_partial_slabs > max_partobj)
-			max_partobj = objects_in_partial_slabs;
+		if (s->objects_partial > max_partobj)
+			max_partobj = s->objects_partial;
 		if (percentage_partial_slabs > max_ppart)
 			max_ppart = percentage_partial_slabs;
 		if (percentage_partial_objs > max_ppartobj)
@@ -864,7 +857,7 @@ void totals(void)
 
 		total_objects += s->objects;
 		total_used += used;
-		total_partobj += objects_in_partial_slabs;
+		total_partobj += s->objects_partial;
 		total_ppart += percentage_partial_slabs;
 		total_ppartobj += percentage_partial_objs;
 
@@ -1160,6 +1153,8 @@ void read_slab_dir(void)
 			slab->hwcache_align = get_obj("hwcache_align");
 			slab->object_size = get_obj("object_size");
 			slab->objects = get_obj("objects");
+			slab->objects_partial = get_obj("objects_partial");
+			slab->objects_total = get_obj("objects_total");
 			slab->objs_per_slab = get_obj("objs_per_slab");
 			slab->order = get_obj("order");
 			slab->partial = get_obj("partial");
diff --git a/trunk/Kbuild b/trunk/Kbuild
index 1570d248ad92..32f19c5c9bb0 100644
--- a/trunk/Kbuild
+++ b/trunk/Kbuild
@@ -1,26 +1,61 @@
 #
 # Kbuild for top-level directory of the kernel
 # This file takes care of the following:
-# 1) Generate asm-offsets.h
-# 2) Check for missing system calls
+# 1) Generate bounds.h
+# 2) Generate asm-offsets.h (may need bounds.h)
+# 3) Check for missing system calls
 
 #####
-# 1) Generate asm-offsets.h
+# 1) Generate bounds.h
+
+bounds-file := include/linux/bounds.h
+
+always  := $(bounds-file)
+targets := $(bounds-file) kernel/bounds.s
+
+quiet_cmd_bounds = GEN     $@
+define cmd_bounds
+	(set -e; \
+	 echo "#ifndef __LINUX_BOUNDS_H__"; \
+	 echo "#define __LINUX_BOUNDS_H__"; \
+	 echo "/*"; \
+	 echo " * DO NOT MODIFY."; \
+	 echo " *"; \
+	 echo " * This file was generated by Kbuild"; \
+	 echo " *"; \
+	 echo " */"; \
+	 echo ""; \
+	 sed -ne $(sed-y) $<; \
+	 echo ""; \
+	 echo "#endif" ) > $@
+endef
+
+# We use internal kbuild rules to avoid the "is up to date" message from make
+kernel/bounds.s: kernel/bounds.c FORCE
+	$(Q)mkdir -p $(dir $@)
+	$(call if_changed_dep,cc_s_c)
+
+$(obj)/$(bounds-file): kernel/bounds.s Kbuild
+	$(Q)mkdir -p $(dir $@)
+	$(call cmd,bounds)
+
+#####
+# 2) Generate asm-offsets.h
 #
 
 offsets-file := include/asm-$(SRCARCH)/asm-offsets.h
 
-always  := $(offsets-file)
-targets := $(offsets-file)
+always  += $(offsets-file)
+targets += $(offsets-file)
 targets += arch/$(SRCARCH)/kernel/asm-offsets.s
-clean-files := $(addprefix $(objtree)/,$(targets))
+
 
 # Default sed regexp - multiline due to syntax constraints
 define sed-y
-	"/^->/{s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; s:->::; p;}"
+	"/^->/{s:->#\(.*\):/* \1 */:; \
+	s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; \
+	s:->::; p;}"
 endef
-# Override default regexp for specific architectures
-sed-$(CONFIG_MIPS) := "/^@@@/{s/^@@@//; s/ \#.*\$$//; p;}"
 
 quiet_cmd_offsets = GEN     $@
 define cmd_offsets
@@ -40,7 +75,8 @@ define cmd_offsets
 endef
 
 # We use internal kbuild rules to avoid the "is up to date" message from make
-arch/$(SRCARCH)/kernel/asm-offsets.s: arch/$(SRCARCH)/kernel/asm-offsets.c FORCE
+arch/$(SRCARCH)/kernel/asm-offsets.s: arch/$(SRCARCH)/kernel/asm-offsets.c \
+                                      $(obj)/$(bounds-file) FORCE
 	$(Q)mkdir -p $(dir $@)
 	$(call if_changed_dep,cc_s_c)
 
@@ -49,7 +85,7 @@ $(obj)/$(offsets-file): arch/$(SRCARCH)/kernel/asm-offsets.s Kbuild
 	$(call cmd,offsets)
 
 #####
-# 2) Check for missing system calls
+# 3) Check for missing system calls
 #
 
 quiet_cmd_syscalls = CALL    $<
@@ -58,3 +94,7 @@ quiet_cmd_syscalls = CALL    $<
 PHONY += missing-syscalls
 missing-syscalls: scripts/checksyscalls.sh FORCE
 	$(call cmd,syscalls)
+
+# Delete all targets during make clean
+clean-files := $(addprefix $(objtree)/,$(targets))
+
diff --git a/trunk/MAINTAINERS b/trunk/MAINTAINERS
index a942f3852499..d103766f3b40 100644
--- a/trunk/MAINTAINERS
+++ b/trunk/MAINTAINERS
@@ -2329,6 +2329,13 @@ L:	kvm-devel@lists.sourceforge.net
 W:	kvm.sourceforge.net
 S:	Supported
 
+KERNEL VIRTUAL MACHINE (KVM) FOR POWERPC
+P:	Hollis Blanchard
+M:	hollisb@us.ibm.com
+L:	kvm-ppc-devel@lists.sourceforge.net
+W:	kvm.sourceforge.net
+S:	Supported
+
 KERNEL VIRTUAL MACHINE For Itanium(KVM/IA64)
 P:	Anthony Xu
 M:	anthony.xu@intel.com
@@ -2338,6 +2345,16 @@ L:	kvm-ia64-devel@lists.sourceforge.net
 W:	kvm.sourceforge.net
 S:	Supported
 
+KERNEL VIRTUAL MACHINE for s390 (KVM/s390)
+P:	Carsten Otte
+M:	cotte@de.ibm.com
+P:	Christian Borntraeger
+M:	borntraeger@de.ibm.com
+M:	linux390@de.ibm.com
+L:	linux-s390@vger.kernel.org
+W:	http://www.ibm.com/developerworks/linux/linux390/
+S:	Supported
+
 KEXEC
 P:	Eric Biederman
 M:	ebiederm@xmission.com
@@ -2677,7 +2694,7 @@ P:	David Howells
 M:	dhowells@redhat.com
 P:	Koichi Yasutake
 M:	yasutake.koichi@jp.panasonic.com
-L:	linux-am33-list@redhat.com
+L:	linux-am33-list@redhat.com (moderated for non-subscribers)
 W:	ftp://ftp.redhat.com/pub/redhat/gnupro/AM33/
 S:	Maintained
 
diff --git a/trunk/Makefile b/trunk/Makefile
index fc3411e6f071..d3634cd6fe35 100644
--- a/trunk/Makefile
+++ b/trunk/Makefile
@@ -1174,8 +1174,10 @@ rpm: include/config/kernel.release FORCE
 # Brief documentation of the typical targets used
 # ---------------------------------------------------------------------------
 
-boards := $(wildcard $(srctree)/arch/$(ARCH)/configs/*_defconfig)
+boards := $(wildcard $(srctree)/arch/$(SRCARCH)/configs/*_defconfig)
 boards := $(notdir $(boards))
+board-dirs := $(dir $(wildcard $(srctree)/arch/$(SRCARCH)/configs/*/*_defconfig))
+board-dirs := $(sort $(notdir $(board-dirs:/=)))
 
 help:
 	@echo  'Cleaning targets:'
@@ -1221,14 +1223,19 @@ help:
 	@echo  'Documentation targets:'
 	@$(MAKE) -f $(srctree)/Documentation/DocBook/Makefile dochelp
 	@echo  ''
-	@echo  'Architecture specific targets ($(ARCH)):'
+	@echo  'Architecture specific targets ($(SRCARCH)):'
 	@$(if $(archhelp),$(archhelp),\
-		echo '  No architecture specific help defined for $(ARCH)')
+		echo '  No architecture specific help defined for $(SRCARCH)')
 	@echo  ''
 	@$(if $(boards), \
 		$(foreach b, $(boards), \
 		printf "  %-24s - Build for %s\\n" $(b) $(subst _defconfig,,$(b));) \
 		echo '')
+	@$(if $(board-dirs), \
+		$(foreach b, $(board-dirs), \
+		printf "  %-16s - Show %s-specific targets\\n" help-$(b) $(b);) \
+		printf "  %-16s - Show all of the above\\n" help-boards; \
+		echo '')
 
 	@echo  '  make V=0|1 [targets] 0 => quiet build (default), 1 => verbose build'
 	@echo  '  make V=2   [targets] 2 => give reason for rebuild of target'
@@ -1240,6 +1247,20 @@ help:
 	@echo  'For further info see the ./README file'
 
 
+help-board-dirs := $(addprefix help-,$(board-dirs))
+
+help-boards: $(help-board-dirs)
+
+boards-per-dir = $(notdir $(wildcard $(srctree)/arch/$(SRCARCH)/configs/$*/*_defconfig))
+
+$(help-board-dirs): help-%:
+	@echo  'Architecture specific targets ($(SRCARCH) $*):'
+	@$(if $(boards-per-dir), \
+		$(foreach b, $(boards-per-dir), \
+		printf "  %-24s - Build for %s\\n" $*/$(b) $(subst _defconfig,,$(b));) \
+		echo '')
+
+
 # Documentation targets
 # ---------------------------------------------------------------------------
 %docs: scripts_basic FORCE
diff --git a/trunk/arch/Kconfig b/trunk/arch/Kconfig
index 694c9af520bb..3ea332b009e5 100644
--- a/trunk/arch/Kconfig
+++ b/trunk/arch/Kconfig
@@ -36,3 +36,6 @@ config HAVE_KPROBES
 
 config HAVE_KRETPROBES
 	def_bool n
+
+config HAVE_DMA_ATTRS
+	def_bool n
diff --git a/trunk/arch/alpha/kernel/asm-offsets.c b/trunk/arch/alpha/kernel/asm-offsets.c
index 6c56c754a0b5..4b18cd94d59d 100644
--- a/trunk/arch/alpha/kernel/asm-offsets.c
+++ b/trunk/arch/alpha/kernel/asm-offsets.c
@@ -8,13 +8,9 @@
 #include <linux/stddef.h>
 #include <linux/sched.h>
 #include <linux/ptrace.h>
+#include <linux/kbuild.h>
 #include <asm/io.h>
 
-#define DEFINE(sym, val) \
-        asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
-
 void foo(void)
 {
 	DEFINE(TI_TASK, offsetof(struct thread_info, task));
diff --git a/trunk/arch/alpha/kernel/core_marvel.c b/trunk/arch/alpha/kernel/core_marvel.c
index f10d2eddd2c3..b04f1feb1dda 100644
--- a/trunk/arch/alpha/kernel/core_marvel.c
+++ b/trunk/arch/alpha/kernel/core_marvel.c
@@ -994,7 +994,7 @@ marvel_agp_configure(alpha_agp_info *agp)
 		 * rate, but warn the user.
 		 */
 		printk("%s: unknown PLL setting RNGB=%lx (PLL6_CTL=%016lx)\n",
-		       __FUNCTION__, IO7_PLL_RNGB(agp_pll), agp_pll);
+		       __func__, IO7_PLL_RNGB(agp_pll), agp_pll);
 		break;
 	}
 
@@ -1044,13 +1044,13 @@ marvel_agp_translate(alpha_agp_info *agp, dma_addr_t addr)
 
 	if (addr < agp->aperture.bus_base ||
 	    addr >= agp->aperture.bus_base + agp->aperture.size) {
-		printk("%s: addr out of range\n", __FUNCTION__);
+		printk("%s: addr out of range\n", __func__);
 		return -EINVAL;
 	}
 
 	pte = aper->arena->ptes[baddr >> PAGE_SHIFT];
 	if (!(pte & 1)) {
-		printk("%s: pte not valid\n", __FUNCTION__);
+		printk("%s: pte not valid\n", __func__);
 		return -EINVAL;
 	} 
 	return (pte >> 1) << PAGE_SHIFT;
diff --git a/trunk/arch/alpha/kernel/core_t2.c b/trunk/arch/alpha/kernel/core_t2.c
index f5ca5255eb06..c0750291b44a 100644
--- a/trunk/arch/alpha/kernel/core_t2.c
+++ b/trunk/arch/alpha/kernel/core_t2.c
@@ -336,10 +336,7 @@ t2_direct_map_window1(unsigned long base, unsigned long length)
 
 #if DEBUG_PRINT_FINAL_SETTINGS
 	printk("%s: setting WBASE1=0x%lx WMASK1=0x%lx TBASE1=0x%lx\n",
-	       __FUNCTION__,
-	       *(vulp)T2_WBASE1,
-	       *(vulp)T2_WMASK1,
-	       *(vulp)T2_TBASE1);
+	       __func__, *(vulp)T2_WBASE1, *(vulp)T2_WMASK1, *(vulp)T2_TBASE1);
 #endif
 }
 
@@ -366,10 +363,7 @@ t2_sg_map_window2(struct pci_controller *hose,
 
 #if DEBUG_PRINT_FINAL_SETTINGS
 	printk("%s: setting WBASE2=0x%lx WMASK2=0x%lx TBASE2=0x%lx\n",
-	       __FUNCTION__,
-	       *(vulp)T2_WBASE2,
-	       *(vulp)T2_WMASK2,
-	       *(vulp)T2_TBASE2);
+	       __func__, *(vulp)T2_WBASE2, *(vulp)T2_WMASK2, *(vulp)T2_TBASE2);
 #endif
 }
 
@@ -377,15 +371,15 @@ static void __init
 t2_save_configuration(void)
 {
 #if DEBUG_PRINT_INITIAL_SETTINGS
-	printk("%s: HAE_1 was 0x%lx\n", __FUNCTION__, srm_hae); /* HW is 0 */
-	printk("%s: HAE_2 was 0x%lx\n", __FUNCTION__, *(vulp)T2_HAE_2);
-	printk("%s: HAE_3 was 0x%lx\n", __FUNCTION__, *(vulp)T2_HAE_3);
-	printk("%s: HAE_4 was 0x%lx\n", __FUNCTION__, *(vulp)T2_HAE_4);
-	printk("%s: HBASE was 0x%lx\n", __FUNCTION__, *(vulp)T2_HBASE);
+	printk("%s: HAE_1 was 0x%lx\n", __func__, srm_hae); /* HW is 0 */
+	printk("%s: HAE_2 was 0x%lx\n", __func__, *(vulp)T2_HAE_2);
+	printk("%s: HAE_3 was 0x%lx\n", __func__, *(vulp)T2_HAE_3);
+	printk("%s: HAE_4 was 0x%lx\n", __func__, *(vulp)T2_HAE_4);
+	printk("%s: HBASE was 0x%lx\n", __func__, *(vulp)T2_HBASE);
 
-	printk("%s: WBASE1=0x%lx WMASK1=0x%lx TBASE1=0x%lx\n", __FUNCTION__, 
+	printk("%s: WBASE1=0x%lx WMASK1=0x%lx TBASE1=0x%lx\n", __func__,
 	       *(vulp)T2_WBASE1, *(vulp)T2_WMASK1, *(vulp)T2_TBASE1);
-	printk("%s: WBASE2=0x%lx WMASK2=0x%lx TBASE2=0x%lx\n", __FUNCTION__, 
+	printk("%s: WBASE2=0x%lx WMASK2=0x%lx TBASE2=0x%lx\n", __func__,
 	       *(vulp)T2_WBASE2, *(vulp)T2_WMASK2, *(vulp)T2_TBASE2);
 #endif
 
diff --git a/trunk/arch/alpha/kernel/core_titan.c b/trunk/arch/alpha/kernel/core_titan.c
index 819326627b96..319fcb74611e 100644
--- a/trunk/arch/alpha/kernel/core_titan.c
+++ b/trunk/arch/alpha/kernel/core_titan.c
@@ -365,21 +365,21 @@ void __init
 titan_init_arch(void)
 {
 #if 0
-	printk("%s: titan_init_arch()\n", __FUNCTION__);
-	printk("%s: CChip registers:\n", __FUNCTION__);
-	printk("%s: CSR_CSC 0x%lx\n", __FUNCTION__, TITAN_cchip->csc.csr);
-	printk("%s: CSR_MTR 0x%lx\n", __FUNCTION__, TITAN_cchip->mtr.csr);
-	printk("%s: CSR_MISC 0x%lx\n", __FUNCTION__, TITAN_cchip->misc.csr);
-	printk("%s: CSR_DIM0 0x%lx\n", __FUNCTION__, TITAN_cchip->dim0.csr);
-	printk("%s: CSR_DIM1 0x%lx\n", __FUNCTION__, TITAN_cchip->dim1.csr);
-	printk("%s: CSR_DIR0 0x%lx\n", __FUNCTION__, TITAN_cchip->dir0.csr);
-	printk("%s: CSR_DIR1 0x%lx\n", __FUNCTION__, TITAN_cchip->dir1.csr);
-	printk("%s: CSR_DRIR 0x%lx\n", __FUNCTION__, TITAN_cchip->drir.csr);
-
-	printk("%s: DChip registers:\n", __FUNCTION__);
-	printk("%s: CSR_DSC 0x%lx\n", __FUNCTION__, TITAN_dchip->dsc.csr);
-	printk("%s: CSR_STR 0x%lx\n", __FUNCTION__, TITAN_dchip->str.csr);
-	printk("%s: CSR_DREV 0x%lx\n", __FUNCTION__, TITAN_dchip->drev.csr);
+	printk("%s: titan_init_arch()\n", __func__);
+	printk("%s: CChip registers:\n", __func__);
+	printk("%s: CSR_CSC 0x%lx\n", __func__, TITAN_cchip->csc.csr);
+	printk("%s: CSR_MTR 0x%lx\n", __func__, TITAN_cchip->mtr.csr);
+	printk("%s: CSR_MISC 0x%lx\n", __func__, TITAN_cchip->misc.csr);
+	printk("%s: CSR_DIM0 0x%lx\n", __func__, TITAN_cchip->dim0.csr);
+	printk("%s: CSR_DIM1 0x%lx\n", __func__, TITAN_cchip->dim1.csr);
+	printk("%s: CSR_DIR0 0x%lx\n", __func__, TITAN_cchip->dir0.csr);
+	printk("%s: CSR_DIR1 0x%lx\n", __func__, TITAN_cchip->dir1.csr);
+	printk("%s: CSR_DRIR 0x%lx\n", __func__, TITAN_cchip->drir.csr);
+
+	printk("%s: DChip registers:\n", __func__);
+	printk("%s: CSR_DSC 0x%lx\n", __func__, TITAN_dchip->dsc.csr);
+	printk("%s: CSR_STR 0x%lx\n", __func__, TITAN_dchip->str.csr);
+	printk("%s: CSR_DREV 0x%lx\n", __func__, TITAN_dchip->drev.csr);
 #endif
 
 	boot_cpuid = __hard_smp_processor_id();
@@ -700,13 +700,13 @@ titan_agp_translate(alpha_agp_info *agp, dma_addr_t addr)
 
 	if (addr < agp->aperture.bus_base ||
 	    addr >= agp->aperture.bus_base + agp->aperture.size) {
-		printk("%s: addr out of range\n", __FUNCTION__);
+		printk("%s: addr out of range\n", __func__);
 		return -EINVAL;
 	}
 
 	pte = aper->arena->ptes[baddr >> PAGE_SHIFT];
 	if (!(pte & 1)) {
-		printk("%s: pte not valid\n", __FUNCTION__);
+		printk("%s: pte not valid\n", __func__);
 		return -EINVAL;
 	}
 
diff --git a/trunk/arch/alpha/kernel/core_tsunami.c b/trunk/arch/alpha/kernel/core_tsunami.c
index ef91e09590d4..5e7c28f92f19 100644
--- a/trunk/arch/alpha/kernel/core_tsunami.c
+++ b/trunk/arch/alpha/kernel/core_tsunami.c
@@ -241,8 +241,6 @@ tsunami_probe_write(volatile unsigned long *vaddr)
 #define tsunami_probe_read(ADDR) 1
 #endif /* NXM_MACHINE_CHECKS_ON_TSUNAMI */
 
-#define FN __FUNCTION__
-
 static void __init
 tsunami_init_one_pchip(tsunami_pchip *pchip, int index)
 {
@@ -383,27 +381,27 @@ tsunami_init_arch(void)
 	/* NXMs just don't matter to Tsunami--unless they make it
 	   choke completely. */
 	tmp = (unsigned long)(TSUNAMI_cchip - 1);
-	printk("%s: probing bogus address:  0x%016lx\n", FN, bogus_addr);
+	printk("%s: probing bogus address:  0x%016lx\n", __func__, bogus_addr);
 	printk("\tprobe %s\n",
 	       tsunami_probe_write((unsigned long *)bogus_addr)
 	       ? "succeeded" : "failed");
 #endif /* NXM_MACHINE_CHECKS_ON_TSUNAMI */
 
 #if 0
-	printk("%s: CChip registers:\n", FN);
-	printk("%s: CSR_CSC 0x%lx\n", FN, TSUNAMI_cchip->csc.csr);
-	printk("%s: CSR_MTR 0x%lx\n", FN, TSUNAMI_cchip.mtr.csr);
-	printk("%s: CSR_MISC 0x%lx\n", FN, TSUNAMI_cchip->misc.csr);
-	printk("%s: CSR_DIM0 0x%lx\n", FN, TSUNAMI_cchip->dim0.csr);
-	printk("%s: CSR_DIM1 0x%lx\n", FN, TSUNAMI_cchip->dim1.csr);
-	printk("%s: CSR_DIR0 0x%lx\n", FN, TSUNAMI_cchip->dir0.csr);
-	printk("%s: CSR_DIR1 0x%lx\n", FN, TSUNAMI_cchip->dir1.csr);
-	printk("%s: CSR_DRIR 0x%lx\n", FN, TSUNAMI_cchip->drir.csr);
+	printk("%s: CChip registers:\n", __func__);
+	printk("%s: CSR_CSC 0x%lx\n", __func__, TSUNAMI_cchip->csc.csr);
+	printk("%s: CSR_MTR 0x%lx\n", __func__, TSUNAMI_cchip.mtr.csr);
+	printk("%s: CSR_MISC 0x%lx\n", __func__, TSUNAMI_cchip->misc.csr);
+	printk("%s: CSR_DIM0 0x%lx\n", __func__, TSUNAMI_cchip->dim0.csr);
+	printk("%s: CSR_DIM1 0x%lx\n", __func__, TSUNAMI_cchip->dim1.csr);
+	printk("%s: CSR_DIR0 0x%lx\n", __func__, TSUNAMI_cchip->dir0.csr);
+	printk("%s: CSR_DIR1 0x%lx\n", __func__, TSUNAMI_cchip->dir1.csr);
+	printk("%s: CSR_DRIR 0x%lx\n", __func__, TSUNAMI_cchip->drir.csr);
 
 	printk("%s: DChip registers:\n");
-	printk("%s: CSR_DSC 0x%lx\n", FN, TSUNAMI_dchip->dsc.csr);
-	printk("%s: CSR_STR 0x%lx\n", FN, TSUNAMI_dchip->str.csr);
-	printk("%s: CSR_DREV 0x%lx\n", FN, TSUNAMI_dchip->drev.csr);
+	printk("%s: CSR_DSC 0x%lx\n", __func__, TSUNAMI_dchip->dsc.csr);
+	printk("%s: CSR_STR 0x%lx\n", __func__, TSUNAMI_dchip->str.csr);
+	printk("%s: CSR_DREV 0x%lx\n", __func__, TSUNAMI_dchip->drev.csr);
 #endif
 	/* With multiple PCI busses, we play with I/O as physical addrs.  */
 	ioport_resource.end = ~0UL;
diff --git a/trunk/arch/alpha/kernel/module.c b/trunk/arch/alpha/kernel/module.c
index 026ba9af6d6a..ebc3c894b5a2 100644
--- a/trunk/arch/alpha/kernel/module.c
+++ b/trunk/arch/alpha/kernel/module.c
@@ -120,6 +120,12 @@ module_frob_arch_sections(Elf64_Ehdr *hdr, Elf64_Shdr *sechdrs,
 
 	nsyms = symtab->sh_size / sizeof(Elf64_Sym);
 	chains = kcalloc(nsyms, sizeof(struct got_entry), GFP_KERNEL);
+	if (!chains) {
+		printk(KERN_ERR
+		       "module %s: no memory for symbol chain buffer\n",
+		       me->name);
+		return -ENOMEM;
+	}
 
 	got->sh_size = 0;
 	got->sh_addralign = 8;
diff --git a/trunk/arch/alpha/kernel/pci.c b/trunk/arch/alpha/kernel/pci.c
index 78357798b6fd..36ab22a7ea12 100644
--- a/trunk/arch/alpha/kernel/pci.c
+++ b/trunk/arch/alpha/kernel/pci.c
@@ -208,7 +208,7 @@ pdev_save_srm_config(struct pci_dev *dev)
 
 	tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
 	if (!tmp) {
-		printk(KERN_ERR "%s: kmalloc() failed!\n", __FUNCTION__);
+		printk(KERN_ERR "%s: kmalloc() failed!\n", __func__);
 		return;
 	}
 	tmp->next = srm_saved_configs;
@@ -514,8 +514,8 @@ sys_pciconfig_iobase(long which, unsigned long bus, unsigned long dfn)
 
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
-	unsigned long start = pci_resource_start(dev, bar);
-	unsigned long len = pci_resource_len(dev, bar);
+	resource_size_t start = pci_resource_start(dev, bar);
+	resource_size_t len = pci_resource_len(dev, bar);
 	unsigned long flags = pci_resource_flags(dev, bar);
 
 	if (!len || !start)
diff --git a/trunk/arch/alpha/kernel/pci_iommu.c b/trunk/arch/alpha/kernel/pci_iommu.c
index dd6e334ab9e1..2179c602032a 100644
--- a/trunk/arch/alpha/kernel/pci_iommu.c
+++ b/trunk/arch/alpha/kernel/pci_iommu.c
@@ -79,25 +79,21 @@ iommu_arena_new_node(int nid, struct pci_controller *hose, dma_addr_t base,
 
 #ifdef CONFIG_DISCONTIGMEM
 
-        if (!NODE_DATA(nid) ||
-            (NULL == (arena = alloc_bootmem_node(NODE_DATA(nid),
-                                                 sizeof(*arena))))) {
-                printk("%s: couldn't allocate arena from node %d\n"
-                       "    falling back to system-wide allocation\n",
-                       __FUNCTION__, nid);
-                arena = alloc_bootmem(sizeof(*arena));
-        }
-
-        if (!NODE_DATA(nid) ||
-            (NULL == (arena->ptes = __alloc_bootmem_node(NODE_DATA(nid),
-                                                         mem_size,
-                                                         align,
-                                                         0)))) {
-                printk("%s: couldn't allocate arena ptes from node %d\n"
-                       "    falling back to system-wide allocation\n",
-                       __FUNCTION__, nid);
-                arena->ptes = __alloc_bootmem(mem_size, align, 0);
-        }
+	arena = alloc_bootmem_node(NODE_DATA(nid), sizeof(*arena));
+	if (!NODE_DATA(nid) || !arena) {
+		printk("%s: couldn't allocate arena from node %d\n"
+		       "    falling back to system-wide allocation\n",
+		       __func__, nid);
+		arena = alloc_bootmem(sizeof(*arena));
+	}
+
+	arena->ptes = __alloc_bootmem_node(NODE_DATA(nid), mem_size, align, 0);
+	if (!NODE_DATA(nid) || !arena->ptes) {
+		printk("%s: couldn't allocate arena ptes from node %d\n"
+		       "    falling back to system-wide allocation\n",
+		       __func__, nid);
+		arena->ptes = __alloc_bootmem(mem_size, align, 0);
+	}
 
 #else /* CONFIG_DISCONTIGMEM */
 
diff --git a/trunk/arch/alpha/kernel/smp.c b/trunk/arch/alpha/kernel/smp.c
index 63c2073401ee..2525692db0ab 100644
--- a/trunk/arch/alpha/kernel/smp.c
+++ b/trunk/arch/alpha/kernel/smp.c
@@ -755,7 +755,7 @@ smp_call_function_on_cpu (void (*func) (void *info), void *info, int retry,
 	if (atomic_read(&data.unstarted_count) > 0) {
 		long start_time = jiffies;
 		printk(KERN_ERR "%s: initial timeout -- trying long wait\n",
-		       __FUNCTION__);
+		       __func__);
 		timeout = jiffies + 30 * HZ;
 		while (atomic_read(&data.unstarted_count) > 0
 		       && time_before(jiffies, timeout))
@@ -764,7 +764,7 @@ smp_call_function_on_cpu (void (*func) (void *info), void *info, int retry,
 			long delta = jiffies - start_time;
 			printk(KERN_ERR 
 			       "%s: response %ld.%ld seconds into long wait\n",
-			       __FUNCTION__, delta / HZ,
+			       __func__, delta / HZ,
 			       (100 * (delta - ((delta / HZ) * HZ))) / HZ);
 		}
 	}
diff --git a/trunk/arch/alpha/kernel/srm_env.c b/trunk/arch/alpha/kernel/srm_env.c
index f7dd081d57ff..78ad7cd1bbd6 100644
--- a/trunk/arch/alpha/kernel/srm_env.c
+++ b/trunk/arch/alpha/kernel/srm_env.c
@@ -199,7 +199,7 @@ srm_env_init(void)
 		printk(KERN_INFO "%s: This Alpha system doesn't "
 				"know about SRM (or you've booted "
 				"SRM->MILO->Linux, which gets "
-				"misdetected)...\n", __FUNCTION__);
+				"misdetected)...\n", __func__);
 		return -ENODEV;
 	}
 
diff --git a/trunk/arch/alpha/kernel/sys_alcor.c b/trunk/arch/alpha/kernel/sys_alcor.c
index d187d01d2a17..e53a1e1c2f21 100644
--- a/trunk/arch/alpha/kernel/sys_alcor.c
+++ b/trunk/arch/alpha/kernel/sys_alcor.c
@@ -259,7 +259,7 @@ alcor_init_pci(void)
 	if (dev && dev->devfn == PCI_DEVFN(6,0)) {
 		alpha_mv.sys.cia.gru_int_req_bits = XLT_GRU_INT_REQ_BITS; 
 		printk(KERN_INFO "%s: Detected AS500 or XLT motherboard.\n",
-		       __FUNCTION__);
+		       __func__);
 	}
 	pci_dev_put(dev);
 }
diff --git a/trunk/arch/alpha/kernel/sys_marvel.c b/trunk/arch/alpha/kernel/sys_marvel.c
index 922143ea1cdb..828449cd2636 100644
--- a/trunk/arch/alpha/kernel/sys_marvel.c
+++ b/trunk/arch/alpha/kernel/sys_marvel.c
@@ -80,7 +80,7 @@ io7_get_irq_ctl(unsigned int irq, struct io7 **pio7)
 	if (!(io7 = marvel_find_io7(pid))) {
 		printk(KERN_ERR 
 		       "%s for nonexistent io7 -- vec %x, pid %d\n",
-		       __FUNCTION__, irq, pid);
+		       __func__, irq, pid);
 		return NULL;
 	}
 
@@ -90,7 +90,7 @@ io7_get_irq_ctl(unsigned int irq, struct io7 **pio7)
 	if (irq >= 0x180) {
 		printk(KERN_ERR 
 		       "%s for invalid irq -- pid %d adjusted irq %x\n",
-		       __FUNCTION__, pid, irq);
+		       __func__, pid, irq);
 		return NULL;
 	}
 
@@ -110,8 +110,8 @@ io7_enable_irq(unsigned int irq)
 
 	ctl = io7_get_irq_ctl(irq, &io7);
 	if (!ctl || !io7) {
-		printk(KERN_ERR "%s: get_ctl failed for irq %x\n", 
-		       __FUNCTION__, irq);
+		printk(KERN_ERR "%s: get_ctl failed for irq %x\n",
+		       __func__, irq);
 		return;
 	}
 		
@@ -130,8 +130,8 @@ io7_disable_irq(unsigned int irq)
 
 	ctl = io7_get_irq_ctl(irq, &io7);
 	if (!ctl || !io7) {
-		printk(KERN_ERR "%s: get_ctl failed for irq %x\n", 
-		       __FUNCTION__, irq);
+		printk(KERN_ERR "%s: get_ctl failed for irq %x\n",
+		       __func__, irq);
 		return;
 	}
 		
diff --git a/trunk/arch/alpha/kernel/sys_sable.c b/trunk/arch/alpha/kernel/sys_sable.c
index 906019cfa681..99a7f19da13a 100644
--- a/trunk/arch/alpha/kernel/sys_sable.c
+++ b/trunk/arch/alpha/kernel/sys_sable.c
@@ -454,7 +454,7 @@ sable_lynx_enable_irq(unsigned int irq)
 	spin_unlock(&sable_lynx_irq_lock);
 #if 0
 	printk("%s: mask 0x%lx bit 0x%x irq 0x%x\n",
-	       __FUNCTION__, mask, bit, irq);
+	       __func__, mask, bit, irq);
 #endif
 }
 
@@ -470,7 +470,7 @@ sable_lynx_disable_irq(unsigned int irq)
 	spin_unlock(&sable_lynx_irq_lock);
 #if 0
 	printk("%s: mask 0x%lx bit 0x%x irq 0x%x\n",
-	       __FUNCTION__, mask, bit, irq);
+	       __func__, mask, bit, irq);
 #endif
 }
 
@@ -524,7 +524,7 @@ sable_lynx_srm_device_interrupt(unsigned long vector)
 	irq = sable_lynx_irq_swizzle->mask_to_irq[bit];
 #if 0
 	printk("%s: vector 0x%lx bit 0x%x irq 0x%x\n",
-	       __FUNCTION__, vector, bit, irq);
+	       __func__, vector, bit, irq);
 #endif
 	handle_irq(irq);
 }
diff --git a/trunk/arch/alpha/kernel/sys_sio.c b/trunk/arch/alpha/kernel/sys_sio.c
index ee7b9009ebb4..d4327e461c22 100644
--- a/trunk/arch/alpha/kernel/sys_sio.c
+++ b/trunk/arch/alpha/kernel/sys_sio.c
@@ -89,7 +89,7 @@ sio_pci_route(void)
 	/* First, ALWAYS read and print the original setting. */
 	pci_bus_read_config_dword(pci_isa_hose->bus, PCI_DEVFN(7, 0), 0x60,
 				  &orig_route_tab);
-	printk("%s: PIRQ original 0x%x new 0x%x\n", __FUNCTION__,
+	printk("%s: PIRQ original 0x%x new 0x%x\n", __func__,
 	       orig_route_tab, alpha_mv.sys.sio.route_tab);
 
 #if defined(ALPHA_RESTORE_SRM_SETUP)
diff --git a/trunk/arch/alpha/kernel/traps.c b/trunk/arch/alpha/kernel/traps.c
index 2dc7f9fed213..dc57790250d2 100644
--- a/trunk/arch/alpha/kernel/traps.c
+++ b/trunk/arch/alpha/kernel/traps.c
@@ -8,6 +8,7 @@
  * This file initializes the trap entry points
  */
 
+#include <linux/jiffies.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/tty.h>
@@ -770,7 +771,7 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 	      unsigned long reg, struct pt_regs *regs)
 {
 	static int cnt = 0;
-	static long last_time = 0;
+	static unsigned long last_time;
 
 	unsigned long tmp1, tmp2, tmp3, tmp4;
 	unsigned long fake_reg, *reg_addr = &fake_reg;
@@ -781,7 +782,7 @@ do_entUnaUser(void __user * va, unsigned long opcode,
 	   with the unaliged access.  */
 
 	if (!test_thread_flag (TIF_UAC_NOPRINT)) {
-		if (cnt >= 5 && jiffies - last_time > 5*HZ) {
+		if (cnt >= 5 && time_after(jiffies, last_time + 5 * HZ)) {
 			cnt = 0;
 		}
 		if (++cnt < 5) {
diff --git a/trunk/arch/arm/Kconfig b/trunk/arch/arm/Kconfig
index d8d253285a94..b786e68914d4 100644
--- a/trunk/arch/arm/Kconfig
+++ b/trunk/arch/arm/Kconfig
@@ -8,6 +8,7 @@ mainmenu "Linux Kernel Configuration"
 config ARM
 	bool
 	default y
+	select HAVE_IDE
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
 	select HAVE_OPROFILE
@@ -223,7 +224,6 @@ config ARCH_CLPS7500
 	select TIMER_ACORN
 	select ISA
 	select NO_IOPORT
-	select HAVE_IDE
 	help
 	  Support for the Cirrus Logic PS7500FE system-on-a-chip.
 
@@ -236,7 +236,6 @@ config ARCH_CO285
 	bool "Co-EBSA285"
 	select FOOTBRIDGE
 	select FOOTBRIDGE_ADDIN
-	select HAVE_IDE
 	help
 	  Support for Intel's EBSA285 companion chip.
 
@@ -262,7 +261,6 @@ config ARCH_EP93XX
 config ARCH_FOOTBRIDGE
 	bool "FootBridge"
 	select FOOTBRIDGE
-	select HAVE_IDE
 	help
 	  Support for systems based on the DC21285 companion chip
 	  ("FootBridge"), such as the Simtec CATS and the Rebel NetWinder.
@@ -301,7 +299,6 @@ config ARCH_IOP32X
 	depends on MMU
 	select PLAT_IOP
 	select PCI
-	select HAVE_IDE
 	help
 	  Support for Intel's 80219 and IOP32X (XScale) family of
 	  processors.
@@ -311,14 +308,12 @@ config ARCH_IOP33X
 	depends on MMU
 	select PLAT_IOP
 	select PCI
-	select HAVE_IDE
 	help
 	  Support for Intel's IOP33X (XScale) family of processors.
 
 config ARCH_IXP23XX
  	bool "IXP23XX-based"
 	depends on MMU
-	select HAVE_IDE
  	select PCI
 	help
 	  Support for Intel's IXP23xx (XScale) family of processors.
@@ -336,14 +331,12 @@ config ARCH_IXP4XX
 	select GENERIC_GPIO
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
-	select HAVE_IDE
 	help
 	  Support for Intel's IXP4XX (XScale) family of processors.
 
 config ARCH_L7200
 	bool "LinkUp-L7200"
 	select FIQ
-	select HAVE_IDE
 	help
 	  Say Y here if you intend to run this kernel on a LinkUp Systems
 	  L7200 Software Development Board which uses an ARM720T processor.
@@ -400,7 +393,6 @@ config ARCH_PXA
 	depends on MMU
 	select ARCH_MTD_XIP
 	select GENERIC_GPIO
-	select HAVE_IDE
 	select HAVE_GPIO_LIB
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
@@ -416,7 +408,6 @@ config ARCH_RPC
 	select ARCH_MAY_HAVE_PC_FDC
 	select ISA_DMA_API
 	select NO_IOPORT
-	select HAVE_IDE
 	help
 	  On the Acorn Risc-PC, Linux can support the internal IDE disk and
 	  CD-ROM interface, serial and parallel port, and the floppy drive.
@@ -432,7 +423,6 @@ config ARCH_SA1100
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 	select TICK_ONESHOT
-	select HAVE_IDE
 	select HAVE_GPIO_LIB
 	help
 	  Support for StrongARM 11x0 based boards.
@@ -440,7 +430,6 @@ config ARCH_SA1100
 config ARCH_S3C2410
 	bool "Samsung S3C2410, S3C2412, S3C2413, S3C2440, S3C2442, S3C2443"
 	select GENERIC_GPIO
-	select HAVE_IDE
 	help
 	  Samsung S3C2410X CPU based systems, such as the Simtec Electronics
 	  BAST (<http://www.simtec.co.uk/products/EB110ITX/>), the IPAQ 1940 or
@@ -448,7 +437,6 @@ config ARCH_S3C2410
 
 config ARCH_SHARK
 	bool "Shark"
-	select HAVE_IDE
 	select ISA
 	select ISA_DMA
 	select PCI
@@ -458,7 +446,6 @@ config ARCH_SHARK
 
 config ARCH_LH7A40X
 	bool "Sharp LH7A40X"
-	select HAVE_IDE
 	help
 	  Say Y here for systems based on one of the Sharp LH7A40X
 	  System on a Chip processors.  These CPUs include an ARM922T
diff --git a/trunk/arch/arm/kernel/asm-offsets.c b/trunk/arch/arm/kernel/asm-offsets.c
index 0a0d2479274b..4a881258bb17 100644
--- a/trunk/arch/arm/kernel/asm-offsets.c
+++ b/trunk/arch/arm/kernel/asm-offsets.c
@@ -16,6 +16,7 @@
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/procinfo.h>
+#include <linux/kbuild.h>
 
 /*
  * Make sure that the compiler and target are compatible.
@@ -35,13 +36,6 @@
 #error    Known good compilers: 3.3
 #endif
 
-/* Use marker if you need to separate the values later */
-
-#define DEFINE(sym, val) \
-        asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
-
 int main(void)
 {
   DEFINE(TSK_ACTIVE_MM,		offsetof(struct task_struct, active_mm));
diff --git a/trunk/arch/arm/kernel/atags.c b/trunk/arch/arm/kernel/atags.c
index e2e934c38080..64c420805e6f 100644
--- a/trunk/arch/arm/kernel/atags.c
+++ b/trunk/arch/arm/kernel/atags.c
@@ -35,7 +35,7 @@ create_proc_entries(void)
 {
 	struct proc_dir_entry* tags_entry;
 
-	tags_entry = create_proc_read_entry("atags", 0400, &proc_root, read_buffer, &tags_buffer);
+	tags_entry = create_proc_read_entry("atags", 0400, NULL, read_buffer, &tags_buffer);
 	if (!tags_entry)
 		return -ENOMEM;
 
diff --git a/trunk/arch/arm/kernel/ecard.c b/trunk/arch/arm/kernel/ecard.c
index f56d48c451ea..a53c0aba5c14 100644
--- a/trunk/arch/arm/kernel/ecard.c
+++ b/trunk/arch/arm/kernel/ecard.c
@@ -37,6 +37,7 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/device.h>
 #include <linux/init.h>
 #include <linux/mutex.h>
@@ -723,17 +724,14 @@ unsigned int __ecard_address(ecard_t *ec, card_type_t type, card_speed_t speed)
 	return address;
 }
 
-static int ecard_prints(char *buffer, ecard_t *ec)
+static int ecard_prints(struct seq_file *m, ecard_t *ec)
 {
-	char *start = buffer;
-
-	buffer += sprintf(buffer, "  %d: %s ", ec->slot_no,
-			  ec->easi ? "EASI" : "    ");
+	seq_printf(m, "  %d: %s ", ec->slot_no, ec->easi ? "EASI" : "    ");
 
 	if (ec->cid.id == 0) {
 		struct in_chunk_dir incd;
 
-		buffer += sprintf(buffer, "[%04X:%04X] ",
+		seq_printf(m, "[%04X:%04X] ",
 			ec->cid.manufacturer, ec->cid.product);
 
 		if (!ec->card_desc && ec->cid.cd &&
@@ -744,43 +742,43 @@ static int ecard_prints(char *buffer, ecard_t *ec)
 				strcpy((char *)ec->card_desc, incd.d.string);
 		}
 
-		buffer += sprintf(buffer, "%s\n", ec->card_desc ? ec->card_desc : "*unknown*");
+		seq_printf(m, "%s\n", ec->card_desc ? ec->card_desc : "*unknown*");
 	} else
-		buffer += sprintf(buffer, "Simple card %d\n", ec->cid.id);
+		seq_printf(m, "Simple card %d\n", ec->cid.id);
 
-	return buffer - start;
+	return 0;
 }
 
-static int get_ecard_dev_info(char *buf, char **start, off_t pos, int count)
+static int ecard_devices_proc_show(struct seq_file *m, void *v)
 {
 	ecard_t *ec = cards;
-	off_t at = 0;
-	int len, cnt;
-
-	cnt = 0;
-	while (ec && count > cnt) {
-		len = ecard_prints(buf, ec);
-		at += len;
-		if (at >= pos) {
-			if (!*start) {
-				*start = buf + (pos - (at - len));
-				cnt = at - pos;
-			} else
-				cnt += len;
-			buf += len;
-		}
+
+	while (ec) {
+		ecard_prints(m, ec);
 		ec = ec->next;
 	}
-	return (count > cnt) ? cnt : count;
+	return 0;
 }
 
+static int ecard_devices_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ecard_devices_proc_show, NULL);
+}
+
+static const struct file_operations bus_ecard_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ecard_devices_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static struct proc_dir_entry *proc_bus_ecard_dir = NULL;
 
 static void ecard_proc_init(void)
 {
-	proc_bus_ecard_dir = proc_mkdir("ecard", proc_bus);
-	create_proc_info_entry("devices", 0, proc_bus_ecard_dir,
-		get_ecard_dev_info);
+	proc_bus_ecard_dir = proc_mkdir("bus/ecard", NULL);
+	proc_create("devices", 0, proc_bus_ecard_dir, &bus_ecard_proc_fops);
 }
 
 #define ec_set_resource(ec,nr,st,sz)				\
diff --git a/trunk/arch/arm/mach-at91/at91sam9261_devices.c b/trunk/arch/arm/mach-at91/at91sam9261_devices.c
index 37cd547855b1..728bb8f39441 100644
--- a/trunk/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/trunk/arch/arm/mach-at91/at91sam9261_devices.c
@@ -539,6 +539,17 @@ void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data)
 	at91_set_B_periph(AT91_PIN_PB28, 0);	/* LCDD23 */
 #endif
 
+	if (ARRAY_SIZE(lcdc_resources) > 2) {
+		void __iomem *fb;
+		struct resource *fb_res = &lcdc_resources[2];
+		size_t fb_len = fb_res->end - fb_res->start + 1;
+
+		fb = ioremap_writecombine(fb_res->start, fb_len);
+		if (fb) {
+			memset(fb, 0, fb_len);
+			iounmap(fb, fb_len);
+		}
+	}
 	lcdc_data = *data;
 	platform_device_register(&at91_lcdc_device);
 }
diff --git a/trunk/arch/arm/mach-at91/at91sam9rl_devices.c b/trunk/arch/arm/mach-at91/at91sam9rl_devices.c
index dbb9a5fc2090..054689804e77 100644
--- a/trunk/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/trunk/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -381,6 +381,20 @@ void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data)
 	at91_set_B_periph(AT91_PIN_PC24, 0);	/* LCDD22 */
 	at91_set_B_periph(AT91_PIN_PC25, 0);	/* LCDD23 */
 
+#ifdef CONFIG_FB_INTSRAM
+	{
+		void __iomem *fb;
+		struct resource *fb_res = &lcdc_resources[2];
+		size_t fb_len = fb_res->end - fb_res->start + 1;
+
+		fb = ioremap_writecombine(fb_res->start, fb_len);
+		if (fb) {
+			memset(fb, 0, fb_len);
+			iounmap(fb, fb_len);
+		}
+	}
+#endif
+
 	lcdc_data = *data;
 	platform_device_register(&at91_lcdc_device);
 }
diff --git a/trunk/arch/arm/mach-davinci/clock.c b/trunk/arch/arm/mach-davinci/clock.c
index 4143828a9684..c6b94f60e0b2 100644
--- a/trunk/arch/arm/mach-davinci/clock.c
+++ b/trunk/arch/arm/mach-davinci/clock.c
@@ -311,11 +311,7 @@ static const struct file_operations proc_davinci_ck_operations = {
 
 static int __init davinci_ck_proc_init(void)
 {
-	struct proc_dir_entry *entry;
-
-	entry = create_proc_entry("davinci_clocks", 0, NULL);
-	if (entry)
-		entry->proc_fops = &proc_davinci_ck_operations;
+	proc_create("davinci_clocks", 0, NULL, &proc_davinci_ck_operations);
 	return 0;
 
 }
diff --git a/trunk/arch/arm/mm/iomap.c b/trunk/arch/arm/mm/iomap.c
index 62066f3020c8..7429f8c01015 100644
--- a/trunk/arch/arm/mm/iomap.c
+++ b/trunk/arch/arm/mm/iomap.c
@@ -26,8 +26,8 @@ EXPORT_SYMBOL(ioport_unmap);
 #ifdef CONFIG_PCI
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
-	unsigned long start = pci_resource_start(dev, bar);
-	unsigned long len   = pci_resource_len(dev, bar);
+	resource_size_t start = pci_resource_start(dev, bar);
+	resource_size_t len   = pci_resource_len(dev, bar);
 	unsigned long flags = pci_resource_flags(dev, bar);
 
 	if (!len || !start)
diff --git a/trunk/arch/avr32/kernel/asm-offsets.c b/trunk/arch/avr32/kernel/asm-offsets.c
index 078cd33f467b..e4796c67a831 100644
--- a/trunk/arch/avr32/kernel/asm-offsets.c
+++ b/trunk/arch/avr32/kernel/asm-offsets.c
@@ -5,14 +5,7 @@
  */
 
 #include <linux/thread_info.h>
-
-#define DEFINE(sym, val) \
-        asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
-
-#define OFFSET(sym, str, mem) \
-        DEFINE(sym, offsetof(struct str, mem));
+#include <linux/kbuild.h>
 
 void foo(void)
 {
diff --git a/trunk/arch/avr32/kernel/setup.c b/trunk/arch/avr32/kernel/setup.c
index 2687b730e2d0..ce48c14f4349 100644
--- a/trunk/arch/avr32/kernel/setup.c
+++ b/trunk/arch/avr32/kernel/setup.c
@@ -274,6 +274,8 @@ static int __init early_parse_fbmem(char *p)
 			printk(KERN_WARNING
 			       "Failed to allocate framebuffer memory\n");
 			fbmem_size = 0;
+		} else {
+			memset(__va(fbmem_start), 0, fbmem_size);
 		}
 	}
 
diff --git a/trunk/arch/avr32/mm/tlb.c b/trunk/arch/avr32/mm/tlb.c
index b835257a8fa3..cd12edbea9f2 100644
--- a/trunk/arch/avr32/mm/tlb.c
+++ b/trunk/arch/avr32/mm/tlb.c
@@ -369,11 +369,7 @@ static const struct file_operations proc_tlb_operations = {
 
 static int __init proctlb_init(void)
 {
-	struct proc_dir_entry *entry;
-
-	entry = create_proc_entry("tlb", 0, NULL);
-	if (entry)
-		entry->proc_fops = &proc_tlb_operations;
+	proc_create("tlb", 0, NULL, &proc_tlb_operations);
 	return 0;
 }
 late_initcall(proctlb_init);
diff --git a/trunk/arch/blackfin/kernel/asm-offsets.c b/trunk/arch/blackfin/kernel/asm-offsets.c
index b56b2741cdea..721f15f3cebf 100644
--- a/trunk/arch/blackfin/kernel/asm-offsets.c
+++ b/trunk/arch/blackfin/kernel/asm-offsets.c
@@ -34,8 +34,7 @@
 #include <linux/hardirq.h>
 #include <linux/irq.h>
 #include <linux/thread_info.h>
-
-#define DEFINE(sym, val) asm volatile("\n->" #sym " %0 " #val : : "i" (val))
+#include <linux/kbuild.h>
 
 int main(void)
 {
diff --git a/trunk/arch/blackfin/kernel/signal.c b/trunk/arch/blackfin/kernel/signal.c
index d1fa24401dc6..cb9d883d493c 100644
--- a/trunk/arch/blackfin/kernel/signal.c
+++ b/trunk/arch/blackfin/kernel/signal.c
@@ -212,7 +212,7 @@ setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t * info,
 
 	/* Set up registers for signal handler */
 	wrusp((unsigned long)frame);
-	if (get_personality & FDPIC_FUNCPTRS) {
+	if (current->personality & FDPIC_FUNCPTRS) {
 		struct fdpic_func_descriptor __user *funcptr =
 			(struct fdpic_func_descriptor *) ka->sa.sa_handler;
 		__get_user(regs->pc, &funcptr->text);
diff --git a/trunk/arch/cris/kernel/profile.c b/trunk/arch/cris/kernel/profile.c
index aad0a9e5991a..44f7b4f79476 100644
--- a/trunk/arch/cris/kernel/profile.c
+++ b/trunk/arch/cris/kernel/profile.c
@@ -75,9 +75,9 @@ __init init_cris_profile(void)
 
 	sample_buffer_pos = sample_buffer;
 
-	entry = create_proc_entry("system_profile", S_IWUSR | S_IRUGO, NULL);
+	entry = proc_create("system_profile", S_IWUSR | S_IRUGO, NULL,
+			    &cris_proc_profile_operations);
 	if (entry) {
-		entry->proc_fops = &cris_proc_profile_operations;
 		entry->size = SAMPLE_BUFFER_SIZE;
 	}
 	prof_running = 1;
diff --git a/trunk/arch/cris/mm/init.c b/trunk/arch/cris/mm/init.c
index 4207a2b52750..5b06ffa15e34 100644
--- a/trunk/arch/cris/mm/init.c
+++ b/trunk/arch/cris/mm/init.c
@@ -27,7 +27,6 @@ show_mem(void)
 
 	printk("\nMem-info:\n");
 	show_free_areas();
-	printk("Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
 	i = max_mapnr;
 	while (i-- > 0) {
 		total++;
diff --git a/trunk/arch/frv/kernel/asm-offsets.c b/trunk/arch/frv/kernel/asm-offsets.c
index fbb19fc1af40..9de96843a278 100644
--- a/trunk/arch/frv/kernel/asm-offsets.c
+++ b/trunk/arch/frv/kernel/asm-offsets.c
@@ -7,15 +7,13 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/personality.h>
+#include <linux/kbuild.h>
 #include <asm/registers.h>
 #include <asm/ucontext.h>
 #include <asm/processor.h>
 #include <asm/thread_info.h>
 #include <asm/gdb-stub.h>
 
-#define DEFINE(sym, val) \
-        asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
 #define DEF_PTREG(sym, reg) \
         asm volatile("\n->" #sym " %0 offsetof(struct pt_regs, " #reg ")" \
 		     : : "i" (offsetof(struct pt_regs, reg)))
@@ -32,11 +30,6 @@
         asm volatile("\n->" #sym " %0 offsetof(struct frv_frame0, " #reg ")" \
 		     : : "i" (offsetof(struct frv_frame0, reg)))
 
-#define BLANK() asm volatile("\n->" : : )
-
-#define OFFSET(sym, str, mem) \
-	DEFINE(sym, offsetof(struct str, mem));
-
 void foo(void)
 {
 	/* offsets into the thread_info structure */
diff --git a/trunk/arch/frv/kernel/signal.c b/trunk/arch/frv/kernel/signal.c
index d64bcaff54cd..3bdb368292a8 100644
--- a/trunk/arch/frv/kernel/signal.c
+++ b/trunk/arch/frv/kernel/signal.c
@@ -297,7 +297,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set)
 	__frame->lr   = (unsigned long) &frame->retcode;
 	__frame->gr8  = sig;
 
-	if (get_personality & FDPIC_FUNCPTRS) {
+	if (current->personality & FDPIC_FUNCPTRS) {
 		struct fdpic_func_descriptor __user *funcptr =
 			(struct fdpic_func_descriptor __user *) ka->sa.sa_handler;
 		__get_user(__frame->pc, &funcptr->text);
@@ -396,7 +396,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	__frame->gr8 = sig;
 	__frame->gr9 = (unsigned long) &frame->info;
 
-	if (get_personality & FDPIC_FUNCPTRS) {
+	if (current->personality & FDPIC_FUNCPTRS) {
 		struct fdpic_func_descriptor __user *funcptr =
 			(struct fdpic_func_descriptor __user *) ka->sa.sa_handler;
 		__get_user(__frame->pc, &funcptr->text);
diff --git a/trunk/arch/frv/kernel/traps.c b/trunk/arch/frv/kernel/traps.c
index 7089c2428b3f..1d2dfe67d442 100644
--- a/trunk/arch/frv/kernel/traps.c
+++ b/trunk/arch/frv/kernel/traps.c
@@ -49,7 +49,7 @@ asmlinkage void insn_access_error(unsigned long esfr1, unsigned long epcr0, unsi
 	info.si_signo	= SIGSEGV;
 	info.si_code	= SEGV_ACCERR;
 	info.si_errno	= 0;
-	info.si_addr	= (void *) ((epcr0 & EPCR0_V) ? (epcr0 & EPCR0_PC) : __frame->pc);
+	info.si_addr	= (void __user *) ((epcr0 & EPCR0_V) ? (epcr0 & EPCR0_PC) : __frame->pc);
 
 	force_sig_info(info.si_signo, &info, current);
 } /* end insn_access_error() */
@@ -73,7 +73,7 @@ asmlinkage void illegal_instruction(unsigned long esfr1, unsigned long epcr0, un
 		      epcr0, esr0, esfr1);
 
 	info.si_errno	= 0;
-	info.si_addr	= (void *) ((epcr0 & EPCR0_V) ? (epcr0 & EPCR0_PC) : __frame->pc);
+	info.si_addr	= (void __user *) ((epcr0 & EPCR0_V) ? (epcr0 & EPCR0_PC) : __frame->pc);
 
 	switch (__frame->tbr & TBR_TT) {
 	case TBR_TT_ILLEGAL_INSTR:
@@ -111,7 +111,8 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
 				 unsigned long esr0)
 {
 	static DEFINE_SPINLOCK(atomic_op_lock);
-	unsigned long x, y, z, *p;
+	unsigned long x, y, z;
+	unsigned long __user *p;
 	mm_segment_t oldfs;
 	siginfo_t info;
 	int ret;
@@ -128,7 +129,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
 		 * u32 __atomic_user_cmpxchg32(u32 *ptr, u32 test, u32 new)
 		 */
 	case TBR_TT_ATOMIC_CMPXCHG32:
-		p = (unsigned long *) __frame->gr8;
+		p = (unsigned long __user *) __frame->gr8;
 		x = __frame->gr9;
 		y = __frame->gr10;
 
@@ -158,7 +159,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
 		 * u32 __atomic_kernel_xchg32(void *v, u32 new)
 		 */
 	case TBR_TT_ATOMIC_XCHG32:
-		p = (unsigned long *) __frame->gr8;
+		p = (unsigned long __user *) __frame->gr8;
 		y = __frame->gr9;
 
 		for (;;) {
@@ -181,7 +182,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
 		 * ulong __atomic_kernel_XOR_return(ulong i, ulong *v)
 		 */
 	case TBR_TT_ATOMIC_XOR:
-		p = (unsigned long *) __frame->gr8;
+		p = (unsigned long __user *) __frame->gr8;
 		x = __frame->gr9;
 
 		for (;;) {
@@ -205,7 +206,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
 		 * ulong __atomic_kernel_OR_return(ulong i, ulong *v)
 		 */
 	case TBR_TT_ATOMIC_OR:
-		p = (unsigned long *) __frame->gr8;
+		p = (unsigned long __user *) __frame->gr8;
 		x = __frame->gr9;
 
 		for (;;) {
@@ -229,7 +230,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
 		 * ulong __atomic_kernel_AND_return(ulong i, ulong *v)
 		 */
 	case TBR_TT_ATOMIC_AND:
-		p = (unsigned long *) __frame->gr8;
+		p = (unsigned long __user *) __frame->gr8;
 		x = __frame->gr9;
 
 		for (;;) {
@@ -253,7 +254,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
 		 * int __atomic_user_sub_return(atomic_t *v, int i)
 		 */
 	case TBR_TT_ATOMIC_SUB:
-		p = (unsigned long *) __frame->gr8;
+		p = (unsigned long __user *) __frame->gr8;
 		x = __frame->gr9;
 
 		for (;;) {
@@ -277,7 +278,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
 		 * int __atomic_user_add_return(atomic_t *v, int i)
 		 */
 	case TBR_TT_ATOMIC_ADD:
-		p = (unsigned long *) __frame->gr8;
+		p = (unsigned long __user *) __frame->gr8;
 		x = __frame->gr9;
 
 		for (;;) {
@@ -322,7 +323,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
 	info.si_signo	= SIGSEGV;
 	info.si_code	= SEGV_ACCERR;
 	info.si_errno	= 0;
-	info.si_addr	= (void *) __frame->pc;
+	info.si_addr	= (void __user *) __frame->pc;
 
 	force_sig_info(info.si_signo, &info, current);
 }
@@ -343,7 +344,7 @@ asmlinkage void media_exception(unsigned long msr0, unsigned long msr1)
 	info.si_signo	= SIGFPE;
 	info.si_code	= FPE_MDAOVF;
 	info.si_errno	= 0;
-	info.si_addr	= (void *) __frame->pc;
+	info.si_addr	= (void __user *) __frame->pc;
 
 	force_sig_info(info.si_signo, &info, current);
 } /* end media_exception() */
@@ -361,11 +362,8 @@ asmlinkage void memory_access_exception(unsigned long esr0,
 #ifdef CONFIG_MMU
 	unsigned long fixup;
 
-	if ((esr0 & ESRx_EC) == ESRx_EC_DATA_ACCESS)
-		if (handle_misalignment(esr0, ear0, epcr0) == 0)
-			return;
-
-	if ((fixup = search_exception_table(__frame->pc)) != 0) {
+	fixup = search_exception_table(__frame->pc);
+	if (fixup) {
 		__frame->pc = fixup;
 		return;
 	}
@@ -383,7 +381,7 @@ asmlinkage void memory_access_exception(unsigned long esr0,
 	info.si_addr	= NULL;
 
 	if ((esr0 & (ESRx_VALID | ESR0_EAV)) == (ESRx_VALID | ESR0_EAV))
-		info.si_addr = (void *) ear0;
+		info.si_addr = (void __user *) ear0;
 
 	force_sig_info(info.si_signo, &info, current);
 
@@ -412,7 +410,7 @@ asmlinkage void data_access_error(unsigned long esfr1, unsigned long esr15, unsi
 	info.si_signo	= SIGSEGV;
 	info.si_code	= SEGV_ACCERR;
 	info.si_errno	= 0;
-	info.si_addr	= (void *)
+	info.si_addr	= (void __user *)
 		(((esr15 & (ESRx_VALID|ESR15_EAV)) == (ESRx_VALID|ESR15_EAV)) ? ear15 : 0);
 
 	force_sig_info(info.si_signo, &info, current);
@@ -446,7 +444,7 @@ asmlinkage void division_exception(unsigned long esfr1, unsigned long esr0, unsi
 	info.si_signo	= SIGFPE;
 	info.si_code	= FPE_INTDIV;
 	info.si_errno	= 0;
-	info.si_addr	= (void *) __frame->pc;
+	info.si_addr	= (void __user *) __frame->pc;
 
 	force_sig_info(info.si_signo, &info, current);
 } /* end division_exception() */
diff --git a/trunk/arch/frv/mb93090-mb00/pci-iomap.c b/trunk/arch/frv/mb93090-mb00/pci-iomap.c
index 068fa04bd527..35f6df28351e 100644
--- a/trunk/arch/frv/mb93090-mb00/pci-iomap.c
+++ b/trunk/arch/frv/mb93090-mb00/pci-iomap.c
@@ -13,8 +13,8 @@
 
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
-	unsigned long start = pci_resource_start(dev, bar);
-	unsigned long len = pci_resource_len(dev, bar);
+	resource_size_t start = pci_resource_start(dev, bar);
+	resource_size_t len = pci_resource_len(dev, bar);
 	unsigned long flags = pci_resource_flags(dev, bar);
 
 	if (!len || !start)
diff --git a/trunk/arch/frv/mm/unaligned.c b/trunk/arch/frv/mm/unaligned.c
deleted file mode 100644
index 8f0375fc15a8..000000000000
--- a/trunk/arch/frv/mm/unaligned.c
+++ /dev/null
@@ -1,217 +0,0 @@
-/* unaligned.c: unalignment fixup handler for CPUs on which it is supported (FR451 only)
- *
- * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/sched.h>
-#include <linux/signal.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <linux/user.h>
-#include <linux/string.h>
-#include <linux/linkage.h>
-#include <linux/init.h>
-
-#include <asm/setup.h>
-#include <asm/system.h>
-#include <asm/uaccess.h>
-
-#if 0
-#define kdebug(fmt, ...) printk("FDPIC "fmt"\n" ,##__VA_ARGS__ )
-#else
-#define kdebug(fmt, ...) do {} while(0)
-#endif
-
-#define _MA_SIGNED	0x01
-#define _MA_HALF	0x02
-#define _MA_WORD	0x04
-#define _MA_DWORD	0x08
-#define _MA_SZ_MASK	0x0e
-#define _MA_LOAD	0x10
-#define _MA_STORE	0x20
-#define _MA_UPDATE	0x40
-#define _MA_IMM		0x80
-
-#define _MA_LDxU	_MA_LOAD | _MA_UPDATE
-#define _MA_LDxI	_MA_LOAD | _MA_IMM
-#define _MA_STxU	_MA_STORE | _MA_UPDATE
-#define _MA_STxI	_MA_STORE | _MA_IMM
-
-static const uint8_t tbl_LDGRk_reg[0x40] = {
-	[0x02] = _MA_LOAD | _MA_HALF | _MA_SIGNED,	/* LDSH  @(GRi,GRj),GRk */
-	[0x03] = _MA_LOAD | _MA_HALF,			/* LDUH  @(GRi,GRj),GRk */
-	[0x04] = _MA_LOAD | _MA_WORD,			/* LD	 @(GRi,GRj),GRk */
-	[0x05] = _MA_LOAD | _MA_DWORD,			/* LDD	 @(GRi,GRj),GRk */
-	[0x12] = _MA_LDxU | _MA_HALF | _MA_SIGNED,	/* LDSHU @(GRi,GRj),GRk */
-	[0x13] = _MA_LDxU | _MA_HALF,			/* LDUHU @(GRi,GRj),GRk */
-	[0x14] = _MA_LDxU | _MA_WORD,			/* LDU	 @(GRi,GRj),GRk */
-	[0x15] = _MA_LDxU | _MA_DWORD,			/* LDDU	 @(GRi,GRj),GRk */
-};
-
-static const uint8_t tbl_STGRk_reg[0x40] = {
-	[0x01] = _MA_STORE | _MA_HALF,			/* STH   @(GRi,GRj),GRk */
-	[0x02] = _MA_STORE | _MA_WORD,			/* ST	 @(GRi,GRj),GRk */
-	[0x03] = _MA_STORE | _MA_DWORD,			/* STD	 @(GRi,GRj),GRk */
-	[0x11] = _MA_STxU  | _MA_HALF,			/* STHU  @(GRi,GRj),GRk */
-	[0x12] = _MA_STxU  | _MA_WORD,			/* STU	 @(GRi,GRj),GRk */
-	[0x13] = _MA_STxU  | _MA_DWORD,			/* STDU	 @(GRi,GRj),GRk */
-};
-
-static const uint8_t tbl_LDSTGRk_imm[0x80] = {
-	[0x31] = _MA_LDxI | _MA_HALF | _MA_SIGNED,	/* LDSHI @(GRi,d12),GRk */
-	[0x32] = _MA_LDxI | _MA_WORD,			/* LDI   @(GRi,d12),GRk */
-	[0x33] = _MA_LDxI | _MA_DWORD,			/* LDDI  @(GRi,d12),GRk */
-	[0x36] = _MA_LDxI | _MA_HALF,			/* LDUHI @(GRi,d12),GRk */
-	[0x51] = _MA_STxI | _MA_HALF,			/* STHI  @(GRi,d12),GRk */
-	[0x52] = _MA_STxI | _MA_WORD,			/* STI   @(GRi,d12),GRk */
-	[0x53] = _MA_STxI | _MA_DWORD,			/* STDI  @(GRi,d12),GRk */
-};
-
-
-/*****************************************************************************/
-/*
- * see if we can handle the exception by fixing up a misaligned memory access
- */
-int handle_misalignment(unsigned long esr0, unsigned long ear0, unsigned long epcr0)
-{
-	unsigned long insn, addr, *greg;
-	int GRi, GRj, GRk, D12, op;
-
-	union {
-		uint64_t _64;
-		uint32_t _32[2];
-		uint16_t _16;
-		uint8_t _8[8];
-	} x;
-
-	if (!(esr0 & ESR0_EAV) || !(epcr0 & EPCR0_V) || !(ear0 & 7))
-		return -EAGAIN;
-
-	epcr0 &= EPCR0_PC;
-
-	if (__frame->pc != epcr0) {
-		kdebug("MISALIGN: Execution not halted on excepting instruction\n");
-		BUG();
-	}
-
-	if (__get_user(insn, (unsigned long *) epcr0) < 0)
-		return -EFAULT;
-
-	/* determine the instruction type first */
-	switch ((insn >> 18) & 0x7f) {
-	case 0x2:
-		/* LDx @(GRi,GRj),GRk */
-		op = tbl_LDGRk_reg[(insn >> 6) & 0x3f];
-		break;
-
-	case 0x3:
-		/* STx GRk,@(GRi,GRj) */
-		op = tbl_STGRk_reg[(insn >> 6) & 0x3f];
-		break;
-
-	default:
-		op = tbl_LDSTGRk_imm[(insn >> 18) & 0x7f];
-		break;
-	}
-
-	if (!op)
-		return -EAGAIN;
-
-	kdebug("MISALIGN: pc=%08lx insn=%08lx ad=%08lx op=%02x\n", epcr0, insn, ear0, op);
-
-	memset(&x, 0xba, 8);
-
-	/* validate the instruction parameters */
-	greg = (unsigned long *) &__frame->tbr;
-
-	GRi = (insn >> 12) & 0x3f;
-	GRk = (insn >> 25) & 0x3f;
-
-	if (GRi > 31 || GRk > 31)
-		return -ENOENT;
-
-	if (op & _MA_DWORD && GRk & 1)
-		return -EINVAL;
-
-	if (op & _MA_IMM) {
-		D12 = insn & 0xfff;
-		asm ("slli %0,#20,%0 ! srai %0,#20,%0" : "=r"(D12) : "0"(D12)); /* sign extend */
-		addr = (GRi ? greg[GRi] : 0) + D12;
-	}
-	else {
-		GRj = (insn >>  0) & 0x3f;
-		if (GRj > 31)
-			return -ENOENT;
-		addr = (GRi ? greg[GRi] : 0) + (GRj ? greg[GRj] : 0);
-	}
-
-	if (addr != ear0) {
-		kdebug("MISALIGN: Calculated addr (%08lx) does not match EAR0 (%08lx)\n",
-		       addr, ear0);
-		return -EFAULT;
-	}
-
-	/* check the address is okay */
-	if (user_mode(__frame) && ___range_ok(ear0, 8) < 0)
-		return -EFAULT;
-
-	/* perform the memory op */
-	if (op & _MA_STORE) {
-		/* perform a store */
-		x._32[0] = 0;
-		if (GRk != 0) {
-			if (op & _MA_HALF) {
-				x._16 = greg[GRk];
-			}
-			else {
-				x._32[0] = greg[GRk];
-			}
-		}
-		if (op & _MA_DWORD)
-			x._32[1] = greg[GRk + 1];
-
-		kdebug("MISALIGN: Store GR%d { %08x:%08x } -> %08lx (%dB)\n",
-		       GRk, x._32[1], x._32[0], addr, op & _MA_SZ_MASK);
-
-		if (__memcpy_user((void *) addr, &x, op & _MA_SZ_MASK) != 0)
-			return -EFAULT;
-	}
-	else {
-		/* perform a load */
-		if (__memcpy_user(&x, (void *) addr, op & _MA_SZ_MASK) != 0)
-			return -EFAULT;
-
-		if (op & _MA_HALF) {
-			if (op & _MA_SIGNED)
-				asm ("slli %0,#16,%0 ! srai %0,#16,%0"
-				     : "=r"(x._32[0]) : "0"(x._16));
-			else
-				asm ("sethi #0,%0"
-				     : "=r"(x._32[0]) : "0"(x._16));
-		}
-
-		kdebug("MISALIGN: Load %08lx (%dB) -> GR%d, { %08x:%08x }\n",
-		       addr, op & _MA_SZ_MASK, GRk, x._32[1], x._32[0]);
-
-		if (GRk != 0)
-			greg[GRk] = x._32[0];
-		if (op & _MA_DWORD)
-			greg[GRk + 1] = x._32[1];
-	}
-
-	/* update the base pointer if required */
-	if (op & _MA_UPDATE)
-		greg[GRi] = addr;
-
-	/* well... we've done that insn */
-	__frame->pc = __frame->pc + 4;
-
-	return 0;
-} /* end handle_misalignment() */
diff --git a/trunk/arch/h8300/kernel/asm-offsets.c b/trunk/arch/h8300/kernel/asm-offsets.c
index fc30b4fd0914..2042552e0871 100644
--- a/trunk/arch/h8300/kernel/asm-offsets.c
+++ b/trunk/arch/h8300/kernel/asm-offsets.c
@@ -13,15 +13,11 @@
 #include <linux/kernel_stat.h>
 #include <linux/ptrace.h>
 #include <linux/hardirq.h>
+#include <linux/kbuild.h>
 #include <asm/bootinfo.h>
 #include <asm/irq.h>
 #include <asm/ptrace.h>
 
-#define DEFINE(sym, val) \
-        asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
-
 int main(void)
 {
 	/* offsets into the task struct */
diff --git a/trunk/arch/ia64/Kconfig b/trunk/arch/ia64/Kconfig
index cd13e138bd03..0df5f6f75edf 100644
--- a/trunk/arch/ia64/Kconfig
+++ b/trunk/arch/ia64/Kconfig
@@ -19,6 +19,8 @@ config IA64
 	select HAVE_OPROFILE
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
+	select HAVE_DMA_ATTRS
+	select HAVE_KVM
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to
@@ -46,6 +48,9 @@ config MMU
 config SWIOTLB
        bool
 
+config IOMMU_HELPER
+       bool
+
 config GENERIC_LOCKBREAK
 	bool
 	default y
@@ -589,6 +594,8 @@ config MSPEC
 
 source "fs/Kconfig"
 
+source "arch/ia64/kvm/Kconfig"
+
 source "lib/Kconfig"
 
 #
@@ -612,7 +619,7 @@ config IRQ_PER_CPU
 	default y
 
 config IOMMU_HELPER
-	def_bool (IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB || IA64_GENERIC)
+	def_bool (IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB || IA64_GENERIC || SWIOTLB)
 
 source "arch/ia64/hp/sim/Kconfig"
 
diff --git a/trunk/arch/ia64/Makefile b/trunk/arch/ia64/Makefile
index f1645c4f7039..ec4cca477f49 100644
--- a/trunk/arch/ia64/Makefile
+++ b/trunk/arch/ia64/Makefile
@@ -57,6 +57,7 @@ core-$(CONFIG_IA64_GENERIC) 	+= arch/ia64/dig/
 core-$(CONFIG_IA64_HP_ZX1)	+= arch/ia64/dig/
 core-$(CONFIG_IA64_HP_ZX1_SWIOTLB) += arch/ia64/dig/
 core-$(CONFIG_IA64_SGI_SN2)	+= arch/ia64/sn/
+core-$(CONFIG_KVM) 		+= arch/ia64/kvm/
 
 drivers-$(CONFIG_PCI)		+= arch/ia64/pci/
 drivers-$(CONFIG_IA64_HP_SIM)	+= arch/ia64/hp/sim/
diff --git a/trunk/arch/ia64/hp/common/hwsw_iommu.c b/trunk/arch/ia64/hp/common/hwsw_iommu.c
index 8f6bcfe1dada..1c44ec2a1d58 100644
--- a/trunk/arch/ia64/hp/common/hwsw_iommu.c
+++ b/trunk/arch/ia64/hp/common/hwsw_iommu.c
@@ -20,10 +20,10 @@
 extern int swiotlb_late_init_with_default_size (size_t size);
 extern ia64_mv_dma_alloc_coherent	swiotlb_alloc_coherent;
 extern ia64_mv_dma_free_coherent	swiotlb_free_coherent;
-extern ia64_mv_dma_map_single		swiotlb_map_single;
-extern ia64_mv_dma_unmap_single		swiotlb_unmap_single;
-extern ia64_mv_dma_map_sg		swiotlb_map_sg;
-extern ia64_mv_dma_unmap_sg		swiotlb_unmap_sg;
+extern ia64_mv_dma_map_single_attrs	swiotlb_map_single_attrs;
+extern ia64_mv_dma_unmap_single_attrs	swiotlb_unmap_single_attrs;
+extern ia64_mv_dma_map_sg_attrs		swiotlb_map_sg_attrs;
+extern ia64_mv_dma_unmap_sg_attrs	swiotlb_unmap_sg_attrs;
 extern ia64_mv_dma_supported		swiotlb_dma_supported;
 extern ia64_mv_dma_mapping_error	swiotlb_dma_mapping_error;
 
@@ -31,19 +31,19 @@ extern ia64_mv_dma_mapping_error	swiotlb_dma_mapping_error;
 
 extern ia64_mv_dma_alloc_coherent	sba_alloc_coherent;
 extern ia64_mv_dma_free_coherent	sba_free_coherent;
-extern ia64_mv_dma_map_single		sba_map_single;
-extern ia64_mv_dma_unmap_single		sba_unmap_single;
-extern ia64_mv_dma_map_sg		sba_map_sg;
-extern ia64_mv_dma_unmap_sg		sba_unmap_sg;
+extern ia64_mv_dma_map_single_attrs	sba_map_single_attrs;
+extern ia64_mv_dma_unmap_single_attrs	sba_unmap_single_attrs;
+extern ia64_mv_dma_map_sg_attrs		sba_map_sg_attrs;
+extern ia64_mv_dma_unmap_sg_attrs	sba_unmap_sg_attrs;
 extern ia64_mv_dma_supported		sba_dma_supported;
 extern ia64_mv_dma_mapping_error	sba_dma_mapping_error;
 
 #define hwiommu_alloc_coherent		sba_alloc_coherent
 #define hwiommu_free_coherent		sba_free_coherent
-#define hwiommu_map_single		sba_map_single
-#define hwiommu_unmap_single		sba_unmap_single
-#define hwiommu_map_sg			sba_map_sg
-#define hwiommu_unmap_sg		sba_unmap_sg
+#define hwiommu_map_single_attrs	sba_map_single_attrs
+#define hwiommu_unmap_single_attrs	sba_unmap_single_attrs
+#define hwiommu_map_sg_attrs		sba_map_sg_attrs
+#define hwiommu_unmap_sg_attrs		sba_unmap_sg_attrs
 #define hwiommu_dma_supported		sba_dma_supported
 #define hwiommu_dma_mapping_error	sba_dma_mapping_error
 #define hwiommu_sync_single_for_cpu	machvec_dma_sync_single
@@ -98,41 +98,48 @@ hwsw_free_coherent (struct device *dev, size_t size, void *vaddr, dma_addr_t dma
 }
 
 dma_addr_t
-hwsw_map_single (struct device *dev, void *addr, size_t size, int dir)
+hwsw_map_single_attrs(struct device *dev, void *addr, size_t size, int dir,
+		       struct dma_attrs *attrs)
 {
 	if (use_swiotlb(dev))
-		return swiotlb_map_single(dev, addr, size, dir);
+		return swiotlb_map_single_attrs(dev, addr, size, dir, attrs);
 	else
-		return hwiommu_map_single(dev, addr, size, dir);
+		return hwiommu_map_single_attrs(dev, addr, size, dir, attrs);
 }
+EXPORT_SYMBOL(hwsw_map_single_attrs);
 
 void
-hwsw_unmap_single (struct device *dev, dma_addr_t iova, size_t size, int dir)
+hwsw_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size,
+			 int dir, struct dma_attrs *attrs)
 {
 	if (use_swiotlb(dev))
-		return swiotlb_unmap_single(dev, iova, size, dir);
+		return swiotlb_unmap_single_attrs(dev, iova, size, dir, attrs);
 	else
-		return hwiommu_unmap_single(dev, iova, size, dir);
+		return hwiommu_unmap_single_attrs(dev, iova, size, dir, attrs);
 }
-
+EXPORT_SYMBOL(hwsw_unmap_single_attrs);
 
 int
-hwsw_map_sg (struct device *dev, struct scatterlist *sglist, int nents, int dir)
+hwsw_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents,
+		   int dir, struct dma_attrs *attrs)
 {
 	if (use_swiotlb(dev))
-		return swiotlb_map_sg(dev, sglist, nents, dir);
+		return swiotlb_map_sg_attrs(dev, sglist, nents, dir, attrs);
 	else
-		return hwiommu_map_sg(dev, sglist, nents, dir);
+		return hwiommu_map_sg_attrs(dev, sglist, nents, dir, attrs);
 }
+EXPORT_SYMBOL(hwsw_map_sg_attrs);
 
 void
-hwsw_unmap_sg (struct device *dev, struct scatterlist *sglist, int nents, int dir)
+hwsw_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents,
+		     int dir, struct dma_attrs *attrs)
 {
 	if (use_swiotlb(dev))
-		return swiotlb_unmap_sg(dev, sglist, nents, dir);
+		return swiotlb_unmap_sg_attrs(dev, sglist, nents, dir, attrs);
 	else
-		return hwiommu_unmap_sg(dev, sglist, nents, dir);
+		return hwiommu_unmap_sg_attrs(dev, sglist, nents, dir, attrs);
 }
+EXPORT_SYMBOL(hwsw_unmap_sg_attrs);
 
 void
 hwsw_sync_single_for_cpu (struct device *dev, dma_addr_t addr, size_t size, int dir)
@@ -185,10 +192,6 @@ hwsw_dma_mapping_error (dma_addr_t dma_addr)
 }
 
 EXPORT_SYMBOL(hwsw_dma_mapping_error);
-EXPORT_SYMBOL(hwsw_map_single);
-EXPORT_SYMBOL(hwsw_unmap_single);
-EXPORT_SYMBOL(hwsw_map_sg);
-EXPORT_SYMBOL(hwsw_unmap_sg);
 EXPORT_SYMBOL(hwsw_dma_supported);
 EXPORT_SYMBOL(hwsw_alloc_coherent);
 EXPORT_SYMBOL(hwsw_free_coherent);
diff --git a/trunk/arch/ia64/hp/common/sba_iommu.c b/trunk/arch/ia64/hp/common/sba_iommu.c
index 9409de5c9441..34421aed1e2a 100644
--- a/trunk/arch/ia64/hp/common/sba_iommu.c
+++ b/trunk/arch/ia64/hp/common/sba_iommu.c
@@ -899,16 +899,18 @@ sba_mark_invalid(struct ioc *ioc, dma_addr_t iova, size_t byte_cnt)
 }
 
 /**
- * sba_map_single - map one buffer and return IOVA for DMA
+ * sba_map_single_attrs - map one buffer and return IOVA for DMA
  * @dev: instance of PCI owned by the driver that's asking.
  * @addr:  driver buffer to map.
  * @size:  number of bytes to map in driver buffer.
  * @dir:  R/W or both.
+ * @attrs: optional dma attributes
  *
  * See Documentation/DMA-mapping.txt
  */
 dma_addr_t
-sba_map_single(struct device *dev, void *addr, size_t size, int dir)
+sba_map_single_attrs(struct device *dev, void *addr, size_t size, int dir,
+		     struct dma_attrs *attrs)
 {
 	struct ioc *ioc;
 	dma_addr_t iovp;
@@ -932,7 +934,8 @@ sba_map_single(struct device *dev, void *addr, size_t size, int dir)
  		** Device is bit capable of DMA'ing to the buffer...
 		** just return the PCI address of ptr
  		*/
-		DBG_BYPASS("sba_map_single() bypass mask/addr: 0x%lx/0x%lx\n",
+		DBG_BYPASS("sba_map_single_attrs() bypass mask/addr: "
+			   "0x%lx/0x%lx\n",
 		           to_pci_dev(dev)->dma_mask, pci_addr);
 		return pci_addr;
 	}
@@ -953,7 +956,7 @@ sba_map_single(struct device *dev, void *addr, size_t size, int dir)
 
 #ifdef ASSERT_PDIR_SANITY
 	spin_lock_irqsave(&ioc->res_lock, flags);
-	if (sba_check_pdir(ioc,"Check before sba_map_single()"))
+	if (sba_check_pdir(ioc,"Check before sba_map_single_attrs()"))
 		panic("Sanity check failed");
 	spin_unlock_irqrestore(&ioc->res_lock, flags);
 #endif
@@ -982,11 +985,12 @@ sba_map_single(struct device *dev, void *addr, size_t size, int dir)
 	/* form complete address */
 #ifdef ASSERT_PDIR_SANITY
 	spin_lock_irqsave(&ioc->res_lock, flags);
-	sba_check_pdir(ioc,"Check after sba_map_single()");
+	sba_check_pdir(ioc,"Check after sba_map_single_attrs()");
 	spin_unlock_irqrestore(&ioc->res_lock, flags);
 #endif
 	return SBA_IOVA(ioc, iovp, offset);
 }
+EXPORT_SYMBOL(sba_map_single_attrs);
 
 #ifdef ENABLE_MARK_CLEAN
 static SBA_INLINE void
@@ -1013,15 +1017,17 @@ sba_mark_clean(struct ioc *ioc, dma_addr_t iova, size_t size)
 #endif
 
 /**
- * sba_unmap_single - unmap one IOVA and free resources
+ * sba_unmap_single_attrs - unmap one IOVA and free resources
  * @dev: instance of PCI owned by the driver that's asking.
  * @iova:  IOVA of driver buffer previously mapped.
  * @size:  number of bytes mapped in driver buffer.
  * @dir:  R/W or both.
+ * @attrs: optional dma attributes
  *
  * See Documentation/DMA-mapping.txt
  */
-void sba_unmap_single(struct device *dev, dma_addr_t iova, size_t size, int dir)
+void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size,
+			    int dir, struct dma_attrs *attrs)
 {
 	struct ioc *ioc;
 #if DELAYED_RESOURCE_CNT > 0
@@ -1038,7 +1044,8 @@ void sba_unmap_single(struct device *dev, dma_addr_t iova, size_t size, int dir)
 		/*
 		** Address does not fall w/in IOVA, must be bypassing
 		*/
-		DBG_BYPASS("sba_unmap_single() bypass addr: 0x%lx\n", iova);
+		DBG_BYPASS("sba_unmap_single_atttrs() bypass addr: 0x%lx\n",
+			   iova);
 
 #ifdef ENABLE_MARK_CLEAN
 		if (dir == DMA_FROM_DEVICE) {
@@ -1087,7 +1094,7 @@ void sba_unmap_single(struct device *dev, dma_addr_t iova, size_t size, int dir)
 	spin_unlock_irqrestore(&ioc->res_lock, flags);
 #endif /* DELAYED_RESOURCE_CNT == 0 */
 }
-
+EXPORT_SYMBOL(sba_unmap_single_attrs);
 
 /**
  * sba_alloc_coherent - allocate/map shared mem for DMA
@@ -1144,7 +1151,8 @@ sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp
 	 * If device can't bypass or bypass is disabled, pass the 32bit fake
 	 * device to map single to get an iova mapping.
 	 */
-	*dma_handle = sba_map_single(&ioc->sac_only_dev->dev, addr, size, 0);
+	*dma_handle = sba_map_single_attrs(&ioc->sac_only_dev->dev, addr,
+					   size, 0, NULL);
 
 	return addr;
 }
@@ -1161,7 +1169,7 @@ sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp
  */
 void sba_free_coherent (struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle)
 {
-	sba_unmap_single(dev, dma_handle, size, 0);
+	sba_unmap_single_attrs(dev, dma_handle, size, 0, NULL);
 	free_pages((unsigned long) vaddr, get_order(size));
 }
 
@@ -1410,10 +1418,12 @@ sba_coalesce_chunks(struct ioc *ioc, struct device *dev,
  * @sglist:  array of buffer/length pairs
  * @nents:  number of entries in list
  * @dir:  R/W or both.
+ * @attrs: optional dma attributes
  *
  * See Documentation/DMA-mapping.txt
  */
-int sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents, int dir)
+int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents,
+		     int dir, struct dma_attrs *attrs)
 {
 	struct ioc *ioc;
 	int coalesced, filled = 0;
@@ -1441,16 +1451,16 @@ int sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents, int di
 	/* Fast path single entry scatterlists. */
 	if (nents == 1) {
 		sglist->dma_length = sglist->length;
-		sglist->dma_address = sba_map_single(dev, sba_sg_address(sglist), sglist->length, dir);
+		sglist->dma_address = sba_map_single_attrs(dev, sba_sg_address(sglist), sglist->length, dir, attrs);
 		return 1;
 	}
 
 #ifdef ASSERT_PDIR_SANITY
 	spin_lock_irqsave(&ioc->res_lock, flags);
-	if (sba_check_pdir(ioc,"Check before sba_map_sg()"))
+	if (sba_check_pdir(ioc,"Check before sba_map_sg_attrs()"))
 	{
 		sba_dump_sg(ioc, sglist, nents);
-		panic("Check before sba_map_sg()");
+		panic("Check before sba_map_sg_attrs()");
 	}
 	spin_unlock_irqrestore(&ioc->res_lock, flags);
 #endif
@@ -1479,10 +1489,10 @@ int sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents, int di
 
 #ifdef ASSERT_PDIR_SANITY
 	spin_lock_irqsave(&ioc->res_lock, flags);
-	if (sba_check_pdir(ioc,"Check after sba_map_sg()"))
+	if (sba_check_pdir(ioc,"Check after sba_map_sg_attrs()"))
 	{
 		sba_dump_sg(ioc, sglist, nents);
-		panic("Check after sba_map_sg()\n");
+		panic("Check after sba_map_sg_attrs()\n");
 	}
 	spin_unlock_irqrestore(&ioc->res_lock, flags);
 #endif
@@ -1492,18 +1502,20 @@ int sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents, int di
 
 	return filled;
 }
-
+EXPORT_SYMBOL(sba_map_sg_attrs);
 
 /**
- * sba_unmap_sg - unmap Scatter/Gather list
+ * sba_unmap_sg_attrs - unmap Scatter/Gather list
  * @dev: instance of PCI owned by the driver that's asking.
  * @sglist:  array of buffer/length pairs
  * @nents:  number of entries in list
  * @dir:  R/W or both.
+ * @attrs: optional dma attributes
  *
  * See Documentation/DMA-mapping.txt
  */
-void sba_unmap_sg (struct device *dev, struct scatterlist *sglist, int nents, int dir)
+void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist,
+			int nents, int dir, struct dma_attrs *attrs)
 {
 #ifdef ASSERT_PDIR_SANITY
 	struct ioc *ioc;
@@ -1518,13 +1530,14 @@ void sba_unmap_sg (struct device *dev, struct scatterlist *sglist, int nents, in
 	ASSERT(ioc);
 
 	spin_lock_irqsave(&ioc->res_lock, flags);
-	sba_check_pdir(ioc,"Check before sba_unmap_sg()");
+	sba_check_pdir(ioc,"Check before sba_unmap_sg_attrs()");
 	spin_unlock_irqrestore(&ioc->res_lock, flags);
 #endif
 
 	while (nents && sglist->dma_length) {
 
-		sba_unmap_single(dev, sglist->dma_address, sglist->dma_length, dir);
+		sba_unmap_single_attrs(dev, sglist->dma_address,
+				       sglist->dma_length, dir, attrs);
 		sglist = sg_next(sglist);
 		nents--;
 	}
@@ -1533,11 +1546,12 @@ void sba_unmap_sg (struct device *dev, struct scatterlist *sglist, int nents, in
 
 #ifdef ASSERT_PDIR_SANITY
 	spin_lock_irqsave(&ioc->res_lock, flags);
-	sba_check_pdir(ioc,"Check after sba_unmap_sg()");
+	sba_check_pdir(ioc,"Check after sba_unmap_sg_attrs()");
 	spin_unlock_irqrestore(&ioc->res_lock, flags);
 #endif
 
 }
+EXPORT_SYMBOL(sba_unmap_sg_attrs);
 
 /**************************************************************
 *
@@ -1918,15 +1932,13 @@ static const struct file_operations ioc_fops = {
 static void __init
 ioc_proc_init(void)
 {
-	struct proc_dir_entry *dir, *entry;
+	struct proc_dir_entry *dir;
 
 	dir = proc_mkdir("bus/mckinley", NULL);
 	if (!dir)
 		return;
 
-	entry = create_proc_entry(ioc_list->name, 0, dir);
-	if (entry)
-		entry->proc_fops = &ioc_fops;
+	proc_create(ioc_list->name, 0, dir, &ioc_fops);
 }
 #endif
 
@@ -2166,10 +2178,6 @@ sba_page_override(char *str)
 __setup("sbapagesize=",sba_page_override);
 
 EXPORT_SYMBOL(sba_dma_mapping_error);
-EXPORT_SYMBOL(sba_map_single);
-EXPORT_SYMBOL(sba_unmap_single);
-EXPORT_SYMBOL(sba_map_sg);
-EXPORT_SYMBOL(sba_unmap_sg);
 EXPORT_SYMBOL(sba_dma_supported);
 EXPORT_SYMBOL(sba_alloc_coherent);
 EXPORT_SYMBOL(sba_free_coherent);
diff --git a/trunk/arch/ia64/kernel/asm-offsets.c b/trunk/arch/ia64/kernel/asm-offsets.c
index 230a6f92367f..c64a55af9b95 100644
--- a/trunk/arch/ia64/kernel/asm-offsets.c
+++ b/trunk/arch/ia64/kernel/asm-offsets.c
@@ -9,7 +9,7 @@
 #include <linux/sched.h>
 #include <linux/pid.h>
 #include <linux/clocksource.h>
-
+#include <linux/kbuild.h>
 #include <asm-ia64/processor.h>
 #include <asm-ia64/ptrace.h>
 #include <asm-ia64/siginfo.h>
@@ -19,11 +19,6 @@
 #include "../kernel/sigframe.h"
 #include "../kernel/fsyscall_gtod_data.h"
 
-#define DEFINE(sym, val) \
-        asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
-
 void foo(void)
 {
 	DEFINE(IA64_TASK_SIZE, sizeof (struct task_struct));
diff --git a/trunk/arch/ia64/kernel/perfmon.c b/trunk/arch/ia64/kernel/perfmon.c
index c8e403752a0c..7fbb51e10bbe 100644
--- a/trunk/arch/ia64/kernel/perfmon.c
+++ b/trunk/arch/ia64/kernel/perfmon.c
@@ -6695,16 +6695,12 @@ pfm_init(void)
 	/*
 	 * create /proc/perfmon (mostly for debugging purposes)
 	 */
- 	perfmon_dir = create_proc_entry("perfmon", S_IRUGO, NULL);
+	perfmon_dir = proc_create("perfmon", S_IRUGO, NULL, &pfm_proc_fops);
 	if (perfmon_dir == NULL) {
 		printk(KERN_ERR "perfmon: cannot create /proc entry, perfmon disabled\n");
 		pmu_conf = NULL;
 		return -1;
 	}
-  	/*
- 	 * install customized file operations for /proc/perfmon entry
- 	 */
- 	perfmon_dir->proc_fops = &pfm_proc_fops;
 
 	/*
 	 * create /proc/sys/kernel/perfmon (for debugging purposes)
diff --git a/trunk/arch/ia64/kernel/salinfo.c b/trunk/arch/ia64/kernel/salinfo.c
index b11bb50a197a..ecb9eb78d687 100644
--- a/trunk/arch/ia64/kernel/salinfo.c
+++ b/trunk/arch/ia64/kernel/salinfo.c
@@ -648,18 +648,16 @@ salinfo_init(void)
 		if (!dir)
 			continue;
 
-		entry = create_proc_entry("event", S_IRUSR, dir);
+		entry = proc_create_data("event", S_IRUSR, dir,
+					 &salinfo_event_fops, data);
 		if (!entry)
 			continue;
-		entry->data = data;
-		entry->proc_fops = &salinfo_event_fops;
 		*sdir++ = entry;
 
-		entry = create_proc_entry("data", S_IRUSR | S_IWUSR, dir);
+		entry = proc_create_data("data", S_IRUSR | S_IWUSR, dir,
+					 &salinfo_data_fops, data);
 		if (!entry)
 			continue;
-		entry->data = data;
-		entry->proc_fops = &salinfo_data_fops;
 		*sdir++ = entry;
 
 		/* we missed any events before now */
diff --git a/trunk/arch/ia64/kvm/Kconfig b/trunk/arch/ia64/kvm/Kconfig
new file mode 100644
index 000000000000..7914e4828504
--- /dev/null
+++ b/trunk/arch/ia64/kvm/Kconfig
@@ -0,0 +1,49 @@
+#
+# KVM configuration
+#
+config HAVE_KVM
+	bool
+
+menuconfig VIRTUALIZATION
+	bool "Virtualization"
+	depends on HAVE_KVM || IA64
+	default y
+	---help---
+	  Say Y here to get to see options for using your Linux host to run other
+	  operating systems inside virtual machines (guests).
+	  This option alone does not add any kernel code.
+
+	  If you say N, all options in this submenu will be skipped and disabled.
+
+if VIRTUALIZATION
+
+config KVM
+	tristate "Kernel-based Virtual Machine (KVM) support"
+	depends on HAVE_KVM && EXPERIMENTAL
+	select PREEMPT_NOTIFIERS
+	select ANON_INODES
+	---help---
+	  Support hosting fully virtualized guest machines using hardware
+	  virtualization extensions.  You will need a fairly recent
+	  processor equipped with virtualization extensions. You will also
+	  need to select one or more of the processor modules below.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  To compile this as a module, choose M here: the module
+	  will be called kvm.
+
+	  If unsure, say N.
+
+config KVM_INTEL
+	tristate "KVM for Intel Itanium 2 processors support"
+	depends on KVM && m
+	---help---
+	  Provides support for KVM on Itanium 2 processors equipped with the VT
+	  extensions.
+
+config KVM_TRACE
+       bool
+
+endif # VIRTUALIZATION
diff --git a/trunk/arch/ia64/kvm/Makefile b/trunk/arch/ia64/kvm/Makefile
new file mode 100644
index 000000000000..52353397a1a4
--- /dev/null
+++ b/trunk/arch/ia64/kvm/Makefile
@@ -0,0 +1,58 @@
+#This Make file is to generate asm-offsets.h and build source.
+#
+
+#Generate asm-offsets.h for vmm module build
+offsets-file := asm-offsets.h
+
+always  := $(offsets-file)
+targets := $(offsets-file)
+targets += arch/ia64/kvm/asm-offsets.s
+clean-files := $(addprefix $(objtree)/,$(targets) $(obj)/memcpy.S $(obj)/memset.S)
+
+# Default sed regexp - multiline due to syntax constraints
+define sed-y
+	"/^->/{s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; s:->::; p;}"
+endef
+
+quiet_cmd_offsets = GEN     $@
+define cmd_offsets
+	(set -e; \
+	 echo "#ifndef __ASM_KVM_OFFSETS_H__"; \
+	 echo "#define __ASM_KVM_OFFSETS_H__"; \
+	 echo "/*"; \
+	 echo " * DO NOT MODIFY."; \
+	 echo " *"; \
+	 echo " * This file was generated by Makefile"; \
+	 echo " *"; \
+	 echo " */"; \
+	 echo ""; \
+	 sed -ne $(sed-y) $<; \
+	 echo ""; \
+	 echo "#endif" ) > $@
+endef
+# We use internal rules to avoid the "is up to date" message from make
+arch/ia64/kvm/asm-offsets.s: arch/ia64/kvm/asm-offsets.c
+	$(call if_changed_dep,cc_s_c)
+
+$(obj)/$(offsets-file): arch/ia64/kvm/asm-offsets.s
+	$(call cmd,offsets)
+
+#
+# Makefile for Kernel-based Virtual Machine module
+#
+
+EXTRA_CFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/
+EXTRA_AFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/
+
+common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o)
+
+kvm-objs := $(common-objs) kvm-ia64.o kvm_fw.o
+obj-$(CONFIG_KVM) += kvm.o
+
+FORCE : $(obj)/$(offsets-file)
+EXTRA_CFLAGS_vcpu.o += -mfixed-range=f2-f5,f12-f127
+kvm-intel-objs = vmm.o vmm_ivt.o trampoline.o vcpu.o optvfault.o mmio.o \
+	vtlb.o process.o
+#Add link memcpy and memset to avoid possible structure assignment error
+kvm-intel-objs += ../lib/memset.o ../lib/memcpy.o
+obj-$(CONFIG_KVM_INTEL) += kvm-intel.o
diff --git a/trunk/arch/ia64/kvm/asm-offsets.c b/trunk/arch/ia64/kvm/asm-offsets.c
new file mode 100644
index 000000000000..4e3dc13a619c
--- /dev/null
+++ b/trunk/arch/ia64/kvm/asm-offsets.c
@@ -0,0 +1,251 @@
+/*
+ * asm-offsets.c Generate definitions needed by assembly language modules.
+ * This code generates raw asm output which is post-processed
+ * to extract and format the required data.
+ *
+ * Anthony Xu    <anthony.xu@intel.com>
+ * Xiantao Zhang <xiantao.zhang@intel.com>
+ * Copyright (c) 2007 Intel Corporation  KVM support.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+
+#include <linux/autoconf.h>
+#include <linux/kvm_host.h>
+
+#include "vcpu.h"
+
+#define task_struct kvm_vcpu
+
+#define DEFINE(sym, val) \
+	asm volatile("\n->" #sym " (%0) " #val : : "i" (val))
+
+#define BLANK() asm volatile("\n->" : :)
+
+#define OFFSET(_sym, _str, _mem) \
+    DEFINE(_sym, offsetof(_str, _mem));
+
+void foo(void)
+{
+	DEFINE(VMM_TASK_SIZE, sizeof(struct kvm_vcpu));
+	DEFINE(VMM_PT_REGS_SIZE, sizeof(struct kvm_pt_regs));
+
+	BLANK();
+
+	DEFINE(VMM_VCPU_META_RR0_OFFSET,
+			offsetof(struct kvm_vcpu, arch.metaphysical_rr0));
+	DEFINE(VMM_VCPU_META_SAVED_RR0_OFFSET,
+			offsetof(struct kvm_vcpu,
+				arch.metaphysical_saved_rr0));
+	DEFINE(VMM_VCPU_VRR0_OFFSET,
+			offsetof(struct kvm_vcpu, arch.vrr[0]));
+	DEFINE(VMM_VPD_IRR0_OFFSET,
+			offsetof(struct vpd, irr[0]));
+	DEFINE(VMM_VCPU_ITC_CHECK_OFFSET,
+			offsetof(struct kvm_vcpu, arch.itc_check));
+	DEFINE(VMM_VCPU_IRQ_CHECK_OFFSET,
+			offsetof(struct kvm_vcpu, arch.irq_check));
+	DEFINE(VMM_VPD_VHPI_OFFSET,
+			offsetof(struct vpd, vhpi));
+	DEFINE(VMM_VCPU_VSA_BASE_OFFSET,
+			offsetof(struct kvm_vcpu, arch.vsa_base));
+	DEFINE(VMM_VCPU_VPD_OFFSET,
+			offsetof(struct kvm_vcpu, arch.vpd));
+	DEFINE(VMM_VCPU_IRQ_CHECK,
+			offsetof(struct kvm_vcpu, arch.irq_check));
+	DEFINE(VMM_VCPU_TIMER_PENDING,
+			offsetof(struct kvm_vcpu, arch.timer_pending));
+	DEFINE(VMM_VCPU_META_SAVED_RR0_OFFSET,
+			offsetof(struct kvm_vcpu, arch.metaphysical_saved_rr0));
+	DEFINE(VMM_VCPU_MODE_FLAGS_OFFSET,
+			offsetof(struct kvm_vcpu, arch.mode_flags));
+	DEFINE(VMM_VCPU_ITC_OFS_OFFSET,
+			offsetof(struct kvm_vcpu, arch.itc_offset));
+	DEFINE(VMM_VCPU_LAST_ITC_OFFSET,
+			offsetof(struct kvm_vcpu, arch.last_itc));
+	DEFINE(VMM_VCPU_SAVED_GP_OFFSET,
+			offsetof(struct kvm_vcpu, arch.saved_gp));
+
+	BLANK();
+
+	DEFINE(VMM_PT_REGS_B6_OFFSET,
+				offsetof(struct kvm_pt_regs, b6));
+	DEFINE(VMM_PT_REGS_B7_OFFSET,
+				offsetof(struct kvm_pt_regs, b7));
+	DEFINE(VMM_PT_REGS_AR_CSD_OFFSET,
+				offsetof(struct kvm_pt_regs, ar_csd));
+	DEFINE(VMM_PT_REGS_AR_SSD_OFFSET,
+				offsetof(struct kvm_pt_regs, ar_ssd));
+	DEFINE(VMM_PT_REGS_R8_OFFSET,
+				offsetof(struct kvm_pt_regs, r8));
+	DEFINE(VMM_PT_REGS_R9_OFFSET,
+				offsetof(struct kvm_pt_regs, r9));
+	DEFINE(VMM_PT_REGS_R10_OFFSET,
+				offsetof(struct kvm_pt_regs, r10));
+	DEFINE(VMM_PT_REGS_R11_OFFSET,
+				offsetof(struct kvm_pt_regs, r11));
+	DEFINE(VMM_PT_REGS_CR_IPSR_OFFSET,
+				offsetof(struct kvm_pt_regs, cr_ipsr));
+	DEFINE(VMM_PT_REGS_CR_IIP_OFFSET,
+				offsetof(struct kvm_pt_regs, cr_iip));
+	DEFINE(VMM_PT_REGS_CR_IFS_OFFSET,
+				offsetof(struct kvm_pt_regs, cr_ifs));
+	DEFINE(VMM_PT_REGS_AR_UNAT_OFFSET,
+				offsetof(struct kvm_pt_regs, ar_unat));
+	DEFINE(VMM_PT_REGS_AR_PFS_OFFSET,
+				offsetof(struct kvm_pt_regs, ar_pfs));
+	DEFINE(VMM_PT_REGS_AR_RSC_OFFSET,
+				offsetof(struct kvm_pt_regs, ar_rsc));
+	DEFINE(VMM_PT_REGS_AR_RNAT_OFFSET,
+				offsetof(struct kvm_pt_regs, ar_rnat));
+
+	DEFINE(VMM_PT_REGS_AR_BSPSTORE_OFFSET,
+				offsetof(struct kvm_pt_regs, ar_bspstore));
+	DEFINE(VMM_PT_REGS_PR_OFFSET,
+				offsetof(struct kvm_pt_regs, pr));
+	DEFINE(VMM_PT_REGS_B0_OFFSET,
+				offsetof(struct kvm_pt_regs, b0));
+	DEFINE(VMM_PT_REGS_LOADRS_OFFSET,
+				offsetof(struct kvm_pt_regs, loadrs));
+	DEFINE(VMM_PT_REGS_R1_OFFSET,
+				offsetof(struct kvm_pt_regs, r1));
+	DEFINE(VMM_PT_REGS_R12_OFFSET,
+				offsetof(struct kvm_pt_regs, r12));
+	DEFINE(VMM_PT_REGS_R13_OFFSET,
+				offsetof(struct kvm_pt_regs, r13));
+	DEFINE(VMM_PT_REGS_AR_FPSR_OFFSET,
+				offsetof(struct kvm_pt_regs, ar_fpsr));
+	DEFINE(VMM_PT_REGS_R15_OFFSET,
+				offsetof(struct kvm_pt_regs, r15));
+	DEFINE(VMM_PT_REGS_R14_OFFSET,
+				offsetof(struct kvm_pt_regs, r14));
+	DEFINE(VMM_PT_REGS_R2_OFFSET,
+				offsetof(struct kvm_pt_regs, r2));
+	DEFINE(VMM_PT_REGS_R3_OFFSET,
+				offsetof(struct kvm_pt_regs, r3));
+	DEFINE(VMM_PT_REGS_R16_OFFSET,
+				offsetof(struct kvm_pt_regs, r16));
+	DEFINE(VMM_PT_REGS_R17_OFFSET,
+				offsetof(struct kvm_pt_regs, r17));
+	DEFINE(VMM_PT_REGS_R18_OFFSET,
+				offsetof(struct kvm_pt_regs, r18));
+	DEFINE(VMM_PT_REGS_R19_OFFSET,
+				offsetof(struct kvm_pt_regs, r19));
+	DEFINE(VMM_PT_REGS_R20_OFFSET,
+				offsetof(struct kvm_pt_regs, r20));
+	DEFINE(VMM_PT_REGS_R21_OFFSET,
+				offsetof(struct kvm_pt_regs, r21));
+	DEFINE(VMM_PT_REGS_R22_OFFSET,
+				offsetof(struct kvm_pt_regs, r22));
+	DEFINE(VMM_PT_REGS_R23_OFFSET,
+				offsetof(struct kvm_pt_regs, r23));
+	DEFINE(VMM_PT_REGS_R24_OFFSET,
+				offsetof(struct kvm_pt_regs, r24));
+	DEFINE(VMM_PT_REGS_R25_OFFSET,
+				offsetof(struct kvm_pt_regs, r25));
+	DEFINE(VMM_PT_REGS_R26_OFFSET,
+				offsetof(struct kvm_pt_regs, r26));
+	DEFINE(VMM_PT_REGS_R27_OFFSET,
+				offsetof(struct kvm_pt_regs, r27));
+	DEFINE(VMM_PT_REGS_R28_OFFSET,
+				offsetof(struct kvm_pt_regs, r28));
+	DEFINE(VMM_PT_REGS_R29_OFFSET,
+				offsetof(struct kvm_pt_regs, r29));
+	DEFINE(VMM_PT_REGS_R30_OFFSET,
+				offsetof(struct kvm_pt_regs, r30));
+	DEFINE(VMM_PT_REGS_R31_OFFSET,
+				offsetof(struct kvm_pt_regs, r31));
+	DEFINE(VMM_PT_REGS_AR_CCV_OFFSET,
+				offsetof(struct kvm_pt_regs, ar_ccv));
+	DEFINE(VMM_PT_REGS_F6_OFFSET,
+				offsetof(struct kvm_pt_regs, f6));
+	DEFINE(VMM_PT_REGS_F7_OFFSET,
+				offsetof(struct kvm_pt_regs, f7));
+	DEFINE(VMM_PT_REGS_F8_OFFSET,
+				offsetof(struct kvm_pt_regs, f8));
+	DEFINE(VMM_PT_REGS_F9_OFFSET,
+				offsetof(struct kvm_pt_regs, f9));
+	DEFINE(VMM_PT_REGS_F10_OFFSET,
+				offsetof(struct kvm_pt_regs, f10));
+	DEFINE(VMM_PT_REGS_F11_OFFSET,
+				offsetof(struct kvm_pt_regs, f11));
+	DEFINE(VMM_PT_REGS_R4_OFFSET,
+				offsetof(struct kvm_pt_regs, r4));
+	DEFINE(VMM_PT_REGS_R5_OFFSET,
+				offsetof(struct kvm_pt_regs, r5));
+	DEFINE(VMM_PT_REGS_R6_OFFSET,
+				offsetof(struct kvm_pt_regs, r6));
+	DEFINE(VMM_PT_REGS_R7_OFFSET,
+				offsetof(struct kvm_pt_regs, r7));
+	DEFINE(VMM_PT_REGS_EML_UNAT_OFFSET,
+				offsetof(struct kvm_pt_regs, eml_unat));
+	DEFINE(VMM_VCPU_IIPA_OFFSET,
+				offsetof(struct kvm_vcpu, arch.cr_iipa));
+	DEFINE(VMM_VCPU_OPCODE_OFFSET,
+				offsetof(struct kvm_vcpu, arch.opcode));
+	DEFINE(VMM_VCPU_CAUSE_OFFSET, offsetof(struct kvm_vcpu, arch.cause));
+	DEFINE(VMM_VCPU_ISR_OFFSET,
+				offsetof(struct kvm_vcpu, arch.cr_isr));
+	DEFINE(VMM_PT_REGS_R16_SLOT,
+				(((offsetof(struct kvm_pt_regs, r16)
+				- sizeof(struct kvm_pt_regs)) >> 3) & 0x3f));
+	DEFINE(VMM_VCPU_MODE_FLAGS_OFFSET,
+				offsetof(struct kvm_vcpu, arch.mode_flags));
+	DEFINE(VMM_VCPU_GP_OFFSET, offsetof(struct kvm_vcpu, arch.__gp));
+	BLANK();
+
+	DEFINE(VMM_VPD_BASE_OFFSET, offsetof(struct kvm_vcpu, arch.vpd));
+	DEFINE(VMM_VPD_VIFS_OFFSET, offsetof(struct vpd, ifs));
+	DEFINE(VMM_VLSAPIC_INSVC_BASE_OFFSET,
+			offsetof(struct kvm_vcpu, arch.insvc[0]));
+	DEFINE(VMM_VPD_VPTA_OFFSET, offsetof(struct vpd, pta));
+	DEFINE(VMM_VPD_VPSR_OFFSET, offsetof(struct vpd, vpsr));
+
+	DEFINE(VMM_CTX_R4_OFFSET, offsetof(union context, gr[4]));
+	DEFINE(VMM_CTX_R5_OFFSET, offsetof(union context, gr[5]));
+	DEFINE(VMM_CTX_R12_OFFSET, offsetof(union context, gr[12]));
+	DEFINE(VMM_CTX_R13_OFFSET, offsetof(union context, gr[13]));
+	DEFINE(VMM_CTX_KR0_OFFSET, offsetof(union context, ar[0]));
+	DEFINE(VMM_CTX_KR1_OFFSET, offsetof(union context, ar[1]));
+	DEFINE(VMM_CTX_B0_OFFSET, offsetof(union context, br[0]));
+	DEFINE(VMM_CTX_B1_OFFSET, offsetof(union context, br[1]));
+	DEFINE(VMM_CTX_B2_OFFSET, offsetof(union context, br[2]));
+	DEFINE(VMM_CTX_RR0_OFFSET, offsetof(union context, rr[0]));
+	DEFINE(VMM_CTX_RSC_OFFSET, offsetof(union context, ar[16]));
+	DEFINE(VMM_CTX_BSPSTORE_OFFSET, offsetof(union context, ar[18]));
+	DEFINE(VMM_CTX_RNAT_OFFSET, offsetof(union context, ar[19]));
+	DEFINE(VMM_CTX_FCR_OFFSET, offsetof(union context, ar[21]));
+	DEFINE(VMM_CTX_EFLAG_OFFSET, offsetof(union context, ar[24]));
+	DEFINE(VMM_CTX_CFLG_OFFSET, offsetof(union context, ar[27]));
+	DEFINE(VMM_CTX_FSR_OFFSET, offsetof(union context, ar[28]));
+	DEFINE(VMM_CTX_FIR_OFFSET, offsetof(union context, ar[29]));
+	DEFINE(VMM_CTX_FDR_OFFSET, offsetof(union context, ar[30]));
+	DEFINE(VMM_CTX_UNAT_OFFSET, offsetof(union context, ar[36]));
+	DEFINE(VMM_CTX_FPSR_OFFSET, offsetof(union context, ar[40]));
+	DEFINE(VMM_CTX_PFS_OFFSET, offsetof(union context, ar[64]));
+	DEFINE(VMM_CTX_LC_OFFSET, offsetof(union context, ar[65]));
+	DEFINE(VMM_CTX_DCR_OFFSET, offsetof(union context, cr[0]));
+	DEFINE(VMM_CTX_IVA_OFFSET, offsetof(union context, cr[2]));
+	DEFINE(VMM_CTX_PTA_OFFSET, offsetof(union context, cr[8]));
+	DEFINE(VMM_CTX_IBR0_OFFSET, offsetof(union context, ibr[0]));
+	DEFINE(VMM_CTX_DBR0_OFFSET, offsetof(union context, dbr[0]));
+	DEFINE(VMM_CTX_F2_OFFSET, offsetof(union context, fr[2]));
+	DEFINE(VMM_CTX_F3_OFFSET, offsetof(union context, fr[3]));
+	DEFINE(VMM_CTX_F32_OFFSET, offsetof(union context, fr[32]));
+	DEFINE(VMM_CTX_F33_OFFSET, offsetof(union context, fr[33]));
+	DEFINE(VMM_CTX_PKR0_OFFSET, offsetof(union context, pkr[0]));
+	DEFINE(VMM_CTX_PSR_OFFSET, offsetof(union context, psr));
+	BLANK();
+}
diff --git a/trunk/arch/ia64/kvm/kvm-ia64.c b/trunk/arch/ia64/kvm/kvm-ia64.c
new file mode 100644
index 000000000000..6df073240135
--- /dev/null
+++ b/trunk/arch/ia64/kvm/kvm-ia64.c
@@ -0,0 +1,1806 @@
+
+/*
+ * kvm_ia64.c: Basic KVM suppport On Itanium series processors
+ *
+ *
+ * 	Copyright (C) 2007, Intel Corporation.
+ *  	Xiantao Zhang  (xiantao.zhang@intel.com)
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/percpu.h>
+#include <linux/gfp.h>
+#include <linux/fs.h>
+#include <linux/smp.h>
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/bitops.h>
+#include <linux/hrtimer.h>
+#include <linux/uaccess.h>
+
+#include <asm/pgtable.h>
+#include <asm/gcc_intrin.h>
+#include <asm/pal.h>
+#include <asm/cacheflush.h>
+#include <asm/div64.h>
+#include <asm/tlb.h>
+
+#include "misc.h"
+#include "vti.h"
+#include "iodev.h"
+#include "ioapic.h"
+#include "lapic.h"
+
+static unsigned long kvm_vmm_base;
+static unsigned long kvm_vsa_base;
+static unsigned long kvm_vm_buffer;
+static unsigned long kvm_vm_buffer_size;
+unsigned long kvm_vmm_gp;
+
+static long vp_env_info;
+
+static struct kvm_vmm_info *kvm_vmm_info;
+
+static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu);
+
+struct kvm_stats_debugfs_item debugfs_entries[] = {
+	{ NULL }
+};
+
+
+struct fdesc{
+    unsigned long ip;
+    unsigned long gp;
+};
+
+static void kvm_flush_icache(unsigned long start, unsigned long len)
+{
+	int l;
+
+	for (l = 0; l < (len + 32); l += 32)
+		ia64_fc(start + l);
+
+	ia64_sync_i();
+	ia64_srlz_i();
+}
+
+static void kvm_flush_tlb_all(void)
+{
+	unsigned long i, j, count0, count1, stride0, stride1, addr;
+	long flags;
+
+	addr    = local_cpu_data->ptce_base;
+	count0  = local_cpu_data->ptce_count[0];
+	count1  = local_cpu_data->ptce_count[1];
+	stride0 = local_cpu_data->ptce_stride[0];
+	stride1 = local_cpu_data->ptce_stride[1];
+
+	local_irq_save(flags);
+	for (i = 0; i < count0; ++i) {
+		for (j = 0; j < count1; ++j) {
+			ia64_ptce(addr);
+			addr += stride1;
+		}
+		addr += stride0;
+	}
+	local_irq_restore(flags);
+	ia64_srlz_i();			/* srlz.i implies srlz.d */
+}
+
+long ia64_pal_vp_create(u64 *vpd, u64 *host_iva, u64 *opt_handler)
+{
+	struct ia64_pal_retval iprv;
+
+	PAL_CALL_STK(iprv, PAL_VP_CREATE, (u64)vpd, (u64)host_iva,
+			(u64)opt_handler);
+
+	return iprv.status;
+}
+
+static  DEFINE_SPINLOCK(vp_lock);
+
+void kvm_arch_hardware_enable(void *garbage)
+{
+	long  status;
+	long  tmp_base;
+	unsigned long pte;
+	unsigned long saved_psr;
+	int slot;
+
+	pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base),
+				PAGE_KERNEL));
+	local_irq_save(saved_psr);
+	slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT);
+	if (slot < 0)
+		return;
+	local_irq_restore(saved_psr);
+
+	spin_lock(&vp_lock);
+	status = ia64_pal_vp_init_env(kvm_vsa_base ?
+				VP_INIT_ENV : VP_INIT_ENV_INITALIZE,
+			__pa(kvm_vm_buffer), KVM_VM_BUFFER_BASE, &tmp_base);
+	if (status != 0) {
+		printk(KERN_WARNING"kvm: Failed to Enable VT Support!!!!\n");
+		return ;
+	}
+
+	if (!kvm_vsa_base) {
+		kvm_vsa_base = tmp_base;
+		printk(KERN_INFO"kvm: kvm_vsa_base:0x%lx\n", kvm_vsa_base);
+	}
+	spin_unlock(&vp_lock);
+	ia64_ptr_entry(0x3, slot);
+}
+
+void kvm_arch_hardware_disable(void *garbage)
+{
+
+	long status;
+	int slot;
+	unsigned long pte;
+	unsigned long saved_psr;
+	unsigned long host_iva = ia64_getreg(_IA64_REG_CR_IVA);
+
+	pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base),
+				PAGE_KERNEL));
+
+	local_irq_save(saved_psr);
+	slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT);
+	if (slot < 0)
+		return;
+	local_irq_restore(saved_psr);
+
+	status = ia64_pal_vp_exit_env(host_iva);
+	if (status)
+		printk(KERN_DEBUG"kvm: Failed to disable VT support! :%ld\n",
+				status);
+	ia64_ptr_entry(0x3, slot);
+}
+
+void kvm_arch_check_processor_compat(void *rtn)
+{
+	*(int *)rtn = 0;
+}
+
+int kvm_dev_ioctl_check_extension(long ext)
+{
+
+	int r;
+
+	switch (ext) {
+	case KVM_CAP_IRQCHIP:
+	case KVM_CAP_USER_MEMORY:
+
+		r = 1;
+		break;
+	default:
+		r = 0;
+	}
+	return r;
+
+}
+
+static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
+					gpa_t addr)
+{
+	struct kvm_io_device *dev;
+
+	dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr);
+
+	return dev;
+}
+
+static int handle_vm_error(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
+	kvm_run->hw.hardware_exit_reason = 1;
+	return 0;
+}
+
+static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	struct kvm_mmio_req *p;
+	struct kvm_io_device *mmio_dev;
+
+	p = kvm_get_vcpu_ioreq(vcpu);
+
+	if ((p->addr & PAGE_MASK) == IOAPIC_DEFAULT_BASE_ADDRESS)
+		goto mmio;
+	vcpu->mmio_needed = 1;
+	vcpu->mmio_phys_addr = kvm_run->mmio.phys_addr = p->addr;
+	vcpu->mmio_size = kvm_run->mmio.len = p->size;
+	vcpu->mmio_is_write = kvm_run->mmio.is_write = !p->dir;
+
+	if (vcpu->mmio_is_write)
+		memcpy(vcpu->mmio_data, &p->data, p->size);
+	memcpy(kvm_run->mmio.data, &p->data, p->size);
+	kvm_run->exit_reason = KVM_EXIT_MMIO;
+	return 0;
+mmio:
+	mmio_dev = vcpu_find_mmio_dev(vcpu, p->addr);
+	if (mmio_dev) {
+		if (!p->dir)
+			kvm_iodevice_write(mmio_dev, p->addr, p->size,
+						&p->data);
+		else
+			kvm_iodevice_read(mmio_dev, p->addr, p->size,
+						&p->data);
+
+	} else
+		printk(KERN_ERR"kvm: No iodevice found! addr:%lx\n", p->addr);
+	p->state = STATE_IORESP_READY;
+
+	return 1;
+}
+
+static int handle_pal_call(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	struct exit_ctl_data *p;
+
+	p = kvm_get_exit_data(vcpu);
+
+	if (p->exit_reason == EXIT_REASON_PAL_CALL)
+		return kvm_pal_emul(vcpu, kvm_run);
+	else {
+		kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
+		kvm_run->hw.hardware_exit_reason = 2;
+		return 0;
+	}
+}
+
+static int handle_sal_call(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	struct exit_ctl_data *p;
+
+	p = kvm_get_exit_data(vcpu);
+
+	if (p->exit_reason == EXIT_REASON_SAL_CALL) {
+		kvm_sal_emul(vcpu);
+		return 1;
+	} else {
+		kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
+		kvm_run->hw.hardware_exit_reason = 3;
+		return 0;
+	}
+
+}
+
+/*
+ *  offset: address offset to IPI space.
+ *  value:  deliver value.
+ */
+static void vcpu_deliver_ipi(struct kvm_vcpu *vcpu, uint64_t dm,
+				uint64_t vector)
+{
+	switch (dm) {
+	case SAPIC_FIXED:
+		kvm_apic_set_irq(vcpu, vector, 0);
+		break;
+	case SAPIC_NMI:
+		kvm_apic_set_irq(vcpu, 2, 0);
+		break;
+	case SAPIC_EXTINT:
+		kvm_apic_set_irq(vcpu, 0, 0);
+		break;
+	case SAPIC_INIT:
+	case SAPIC_PMI:
+	default:
+		printk(KERN_ERR"kvm: Unimplemented Deliver reserved IPI!\n");
+		break;
+	}
+}
+
+static struct kvm_vcpu *lid_to_vcpu(struct kvm *kvm, unsigned long id,
+			unsigned long eid)
+{
+	union ia64_lid lid;
+	int i;
+
+	for (i = 0; i < KVM_MAX_VCPUS; i++) {
+		if (kvm->vcpus[i]) {
+			lid.val = VCPU_LID(kvm->vcpus[i]);
+			if (lid.id == id && lid.eid == eid)
+				return kvm->vcpus[i];
+		}
+	}
+
+	return NULL;
+}
+
+static int handle_ipi(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	struct exit_ctl_data *p = kvm_get_exit_data(vcpu);
+	struct kvm_vcpu *target_vcpu;
+	struct kvm_pt_regs *regs;
+	union ia64_ipi_a addr = p->u.ipi_data.addr;
+	union ia64_ipi_d data = p->u.ipi_data.data;
+
+	target_vcpu = lid_to_vcpu(vcpu->kvm, addr.id, addr.eid);
+	if (!target_vcpu)
+		return handle_vm_error(vcpu, kvm_run);
+
+	if (!target_vcpu->arch.launched) {
+		regs = vcpu_regs(target_vcpu);
+
+		regs->cr_iip = vcpu->kvm->arch.rdv_sal_data.boot_ip;
+		regs->r1 = vcpu->kvm->arch.rdv_sal_data.boot_gp;
+
+		target_vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+		if (waitqueue_active(&target_vcpu->wq))
+			wake_up_interruptible(&target_vcpu->wq);
+	} else {
+		vcpu_deliver_ipi(target_vcpu, data.dm, data.vector);
+		if (target_vcpu != vcpu)
+			kvm_vcpu_kick(target_vcpu);
+	}
+
+	return 1;
+}
+
+struct call_data {
+	struct kvm_ptc_g ptc_g_data;
+	struct kvm_vcpu *vcpu;
+};
+
+static void vcpu_global_purge(void *info)
+{
+	struct call_data *p = (struct call_data *)info;
+	struct kvm_vcpu *vcpu = p->vcpu;
+
+	if (test_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
+		return;
+
+	set_bit(KVM_REQ_PTC_G, &vcpu->requests);
+	if (vcpu->arch.ptc_g_count < MAX_PTC_G_NUM) {
+		vcpu->arch.ptc_g_data[vcpu->arch.ptc_g_count++] =
+							p->ptc_g_data;
+	} else {
+		clear_bit(KVM_REQ_PTC_G, &vcpu->requests);
+		vcpu->arch.ptc_g_count = 0;
+		set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests);
+	}
+}
+
+static int handle_global_purge(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	struct exit_ctl_data *p = kvm_get_exit_data(vcpu);
+	struct kvm *kvm = vcpu->kvm;
+	struct call_data call_data;
+	int i;
+	call_data.ptc_g_data = p->u.ptc_g_data;
+
+	for (i = 0; i < KVM_MAX_VCPUS; i++) {
+		if (!kvm->vcpus[i] || kvm->vcpus[i]->arch.mp_state ==
+						KVM_MP_STATE_UNINITIALIZED ||
+					vcpu == kvm->vcpus[i])
+			continue;
+
+		if (waitqueue_active(&kvm->vcpus[i]->wq))
+			wake_up_interruptible(&kvm->vcpus[i]->wq);
+
+		if (kvm->vcpus[i]->cpu != -1) {
+			call_data.vcpu = kvm->vcpus[i];
+			smp_call_function_single(kvm->vcpus[i]->cpu,
+					vcpu_global_purge, &call_data, 0, 1);
+		} else
+			printk(KERN_WARNING"kvm: Uninit vcpu received ipi!\n");
+
+	}
+	return 1;
+}
+
+static int handle_switch_rr6(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	return 1;
+}
+
+int kvm_emulate_halt(struct kvm_vcpu *vcpu)
+{
+
+	ktime_t kt;
+	long itc_diff;
+	unsigned long vcpu_now_itc;
+
+	unsigned long expires;
+	struct hrtimer *p_ht = &vcpu->arch.hlt_timer;
+	unsigned long cyc_per_usec = local_cpu_data->cyc_per_usec;
+	struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+
+	vcpu_now_itc = ia64_getreg(_IA64_REG_AR_ITC) + vcpu->arch.itc_offset;
+
+	if (time_after(vcpu_now_itc, vpd->itm)) {
+		vcpu->arch.timer_check = 1;
+		return 1;
+	}
+	itc_diff = vpd->itm - vcpu_now_itc;
+	if (itc_diff < 0)
+		itc_diff = -itc_diff;
+
+	expires = div64_64(itc_diff, cyc_per_usec);
+	kt = ktime_set(0, 1000 * expires);
+	vcpu->arch.ht_active = 1;
+	hrtimer_start(p_ht, kt, HRTIMER_MODE_ABS);
+
+	if (irqchip_in_kernel(vcpu->kvm)) {
+		vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
+		kvm_vcpu_block(vcpu);
+		hrtimer_cancel(p_ht);
+		vcpu->arch.ht_active = 0;
+
+		if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
+			return -EINTR;
+		return 1;
+	} else {
+		printk(KERN_ERR"kvm: Unsupported userspace halt!");
+		return 0;
+	}
+}
+
+static int handle_vm_shutdown(struct kvm_vcpu *vcpu,
+		struct kvm_run *kvm_run)
+{
+	kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
+	return 0;
+}
+
+static int handle_external_interrupt(struct kvm_vcpu *vcpu,
+		struct kvm_run *kvm_run)
+{
+	return 1;
+}
+
+static int (*kvm_vti_exit_handlers[])(struct kvm_vcpu *vcpu,
+		struct kvm_run *kvm_run) = {
+	[EXIT_REASON_VM_PANIC]              = handle_vm_error,
+	[EXIT_REASON_MMIO_INSTRUCTION]      = handle_mmio,
+	[EXIT_REASON_PAL_CALL]              = handle_pal_call,
+	[EXIT_REASON_SAL_CALL]              = handle_sal_call,
+	[EXIT_REASON_SWITCH_RR6]            = handle_switch_rr6,
+	[EXIT_REASON_VM_DESTROY]            = handle_vm_shutdown,
+	[EXIT_REASON_EXTERNAL_INTERRUPT]    = handle_external_interrupt,
+	[EXIT_REASON_IPI]		    = handle_ipi,
+	[EXIT_REASON_PTC_G]		    = handle_global_purge,
+
+};
+
+static const int kvm_vti_max_exit_handlers =
+		sizeof(kvm_vti_exit_handlers)/sizeof(*kvm_vti_exit_handlers);
+
+static void kvm_prepare_guest_switch(struct kvm_vcpu *vcpu)
+{
+}
+
+static uint32_t kvm_get_exit_reason(struct kvm_vcpu *vcpu)
+{
+	struct exit_ctl_data *p_exit_data;
+
+	p_exit_data = kvm_get_exit_data(vcpu);
+	return p_exit_data->exit_reason;
+}
+
+/*
+ * The guest has exited.  See if we can fix it or if we need userspace
+ * assistance.
+ */
+static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+{
+	u32 exit_reason = kvm_get_exit_reason(vcpu);
+	vcpu->arch.last_exit = exit_reason;
+
+	if (exit_reason < kvm_vti_max_exit_handlers
+			&& kvm_vti_exit_handlers[exit_reason])
+		return kvm_vti_exit_handlers[exit_reason](vcpu, kvm_run);
+	else {
+		kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
+		kvm_run->hw.hardware_exit_reason = exit_reason;
+	}
+	return 0;
+}
+
+static inline void vti_set_rr6(unsigned long rr6)
+{
+	ia64_set_rr(RR6, rr6);
+	ia64_srlz_i();
+}
+
+static int kvm_insert_vmm_mapping(struct kvm_vcpu *vcpu)
+{
+	unsigned long pte;
+	struct kvm *kvm = vcpu->kvm;
+	int r;
+
+	/*Insert a pair of tr to map vmm*/
+	pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base), PAGE_KERNEL));
+	r = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT);
+	if (r < 0)
+		goto out;
+	vcpu->arch.vmm_tr_slot = r;
+	/*Insert a pairt of tr to map data of vm*/
+	pte = pte_val(mk_pte_phys(__pa(kvm->arch.vm_base), PAGE_KERNEL));
+	r = ia64_itr_entry(0x3, KVM_VM_DATA_BASE,
+					pte, KVM_VM_DATA_SHIFT);
+	if (r < 0)
+		goto out;
+	vcpu->arch.vm_tr_slot = r;
+	r = 0;
+out:
+	return r;
+
+}
+
+static void kvm_purge_vmm_mapping(struct kvm_vcpu *vcpu)
+{
+
+	ia64_ptr_entry(0x3, vcpu->arch.vmm_tr_slot);
+	ia64_ptr_entry(0x3, vcpu->arch.vm_tr_slot);
+
+}
+
+static int kvm_vcpu_pre_transition(struct kvm_vcpu *vcpu)
+{
+	int cpu = smp_processor_id();
+
+	if (vcpu->arch.last_run_cpu != cpu ||
+			per_cpu(last_vcpu, cpu) != vcpu) {
+		per_cpu(last_vcpu, cpu) = vcpu;
+		vcpu->arch.last_run_cpu = cpu;
+		kvm_flush_tlb_all();
+	}
+
+	vcpu->arch.host_rr6 = ia64_get_rr(RR6);
+	vti_set_rr6(vcpu->arch.vmm_rr);
+	return kvm_insert_vmm_mapping(vcpu);
+}
+static void kvm_vcpu_post_transition(struct kvm_vcpu *vcpu)
+{
+	kvm_purge_vmm_mapping(vcpu);
+	vti_set_rr6(vcpu->arch.host_rr6);
+}
+
+static int  vti_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	union context *host_ctx, *guest_ctx;
+	int r;
+
+	/*Get host and guest context with guest address space.*/
+	host_ctx = kvm_get_host_context(vcpu);
+	guest_ctx = kvm_get_guest_context(vcpu);
+
+	r = kvm_vcpu_pre_transition(vcpu);
+	if (r < 0)
+		goto out;
+	kvm_vmm_info->tramp_entry(host_ctx, guest_ctx);
+	kvm_vcpu_post_transition(vcpu);
+	r = 0;
+out:
+	return r;
+}
+
+static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	int r;
+
+again:
+	preempt_disable();
+
+	kvm_prepare_guest_switch(vcpu);
+	local_irq_disable();
+
+	if (signal_pending(current)) {
+		local_irq_enable();
+		preempt_enable();
+		r = -EINTR;
+		kvm_run->exit_reason = KVM_EXIT_INTR;
+		goto out;
+	}
+
+	vcpu->guest_mode = 1;
+	kvm_guest_enter();
+
+	r = vti_vcpu_run(vcpu, kvm_run);
+	if (r < 0) {
+		local_irq_enable();
+		preempt_enable();
+		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+		goto out;
+	}
+
+	vcpu->arch.launched = 1;
+	vcpu->guest_mode = 0;
+	local_irq_enable();
+
+	/*
+	 * We must have an instruction between local_irq_enable() and
+	 * kvm_guest_exit(), so the timer interrupt isn't delayed by
+	 * the interrupt shadow.  The stat.exits increment will do nicely.
+	 * But we need to prevent reordering, hence this barrier():
+	 */
+	barrier();
+
+	kvm_guest_exit();
+
+	preempt_enable();
+
+	r = kvm_handle_exit(kvm_run, vcpu);
+
+	if (r > 0) {
+		if (!need_resched())
+			goto again;
+	}
+
+out:
+	if (r > 0) {
+		kvm_resched(vcpu);
+		goto again;
+	}
+
+	return r;
+}
+
+static void kvm_set_mmio_data(struct kvm_vcpu *vcpu)
+{
+	struct kvm_mmio_req *p = kvm_get_vcpu_ioreq(vcpu);
+
+	if (!vcpu->mmio_is_write)
+		memcpy(&p->data, vcpu->mmio_data, 8);
+	p->state = STATE_IORESP_READY;
+}
+
+int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	int r;
+	sigset_t sigsaved;
+
+	vcpu_load(vcpu);
+
+	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
+		kvm_vcpu_block(vcpu);
+		vcpu_put(vcpu);
+		return -EAGAIN;
+	}
+
+	if (vcpu->sigset_active)
+		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+
+	if (vcpu->mmio_needed) {
+		memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
+		kvm_set_mmio_data(vcpu);
+		vcpu->mmio_read_completed = 1;
+		vcpu->mmio_needed = 0;
+	}
+	r = __vcpu_run(vcpu, kvm_run);
+
+	if (vcpu->sigset_active)
+		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+	vcpu_put(vcpu);
+	return r;
+}
+
+/*
+ * Allocate 16M memory for every vm to hold its specific data.
+ * Its memory map is defined in kvm_host.h.
+ */
+static struct kvm *kvm_alloc_kvm(void)
+{
+
+	struct kvm *kvm;
+	uint64_t  vm_base;
+
+	vm_base = __get_free_pages(GFP_KERNEL, get_order(KVM_VM_DATA_SIZE));
+
+	if (!vm_base)
+		return ERR_PTR(-ENOMEM);
+	printk(KERN_DEBUG"kvm: VM data's base Address:0x%lx\n", vm_base);
+
+	/* Zero all pages before use! */
+	memset((void *)vm_base, 0, KVM_VM_DATA_SIZE);
+
+	kvm = (struct kvm *)(vm_base + KVM_VM_OFS);
+	kvm->arch.vm_base = vm_base;
+
+	return kvm;
+}
+
+struct kvm_io_range {
+	unsigned long start;
+	unsigned long size;
+	unsigned long type;
+};
+
+static const struct kvm_io_range io_ranges[] = {
+	{VGA_IO_START, VGA_IO_SIZE, GPFN_FRAME_BUFFER},
+	{MMIO_START, MMIO_SIZE, GPFN_LOW_MMIO},
+	{LEGACY_IO_START, LEGACY_IO_SIZE, GPFN_LEGACY_IO},
+	{IO_SAPIC_START, IO_SAPIC_SIZE, GPFN_IOSAPIC},
+	{PIB_START, PIB_SIZE, GPFN_PIB},
+};
+
+static void kvm_build_io_pmt(struct kvm *kvm)
+{
+	unsigned long i, j;
+
+	/* Mark I/O ranges */
+	for (i = 0; i < (sizeof(io_ranges) / sizeof(struct kvm_io_range));
+							i++) {
+		for (j = io_ranges[i].start;
+				j < io_ranges[i].start + io_ranges[i].size;
+				j += PAGE_SIZE)
+			kvm_set_pmt_entry(kvm, j >> PAGE_SHIFT,
+					io_ranges[i].type, 0);
+	}
+
+}
+
+/*Use unused rids to virtualize guest rid.*/
+#define GUEST_PHYSICAL_RR0	0x1739
+#define GUEST_PHYSICAL_RR4	0x2739
+#define VMM_INIT_RR		0x1660
+
+static void kvm_init_vm(struct kvm *kvm)
+{
+	long vm_base;
+
+	BUG_ON(!kvm);
+
+	kvm->arch.metaphysical_rr0 = GUEST_PHYSICAL_RR0;
+	kvm->arch.metaphysical_rr4 = GUEST_PHYSICAL_RR4;
+	kvm->arch.vmm_init_rr = VMM_INIT_RR;
+
+	vm_base = kvm->arch.vm_base;
+	if (vm_base) {
+		kvm->arch.vhpt_base = vm_base + KVM_VHPT_OFS;
+		kvm->arch.vtlb_base = vm_base + KVM_VTLB_OFS;
+		kvm->arch.vpd_base  = vm_base + KVM_VPD_OFS;
+	}
+
+	/*
+	 *Fill P2M entries for MMIO/IO ranges
+	 */
+	kvm_build_io_pmt(kvm);
+
+}
+
+struct  kvm *kvm_arch_create_vm(void)
+{
+	struct kvm *kvm = kvm_alloc_kvm();
+
+	if (IS_ERR(kvm))
+		return ERR_PTR(-ENOMEM);
+	kvm_init_vm(kvm);
+
+	return kvm;
+
+}
+
+static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm,
+					struct kvm_irqchip *chip)
+{
+	int r;
+
+	r = 0;
+	switch (chip->chip_id) {
+	case KVM_IRQCHIP_IOAPIC:
+		memcpy(&chip->chip.ioapic, ioapic_irqchip(kvm),
+				sizeof(struct kvm_ioapic_state));
+		break;
+	default:
+		r = -EINVAL;
+		break;
+	}
+	return r;
+}
+
+static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
+{
+	int r;
+
+	r = 0;
+	switch (chip->chip_id) {
+	case KVM_IRQCHIP_IOAPIC:
+		memcpy(ioapic_irqchip(kvm),
+				&chip->chip.ioapic,
+				sizeof(struct kvm_ioapic_state));
+		break;
+	default:
+		r = -EINVAL;
+		break;
+	}
+	return r;
+}
+
+#define RESTORE_REGS(_x) vcpu->arch._x = regs->_x
+
+int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+	int i;
+	struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+	int r;
+
+	vcpu_load(vcpu);
+
+	for (i = 0; i < 16; i++) {
+		vpd->vgr[i] = regs->vpd.vgr[i];
+		vpd->vbgr[i] = regs->vpd.vbgr[i];
+	}
+	for (i = 0; i < 128; i++)
+		vpd->vcr[i] = regs->vpd.vcr[i];
+	vpd->vhpi = regs->vpd.vhpi;
+	vpd->vnat = regs->vpd.vnat;
+	vpd->vbnat = regs->vpd.vbnat;
+	vpd->vpsr = regs->vpd.vpsr;
+
+	vpd->vpr = regs->vpd.vpr;
+
+	r = -EFAULT;
+	r = copy_from_user(&vcpu->arch.guest, regs->saved_guest,
+						sizeof(union context));
+	if (r)
+		goto out;
+	r = copy_from_user(vcpu + 1, regs->saved_stack +
+			sizeof(struct kvm_vcpu),
+			IA64_STK_OFFSET - sizeof(struct kvm_vcpu));
+	if (r)
+		goto out;
+	vcpu->arch.exit_data =
+		((struct kvm_vcpu *)(regs->saved_stack))->arch.exit_data;
+
+	RESTORE_REGS(mp_state);
+	RESTORE_REGS(vmm_rr);
+	memcpy(vcpu->arch.itrs, regs->itrs, sizeof(struct thash_data) * NITRS);
+	memcpy(vcpu->arch.dtrs, regs->dtrs, sizeof(struct thash_data) * NDTRS);
+	RESTORE_REGS(itr_regions);
+	RESTORE_REGS(dtr_regions);
+	RESTORE_REGS(tc_regions);
+	RESTORE_REGS(irq_check);
+	RESTORE_REGS(itc_check);
+	RESTORE_REGS(timer_check);
+	RESTORE_REGS(timer_pending);
+	RESTORE_REGS(last_itc);
+	for (i = 0; i < 8; i++) {
+		vcpu->arch.vrr[i] = regs->vrr[i];
+		vcpu->arch.ibr[i] = regs->ibr[i];
+		vcpu->arch.dbr[i] = regs->dbr[i];
+	}
+	for (i = 0; i < 4; i++)
+		vcpu->arch.insvc[i] = regs->insvc[i];
+	RESTORE_REGS(xtp);
+	RESTORE_REGS(metaphysical_rr0);
+	RESTORE_REGS(metaphysical_rr4);
+	RESTORE_REGS(metaphysical_saved_rr0);
+	RESTORE_REGS(metaphysical_saved_rr4);
+	RESTORE_REGS(fp_psr);
+	RESTORE_REGS(saved_gp);
+
+	vcpu->arch.irq_new_pending = 1;
+	vcpu->arch.itc_offset = regs->saved_itc - ia64_getreg(_IA64_REG_AR_ITC);
+	set_bit(KVM_REQ_RESUME, &vcpu->requests);
+
+	vcpu_put(vcpu);
+	r = 0;
+out:
+	return r;
+}
+
+long kvm_arch_vm_ioctl(struct file *filp,
+		unsigned int ioctl, unsigned long arg)
+{
+	struct kvm *kvm = filp->private_data;
+	void __user *argp = (void __user *)arg;
+	int r = -EINVAL;
+
+	switch (ioctl) {
+	case KVM_SET_MEMORY_REGION: {
+		struct kvm_memory_region kvm_mem;
+		struct kvm_userspace_memory_region kvm_userspace_mem;
+
+		r = -EFAULT;
+		if (copy_from_user(&kvm_mem, argp, sizeof kvm_mem))
+			goto out;
+		kvm_userspace_mem.slot = kvm_mem.slot;
+		kvm_userspace_mem.flags = kvm_mem.flags;
+		kvm_userspace_mem.guest_phys_addr =
+					kvm_mem.guest_phys_addr;
+		kvm_userspace_mem.memory_size = kvm_mem.memory_size;
+		r = kvm_vm_ioctl_set_memory_region(kvm,
+					&kvm_userspace_mem, 0);
+		if (r)
+			goto out;
+		break;
+		}
+	case KVM_CREATE_IRQCHIP:
+		r = -EFAULT;
+		r = kvm_ioapic_init(kvm);
+		if (r)
+			goto out;
+		break;
+	case KVM_IRQ_LINE: {
+		struct kvm_irq_level irq_event;
+
+		r = -EFAULT;
+		if (copy_from_user(&irq_event, argp, sizeof irq_event))
+			goto out;
+		if (irqchip_in_kernel(kvm)) {
+			mutex_lock(&kvm->lock);
+			kvm_ioapic_set_irq(kvm->arch.vioapic,
+						irq_event.irq,
+						irq_event.level);
+			mutex_unlock(&kvm->lock);
+			r = 0;
+		}
+		break;
+		}
+	case KVM_GET_IRQCHIP: {
+		/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
+		struct kvm_irqchip chip;
+
+		r = -EFAULT;
+		if (copy_from_user(&chip, argp, sizeof chip))
+				goto out;
+		r = -ENXIO;
+		if (!irqchip_in_kernel(kvm))
+			goto out;
+		r = kvm_vm_ioctl_get_irqchip(kvm, &chip);
+		if (r)
+			goto out;
+		r = -EFAULT;
+		if (copy_to_user(argp, &chip, sizeof chip))
+				goto out;
+		r = 0;
+		break;
+		}
+	case KVM_SET_IRQCHIP: {
+		/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
+		struct kvm_irqchip chip;
+
+		r = -EFAULT;
+		if (copy_from_user(&chip, argp, sizeof chip))
+				goto out;
+		r = -ENXIO;
+		if (!irqchip_in_kernel(kvm))
+			goto out;
+		r = kvm_vm_ioctl_set_irqchip(kvm, &chip);
+		if (r)
+			goto out;
+		r = 0;
+		break;
+		}
+	default:
+		;
+	}
+out:
+	return r;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+		struct kvm_sregs *sregs)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+		struct kvm_sregs *sregs)
+{
+	return -EINVAL;
+
+}
+int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+		struct kvm_translation *tr)
+{
+
+	return -EINVAL;
+}
+
+static int kvm_alloc_vmm_area(void)
+{
+	if (!kvm_vmm_base && (kvm_vm_buffer_size < KVM_VM_BUFFER_SIZE)) {
+		kvm_vmm_base = __get_free_pages(GFP_KERNEL,
+				get_order(KVM_VMM_SIZE));
+		if (!kvm_vmm_base)
+			return -ENOMEM;
+
+		memset((void *)kvm_vmm_base, 0, KVM_VMM_SIZE);
+		kvm_vm_buffer = kvm_vmm_base + VMM_SIZE;
+
+		printk(KERN_DEBUG"kvm:VMM's Base Addr:0x%lx, vm_buffer:0x%lx\n",
+				kvm_vmm_base, kvm_vm_buffer);
+	}
+
+	return 0;
+}
+
+static void kvm_free_vmm_area(void)
+{
+	if (kvm_vmm_base) {
+		/*Zero this area before free to avoid bits leak!!*/
+		memset((void *)kvm_vmm_base, 0, KVM_VMM_SIZE);
+		free_pages(kvm_vmm_base, get_order(KVM_VMM_SIZE));
+		kvm_vmm_base  = 0;
+		kvm_vm_buffer = 0;
+		kvm_vsa_base = 0;
+	}
+}
+
+/*
+ * Make sure that a cpu that is being hot-unplugged does not have any vcpus
+ * cached on it. Leave it as blank for IA64.
+ */
+void decache_vcpus_on_cpu(int cpu)
+{
+}
+
+static void vti_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
+static int vti_init_vpd(struct kvm_vcpu *vcpu)
+{
+	int i;
+	union cpuid3_t cpuid3;
+	struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+
+	if (IS_ERR(vpd))
+		return PTR_ERR(vpd);
+
+	/* CPUID init */
+	for (i = 0; i < 5; i++)
+		vpd->vcpuid[i] = ia64_get_cpuid(i);
+
+	/* Limit the CPUID number to 5 */
+	cpuid3.value = vpd->vcpuid[3];
+	cpuid3.number = 4;	/* 5 - 1 */
+	vpd->vcpuid[3] = cpuid3.value;
+
+	/*Set vac and vdc fields*/
+	vpd->vac.a_from_int_cr = 1;
+	vpd->vac.a_to_int_cr = 1;
+	vpd->vac.a_from_psr = 1;
+	vpd->vac.a_from_cpuid = 1;
+	vpd->vac.a_cover = 1;
+	vpd->vac.a_bsw = 1;
+	vpd->vac.a_int = 1;
+	vpd->vdc.d_vmsw = 1;
+
+	/*Set virtual buffer*/
+	vpd->virt_env_vaddr = KVM_VM_BUFFER_BASE;
+
+	return 0;
+}
+
+static int vti_create_vp(struct kvm_vcpu *vcpu)
+{
+	long ret;
+	struct vpd *vpd = vcpu->arch.vpd;
+	unsigned long  vmm_ivt;
+
+	vmm_ivt = kvm_vmm_info->vmm_ivt;
+
+	printk(KERN_DEBUG "kvm: vcpu:%p,ivt: 0x%lx\n", vcpu, vmm_ivt);
+
+	ret = ia64_pal_vp_create((u64 *)vpd, (u64 *)vmm_ivt, 0);
+
+	if (ret) {
+		printk(KERN_ERR"kvm: ia64_pal_vp_create failed!\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void init_ptce_info(struct kvm_vcpu *vcpu)
+{
+	ia64_ptce_info_t ptce = {0};
+
+	ia64_get_ptce(&ptce);
+	vcpu->arch.ptce_base = ptce.base;
+	vcpu->arch.ptce_count[0] = ptce.count[0];
+	vcpu->arch.ptce_count[1] = ptce.count[1];
+	vcpu->arch.ptce_stride[0] = ptce.stride[0];
+	vcpu->arch.ptce_stride[1] = ptce.stride[1];
+}
+
+static void kvm_migrate_hlt_timer(struct kvm_vcpu *vcpu)
+{
+	struct hrtimer *p_ht = &vcpu->arch.hlt_timer;
+
+	if (hrtimer_cancel(p_ht))
+		hrtimer_start(p_ht, p_ht->expires, HRTIMER_MODE_ABS);
+}
+
+static enum hrtimer_restart hlt_timer_fn(struct hrtimer *data)
+{
+	struct kvm_vcpu *vcpu;
+	wait_queue_head_t *q;
+
+	vcpu  = container_of(data, struct kvm_vcpu, arch.hlt_timer);
+	if (vcpu->arch.mp_state != KVM_MP_STATE_HALTED)
+		goto out;
+
+	q = &vcpu->wq;
+	if (waitqueue_active(q)) {
+		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+		wake_up_interruptible(q);
+	}
+out:
+	vcpu->arch.timer_check = 1;
+	return HRTIMER_NORESTART;
+}
+
+#define PALE_RESET_ENTRY    0x80000000ffffffb0UL
+
+int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu *v;
+	int r;
+	int i;
+	long itc_offset;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+	union context *p_ctx = &vcpu->arch.guest;
+	struct kvm_vcpu *vmm_vcpu = to_guest(vcpu->kvm, vcpu);
+
+	/*Init vcpu context for first run.*/
+	if (IS_ERR(vmm_vcpu))
+		return PTR_ERR(vmm_vcpu);
+
+	if (vcpu->vcpu_id == 0) {
+		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+
+		/*Set entry address for first run.*/
+		regs->cr_iip = PALE_RESET_ENTRY;
+
+		/*Initilize itc offset for vcpus*/
+		itc_offset = 0UL - ia64_getreg(_IA64_REG_AR_ITC);
+		for (i = 0; i < MAX_VCPU_NUM; i++) {
+			v = (struct kvm_vcpu *)((char *)vcpu + VCPU_SIZE * i);
+			v->arch.itc_offset = itc_offset;
+			v->arch.last_itc = 0;
+		}
+	} else
+		vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED;
+
+	r = -ENOMEM;
+	vcpu->arch.apic = kzalloc(sizeof(struct kvm_lapic), GFP_KERNEL);
+	if (!vcpu->arch.apic)
+		goto out;
+	vcpu->arch.apic->vcpu = vcpu;
+
+	p_ctx->gr[1] = 0;
+	p_ctx->gr[12] = (unsigned long)((char *)vmm_vcpu + IA64_STK_OFFSET);
+	p_ctx->gr[13] = (unsigned long)vmm_vcpu;
+	p_ctx->psr = 0x1008522000UL;
+	p_ctx->ar[40] = FPSR_DEFAULT; /*fpsr*/
+	p_ctx->caller_unat = 0;
+	p_ctx->pr = 0x0;
+	p_ctx->ar[36] = 0x0; /*unat*/
+	p_ctx->ar[19] = 0x0; /*rnat*/
+	p_ctx->ar[18] = (unsigned long)vmm_vcpu +
+				((sizeof(struct kvm_vcpu)+15) & ~15);
+	p_ctx->ar[64] = 0x0; /*pfs*/
+	p_ctx->cr[0] = 0x7e04UL;
+	p_ctx->cr[2] = (unsigned long)kvm_vmm_info->vmm_ivt;
+	p_ctx->cr[8] = 0x3c;
+
+	/*Initilize region register*/
+	p_ctx->rr[0] = 0x30;
+	p_ctx->rr[1] = 0x30;
+	p_ctx->rr[2] = 0x30;
+	p_ctx->rr[3] = 0x30;
+	p_ctx->rr[4] = 0x30;
+	p_ctx->rr[5] = 0x30;
+	p_ctx->rr[7] = 0x30;
+
+	/*Initilize branch register 0*/
+	p_ctx->br[0] = *(unsigned long *)kvm_vmm_info->vmm_entry;
+
+	vcpu->arch.vmm_rr = kvm->arch.vmm_init_rr;
+	vcpu->arch.metaphysical_rr0 = kvm->arch.metaphysical_rr0;
+	vcpu->arch.metaphysical_rr4 = kvm->arch.metaphysical_rr4;
+
+	hrtimer_init(&vcpu->arch.hlt_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	vcpu->arch.hlt_timer.function = hlt_timer_fn;
+
+	vcpu->arch.last_run_cpu = -1;
+	vcpu->arch.vpd = (struct vpd *)VPD_ADDR(vcpu->vcpu_id);
+	vcpu->arch.vsa_base = kvm_vsa_base;
+	vcpu->arch.__gp = kvm_vmm_gp;
+	vcpu->arch.dirty_log_lock_pa = __pa(&kvm->arch.dirty_log_lock);
+	vcpu->arch.vhpt.hash = (struct thash_data *)VHPT_ADDR(vcpu->vcpu_id);
+	vcpu->arch.vtlb.hash = (struct thash_data *)VTLB_ADDR(vcpu->vcpu_id);
+	init_ptce_info(vcpu);
+
+	r = 0;
+out:
+	return r;
+}
+
+static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id)
+{
+	unsigned long psr;
+	int r;
+
+	local_irq_save(psr);
+	r = kvm_insert_vmm_mapping(vcpu);
+	if (r)
+		goto fail;
+	r = kvm_vcpu_init(vcpu, vcpu->kvm, id);
+	if (r)
+		goto fail;
+
+	r = vti_init_vpd(vcpu);
+	if (r) {
+		printk(KERN_DEBUG"kvm: vpd init error!!\n");
+		goto uninit;
+	}
+
+	r = vti_create_vp(vcpu);
+	if (r)
+		goto uninit;
+
+	kvm_purge_vmm_mapping(vcpu);
+	local_irq_restore(psr);
+
+	return 0;
+uninit:
+	kvm_vcpu_uninit(vcpu);
+fail:
+	return r;
+}
+
+struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
+		unsigned int id)
+{
+	struct kvm_vcpu *vcpu;
+	unsigned long vm_base = kvm->arch.vm_base;
+	int r;
+	int cpu;
+
+	r = -ENOMEM;
+	if (!vm_base) {
+		printk(KERN_ERR"kvm: Create vcpu[%d] error!\n", id);
+		goto fail;
+	}
+	vcpu = (struct kvm_vcpu *)(vm_base + KVM_VCPU_OFS + VCPU_SIZE * id);
+	vcpu->kvm = kvm;
+
+	cpu = get_cpu();
+	vti_vcpu_load(vcpu, cpu);
+	r = vti_vcpu_setup(vcpu, id);
+	put_cpu();
+
+	if (r) {
+		printk(KERN_DEBUG"kvm: vcpu_setup error!!\n");
+		goto fail;
+	}
+
+	return vcpu;
+fail:
+	return ERR_PTR(r);
+}
+
+int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
+		struct kvm_debug_guest *dbg)
+{
+	return -EINVAL;
+}
+
+static void free_kvm(struct kvm *kvm)
+{
+	unsigned long vm_base = kvm->arch.vm_base;
+
+	if (vm_base) {
+		memset((void *)vm_base, 0, KVM_VM_DATA_SIZE);
+		free_pages(vm_base, get_order(KVM_VM_DATA_SIZE));
+	}
+
+}
+
+static void kvm_release_vm_pages(struct kvm *kvm)
+{
+	struct kvm_memory_slot *memslot;
+	int i, j;
+	unsigned long base_gfn;
+
+	for (i = 0; i < kvm->nmemslots; i++) {
+		memslot = &kvm->memslots[i];
+		base_gfn = memslot->base_gfn;
+
+		for (j = 0; j < memslot->npages; j++) {
+			if (memslot->rmap[j])
+				put_page((struct page *)memslot->rmap[j]);
+		}
+	}
+}
+
+void kvm_arch_destroy_vm(struct kvm *kvm)
+{
+	kfree(kvm->arch.vioapic);
+	kvm_release_vm_pages(kvm);
+	kvm_free_physmem(kvm);
+	free_kvm(kvm);
+}
+
+void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
+{
+}
+
+void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	if (cpu != vcpu->cpu) {
+		vcpu->cpu = cpu;
+		if (vcpu->arch.ht_active)
+			kvm_migrate_hlt_timer(vcpu);
+	}
+}
+
+#define SAVE_REGS(_x) 	regs->_x = vcpu->arch._x
+
+int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+	int i;
+	int r;
+	struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+	vcpu_load(vcpu);
+
+	for (i = 0; i < 16; i++) {
+		regs->vpd.vgr[i] = vpd->vgr[i];
+		regs->vpd.vbgr[i] = vpd->vbgr[i];
+	}
+	for (i = 0; i < 128; i++)
+		regs->vpd.vcr[i] = vpd->vcr[i];
+	regs->vpd.vhpi = vpd->vhpi;
+	regs->vpd.vnat = vpd->vnat;
+	regs->vpd.vbnat = vpd->vbnat;
+	regs->vpd.vpsr = vpd->vpsr;
+	regs->vpd.vpr = vpd->vpr;
+
+	r = -EFAULT;
+	r = copy_to_user(regs->saved_guest, &vcpu->arch.guest,
+					sizeof(union context));
+	if (r)
+		goto out;
+	r = copy_to_user(regs->saved_stack, (void *)vcpu, IA64_STK_OFFSET);
+	if (r)
+		goto out;
+	SAVE_REGS(mp_state);
+	SAVE_REGS(vmm_rr);
+	memcpy(regs->itrs, vcpu->arch.itrs, sizeof(struct thash_data) * NITRS);
+	memcpy(regs->dtrs, vcpu->arch.dtrs, sizeof(struct thash_data) * NDTRS);
+	SAVE_REGS(itr_regions);
+	SAVE_REGS(dtr_regions);
+	SAVE_REGS(tc_regions);
+	SAVE_REGS(irq_check);
+	SAVE_REGS(itc_check);
+	SAVE_REGS(timer_check);
+	SAVE_REGS(timer_pending);
+	SAVE_REGS(last_itc);
+	for (i = 0; i < 8; i++) {
+		regs->vrr[i] = vcpu->arch.vrr[i];
+		regs->ibr[i] = vcpu->arch.ibr[i];
+		regs->dbr[i] = vcpu->arch.dbr[i];
+	}
+	for (i = 0; i < 4; i++)
+		regs->insvc[i] = vcpu->arch.insvc[i];
+	regs->saved_itc = vcpu->arch.itc_offset + ia64_getreg(_IA64_REG_AR_ITC);
+	SAVE_REGS(xtp);
+	SAVE_REGS(metaphysical_rr0);
+	SAVE_REGS(metaphysical_rr4);
+	SAVE_REGS(metaphysical_saved_rr0);
+	SAVE_REGS(metaphysical_saved_rr4);
+	SAVE_REGS(fp_psr);
+	SAVE_REGS(saved_gp);
+	vcpu_put(vcpu);
+	r = 0;
+out:
+	return r;
+}
+
+void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+
+	hrtimer_cancel(&vcpu->arch.hlt_timer);
+	kfree(vcpu->arch.apic);
+}
+
+
+long kvm_arch_vcpu_ioctl(struct file *filp,
+		unsigned int ioctl, unsigned long arg)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_set_memory_region(struct kvm *kvm,
+		struct kvm_userspace_memory_region *mem,
+		struct kvm_memory_slot old,
+		int user_alloc)
+{
+	unsigned long i;
+	struct page *page;
+	int npages = mem->memory_size >> PAGE_SHIFT;
+	struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot];
+	unsigned long base_gfn = memslot->base_gfn;
+
+	for (i = 0; i < npages; i++) {
+		page = gfn_to_page(kvm, base_gfn + i);
+		kvm_set_pmt_entry(kvm, base_gfn + i,
+				page_to_pfn(page) << PAGE_SHIFT,
+				_PAGE_AR_RWX|_PAGE_MA_WB);
+		memslot->rmap[i] = (unsigned long)page;
+	}
+
+	return 0;
+}
+
+
+long kvm_arch_dev_ioctl(struct file *filp,
+		unsigned int ioctl, unsigned long arg)
+{
+	return -EINVAL;
+}
+
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	kvm_vcpu_uninit(vcpu);
+}
+
+static int vti_cpu_has_kvm_support(void)
+{
+	long  avail = 1, status = 1, control = 1;
+	long ret;
+
+	ret = ia64_pal_proc_get_features(&avail, &status, &control, 0);
+	if (ret)
+		goto out;
+
+	if (!(avail & PAL_PROC_VM_BIT))
+		goto out;
+
+	printk(KERN_DEBUG"kvm: Hardware Supports VT\n");
+
+	ret = ia64_pal_vp_env_info(&kvm_vm_buffer_size, &vp_env_info);
+	if (ret)
+		goto out;
+	printk(KERN_DEBUG"kvm: VM Buffer Size:0x%lx\n", kvm_vm_buffer_size);
+
+	if (!(vp_env_info & VP_OPCODE)) {
+		printk(KERN_WARNING"kvm: No opcode ability on hardware, "
+				"vm_env_info:0x%lx\n", vp_env_info);
+	}
+
+	return 1;
+out:
+	return 0;
+}
+
+static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info,
+						struct module *module)
+{
+	unsigned long module_base;
+	unsigned long vmm_size;
+
+	unsigned long vmm_offset, func_offset, fdesc_offset;
+	struct fdesc *p_fdesc;
+
+	BUG_ON(!module);
+
+	if (!kvm_vmm_base) {
+		printk("kvm: kvm area hasn't been initilized yet!!\n");
+		return -EFAULT;
+	}
+
+	/*Calculate new position of relocated vmm module.*/
+	module_base = (unsigned long)module->module_core;
+	vmm_size = module->core_size;
+	if (unlikely(vmm_size > KVM_VMM_SIZE))
+		return -EFAULT;
+
+	memcpy((void *)kvm_vmm_base, (void *)module_base, vmm_size);
+	kvm_flush_icache(kvm_vmm_base, vmm_size);
+
+	/*Recalculate kvm_vmm_info based on new VMM*/
+	vmm_offset = vmm_info->vmm_ivt - module_base;
+	kvm_vmm_info->vmm_ivt = KVM_VMM_BASE + vmm_offset;
+	printk(KERN_DEBUG"kvm: Relocated VMM's IVT Base Addr:%lx\n",
+			kvm_vmm_info->vmm_ivt);
+
+	fdesc_offset = (unsigned long)vmm_info->vmm_entry - module_base;
+	kvm_vmm_info->vmm_entry = (kvm_vmm_entry *)(KVM_VMM_BASE +
+							fdesc_offset);
+	func_offset = *(unsigned long *)vmm_info->vmm_entry - module_base;
+	p_fdesc = (struct fdesc *)(kvm_vmm_base + fdesc_offset);
+	p_fdesc->ip = KVM_VMM_BASE + func_offset;
+	p_fdesc->gp = KVM_VMM_BASE+(p_fdesc->gp - module_base);
+
+	printk(KERN_DEBUG"kvm: Relocated VMM's Init Entry Addr:%lx\n",
+			KVM_VMM_BASE+func_offset);
+
+	fdesc_offset = (unsigned long)vmm_info->tramp_entry - module_base;
+	kvm_vmm_info->tramp_entry = (kvm_tramp_entry *)(KVM_VMM_BASE +
+			fdesc_offset);
+	func_offset = *(unsigned long *)vmm_info->tramp_entry - module_base;
+	p_fdesc = (struct fdesc *)(kvm_vmm_base + fdesc_offset);
+	p_fdesc->ip = KVM_VMM_BASE + func_offset;
+	p_fdesc->gp = KVM_VMM_BASE + (p_fdesc->gp - module_base);
+
+	kvm_vmm_gp = p_fdesc->gp;
+
+	printk(KERN_DEBUG"kvm: Relocated VMM's Entry IP:%p\n",
+						kvm_vmm_info->vmm_entry);
+	printk(KERN_DEBUG"kvm: Relocated VMM's Trampoline Entry IP:0x%lx\n",
+						KVM_VMM_BASE + func_offset);
+
+	return 0;
+}
+
+int kvm_arch_init(void *opaque)
+{
+	int r;
+	struct kvm_vmm_info *vmm_info = (struct kvm_vmm_info *)opaque;
+
+	if (!vti_cpu_has_kvm_support()) {
+		printk(KERN_ERR "kvm: No Hardware Virtualization Support!\n");
+		r = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (kvm_vmm_info) {
+		printk(KERN_ERR "kvm: Already loaded VMM module!\n");
+		r = -EEXIST;
+		goto out;
+	}
+
+	r = -ENOMEM;
+	kvm_vmm_info = kzalloc(sizeof(struct kvm_vmm_info), GFP_KERNEL);
+	if (!kvm_vmm_info)
+		goto out;
+
+	if (kvm_alloc_vmm_area())
+		goto out_free0;
+
+	r = kvm_relocate_vmm(vmm_info, vmm_info->module);
+	if (r)
+		goto out_free1;
+
+	return 0;
+
+out_free1:
+	kvm_free_vmm_area();
+out_free0:
+	kfree(kvm_vmm_info);
+out:
+	return r;
+}
+
+void kvm_arch_exit(void)
+{
+	kvm_free_vmm_area();
+	kfree(kvm_vmm_info);
+	kvm_vmm_info = NULL;
+}
+
+static int kvm_ia64_sync_dirty_log(struct kvm *kvm,
+		struct kvm_dirty_log *log)
+{
+	struct kvm_memory_slot *memslot;
+	int r, i;
+	long n, base;
+	unsigned long *dirty_bitmap = (unsigned long *)((void *)kvm - KVM_VM_OFS
+					+ KVM_MEM_DIRTY_LOG_OFS);
+
+	r = -EINVAL;
+	if (log->slot >= KVM_MEMORY_SLOTS)
+		goto out;
+
+	memslot = &kvm->memslots[log->slot];
+	r = -ENOENT;
+	if (!memslot->dirty_bitmap)
+		goto out;
+
+	n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+	base = memslot->base_gfn / BITS_PER_LONG;
+
+	for (i = 0; i < n/sizeof(long); ++i) {
+		memslot->dirty_bitmap[i] = dirty_bitmap[base + i];
+		dirty_bitmap[base + i] = 0;
+	}
+	r = 0;
+out:
+	return r;
+}
+
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
+		struct kvm_dirty_log *log)
+{
+	int r;
+	int n;
+	struct kvm_memory_slot *memslot;
+	int is_dirty = 0;
+
+	spin_lock(&kvm->arch.dirty_log_lock);
+
+	r = kvm_ia64_sync_dirty_log(kvm, log);
+	if (r)
+		goto out;
+
+	r = kvm_get_dirty_log(kvm, log, &is_dirty);
+	if (r)
+		goto out;
+
+	/* If nothing is dirty, don't bother messing with page tables. */
+	if (is_dirty) {
+		kvm_flush_remote_tlbs(kvm);
+		memslot = &kvm->memslots[log->slot];
+		n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+		memset(memslot->dirty_bitmap, 0, n);
+	}
+	r = 0;
+out:
+	spin_unlock(&kvm->arch.dirty_log_lock);
+	return r;
+}
+
+int kvm_arch_hardware_setup(void)
+{
+	return 0;
+}
+
+void kvm_arch_hardware_unsetup(void)
+{
+}
+
+static void vcpu_kick_intr(void *info)
+{
+#ifdef DEBUG
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)info;
+	printk(KERN_DEBUG"vcpu_kick_intr %p \n", vcpu);
+#endif
+}
+
+void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
+{
+	int ipi_pcpu = vcpu->cpu;
+
+	if (waitqueue_active(&vcpu->wq))
+		wake_up_interruptible(&vcpu->wq);
+
+	if (vcpu->guest_mode)
+		smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0, 0);
+}
+
+int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig)
+{
+
+	struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+
+	if (!test_and_set_bit(vec, &vpd->irr[0])) {
+		vcpu->arch.irq_new_pending = 1;
+		 if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
+			kvm_vcpu_kick(vcpu);
+		else if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) {
+			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+			if (waitqueue_active(&vcpu->wq))
+				wake_up_interruptible(&vcpu->wq);
+		}
+		return 1;
+	}
+	return 0;
+}
+
+int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest)
+{
+	return apic->vcpu->vcpu_id == dest;
+}
+
+int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
+{
+	return 0;
+}
+
+struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector,
+				       unsigned long bitmap)
+{
+	struct kvm_vcpu *lvcpu = kvm->vcpus[0];
+	int i;
+
+	for (i = 1; i < KVM_MAX_VCPUS; i++) {
+		if (!kvm->vcpus[i])
+			continue;
+		if (lvcpu->arch.xtp > kvm->vcpus[i]->arch.xtp)
+			lvcpu = kvm->vcpus[i];
+	}
+
+	return lvcpu;
+}
+
+static int find_highest_bits(int *dat)
+{
+	u32  bits, bitnum;
+	int i;
+
+	/* loop for all 256 bits */
+	for (i = 7; i >= 0 ; i--) {
+		bits = dat[i];
+		if (bits) {
+			bitnum = fls(bits);
+			return i * 32 + bitnum - 1;
+		}
+	}
+
+	return -1;
+}
+
+int kvm_highest_pending_irq(struct kvm_vcpu *vcpu)
+{
+    struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+
+    if (vpd->irr[0] & (1UL << NMI_VECTOR))
+		return NMI_VECTOR;
+    if (vpd->irr[0] & (1UL << ExtINT_VECTOR))
+		return ExtINT_VECTOR;
+
+    return find_highest_bits((int *)&vpd->irr[0]);
+}
+
+int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
+{
+	if (kvm_highest_pending_irq(vcpu) != -1)
+		return 1;
+	return 0;
+}
+
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
+{
+	return gfn;
+}
+
+int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE;
+}
+
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state)
+{
+	return -EINVAL;
+}
diff --git a/trunk/arch/ia64/kvm/kvm_fw.c b/trunk/arch/ia64/kvm/kvm_fw.c
new file mode 100644
index 000000000000..091f936c4485
--- /dev/null
+++ b/trunk/arch/ia64/kvm/kvm_fw.c
@@ -0,0 +1,500 @@
+/*
+ * PAL/SAL call delegation
+ *
+ * Copyright (c) 2004 Li Susie <susie.li@intel.com>
+ * Copyright (c) 2005 Yu Ke <ke.yu@intel.com>
+ * Copyright (c) 2007 Xiantao Zhang <xiantao.zhang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/smp.h>
+
+#include "vti.h"
+#include "misc.h"
+
+#include <asm/pal.h>
+#include <asm/sal.h>
+#include <asm/tlb.h>
+
+/*
+ * Handy macros to make sure that the PAL return values start out
+ * as something meaningful.
+ */
+#define INIT_PAL_STATUS_UNIMPLEMENTED(x)		\
+	{						\
+		x.status = PAL_STATUS_UNIMPLEMENTED;	\
+		x.v0 = 0;				\
+		x.v1 = 0;				\
+		x.v2 = 0;				\
+	}
+
+#define INIT_PAL_STATUS_SUCCESS(x)			\
+	{						\
+		x.status = PAL_STATUS_SUCCESS;		\
+		x.v0 = 0;				\
+		x.v1 = 0;				\
+		x.v2 = 0;				\
+    }
+
+static void kvm_get_pal_call_data(struct kvm_vcpu *vcpu,
+		u64 *gr28, u64 *gr29, u64 *gr30, u64 *gr31) {
+	struct exit_ctl_data *p;
+
+	if (vcpu) {
+		p = &vcpu->arch.exit_data;
+		if (p->exit_reason == EXIT_REASON_PAL_CALL) {
+			*gr28 = p->u.pal_data.gr28;
+			*gr29 = p->u.pal_data.gr29;
+			*gr30 = p->u.pal_data.gr30;
+			*gr31 = p->u.pal_data.gr31;
+			return ;
+		}
+	}
+	printk(KERN_DEBUG"Failed to get vcpu pal data!!!\n");
+}
+
+static void set_pal_result(struct kvm_vcpu *vcpu,
+		struct ia64_pal_retval result) {
+
+	struct exit_ctl_data *p;
+
+	p = kvm_get_exit_data(vcpu);
+	if (p && p->exit_reason == EXIT_REASON_PAL_CALL) {
+		p->u.pal_data.ret = result;
+		return ;
+	}
+	INIT_PAL_STATUS_UNIMPLEMENTED(p->u.pal_data.ret);
+}
+
+static void set_sal_result(struct kvm_vcpu *vcpu,
+		struct sal_ret_values result) {
+	struct exit_ctl_data *p;
+
+	p = kvm_get_exit_data(vcpu);
+	if (p && p->exit_reason == EXIT_REASON_SAL_CALL) {
+		p->u.sal_data.ret = result;
+		return ;
+	}
+	printk(KERN_WARNING"Failed to set sal result!!\n");
+}
+
+struct cache_flush_args {
+	u64 cache_type;
+	u64 operation;
+	u64 progress;
+	long status;
+};
+
+cpumask_t cpu_cache_coherent_map;
+
+static void remote_pal_cache_flush(void *data)
+{
+	struct cache_flush_args *args = data;
+	long status;
+	u64 progress = args->progress;
+
+	status = ia64_pal_cache_flush(args->cache_type, args->operation,
+					&progress, NULL);
+	if (status != 0)
+	args->status = status;
+}
+
+static struct ia64_pal_retval pal_cache_flush(struct kvm_vcpu *vcpu)
+{
+	u64 gr28, gr29, gr30, gr31;
+	struct ia64_pal_retval result = {0, 0, 0, 0};
+	struct cache_flush_args args = {0, 0, 0, 0};
+	long psr;
+
+	gr28 = gr29 = gr30 = gr31 = 0;
+	kvm_get_pal_call_data(vcpu, &gr28, &gr29, &gr30, &gr31);
+
+	if (gr31 != 0)
+		printk(KERN_ERR"vcpu:%p called cache_flush error!\n", vcpu);
+
+	/* Always call Host Pal in int=1 */
+	gr30 &= ~PAL_CACHE_FLUSH_CHK_INTRS;
+	args.cache_type = gr29;
+	args.operation = gr30;
+	smp_call_function(remote_pal_cache_flush,
+				(void *)&args, 1, 1);
+	if (args.status != 0)
+		printk(KERN_ERR"pal_cache_flush error!,"
+				"status:0x%lx\n", args.status);
+	/*
+	 * Call Host PAL cache flush
+	 * Clear psr.ic when call PAL_CACHE_FLUSH
+	 */
+	local_irq_save(psr);
+	result.status = ia64_pal_cache_flush(gr29, gr30, &result.v1,
+						&result.v0);
+	local_irq_restore(psr);
+	if (result.status != 0)
+		printk(KERN_ERR"vcpu:%p crashed due to cache_flush err:%ld"
+				"in1:%lx,in2:%lx\n",
+				vcpu, result.status, gr29, gr30);
+
+#if 0
+	if (gr29 == PAL_CACHE_TYPE_COHERENT) {
+		cpus_setall(vcpu->arch.cache_coherent_map);
+		cpu_clear(vcpu->cpu, vcpu->arch.cache_coherent_map);
+		cpus_setall(cpu_cache_coherent_map);
+		cpu_clear(vcpu->cpu, cpu_cache_coherent_map);
+	}
+#endif
+	return result;
+}
+
+struct ia64_pal_retval pal_cache_summary(struct kvm_vcpu *vcpu)
+{
+
+	struct ia64_pal_retval result;
+
+	PAL_CALL(result, PAL_CACHE_SUMMARY, 0, 0, 0);
+	return result;
+}
+
+static struct ia64_pal_retval pal_freq_base(struct kvm_vcpu *vcpu)
+{
+
+	struct ia64_pal_retval result;
+
+	PAL_CALL(result, PAL_FREQ_BASE, 0, 0, 0);
+
+	/*
+	 * PAL_FREQ_BASE may not be implemented in some platforms,
+	 * call SAL instead.
+	 */
+	if (result.v0 == 0) {
+		result.status = ia64_sal_freq_base(SAL_FREQ_BASE_PLATFORM,
+							&result.v0,
+							&result.v1);
+		result.v2 = 0;
+	}
+
+	return result;
+}
+
+static struct ia64_pal_retval pal_freq_ratios(struct kvm_vcpu *vcpu)
+{
+
+	struct ia64_pal_retval result;
+
+	PAL_CALL(result, PAL_FREQ_RATIOS, 0, 0, 0);
+	return result;
+}
+
+static struct ia64_pal_retval pal_logical_to_physica(struct kvm_vcpu *vcpu)
+{
+	struct ia64_pal_retval result;
+
+	INIT_PAL_STATUS_UNIMPLEMENTED(result);
+	return result;
+}
+
+static struct ia64_pal_retval pal_platform_addr(struct kvm_vcpu *vcpu)
+{
+
+	struct ia64_pal_retval result;
+
+	INIT_PAL_STATUS_SUCCESS(result);
+	return result;
+}
+
+static struct ia64_pal_retval pal_proc_get_features(struct kvm_vcpu *vcpu)
+{
+
+	struct ia64_pal_retval result = {0, 0, 0, 0};
+	long in0, in1, in2, in3;
+
+	kvm_get_pal_call_data(vcpu, &in0, &in1, &in2, &in3);
+	result.status = ia64_pal_proc_get_features(&result.v0, &result.v1,
+			&result.v2, in2);
+
+	return result;
+}
+
+static struct ia64_pal_retval pal_cache_info(struct kvm_vcpu *vcpu)
+{
+
+	pal_cache_config_info_t ci;
+	long status;
+	unsigned long in0, in1, in2, in3, r9, r10;
+
+	kvm_get_pal_call_data(vcpu, &in0, &in1, &in2, &in3);
+	status = ia64_pal_cache_config_info(in1, in2, &ci);
+	r9 = ci.pcci_info_1.pcci1_data;
+	r10 = ci.pcci_info_2.pcci2_data;
+	return ((struct ia64_pal_retval){status, r9, r10, 0});
+}
+
+#define GUEST_IMPL_VA_MSB	59
+#define GUEST_RID_BITS		18
+
+static struct ia64_pal_retval pal_vm_summary(struct kvm_vcpu *vcpu)
+{
+
+	pal_vm_info_1_u_t vminfo1;
+	pal_vm_info_2_u_t vminfo2;
+	struct ia64_pal_retval result;
+
+	PAL_CALL(result, PAL_VM_SUMMARY, 0, 0, 0);
+	if (!result.status) {
+		vminfo1.pvi1_val = result.v0;
+		vminfo1.pal_vm_info_1_s.max_itr_entry = 8;
+		vminfo1.pal_vm_info_1_s.max_dtr_entry = 8;
+		result.v0 = vminfo1.pvi1_val;
+		vminfo2.pal_vm_info_2_s.impl_va_msb = GUEST_IMPL_VA_MSB;
+		vminfo2.pal_vm_info_2_s.rid_size = GUEST_RID_BITS;
+		result.v1 = vminfo2.pvi2_val;
+	}
+
+	return result;
+}
+
+static struct ia64_pal_retval pal_vm_info(struct kvm_vcpu *vcpu)
+{
+	struct ia64_pal_retval result;
+
+	INIT_PAL_STATUS_UNIMPLEMENTED(result);
+
+	return result;
+}
+
+static  u64 kvm_get_pal_call_index(struct kvm_vcpu *vcpu)
+{
+	u64 index = 0;
+	struct exit_ctl_data *p;
+
+	p = kvm_get_exit_data(vcpu);
+	if (p && (p->exit_reason == EXIT_REASON_PAL_CALL))
+		index = p->u.pal_data.gr28;
+
+	return index;
+}
+
+int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+
+	u64 gr28;
+	struct ia64_pal_retval result;
+	int ret = 1;
+
+	gr28 = kvm_get_pal_call_index(vcpu);
+	/*printk("pal_call index:%lx\n",gr28);*/
+	switch (gr28) {
+	case PAL_CACHE_FLUSH:
+		result = pal_cache_flush(vcpu);
+		break;
+	case PAL_CACHE_SUMMARY:
+		result = pal_cache_summary(vcpu);
+		break;
+	case PAL_HALT_LIGHT:
+	{
+		vcpu->arch.timer_pending = 1;
+		INIT_PAL_STATUS_SUCCESS(result);
+		if (kvm_highest_pending_irq(vcpu) == -1)
+			ret = kvm_emulate_halt(vcpu);
+
+	}
+		break;
+
+	case PAL_FREQ_RATIOS:
+		result = pal_freq_ratios(vcpu);
+		break;
+
+	case PAL_FREQ_BASE:
+		result = pal_freq_base(vcpu);
+		break;
+
+	case PAL_LOGICAL_TO_PHYSICAL :
+		result = pal_logical_to_physica(vcpu);
+		break;
+
+	case PAL_VM_SUMMARY :
+		result = pal_vm_summary(vcpu);
+		break;
+
+	case PAL_VM_INFO :
+		result = pal_vm_info(vcpu);
+		break;
+	case PAL_PLATFORM_ADDR :
+		result = pal_platform_addr(vcpu);
+		break;
+	case PAL_CACHE_INFO:
+		result = pal_cache_info(vcpu);
+		break;
+	case PAL_PTCE_INFO:
+		INIT_PAL_STATUS_SUCCESS(result);
+		result.v1 = (1L << 32) | 1L;
+		break;
+	case PAL_VM_PAGE_SIZE:
+		result.status = ia64_pal_vm_page_size(&result.v0,
+							&result.v1);
+		break;
+	case PAL_RSE_INFO:
+		result.status = ia64_pal_rse_info(&result.v0,
+					(pal_hints_u_t *)&result.v1);
+		break;
+	case PAL_PROC_GET_FEATURES:
+		result = pal_proc_get_features(vcpu);
+		break;
+	case PAL_DEBUG_INFO:
+		result.status = ia64_pal_debug_info(&result.v0,
+							&result.v1);
+		break;
+	case PAL_VERSION:
+		result.status = ia64_pal_version(
+				(pal_version_u_t *)&result.v0,
+				(pal_version_u_t *)&result.v1);
+
+		break;
+	case PAL_FIXED_ADDR:
+		result.status = PAL_STATUS_SUCCESS;
+		result.v0 = vcpu->vcpu_id;
+		break;
+	default:
+		INIT_PAL_STATUS_UNIMPLEMENTED(result);
+		printk(KERN_WARNING"kvm: Unsupported pal call,"
+					" index:0x%lx\n", gr28);
+	}
+	set_pal_result(vcpu, result);
+	return ret;
+}
+
+static struct sal_ret_values sal_emulator(struct kvm *kvm,
+				long index, unsigned long in1,
+				unsigned long in2, unsigned long in3,
+				unsigned long in4, unsigned long in5,
+				unsigned long in6, unsigned long in7)
+{
+	unsigned long r9  = 0;
+	unsigned long r10 = 0;
+	long r11 = 0;
+	long status;
+
+	status = 0;
+	switch (index) {
+	case SAL_FREQ_BASE:
+		status = ia64_sal_freq_base(in1, &r9, &r10);
+		break;
+	case SAL_PCI_CONFIG_READ:
+		printk(KERN_WARNING"kvm: Not allowed to call here!"
+			" SAL_PCI_CONFIG_READ\n");
+		break;
+	case SAL_PCI_CONFIG_WRITE:
+		printk(KERN_WARNING"kvm: Not allowed to call here!"
+			" SAL_PCI_CONFIG_WRITE\n");
+		break;
+	case SAL_SET_VECTORS:
+		if (in1 == SAL_VECTOR_OS_BOOT_RENDEZ) {
+			if (in4 != 0 || in5 != 0 || in6 != 0 || in7 != 0) {
+				status = -2;
+			} else {
+				kvm->arch.rdv_sal_data.boot_ip = in2;
+				kvm->arch.rdv_sal_data.boot_gp = in3;
+			}
+			printk("Rendvous called! iip:%lx\n\n", in2);
+		} else
+			printk(KERN_WARNING"kvm: CALLED SAL_SET_VECTORS %lu."
+							"ignored...\n", in1);
+		break;
+	case SAL_GET_STATE_INFO:
+		/* No more info.  */
+		status = -5;
+		r9 = 0;
+		break;
+	case SAL_GET_STATE_INFO_SIZE:
+		/* Return a dummy size.  */
+		status = 0;
+		r9 = 128;
+		break;
+	case SAL_CLEAR_STATE_INFO:
+		/* Noop.  */
+		break;
+	case SAL_MC_RENDEZ:
+		printk(KERN_WARNING
+			"kvm: called SAL_MC_RENDEZ. ignored...\n");
+		break;
+	case SAL_MC_SET_PARAMS:
+		printk(KERN_WARNING
+			"kvm: called  SAL_MC_SET_PARAMS.ignored!\n");
+		break;
+	case SAL_CACHE_FLUSH:
+		if (1) {
+			/*Flush using SAL.
+			This method is faster but has a side
+			effect on other vcpu running on
+			this cpu.  */
+			status = ia64_sal_cache_flush(in1);
+		} else {
+			/*Maybe need to implement the method
+			without side effect!*/
+			status = 0;
+		}
+		break;
+	case SAL_CACHE_INIT:
+		printk(KERN_WARNING
+			"kvm: called SAL_CACHE_INIT.  ignored...\n");
+		break;
+	case SAL_UPDATE_PAL:
+		printk(KERN_WARNING
+			"kvm: CALLED SAL_UPDATE_PAL.  ignored...\n");
+		break;
+	default:
+		printk(KERN_WARNING"kvm: called SAL_CALL with unknown index."
+						" index:%ld\n", index);
+		status = -1;
+		break;
+	}
+	return ((struct sal_ret_values) {status, r9, r10, r11});
+}
+
+static void kvm_get_sal_call_data(struct kvm_vcpu *vcpu, u64 *in0, u64 *in1,
+		u64 *in2, u64 *in3, u64 *in4, u64 *in5, u64 *in6, u64 *in7){
+
+	struct exit_ctl_data *p;
+
+	p = kvm_get_exit_data(vcpu);
+
+	if (p) {
+		if (p->exit_reason == EXIT_REASON_SAL_CALL) {
+			*in0 = p->u.sal_data.in0;
+			*in1 = p->u.sal_data.in1;
+			*in2 = p->u.sal_data.in2;
+			*in3 = p->u.sal_data.in3;
+			*in4 = p->u.sal_data.in4;
+			*in5 = p->u.sal_data.in5;
+			*in6 = p->u.sal_data.in6;
+			*in7 = p->u.sal_data.in7;
+			return ;
+		}
+	}
+	*in0 = 0;
+}
+
+void kvm_sal_emul(struct kvm_vcpu *vcpu)
+{
+
+	struct sal_ret_values result;
+	u64 index, in1, in2, in3, in4, in5, in6, in7;
+
+	kvm_get_sal_call_data(vcpu, &index, &in1, &in2,
+			&in3, &in4, &in5, &in6, &in7);
+	result = sal_emulator(vcpu->kvm, index, in1, in2, in3,
+					in4, in5, in6, in7);
+	set_sal_result(vcpu, result);
+}
diff --git a/trunk/arch/ia64/kvm/kvm_minstate.h b/trunk/arch/ia64/kvm/kvm_minstate.h
new file mode 100644
index 000000000000..13980d9b8bcf
--- /dev/null
+++ b/trunk/arch/ia64/kvm/kvm_minstate.h
@@ -0,0 +1,273 @@
+/*
+ *  kvm_minstate.h: min save macros
+ *  Copyright (c) 2007, Intel Corporation.
+ *
+ *  Xuefei Xu (Anthony Xu) (Anthony.xu@intel.com)
+ *  Xiantao Zhang (xiantao.zhang@intel.com)
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+
+
+#include <asm/asmmacro.h>
+#include <asm/types.h>
+#include <asm/kregs.h>
+#include "asm-offsets.h"
+
+#define KVM_MINSTATE_START_SAVE_MIN	     					\
+	mov ar.rsc = 0;/* set enforced lazy mode, pl 0, little-endian, loadrs=0 */\
+	;;									\
+	mov.m r28 = ar.rnat;                                  			\
+	addl r22 = VMM_RBS_OFFSET,r1;            /* compute base of RBS */	\
+	;;									\
+	lfetch.fault.excl.nt1 [r22];						\
+	addl r1 = IA64_STK_OFFSET-VMM_PT_REGS_SIZE,r1;  /* compute base of memory stack */  \
+	mov r23 = ar.bspstore;			/* save ar.bspstore */          \
+	;;									\
+	mov ar.bspstore = r22;				/* switch to kernel RBS */\
+	;;									\
+	mov r18 = ar.bsp;							\
+	mov ar.rsc = 0x3;     /* set eager mode, pl 0, little-endian, loadrs=0 */
+
+
+
+#define KVM_MINSTATE_END_SAVE_MIN						\
+	bsw.1;          /* switch back to bank 1 (must be last in insn group) */\
+	;;
+
+
+#define PAL_VSA_SYNC_READ						\
+	/* begin to call pal vps sync_read */				\
+	add r25 = VMM_VPD_BASE_OFFSET, r21;				\
+	adds r20 = VMM_VCPU_VSA_BASE_OFFSET, r21;  /* entry point */	\
+	;;								\
+	ld8 r25 = [r25];      /* read vpd base */			\
+	ld8 r20 = [r20];						\
+	;;								\
+	add r20 = PAL_VPS_SYNC_READ,r20;				\
+	;;								\
+{ .mii;									\
+	nop 0x0;							\
+	mov r24 = ip;							\
+	mov b0 = r20;							\
+	;;								\
+};									\
+{ .mmb;									\
+	add r24 = 0x20, r24;						\
+	nop 0x0;							\
+	br.cond.sptk b0;        /*  call the service */			\
+	;;								\
+};
+
+
+
+#define KVM_MINSTATE_GET_CURRENT(reg)   mov reg=r21
+
+/*
+ * KVM_DO_SAVE_MIN switches to the kernel stacks (if necessary) and saves
+ * the minimum state necessary that allows us to turn psr.ic back
+ * on.
+ *
+ * Assumed state upon entry:
+ *  psr.ic: off
+ *  r31:	contains saved predicates (pr)
+ *
+ * Upon exit, the state is as follows:
+ *  psr.ic: off
+ *   r2 = points to &pt_regs.r16
+ *   r8 = contents of ar.ccv
+ *   r9 = contents of ar.csd
+ *  r10 = contents of ar.ssd
+ *  r11 = FPSR_DEFAULT
+ *  r12 = kernel sp (kernel virtual address)
+ *  r13 = points to current task_struct (kernel virtual address)
+ *  p15 = TRUE if psr.i is set in cr.ipsr
+ *  predicate registers (other than p2, p3, and p15), b6, r3, r14, r15:
+ *	  preserved
+ *
+ * Note that psr.ic is NOT turned on by this macro.  This is so that
+ * we can pass interruption state as arguments to a handler.
+ */
+
+
+#define PT(f) (VMM_PT_REGS_##f##_OFFSET)
+
+#define KVM_DO_SAVE_MIN(COVER,SAVE_IFS,EXTRA)			\
+	KVM_MINSTATE_GET_CURRENT(r16);  /* M (or M;;I) */	\
+	mov r27 = ar.rsc;         /* M */			\
+	mov r20 = r1;         /* A */				\
+	mov r25 = ar.unat;        /* M */			\
+	mov r29 = cr.ipsr;        /* M */			\
+	mov r26 = ar.pfs;         /* I */			\
+	mov r18 = cr.isr;         				\
+	COVER;              /* B;; (or nothing) */		\
+	;;							\
+	tbit.z p0,p15 = r29,IA64_PSR_I_BIT;			\
+	mov r1 = r16;						\
+/*	mov r21=r16;	*/					\
+	/* switch from user to kernel RBS: */			\
+	;;							\
+	invala;             /* M */				\
+	SAVE_IFS;						\
+	;;							\
+	KVM_MINSTATE_START_SAVE_MIN				\
+	adds r17 = 2*L1_CACHE_BYTES,r1;/* cache-line size */	\
+	adds r16 = PT(CR_IPSR),r1;				\
+	;;							\
+	lfetch.fault.excl.nt1 [r17],L1_CACHE_BYTES;		\
+	st8 [r16] = r29;      /* save cr.ipsr */		\
+	;;							\
+	lfetch.fault.excl.nt1 [r17];				\
+	tbit.nz p15,p0 = r29,IA64_PSR_I_BIT;			\
+	mov r29 = b0						\
+	;;							\
+	adds r16 = PT(R8),r1; /* initialize first base pointer */\
+	adds r17 = PT(R9),r1; /* initialize second base pointer */\
+	;;							\
+.mem.offset 0,0; st8.spill [r16] = r8,16;			\
+.mem.offset 8,0; st8.spill [r17] = r9,16;			\
+	;;							\
+.mem.offset 0,0; st8.spill [r16] = r10,24;			\
+.mem.offset 8,0; st8.spill [r17] = r11,24;			\
+	;;							\
+	mov r9 = cr.iip;         /* M */			\
+	mov r10 = ar.fpsr;        /* M */			\
+	;;							\
+	st8 [r16] = r9,16;    /* save cr.iip */			\
+	st8 [r17] = r30,16;   /* save cr.ifs */			\
+	sub r18 = r18,r22;    /* r18=RSE.ndirty*8 */		\
+	;;							\
+	st8 [r16] = r25,16;   /* save ar.unat */		\
+	st8 [r17] = r26,16;    /* save ar.pfs */		\
+	shl r18 = r18,16;     /* calu ar.rsc used for "loadrs" */\
+	;;							\
+	st8 [r16] = r27,16;   /* save ar.rsc */			\
+	st8 [r17] = r28,16;   /* save ar.rnat */		\
+	;;          /* avoid RAW on r16 & r17 */		\
+	st8 [r16] = r23,16;   /* save ar.bspstore */		\
+	st8 [r17] = r31,16;   /* save predicates */		\
+	;;							\
+	st8 [r16] = r29,16;   /* save b0 */			\
+	st8 [r17] = r18,16;   /* save ar.rsc value for "loadrs" */\
+	;;							\
+.mem.offset 0,0; st8.spill [r16] = r20,16;/* save original r1 */  \
+.mem.offset 8,0; st8.spill [r17] = r12,16;			\
+	adds r12 = -16,r1;    /* switch to kernel memory stack */  \
+	;;							\
+.mem.offset 0,0; st8.spill [r16] = r13,16;			\
+.mem.offset 8,0; st8.spill [r17] = r10,16;	/* save ar.fpsr */\
+	mov r13 = r21;   /* establish `current' */		\
+	;;							\
+.mem.offset 0,0; st8.spill [r16] = r15,16;			\
+.mem.offset 8,0; st8.spill [r17] = r14,16;			\
+	;;							\
+.mem.offset 0,0; st8.spill [r16] = r2,16;			\
+.mem.offset 8,0; st8.spill [r17] = r3,16;			\
+	adds r2 = VMM_PT_REGS_R16_OFFSET,r1;			\
+	 ;;							\
+	adds r16 = VMM_VCPU_IIPA_OFFSET,r13;			\
+	adds r17 = VMM_VCPU_ISR_OFFSET,r13;			\
+	mov r26 = cr.iipa;					\
+	mov r27 = cr.isr;					\
+	;;							\
+	st8 [r16] = r26;					\
+	st8 [r17] = r27;					\
+	;;							\
+	EXTRA;							\
+	mov r8 = ar.ccv;					\
+	mov r9 = ar.csd;					\
+	mov r10 = ar.ssd;					\
+	movl r11 = FPSR_DEFAULT;   /* L-unit */			\
+	adds r17 = VMM_VCPU_GP_OFFSET,r13;			\
+	;;							\
+	ld8 r1 = [r17];/* establish kernel global pointer */	\
+	;;							\
+	PAL_VSA_SYNC_READ					\
+	KVM_MINSTATE_END_SAVE_MIN
+
+/*
+ * SAVE_REST saves the remainder of pt_regs (with psr.ic on).
+ *
+ * Assumed state upon entry:
+ *  psr.ic: on
+ *  r2: points to &pt_regs.f6
+ *  r3: points to &pt_regs.f7
+ *  r8: contents of ar.ccv
+ *  r9: contents of ar.csd
+ *  r10:	contents of ar.ssd
+ *  r11:	FPSR_DEFAULT
+ *
+ * Registers r14 and r15 are guaranteed not to be touched by SAVE_REST.
+ */
+#define KVM_SAVE_REST				\
+.mem.offset 0,0; st8.spill [r2] = r16,16;	\
+.mem.offset 8,0; st8.spill [r3] = r17,16;	\
+	;;				\
+.mem.offset 0,0; st8.spill [r2] = r18,16;	\
+.mem.offset 8,0; st8.spill [r3] = r19,16;	\
+	;;				\
+.mem.offset 0,0; st8.spill [r2] = r20,16;	\
+.mem.offset 8,0; st8.spill [r3] = r21,16;	\
+	mov r18=b6;			\
+	;;				\
+.mem.offset 0,0; st8.spill [r2] = r22,16;	\
+.mem.offset 8,0; st8.spill [r3] = r23,16;	\
+	mov r19 = b7;				\
+	;;					\
+.mem.offset 0,0; st8.spill [r2] = r24,16;	\
+.mem.offset 8,0; st8.spill [r3] = r25,16;	\
+	;;					\
+.mem.offset 0,0; st8.spill [r2] = r26,16;	\
+.mem.offset 8,0; st8.spill [r3] = r27,16;	\
+	;;					\
+.mem.offset 0,0; st8.spill [r2] = r28,16;	\
+.mem.offset 8,0; st8.spill [r3] = r29,16;	\
+	;;					\
+.mem.offset 0,0; st8.spill [r2] = r30,16;	\
+.mem.offset 8,0; st8.spill [r3] = r31,32;	\
+	;;					\
+	mov ar.fpsr = r11;			\
+	st8 [r2] = r8,8;			\
+	adds r24 = PT(B6)-PT(F7),r3;		\
+	adds r25 = PT(B7)-PT(F7),r3;		\
+	;;					\
+	st8 [r24] = r18,16;       /* b6 */	\
+	st8 [r25] = r19,16;       /* b7 */	\
+	adds r2 = PT(R4)-PT(F6),r2;		\
+	adds r3 = PT(R5)-PT(F7),r3;		\
+	;;					\
+	st8 [r24] = r9;	/* ar.csd */		\
+	st8 [r25] = r10;	/* ar.ssd */	\
+	;;					\
+	mov r18 = ar.unat;			\
+	adds r19 = PT(EML_UNAT)-PT(R4),r2;	\
+	;;					\
+	st8 [r19] = r18; /* eml_unat */ 	\
+
+
+#define KVM_SAVE_EXTRA				\
+.mem.offset 0,0; st8.spill [r2] = r4,16;	\
+.mem.offset 8,0; st8.spill [r3] = r5,16;	\
+	;;					\
+.mem.offset 0,0; st8.spill [r2] = r6,16;	\
+.mem.offset 8,0; st8.spill [r3] = r7;		\
+	;;					\
+	mov r26 = ar.unat;			\
+	;;					\
+	st8 [r2] = r26;/* eml_unat */ 		\
+
+#define KVM_SAVE_MIN_WITH_COVER		KVM_DO_SAVE_MIN(cover, mov r30 = cr.ifs,)
+#define KVM_SAVE_MIN_WITH_COVER_R19	KVM_DO_SAVE_MIN(cover, mov r30 = cr.ifs, mov r15 = r19)
+#define KVM_SAVE_MIN			KVM_DO_SAVE_MIN(     , mov r30 = r0, )
diff --git a/trunk/arch/ia64/kvm/lapic.h b/trunk/arch/ia64/kvm/lapic.h
new file mode 100644
index 000000000000..6d6cbcb14893
--- /dev/null
+++ b/trunk/arch/ia64/kvm/lapic.h
@@ -0,0 +1,25 @@
+#ifndef __KVM_IA64_LAPIC_H
+#define __KVM_IA64_LAPIC_H
+
+#include <linux/kvm_host.h>
+
+/*
+ * vlsapic
+ */
+struct kvm_lapic{
+	struct kvm_vcpu *vcpu;
+	uint64_t insvc[4];
+	uint64_t vhpi;
+	uint8_t xtp;
+	uint8_t pal_init_pending;
+	uint8_t pad[2];
+};
+
+int kvm_create_lapic(struct kvm_vcpu *vcpu);
+void kvm_free_lapic(struct kvm_vcpu *vcpu);
+
+int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest);
+int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda);
+int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig);
+
+#endif
diff --git a/trunk/arch/ia64/kvm/misc.h b/trunk/arch/ia64/kvm/misc.h
new file mode 100644
index 000000000000..e585c4607344
--- /dev/null
+++ b/trunk/arch/ia64/kvm/misc.h
@@ -0,0 +1,93 @@
+#ifndef __KVM_IA64_MISC_H
+#define __KVM_IA64_MISC_H
+
+#include <linux/kvm_host.h>
+/*
+ * misc.h
+ * 	Copyright (C) 2007, Intel Corporation.
+ *  	Xiantao Zhang  (xiantao.zhang@intel.com)
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+
+/*
+ *Return p2m base address at host side!
+ */
+static inline uint64_t *kvm_host_get_pmt(struct kvm *kvm)
+{
+	return (uint64_t *)(kvm->arch.vm_base + KVM_P2M_OFS);
+}
+
+static inline void kvm_set_pmt_entry(struct kvm *kvm, gfn_t gfn,
+		u64 paddr, u64 mem_flags)
+{
+	uint64_t *pmt_base = kvm_host_get_pmt(kvm);
+	unsigned long pte;
+
+	pte = PAGE_ALIGN(paddr) | mem_flags;
+	pmt_base[gfn] = pte;
+}
+
+/*Function for translating host address to guest address*/
+
+static inline void *to_guest(struct kvm *kvm, void *addr)
+{
+	return (void *)((unsigned long)(addr) - kvm->arch.vm_base +
+			KVM_VM_DATA_BASE);
+}
+
+/*Function for translating guest address to host address*/
+
+static inline void *to_host(struct kvm *kvm, void *addr)
+{
+	return (void *)((unsigned long)addr - KVM_VM_DATA_BASE
+			+ kvm->arch.vm_base);
+}
+
+/* Get host context of the vcpu */
+static inline union context *kvm_get_host_context(struct kvm_vcpu *vcpu)
+{
+	union context *ctx = &vcpu->arch.host;
+	return to_guest(vcpu->kvm, ctx);
+}
+
+/* Get guest context of the vcpu */
+static inline union context *kvm_get_guest_context(struct kvm_vcpu *vcpu)
+{
+	union context *ctx = &vcpu->arch.guest;
+	return  to_guest(vcpu->kvm, ctx);
+}
+
+/* kvm get exit data from gvmm! */
+static inline struct exit_ctl_data *kvm_get_exit_data(struct kvm_vcpu *vcpu)
+{
+	return &vcpu->arch.exit_data;
+}
+
+/*kvm get vcpu ioreq for kvm module!*/
+static inline struct kvm_mmio_req *kvm_get_vcpu_ioreq(struct kvm_vcpu *vcpu)
+{
+	struct exit_ctl_data *p_ctl_data;
+
+	if (vcpu) {
+		p_ctl_data = kvm_get_exit_data(vcpu);
+		if (p_ctl_data->exit_reason == EXIT_REASON_MMIO_INSTRUCTION)
+			return &p_ctl_data->u.ioreq;
+	}
+
+	return NULL;
+}
+
+#endif
diff --git a/trunk/arch/ia64/kvm/mmio.c b/trunk/arch/ia64/kvm/mmio.c
new file mode 100644
index 000000000000..351bf70da463
--- /dev/null
+++ b/trunk/arch/ia64/kvm/mmio.c
@@ -0,0 +1,341 @@
+/*
+ * mmio.c: MMIO emulation components.
+ * Copyright (c) 2004, Intel Corporation.
+ *  Yaozu Dong (Eddie Dong) (Eddie.dong@intel.com)
+ *  Kun Tian (Kevin Tian) (Kevin.tian@intel.com)
+ *
+ * Copyright (c) 2007 Intel Corporation  KVM support.
+ * Xuefei Xu (Anthony Xu) (anthony.xu@intel.com)
+ * Xiantao Zhang  (xiantao.zhang@intel.com)
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+
+#include <linux/kvm_host.h>
+
+#include "vcpu.h"
+
+static void vlsapic_write_xtp(struct kvm_vcpu *v, uint8_t val)
+{
+	VLSAPIC_XTP(v) = val;
+}
+
+/*
+ * LSAPIC OFFSET
+ */
+#define PIB_LOW_HALF(ofst)     !(ofst & (1 << 20))
+#define PIB_OFST_INTA          0x1E0000
+#define PIB_OFST_XTP           0x1E0008
+
+/*
+ * execute write IPI op.
+ */
+static void vlsapic_write_ipi(struct kvm_vcpu *vcpu,
+					uint64_t addr, uint64_t data)
+{
+	struct exit_ctl_data *p = &current_vcpu->arch.exit_data;
+	unsigned long psr;
+
+	local_irq_save(psr);
+
+	p->exit_reason = EXIT_REASON_IPI;
+	p->u.ipi_data.addr.val = addr;
+	p->u.ipi_data.data.val = data;
+	vmm_transition(current_vcpu);
+
+	local_irq_restore(psr);
+
+}
+
+void lsapic_write(struct kvm_vcpu *v, unsigned long addr,
+			unsigned long length, unsigned long val)
+{
+	addr &= (PIB_SIZE - 1);
+
+	switch (addr) {
+	case PIB_OFST_INTA:
+		/*panic_domain(NULL, "Undefined write on PIB INTA\n");*/
+		panic_vm(v);
+		break;
+	case PIB_OFST_XTP:
+		if (length == 1) {
+			vlsapic_write_xtp(v, val);
+		} else {
+			/*panic_domain(NULL,
+			"Undefined write on PIB XTP\n");*/
+			panic_vm(v);
+		}
+		break;
+	default:
+		if (PIB_LOW_HALF(addr)) {
+			/*lower half */
+			if (length != 8)
+				/*panic_domain(NULL,
+				"Can't LHF write with size %ld!\n",
+				length);*/
+				panic_vm(v);
+			else
+				vlsapic_write_ipi(v, addr, val);
+		} else {   /*	upper half
+				printk("IPI-UHF write %lx\n",addr);*/
+			panic_vm(v);
+		}
+		break;
+	}
+}
+
+unsigned long lsapic_read(struct kvm_vcpu *v, unsigned long addr,
+		unsigned long length)
+{
+	uint64_t result = 0;
+
+	addr &= (PIB_SIZE - 1);
+
+	switch (addr) {
+	case PIB_OFST_INTA:
+		if (length == 1) /* 1 byte load */
+			; /* There is no i8259, there is no INTA access*/
+		else
+			/*panic_domain(NULL,"Undefined read on PIB INTA\n"); */
+			panic_vm(v);
+
+		break;
+	case PIB_OFST_XTP:
+		if (length == 1) {
+			result = VLSAPIC_XTP(v);
+			/* printk("read xtp %lx\n", result); */
+		} else {
+			/*panic_domain(NULL,
+			"Undefined read on PIB XTP\n");*/
+			panic_vm(v);
+		}
+		break;
+	default:
+		panic_vm(v);
+		break;
+	}
+	return result;
+}
+
+static void mmio_access(struct kvm_vcpu *vcpu, u64 src_pa, u64 *dest,
+					u16 s, int ma, int dir)
+{
+	unsigned long iot;
+	struct exit_ctl_data *p = &vcpu->arch.exit_data;
+	unsigned long psr;
+
+	iot = __gpfn_is_io(src_pa >> PAGE_SHIFT);
+
+	local_irq_save(psr);
+
+	/*Intercept the acces for PIB range*/
+	if (iot == GPFN_PIB) {
+		if (!dir)
+			lsapic_write(vcpu, src_pa, s, *dest);
+		else
+			*dest = lsapic_read(vcpu, src_pa, s);
+		goto out;
+	}
+	p->exit_reason = EXIT_REASON_MMIO_INSTRUCTION;
+	p->u.ioreq.addr = src_pa;
+	p->u.ioreq.size = s;
+	p->u.ioreq.dir = dir;
+	if (dir == IOREQ_WRITE)
+		p->u.ioreq.data = *dest;
+	p->u.ioreq.state = STATE_IOREQ_READY;
+	vmm_transition(vcpu);
+
+	if (p->u.ioreq.state == STATE_IORESP_READY) {
+		if (dir == IOREQ_READ)
+			*dest = p->u.ioreq.data;
+	} else
+		panic_vm(vcpu);
+out:
+	local_irq_restore(psr);
+	return ;
+}
+
+/*
+   dir 1: read 0:write
+   inst_type 0:integer 1:floating point
+ */
+#define SL_INTEGER	0	/* store/load interger*/
+#define SL_FLOATING	1     	/* store/load floating*/
+
+void emulate_io_inst(struct kvm_vcpu *vcpu, u64 padr, u64 ma)
+{
+	struct kvm_pt_regs *regs;
+	IA64_BUNDLE bundle;
+	int slot, dir = 0;
+	int inst_type = -1;
+	u16 size = 0;
+	u64 data, slot1a, slot1b, temp, update_reg;
+	s32 imm;
+	INST64 inst;
+
+	regs = vcpu_regs(vcpu);
+
+	if (fetch_code(vcpu, regs->cr_iip, &bundle)) {
+		/* if fetch code fail, return and try again */
+		return;
+	}
+	slot = ((struct ia64_psr *)&(regs->cr_ipsr))->ri;
+	if (!slot)
+		inst.inst = bundle.slot0;
+	else if (slot == 1) {
+		slot1a = bundle.slot1a;
+		slot1b = bundle.slot1b;
+		inst.inst = slot1a + (slot1b << 18);
+	} else if (slot == 2)
+		inst.inst = bundle.slot2;
+
+	/* Integer Load/Store */
+	if (inst.M1.major == 4 && inst.M1.m == 0 && inst.M1.x == 0) {
+		inst_type = SL_INTEGER;
+		size = (inst.M1.x6 & 0x3);
+		if ((inst.M1.x6 >> 2) > 0xb) {
+			/*write*/
+			dir = IOREQ_WRITE;
+			data = vcpu_get_gr(vcpu, inst.M4.r2);
+		} else if ((inst.M1.x6 >> 2) < 0xb) {
+			/*read*/
+			dir = IOREQ_READ;
+		}
+	} else if (inst.M2.major == 4 && inst.M2.m == 1 && inst.M2.x == 0) {
+		/* Integer Load + Reg update */
+		inst_type = SL_INTEGER;
+		dir = IOREQ_READ;
+		size = (inst.M2.x6 & 0x3);
+		temp = vcpu_get_gr(vcpu, inst.M2.r3);
+		update_reg = vcpu_get_gr(vcpu, inst.M2.r2);
+		temp += update_reg;
+		vcpu_set_gr(vcpu, inst.M2.r3, temp, 0);
+	} else if (inst.M3.major == 5) {
+		/*Integer Load/Store + Imm update*/
+		inst_type = SL_INTEGER;
+		size = (inst.M3.x6&0x3);
+		if ((inst.M5.x6 >> 2) > 0xb) {
+			/*write*/
+			dir = IOREQ_WRITE;
+			data = vcpu_get_gr(vcpu, inst.M5.r2);
+			temp = vcpu_get_gr(vcpu, inst.M5.r3);
+			imm = (inst.M5.s << 31) | (inst.M5.i << 30) |
+				(inst.M5.imm7 << 23);
+			temp += imm >> 23;
+			vcpu_set_gr(vcpu, inst.M5.r3, temp, 0);
+
+		} else if ((inst.M3.x6 >> 2) < 0xb) {
+			/*read*/
+			dir = IOREQ_READ;
+			temp = vcpu_get_gr(vcpu, inst.M3.r3);
+			imm = (inst.M3.s << 31) | (inst.M3.i << 30) |
+				(inst.M3.imm7 << 23);
+			temp += imm >> 23;
+			vcpu_set_gr(vcpu, inst.M3.r3, temp, 0);
+
+		}
+	} else if (inst.M9.major == 6 && inst.M9.x6 == 0x3B
+				&& inst.M9.m == 0 && inst.M9.x == 0) {
+		/* Floating-point spill*/
+		struct ia64_fpreg v;
+
+		inst_type = SL_FLOATING;
+		dir = IOREQ_WRITE;
+		vcpu_get_fpreg(vcpu, inst.M9.f2, &v);
+		/* Write high word. FIXME: this is a kludge!  */
+		v.u.bits[1] &= 0x3ffff;
+		mmio_access(vcpu, padr + 8, &v.u.bits[1], 8, ma, IOREQ_WRITE);
+		data = v.u.bits[0];
+		size = 3;
+	} else if (inst.M10.major == 7 && inst.M10.x6 == 0x3B) {
+		/* Floating-point spill + Imm update */
+		struct ia64_fpreg v;
+
+		inst_type = SL_FLOATING;
+		dir = IOREQ_WRITE;
+		vcpu_get_fpreg(vcpu, inst.M10.f2, &v);
+		temp = vcpu_get_gr(vcpu, inst.M10.r3);
+		imm = (inst.M10.s << 31) | (inst.M10.i << 30) |
+			(inst.M10.imm7 << 23);
+		temp += imm >> 23;
+		vcpu_set_gr(vcpu, inst.M10.r3, temp, 0);
+
+		/* Write high word.FIXME: this is a kludge!  */
+		v.u.bits[1] &= 0x3ffff;
+		mmio_access(vcpu, padr + 8, &v.u.bits[1], 8, ma, IOREQ_WRITE);
+		data = v.u.bits[0];
+		size = 3;
+	} else if (inst.M10.major == 7 && inst.M10.x6 == 0x31) {
+		/* Floating-point stf8 + Imm update */
+		struct ia64_fpreg v;
+		inst_type = SL_FLOATING;
+		dir = IOREQ_WRITE;
+		size = 3;
+		vcpu_get_fpreg(vcpu, inst.M10.f2, &v);
+		data = v.u.bits[0]; /* Significand.  */
+		temp = vcpu_get_gr(vcpu, inst.M10.r3);
+		imm = (inst.M10.s << 31) | (inst.M10.i << 30) |
+			(inst.M10.imm7 << 23);
+		temp += imm >> 23;
+		vcpu_set_gr(vcpu, inst.M10.r3, temp, 0);
+	} else if (inst.M15.major == 7 && inst.M15.x6 >= 0x2c
+			&& inst.M15.x6 <= 0x2f) {
+		temp = vcpu_get_gr(vcpu, inst.M15.r3);
+		imm = (inst.M15.s << 31) | (inst.M15.i << 30) |
+			(inst.M15.imm7 << 23);
+		temp += imm >> 23;
+		vcpu_set_gr(vcpu, inst.M15.r3, temp, 0);
+
+		vcpu_increment_iip(vcpu);
+		return;
+	} else if (inst.M12.major == 6 && inst.M12.m == 1
+			&& inst.M12.x == 1 && inst.M12.x6 == 1) {
+		/* Floating-point Load Pair + Imm ldfp8 M12*/
+		struct ia64_fpreg v;
+
+		inst_type = SL_FLOATING;
+		dir = IOREQ_READ;
+		size = 8;     /*ldfd*/
+		mmio_access(vcpu, padr, &data, size, ma, dir);
+		v.u.bits[0] = data;
+		v.u.bits[1] = 0x1003E;
+		vcpu_set_fpreg(vcpu, inst.M12.f1, &v);
+		padr += 8;
+		mmio_access(vcpu, padr, &data, size, ma, dir);
+		v.u.bits[0] = data;
+		v.u.bits[1] = 0x1003E;
+		vcpu_set_fpreg(vcpu, inst.M12.f2, &v);
+		padr += 8;
+		vcpu_set_gr(vcpu, inst.M12.r3, padr, 0);
+		vcpu_increment_iip(vcpu);
+		return;
+	} else {
+		inst_type = -1;
+		panic_vm(vcpu);
+	}
+
+	size = 1 << size;
+	if (dir == IOREQ_WRITE) {
+		mmio_access(vcpu, padr, &data, size, ma, dir);
+	} else {
+		mmio_access(vcpu, padr, &data, size, ma, dir);
+		if (inst_type == SL_INTEGER)
+			vcpu_set_gr(vcpu, inst.M1.r1, data, 0);
+		else
+			panic_vm(vcpu);
+
+	}
+	vcpu_increment_iip(vcpu);
+}
diff --git a/trunk/arch/ia64/kvm/optvfault.S b/trunk/arch/ia64/kvm/optvfault.S
new file mode 100644
index 000000000000..e4f15d641b22
--- /dev/null
+++ b/trunk/arch/ia64/kvm/optvfault.S
@@ -0,0 +1,918 @@
+/*
+ * arch/ia64/vmx/optvfault.S
+ * optimize virtualization fault handler
+ *
+ * Copyright (C) 2006 Intel Co
+ *	Xuefei Xu (Anthony Xu) <anthony.xu@intel.com>
+ */
+
+#include <asm/asmmacro.h>
+#include <asm/processor.h>
+
+#include "vti.h"
+#include "asm-offsets.h"
+
+#define ACCE_MOV_FROM_AR
+#define ACCE_MOV_FROM_RR
+#define ACCE_MOV_TO_RR
+#define ACCE_RSM
+#define ACCE_SSM
+#define ACCE_MOV_TO_PSR
+#define ACCE_THASH
+
+//mov r1=ar3
+GLOBAL_ENTRY(kvm_asm_mov_from_ar)
+#ifndef ACCE_MOV_FROM_AR
+	br.many kvm_virtualization_fault_back
+#endif
+	add r18=VMM_VCPU_ITC_OFS_OFFSET, r21
+	add r16=VMM_VCPU_LAST_ITC_OFFSET,r21
+	extr.u r17=r25,6,7
+	;;
+	ld8 r18=[r18]
+	mov r19=ar.itc
+	mov r24=b0
+	;;
+	add r19=r19,r18
+	addl r20=@gprel(asm_mov_to_reg),gp
+	;;
+	st8 [r16] = r19
+	adds r30=kvm_resume_to_guest-asm_mov_to_reg,r20
+	shladd r17=r17,4,r20
+	;;
+	mov b0=r17
+	br.sptk.few b0
+	;;
+END(kvm_asm_mov_from_ar)
+
+
+// mov r1=rr[r3]
+GLOBAL_ENTRY(kvm_asm_mov_from_rr)
+#ifndef ACCE_MOV_FROM_RR
+	br.many kvm_virtualization_fault_back
+#endif
+	extr.u r16=r25,20,7
+	extr.u r17=r25,6,7
+	addl r20=@gprel(asm_mov_from_reg),gp
+	;;
+	adds r30=kvm_asm_mov_from_rr_back_1-asm_mov_from_reg,r20
+	shladd r16=r16,4,r20
+	mov r24=b0
+	;;
+	add r27=VMM_VCPU_VRR0_OFFSET,r21
+	mov b0=r16
+	br.many b0
+	;;
+kvm_asm_mov_from_rr_back_1:
+	adds r30=kvm_resume_to_guest-asm_mov_from_reg,r20
+	adds r22=asm_mov_to_reg-asm_mov_from_reg,r20
+	shr.u r26=r19,61
+	;;
+	shladd r17=r17,4,r22
+	shladd r27=r26,3,r27
+	;;
+	ld8 r19=[r27]
+	mov b0=r17
+	br.many b0
+END(kvm_asm_mov_from_rr)
+
+
+// mov rr[r3]=r2
+GLOBAL_ENTRY(kvm_asm_mov_to_rr)
+#ifndef ACCE_MOV_TO_RR
+	br.many kvm_virtualization_fault_back
+#endif
+	extr.u r16=r25,20,7
+	extr.u r17=r25,13,7
+	addl r20=@gprel(asm_mov_from_reg),gp
+	;;
+	adds r30=kvm_asm_mov_to_rr_back_1-asm_mov_from_reg,r20
+	shladd r16=r16,4,r20
+	mov r22=b0
+	;;
+	add r27=VMM_VCPU_VRR0_OFFSET,r21
+	mov b0=r16
+	br.many b0
+	;;
+kvm_asm_mov_to_rr_back_1:
+	adds r30=kvm_asm_mov_to_rr_back_2-asm_mov_from_reg,r20
+	shr.u r23=r19,61
+	shladd r17=r17,4,r20
+	;;
+	//if rr6, go back
+	cmp.eq p6,p0=6,r23
+	mov b0=r22
+	(p6) br.cond.dpnt.many kvm_virtualization_fault_back
+	;;
+	mov r28=r19
+	mov b0=r17
+	br.many b0
+kvm_asm_mov_to_rr_back_2:
+	adds r30=kvm_resume_to_guest-asm_mov_from_reg,r20
+	shladd r27=r23,3,r27
+	;; // vrr.rid<<4 |0xe
+	st8 [r27]=r19
+	mov b0=r30
+	;;
+	extr.u r16=r19,8,26
+	extr.u r18 =r19,2,6
+	mov r17 =0xe
+	;;
+	shladd r16 = r16, 4, r17
+	extr.u r19 =r19,0,8
+	;;
+	shl r16 = r16,8
+	;;
+	add r19 = r19, r16
+	;; //set ve 1
+	dep r19=-1,r19,0,1
+	cmp.lt p6,p0=14,r18
+	;;
+	(p6) mov r18=14
+	;;
+	(p6) dep r19=r18,r19,2,6
+	;;
+	cmp.eq p6,p0=0,r23
+	;;
+	cmp.eq.or p6,p0=4,r23
+	;;
+	adds r16=VMM_VCPU_MODE_FLAGS_OFFSET,r21
+	(p6) adds r17=VMM_VCPU_META_SAVED_RR0_OFFSET,r21
+	;;
+	ld4 r16=[r16]
+	cmp.eq p7,p0=r0,r0
+	(p6) shladd r17=r23,1,r17
+	;;
+	(p6) st8 [r17]=r19
+	(p6) tbit.nz p6,p7=r16,0
+	;;
+	(p7) mov rr[r28]=r19
+	mov r24=r22
+	br.many b0
+END(kvm_asm_mov_to_rr)
+
+
+//rsm
+GLOBAL_ENTRY(kvm_asm_rsm)
+#ifndef ACCE_RSM
+	br.many kvm_virtualization_fault_back
+#endif
+	add r16=VMM_VPD_BASE_OFFSET,r21
+	extr.u r26=r25,6,21
+	extr.u r27=r25,31,2
+	;;
+	ld8 r16=[r16]
+	extr.u r28=r25,36,1
+	dep r26=r27,r26,21,2
+	;;
+	add r17=VPD_VPSR_START_OFFSET,r16
+	add r22=VMM_VCPU_MODE_FLAGS_OFFSET,r21
+	//r26 is imm24
+	dep r26=r28,r26,23,1
+	;;
+	ld8 r18=[r17]
+	movl r28=IA64_PSR_IC+IA64_PSR_I+IA64_PSR_DT+IA64_PSR_SI
+	ld4 r23=[r22]
+	sub r27=-1,r26
+	mov r24=b0
+	;;
+	mov r20=cr.ipsr
+	or r28=r27,r28
+	and r19=r18,r27
+	;;
+	st8 [r17]=r19
+	and r20=r20,r28
+	/* Comment it out due to short of fp lazy alorgithm support
+	adds r27=IA64_VCPU_FP_PSR_OFFSET,r21
+	;;
+	ld8 r27=[r27]
+	;;
+	tbit.nz p8,p0= r27,IA64_PSR_DFH_BIT
+	;;
+	(p8) dep r20=-1,r20,IA64_PSR_DFH_BIT,1
+	*/
+	;;
+	mov cr.ipsr=r20
+	tbit.nz p6,p0=r23,0
+	;;
+	tbit.z.or p6,p0=r26,IA64_PSR_DT_BIT
+	(p6) br.dptk kvm_resume_to_guest
+	;;
+	add r26=VMM_VCPU_META_RR0_OFFSET,r21
+	add r27=VMM_VCPU_META_RR0_OFFSET+8,r21
+	dep r23=-1,r23,0,1
+	;;
+	ld8 r26=[r26]
+	ld8 r27=[r27]
+	st4 [r22]=r23
+	dep.z r28=4,61,3
+	;;
+	mov rr[r0]=r26
+	;;
+	mov rr[r28]=r27
+	;;
+	srlz.d
+	br.many kvm_resume_to_guest
+END(kvm_asm_rsm)
+
+
+//ssm
+GLOBAL_ENTRY(kvm_asm_ssm)
+#ifndef ACCE_SSM
+	br.many kvm_virtualization_fault_back
+#endif
+	add r16=VMM_VPD_BASE_OFFSET,r21
+	extr.u r26=r25,6,21
+	extr.u r27=r25,31,2
+	;;
+	ld8 r16=[r16]
+	extr.u r28=r25,36,1
+	dep r26=r27,r26,21,2
+	;;  //r26 is imm24
+	add r27=VPD_VPSR_START_OFFSET,r16
+	dep r26=r28,r26,23,1
+	;;  //r19 vpsr
+	ld8 r29=[r27]
+	mov r24=b0
+	;;
+	add r22=VMM_VCPU_MODE_FLAGS_OFFSET,r21
+	mov r20=cr.ipsr
+	or r19=r29,r26
+	;;
+	ld4 r23=[r22]
+	st8 [r27]=r19
+	or r20=r20,r26
+	;;
+	mov cr.ipsr=r20
+	movl r28=IA64_PSR_DT+IA64_PSR_RT+IA64_PSR_IT
+	;;
+	and r19=r28,r19
+	tbit.z p6,p0=r23,0
+	;;
+	cmp.ne.or p6,p0=r28,r19
+	(p6) br.dptk kvm_asm_ssm_1
+	;;
+	add r26=VMM_VCPU_META_SAVED_RR0_OFFSET,r21
+	add r27=VMM_VCPU_META_SAVED_RR0_OFFSET+8,r21
+	dep r23=0,r23,0,1
+	;;
+	ld8 r26=[r26]
+	ld8 r27=[r27]
+	st4 [r22]=r23
+	dep.z r28=4,61,3
+	;;
+	mov rr[r0]=r26
+	;;
+	mov rr[r28]=r27
+	;;
+	srlz.d
+	;;
+kvm_asm_ssm_1:
+	tbit.nz p6,p0=r29,IA64_PSR_I_BIT
+	;;
+	tbit.z.or p6,p0=r19,IA64_PSR_I_BIT
+	(p6) br.dptk kvm_resume_to_guest
+	;;
+	add r29=VPD_VTPR_START_OFFSET,r16
+	add r30=VPD_VHPI_START_OFFSET,r16
+	;;
+	ld8 r29=[r29]
+	ld8 r30=[r30]
+	;;
+	extr.u r17=r29,4,4
+	extr.u r18=r29,16,1
+	;;
+	dep r17=r18,r17,4,1
+	;;
+	cmp.gt p6,p0=r30,r17
+	(p6) br.dpnt.few kvm_asm_dispatch_vexirq
+	br.many kvm_resume_to_guest
+END(kvm_asm_ssm)
+
+
+//mov psr.l=r2
+GLOBAL_ENTRY(kvm_asm_mov_to_psr)
+#ifndef ACCE_MOV_TO_PSR
+	br.many kvm_virtualization_fault_back
+#endif
+	add r16=VMM_VPD_BASE_OFFSET,r21
+	extr.u r26=r25,13,7 //r2
+	;;
+	ld8 r16=[r16]
+	addl r20=@gprel(asm_mov_from_reg),gp
+	;;
+	adds r30=kvm_asm_mov_to_psr_back-asm_mov_from_reg,r20
+	shladd r26=r26,4,r20
+	mov r24=b0
+	;;
+	add r27=VPD_VPSR_START_OFFSET,r16
+	mov b0=r26
+	br.many b0
+	;;
+kvm_asm_mov_to_psr_back:
+	ld8 r17=[r27]
+	add r22=VMM_VCPU_MODE_FLAGS_OFFSET,r21
+	dep r19=0,r19,32,32
+	;;
+	ld4 r23=[r22]
+	dep r18=0,r17,0,32
+	;;
+	add r30=r18,r19
+	movl r28=IA64_PSR_DT+IA64_PSR_RT+IA64_PSR_IT
+	;;
+	st8 [r27]=r30
+	and r27=r28,r30
+	and r29=r28,r17
+	;;
+	cmp.eq p5,p0=r29,r27
+	cmp.eq p6,p7=r28,r27
+	(p5) br.many kvm_asm_mov_to_psr_1
+	;;
+	//virtual to physical
+	(p7) add r26=VMM_VCPU_META_RR0_OFFSET,r21
+	(p7) add r27=VMM_VCPU_META_RR0_OFFSET+8,r21
+	(p7) dep r23=-1,r23,0,1
+	;;
+	//physical to virtual
+	(p6) add r26=VMM_VCPU_META_SAVED_RR0_OFFSET,r21
+	(p6) add r27=VMM_VCPU_META_SAVED_RR0_OFFSET+8,r21
+	(p6) dep r23=0,r23,0,1
+	;;
+	ld8 r26=[r26]
+	ld8 r27=[r27]
+	st4 [r22]=r23
+	dep.z r28=4,61,3
+	;;
+	mov rr[r0]=r26
+	;;
+	mov rr[r28]=r27
+	;;
+	srlz.d
+	;;
+kvm_asm_mov_to_psr_1:
+	mov r20=cr.ipsr
+	movl r28=IA64_PSR_IC+IA64_PSR_I+IA64_PSR_DT+IA64_PSR_SI+IA64_PSR_RT
+	;;
+	or r19=r19,r28
+	dep r20=0,r20,0,32
+	;;
+	add r20=r19,r20
+	mov b0=r24
+	;;
+	/* Comment it out due to short of fp lazy algorithm support
+	adds r27=IA64_VCPU_FP_PSR_OFFSET,r21
+	;;
+	ld8 r27=[r27]
+	;;
+	tbit.nz p8,p0=r27,IA64_PSR_DFH_BIT
+	;;
+	(p8) dep r20=-1,r20,IA64_PSR_DFH_BIT,1
+	;;
+	*/
+	mov cr.ipsr=r20
+	cmp.ne p6,p0=r0,r0
+	;;
+	tbit.nz.or p6,p0=r17,IA64_PSR_I_BIT
+	tbit.z.or p6,p0=r30,IA64_PSR_I_BIT
+	(p6) br.dpnt.few kvm_resume_to_guest
+	;;
+	add r29=VPD_VTPR_START_OFFSET,r16
+	add r30=VPD_VHPI_START_OFFSET,r16
+	;;
+	ld8 r29=[r29]
+	ld8 r30=[r30]
+	;;
+	extr.u r17=r29,4,4
+	extr.u r18=r29,16,1
+	;;
+	dep r17=r18,r17,4,1
+	;;
+	cmp.gt p6,p0=r30,r17
+	(p6) br.dpnt.few kvm_asm_dispatch_vexirq
+	br.many kvm_resume_to_guest
+END(kvm_asm_mov_to_psr)
+
+
+ENTRY(kvm_asm_dispatch_vexirq)
+//increment iip
+	mov r16=cr.ipsr
+	;;
+	extr.u r17=r16,IA64_PSR_RI_BIT,2
+	tbit.nz p6,p7=r16,IA64_PSR_RI_BIT+1
+	;;
+	(p6) mov r18=cr.iip
+	(p6) mov r17=r0
+	(p7) add r17=1,r17
+	;;
+	(p6) add r18=0x10,r18
+	dep r16=r17,r16,IA64_PSR_RI_BIT,2
+	;;
+	(p6) mov cr.iip=r18
+	mov cr.ipsr=r16
+	mov r30 =1
+	br.many kvm_dispatch_vexirq
+END(kvm_asm_dispatch_vexirq)
+
+// thash
+// TODO: add support when pta.vf = 1
+GLOBAL_ENTRY(kvm_asm_thash)
+#ifndef ACCE_THASH
+	br.many kvm_virtualization_fault_back
+#endif
+	extr.u r17=r25,20,7		// get r3 from opcode in r25
+	extr.u r18=r25,6,7		// get r1 from opcode in r25
+	addl r20=@gprel(asm_mov_from_reg),gp
+	;;
+	adds r30=kvm_asm_thash_back1-asm_mov_from_reg,r20
+	shladd r17=r17,4,r20	// get addr of MOVE_FROM_REG(r17)
+	adds r16=VMM_VPD_BASE_OFFSET,r21	// get vcpu.arch.priveregs
+	;;
+	mov r24=b0
+	;;
+	ld8 r16=[r16]		// get VPD addr
+	mov b0=r17
+	br.many b0			// r19 return value
+	;;
+kvm_asm_thash_back1:
+	shr.u r23=r19,61		// get RR number
+	adds r25=VMM_VCPU_VRR0_OFFSET,r21	// get vcpu->arch.vrr[0]'s addr
+	adds r16=VMM_VPD_VPTA_OFFSET,r16	// get vpta
+	;;
+	shladd r27=r23,3,r25	// get vcpu->arch.vrr[r23]'s addr
+	ld8 r17=[r16]		// get PTA
+	mov r26=1
+	;;
+	extr.u r29=r17,2,6		// get pta.size
+	ld8 r25=[r27]		// get vcpu->arch.vrr[r23]'s value
+	;;
+	extr.u r25=r25,2,6		// get rr.ps
+	shl r22=r26,r29		// 1UL << pta.size
+	;;
+	shr.u r23=r19,r25		// vaddr >> rr.ps
+	adds r26=3,r29		// pta.size + 3
+	shl r27=r17,3		// pta << 3
+	;;
+	shl r23=r23,3		// (vaddr >> rr.ps) << 3
+	shr.u r27=r27,r26		// (pta << 3) >> (pta.size+3)
+	movl r16=7<<61
+	;;
+	adds r22=-1,r22		// (1UL << pta.size) - 1
+	shl r27=r27,r29		// ((pta<<3)>>(pta.size+3))<<pta.size
+	and r19=r19,r16		// vaddr & VRN_MASK
+	;;
+	and r22=r22,r23		// vhpt_offset
+	or r19=r19,r27 // (vadr&VRN_MASK)|(((pta<<3)>>(pta.size + 3))<<pta.size)
+	adds r26=asm_mov_to_reg-asm_mov_from_reg,r20
+	;;
+	or r19=r19,r22		// calc pval
+	shladd r17=r18,4,r26
+	adds r30=kvm_resume_to_guest-asm_mov_from_reg,r20
+	;;
+	mov b0=r17
+	br.many b0
+END(kvm_asm_thash)
+
+#define MOV_TO_REG0	\
+{;			\
+	nop.b 0x0;		\
+	nop.b 0x0;		\
+	nop.b 0x0;		\
+	;;			\
+};
+
+
+#define MOV_TO_REG(n)	\
+{;			\
+	mov r##n##=r19;	\
+	mov b0=r30;	\
+	br.sptk.many b0;	\
+	;;			\
+};
+
+
+#define MOV_FROM_REG(n)	\
+{;				\
+	mov r19=r##n##;		\
+	mov b0=r30;		\
+	br.sptk.many b0;		\
+	;;				\
+};
+
+
+#define MOV_TO_BANK0_REG(n)			\
+ENTRY_MIN_ALIGN(asm_mov_to_bank0_reg##n##);	\
+{;						\
+	mov r26=r2;				\
+	mov r2=r19;				\
+	bsw.1;					\
+	;;						\
+};						\
+{;						\
+	mov r##n##=r2;				\
+	nop.b 0x0;					\
+	bsw.0;					\
+	;;						\
+};						\
+{;						\
+	mov r2=r26;				\
+	mov b0=r30;				\
+	br.sptk.many b0;				\
+	;;						\
+};						\
+END(asm_mov_to_bank0_reg##n##)
+
+
+#define MOV_FROM_BANK0_REG(n)			\
+ENTRY_MIN_ALIGN(asm_mov_from_bank0_reg##n##);	\
+{;						\
+	mov r26=r2;				\
+	nop.b 0x0;					\
+	bsw.1;					\
+	;;						\
+};						\
+{;						\
+	mov r2=r##n##;				\
+	nop.b 0x0;					\
+	bsw.0;					\
+	;;						\
+};						\
+{;						\
+	mov r19=r2;				\
+	mov r2=r26;				\
+	mov b0=r30;				\
+};						\
+{;						\
+	nop.b 0x0;					\
+	nop.b 0x0;					\
+	br.sptk.many b0;				\
+	;;						\
+};						\
+END(asm_mov_from_bank0_reg##n##)
+
+
+#define JMP_TO_MOV_TO_BANK0_REG(n)		\
+{;						\
+	nop.b 0x0;					\
+	nop.b 0x0;					\
+	br.sptk.many asm_mov_to_bank0_reg##n##;	\
+	;;						\
+}
+
+
+#define JMP_TO_MOV_FROM_BANK0_REG(n)		\
+{;						\
+	nop.b 0x0;					\
+	nop.b 0x0;					\
+	br.sptk.many asm_mov_from_bank0_reg##n##;	\
+	;;						\
+}
+
+
+MOV_FROM_BANK0_REG(16)
+MOV_FROM_BANK0_REG(17)
+MOV_FROM_BANK0_REG(18)
+MOV_FROM_BANK0_REG(19)
+MOV_FROM_BANK0_REG(20)
+MOV_FROM_BANK0_REG(21)
+MOV_FROM_BANK0_REG(22)
+MOV_FROM_BANK0_REG(23)
+MOV_FROM_BANK0_REG(24)
+MOV_FROM_BANK0_REG(25)
+MOV_FROM_BANK0_REG(26)
+MOV_FROM_BANK0_REG(27)
+MOV_FROM_BANK0_REG(28)
+MOV_FROM_BANK0_REG(29)
+MOV_FROM_BANK0_REG(30)
+MOV_FROM_BANK0_REG(31)
+
+
+// mov from reg table
+ENTRY(asm_mov_from_reg)
+	MOV_FROM_REG(0)
+	MOV_FROM_REG(1)
+	MOV_FROM_REG(2)
+	MOV_FROM_REG(3)
+	MOV_FROM_REG(4)
+	MOV_FROM_REG(5)
+	MOV_FROM_REG(6)
+	MOV_FROM_REG(7)
+	MOV_FROM_REG(8)
+	MOV_FROM_REG(9)
+	MOV_FROM_REG(10)
+	MOV_FROM_REG(11)
+	MOV_FROM_REG(12)
+	MOV_FROM_REG(13)
+	MOV_FROM_REG(14)
+	MOV_FROM_REG(15)
+	JMP_TO_MOV_FROM_BANK0_REG(16)
+	JMP_TO_MOV_FROM_BANK0_REG(17)
+	JMP_TO_MOV_FROM_BANK0_REG(18)
+	JMP_TO_MOV_FROM_BANK0_REG(19)
+	JMP_TO_MOV_FROM_BANK0_REG(20)
+	JMP_TO_MOV_FROM_BANK0_REG(21)
+	JMP_TO_MOV_FROM_BANK0_REG(22)
+	JMP_TO_MOV_FROM_BANK0_REG(23)
+	JMP_TO_MOV_FROM_BANK0_REG(24)
+	JMP_TO_MOV_FROM_BANK0_REG(25)
+	JMP_TO_MOV_FROM_BANK0_REG(26)
+	JMP_TO_MOV_FROM_BANK0_REG(27)
+	JMP_TO_MOV_FROM_BANK0_REG(28)
+	JMP_TO_MOV_FROM_BANK0_REG(29)
+	JMP_TO_MOV_FROM_BANK0_REG(30)
+	JMP_TO_MOV_FROM_BANK0_REG(31)
+	MOV_FROM_REG(32)
+	MOV_FROM_REG(33)
+	MOV_FROM_REG(34)
+	MOV_FROM_REG(35)
+	MOV_FROM_REG(36)
+	MOV_FROM_REG(37)
+	MOV_FROM_REG(38)
+	MOV_FROM_REG(39)
+	MOV_FROM_REG(40)
+	MOV_FROM_REG(41)
+	MOV_FROM_REG(42)
+	MOV_FROM_REG(43)
+	MOV_FROM_REG(44)
+	MOV_FROM_REG(45)
+	MOV_FROM_REG(46)
+	MOV_FROM_REG(47)
+	MOV_FROM_REG(48)
+	MOV_FROM_REG(49)
+	MOV_FROM_REG(50)
+	MOV_FROM_REG(51)
+	MOV_FROM_REG(52)
+	MOV_FROM_REG(53)
+	MOV_FROM_REG(54)
+	MOV_FROM_REG(55)
+	MOV_FROM_REG(56)
+	MOV_FROM_REG(57)
+	MOV_FROM_REG(58)
+	MOV_FROM_REG(59)
+	MOV_FROM_REG(60)
+	MOV_FROM_REG(61)
+	MOV_FROM_REG(62)
+	MOV_FROM_REG(63)
+	MOV_FROM_REG(64)
+	MOV_FROM_REG(65)
+	MOV_FROM_REG(66)
+	MOV_FROM_REG(67)
+	MOV_FROM_REG(68)
+	MOV_FROM_REG(69)
+	MOV_FROM_REG(70)
+	MOV_FROM_REG(71)
+	MOV_FROM_REG(72)
+	MOV_FROM_REG(73)
+	MOV_FROM_REG(74)
+	MOV_FROM_REG(75)
+	MOV_FROM_REG(76)
+	MOV_FROM_REG(77)
+	MOV_FROM_REG(78)
+	MOV_FROM_REG(79)
+	MOV_FROM_REG(80)
+	MOV_FROM_REG(81)
+	MOV_FROM_REG(82)
+	MOV_FROM_REG(83)
+	MOV_FROM_REG(84)
+	MOV_FROM_REG(85)
+	MOV_FROM_REG(86)
+	MOV_FROM_REG(87)
+	MOV_FROM_REG(88)
+	MOV_FROM_REG(89)
+	MOV_FROM_REG(90)
+	MOV_FROM_REG(91)
+	MOV_FROM_REG(92)
+	MOV_FROM_REG(93)
+	MOV_FROM_REG(94)
+	MOV_FROM_REG(95)
+	MOV_FROM_REG(96)
+	MOV_FROM_REG(97)
+	MOV_FROM_REG(98)
+	MOV_FROM_REG(99)
+	MOV_FROM_REG(100)
+	MOV_FROM_REG(101)
+	MOV_FROM_REG(102)
+	MOV_FROM_REG(103)
+	MOV_FROM_REG(104)
+	MOV_FROM_REG(105)
+	MOV_FROM_REG(106)
+	MOV_FROM_REG(107)
+	MOV_FROM_REG(108)
+	MOV_FROM_REG(109)
+	MOV_FROM_REG(110)
+	MOV_FROM_REG(111)
+	MOV_FROM_REG(112)
+	MOV_FROM_REG(113)
+	MOV_FROM_REG(114)
+	MOV_FROM_REG(115)
+	MOV_FROM_REG(116)
+	MOV_FROM_REG(117)
+	MOV_FROM_REG(118)
+	MOV_FROM_REG(119)
+	MOV_FROM_REG(120)
+	MOV_FROM_REG(121)
+	MOV_FROM_REG(122)
+	MOV_FROM_REG(123)
+	MOV_FROM_REG(124)
+	MOV_FROM_REG(125)
+	MOV_FROM_REG(126)
+	MOV_FROM_REG(127)
+END(asm_mov_from_reg)
+
+
+/* must be in bank 0
+ * parameter:
+ * r31: pr
+ * r24: b0
+ */
+ENTRY(kvm_resume_to_guest)
+	adds r16 = VMM_VCPU_SAVED_GP_OFFSET,r21
+	;;
+	ld8 r1 =[r16]
+	adds r20 = VMM_VCPU_VSA_BASE_OFFSET,r21
+	;;
+	mov r16=cr.ipsr
+	;;
+	ld8 r20 = [r20]
+	adds r19=VMM_VPD_BASE_OFFSET,r21
+	;;
+	ld8 r25=[r19]
+	extr.u r17=r16,IA64_PSR_RI_BIT,2
+	tbit.nz p6,p7=r16,IA64_PSR_RI_BIT+1
+	;;
+	(p6) mov r18=cr.iip
+	(p6) mov r17=r0
+	;;
+	(p6) add r18=0x10,r18
+	(p7) add r17=1,r17
+	;;
+	(p6) mov cr.iip=r18
+	dep r16=r17,r16,IA64_PSR_RI_BIT,2
+	;;
+	mov cr.ipsr=r16
+	adds r19= VPD_VPSR_START_OFFSET,r25
+	add r28=PAL_VPS_RESUME_NORMAL,r20
+	add r29=PAL_VPS_RESUME_HANDLER,r20
+	;;
+	ld8 r19=[r19]
+	mov b0=r29
+	cmp.ne p6,p7 = r0,r0
+	;;
+	tbit.z p6,p7 = r19,IA64_PSR_IC_BIT		// p1=vpsr.ic
+	;;
+	(p6) ld8 r26=[r25]
+	(p7) mov b0=r28
+	mov pr=r31,-2
+	br.sptk.many b0             // call pal service
+	;;
+END(kvm_resume_to_guest)
+
+
+MOV_TO_BANK0_REG(16)
+MOV_TO_BANK0_REG(17)
+MOV_TO_BANK0_REG(18)
+MOV_TO_BANK0_REG(19)
+MOV_TO_BANK0_REG(20)
+MOV_TO_BANK0_REG(21)
+MOV_TO_BANK0_REG(22)
+MOV_TO_BANK0_REG(23)
+MOV_TO_BANK0_REG(24)
+MOV_TO_BANK0_REG(25)
+MOV_TO_BANK0_REG(26)
+MOV_TO_BANK0_REG(27)
+MOV_TO_BANK0_REG(28)
+MOV_TO_BANK0_REG(29)
+MOV_TO_BANK0_REG(30)
+MOV_TO_BANK0_REG(31)
+
+
+// mov to reg table
+ENTRY(asm_mov_to_reg)
+	MOV_TO_REG0
+	MOV_TO_REG(1)
+	MOV_TO_REG(2)
+	MOV_TO_REG(3)
+	MOV_TO_REG(4)
+	MOV_TO_REG(5)
+	MOV_TO_REG(6)
+	MOV_TO_REG(7)
+	MOV_TO_REG(8)
+	MOV_TO_REG(9)
+	MOV_TO_REG(10)
+	MOV_TO_REG(11)
+	MOV_TO_REG(12)
+	MOV_TO_REG(13)
+	MOV_TO_REG(14)
+	MOV_TO_REG(15)
+	JMP_TO_MOV_TO_BANK0_REG(16)
+	JMP_TO_MOV_TO_BANK0_REG(17)
+	JMP_TO_MOV_TO_BANK0_REG(18)
+	JMP_TO_MOV_TO_BANK0_REG(19)
+	JMP_TO_MOV_TO_BANK0_REG(20)
+	JMP_TO_MOV_TO_BANK0_REG(21)
+	JMP_TO_MOV_TO_BANK0_REG(22)
+	JMP_TO_MOV_TO_BANK0_REG(23)
+	JMP_TO_MOV_TO_BANK0_REG(24)
+	JMP_TO_MOV_TO_BANK0_REG(25)
+	JMP_TO_MOV_TO_BANK0_REG(26)
+	JMP_TO_MOV_TO_BANK0_REG(27)
+	JMP_TO_MOV_TO_BANK0_REG(28)
+	JMP_TO_MOV_TO_BANK0_REG(29)
+	JMP_TO_MOV_TO_BANK0_REG(30)
+	JMP_TO_MOV_TO_BANK0_REG(31)
+	MOV_TO_REG(32)
+	MOV_TO_REG(33)
+	MOV_TO_REG(34)
+	MOV_TO_REG(35)
+	MOV_TO_REG(36)
+	MOV_TO_REG(37)
+	MOV_TO_REG(38)
+	MOV_TO_REG(39)
+	MOV_TO_REG(40)
+	MOV_TO_REG(41)
+	MOV_TO_REG(42)
+	MOV_TO_REG(43)
+	MOV_TO_REG(44)
+	MOV_TO_REG(45)
+	MOV_TO_REG(46)
+	MOV_TO_REG(47)
+	MOV_TO_REG(48)
+	MOV_TO_REG(49)
+	MOV_TO_REG(50)
+	MOV_TO_REG(51)
+	MOV_TO_REG(52)
+	MOV_TO_REG(53)
+	MOV_TO_REG(54)
+	MOV_TO_REG(55)
+	MOV_TO_REG(56)
+	MOV_TO_REG(57)
+	MOV_TO_REG(58)
+	MOV_TO_REG(59)
+	MOV_TO_REG(60)
+	MOV_TO_REG(61)
+	MOV_TO_REG(62)
+	MOV_TO_REG(63)
+	MOV_TO_REG(64)
+	MOV_TO_REG(65)
+	MOV_TO_REG(66)
+	MOV_TO_REG(67)
+	MOV_TO_REG(68)
+	MOV_TO_REG(69)
+	MOV_TO_REG(70)
+	MOV_TO_REG(71)
+	MOV_TO_REG(72)
+	MOV_TO_REG(73)
+	MOV_TO_REG(74)
+	MOV_TO_REG(75)
+	MOV_TO_REG(76)
+	MOV_TO_REG(77)
+	MOV_TO_REG(78)
+	MOV_TO_REG(79)
+	MOV_TO_REG(80)
+	MOV_TO_REG(81)
+	MOV_TO_REG(82)
+	MOV_TO_REG(83)
+	MOV_TO_REG(84)
+	MOV_TO_REG(85)
+	MOV_TO_REG(86)
+	MOV_TO_REG(87)
+	MOV_TO_REG(88)
+	MOV_TO_REG(89)
+	MOV_TO_REG(90)
+	MOV_TO_REG(91)
+	MOV_TO_REG(92)
+	MOV_TO_REG(93)
+	MOV_TO_REG(94)
+	MOV_TO_REG(95)
+	MOV_TO_REG(96)
+	MOV_TO_REG(97)
+	MOV_TO_REG(98)
+	MOV_TO_REG(99)
+	MOV_TO_REG(100)
+	MOV_TO_REG(101)
+	MOV_TO_REG(102)
+	MOV_TO_REG(103)
+	MOV_TO_REG(104)
+	MOV_TO_REG(105)
+	MOV_TO_REG(106)
+	MOV_TO_REG(107)
+	MOV_TO_REG(108)
+	MOV_TO_REG(109)
+	MOV_TO_REG(110)
+	MOV_TO_REG(111)
+	MOV_TO_REG(112)
+	MOV_TO_REG(113)
+	MOV_TO_REG(114)
+	MOV_TO_REG(115)
+	MOV_TO_REG(116)
+	MOV_TO_REG(117)
+	MOV_TO_REG(118)
+	MOV_TO_REG(119)
+	MOV_TO_REG(120)
+	MOV_TO_REG(121)
+	MOV_TO_REG(122)
+	MOV_TO_REG(123)
+	MOV_TO_REG(124)
+	MOV_TO_REG(125)
+	MOV_TO_REG(126)
+	MOV_TO_REG(127)
+END(asm_mov_to_reg)
diff --git a/trunk/arch/ia64/kvm/process.c b/trunk/arch/ia64/kvm/process.c
new file mode 100644
index 000000000000..5a33f7ed29a0
--- /dev/null
+++ b/trunk/arch/ia64/kvm/process.c
@@ -0,0 +1,970 @@
+/*
+ * process.c: handle interruption inject for guests.
+ * Copyright (c) 2005, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ *  	Shaofan Li (Susue Li) <susie.li@intel.com>
+ *  	Xiaoyan Feng (Fleming Feng)  <fleming.feng@intel.com>
+ *  	Xuefei Xu (Anthony Xu) (Anthony.xu@intel.com)
+ *  	Xiantao Zhang (xiantao.zhang@intel.com)
+ */
+#include "vcpu.h"
+
+#include <asm/pal.h>
+#include <asm/sal.h>
+#include <asm/fpswa.h>
+#include <asm/kregs.h>
+#include <asm/tlb.h>
+
+fpswa_interface_t *vmm_fpswa_interface;
+
+#define IA64_VHPT_TRANS_VECTOR			0x0000
+#define IA64_INST_TLB_VECTOR			0x0400
+#define IA64_DATA_TLB_VECTOR			0x0800
+#define IA64_ALT_INST_TLB_VECTOR		0x0c00
+#define IA64_ALT_DATA_TLB_VECTOR		0x1000
+#define IA64_DATA_NESTED_TLB_VECTOR		0x1400
+#define IA64_INST_KEY_MISS_VECTOR		0x1800
+#define IA64_DATA_KEY_MISS_VECTOR		0x1c00
+#define IA64_DIRTY_BIT_VECTOR			0x2000
+#define IA64_INST_ACCESS_BIT_VECTOR		0x2400
+#define IA64_DATA_ACCESS_BIT_VECTOR		0x2800
+#define IA64_BREAK_VECTOR			0x2c00
+#define IA64_EXTINT_VECTOR			0x3000
+#define IA64_PAGE_NOT_PRESENT_VECTOR		0x5000
+#define IA64_KEY_PERMISSION_VECTOR		0x5100
+#define IA64_INST_ACCESS_RIGHTS_VECTOR		0x5200
+#define IA64_DATA_ACCESS_RIGHTS_VECTOR		0x5300
+#define IA64_GENEX_VECTOR			0x5400
+#define IA64_DISABLED_FPREG_VECTOR		0x5500
+#define IA64_NAT_CONSUMPTION_VECTOR		0x5600
+#define IA64_SPECULATION_VECTOR		0x5700 /* UNUSED */
+#define IA64_DEBUG_VECTOR			0x5900
+#define IA64_UNALIGNED_REF_VECTOR		0x5a00
+#define IA64_UNSUPPORTED_DATA_REF_VECTOR	0x5b00
+#define IA64_FP_FAULT_VECTOR			0x5c00
+#define IA64_FP_TRAP_VECTOR			0x5d00
+#define IA64_LOWERPRIV_TRANSFER_TRAP_VECTOR 	0x5e00
+#define IA64_TAKEN_BRANCH_TRAP_VECTOR		0x5f00
+#define IA64_SINGLE_STEP_TRAP_VECTOR		0x6000
+
+/* SDM vol2 5.5 - IVA based interruption handling */
+#define INITIAL_PSR_VALUE_AT_INTERRUPTION (IA64_PSR_UP | IA64_PSR_MFL |\
+			IA64_PSR_MFH | IA64_PSR_PK | IA64_PSR_DT |    	\
+			IA64_PSR_RT | IA64_PSR_MC|IA64_PSR_IT)
+
+#define DOMN_PAL_REQUEST    0x110000
+#define DOMN_SAL_REQUEST    0x110001
+
+static u64 vec2off[68] = {0x0, 0x400, 0x800, 0xc00, 0x1000, 0x1400, 0x1800,
+	0x1c00, 0x2000, 0x2400, 0x2800, 0x2c00, 0x3000, 0x3400, 0x3800, 0x3c00,
+	0x4000, 0x4400, 0x4800, 0x4c00, 0x5000, 0x5100, 0x5200, 0x5300, 0x5400,
+	0x5500, 0x5600, 0x5700, 0x5800, 0x5900, 0x5a00, 0x5b00, 0x5c00, 0x5d00,
+	0x5e00, 0x5f00, 0x6000, 0x6100, 0x6200, 0x6300, 0x6400, 0x6500, 0x6600,
+	0x6700, 0x6800, 0x6900, 0x6a00, 0x6b00, 0x6c00, 0x6d00, 0x6e00, 0x6f00,
+	0x7000, 0x7100, 0x7200, 0x7300, 0x7400, 0x7500, 0x7600, 0x7700, 0x7800,
+	0x7900, 0x7a00, 0x7b00, 0x7c00, 0x7d00, 0x7e00, 0x7f00
+};
+
+static void collect_interruption(struct kvm_vcpu *vcpu)
+{
+	u64 ipsr;
+	u64 vdcr;
+	u64 vifs;
+	unsigned long vpsr;
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+	vpsr = vcpu_get_psr(vcpu);
+	vcpu_bsw0(vcpu);
+	if (vpsr & IA64_PSR_IC) {
+
+		/* Sync mpsr id/da/dd/ss/ed bits to vipsr
+		 * since after guest do rfi, we still want these bits on in
+		 * mpsr
+		 */
+
+		ipsr = regs->cr_ipsr;
+		vpsr = vpsr | (ipsr & (IA64_PSR_ID | IA64_PSR_DA
+					| IA64_PSR_DD | IA64_PSR_SS
+					| IA64_PSR_ED));
+		vcpu_set_ipsr(vcpu, vpsr);
+
+		/* Currently, for trap, we do not advance IIP to next
+		 * instruction. That's because we assume caller already
+		 * set up IIP correctly
+		 */
+
+		vcpu_set_iip(vcpu , regs->cr_iip);
+
+		/* set vifs.v to zero */
+		vifs = VCPU(vcpu, ifs);
+		vifs &= ~IA64_IFS_V;
+		vcpu_set_ifs(vcpu, vifs);
+
+		vcpu_set_iipa(vcpu, VMX(vcpu, cr_iipa));
+	}
+
+	vdcr = VCPU(vcpu, dcr);
+
+	/* Set guest psr
+	 * up/mfl/mfh/pk/dt/rt/mc/it keeps unchanged
+	 * be: set to the value of dcr.be
+	 * pp: set to the value of dcr.pp
+	 */
+	vpsr &= INITIAL_PSR_VALUE_AT_INTERRUPTION;
+	vpsr |= (vdcr & IA64_DCR_BE);
+
+	/* VDCR pp bit position is different from VPSR pp bit */
+	if (vdcr & IA64_DCR_PP) {
+		vpsr |= IA64_PSR_PP;
+	} else {
+		vpsr &= ~IA64_PSR_PP;;
+	}
+
+	vcpu_set_psr(vcpu, vpsr);
+
+}
+
+void inject_guest_interruption(struct kvm_vcpu *vcpu, u64 vec)
+{
+	u64 viva;
+	struct kvm_pt_regs *regs;
+	union ia64_isr pt_isr;
+
+	regs = vcpu_regs(vcpu);
+
+	/* clear cr.isr.ir (incomplete register frame)*/
+	pt_isr.val = VMX(vcpu, cr_isr);
+	pt_isr.ir = 0;
+	VMX(vcpu, cr_isr) = pt_isr.val;
+
+	collect_interruption(vcpu);
+
+	viva = vcpu_get_iva(vcpu);
+	regs->cr_iip = viva + vec;
+}
+
+static u64 vcpu_get_itir_on_fault(struct kvm_vcpu *vcpu, u64 ifa)
+{
+	union ia64_rr rr, rr1;
+
+	rr.val = vcpu_get_rr(vcpu, ifa);
+	rr1.val = 0;
+	rr1.ps = rr.ps;
+	rr1.rid = rr.rid;
+	return (rr1.val);
+}
+
+
+/*
+ * Set vIFA & vITIR & vIHA, when vPSR.ic =1
+ * Parameter:
+ *  set_ifa: if true, set vIFA
+ *  set_itir: if true, set vITIR
+ *  set_iha: if true, set vIHA
+ */
+void set_ifa_itir_iha(struct kvm_vcpu *vcpu, u64 vadr,
+		int set_ifa, int set_itir, int set_iha)
+{
+	long vpsr;
+	u64 value;
+
+	vpsr = VCPU(vcpu, vpsr);
+	/* Vol2, Table 8-1 */
+	if (vpsr & IA64_PSR_IC) {
+		if (set_ifa)
+			vcpu_set_ifa(vcpu, vadr);
+		if (set_itir) {
+			value = vcpu_get_itir_on_fault(vcpu, vadr);
+			vcpu_set_itir(vcpu, value);
+		}
+
+		if (set_iha) {
+			value = vcpu_thash(vcpu, vadr);
+			vcpu_set_iha(vcpu, value);
+		}
+	}
+}
+
+/*
+ * Data TLB Fault
+ *  @ Data TLB vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void dtlb_fault(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	/* If vPSR.ic, IFA, ITIR, IHA */
+	set_ifa_itir_iha(vcpu, vadr, 1, 1, 1);
+	inject_guest_interruption(vcpu, IA64_DATA_TLB_VECTOR);
+}
+
+/*
+ * Instruction TLB Fault
+ *  @ Instruction TLB vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void itlb_fault(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	/* If vPSR.ic, IFA, ITIR, IHA */
+	set_ifa_itir_iha(vcpu, vadr, 1, 1, 1);
+	inject_guest_interruption(vcpu, IA64_INST_TLB_VECTOR);
+}
+
+
+
+/*
+ * Data Nested TLB Fault
+ *  @ Data Nested TLB Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void nested_dtlb(struct kvm_vcpu *vcpu)
+{
+	inject_guest_interruption(vcpu, IA64_DATA_NESTED_TLB_VECTOR);
+}
+
+/*
+ * Alternate Data TLB Fault
+ *  @ Alternate Data TLB vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void alt_dtlb(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	set_ifa_itir_iha(vcpu, vadr, 1, 1, 0);
+	inject_guest_interruption(vcpu, IA64_ALT_DATA_TLB_VECTOR);
+}
+
+
+/*
+ * Data TLB Fault
+ *  @ Data TLB vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void alt_itlb(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	set_ifa_itir_iha(vcpu, vadr, 1, 1, 0);
+	inject_guest_interruption(vcpu, IA64_ALT_INST_TLB_VECTOR);
+}
+
+/* Deal with:
+ *  VHPT Translation Vector
+ */
+static void _vhpt_fault(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	/* If vPSR.ic, IFA, ITIR, IHA*/
+	set_ifa_itir_iha(vcpu, vadr, 1, 1, 1);
+	inject_guest_interruption(vcpu, IA64_VHPT_TRANS_VECTOR);
+
+
+}
+
+/*
+ * VHPT Instruction Fault
+ *  @ VHPT Translation vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void ivhpt_fault(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	_vhpt_fault(vcpu, vadr);
+}
+
+
+/*
+ * VHPT Data Fault
+ *  @ VHPT Translation vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void dvhpt_fault(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	_vhpt_fault(vcpu, vadr);
+}
+
+
+
+/*
+ * Deal with:
+ *  General Exception vector
+ */
+void _general_exception(struct kvm_vcpu *vcpu)
+{
+	inject_guest_interruption(vcpu, IA64_GENEX_VECTOR);
+}
+
+
+/*
+ * Illegal Operation Fault
+ *  @ General Exception Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void illegal_op(struct kvm_vcpu *vcpu)
+{
+	_general_exception(vcpu);
+}
+
+/*
+ * Illegal Dependency Fault
+ *  @ General Exception Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void illegal_dep(struct kvm_vcpu *vcpu)
+{
+	_general_exception(vcpu);
+}
+
+/*
+ * Reserved Register/Field Fault
+ *  @ General Exception Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void rsv_reg_field(struct kvm_vcpu *vcpu)
+{
+	_general_exception(vcpu);
+}
+/*
+ * Privileged Operation Fault
+ *  @ General Exception Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+
+void privilege_op(struct kvm_vcpu *vcpu)
+{
+	_general_exception(vcpu);
+}
+
+/*
+ * Unimplement Data Address Fault
+ *  @ General Exception Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void unimpl_daddr(struct kvm_vcpu *vcpu)
+{
+	_general_exception(vcpu);
+}
+
+/*
+ * Privileged Register Fault
+ *  @ General Exception Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void privilege_reg(struct kvm_vcpu *vcpu)
+{
+	_general_exception(vcpu);
+}
+
+/* Deal with
+ *  Nat consumption vector
+ * Parameter:
+ *  vaddr: Optional, if t == REGISTER
+ */
+static void _nat_consumption_fault(struct kvm_vcpu *vcpu, u64 vadr,
+						enum tlb_miss_type t)
+{
+	/* If vPSR.ic && t == DATA/INST, IFA */
+	if (t == DATA || t == INSTRUCTION) {
+		/* IFA */
+		set_ifa_itir_iha(vcpu, vadr, 1, 0, 0);
+	}
+
+	inject_guest_interruption(vcpu, IA64_NAT_CONSUMPTION_VECTOR);
+}
+
+/*
+ * Instruction Nat Page Consumption Fault
+ *  @ Nat Consumption Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void inat_page_consumption(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	_nat_consumption_fault(vcpu, vadr, INSTRUCTION);
+}
+
+/*
+ * Register Nat Consumption Fault
+ *  @ Nat Consumption Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void rnat_consumption(struct kvm_vcpu *vcpu)
+{
+	_nat_consumption_fault(vcpu, 0, REGISTER);
+}
+
+/*
+ * Data Nat Page Consumption Fault
+ *  @ Nat Consumption Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void dnat_page_consumption(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	_nat_consumption_fault(vcpu, vadr, DATA);
+}
+
+/* Deal with
+ *  Page not present vector
+ */
+static void __page_not_present(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	/* If vPSR.ic, IFA, ITIR */
+	set_ifa_itir_iha(vcpu, vadr, 1, 1, 0);
+	inject_guest_interruption(vcpu, IA64_PAGE_NOT_PRESENT_VECTOR);
+}
+
+
+void data_page_not_present(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	__page_not_present(vcpu, vadr);
+}
+
+
+void inst_page_not_present(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	__page_not_present(vcpu, vadr);
+}
+
+
+/* Deal with
+ *  Data access rights vector
+ */
+void data_access_rights(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	/* If vPSR.ic, IFA, ITIR */
+	set_ifa_itir_iha(vcpu, vadr, 1, 1, 0);
+	inject_guest_interruption(vcpu, IA64_DATA_ACCESS_RIGHTS_VECTOR);
+}
+
+fpswa_ret_t vmm_fp_emulate(int fp_fault, void *bundle, unsigned long *ipsr,
+		unsigned long *fpsr, unsigned long *isr, unsigned long *pr,
+		unsigned long *ifs, struct kvm_pt_regs *regs)
+{
+	fp_state_t fp_state;
+	fpswa_ret_t ret;
+	struct kvm_vcpu *vcpu = current_vcpu;
+
+	uint64_t old_rr7 = ia64_get_rr(7UL<<61);
+
+	if (!vmm_fpswa_interface)
+		return (fpswa_ret_t) {-1, 0, 0, 0};
+
+	/*
+	 * Just let fpswa driver to use hardware fp registers.
+	 * No fp register is valid in memory.
+	 */
+	memset(&fp_state, 0, sizeof(fp_state_t));
+
+	/*
+	 * unsigned long (*EFI_FPSWA) (
+	 *      unsigned long    trap_type,
+	 *      void             *Bundle,
+	 *      unsigned long    *pipsr,
+	 *      unsigned long    *pfsr,
+	 *      unsigned long    *pisr,
+	 *      unsigned long    *ppreds,
+	 *      unsigned long    *pifs,
+	 *      void             *fp_state);
+	 */
+	/*Call host fpswa interface directly to virtualize
+	 *guest fpswa request!
+	 */
+	ia64_set_rr(7UL << 61, vcpu->arch.host.rr[7]);
+	ia64_srlz_d();
+
+	ret = (*vmm_fpswa_interface->fpswa) (fp_fault, bundle,
+			ipsr, fpsr, isr, pr, ifs, &fp_state);
+	ia64_set_rr(7UL << 61, old_rr7);
+	ia64_srlz_d();
+	return ret;
+}
+
+/*
+ * Handle floating-point assist faults and traps for domain.
+ */
+unsigned long vmm_handle_fpu_swa(int fp_fault, struct kvm_pt_regs *regs,
+					unsigned long isr)
+{
+	struct kvm_vcpu *v = current_vcpu;
+	IA64_BUNDLE bundle;
+	unsigned long fault_ip;
+	fpswa_ret_t ret;
+
+	fault_ip = regs->cr_iip;
+	/*
+	 * When the FP trap occurs, the trapping instruction is completed.
+	 * If ipsr.ri == 0, there is the trapping instruction in previous
+	 * bundle.
+	 */
+	if (!fp_fault && (ia64_psr(regs)->ri == 0))
+		fault_ip -= 16;
+
+	if (fetch_code(v, fault_ip, &bundle))
+		return -EAGAIN;
+
+	if (!bundle.i64[0] && !bundle.i64[1])
+		return -EACCES;
+
+	ret = vmm_fp_emulate(fp_fault, &bundle, &regs->cr_ipsr, &regs->ar_fpsr,
+			&isr, &regs->pr, &regs->cr_ifs, regs);
+	return ret.status;
+}
+
+void reflect_interruption(u64 ifa, u64 isr, u64 iim,
+		u64 vec, struct kvm_pt_regs *regs)
+{
+	u64 vector;
+	int status ;
+	struct kvm_vcpu *vcpu = current_vcpu;
+	u64 vpsr = VCPU(vcpu, vpsr);
+
+	vector = vec2off[vec];
+
+	if (!(vpsr & IA64_PSR_IC) && (vector != IA64_DATA_NESTED_TLB_VECTOR)) {
+		panic_vm(vcpu);
+		return;
+	}
+
+	switch (vec) {
+	case 32: 	/*IA64_FP_FAULT_VECTOR*/
+		status = vmm_handle_fpu_swa(1, regs, isr);
+		if (!status) {
+			vcpu_increment_iip(vcpu);
+			return;
+		} else if (-EAGAIN == status)
+			return;
+		break;
+	case 33:	/*IA64_FP_TRAP_VECTOR*/
+		status = vmm_handle_fpu_swa(0, regs, isr);
+		if (!status)
+			return ;
+		else if (-EAGAIN == status) {
+			vcpu_decrement_iip(vcpu);
+			return ;
+		}
+		break;
+	}
+
+	VCPU(vcpu, isr) = isr;
+	VCPU(vcpu, iipa) = regs->cr_iip;
+	if (vector == IA64_BREAK_VECTOR || vector == IA64_SPECULATION_VECTOR)
+		VCPU(vcpu, iim) = iim;
+	else
+		set_ifa_itir_iha(vcpu, ifa, 1, 1, 1);
+
+	inject_guest_interruption(vcpu, vector);
+}
+
+static void set_pal_call_data(struct kvm_vcpu *vcpu)
+{
+	struct exit_ctl_data *p = &vcpu->arch.exit_data;
+
+	/*FIXME:For static and stacked convention, firmware
+	 * has put the parameters in gr28-gr31 before
+	 * break to vmm  !!*/
+
+	p->u.pal_data.gr28 = vcpu_get_gr(vcpu, 28);
+	p->u.pal_data.gr29 = vcpu_get_gr(vcpu, 29);
+	p->u.pal_data.gr30 = vcpu_get_gr(vcpu, 30);
+	p->u.pal_data.gr31 = vcpu_get_gr(vcpu, 31);
+	p->exit_reason = EXIT_REASON_PAL_CALL;
+}
+
+static void set_pal_call_result(struct kvm_vcpu *vcpu)
+{
+	struct exit_ctl_data *p = &vcpu->arch.exit_data;
+
+	if (p->exit_reason == EXIT_REASON_PAL_CALL) {
+		vcpu_set_gr(vcpu, 8, p->u.pal_data.ret.status, 0);
+		vcpu_set_gr(vcpu, 9, p->u.pal_data.ret.v0, 0);
+		vcpu_set_gr(vcpu, 10, p->u.pal_data.ret.v1, 0);
+		vcpu_set_gr(vcpu, 11, p->u.pal_data.ret.v2, 0);
+	} else
+		panic_vm(vcpu);
+}
+
+static void set_sal_call_data(struct kvm_vcpu *vcpu)
+{
+	struct exit_ctl_data *p = &vcpu->arch.exit_data;
+
+	p->u.sal_data.in0 = vcpu_get_gr(vcpu, 32);
+	p->u.sal_data.in1 = vcpu_get_gr(vcpu, 33);
+	p->u.sal_data.in2 = vcpu_get_gr(vcpu, 34);
+	p->u.sal_data.in3 = vcpu_get_gr(vcpu, 35);
+	p->u.sal_data.in4 = vcpu_get_gr(vcpu, 36);
+	p->u.sal_data.in5 = vcpu_get_gr(vcpu, 37);
+	p->u.sal_data.in6 = vcpu_get_gr(vcpu, 38);
+	p->u.sal_data.in7 = vcpu_get_gr(vcpu, 39);
+	p->exit_reason = EXIT_REASON_SAL_CALL;
+}
+
+static void set_sal_call_result(struct kvm_vcpu *vcpu)
+{
+	struct exit_ctl_data *p = &vcpu->arch.exit_data;
+
+	if (p->exit_reason == EXIT_REASON_SAL_CALL) {
+		vcpu_set_gr(vcpu, 8, p->u.sal_data.ret.r8, 0);
+		vcpu_set_gr(vcpu, 9, p->u.sal_data.ret.r9, 0);
+		vcpu_set_gr(vcpu, 10, p->u.sal_data.ret.r10, 0);
+		vcpu_set_gr(vcpu, 11, p->u.sal_data.ret.r11, 0);
+	} else
+		panic_vm(vcpu);
+}
+
+void  kvm_ia64_handle_break(unsigned long ifa, struct kvm_pt_regs *regs,
+		unsigned long isr, unsigned long iim)
+{
+	struct kvm_vcpu *v = current_vcpu;
+
+	if (ia64_psr(regs)->cpl == 0) {
+		/* Allow hypercalls only when cpl = 0.  */
+		if (iim == DOMN_PAL_REQUEST) {
+			set_pal_call_data(v);
+			vmm_transition(v);
+			set_pal_call_result(v);
+			vcpu_increment_iip(v);
+			return;
+		} else if (iim == DOMN_SAL_REQUEST) {
+			set_sal_call_data(v);
+			vmm_transition(v);
+			set_sal_call_result(v);
+			vcpu_increment_iip(v);
+			return;
+		}
+	}
+	reflect_interruption(ifa, isr, iim, 11, regs);
+}
+
+void check_pending_irq(struct kvm_vcpu *vcpu)
+{
+	int  mask, h_pending, h_inservice;
+	u64 isr;
+	unsigned long  vpsr;
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+	h_pending = highest_pending_irq(vcpu);
+	if (h_pending == NULL_VECTOR) {
+		update_vhpi(vcpu, NULL_VECTOR);
+		return;
+	}
+	h_inservice = highest_inservice_irq(vcpu);
+
+	vpsr = VCPU(vcpu, vpsr);
+	mask = irq_masked(vcpu, h_pending, h_inservice);
+	if ((vpsr & IA64_PSR_I) && IRQ_NO_MASKED == mask) {
+		isr = vpsr & IA64_PSR_RI;
+		update_vhpi(vcpu, h_pending);
+		reflect_interruption(0, isr, 0, 12, regs); /* EXT IRQ */
+	} else if (mask == IRQ_MASKED_BY_INSVC) {
+		if (VCPU(vcpu, vhpi))
+			update_vhpi(vcpu, NULL_VECTOR);
+	} else {
+		/* masked by vpsr.i or vtpr.*/
+		update_vhpi(vcpu, h_pending);
+	}
+}
+
+static void generate_exirq(struct kvm_vcpu *vcpu)
+{
+	unsigned  vpsr;
+	uint64_t isr;
+
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+	vpsr = VCPU(vcpu, vpsr);
+	isr = vpsr & IA64_PSR_RI;
+	if (!(vpsr & IA64_PSR_IC))
+		panic_vm(vcpu);
+	reflect_interruption(0, isr, 0, 12, regs); /* EXT IRQ */
+}
+
+void vhpi_detection(struct kvm_vcpu *vcpu)
+{
+	uint64_t    threshold, vhpi;
+	union ia64_tpr       vtpr;
+	struct ia64_psr vpsr;
+
+	vpsr = *(struct ia64_psr *)&VCPU(vcpu, vpsr);
+	vtpr.val = VCPU(vcpu, tpr);
+
+	threshold = ((!vpsr.i) << 5) | (vtpr.mmi << 4) | vtpr.mic;
+	vhpi = VCPU(vcpu, vhpi);
+	if (vhpi > threshold) {
+		/* interrupt actived*/
+		generate_exirq(vcpu);
+	}
+}
+
+
+void leave_hypervisor_tail(void)
+{
+	struct kvm_vcpu *v = current_vcpu;
+
+	if (VMX(v, timer_check)) {
+		VMX(v, timer_check) = 0;
+		if (VMX(v, itc_check)) {
+			if (vcpu_get_itc(v) > VCPU(v, itm)) {
+				if (!(VCPU(v, itv) & (1 << 16))) {
+					vcpu_pend_interrupt(v, VCPU(v, itv)
+							& 0xff);
+				VMX(v, itc_check) = 0;
+				} else {
+					v->arch.timer_pending = 1;
+				}
+				VMX(v, last_itc) = VCPU(v, itm) + 1;
+			}
+		}
+	}
+
+	rmb();
+	if (v->arch.irq_new_pending) {
+		v->arch.irq_new_pending = 0;
+		VMX(v, irq_check) = 0;
+		check_pending_irq(v);
+		return;
+	}
+	if (VMX(v, irq_check)) {
+		VMX(v, irq_check) = 0;
+		vhpi_detection(v);
+	}
+}
+
+
+static inline void handle_lds(struct kvm_pt_regs *regs)
+{
+	regs->cr_ipsr |= IA64_PSR_ED;
+}
+
+void physical_tlb_miss(struct kvm_vcpu *vcpu, unsigned long vadr, int type)
+{
+	unsigned long pte;
+	union ia64_rr rr;
+
+	rr.val = ia64_get_rr(vadr);
+	pte =  vadr & _PAGE_PPN_MASK;
+	pte = pte | PHY_PAGE_WB;
+	thash_vhpt_insert(vcpu, pte, (u64)(rr.ps << 2), vadr, type);
+	return;
+}
+
+void kvm_page_fault(u64 vadr , u64 vec, struct kvm_pt_regs *regs)
+{
+	unsigned long vpsr;
+	int type;
+
+	u64 vhpt_adr, gppa, pteval, rr, itir;
+	union ia64_isr misr;
+	union ia64_pta vpta;
+	struct thash_data *data;
+	struct kvm_vcpu *v = current_vcpu;
+
+	vpsr = VCPU(v, vpsr);
+	misr.val = VMX(v, cr_isr);
+
+	type = vec;
+
+	if (is_physical_mode(v) && (!(vadr << 1 >> 62))) {
+		if (vec == 2) {
+			if (__gpfn_is_io((vadr << 1) >> (PAGE_SHIFT + 1))) {
+				emulate_io_inst(v, ((vadr << 1) >> 1), 4);
+				return;
+			}
+		}
+		physical_tlb_miss(v, vadr, type);
+		return;
+	}
+	data = vtlb_lookup(v, vadr, type);
+	if (data != 0) {
+		if (type == D_TLB) {
+			gppa = (vadr & ((1UL << data->ps) - 1))
+				+ (data->ppn >> (data->ps - 12) << data->ps);
+			if (__gpfn_is_io(gppa >> PAGE_SHIFT)) {
+				if (data->pl >= ((regs->cr_ipsr >>
+						IA64_PSR_CPL0_BIT) & 3))
+					emulate_io_inst(v, gppa, data->ma);
+				else {
+					vcpu_set_isr(v, misr.val);
+					data_access_rights(v, vadr);
+				}
+				return ;
+			}
+		}
+		thash_vhpt_insert(v, data->page_flags, data->itir, vadr, type);
+
+	} else if (type == D_TLB) {
+		if (misr.sp) {
+			handle_lds(regs);
+			return;
+		}
+
+		rr = vcpu_get_rr(v, vadr);
+		itir = rr & (RR_RID_MASK | RR_PS_MASK);
+
+		if (!vhpt_enabled(v, vadr, misr.rs ? RSE_REF : DATA_REF)) {
+			if (vpsr & IA64_PSR_IC) {
+				vcpu_set_isr(v, misr.val);
+				alt_dtlb(v, vadr);
+			} else {
+				nested_dtlb(v);
+			}
+			return ;
+		}
+
+		vpta.val = vcpu_get_pta(v);
+		/* avoid recursively walking (short format) VHPT */
+
+		vhpt_adr = vcpu_thash(v, vadr);
+		if (!guest_vhpt_lookup(vhpt_adr, &pteval)) {
+			/* VHPT successfully read.  */
+			if (!(pteval & _PAGE_P)) {
+				if (vpsr & IA64_PSR_IC) {
+					vcpu_set_isr(v, misr.val);
+					dtlb_fault(v, vadr);
+				} else {
+					nested_dtlb(v);
+				}
+			} else if ((pteval & _PAGE_MA_MASK) != _PAGE_MA_ST) {
+				thash_purge_and_insert(v, pteval, itir,
+								vadr, D_TLB);
+			} else if (vpsr & IA64_PSR_IC) {
+				vcpu_set_isr(v, misr.val);
+				dtlb_fault(v, vadr);
+			} else {
+				nested_dtlb(v);
+			}
+		} else {
+			/* Can't read VHPT.  */
+			if (vpsr & IA64_PSR_IC) {
+				vcpu_set_isr(v, misr.val);
+				dvhpt_fault(v, vadr);
+			} else {
+				nested_dtlb(v);
+			}
+		}
+	} else if (type == I_TLB) {
+		if (!(vpsr & IA64_PSR_IC))
+			misr.ni = 1;
+		if (!vhpt_enabled(v, vadr, INST_REF)) {
+			vcpu_set_isr(v, misr.val);
+			alt_itlb(v, vadr);
+			return;
+		}
+
+		vpta.val = vcpu_get_pta(v);
+
+		vhpt_adr = vcpu_thash(v, vadr);
+		if (!guest_vhpt_lookup(vhpt_adr, &pteval)) {
+			/* VHPT successfully read.  */
+			if (pteval & _PAGE_P) {
+				if ((pteval & _PAGE_MA_MASK) == _PAGE_MA_ST) {
+					vcpu_set_isr(v, misr.val);
+					itlb_fault(v, vadr);
+					return ;
+				}
+				rr = vcpu_get_rr(v, vadr);
+				itir = rr & (RR_RID_MASK | RR_PS_MASK);
+				thash_purge_and_insert(v, pteval, itir,
+							vadr, I_TLB);
+			} else {
+				vcpu_set_isr(v, misr.val);
+				inst_page_not_present(v, vadr);
+			}
+		} else {
+			vcpu_set_isr(v, misr.val);
+			ivhpt_fault(v, vadr);
+		}
+	}
+}
+
+void kvm_vexirq(struct kvm_vcpu *vcpu)
+{
+	u64 vpsr, isr;
+	struct kvm_pt_regs *regs;
+
+	regs = vcpu_regs(vcpu);
+	vpsr = VCPU(vcpu, vpsr);
+	isr = vpsr & IA64_PSR_RI;
+	reflect_interruption(0, isr, 0, 12, regs); /*EXT IRQ*/
+}
+
+void kvm_ia64_handle_irq(struct kvm_vcpu *v)
+{
+	struct exit_ctl_data *p = &v->arch.exit_data;
+	long psr;
+
+	local_irq_save(psr);
+	p->exit_reason = EXIT_REASON_EXTERNAL_INTERRUPT;
+	vmm_transition(v);
+	local_irq_restore(psr);
+
+	VMX(v, timer_check) = 1;
+
+}
+
+static void ptc_ga_remote_func(struct kvm_vcpu *v, int pos)
+{
+	u64 oldrid, moldrid, oldpsbits, vaddr;
+	struct kvm_ptc_g *p = &v->arch.ptc_g_data[pos];
+	vaddr = p->vaddr;
+
+	oldrid = VMX(v, vrr[0]);
+	VMX(v, vrr[0]) = p->rr;
+	oldpsbits = VMX(v, psbits[0]);
+	VMX(v, psbits[0]) = VMX(v, psbits[REGION_NUMBER(vaddr)]);
+	moldrid = ia64_get_rr(0x0);
+	ia64_set_rr(0x0, vrrtomrr(p->rr));
+	ia64_srlz_d();
+
+	vaddr = PAGEALIGN(vaddr, p->ps);
+	thash_purge_entries_remote(v, vaddr, p->ps);
+
+	VMX(v, vrr[0]) = oldrid;
+	VMX(v, psbits[0]) = oldpsbits;
+	ia64_set_rr(0x0, moldrid);
+	ia64_dv_serialize_data();
+}
+
+static void vcpu_do_resume(struct kvm_vcpu *vcpu)
+{
+	/*Re-init VHPT and VTLB once from resume*/
+	vcpu->arch.vhpt.num = VHPT_NUM_ENTRIES;
+	thash_init(&vcpu->arch.vhpt, VHPT_SHIFT);
+	vcpu->arch.vtlb.num = VTLB_NUM_ENTRIES;
+	thash_init(&vcpu->arch.vtlb, VTLB_SHIFT);
+
+	ia64_set_pta(vcpu->arch.vhpt.pta.val);
+}
+
+static void kvm_do_resume_op(struct kvm_vcpu *vcpu)
+{
+	if (test_and_clear_bit(KVM_REQ_RESUME, &vcpu->requests)) {
+		vcpu_do_resume(vcpu);
+		return;
+	}
+
+	if (unlikely(test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))) {
+		thash_purge_all(vcpu);
+		return;
+	}
+
+	if (test_and_clear_bit(KVM_REQ_PTC_G, &vcpu->requests)) {
+		while (vcpu->arch.ptc_g_count > 0)
+			ptc_ga_remote_func(vcpu, --vcpu->arch.ptc_g_count);
+	}
+}
+
+void vmm_transition(struct kvm_vcpu *vcpu)
+{
+	ia64_call_vsa(PAL_VPS_SAVE, (unsigned long)vcpu->arch.vpd,
+			0, 0, 0, 0, 0, 0);
+	vmm_trampoline(&vcpu->arch.guest, &vcpu->arch.host);
+	ia64_call_vsa(PAL_VPS_RESTORE, (unsigned long)vcpu->arch.vpd,
+						0, 0, 0, 0, 0, 0);
+	kvm_do_resume_op(vcpu);
+}
diff --git a/trunk/arch/ia64/kvm/trampoline.S b/trunk/arch/ia64/kvm/trampoline.S
new file mode 100644
index 000000000000..30897d44d61e
--- /dev/null
+++ b/trunk/arch/ia64/kvm/trampoline.S
@@ -0,0 +1,1038 @@
+/* Save all processor states
+ *
+ * Copyright (c) 2007 Fleming Feng <fleming.feng@intel.com>
+ * Copyright (c) 2007 Anthony Xu   <anthony.xu@intel.com>
+ */
+
+#include <asm/asmmacro.h>
+#include "asm-offsets.h"
+
+
+#define CTX(name)    VMM_CTX_##name##_OFFSET
+
+	/*
+	 *	r32:		context_t base address
+	 */
+#define	SAVE_BRANCH_REGS			\
+	add	r2 = CTX(B0),r32;		\
+	add	r3 = CTX(B1),r32;		\
+	mov	r16 = b0;			\
+	mov	r17 = b1;			\
+	;;					\
+	st8	[r2]=r16,16;			\
+	st8	[r3]=r17,16;			\
+	;;					\
+	mov	r16 = b2;			\
+	mov	r17 = b3;			\
+	;;					\
+	st8	[r2]=r16,16;			\
+	st8	[r3]=r17,16;			\
+	;;					\
+	mov	r16 = b4;			\
+	mov	r17 = b5;			\
+	;;					\
+	st8	[r2]=r16;   			\
+	st8	[r3]=r17;   			\
+	;;
+
+	/*
+	 *	r33:		context_t base address
+	 */
+#define	RESTORE_BRANCH_REGS			\
+	add	r2 = CTX(B0),r33;		\
+	add	r3 = CTX(B1),r33;		\
+	;;					\
+	ld8	r16=[r2],16;			\
+	ld8	r17=[r3],16;			\
+	;;					\
+	mov	b0 = r16;			\
+	mov	b1 = r17;			\
+	;;					\
+	ld8	r16=[r2],16;			\
+	ld8	r17=[r3],16;			\
+	;;					\
+	mov	b2 = r16;			\
+	mov	b3 = r17;			\
+	;;					\
+	ld8	r16=[r2];   			\
+	ld8	r17=[r3];   			\
+	;;					\
+	mov	b4=r16;				\
+	mov	b5=r17;				\
+	;;
+
+
+	/*
+	 *	r32: context_t base address
+	 *	bsw == 1
+	 *	Save all bank1 general registers, r4 ~ r7
+	 */
+#define	SAVE_GENERAL_REGS			\
+	add	r2=CTX(R4),r32;			\
+	add	r3=CTX(R5),r32;			\
+	;;					\
+.mem.offset 0,0;        			\
+	st8.spill	[r2]=r4,16;		\
+.mem.offset 8,0;        			\
+	st8.spill	[r3]=r5,16;		\
+	;;					\
+.mem.offset 0,0;        			\
+	st8.spill	[r2]=r6,48;		\
+.mem.offset 8,0;        			\
+	st8.spill	[r3]=r7,48;		\
+	;;                          		\
+.mem.offset 0,0;        			\
+    st8.spill    [r2]=r12;			\
+.mem.offset 8,0;				\
+    st8.spill    [r3]=r13;			\
+    ;;
+
+	/*
+	 *	r33: context_t base address
+	 *	bsw == 1
+	 */
+#define	RESTORE_GENERAL_REGS			\
+	add	r2=CTX(R4),r33;			\
+	add	r3=CTX(R5),r33;			\
+	;;					\
+	ld8.fill	r4=[r2],16;		\
+	ld8.fill	r5=[r3],16;		\
+	;;					\
+	ld8.fill	r6=[r2],48;		\
+	ld8.fill	r7=[r3],48;		\
+	;;					\
+	ld8.fill    r12=[r2];			\
+	ld8.fill    r13 =[r3];			\
+	;;
+
+
+
+
+	/*
+	 *	r32:		context_t base address
+	 */
+#define	SAVE_KERNEL_REGS			\
+	add	r2 = CTX(KR0),r32;		\
+	add	r3 = CTX(KR1),r32;		\
+	mov	r16 = ar.k0;			\
+	mov	r17 = ar.k1;			\
+	;;		        		\
+	st8	[r2] = r16,16;			\
+	st8	[r3] = r17,16;			\
+	;;		        		\
+	mov	r16 = ar.k2;			\
+	mov	r17 = ar.k3;			\
+	;;		        		\
+	st8	[r2] = r16,16;			\
+	st8	[r3] = r17,16;			\
+	;;					\
+	mov	r16 = ar.k4;			\
+	mov	r17 = ar.k5;			\
+	;;				    	\
+	st8	[r2] = r16,16;			\
+	st8	[r3] = r17,16;			\
+	;;					\
+	mov	r16 = ar.k6;			\
+	mov	r17 = ar.k7;			\
+	;;		    			\
+	st8	[r2] = r16;     		\
+	st8	[r3] = r17;			\
+	;;
+
+
+
+	/*
+	 *	r33:		context_t base address
+	 */
+#define	RESTORE_KERNEL_REGS			\
+	add	r2 = CTX(KR0),r33;		\
+	add	r3 = CTX(KR1),r33;		\
+	;;		    			\
+	ld8	r16=[r2],16;     		\
+	ld8	r17=[r3],16;			\
+	;;					\
+	mov	ar.k0=r16;  			\
+	mov	ar.k1=r17;	    		\
+	;;		        		\
+	ld8	r16=[r2],16;			\
+	ld8	r17=[r3],16;			\
+	;;		        		\
+	mov	ar.k2=r16;   			\
+	mov	ar.k3=r17;	    		\
+	;;		        		\
+	ld8	r16=[r2],16;			\
+	ld8	r17=[r3],16;			\
+	;;					\
+	mov	ar.k4=r16;			\
+	mov	ar.k5=r17;	    		\
+	;;				    	\
+	ld8	r16=[r2],16;			\
+	ld8	r17=[r3],16;			\
+	;;					\
+	mov	ar.k6=r16;  			\
+	mov	ar.k7=r17;	    		\
+	;;
+
+
+
+	/*
+	 *	r32:		context_t base address
+	 */
+#define	SAVE_APP_REGS				\
+	add  r2 = CTX(BSPSTORE),r32;		\
+	mov  r16 = ar.bspstore;			\
+	;;					\
+	st8  [r2] = r16,CTX(RNAT)-CTX(BSPSTORE);\
+	mov  r16 = ar.rnat;			\
+	;;					\
+	st8  [r2] = r16,CTX(FCR)-CTX(RNAT);	\
+	mov  r16 = ar.fcr;			\
+	;;					\
+	st8  [r2] = r16,CTX(EFLAG)-CTX(FCR);	\
+	mov  r16 = ar.eflag;			\
+	;;					\
+	st8  [r2] = r16,CTX(CFLG)-CTX(EFLAG);	\
+	mov  r16 = ar.cflg;			\
+	;;					\
+	st8  [r2] = r16,CTX(FSR)-CTX(CFLG);	\
+	mov  r16 = ar.fsr;			\
+	;;					\
+	st8  [r2] = r16,CTX(FIR)-CTX(FSR);	\
+	mov  r16 = ar.fir;			\
+	;;					\
+	st8  [r2] = r16,CTX(FDR)-CTX(FIR);	\
+	mov  r16 = ar.fdr;			\
+	;;					\
+	st8  [r2] = r16,CTX(UNAT)-CTX(FDR);	\
+	mov  r16 = ar.unat;			\
+	;;					\
+	st8  [r2] = r16,CTX(FPSR)-CTX(UNAT);	\
+	mov  r16 = ar.fpsr;			\
+	;;					\
+	st8  [r2] = r16,CTX(PFS)-CTX(FPSR);	\
+	mov  r16 = ar.pfs;			\
+	;;					\
+	st8  [r2] = r16,CTX(LC)-CTX(PFS);	\
+	mov  r16 = ar.lc;			\
+	;;					\
+	st8  [r2] = r16;			\
+	;;
+
+	/*
+	 *	r33:		context_t base address
+	 */
+#define	RESTORE_APP_REGS			\
+	add  r2=CTX(BSPSTORE),r33;		\
+	;;					\
+	ld8  r16=[r2],CTX(RNAT)-CTX(BSPSTORE);	\
+	;;					\
+	mov  ar.bspstore=r16;			\
+	ld8  r16=[r2],CTX(FCR)-CTX(RNAT);	\
+	;;					\
+	mov  ar.rnat=r16;			\
+	ld8  r16=[r2],CTX(EFLAG)-CTX(FCR);	\
+	;;					\
+	mov  ar.fcr=r16;			\
+	ld8  r16=[r2],CTX(CFLG)-CTX(EFLAG);	\
+	;;					\
+	mov  ar.eflag=r16;			\
+	ld8  r16=[r2],CTX(FSR)-CTX(CFLG);	\
+	;;					\
+	mov  ar.cflg=r16;			\
+	ld8  r16=[r2],CTX(FIR)-CTX(FSR);	\
+	;;					\
+	mov  ar.fsr=r16;			\
+	ld8  r16=[r2],CTX(FDR)-CTX(FIR);	\
+	;;					\
+	mov  ar.fir=r16;			\
+	ld8  r16=[r2],CTX(UNAT)-CTX(FDR);	\
+	;;					\
+	mov  ar.fdr=r16;			\
+	ld8  r16=[r2],CTX(FPSR)-CTX(UNAT);	\
+	;;					\
+	mov  ar.unat=r16;			\
+	ld8  r16=[r2],CTX(PFS)-CTX(FPSR);	\
+	;;					\
+	mov  ar.fpsr=r16;			\
+	ld8  r16=[r2],CTX(LC)-CTX(PFS);		\
+	;;					\
+	mov  ar.pfs=r16;			\
+	ld8  r16=[r2];				\
+	;;					\
+	mov  ar.lc=r16;				\
+	;;
+
+	/*
+	 *	r32:		context_t base address
+	 */
+#define	SAVE_CTL_REGS				\
+	add	r2 = CTX(DCR),r32;		\
+	mov	r16 = cr.dcr;			\
+	;;					\
+	st8	[r2] = r16,CTX(IVA)-CTX(DCR);	\
+	;;                          		\
+	mov	r16 = cr.iva;			\
+	;;					\
+	st8	[r2] = r16,CTX(PTA)-CTX(IVA);	\
+	;;					\
+	mov r16 = cr.pta;			\
+	;;					\
+	st8 [r2] = r16 ;			\
+	;;
+
+	/*
+	 *	r33:		context_t base address
+	 */
+#define	RESTORE_CTL_REGS				\
+	add	r2 = CTX(DCR),r33;	        	\
+	;;						\
+	ld8	r16 = [r2],CTX(IVA)-CTX(DCR);		\
+	;;                      			\
+	mov	cr.dcr = r16;				\
+	dv_serialize_data;				\
+	;;						\
+	ld8	r16 = [r2],CTX(PTA)-CTX(IVA);		\
+	;;						\
+	mov	cr.iva = r16;				\
+	dv_serialize_data;				\
+	;;						\
+	ld8 r16 = [r2];					\
+	;;						\
+	mov cr.pta = r16;				\
+	dv_serialize_data;				\
+	;;
+
+
+	/*
+	 *	r32:		context_t base address
+	 */
+#define	SAVE_REGION_REGS			\
+	add	r2=CTX(RR0),r32;		\
+	mov	r16=rr[r0];			\
+	dep.z	r18=1,61,3;			\
+	;;					\
+	st8	[r2]=r16,8;			\
+	mov	r17=rr[r18];			\
+	dep.z	r18=2,61,3;			\
+	;;					\
+	st8	[r2]=r17,8;			\
+	mov	r16=rr[r18];			\
+	dep.z	r18=3,61,3;			\
+	;;					\
+	st8	[r2]=r16,8;			\
+	mov	r17=rr[r18];			\
+	dep.z	r18=4,61,3;			\
+	;;					\
+	st8	[r2]=r17,8;			\
+	mov	r16=rr[r18];			\
+	dep.z	r18=5,61,3;			\
+	;;					\
+	st8	[r2]=r16,8;			\
+	mov	r17=rr[r18];			\
+	dep.z	r18=7,61,3;			\
+	;;					\
+	st8	[r2]=r17,16;			\
+	mov	r16=rr[r18];			\
+	;;					\
+	st8	[r2]=r16,8;			\
+	;;
+
+	/*
+	 *	r33:context_t base address
+	 */
+#define	RESTORE_REGION_REGS	\
+	add	r2=CTX(RR0),r33;\
+	mov r18=r0;		\
+	;;			\
+	ld8	r20=[r2],8;	\
+	;;	/* rr0 */	\
+	ld8	r21=[r2],8;	\
+	;;	/* rr1 */	\
+	ld8	r22=[r2],8;	\
+	;;	/* rr2 */	\
+	ld8	r23=[r2],8;	\
+	;;	/* rr3 */	\
+	ld8	r24=[r2],8;	\
+	;;	/* rr4 */	\
+	ld8	r25=[r2],16;	\
+	;;	/* rr5 */	\
+	ld8	r27=[r2];	\
+	;;	/* rr7 */	\
+	mov rr[r18]=r20;	\
+	dep.z	r18=1,61,3;	\
+	;;  /* rr1 */		\
+	mov rr[r18]=r21;	\
+	dep.z	r18=2,61,3;	\
+	;;  /* rr2 */		\
+	mov rr[r18]=r22;	\
+	dep.z	r18=3,61,3;	\
+	;;  /* rr3 */		\
+	mov rr[r18]=r23;	\
+	dep.z	r18=4,61,3;	\
+	;;  /* rr4 */		\
+	mov rr[r18]=r24;	\
+	dep.z	r18=5,61,3;	\
+	;;  /* rr5 */		\
+	mov rr[r18]=r25;	\
+	dep.z	r18=7,61,3;	\
+	;;  /* rr7 */		\
+	mov rr[r18]=r27;	\
+	;;			\
+	srlz.i;			\
+	;;
+
+
+
+	/*
+	 *	r32:	context_t base address
+	 *	r36~r39:scratch registers
+	 */
+#define	SAVE_DEBUG_REGS				\
+	add	r2=CTX(IBR0),r32;		\
+	add	r3=CTX(DBR0),r32;		\
+	mov	r16=ibr[r0];			\
+	mov	r17=dbr[r0];			\
+	;;					\
+	st8	[r2]=r16,8; 			\
+	st8	[r3]=r17,8;	    		\
+	add	r18=1,r0;		    	\
+	;;					\
+	mov	r16=ibr[r18];			\
+	mov	r17=dbr[r18];			\
+	;;					\
+	st8	[r2]=r16,8;		    	\
+	st8	[r3]=r17,8;			\
+	add	r18=2,r0;			\
+	;;					\
+	mov	r16=ibr[r18];			\
+	mov	r17=dbr[r18];			\
+	;;					\
+	st8	[r2]=r16,8;		    	\
+	st8	[r3]=r17,8;			\
+	add	r18=2,r0;			\
+	;;					\
+	mov	r16=ibr[r18];			\
+	mov	r17=dbr[r18];			\
+	;;					\
+	st8	[r2]=r16,8;		    	\
+	st8	[r3]=r17,8;			\
+	add	r18=3,r0;			\
+	;;					\
+	mov	r16=ibr[r18];			\
+	mov	r17=dbr[r18];			\
+	;;					\
+	st8	[r2]=r16,8;		    	\
+	st8	[r3]=r17,8;			\
+	add	r18=4,r0;			\
+	;;					\
+	mov	r16=ibr[r18];			\
+	mov	r17=dbr[r18];			\
+	;;					\
+	st8	[r2]=r16,8;		    	\
+	st8	[r3]=r17,8;			\
+	add	r18=5,r0;			\
+	;;					\
+	mov	r16=ibr[r18];			\
+	mov	r17=dbr[r18];			\
+	;;					\
+	st8	[r2]=r16,8;		    	\
+	st8	[r3]=r17,8;			\
+	add	r18=6,r0;			\
+	;;					\
+	mov	r16=ibr[r18];			\
+	mov	r17=dbr[r18];			\
+	;;					\
+	st8	[r2]=r16,8;		    	\
+	st8	[r3]=r17,8;			\
+	add	r18=7,r0;			\
+	;;					\
+	mov	r16=ibr[r18];			\
+	mov	r17=dbr[r18];			\
+	;;					\
+	st8	[r2]=r16,8;		    	\
+	st8	[r3]=r17,8;			\
+	;;
+
+
+/*
+ *      r33:    point to context_t structure
+ *      ar.lc are corrupted.
+ */
+#define RESTORE_DEBUG_REGS			\
+	add	r2=CTX(IBR0),r33;		\
+	add	r3=CTX(DBR0),r33;		\
+	mov r16=7;    				\
+	mov r17=r0;				\
+	;;                    			\
+	mov ar.lc = r16;			\
+	;; 					\
+1:						\
+	ld8 r18=[r2],8;		    		\
+	ld8 r19=[r3],8;				\
+	;;					\
+	mov ibr[r17]=r18;			\
+	mov dbr[r17]=r19;			\
+	;;   					\
+	srlz.i;					\
+	;; 					\
+	add r17=1,r17;				\
+	br.cloop.sptk 1b;			\
+	;;
+
+
+	/*
+	 *	r32:		context_t base address
+	 */
+#define	SAVE_FPU_LOW				\
+	add	r2=CTX(F2),r32;			\
+	add	r3=CTX(F3),r32;			\
+	;;					\
+	stf.spill.nta	[r2]=f2,32;		\
+	stf.spill.nta	[r3]=f3,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f4,32;		\
+	stf.spill.nta	[r3]=f5,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f6,32;		\
+	stf.spill.nta	[r3]=f7,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f8,32;		\
+	stf.spill.nta	[r3]=f9,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f10,32;		\
+	stf.spill.nta	[r3]=f11,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f12,32;		\
+	stf.spill.nta	[r3]=f13,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f14,32;		\
+	stf.spill.nta	[r3]=f15,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f16,32;		\
+	stf.spill.nta	[r3]=f17,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f18,32;		\
+	stf.spill.nta	[r3]=f19,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f20,32;		\
+	stf.spill.nta	[r3]=f21,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f22,32;		\
+	stf.spill.nta	[r3]=f23,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f24,32;		\
+	stf.spill.nta	[r3]=f25,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f26,32;		\
+	stf.spill.nta	[r3]=f27,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f28,32;		\
+	stf.spill.nta	[r3]=f29,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f30;		\
+	stf.spill.nta	[r3]=f31;		\
+	;;
+
+	/*
+	 *	r32:		context_t base address
+	 */
+#define	SAVE_FPU_HIGH				\
+	add	r2=CTX(F32),r32;		\
+	add	r3=CTX(F33),r32;		\
+	;;					\
+	stf.spill.nta	[r2]=f32,32;		\
+	stf.spill.nta	[r3]=f33,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f34,32;		\
+	stf.spill.nta	[r3]=f35,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f36,32;		\
+	stf.spill.nta	[r3]=f37,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f38,32;		\
+	stf.spill.nta	[r3]=f39,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f40,32;		\
+	stf.spill.nta	[r3]=f41,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f42,32;		\
+	stf.spill.nta	[r3]=f43,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f44,32;		\
+	stf.spill.nta	[r3]=f45,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f46,32;		\
+	stf.spill.nta	[r3]=f47,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f48,32;		\
+	stf.spill.nta	[r3]=f49,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f50,32;		\
+	stf.spill.nta	[r3]=f51,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f52,32;		\
+	stf.spill.nta	[r3]=f53,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f54,32;		\
+	stf.spill.nta	[r3]=f55,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f56,32;		\
+	stf.spill.nta	[r3]=f57,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f58,32;		\
+	stf.spill.nta	[r3]=f59,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f60,32;		\
+	stf.spill.nta	[r3]=f61,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f62,32;		\
+	stf.spill.nta	[r3]=f63,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f64,32;		\
+	stf.spill.nta	[r3]=f65,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f66,32;		\
+	stf.spill.nta	[r3]=f67,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f68,32;		\
+	stf.spill.nta	[r3]=f69,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f70,32;		\
+	stf.spill.nta	[r3]=f71,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f72,32;		\
+	stf.spill.nta	[r3]=f73,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f74,32;		\
+	stf.spill.nta	[r3]=f75,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f76,32;		\
+	stf.spill.nta	[r3]=f77,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f78,32;		\
+	stf.spill.nta	[r3]=f79,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f80,32;		\
+	stf.spill.nta	[r3]=f81,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f82,32;		\
+	stf.spill.nta	[r3]=f83,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f84,32;		\
+	stf.spill.nta	[r3]=f85,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f86,32;		\
+	stf.spill.nta	[r3]=f87,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f88,32;		\
+	stf.spill.nta	[r3]=f89,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f90,32;		\
+	stf.spill.nta	[r3]=f91,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f92,32;		\
+	stf.spill.nta	[r3]=f93,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f94,32;		\
+	stf.spill.nta	[r3]=f95,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f96,32;		\
+	stf.spill.nta	[r3]=f97,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f98,32;		\
+	stf.spill.nta	[r3]=f99,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f100,32;		\
+	stf.spill.nta	[r3]=f101,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f102,32;		\
+	stf.spill.nta	[r3]=f103,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f104,32;		\
+	stf.spill.nta	[r3]=f105,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f106,32;		\
+	stf.spill.nta	[r3]=f107,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f108,32;		\
+	stf.spill.nta	[r3]=f109,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f110,32;		\
+	stf.spill.nta	[r3]=f111,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f112,32;		\
+	stf.spill.nta	[r3]=f113,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f114,32;		\
+	stf.spill.nta	[r3]=f115,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f116,32;		\
+	stf.spill.nta	[r3]=f117,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f118,32;		\
+	stf.spill.nta	[r3]=f119,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f120,32;		\
+	stf.spill.nta	[r3]=f121,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f122,32;		\
+	stf.spill.nta	[r3]=f123,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f124,32;		\
+	stf.spill.nta	[r3]=f125,32;		\
+	;;					\
+	stf.spill.nta	[r2]=f126;		\
+	stf.spill.nta	[r3]=f127;		\
+	;;
+
+     /*
+      *      r33:    point to context_t structure
+      */
+#define	RESTORE_FPU_LOW				\
+    add     r2 = CTX(F2), r33;			\
+    add     r3 = CTX(F3), r33;			\
+    ;;						\
+    ldf.fill.nta f2 = [r2], 32;			\
+    ldf.fill.nta f3 = [r3], 32;			\
+    ;;						\
+    ldf.fill.nta f4 = [r2], 32;			\
+    ldf.fill.nta f5 = [r3], 32;			\
+    ;;						\
+    ldf.fill.nta f6 = [r2], 32;			\
+    ldf.fill.nta f7 = [r3], 32;			\
+    ;;						\
+    ldf.fill.nta f8 = [r2], 32;			\
+    ldf.fill.nta f9 = [r3], 32;			\
+    ;;						\
+    ldf.fill.nta f10 = [r2], 32;		\
+    ldf.fill.nta f11 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f12 = [r2], 32;		\
+    ldf.fill.nta f13 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f14 = [r2], 32;		\
+    ldf.fill.nta f15 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f16 = [r2], 32;		\
+    ldf.fill.nta f17 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f18 = [r2], 32;		\
+    ldf.fill.nta f19 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f20 = [r2], 32;		\
+    ldf.fill.nta f21 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f22 = [r2], 32;		\
+    ldf.fill.nta f23 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f24 = [r2], 32;		\
+    ldf.fill.nta f25 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f26 = [r2], 32;		\
+    ldf.fill.nta f27 = [r3], 32;		\
+	;;					\
+    ldf.fill.nta f28 = [r2], 32;		\
+    ldf.fill.nta f29 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f30 = [r2], 32;		\
+    ldf.fill.nta f31 = [r3], 32;		\
+    ;;
+
+
+
+    /*
+     *      r33:    point to context_t structure
+     */
+#define	RESTORE_FPU_HIGH			\
+    add     r2 = CTX(F32), r33;			\
+    add     r3 = CTX(F33), r33;			\
+    ;;						\
+    ldf.fill.nta f32 = [r2], 32;		\
+    ldf.fill.nta f33 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f34 = [r2], 32;		\
+    ldf.fill.nta f35 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f36 = [r2], 32;		\
+    ldf.fill.nta f37 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f38 = [r2], 32;		\
+    ldf.fill.nta f39 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f40 = [r2], 32;		\
+    ldf.fill.nta f41 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f42 = [r2], 32;		\
+    ldf.fill.nta f43 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f44 = [r2], 32;		\
+    ldf.fill.nta f45 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f46 = [r2], 32;		\
+    ldf.fill.nta f47 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f48 = [r2], 32;		\
+    ldf.fill.nta f49 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f50 = [r2], 32;		\
+    ldf.fill.nta f51 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f52 = [r2], 32;		\
+    ldf.fill.nta f53 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f54 = [r2], 32;		\
+    ldf.fill.nta f55 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f56 = [r2], 32;		\
+    ldf.fill.nta f57 = [r3], 32;   		\
+    ;;						\
+    ldf.fill.nta f58 = [r2], 32;		\
+    ldf.fill.nta f59 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f60 = [r2], 32;		\
+    ldf.fill.nta f61 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f62 = [r2], 32;		\
+    ldf.fill.nta f63 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f64 = [r2], 32;		\
+    ldf.fill.nta f65 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f66 = [r2], 32;		\
+    ldf.fill.nta f67 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f68 = [r2], 32;		\
+    ldf.fill.nta f69 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f70 = [r2], 32;		\
+    ldf.fill.nta f71 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f72 = [r2], 32;		\
+    ldf.fill.nta f73 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f74 = [r2], 32;		\
+    ldf.fill.nta f75 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f76 = [r2], 32;		\
+    ldf.fill.nta f77 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f78 = [r2], 32;		\
+    ldf.fill.nta f79 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f80 = [r2], 32;		\
+    ldf.fill.nta f81 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f82 = [r2], 32;		\
+    ldf.fill.nta f83 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f84 = [r2], 32;		\
+    ldf.fill.nta f85 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f86 = [r2], 32;		\
+    ldf.fill.nta f87 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f88 = [r2], 32;		\
+    ldf.fill.nta f89 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f90 = [r2], 32;		\
+    ldf.fill.nta f91 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f92 = [r2], 32;		\
+    ldf.fill.nta f93 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f94 = [r2], 32;		\
+    ldf.fill.nta f95 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f96 = [r2], 32;		\
+    ldf.fill.nta f97 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f98 = [r2], 32;		\
+    ldf.fill.nta f99 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f100 = [r2], 32;		\
+    ldf.fill.nta f101 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f102 = [r2], 32;		\
+    ldf.fill.nta f103 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f104 = [r2], 32;		\
+    ldf.fill.nta f105 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f106 = [r2], 32;		\
+    ldf.fill.nta f107 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f108 = [r2], 32;		\
+    ldf.fill.nta f109 = [r3], 32;   		\
+    ;;						\
+    ldf.fill.nta f110 = [r2], 32;		\
+    ldf.fill.nta f111 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f112 = [r2], 32;		\
+    ldf.fill.nta f113 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f114 = [r2], 32;		\
+    ldf.fill.nta f115 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f116 = [r2], 32;		\
+    ldf.fill.nta f117 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f118 = [r2], 32;		\
+    ldf.fill.nta f119 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f120 = [r2], 32;		\
+    ldf.fill.nta f121 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f122 = [r2], 32;		\
+    ldf.fill.nta f123 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f124 = [r2], 32;		\
+    ldf.fill.nta f125 = [r3], 32;		\
+    ;;						\
+    ldf.fill.nta f126 = [r2], 32;		\
+    ldf.fill.nta f127 = [r3], 32;		\
+    ;;
+
+	/*
+	 *	r32:		context_t base address
+	 */
+#define	SAVE_PTK_REGS				\
+    add r2=CTX(PKR0), r32;			\
+    mov r16=7;    				\
+    ;;                         			\
+    mov ar.lc=r16;  				\
+    mov r17=r0;					\
+    ;;						\
+1:						\
+    mov r18=pkr[r17];				\
+    ;;                     			\
+    srlz.i;					\
+    ;; 						\
+    st8 [r2]=r18, 8;				\
+    ;;    					\
+    add r17 =1,r17;				\
+    ;;                     			\
+    br.cloop.sptk 1b;				\
+    ;;
+
+/*
+ *      r33:    point to context_t structure
+ *      ar.lc are corrupted.
+ */
+#define RESTORE_PTK_REGS	    		\
+    add r2=CTX(PKR0), r33;			\
+    mov r16=7;    				\
+    ;;                         			\
+    mov ar.lc=r16;  				\
+    mov r17=r0;					\
+    ;;						\
+1: 						\
+    ld8 r18=[r2], 8;				\
+    ;;						\
+    mov pkr[r17]=r18;				\
+    ;;    					\
+    srlz.i;					\
+    ;; 						\
+    add r17 =1,r17;				\
+    ;;                     			\
+    br.cloop.sptk 1b;				\
+    ;;
+
+
+/*
+ * void vmm_trampoline( context_t * from,
+ *			context_t * to)
+ *
+ * 	from:	r32
+ *	to:	r33
+ *  note: interrupt disabled before call this function.
+ */
+GLOBAL_ENTRY(vmm_trampoline)
+    mov r16 = psr
+    adds r2 = CTX(PSR), r32
+    ;;
+    st8 [r2] = r16, 8       // psr
+    mov r17 = pr
+    ;;
+    st8 [r2] = r17, 8       // pr
+    mov r18 = ar.unat
+    ;;
+    st8 [r2] = r18
+    mov r17 = ar.rsc
+    ;;
+    adds r2 = CTX(RSC),r32
+    ;;
+    st8 [r2]= r17
+    mov ar.rsc =0
+    flushrs
+    ;;
+    SAVE_GENERAL_REGS
+    ;;
+    SAVE_KERNEL_REGS
+    ;;
+    SAVE_APP_REGS
+    ;;
+    SAVE_BRANCH_REGS
+    ;;
+    SAVE_CTL_REGS
+    ;;
+    SAVE_REGION_REGS
+    ;;
+    //SAVE_DEBUG_REGS
+    ;;
+    rsm  psr.dfl
+    ;;
+    srlz.d
+    ;;
+    SAVE_FPU_LOW
+    ;;
+    rsm  psr.dfh
+    ;;
+    srlz.d
+    ;;
+    SAVE_FPU_HIGH
+    ;;
+    SAVE_PTK_REGS
+    ;;
+    RESTORE_PTK_REGS
+    ;;
+    RESTORE_FPU_HIGH
+    ;;
+    RESTORE_FPU_LOW
+    ;;
+    //RESTORE_DEBUG_REGS
+    ;;
+    RESTORE_REGION_REGS
+    ;;
+    RESTORE_CTL_REGS
+    ;;
+    RESTORE_BRANCH_REGS
+    ;;
+    RESTORE_APP_REGS
+    ;;
+    RESTORE_KERNEL_REGS
+    ;;
+    RESTORE_GENERAL_REGS
+    ;;
+    adds r2=CTX(PSR), r33
+    ;;
+    ld8 r16=[r2], 8       // psr
+    ;;
+    mov psr.l=r16
+    ;;
+    srlz.d
+    ;;
+    ld8 r16=[r2], 8       // pr
+    ;;
+    mov pr =r16,-1
+    ld8 r16=[r2]       // unat
+    ;;
+    mov ar.unat=r16
+    ;;
+    adds r2=CTX(RSC),r33
+    ;;
+    ld8 r16 =[r2]
+    ;;
+    mov ar.rsc = r16
+    ;;
+    br.ret.sptk.few b0
+END(vmm_trampoline)
diff --git a/trunk/arch/ia64/kvm/vcpu.c b/trunk/arch/ia64/kvm/vcpu.c
new file mode 100644
index 000000000000..e44027ce5667
--- /dev/null
+++ b/trunk/arch/ia64/kvm/vcpu.c
@@ -0,0 +1,2163 @@
+/*
+ * kvm_vcpu.c: handling all virtual cpu related thing.
+ * Copyright (c) 2005, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ *  Shaofan Li (Susue Li) <susie.li@intel.com>
+ *  Yaozu Dong (Eddie Dong) (Eddie.dong@intel.com)
+ *  Xuefei Xu (Anthony Xu) (Anthony.xu@intel.com)
+ *  Xiantao Zhang <xiantao.zhang@intel.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+
+#include <asm/processor.h>
+#include <asm/ia64regs.h>
+#include <asm/gcc_intrin.h>
+#include <asm/kregs.h>
+#include <asm/pgtable.h>
+#include <asm/tlb.h>
+
+#include "asm-offsets.h"
+#include "vcpu.h"
+
+/*
+ * Special notes:
+ * - Index by it/dt/rt sequence
+ * - Only existing mode transitions are allowed in this table
+ * - RSE is placed at lazy mode when emulating guest partial mode
+ * - If gva happens to be rr0 and rr4, only allowed case is identity
+ *   mapping (gva=gpa), or panic! (How?)
+ */
+int mm_switch_table[8][8] = {
+	/*  2004/09/12(Kevin): Allow switch to self */
+	/*
+	 *  (it,dt,rt): (0,0,0) -> (1,1,1)
+	 *  This kind of transition usually occurs in the very early
+	 *  stage of Linux boot up procedure. Another case is in efi
+	 *  and pal calls. (see "arch/ia64/kernel/head.S")
+	 *
+	 *  (it,dt,rt): (0,0,0) -> (0,1,1)
+	 *  This kind of transition is found when OSYa exits efi boot
+	 *  service. Due to gva = gpa in this case (Same region),
+	 *  data access can be satisfied though itlb entry for physical
+	 *  emulation is hit.
+	 */
+	{SW_SELF, 0,  0,  SW_NOP, 0,  0,  0,  SW_P2V},
+	{0,  0,  0,  0,  0,  0,  0,  0},
+	{0,  0,  0,  0,  0,  0,  0,  0},
+	/*
+	 *  (it,dt,rt): (0,1,1) -> (1,1,1)
+	 *  This kind of transition is found in OSYa.
+	 *
+	 *  (it,dt,rt): (0,1,1) -> (0,0,0)
+	 *  This kind of transition is found in OSYa
+	 */
+	{SW_NOP, 0,  0,  SW_SELF, 0,  0,  0,  SW_P2V},
+	/* (1,0,0)->(1,1,1) */
+	{0,  0,  0,  0,  0,  0,  0,  SW_P2V},
+	/*
+	 *  (it,dt,rt): (1,0,1) -> (1,1,1)
+	 *  This kind of transition usually occurs when Linux returns
+	 *  from the low level TLB miss handlers.
+	 *  (see "arch/ia64/kernel/ivt.S")
+	 */
+	{0,  0,  0,  0,  0,  SW_SELF, 0,  SW_P2V},
+	{0,  0,  0,  0,  0,  0,  0,  0},
+	/*
+	 *  (it,dt,rt): (1,1,1) -> (1,0,1)
+	 *  This kind of transition usually occurs in Linux low level
+	 *  TLB miss handler. (see "arch/ia64/kernel/ivt.S")
+	 *
+	 *  (it,dt,rt): (1,1,1) -> (0,0,0)
+	 *  This kind of transition usually occurs in pal and efi calls,
+	 *  which requires running in physical mode.
+	 *  (see "arch/ia64/kernel/head.S")
+	 *  (1,1,1)->(1,0,0)
+	 */
+
+	{SW_V2P, 0,  0,  0,  SW_V2P, SW_V2P, 0,  SW_SELF},
+};
+
+void physical_mode_init(struct kvm_vcpu  *vcpu)
+{
+	vcpu->arch.mode_flags = GUEST_IN_PHY;
+}
+
+void switch_to_physical_rid(struct kvm_vcpu *vcpu)
+{
+	unsigned long psr;
+
+	/* Save original virtual mode rr[0] and rr[4] */
+	psr = ia64_clear_ic();
+	ia64_set_rr(VRN0<<VRN_SHIFT, vcpu->arch.metaphysical_rr0);
+	ia64_srlz_d();
+	ia64_set_rr(VRN4<<VRN_SHIFT, vcpu->arch.metaphysical_rr4);
+	ia64_srlz_d();
+
+	ia64_set_psr(psr);
+	return;
+}
+
+
+void switch_to_virtual_rid(struct kvm_vcpu *vcpu)
+{
+	unsigned long psr;
+
+	psr = ia64_clear_ic();
+	ia64_set_rr(VRN0 << VRN_SHIFT, vcpu->arch.metaphysical_saved_rr0);
+	ia64_srlz_d();
+	ia64_set_rr(VRN4 << VRN_SHIFT, vcpu->arch.metaphysical_saved_rr4);
+	ia64_srlz_d();
+	ia64_set_psr(psr);
+	return;
+}
+
+static int mm_switch_action(struct ia64_psr opsr, struct ia64_psr npsr)
+{
+	return mm_switch_table[MODE_IND(opsr)][MODE_IND(npsr)];
+}
+
+void switch_mm_mode(struct kvm_vcpu *vcpu, struct ia64_psr old_psr,
+					struct ia64_psr new_psr)
+{
+	int act;
+	act = mm_switch_action(old_psr, new_psr);
+	switch (act) {
+	case SW_V2P:
+		/*printk("V -> P mode transition: (0x%lx -> 0x%lx)\n",
+		old_psr.val, new_psr.val);*/
+		switch_to_physical_rid(vcpu);
+		/*
+		 * Set rse to enforced lazy, to prevent active rse
+		 *save/restor when guest physical mode.
+		 */
+		vcpu->arch.mode_flags |= GUEST_IN_PHY;
+		break;
+	case SW_P2V:
+		switch_to_virtual_rid(vcpu);
+		/*
+		 * recover old mode which is saved when entering
+		 * guest physical mode
+		 */
+		vcpu->arch.mode_flags &= ~GUEST_IN_PHY;
+		break;
+	case SW_SELF:
+		break;
+	case SW_NOP:
+		break;
+	default:
+		/* Sanity check */
+		break;
+	}
+	return;
+}
+
+
+
+/*
+ * In physical mode, insert tc/tr for region 0 and 4 uses
+ * RID[0] and RID[4] which is for physical mode emulation.
+ * However what those inserted tc/tr wants is rid for
+ * virtual mode. So original virtual rid needs to be restored
+ * before insert.
+ *
+ * Operations which required such switch include:
+ *  - insertions (itc.*, itr.*)
+ *  - purges (ptc.* and ptr.*)
+ *  - tpa
+ *  - tak
+ *  - thash?, ttag?
+ * All above needs actual virtual rid for destination entry.
+ */
+
+void check_mm_mode_switch(struct kvm_vcpu *vcpu,  struct ia64_psr old_psr,
+					struct ia64_psr new_psr)
+{
+
+	if ((old_psr.dt != new_psr.dt)
+			|| (old_psr.it != new_psr.it)
+			|| (old_psr.rt != new_psr.rt))
+		switch_mm_mode(vcpu, old_psr, new_psr);
+
+	return;
+}
+
+
+/*
+ * In physical mode, insert tc/tr for region 0 and 4 uses
+ * RID[0] and RID[4] which is for physical mode emulation.
+ * However what those inserted tc/tr wants is rid for
+ * virtual mode. So original virtual rid needs to be restored
+ * before insert.
+ *
+ * Operations which required such switch include:
+ *  - insertions (itc.*, itr.*)
+ *  - purges (ptc.* and ptr.*)
+ *  - tpa
+ *  - tak
+ *  - thash?, ttag?
+ * All above needs actual virtual rid for destination entry.
+ */
+
+void prepare_if_physical_mode(struct kvm_vcpu *vcpu)
+{
+	if (is_physical_mode(vcpu)) {
+		vcpu->arch.mode_flags |= GUEST_PHY_EMUL;
+		switch_to_virtual_rid(vcpu);
+	}
+	return;
+}
+
+/* Recover always follows prepare */
+void recover_if_physical_mode(struct kvm_vcpu *vcpu)
+{
+	if (is_physical_mode(vcpu))
+		switch_to_physical_rid(vcpu);
+	vcpu->arch.mode_flags &= ~GUEST_PHY_EMUL;
+	return;
+}
+
+#define RPT(x)	((u16) &((struct kvm_pt_regs *)0)->x)
+
+static u16 gr_info[32] = {
+	0, 	/* r0 is read-only : WE SHOULD NEVER GET THIS */
+	RPT(r1), RPT(r2), RPT(r3),
+	RPT(r4), RPT(r5), RPT(r6), RPT(r7),
+	RPT(r8), RPT(r9), RPT(r10), RPT(r11),
+	RPT(r12), RPT(r13), RPT(r14), RPT(r15),
+	RPT(r16), RPT(r17), RPT(r18), RPT(r19),
+	RPT(r20), RPT(r21), RPT(r22), RPT(r23),
+	RPT(r24), RPT(r25), RPT(r26), RPT(r27),
+	RPT(r28), RPT(r29), RPT(r30), RPT(r31)
+};
+
+#define IA64_FIRST_STACKED_GR   32
+#define IA64_FIRST_ROTATING_FR  32
+
+static inline unsigned long
+rotate_reg(unsigned long sor, unsigned long rrb, unsigned long reg)
+{
+	reg += rrb;
+	if (reg >= sor)
+		reg -= sor;
+	return reg;
+}
+
+/*
+ * Return the (rotated) index for floating point register
+ * be in the REGNUM (REGNUM must range from 32-127,
+ * result is in the range from 0-95.
+ */
+static inline unsigned long fph_index(struct kvm_pt_regs *regs,
+						long regnum)
+{
+	unsigned long rrb_fr = (regs->cr_ifs >> 25) & 0x7f;
+	return rotate_reg(96, rrb_fr, (regnum - IA64_FIRST_ROTATING_FR));
+}
+
+
+/*
+ * The inverse of the above: given bspstore and the number of
+ * registers, calculate ar.bsp.
+ */
+static inline unsigned long *kvm_rse_skip_regs(unsigned long *addr,
+							long num_regs)
+{
+	long delta = ia64_rse_slot_num(addr) + num_regs;
+	int i = 0;
+
+	if (num_regs < 0)
+		delta -= 0x3e;
+	if (delta < 0) {
+		while (delta <= -0x3f) {
+			i--;
+			delta += 0x3f;
+		}
+	} else {
+		while (delta >= 0x3f) {
+			i++;
+			delta -= 0x3f;
+		}
+	}
+
+	return addr + num_regs + i;
+}
+
+static void get_rse_reg(struct kvm_pt_regs *regs, unsigned long r1,
+					unsigned long *val, int *nat)
+{
+	unsigned long *bsp, *addr, *rnat_addr, *bspstore;
+	unsigned long *kbs = (void *) current_vcpu + VMM_RBS_OFFSET;
+	unsigned long nat_mask;
+	unsigned long old_rsc, new_rsc;
+	long sof = (regs->cr_ifs) & 0x7f;
+	long sor = (((regs->cr_ifs >> 14) & 0xf) << 3);
+	long rrb_gr = (regs->cr_ifs >> 18) & 0x7f;
+	long ridx = r1 - 32;
+
+	if (ridx < sor)
+		ridx = rotate_reg(sor, rrb_gr, ridx);
+
+	old_rsc = ia64_getreg(_IA64_REG_AR_RSC);
+	new_rsc = old_rsc&(~(0x3));
+	ia64_setreg(_IA64_REG_AR_RSC, new_rsc);
+
+	bspstore = (unsigned long *)ia64_getreg(_IA64_REG_AR_BSPSTORE);
+	bsp = kbs + (regs->loadrs >> 19);
+
+	addr = kvm_rse_skip_regs(bsp, -sof + ridx);
+	nat_mask = 1UL << ia64_rse_slot_num(addr);
+	rnat_addr = ia64_rse_rnat_addr(addr);
+
+	if (addr >= bspstore) {
+		ia64_flushrs();
+		ia64_mf();
+		bspstore = (unsigned long *)ia64_getreg(_IA64_REG_AR_BSPSTORE);
+	}
+	*val = *addr;
+	if (nat) {
+		if (bspstore < rnat_addr)
+			*nat = (int)!!(ia64_getreg(_IA64_REG_AR_RNAT)
+							& nat_mask);
+		else
+			*nat = (int)!!((*rnat_addr) & nat_mask);
+		ia64_setreg(_IA64_REG_AR_RSC, old_rsc);
+	}
+}
+
+void set_rse_reg(struct kvm_pt_regs *regs, unsigned long r1,
+				unsigned long val, unsigned long nat)
+{
+	unsigned long *bsp, *bspstore, *addr, *rnat_addr;
+	unsigned long *kbs = (void *) current_vcpu + VMM_RBS_OFFSET;
+	unsigned long nat_mask;
+	unsigned long old_rsc, new_rsc, psr;
+	unsigned long rnat;
+	long sof = (regs->cr_ifs) & 0x7f;
+	long sor = (((regs->cr_ifs >> 14) & 0xf) << 3);
+	long rrb_gr = (regs->cr_ifs >> 18) & 0x7f;
+	long ridx = r1 - 32;
+
+	if (ridx < sor)
+		ridx = rotate_reg(sor, rrb_gr, ridx);
+
+	old_rsc = ia64_getreg(_IA64_REG_AR_RSC);
+	/* put RSC to lazy mode, and set loadrs 0 */
+	new_rsc = old_rsc & (~0x3fff0003);
+	ia64_setreg(_IA64_REG_AR_RSC, new_rsc);
+	bsp = kbs + (regs->loadrs >> 19); /* 16 + 3 */
+
+	addr = kvm_rse_skip_regs(bsp, -sof + ridx);
+	nat_mask = 1UL << ia64_rse_slot_num(addr);
+	rnat_addr = ia64_rse_rnat_addr(addr);
+
+	local_irq_save(psr);
+	bspstore = (unsigned long *)ia64_getreg(_IA64_REG_AR_BSPSTORE);
+	if (addr >= bspstore) {
+
+		ia64_flushrs();
+		ia64_mf();
+		*addr = val;
+		bspstore = (unsigned long *)ia64_getreg(_IA64_REG_AR_BSPSTORE);
+		rnat = ia64_getreg(_IA64_REG_AR_RNAT);
+		if (bspstore < rnat_addr)
+			rnat = rnat & (~nat_mask);
+		else
+			*rnat_addr = (*rnat_addr)&(~nat_mask);
+
+		ia64_mf();
+		ia64_loadrs();
+		ia64_setreg(_IA64_REG_AR_RNAT, rnat);
+	} else {
+		rnat = ia64_getreg(_IA64_REG_AR_RNAT);
+		*addr = val;
+		if (bspstore < rnat_addr)
+			rnat = rnat&(~nat_mask);
+		else
+			*rnat_addr = (*rnat_addr) & (~nat_mask);
+
+		ia64_setreg(_IA64_REG_AR_BSPSTORE, bspstore);
+		ia64_setreg(_IA64_REG_AR_RNAT, rnat);
+	}
+	local_irq_restore(psr);
+	ia64_setreg(_IA64_REG_AR_RSC, old_rsc);
+}
+
+void getreg(unsigned long regnum, unsigned long *val,
+				int *nat, struct kvm_pt_regs *regs)
+{
+	unsigned long addr, *unat;
+	if (regnum >= IA64_FIRST_STACKED_GR) {
+		get_rse_reg(regs, regnum, val, nat);
+		return;
+	}
+
+	/*
+	 * Now look at registers in [0-31] range and init correct UNAT
+	 */
+	addr = (unsigned long)regs;
+	unat = &regs->eml_unat;;
+
+	addr += gr_info[regnum];
+
+	*val  = *(unsigned long *)addr;
+	/*
+	 * do it only when requested
+	 */
+	if (nat)
+		*nat  = (*unat >> ((addr >> 3) & 0x3f)) & 0x1UL;
+}
+
+void setreg(unsigned long regnum, unsigned long val,
+			int nat, struct kvm_pt_regs *regs)
+{
+	unsigned long addr;
+	unsigned long bitmask;
+	unsigned long *unat;
+
+	/*
+	 * First takes care of stacked registers
+	 */
+	if (regnum >= IA64_FIRST_STACKED_GR) {
+		set_rse_reg(regs, regnum, val, nat);
+		return;
+	}
+
+	/*
+	 * Now look at registers in [0-31] range and init correct UNAT
+	 */
+	addr = (unsigned long)regs;
+	unat = &regs->eml_unat;
+	/*
+	 * add offset from base of struct
+	 * and do it !
+	 */
+	addr += gr_info[regnum];
+
+	*(unsigned long *)addr = val;
+
+	/*
+	 * We need to clear the corresponding UNAT bit to fully emulate the load
+	 * UNAT bit_pos = GR[r3]{8:3} form EAS-2.4
+	 */
+	bitmask   = 1UL << ((addr >> 3) & 0x3f);
+	if (nat)
+		*unat |= bitmask;
+	 else
+		*unat &= ~bitmask;
+
+}
+
+u64 vcpu_get_gr(struct kvm_vcpu *vcpu, unsigned long reg)
+{
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+	u64 val;
+
+	if (!reg)
+		return 0;
+	getreg(reg, &val, 0, regs);
+	return val;
+}
+
+void vcpu_set_gr(struct kvm_vcpu *vcpu, u64 reg, u64 value, int nat)
+{
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+	long sof = (regs->cr_ifs) & 0x7f;
+
+	if (!reg)
+		return;
+	if (reg >= sof + 32)
+		return;
+	setreg(reg, value, nat, regs);	/* FIXME: handle NATs later*/
+}
+
+void getfpreg(unsigned long regnum, struct ia64_fpreg *fpval,
+				struct kvm_pt_regs *regs)
+{
+	/* Take floating register rotation into consideration*/
+	if (regnum >= IA64_FIRST_ROTATING_FR)
+		regnum = IA64_FIRST_ROTATING_FR + fph_index(regs, regnum);
+#define CASE_FIXED_FP(reg)			\
+	case  (reg) :				\
+		ia64_stf_spill(fpval, reg);	\
+	break
+
+	switch (regnum) {
+		CASE_FIXED_FP(0);
+		CASE_FIXED_FP(1);
+		CASE_FIXED_FP(2);
+		CASE_FIXED_FP(3);
+		CASE_FIXED_FP(4);
+		CASE_FIXED_FP(5);
+
+		CASE_FIXED_FP(6);
+		CASE_FIXED_FP(7);
+		CASE_FIXED_FP(8);
+		CASE_FIXED_FP(9);
+		CASE_FIXED_FP(10);
+		CASE_FIXED_FP(11);
+
+		CASE_FIXED_FP(12);
+		CASE_FIXED_FP(13);
+		CASE_FIXED_FP(14);
+		CASE_FIXED_FP(15);
+		CASE_FIXED_FP(16);
+		CASE_FIXED_FP(17);
+		CASE_FIXED_FP(18);
+		CASE_FIXED_FP(19);
+		CASE_FIXED_FP(20);
+		CASE_FIXED_FP(21);
+		CASE_FIXED_FP(22);
+		CASE_FIXED_FP(23);
+		CASE_FIXED_FP(24);
+		CASE_FIXED_FP(25);
+		CASE_FIXED_FP(26);
+		CASE_FIXED_FP(27);
+		CASE_FIXED_FP(28);
+		CASE_FIXED_FP(29);
+		CASE_FIXED_FP(30);
+		CASE_FIXED_FP(31);
+		CASE_FIXED_FP(32);
+		CASE_FIXED_FP(33);
+		CASE_FIXED_FP(34);
+		CASE_FIXED_FP(35);
+		CASE_FIXED_FP(36);
+		CASE_FIXED_FP(37);
+		CASE_FIXED_FP(38);
+		CASE_FIXED_FP(39);
+		CASE_FIXED_FP(40);
+		CASE_FIXED_FP(41);
+		CASE_FIXED_FP(42);
+		CASE_FIXED_FP(43);
+		CASE_FIXED_FP(44);
+		CASE_FIXED_FP(45);
+		CASE_FIXED_FP(46);
+		CASE_FIXED_FP(47);
+		CASE_FIXED_FP(48);
+		CASE_FIXED_FP(49);
+		CASE_FIXED_FP(50);
+		CASE_FIXED_FP(51);
+		CASE_FIXED_FP(52);
+		CASE_FIXED_FP(53);
+		CASE_FIXED_FP(54);
+		CASE_FIXED_FP(55);
+		CASE_FIXED_FP(56);
+		CASE_FIXED_FP(57);
+		CASE_FIXED_FP(58);
+		CASE_FIXED_FP(59);
+		CASE_FIXED_FP(60);
+		CASE_FIXED_FP(61);
+		CASE_FIXED_FP(62);
+		CASE_FIXED_FP(63);
+		CASE_FIXED_FP(64);
+		CASE_FIXED_FP(65);
+		CASE_FIXED_FP(66);
+		CASE_FIXED_FP(67);
+		CASE_FIXED_FP(68);
+		CASE_FIXED_FP(69);
+		CASE_FIXED_FP(70);
+		CASE_FIXED_FP(71);
+		CASE_FIXED_FP(72);
+		CASE_FIXED_FP(73);
+		CASE_FIXED_FP(74);
+		CASE_FIXED_FP(75);
+		CASE_FIXED_FP(76);
+		CASE_FIXED_FP(77);
+		CASE_FIXED_FP(78);
+		CASE_FIXED_FP(79);
+		CASE_FIXED_FP(80);
+		CASE_FIXED_FP(81);
+		CASE_FIXED_FP(82);
+		CASE_FIXED_FP(83);
+		CASE_FIXED_FP(84);
+		CASE_FIXED_FP(85);
+		CASE_FIXED_FP(86);
+		CASE_FIXED_FP(87);
+		CASE_FIXED_FP(88);
+		CASE_FIXED_FP(89);
+		CASE_FIXED_FP(90);
+		CASE_FIXED_FP(91);
+		CASE_FIXED_FP(92);
+		CASE_FIXED_FP(93);
+		CASE_FIXED_FP(94);
+		CASE_FIXED_FP(95);
+		CASE_FIXED_FP(96);
+		CASE_FIXED_FP(97);
+		CASE_FIXED_FP(98);
+		CASE_FIXED_FP(99);
+		CASE_FIXED_FP(100);
+		CASE_FIXED_FP(101);
+		CASE_FIXED_FP(102);
+		CASE_FIXED_FP(103);
+		CASE_FIXED_FP(104);
+		CASE_FIXED_FP(105);
+		CASE_FIXED_FP(106);
+		CASE_FIXED_FP(107);
+		CASE_FIXED_FP(108);
+		CASE_FIXED_FP(109);
+		CASE_FIXED_FP(110);
+		CASE_FIXED_FP(111);
+		CASE_FIXED_FP(112);
+		CASE_FIXED_FP(113);
+		CASE_FIXED_FP(114);
+		CASE_FIXED_FP(115);
+		CASE_FIXED_FP(116);
+		CASE_FIXED_FP(117);
+		CASE_FIXED_FP(118);
+		CASE_FIXED_FP(119);
+		CASE_FIXED_FP(120);
+		CASE_FIXED_FP(121);
+		CASE_FIXED_FP(122);
+		CASE_FIXED_FP(123);
+		CASE_FIXED_FP(124);
+		CASE_FIXED_FP(125);
+		CASE_FIXED_FP(126);
+		CASE_FIXED_FP(127);
+	}
+#undef CASE_FIXED_FP
+}
+
+void setfpreg(unsigned long regnum, struct ia64_fpreg *fpval,
+					struct kvm_pt_regs *regs)
+{
+	/* Take floating register rotation into consideration*/
+	if (regnum >= IA64_FIRST_ROTATING_FR)
+		regnum = IA64_FIRST_ROTATING_FR + fph_index(regs, regnum);
+
+#define CASE_FIXED_FP(reg)			\
+	case (reg) :				\
+		ia64_ldf_fill(reg, fpval);	\
+	break
+
+	switch (regnum) {
+		CASE_FIXED_FP(2);
+		CASE_FIXED_FP(3);
+		CASE_FIXED_FP(4);
+		CASE_FIXED_FP(5);
+
+		CASE_FIXED_FP(6);
+		CASE_FIXED_FP(7);
+		CASE_FIXED_FP(8);
+		CASE_FIXED_FP(9);
+		CASE_FIXED_FP(10);
+		CASE_FIXED_FP(11);
+
+		CASE_FIXED_FP(12);
+		CASE_FIXED_FP(13);
+		CASE_FIXED_FP(14);
+		CASE_FIXED_FP(15);
+		CASE_FIXED_FP(16);
+		CASE_FIXED_FP(17);
+		CASE_FIXED_FP(18);
+		CASE_FIXED_FP(19);
+		CASE_FIXED_FP(20);
+		CASE_FIXED_FP(21);
+		CASE_FIXED_FP(22);
+		CASE_FIXED_FP(23);
+		CASE_FIXED_FP(24);
+		CASE_FIXED_FP(25);
+		CASE_FIXED_FP(26);
+		CASE_FIXED_FP(27);
+		CASE_FIXED_FP(28);
+		CASE_FIXED_FP(29);
+		CASE_FIXED_FP(30);
+		CASE_FIXED_FP(31);
+		CASE_FIXED_FP(32);
+		CASE_FIXED_FP(33);
+		CASE_FIXED_FP(34);
+		CASE_FIXED_FP(35);
+		CASE_FIXED_FP(36);
+		CASE_FIXED_FP(37);
+		CASE_FIXED_FP(38);
+		CASE_FIXED_FP(39);
+		CASE_FIXED_FP(40);
+		CASE_FIXED_FP(41);
+		CASE_FIXED_FP(42);
+		CASE_FIXED_FP(43);
+		CASE_FIXED_FP(44);
+		CASE_FIXED_FP(45);
+		CASE_FIXED_FP(46);
+		CASE_FIXED_FP(47);
+		CASE_FIXED_FP(48);
+		CASE_FIXED_FP(49);
+		CASE_FIXED_FP(50);
+		CASE_FIXED_FP(51);
+		CASE_FIXED_FP(52);
+		CASE_FIXED_FP(53);
+		CASE_FIXED_FP(54);
+		CASE_FIXED_FP(55);
+		CASE_FIXED_FP(56);
+		CASE_FIXED_FP(57);
+		CASE_FIXED_FP(58);
+		CASE_FIXED_FP(59);
+		CASE_FIXED_FP(60);
+		CASE_FIXED_FP(61);
+		CASE_FIXED_FP(62);
+		CASE_FIXED_FP(63);
+		CASE_FIXED_FP(64);
+		CASE_FIXED_FP(65);
+		CASE_FIXED_FP(66);
+		CASE_FIXED_FP(67);
+		CASE_FIXED_FP(68);
+		CASE_FIXED_FP(69);
+		CASE_FIXED_FP(70);
+		CASE_FIXED_FP(71);
+		CASE_FIXED_FP(72);
+		CASE_FIXED_FP(73);
+		CASE_FIXED_FP(74);
+		CASE_FIXED_FP(75);
+		CASE_FIXED_FP(76);
+		CASE_FIXED_FP(77);
+		CASE_FIXED_FP(78);
+		CASE_FIXED_FP(79);
+		CASE_FIXED_FP(80);
+		CASE_FIXED_FP(81);
+		CASE_FIXED_FP(82);
+		CASE_FIXED_FP(83);
+		CASE_FIXED_FP(84);
+		CASE_FIXED_FP(85);
+		CASE_FIXED_FP(86);
+		CASE_FIXED_FP(87);
+		CASE_FIXED_FP(88);
+		CASE_FIXED_FP(89);
+		CASE_FIXED_FP(90);
+		CASE_FIXED_FP(91);
+		CASE_FIXED_FP(92);
+		CASE_FIXED_FP(93);
+		CASE_FIXED_FP(94);
+		CASE_FIXED_FP(95);
+		CASE_FIXED_FP(96);
+		CASE_FIXED_FP(97);
+		CASE_FIXED_FP(98);
+		CASE_FIXED_FP(99);
+		CASE_FIXED_FP(100);
+		CASE_FIXED_FP(101);
+		CASE_FIXED_FP(102);
+		CASE_FIXED_FP(103);
+		CASE_FIXED_FP(104);
+		CASE_FIXED_FP(105);
+		CASE_FIXED_FP(106);
+		CASE_FIXED_FP(107);
+		CASE_FIXED_FP(108);
+		CASE_FIXED_FP(109);
+		CASE_FIXED_FP(110);
+		CASE_FIXED_FP(111);
+		CASE_FIXED_FP(112);
+		CASE_FIXED_FP(113);
+		CASE_FIXED_FP(114);
+		CASE_FIXED_FP(115);
+		CASE_FIXED_FP(116);
+		CASE_FIXED_FP(117);
+		CASE_FIXED_FP(118);
+		CASE_FIXED_FP(119);
+		CASE_FIXED_FP(120);
+		CASE_FIXED_FP(121);
+		CASE_FIXED_FP(122);
+		CASE_FIXED_FP(123);
+		CASE_FIXED_FP(124);
+		CASE_FIXED_FP(125);
+		CASE_FIXED_FP(126);
+		CASE_FIXED_FP(127);
+	}
+}
+
+void vcpu_get_fpreg(struct kvm_vcpu *vcpu, unsigned long reg,
+						struct ia64_fpreg *val)
+{
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+	getfpreg(reg, val, regs);   /* FIXME: handle NATs later*/
+}
+
+void vcpu_set_fpreg(struct kvm_vcpu *vcpu, unsigned long reg,
+						struct ia64_fpreg *val)
+{
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+	if (reg > 1)
+		setfpreg(reg, val, regs);   /* FIXME: handle NATs later*/
+}
+
+/************************************************************************
+ * lsapic timer
+ ***********************************************************************/
+u64 vcpu_get_itc(struct kvm_vcpu *vcpu)
+{
+	unsigned long guest_itc;
+	guest_itc = VMX(vcpu, itc_offset) + ia64_getreg(_IA64_REG_AR_ITC);
+
+	if (guest_itc >= VMX(vcpu, last_itc)) {
+		VMX(vcpu, last_itc) = guest_itc;
+		return  guest_itc;
+	} else
+		return VMX(vcpu, last_itc);
+}
+
+static inline void vcpu_set_itm(struct kvm_vcpu *vcpu, u64 val);
+static void vcpu_set_itc(struct kvm_vcpu *vcpu, u64 val)
+{
+	struct kvm_vcpu *v;
+	int i;
+	long itc_offset = val - ia64_getreg(_IA64_REG_AR_ITC);
+	unsigned long vitv = VCPU(vcpu, itv);
+
+	if (vcpu->vcpu_id == 0) {
+		for (i = 0; i < MAX_VCPU_NUM; i++) {
+			v = (struct kvm_vcpu *)((char *)vcpu + VCPU_SIZE * i);
+			VMX(v, itc_offset) = itc_offset;
+			VMX(v, last_itc) = 0;
+		}
+	}
+	VMX(vcpu, last_itc) = 0;
+	if (VCPU(vcpu, itm) <= val) {
+		VMX(vcpu, itc_check) = 0;
+		vcpu_unpend_interrupt(vcpu, vitv);
+	} else {
+		VMX(vcpu, itc_check) = 1;
+		vcpu_set_itm(vcpu, VCPU(vcpu, itm));
+	}
+
+}
+
+static inline u64 vcpu_get_itm(struct kvm_vcpu *vcpu)
+{
+	return ((u64)VCPU(vcpu, itm));
+}
+
+static inline void vcpu_set_itm(struct kvm_vcpu *vcpu, u64 val)
+{
+	unsigned long vitv = VCPU(vcpu, itv);
+	VCPU(vcpu, itm) = val;
+
+	if (val > vcpu_get_itc(vcpu)) {
+		VMX(vcpu, itc_check) = 1;
+		vcpu_unpend_interrupt(vcpu, vitv);
+		VMX(vcpu, timer_pending) = 0;
+	} else
+		VMX(vcpu, itc_check) = 0;
+}
+
+#define  ITV_VECTOR(itv)    (itv&0xff)
+#define  ITV_IRQ_MASK(itv)  (itv&(1<<16))
+
+static inline void vcpu_set_itv(struct kvm_vcpu *vcpu, u64 val)
+{
+	VCPU(vcpu, itv) = val;
+	if (!ITV_IRQ_MASK(val) && vcpu->arch.timer_pending) {
+		vcpu_pend_interrupt(vcpu, ITV_VECTOR(val));
+		vcpu->arch.timer_pending = 0;
+	}
+}
+
+static inline void vcpu_set_eoi(struct kvm_vcpu *vcpu, u64 val)
+{
+	int vec;
+
+	vec = highest_inservice_irq(vcpu);
+	if (vec == NULL_VECTOR)
+		return;
+	VMX(vcpu, insvc[vec >> 6]) &= ~(1UL << (vec & 63));
+	VCPU(vcpu, eoi) = 0;
+	vcpu->arch.irq_new_pending = 1;
+
+}
+
+/* See Table 5-8 in SDM vol2 for the definition */
+int irq_masked(struct kvm_vcpu *vcpu, int h_pending, int h_inservice)
+{
+	union ia64_tpr vtpr;
+
+	vtpr.val = VCPU(vcpu, tpr);
+
+	if (h_inservice == NMI_VECTOR)
+		return IRQ_MASKED_BY_INSVC;
+
+	if (h_pending == NMI_VECTOR) {
+		/* Non Maskable Interrupt */
+		return IRQ_NO_MASKED;
+	}
+
+	if (h_inservice == ExtINT_VECTOR)
+		return IRQ_MASKED_BY_INSVC;
+
+	if (h_pending == ExtINT_VECTOR) {
+		if (vtpr.mmi) {
+			/* mask all external IRQ */
+			return IRQ_MASKED_BY_VTPR;
+		} else
+			return IRQ_NO_MASKED;
+	}
+
+	if (is_higher_irq(h_pending, h_inservice)) {
+		if (is_higher_class(h_pending, vtpr.mic + (vtpr.mmi << 4)))
+			return IRQ_NO_MASKED;
+		else
+			return IRQ_MASKED_BY_VTPR;
+	} else {
+		return IRQ_MASKED_BY_INSVC;
+	}
+}
+
+void vcpu_pend_interrupt(struct kvm_vcpu *vcpu, u8 vec)
+{
+	long spsr;
+	int ret;
+
+	local_irq_save(spsr);
+	ret = test_and_set_bit(vec, &VCPU(vcpu, irr[0]));
+	local_irq_restore(spsr);
+
+	vcpu->arch.irq_new_pending = 1;
+}
+
+void vcpu_unpend_interrupt(struct kvm_vcpu *vcpu, u8 vec)
+{
+	long spsr;
+	int ret;
+
+	local_irq_save(spsr);
+	ret = test_and_clear_bit(vec, &VCPU(vcpu, irr[0]));
+	local_irq_restore(spsr);
+	if (ret) {
+		vcpu->arch.irq_new_pending = 1;
+		wmb();
+	}
+}
+
+void update_vhpi(struct kvm_vcpu *vcpu, int vec)
+{
+	u64 vhpi;
+
+	if (vec == NULL_VECTOR)
+		vhpi = 0;
+	else if (vec == NMI_VECTOR)
+		vhpi = 32;
+	else if (vec == ExtINT_VECTOR)
+		vhpi = 16;
+	else
+		vhpi = vec >> 4;
+
+	VCPU(vcpu, vhpi) = vhpi;
+	if (VCPU(vcpu, vac).a_int)
+		ia64_call_vsa(PAL_VPS_SET_PENDING_INTERRUPT,
+				(u64)vcpu->arch.vpd, 0, 0, 0, 0, 0, 0);
+}
+
+u64 vcpu_get_ivr(struct kvm_vcpu *vcpu)
+{
+	int vec, h_inservice, mask;
+
+	vec = highest_pending_irq(vcpu);
+	h_inservice = highest_inservice_irq(vcpu);
+	mask = irq_masked(vcpu, vec, h_inservice);
+	if (vec == NULL_VECTOR || mask == IRQ_MASKED_BY_INSVC) {
+		if (VCPU(vcpu, vhpi))
+			update_vhpi(vcpu, NULL_VECTOR);
+		return IA64_SPURIOUS_INT_VECTOR;
+	}
+	if (mask == IRQ_MASKED_BY_VTPR) {
+		update_vhpi(vcpu, vec);
+		return IA64_SPURIOUS_INT_VECTOR;
+	}
+	VMX(vcpu, insvc[vec >> 6]) |= (1UL << (vec & 63));
+	vcpu_unpend_interrupt(vcpu, vec);
+	return  (u64)vec;
+}
+
+/**************************************************************************
+  Privileged operation emulation routines
+ **************************************************************************/
+u64 vcpu_thash(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	union ia64_pta vpta;
+	union ia64_rr vrr;
+	u64 pval;
+	u64 vhpt_offset;
+
+	vpta.val = vcpu_get_pta(vcpu);
+	vrr.val = vcpu_get_rr(vcpu, vadr);
+	vhpt_offset = ((vadr >> vrr.ps) << 3) & ((1UL << (vpta.size)) - 1);
+	if (vpta.vf) {
+		pval = ia64_call_vsa(PAL_VPS_THASH, vadr, vrr.val,
+				vpta.val, 0, 0, 0, 0);
+	} else {
+		pval = (vadr & VRN_MASK) | vhpt_offset |
+			(vpta.val << 3 >> (vpta.size + 3) << (vpta.size));
+	}
+	return  pval;
+}
+
+u64 vcpu_ttag(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	union ia64_rr vrr;
+	union ia64_pta vpta;
+	u64 pval;
+
+	vpta.val = vcpu_get_pta(vcpu);
+	vrr.val = vcpu_get_rr(vcpu, vadr);
+	if (vpta.vf) {
+		pval = ia64_call_vsa(PAL_VPS_TTAG, vadr, vrr.val,
+						0, 0, 0, 0, 0);
+	} else
+		pval = 1;
+
+	return  pval;
+}
+
+u64 vcpu_tak(struct kvm_vcpu *vcpu, u64 vadr)
+{
+	struct thash_data *data;
+	union ia64_pta vpta;
+	u64 key;
+
+	vpta.val = vcpu_get_pta(vcpu);
+	if (vpta.vf == 0) {
+		key = 1;
+		return key;
+	}
+	data = vtlb_lookup(vcpu, vadr, D_TLB);
+	if (!data || !data->p)
+		key = 1;
+	else
+		key = data->key;
+
+	return key;
+}
+
+
+
+void kvm_thash(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long thash, vadr;
+
+	vadr = vcpu_get_gr(vcpu, inst.M46.r3);
+	thash = vcpu_thash(vcpu, vadr);
+	vcpu_set_gr(vcpu, inst.M46.r1, thash, 0);
+}
+
+
+void kvm_ttag(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long tag, vadr;
+
+	vadr = vcpu_get_gr(vcpu, inst.M46.r3);
+	tag = vcpu_ttag(vcpu, vadr);
+	vcpu_set_gr(vcpu, inst.M46.r1, tag, 0);
+}
+
+int vcpu_tpa(struct kvm_vcpu *vcpu, u64 vadr, u64 *padr)
+{
+	struct thash_data *data;
+	union ia64_isr visr, pt_isr;
+	struct kvm_pt_regs *regs;
+	struct ia64_psr vpsr;
+
+	regs = vcpu_regs(vcpu);
+	pt_isr.val = VMX(vcpu, cr_isr);
+	visr.val = 0;
+	visr.ei = pt_isr.ei;
+	visr.ir = pt_isr.ir;
+	vpsr = *(struct ia64_psr *)&VCPU(vcpu, vpsr);
+	visr.na = 1;
+
+	data = vhpt_lookup(vadr);
+	if (data) {
+		if (data->p == 0) {
+			vcpu_set_isr(vcpu, visr.val);
+			data_page_not_present(vcpu, vadr);
+			return IA64_FAULT;
+		} else if (data->ma == VA_MATTR_NATPAGE) {
+			vcpu_set_isr(vcpu, visr.val);
+			dnat_page_consumption(vcpu, vadr);
+			return IA64_FAULT;
+		} else {
+			*padr = (data->gpaddr >> data->ps << data->ps) |
+				(vadr & (PSIZE(data->ps) - 1));
+			return IA64_NO_FAULT;
+		}
+	}
+
+	data = vtlb_lookup(vcpu, vadr, D_TLB);
+	if (data) {
+		if (data->p == 0) {
+			vcpu_set_isr(vcpu, visr.val);
+			data_page_not_present(vcpu, vadr);
+			return IA64_FAULT;
+		} else if (data->ma == VA_MATTR_NATPAGE) {
+			vcpu_set_isr(vcpu, visr.val);
+			dnat_page_consumption(vcpu, vadr);
+			return IA64_FAULT;
+		} else{
+			*padr = ((data->ppn >> (data->ps - 12)) << data->ps)
+				| (vadr & (PSIZE(data->ps) - 1));
+			return IA64_NO_FAULT;
+		}
+	}
+	if (!vhpt_enabled(vcpu, vadr, NA_REF)) {
+		if (vpsr.ic) {
+			vcpu_set_isr(vcpu, visr.val);
+			alt_dtlb(vcpu, vadr);
+			return IA64_FAULT;
+		} else {
+			nested_dtlb(vcpu);
+			return IA64_FAULT;
+		}
+	} else {
+		if (vpsr.ic) {
+			vcpu_set_isr(vcpu, visr.val);
+			dvhpt_fault(vcpu, vadr);
+			return IA64_FAULT;
+		} else{
+			nested_dtlb(vcpu);
+			return IA64_FAULT;
+		}
+	}
+
+	return IA64_NO_FAULT;
+}
+
+
+int kvm_tpa(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long r1, r3;
+
+	r3 = vcpu_get_gr(vcpu, inst.M46.r3);
+
+	if (vcpu_tpa(vcpu, r3, &r1))
+		return IA64_FAULT;
+
+	vcpu_set_gr(vcpu, inst.M46.r1, r1, 0);
+	return(IA64_NO_FAULT);
+}
+
+void kvm_tak(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long r1, r3;
+
+	r3 = vcpu_get_gr(vcpu, inst.M46.r3);
+	r1 = vcpu_tak(vcpu, r3);
+	vcpu_set_gr(vcpu, inst.M46.r1, r1, 0);
+}
+
+
+/************************************
+ * Insert/Purge translation register/cache
+ ************************************/
+void vcpu_itc_i(struct kvm_vcpu *vcpu, u64 pte, u64 itir, u64 ifa)
+{
+	thash_purge_and_insert(vcpu, pte, itir, ifa, I_TLB);
+}
+
+void vcpu_itc_d(struct kvm_vcpu *vcpu, u64 pte, u64 itir, u64 ifa)
+{
+	thash_purge_and_insert(vcpu, pte, itir, ifa, D_TLB);
+}
+
+void vcpu_itr_i(struct kvm_vcpu *vcpu, u64 slot, u64 pte, u64 itir, u64 ifa)
+{
+	u64 ps, va, rid;
+	struct thash_data *p_itr;
+
+	ps = itir_ps(itir);
+	va = PAGEALIGN(ifa, ps);
+	pte &= ~PAGE_FLAGS_RV_MASK;
+	rid = vcpu_get_rr(vcpu, ifa);
+	rid = rid & RR_RID_MASK;
+	p_itr = (struct thash_data *)&vcpu->arch.itrs[slot];
+	vcpu_set_tr(p_itr, pte, itir, va, rid);
+	vcpu_quick_region_set(VMX(vcpu, itr_regions), va);
+}
+
+
+void vcpu_itr_d(struct kvm_vcpu *vcpu, u64 slot, u64 pte, u64 itir, u64 ifa)
+{
+	u64 gpfn;
+	u64 ps, va, rid;
+	struct thash_data *p_dtr;
+
+	ps = itir_ps(itir);
+	va = PAGEALIGN(ifa, ps);
+	pte &= ~PAGE_FLAGS_RV_MASK;
+
+	if (ps != _PAGE_SIZE_16M)
+		thash_purge_entries(vcpu, va, ps);
+	gpfn = (pte & _PAGE_PPN_MASK) >> PAGE_SHIFT;
+	if (__gpfn_is_io(gpfn))
+		pte |= VTLB_PTE_IO;
+	rid = vcpu_get_rr(vcpu, va);
+	rid = rid & RR_RID_MASK;
+	p_dtr = (struct thash_data *)&vcpu->arch.dtrs[slot];
+	vcpu_set_tr((struct thash_data *)&vcpu->arch.dtrs[slot],
+							pte, itir, va, rid);
+	vcpu_quick_region_set(VMX(vcpu, dtr_regions), va);
+}
+
+void vcpu_ptr_d(struct kvm_vcpu *vcpu, u64 ifa, u64 ps)
+{
+	int index;
+	u64 va;
+
+	va = PAGEALIGN(ifa, ps);
+	while ((index = vtr_find_overlap(vcpu, va, ps, D_TLB)) >= 0)
+		vcpu->arch.dtrs[index].page_flags = 0;
+
+	thash_purge_entries(vcpu, va, ps);
+}
+
+void vcpu_ptr_i(struct kvm_vcpu *vcpu, u64 ifa, u64 ps)
+{
+	int index;
+	u64 va;
+
+	va = PAGEALIGN(ifa, ps);
+	while ((index = vtr_find_overlap(vcpu, va, ps, I_TLB)) >= 0)
+		vcpu->arch.itrs[index].page_flags = 0;
+
+	thash_purge_entries(vcpu, va, ps);
+}
+
+void vcpu_ptc_l(struct kvm_vcpu *vcpu, u64 va, u64 ps)
+{
+	va = PAGEALIGN(va, ps);
+	thash_purge_entries(vcpu, va, ps);
+}
+
+void vcpu_ptc_e(struct kvm_vcpu *vcpu, u64 va)
+{
+	thash_purge_all(vcpu);
+}
+
+void vcpu_ptc_ga(struct kvm_vcpu *vcpu, u64 va, u64 ps)
+{
+	struct exit_ctl_data *p = &vcpu->arch.exit_data;
+	long psr;
+	local_irq_save(psr);
+	p->exit_reason = EXIT_REASON_PTC_G;
+
+	p->u.ptc_g_data.rr = vcpu_get_rr(vcpu, va);
+	p->u.ptc_g_data.vaddr = va;
+	p->u.ptc_g_data.ps = ps;
+	vmm_transition(vcpu);
+	/* Do Local Purge Here*/
+	vcpu_ptc_l(vcpu, va, ps);
+	local_irq_restore(psr);
+}
+
+
+void vcpu_ptc_g(struct kvm_vcpu *vcpu, u64 va, u64 ps)
+{
+	vcpu_ptc_ga(vcpu, va, ps);
+}
+
+void kvm_ptc_e(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long ifa;
+
+	ifa = vcpu_get_gr(vcpu, inst.M45.r3);
+	vcpu_ptc_e(vcpu, ifa);
+}
+
+void kvm_ptc_g(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long ifa, itir;
+
+	ifa = vcpu_get_gr(vcpu, inst.M45.r3);
+	itir = vcpu_get_gr(vcpu, inst.M45.r2);
+	vcpu_ptc_g(vcpu, ifa, itir_ps(itir));
+}
+
+void kvm_ptc_ga(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long ifa, itir;
+
+	ifa = vcpu_get_gr(vcpu, inst.M45.r3);
+	itir = vcpu_get_gr(vcpu, inst.M45.r2);
+	vcpu_ptc_ga(vcpu, ifa, itir_ps(itir));
+}
+
+void kvm_ptc_l(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long ifa, itir;
+
+	ifa = vcpu_get_gr(vcpu, inst.M45.r3);
+	itir = vcpu_get_gr(vcpu, inst.M45.r2);
+	vcpu_ptc_l(vcpu, ifa, itir_ps(itir));
+}
+
+void kvm_ptr_d(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long ifa, itir;
+
+	ifa = vcpu_get_gr(vcpu, inst.M45.r3);
+	itir = vcpu_get_gr(vcpu, inst.M45.r2);
+	vcpu_ptr_d(vcpu, ifa, itir_ps(itir));
+}
+
+void kvm_ptr_i(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long ifa, itir;
+
+	ifa = vcpu_get_gr(vcpu, inst.M45.r3);
+	itir = vcpu_get_gr(vcpu, inst.M45.r2);
+	vcpu_ptr_i(vcpu, ifa, itir_ps(itir));
+}
+
+void kvm_itr_d(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long itir, ifa, pte, slot;
+
+	slot = vcpu_get_gr(vcpu, inst.M45.r3);
+	pte = vcpu_get_gr(vcpu, inst.M45.r2);
+	itir = vcpu_get_itir(vcpu);
+	ifa = vcpu_get_ifa(vcpu);
+	vcpu_itr_d(vcpu, slot, pte, itir, ifa);
+}
+
+
+
+void kvm_itr_i(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long itir, ifa, pte, slot;
+
+	slot = vcpu_get_gr(vcpu, inst.M45.r3);
+	pte = vcpu_get_gr(vcpu, inst.M45.r2);
+	itir = vcpu_get_itir(vcpu);
+	ifa = vcpu_get_ifa(vcpu);
+	vcpu_itr_i(vcpu, slot, pte, itir, ifa);
+}
+
+void kvm_itc_d(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long itir, ifa, pte;
+
+	itir = vcpu_get_itir(vcpu);
+	ifa = vcpu_get_ifa(vcpu);
+	pte = vcpu_get_gr(vcpu, inst.M45.r2);
+	vcpu_itc_d(vcpu, pte, itir, ifa);
+}
+
+void kvm_itc_i(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long itir, ifa, pte;
+
+	itir = vcpu_get_itir(vcpu);
+	ifa = vcpu_get_ifa(vcpu);
+	pte = vcpu_get_gr(vcpu, inst.M45.r2);
+	vcpu_itc_i(vcpu, pte, itir, ifa);
+}
+
+/*************************************
+ * Moves to semi-privileged registers
+ *************************************/
+
+void kvm_mov_to_ar_imm(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long imm;
+
+	if (inst.M30.s)
+		imm = -inst.M30.imm;
+	else
+		imm = inst.M30.imm;
+
+	vcpu_set_itc(vcpu, imm);
+}
+
+void kvm_mov_to_ar_reg(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long r2;
+
+	r2 = vcpu_get_gr(vcpu, inst.M29.r2);
+	vcpu_set_itc(vcpu, r2);
+}
+
+
+void kvm_mov_from_ar_reg(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long r1;
+
+	r1 = vcpu_get_itc(vcpu);
+	vcpu_set_gr(vcpu, inst.M31.r1, r1, 0);
+}
+/**************************************************************************
+  struct kvm_vcpu*protection key register access routines
+ **************************************************************************/
+
+unsigned long vcpu_get_pkr(struct kvm_vcpu *vcpu, unsigned long reg)
+{
+	return ((unsigned long)ia64_get_pkr(reg));
+}
+
+void vcpu_set_pkr(struct kvm_vcpu *vcpu, unsigned long reg, unsigned long val)
+{
+	ia64_set_pkr(reg, val);
+}
+
+
+unsigned long vcpu_get_itir_on_fault(struct kvm_vcpu *vcpu, unsigned long ifa)
+{
+	union ia64_rr rr, rr1;
+
+	rr.val = vcpu_get_rr(vcpu, ifa);
+	rr1.val = 0;
+	rr1.ps = rr.ps;
+	rr1.rid = rr.rid;
+	return (rr1.val);
+}
+
+
+
+/********************************
+ * Moves to privileged registers
+ ********************************/
+unsigned long vcpu_set_rr(struct kvm_vcpu *vcpu, unsigned long reg,
+					unsigned long val)
+{
+	union ia64_rr oldrr, newrr;
+	unsigned long rrval;
+	struct exit_ctl_data *p = &vcpu->arch.exit_data;
+	unsigned long psr;
+
+	oldrr.val = vcpu_get_rr(vcpu, reg);
+	newrr.val = val;
+	vcpu->arch.vrr[reg >> VRN_SHIFT] = val;
+
+	switch ((unsigned long)(reg >> VRN_SHIFT)) {
+	case VRN6:
+		vcpu->arch.vmm_rr = vrrtomrr(val);
+		local_irq_save(psr);
+		p->exit_reason = EXIT_REASON_SWITCH_RR6;
+		vmm_transition(vcpu);
+		local_irq_restore(psr);
+		break;
+	case VRN4:
+		rrval = vrrtomrr(val);
+		vcpu->arch.metaphysical_saved_rr4 = rrval;
+		if (!is_physical_mode(vcpu))
+			ia64_set_rr(reg, rrval);
+		break;
+	case VRN0:
+		rrval = vrrtomrr(val);
+		vcpu->arch.metaphysical_saved_rr0 = rrval;
+		if (!is_physical_mode(vcpu))
+			ia64_set_rr(reg, rrval);
+		break;
+	default:
+		ia64_set_rr(reg, vrrtomrr(val));
+		break;
+	}
+
+	return (IA64_NO_FAULT);
+}
+
+
+
+void kvm_mov_to_rr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long r3, r2;
+
+	r3 = vcpu_get_gr(vcpu, inst.M42.r3);
+	r2 = vcpu_get_gr(vcpu, inst.M42.r2);
+	vcpu_set_rr(vcpu, r3, r2);
+}
+
+void kvm_mov_to_dbr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+}
+
+void kvm_mov_to_ibr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+}
+
+void kvm_mov_to_pmc(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long r3, r2;
+
+	r3 = vcpu_get_gr(vcpu, inst.M42.r3);
+	r2 = vcpu_get_gr(vcpu, inst.M42.r2);
+	vcpu_set_pmc(vcpu, r3, r2);
+}
+
+void kvm_mov_to_pmd(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long r3, r2;
+
+	r3 = vcpu_get_gr(vcpu, inst.M42.r3);
+	r2 = vcpu_get_gr(vcpu, inst.M42.r2);
+	vcpu_set_pmd(vcpu, r3, r2);
+}
+
+void kvm_mov_to_pkr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	u64 r3, r2;
+
+	r3 = vcpu_get_gr(vcpu, inst.M42.r3);
+	r2 = vcpu_get_gr(vcpu, inst.M42.r2);
+	vcpu_set_pkr(vcpu, r3, r2);
+}
+
+
+
+void kvm_mov_from_rr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long r3, r1;
+
+	r3 = vcpu_get_gr(vcpu, inst.M43.r3);
+	r1 = vcpu_get_rr(vcpu, r3);
+	vcpu_set_gr(vcpu, inst.M43.r1, r1, 0);
+}
+
+void kvm_mov_from_pkr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long r3, r1;
+
+	r3 = vcpu_get_gr(vcpu, inst.M43.r3);
+	r1 = vcpu_get_pkr(vcpu, r3);
+	vcpu_set_gr(vcpu, inst.M43.r1, r1, 0);
+}
+
+void kvm_mov_from_dbr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long r3, r1;
+
+	r3 = vcpu_get_gr(vcpu, inst.M43.r3);
+	r1 = vcpu_get_dbr(vcpu, r3);
+	vcpu_set_gr(vcpu, inst.M43.r1, r1, 0);
+}
+
+void kvm_mov_from_ibr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long r3, r1;
+
+	r3 = vcpu_get_gr(vcpu, inst.M43.r3);
+	r1 = vcpu_get_ibr(vcpu, r3);
+	vcpu_set_gr(vcpu, inst.M43.r1, r1, 0);
+}
+
+void kvm_mov_from_pmc(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long r3, r1;
+
+	r3 = vcpu_get_gr(vcpu, inst.M43.r3);
+	r1 = vcpu_get_pmc(vcpu, r3);
+	vcpu_set_gr(vcpu, inst.M43.r1, r1, 0);
+}
+
+
+unsigned long vcpu_get_cpuid(struct kvm_vcpu *vcpu, unsigned long reg)
+{
+	/* FIXME: This could get called as a result of a rsvd-reg fault */
+	if (reg > (ia64_get_cpuid(3) & 0xff))
+		return 0;
+	else
+		return ia64_get_cpuid(reg);
+}
+
+void kvm_mov_from_cpuid(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long r3, r1;
+
+	r3 = vcpu_get_gr(vcpu, inst.M43.r3);
+	r1 = vcpu_get_cpuid(vcpu, r3);
+	vcpu_set_gr(vcpu, inst.M43.r1, r1, 0);
+}
+
+void vcpu_set_tpr(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	VCPU(vcpu, tpr) = val;
+	vcpu->arch.irq_check = 1;
+}
+
+unsigned long kvm_mov_to_cr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long r2;
+
+	r2 = vcpu_get_gr(vcpu, inst.M32.r2);
+	VCPU(vcpu, vcr[inst.M32.cr3]) = r2;
+
+	switch (inst.M32.cr3) {
+	case 0:
+		vcpu_set_dcr(vcpu, r2);
+		break;
+	case 1:
+		vcpu_set_itm(vcpu, r2);
+		break;
+	case 66:
+		vcpu_set_tpr(vcpu, r2);
+		break;
+	case 67:
+		vcpu_set_eoi(vcpu, r2);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+
+unsigned long kvm_mov_from_cr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long tgt = inst.M33.r1;
+	unsigned long val;
+
+	switch (inst.M33.cr3) {
+	case 65:
+		val = vcpu_get_ivr(vcpu);
+		vcpu_set_gr(vcpu, tgt, val, 0);
+		break;
+
+	case 67:
+		vcpu_set_gr(vcpu, tgt, 0L, 0);
+		break;
+	default:
+		val = VCPU(vcpu, vcr[inst.M33.cr3]);
+		vcpu_set_gr(vcpu, tgt, val, 0);
+		break;
+	}
+
+	return 0;
+}
+
+
+
+void vcpu_set_psr(struct kvm_vcpu *vcpu, unsigned long val)
+{
+
+	unsigned long mask;
+	struct kvm_pt_regs *regs;
+	struct ia64_psr old_psr, new_psr;
+
+	old_psr = *(struct ia64_psr *)&VCPU(vcpu, vpsr);
+
+	regs = vcpu_regs(vcpu);
+	/* We only support guest as:
+	 *  vpsr.pk = 0
+	 *  vpsr.is = 0
+	 * Otherwise panic
+	 */
+	if (val & (IA64_PSR_PK | IA64_PSR_IS | IA64_PSR_VM))
+		panic_vm(vcpu);
+
+	/*
+	 * For those IA64_PSR bits: id/da/dd/ss/ed/ia
+	 * Since these bits will become 0, after success execution of each
+	 * instruction, we will change set them to mIA64_PSR
+	 */
+	VCPU(vcpu, vpsr) = val
+		& (~(IA64_PSR_ID | IA64_PSR_DA | IA64_PSR_DD |
+			IA64_PSR_SS | IA64_PSR_ED | IA64_PSR_IA));
+
+	if (!old_psr.i && (val & IA64_PSR_I)) {
+		/* vpsr.i 0->1 */
+		vcpu->arch.irq_check = 1;
+	}
+	new_psr = *(struct ia64_psr *)&VCPU(vcpu, vpsr);
+
+	/*
+	 * All vIA64_PSR bits shall go to mPSR (v->tf->tf_special.psr)
+	 * , except for the following bits:
+	 *  ic/i/dt/si/rt/mc/it/bn/vm
+	 */
+	mask =  IA64_PSR_IC + IA64_PSR_I + IA64_PSR_DT + IA64_PSR_SI +
+		IA64_PSR_RT + IA64_PSR_MC + IA64_PSR_IT + IA64_PSR_BN +
+		IA64_PSR_VM;
+
+	regs->cr_ipsr = (regs->cr_ipsr & mask) | (val & (~mask));
+
+	check_mm_mode_switch(vcpu, old_psr, new_psr);
+
+	return ;
+}
+
+unsigned long vcpu_cover(struct kvm_vcpu *vcpu)
+{
+	struct ia64_psr vpsr;
+
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+	vpsr = *(struct ia64_psr *)&VCPU(vcpu, vpsr);
+
+	if (!vpsr.ic)
+		VCPU(vcpu, ifs) = regs->cr_ifs;
+	regs->cr_ifs = IA64_IFS_V;
+	return (IA64_NO_FAULT);
+}
+
+
+
+/**************************************************************************
+  VCPU banked general register access routines
+ **************************************************************************/
+#define vcpu_bsw0_unat(i, b0unat, b1unat, runat, VMM_PT_REGS_R16_SLOT)	\
+	do {     							\
+		__asm__ __volatile__ (					\
+				";;extr.u %0 = %3,%6,16;;\n"		\
+				"dep %1 = %0, %1, 0, 16;;\n"		\
+				"st8 [%4] = %1\n"			\
+				"extr.u %0 = %2, 16, 16;;\n"		\
+				"dep %3 = %0, %3, %6, 16;;\n"		\
+				"st8 [%5] = %3\n"			\
+				::"r"(i), "r"(*b1unat), "r"(*b0unat),	\
+				"r"(*runat), "r"(b1unat), "r"(runat),	\
+				"i"(VMM_PT_REGS_R16_SLOT) : "memory");	\
+	} while (0)
+
+void vcpu_bsw0(struct kvm_vcpu *vcpu)
+{
+	unsigned long i;
+
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+	unsigned long *r = &regs->r16;
+	unsigned long *b0 = &VCPU(vcpu, vbgr[0]);
+	unsigned long *b1 = &VCPU(vcpu, vgr[0]);
+	unsigned long *runat = &regs->eml_unat;
+	unsigned long *b0unat = &VCPU(vcpu, vbnat);
+	unsigned long *b1unat = &VCPU(vcpu, vnat);
+
+
+	if (VCPU(vcpu, vpsr) & IA64_PSR_BN) {
+		for (i = 0; i < 16; i++) {
+			*b1++ = *r;
+			*r++ = *b0++;
+		}
+		vcpu_bsw0_unat(i, b0unat, b1unat, runat,
+				VMM_PT_REGS_R16_SLOT);
+		VCPU(vcpu, vpsr) &= ~IA64_PSR_BN;
+	}
+}
+
+#define vcpu_bsw1_unat(i, b0unat, b1unat, runat, VMM_PT_REGS_R16_SLOT)	\
+	do {             						\
+		__asm__ __volatile__ (";;extr.u %0 = %3, %6, 16;;\n"	\
+				"dep %1 = %0, %1, 16, 16;;\n"		\
+				"st8 [%4] = %1\n"			\
+				"extr.u %0 = %2, 0, 16;;\n"		\
+				"dep %3 = %0, %3, %6, 16;;\n"		\
+				"st8 [%5] = %3\n"			\
+				::"r"(i), "r"(*b0unat), "r"(*b1unat),	\
+				"r"(*runat), "r"(b0unat), "r"(runat),	\
+				"i"(VMM_PT_REGS_R16_SLOT) : "memory");	\
+	} while (0)
+
+void vcpu_bsw1(struct kvm_vcpu *vcpu)
+{
+	unsigned long i;
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+	unsigned long *r = &regs->r16;
+	unsigned long *b0 = &VCPU(vcpu, vbgr[0]);
+	unsigned long *b1 = &VCPU(vcpu, vgr[0]);
+	unsigned long *runat = &regs->eml_unat;
+	unsigned long *b0unat = &VCPU(vcpu, vbnat);
+	unsigned long *b1unat = &VCPU(vcpu, vnat);
+
+	if (!(VCPU(vcpu, vpsr) & IA64_PSR_BN)) {
+		for (i = 0; i < 16; i++) {
+			*b0++ = *r;
+			*r++ = *b1++;
+		}
+		vcpu_bsw1_unat(i, b0unat, b1unat, runat,
+				VMM_PT_REGS_R16_SLOT);
+		VCPU(vcpu, vpsr) |= IA64_PSR_BN;
+	}
+}
+
+
+
+
+void vcpu_rfi(struct kvm_vcpu *vcpu)
+{
+	unsigned long ifs, psr;
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+	psr = VCPU(vcpu, ipsr);
+	if (psr & IA64_PSR_BN)
+		vcpu_bsw1(vcpu);
+	else
+		vcpu_bsw0(vcpu);
+	vcpu_set_psr(vcpu, psr);
+	ifs = VCPU(vcpu, ifs);
+	if (ifs >> 63)
+		regs->cr_ifs = ifs;
+	regs->cr_iip = VCPU(vcpu, iip);
+}
+
+
+/*
+   VPSR can't keep track of below bits of guest PSR
+   This function gets guest PSR
+ */
+
+unsigned long vcpu_get_psr(struct kvm_vcpu *vcpu)
+{
+	unsigned long mask;
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+	mask = IA64_PSR_BE | IA64_PSR_UP | IA64_PSR_AC | IA64_PSR_MFL |
+		IA64_PSR_MFH | IA64_PSR_CPL | IA64_PSR_RI;
+	return (VCPU(vcpu, vpsr) & ~mask) | (regs->cr_ipsr & mask);
+}
+
+void kvm_rsm(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long vpsr;
+	unsigned long imm24 = (inst.M44.i<<23) | (inst.M44.i2<<21)
+					| inst.M44.imm;
+
+	vpsr = vcpu_get_psr(vcpu);
+	vpsr &= (~imm24);
+	vcpu_set_psr(vcpu, vpsr);
+}
+
+void kvm_ssm(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long vpsr;
+	unsigned long imm24 = (inst.M44.i << 23) | (inst.M44.i2 << 21)
+				| inst.M44.imm;
+
+	vpsr = vcpu_get_psr(vcpu);
+	vpsr |= imm24;
+	vcpu_set_psr(vcpu, vpsr);
+}
+
+/* Generate Mask
+ * Parameter:
+ *  bit -- starting bit
+ *  len -- how many bits
+ */
+#define MASK(bit,len)				   	\
+({							\
+		__u64	ret;				\
+							\
+		__asm __volatile("dep %0=-1, r0, %1, %2"\
+				: "=r" (ret):		\
+		  "M" (bit),				\
+		  "M" (len));				\
+		ret;					\
+})
+
+void vcpu_set_psr_l(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	val = (val & MASK(0, 32)) | (vcpu_get_psr(vcpu) & MASK(32, 32));
+	vcpu_set_psr(vcpu, val);
+}
+
+void kvm_mov_to_psr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long val;
+
+	val = vcpu_get_gr(vcpu, inst.M35.r2);
+	vcpu_set_psr_l(vcpu, val);
+}
+
+void kvm_mov_from_psr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+	unsigned long val;
+
+	val = vcpu_get_psr(vcpu);
+	val = (val & MASK(0, 32)) | (val & MASK(35, 2));
+	vcpu_set_gr(vcpu, inst.M33.r1, val, 0);
+}
+
+void vcpu_increment_iip(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+	struct ia64_psr *ipsr = (struct ia64_psr *)&regs->cr_ipsr;
+	if (ipsr->ri == 2) {
+		ipsr->ri = 0;
+		regs->cr_iip += 16;
+	} else
+		ipsr->ri++;
+}
+
+void vcpu_decrement_iip(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+	struct ia64_psr *ipsr = (struct ia64_psr *)&regs->cr_ipsr;
+
+	if (ipsr->ri == 0) {
+		ipsr->ri = 2;
+		regs->cr_iip -= 16;
+	} else
+		ipsr->ri--;
+}
+
+/** Emulate a privileged operation.
+ *
+ *
+ * @param vcpu virtual cpu
+ * @cause the reason cause virtualization fault
+ * @opcode the instruction code which cause virtualization fault
+ */
+
+void kvm_emulate(struct kvm_vcpu *vcpu, struct kvm_pt_regs *regs)
+{
+	unsigned long status, cause, opcode ;
+	INST64 inst;
+
+	status = IA64_NO_FAULT;
+	cause = VMX(vcpu, cause);
+	opcode = VMX(vcpu, opcode);
+	inst.inst = opcode;
+	/*
+	 * Switch to actual virtual rid in rr0 and rr4,
+	 * which is required by some tlb related instructions.
+	 */
+	prepare_if_physical_mode(vcpu);
+
+	switch (cause) {
+	case EVENT_RSM:
+		kvm_rsm(vcpu, inst);
+		break;
+	case EVENT_SSM:
+		kvm_ssm(vcpu, inst);
+		break;
+	case EVENT_MOV_TO_PSR:
+		kvm_mov_to_psr(vcpu, inst);
+		break;
+	case EVENT_MOV_FROM_PSR:
+		kvm_mov_from_psr(vcpu, inst);
+		break;
+	case EVENT_MOV_FROM_CR:
+		kvm_mov_from_cr(vcpu, inst);
+		break;
+	case EVENT_MOV_TO_CR:
+		kvm_mov_to_cr(vcpu, inst);
+		break;
+	case EVENT_BSW_0:
+		vcpu_bsw0(vcpu);
+		break;
+	case EVENT_BSW_1:
+		vcpu_bsw1(vcpu);
+		break;
+	case EVENT_COVER:
+		vcpu_cover(vcpu);
+		break;
+	case EVENT_RFI:
+		vcpu_rfi(vcpu);
+		break;
+	case EVENT_ITR_D:
+		kvm_itr_d(vcpu, inst);
+		break;
+	case EVENT_ITR_I:
+		kvm_itr_i(vcpu, inst);
+		break;
+	case EVENT_PTR_D:
+		kvm_ptr_d(vcpu, inst);
+		break;
+	case EVENT_PTR_I:
+		kvm_ptr_i(vcpu, inst);
+		break;
+	case EVENT_ITC_D:
+		kvm_itc_d(vcpu, inst);
+		break;
+	case EVENT_ITC_I:
+		kvm_itc_i(vcpu, inst);
+		break;
+	case EVENT_PTC_L:
+		kvm_ptc_l(vcpu, inst);
+		break;
+	case EVENT_PTC_G:
+		kvm_ptc_g(vcpu, inst);
+		break;
+	case EVENT_PTC_GA:
+		kvm_ptc_ga(vcpu, inst);
+		break;
+	case EVENT_PTC_E:
+		kvm_ptc_e(vcpu, inst);
+		break;
+	case EVENT_MOV_TO_RR:
+		kvm_mov_to_rr(vcpu, inst);
+		break;
+	case EVENT_MOV_FROM_RR:
+		kvm_mov_from_rr(vcpu, inst);
+		break;
+	case EVENT_THASH:
+		kvm_thash(vcpu, inst);
+		break;
+	case EVENT_TTAG:
+		kvm_ttag(vcpu, inst);
+		break;
+	case EVENT_TPA:
+		status = kvm_tpa(vcpu, inst);
+		break;
+	case EVENT_TAK:
+		kvm_tak(vcpu, inst);
+		break;
+	case EVENT_MOV_TO_AR_IMM:
+		kvm_mov_to_ar_imm(vcpu, inst);
+		break;
+	case EVENT_MOV_TO_AR:
+		kvm_mov_to_ar_reg(vcpu, inst);
+		break;
+	case EVENT_MOV_FROM_AR:
+		kvm_mov_from_ar_reg(vcpu, inst);
+		break;
+	case EVENT_MOV_TO_DBR:
+		kvm_mov_to_dbr(vcpu, inst);
+		break;
+	case EVENT_MOV_TO_IBR:
+		kvm_mov_to_ibr(vcpu, inst);
+		break;
+	case EVENT_MOV_TO_PMC:
+		kvm_mov_to_pmc(vcpu, inst);
+		break;
+	case EVENT_MOV_TO_PMD:
+		kvm_mov_to_pmd(vcpu, inst);
+		break;
+	case EVENT_MOV_TO_PKR:
+		kvm_mov_to_pkr(vcpu, inst);
+		break;
+	case EVENT_MOV_FROM_DBR:
+		kvm_mov_from_dbr(vcpu, inst);
+		break;
+	case EVENT_MOV_FROM_IBR:
+		kvm_mov_from_ibr(vcpu, inst);
+		break;
+	case EVENT_MOV_FROM_PMC:
+		kvm_mov_from_pmc(vcpu, inst);
+		break;
+	case EVENT_MOV_FROM_PKR:
+		kvm_mov_from_pkr(vcpu, inst);
+		break;
+	case EVENT_MOV_FROM_CPUID:
+		kvm_mov_from_cpuid(vcpu, inst);
+		break;
+	case EVENT_VMSW:
+		status = IA64_FAULT;
+		break;
+	default:
+		break;
+	};
+	/*Assume all status is NO_FAULT ?*/
+	if (status == IA64_NO_FAULT && cause != EVENT_RFI)
+		vcpu_increment_iip(vcpu);
+
+	recover_if_physical_mode(vcpu);
+}
+
+void init_vcpu(struct kvm_vcpu *vcpu)
+{
+	int i;
+
+	vcpu->arch.mode_flags = GUEST_IN_PHY;
+	VMX(vcpu, vrr[0]) = 0x38;
+	VMX(vcpu, vrr[1]) = 0x38;
+	VMX(vcpu, vrr[2]) = 0x38;
+	VMX(vcpu, vrr[3]) = 0x38;
+	VMX(vcpu, vrr[4]) = 0x38;
+	VMX(vcpu, vrr[5]) = 0x38;
+	VMX(vcpu, vrr[6]) = 0x38;
+	VMX(vcpu, vrr[7]) = 0x38;
+	VCPU(vcpu, vpsr) = IA64_PSR_BN;
+	VCPU(vcpu, dcr) = 0;
+	/* pta.size must not be 0.  The minimum is 15 (32k) */
+	VCPU(vcpu, pta) = 15 << 2;
+	VCPU(vcpu, itv) = 0x10000;
+	VCPU(vcpu, itm) = 0;
+	VMX(vcpu, last_itc) = 0;
+
+	VCPU(vcpu, lid) = VCPU_LID(vcpu);
+	VCPU(vcpu, ivr) = 0;
+	VCPU(vcpu, tpr) = 0x10000;
+	VCPU(vcpu, eoi) = 0;
+	VCPU(vcpu, irr[0]) = 0;
+	VCPU(vcpu, irr[1]) = 0;
+	VCPU(vcpu, irr[2]) = 0;
+	VCPU(vcpu, irr[3]) = 0;
+	VCPU(vcpu, pmv) = 0x10000;
+	VCPU(vcpu, cmcv) = 0x10000;
+	VCPU(vcpu, lrr0) = 0x10000;   /* default reset value? */
+	VCPU(vcpu, lrr1) = 0x10000;   /* default reset value? */
+	update_vhpi(vcpu, NULL_VECTOR);
+	VLSAPIC_XTP(vcpu) = 0x80;	/* disabled */
+
+	for (i = 0; i < 4; i++)
+		VLSAPIC_INSVC(vcpu, i) = 0;
+}
+
+void kvm_init_all_rr(struct kvm_vcpu *vcpu)
+{
+	unsigned long psr;
+
+	local_irq_save(psr);
+
+	/* WARNING: not allow co-exist of both virtual mode and physical
+	 * mode in same region
+	 */
+
+	vcpu->arch.metaphysical_saved_rr0 = vrrtomrr(VMX(vcpu, vrr[VRN0]));
+	vcpu->arch.metaphysical_saved_rr4 = vrrtomrr(VMX(vcpu, vrr[VRN4]));
+
+	if (is_physical_mode(vcpu)) {
+		if (vcpu->arch.mode_flags & GUEST_PHY_EMUL)
+			panic_vm(vcpu);
+
+		ia64_set_rr((VRN0 << VRN_SHIFT), vcpu->arch.metaphysical_rr0);
+		ia64_dv_serialize_data();
+		ia64_set_rr((VRN4 << VRN_SHIFT), vcpu->arch.metaphysical_rr4);
+		ia64_dv_serialize_data();
+	} else {
+		ia64_set_rr((VRN0 << VRN_SHIFT),
+				vcpu->arch.metaphysical_saved_rr0);
+		ia64_dv_serialize_data();
+		ia64_set_rr((VRN4 << VRN_SHIFT),
+				vcpu->arch.metaphysical_saved_rr4);
+		ia64_dv_serialize_data();
+	}
+	ia64_set_rr((VRN1 << VRN_SHIFT),
+			vrrtomrr(VMX(vcpu, vrr[VRN1])));
+	ia64_dv_serialize_data();
+	ia64_set_rr((VRN2 << VRN_SHIFT),
+			vrrtomrr(VMX(vcpu, vrr[VRN2])));
+	ia64_dv_serialize_data();
+	ia64_set_rr((VRN3 << VRN_SHIFT),
+			vrrtomrr(VMX(vcpu, vrr[VRN3])));
+	ia64_dv_serialize_data();
+	ia64_set_rr((VRN5 << VRN_SHIFT),
+			vrrtomrr(VMX(vcpu, vrr[VRN5])));
+	ia64_dv_serialize_data();
+	ia64_set_rr((VRN7 << VRN_SHIFT),
+			vrrtomrr(VMX(vcpu, vrr[VRN7])));
+	ia64_dv_serialize_data();
+	ia64_srlz_d();
+	ia64_set_psr(psr);
+}
+
+int vmm_entry(void)
+{
+	struct kvm_vcpu *v;
+	v = current_vcpu;
+
+	ia64_call_vsa(PAL_VPS_RESTORE, (unsigned long)v->arch.vpd,
+						0, 0, 0, 0, 0, 0);
+	kvm_init_vtlb(v);
+	kvm_init_vhpt(v);
+	init_vcpu(v);
+	kvm_init_all_rr(v);
+	vmm_reset_entry();
+
+	return 0;
+}
+
+void panic_vm(struct kvm_vcpu *v)
+{
+	struct exit_ctl_data *p = &v->arch.exit_data;
+
+	p->exit_reason = EXIT_REASON_VM_PANIC;
+	vmm_transition(v);
+	/*Never to return*/
+	while (1);
+}
diff --git a/trunk/arch/ia64/kvm/vcpu.h b/trunk/arch/ia64/kvm/vcpu.h
new file mode 100644
index 000000000000..b0fcfb62c49e
--- /dev/null
+++ b/trunk/arch/ia64/kvm/vcpu.h
@@ -0,0 +1,740 @@
+/*
+ *  vcpu.h: vcpu routines
+ *  	Copyright (c) 2005, Intel Corporation.
+ *  	Xuefei Xu (Anthony Xu) (Anthony.xu@intel.com)
+ *  	Yaozu Dong (Eddie Dong) (Eddie.dong@intel.com)
+ *
+ * 	Copyright (c) 2007, Intel Corporation.
+ *  	Xuefei Xu (Anthony Xu) (Anthony.xu@intel.com)
+ *	Xiantao Zhang (xiantao.zhang@intel.com)
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+
+
+#ifndef __KVM_VCPU_H__
+#define __KVM_VCPU_H__
+
+#include <asm/types.h>
+#include <asm/fpu.h>
+#include <asm/processor.h>
+
+#ifndef __ASSEMBLY__
+#include "vti.h"
+
+#include <linux/kvm_host.h>
+#include <linux/spinlock.h>
+
+typedef unsigned long IA64_INST;
+
+typedef union U_IA64_BUNDLE {
+	unsigned long i64[2];
+	struct { unsigned long template:5, slot0:41, slot1a:18,
+		slot1b:23, slot2:41; };
+	/* NOTE: following doesn't work because bitfields can't cross natural
+	   size boundaries
+	   struct { unsigned long template:5, slot0:41, slot1:41, slot2:41; }; */
+} IA64_BUNDLE;
+
+typedef union U_INST64_A5 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, r1:7, imm7b:7, r3:2, imm5c:5,
+		imm9d:9, s:1, major:4; };
+} INST64_A5;
+
+typedef union U_INST64_B4 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, btype:3, un3:3, p:1, b2:3, un11:11, x6:6,
+		wh:2, d:1, un1:1, major:4; };
+} INST64_B4;
+
+typedef union U_INST64_B8 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, un21:21, x6:6, un4:4, major:4; };
+} INST64_B8;
+
+typedef union U_INST64_B9 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, imm20:20, :1, x6:6, :3, i:1, major:4; };
+} INST64_B9;
+
+typedef union U_INST64_I19 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, imm20:20, :1, x6:6, x3:3, i:1, major:4; };
+} INST64_I19;
+
+typedef union U_INST64_I26 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, :7, r2:7, ar3:7, x6:6, x3:3, :1, major:4; };
+} INST64_I26;
+
+typedef union U_INST64_I27 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, :7, imm:7, ar3:7, x6:6, x3:3, s:1, major:4; };
+} INST64_I27;
+
+typedef union U_INST64_I28 { /* not privileged (mov from AR) */
+	IA64_INST inst;
+	struct { unsigned long qp:6, r1:7, :7, ar3:7, x6:6, x3:3, :1, major:4; };
+} INST64_I28;
+
+typedef union U_INST64_M28 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, :14, r3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M28;
+
+typedef union U_INST64_M29 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, :7, r2:7, ar3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M29;
+
+typedef union U_INST64_M30 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, :7, imm:7, ar3:7, x4:4, x2:2,
+		x3:3, s:1, major:4; };
+} INST64_M30;
+
+typedef union U_INST64_M31 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, r1:7, :7, ar3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M31;
+
+typedef union U_INST64_M32 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, :7, r2:7, cr3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M32;
+
+typedef union U_INST64_M33 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, r1:7, :7, cr3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M33;
+
+typedef union U_INST64_M35 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, :7, r2:7, :7, x6:6, x3:3, :1, major:4; };
+
+} INST64_M35;
+
+typedef union U_INST64_M36 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, r1:7, :14, x6:6, x3:3, :1, major:4; };
+} INST64_M36;
+
+typedef union U_INST64_M37 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, imm20a:20, :1, x4:4, x2:2, x3:3,
+		i:1, major:4; };
+} INST64_M37;
+
+typedef union U_INST64_M41 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, :7, r2:7, :7, x6:6, x3:3, :1, major:4; };
+} INST64_M41;
+
+typedef union U_INST64_M42 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, :7, r2:7, r3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M42;
+
+typedef union U_INST64_M43 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, r1:7, :7, r3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M43;
+
+typedef union U_INST64_M44 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, imm:21, x4:4, i2:2, x3:3, i:1, major:4; };
+} INST64_M44;
+
+typedef union U_INST64_M45 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, :7, r2:7, r3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M45;
+
+typedef union U_INST64_M46 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, r1:7, un7:7, r3:7, x6:6,
+		x3:3, un1:1, major:4; };
+} INST64_M46;
+
+typedef union U_INST64_M47 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, un14:14, r3:7, x6:6, x3:3, un1:1, major:4; };
+} INST64_M47;
+
+typedef union U_INST64_M1{
+	IA64_INST inst;
+	struct { unsigned long qp:6, r1:7, un7:7, r3:7, x:1, hint:2,
+		x6:6, m:1, major:4; };
+} INST64_M1;
+
+typedef union U_INST64_M2{
+	IA64_INST inst;
+	struct { unsigned long qp:6, r1:7, r2:7, r3:7, x:1, hint:2,
+		x6:6, m:1, major:4; };
+} INST64_M2;
+
+typedef union U_INST64_M3{
+	IA64_INST inst;
+	struct { unsigned long qp:6, r1:7, imm7:7, r3:7, i:1, hint:2,
+		x6:6, s:1, major:4; };
+} INST64_M3;
+
+typedef union U_INST64_M4 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, un7:7, r2:7, r3:7, x:1, hint:2,
+		x6:6, m:1, major:4; };
+} INST64_M4;
+
+typedef union U_INST64_M5 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, imm7:7, r2:7, r3:7, i:1, hint:2,
+		x6:6, s:1, major:4; };
+} INST64_M5;
+
+typedef union U_INST64_M6 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, f1:7, un7:7, r3:7, x:1, hint:2,
+		x6:6, m:1, major:4; };
+} INST64_M6;
+
+typedef union U_INST64_M9 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, :7, f2:7, r3:7, x:1, hint:2,
+		x6:6, m:1, major:4; };
+} INST64_M9;
+
+typedef union U_INST64_M10 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, imm7:7, f2:7, r3:7, i:1, hint:2,
+		x6:6, s:1, major:4; };
+} INST64_M10;
+
+typedef union U_INST64_M12 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, f1:7, f2:7, r3:7, x:1, hint:2,
+		x6:6, m:1, major:4; };
+} INST64_M12;
+
+typedef union U_INST64_M15 {
+	IA64_INST inst;
+	struct { unsigned long qp:6, :7, imm7:7, r3:7, i:1, hint:2,
+		x6:6, s:1, major:4; };
+} INST64_M15;
+
+typedef union U_INST64 {
+	IA64_INST inst;
+	struct { unsigned long :37, major:4; } generic;
+	INST64_A5 A5;	/* used in build_hypercall_bundle only */
+	INST64_B4 B4;	/* used in build_hypercall_bundle only */
+	INST64_B8 B8;	/* rfi, bsw.[01] */
+	INST64_B9 B9;	/* break.b */
+	INST64_I19 I19;	/* used in build_hypercall_bundle only */
+	INST64_I26 I26;	/* mov register to ar (I unit) */
+	INST64_I27 I27;	/* mov immediate to ar (I unit) */
+	INST64_I28 I28;	/* mov from ar (I unit) */
+	INST64_M1  M1;	/* ld integer */
+	INST64_M2  M2;
+	INST64_M3  M3;
+	INST64_M4  M4;	/* st integer */
+	INST64_M5  M5;
+	INST64_M6  M6;	/* ldfd floating pointer 		*/
+	INST64_M9  M9;	/* stfd floating pointer		*/
+	INST64_M10 M10;	/* stfd floating pointer		*/
+	INST64_M12 M12;     /* ldfd pair floating pointer		*/
+	INST64_M15 M15;	/* lfetch + imm update			*/
+	INST64_M28 M28;	/* purge translation cache entry	*/
+	INST64_M29 M29;	/* mov register to ar (M unit)		*/
+	INST64_M30 M30;	/* mov immediate to ar (M unit)		*/
+	INST64_M31 M31;	/* mov from ar (M unit)			*/
+	INST64_M32 M32;	/* mov reg to cr			*/
+	INST64_M33 M33;	/* mov from cr				*/
+	INST64_M35 M35;	/* mov to psr				*/
+	INST64_M36 M36;	/* mov from psr				*/
+	INST64_M37 M37;	/* break.m				*/
+	INST64_M41 M41;	/* translation cache insert		*/
+	INST64_M42 M42;	/* mov to indirect reg/translation reg insert*/
+	INST64_M43 M43;	/* mov from indirect reg		*/
+	INST64_M44 M44;	/* set/reset system mask		*/
+	INST64_M45 M45;	/* translation purge			*/
+	INST64_M46 M46;	/* translation access (tpa,tak)		*/
+	INST64_M47 M47;	/* purge translation entry		*/
+} INST64;
+
+#define MASK_41 ((unsigned long)0x1ffffffffff)
+
+/* Virtual address memory attributes encoding */
+#define VA_MATTR_WB         0x0
+#define VA_MATTR_UC         0x4
+#define VA_MATTR_UCE        0x5
+#define VA_MATTR_WC         0x6
+#define VA_MATTR_NATPAGE    0x7
+
+#define PMASK(size)         (~((size) - 1))
+#define PSIZE(size)         (1UL<<(size))
+#define CLEARLSB(ppn, nbits)    (((ppn) >> (nbits)) << (nbits))
+#define PAGEALIGN(va, ps)	CLEARLSB(va, ps)
+#define PAGE_FLAGS_RV_MASK   (0x2|(0x3UL<<50)|(((1UL<<11)-1)<<53))
+#define _PAGE_MA_ST     (0x1 <<  2) /* is reserved for software use */
+
+#define ARCH_PAGE_SHIFT   12
+
+#define INVALID_TI_TAG (1UL << 63)
+
+#define VTLB_PTE_P_BIT      0
+#define VTLB_PTE_IO_BIT     60
+#define VTLB_PTE_IO         (1UL<<VTLB_PTE_IO_BIT)
+#define VTLB_PTE_P          (1UL<<VTLB_PTE_P_BIT)
+
+#define vcpu_quick_region_check(_tr_regions,_ifa)		\
+	(_tr_regions & (1 << ((unsigned long)_ifa >> 61)))
+
+#define vcpu_quick_region_set(_tr_regions,_ifa)             \
+	do {_tr_regions |= (1 << ((unsigned long)_ifa >> 61)); } while (0)
+
+static inline void vcpu_set_tr(struct thash_data *trp, u64 pte, u64 itir,
+		u64 va, u64 rid)
+{
+	trp->page_flags = pte;
+	trp->itir = itir;
+	trp->vadr = va;
+	trp->rid = rid;
+}
+
+extern u64 kvm_lookup_mpa(u64 gpfn);
+extern u64 kvm_gpa_to_mpa(u64 gpa);
+
+/* Return I/O type if trye */
+#define __gpfn_is_io(gpfn)			\
+	({						\
+	 u64 pte, ret = 0;			\
+	 pte = kvm_lookup_mpa(gpfn);		\
+	 if (!(pte & GPFN_INV_MASK))		\
+	 ret = pte & GPFN_IO_MASK;	\
+	 ret;					\
+	 })
+
+#endif
+
+#define IA64_NO_FAULT	0
+#define IA64_FAULT	1
+
+#define VMM_RBS_OFFSET  ((VMM_TASK_SIZE + 15) & ~15)
+
+#define SW_BAD  0   /* Bad mode transitition */
+#define SW_V2P  1   /* Physical emulatino is activated */
+#define SW_P2V  2   /* Exit physical mode emulation */
+#define SW_SELF 3   /* No mode transition */
+#define SW_NOP  4   /* Mode transition, but without action required */
+
+#define GUEST_IN_PHY    0x1
+#define GUEST_PHY_EMUL  0x2
+
+#define current_vcpu ((struct kvm_vcpu *) ia64_getreg(_IA64_REG_TP))
+
+#define VRN_SHIFT	61
+#define VRN_MASK	0xe000000000000000
+#define VRN0		0x0UL
+#define VRN1		0x1UL
+#define VRN2		0x2UL
+#define VRN3		0x3UL
+#define VRN4		0x4UL
+#define VRN5		0x5UL
+#define VRN6		0x6UL
+#define VRN7		0x7UL
+
+#define IRQ_NO_MASKED         0
+#define IRQ_MASKED_BY_VTPR    1
+#define IRQ_MASKED_BY_INSVC   2   /* masked by inservice IRQ */
+
+#define PTA_BASE_SHIFT      15
+
+#define IA64_PSR_VM_BIT     46
+#define IA64_PSR_VM (__IA64_UL(1) << IA64_PSR_VM_BIT)
+
+/* Interruption Function State */
+#define IA64_IFS_V_BIT      63
+#define IA64_IFS_V  (__IA64_UL(1) << IA64_IFS_V_BIT)
+
+#define PHY_PAGE_UC (_PAGE_A|_PAGE_D|_PAGE_P|_PAGE_MA_UC|_PAGE_AR_RWX)
+#define PHY_PAGE_WB (_PAGE_A|_PAGE_D|_PAGE_P|_PAGE_MA_WB|_PAGE_AR_RWX)
+
+#ifndef __ASSEMBLY__
+
+#include <asm/gcc_intrin.h>
+
+#define is_physical_mode(v)		\
+	((v->arch.mode_flags) & GUEST_IN_PHY)
+
+#define is_virtual_mode(v)	\
+	(!is_physical_mode(v))
+
+#define MODE_IND(psr)	\
+	(((psr).it << 2) + ((psr).dt << 1) + (psr).rt)
+
+#define _vmm_raw_spin_lock(x)						\
+	do {								\
+		__u32 *ia64_spinlock_ptr = (__u32 *) (x);		\
+		__u64 ia64_spinlock_val;				\
+		ia64_spinlock_val = ia64_cmpxchg4_acq(ia64_spinlock_ptr, 1, 0);\
+		if (unlikely(ia64_spinlock_val)) {			\
+			do {						\
+				while (*ia64_spinlock_ptr)		\
+				ia64_barrier();				\
+				ia64_spinlock_val =			\
+				ia64_cmpxchg4_acq(ia64_spinlock_ptr, 1, 0);\
+			} while (ia64_spinlock_val);			\
+		}							\
+	} while (0)
+
+#define _vmm_raw_spin_unlock(x)				\
+	do { barrier();				\
+		((spinlock_t *)x)->raw_lock.lock = 0; } \
+while (0)
+
+void vmm_spin_lock(spinlock_t *lock);
+void vmm_spin_unlock(spinlock_t *lock);
+enum {
+	I_TLB = 1,
+	D_TLB = 2
+};
+
+union kvm_va {
+	struct {
+		unsigned long off : 60;		/* intra-region offset */
+		unsigned long reg :  4;		/* region number */
+	} f;
+	unsigned long l;
+	void *p;
+};
+
+#define __kvm_pa(x)     ({union kvm_va _v; _v.l = (long) (x);		\
+						_v.f.reg = 0; _v.l; })
+#define __kvm_va(x)     ({union kvm_va _v; _v.l = (long) (x);		\
+				_v.f.reg = -1; _v.p; })
+
+#define _REGION_ID(x)           ({union ia64_rr _v; _v.val = (long)(x); \
+						_v.rid; })
+#define _REGION_PAGE_SIZE(x)    ({union ia64_rr _v; _v.val = (long)(x); \
+						_v.ps; })
+#define _REGION_HW_WALKER(x)    ({union ia64_rr _v; _v.val = (long)(x);	\
+						_v.ve; })
+
+enum vhpt_ref{ DATA_REF, NA_REF, INST_REF, RSE_REF };
+enum tlb_miss_type { INSTRUCTION, DATA, REGISTER };
+
+#define VCPU(_v, _x) ((_v)->arch.vpd->_x)
+#define VMX(_v, _x)  ((_v)->arch._x)
+
+#define VLSAPIC_INSVC(vcpu, i) ((vcpu)->arch.insvc[i])
+#define VLSAPIC_XTP(_v)        VMX(_v, xtp)
+
+static inline unsigned long itir_ps(unsigned long itir)
+{
+	return ((itir >> 2) & 0x3f);
+}
+
+
+/**************************************************************************
+  VCPU control register access routines
+ **************************************************************************/
+
+static inline u64 vcpu_get_itir(struct kvm_vcpu *vcpu)
+{
+	return ((u64)VCPU(vcpu, itir));
+}
+
+static inline void vcpu_set_itir(struct kvm_vcpu *vcpu, u64 val)
+{
+	VCPU(vcpu, itir) = val;
+}
+
+static inline u64 vcpu_get_ifa(struct kvm_vcpu *vcpu)
+{
+	return ((u64)VCPU(vcpu, ifa));
+}
+
+static inline void vcpu_set_ifa(struct kvm_vcpu *vcpu, u64 val)
+{
+	VCPU(vcpu, ifa) = val;
+}
+
+static inline u64 vcpu_get_iva(struct kvm_vcpu *vcpu)
+{
+	return ((u64)VCPU(vcpu, iva));
+}
+
+static inline u64 vcpu_get_pta(struct kvm_vcpu *vcpu)
+{
+	return ((u64)VCPU(vcpu, pta));
+}
+
+static inline u64 vcpu_get_lid(struct kvm_vcpu *vcpu)
+{
+	return ((u64)VCPU(vcpu, lid));
+}
+
+static inline u64 vcpu_get_tpr(struct kvm_vcpu *vcpu)
+{
+	return ((u64)VCPU(vcpu, tpr));
+}
+
+static inline u64 vcpu_get_eoi(struct kvm_vcpu *vcpu)
+{
+	return (0UL);		/*reads of eoi always return 0 */
+}
+
+static inline u64 vcpu_get_irr0(struct kvm_vcpu *vcpu)
+{
+	return ((u64)VCPU(vcpu, irr[0]));
+}
+
+static inline u64 vcpu_get_irr1(struct kvm_vcpu *vcpu)
+{
+	return ((u64)VCPU(vcpu, irr[1]));
+}
+
+static inline u64 vcpu_get_irr2(struct kvm_vcpu *vcpu)
+{
+	return ((u64)VCPU(vcpu, irr[2]));
+}
+
+static inline u64 vcpu_get_irr3(struct kvm_vcpu *vcpu)
+{
+	return ((u64)VCPU(vcpu, irr[3]));
+}
+
+static inline void vcpu_set_dcr(struct kvm_vcpu *vcpu, u64 val)
+{
+	ia64_setreg(_IA64_REG_CR_DCR, val);
+}
+
+static inline void vcpu_set_isr(struct kvm_vcpu *vcpu, u64 val)
+{
+	VCPU(vcpu, isr) = val;
+}
+
+static inline void vcpu_set_lid(struct kvm_vcpu *vcpu, u64 val)
+{
+	VCPU(vcpu, lid) = val;
+}
+
+static inline void vcpu_set_ipsr(struct kvm_vcpu *vcpu, u64 val)
+{
+	VCPU(vcpu, ipsr) = val;
+}
+
+static inline void vcpu_set_iip(struct kvm_vcpu *vcpu, u64 val)
+{
+	VCPU(vcpu, iip) = val;
+}
+
+static inline void vcpu_set_ifs(struct kvm_vcpu *vcpu, u64 val)
+{
+	VCPU(vcpu, ifs) = val;
+}
+
+static inline void vcpu_set_iipa(struct kvm_vcpu *vcpu, u64 val)
+{
+	VCPU(vcpu, iipa) = val;
+}
+
+static inline void vcpu_set_iha(struct kvm_vcpu *vcpu, u64 val)
+{
+	VCPU(vcpu, iha) = val;
+}
+
+
+static inline u64 vcpu_get_rr(struct kvm_vcpu *vcpu, u64 reg)
+{
+	return vcpu->arch.vrr[reg>>61];
+}
+
+/**************************************************************************
+  VCPU debug breakpoint register access routines
+ **************************************************************************/
+
+static inline void vcpu_set_dbr(struct kvm_vcpu *vcpu, u64 reg, u64 val)
+{
+	__ia64_set_dbr(reg, val);
+}
+
+static inline void vcpu_set_ibr(struct kvm_vcpu *vcpu, u64 reg, u64 val)
+{
+	ia64_set_ibr(reg, val);
+}
+
+static inline u64 vcpu_get_dbr(struct kvm_vcpu *vcpu, u64 reg)
+{
+	return ((u64)__ia64_get_dbr(reg));
+}
+
+static inline u64 vcpu_get_ibr(struct kvm_vcpu *vcpu, u64 reg)
+{
+	return ((u64)ia64_get_ibr(reg));
+}
+
+/**************************************************************************
+  VCPU performance monitor register access routines
+ **************************************************************************/
+static inline void vcpu_set_pmc(struct kvm_vcpu *vcpu, u64 reg, u64 val)
+{
+	/* NOTE: Writes to unimplemented PMC registers are discarded */
+	ia64_set_pmc(reg, val);
+}
+
+static inline void vcpu_set_pmd(struct kvm_vcpu *vcpu, u64 reg, u64 val)
+{
+	/* NOTE: Writes to unimplemented PMD registers are discarded */
+	ia64_set_pmd(reg, val);
+}
+
+static inline u64 vcpu_get_pmc(struct kvm_vcpu *vcpu, u64 reg)
+{
+	/* NOTE: Reads from unimplemented PMC registers return zero */
+	return ((u64)ia64_get_pmc(reg));
+}
+
+static inline u64 vcpu_get_pmd(struct kvm_vcpu *vcpu, u64 reg)
+{
+	/* NOTE: Reads from unimplemented PMD registers return zero */
+	return ((u64)ia64_get_pmd(reg));
+}
+
+static inline unsigned long vrrtomrr(unsigned long val)
+{
+	union ia64_rr rr;
+	rr.val = val;
+	rr.rid = (rr.rid << 4) | 0xe;
+	if (rr.ps > PAGE_SHIFT)
+		rr.ps = PAGE_SHIFT;
+	rr.ve = 1;
+	return rr.val;
+}
+
+
+static inline int highest_bits(int *dat)
+{
+	u32  bits, bitnum;
+	int i;
+
+	/* loop for all 256 bits */
+	for (i = 7; i >= 0 ; i--) {
+		bits = dat[i];
+		if (bits) {
+			bitnum = fls(bits);
+			return i * 32 + bitnum - 1;
+		}
+	}
+	return NULL_VECTOR;
+}
+
+/*
+ * The pending irq is higher than the inservice one.
+ *
+ */
+static inline int is_higher_irq(int pending, int inservice)
+{
+	return ((pending > inservice)
+			|| ((pending != NULL_VECTOR)
+				&& (inservice == NULL_VECTOR)));
+}
+
+static inline int is_higher_class(int pending, int mic)
+{
+	return ((pending >> 4) > mic);
+}
+
+/*
+ * Return 0-255 for pending irq.
+ *        NULL_VECTOR: when no pending.
+ */
+static inline int highest_pending_irq(struct kvm_vcpu *vcpu)
+{
+	if (VCPU(vcpu, irr[0]) & (1UL<<NMI_VECTOR))
+		return NMI_VECTOR;
+	if (VCPU(vcpu, irr[0]) & (1UL<<ExtINT_VECTOR))
+		return ExtINT_VECTOR;
+
+	return highest_bits((int *)&VCPU(vcpu, irr[0]));
+}
+
+static inline int highest_inservice_irq(struct kvm_vcpu *vcpu)
+{
+	if (VMX(vcpu, insvc[0]) & (1UL<<NMI_VECTOR))
+		return NMI_VECTOR;
+	if (VMX(vcpu, insvc[0]) & (1UL<<ExtINT_VECTOR))
+		return ExtINT_VECTOR;
+
+	return highest_bits((int *)&(VMX(vcpu, insvc[0])));
+}
+
+extern void vcpu_get_fpreg(struct kvm_vcpu *vcpu, u64 reg,
+					struct ia64_fpreg *val);
+extern void vcpu_set_fpreg(struct kvm_vcpu *vcpu, u64 reg,
+					struct ia64_fpreg *val);
+extern u64 vcpu_get_gr(struct kvm_vcpu *vcpu, u64 reg);
+extern void vcpu_set_gr(struct kvm_vcpu *vcpu, u64 reg, u64 val, int nat);
+extern u64 vcpu_get_psr(struct kvm_vcpu *vcpu);
+extern void vcpu_set_psr(struct kvm_vcpu *vcpu, u64 val);
+extern u64 vcpu_thash(struct kvm_vcpu *vcpu, u64 vadr);
+extern void vcpu_bsw0(struct kvm_vcpu *vcpu);
+extern void thash_vhpt_insert(struct kvm_vcpu *v, u64 pte,
+					u64 itir, u64 va, int type);
+extern struct thash_data *vhpt_lookup(u64 va);
+extern u64 guest_vhpt_lookup(u64 iha, u64 *pte);
+extern void thash_purge_entries(struct kvm_vcpu *v, u64 va, u64 ps);
+extern void thash_purge_entries_remote(struct kvm_vcpu *v, u64 va, u64 ps);
+extern u64 translate_phy_pte(u64 *pte, u64 itir, u64 va);
+extern int thash_purge_and_insert(struct kvm_vcpu *v, u64 pte,
+		u64 itir, u64 ifa, int type);
+extern void thash_purge_all(struct kvm_vcpu *v);
+extern struct thash_data *vtlb_lookup(struct kvm_vcpu *v,
+						u64 va, int is_data);
+extern int vtr_find_overlap(struct kvm_vcpu *vcpu, u64 va,
+						u64 ps, int is_data);
+
+extern void vcpu_increment_iip(struct kvm_vcpu *v);
+extern void vcpu_decrement_iip(struct kvm_vcpu *vcpu);
+extern void vcpu_pend_interrupt(struct kvm_vcpu *vcpu, u8 vec);
+extern void vcpu_unpend_interrupt(struct kvm_vcpu *vcpu, u8 vec);
+extern void data_page_not_present(struct kvm_vcpu *vcpu, u64 vadr);
+extern void dnat_page_consumption(struct kvm_vcpu *vcpu, u64 vadr);
+extern void alt_dtlb(struct kvm_vcpu *vcpu, u64 vadr);
+extern void nested_dtlb(struct kvm_vcpu *vcpu);
+extern void dvhpt_fault(struct kvm_vcpu *vcpu, u64 vadr);
+extern int vhpt_enabled(struct kvm_vcpu *vcpu, u64 vadr, enum vhpt_ref ref);
+
+extern void update_vhpi(struct kvm_vcpu *vcpu, int vec);
+extern int irq_masked(struct kvm_vcpu *vcpu, int h_pending, int h_inservice);
+
+extern int fetch_code(struct kvm_vcpu *vcpu, u64 gip, IA64_BUNDLE *pbundle);
+extern void emulate_io_inst(struct kvm_vcpu *vcpu, u64 padr, u64 ma);
+extern void vmm_transition(struct kvm_vcpu *vcpu);
+extern void vmm_trampoline(union context *from, union context *to);
+extern int vmm_entry(void);
+extern  u64 vcpu_get_itc(struct kvm_vcpu *vcpu);
+
+extern void vmm_reset_entry(void);
+void kvm_init_vtlb(struct kvm_vcpu *v);
+void kvm_init_vhpt(struct kvm_vcpu *v);
+void thash_init(struct thash_cb *hcb, u64 sz);
+
+void panic_vm(struct kvm_vcpu *v);
+
+extern u64 ia64_call_vsa(u64 proc, u64 arg1, u64 arg2, u64 arg3,
+		u64 arg4, u64 arg5, u64 arg6, u64 arg7);
+#endif
+#endif	/* __VCPU_H__ */
diff --git a/trunk/arch/ia64/kvm/vmm.c b/trunk/arch/ia64/kvm/vmm.c
new file mode 100644
index 000000000000..2275bf4e681a
--- /dev/null
+++ b/trunk/arch/ia64/kvm/vmm.c
@@ -0,0 +1,66 @@
+/*
+ * vmm.c: vmm module interface with kvm module
+ *
+ * Copyright (c) 2007, Intel Corporation.
+ *
+ *  Xiantao Zhang (xiantao.zhang@intel.com)
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ */
+
+
+#include<linux/module.h>
+#include<asm/fpswa.h>
+
+#include "vcpu.h"
+
+MODULE_AUTHOR("Intel");
+MODULE_LICENSE("GPL");
+
+extern char kvm_ia64_ivt;
+extern fpswa_interface_t *vmm_fpswa_interface;
+
+struct kvm_vmm_info vmm_info = {
+	.module	     = THIS_MODULE,
+	.vmm_entry   = vmm_entry,
+	.tramp_entry = vmm_trampoline,
+	.vmm_ivt     = (unsigned long)&kvm_ia64_ivt,
+};
+
+static int __init  kvm_vmm_init(void)
+{
+
+	vmm_fpswa_interface = fpswa_interface;
+
+	/*Register vmm data to kvm side*/
+	return kvm_init(&vmm_info, 1024, THIS_MODULE);
+}
+
+static void __exit kvm_vmm_exit(void)
+{
+	kvm_exit();
+	return ;
+}
+
+void vmm_spin_lock(spinlock_t *lock)
+{
+	_vmm_raw_spin_lock(lock);
+}
+
+void vmm_spin_unlock(spinlock_t *lock)
+{
+	_vmm_raw_spin_unlock(lock);
+}
+module_init(kvm_vmm_init)
+module_exit(kvm_vmm_exit)
diff --git a/trunk/arch/ia64/kvm/vmm_ivt.S b/trunk/arch/ia64/kvm/vmm_ivt.S
new file mode 100644
index 000000000000..3ee5f481c06d
--- /dev/null
+++ b/trunk/arch/ia64/kvm/vmm_ivt.S
@@ -0,0 +1,1424 @@
+/*
+ * /ia64/kvm_ivt.S
+ *
+ * Copyright (C) 1998-2001, 2003 Hewlett-Packard Co
+ *      Stephane Eranian <eranian@hpl.hp.com>
+ *      David Mosberger <davidm@hpl.hp.com>
+ * Copyright (C) 2000, 2002-2003 Intel Co
+ *      Asit Mallick <asit.k.mallick@intel.com>
+ *      Suresh Siddha <suresh.b.siddha@intel.com>
+ *      Kenneth Chen <kenneth.w.chen@intel.com>
+ *      Fenghua Yu <fenghua.yu@intel.com>
+ *
+ *
+ * 00/08/23 Asit Mallick <asit.k.mallick@intel.com> TLB handling
+ * for SMP
+ * 00/12/20 David Mosberger-Tang <davidm@hpl.hp.com> DTLB/ITLB
+ * handler now uses virtual PT.
+ *
+ * 07/6/20 Xuefei Xu  (Anthony Xu) (anthony.xu@intel.com)
+ *              Supporting Intel virtualization architecture
+ *
+ */
+
+/*
+ * This file defines the interruption vector table used by the CPU.
+ * It does not include one entry per possible cause of interruption.
+ *
+ * The first 20 entries of the table contain 64 bundles each while the
+ * remaining 48 entries contain only 16 bundles each.
+ *
+ * The 64 bundles are used to allow inlining the whole handler for
+ * critical
+ * interruptions like TLB misses.
+ *
+ *  For each entry, the comment is as follows:
+ *
+ *              // 0x1c00 Entry 7 (size 64 bundles) Data Key Miss
+ *              (12,51)
+ *  entry offset ----/     /         /                  /
+ *  /
+ *  entry number ---------/         /                  /
+ *  /
+ *  size of the entry -------------/                  /
+ *  /
+ *  vector name -------------------------------------/
+ *  /
+ *  interruptions triggering this vector
+ *  ----------------------/
+ *
+ * The table is 32KB in size and must be aligned on 32KB
+ * boundary.
+ * (The CPU ignores the 15 lower bits of the address)
+ *
+ * Table is based upon EAS2.6 (Oct 1999)
+ */
+
+
+#include <asm/asmmacro.h>
+#include <asm/cache.h>
+#include <asm/pgtable.h>
+
+#include "asm-offsets.h"
+#include "vcpu.h"
+#include "kvm_minstate.h"
+#include "vti.h"
+
+#if 1
+# define PSR_DEFAULT_BITS   psr.ac
+#else
+# define PSR_DEFAULT_BITS   0
+#endif
+
+
+#define KVM_FAULT(n)    \
+    kvm_fault_##n:;          \
+    mov r19=n;;          \
+    br.sptk.many kvm_fault_##n;         \
+    ;;                  \
+
+
+#define KVM_REFLECT(n)    \
+    mov r31=pr;           \
+    mov r19=n;       /* prepare to save predicates */ \
+    mov r29=cr.ipsr;      \
+    ;;      \
+    tbit.z p6,p7=r29,IA64_PSR_VM_BIT;       \
+(p7)br.sptk.many kvm_dispatch_reflection;        \
+    br.sptk.many kvm_panic;      \
+
+
+GLOBAL_ENTRY(kvm_panic)
+    br.sptk.many kvm_panic
+    ;;
+END(kvm_panic)
+
+
+
+
+
+    .section .text.ivt,"ax"
+
+    .align 32768    // align on 32KB boundary
+    .global kvm_ia64_ivt
+kvm_ia64_ivt:
+///////////////////////////////////////////////////////////////
+// 0x0000 Entry 0 (size 64 bundles) VHPT Translation (8,20,47)
+ENTRY(kvm_vhpt_miss)
+    KVM_FAULT(0)
+END(kvm_vhpt_miss)
+
+
+    .org kvm_ia64_ivt+0x400
+////////////////////////////////////////////////////////////////
+// 0x0400 Entry 1 (size 64 bundles) ITLB (21)
+ENTRY(kvm_itlb_miss)
+    mov r31 = pr
+    mov r29=cr.ipsr;
+    ;;
+    tbit.z p6,p7=r29,IA64_PSR_VM_BIT;
+    (p6) br.sptk kvm_alt_itlb_miss
+    mov r19 = 1
+    br.sptk kvm_itlb_miss_dispatch
+    KVM_FAULT(1);
+END(kvm_itlb_miss)
+
+    .org kvm_ia64_ivt+0x0800
+//////////////////////////////////////////////////////////////////
+// 0x0800 Entry 2 (size 64 bundles) DTLB (9,48)
+ENTRY(kvm_dtlb_miss)
+    mov r31 = pr
+    mov r29=cr.ipsr;
+    ;;
+    tbit.z p6,p7=r29,IA64_PSR_VM_BIT;
+(p6)br.sptk kvm_alt_dtlb_miss
+    br.sptk kvm_dtlb_miss_dispatch
+END(kvm_dtlb_miss)
+
+     .org kvm_ia64_ivt+0x0c00
+////////////////////////////////////////////////////////////////////
+// 0x0c00 Entry 3 (size 64 bundles) Alt ITLB (19)
+ENTRY(kvm_alt_itlb_miss)
+    mov r16=cr.ifa    // get address that caused the TLB miss
+    ;;
+    movl r17=PAGE_KERNEL
+    mov r24=cr.ipsr
+    movl r19=(((1 << IA64_MAX_PHYS_BITS) - 1) & ~0xfff)
+    ;;
+    and r19=r19,r16     // clear ed, reserved bits, and PTE control bits
+    ;;
+    or r19=r17,r19      // insert PTE control bits into r19
+    ;;
+    movl r20=IA64_GRANULE_SHIFT<<2
+    ;;
+    mov cr.itir=r20
+    ;;
+    itc.i r19		// insert the TLB entry
+    mov pr=r31,-1
+    rfi
+END(kvm_alt_itlb_miss)
+
+    .org kvm_ia64_ivt+0x1000
+/////////////////////////////////////////////////////////////////////
+// 0x1000 Entry 4 (size 64 bundles) Alt DTLB (7,46)
+ENTRY(kvm_alt_dtlb_miss)
+    mov r16=cr.ifa		// get address that caused the TLB miss
+    ;;
+    movl r17=PAGE_KERNEL
+    movl r19=(((1 << IA64_MAX_PHYS_BITS) - 1) & ~0xfff)
+    mov r24=cr.ipsr
+    ;;
+    and r19=r19,r16     // clear ed, reserved bits, and PTE control bits
+    ;;
+    or r19=r19,r17	// insert PTE control bits into r19
+    ;;
+    movl r20=IA64_GRANULE_SHIFT<<2
+    ;;
+    mov cr.itir=r20
+    ;;
+    itc.d r19		// insert the TLB entry
+    mov pr=r31,-1
+    rfi
+END(kvm_alt_dtlb_miss)
+
+    .org kvm_ia64_ivt+0x1400
+//////////////////////////////////////////////////////////////////////
+// 0x1400 Entry 5 (size 64 bundles) Data nested TLB (6,45)
+ENTRY(kvm_nested_dtlb_miss)
+    KVM_FAULT(5)
+END(kvm_nested_dtlb_miss)
+
+    .org kvm_ia64_ivt+0x1800
+/////////////////////////////////////////////////////////////////////
+// 0x1800 Entry 6 (size 64 bundles) Instruction Key Miss (24)
+ENTRY(kvm_ikey_miss)
+    KVM_REFLECT(6)
+END(kvm_ikey_miss)
+
+    .org kvm_ia64_ivt+0x1c00
+/////////////////////////////////////////////////////////////////////
+// 0x1c00 Entry 7 (size 64 bundles) Data Key Miss (12,51)
+ENTRY(kvm_dkey_miss)
+    KVM_REFLECT(7)
+END(kvm_dkey_miss)
+
+    .org kvm_ia64_ivt+0x2000
+////////////////////////////////////////////////////////////////////
+// 0x2000 Entry 8 (size 64 bundles) Dirty-bit (54)
+ENTRY(kvm_dirty_bit)
+    KVM_REFLECT(8)
+END(kvm_dirty_bit)
+
+    .org kvm_ia64_ivt+0x2400
+////////////////////////////////////////////////////////////////////
+// 0x2400 Entry 9 (size 64 bundles) Instruction Access-bit (27)
+ENTRY(kvm_iaccess_bit)
+    KVM_REFLECT(9)
+END(kvm_iaccess_bit)
+
+    .org kvm_ia64_ivt+0x2800
+///////////////////////////////////////////////////////////////////
+// 0x2800 Entry 10 (size 64 bundles) Data Access-bit (15,55)
+ENTRY(kvm_daccess_bit)
+    KVM_REFLECT(10)
+END(kvm_daccess_bit)
+
+    .org kvm_ia64_ivt+0x2c00
+/////////////////////////////////////////////////////////////////
+// 0x2c00 Entry 11 (size 64 bundles) Break instruction (33)
+ENTRY(kvm_break_fault)
+    mov r31=pr
+    mov r19=11
+    mov r29=cr.ipsr
+    ;;
+    KVM_SAVE_MIN_WITH_COVER_R19
+    ;;
+    alloc r14=ar.pfs,0,0,4,0 // now it's safe (must be first in insn group!)
+    mov out0=cr.ifa
+    mov out2=cr.isr     // FIXME: pity to make this slow access twice
+    mov out3=cr.iim     // FIXME: pity to make this slow access twice
+    adds r3=8,r2                // set up second base pointer
+    ;;
+    ssm psr.ic
+    ;;
+    srlz.i                  // guarantee that interruption collection is on
+    ;;
+    //(p15)ssm psr.i               // restore psr.i
+    addl r14=@gprel(ia64_leave_hypervisor),gp
+    ;;
+    KVM_SAVE_REST
+    mov rp=r14
+    ;;
+    adds out1=16,sp
+    br.call.sptk.many b6=kvm_ia64_handle_break
+    ;;
+END(kvm_break_fault)
+
+    .org kvm_ia64_ivt+0x3000
+/////////////////////////////////////////////////////////////////
+// 0x3000 Entry 12 (size 64 bundles) External Interrupt (4)
+ENTRY(kvm_interrupt)
+    mov r31=pr		// prepare to save predicates
+    mov r19=12
+    mov r29=cr.ipsr
+    ;;
+    tbit.z p6,p7=r29,IA64_PSR_VM_BIT
+    tbit.z p0,p15=r29,IA64_PSR_I_BIT
+    ;;
+(p7) br.sptk kvm_dispatch_interrupt
+    ;;
+    mov r27=ar.rsc		/* M */
+    mov r20=r1			/* A */
+    mov r25=ar.unat		/* M */
+    mov r26=ar.pfs		/* I */
+    mov r28=cr.iip		/* M */
+    cover			/* B (or nothing) */
+    ;;
+    mov r1=sp
+    ;;
+    invala			/* M */
+    mov r30=cr.ifs
+    ;;
+    addl r1=-VMM_PT_REGS_SIZE,r1
+    ;;
+    adds r17=2*L1_CACHE_BYTES,r1	/* really: biggest cache-line size */
+    adds r16=PT(CR_IPSR),r1
+    ;;
+    lfetch.fault.excl.nt1 [r17],L1_CACHE_BYTES
+    st8 [r16]=r29			/* save cr.ipsr */
+    ;;
+    lfetch.fault.excl.nt1 [r17]
+    mov r29=b0
+    ;;
+    adds r16=PT(R8),r1  	/* initialize first base pointer */
+    adds r17=PT(R9),r1  	/* initialize second base pointer */
+    mov r18=r0      		/* make sure r18 isn't NaT */
+    ;;
+.mem.offset 0,0; st8.spill [r16]=r8,16
+.mem.offset 8,0; st8.spill [r17]=r9,16
+        ;;
+.mem.offset 0,0; st8.spill [r16]=r10,24
+.mem.offset 8,0; st8.spill [r17]=r11,24
+        ;;
+    st8 [r16]=r28,16		/* save cr.iip */
+    st8 [r17]=r30,16		/* save cr.ifs */
+    mov r8=ar.fpsr		/* M */
+    mov r9=ar.csd
+    mov r10=ar.ssd
+    movl r11=FPSR_DEFAULT	/* L-unit */
+    ;;
+    st8 [r16]=r25,16		/* save ar.unat */
+    st8 [r17]=r26,16		/* save ar.pfs */
+    shl r18=r18,16		/* compute ar.rsc to be used for "loadrs" */
+    ;;
+    st8 [r16]=r27,16		/* save ar.rsc */
+    adds r17=16,r17		/* skip over ar_rnat field */
+    ;;
+    st8 [r17]=r31,16		/* save predicates */
+    adds r16=16,r16		/* skip over ar_bspstore field */
+    ;;
+    st8 [r16]=r29,16		/* save b0 */
+    st8 [r17]=r18,16		/* save ar.rsc value for "loadrs" */
+    ;;
+.mem.offset 0,0; st8.spill [r16]=r20,16    /* save original r1 */
+.mem.offset 8,0; st8.spill [r17]=r12,16
+    adds r12=-16,r1
+    /* switch to kernel memory stack (with 16 bytes of scratch) */
+    ;;
+.mem.offset 0,0; st8.spill [r16]=r13,16
+.mem.offset 8,0; st8.spill [r17]=r8,16 /* save ar.fpsr */
+    ;;
+.mem.offset 0,0; st8.spill [r16]=r15,16
+.mem.offset 8,0; st8.spill [r17]=r14,16
+    dep r14=-1,r0,60,4
+    ;;
+.mem.offset 0,0; st8.spill [r16]=r2,16
+.mem.offset 8,0; st8.spill [r17]=r3,16
+    adds r2=VMM_PT_REGS_R16_OFFSET,r1
+    adds r14 = VMM_VCPU_GP_OFFSET,r13
+    ;;
+    mov r8=ar.ccv
+    ld8 r14 = [r14]
+    ;;
+    mov r1=r14       /* establish kernel global pointer */
+    ;;                                          \
+    bsw.1
+    ;;
+    alloc r14=ar.pfs,0,0,1,0	// must be first in an insn group
+    mov out0=r13
+    ;;
+    ssm psr.ic
+    ;;
+    srlz.i
+    ;;
+    //(p15) ssm psr.i
+    adds r3=8,r2		// set up second base pointer for SAVE_REST
+    srlz.i			// ensure everybody knows psr.ic is back on
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r16,16
+.mem.offset 8,0; st8.spill [r3]=r17,16
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r18,16
+.mem.offset 8,0; st8.spill [r3]=r19,16
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r20,16
+.mem.offset 8,0; st8.spill [r3]=r21,16
+    mov r18=b6
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r22,16
+.mem.offset 8,0; st8.spill [r3]=r23,16
+    mov r19=b7
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r24,16
+.mem.offset 8,0; st8.spill [r3]=r25,16
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r26,16
+.mem.offset 8,0; st8.spill [r3]=r27,16
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r28,16
+.mem.offset 8,0; st8.spill [r3]=r29,16
+    ;;
+.mem.offset 0,0; st8.spill [r2]=r30,16
+.mem.offset 8,0; st8.spill [r3]=r31,32
+    ;;
+    mov ar.fpsr=r11       /* M-unit */
+    st8 [r2]=r8,8         /* ar.ccv */
+    adds r24=PT(B6)-PT(F7),r3
+    ;;
+    stf.spill [r2]=f6,32
+    stf.spill [r3]=f7,32
+    ;;
+    stf.spill [r2]=f8,32
+    stf.spill [r3]=f9,32
+    ;;
+    stf.spill [r2]=f10
+    stf.spill [r3]=f11
+    adds r25=PT(B7)-PT(F11),r3
+    ;;
+    st8 [r24]=r18,16       /* b6 */
+    st8 [r25]=r19,16       /* b7 */
+    ;;
+    st8 [r24]=r9           /* ar.csd */
+    st8 [r25]=r10          /* ar.ssd */
+    ;;
+    srlz.d		// make sure we see the effect of cr.ivr
+    addl r14=@gprel(ia64_leave_nested),gp
+    ;;
+    mov rp=r14
+    br.call.sptk.many b6=kvm_ia64_handle_irq
+    ;;
+END(kvm_interrupt)
+
+    .global kvm_dispatch_vexirq
+    .org kvm_ia64_ivt+0x3400
+//////////////////////////////////////////////////////////////////////
+// 0x3400 Entry 13 (size 64 bundles) Reserved
+ENTRY(kvm_virtual_exirq)
+    mov r31=pr
+    mov r19=13
+    mov r30 =r0
+    ;;
+kvm_dispatch_vexirq:
+    cmp.eq p6,p0 = 1,r30
+    ;;
+(p6)add r29 = VMM_VCPU_SAVED_GP_OFFSET,r21
+    ;;
+(p6)ld8 r1 = [r29]
+    ;;
+    KVM_SAVE_MIN_WITH_COVER_R19
+    alloc r14=ar.pfs,0,0,1,0
+    mov out0=r13
+
+    ssm psr.ic
+    ;;
+    srlz.i                  // guarantee that interruption collection is on
+    ;;
+    //(p15) ssm psr.i               // restore psr.i
+    adds r3=8,r2                // set up second base pointer
+    ;;
+    KVM_SAVE_REST
+    addl r14=@gprel(ia64_leave_hypervisor),gp
+    ;;
+    mov rp=r14
+    br.call.sptk.many b6=kvm_vexirq
+END(kvm_virtual_exirq)
+
+    .org kvm_ia64_ivt+0x3800
+/////////////////////////////////////////////////////////////////////
+// 0x3800 Entry 14 (size 64 bundles) Reserved
+    KVM_FAULT(14)
+    // this code segment is from 2.6.16.13
+
+
+    .org kvm_ia64_ivt+0x3c00
+///////////////////////////////////////////////////////////////////////
+// 0x3c00 Entry 15 (size 64 bundles) Reserved
+    KVM_FAULT(15)
+
+
+    .org kvm_ia64_ivt+0x4000
+///////////////////////////////////////////////////////////////////////
+// 0x4000 Entry 16 (size 64 bundles) Reserved
+    KVM_FAULT(16)
+
+    .org kvm_ia64_ivt+0x4400
+//////////////////////////////////////////////////////////////////////
+// 0x4400 Entry 17 (size 64 bundles) Reserved
+    KVM_FAULT(17)
+
+    .org kvm_ia64_ivt+0x4800
+//////////////////////////////////////////////////////////////////////
+// 0x4800 Entry 18 (size 64 bundles) Reserved
+    KVM_FAULT(18)
+
+    .org kvm_ia64_ivt+0x4c00
+//////////////////////////////////////////////////////////////////////
+// 0x4c00 Entry 19 (size 64 bundles) Reserved
+    KVM_FAULT(19)
+
+    .org kvm_ia64_ivt+0x5000
+//////////////////////////////////////////////////////////////////////
+// 0x5000 Entry 20 (size 16 bundles) Page Not Present
+ENTRY(kvm_page_not_present)
+    KVM_REFLECT(20)
+END(kvm_page_not_present)
+
+    .org kvm_ia64_ivt+0x5100
+///////////////////////////////////////////////////////////////////////
+// 0x5100 Entry 21 (size 16 bundles) Key Permission vector
+ENTRY(kvm_key_permission)
+    KVM_REFLECT(21)
+END(kvm_key_permission)
+
+    .org kvm_ia64_ivt+0x5200
+//////////////////////////////////////////////////////////////////////
+// 0x5200 Entry 22 (size 16 bundles) Instruction Access Rights (26)
+ENTRY(kvm_iaccess_rights)
+    KVM_REFLECT(22)
+END(kvm_iaccess_rights)
+
+    .org kvm_ia64_ivt+0x5300
+//////////////////////////////////////////////////////////////////////
+// 0x5300 Entry 23 (size 16 bundles) Data Access Rights (14,53)
+ENTRY(kvm_daccess_rights)
+    KVM_REFLECT(23)
+END(kvm_daccess_rights)
+
+    .org kvm_ia64_ivt+0x5400
+/////////////////////////////////////////////////////////////////////
+// 0x5400 Entry 24 (size 16 bundles) General Exception (5,32,34,36,38,39)
+ENTRY(kvm_general_exception)
+   KVM_REFLECT(24)
+   KVM_FAULT(24)
+END(kvm_general_exception)
+
+    .org kvm_ia64_ivt+0x5500
+//////////////////////////////////////////////////////////////////////
+// 0x5500 Entry 25 (size 16 bundles) Disabled FP-Register (35)
+ENTRY(kvm_disabled_fp_reg)
+    KVM_REFLECT(25)
+END(kvm_disabled_fp_reg)
+
+    .org kvm_ia64_ivt+0x5600
+////////////////////////////////////////////////////////////////////
+// 0x5600 Entry 26 (size 16 bundles) Nat Consumption (11,23,37,50)
+ENTRY(kvm_nat_consumption)
+    KVM_REFLECT(26)
+END(kvm_nat_consumption)
+
+    .org kvm_ia64_ivt+0x5700
+/////////////////////////////////////////////////////////////////////
+// 0x5700 Entry 27 (size 16 bundles) Speculation (40)
+ENTRY(kvm_speculation_vector)
+    KVM_REFLECT(27)
+END(kvm_speculation_vector)
+
+    .org kvm_ia64_ivt+0x5800
+/////////////////////////////////////////////////////////////////////
+// 0x5800 Entry 28 (size 16 bundles) Reserved
+    KVM_FAULT(28)
+
+    .org kvm_ia64_ivt+0x5900
+///////////////////////////////////////////////////////////////////
+// 0x5900 Entry 29 (size 16 bundles) Debug (16,28,56)
+ENTRY(kvm_debug_vector)
+    KVM_FAULT(29)
+END(kvm_debug_vector)
+
+    .org kvm_ia64_ivt+0x5a00
+///////////////////////////////////////////////////////////////
+// 0x5a00 Entry 30 (size 16 bundles) Unaligned Reference (57)
+ENTRY(kvm_unaligned_access)
+    KVM_REFLECT(30)
+END(kvm_unaligned_access)
+
+    .org kvm_ia64_ivt+0x5b00
+//////////////////////////////////////////////////////////////////////
+// 0x5b00 Entry 31 (size 16 bundles) Unsupported Data Reference (57)
+ENTRY(kvm_unsupported_data_reference)
+    KVM_REFLECT(31)
+END(kvm_unsupported_data_reference)
+
+    .org kvm_ia64_ivt+0x5c00
+////////////////////////////////////////////////////////////////////
+// 0x5c00 Entry 32 (size 16 bundles) Floating Point FAULT (65)
+ENTRY(kvm_floating_point_fault)
+    KVM_REFLECT(32)
+END(kvm_floating_point_fault)
+
+    .org kvm_ia64_ivt+0x5d00
+/////////////////////////////////////////////////////////////////////
+// 0x5d00 Entry 33 (size 16 bundles) Floating Point Trap (66)
+ENTRY(kvm_floating_point_trap)
+    KVM_REFLECT(33)
+END(kvm_floating_point_trap)
+
+    .org kvm_ia64_ivt+0x5e00
+//////////////////////////////////////////////////////////////////////
+// 0x5e00 Entry 34 (size 16 bundles) Lower Privilege Transfer Trap (66)
+ENTRY(kvm_lower_privilege_trap)
+    KVM_REFLECT(34)
+END(kvm_lower_privilege_trap)
+
+    .org kvm_ia64_ivt+0x5f00
+//////////////////////////////////////////////////////////////////////
+// 0x5f00 Entry 35 (size 16 bundles) Taken Branch Trap (68)
+ENTRY(kvm_taken_branch_trap)
+    KVM_REFLECT(35)
+END(kvm_taken_branch_trap)
+
+    .org kvm_ia64_ivt+0x6000
+////////////////////////////////////////////////////////////////////
+// 0x6000 Entry 36 (size 16 bundles) Single Step Trap (69)
+ENTRY(kvm_single_step_trap)
+    KVM_REFLECT(36)
+END(kvm_single_step_trap)
+    .global kvm_virtualization_fault_back
+    .org kvm_ia64_ivt+0x6100
+/////////////////////////////////////////////////////////////////////
+// 0x6100 Entry 37 (size 16 bundles) Virtualization Fault
+ENTRY(kvm_virtualization_fault)
+    mov r31=pr
+    adds r16 = VMM_VCPU_SAVED_GP_OFFSET,r21
+    ;;
+    st8 [r16] = r1
+    adds r17 = VMM_VCPU_GP_OFFSET, r21
+    ;;
+    ld8 r1 = [r17]
+    cmp.eq p6,p0=EVENT_MOV_FROM_AR,r24
+    cmp.eq p7,p0=EVENT_MOV_FROM_RR,r24
+    cmp.eq p8,p0=EVENT_MOV_TO_RR,r24
+    cmp.eq p9,p0=EVENT_RSM,r24
+    cmp.eq p10,p0=EVENT_SSM,r24
+    cmp.eq p11,p0=EVENT_MOV_TO_PSR,r24
+    cmp.eq p12,p0=EVENT_THASH,r24
+    (p6) br.dptk.many kvm_asm_mov_from_ar
+    (p7) br.dptk.many kvm_asm_mov_from_rr
+    (p8) br.dptk.many kvm_asm_mov_to_rr
+    (p9) br.dptk.many kvm_asm_rsm
+    (p10) br.dptk.many kvm_asm_ssm
+    (p11) br.dptk.many kvm_asm_mov_to_psr
+    (p12) br.dptk.many kvm_asm_thash
+    ;;
+kvm_virtualization_fault_back:
+    adds r16 = VMM_VCPU_SAVED_GP_OFFSET,r21
+    ;;
+    ld8 r1 = [r16]
+    ;;
+    mov r19=37
+    adds r16 = VMM_VCPU_CAUSE_OFFSET,r21
+    adds r17 = VMM_VCPU_OPCODE_OFFSET,r21
+    ;;
+    st8 [r16] = r24
+    st8 [r17] = r25
+    ;;
+    cmp.ne p6,p0=EVENT_RFI, r24
+    (p6) br.sptk kvm_dispatch_virtualization_fault
+    ;;
+    adds r18=VMM_VPD_BASE_OFFSET,r21
+    ;;
+    ld8 r18=[r18]
+    ;;
+    adds r18=VMM_VPD_VIFS_OFFSET,r18
+    ;;
+    ld8 r18=[r18]
+    ;;
+    tbit.z p6,p0=r18,63
+    (p6) br.sptk kvm_dispatch_virtualization_fault
+    ;;
+    //if vifs.v=1 desert current register frame
+    alloc r18=ar.pfs,0,0,0,0
+    br.sptk kvm_dispatch_virtualization_fault
+END(kvm_virtualization_fault)
+
+    .org kvm_ia64_ivt+0x6200
+//////////////////////////////////////////////////////////////
+// 0x6200 Entry 38 (size 16 bundles) Reserved
+    KVM_FAULT(38)
+
+    .org kvm_ia64_ivt+0x6300
+/////////////////////////////////////////////////////////////////
+// 0x6300 Entry 39 (size 16 bundles) Reserved
+    KVM_FAULT(39)
+
+    .org kvm_ia64_ivt+0x6400
+/////////////////////////////////////////////////////////////////
+// 0x6400 Entry 40 (size 16 bundles) Reserved
+    KVM_FAULT(40)
+
+    .org kvm_ia64_ivt+0x6500
+//////////////////////////////////////////////////////////////////
+// 0x6500 Entry 41 (size 16 bundles) Reserved
+    KVM_FAULT(41)
+
+    .org kvm_ia64_ivt+0x6600
+//////////////////////////////////////////////////////////////////
+// 0x6600 Entry 42 (size 16 bundles) Reserved
+    KVM_FAULT(42)
+
+    .org kvm_ia64_ivt+0x6700
+//////////////////////////////////////////////////////////////////
+// 0x6700 Entry 43 (size 16 bundles) Reserved
+    KVM_FAULT(43)
+
+    .org kvm_ia64_ivt+0x6800
+//////////////////////////////////////////////////////////////////
+// 0x6800 Entry 44 (size 16 bundles) Reserved
+    KVM_FAULT(44)
+
+    .org kvm_ia64_ivt+0x6900
+///////////////////////////////////////////////////////////////////
+// 0x6900 Entry 45 (size 16 bundles) IA-32 Exeception
+//(17,18,29,41,42,43,44,58,60,61,62,72,73,75,76,77)
+ENTRY(kvm_ia32_exception)
+    KVM_FAULT(45)
+END(kvm_ia32_exception)
+
+    .org kvm_ia64_ivt+0x6a00
+////////////////////////////////////////////////////////////////////
+// 0x6a00 Entry 46 (size 16 bundles) IA-32 Intercept  (30,31,59,70,71)
+ENTRY(kvm_ia32_intercept)
+    KVM_FAULT(47)
+END(kvm_ia32_intercept)
+
+    .org kvm_ia64_ivt+0x6c00
+/////////////////////////////////////////////////////////////////////
+// 0x6c00 Entry 48 (size 16 bundles) Reserved
+    KVM_FAULT(48)
+
+    .org kvm_ia64_ivt+0x6d00
+//////////////////////////////////////////////////////////////////////
+// 0x6d00 Entry 49 (size 16 bundles) Reserved
+    KVM_FAULT(49)
+
+    .org kvm_ia64_ivt+0x6e00
+//////////////////////////////////////////////////////////////////////
+// 0x6e00 Entry 50 (size 16 bundles) Reserved
+    KVM_FAULT(50)
+
+    .org kvm_ia64_ivt+0x6f00
+/////////////////////////////////////////////////////////////////////
+// 0x6f00 Entry 51 (size 16 bundles) Reserved
+    KVM_FAULT(52)
+
+    .org kvm_ia64_ivt+0x7100
+////////////////////////////////////////////////////////////////////
+// 0x7100 Entry 53 (size 16 bundles) Reserved
+    KVM_FAULT(53)
+
+    .org kvm_ia64_ivt+0x7200
+/////////////////////////////////////////////////////////////////////
+// 0x7200 Entry 54 (size 16 bundles) Reserved
+    KVM_FAULT(54)
+
+    .org kvm_ia64_ivt+0x7300
+////////////////////////////////////////////////////////////////////
+// 0x7300 Entry 55 (size 16 bundles) Reserved
+    KVM_FAULT(55)
+
+    .org kvm_ia64_ivt+0x7400
+////////////////////////////////////////////////////////////////////
+// 0x7400 Entry 56 (size 16 bundles) Reserved
+    KVM_FAULT(56)
+
+    .org kvm_ia64_ivt+0x7500
+/////////////////////////////////////////////////////////////////////
+// 0x7500 Entry 57 (size 16 bundles) Reserved
+    KVM_FAULT(57)
+
+    .org kvm_ia64_ivt+0x7600
+/////////////////////////////////////////////////////////////////////
+// 0x7600 Entry 58 (size 16 bundles) Reserved
+    KVM_FAULT(58)
+
+    .org kvm_ia64_ivt+0x7700
+////////////////////////////////////////////////////////////////////
+// 0x7700 Entry 59 (size 16 bundles) Reserved
+    KVM_FAULT(59)
+
+    .org kvm_ia64_ivt+0x7800
+////////////////////////////////////////////////////////////////////
+// 0x7800 Entry 60 (size 16 bundles) Reserved
+    KVM_FAULT(60)
+
+    .org kvm_ia64_ivt+0x7900
+/////////////////////////////////////////////////////////////////////
+// 0x7900 Entry 61 (size 16 bundles) Reserved
+    KVM_FAULT(61)
+
+    .org kvm_ia64_ivt+0x7a00
+/////////////////////////////////////////////////////////////////////
+// 0x7a00 Entry 62 (size 16 bundles) Reserved
+    KVM_FAULT(62)
+
+    .org kvm_ia64_ivt+0x7b00
+/////////////////////////////////////////////////////////////////////
+// 0x7b00 Entry 63 (size 16 bundles) Reserved
+    KVM_FAULT(63)
+
+    .org kvm_ia64_ivt+0x7c00
+////////////////////////////////////////////////////////////////////
+// 0x7c00 Entry 64 (size 16 bundles) Reserved
+    KVM_FAULT(64)
+
+    .org kvm_ia64_ivt+0x7d00
+/////////////////////////////////////////////////////////////////////
+// 0x7d00 Entry 65 (size 16 bundles) Reserved
+    KVM_FAULT(65)
+
+    .org kvm_ia64_ivt+0x7e00
+/////////////////////////////////////////////////////////////////////
+// 0x7e00 Entry 66 (size 16 bundles) Reserved
+    KVM_FAULT(66)
+
+    .org kvm_ia64_ivt+0x7f00
+////////////////////////////////////////////////////////////////////
+// 0x7f00 Entry 67 (size 16 bundles) Reserved
+    KVM_FAULT(67)
+
+    .org kvm_ia64_ivt+0x8000
+// There is no particular reason for this code to be here, other than that
+// there happens to be space here that would go unused otherwise.  If this
+// fault ever gets "unreserved", simply moved the following code to a more
+// suitable spot...
+
+
+ENTRY(kvm_dtlb_miss_dispatch)
+    mov r19 = 2
+    KVM_SAVE_MIN_WITH_COVER_R19
+    alloc r14=ar.pfs,0,0,3,0
+    mov out0=cr.ifa
+    mov out1=r15
+    adds r3=8,r2                // set up second base pointer
+    ;;
+    ssm psr.ic
+    ;;
+    srlz.i                  // guarantee that interruption collection is on
+    ;;
+    //(p15) ssm psr.i               // restore psr.i
+    addl r14=@gprel(ia64_leave_hypervisor_prepare),gp
+    ;;
+    KVM_SAVE_REST
+    KVM_SAVE_EXTRA
+    mov rp=r14
+    ;;
+    adds out2=16,r12
+    br.call.sptk.many b6=kvm_page_fault
+END(kvm_dtlb_miss_dispatch)
+
+ENTRY(kvm_itlb_miss_dispatch)
+
+    KVM_SAVE_MIN_WITH_COVER_R19
+    alloc r14=ar.pfs,0,0,3,0
+    mov out0=cr.ifa
+    mov out1=r15
+    adds r3=8,r2                // set up second base pointer
+    ;;
+    ssm psr.ic
+    ;;
+    srlz.i                  // guarantee that interruption collection is on
+    ;;
+    //(p15) ssm psr.i               // restore psr.i
+    addl r14=@gprel(ia64_leave_hypervisor),gp
+    ;;
+    KVM_SAVE_REST
+    mov rp=r14
+    ;;
+    adds out2=16,r12
+    br.call.sptk.many b6=kvm_page_fault
+END(kvm_itlb_miss_dispatch)
+
+ENTRY(kvm_dispatch_reflection)
+    /*
+     * Input:
+     *  psr.ic: off
+     *  r19:    intr type (offset into ivt, see ia64_int.h)
+     *  r31:    contains saved predicates (pr)
+     */
+    KVM_SAVE_MIN_WITH_COVER_R19
+    alloc r14=ar.pfs,0,0,5,0
+    mov out0=cr.ifa
+    mov out1=cr.isr
+    mov out2=cr.iim
+    mov out3=r15
+    adds r3=8,r2                // set up second base pointer
+    ;;
+    ssm psr.ic
+    ;;
+    srlz.i                  // guarantee that interruption collection is on
+    ;;
+    //(p15) ssm psr.i               // restore psr.i
+    addl r14=@gprel(ia64_leave_hypervisor),gp
+    ;;
+    KVM_SAVE_REST
+    mov rp=r14
+    ;;
+    adds out4=16,r12
+    br.call.sptk.many b6=reflect_interruption
+END(kvm_dispatch_reflection)
+
+ENTRY(kvm_dispatch_virtualization_fault)
+    adds r16 = VMM_VCPU_CAUSE_OFFSET,r21
+    adds r17 = VMM_VCPU_OPCODE_OFFSET,r21
+    ;;
+    st8 [r16] = r24
+    st8 [r17] = r25
+    ;;
+    KVM_SAVE_MIN_WITH_COVER_R19
+    ;;
+    alloc r14=ar.pfs,0,0,2,0 // now it's safe (must be first in insn group!)
+    mov out0=r13        //vcpu
+    adds r3=8,r2                // set up second base pointer
+    ;;
+    ssm psr.ic
+    ;;
+    srlz.i                  // guarantee that interruption collection is on
+    ;;
+    //(p15) ssm psr.i               // restore psr.i
+    addl r14=@gprel(ia64_leave_hypervisor_prepare),gp
+    ;;
+    KVM_SAVE_REST
+    KVM_SAVE_EXTRA
+    mov rp=r14
+    ;;
+    adds out1=16,sp         //regs
+    br.call.sptk.many b6=kvm_emulate
+END(kvm_dispatch_virtualization_fault)
+
+
+ENTRY(kvm_dispatch_interrupt)
+    KVM_SAVE_MIN_WITH_COVER_R19	// uses r31; defines r2 and r3
+    ;;
+    alloc r14=ar.pfs,0,0,1,0 // must be first in an insn group
+    //mov out0=cr.ivr		// pass cr.ivr as first arg
+    adds r3=8,r2		// set up second base pointer for SAVE_REST
+    ;;
+    ssm psr.ic
+    ;;
+    srlz.i
+    ;;
+    //(p15) ssm psr.i
+    addl r14=@gprel(ia64_leave_hypervisor),gp
+    ;;
+    KVM_SAVE_REST
+    mov rp=r14
+    ;;
+    mov out0=r13		// pass pointer to pt_regs as second arg
+    br.call.sptk.many b6=kvm_ia64_handle_irq
+END(kvm_dispatch_interrupt)
+
+
+
+
+GLOBAL_ENTRY(ia64_leave_nested)
+	rsm psr.i
+	;;
+	adds r21=PT(PR)+16,r12
+	;;
+	lfetch [r21],PT(CR_IPSR)-PT(PR)
+	adds r2=PT(B6)+16,r12
+	adds r3=PT(R16)+16,r12
+	;;
+	lfetch [r21]
+	ld8 r28=[r2],8		// load b6
+	adds r29=PT(R24)+16,r12
+
+	ld8.fill r16=[r3]
+	adds r3=PT(AR_CSD)-PT(R16),r3
+	adds r30=PT(AR_CCV)+16,r12
+	;;
+	ld8.fill r24=[r29]
+	ld8 r15=[r30]		// load ar.ccv
+	;;
+	ld8 r29=[r2],16		// load b7
+	ld8 r30=[r3],16		// load ar.csd
+	;;
+	ld8 r31=[r2],16		// load ar.ssd
+	ld8.fill r8=[r3],16
+	;;
+	ld8.fill r9=[r2],16
+	ld8.fill r10=[r3],PT(R17)-PT(R10)
+	;;
+	ld8.fill r11=[r2],PT(R18)-PT(R11)
+	ld8.fill r17=[r3],16
+	;;
+	ld8.fill r18=[r2],16
+	ld8.fill r19=[r3],16
+	;;
+	ld8.fill r20=[r2],16
+	ld8.fill r21=[r3],16
+	mov ar.csd=r30
+	mov ar.ssd=r31
+	;;
+	rsm psr.i | psr.ic
+	// initiate turning off of interrupt and interruption collection
+	invala			// invalidate ALAT
+	;;
+	srlz.i
+	;;
+	ld8.fill r22=[r2],24
+	ld8.fill r23=[r3],24
+	mov b6=r28
+	;;
+	ld8.fill r25=[r2],16
+	ld8.fill r26=[r3],16
+	mov b7=r29
+	;;
+	ld8.fill r27=[r2],16
+	ld8.fill r28=[r3],16
+	;;
+	ld8.fill r29=[r2],16
+	ld8.fill r30=[r3],24
+	;;
+	ld8.fill r31=[r2],PT(F9)-PT(R31)
+	adds r3=PT(F10)-PT(F6),r3
+	;;
+	ldf.fill f9=[r2],PT(F6)-PT(F9)
+	ldf.fill f10=[r3],PT(F8)-PT(F10)
+	;;
+	ldf.fill f6=[r2],PT(F7)-PT(F6)
+	;;
+	ldf.fill f7=[r2],PT(F11)-PT(F7)
+	ldf.fill f8=[r3],32
+	;;
+	srlz.i			// ensure interruption collection is off
+	mov ar.ccv=r15
+	;;
+	bsw.0	// switch back to bank 0 (no stop bit required beforehand...)
+	;;
+	ldf.fill f11=[r2]
+//	mov r18=r13
+//    mov r21=r13
+	adds r16=PT(CR_IPSR)+16,r12
+	adds r17=PT(CR_IIP)+16,r12
+	;;
+	ld8 r29=[r16],16	// load cr.ipsr
+	ld8 r28=[r17],16	// load cr.iip
+	;;
+	ld8 r30=[r16],16	// load cr.ifs
+	ld8 r25=[r17],16	// load ar.unat
+	;;
+	ld8 r26=[r16],16	// load ar.pfs
+	ld8 r27=[r17],16	// load ar.rsc
+	cmp.eq p9,p0=r0,r0
+	// set p9 to indicate that we should restore cr.ifs
+	;;
+	ld8 r24=[r16],16	// load ar.rnat (may be garbage)
+	ld8 r23=[r17],16// load ar.bspstore (may be garbage)
+	;;
+	ld8 r31=[r16],16	// load predicates
+	ld8 r22=[r17],16	// load b0
+	;;
+	ld8 r19=[r16],16	// load ar.rsc value for "loadrs"
+	ld8.fill r1=[r17],16	// load r1
+	;;
+	ld8.fill r12=[r16],16
+	ld8.fill r13=[r17],16
+	;;
+	ld8 r20=[r16],16	// ar.fpsr
+	ld8.fill r15=[r17],16
+	;;
+	ld8.fill r14=[r16],16
+	ld8.fill r2=[r17]
+	;;
+	ld8.fill r3=[r16]
+	;;
+	mov r16=ar.bsp		// get existing backing store pointer
+	;;
+	mov b0=r22
+	mov ar.pfs=r26
+	mov cr.ifs=r30
+	mov cr.ipsr=r29
+	mov ar.fpsr=r20
+	mov cr.iip=r28
+	;;
+	mov ar.rsc=r27
+	mov ar.unat=r25
+	mov pr=r31,-1
+	rfi
+END(ia64_leave_nested)
+
+
+
+GLOBAL_ENTRY(ia64_leave_hypervisor_prepare)
+    /*
+     * work.need_resched etc. mustn't get changed
+     *by this CPU before it returns to
+    ;;
+     * user- or fsys-mode, hence we disable interrupts early on:
+     */
+    adds r2 = PT(R4)+16,r12
+    adds r3 = PT(R5)+16,r12
+    adds r8 = PT(EML_UNAT)+16,r12
+    ;;
+    ld8 r8 = [r8]
+    ;;
+    mov ar.unat=r8
+    ;;
+    ld8.fill r4=[r2],16    //load r4
+    ld8.fill r5=[r3],16    //load r5
+    ;;
+    ld8.fill r6=[r2]    //load r6
+    ld8.fill r7=[r3]    //load r7
+    ;;
+END(ia64_leave_hypervisor_prepare)
+//fall through
+GLOBAL_ENTRY(ia64_leave_hypervisor)
+    rsm psr.i
+    ;;
+    br.call.sptk.many b0=leave_hypervisor_tail
+    ;;
+    adds r20=PT(PR)+16,r12
+    adds r8=PT(EML_UNAT)+16,r12
+    ;;
+    ld8 r8=[r8]
+    ;;
+    mov ar.unat=r8
+    ;;
+    lfetch [r20],PT(CR_IPSR)-PT(PR)
+    adds r2 = PT(B6)+16,r12
+    adds r3 = PT(B7)+16,r12
+    ;;
+    lfetch [r20]
+    ;;
+    ld8 r24=[r2],16        /* B6 */
+    ld8 r25=[r3],16        /* B7 */
+    ;;
+    ld8 r26=[r2],16        /* ar_csd */
+    ld8 r27=[r3],16        /* ar_ssd */
+    mov b6 = r24
+    ;;
+    ld8.fill r8=[r2],16
+    ld8.fill r9=[r3],16
+    mov b7 = r25
+    ;;
+    mov ar.csd = r26
+    mov ar.ssd = r27
+    ;;
+    ld8.fill r10=[r2],PT(R15)-PT(R10)
+    ld8.fill r11=[r3],PT(R14)-PT(R11)
+    ;;
+    ld8.fill r15=[r2],PT(R16)-PT(R15)
+    ld8.fill r14=[r3],PT(R17)-PT(R14)
+    ;;
+    ld8.fill r16=[r2],16
+    ld8.fill r17=[r3],16
+    ;;
+    ld8.fill r18=[r2],16
+    ld8.fill r19=[r3],16
+    ;;
+    ld8.fill r20=[r2],16
+    ld8.fill r21=[r3],16
+    ;;
+    ld8.fill r22=[r2],16
+    ld8.fill r23=[r3],16
+    ;;
+    ld8.fill r24=[r2],16
+    ld8.fill r25=[r3],16
+    ;;
+    ld8.fill r26=[r2],16
+    ld8.fill r27=[r3],16
+    ;;
+    ld8.fill r28=[r2],16
+    ld8.fill r29=[r3],16
+    ;;
+    ld8.fill r30=[r2],PT(F6)-PT(R30)
+    ld8.fill r31=[r3],PT(F7)-PT(R31)
+    ;;
+    rsm psr.i | psr.ic
+    // initiate turning off of interrupt and interruption collection
+    invala          // invalidate ALAT
+    ;;
+    srlz.i          // ensure interruption collection is off
+    ;;
+    bsw.0
+    ;;
+    adds r16 = PT(CR_IPSR)+16,r12
+    adds r17 = PT(CR_IIP)+16,r12
+    mov r21=r13		// get current
+    ;;
+    ld8 r31=[r16],16    // load cr.ipsr
+    ld8 r30=[r17],16    // load cr.iip
+    ;;
+    ld8 r29=[r16],16    // load cr.ifs
+    ld8 r28=[r17],16    // load ar.unat
+    ;;
+    ld8 r27=[r16],16    // load ar.pfs
+    ld8 r26=[r17],16    // load ar.rsc
+    ;;
+    ld8 r25=[r16],16    // load ar.rnat
+    ld8 r24=[r17],16    // load ar.bspstore
+    ;;
+    ld8 r23=[r16],16    // load predicates
+    ld8 r22=[r17],16    // load b0
+    ;;
+    ld8 r20=[r16],16    // load ar.rsc value for "loadrs"
+    ld8.fill r1=[r17],16    //load r1
+    ;;
+    ld8.fill r12=[r16],16    //load r12
+    ld8.fill r13=[r17],PT(R2)-PT(R13)    //load r13
+    ;;
+    ld8 r19=[r16],PT(R3)-PT(AR_FPSR)    //load ar_fpsr
+    ld8.fill r2=[r17],PT(AR_CCV)-PT(R2)    //load r2
+    ;;
+    ld8.fill r3=[r16]	//load r3
+    ld8 r18=[r17]	//load ar_ccv
+    ;;
+    mov ar.fpsr=r19
+    mov ar.ccv=r18
+    shr.u r18=r20,16
+    ;;
+kvm_rbs_switch:
+    mov r19=96
+
+kvm_dont_preserve_current_frame:
+/*
+    * To prevent leaking bits between the hypervisor and guest domain,
+    * we must clear the stacked registers in the "invalid" partition here.
+    * 5 registers/cycle on McKinley).
+    */
+#   define pRecurse	p6
+#   define pReturn	p7
+#   define Nregs	14
+
+    alloc loc0=ar.pfs,2,Nregs-2,2,0
+    shr.u loc1=r18,9		// RNaTslots <= floor(dirtySize / (64*8))
+    sub r19=r19,r18		// r19 = (physStackedSize + 8) - dirtySize
+    ;;
+    mov ar.rsc=r20		// load ar.rsc to be used for "loadrs"
+    shladd in0=loc1,3,r19
+    mov in1=0
+    ;;
+    TEXT_ALIGN(32)
+kvm_rse_clear_invalid:
+    alloc loc0=ar.pfs,2,Nregs-2,2,0
+    cmp.lt pRecurse,p0=Nregs*8,in0
+    // if more than Nregs regs left to clear, (re)curse
+    add out0=-Nregs*8,in0
+    add out1=1,in1		// increment recursion count
+    mov loc1=0
+    mov loc2=0
+    ;;
+    mov loc3=0
+    mov loc4=0
+    mov loc5=0
+    mov loc6=0
+    mov loc7=0
+(pRecurse) br.call.dptk.few b0=kvm_rse_clear_invalid
+    ;;
+    mov loc8=0
+    mov loc9=0
+    cmp.ne pReturn,p0=r0,in1
+    // if recursion count != 0, we need to do a br.ret
+    mov loc10=0
+    mov loc11=0
+(pReturn) br.ret.dptk.many b0
+
+#	undef pRecurse
+#	undef pReturn
+
+// loadrs has already been shifted
+    alloc r16=ar.pfs,0,0,0,0    // drop current register frame
+    ;;
+    loadrs
+    ;;
+    mov ar.bspstore=r24
+    ;;
+    mov ar.unat=r28
+    mov ar.rnat=r25
+    mov ar.rsc=r26
+    ;;
+    mov cr.ipsr=r31
+    mov cr.iip=r30
+    mov cr.ifs=r29
+    mov ar.pfs=r27
+    adds r18=VMM_VPD_BASE_OFFSET,r21
+    ;;
+    ld8 r18=[r18]   //vpd
+    adds r17=VMM_VCPU_ISR_OFFSET,r21
+    ;;
+    ld8 r17=[r17]
+    adds r19=VMM_VPD_VPSR_OFFSET,r18
+    ;;
+    ld8 r19=[r19]        //vpsr
+    adds r20=VMM_VCPU_VSA_BASE_OFFSET,r21
+    ;;
+    ld8 r20=[r20]
+    ;;
+//vsa_sync_write_start
+    mov r25=r18
+    adds r16= VMM_VCPU_GP_OFFSET,r21
+    ;;
+    ld8 r16= [r16] // Put gp in r24
+    movl r24=@gprel(ia64_vmm_entry)  // calculate return address
+    ;;
+    add  r24=r24,r16
+    ;;
+    add r16=PAL_VPS_SYNC_WRITE,r20
+    ;;
+    mov b0=r16
+    br.cond.sptk b0         // call the service
+    ;;
+END(ia64_leave_hypervisor)
+// fall through
+GLOBAL_ENTRY(ia64_vmm_entry)
+/*
+ *  must be at bank 0
+ *  parameter:
+ *  r17:cr.isr
+ *  r18:vpd
+ *  r19:vpsr
+ *  r20:__vsa_base
+ *  r22:b0
+ *  r23:predicate
+ */
+    mov r24=r22
+    mov r25=r18
+    tbit.nz p1,p2 = r19,IA64_PSR_IC_BIT        // p1=vpsr.ic
+    ;;
+    (p1) add r29=PAL_VPS_RESUME_NORMAL,r20
+    (p1) br.sptk.many ia64_vmm_entry_out
+    ;;
+    tbit.nz p1,p2 = r17,IA64_ISR_IR_BIT		//p1=cr.isr.ir
+    ;;
+    (p1) add r29=PAL_VPS_RESUME_NORMAL,r20
+    (p2) add r29=PAL_VPS_RESUME_HANDLER,r20
+    (p2) ld8 r26=[r25]
+    ;;
+ia64_vmm_entry_out:
+    mov pr=r23,-2
+    mov b0=r29
+    ;;
+    br.cond.sptk b0             // call pal service
+END(ia64_vmm_entry)
+
+
+
+/*
+ * extern u64 ia64_call_vsa(u64 proc, u64 arg1, u64 arg2,
+ *                  u64 arg3, u64 arg4, u64 arg5,
+ *                  u64 arg6, u64 arg7);
+ *
+ * XXX: The currently defined services use only 4 args at the max. The
+ *  rest are not consumed.
+ */
+GLOBAL_ENTRY(ia64_call_vsa)
+    .regstk 4,4,0,0
+
+rpsave  =   loc0
+pfssave =   loc1
+psrsave =   loc2
+entry   =   loc3
+hostret =   r24
+
+    alloc   pfssave=ar.pfs,4,4,0,0
+    mov rpsave=rp
+    adds entry=VMM_VCPU_VSA_BASE_OFFSET, r13
+    ;;
+    ld8 entry=[entry]
+1:  mov hostret=ip
+    mov r25=in1         // copy arguments
+    mov r26=in2
+    mov r27=in3
+    mov psrsave=psr
+    ;;
+    tbit.nz p6,p0=psrsave,14    // IA64_PSR_I
+    tbit.nz p7,p0=psrsave,13    // IA64_PSR_IC
+    ;;
+    add hostret=2f-1b,hostret   // calculate return address
+    add entry=entry,in0
+    ;;
+    rsm psr.i | psr.ic
+    ;;
+    srlz.i
+    mov b6=entry
+    br.cond.sptk b6         // call the service
+2:
+    // Architectural sequence for enabling interrupts if necessary
+(p7)    ssm psr.ic
+    ;;
+(p7)    srlz.i
+    ;;
+//(p6)    ssm psr.i
+    ;;
+    mov rp=rpsave
+    mov ar.pfs=pfssave
+    mov r8=r31
+    ;;
+    srlz.d
+    br.ret.sptk rp
+
+END(ia64_call_vsa)
+
+#define  INIT_BSPSTORE  ((4<<30)-(12<<20)-0x100)
+
+GLOBAL_ENTRY(vmm_reset_entry)
+    //set up ipsr, iip, vpd.vpsr, dcr
+    // For IPSR: it/dt/rt=1, i/ic=1, si=1, vm/bn=1
+    // For DCR: all bits 0
+    adds r14=-VMM_PT_REGS_SIZE, r12
+    ;;
+    movl r6=0x501008826000      // IPSR dt/rt/it:1;i/ic:1, si:1, vm/bn:1
+    movl r10=0x8000000000000000
+    adds r16=PT(CR_IIP), r14
+    adds r20=PT(R1), r14
+    ;;
+    rsm psr.ic | psr.i
+    ;;
+    srlz.i
+    ;;
+    bsw.0
+    ;;
+    mov r21 =r13
+    ;;
+    bsw.1
+    ;;
+    mov ar.rsc = 0
+    ;;
+    flushrs
+    ;;
+    mov ar.bspstore = 0
+    // clear BSPSTORE
+    ;;
+    mov cr.ipsr=r6
+    mov cr.ifs=r10
+    ld8 r4 = [r16] // Set init iip for first run.
+    ld8 r1 = [r20]
+    ;;
+    mov cr.iip=r4
+    ;;
+    adds r16=VMM_VPD_BASE_OFFSET,r13
+    adds r20=VMM_VCPU_VSA_BASE_OFFSET,r13
+    ;;
+    ld8 r18=[r16]
+    ld8 r20=[r20]
+    ;;
+    adds r19=VMM_VPD_VPSR_OFFSET,r18
+    ;;
+    ld8 r19=[r19]
+    mov r17=r0
+    mov r22=r0
+    mov r23=r0
+    br.cond.sptk ia64_vmm_entry
+    br.ret.sptk  b0
+END(vmm_reset_entry)
diff --git a/trunk/arch/ia64/kvm/vti.h b/trunk/arch/ia64/kvm/vti.h
new file mode 100644
index 000000000000..f6c5617e16af
--- /dev/null
+++ b/trunk/arch/ia64/kvm/vti.h
@@ -0,0 +1,290 @@
+/*
+ * vti.h: prototype for generial vt related interface
+ *   	Copyright (c) 2004, Intel Corporation.
+ *
+ *	Xuefei Xu (Anthony Xu) (anthony.xu@intel.com)
+ *	Fred Yang (fred.yang@intel.com)
+ * 	Kun Tian (Kevin Tian) (kevin.tian@intel.com)
+ *
+ *  	Copyright (c) 2007, Intel Corporation.
+ *  	Zhang xiantao <xiantao.zhang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ */
+#ifndef _KVM_VT_I_H
+#define _KVM_VT_I_H
+
+#ifndef __ASSEMBLY__
+#include <asm/page.h>
+
+#include <linux/kvm_host.h>
+
+/* define itr.i and itr.d  in ia64_itr function */
+#define	ITR	0x01
+#define	DTR	0x02
+#define	IaDTR	0x03
+
+#define IA64_TR_VMM       6 /*itr6, dtr6 : maps vmm code, vmbuffer*/
+#define IA64_TR_VM_DATA   7 /*dtr7       : maps current vm data*/
+
+#define RR6 (6UL<<61)
+#define RR7 (7UL<<61)
+
+
+/* config_options in pal_vp_init_env */
+#define	VP_INITIALIZE	1UL
+#define	VP_FR_PMC	1UL<<1
+#define	VP_OPCODE	1UL<<8
+#define	VP_CAUSE	1UL<<9
+#define VP_FW_ACC   	1UL<<63
+
+/* init vp env with initializing vm_buffer */
+#define	VP_INIT_ENV_INITALIZE  (VP_INITIALIZE | VP_FR_PMC |\
+	VP_OPCODE | VP_CAUSE | VP_FW_ACC)
+/* init vp env without initializing vm_buffer */
+#define	VP_INIT_ENV  VP_FR_PMC | VP_OPCODE | VP_CAUSE | VP_FW_ACC
+
+#define		PAL_VP_CREATE   265
+/* Stacked Virt. Initializes a new VPD for the operation of
+ * a new virtual processor in the virtual environment.
+ */
+#define		PAL_VP_ENV_INFO 266
+/*Stacked Virt. Returns the parameters needed to enter a virtual environment.*/
+#define		PAL_VP_EXIT_ENV 267
+/*Stacked Virt. Allows a logical processor to exit a virtual environment.*/
+#define		PAL_VP_INIT_ENV 268
+/*Stacked Virt. Allows a logical processor to enter a virtual environment.*/
+#define		PAL_VP_REGISTER 269
+/*Stacked Virt. Register a different host IVT for the virtual processor.*/
+#define		PAL_VP_RESUME   270
+/* Renamed from PAL_VP_RESUME */
+#define		PAL_VP_RESTORE  270
+/*Stacked Virt. Resumes virtual processor operation on the logical processor.*/
+#define		PAL_VP_SUSPEND  271
+/* Renamed from PAL_VP_SUSPEND */
+#define		PAL_VP_SAVE	271
+/* Stacked Virt. Suspends operation for the specified virtual processor on
+ * the logical processor.
+ */
+#define		PAL_VP_TERMINATE 272
+/* Stacked Virt. Terminates operation for the specified virtual processor.*/
+
+union vac {
+	unsigned long value;
+	struct {
+		int a_int:1;
+		int a_from_int_cr:1;
+		int a_to_int_cr:1;
+		int a_from_psr:1;
+		int a_from_cpuid:1;
+		int a_cover:1;
+		int a_bsw:1;
+		long reserved:57;
+	};
+};
+
+union vdc {
+	unsigned long value;
+	struct {
+		int d_vmsw:1;
+		int d_extint:1;
+		int d_ibr_dbr:1;
+		int d_pmc:1;
+		int d_to_pmd:1;
+		int d_itm:1;
+		long reserved:58;
+	};
+};
+
+struct vpd {
+	union vac   vac;
+	union vdc   vdc;
+	unsigned long  virt_env_vaddr;
+	unsigned long  reserved1[29];
+	unsigned long  vhpi;
+	unsigned long  reserved2[95];
+	unsigned long  vgr[16];
+	unsigned long  vbgr[16];
+	unsigned long  vnat;
+	unsigned long  vbnat;
+	unsigned long  vcpuid[5];
+	unsigned long  reserved3[11];
+	unsigned long  vpsr;
+	unsigned long  vpr;
+	unsigned long  reserved4[76];
+	union {
+		unsigned long  vcr[128];
+		struct {
+			unsigned long dcr;
+			unsigned long itm;
+			unsigned long iva;
+			unsigned long rsv1[5];
+			unsigned long pta;
+			unsigned long rsv2[7];
+			unsigned long ipsr;
+			unsigned long isr;
+			unsigned long rsv3;
+			unsigned long iip;
+			unsigned long ifa;
+			unsigned long itir;
+			unsigned long iipa;
+			unsigned long ifs;
+			unsigned long iim;
+			unsigned long iha;
+			unsigned long rsv4[38];
+			unsigned long lid;
+			unsigned long ivr;
+			unsigned long tpr;
+			unsigned long eoi;
+			unsigned long irr[4];
+			unsigned long itv;
+			unsigned long pmv;
+			unsigned long cmcv;
+			unsigned long rsv5[5];
+			unsigned long lrr0;
+			unsigned long lrr1;
+			unsigned long rsv6[46];
+		};
+	};
+	unsigned long  reserved5[128];
+	unsigned long  reserved6[3456];
+	unsigned long  vmm_avail[128];
+	unsigned long  reserved7[4096];
+};
+
+#define PAL_PROC_VM_BIT		(1UL << 40)
+#define PAL_PROC_VMSW_BIT	(1UL << 54)
+
+static inline s64 ia64_pal_vp_env_info(u64 *buffer_size,
+		u64 *vp_env_info)
+{
+	struct ia64_pal_retval iprv;
+	PAL_CALL_STK(iprv, PAL_VP_ENV_INFO, 0, 0, 0);
+	*buffer_size = iprv.v0;
+	*vp_env_info = iprv.v1;
+	return iprv.status;
+}
+
+static inline s64 ia64_pal_vp_exit_env(u64 iva)
+{
+	struct ia64_pal_retval iprv;
+
+	PAL_CALL_STK(iprv, PAL_VP_EXIT_ENV, (u64)iva, 0, 0);
+	return iprv.status;
+}
+
+static inline s64 ia64_pal_vp_init_env(u64 config_options, u64 pbase_addr,
+			u64 vbase_addr, u64 *vsa_base)
+{
+	struct ia64_pal_retval iprv;
+
+	PAL_CALL_STK(iprv, PAL_VP_INIT_ENV, config_options, pbase_addr,
+			vbase_addr);
+	*vsa_base = iprv.v0;
+
+	return iprv.status;
+}
+
+static inline s64 ia64_pal_vp_restore(u64 *vpd, u64 pal_proc_vector)
+{
+	struct ia64_pal_retval iprv;
+
+	PAL_CALL_STK(iprv, PAL_VP_RESTORE, (u64)vpd, pal_proc_vector, 0);
+
+	return iprv.status;
+}
+
+static inline s64 ia64_pal_vp_save(u64 *vpd, u64 pal_proc_vector)
+{
+	struct ia64_pal_retval iprv;
+
+	PAL_CALL_STK(iprv, PAL_VP_SAVE, (u64)vpd, pal_proc_vector, 0);
+
+	return iprv.status;
+}
+
+#endif
+
+/*VPD field offset*/
+#define VPD_VAC_START_OFFSET		0
+#define VPD_VDC_START_OFFSET		8
+#define VPD_VHPI_START_OFFSET		256
+#define VPD_VGR_START_OFFSET		1024
+#define VPD_VBGR_START_OFFSET		1152
+#define VPD_VNAT_START_OFFSET		1280
+#define VPD_VBNAT_START_OFFSET		1288
+#define VPD_VCPUID_START_OFFSET		1296
+#define VPD_VPSR_START_OFFSET		1424
+#define VPD_VPR_START_OFFSET		1432
+#define VPD_VRSE_CFLE_START_OFFSET	1440
+#define VPD_VCR_START_OFFSET		2048
+#define VPD_VTPR_START_OFFSET		2576
+#define VPD_VRR_START_OFFSET		3072
+#define VPD_VMM_VAIL_START_OFFSET	31744
+
+/*Virtualization faults*/
+
+#define EVENT_MOV_TO_AR			 1
+#define EVENT_MOV_TO_AR_IMM		 2
+#define EVENT_MOV_FROM_AR		 3
+#define EVENT_MOV_TO_CR			 4
+#define EVENT_MOV_FROM_CR		 5
+#define EVENT_MOV_TO_PSR		 6
+#define EVENT_MOV_FROM_PSR		 7
+#define EVENT_ITC_D			 8
+#define EVENT_ITC_I			 9
+#define EVENT_MOV_TO_RR			 10
+#define EVENT_MOV_TO_DBR		 11
+#define EVENT_MOV_TO_IBR		 12
+#define EVENT_MOV_TO_PKR		 13
+#define EVENT_MOV_TO_PMC		 14
+#define EVENT_MOV_TO_PMD		 15
+#define EVENT_ITR_D			 16
+#define EVENT_ITR_I			 17
+#define EVENT_MOV_FROM_RR		 18
+#define EVENT_MOV_FROM_DBR		 19
+#define EVENT_MOV_FROM_IBR		 20
+#define EVENT_MOV_FROM_PKR		 21
+#define EVENT_MOV_FROM_PMC		 22
+#define EVENT_MOV_FROM_CPUID		 23
+#define EVENT_SSM			 24
+#define EVENT_RSM			 25
+#define EVENT_PTC_L			 26
+#define EVENT_PTC_G			 27
+#define EVENT_PTC_GA			 28
+#define EVENT_PTR_D			 29
+#define EVENT_PTR_I			 30
+#define EVENT_THASH			 31
+#define EVENT_TTAG			 32
+#define EVENT_TPA			 33
+#define EVENT_TAK			 34
+#define EVENT_PTC_E			 35
+#define EVENT_COVER			 36
+#define EVENT_RFI			 37
+#define EVENT_BSW_0			 38
+#define EVENT_BSW_1			 39
+#define EVENT_VMSW			 40
+
+/**PAL virtual services offsets */
+#define PAL_VPS_RESUME_NORMAL           0x0000
+#define PAL_VPS_RESUME_HANDLER          0x0400
+#define PAL_VPS_SYNC_READ               0x0800
+#define PAL_VPS_SYNC_WRITE              0x0c00
+#define PAL_VPS_SET_PENDING_INTERRUPT   0x1000
+#define PAL_VPS_THASH                   0x1400
+#define PAL_VPS_TTAG                    0x1800
+#define PAL_VPS_RESTORE                 0x1c00
+#define PAL_VPS_SAVE                    0x2000
+
+#endif/* _VT_I_H*/
diff --git a/trunk/arch/ia64/kvm/vtlb.c b/trunk/arch/ia64/kvm/vtlb.c
new file mode 100644
index 000000000000..def4576d22b1
--- /dev/null
+++ b/trunk/arch/ia64/kvm/vtlb.c
@@ -0,0 +1,636 @@
+/*
+ * vtlb.c: guest virtual tlb handling module.
+ * Copyright (c) 2004, Intel Corporation.
+ *  Yaozu Dong (Eddie Dong) <Eddie.dong@intel.com>
+ *  Xuefei Xu (Anthony Xu) <anthony.xu@intel.com>
+ *
+ * Copyright (c) 2007, Intel Corporation.
+ *  Xuefei Xu (Anthony Xu) <anthony.xu@intel.com>
+ *  Xiantao Zhang <xiantao.zhang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+
+#include "vcpu.h"
+
+#include <linux/rwsem.h>
+
+#include <asm/tlb.h>
+
+/*
+ * Check to see if the address rid:va is translated by the TLB
+ */
+
+static int __is_tr_translated(struct thash_data *trp, u64 rid, u64 va)
+{
+	return ((trp->p) && (trp->rid == rid)
+				&& ((va-trp->vadr) < PSIZE(trp->ps)));
+}
+
+/*
+ * Only for GUEST TR format.
+ */
+static int __is_tr_overlap(struct thash_data *trp, u64 rid, u64 sva, u64 eva)
+{
+	u64 sa1, ea1;
+
+	if (!trp->p || trp->rid != rid)
+		return 0;
+
+	sa1 = trp->vadr;
+	ea1 = sa1 + PSIZE(trp->ps) - 1;
+	eva -= 1;
+	if ((sva > ea1) || (sa1 > eva))
+		return 0;
+	else
+		return 1;
+
+}
+
+void machine_tlb_purge(u64 va, u64 ps)
+{
+	ia64_ptcl(va, ps << 2);
+}
+
+void local_flush_tlb_all(void)
+{
+	int i, j;
+	unsigned long flags, count0, count1;
+	unsigned long stride0, stride1, addr;
+
+	addr    = current_vcpu->arch.ptce_base;
+	count0  = current_vcpu->arch.ptce_count[0];
+	count1  = current_vcpu->arch.ptce_count[1];
+	stride0 = current_vcpu->arch.ptce_stride[0];
+	stride1 = current_vcpu->arch.ptce_stride[1];
+
+	local_irq_save(flags);
+	for (i = 0; i < count0; ++i) {
+		for (j = 0; j < count1; ++j) {
+			ia64_ptce(addr);
+			addr += stride1;
+		}
+		addr += stride0;
+	}
+	local_irq_restore(flags);
+	ia64_srlz_i();          /* srlz.i implies srlz.d */
+}
+
+int vhpt_enabled(struct kvm_vcpu *vcpu, u64 vadr, enum vhpt_ref ref)
+{
+	union ia64_rr    vrr;
+	union ia64_pta   vpta;
+	struct  ia64_psr   vpsr;
+
+	vpsr = *(struct ia64_psr *)&VCPU(vcpu, vpsr);
+	vrr.val = vcpu_get_rr(vcpu, vadr);
+	vpta.val = vcpu_get_pta(vcpu);
+
+	if (vrr.ve & vpta.ve) {
+		switch (ref) {
+		case DATA_REF:
+		case NA_REF:
+			return vpsr.dt;
+		case INST_REF:
+			return vpsr.dt && vpsr.it && vpsr.ic;
+		case RSE_REF:
+			return vpsr.dt && vpsr.rt;
+
+		}
+	}
+	return 0;
+}
+
+struct thash_data *vsa_thash(union ia64_pta vpta, u64 va, u64 vrr, u64 *tag)
+{
+	u64 index, pfn, rid, pfn_bits;
+
+	pfn_bits = vpta.size - 5 - 8;
+	pfn = REGION_OFFSET(va) >> _REGION_PAGE_SIZE(vrr);
+	rid = _REGION_ID(vrr);
+	index = ((rid & 0xff) << pfn_bits)|(pfn & ((1UL << pfn_bits) - 1));
+	*tag = ((rid >> 8) & 0xffff) | ((pfn >> pfn_bits) << 16);
+
+	return (struct thash_data *)((vpta.base << PTA_BASE_SHIFT) +
+				(index << 5));
+}
+
+struct thash_data *__vtr_lookup(struct kvm_vcpu *vcpu, u64 va, int type)
+{
+
+	struct thash_data *trp;
+	int  i;
+	u64 rid;
+
+	rid = vcpu_get_rr(vcpu, va);
+	rid = rid & RR_RID_MASK;;
+	if (type == D_TLB) {
+		if (vcpu_quick_region_check(vcpu->arch.dtr_regions, va)) {
+			for (trp = (struct thash_data *)&vcpu->arch.dtrs, i = 0;
+						i < NDTRS; i++, trp++) {
+				if (__is_tr_translated(trp, rid, va))
+					return trp;
+			}
+		}
+	} else {
+		if (vcpu_quick_region_check(vcpu->arch.itr_regions, va)) {
+			for (trp = (struct thash_data *)&vcpu->arch.itrs, i = 0;
+					i < NITRS; i++, trp++) {
+				if (__is_tr_translated(trp, rid, va))
+					return trp;
+			}
+		}
+	}
+
+	return NULL;
+}
+
+static void vhpt_insert(u64 pte, u64 itir, u64 ifa, u64 gpte)
+{
+	union ia64_rr rr;
+	struct thash_data *head;
+	unsigned long ps, gpaddr;
+
+	ps = itir_ps(itir);
+
+	gpaddr = ((gpte & _PAGE_PPN_MASK) >> ps << ps) |
+		(ifa & ((1UL << ps) - 1));
+
+	rr.val = ia64_get_rr(ifa);
+	head = (struct thash_data *)ia64_thash(ifa);
+	head->etag = INVALID_TI_TAG;
+	ia64_mf();
+	head->page_flags = pte & ~PAGE_FLAGS_RV_MASK;
+	head->itir = rr.ps << 2;
+	head->etag = ia64_ttag(ifa);
+	head->gpaddr = gpaddr;
+}
+
+void mark_pages_dirty(struct kvm_vcpu *v, u64 pte, u64 ps)
+{
+	u64 i, dirty_pages = 1;
+	u64 base_gfn = (pte&_PAGE_PPN_MASK) >> PAGE_SHIFT;
+	spinlock_t *lock = __kvm_va(v->arch.dirty_log_lock_pa);
+	void *dirty_bitmap = (void *)v - (KVM_VCPU_OFS + v->vcpu_id * VCPU_SIZE)
+						+ KVM_MEM_DIRTY_LOG_OFS;
+	dirty_pages <<= ps <= PAGE_SHIFT ? 0 : ps - PAGE_SHIFT;
+
+	vmm_spin_lock(lock);
+	for (i = 0; i < dirty_pages; i++) {
+		/* avoid RMW */
+		if (!test_bit(base_gfn + i, dirty_bitmap))
+			set_bit(base_gfn + i , dirty_bitmap);
+	}
+	vmm_spin_unlock(lock);
+}
+
+void thash_vhpt_insert(struct kvm_vcpu *v, u64 pte, u64 itir, u64 va, int type)
+{
+	u64 phy_pte, psr;
+	union ia64_rr mrr;
+
+	mrr.val = ia64_get_rr(va);
+	phy_pte = translate_phy_pte(&pte, itir, va);
+
+	if (itir_ps(itir) >= mrr.ps) {
+		vhpt_insert(phy_pte, itir, va, pte);
+	} else {
+		phy_pte  &= ~PAGE_FLAGS_RV_MASK;
+		psr = ia64_clear_ic();
+		ia64_itc(type, va, phy_pte, itir_ps(itir));
+		ia64_set_psr(psr);
+	}
+
+	if (!(pte&VTLB_PTE_IO))
+		mark_pages_dirty(v, pte, itir_ps(itir));
+}
+
+/*
+ *   vhpt lookup
+ */
+struct thash_data *vhpt_lookup(u64 va)
+{
+	struct thash_data *head;
+	u64 tag;
+
+	head = (struct thash_data *)ia64_thash(va);
+	tag = ia64_ttag(va);
+	if (head->etag == tag)
+		return head;
+	return NULL;
+}
+
+u64 guest_vhpt_lookup(u64 iha, u64 *pte)
+{
+	u64 ret;
+	struct thash_data *data;
+
+	data = __vtr_lookup(current_vcpu, iha, D_TLB);
+	if (data != NULL)
+		thash_vhpt_insert(current_vcpu, data->page_flags,
+			data->itir, iha, D_TLB);
+
+	asm volatile ("rsm psr.ic|psr.i;;"
+			"srlz.d;;"
+			"ld8.s r9=[%1];;"
+			"tnat.nz p6,p7=r9;;"
+			"(p6) mov %0=1;"
+			"(p6) mov r9=r0;"
+			"(p7) extr.u r9=r9,0,53;;"
+			"(p7) mov %0=r0;"
+			"(p7) st8 [%2]=r9;;"
+			"ssm psr.ic;;"
+			"srlz.d;;"
+			/* "ssm psr.i;;" Once interrupts in vmm open, need fix*/
+			: "=r"(ret) : "r"(iha), "r"(pte):"memory");
+
+	return ret;
+}
+
+/*
+ *  purge software guest tlb
+ */
+
+static void vtlb_purge(struct kvm_vcpu *v, u64 va, u64 ps)
+{
+	struct thash_data *cur;
+	u64 start, curadr, size, psbits, tag, rr_ps, num;
+	union ia64_rr vrr;
+	struct thash_cb *hcb = &v->arch.vtlb;
+
+	vrr.val = vcpu_get_rr(v, va);
+	psbits = VMX(v, psbits[(va >> 61)]);
+	start = va & ~((1UL << ps) - 1);
+	while (psbits) {
+		curadr = start;
+		rr_ps = __ffs(psbits);
+		psbits &= ~(1UL << rr_ps);
+		num = 1UL << ((ps < rr_ps) ? 0 : (ps - rr_ps));
+		size = PSIZE(rr_ps);
+		vrr.ps = rr_ps;
+		while (num) {
+			cur = vsa_thash(hcb->pta, curadr, vrr.val, &tag);
+			if (cur->etag == tag && cur->ps == rr_ps)
+				cur->etag = INVALID_TI_TAG;
+			curadr += size;
+			num--;
+		}
+	}
+}
+
+
+/*
+ *  purge VHPT and machine TLB
+ */
+static void vhpt_purge(struct kvm_vcpu *v, u64 va, u64 ps)
+{
+	struct thash_data *cur;
+	u64 start, size, tag, num;
+	union ia64_rr rr;
+
+	start = va & ~((1UL << ps) - 1);
+	rr.val = ia64_get_rr(va);
+	size = PSIZE(rr.ps);
+	num = 1UL << ((ps < rr.ps) ? 0 : (ps - rr.ps));
+	while (num) {
+		cur = (struct thash_data *)ia64_thash(start);
+		tag = ia64_ttag(start);
+		if (cur->etag == tag)
+			cur->etag = INVALID_TI_TAG;
+		start += size;
+		num--;
+	}
+	machine_tlb_purge(va, ps);
+}
+
+/*
+ * Insert an entry into hash TLB or VHPT.
+ * NOTES:
+ *  1: When inserting VHPT to thash, "va" is a must covered
+ *  address by the inserted machine VHPT entry.
+ *  2: The format of entry is always in TLB.
+ *  3: The caller need to make sure the new entry will not overlap
+ *     with any existed entry.
+ */
+void vtlb_insert(struct kvm_vcpu *v, u64 pte, u64 itir, u64 va)
+{
+	struct thash_data *head;
+	union ia64_rr vrr;
+	u64 tag;
+	struct thash_cb *hcb = &v->arch.vtlb;
+
+	vrr.val = vcpu_get_rr(v, va);
+	vrr.ps = itir_ps(itir);
+	VMX(v, psbits[va >> 61]) |= (1UL << vrr.ps);
+	head = vsa_thash(hcb->pta, va, vrr.val, &tag);
+	head->page_flags = pte;
+	head->itir = itir;
+	head->etag = tag;
+}
+
+int vtr_find_overlap(struct kvm_vcpu *vcpu, u64 va, u64 ps, int type)
+{
+	struct thash_data  *trp;
+	int  i;
+	u64 end, rid;
+
+	rid = vcpu_get_rr(vcpu, va);
+	rid = rid & RR_RID_MASK;
+	end = va + PSIZE(ps);
+	if (type == D_TLB) {
+		if (vcpu_quick_region_check(vcpu->arch.dtr_regions, va)) {
+			for (trp = (struct thash_data *)&vcpu->arch.dtrs, i = 0;
+					i < NDTRS; i++, trp++) {
+				if (__is_tr_overlap(trp, rid, va, end))
+					return i;
+			}
+		}
+	} else {
+		if (vcpu_quick_region_check(vcpu->arch.itr_regions, va)) {
+			for (trp = (struct thash_data *)&vcpu->arch.itrs, i = 0;
+					i < NITRS; i++, trp++) {
+				if (__is_tr_overlap(trp, rid, va, end))
+					return i;
+			}
+		}
+	}
+	return -1;
+}
+
+/*
+ * Purge entries in VTLB and VHPT
+ */
+void thash_purge_entries(struct kvm_vcpu *v, u64 va, u64 ps)
+{
+	if (vcpu_quick_region_check(v->arch.tc_regions, va))
+		vtlb_purge(v, va, ps);
+	vhpt_purge(v, va, ps);
+}
+
+void thash_purge_entries_remote(struct kvm_vcpu *v, u64 va, u64 ps)
+{
+	u64 old_va = va;
+	va = REGION_OFFSET(va);
+	if (vcpu_quick_region_check(v->arch.tc_regions, old_va))
+		vtlb_purge(v, va, ps);
+	vhpt_purge(v, va, ps);
+}
+
+u64 translate_phy_pte(u64 *pte, u64 itir, u64 va)
+{
+	u64 ps, ps_mask, paddr, maddr;
+	union pte_flags phy_pte;
+
+	ps = itir_ps(itir);
+	ps_mask = ~((1UL << ps) - 1);
+	phy_pte.val = *pte;
+	paddr = *pte;
+	paddr = ((paddr & _PAGE_PPN_MASK) & ps_mask) | (va & ~ps_mask);
+	maddr = kvm_lookup_mpa(paddr >> PAGE_SHIFT);
+	if (maddr & GPFN_IO_MASK) {
+		*pte |= VTLB_PTE_IO;
+		return -1;
+	}
+	maddr = ((maddr & _PAGE_PPN_MASK) & PAGE_MASK) |
+					(paddr & ~PAGE_MASK);
+	phy_pte.ppn = maddr >> ARCH_PAGE_SHIFT;
+	return phy_pte.val;
+}
+
+/*
+ * Purge overlap TCs and then insert the new entry to emulate itc ops.
+ *    Notes: Only TC entry can purge and insert.
+ *    1 indicates this is MMIO
+ */
+int thash_purge_and_insert(struct kvm_vcpu *v, u64 pte, u64 itir,
+						u64 ifa, int type)
+{
+	u64 ps;
+	u64 phy_pte;
+	union ia64_rr vrr, mrr;
+	int ret = 0;
+
+	ps = itir_ps(itir);
+	vrr.val = vcpu_get_rr(v, ifa);
+	mrr.val = ia64_get_rr(ifa);
+
+	phy_pte = translate_phy_pte(&pte, itir, ifa);
+
+	/* Ensure WB attribute if pte is related to a normal mem page,
+	 * which is required by vga acceleration since qemu maps shared
+	 * vram buffer with WB.
+	 */
+	if (!(pte & VTLB_PTE_IO) && ((pte & _PAGE_MA_MASK) != _PAGE_MA_NAT)) {
+		pte &= ~_PAGE_MA_MASK;
+		phy_pte &= ~_PAGE_MA_MASK;
+	}
+
+	if (pte & VTLB_PTE_IO)
+		ret = 1;
+
+	vtlb_purge(v, ifa, ps);
+	vhpt_purge(v, ifa, ps);
+
+	if (ps == mrr.ps) {
+		if (!(pte&VTLB_PTE_IO)) {
+			vhpt_insert(phy_pte, itir, ifa, pte);
+		} else {
+			vtlb_insert(v, pte, itir, ifa);
+			vcpu_quick_region_set(VMX(v, tc_regions), ifa);
+		}
+	} else if (ps > mrr.ps) {
+		vtlb_insert(v, pte, itir, ifa);
+		vcpu_quick_region_set(VMX(v, tc_regions), ifa);
+		if (!(pte&VTLB_PTE_IO))
+			vhpt_insert(phy_pte, itir, ifa, pte);
+	} else {
+		u64 psr;
+		phy_pte  &= ~PAGE_FLAGS_RV_MASK;
+		psr = ia64_clear_ic();
+		ia64_itc(type, ifa, phy_pte, ps);
+		ia64_set_psr(psr);
+	}
+	if (!(pte&VTLB_PTE_IO))
+		mark_pages_dirty(v, pte, ps);
+
+	return ret;
+}
+
+/*
+ * Purge all TCs or VHPT entries including those in Hash table.
+ *
+ */
+
+void thash_purge_all(struct kvm_vcpu *v)
+{
+	int i;
+	struct thash_data *head;
+	struct thash_cb  *vtlb, *vhpt;
+	vtlb = &v->arch.vtlb;
+	vhpt = &v->arch.vhpt;
+
+	for (i = 0; i < 8; i++)
+		VMX(v, psbits[i]) = 0;
+
+	head = vtlb->hash;
+	for (i = 0; i < vtlb->num; i++) {
+		head->page_flags = 0;
+		head->etag = INVALID_TI_TAG;
+		head->itir = 0;
+		head->next = 0;
+		head++;
+	};
+
+	head = vhpt->hash;
+	for (i = 0; i < vhpt->num; i++) {
+		head->page_flags = 0;
+		head->etag = INVALID_TI_TAG;
+		head->itir = 0;
+		head->next = 0;
+		head++;
+	};
+
+	local_flush_tlb_all();
+}
+
+
+/*
+ * Lookup the hash table and its collision chain to find an entry
+ * covering this address rid:va or the entry.
+ *
+ * INPUT:
+ *  in: TLB format for both VHPT & TLB.
+ */
+
+struct thash_data *vtlb_lookup(struct kvm_vcpu *v, u64 va, int is_data)
+{
+	struct thash_data  *cch;
+	u64    psbits, ps, tag;
+	union ia64_rr vrr;
+
+	struct thash_cb *hcb = &v->arch.vtlb;
+
+	cch = __vtr_lookup(v, va, is_data);;
+	if (cch)
+		return cch;
+
+	if (vcpu_quick_region_check(v->arch.tc_regions, va) == 0)
+		return NULL;
+
+	psbits = VMX(v, psbits[(va >> 61)]);
+	vrr.val = vcpu_get_rr(v, va);
+	while (psbits) {
+		ps = __ffs(psbits);
+		psbits &= ~(1UL << ps);
+		vrr.ps = ps;
+		cch = vsa_thash(hcb->pta, va, vrr.val, &tag);
+		if (cch->etag == tag && cch->ps == ps)
+			return cch;
+	}
+
+	return NULL;
+}
+
+
+/*
+ * Initialize internal control data before service.
+ */
+void thash_init(struct thash_cb *hcb, u64 sz)
+{
+	int i;
+	struct thash_data *head;
+
+	hcb->pta.val = (unsigned long)hcb->hash;
+	hcb->pta.vf = 1;
+	hcb->pta.ve = 1;
+	hcb->pta.size = sz;
+	head = hcb->hash;
+	for (i = 0; i < hcb->num; i++) {
+		head->page_flags = 0;
+		head->itir = 0;
+		head->etag = INVALID_TI_TAG;
+		head->next = 0;
+		head++;
+	}
+}
+
+u64 kvm_lookup_mpa(u64 gpfn)
+{
+	u64 *base = (u64 *) KVM_P2M_BASE;
+	return *(base + gpfn);
+}
+
+u64 kvm_gpa_to_mpa(u64 gpa)
+{
+	u64 pte = kvm_lookup_mpa(gpa >> PAGE_SHIFT);
+	return (pte >> PAGE_SHIFT << PAGE_SHIFT) | (gpa & ~PAGE_MASK);
+}
+
+
+/*
+ * Fetch guest bundle code.
+ * INPUT:
+ *  gip: guest ip
+ *  pbundle: used to return fetched bundle.
+ */
+int fetch_code(struct kvm_vcpu *vcpu, u64 gip, IA64_BUNDLE *pbundle)
+{
+	u64     gpip = 0;   /* guest physical IP*/
+	u64     *vpa;
+	struct thash_data    *tlb;
+	u64     maddr;
+
+	if (!(VCPU(vcpu, vpsr) & IA64_PSR_IT)) {
+		/* I-side physical mode */
+		gpip = gip;
+	} else {
+		tlb = vtlb_lookup(vcpu, gip, I_TLB);
+		if (tlb)
+			gpip = (tlb->ppn >> (tlb->ps - 12) << tlb->ps) |
+				(gip & (PSIZE(tlb->ps) - 1));
+	}
+	if (gpip) {
+		maddr = kvm_gpa_to_mpa(gpip);
+	} else {
+		tlb = vhpt_lookup(gip);
+		if (tlb == NULL) {
+			ia64_ptcl(gip, ARCH_PAGE_SHIFT << 2);
+			return IA64_FAULT;
+		}
+		maddr = (tlb->ppn >> (tlb->ps - 12) << tlb->ps)
+					| (gip & (PSIZE(tlb->ps) - 1));
+	}
+	vpa = (u64 *)__kvm_va(maddr);
+
+	pbundle->i64[0] = *vpa++;
+	pbundle->i64[1] = *vpa;
+
+	return IA64_NO_FAULT;
+}
+
+
+void kvm_init_vhpt(struct kvm_vcpu *v)
+{
+	v->arch.vhpt.num = VHPT_NUM_ENTRIES;
+	thash_init(&v->arch.vhpt, VHPT_SHIFT);
+	ia64_set_pta(v->arch.vhpt.pta.val);
+	/*Enable VHPT here?*/
+}
+
+void kvm_init_vtlb(struct kvm_vcpu *v)
+{
+	v->arch.vtlb.num = VTLB_NUM_ENTRIES;
+	thash_init(&v->arch.vtlb, VTLB_SHIFT);
+}
diff --git a/trunk/arch/ia64/mm/init.c b/trunk/arch/ia64/mm/init.c
index 5c1de53c8c1c..fc6c6636ffda 100644
--- a/trunk/arch/ia64/mm/init.c
+++ b/trunk/arch/ia64/mm/init.c
@@ -682,15 +682,6 @@ mem_init (void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-void online_page(struct page *page)
-{
-	ClearPageReserved(page);
-	init_page_count(page);
-	__free_page(page);
-	totalram_pages++;
-	num_physpages++;
-}
-
 int arch_add_memory(int nid, u64 start, u64 size)
 {
 	pg_data_t *pgdat;
diff --git a/trunk/arch/ia64/sn/kernel/sn2/sn2_smp.c b/trunk/arch/ia64/sn/kernel/sn2/sn2_smp.c
index dfc6bf1c7b41..49d3120415eb 100644
--- a/trunk/arch/ia64/sn/kernel/sn2/sn2_smp.c
+++ b/trunk/arch/ia64/sn/kernel/sn2/sn2_smp.c
@@ -550,11 +550,12 @@ static int __init sn2_ptc_init(void)
 	if (!ia64_platform_is("sn2"))
 		return 0;
 
-	if (!(proc_sn2_ptc = create_proc_entry(PTC_BASENAME, 0444, NULL))) {
+	proc_sn2_ptc = proc_create(PTC_BASENAME, 0444,
+				   NULL, &proc_sn2_ptc_operations);
+	if (!&proc_sn2_ptc_operations) {
 		printk(KERN_ERR "unable to create %s proc entry", PTC_BASENAME);
 		return -EINVAL;
 	}
-	proc_sn2_ptc->proc_fops = &proc_sn2_ptc_operations;
 	spin_lock_init(&sn2_global_ptc_lock);
 	return 0;
 }
diff --git a/trunk/arch/ia64/sn/kernel/sn2/sn_proc_fs.c b/trunk/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
index 62b3e9a496ac..2526e5c783a4 100644
--- a/trunk/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
+++ b/trunk/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
@@ -139,30 +139,21 @@ static const struct file_operations proc_sn_topo_fops = {
 void register_sn_procfs(void)
 {
 	static struct proc_dir_entry *sgi_proc_dir = NULL;
-	struct proc_dir_entry *pde;
 
 	BUG_ON(sgi_proc_dir != NULL);
 	if (!(sgi_proc_dir = proc_mkdir("sgi_sn", NULL)))
 		return;
 
-	pde = create_proc_entry("partition_id", 0444, sgi_proc_dir);
-	if (pde)
-		pde->proc_fops = &proc_partition_id_fops;
-	pde = create_proc_entry("system_serial_number", 0444, sgi_proc_dir);
-	if (pde)
-		pde->proc_fops = &proc_system_sn_fops;
-	pde = create_proc_entry("licenseID", 0444, sgi_proc_dir);
-	if (pde)
-		pde->proc_fops = &proc_license_id_fops;
-	pde = create_proc_entry("sn_force_interrupt", 0644, sgi_proc_dir);
-	if (pde)
-		pde->proc_fops = &proc_sn_force_intr_fops;
-	pde = create_proc_entry("coherence_id", 0444, sgi_proc_dir);
-	if (pde)
-		pde->proc_fops = &proc_coherence_id_fops;
-	pde = create_proc_entry("sn_topology", 0444, sgi_proc_dir);
-	if (pde)
-		pde->proc_fops = &proc_sn_topo_fops;
+	proc_create("partition_id", 0444, sgi_proc_dir,
+		    &proc_partition_id_fops);
+	proc_create("system_serial_number", 0444, sgi_proc_dir,
+		    &proc_system_sn_fops);
+	proc_create("licenseID", 0444, sgi_proc_dir, &proc_license_id_fops);
+	proc_create("sn_force_interrupt", 0644, sgi_proc_dir,
+		    &proc_sn_force_intr_fops);
+	proc_create("coherence_id", 0444, sgi_proc_dir,
+		    &proc_coherence_id_fops);
+	proc_create("sn_topology", 0444, sgi_proc_dir, &proc_sn_topo_fops);
 }
 
 #endif /* CONFIG_PROC_FS */
diff --git a/trunk/arch/ia64/sn/pci/pci_dma.c b/trunk/arch/ia64/sn/pci/pci_dma.c
index 18b94b792d54..52175af299a0 100644
--- a/trunk/arch/ia64/sn/pci/pci_dma.c
+++ b/trunk/arch/ia64/sn/pci/pci_dma.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/dma-attrs.h>
 #include <asm/dma.h>
 #include <asm/sn/intr.h>
 #include <asm/sn/pcibus_provider_defs.h>
@@ -149,11 +150,12 @@ void sn_dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
 EXPORT_SYMBOL(sn_dma_free_coherent);
 
 /**
- * sn_dma_map_single - map a single page for DMA
+ * sn_dma_map_single_attrs - map a single page for DMA
  * @dev: device to map for
  * @cpu_addr: kernel virtual address of the region to map
  * @size: size of the region
  * @direction: DMA direction
+ * @attrs: optional dma attributes
  *
  * Map the region pointed to by @cpu_addr for DMA and return the
  * DMA address.
@@ -163,42 +165,59 @@ EXPORT_SYMBOL(sn_dma_free_coherent);
  * no way of saving the dmamap handle from the alloc to later free
  * (which is pretty much unacceptable).
  *
+ * mappings with the DMA_ATTR_WRITE_BARRIER get mapped with
+ * dma_map_consistent() so that writes force a flush of pending DMA.
+ * (See "SGI Altix Architecture Considerations for Linux Device Drivers",
+ * Document Number: 007-4763-001)
+ *
  * TODO: simplify our interface;
  *       figure out how to save dmamap handle so can use two step.
  */
-dma_addr_t sn_dma_map_single(struct device *dev, void *cpu_addr, size_t size,
-			     int direction)
+dma_addr_t sn_dma_map_single_attrs(struct device *dev, void *cpu_addr,
+				   size_t size, int direction,
+				   struct dma_attrs *attrs)
 {
 	dma_addr_t dma_addr;
 	unsigned long phys_addr;
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
+	int dmabarr;
+
+	dmabarr = dma_get_attr(DMA_ATTR_WRITE_BARRIER, attrs);
 
 	BUG_ON(dev->bus != &pci_bus_type);
 
 	phys_addr = __pa(cpu_addr);
-	dma_addr = provider->dma_map(pdev, phys_addr, size, SN_DMA_ADDR_PHYS);
+	if (dmabarr)
+		dma_addr = provider->dma_map_consistent(pdev, phys_addr,
+							size, SN_DMA_ADDR_PHYS);
+	else
+		dma_addr = provider->dma_map(pdev, phys_addr, size,
+					     SN_DMA_ADDR_PHYS);
+
 	if (!dma_addr) {
 		printk(KERN_ERR "%s: out of ATEs\n", __func__);
 		return 0;
 	}
 	return dma_addr;
 }
-EXPORT_SYMBOL(sn_dma_map_single);
+EXPORT_SYMBOL(sn_dma_map_single_attrs);
 
 /**
- * sn_dma_unmap_single - unamp a DMA mapped page
+ * sn_dma_unmap_single_attrs - unamp a DMA mapped page
  * @dev: device to sync
  * @dma_addr: DMA address to sync
  * @size: size of region
  * @direction: DMA direction
+ * @attrs: optional dma attributes
  *
  * This routine is supposed to sync the DMA region specified
  * by @dma_handle into the coherence domain.  On SN, we're always cache
  * coherent, so we just need to free any ATEs associated with this mapping.
  */
-void sn_dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-			 int direction)
+void sn_dma_unmap_single_attrs(struct device *dev, dma_addr_t dma_addr,
+			       size_t size, int direction,
+			       struct dma_attrs *attrs)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
@@ -207,19 +226,21 @@ void sn_dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
 
 	provider->dma_unmap(pdev, dma_addr, direction);
 }
-EXPORT_SYMBOL(sn_dma_unmap_single);
+EXPORT_SYMBOL(sn_dma_unmap_single_attrs);
 
 /**
- * sn_dma_unmap_sg - unmap a DMA scatterlist
+ * sn_dma_unmap_sg_attrs - unmap a DMA scatterlist
  * @dev: device to unmap
  * @sg: scatterlist to unmap
  * @nhwentries: number of scatterlist entries
  * @direction: DMA direction
+ * @attrs: optional dma attributes
  *
  * Unmap a set of streaming mode DMA translations.
  */
-void sn_dma_unmap_sg(struct device *dev, struct scatterlist *sgl,
-		     int nhwentries, int direction)
+void sn_dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl,
+			   int nhwentries, int direction,
+			   struct dma_attrs *attrs)
 {
 	int i;
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -234,25 +255,34 @@ void sn_dma_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		sg->dma_length = 0;
 	}
 }
-EXPORT_SYMBOL(sn_dma_unmap_sg);
+EXPORT_SYMBOL(sn_dma_unmap_sg_attrs);
 
 /**
- * sn_dma_map_sg - map a scatterlist for DMA
+ * sn_dma_map_sg_attrs - map a scatterlist for DMA
  * @dev: device to map for
  * @sg: scatterlist to map
  * @nhwentries: number of entries
  * @direction: direction of the DMA transaction
+ * @attrs: optional dma attributes
+ *
+ * mappings with the DMA_ATTR_WRITE_BARRIER get mapped with
+ * dma_map_consistent() so that writes force a flush of pending DMA.
+ * (See "SGI Altix Architecture Considerations for Linux Device Drivers",
+ * Document Number: 007-4763-001)
  *
  * Maps each entry of @sg for DMA.
  */
-int sn_dma_map_sg(struct device *dev, struct scatterlist *sgl, int nhwentries,
-		  int direction)
+int sn_dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
+			int nhwentries, int direction, struct dma_attrs *attrs)
 {
 	unsigned long phys_addr;
 	struct scatterlist *saved_sg = sgl, *sg;
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
 	int i;
+	int dmabarr;
+
+	dmabarr = dma_get_attr(DMA_ATTR_WRITE_BARRIER, attrs);
 
 	BUG_ON(dev->bus != &pci_bus_type);
 
@@ -260,11 +290,19 @@ int sn_dma_map_sg(struct device *dev, struct scatterlist *sgl, int nhwentries,
 	 * Setup a DMA address for each entry in the scatterlist.
 	 */
 	for_each_sg(sgl, sg, nhwentries, i) {
+		dma_addr_t dma_addr;
 		phys_addr = SG_ENT_PHYS_ADDRESS(sg);
-		sg->dma_address = provider->dma_map(pdev,
-						    phys_addr, sg->length,
-						    SN_DMA_ADDR_PHYS);
+		if (dmabarr)
+			dma_addr = provider->dma_map_consistent(pdev,
+								phys_addr,
+								sg->length,
+								SN_DMA_ADDR_PHYS);
+		else
+			dma_addr = provider->dma_map(pdev, phys_addr,
+						     sg->length,
+						     SN_DMA_ADDR_PHYS);
 
+		sg->dma_address = dma_addr;
 		if (!sg->dma_address) {
 			printk(KERN_ERR "%s: out of ATEs\n", __func__);
 
@@ -272,7 +310,8 @@ int sn_dma_map_sg(struct device *dev, struct scatterlist *sgl, int nhwentries,
 			 * Free any successfully allocated entries.
 			 */
 			if (i > 0)
-				sn_dma_unmap_sg(dev, saved_sg, i, direction);
+				sn_dma_unmap_sg_attrs(dev, saved_sg, i,
+						      direction, attrs);
 			return 0;
 		}
 
@@ -281,7 +320,7 @@ int sn_dma_map_sg(struct device *dev, struct scatterlist *sgl, int nhwentries,
 
 	return nhwentries;
 }
-EXPORT_SYMBOL(sn_dma_map_sg);
+EXPORT_SYMBOL(sn_dma_map_sg_attrs);
 
 void sn_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
 				size_t size, int direction)
diff --git a/trunk/arch/m68k/kernel/asm-offsets.c b/trunk/arch/m68k/kernel/asm-offsets.c
index 246a8820c223..b1f012f6c493 100644
--- a/trunk/arch/m68k/kernel/asm-offsets.c
+++ b/trunk/arch/m68k/kernel/asm-offsets.c
@@ -11,14 +11,12 @@
 #include <linux/stddef.h>
 #include <linux/sched.h>
 #include <linux/kernel_stat.h>
+#include <linux/kbuild.h>
 #include <asm/bootinfo.h>
 #include <asm/irq.h>
 #include <asm/amigahw.h>
 #include <linux/font.h>
 
-#define DEFINE(sym, val) \
-	asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
 int main(void)
 {
 	/* offsets into the task struct */
diff --git a/trunk/arch/m68k/kernel/ints.c b/trunk/arch/m68k/kernel/ints.c
index 2b412454cb41..ded7dd2f67b2 100644
--- a/trunk/arch/m68k/kernel/ints.c
+++ b/trunk/arch/m68k/kernel/ints.c
@@ -186,7 +186,7 @@ int setup_irq(unsigned int irq, struct irq_node *node)
 
 	if (irq >= NR_IRQS || !(contr = irq_controller[irq])) {
 		printk("%s: Incorrect IRQ %d from %s\n",
-		       __FUNCTION__, irq, node->devname);
+		       __func__, irq, node->devname);
 		return -ENXIO;
 	}
 
@@ -249,7 +249,7 @@ void free_irq(unsigned int irq, void *dev_id)
 	unsigned long flags;
 
 	if (irq >= NR_IRQS || !(contr = irq_controller[irq])) {
-		printk("%s: Incorrect IRQ %d\n", __FUNCTION__, irq);
+		printk("%s: Incorrect IRQ %d\n", __func__, irq);
 		return;
 	}
 
@@ -267,7 +267,7 @@ void free_irq(unsigned int irq, void *dev_id)
 		node->handler = NULL;
 	} else
 		printk("%s: Removing probably wrong IRQ %d\n",
-		       __FUNCTION__, irq);
+		       __func__, irq);
 
 	if (!irq_list[irq]) {
 		if (contr->shutdown)
@@ -288,7 +288,7 @@ void enable_irq(unsigned int irq)
 
 	if (irq >= NR_IRQS || !(contr = irq_controller[irq])) {
 		printk("%s: Incorrect IRQ %d\n",
-		       __FUNCTION__, irq);
+		       __func__, irq);
 		return;
 	}
 
@@ -312,7 +312,7 @@ void disable_irq(unsigned int irq)
 
 	if (irq >= NR_IRQS || !(contr = irq_controller[irq])) {
 		printk("%s: Incorrect IRQ %d\n",
-		       __FUNCTION__, irq);
+		       __func__, irq);
 		return;
 	}
 
diff --git a/trunk/arch/m68k/mac/iop.c b/trunk/arch/m68k/mac/iop.c
index 5b2799eb96a6..326fb9978094 100644
--- a/trunk/arch/m68k/mac/iop.c
+++ b/trunk/arch/m68k/mac/iop.c
@@ -109,7 +109,6 @@
 #include <linux/mm.h>
 #include <linux/delay.h>
 #include <linux/init.h>
-#include <linux/proc_fs.h>
 #include <linux/interrupt.h>
 
 #include <asm/bootinfo.h>
@@ -124,10 +123,6 @@
 
 int iop_scc_present,iop_ism_present;
 
-#ifdef CONFIG_PROC_FS
-static int iop_get_proc_info(char *, char **, off_t, int);
-#endif /* CONFIG_PROC_FS */
-
 /* structure for tracking channel listeners */
 
 struct listener {
@@ -299,12 +294,6 @@ void __init iop_init(void)
 		iop_listeners[IOP_NUM_ISM][i].devname = NULL;
 		iop_listeners[IOP_NUM_ISM][i].handler = NULL;
 	}
-
-#if 0	/* Crashing in 2.4 now, not yet sure why.   --jmt */
-#ifdef CONFIG_PROC_FS
-	create_proc_info_entry("mac_iop", 0, &proc_root, iop_get_proc_info);
-#endif
-#endif
 }
 
 /*
@@ -637,77 +626,3 @@ irqreturn_t iop_ism_irq(int irq, void *dev_id)
 	}
 	return IRQ_HANDLED;
 }
-
-#ifdef CONFIG_PROC_FS
-
-char *iop_chan_state(int state)
-{
-	switch(state) {
-		case IOP_MSG_IDLE	: return "idle      ";
-		case IOP_MSG_NEW	: return "new       ";
-		case IOP_MSG_RCVD	: return "received  ";
-		case IOP_MSG_COMPLETE	: return "completed ";
-		default			: return "unknown   ";
-	}
-}
-
-int iop_dump_one_iop(char *buf, int iop_num, char *iop_name)
-{
-	int i,len = 0;
-	volatile struct mac_iop *iop = iop_base[iop_num];
-
-	len += sprintf(buf+len, "%s IOP channel states:\n\n", iop_name);
-	len += sprintf(buf+len, "##  send_state  recv_state  device\n");
-	len += sprintf(buf+len, "------------------------------------------------\n");
-	for (i = 0 ; i < NUM_IOP_CHAN ; i++) {
-		len += sprintf(buf+len, "%2d  %10s  %10s  %s\n", i,
-			iop_chan_state(iop_readb(iop, IOP_ADDR_SEND_STATE+i)),
-			iop_chan_state(iop_readb(iop, IOP_ADDR_RECV_STATE+i)),
-			iop_listeners[iop_num][i].handler?
-				      iop_listeners[iop_num][i].devname : "");
-
-	}
-	len += sprintf(buf+len, "\n");
-	return len;
-}
-
-static int iop_get_proc_info(char *buf, char **start, off_t pos, int count)
-{
-	int len, cnt;
-
-	cnt = 0;
-	len =  sprintf(buf, "IOPs detected:\n\n");
-
-	if (iop_scc_present) {
-		len += sprintf(buf+len, "SCC IOP (%p): status %02X\n",
-				iop_base[IOP_NUM_SCC],
-				(uint) iop_base[IOP_NUM_SCC]->status_ctrl);
-	}
-	if (iop_ism_present) {
-		len += sprintf(buf+len, "ISM IOP (%p): status %02X\n\n",
-				iop_base[IOP_NUM_ISM],
-				(uint) iop_base[IOP_NUM_ISM]->status_ctrl);
-	}
-
-	if (iop_scc_present) {
-		len += iop_dump_one_iop(buf+len, IOP_NUM_SCC, "SCC");
-
-	}
-
-	if (iop_ism_present) {
-		len += iop_dump_one_iop(buf+len, IOP_NUM_ISM, "ISM");
-
-	}
-
-	if (len >= pos) {
-		if (!*start) {
-			*start = buf + pos;
-			cnt = len - pos;
-		} else {
-			cnt += len;
-		}
-	}
-	return (count > cnt) ? cnt : count;
-}
-
-#endif /* CONFIG_PROC_FS */
diff --git a/trunk/arch/m68k/mac/oss.c b/trunk/arch/m68k/mac/oss.c
index 50603d3dce84..3c943d2ec570 100644
--- a/trunk/arch/m68k/mac/oss.c
+++ b/trunk/arch/m68k/mac/oss.c
@@ -190,7 +190,7 @@ void oss_irq_enable(int irq) {
 			break;
 #ifdef DEBUG_IRQUSE
 		default:
-			printk("%s unknown irq %d\n",__FUNCTION__, irq);
+			printk("%s unknown irq %d\n", __func__, irq);
 			break;
 #endif
 	}
@@ -230,7 +230,7 @@ void oss_irq_disable(int irq) {
 			break;
 #ifdef DEBUG_IRQUSE
 		default:
-			printk("%s unknown irq %d\n", __FUNCTION__, irq);
+			printk("%s unknown irq %d\n", __func__, irq);
 			break;
 #endif
 	}
diff --git a/trunk/arch/m68k/mm/init.c b/trunk/arch/m68k/mm/init.c
index f42caa79e4e8..a2bb01f59642 100644
--- a/trunk/arch/m68k/mm/init.c
+++ b/trunk/arch/m68k/mm/init.c
@@ -79,7 +79,6 @@ void show_mem(void)
 
 	printk("\nMem-info:\n");
 	show_free_areas();
-	printk("Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
 	for_each_online_pgdat(pgdat) {
 		for (i = 0; i < pgdat->node_spanned_pages; i++) {
 			struct page *page = pgdat->node_mem_map + i;
diff --git a/trunk/arch/m68k/q40/q40ints.c b/trunk/arch/m68k/q40/q40ints.c
index 46161cef08b9..9f0e3d59bf92 100644
--- a/trunk/arch/m68k/q40/q40ints.c
+++ b/trunk/arch/m68k/q40/q40ints.c
@@ -47,7 +47,7 @@ static int q40_irq_startup(unsigned int irq)
 	switch (irq) {
 	case 1: case 2: case 8: case 9:
 	case 11: case 12: case 13:
-		printk("%s: ISA IRQ %d not implemented by HW\n", __FUNCTION__, irq);
+		printk("%s: ISA IRQ %d not implemented by HW\n", __func__, irq);
 		return -ENXIO;
 	}
 	return 0;
diff --git a/trunk/arch/m68knommu/kernel/asm-offsets.c b/trunk/arch/m68knommu/kernel/asm-offsets.c
index d97b89bae53c..fd0c685a7f11 100644
--- a/trunk/arch/m68knommu/kernel/asm-offsets.c
+++ b/trunk/arch/m68knommu/kernel/asm-offsets.c
@@ -13,15 +13,11 @@
 #include <linux/kernel_stat.h>
 #include <linux/ptrace.h>
 #include <linux/hardirq.h>
+#include <linux/kbuild.h>
 #include <asm/bootinfo.h>
 #include <asm/irq.h>
 #include <asm/thread_info.h>
 
-#define DEFINE(sym, val) \
-        asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
-
 int main(void)
 {
 	/* offsets into the task struct */
diff --git a/trunk/arch/mips/Kconfig b/trunk/arch/mips/Kconfig
index 8724ed3298d3..e5a7c5d96364 100644
--- a/trunk/arch/mips/Kconfig
+++ b/trunk/arch/mips/Kconfig
@@ -81,7 +81,9 @@ config MIPS_COBALT
 config MACH_DECSTATION
 	bool "DECstations"
 	select BOOT_ELF32
+	select CEVT_DS1287
 	select CEVT_R4K
+	select CSRC_IOASIC
 	select CSRC_R4K
 	select CPU_DADDI_WORKAROUNDS if 64BIT
 	select CPU_R4000_WORKAROUNDS if 64BIT
@@ -221,6 +223,7 @@ config MIPS_MALTA
 	select DMA_NONCOHERENT
 	select GENERIC_ISA_DMA
 	select IRQ_CPU
+	select IRQ_GIC
 	select HW_HAS_PCI
 	select I8253
 	select I8259
@@ -309,12 +312,12 @@ config MACH_VR41XX
 	select GENERIC_HARDIRQS_NO__DO_IRQ
 
 config PNX8550_JBS
-	bool "Philips PNX8550 based JBS board"
+	bool "NXP PNX8550 based JBS board"
 	select PNX8550
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 
 config PNX8550_STB810
-	bool "Philips PNX8550 based STB810 board"
+	bool "NXP PNX8550 based STB810 board"
 	select PNX8550
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 
@@ -612,6 +615,7 @@ config TOSHIBA_JMR3927
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select GENERIC_HARDIRQS_NO__DO_IRQ
+	select GPIO_TXX9
 
 config TOSHIBA_RBTX4927
 	bool "Toshiba RBTX49[23]7 board"
@@ -653,7 +657,7 @@ config TOSHIBA_RBTX4938
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_KGDB
 	select GENERIC_HARDIRQS_NO__DO_IRQ
-	select GENERIC_GPIO
+	select GPIO_TXX9
 	help
 	  This Toshiba board is based on the TX4938 processor. Say Y here to
 	  support this machine type
@@ -767,6 +771,9 @@ config BOOT_RAW
 config CEVT_BCM1480
 	bool
 
+config CEVT_DS1287
+	bool
+
 config CEVT_GT641XX
 	bool
 
@@ -782,12 +789,20 @@ config CEVT_TXX9
 config CSRC_BCM1480
 	bool
 
+config CSRC_IOASIC
+	bool
+
 config CSRC_R4K
 	bool
 
 config CSRC_SB1250
 	bool
 
+config GPIO_TXX9
+	select GENERIC_GPIO
+	select HAVE_GPIO_LIB
+	bool
+
 config CFE
 	bool
 
@@ -840,6 +855,9 @@ config MIPS_NILE4
 config MIPS_DISABLE_OBSOLETE_IDE
 	bool
 
+config SYNC_R4K
+	bool
+
 config NO_IOPORT
 	def_bool n
 
@@ -909,6 +927,9 @@ config IRQ_TXX9
 config IRQ_GT641XX
 	bool
 
+config IRQ_GIC
+	bool
+
 config MIPS_BOARDS_GEN
 	bool
 
@@ -1811,6 +1832,17 @@ config NR_CPUS
 	  performance should round up your number of processors to the next
 	  power of two.
 
+config MIPS_CMP
+	bool "MIPS CMP framework support"
+	depends on SMP
+	select SYNC_R4K
+	select SYS_SUPPORTS_SCHED_SMT
+	select WEAK_ORDERING
+	default n
+	help
+	  This is a placeholder option for the GCMP work. It will need to
+	  be handled differently...
+
 source "kernel/time/Kconfig"
 
 #
diff --git a/trunk/arch/mips/Kconfig.debug b/trunk/arch/mips/Kconfig.debug
index fd7124c1b75a..f18cf92650e3 100644
--- a/trunk/arch/mips/Kconfig.debug
+++ b/trunk/arch/mips/Kconfig.debug
@@ -73,14 +73,4 @@ config RUNTIME_DEBUG
 	  include/asm-mips/debug.h for debuging macros.
 	  If unsure, say N.
 
-config MIPS_UNCACHED
-	bool "Run uncached"
-	depends on DEBUG_KERNEL && !SMP && !SGI_IP27
-	help
-	  If you say Y here there kernel will disable all CPU caches.  This will
-	  reduce the system's performance dramatically but can help finding
-	  otherwise hard to track bugs.  It can also useful if you're doing
-	  hardware debugging with a logic analyzer and need to see all traffic
-	  on the bus.
-
 endmenu
diff --git a/trunk/arch/mips/Makefile b/trunk/arch/mips/Makefile
index 1c62381f5c23..69648d01acc0 100644
--- a/trunk/arch/mips/Makefile
+++ b/trunk/arch/mips/Makefile
@@ -410,21 +410,21 @@ load-$(CONFIG_CASIO_E55)	+= 0xffffffff80004000
 load-$(CONFIG_TANBAC_TB022X)	+= 0xffffffff80000000
 
 #
-# Common Philips PNX8550
+# Common NXP PNX8550
 #
-core-$(CONFIG_SOC_PNX8550)	+= arch/mips/philips/pnx8550/common/
+core-$(CONFIG_SOC_PNX8550)	+= arch/mips/nxp/pnx8550/common/
 cflags-$(CONFIG_SOC_PNX8550)	+= -Iinclude/asm-mips/mach-pnx8550
 
 #
-# Philips PNX8550 JBS board
+# NXP PNX8550 JBS board
 #
-libs-$(CONFIG_PNX8550_JBS)	+= arch/mips/philips/pnx8550/jbs/
+libs-$(CONFIG_PNX8550_JBS)	+= arch/mips/nxp/pnx8550/jbs/
 #cflags-$(CONFIG_PNX8550_JBS)	+= -Iinclude/asm-mips/mach-pnx8550
 load-$(CONFIG_PNX8550_JBS)	+= 0xffffffff80060000
 
-# Philips PNX8550 STB810 board
+# NXP PNX8550 STB810 board
 #
-libs-$(CONFIG_PNX8550_STB810)	+= arch/mips/philips/pnx8550/stb810/
+libs-$(CONFIG_PNX8550_STB810)	+= arch/mips/nxp/pnx8550/stb810/
 load-$(CONFIG_PNX8550_STB810)	+= 0xffffffff80060000
 
 # NEC EMMA2RH boards
diff --git a/trunk/arch/mips/au1000/common/cputable.c b/trunk/arch/mips/au1000/common/cputable.c
index 5c0d35d6e22a..8c93a05d7382 100644
--- a/trunk/arch/mips/au1000/common/cputable.c
+++ b/trunk/arch/mips/au1000/common/cputable.c
@@ -11,10 +11,7 @@
  *  as published by the Free Software Foundation; either version
  *  2 of the License, or (at your option) any later version.
  */
-#include <linux/string.h>
-#include <linux/sched.h>
-#include <linux/threads.h>
-#include <linux/init.h>
+
 #include <asm/mach-au1x00/au1000.h>
 
 struct cpu_spec* cur_cpu_spec[NR_CPUS];
diff --git a/trunk/arch/mips/au1000/common/dbdma.c b/trunk/arch/mips/au1000/common/dbdma.c
index 57f17b41098d..53377dfc0640 100644
--- a/trunk/arch/mips/au1000/common/dbdma.c
+++ b/trunk/arch/mips/au1000/common/dbdma.c
@@ -31,18 +31,12 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
-#include <linux/string.h>
-#include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-au1x00/au1xxx_dbdma.h>
-#include <asm/system.h>
-
 
 #if defined(CONFIG_SOC_AU1550) || defined(CONFIG_SOC_AU1200)
 
diff --git a/trunk/arch/mips/au1000/common/dbg_io.c b/trunk/arch/mips/au1000/common/dbg_io.c
index 79e0b0a51ace..eae1bb2ca26e 100644
--- a/trunk/arch/mips/au1000/common/dbg_io.c
+++ b/trunk/arch/mips/au1000/common/dbg_io.c
@@ -1,5 +1,4 @@
 
-#include <asm/io.h>
 #include <asm/mach-au1x00/au1000.h>
 
 #ifdef CONFIG_KGDB
@@ -55,8 +54,7 @@ typedef         unsigned int  uint32;
 #define UART16550_READ(y)    (au_readl(DEBUG_BASE + y) & 0xff)
 #define UART16550_WRITE(y, z) (au_writel(z&0xff, DEBUG_BASE + y))
 
-extern unsigned long get_au1x00_uart_baud_base(void);
-extern unsigned long cal_r4koff(void);
+extern unsigned long calc_clock(void);
 
 void debugInit(uint32 baud, uint8 data, uint8 parity, uint8 stop)
 {
@@ -64,7 +62,7 @@ void debugInit(uint32 baud, uint8 data, uint8 parity, uint8 stop)
 	if (UART16550_READ(UART_MOD_CNTRL) != 0x3) {
 		UART16550_WRITE(UART_MOD_CNTRL, 3);
 	}
-	cal_r4koff();
+	calc_clock();
 
 	/* disable interrupts */
 	UART16550_WRITE(UART_IER, 0);
diff --git a/trunk/arch/mips/au1000/common/dma.c b/trunk/arch/mips/au1000/common/dma.c
index c78260d4e837..95f69ea146e9 100644
--- a/trunk/arch/mips/au1000/common/dma.c
+++ b/trunk/arch/mips/au1000/common/dma.c
@@ -33,12 +33,9 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
-#include <linux/sched.h>
 #include <linux/spinlock.h>
-#include <linux/string.h>
-#include <linux/delay.h>
 #include <linux/interrupt.h>
-#include <asm/system.h>
+
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-au1x00/au1000_dma.h>
 
diff --git a/trunk/arch/mips/au1000/common/gpio.c b/trunk/arch/mips/au1000/common/gpio.c
index 0b658f1db4ce..525452589971 100644
--- a/trunk/arch/mips/au1000/common/gpio.c
+++ b/trunk/arch/mips/au1000/common/gpio.c
@@ -27,13 +27,8 @@
  * 	others have a second one : GPIO2
  */
 
-#include <linux/init.h>
-#include <linux/io.h>
-#include <linux/types.h>
 #include <linux/module.h>
 
-#include <asm/addrspace.h>
-
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/gpio.h>
 
diff --git a/trunk/arch/mips/au1000/common/irq.c b/trunk/arch/mips/au1000/common/irq.c
index 3c7714f057ac..f0626992fd75 100644
--- a/trunk/arch/mips/au1000/common/irq.c
+++ b/trunk/arch/mips/au1000/common/irq.c
@@ -1,7 +1,6 @@
 /*
- * Copyright 2001 MontaVista Software Inc.
- * Author: MontaVista Software, Inc.
- *		ppopov@mvista.com or source@mvista.com
+ * Copyright 2001, 2007-2008 MontaVista Software Inc.
+ * Author: MontaVista Software, Inc. <source@mvista.com>
  *
  * Copyright (C) 2007 Ralf Baechle (ralf@linux-mips.org)
  *
@@ -27,7 +26,6 @@
  */
 #include <linux/bitops.h>
 #include <linux/init.h>
-#include <linux/io.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 
@@ -591,7 +589,7 @@ void __init arch_init_irq(void)
 		imp++;
 	}
 
-	set_c0_status(ALLINTS);
+	set_c0_status(IE_IRQ0 | IE_IRQ1 | IE_IRQ2 | IE_IRQ3 | IE_IRQ4);
 
 	/* Board specific IRQ initialization.
 	*/
diff --git a/trunk/arch/mips/au1000/common/pci.c b/trunk/arch/mips/au1000/common/pci.c
index ce771487567d..7e966b31e3e1 100644
--- a/trunk/arch/mips/au1000/common/pci.c
+++ b/trunk/arch/mips/au1000/common/pci.c
@@ -30,7 +30,7 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/types.h>
+
 #include <linux/pci.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
diff --git a/trunk/arch/mips/au1000/common/platform.c b/trunk/arch/mips/au1000/common/platform.c
index 39d681265297..31d2a2270878 100644
--- a/trunk/arch/mips/au1000/common/platform.c
+++ b/trunk/arch/mips/au1000/common/platform.c
@@ -3,18 +3,65 @@
  *
  * Copyright 2004, Matt Porter <mporter@kernel.crashing.org>
  *
+ * (C) Copyright Embedded Alley Solutions, Inc 2005
+ * Author: Pantelis Antoniou <pantelis@embeddedalley.com>
+ *
  * This file is licensed under the terms of the GNU General Public
  * License version 2.  This program is licensed "as is" without any
  * warranty of any kind, whether express or implied.
  */
-#include <linux/device.h>
+
 #include <linux/platform_device.h>
-#include <linux/kernel.h>
+#include <linux/serial_8250.h>
 #include <linux/init.h>
-#include <linux/resource.h>
 
 #include <asm/mach-au1x00/au1xxx.h>
 
+#define PORT(_base, _irq)				\
+	{						\
+		.iobase		= _base,		\
+		.membase	= (void __iomem *)_base,\
+		.mapbase	= CPHYSADDR(_base),	\
+		.irq		= _irq,			\
+		.regshift	= 2,			\
+		.iotype		= UPIO_AU,		\
+		.flags		= UPF_SKIP_TEST 	\
+	}
+
+static struct plat_serial8250_port au1x00_uart_data[] = {
+#if defined(CONFIG_SERIAL_8250_AU1X00)
+#if defined(CONFIG_SOC_AU1000)
+	PORT(UART0_ADDR, AU1000_UART0_INT),
+	PORT(UART1_ADDR, AU1000_UART1_INT),
+	PORT(UART2_ADDR, AU1000_UART2_INT),
+	PORT(UART3_ADDR, AU1000_UART3_INT),
+#elif defined(CONFIG_SOC_AU1500)
+	PORT(UART0_ADDR, AU1500_UART0_INT),
+	PORT(UART3_ADDR, AU1500_UART3_INT),
+#elif defined(CONFIG_SOC_AU1100)
+	PORT(UART0_ADDR, AU1100_UART0_INT),
+	PORT(UART1_ADDR, AU1100_UART1_INT),
+	PORT(UART3_ADDR, AU1100_UART3_INT),
+#elif defined(CONFIG_SOC_AU1550)
+	PORT(UART0_ADDR, AU1550_UART0_INT),
+	PORT(UART1_ADDR, AU1550_UART1_INT),
+	PORT(UART3_ADDR, AU1550_UART3_INT),
+#elif defined(CONFIG_SOC_AU1200)
+	PORT(UART0_ADDR, AU1200_UART0_INT),
+	PORT(UART1_ADDR, AU1200_UART1_INT),
+#endif
+#endif	/* CONFIG_SERIAL_8250_AU1X00 */
+	{ },
+};
+
+static struct platform_device au1xx0_uart_device = {
+	.name			= "serial8250",
+	.id			= PLAT8250_DEV_AU1X00,
+	.dev			= {
+		.platform_data	= au1x00_uart_data,
+	},
+};
+
 /* OHCI (USB full speed host controller) */
 static struct resource au1xxx_usb_ohci_resources[] = {
 	[0] = {
@@ -186,19 +233,6 @@ static struct resource au1200_lcd_resources[] = {
 	}
 };
 
-static struct resource au1200_ide0_resources[] = {
-	[0] = {
-		.start		= AU1XXX_ATA_PHYS_ADDR,
-		.end 		= AU1XXX_ATA_PHYS_ADDR + AU1XXX_ATA_PHYS_LEN - 1,
-		.flags		= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start		= AU1XXX_ATA_INT,
-		.end		= AU1XXX_ATA_INT,
-		.flags		= IORESOURCE_IRQ,
-	}
-};
-
 static u64 au1200_lcd_dmamask = ~(u32)0;
 
 static struct platform_device au1200_lcd_device = {
@@ -212,20 +246,6 @@ static struct platform_device au1200_lcd_device = {
 	.resource       = au1200_lcd_resources,
 };
 
-
-static u64 ide0_dmamask = ~(u32)0;
-
-static struct platform_device au1200_ide0_device = {
-	.name		= "au1200-ide",
-	.id		= 0,
-	.dev = {
-		.dma_mask 		= &ide0_dmamask,
-		.coherent_dma_mask	= 0xffffffff,
-	},
-	.num_resources = ARRAY_SIZE(au1200_ide0_resources),
-	.resource	= au1200_ide0_resources,
-};
-
 static u64 au1xxx_mmc_dmamask =  ~(u32)0;
 
 static struct platform_device au1xxx_mmc_device = {
@@ -245,31 +265,6 @@ static struct platform_device au1x00_pcmcia_device = {
 	.id 		= 0,
 };
 
-#ifdef CONFIG_MIPS_DB1200
-
-static struct resource smc91x_resources[] = {
-	[0] = {
-		.name	= "smc91x-regs",
-		.start	= AU1XXX_SMC91111_PHYS_ADDR,
-		.end	= AU1XXX_SMC91111_PHYS_ADDR + 0xfffff,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= AU1XXX_SMC91111_IRQ,
-		.end	= AU1XXX_SMC91111_IRQ,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device smc91x_device = {
-	.name		= "smc91x",
-	.id		= -1,
-	.num_resources	= ARRAY_SIZE(smc91x_resources),
-	.resource	= smc91x_resources,
-};
-
-#endif
-
 /* All Alchemy demoboards with I2C have this #define in their headers */
 #ifdef SMBUS_PSC_BASE
 static struct resource pbdb_smbus_resources[] = {
@@ -289,6 +284,7 @@ static struct platform_device pbdb_smbus_device = {
 #endif
 
 static struct platform_device *au1xxx_platform_devices[] __initdata = {
+	&au1xx0_uart_device,
 	&au1xxx_usb_ohci_device,
 	&au1x00_pcmcia_device,
 #ifdef CONFIG_FB_AU1100
@@ -299,12 +295,8 @@ static struct platform_device *au1xxx_platform_devices[] __initdata = {
 	&au1xxx_usb_gdt_device,
 	&au1xxx_usb_otg_device,
 	&au1200_lcd_device,
-	&au1200_ide0_device,
 	&au1xxx_mmc_device,
 #endif
-#ifdef CONFIG_MIPS_DB1200
-	&smc91x_device,
-#endif
 #ifdef SMBUS_PSC_BASE
 	&pbdb_smbus_device,
 #endif
@@ -312,6 +304,13 @@ static struct platform_device *au1xxx_platform_devices[] __initdata = {
 
 int __init au1xxx_platform_init(void)
 {
+	unsigned int uartclk = get_au1x00_uart_baud_base() * 16;
+	int i;
+
+	/* Fill up uartclk. */
+	for (i = 0; au1x00_uart_data[i].flags ; i++)
+		au1x00_uart_data[i].uartclk = uartclk;
+
 	return platform_add_devices(au1xxx_platform_devices, ARRAY_SIZE(au1xxx_platform_devices));
 }
 
diff --git a/trunk/arch/mips/au1000/common/power.c b/trunk/arch/mips/au1000/common/power.c
index 54047d69b820..812a5f8b7d26 100644
--- a/trunk/arch/mips/au1000/common/power.c
+++ b/trunk/arch/mips/au1000/common/power.c
@@ -29,17 +29,14 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
 #include <linux/pm.h>
 #include <linux/pm_legacy.h>
-#include <linux/slab.h>
 #include <linux/sysctl.h>
 #include <linux/jiffies.h>
 
-#include <asm/string.h>
 #include <asm/uaccess.h>
-#include <asm/io.h>
-#include <asm/system.h>
 #include <asm/cacheflush.h>
 #include <asm/mach-au1x00/au1000.h>
 
@@ -47,17 +44,13 @@
 
 #define DEBUG 1
 #ifdef DEBUG
-#  define DPRINTK(fmt, args...)	printk("%s: " fmt, __FUNCTION__ , ## args)
+#  define DPRINTK(fmt, args...)	printk("%s: " fmt, __func__, ## args)
 #else
 #  define DPRINTK(fmt, args...)
 #endif
 
 static void au1000_calibrate_delay(void);
 
-extern void set_au1x00_speed(unsigned int new_freq);
-extern unsigned int get_au1x00_speed(void);
-extern unsigned long get_au1x00_uart_baud_base(void);
-extern void set_au1x00_uart_baud_base(unsigned long new_baud_base);
 extern unsigned long save_local_and_disable(int controller);
 extern void restore_local_and_enable(int controller, unsigned long mask);
 extern void local_enable_irq(unsigned int irq_nr);
diff --git a/trunk/arch/mips/au1000/common/prom.c b/trunk/arch/mips/au1000/common/prom.c
index 90d70695aa60..f10af829e4ec 100644
--- a/trunk/arch/mips/au1000/common/prom.c
+++ b/trunk/arch/mips/au1000/common/prom.c
@@ -33,8 +33,8 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/module.h>
-#include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/string.h>
 
diff --git a/trunk/arch/mips/au1000/common/puts.c b/trunk/arch/mips/au1000/common/puts.c
index 2705829cd466..e34c67e89293 100644
--- a/trunk/arch/mips/au1000/common/puts.c
+++ b/trunk/arch/mips/au1000/common/puts.c
@@ -28,7 +28,6 @@
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#include <linux/types.h>
 #include <asm/mach-au1x00/au1000.h>
 
 #define SERIAL_BASE   UART_BASE
diff --git a/trunk/arch/mips/au1000/common/reset.c b/trunk/arch/mips/au1000/common/reset.c
index b8638d293cf9..60cec537c745 100644
--- a/trunk/arch/mips/au1000/common/reset.c
+++ b/trunk/arch/mips/au1000/common/reset.c
@@ -27,13 +27,7 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <asm/io.h>
-#include <asm/pgtable.h>
-#include <asm/processor.h>
-#include <asm/reboot.h>
-#include <asm/system.h>
+
 #include <asm/mach-au1x00/au1000.h>
 
 extern int au_sleep(void);
diff --git a/trunk/arch/mips/au1000/common/setup.c b/trunk/arch/mips/au1000/common/setup.c
index 9e4ab80caab6..0e86f7a6b4a7 100644
--- a/trunk/arch/mips/au1000/common/setup.c
+++ b/trunk/arch/mips/au1000/common/setup.c
@@ -25,21 +25,14 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
-#include <linux/sched.h>
 #include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/pm.h>
 
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
 #include <asm/mipsregs.h>
 #include <asm/reboot.h>
-#include <asm/pgtable.h>
 #include <asm/time.h>
 
 #include <au1000.h>
@@ -49,8 +42,6 @@ extern void __init board_setup(void);
 extern void au1000_restart(char *);
 extern void au1000_halt(void);
 extern void au1000_power_off(void);
-extern void au1x_time_init(void);
-extern void au1x_timer_setup(struct irqaction *irq);
 extern void set_cpuspec(void);
 
 void __init plat_mem_setup(void)
diff --git a/trunk/arch/mips/au1000/common/sleeper.S b/trunk/arch/mips/au1000/common/sleeper.S
index 683d9da84b66..4b3cf021a454 100644
--- a/trunk/arch/mips/au1000/common/sleeper.S
+++ b/trunk/arch/mips/au1000/common/sleeper.S
@@ -9,9 +9,9 @@
  * Free Software Foundation;  either version 2 of the  License, or (at your
  * option) any later version.
  */
+
 #include <asm/asm.h>
 #include <asm/mipsregs.h>
-#include <asm/addrspace.h>
 #include <asm/regdef.h>
 #include <asm/stackframe.h>
 
diff --git a/trunk/arch/mips/au1000/common/time.c b/trunk/arch/mips/au1000/common/time.c
index e122bbc6cd88..bdb6d73b26fb 100644
--- a/trunk/arch/mips/au1000/common/time.c
+++ b/trunk/arch/mips/au1000/common/time.c
@@ -1,6 +1,6 @@
 /*
  *
- * Copyright (C) 2001 MontaVista Software, ppopov@mvista.com
+ * Copyright (C) 2001, 2006, 2008 MontaVista Software, <source@mvista.com>
  * Copied and modified Carsten Langgaard's time.c
  *
  * Carsten Langgaard, carstenl@mips.com
@@ -34,23 +34,13 @@
 
 #include <linux/types.h>
 #include <linux/init.h>
-#include <linux/kernel_stat.h>
-#include <linux/sched.h>
 #include <linux/spinlock.h>
-#include <linux/hardirq.h>
 
-#include <asm/compiler.h>
 #include <asm/mipsregs.h>
 #include <asm/time.h>
-#include <asm/div64.h>
 #include <asm/mach-au1x00/au1000.h>
 
-#include <linux/mc146818rtc.h>
-#include <linux/timex.h>
-
-static unsigned long r4k_offset; /* Amount to increment compare reg each time */
-static unsigned long r4k_cur;    /* What counter should be at next timer irq */
-int	no_au1xxx_32khz;
+static int no_au1xxx_32khz;
 extern int allow_au1k_wait; /* default off for CP0 Counter */
 
 #ifdef CONFIG_PM
@@ -184,7 +174,7 @@ wakeup_counter0_set(int ticks)
  * "wait" is enabled, and we need to detect if the 32KHz isn't present
  * but requested......got it? :-)		-- Dan
  */
-unsigned long cal_r4koff(void)
+unsigned long calc_clock(void)
 {
 	unsigned long cpu_speed;
 	unsigned long flags;
@@ -229,19 +219,13 @@ unsigned long cal_r4koff(void)
 	// Equation: Baudrate = CPU / (SD * 2 * CLKDIV * 16)
 	set_au1x00_uart_baud_base(cpu_speed / (2 * ((int)(au_readl(SYS_POWERCTRL)&0x03) + 2) * 16));
 	spin_unlock_irqrestore(&time_lock, flags);
-	return (cpu_speed / HZ);
+	return cpu_speed;
 }
 
 void __init plat_time_init(void)
 {
-	unsigned int est_freq;
-
-	printk("calculating r4koff... ");
-	r4k_offset = cal_r4koff();
-	printk("%08lx(%d)\n", r4k_offset, (int) r4k_offset);
+	unsigned int est_freq = calc_clock();
 
-	//est_freq = 2*r4k_offset*HZ;
-	est_freq = r4k_offset*HZ;
 	est_freq += 5000;    /* round */
 	est_freq -= est_freq%10000;
 	printk("CPU frequency %d.%02d MHz\n", est_freq/1000000,
@@ -249,9 +233,6 @@ void __init plat_time_init(void)
  	set_au1x00_speed(est_freq);
  	set_au1x00_lcd_clock(); // program the LCD clock
 
-	r4k_cur = (read_c0_count() + r4k_offset);
-	write_c0_compare(r4k_cur);
-
 #ifdef CONFIG_PM
 	/*
 	 * setup counter 0, since it keeps ticking after a
@@ -265,12 +246,8 @@ void __init plat_time_init(void)
 	 * Check to ensure we really have a 32KHz oscillator before
 	 * we do this.
 	 */
-	if (no_au1xxx_32khz) {
+	if (no_au1xxx_32khz)
 		printk("WARNING: no 32KHz clock found.\n");
-
-		/* Ensure we get CPO_COUNTER interrupts.  */
-		set_c0_status(IE_IRQ5);
-	}
 	else {
 		while (au_readl(SYS_COUNTER_CNTRL) & SYS_CNTRL_C0S);
 		au_writel(0, SYS_TOYWRITE);
diff --git a/trunk/arch/mips/au1000/db1x00/board_setup.c b/trunk/arch/mips/au1000/db1x00/board_setup.c
index 99eafeada518..b7dcbad5c586 100644
--- a/trunk/arch/mips/au1000/db1x00/board_setup.c
+++ b/trunk/arch/mips/au1000/db1x00/board_setup.c
@@ -27,20 +27,9 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
-#include <linux/mc146818rtc.h>
-#include <linux/delay.h>
-
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
+
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-db1x00/db1x00.h>
 
diff --git a/trunk/arch/mips/au1000/db1x00/init.c b/trunk/arch/mips/au1000/db1x00/init.c
index e822c123eab8..d3b967caf70c 100644
--- a/trunk/arch/mips/au1000/db1x00/init.c
+++ b/trunk/arch/mips/au1000/db1x00/init.c
@@ -28,13 +28,8 @@
  */
 
 #include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/string.h>
 #include <linux/kernel.h>
 
-#include <asm/addrspace.h>
 #include <asm/bootinfo.h>
 
 #include <prom.h>
diff --git a/trunk/arch/mips/au1000/db1x00/irqmap.c b/trunk/arch/mips/au1000/db1x00/irqmap.c
index 09cea03411b0..eaa50c7b6341 100644
--- a/trunk/arch/mips/au1000/db1x00/irqmap.c
+++ b/trunk/arch/mips/au1000/db1x00/irqmap.c
@@ -25,26 +25,9 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/errno.h>
+
 #include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
 
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
 #include <asm/mach-au1x00/au1000.h>
 
 #ifdef CONFIG_MIPS_DB1500
diff --git a/trunk/arch/mips/au1000/mtx-1/board_setup.c b/trunk/arch/mips/au1000/mtx-1/board_setup.c
index 310d5dff89fc..5736354829c6 100644
--- a/trunk/arch/mips/au1000/mtx-1/board_setup.c
+++ b/trunk/arch/mips/au1000/mtx-1/board_setup.c
@@ -28,19 +28,9 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
-#include <linux/delay.h>
 
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
 #include <asm/mach-au1x00/au1000.h>
 
 extern int (*board_pci_idsel)(unsigned int devsel, int assert);
diff --git a/trunk/arch/mips/au1000/mtx-1/init.c b/trunk/arch/mips/au1000/mtx-1/init.c
index e700fd312a24..c015cbce1cca 100644
--- a/trunk/arch/mips/au1000/mtx-1/init.c
+++ b/trunk/arch/mips/au1000/mtx-1/init.c
@@ -28,14 +28,10 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/string.h>
+
 #include <linux/kernel.h>
-#include <linux/sched.h>
 #include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/bootmem.h>
 
-#include <asm/addrspace.h>
 #include <asm/bootinfo.h>
 
 #include <prom.h>
diff --git a/trunk/arch/mips/au1000/mtx-1/irqmap.c b/trunk/arch/mips/au1000/mtx-1/irqmap.c
index 49c612aeddcf..78d70c42c9db 100644
--- a/trunk/arch/mips/au1000/mtx-1/irqmap.c
+++ b/trunk/arch/mips/au1000/mtx-1/irqmap.c
@@ -25,26 +25,9 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/errno.h>
+
 #include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
 
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
 #include <asm/mach-au1x00/au1000.h>
 
 char irq_tab_alchemy[][5] __initdata = {
diff --git a/trunk/arch/mips/au1000/mtx-1/platform.c b/trunk/arch/mips/au1000/mtx-1/platform.c
index ce8637b3afa9..a7edbf0829ac 100644
--- a/trunk/arch/mips/au1000/mtx-1/platform.c
+++ b/trunk/arch/mips/au1000/mtx-1/platform.c
@@ -19,7 +19,6 @@
  */
 
 #include <linux/init.h>
-#include <linux/types.h>
 #include <linux/platform_device.h>
 #include <linux/leds.h>
 #include <linux/gpio_keys.h>
diff --git a/trunk/arch/mips/au1000/pb1000/board_setup.c b/trunk/arch/mips/au1000/pb1000/board_setup.c
index 5198c4f98b43..33f15acc1b17 100644
--- a/trunk/arch/mips/au1000/pb1000/board_setup.c
+++ b/trunk/arch/mips/au1000/pb1000/board_setup.c
@@ -23,19 +23,10 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
 #include <linux/delay.h>
 
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-pb1x00/pb1000.h>
 
diff --git a/trunk/arch/mips/au1000/pb1000/init.c b/trunk/arch/mips/au1000/pb1000/init.c
index 2515b9fb24af..549447df71d6 100644
--- a/trunk/arch/mips/au1000/pb1000/init.c
+++ b/trunk/arch/mips/au1000/pb1000/init.c
@@ -26,14 +26,10 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/string.h>
 #include <linux/kernel.h>
 
-#include <asm/addrspace.h>
 #include <asm/bootinfo.h>
 
 #include <prom.h>
diff --git a/trunk/arch/mips/au1000/pb1000/irqmap.c b/trunk/arch/mips/au1000/pb1000/irqmap.c
index 88e354508204..b3d56b0af321 100644
--- a/trunk/arch/mips/au1000/pb1000/irqmap.c
+++ b/trunk/arch/mips/au1000/pb1000/irqmap.c
@@ -25,26 +25,10 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/errno.h>
+
 #include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
 #include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
 
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
 #include <asm/mach-au1x00/au1000.h>
 
 struct au1xxx_irqmap __initdata au1xxx_irq_map[] = {
diff --git a/trunk/arch/mips/au1000/pb1100/board_setup.c b/trunk/arch/mips/au1000/pb1100/board_setup.c
index 42874a6b31d1..656164c8e9ca 100644
--- a/trunk/arch/mips/au1000/pb1100/board_setup.c
+++ b/trunk/arch/mips/au1000/pb1100/board_setup.c
@@ -23,19 +23,10 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
 #include <linux/delay.h>
 
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-pb1x00/pb1100.h>
 
diff --git a/trunk/arch/mips/au1000/pb1100/init.c b/trunk/arch/mips/au1000/pb1100/init.c
index 490c3801c275..c91344648ed3 100644
--- a/trunk/arch/mips/au1000/pb1100/init.c
+++ b/trunk/arch/mips/au1000/pb1100/init.c
@@ -27,14 +27,10 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/string.h>
 #include <linux/kernel.h>
 
-#include <asm/addrspace.h>
 #include <asm/bootinfo.h>
 
 #include <prom.h>
diff --git a/trunk/arch/mips/au1000/pb1100/irqmap.c b/trunk/arch/mips/au1000/pb1100/irqmap.c
index 880456bf8c11..b5021e3d477f 100644
--- a/trunk/arch/mips/au1000/pb1100/irqmap.c
+++ b/trunk/arch/mips/au1000/pb1100/irqmap.c
@@ -25,26 +25,9 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/errno.h>
+
 #include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
 
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
 #include <asm/mach-au1x00/au1000.h>
 
 struct au1xxx_irqmap __initdata au1xxx_irq_map[] = {
diff --git a/trunk/arch/mips/au1000/pb1200/Makefile b/trunk/arch/mips/au1000/pb1200/Makefile
index 970b1b1d5cda..4fe02ea65a60 100644
--- a/trunk/arch/mips/au1000/pb1200/Makefile
+++ b/trunk/arch/mips/au1000/pb1200/Makefile
@@ -3,5 +3,6 @@
 #
 
 lib-y := init.o board_setup.o irqmap.o
+obj-y += platform.o
 
 EXTRA_CFLAGS += -Werror
diff --git a/trunk/arch/mips/au1000/pb1200/board_setup.c b/trunk/arch/mips/au1000/pb1200/board_setup.c
index b98bebfa87c6..4493a792cc4c 100644
--- a/trunk/arch/mips/au1000/pb1200/board_setup.c
+++ b/trunk/arch/mips/au1000/pb1200/board_setup.c
@@ -23,27 +23,11 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
 #include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
-#include <linux/mc146818rtc.h>
-#include <linux/delay.h>
-
-#if defined(CONFIG_BLK_DEV_IDE_AU1XXX)
-#include <linux/ide.h>
-#endif
-
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
 
 #include <au1000.h>
-#include <au1xxx_dbdma.h>
 #include <prom.h>
 
 #ifdef CONFIG_MIPS_PB1200
@@ -52,8 +36,6 @@
 
 #ifdef CONFIG_MIPS_DB1200
 #include <asm/mach-db1x00/db1200.h>
-#define PB1200_ETH_INT DB1200_ETH_INT
-#define PB1200_IDE_INT DB1200_IDE_INT
 #endif
 
 extern void _board_init_irq(void);
diff --git a/trunk/arch/mips/au1000/pb1200/init.c b/trunk/arch/mips/au1000/pb1200/init.c
index 069ed45f04f2..72af5500660b 100644
--- a/trunk/arch/mips/au1000/pb1200/init.c
+++ b/trunk/arch/mips/au1000/pb1200/init.c
@@ -27,14 +27,10 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/string.h>
 #include <linux/kernel.h>
 
-#include <asm/addrspace.h>
 #include <asm/bootinfo.h>
 
 #include <prom.h>
diff --git a/trunk/arch/mips/au1000/pb1200/irqmap.c b/trunk/arch/mips/au1000/pb1200/irqmap.c
index 8fcd0df86f93..e61eb8e0b76b 100644
--- a/trunk/arch/mips/au1000/pb1200/irqmap.c
+++ b/trunk/arch/mips/au1000/pb1200/irqmap.c
@@ -22,26 +22,10 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/errno.h>
+
 #include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
 #include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
-
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
+
 #include <asm/mach-au1x00/au1000.h>
 
 #ifdef CONFIG_MIPS_PB1200
diff --git a/trunk/arch/mips/au1000/pb1200/platform.c b/trunk/arch/mips/au1000/pb1200/platform.c
new file mode 100644
index 000000000000..5930110b9b6d
--- /dev/null
+++ b/trunk/arch/mips/au1000/pb1200/platform.c
@@ -0,0 +1,84 @@
+/*
+ * Pb1200/DBAu1200 board platform device registration
+ *
+ * Copyright (C) 2008 MontaVista Software Inc. <source@mvista.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include <linux/init.h>
+#include <linux/platform_device.h>
+
+#include <asm/mach-au1x00/au1xxx.h>
+
+static struct resource ide_resources[] = {
+	[0] = {
+		.start	= IDE_PHYS_ADDR,
+		.end 	= IDE_PHYS_ADDR + IDE_PHYS_LEN - 1,
+		.flags	= IORESOURCE_MEM
+	},
+	[1] = {
+		.start	= IDE_INT,
+		.end	= IDE_INT,
+		.flags	= IORESOURCE_IRQ
+	}
+};
+
+static u64 ide_dmamask = ~(u32)0;
+
+static struct platform_device ide_device = {
+	.name		= "au1200-ide",
+	.id		= 0,
+	.dev = {
+		.dma_mask 		= &ide_dmamask,
+		.coherent_dma_mask	= 0xffffffff,
+	},
+	.num_resources	= ARRAY_SIZE(ide_resources),
+	.resource	= ide_resources
+};
+
+static struct resource smc91c111_resources[] = {
+	[0] = {
+		.name	= "smc91x-regs",
+		.start	= SMC91C111_PHYS_ADDR,
+		.end	= SMC91C111_PHYS_ADDR + 0xf,
+		.flags	= IORESOURCE_MEM
+	},
+	[1] = {
+		.start	= SMC91C111_INT,
+		.end	= SMC91C111_INT,
+		.flags	= IORESOURCE_IRQ
+	},
+};
+
+static struct platform_device smc91c111_device = {
+	.name		= "smc91x",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(smc91c111_resources),
+	.resource	= smc91c111_resources
+};
+
+static struct platform_device *board_platform_devices[] __initdata = {
+	&ide_device,
+	&smc91c111_device
+};
+
+static int __init board_register_devices(void)
+{
+	return platform_add_devices(board_platform_devices,
+				    ARRAY_SIZE(board_platform_devices));
+}
+
+arch_initcall(board_register_devices);
diff --git a/trunk/arch/mips/au1000/pb1500/board_setup.c b/trunk/arch/mips/au1000/pb1500/board_setup.c
index 5446836869d6..24c652e8ec4b 100644
--- a/trunk/arch/mips/au1000/pb1500/board_setup.c
+++ b/trunk/arch/mips/au1000/pb1500/board_setup.c
@@ -23,19 +23,10 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
 #include <linux/delay.h>
 
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-pb1x00/pb1500.h>
 
diff --git a/trunk/arch/mips/au1000/pb1500/init.c b/trunk/arch/mips/au1000/pb1500/init.c
index db558c967048..488507c07db9 100644
--- a/trunk/arch/mips/au1000/pb1500/init.c
+++ b/trunk/arch/mips/au1000/pb1500/init.c
@@ -27,14 +27,10 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/string.h>
 #include <linux/kernel.h>
 
-#include <asm/addrspace.h>
 #include <asm/bootinfo.h>
 
 #include <prom.h>
diff --git a/trunk/arch/mips/au1000/pb1500/irqmap.c b/trunk/arch/mips/au1000/pb1500/irqmap.c
index 810f695e24bb..4817ab44d07f 100644
--- a/trunk/arch/mips/au1000/pb1500/irqmap.c
+++ b/trunk/arch/mips/au1000/pb1500/irqmap.c
@@ -25,26 +25,9 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/errno.h>
+
 #include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
 
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
 #include <asm/mach-au1x00/au1000.h>
 
 char irq_tab_alchemy[][5] __initdata = {
diff --git a/trunk/arch/mips/au1000/pb1550/board_setup.c b/trunk/arch/mips/au1000/pb1550/board_setup.c
index e3cfb0d73180..45d60872b565 100644
--- a/trunk/arch/mips/au1000/pb1550/board_setup.c
+++ b/trunk/arch/mips/au1000/pb1550/board_setup.c
@@ -27,20 +27,9 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
-#include <linux/mc146818rtc.h>
-#include <linux/delay.h>
 
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-pb1x00/pb1550.h>
 
diff --git a/trunk/arch/mips/au1000/pb1550/init.c b/trunk/arch/mips/au1000/pb1550/init.c
index b716363ea564..f6b2fc587980 100644
--- a/trunk/arch/mips/au1000/pb1550/init.c
+++ b/trunk/arch/mips/au1000/pb1550/init.c
@@ -27,14 +27,10 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/string.h>
 #include <linux/kernel.h>
 
-#include <asm/addrspace.h>
 #include <asm/bootinfo.h>
 
 #include <prom.h>
diff --git a/trunk/arch/mips/au1000/pb1550/irqmap.c b/trunk/arch/mips/au1000/pb1550/irqmap.c
index 56becab28e5d..e1dac37af08a 100644
--- a/trunk/arch/mips/au1000/pb1550/irqmap.c
+++ b/trunk/arch/mips/au1000/pb1550/irqmap.c
@@ -25,26 +25,9 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/errno.h>
+
 #include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
 
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
 #include <asm/mach-au1x00/au1000.h>
 
 char irq_tab_alchemy[][5] __initdata = {
diff --git a/trunk/arch/mips/au1000/xxs1500/board_setup.c b/trunk/arch/mips/au1000/xxs1500/board_setup.c
index b2e413e597a8..79d1798621bf 100644
--- a/trunk/arch/mips/au1000/xxs1500/board_setup.c
+++ b/trunk/arch/mips/au1000/xxs1500/board_setup.c
@@ -23,19 +23,10 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
 #include <linux/delay.h>
 
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
 #include <asm/mach-au1x00/au1000.h>
 
 void board_reset(void)
diff --git a/trunk/arch/mips/au1000/xxs1500/init.c b/trunk/arch/mips/au1000/xxs1500/init.c
index 7e6878c1b0a5..24fc6e132dc0 100644
--- a/trunk/arch/mips/au1000/xxs1500/init.c
+++ b/trunk/arch/mips/au1000/xxs1500/init.c
@@ -26,14 +26,10 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
+
 #include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/string.h>
 #include <linux/kernel.h>
 
-#include <asm/addrspace.h>
 #include <asm/bootinfo.h>
 
 #include <prom.h>
diff --git a/trunk/arch/mips/au1000/xxs1500/irqmap.c b/trunk/arch/mips/au1000/xxs1500/irqmap.c
index a343da134334..dd6e3d1eb4d4 100644
--- a/trunk/arch/mips/au1000/xxs1500/irqmap.c
+++ b/trunk/arch/mips/au1000/xxs1500/irqmap.c
@@ -25,26 +25,9 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/errno.h>
+
 #include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
 
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
 #include <asm/mach-au1x00/au1000.h>
 
 struct au1xxx_irqmap __initdata au1xxx_irq_map[] = {
diff --git a/trunk/arch/mips/basler/excite/excite_procfs.c b/trunk/arch/mips/basler/excite/excite_procfs.c
index 9ee67a95f6b9..08923e6825b5 100644
--- a/trunk/arch/mips/basler/excite/excite_procfs.c
+++ b/trunk/arch/mips/basler/excite/excite_procfs.c
@@ -18,8 +18,9 @@
  *  along with this program; if not, write to the Free Software
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
-
+#include <linux/module.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/stat.h>
 #include <asm/page.h>
 #include <asm/io.h>
@@ -28,14 +29,25 @@
 
 #include <excite.h>
 
-static int excite_get_unit_id(char *buf, char **addr, off_t offs, int size)
+static int excite_unit_id_proc_show(struct seq_file *m, void *v)
 {
-	const int len = snprintf(buf, PAGE_SIZE, "%06x", unit_id);
-	const int w = len - offs;
-	*addr = buf + offs;
-	return w < size ? w : size;
+	seq_printf(m, "%06x", unit_id);
+	return 0;
 }
 
+static int excite_unit_id_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, excite_unit_id_proc_show, NULL);
+}
+
+static const struct file_operations excite_unit_id_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= excite_unit_id_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static int
 excite_bootrom_read(char *page, char **start, off_t off, int count,
 		  int *eof, void *data)
@@ -65,12 +77,12 @@ excite_bootrom_read(char *page, char **start, off_t off, int count,
 void excite_procfs_init(void)
 {
 	/* Create & populate /proc/excite */
-	struct proc_dir_entry * const pdir = proc_mkdir("excite", &proc_root);
+	struct proc_dir_entry * const pdir = proc_mkdir("excite", NULL);
 	if (pdir) {
 		struct proc_dir_entry * e;
 
-		e = create_proc_info_entry("unit_id", S_IRUGO, pdir,
-					   excite_get_unit_id);
+		e = proc_create("unit_id", S_IRUGO, pdir,
+				&excite_unit_id_proc_fops);
 		if (e) e->size = 6;
 
 		e = create_proc_read_entry("bootrom", S_IRUGO, pdir,
diff --git a/trunk/arch/mips/configs/mipssim_defconfig b/trunk/arch/mips/configs/mipssim_defconfig
index 6db0bdaefb27..4f6bce99d5cf 100644
--- a/trunk/arch/mips/configs/mipssim_defconfig
+++ b/trunk/arch/mips/configs/mipssim_defconfig
@@ -641,7 +641,6 @@ CONFIG_CROSSCOMPILE=y
 CONFIG_CMDLINE="nfsroot=192.168.192.169:/u1/mipsel,timeo=20 ip=dhcp"
 # CONFIG_DEBUG_STACK_USAGE is not set
 # CONFIG_RUNTIME_DEBUG is not set
-# CONFIG_MIPS_UNCACHED is not set
 
 #
 # Security options
diff --git a/trunk/arch/mips/configs/pnx8550-jbs_defconfig b/trunk/arch/mips/configs/pnx8550-jbs_defconfig
index 518a60892b78..780c7fc24b82 100644
--- a/trunk/arch/mips/configs/pnx8550-jbs_defconfig
+++ b/trunk/arch/mips/configs/pnx8550-jbs_defconfig
@@ -1223,7 +1223,6 @@ CONFIG_CMDLINE="console=ttyS1,38400n8 kgdb=ttyS0 root=/dev/nfs ip=bootp"
 # CONFIG_KGDB is not set
 CONFIG_SYS_SUPPORTS_KGDB=y
 # CONFIG_RUNTIME_DEBUG is not set
-# CONFIG_MIPS_UNCACHED is not set
 
 #
 # Security options
diff --git a/trunk/arch/mips/configs/pnx8550-stb810_defconfig b/trunk/arch/mips/configs/pnx8550-stb810_defconfig
index 68351eb81bc8..267f21ed1d0f 100644
--- a/trunk/arch/mips/configs/pnx8550-stb810_defconfig
+++ b/trunk/arch/mips/configs/pnx8550-stb810_defconfig
@@ -1213,7 +1213,6 @@ CONFIG_CMDLINE="console=ttyS1,38400n8 kgdb=ttyS0 root=/dev/nfs ip=bootp"
 # CONFIG_KGDB is not set
 CONFIG_SYS_SUPPORTS_KGDB=y
 # CONFIG_RUNTIME_DEBUG is not set
-# CONFIG_MIPS_UNCACHED is not set
 
 #
 # Security options
diff --git a/trunk/arch/mips/dec/time.c b/trunk/arch/mips/dec/time.c
index 60349062595a..3965fda94a89 100644
--- a/trunk/arch/mips/dec/time.c
+++ b/trunk/arch/mips/dec/time.c
@@ -9,30 +9,15 @@
  *
  */
 #include <linux/bcd.h>
-#include <linux/errno.h>
 #include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
 #include <linux/mc146818rtc.h>
-#include <linux/mm.h>
-#include <linux/module.h>
 #include <linux/param.h>
-#include <linux/sched.h>
-#include <linux/string.h>
-#include <linux/time.h>
-#include <linux/types.h>
-
-#include <asm/bootinfo.h>
-#include <asm/cpu.h>
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/sections.h>
-#include <asm/time.h>
 
+#include <asm/cpu-features.h>
+#include <asm/ds1287.h>
+#include <asm/time.h>
 #include <asm/dec/interrupts.h>
 #include <asm/dec/ioasic.h>
-#include <asm/dec/ioasic_addrs.h>
 #include <asm/dec/machtype.h>
 
 unsigned long read_persistent_clock(void)
@@ -139,42 +124,32 @@ int rtc_mips_set_mmss(unsigned long nowtime)
 	return retval;
 }
 
-static int dec_timer_state(void)
+void __init plat_time_init(void)
 {
-	return (CMOS_READ(RTC_REG_C) & RTC_PF) != 0;
-}
+	u32 start, end;
+	int i = HZ / 10;
 
-static void dec_timer_ack(void)
-{
-	CMOS_READ(RTC_REG_C);			/* Ack the RTC interrupt.  */
-}
-
-static cycle_t dec_ioasic_hpt_read(void)
-{
-	/*
-	 * The free-running counter is 32-bit which is good for about
-	 * 2 minutes, 50 seconds at possible count rates of up to 25MHz.
-	 */
-	return ioasic_read(IO_REG_FCTR);
-}
+	/* Set up the rate of periodic DS1287 interrupts. */
+	ds1287_set_base_clock(HZ);
 
+	if (cpu_has_counter) {
+		while (!ds1287_timer_state())
+			;
 
-void __init plat_time_init(void)
-{
-	mips_timer_ack = dec_timer_ack;
+		start = read_c0_count();
 
-	if (!cpu_has_counter && IOASIC)
-		/* For pre-R4k systems we use the I/O ASIC's counter.  */
-		clocksource_mips.read = dec_ioasic_hpt_read;
+		while (i--)
+			while (!ds1287_timer_state())
+				;
 
-	/* Set up the rate of periodic DS1287 interrupts.  */
-	CMOS_WRITE(RTC_REF_CLCK_32KHZ | (16 - __ffs(HZ)), RTC_REG_A);
-}
+		end = read_c0_count();
 
-void __init plat_timer_setup(struct irqaction *irq)
-{
-	setup_irq(dec_interrupt[DEC_IRQ_RTC], irq);
+		mips_hpt_frequency = (end - start) * 10;
+		printk(KERN_INFO "MIPS counter frequency %dHz\n",
+			mips_hpt_frequency);
+	} else if (IOASIC)
+		/* For pre-R4k systems we use the I/O ASIC's counter.  */
+		dec_ioasic_clocksource_init();
 
-	/* Enable periodic DS1287 interrupts.  */
-	CMOS_WRITE(CMOS_READ(RTC_REG_B) | RTC_PIE, RTC_REG_B);
+	ds1287_clockevent_init(dec_interrupt[DEC_IRQ_RTC]);
 }
diff --git a/trunk/arch/mips/jmr3927/rbhma3100/setup.c b/trunk/arch/mips/jmr3927/rbhma3100/setup.c
index c886d804d303..f39c444e42d4 100644
--- a/trunk/arch/mips/jmr3927/rbhma3100/setup.c
+++ b/trunk/arch/mips/jmr3927/rbhma3100/setup.c
@@ -36,11 +36,13 @@
 #include <linux/pm.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
+#include <linux/gpio.h>
 #ifdef CONFIG_SERIAL_TXX9
 #include <linux/serial_core.h>
 #endif
 
 #include <asm/txx9tmr.h>
+#include <asm/txx9pio.h>
 #include <asm/reboot.h>
 #include <asm/jmr3927/jmr3927.h>
 #include <asm/mipsregs.h>
@@ -340,9 +342,12 @@ static void __init tx3927_setup(void)
 
 	/* PIO */
 	/* PIO[15:12] connected to LEDs */
-	tx3927_pioptr->dir = 0x0000f000;
-	tx3927_pioptr->maskcpu = 0;
-	tx3927_pioptr->maskext = 0;
+	__raw_writel(0x0000f000, &tx3927_pioptr->dir);
+	__raw_writel(0, &tx3927_pioptr->maskcpu);
+	__raw_writel(0, &tx3927_pioptr->maskext);
+	txx9_gpio_init(TX3927_PIO_REG, 0, 16);
+	gpio_request(11, "dipsw1");
+	gpio_request(10, "dipsw2");
 	{
 		unsigned int conf;
 
diff --git a/trunk/arch/mips/kernel/Makefile b/trunk/arch/mips/kernel/Makefile
index 6fcdb6fda2e2..45545be3eb86 100644
--- a/trunk/arch/mips/kernel/Makefile
+++ b/trunk/arch/mips/kernel/Makefile
@@ -10,12 +10,15 @@ obj-y		+= cpu-probe.o branch.o entry.o genex.o irq.o process.o \
 
 obj-$(CONFIG_CEVT_BCM1480)	+= cevt-bcm1480.o
 obj-$(CONFIG_CEVT_R4K)		+= cevt-r4k.o
+obj-$(CONFIG_CEVT_DS1287)	+= cevt-ds1287.o
 obj-$(CONFIG_CEVT_GT641XX)	+= cevt-gt641xx.o
 obj-$(CONFIG_CEVT_SB1250)	+= cevt-sb1250.o
 obj-$(CONFIG_CEVT_TXX9)		+= cevt-txx9.o
 obj-$(CONFIG_CSRC_BCM1480)	+= csrc-bcm1480.o
+obj-$(CONFIG_CSRC_IOASIC)	+= csrc-ioasic.o
 obj-$(CONFIG_CSRC_R4K)		+= csrc-r4k.o
 obj-$(CONFIG_CSRC_SB1250)	+= csrc-sb1250.o
+obj-$(CONFIG_SYNC_R4K)		+= sync-r4k.o
 
 binfmt_irix-objs	:= irixelf.o irixinv.o irixioctl.o irixsig.o	\
 			   irix5sys.o sysirix.o
@@ -50,6 +53,8 @@ obj-$(CONFIG_MIPS_MT)		+= mips-mt.o
 obj-$(CONFIG_MIPS_MT_FPAFF)	+= mips-mt-fpaff.o
 obj-$(CONFIG_MIPS_MT_SMTC)	+= smtc.o smtc-asm.o smtc-proc.o
 obj-$(CONFIG_MIPS_MT_SMP)	+= smp-mt.o
+obj-$(CONFIG_MIPS_CMP)		+= smp-cmp.o
+obj-$(CONFIG_CPU_MIPSR2)	+= spram.o
 
 obj-$(CONFIG_MIPS_APSP_KSPD)	+= kspd.o
 obj-$(CONFIG_MIPS_VPE_LOADER)	+= vpe.o
@@ -62,6 +67,7 @@ obj-$(CONFIG_IRQ_CPU_RM9K)	+= irq-rm9000.o
 obj-$(CONFIG_MIPS_BOARDS_GEN)	+= irq-msc01.o
 obj-$(CONFIG_IRQ_TXX9)		+= irq_txx9.o
 obj-$(CONFIG_IRQ_GT641XX)	+= irq-gt641xx.o
+obj-$(CONFIG_IRQ_GIC)		+= irq-gic.o
 
 obj-$(CONFIG_32BIT)		+= scall32-o32.o
 obj-$(CONFIG_64BIT)		+= scall64-64.o
@@ -77,6 +83,8 @@ obj-$(CONFIG_64BIT)		+= cpu-bugs64.o
 
 obj-$(CONFIG_I8253)		+= i8253.o
 
+obj-$(CONFIG_GPIO_TXX9)		+= gpio_txx9.o
+
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 
diff --git a/trunk/arch/mips/kernel/asm-offsets.c b/trunk/arch/mips/kernel/asm-offsets.c
index ca136298acdc..72942226fcdd 100644
--- a/trunk/arch/mips/kernel/asm-offsets.c
+++ b/trunk/arch/mips/kernel/asm-offsets.c
@@ -13,327 +13,285 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
-
+#include <linux/kbuild.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
 
-#define text(t) __asm__("\n@@@" t)
-#define _offset(type, member) (&(((type *)NULL)->member))
-#define offset(string, ptr, member) \
-	__asm__("\n@@@" string "%0" : : "i" (_offset(ptr, member)))
-#define constant(string, member) \
-	__asm__("\n@@@" string "%X0" : : "ri" (member))
-#define size(string, size) \
-	__asm__("\n@@@" string "%0" : : "i" (sizeof(size)))
-#define linefeed text("")
-
 void output_ptreg_defines(void)
 {
-	text("/* MIPS pt_regs offsets. */");
-	offset("#define PT_R0     ", struct pt_regs, regs[0]);
-	offset("#define PT_R1     ", struct pt_regs, regs[1]);
-	offset("#define PT_R2     ", struct pt_regs, regs[2]);
-	offset("#define PT_R3     ", struct pt_regs, regs[3]);
-	offset("#define PT_R4     ", struct pt_regs, regs[4]);
-	offset("#define PT_R5     ", struct pt_regs, regs[5]);
-	offset("#define PT_R6     ", struct pt_regs, regs[6]);
-	offset("#define PT_R7     ", struct pt_regs, regs[7]);
-	offset("#define PT_R8     ", struct pt_regs, regs[8]);
-	offset("#define PT_R9     ", struct pt_regs, regs[9]);
-	offset("#define PT_R10    ", struct pt_regs, regs[10]);
-	offset("#define PT_R11    ", struct pt_regs, regs[11]);
-	offset("#define PT_R12    ", struct pt_regs, regs[12]);
-	offset("#define PT_R13    ", struct pt_regs, regs[13]);
-	offset("#define PT_R14    ", struct pt_regs, regs[14]);
-	offset("#define PT_R15    ", struct pt_regs, regs[15]);
-	offset("#define PT_R16    ", struct pt_regs, regs[16]);
-	offset("#define PT_R17    ", struct pt_regs, regs[17]);
-	offset("#define PT_R18    ", struct pt_regs, regs[18]);
-	offset("#define PT_R19    ", struct pt_regs, regs[19]);
-	offset("#define PT_R20    ", struct pt_regs, regs[20]);
-	offset("#define PT_R21    ", struct pt_regs, regs[21]);
-	offset("#define PT_R22    ", struct pt_regs, regs[22]);
-	offset("#define PT_R23    ", struct pt_regs, regs[23]);
-	offset("#define PT_R24    ", struct pt_regs, regs[24]);
-	offset("#define PT_R25    ", struct pt_regs, regs[25]);
-	offset("#define PT_R26    ", struct pt_regs, regs[26]);
-	offset("#define PT_R27    ", struct pt_regs, regs[27]);
-	offset("#define PT_R28    ", struct pt_regs, regs[28]);
-	offset("#define PT_R29    ", struct pt_regs, regs[29]);
-	offset("#define PT_R30    ", struct pt_regs, regs[30]);
-	offset("#define PT_R31    ", struct pt_regs, regs[31]);
-	offset("#define PT_LO     ", struct pt_regs, lo);
-	offset("#define PT_HI     ", struct pt_regs, hi);
+	COMMENT("MIPS pt_regs offsets.");
+	OFFSET(PT_R0, pt_regs, regs[0]);
+	OFFSET(PT_R1, pt_regs, regs[1]);
+	OFFSET(PT_R2, pt_regs, regs[2]);
+	OFFSET(PT_R3, pt_regs, regs[3]);
+	OFFSET(PT_R4, pt_regs, regs[4]);
+	OFFSET(PT_R5, pt_regs, regs[5]);
+	OFFSET(PT_R6, pt_regs, regs[6]);
+	OFFSET(PT_R7, pt_regs, regs[7]);
+	OFFSET(PT_R8, pt_regs, regs[8]);
+	OFFSET(PT_R9, pt_regs, regs[9]);
+	OFFSET(PT_R10, pt_regs, regs[10]);
+	OFFSET(PT_R11, pt_regs, regs[11]);
+	OFFSET(PT_R12, pt_regs, regs[12]);
+	OFFSET(PT_R13, pt_regs, regs[13]);
+	OFFSET(PT_R14, pt_regs, regs[14]);
+	OFFSET(PT_R15, pt_regs, regs[15]);
+	OFFSET(PT_R16, pt_regs, regs[16]);
+	OFFSET(PT_R17, pt_regs, regs[17]);
+	OFFSET(PT_R18, pt_regs, regs[18]);
+	OFFSET(PT_R19, pt_regs, regs[19]);
+	OFFSET(PT_R20, pt_regs, regs[20]);
+	OFFSET(PT_R21, pt_regs, regs[21]);
+	OFFSET(PT_R22, pt_regs, regs[22]);
+	OFFSET(PT_R23, pt_regs, regs[23]);
+	OFFSET(PT_R24, pt_regs, regs[24]);
+	OFFSET(PT_R25, pt_regs, regs[25]);
+	OFFSET(PT_R26, pt_regs, regs[26]);
+	OFFSET(PT_R27, pt_regs, regs[27]);
+	OFFSET(PT_R28, pt_regs, regs[28]);
+	OFFSET(PT_R29, pt_regs, regs[29]);
+	OFFSET(PT_R30, pt_regs, regs[30]);
+	OFFSET(PT_R31, pt_regs, regs[31]);
+	OFFSET(PT_LO, pt_regs, lo);
+	OFFSET(PT_HI, pt_regs, hi);
 #ifdef CONFIG_CPU_HAS_SMARTMIPS
-	offset("#define PT_ACX    ", struct pt_regs, acx);
+	OFFSET(PT_ACX, pt_regs, acx);
 #endif
-	offset("#define PT_EPC    ", struct pt_regs, cp0_epc);
-	offset("#define PT_BVADDR ", struct pt_regs, cp0_badvaddr);
-	offset("#define PT_STATUS ", struct pt_regs, cp0_status);
-	offset("#define PT_CAUSE  ", struct pt_regs, cp0_cause);
+	OFFSET(PT_EPC, pt_regs, cp0_epc);
+	OFFSET(PT_BVADDR, pt_regs, cp0_badvaddr);
+	OFFSET(PT_STATUS, pt_regs, cp0_status);
+	OFFSET(PT_CAUSE, pt_regs, cp0_cause);
 #ifdef CONFIG_MIPS_MT_SMTC
-	offset("#define PT_TCSTATUS  ", struct pt_regs, cp0_tcstatus);
+	OFFSET(PT_TCSTATUS, pt_regs, cp0_tcstatus);
 #endif /* CONFIG_MIPS_MT_SMTC */
-	size("#define PT_SIZE   ", struct pt_regs);
-	linefeed;
+	DEFINE(PT_SIZE, sizeof(struct pt_regs));
+	BLANK();
 }
 
 void output_task_defines(void)
 {
-	text("/* MIPS task_struct offsets. */");
-	offset("#define TASK_STATE         ", struct task_struct, state);
-	offset("#define TASK_THREAD_INFO   ", struct task_struct, stack);
-	offset("#define TASK_FLAGS         ", struct task_struct, flags);
-	offset("#define TASK_MM            ", struct task_struct, mm);
-	offset("#define TASK_PID           ", struct task_struct, pid);
-	size(  "#define TASK_STRUCT_SIZE   ", struct task_struct);
-	linefeed;
+	COMMENT("MIPS task_struct offsets.");
+	OFFSET(TASK_STATE, task_struct, state);
+	OFFSET(TASK_THREAD_INFO, task_struct, stack);
+	OFFSET(TASK_FLAGS, task_struct, flags);
+	OFFSET(TASK_MM, task_struct, mm);
+	OFFSET(TASK_PID, task_struct, pid);
+	DEFINE(TASK_STRUCT_SIZE, sizeof(struct task_struct));
+	BLANK();
 }
 
 void output_thread_info_defines(void)
 {
-	text("/* MIPS thread_info offsets. */");
-	offset("#define TI_TASK            ", struct thread_info, task);
-	offset("#define TI_EXEC_DOMAIN     ", struct thread_info, exec_domain);
-	offset("#define TI_FLAGS           ", struct thread_info, flags);
-	offset("#define TI_TP_VALUE	   ", struct thread_info, tp_value);
-	offset("#define TI_CPU             ", struct thread_info, cpu);
-	offset("#define TI_PRE_COUNT       ", struct thread_info, preempt_count);
-	offset("#define TI_ADDR_LIMIT      ", struct thread_info, addr_limit);
-	offset("#define TI_RESTART_BLOCK   ", struct thread_info, restart_block);
-	offset("#define TI_REGS            ", struct thread_info, regs);
-	constant("#define _THREAD_SIZE       ", THREAD_SIZE);
-	constant("#define _THREAD_MASK       ", THREAD_MASK);
-	linefeed;
+	COMMENT("MIPS thread_info offsets.");
+	OFFSET(TI_TASK, thread_info, task);
+	OFFSET(TI_EXEC_DOMAIN, thread_info, exec_domain);
+	OFFSET(TI_FLAGS, thread_info, flags);
+	OFFSET(TI_TP_VALUE, thread_info, tp_value);
+	OFFSET(TI_CPU, thread_info, cpu);
+	OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
+	OFFSET(TI_ADDR_LIMIT, thread_info, addr_limit);
+	OFFSET(TI_RESTART_BLOCK, thread_info, restart_block);
+	OFFSET(TI_REGS, thread_info, regs);
+	DEFINE(_THREAD_SIZE, THREAD_SIZE);
+	DEFINE(_THREAD_MASK, THREAD_MASK);
+	BLANK();
 }
 
 void output_thread_defines(void)
 {
-	text("/* MIPS specific thread_struct offsets. */");
-	offset("#define THREAD_REG16   ", struct task_struct, thread.reg16);
-	offset("#define THREAD_REG17   ", struct task_struct, thread.reg17);
-	offset("#define THREAD_REG18   ", struct task_struct, thread.reg18);
-	offset("#define THREAD_REG19   ", struct task_struct, thread.reg19);
-	offset("#define THREAD_REG20   ", struct task_struct, thread.reg20);
-	offset("#define THREAD_REG21   ", struct task_struct, thread.reg21);
-	offset("#define THREAD_REG22   ", struct task_struct, thread.reg22);
-	offset("#define THREAD_REG23   ", struct task_struct, thread.reg23);
-	offset("#define THREAD_REG29   ", struct task_struct, thread.reg29);
-	offset("#define THREAD_REG30   ", struct task_struct, thread.reg30);
-	offset("#define THREAD_REG31   ", struct task_struct, thread.reg31);
-	offset("#define THREAD_STATUS  ", struct task_struct,
+	COMMENT("MIPS specific thread_struct offsets.");
+	OFFSET(THREAD_REG16, task_struct, thread.reg16);
+	OFFSET(THREAD_REG17, task_struct, thread.reg17);
+	OFFSET(THREAD_REG18, task_struct, thread.reg18);
+	OFFSET(THREAD_REG19, task_struct, thread.reg19);
+	OFFSET(THREAD_REG20, task_struct, thread.reg20);
+	OFFSET(THREAD_REG21, task_struct, thread.reg21);
+	OFFSET(THREAD_REG22, task_struct, thread.reg22);
+	OFFSET(THREAD_REG23, task_struct, thread.reg23);
+	OFFSET(THREAD_REG29, task_struct, thread.reg29);
+	OFFSET(THREAD_REG30, task_struct, thread.reg30);
+	OFFSET(THREAD_REG31, task_struct, thread.reg31);
+	OFFSET(THREAD_STATUS, task_struct,
 	       thread.cp0_status);
-	offset("#define THREAD_FPU     ", struct task_struct, thread.fpu);
+	OFFSET(THREAD_FPU, task_struct, thread.fpu);
 
-	offset("#define THREAD_BVADDR  ", struct task_struct, \
+	OFFSET(THREAD_BVADDR, task_struct, \
 	       thread.cp0_badvaddr);
-	offset("#define THREAD_BUADDR  ", struct task_struct, \
+	OFFSET(THREAD_BUADDR, task_struct, \
 	       thread.cp0_baduaddr);
-	offset("#define THREAD_ECODE   ", struct task_struct, \
+	OFFSET(THREAD_ECODE, task_struct, \
 	       thread.error_code);
-	offset("#define THREAD_TRAPNO  ", struct task_struct, thread.trap_no);
-	offset("#define THREAD_TRAMP   ", struct task_struct, \
+	OFFSET(THREAD_TRAPNO, task_struct, thread.trap_no);
+	OFFSET(THREAD_TRAMP, task_struct, \
 	       thread.irix_trampoline);
-	offset("#define THREAD_OLDCTX  ", struct task_struct, \
+	OFFSET(THREAD_OLDCTX, task_struct, \
 	       thread.irix_oldctx);
-	linefeed;
+	BLANK();
 }
 
 void output_thread_fpu_defines(void)
 {
-	offset("#define THREAD_FPR0    ",
-	       struct task_struct, thread.fpu.fpr[0]);
-	offset("#define THREAD_FPR1    ",
-	       struct task_struct, thread.fpu.fpr[1]);
-	offset("#define THREAD_FPR2    ",
-	       struct task_struct, thread.fpu.fpr[2]);
-	offset("#define THREAD_FPR3    ",
-	       struct task_struct, thread.fpu.fpr[3]);
-	offset("#define THREAD_FPR4    ",
-	       struct task_struct, thread.fpu.fpr[4]);
-	offset("#define THREAD_FPR5    ",
-	       struct task_struct, thread.fpu.fpr[5]);
-	offset("#define THREAD_FPR6    ",
-	       struct task_struct, thread.fpu.fpr[6]);
-	offset("#define THREAD_FPR7    ",
-	       struct task_struct, thread.fpu.fpr[7]);
-	offset("#define THREAD_FPR8    ",
-	       struct task_struct, thread.fpu.fpr[8]);
-	offset("#define THREAD_FPR9    ",
-	       struct task_struct, thread.fpu.fpr[9]);
-	offset("#define THREAD_FPR10   ",
-	       struct task_struct, thread.fpu.fpr[10]);
-	offset("#define THREAD_FPR11   ",
-	       struct task_struct, thread.fpu.fpr[11]);
-	offset("#define THREAD_FPR12   ",
-	       struct task_struct, thread.fpu.fpr[12]);
-	offset("#define THREAD_FPR13   ",
-	       struct task_struct, thread.fpu.fpr[13]);
-	offset("#define THREAD_FPR14   ",
-	       struct task_struct, thread.fpu.fpr[14]);
-	offset("#define THREAD_FPR15   ",
-	       struct task_struct, thread.fpu.fpr[15]);
-	offset("#define THREAD_FPR16   ",
-	       struct task_struct, thread.fpu.fpr[16]);
-	offset("#define THREAD_FPR17   ",
-	       struct task_struct, thread.fpu.fpr[17]);
-	offset("#define THREAD_FPR18   ",
-	       struct task_struct, thread.fpu.fpr[18]);
-	offset("#define THREAD_FPR19   ",
-	       struct task_struct, thread.fpu.fpr[19]);
-	offset("#define THREAD_FPR20   ",
-	       struct task_struct, thread.fpu.fpr[20]);
-	offset("#define THREAD_FPR21   ",
-	       struct task_struct, thread.fpu.fpr[21]);
-	offset("#define THREAD_FPR22   ",
-	       struct task_struct, thread.fpu.fpr[22]);
-	offset("#define THREAD_FPR23   ",
-	       struct task_struct, thread.fpu.fpr[23]);
-	offset("#define THREAD_FPR24   ",
-	       struct task_struct, thread.fpu.fpr[24]);
-	offset("#define THREAD_FPR25   ",
-	       struct task_struct, thread.fpu.fpr[25]);
-	offset("#define THREAD_FPR26   ",
-	       struct task_struct, thread.fpu.fpr[26]);
-	offset("#define THREAD_FPR27   ",
-	       struct task_struct, thread.fpu.fpr[27]);
-	offset("#define THREAD_FPR28   ",
-	       struct task_struct, thread.fpu.fpr[28]);
-	offset("#define THREAD_FPR29   ",
-	       struct task_struct, thread.fpu.fpr[29]);
-	offset("#define THREAD_FPR30   ",
-	       struct task_struct, thread.fpu.fpr[30]);
-	offset("#define THREAD_FPR31   ",
-	       struct task_struct, thread.fpu.fpr[31]);
+	OFFSET(THREAD_FPR0, task_struct, thread.fpu.fpr[0]);
+	OFFSET(THREAD_FPR1, task_struct, thread.fpu.fpr[1]);
+	OFFSET(THREAD_FPR2, task_struct, thread.fpu.fpr[2]);
+	OFFSET(THREAD_FPR3, task_struct, thread.fpu.fpr[3]);
+	OFFSET(THREAD_FPR4, task_struct, thread.fpu.fpr[4]);
+	OFFSET(THREAD_FPR5, task_struct, thread.fpu.fpr[5]);
+	OFFSET(THREAD_FPR6, task_struct, thread.fpu.fpr[6]);
+	OFFSET(THREAD_FPR7, task_struct, thread.fpu.fpr[7]);
+	OFFSET(THREAD_FPR8, task_struct, thread.fpu.fpr[8]);
+	OFFSET(THREAD_FPR9, task_struct, thread.fpu.fpr[9]);
+	OFFSET(THREAD_FPR10, task_struct, thread.fpu.fpr[10]);
+	OFFSET(THREAD_FPR11, task_struct, thread.fpu.fpr[11]);
+	OFFSET(THREAD_FPR12, task_struct, thread.fpu.fpr[12]);
+	OFFSET(THREAD_FPR13, task_struct, thread.fpu.fpr[13]);
+	OFFSET(THREAD_FPR14, task_struct, thread.fpu.fpr[14]);
+	OFFSET(THREAD_FPR15, task_struct, thread.fpu.fpr[15]);
+	OFFSET(THREAD_FPR16, task_struct, thread.fpu.fpr[16]);
+	OFFSET(THREAD_FPR17, task_struct, thread.fpu.fpr[17]);
+	OFFSET(THREAD_FPR18, task_struct, thread.fpu.fpr[18]);
+	OFFSET(THREAD_FPR19, task_struct, thread.fpu.fpr[19]);
+	OFFSET(THREAD_FPR20, task_struct, thread.fpu.fpr[20]);
+	OFFSET(THREAD_FPR21, task_struct, thread.fpu.fpr[21]);
+	OFFSET(THREAD_FPR22, task_struct, thread.fpu.fpr[22]);
+	OFFSET(THREAD_FPR23, task_struct, thread.fpu.fpr[23]);
+	OFFSET(THREAD_FPR24, task_struct, thread.fpu.fpr[24]);
+	OFFSET(THREAD_FPR25, task_struct, thread.fpu.fpr[25]);
+	OFFSET(THREAD_FPR26, task_struct, thread.fpu.fpr[26]);
+	OFFSET(THREAD_FPR27, task_struct, thread.fpu.fpr[27]);
+	OFFSET(THREAD_FPR28, task_struct, thread.fpu.fpr[28]);
+	OFFSET(THREAD_FPR29, task_struct, thread.fpu.fpr[29]);
+	OFFSET(THREAD_FPR30, task_struct, thread.fpu.fpr[30]);
+	OFFSET(THREAD_FPR31, task_struct, thread.fpu.fpr[31]);
 
-	offset("#define THREAD_FCR31   ",
-	       struct task_struct, thread.fpu.fcr31);
-	linefeed;
+	OFFSET(THREAD_FCR31, task_struct, thread.fpu.fcr31);
+	BLANK();
 }
 
 void output_mm_defines(void)
 {
-	text("/* Size of struct page  */");
-	size("#define STRUCT_PAGE_SIZE   ", struct page);
-	linefeed;
-	text("/* Linux mm_struct offsets. */");
-	offset("#define MM_USERS      ", struct mm_struct, mm_users);
-	offset("#define MM_PGD        ", struct mm_struct, pgd);
-	offset("#define MM_CONTEXT    ", struct mm_struct, context);
-	linefeed;
-	constant("#define _PAGE_SIZE     ", PAGE_SIZE);
-	constant("#define _PAGE_SHIFT    ", PAGE_SHIFT);
-	linefeed;
-	constant("#define _PGD_T_SIZE    ", sizeof(pgd_t));
-	constant("#define _PMD_T_SIZE    ", sizeof(pmd_t));
-	constant("#define _PTE_T_SIZE    ", sizeof(pte_t));
-	linefeed;
-	constant("#define _PGD_T_LOG2    ", PGD_T_LOG2);
-	constant("#define _PMD_T_LOG2    ", PMD_T_LOG2);
-	constant("#define _PTE_T_LOG2    ", PTE_T_LOG2);
-	linefeed;
-	constant("#define _PGD_ORDER     ", PGD_ORDER);
-	constant("#define _PMD_ORDER     ", PMD_ORDER);
-	constant("#define _PTE_ORDER     ", PTE_ORDER);
-	linefeed;
-	constant("#define _PMD_SHIFT     ", PMD_SHIFT);
-	constant("#define _PGDIR_SHIFT   ", PGDIR_SHIFT);
-	linefeed;
-	constant("#define _PTRS_PER_PGD  ", PTRS_PER_PGD);
-	constant("#define _PTRS_PER_PMD  ", PTRS_PER_PMD);
-	constant("#define _PTRS_PER_PTE  ", PTRS_PER_PTE);
-	linefeed;
+	COMMENT("Size of struct page");
+	DEFINE(STRUCT_PAGE_SIZE, sizeof(struct page));
+	BLANK();
+	COMMENT("Linux mm_struct offsets.");
+	OFFSET(MM_USERS, mm_struct, mm_users);
+	OFFSET(MM_PGD, mm_struct, pgd);
+	OFFSET(MM_CONTEXT, mm_struct, context);
+	BLANK();
+	DEFINE(_PAGE_SIZE, PAGE_SIZE);
+	DEFINE(_PAGE_SHIFT, PAGE_SHIFT);
+	BLANK();
+	DEFINE(_PGD_T_SIZE, sizeof(pgd_t));
+	DEFINE(_PMD_T_SIZE, sizeof(pmd_t));
+	DEFINE(_PTE_T_SIZE, sizeof(pte_t));
+	BLANK();
+	DEFINE(_PGD_T_LOG2, PGD_T_LOG2);
+	DEFINE(_PMD_T_LOG2, PMD_T_LOG2);
+	DEFINE(_PTE_T_LOG2, PTE_T_LOG2);
+	BLANK();
+	DEFINE(_PGD_ORDER, PGD_ORDER);
+	DEFINE(_PMD_ORDER, PMD_ORDER);
+	DEFINE(_PTE_ORDER, PTE_ORDER);
+	BLANK();
+	DEFINE(_PMD_SHIFT, PMD_SHIFT);
+	DEFINE(_PGDIR_SHIFT, PGDIR_SHIFT);
+	BLANK();
+	DEFINE(_PTRS_PER_PGD, PTRS_PER_PGD);
+	DEFINE(_PTRS_PER_PMD, PTRS_PER_PMD);
+	DEFINE(_PTRS_PER_PTE, PTRS_PER_PTE);
+	BLANK();
 }
 
 #ifdef CONFIG_32BIT
 void output_sc_defines(void)
 {
-	text("/* Linux sigcontext offsets. */");
-	offset("#define SC_REGS       ", struct sigcontext, sc_regs);
-	offset("#define SC_FPREGS     ", struct sigcontext, sc_fpregs);
-	offset("#define SC_ACX        ", struct sigcontext, sc_acx);
-	offset("#define SC_MDHI       ", struct sigcontext, sc_mdhi);
-	offset("#define SC_MDLO       ", struct sigcontext, sc_mdlo);
-	offset("#define SC_PC         ", struct sigcontext, sc_pc);
-	offset("#define SC_FPC_CSR    ", struct sigcontext, sc_fpc_csr);
-	offset("#define SC_FPC_EIR    ", struct sigcontext, sc_fpc_eir);
-	offset("#define SC_HI1        ", struct sigcontext, sc_hi1);
-	offset("#define SC_LO1        ", struct sigcontext, sc_lo1);
-	offset("#define SC_HI2        ", struct sigcontext, sc_hi2);
-	offset("#define SC_LO2        ", struct sigcontext, sc_lo2);
-	offset("#define SC_HI3        ", struct sigcontext, sc_hi3);
-	offset("#define SC_LO3        ", struct sigcontext, sc_lo3);
-	linefeed;
+	COMMENT("Linux sigcontext offsets.");
+	OFFSET(SC_REGS, sigcontext, sc_regs);
+	OFFSET(SC_FPREGS, sigcontext, sc_fpregs);
+	OFFSET(SC_ACX, sigcontext, sc_acx);
+	OFFSET(SC_MDHI, sigcontext, sc_mdhi);
+	OFFSET(SC_MDLO, sigcontext, sc_mdlo);
+	OFFSET(SC_PC, sigcontext, sc_pc);
+	OFFSET(SC_FPC_CSR, sigcontext, sc_fpc_csr);
+	OFFSET(SC_FPC_EIR, sigcontext, sc_fpc_eir);
+	OFFSET(SC_HI1, sigcontext, sc_hi1);
+	OFFSET(SC_LO1, sigcontext, sc_lo1);
+	OFFSET(SC_HI2, sigcontext, sc_hi2);
+	OFFSET(SC_LO2, sigcontext, sc_lo2);
+	OFFSET(SC_HI3, sigcontext, sc_hi3);
+	OFFSET(SC_LO3, sigcontext, sc_lo3);
+	BLANK();
 }
 #endif
 
 #ifdef CONFIG_64BIT
 void output_sc_defines(void)
 {
-	text("/* Linux sigcontext offsets. */");
-	offset("#define SC_REGS       ", struct sigcontext, sc_regs);
-	offset("#define SC_FPREGS     ", struct sigcontext, sc_fpregs);
-	offset("#define SC_MDHI       ", struct sigcontext, sc_mdhi);
-	offset("#define SC_MDLO       ", struct sigcontext, sc_mdlo);
-	offset("#define SC_PC         ", struct sigcontext, sc_pc);
-	offset("#define SC_FPC_CSR    ", struct sigcontext, sc_fpc_csr);
-	linefeed;
+	COMMENT("Linux sigcontext offsets.");
+	OFFSET(SC_REGS, sigcontext, sc_regs);
+	OFFSET(SC_FPREGS, sigcontext, sc_fpregs);
+	OFFSET(SC_MDHI, sigcontext, sc_mdhi);
+	OFFSET(SC_MDLO, sigcontext, sc_mdlo);
+	OFFSET(SC_PC, sigcontext, sc_pc);
+	OFFSET(SC_FPC_CSR, sigcontext, sc_fpc_csr);
+	BLANK();
 }
 #endif
 
 #ifdef CONFIG_MIPS32_COMPAT
 void output_sc32_defines(void)
 {
-	text("/* Linux 32-bit sigcontext offsets. */");
-	offset("#define SC32_FPREGS     ", struct sigcontext32, sc_fpregs);
-	offset("#define SC32_FPC_CSR    ", struct sigcontext32, sc_fpc_csr);
-	offset("#define SC32_FPC_EIR    ", struct sigcontext32, sc_fpc_eir);
-	linefeed;
+	COMMENT("Linux 32-bit sigcontext offsets.");
+	OFFSET(SC32_FPREGS, sigcontext32, sc_fpregs);
+	OFFSET(SC32_FPC_CSR, sigcontext32, sc_fpc_csr);
+	OFFSET(SC32_FPC_EIR, sigcontext32, sc_fpc_eir);
+	BLANK();
 }
 #endif
 
 void output_signal_defined(void)
 {
-	text("/* Linux signal numbers. */");
-	constant("#define _SIGHUP     ", SIGHUP);
-	constant("#define _SIGINT     ", SIGINT);
-	constant("#define _SIGQUIT    ", SIGQUIT);
-	constant("#define _SIGILL     ", SIGILL);
-	constant("#define _SIGTRAP    ", SIGTRAP);
-	constant("#define _SIGIOT     ", SIGIOT);
-	constant("#define _SIGABRT    ", SIGABRT);
-	constant("#define _SIGEMT     ", SIGEMT);
-	constant("#define _SIGFPE     ", SIGFPE);
-	constant("#define _SIGKILL    ", SIGKILL);
-	constant("#define _SIGBUS     ", SIGBUS);
-	constant("#define _SIGSEGV    ", SIGSEGV);
-	constant("#define _SIGSYS     ", SIGSYS);
-	constant("#define _SIGPIPE    ", SIGPIPE);
-	constant("#define _SIGALRM    ", SIGALRM);
-	constant("#define _SIGTERM    ", SIGTERM);
-	constant("#define _SIGUSR1    ", SIGUSR1);
-	constant("#define _SIGUSR2    ", SIGUSR2);
-	constant("#define _SIGCHLD    ", SIGCHLD);
-	constant("#define _SIGPWR     ", SIGPWR);
-	constant("#define _SIGWINCH   ", SIGWINCH);
-	constant("#define _SIGURG     ", SIGURG);
-	constant("#define _SIGIO      ", SIGIO);
-	constant("#define _SIGSTOP    ", SIGSTOP);
-	constant("#define _SIGTSTP    ", SIGTSTP);
-	constant("#define _SIGCONT    ", SIGCONT);
-	constant("#define _SIGTTIN    ", SIGTTIN);
-	constant("#define _SIGTTOU    ", SIGTTOU);
-	constant("#define _SIGVTALRM  ", SIGVTALRM);
-	constant("#define _SIGPROF    ", SIGPROF);
-	constant("#define _SIGXCPU    ", SIGXCPU);
-	constant("#define _SIGXFSZ    ", SIGXFSZ);
-	linefeed;
+	COMMENT("Linux signal numbers.");
+	DEFINE(_SIGHUP, SIGHUP);
+	DEFINE(_SIGINT, SIGINT);
+	DEFINE(_SIGQUIT, SIGQUIT);
+	DEFINE(_SIGILL, SIGILL);
+	DEFINE(_SIGTRAP, SIGTRAP);
+	DEFINE(_SIGIOT, SIGIOT);
+	DEFINE(_SIGABRT, SIGABRT);
+	DEFINE(_SIGEMT, SIGEMT);
+	DEFINE(_SIGFPE, SIGFPE);
+	DEFINE(_SIGKILL, SIGKILL);
+	DEFINE(_SIGBUS, SIGBUS);
+	DEFINE(_SIGSEGV, SIGSEGV);
+	DEFINE(_SIGSYS, SIGSYS);
+	DEFINE(_SIGPIPE, SIGPIPE);
+	DEFINE(_SIGALRM, SIGALRM);
+	DEFINE(_SIGTERM, SIGTERM);
+	DEFINE(_SIGUSR1, SIGUSR1);
+	DEFINE(_SIGUSR2, SIGUSR2);
+	DEFINE(_SIGCHLD, SIGCHLD);
+	DEFINE(_SIGPWR, SIGPWR);
+	DEFINE(_SIGWINCH, SIGWINCH);
+	DEFINE(_SIGURG, SIGURG);
+	DEFINE(_SIGIO, SIGIO);
+	DEFINE(_SIGSTOP, SIGSTOP);
+	DEFINE(_SIGTSTP, SIGTSTP);
+	DEFINE(_SIGCONT, SIGCONT);
+	DEFINE(_SIGTTIN, SIGTTIN);
+	DEFINE(_SIGTTOU, SIGTTOU);
+	DEFINE(_SIGVTALRM, SIGVTALRM);
+	DEFINE(_SIGPROF, SIGPROF);
+	DEFINE(_SIGXCPU, SIGXCPU);
+	DEFINE(_SIGXFSZ, SIGXFSZ);
+	BLANK();
 }
 
 void output_irq_cpustat_t_defines(void)
 {
-	text("/* Linux irq_cpustat_t offsets. */");
-	offset("#define IC_SOFTIRQ_PENDING ", irq_cpustat_t, __softirq_pending);
-	size("#define IC_IRQ_CPUSTAT_T   ", irq_cpustat_t);
-	linefeed;
+	COMMENT("Linux irq_cpustat_t offsets.");
+	DEFINE(IC_SOFTIRQ_PENDING,
+			offsetof(irq_cpustat_t, __softirq_pending));
+	DEFINE(IC_IRQ_CPUSTAT_T, sizeof(irq_cpustat_t));
+	BLANK();
 }
diff --git a/trunk/arch/mips/kernel/cevt-ds1287.c b/trunk/arch/mips/kernel/cevt-ds1287.c
new file mode 100644
index 000000000000..df4acb68bfb5
--- /dev/null
+++ b/trunk/arch/mips/kernel/cevt-ds1287.c
@@ -0,0 +1,129 @@
+/*
+ *  DS1287 clockevent driver
+ *
+ *  Copyright (C) 2008  Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#include <linux/clockchips.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/mc146818rtc.h>
+
+#include <asm/time.h>
+
+int ds1287_timer_state(void)
+{
+	return (CMOS_READ(RTC_REG_C) & RTC_PF) != 0;
+}
+
+int ds1287_set_base_clock(unsigned int hz)
+{
+	u8 rate;
+
+	switch (hz) {
+	case 128:
+		rate = 0x9;
+		break;
+	case 256:
+		rate = 0x8;
+		break;
+	case 1024:
+		rate = 0x6;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	CMOS_WRITE(RTC_REF_CLCK_32KHZ | rate, RTC_REG_A);
+
+	return 0;
+}
+
+static int ds1287_set_next_event(unsigned long delta,
+				 struct clock_event_device *evt)
+{
+	return -EINVAL;
+}
+
+static void ds1287_set_mode(enum clock_event_mode mode,
+			    struct clock_event_device *evt)
+{
+	u8 val;
+
+	spin_lock(&rtc_lock);
+
+	val = CMOS_READ(RTC_REG_B);
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		val |= RTC_PIE;
+		break;
+	default:
+		val &= ~RTC_PIE;
+		break;
+	}
+
+	CMOS_WRITE(val, RTC_REG_B);
+
+	spin_unlock(&rtc_lock);
+}
+
+static void ds1287_event_handler(struct clock_event_device *dev)
+{
+}
+
+static struct clock_event_device ds1287_clockevent = {
+	.name		= "ds1287",
+	.features	= CLOCK_EVT_FEAT_PERIODIC,
+	.cpumask	= CPU_MASK_CPU0,
+	.set_next_event	= ds1287_set_next_event,
+	.set_mode	= ds1287_set_mode,
+	.event_handler	= ds1287_event_handler,
+};
+
+static irqreturn_t ds1287_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *cd = &ds1287_clockevent;
+
+	/* Ack the RTC interrupt. */
+	CMOS_READ(RTC_REG_C);
+
+	cd->event_handler(cd);
+
+	return IRQ_HANDLED;
+}
+
+static struct irqaction ds1287_irqaction = {
+	.handler	= ds1287_interrupt,
+	.flags		= IRQF_DISABLED | IRQF_PERCPU,
+	.name		= "ds1287",
+};
+
+int __init ds1287_clockevent_init(int irq)
+{
+	struct clock_event_device *cd;
+
+	cd = &ds1287_clockevent;
+	cd->rating = 100;
+	cd->irq = irq;
+	clockevent_set_clock(cd, 32768);
+	cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd);
+	cd->min_delta_ns = clockevent_delta2ns(0x300, cd);
+
+	clockevents_register_device(&ds1287_clockevent);
+
+	return setup_irq(irq, &ds1287_irqaction);
+}
diff --git a/trunk/arch/mips/kernel/cevt-gt641xx.c b/trunk/arch/mips/kernel/cevt-gt641xx.c
index c36772631fe0..6e2f58520afb 100644
--- a/trunk/arch/mips/kernel/cevt-gt641xx.c
+++ b/trunk/arch/mips/kernel/cevt-gt641xx.c
@@ -25,8 +25,6 @@
 #include <asm/gt64120.h>
 #include <asm/time.h>
 
-#include <irq.h>
-
 static DEFINE_SPINLOCK(gt641xx_timer_lock);
 static unsigned int gt641xx_base_clock;
 
diff --git a/trunk/arch/mips/kernel/cpu-probe.c b/trunk/arch/mips/kernel/cpu-probe.c
index 89c3304cb93c..335a6ae3d594 100644
--- a/trunk/arch/mips/kernel/cpu-probe.c
+++ b/trunk/arch/mips/kernel/cpu-probe.c
@@ -169,6 +169,7 @@ static inline void check_wait(void)
 
 	case CPU_24K:
 	case CPU_34K:
+	case CPU_1004K:
 		cpu_wait = r4k_wait;
 		if (read_c0_config7() & MIPS_CONF7_WII)
 			cpu_wait = r4k_wait_irqoff;
@@ -675,6 +676,12 @@ static void __cpuinit decode_configs(struct cpuinfo_mips *c)
 		return;
 }
 
+#ifdef CONFIG_CPU_MIPSR2
+extern void spram_config(void);
+#else
+static inline void spram_config(void) {}
+#endif
+
 static inline void cpu_probe_mips(struct cpuinfo_mips *c)
 {
 	decode_configs(c);
@@ -711,7 +718,12 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c)
 	case PRID_IMP_74K:
 		c->cputype = CPU_74K;
 		break;
+	case PRID_IMP_1004K:
+		c->cputype = CPU_1004K;
+		break;
 	}
+
+	spram_config();
 }
 
 static inline void cpu_probe_alchemy(struct cpuinfo_mips *c)
@@ -778,7 +790,7 @@ static inline void cpu_probe_sandcraft(struct cpuinfo_mips *c)
 	}
 }
 
-static inline void cpu_probe_philips(struct cpuinfo_mips *c)
+static inline void cpu_probe_nxp(struct cpuinfo_mips *c)
 {
 	decode_configs(c);
 	switch (c->processor_id & 0xff00) {
@@ -787,7 +799,7 @@ static inline void cpu_probe_philips(struct cpuinfo_mips *c)
 		c->isa_level = MIPS_CPU_ISA_M32R1;
 		break;
 	default:
-		panic("Unknown Philips Core!"); /* REVISIT: die? */
+		panic("Unknown NXP Core!"); /* REVISIT: die? */
 		break;
 	}
 }
@@ -876,6 +888,7 @@ static __cpuinit const char *cpu_to_name(struct cpuinfo_mips *c)
 	case CPU_24K:		name = "MIPS 24K"; break;
 	case CPU_25KF:		name = "MIPS 25Kf"; break;
 	case CPU_34K:		name = "MIPS 34K"; break;
+	case CPU_1004K:		name = "MIPS 1004K"; break;
 	case CPU_74K:		name = "MIPS 74K"; break;
 	case CPU_VR4111:	name = "NEC VR4111"; break;
 	case CPU_VR4121:	name = "NEC VR4121"; break;
@@ -925,8 +938,8 @@ __cpuinit void cpu_probe(void)
 	case PRID_COMP_SANDCRAFT:
 		cpu_probe_sandcraft(c);
 		break;
- 	case PRID_COMP_PHILIPS:
-		cpu_probe_philips(c);
+	case PRID_COMP_NXP:
+		cpu_probe_nxp(c);
 		break;
 	default:
 		c->cputype = CPU_UNKNOWN;
diff --git a/trunk/arch/mips/kernel/csrc-ioasic.c b/trunk/arch/mips/kernel/csrc-ioasic.c
new file mode 100644
index 000000000000..1d5f63cf8997
--- /dev/null
+++ b/trunk/arch/mips/kernel/csrc-ioasic.c
@@ -0,0 +1,65 @@
+/*
+ *  DEC I/O ASIC's counter clocksource
+ *
+ *  Copyright (C) 2008  Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#include <linux/clocksource.h>
+#include <linux/init.h>
+
+#include <asm/ds1287.h>
+#include <asm/time.h>
+#include <asm/dec/ioasic.h>
+#include <asm/dec/ioasic_addrs.h>
+
+static cycle_t dec_ioasic_hpt_read(void)
+{
+	return ioasic_read(IO_REG_FCTR);
+}
+
+static struct clocksource clocksource_dec = {
+	.name		= "dec-ioasic",
+	.read		= dec_ioasic_hpt_read,
+	.mask		= CLOCKSOURCE_MASK(32),
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+void __init dec_ioasic_clocksource_init(void)
+{
+	unsigned int freq;
+	u32 start, end;
+	int i = HZ / 10;
+
+
+	while (!ds1287_timer_state())
+		;
+
+	start = dec_ioasic_hpt_read();
+
+	while (i--)
+		while (!ds1287_timer_state())
+			;
+
+	end = dec_ioasic_hpt_read();
+
+	freq = (end - start) * 10;
+	printk(KERN_INFO "I/O ASIC clock frequency %dHz\n", freq);
+
+	clocksource_dec.rating = 200 + freq / 10000000;
+	clocksource_set_clock(&clocksource_dec, freq);
+
+	clocksource_register(&clocksource_dec);
+}
diff --git a/trunk/arch/mips/kernel/gpio_txx9.c b/trunk/arch/mips/kernel/gpio_txx9.c
new file mode 100644
index 000000000000..b1436a857998
--- /dev/null
+++ b/trunk/arch/mips/kernel/gpio_txx9.c
@@ -0,0 +1,87 @@
+/*
+ * A gpio chip driver for TXx9 SoCs
+ *
+ * Copyright (C) 2008 Atsushi Nemoto <anemo@mba.ocn.ne.jp>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/gpio.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <asm/txx9pio.h>
+
+static DEFINE_SPINLOCK(txx9_gpio_lock);
+
+static struct txx9_pio_reg __iomem *txx9_pioptr;
+
+static int txx9_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+	return __raw_readl(&txx9_pioptr->din) & (1 << offset);
+}
+
+static void txx9_gpio_set_raw(unsigned int offset, int value)
+{
+	u32 val;
+	val = __raw_readl(&txx9_pioptr->dout);
+	if (value)
+		val |= 1 << offset;
+	else
+		val &= ~(1 << offset);
+	__raw_writel(val, &txx9_pioptr->dout);
+}
+
+static void txx9_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			  int value)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&txx9_gpio_lock, flags);
+	txx9_gpio_set_raw(offset, value);
+	mmiowb();
+	spin_unlock_irqrestore(&txx9_gpio_lock, flags);
+}
+
+static int txx9_gpio_dir_in(struct gpio_chip *chip, unsigned int offset)
+{
+	spin_lock_irq(&txx9_gpio_lock);
+	__raw_writel(__raw_readl(&txx9_pioptr->dir) & ~(1 << offset),
+		     &txx9_pioptr->dir);
+	mmiowb();
+	spin_unlock_irq(&txx9_gpio_lock);
+	return 0;
+}
+
+static int txx9_gpio_dir_out(struct gpio_chip *chip, unsigned int offset,
+			     int value)
+{
+	spin_lock_irq(&txx9_gpio_lock);
+	txx9_gpio_set_raw(offset, value);
+	__raw_writel(__raw_readl(&txx9_pioptr->dir) | (1 << offset),
+		     &txx9_pioptr->dir);
+	mmiowb();
+	spin_unlock_irq(&txx9_gpio_lock);
+	return 0;
+}
+
+static struct gpio_chip txx9_gpio_chip = {
+	.get = txx9_gpio_get,
+	.set = txx9_gpio_set,
+	.direction_input = txx9_gpio_dir_in,
+	.direction_output = txx9_gpio_dir_out,
+	.label = "TXx9",
+};
+
+int __init txx9_gpio_init(unsigned long baseaddr,
+			  unsigned int base, unsigned int num)
+{
+	txx9_pioptr = ioremap(baseaddr, sizeof(struct txx9_pio_reg));
+	if (!txx9_pioptr)
+		return -ENODEV;
+	txx9_gpio_chip.base = base;
+	txx9_gpio_chip.ngpio = num;
+	return gpiochip_add(&txx9_gpio_chip);
+}
diff --git a/trunk/arch/mips/kernel/irq-gic.c b/trunk/arch/mips/kernel/irq-gic.c
new file mode 100644
index 000000000000..f0a4bb19e096
--- /dev/null
+++ b/trunk/arch/mips/kernel/irq-gic.c
@@ -0,0 +1,295 @@
+#undef DEBUG
+
+#include <linux/bitmap.h>
+#include <linux/init.h>
+
+#include <asm/io.h>
+#include <asm/gic.h>
+#include <asm/gcmpregs.h>
+#include <asm/mips-boards/maltaint.h>
+#include <asm/irq.h>
+#include <linux/hardirq.h>
+#include <asm-generic/bitops/find.h>
+
+
+static unsigned long _gic_base;
+static unsigned int _irqbase, _mapsize, numvpes, numintrs;
+static struct gic_intr_map *_intrmap;
+
+static struct gic_pcpu_mask pcpu_masks[NR_CPUS];
+static struct gic_pending_regs pending_regs[NR_CPUS];
+static struct gic_intrmask_regs intrmask_regs[NR_CPUS];
+
+#define gic_wedgeb2bok 0	/*
+				 * Can GIC handle b2b writes to wedge register?
+				 */
+#if gic_wedgeb2bok == 0
+static DEFINE_SPINLOCK(gic_wedgeb2b_lock);
+#endif
+
+void gic_send_ipi(unsigned int intr)
+{
+#if gic_wedgeb2bok == 0
+	unsigned long flags;
+#endif
+	pr_debug("CPU%d: %s status %08x\n", smp_processor_id(), __func__,
+		 read_c0_status());
+	if (!gic_wedgeb2bok)
+		spin_lock_irqsave(&gic_wedgeb2b_lock, flags);
+	GICWRITE(GIC_REG(SHARED, GIC_SH_WEDGE), 0x80000000 | intr);
+	if (!gic_wedgeb2bok) {
+		(void) GIC_REG(SHARED, GIC_SH_CONFIG);
+		spin_unlock_irqrestore(&gic_wedgeb2b_lock, flags);
+	}
+}
+
+/* This is Malta specific and needs to be exported */
+static void vpe_local_setup(unsigned int numvpes)
+{
+	int i;
+	unsigned long timer_interrupt = 5, perf_interrupt = 5;
+	unsigned int vpe_ctl;
+
+	/*
+	 * Setup the default performance counter timer interrupts
+	 * for all VPEs
+	 */
+	for (i = 0; i < numvpes; i++) {
+		GICWRITE(GIC_REG(VPE_LOCAL, GIC_VPE_OTHER_ADDR), i);
+
+		/* Are Interrupts locally routable? */
+		GICREAD(GIC_REG(VPE_OTHER, GIC_VPE_CTL), vpe_ctl);
+		if (vpe_ctl & GIC_VPE_CTL_TIMER_RTBL_MSK)
+			GICWRITE(GIC_REG(VPE_OTHER, GIC_VPE_TIMER_MAP),
+				 GIC_MAP_TO_PIN_MSK | timer_interrupt);
+
+		if (vpe_ctl & GIC_VPE_CTL_PERFCNT_RTBL_MSK)
+			GICWRITE(GIC_REG(VPE_OTHER, GIC_VPE_PERFCTR_MAP),
+				 GIC_MAP_TO_PIN_MSK | perf_interrupt);
+	}
+}
+
+unsigned int gic_get_int(void)
+{
+	unsigned int i;
+	unsigned long *pending, *intrmask, *pcpu_mask;
+	unsigned long *pending_abs, *intrmask_abs;
+
+	/* Get per-cpu bitmaps */
+	pending = pending_regs[smp_processor_id()].pending;
+	intrmask = intrmask_regs[smp_processor_id()].intrmask;
+	pcpu_mask = pcpu_masks[smp_processor_id()].pcpu_mask;
+
+	pending_abs = (unsigned long *) GIC_REG_ABS_ADDR(SHARED,
+							 GIC_SH_PEND_31_0_OFS);
+	intrmask_abs = (unsigned long *) GIC_REG_ABS_ADDR(SHARED,
+							  GIC_SH_MASK_31_0_OFS);
+
+	for (i = 0; i < BITS_TO_LONGS(GIC_NUM_INTRS); i++) {
+		GICREAD(*pending_abs, pending[i]);
+		GICREAD(*intrmask_abs, intrmask[i]);
+		pending_abs++;
+		intrmask_abs++;
+	}
+
+	bitmap_and(pending, pending, intrmask, GIC_NUM_INTRS);
+	bitmap_and(pending, pending, pcpu_mask, GIC_NUM_INTRS);
+
+	i = find_first_bit(pending, GIC_NUM_INTRS);
+
+	pr_debug("CPU%d: %s pend=%d\n", smp_processor_id(), __func__, i);
+
+	return i;
+}
+
+static unsigned int gic_irq_startup(unsigned int irq)
+{
+	pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq);
+	irq -= _irqbase;
+	/* FIXME: this is wrong for !GICISWORDLITTLEENDIAN */
+	GICWRITE(GIC_REG_ADDR(SHARED, (GIC_SH_SMASK_31_0_OFS + (irq / 32))),
+		 1 << (irq % 32));
+	return 0;
+}
+
+static void gic_irq_ack(unsigned int irq)
+{
+#if gic_wedgeb2bok == 0
+	unsigned long flags;
+#endif
+	pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq);
+	irq -= _irqbase;
+	GICWRITE(GIC_REG_ADDR(SHARED, (GIC_SH_RMASK_31_0_OFS + (irq / 32))),
+		 1 << (irq % 32));
+
+	if (_intrmap[irq].trigtype == GIC_TRIG_EDGE) {
+		if (!gic_wedgeb2bok)
+			spin_lock_irqsave(&gic_wedgeb2b_lock, flags);
+		GICWRITE(GIC_REG(SHARED, GIC_SH_WEDGE), irq);
+		if (!gic_wedgeb2bok) {
+			(void) GIC_REG(SHARED, GIC_SH_CONFIG);
+			spin_unlock_irqrestore(&gic_wedgeb2b_lock, flags);
+		}
+	}
+}
+
+static void gic_mask_irq(unsigned int irq)
+{
+	pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq);
+	irq -= _irqbase;
+	/* FIXME: this is wrong for !GICISWORDLITTLEENDIAN */
+	GICWRITE(GIC_REG_ADDR(SHARED, (GIC_SH_RMASK_31_0_OFS + (irq / 32))),
+		 1 << (irq % 32));
+}
+
+static void gic_unmask_irq(unsigned int irq)
+{
+	pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq);
+	irq -= _irqbase;
+	/* FIXME: this is wrong for !GICISWORDLITTLEENDIAN */
+	GICWRITE(GIC_REG_ADDR(SHARED, (GIC_SH_SMASK_31_0_OFS + (irq / 32))),
+		 1 << (irq % 32));
+}
+
+#ifdef CONFIG_SMP
+
+static DEFINE_SPINLOCK(gic_lock);
+
+static void gic_set_affinity(unsigned int irq, cpumask_t cpumask)
+{
+	cpumask_t	tmp = CPU_MASK_NONE;
+	unsigned long	flags;
+	int		i;
+
+	pr_debug(KERN_DEBUG "%s called\n", __func__);
+	irq -= _irqbase;
+
+	cpus_and(tmp, cpumask, cpu_online_map);
+	if (cpus_empty(tmp))
+		return;
+
+	/* Assumption : cpumask refers to a single CPU */
+	spin_lock_irqsave(&gic_lock, flags);
+	for (;;) {
+		/* Re-route this IRQ */
+		GIC_SH_MAP_TO_VPE_SMASK(irq, first_cpu(tmp));
+
+		/*
+		 * FIXME: assumption that _intrmap is ordered and has no holes
+		 */
+
+		/* Update the intr_map */
+		_intrmap[irq].cpunum = first_cpu(tmp);
+
+		/* Update the pcpu_masks */
+		for (i = 0; i < NR_CPUS; i++)
+			clear_bit(irq, pcpu_masks[i].pcpu_mask);
+		set_bit(irq, pcpu_masks[first_cpu(tmp)].pcpu_mask);
+
+	}
+	irq_desc[irq].affinity = cpumask;
+	spin_unlock_irqrestore(&gic_lock, flags);
+
+}
+#endif
+
+static struct irq_chip gic_irq_controller = {
+	.name		=	"MIPS GIC",
+	.startup	=	gic_irq_startup,
+	.ack		=	gic_irq_ack,
+	.mask		=	gic_mask_irq,
+	.mask_ack	=	gic_mask_irq,
+	.unmask		=	gic_unmask_irq,
+	.eoi		=	gic_unmask_irq,
+#ifdef CONFIG_SMP
+	.set_affinity	=	gic_set_affinity,
+#endif
+};
+
+static void __init setup_intr(unsigned int intr, unsigned int cpu,
+	unsigned int pin, unsigned int polarity, unsigned int trigtype)
+{
+	/* Setup Intr to Pin mapping */
+	if (pin & GIC_MAP_TO_NMI_MSK) {
+		GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_MAP_TO_PIN(intr)), pin);
+		/* FIXME: hack to route NMI to all cpu's */
+		for (cpu = 0; cpu < NR_CPUS; cpu += 32) {
+			GICWRITE(GIC_REG_ADDR(SHARED,
+					  GIC_SH_MAP_TO_VPE_REG_OFF(intr, cpu)),
+				 0xffffffff);
+		}
+	} else {
+		GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_MAP_TO_PIN(intr)),
+			 GIC_MAP_TO_PIN_MSK | pin);
+		/* Setup Intr to CPU mapping */
+		GIC_SH_MAP_TO_VPE_SMASK(intr, cpu);
+	}
+
+	/* Setup Intr Polarity */
+	GIC_SET_POLARITY(intr, polarity);
+
+	/* Setup Intr Trigger Type */
+	GIC_SET_TRIGGER(intr, trigtype);
+
+	/* Init Intr Masks */
+	GIC_SET_INTR_MASK(intr, 0);
+}
+
+static void __init gic_basic_init(void)
+{
+	unsigned int i, cpu;
+
+	/* Setup defaults */
+	for (i = 0; i < GIC_NUM_INTRS; i++) {
+		GIC_SET_POLARITY(i, GIC_POL_POS);
+		GIC_SET_TRIGGER(i, GIC_TRIG_LEVEL);
+		GIC_SET_INTR_MASK(i, 0);
+	}
+
+	/* Setup specifics */
+	for (i = 0; i < _mapsize; i++) {
+		cpu = _intrmap[i].cpunum;
+		if (cpu == X)
+			continue;
+
+		setup_intr(_intrmap[i].intrnum,
+				_intrmap[i].cpunum,
+				_intrmap[i].pin,
+				_intrmap[i].polarity,
+				_intrmap[i].trigtype);
+		/* Initialise per-cpu Interrupt software masks */
+		if (_intrmap[i].ipiflag)
+			set_bit(_intrmap[i].intrnum, pcpu_masks[cpu].pcpu_mask);
+	}
+
+	vpe_local_setup(numvpes);
+
+	for (i = _irqbase; i < (_irqbase + numintrs); i++)
+		set_irq_chip(i, &gic_irq_controller);
+}
+
+void __init gic_init(unsigned long gic_base_addr,
+		     unsigned long gic_addrspace_size,
+		     struct gic_intr_map *intr_map, unsigned int intr_map_size,
+		     unsigned int irqbase)
+{
+	unsigned int gicconfig;
+
+	_gic_base = (unsigned long) ioremap_nocache(gic_base_addr,
+						    gic_addrspace_size);
+	_irqbase = irqbase;
+	_intrmap = intr_map;
+	_mapsize = intr_map_size;
+
+	GICREAD(GIC_REG(SHARED, GIC_SH_CONFIG), gicconfig);
+	numintrs = (gicconfig & GIC_SH_CONFIG_NUMINTRS_MSK) >>
+		   GIC_SH_CONFIG_NUMINTRS_SHF;
+	numintrs = ((numintrs + 1) * 8);
+
+	numvpes = (gicconfig & GIC_SH_CONFIG_NUMVPES_MSK) >>
+		  GIC_SH_CONFIG_NUMVPES_SHF;
+
+	pr_debug("%s called\n", __func__);
+
+	gic_basic_init();
+}
diff --git a/trunk/arch/mips/kernel/irq-msc01.c b/trunk/arch/mips/kernel/irq-msc01.c
index 4edc7e451d91..963c16d266ab 100644
--- a/trunk/arch/mips/kernel/irq-msc01.c
+++ b/trunk/arch/mips/kernel/irq-msc01.c
@@ -17,6 +17,7 @@
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/msc01_ic.h>
+#include <asm/traps.h>
 
 static unsigned long _icctrl_msc;
 #define MSC01_IC_REG_BASE	_icctrl_msc
@@ -98,14 +99,13 @@ void ll_msc_irq(void)
 	}
 }
 
-void
-msc_bind_eic_interrupt(unsigned int irq, unsigned int set)
+static void msc_bind_eic_interrupt(int irq, int set)
 {
 	MSCIC_WRITE(MSC01_IC_RAMW,
 		    (irq<<MSC01_IC_RAMW_ADDR_SHF) | (set<<MSC01_IC_RAMW_DATA_SHF));
 }
 
-struct irq_chip msc_levelirq_type = {
+static struct irq_chip msc_levelirq_type = {
 	.name = "SOC-it-Level",
 	.ack = level_mask_and_ack_msc_irq,
 	.mask = mask_msc_irq,
@@ -115,7 +115,7 @@ struct irq_chip msc_levelirq_type = {
 	.end = end_msc_irq,
 };
 
-struct irq_chip msc_edgeirq_type = {
+static struct irq_chip msc_edgeirq_type = {
 	.name = "SOC-it-Edge",
 	.ack = edge_mask_and_ack_msc_irq,
 	.mask = mask_msc_irq,
@@ -128,8 +128,6 @@ struct irq_chip msc_edgeirq_type = {
 
 void __init init_msc_irqs(unsigned long icubase, unsigned int irqbase, msc_irqmap_t *imp, int nirq)
 {
-	extern void (*board_bind_eic_interrupt)(unsigned int irq, unsigned int regset);
-
 	_icctrl_msc = (unsigned long) ioremap(icubase, 0x40000);
 
 	/* Reset interrupt controller - initialises all registers to 0 */
diff --git a/trunk/arch/mips/kernel/signal-common.h b/trunk/arch/mips/kernel/signal-common.h
index c0faabd52010..6c8e8c4246f7 100644
--- a/trunk/arch/mips/kernel/signal-common.h
+++ b/trunk/arch/mips/kernel/signal-common.h
@@ -14,7 +14,7 @@
 /* #define DEBUG_SIG */
 
 #ifdef DEBUG_SIG
-#  define DEBUGP(fmt, args...) printk("%s: " fmt, __FUNCTION__ , ##args)
+#  define DEBUGP(fmt, args...) printk("%s: " fmt, __func__, ##args)
 #else
 #  define DEBUGP(fmt, args...)
 #endif
diff --git a/trunk/arch/mips/kernel/smp-cmp.c b/trunk/arch/mips/kernel/smp-cmp.c
new file mode 100644
index 000000000000..ca476c4f62a5
--- /dev/null
+++ b/trunk/arch/mips/kernel/smp-cmp.c
@@ -0,0 +1,265 @@
+/*
+ *  This program is free software; you can distribute it and/or modify it
+ *  under the terms of the GNU General Public License (Version 2) as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope it will be useful, but WITHOUT
+ *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ *  for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
+ *
+ * Copyright (C) 2007 MIPS Technologies, Inc.
+ *    Chris Dearman (chris@mips.com)
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cpumask.h>
+#include <linux/interrupt.h>
+#include <linux/compiler.h>
+
+#include <asm/atomic.h>
+#include <asm/cacheflush.h>
+#include <asm/cpu.h>
+#include <asm/processor.h>
+#include <asm/system.h>
+#include <asm/hardirq.h>
+#include <asm/mmu_context.h>
+#include <asm/smp.h>
+#include <asm/time.h>
+#include <asm/mipsregs.h>
+#include <asm/mipsmtregs.h>
+#include <asm/mips_mt.h>
+
+/*
+ * Crude manipulation of the CPU masks to control which
+ * which CPU's are brought online during initialisation
+ *
+ * Beware... this needs to be called after CPU discovery
+ * but before CPU bringup
+ */
+static int __init allowcpus(char *str)
+{
+	cpumask_t cpu_allow_map;
+	char buf[256];
+	int len;
+
+	cpus_clear(cpu_allow_map);
+	if (cpulist_parse(str, cpu_allow_map) == 0) {
+		cpu_set(0, cpu_allow_map);
+		cpus_and(cpu_possible_map, cpu_possible_map, cpu_allow_map);
+		len = cpulist_scnprintf(buf, sizeof(buf)-1, cpu_possible_map);
+		buf[len] = '\0';
+		pr_debug("Allowable CPUs: %s\n", buf);
+		return 1;
+	} else
+		return 0;
+}
+__setup("allowcpus=", allowcpus);
+
+static void ipi_call_function(unsigned int cpu)
+{
+	unsigned int action = 0;
+
+	pr_debug("CPU%d: %s cpu %d status %08x\n",
+		 smp_processor_id(), __func__, cpu, read_c0_status());
+
+	switch (cpu) {
+	case 0:
+		action = GIC_IPI_EXT_INTR_CALLFNC_VPE0;
+		break;
+	case 1:
+		action = GIC_IPI_EXT_INTR_CALLFNC_VPE1;
+		break;
+	case 2:
+		action = GIC_IPI_EXT_INTR_CALLFNC_VPE2;
+		break;
+	case 3:
+		action = GIC_IPI_EXT_INTR_CALLFNC_VPE3;
+		break;
+	}
+	gic_send_ipi(action);
+}
+
+
+static void ipi_resched(unsigned int cpu)
+{
+	unsigned int action = 0;
+
+	pr_debug("CPU%d: %s cpu %d status %08x\n",
+		 smp_processor_id(), __func__, cpu, read_c0_status());
+
+	switch (cpu) {
+	case 0:
+		action = GIC_IPI_EXT_INTR_RESCHED_VPE0;
+		break;
+	case 1:
+		action = GIC_IPI_EXT_INTR_RESCHED_VPE1;
+		break;
+	case 2:
+		action = GIC_IPI_EXT_INTR_RESCHED_VPE2;
+		break;
+	case 3:
+		action = GIC_IPI_EXT_INTR_RESCHED_VPE3;
+		break;
+	}
+	gic_send_ipi(action);
+}
+
+/*
+ * FIXME: This isn't restricted to CMP
+ * The SMVP kernel could use GIC interrupts if available
+ */
+void cmp_send_ipi_single(int cpu, unsigned int action)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	switch (action) {
+	case SMP_CALL_FUNCTION:
+		ipi_call_function(cpu);
+		break;
+
+	case SMP_RESCHEDULE_YOURSELF:
+		ipi_resched(cpu);
+		break;
+	}
+
+	local_irq_restore(flags);
+}
+
+static void cmp_send_ipi_mask(cpumask_t mask, unsigned int action)
+{
+	unsigned int i;
+
+	for_each_cpu_mask(i, mask)
+		cmp_send_ipi_single(i, action);
+}
+
+static void cmp_init_secondary(void)
+{
+	struct cpuinfo_mips *c = &current_cpu_data;
+
+	/* Assume GIC is present */
+	change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 | STATUSF_IP6 |
+				 STATUSF_IP7);
+
+	/* Enable per-cpu interrupts: platform specific */
+
+	c->core = (read_c0_ebase() >> 1) & 0xff;
+#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC)
+	c->vpe_id = (read_c0_tcbind() >> TCBIND_CURVPE_SHIFT) & TCBIND_CURVPE;
+#endif
+#ifdef CONFIG_MIPS_MT_SMTC
+	c->tc_id  = (read_c0_tcbind() >> TCBIND_CURTC_SHIFT) & TCBIND_CURTC;
+#endif
+}
+
+static void cmp_smp_finish(void)
+{
+	pr_debug("SMPCMP: CPU%d: %s\n", smp_processor_id(), __func__);
+
+	/* CDFIXME: remove this? */
+	write_c0_compare(read_c0_count() + (8 * mips_hpt_frequency / HZ));
+
+#ifdef CONFIG_MIPS_MT_FPAFF
+	/* If we have an FPU, enroll ourselves in the FPU-full mask */
+	if (cpu_has_fpu)
+		cpu_set(smp_processor_id(), mt_fpu_cpumask);
+#endif /* CONFIG_MIPS_MT_FPAFF */
+
+	local_irq_enable();
+}
+
+static void cmp_cpus_done(void)
+{
+	pr_debug("SMPCMP: CPU%d: %s\n", smp_processor_id(), __func__);
+}
+
+/*
+ * Setup the PC, SP, and GP of a secondary processor and start it running
+ * smp_bootstrap is the place to resume from
+ * __KSTK_TOS(idle) is apparently the stack pointer
+ * (unsigned long)idle->thread_info the gp
+ */
+static void cmp_boot_secondary(int cpu, struct task_struct *idle)
+{
+	struct thread_info *gp = task_thread_info(idle);
+	unsigned long sp = __KSTK_TOS(idle);
+	unsigned long pc = (unsigned long)&smp_bootstrap;
+	unsigned long a0 = 0;
+
+	pr_debug("SMPCMP: CPU%d: %s cpu %d\n", smp_processor_id(),
+		__func__, cpu);
+
+#if 0
+	/* Needed? */
+	flush_icache_range((unsigned long)gp,
+			   (unsigned long)(gp + sizeof(struct thread_info)));
+#endif
+
+	amon_cpu_start(cpu, pc, sp, gp, a0);
+}
+
+/*
+ * Common setup before any secondaries are started
+ */
+void __init cmp_smp_setup(void)
+{
+	int i;
+	int ncpu = 0;
+
+	pr_debug("SMPCMP: CPU%d: %s\n", smp_processor_id(), __func__);
+
+#ifdef CONFIG_MIPS_MT_FPAFF
+	/* If we have an FPU, enroll ourselves in the FPU-full mask */
+	if (cpu_has_fpu)
+		cpu_set(0, mt_fpu_cpumask);
+#endif /* CONFIG_MIPS_MT_FPAFF */
+
+	for (i = 1; i < NR_CPUS; i++) {
+		if (amon_cpu_avail(i)) {
+			cpu_set(i, phys_cpu_present_map);
+			__cpu_number_map[i]	= ++ncpu;
+			__cpu_logical_map[ncpu]	= i;
+		}
+	}
+
+	if (cpu_has_mipsmt) {
+		unsigned int nvpe, mvpconf0 = read_c0_mvpconf0();
+
+		nvpe = ((mvpconf0 & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1;
+		smp_num_siblings = nvpe;
+	}
+	pr_info("Detected %i available secondary CPU(s)\n", ncpu);
+}
+
+void __init cmp_prepare_cpus(unsigned int max_cpus)
+{
+	pr_debug("SMPCMP: CPU%d: %s max_cpus=%d\n",
+		 smp_processor_id(), __func__, max_cpus);
+
+	/*
+	 * FIXME: some of these options are per-system, some per-core and
+	 * some per-cpu
+	 */
+	mips_mt_set_cpuoptions();
+}
+
+struct plat_smp_ops cmp_smp_ops = {
+	.send_ipi_single	= cmp_send_ipi_single,
+	.send_ipi_mask		= cmp_send_ipi_mask,
+	.init_secondary		= cmp_init_secondary,
+	.smp_finish		= cmp_smp_finish,
+	.cpus_done		= cmp_cpus_done,
+	.boot_secondary		= cmp_boot_secondary,
+	.smp_setup		= cmp_smp_setup,
+	.prepare_cpus		= cmp_prepare_cpus,
+};
diff --git a/trunk/arch/mips/kernel/smp-mt.c b/trunk/arch/mips/kernel/smp-mt.c
index 89e6f6aa5166..87a1816c1f45 100644
--- a/trunk/arch/mips/kernel/smp-mt.c
+++ b/trunk/arch/mips/kernel/smp-mt.c
@@ -36,110 +36,7 @@
 #include <asm/mipsmtregs.h>
 #include <asm/mips_mt.h>
 
-#define MIPS_CPU_IPI_RESCHED_IRQ 0
-#define MIPS_CPU_IPI_CALL_IRQ 1
-
-static int cpu_ipi_resched_irq, cpu_ipi_call_irq;
-
-#if 0
-static void dump_mtregisters(int vpe, int tc)
-{
-	printk("vpe %d tc %d\n", vpe, tc);
-
-	settc(tc);
-
-	printk("  c0 status  0x%lx\n", read_vpe_c0_status());
-	printk("  vpecontrol 0x%lx\n", read_vpe_c0_vpecontrol());
-	printk("  vpeconf0    0x%lx\n", read_vpe_c0_vpeconf0());
-	printk("  tcstatus 0x%lx\n", read_tc_c0_tcstatus());
-	printk("  tcrestart 0x%lx\n", read_tc_c0_tcrestart());
-	printk("  tcbind 0x%lx\n", read_tc_c0_tcbind());
-	printk("  tchalt 0x%lx\n", read_tc_c0_tchalt());
-}
-#endif
-
-void __init sanitize_tlb_entries(void)
-{
-	int i, tlbsiz;
-	unsigned long mvpconf0, ncpu;
-
-	if (!cpu_has_mipsmt)
-		return;
-
-	/* Enable VPC */
-	set_c0_mvpcontrol(MVPCONTROL_VPC);
-
-	back_to_back_c0_hazard();
-
-	/* Disable TLB sharing */
-	clear_c0_mvpcontrol(MVPCONTROL_STLB);
-
-	mvpconf0 = read_c0_mvpconf0();
-
-	printk(KERN_INFO "MVPConf0 0x%lx TLBS %lx PTLBE %ld\n", mvpconf0,
-		   (mvpconf0 & MVPCONF0_TLBS) >> MVPCONF0_TLBS_SHIFT,
-			   (mvpconf0 & MVPCONF0_PTLBE) >> MVPCONF0_PTLBE_SHIFT);
-
-	tlbsiz = (mvpconf0 & MVPCONF0_PTLBE) >> MVPCONF0_PTLBE_SHIFT;
-	ncpu = ((mvpconf0 & MVPCONF0_PVPE) >> MVPCONF0_PVPE_SHIFT) + 1;
-
-	printk(" tlbsiz %d ncpu %ld\n", tlbsiz, ncpu);
-
-	if (tlbsiz > 0) {
-		/* share them out across the vpe's */
-		tlbsiz /= ncpu;
-
-		printk(KERN_INFO "setting Config1.MMU_size to %d\n", tlbsiz);
-
-		for (i = 0; i < ncpu; i++) {
-			settc(i);
-
-			if (i == 0)
-				write_c0_config1((read_c0_config1() & ~(0x3f << 25)) | (tlbsiz << 25));
-			else
-				write_vpe_c0_config1((read_vpe_c0_config1() & ~(0x3f << 25)) |
-						   (tlbsiz << 25));
-		}
-	}
-
-	clear_c0_mvpcontrol(MVPCONTROL_VPC);
-}
-
-static void ipi_resched_dispatch(void)
-{
-	do_IRQ(MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_RESCHED_IRQ);
-}
-
-static void ipi_call_dispatch(void)
-{
-	do_IRQ(MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_CALL_IRQ);
-}
-
-static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
-{
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
-{
-	smp_call_function_interrupt();
-
-	return IRQ_HANDLED;
-}
-
-static struct irqaction irq_resched = {
-	.handler	= ipi_resched_interrupt,
-	.flags		= IRQF_DISABLED|IRQF_PERCPU,
-	.name		= "IPI_resched"
-};
-
-static struct irqaction irq_call = {
-	.handler	= ipi_call_interrupt,
-	.flags		= IRQF_DISABLED|IRQF_PERCPU,
-	.name		= "IPI_call"
-};
-
-static void __init smp_copy_vpe_config(void)
+static void __init smvp_copy_vpe_config(void)
 {
 	write_vpe_c0_status(
 		(read_c0_status() & ~(ST0_IM | ST0_IE | ST0_KSU)) | ST0_CU0);
@@ -156,7 +53,7 @@ static void __init smp_copy_vpe_config(void)
 	write_vpe_c0_count(read_c0_count());
 }
 
-static unsigned int __init smp_vpe_init(unsigned int tc, unsigned int mvpconf0,
+static unsigned int __init smvp_vpe_init(unsigned int tc, unsigned int mvpconf0,
 	unsigned int ncpu)
 {
 	if (tc > ((mvpconf0 & MVPCONF0_PVPE) >> MVPCONF0_PVPE_SHIFT))
@@ -182,12 +79,12 @@ static unsigned int __init smp_vpe_init(unsigned int tc, unsigned int mvpconf0,
 	write_vpe_c0_vpecontrol(read_vpe_c0_vpecontrol() & ~VPECONTROL_TE);
 
 	if (tc != 0)
-		smp_copy_vpe_config();
+		smvp_copy_vpe_config();
 
 	return ncpu;
 }
 
-static void __init smp_tc_init(unsigned int tc, unsigned int mvpconf0)
+static void __init smvp_tc_init(unsigned int tc, unsigned int mvpconf0)
 {
 	unsigned long tmp;
 
@@ -254,15 +151,20 @@ static void vsmp_send_ipi_mask(cpumask_t mask, unsigned int action)
 
 static void __cpuinit vsmp_init_secondary(void)
 {
-	/* Enable per-cpu interrupts */
+	extern int gic_present;
 
 	/* This is Malta specific: IPI,performance and timer inetrrupts */
-	write_c0_status((read_c0_status() & ~ST0_IM ) |
-	                (STATUSF_IP0 | STATUSF_IP1 | STATUSF_IP6 | STATUSF_IP7));
+	if (gic_present)
+		change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 |
+					 STATUSF_IP6 | STATUSF_IP7);
+	else
+		change_c0_status(ST0_IM, STATUSF_IP0 | STATUSF_IP1 |
+					 STATUSF_IP6 | STATUSF_IP7);
 }
 
 static void __cpuinit vsmp_smp_finish(void)
 {
+	/* CDFIXME: remove this? */
 	write_c0_compare(read_c0_count() + (8* mips_hpt_frequency/HZ));
 
 #ifdef CONFIG_MIPS_MT_FPAFF
@@ -323,7 +225,7 @@ static void __cpuinit vsmp_boot_secondary(int cpu, struct task_struct *idle)
 /*
  * Common setup before any secondaries are started
  * Make sure all CPU's are in a sensible state before we boot any of the
- * secondarys
+ * secondaries
  */
 static void __init vsmp_smp_setup(void)
 {
@@ -356,8 +258,8 @@ static void __init vsmp_smp_setup(void)
 	for (tc = 0; tc <= ntc; tc++) {
 		settc(tc);
 
-		smp_tc_init(tc, mvpconf0);
-		ncpu = smp_vpe_init(tc, mvpconf0, ncpu);
+		smvp_tc_init(tc, mvpconf0);
+		ncpu = smvp_vpe_init(tc, mvpconf0, ncpu);
 	}
 
 	/* Release config state */
@@ -371,21 +273,6 @@ static void __init vsmp_smp_setup(void)
 static void __init vsmp_prepare_cpus(unsigned int max_cpus)
 {
 	mips_mt_set_cpuoptions();
-
-	/* set up ipi interrupts */
-	if (cpu_has_vint) {
-		set_vi_handler(MIPS_CPU_IPI_RESCHED_IRQ, ipi_resched_dispatch);
-		set_vi_handler(MIPS_CPU_IPI_CALL_IRQ, ipi_call_dispatch);
-	}
-
-	cpu_ipi_resched_irq = MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_RESCHED_IRQ;
-	cpu_ipi_call_irq = MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_CALL_IRQ;
-
-	setup_irq(cpu_ipi_resched_irq, &irq_resched);
-	setup_irq(cpu_ipi_call_irq, &irq_call);
-
-	set_irq_handler(cpu_ipi_resched_irq, handle_percpu_irq);
-	set_irq_handler(cpu_ipi_call_irq, handle_percpu_irq);
 }
 
 struct plat_smp_ops vsmp_smp_ops = {
diff --git a/trunk/arch/mips/kernel/smp.c b/trunk/arch/mips/kernel/smp.c
index 9d41dab90a80..33780cc61ce9 100644
--- a/trunk/arch/mips/kernel/smp.c
+++ b/trunk/arch/mips/kernel/smp.c
@@ -35,6 +35,7 @@
 #include <asm/atomic.h>
 #include <asm/cpu.h>
 #include <asm/processor.h>
+#include <asm/r4k-timer.h>
 #include <asm/system.h>
 #include <asm/mmu_context.h>
 #include <asm/time.h>
@@ -125,6 +126,8 @@ asmlinkage __cpuinit void start_secondary(void)
 
 	cpu_set(cpu, cpu_callin_map);
 
+	synchronise_count_slave();
+
 	cpu_idle();
 }
 
@@ -287,6 +290,7 @@ void smp_send_stop(void)
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	mp_ops->cpus_done();
+	synchronise_count_master();
 }
 
 /* called from main before smp_init() */
diff --git a/trunk/arch/mips/kernel/smtc.c b/trunk/arch/mips/kernel/smtc.c
index b42e71c71119..3e863186cd22 100644
--- a/trunk/arch/mips/kernel/smtc.c
+++ b/trunk/arch/mips/kernel/smtc.c
@@ -174,14 +174,6 @@ static int clock_hang_reported[NR_CPUS];
 
 #endif /* CONFIG_SMTC_IDLE_HOOK_DEBUG */
 
-/* Initialize shared TLB - the should probably migrate to smtc_setup_cpus() */
-
-void __init sanitize_tlb_entries(void)
-{
-	printk("Deprecated sanitize_tlb_entries() invoked\n");
-}
-
-
 /*
  * Configure shared TLB - VPC configuration bit must be set by caller
  */
@@ -339,7 +331,8 @@ static void smtc_tc_setup(int vpe, int tc, int cpu)
 	/* In general, all TCs should have the same cpu_data indications */
 	memcpy(&cpu_data[cpu], &cpu_data[0], sizeof(struct cpuinfo_mips));
 	/* For 34Kf, start with TC/CPU 0 as sole owner of single FPU context */
-	if (cpu_data[0].cputype == CPU_34K)
+	if (cpu_data[0].cputype == CPU_34K ||
+	    cpu_data[0].cputype == CPU_1004K)
 		cpu_data[cpu].options &= ~MIPS_CPU_FPU;
 	cpu_data[cpu].vpe_id = vpe;
 	cpu_data[cpu].tc_id = tc;
diff --git a/trunk/arch/mips/kernel/spram.c b/trunk/arch/mips/kernel/spram.c
new file mode 100644
index 000000000000..6ddb507a87ef
--- /dev/null
+++ b/trunk/arch/mips/kernel/spram.c
@@ -0,0 +1,221 @@
+/*
+ * MIPS SPRAM support
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Copyright (C) 2007, 2008 MIPS Technologies, Inc.
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/ptrace.h>
+#include <linux/stddef.h>
+
+#include <asm/cpu.h>
+#include <asm/fpu.h>
+#include <asm/mipsregs.h>
+#include <asm/system.h>
+#include <asm/r4kcache.h>
+#include <asm/hazards.h>
+
+/*
+ * These definitions are correct for the 24K/34K/74K SPRAM sample
+ * implementation. The 4KS interpreted the tags differently...
+ */
+#define SPRAM_TAG0_ENABLE	0x00000080
+#define SPRAM_TAG0_PA_MASK	0xfffff000
+#define SPRAM_TAG1_SIZE_MASK	0xfffff000
+
+#define SPRAM_TAG_STRIDE	8
+
+#define ERRCTL_SPRAM		(1 << 28)
+
+/* errctl access */
+#define read_c0_errctl(x) read_c0_ecc(x)
+#define write_c0_errctl(x) write_c0_ecc(x)
+
+/*
+ * Different semantics to the set_c0_* function built by __BUILD_SET_C0
+ */
+static __cpuinit unsigned int bis_c0_errctl(unsigned int set)
+{
+	unsigned int res;
+	res = read_c0_errctl();
+	write_c0_errctl(res | set);
+	return res;
+}
+
+static __cpuinit void ispram_store_tag(unsigned int offset, unsigned int data)
+{
+	unsigned int errctl;
+
+	/* enable SPRAM tag access */
+	errctl = bis_c0_errctl(ERRCTL_SPRAM);
+	ehb();
+
+	write_c0_taglo(data);
+	ehb();
+
+	cache_op(Index_Store_Tag_I, CKSEG0|offset);
+	ehb();
+
+	write_c0_errctl(errctl);
+	ehb();
+}
+
+
+static __cpuinit unsigned int ispram_load_tag(unsigned int offset)
+{
+	unsigned int data;
+	unsigned int errctl;
+
+	/* enable SPRAM tag access */
+	errctl = bis_c0_errctl(ERRCTL_SPRAM);
+	ehb();
+	cache_op(Index_Load_Tag_I, CKSEG0 | offset);
+	ehb();
+	data = read_c0_taglo();
+	ehb();
+	write_c0_errctl(errctl);
+	ehb();
+
+	return data;
+}
+
+static __cpuinit void dspram_store_tag(unsigned int offset, unsigned int data)
+{
+	unsigned int errctl;
+
+	/* enable SPRAM tag access */
+	errctl = bis_c0_errctl(ERRCTL_SPRAM);
+	ehb();
+	write_c0_dtaglo(data);
+	ehb();
+	cache_op(Index_Store_Tag_D, CKSEG0 | offset);
+	ehb();
+	write_c0_errctl(errctl);
+	ehb();
+}
+
+
+static __cpuinit unsigned int dspram_load_tag(unsigned int offset)
+{
+	unsigned int data;
+	unsigned int errctl;
+
+	errctl = bis_c0_errctl(ERRCTL_SPRAM);
+	ehb();
+	cache_op(Index_Load_Tag_D, CKSEG0 | offset);
+	ehb();
+	data = read_c0_dtaglo();
+	ehb();
+	write_c0_errctl(errctl);
+	ehb();
+
+	return data;
+}
+
+static __cpuinit void probe_spram(char *type,
+	    unsigned int base,
+	    unsigned int (*read)(unsigned int),
+	    void (*write)(unsigned int, unsigned int))
+{
+	unsigned int firstsize = 0, lastsize = 0;
+	unsigned int firstpa = 0, lastpa = 0, pa = 0;
+	unsigned int offset = 0;
+	unsigned int size, tag0, tag1;
+	unsigned int enabled;
+	int i;
+
+	/*
+	 * The limit is arbitrary but avoids the loop running away if
+	 * the SPRAM tags are implemented differently
+	 */
+
+	for (i = 0; i < 8; i++) {
+		tag0 = read(offset);
+		tag1 = read(offset+SPRAM_TAG_STRIDE);
+		pr_debug("DBG %s%d: tag0=%08x tag1=%08x\n",
+			 type, i, tag0, tag1);
+
+		size = tag1 & SPRAM_TAG1_SIZE_MASK;
+
+		if (size == 0)
+			break;
+
+		if (i != 0) {
+			/* tags may repeat... */
+			if ((pa == firstpa && size == firstsize) ||
+			    (pa == lastpa && size == lastsize))
+				break;
+		}
+
+		/* Align base with size */
+		base = (base + size - 1) & ~(size-1);
+
+		/* reprogram the base address base address and enable */
+		tag0 = (base & SPRAM_TAG0_PA_MASK) | SPRAM_TAG0_ENABLE;
+		write(offset, tag0);
+
+		base += size;
+
+		/* reread the tag */
+		tag0 = read(offset);
+		pa = tag0 & SPRAM_TAG0_PA_MASK;
+		enabled = tag0 & SPRAM_TAG0_ENABLE;
+
+		if (i == 0) {
+			firstpa = pa;
+			firstsize = size;
+		}
+
+		lastpa = pa;
+		lastsize = size;
+
+		if (strcmp(type, "DSPRAM") == 0) {
+			unsigned int *vp = (unsigned int *)(CKSEG1 | pa);
+			unsigned int v;
+#define TDAT	0x5a5aa5a5
+			vp[0] = TDAT;
+			vp[1] = ~TDAT;
+
+			mb();
+
+			v = vp[0];
+			if (v != TDAT)
+				printk(KERN_ERR "vp=%p wrote=%08x got=%08x\n",
+				       vp, TDAT, v);
+			v = vp[1];
+			if (v != ~TDAT)
+				printk(KERN_ERR "vp=%p wrote=%08x got=%08x\n",
+				       vp+1, ~TDAT, v);
+		}
+
+		pr_info("%s%d: PA=%08x,Size=%08x%s\n",
+			type, i, pa, size, enabled ? ",enabled" : "");
+		offset += 2 * SPRAM_TAG_STRIDE;
+	}
+}
+
+__cpuinit void spram_config(void)
+{
+	struct cpuinfo_mips *c = &current_cpu_data;
+	unsigned int config0;
+
+	switch (c->cputype) {
+	case CPU_24K:
+	case CPU_34K:
+	case CPU_74K:
+		config0 = read_c0_config();
+		/* FIXME: addresses are Malta specific */
+		if (config0 & (1<<24)) {
+			probe_spram("ISPRAM", 0x1c000000,
+				    &ispram_load_tag, &ispram_store_tag);
+		}
+		if (config0 & (1<<23))
+			probe_spram("DSPRAM", 0x1c100000,
+				    &dspram_load_tag, &dspram_store_tag);
+	}
+}
diff --git a/trunk/arch/mips/kernel/sync-r4k.c b/trunk/arch/mips/kernel/sync-r4k.c
new file mode 100644
index 000000000000..9021108eb9c1
--- /dev/null
+++ b/trunk/arch/mips/kernel/sync-r4k.c
@@ -0,0 +1,159 @@
+/*
+ * Count register synchronisation.
+ *
+ * All CPUs will have their count registers synchronised to the CPU0 expirelo
+ * value. This can cause a small timewarp for CPU0. All other CPU's should
+ * not have done anything significant (but they may have had interrupts
+ * enabled briefly - prom_smp_finish() should not be responsible for enabling
+ * interrupts...)
+ *
+ * FIXME: broken for SMTC
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/irqflags.h>
+#include <linux/r4k-timer.h>
+
+#include <asm/atomic.h>
+#include <asm/barrier.h>
+#include <asm/cpumask.h>
+#include <asm/mipsregs.h>
+
+static atomic_t __initdata count_start_flag = ATOMIC_INIT(0);
+static atomic_t __initdata count_count_start = ATOMIC_INIT(0);
+static atomic_t __initdata count_count_stop = ATOMIC_INIT(0);
+
+#define COUNTON	100
+#define NR_LOOPS 5
+
+void __init synchronise_count_master(void)
+{
+	int i;
+	unsigned long flags;
+	unsigned int initcount;
+	int nslaves;
+
+#ifdef CONFIG_MIPS_MT_SMTC
+	/*
+	 * SMTC needs to synchronise per VPE, not per CPU
+	 * ignore for now
+	 */
+	return;
+#endif
+
+	pr_info("Checking COUNT synchronization across %u CPUs: ",
+		num_online_cpus());
+
+	local_irq_save(flags);
+
+	/*
+	 * Notify the slaves that it's time to start
+	 */
+	atomic_set(&count_start_flag, 1);
+	smp_wmb();
+
+	/* Count will be initialised to expirelo for all CPU's */
+	initcount = expirelo;
+
+	/*
+	 * We loop a few times to get a primed instruction cache,
+	 * then the last pass is more or less synchronised and
+	 * the master and slaves each set their cycle counters to a known
+	 * value all at once. This reduces the chance of having random offsets
+	 * between the processors, and guarantees that the maximum
+	 * delay between the cycle counters is never bigger than
+	 * the latency of information-passing (cachelines) between
+	 * two CPUs.
+	 */
+
+	nslaves = num_online_cpus()-1;
+	for (i = 0; i < NR_LOOPS; i++) {
+		/* slaves loop on '!= ncpus' */
+		while (atomic_read(&count_count_start) != nslaves)
+			mb();
+		atomic_set(&count_count_stop, 0);
+		smp_wmb();
+
+		/* this lets the slaves write their count register */
+		atomic_inc(&count_count_start);
+
+		/*
+		 * Everyone initialises count in the last loop:
+		 */
+		if (i == NR_LOOPS-1)
+			write_c0_count(initcount);
+
+		/*
+		 * Wait for all slaves to leave the synchronization point:
+		 */
+		while (atomic_read(&count_count_stop) != nslaves)
+			mb();
+		atomic_set(&count_count_start, 0);
+		smp_wmb();
+		atomic_inc(&count_count_stop);
+	}
+	/* Arrange for an interrupt in a short while */
+	write_c0_compare(read_c0_count() + COUNTON);
+
+	local_irq_restore(flags);
+
+	/*
+	 * i386 code reported the skew here, but the
+	 * count registers were almost certainly out of sync
+	 * so no point in alarming people
+	 */
+	printk("done.\n");
+}
+
+void __init synchronise_count_slave(void)
+{
+	int i;
+	unsigned long flags;
+	unsigned int initcount;
+	int ncpus;
+
+#ifdef CONFIG_MIPS_MT_SMTC
+	/*
+	 * SMTC needs to synchronise per VPE, not per CPU
+	 * ignore for now
+	 */
+	return;
+#endif
+
+	local_irq_save(flags);
+
+	/*
+	 * Not every cpu is online at the time this gets called,
+	 * so we first wait for the master to say everyone is ready
+	 */
+
+	while (!atomic_read(&count_start_flag))
+		mb();
+
+	/* Count will be initialised to expirelo for all CPU's */
+	initcount = expirelo;
+
+	ncpus = num_online_cpus();
+	for (i = 0; i < NR_LOOPS; i++) {
+		atomic_inc(&count_count_start);
+		while (atomic_read(&count_count_start) != ncpus)
+			mb();
+
+		/*
+		 * Everyone initialises count in the last loop:
+		 */
+		if (i == NR_LOOPS-1)
+			write_c0_count(initcount);
+
+		atomic_inc(&count_count_stop);
+		while (atomic_read(&count_count_stop) != ncpus)
+			mb();
+	}
+	/* Arrange for an interrupt in a short while */
+	write_c0_compare(read_c0_count() + COUNTON);
+
+	local_irq_restore(flags);
+}
+#undef NR_LOOPS
+#endif
diff --git a/trunk/arch/mips/kernel/time.c b/trunk/arch/mips/kernel/time.c
index b45a7093ca2d..1f467d534642 100644
--- a/trunk/arch/mips/kernel/time.c
+++ b/trunk/arch/mips/kernel/time.c
@@ -38,7 +38,6 @@ int __weak rtc_mips_set_time(unsigned long sec)
 {
 	return 0;
 }
-EXPORT_SYMBOL(rtc_mips_set_time);
 
 int __weak rtc_mips_set_mmss(unsigned long nowtime)
 {
@@ -50,13 +49,11 @@ int update_persistent_clock(struct timespec now)
 	return rtc_mips_set_mmss(now.tv_sec);
 }
 
-int null_perf_irq(void)
+static int null_perf_irq(void)
 {
 	return 0;
 }
 
-EXPORT_SYMBOL(null_perf_irq);
-
 int (*perf_irq)(void) = null_perf_irq;
 
 EXPORT_SYMBOL(perf_irq);
diff --git a/trunk/arch/mips/kernel/traps.c b/trunk/arch/mips/kernel/traps.c
index 984c0d0a7b4d..cb8b0e2c7954 100644
--- a/trunk/arch/mips/kernel/traps.c
+++ b/trunk/arch/mips/kernel/traps.c
@@ -22,6 +22,7 @@
 #include <linux/kallsyms.h>
 #include <linux/bootmem.h>
 #include <linux/interrupt.h>
+#include <linux/ptrace.h>
 
 #include <asm/bootinfo.h>
 #include <asm/branch.h>
@@ -80,19 +81,22 @@ void (*board_bind_eic_interrupt)(int irq, int regset);
 
 static void show_raw_backtrace(unsigned long reg29)
 {
-	unsigned long *sp = (unsigned long *)reg29;
+	unsigned long *sp = (unsigned long *)(reg29 & ~3);
 	unsigned long addr;
 
 	printk("Call Trace:");
 #ifdef CONFIG_KALLSYMS
 	printk("\n");
 #endif
-	while (!kstack_end(sp)) {
-		addr = *sp++;
-		if (__kernel_text_address(addr))
-			print_ip_sym(addr);
+#define IS_KVA01(a) ((((unsigned int)a) & 0xc0000000) == 0x80000000)
+	if (IS_KVA01(sp)) {
+		while (!kstack_end(sp)) {
+			addr = *sp++;
+			if (__kernel_text_address(addr))
+				print_ip_sym(addr);
+		}
+		printk("\n");
 	}
-	printk("\n");
 }
 
 #ifdef CONFIG_KALLSYMS
@@ -192,16 +196,19 @@ EXPORT_SYMBOL(dump_stack);
 static void show_code(unsigned int __user *pc)
 {
 	long i;
+	unsigned short __user *pc16 = NULL;
 
 	printk("\nCode:");
 
+	if ((unsigned long)pc & 1)
+		pc16 = (unsigned short __user *)((unsigned long)pc & ~1);
 	for(i = -3 ; i < 6 ; i++) {
 		unsigned int insn;
-		if (__get_user(insn, pc + i)) {
+		if (pc16 ? __get_user(insn, pc16 + i) : __get_user(insn, pc + i)) {
 			printk(" (Bad address in epc)\n");
 			break;
 		}
-		printk("%c%08x%c", (i?' ':'<'), insn, (i?' ':'>'));
+		printk("%c%0*x%c", (i?' ':'<'), pc16 ? 4 : 8, insn, (i?' ':'>'));
 	}
 }
 
@@ -311,10 +318,21 @@ void show_regs(struct pt_regs *regs)
 
 void show_registers(const struct pt_regs *regs)
 {
+	const int field = 2 * sizeof(unsigned long);
+
 	__show_regs(regs);
 	print_modules();
-	printk("Process %s (pid: %d, threadinfo=%p, task=%p)\n",
-	        current->comm, task_pid_nr(current), current_thread_info(), current);
+	printk("Process %s (pid: %d, threadinfo=%p, task=%p, tls=%0*lx)\n",
+	       current->comm, current->pid, current_thread_info(), current,
+	      field, current_thread_info()->tp_value);
+	if (cpu_has_userlocal) {
+		unsigned long tls;
+
+		tls = read_c0_userlocal();
+		if (tls != current_thread_info()->tp_value)
+			printk("*HwTLS: %0*lx\n", field, tls);
+	}
+
 	show_stacktrace(current, regs);
 	show_code((unsigned int __user *) regs->cp0_epc);
 	printk("\n");
@@ -657,35 +675,24 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
 	force_sig_info(SIGFPE, &info, current);
 }
 
-asmlinkage void do_bp(struct pt_regs *regs)
+static void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
+	const char *str)
 {
-	unsigned int opcode, bcode;
 	siginfo_t info;
-
-	if (__get_user(opcode, (unsigned int __user *) exception_epc(regs)))
-		goto out_sigsegv;
-
-	/*
-	 * There is the ancient bug in the MIPS assemblers that the break
-	 * code starts left to bit 16 instead to bit 6 in the opcode.
-	 * Gas is bug-compatible, but not always, grrr...
-	 * We handle both cases with a simple heuristics.  --macro
-	 */
-	bcode = ((opcode >> 6) & ((1 << 20) - 1));
-	if (bcode < (1 << 10))
-		bcode <<= 10;
+	char b[40];
 
 	/*
-	 * (A short test says that IRIX 5.3 sends SIGTRAP for all break
-	 * insns, even for break codes that indicate arithmetic failures.
-	 * Weird ...)
+	 * A short test says that IRIX 5.3 sends SIGTRAP for all trap
+	 * insns, even for trap and break codes that indicate arithmetic
+	 * failures.  Weird ...
 	 * But should we continue the brokenness???  --macro
 	 */
-	switch (bcode) {
-	case BRK_OVERFLOW << 10:
-	case BRK_DIVZERO << 10:
-		die_if_kernel("Break instruction in kernel code", regs);
-		if (bcode == (BRK_DIVZERO << 10))
+	switch (code) {
+	case BRK_OVERFLOW:
+	case BRK_DIVZERO:
+		scnprintf(b, sizeof(b), "%s instruction in kernel code", str);
+		die_if_kernel(b, regs);
+		if (code == BRK_DIVZERO)
 			info.si_code = FPE_INTDIV;
 		else
 			info.si_code = FPE_INTOVF;
@@ -695,12 +702,34 @@ asmlinkage void do_bp(struct pt_regs *regs)
 		force_sig_info(SIGFPE, &info, current);
 		break;
 	case BRK_BUG:
-		die("Kernel bug detected", regs);
+		die_if_kernel("Kernel bug detected", regs);
+		force_sig(SIGTRAP, current);
 		break;
 	default:
-		die_if_kernel("Break instruction in kernel code", regs);
+		scnprintf(b, sizeof(b), "%s instruction in kernel code", str);
+		die_if_kernel(b, regs);
 		force_sig(SIGTRAP, current);
 	}
+}
+
+asmlinkage void do_bp(struct pt_regs *regs)
+{
+	unsigned int opcode, bcode;
+
+	if (__get_user(opcode, (unsigned int __user *) exception_epc(regs)))
+		goto out_sigsegv;
+
+	/*
+	 * There is the ancient bug in the MIPS assemblers that the break
+	 * code starts left to bit 16 instead to bit 6 in the opcode.
+	 * Gas is bug-compatible, but not always, grrr...
+	 * We handle both cases with a simple heuristics.  --macro
+	 */
+	bcode = ((opcode >> 6) & ((1 << 20) - 1));
+	if (bcode >= (1 << 10))
+		bcode >>= 10;
+
+	do_trap_or_bp(regs, bcode, "Break");
 	return;
 
 out_sigsegv:
@@ -710,7 +739,6 @@ asmlinkage void do_bp(struct pt_regs *regs)
 asmlinkage void do_tr(struct pt_regs *regs)
 {
 	unsigned int opcode, tcode = 0;
-	siginfo_t info;
 
 	if (__get_user(opcode, (unsigned int __user *) exception_epc(regs)))
 		goto out_sigsegv;
@@ -719,32 +747,7 @@ asmlinkage void do_tr(struct pt_regs *regs)
 	if (!(opcode & OPCODE))
 		tcode = ((opcode >> 6) & ((1 << 10) - 1));
 
-	/*
-	 * (A short test says that IRIX 5.3 sends SIGTRAP for all trap
-	 * insns, even for trap codes that indicate arithmetic failures.
-	 * Weird ...)
-	 * But should we continue the brokenness???  --macro
-	 */
-	switch (tcode) {
-	case BRK_OVERFLOW:
-	case BRK_DIVZERO:
-		die_if_kernel("Trap instruction in kernel code", regs);
-		if (tcode == BRK_DIVZERO)
-			info.si_code = FPE_INTDIV;
-		else
-			info.si_code = FPE_INTOVF;
-		info.si_signo = SIGFPE;
-		info.si_errno = 0;
-		info.si_addr = (void __user *) regs->cp0_epc;
-		force_sig_info(SIGFPE, &info, current);
-		break;
-	case BRK_BUG:
-		die("Kernel bug detected", regs);
-		break;
-	default:
-		die_if_kernel("Trap instruction in kernel code", regs);
-		force_sig(SIGTRAP, current);
-	}
+	do_trap_or_bp(regs, tcode, "Trap");
 	return;
 
 out_sigsegv:
@@ -985,6 +988,21 @@ asmlinkage void do_reserved(struct pt_regs *regs)
 	      (regs->cp0_cause & 0x7f) >> 2);
 }
 
+static int __initdata l1parity = 1;
+static int __init nol1parity(char *s)
+{
+	l1parity = 0;
+	return 1;
+}
+__setup("nol1par", nol1parity);
+static int __initdata l2parity = 1;
+static int __init nol2parity(char *s)
+{
+	l2parity = 0;
+	return 1;
+}
+__setup("nol2par", nol2parity);
+
 /*
  * Some MIPS CPUs can enable/disable for cache parity detection, but do
  * it different ways.
@@ -994,6 +1012,62 @@ static inline void parity_protection_init(void)
 	switch (current_cpu_type()) {
 	case CPU_24K:
 	case CPU_34K:
+	case CPU_74K:
+	case CPU_1004K:
+		{
+#define ERRCTL_PE	0x80000000
+#define ERRCTL_L2P	0x00800000
+			unsigned long errctl;
+			unsigned int l1parity_present, l2parity_present;
+
+			errctl = read_c0_ecc();
+			errctl &= ~(ERRCTL_PE|ERRCTL_L2P);
+
+			/* probe L1 parity support */
+			write_c0_ecc(errctl | ERRCTL_PE);
+			back_to_back_c0_hazard();
+			l1parity_present = (read_c0_ecc() & ERRCTL_PE);
+
+			/* probe L2 parity support */
+			write_c0_ecc(errctl|ERRCTL_L2P);
+			back_to_back_c0_hazard();
+			l2parity_present = (read_c0_ecc() & ERRCTL_L2P);
+
+			if (l1parity_present && l2parity_present) {
+				if (l1parity)
+					errctl |= ERRCTL_PE;
+				if (l1parity ^ l2parity)
+					errctl |= ERRCTL_L2P;
+			} else if (l1parity_present) {
+				if (l1parity)
+					errctl |= ERRCTL_PE;
+			} else if (l2parity_present) {
+				if (l2parity)
+					errctl |= ERRCTL_L2P;
+			} else {
+				/* No parity available */
+			}
+
+			printk(KERN_INFO "Writing ErrCtl register=%08lx\n", errctl);
+
+			write_c0_ecc(errctl);
+			back_to_back_c0_hazard();
+			errctl = read_c0_ecc();
+			printk(KERN_INFO "Readback ErrCtl register=%08lx\n", errctl);
+
+			if (l1parity_present)
+				printk(KERN_INFO "Cache parity protection %sabled\n",
+				       (errctl & ERRCTL_PE) ? "en" : "dis");
+
+			if (l2parity_present) {
+				if (l1parity_present && l1parity)
+					errctl ^= ERRCTL_L2P;
+				printk(KERN_INFO "L2 cache parity protection %sabled\n",
+				       (errctl & ERRCTL_L2P) ? "en" : "dis");
+			}
+		}
+		break;
+
 	case CPU_5KC:
 		write_c0_ecc(0x80000000);
 		back_to_back_c0_hazard();
@@ -1306,6 +1380,17 @@ int cp0_compare_irq;
 int cp0_perfcount_irq;
 EXPORT_SYMBOL_GPL(cp0_perfcount_irq);
 
+static int __cpuinitdata noulri;
+
+static int __init ulri_disable(char *s)
+{
+	pr_info("Disabling ulri\n");
+	noulri = 1;
+
+	return 1;
+}
+__setup("noulri", ulri_disable);
+
 void __cpuinit per_cpu_trap_init(void)
 {
 	unsigned int cpu = smp_processor_id();
@@ -1342,16 +1427,14 @@ void __cpuinit per_cpu_trap_init(void)
 	change_c0_status(ST0_CU|ST0_MX|ST0_RE|ST0_FR|ST0_BEV|ST0_TS|ST0_KX|ST0_SX|ST0_UX,
 			 status_set);
 
-#ifdef CONFIG_CPU_MIPSR2
 	if (cpu_has_mips_r2) {
 		unsigned int enable = 0x0000000f;
 
-		if (cpu_has_userlocal)
+		if (!noulri && cpu_has_userlocal)
 			enable |= (1 << 29);
 
 		write_c0_hwrena(enable);
 	}
-#endif
 
 #ifdef CONFIG_MIPS_MT_SMTC
 	if (!secondaryTC) {
diff --git a/trunk/arch/mips/lib/iomap-pci.c b/trunk/arch/mips/lib/iomap-pci.c
index c11b2494bb6e..2ab899c4b4ce 100644
--- a/trunk/arch/mips/lib/iomap-pci.c
+++ b/trunk/arch/mips/lib/iomap-pci.c
@@ -45,8 +45,8 @@ static void __iomem *ioport_map_pci(struct pci_dev *dev,
  */
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
-	unsigned long start = pci_resource_start(dev, bar);
-	unsigned long len = pci_resource_len(dev, bar);
+	resource_size_t start = pci_resource_start(dev, bar);
+	resource_size_t len = pci_resource_len(dev, bar);
 	unsigned long flags = pci_resource_flags(dev, bar);
 
 	if (!len || !start)
diff --git a/trunk/arch/mips/math-emu/ieee754dp.h b/trunk/arch/mips/math-emu/ieee754dp.h
index 8977eb585a37..762786538449 100644
--- a/trunk/arch/mips/math-emu/ieee754dp.h
+++ b/trunk/arch/mips/math-emu/ieee754dp.h
@@ -46,7 +46,7 @@
 #define DPDNORMX	DPDNORMx(xm, xe)
 #define DPDNORMY	DPDNORMx(ym, ye)
 
-static __inline ieee754dp builddp(int s, int bx, u64 m)
+static inline ieee754dp builddp(int s, int bx, u64 m)
 {
 	ieee754dp r;
 
diff --git a/trunk/arch/mips/math-emu/ieee754sp.h b/trunk/arch/mips/math-emu/ieee754sp.h
index 9917c1e4d947..d9e3586b5bce 100644
--- a/trunk/arch/mips/math-emu/ieee754sp.h
+++ b/trunk/arch/mips/math-emu/ieee754sp.h
@@ -51,7 +51,7 @@
 #define SPDNORMX	SPDNORMx(xm, xe)
 #define SPDNORMY	SPDNORMx(ym, ye)
 
-static __inline ieee754sp buildsp(int s, int bx, unsigned m)
+static inline ieee754sp buildsp(int s, int bx, unsigned m)
 {
 	ieee754sp r;
 
diff --git a/trunk/arch/mips/mips-boards/generic/Makefile b/trunk/arch/mips/mips-boards/generic/Makefile
index b31d8dfed1be..f7f87fc09d1e 100644
--- a/trunk/arch/mips/mips-boards/generic/Makefile
+++ b/trunk/arch/mips/mips-boards/generic/Makefile
@@ -20,6 +20,7 @@
 
 obj-y				:= reset.o display.o init.o memory.o \
 				   cmdline.o time.o
+obj-y				+= amon.o
 
 obj-$(CONFIG_EARLY_PRINTK)	+= console.o
 obj-$(CONFIG_PCI)		+= pci.o
diff --git a/trunk/arch/mips/mips-boards/generic/amon.c b/trunk/arch/mips/mips-boards/generic/amon.c
new file mode 100644
index 000000000000..b7633fda4180
--- /dev/null
+++ b/trunk/arch/mips/mips-boards/generic/amon.c
@@ -0,0 +1,80 @@
+/*
+ * Copyright (C) 2007  MIPS Technologies, Inc.
+ *	All rights reserved.
+
+ *  This program is free software; you can distribute it and/or modify it
+ *  under the terms of the GNU General Public License (Version 2) as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope it will be useful, but WITHOUT
+ *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ *  for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
+ *
+ * Arbitrary Monitor interface
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+
+#include <asm-mips/addrspace.h>
+#include <asm-mips/mips-boards/launch.h>
+#include <asm-mips/mipsmtregs.h>
+
+int amon_cpu_avail(int cpu)
+{
+	struct cpulaunch *launch = (struct cpulaunch *)KSEG0ADDR(CPULAUNCH);
+
+	if (cpu < 0 || cpu >= NCPULAUNCH) {
+		pr_debug("avail: cpu%d is out of range\n", cpu);
+		return 0;
+	}
+
+	launch += cpu;
+	if (!(launch->flags & LAUNCH_FREADY)) {
+		pr_debug("avail: cpu%d is not ready\n", cpu);
+		return 0;
+	}
+	if (launch->flags & (LAUNCH_FGO|LAUNCH_FGONE)) {
+		pr_debug("avail: too late.. cpu%d is already gone\n", cpu);
+		return 0;
+	}
+
+	return 1;
+}
+
+void amon_cpu_start(int cpu,
+		    unsigned long pc, unsigned long sp,
+		    unsigned long gp, unsigned long a0)
+{
+	volatile struct cpulaunch *launch =
+		(struct cpulaunch  *)KSEG0ADDR(CPULAUNCH);
+
+	if (!amon_cpu_avail(cpu))
+		return;
+	if (cpu == smp_processor_id()) {
+		pr_debug("launch: I am cpu%d!\n", cpu);
+		return;
+	}
+	launch += cpu;
+
+	pr_debug("launch: starting cpu%d\n", cpu);
+
+	launch->pc = pc;
+	launch->gp = gp;
+	launch->sp = sp;
+	launch->a0 = a0;
+
+	/* Make sure target sees parameters before the go bit */
+	smp_mb();
+
+	launch->flags |= LAUNCH_FGO;
+	while ((launch->flags & LAUNCH_FGONE) == 0)
+		;
+	pr_debug("launch: cpu%d gone!\n", cpu);
+}
diff --git a/trunk/arch/mips/mips-boards/generic/init.c b/trunk/arch/mips/mips-boards/generic/init.c
index 1695dca5506b..83b9dc739203 100644
--- a/trunk/arch/mips/mips-boards/generic/init.c
+++ b/trunk/arch/mips/mips-boards/generic/init.c
@@ -226,7 +226,7 @@ void __init kgdb_config(void)
 }
 #endif
 
-void __init mips_nmi_setup(void)
+static void __init mips_nmi_setup(void)
 {
 	void *base;
 	extern char except_vec_nmi;
@@ -238,7 +238,7 @@ void __init mips_nmi_setup(void)
 	flush_icache_range((unsigned long)base, (unsigned long)base + 0x80);
 }
 
-void __init mips_ejtag_setup(void)
+static void __init mips_ejtag_setup(void)
 {
 	void *base;
 	extern char except_vec_ejtag_debug;
@@ -295,15 +295,21 @@ void __init prom_init(void)
 			break;
 		case MIPS_REVISION_CORID_CORE_MSC:
 		case MIPS_REVISION_CORID_CORE_FPGA2:
-		case MIPS_REVISION_CORID_CORE_FPGA3:
-		case MIPS_REVISION_CORID_CORE_FPGA4:
 		case MIPS_REVISION_CORID_CORE_24K:
-		case MIPS_REVISION_CORID_CORE_EMUL_MSC:
+			/*
+			 * SOCit/ROCit support is essentially identical
+			 * but make an attempt to distinguish them
+			 */
 			mips_revision_sconid = MIPS_REVISION_SCON_SOCIT;
 			break;
+		case MIPS_REVISION_CORID_CORE_FPGA3:
+		case MIPS_REVISION_CORID_CORE_FPGA4:
+		case MIPS_REVISION_CORID_CORE_FPGA5:
+		case MIPS_REVISION_CORID_CORE_EMUL_MSC:
 		default:
-			mips_display_message("CC Error");
-			while (1);   /* We die here... */
+			/* See above */
+			mips_revision_sconid = MIPS_REVISION_SCON_ROCIT;
+			break;
 		}
 	}
 
@@ -418,6 +424,9 @@ void __init prom_init(void)
 #ifdef CONFIG_SERIAL_8250_CONSOLE
 	console_config();
 #endif
+#ifdef CONFIG_MIPS_CMP
+	register_smp_ops(&cmp_smp_ops);
+#endif
 #ifdef CONFIG_MIPS_MT_SMP
 	register_smp_ops(&vsmp_smp_ops);
 #endif
diff --git a/trunk/arch/mips/mips-boards/generic/memory.c b/trunk/arch/mips/mips-boards/generic/memory.c
index dc272c188233..5e443bba5662 100644
--- a/trunk/arch/mips/mips-boards/generic/memory.c
+++ b/trunk/arch/mips/mips-boards/generic/memory.c
@@ -37,7 +37,7 @@ enum yamon_memtypes {
 	yamon_prom,
 	yamon_free,
 };
-struct prom_pmemblock mdesc[PROM_MAX_PMEMBLOCKS];
+static struct prom_pmemblock mdesc[PROM_MAX_PMEMBLOCKS];
 
 #ifdef DEBUG
 static char *mtypes[3] = {
@@ -50,7 +50,7 @@ static char *mtypes[3] = {
 /* determined physical memory size, not overridden by command line args  */
 unsigned long physical_memsize = 0L;
 
-struct prom_pmemblock * __init prom_getmdesc(void)
+static struct prom_pmemblock * __init prom_getmdesc(void)
 {
 	char *memsize_str;
 	unsigned int memsize;
diff --git a/trunk/arch/mips/mips-boards/generic/time.c b/trunk/arch/mips/mips-boards/generic/time.c
index b50e0fc406ac..008fd82b5840 100644
--- a/trunk/arch/mips/mips-boards/generic/time.c
+++ b/trunk/arch/mips/mips-boards/generic/time.c
@@ -55,16 +55,36 @@
 unsigned long cpu_khz;
 
 static int mips_cpu_timer_irq;
+static int mips_cpu_perf_irq;
 extern int cp0_perfcount_irq;
 
+DEFINE_PER_CPU(unsigned int, tickcount);
+#define tickcount_this_cpu __get_cpu_var(tickcount)
+static unsigned long ledbitmask;
+
 static void mips_timer_dispatch(void)
 {
+#if defined(CONFIG_MIPS_MALTA) || defined(CONFIG_MIPS_ATLAS)
+	/*
+	 * Yes, this is very tacky, won't work as expected with SMTC and
+	 * dyntick will break it,
+	 * but it gives me a nice warm feeling during debug
+	 */
+#define LEDBAR 0xbf000408
+	if (tickcount_this_cpu++ >= HZ) {
+		tickcount_this_cpu = 0;
+		change_bit(smp_processor_id(), &ledbitmask);
+		smp_wmb(); /* Make sure every one else sees the change */
+		/* This will pick up any recent changes made by other CPU's */
+		*(unsigned int *)LEDBAR = ledbitmask;
+	}
+#endif
 	do_IRQ(mips_cpu_timer_irq);
 }
 
 static void mips_perf_dispatch(void)
 {
-	do_IRQ(cp0_perfcount_irq);
+	do_IRQ(mips_cpu_perf_irq);
 }
 
 /*
@@ -127,21 +147,20 @@ unsigned long read_persistent_clock(void)
 	return mc146818_get_cmos_time();
 }
 
-void __init plat_perf_setup(void)
+static void __init plat_perf_setup(void)
 {
-	cp0_perfcount_irq = -1;
-
 #ifdef MSC01E_INT_BASE
 	if (cpu_has_veic) {
 		set_vi_handler(MSC01E_INT_PERFCTR, mips_perf_dispatch);
-		cp0_perfcount_irq = MSC01E_INT_BASE + MSC01E_INT_PERFCTR;
+		mips_cpu_perf_irq = MSC01E_INT_BASE + MSC01E_INT_PERFCTR;
 	} else
 #endif
 	if (cp0_perfcount_irq >= 0) {
 		if (cpu_has_vint)
 			set_vi_handler(cp0_perfcount_irq, mips_perf_dispatch);
+		mips_cpu_perf_irq = MIPS_CPU_IRQ_BASE + cp0_perfcount_irq;
 #ifdef CONFIG_SMP
-		set_irq_handler(cp0_perfcount_irq, handle_percpu_irq);
+		set_irq_handler(mips_cpu_perf_irq, handle_percpu_irq);
 #endif
 	}
 }
diff --git a/trunk/arch/mips/mips-boards/malta/Makefile b/trunk/arch/mips/mips-boards/malta/Makefile
index 931ca4600a63..8dc6e2ac4c03 100644
--- a/trunk/arch/mips/mips-boards/malta/Makefile
+++ b/trunk/arch/mips/mips-boards/malta/Makefile
@@ -22,6 +22,7 @@
 obj-y := malta_int.o malta_platform.o malta_setup.o
 
 obj-$(CONFIG_MTD) += malta_mtd.o
+# FIXME FIXME FIXME
 obj-$(CONFIG_MIPS_MT_SMTC) += malta_smtc.o
 
 EXTRA_CFLAGS += -Werror
diff --git a/trunk/arch/mips/mips-boards/malta/malta_int.c b/trunk/arch/mips/mips-boards/malta/malta_int.c
index dbe60eb55e29..8c495104b321 100644
--- a/trunk/arch/mips/mips-boards/malta/malta_int.c
+++ b/trunk/arch/mips/mips-boards/malta/malta_int.c
@@ -31,6 +31,7 @@
 #include <linux/kernel.h>
 #include <linux/random.h>
 
+#include <asm/traps.h>
 #include <asm/i8259.h>
 #include <asm/irq_cpu.h>
 #include <asm/irq_regs.h>
@@ -41,6 +42,14 @@
 #include <asm/mips-boards/generic.h>
 #include <asm/mips-boards/msc01_pci.h>
 #include <asm/msc01_ic.h>
+#include <asm/gic.h>
+#include <asm/gcmpregs.h>
+
+int gcmp_present = -1;
+int gic_present;
+static unsigned long _msc01_biu_base;
+static unsigned long _gcmp_base;
+static unsigned int ipi_map[NR_CPUS];
 
 static DEFINE_SPINLOCK(mips_irq_lock);
 
@@ -121,6 +130,17 @@ static void malta_hw0_irqdispatch(void)
 	do_IRQ(MALTA_INT_BASE + irq);
 }
 
+static void malta_ipi_irqdispatch(void)
+{
+	int irq;
+
+	irq = gic_get_int();
+	if (irq < 0)
+		return;  /* interrupt has already been cleared */
+
+	do_IRQ(MIPS_GIC_IRQ_BASE + irq);
+}
+
 static void corehi_irqdispatch(void)
 {
 	unsigned int intedge, intsteer, pcicmd, pcibadaddr;
@@ -257,12 +277,61 @@ asmlinkage void plat_irq_dispatch(void)
 
 	if (irq == MIPSCPU_INT_I8259A)
 		malta_hw0_irqdispatch();
+	else if (gic_present && ((1 << irq) & ipi_map[smp_processor_id()]))
+		malta_ipi_irqdispatch();
 	else if (irq >= 0)
 		do_IRQ(MIPS_CPU_IRQ_BASE + irq);
 	else
 		spurious_interrupt();
 }
 
+#ifdef CONFIG_MIPS_MT_SMP
+
+
+#define GIC_MIPS_CPU_IPI_RESCHED_IRQ	3
+#define GIC_MIPS_CPU_IPI_CALL_IRQ	4
+
+#define MIPS_CPU_IPI_RESCHED_IRQ 0	/* SW int 0 for resched */
+#define C_RESCHED C_SW0
+#define MIPS_CPU_IPI_CALL_IRQ 1		/* SW int 1 for resched */
+#define C_CALL C_SW1
+static int cpu_ipi_resched_irq, cpu_ipi_call_irq;
+
+static void ipi_resched_dispatch(void)
+{
+	do_IRQ(MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_RESCHED_IRQ);
+}
+
+static void ipi_call_dispatch(void)
+{
+	do_IRQ(MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_CALL_IRQ);
+}
+
+static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
+{
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
+{
+	smp_call_function_interrupt();
+
+	return IRQ_HANDLED;
+}
+
+static struct irqaction irq_resched = {
+	.handler	= ipi_resched_interrupt,
+	.flags		= IRQF_DISABLED|IRQF_PERCPU,
+	.name		= "IPI_resched"
+};
+
+static struct irqaction irq_call = {
+	.handler	= ipi_call_interrupt,
+	.flags		= IRQF_DISABLED|IRQF_PERCPU,
+	.name		= "IPI_call"
+};
+#endif /* CONFIG_MIPS_MT_SMP */
+
 static struct irqaction i8259irq = {
 	.handler = no_action,
 	.name = "XT-PIC cascade"
@@ -273,13 +342,13 @@ static struct irqaction corehi_irqaction = {
 	.name = "CoreHi"
 };
 
-msc_irqmap_t __initdata msc_irqmap[] = {
+static msc_irqmap_t __initdata msc_irqmap[] = {
 	{MSC01C_INT_TMR,		MSC01_IRQ_EDGE, 0},
 	{MSC01C_INT_PCI,		MSC01_IRQ_LEVEL, 0},
 };
-int __initdata msc_nr_irqs = ARRAY_SIZE(msc_irqmap);
+static int __initdata msc_nr_irqs = ARRAY_SIZE(msc_irqmap);
 
-msc_irqmap_t __initdata msc_eicirqmap[] = {
+static msc_irqmap_t __initdata msc_eicirqmap[] = {
 	{MSC01E_INT_SW0,		MSC01_IRQ_LEVEL, 0},
 	{MSC01E_INT_SW1,		MSC01_IRQ_LEVEL, 0},
 	{MSC01E_INT_I8259A,		MSC01_IRQ_LEVEL, 0},
@@ -291,15 +360,90 @@ msc_irqmap_t __initdata msc_eicirqmap[] = {
 	{MSC01E_INT_PERFCTR,		MSC01_IRQ_LEVEL, 0},
 	{MSC01E_INT_CPUCTR,		MSC01_IRQ_LEVEL, 0}
 };
-int __initdata msc_nr_eicirqs = ARRAY_SIZE(msc_eicirqmap);
+
+static int __initdata msc_nr_eicirqs = ARRAY_SIZE(msc_eicirqmap);
+
+/*
+ * This GIC specific tabular array defines the association between External
+ * Interrupts and CPUs/Core Interrupts. The nature of the External
+ * Interrupts is also defined here - polarity/trigger.
+ */
+static struct gic_intr_map gic_intr_map[] = {
+	{ GIC_EXT_INTR(0), 	X,	X,		X, 		X,		0 },
+	{ GIC_EXT_INTR(1), 	X,	X,		X, 		X,		0 },
+	{ GIC_EXT_INTR(2), 	X,	X,		X, 		X,		0 },
+	{ GIC_EXT_INTR(3), 	0,	GIC_CPU_INT0,	GIC_POL_POS, 	GIC_TRIG_LEVEL,	0 },
+	{ GIC_EXT_INTR(4), 	0,	GIC_CPU_INT1,	GIC_POL_POS, 	GIC_TRIG_LEVEL,	0 },
+	{ GIC_EXT_INTR(5), 	0,	GIC_CPU_INT2,	GIC_POL_POS, 	GIC_TRIG_LEVEL,	0 },
+	{ GIC_EXT_INTR(6), 	0,	GIC_CPU_INT3,	GIC_POL_POS, 	GIC_TRIG_LEVEL,	0 },
+	{ GIC_EXT_INTR(7), 	0,	GIC_CPU_INT4,	GIC_POL_POS, 	GIC_TRIG_LEVEL,	0 },
+	{ GIC_EXT_INTR(8), 	0,	GIC_CPU_INT3,	GIC_POL_POS, 	GIC_TRIG_LEVEL,	0 },
+	{ GIC_EXT_INTR(9), 	0,	GIC_CPU_INT3,	GIC_POL_POS, 	GIC_TRIG_LEVEL,	0 },
+	{ GIC_EXT_INTR(10), 	X,	X,		X, 		X,		0 },
+	{ GIC_EXT_INTR(11), 	X,	X,		X, 		X,		0 },
+	{ GIC_EXT_INTR(12), 	0,	GIC_CPU_INT3,	GIC_POL_POS, 	GIC_TRIG_LEVEL,	0 },
+	{ GIC_EXT_INTR(13), 	0,	GIC_MAP_TO_NMI_MSK,	GIC_POL_POS, GIC_TRIG_LEVEL,	0 },
+	{ GIC_EXT_INTR(14), 	0,	GIC_MAP_TO_NMI_MSK,	GIC_POL_POS, GIC_TRIG_LEVEL,	0 },
+	{ GIC_EXT_INTR(15), 	X,	X,		X, 		X,		0 },
+	{ GIC_EXT_INTR(16), 	0,	GIC_CPU_INT1,	GIC_POL_POS, GIC_TRIG_EDGE,	1 },
+	{ GIC_EXT_INTR(17), 	0,	GIC_CPU_INT2,	GIC_POL_POS, GIC_TRIG_EDGE,	1 },
+	{ GIC_EXT_INTR(18), 	1,	GIC_CPU_INT1,	GIC_POL_POS, GIC_TRIG_EDGE,	1 },
+	{ GIC_EXT_INTR(19), 	1,	GIC_CPU_INT2,	GIC_POL_POS, GIC_TRIG_EDGE,	1 },
+	{ GIC_EXT_INTR(20), 	2,	GIC_CPU_INT1,	GIC_POL_POS, GIC_TRIG_EDGE,	1 },
+	{ GIC_EXT_INTR(21), 	2,	GIC_CPU_INT2,	GIC_POL_POS, GIC_TRIG_EDGE,	1 },
+	{ GIC_EXT_INTR(22), 	3,	GIC_CPU_INT1,	GIC_POL_POS, GIC_TRIG_EDGE,	1 },
+	{ GIC_EXT_INTR(23), 	3,	GIC_CPU_INT2,	GIC_POL_POS, GIC_TRIG_EDGE,	1 },
+};
+
+/*
+ * GCMP needs to be detected before any SMP initialisation
+ */
+int __init gcmp_probe(unsigned long addr, unsigned long size)
+{
+	if (gcmp_present >= 0)
+		return gcmp_present;
+
+	_gcmp_base = (unsigned long) ioremap_nocache(GCMP_BASE_ADDR, GCMP_ADDRSPACE_SZ);
+	_msc01_biu_base = (unsigned long) ioremap_nocache(MSC01_BIU_REG_BASE, MSC01_BIU_ADDRSPACE_SZ);
+	gcmp_present = (GCMPGCB(GCMPB) & GCMP_GCB_GCMPB_GCMPBASE_MSK) == GCMP_BASE_ADDR;
+
+	if (gcmp_present)
+		printk(KERN_DEBUG "GCMP present\n");
+	return gcmp_present;
+}
+
+void __init fill_ipi_map(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(gic_intr_map); i++) {
+		if (gic_intr_map[i].ipiflag && (gic_intr_map[i].cpunum != X))
+			ipi_map[gic_intr_map[i].cpunum] |=
+				(1 << (gic_intr_map[i].pin + 2));
+	}
+}
 
 void __init arch_init_irq(void)
 {
+	int gic_present, gcmp_present;
+
 	init_i8259_irqs();
 
 	if (!cpu_has_veic)
 		mips_cpu_irq_init();
 
+	gcmp_present = gcmp_probe(GCMP_BASE_ADDR, GCMP_ADDRSPACE_SZ);
+	if (gcmp_present)  {
+		GCMPGCB(GICBA) = GIC_BASE_ADDR | GCMP_GCB_GICBA_EN_MSK;
+		gic_present = 1;
+	} else {
+		_msc01_biu_base = (unsigned long) ioremap_nocache(MSC01_BIU_REG_BASE, MSC01_BIU_ADDRSPACE_SZ);
+		gic_present = (REG(_msc01_biu_base, MSC01_SC_CFG) &
+		MSC01_SC_CFG_GICPRES_MSK) >> MSC01_SC_CFG_GICPRES_SHF;
+	}
+	if (gic_present)
+		printk(KERN_DEBUG "GIC present\n");
+
 	switch (mips_revision_sconid) {
 	case MIPS_REVISION_SCON_SOCIT:
 	case MIPS_REVISION_SCON_ROCIT:
@@ -360,4 +504,206 @@ void __init arch_init_irq(void)
 		setup_irq(MIPS_CPU_IRQ_BASE+MIPSCPU_INT_COREHI,
 						&corehi_irqaction);
 	}
+
+#if defined(CONFIG_MIPS_MT_SMP)
+	if (gic_present) {
+		/* FIXME */
+		int i;
+		struct {
+			unsigned int resched;
+			unsigned int call;
+		} ipiirq[] = {
+			{
+				.resched = GIC_IPI_EXT_INTR_RESCHED_VPE0,
+				.call =  GIC_IPI_EXT_INTR_CALLFNC_VPE0},
+			{
+				.resched = GIC_IPI_EXT_INTR_RESCHED_VPE1,
+				.call =  GIC_IPI_EXT_INTR_CALLFNC_VPE1
+			}, {
+				.resched = GIC_IPI_EXT_INTR_RESCHED_VPE2,
+				.call =  GIC_IPI_EXT_INTR_CALLFNC_VPE2
+			}, {
+				.resched = GIC_IPI_EXT_INTR_RESCHED_VPE3,
+				.call =  GIC_IPI_EXT_INTR_CALLFNC_VPE3
+			}
+		};
+#define NIPI (sizeof(ipiirq)/sizeof(ipiirq[0]))
+		fill_ipi_map();
+		gic_init(GIC_BASE_ADDR, GIC_ADDRSPACE_SZ, gic_intr_map, ARRAY_SIZE(gic_intr_map), MIPS_GIC_IRQ_BASE);
+		if (!gcmp_present) {
+			/* Enable the GIC */
+			i = REG(_msc01_biu_base, MSC01_SC_CFG);
+			REG(_msc01_biu_base, MSC01_SC_CFG) =
+				(i | (0x1 << MSC01_SC_CFG_GICENA_SHF));
+			pr_debug("GIC Enabled\n");
+		}
+
+		/* set up ipi interrupts */
+		if (cpu_has_vint) {
+			set_vi_handler(MIPSCPU_INT_IPI0, malta_ipi_irqdispatch);
+			set_vi_handler(MIPSCPU_INT_IPI1, malta_ipi_irqdispatch);
+		}
+		/* Argh.. this really needs sorting out.. */
+		printk("CPU%d: status register was %08x\n", smp_processor_id(), read_c0_status());
+		write_c0_status(read_c0_status() | STATUSF_IP3 | STATUSF_IP4);
+		printk("CPU%d: status register now %08x\n", smp_processor_id(), read_c0_status());
+		write_c0_status(0x1100dc00);
+		printk("CPU%d: status register frc %08x\n", smp_processor_id(), read_c0_status());
+		for (i = 0; i < NIPI; i++) {
+			setup_irq(MIPS_GIC_IRQ_BASE + ipiirq[i].resched, &irq_resched);
+			setup_irq(MIPS_GIC_IRQ_BASE + ipiirq[i].call, &irq_call);
+
+			set_irq_handler(MIPS_GIC_IRQ_BASE + ipiirq[i].resched, handle_percpu_irq);
+			set_irq_handler(MIPS_GIC_IRQ_BASE + ipiirq[i].call, handle_percpu_irq);
+		}
+	} else {
+		/* set up ipi interrupts */
+		if (cpu_has_veic) {
+			set_vi_handler (MSC01E_INT_SW0, ipi_resched_dispatch);
+			set_vi_handler (MSC01E_INT_SW1, ipi_call_dispatch);
+			cpu_ipi_resched_irq = MSC01E_INT_SW0;
+			cpu_ipi_call_irq = MSC01E_INT_SW1;
+		} else {
+			if (cpu_has_vint) {
+				set_vi_handler (MIPS_CPU_IPI_RESCHED_IRQ, ipi_resched_dispatch);
+				set_vi_handler (MIPS_CPU_IPI_CALL_IRQ, ipi_call_dispatch);
+			}
+			cpu_ipi_resched_irq = MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_RESCHED_IRQ;
+			cpu_ipi_call_irq = MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_CALL_IRQ;
+		}
+
+		setup_irq(cpu_ipi_resched_irq, &irq_resched);
+		setup_irq(cpu_ipi_call_irq, &irq_call);
+
+		set_irq_handler(cpu_ipi_resched_irq, handle_percpu_irq);
+		set_irq_handler(cpu_ipi_call_irq, handle_percpu_irq);
+	}
+#endif
+}
+
+void malta_be_init(void)
+{
+	if (gcmp_present) {
+		/* Could change CM error mask register */
+	}
+}
+
+
+static char *tr[8] = {
+	"mem",	"gcr",	"gic",	"mmio",
+	"0x04",	"0x05",	"0x06",	"0x07"
+};
+
+static char *mcmd[32] = {
+	[0x00] = "0x00",
+	[0x01] = "Legacy Write",
+	[0x02] = "Legacy Read",
+	[0x03] = "0x03",
+	[0x04] = "0x04",
+	[0x05] = "0x05",
+	[0x06] = "0x06",
+	[0x07] = "0x07",
+	[0x08] = "Coherent Read Own",
+	[0x09] = "Coherent Read Share",
+	[0x0a] = "Coherent Read Discard",
+	[0x0b] = "Coherent Ready Share Always",
+	[0x0c] = "Coherent Upgrade",
+	[0x0d] = "Coherent Writeback",
+	[0x0e] = "0x0e",
+	[0x0f] = "0x0f",
+	[0x10] = "Coherent Copyback",
+	[0x11] = "Coherent Copyback Invalidate",
+	[0x12] = "Coherent Invalidate",
+	[0x13] = "Coherent Write Invalidate",
+	[0x14] = "Coherent Completion Sync",
+	[0x15] = "0x15",
+	[0x16] = "0x16",
+	[0x17] = "0x17",
+	[0x18] = "0x18",
+	[0x19] = "0x19",
+	[0x1a] = "0x1a",
+	[0x1b] = "0x1b",
+	[0x1c] = "0x1c",
+	[0x1d] = "0x1d",
+	[0x1e] = "0x1e",
+	[0x1f] = "0x1f"
+};
+
+static char *core[8] = {
+	"Invalid/OK", 	"Invalid/Data",
+	"Shared/OK",	"Shared/Data",
+	"Modified/OK",	"Modified/Data",
+	"Exclusive/OK",	"Exclusive/Data"
+};
+
+static char *causes[32] = {
+	"None", "GC_WR_ERR", "GC_RD_ERR", "COH_WR_ERR",
+	"COH_RD_ERR", "MMIO_WR_ERR", "MMIO_RD_ERR", "0x07",
+	"0x08", "0x09", "0x0a", "0x0b",
+	"0x0c", "0x0d", "0x0e", "0x0f",
+	"0x10", "0x11", "0x12", "0x13",
+	"0x14", "0x15", "0x16", "INTVN_WR_ERR",
+	"INTVN_RD_ERR", "0x19", "0x1a", "0x1b",
+	"0x1c", "0x1d", "0x1e", "0x1f"
+};
+
+int malta_be_handler(struct pt_regs *regs, int is_fixup)
+{
+	/* This duplicates the handling in do_be which seems wrong */
+	int retval = is_fixup ? MIPS_BE_FIXUP : MIPS_BE_FATAL;
+
+	if (gcmp_present) {
+		unsigned long cm_error = GCMPGCB(GCMEC);
+		unsigned long cm_addr = GCMPGCB(GCMEA);
+		unsigned long cm_other = GCMPGCB(GCMEO);
+		unsigned long cause, ocause;
+		char buf[256];
+
+		cause = (cm_error & GCMP_GCB_GMEC_ERROR_TYPE_MSK);
+		if (cause != 0) {
+			cause >>= GCMP_GCB_GMEC_ERROR_TYPE_SHF;
+			if (cause < 16) {
+				unsigned long cca_bits = (cm_error >> 15) & 7;
+				unsigned long tr_bits = (cm_error >> 12) & 7;
+				unsigned long mcmd_bits = (cm_error >> 7) & 0x1f;
+				unsigned long stag_bits = (cm_error >> 3) & 15;
+				unsigned long sport_bits = (cm_error >> 0) & 7;
+
+				snprintf(buf, sizeof(buf),
+					 "CCA=%lu TR=%s MCmd=%s STag=%lu "
+					 "SPort=%lu\n",
+					 cca_bits, tr[tr_bits], mcmd[mcmd_bits],
+					 stag_bits, sport_bits);
+			} else {
+				/* glob state & sresp together */
+				unsigned long c3_bits = (cm_error >> 18) & 7;
+				unsigned long c2_bits = (cm_error >> 15) & 7;
+				unsigned long c1_bits = (cm_error >> 12) & 7;
+				unsigned long c0_bits = (cm_error >> 9) & 7;
+				unsigned long sc_bit = (cm_error >> 8) & 1;
+				unsigned long mcmd_bits = (cm_error >> 3) & 0x1f;
+				unsigned long sport_bits = (cm_error >> 0) & 7;
+				snprintf(buf, sizeof(buf),
+					 "C3=%s C2=%s C1=%s C0=%s SC=%s "
+					 "MCmd=%s SPort=%lu\n",
+					 core[c3_bits], core[c2_bits],
+					 core[c1_bits], core[c0_bits],
+					 sc_bit ? "True" : "False",
+					 mcmd[mcmd_bits], sport_bits);
+			}
+
+			ocause = (cm_other & GCMP_GCB_GMEO_ERROR_2ND_MSK) >>
+				 GCMP_GCB_GMEO_ERROR_2ND_SHF;
+
+			printk("CM_ERROR=%08lx %s <%s>\n", cm_error,
+			       causes[cause], buf);
+			printk("CM_ADDR =%08lx\n", cm_addr);
+			printk("CM_OTHER=%08lx %s\n", cm_other, causes[ocause]);
+
+			/* reprime cause register */
+			GCMPGCB(GCMEC) = 0;
+		}
+	}
+
+	return retval;
 }
diff --git a/trunk/arch/mips/mips-boards/malta/malta_setup.c b/trunk/arch/mips/mips-boards/malta/malta_setup.c
index 2cd8f5734b36..e7cad54936ca 100644
--- a/trunk/arch/mips/mips-boards/malta/malta_setup.c
+++ b/trunk/arch/mips/mips-boards/malta/malta_setup.c
@@ -1,7 +1,7 @@
 /*
  * Carsten Langgaard, carstenl@mips.com
  * Copyright (C) 2000 MIPS Technologies, Inc.  All rights reserved.
- * Copyright (C) Dmitri Vorobiev
+ * Copyright (C) 2008 Dmitri Vorobiev
  *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
@@ -36,7 +36,10 @@
 #include <linux/console.h>
 #endif
 
-struct resource standard_io_resources[] = {
+extern void malta_be_init(void);
+extern int malta_be_handler(struct pt_regs *regs, int is_fixup);
+
+static struct resource standard_io_resources[] = {
 	{
 		.name = "dma1",
 		.start = 0x00,
@@ -220,4 +223,7 @@ void __init plat_mem_setup(void)
 	screen_info_setup();
 #endif
 	mips_reboot_setup();
+
+	board_be_init = malta_be_init;
+	board_be_handler = malta_be_handler;
 }
diff --git a/trunk/arch/mips/mipssim/sim_setup.c b/trunk/arch/mips/mipssim/sim_setup.c
index d49fe73426b7..7c7148ef2646 100644
--- a/trunk/arch/mips/mipssim/sim_setup.c
+++ b/trunk/arch/mips/mipssim/sim_setup.c
@@ -39,9 +39,6 @@
 static void __init serial_init(void);
 unsigned int _isbonito = 0;
 
-extern void __init sanitize_tlb_entries(void);
-
-
 const char *get_system_type(void)
 {
 	return "MIPSsim";
@@ -55,9 +52,6 @@ void __init plat_mem_setup(void)
 
 	pr_info("Linux started...\n");
 
-#ifdef CONFIG_MIPS_MT_SMP
-	sanitize_tlb_entries();
-#endif
 }
 
 extern struct plat_smp_ops ssmtc_smp_ops;
diff --git a/trunk/arch/mips/mm/Makefile b/trunk/arch/mips/mm/Makefile
index c6f832e0f41c..48731020ca0e 100644
--- a/trunk/arch/mips/mm/Makefile
+++ b/trunk/arch/mips/mm/Makefile
@@ -4,30 +4,29 @@
 
 obj-y				+= cache.o dma-default.o extable.o fault.o \
 				   init.o pgtable.o tlbex.o tlbex-fault.o \
-				   uasm.o
+				   uasm.o page.o
 
 obj-$(CONFIG_32BIT)		+= ioremap.o pgtable-32.o
 obj-$(CONFIG_64BIT)		+= pgtable-64.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
 
-obj-$(CONFIG_CPU_LOONGSON2)	+= c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_MIPS32)	+= c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_MIPS64)	+= c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_NEVADA)	+= c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_R10000)	+= c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_R3000)		+= c-r3k.o tlb-r3k.o pg-r4k.o
-obj-$(CONFIG_CPU_R4300)		+= c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_R4X00)		+= c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_R5000)		+= c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_R5432)		+= c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_R8000)		+= c-r4k.o cex-gen.o pg-r4k.o tlb-r8k.o
-obj-$(CONFIG_CPU_RM7000)	+= c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_RM9000)	+= c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_SB1)		+= c-r4k.o cerr-sb1.o cex-sb1.o pg-sb1.o \
-				   tlb-r4k.o
-obj-$(CONFIG_CPU_TX39XX)	+= c-tx39.o pg-r4k.o tlb-r3k.o
-obj-$(CONFIG_CPU_TX49XX)	+= c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_VR41XX)	+= c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
+obj-$(CONFIG_CPU_LOONGSON2)	+= c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_MIPS32)	+= c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_MIPS64)	+= c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_NEVADA)	+= c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_R10000)	+= c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_R3000)		+= c-r3k.o tlb-r3k.o
+obj-$(CONFIG_CPU_R4300)		+= c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_R4X00)		+= c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_R5000)		+= c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_R5432)		+= c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_R8000)		+= c-r4k.o cex-gen.o tlb-r8k.o
+obj-$(CONFIG_CPU_RM7000)	+= c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_RM9000)	+= c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_SB1)		+= c-r4k.o cerr-sb1.o cex-sb1.o tlb-r4k.o
+obj-$(CONFIG_CPU_TX39XX)	+= c-tx39.o tlb-r3k.o
+obj-$(CONFIG_CPU_TX49XX)	+= c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_VR41XX)	+= c-r4k.o cex-gen.o tlb-r4k.o
 
 obj-$(CONFIG_IP22_CPU_SCACHE)	+= sc-ip22.o
 obj-$(CONFIG_R5000_CPU_SCACHE)  += sc-r5k.o
diff --git a/trunk/arch/mips/mm/c-r4k.c b/trunk/arch/mips/mm/c-r4k.c
index 77aefb4ebedd..643c8bcffff3 100644
--- a/trunk/arch/mips/mm/c-r4k.c
+++ b/trunk/arch/mips/mm/c-r4k.c
@@ -14,6 +14,7 @@
 #include <linux/linkage.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/module.h>
 #include <linux/bitops.h>
 
 #include <asm/bcache.h>
@@ -53,6 +54,12 @@ static inline void r4k_on_each_cpu(void (*func) (void *info), void *info,
 	preempt_enable();
 }
 
+#if defined(CONFIG_MIPS_CMP)
+#define cpu_has_safe_index_cacheops 0
+#else
+#define cpu_has_safe_index_cacheops 1
+#endif
+
 /*
  * Must die.
  */
@@ -481,6 +488,8 @@ static inline void local_r4k_flush_cache_page(void *args)
 
 	if (cpu_has_dc_aliases || (exec && !cpu_has_ic_fills_f_dc)) {
 		r4k_blast_dcache_page(addr);
+		if (exec && !cpu_icache_snoops_remote_store)
+			r4k_blast_scache_page(addr);
 	}
 	if (exec) {
 		if (vaddr && cpu_has_vtag_icache && mm == current->active_mm) {
@@ -583,7 +592,7 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 	 * subset property so we have to flush the primary caches
 	 * explicitly
 	 */
-	if (size >= dcache_size) {
+	if (cpu_has_safe_index_cacheops && size >= dcache_size) {
 		r4k_blast_dcache();
 	} else {
 		R4600_HIT_CACHEOP_WAR_IMPL;
@@ -606,7 +615,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 		return;
 	}
 
-	if (size >= dcache_size) {
+	if (cpu_has_safe_index_cacheops && size >= dcache_size) {
 		r4k_blast_dcache();
 	} else {
 		R4600_HIT_CACHEOP_WAR_IMPL;
@@ -968,6 +977,7 @@ static void __cpuinit probe_pcache(void)
 	case CPU_24K:
 	case CPU_34K:
 	case CPU_74K:
+	case CPU_1004K:
 		if ((read_c0_config7() & (1 << 16))) {
 			/* effectively physically indexed dcache,
 			   thus no virtual aliases. */
@@ -1216,9 +1226,25 @@ void au1x00_fixup_config_od(void)
 	}
 }
 
+static int __cpuinitdata cca = -1;
+
+static int __init cca_setup(char *str)
+{
+	get_option(&str, &cca);
+
+	return 1;
+}
+
+__setup("cca=", cca_setup);
+
 static void __cpuinit coherency_setup(void)
 {
-	change_c0_config(CONF_CM_CMASK, CONF_CM_DEFAULT);
+	if (cca < 0 || cca > 7)
+		cca = read_c0_config() & CONF_CM_CMASK;
+	_page_cachable_default = cca << _CACHE_SHIFT;
+
+	pr_debug("Using cache attribute %d\n", cca);
+	change_c0_config(CONF_CM_CMASK, cca);
 
 	/*
 	 * c0_status.cu=0 specifies that updates by the sc instruction use
@@ -1248,6 +1274,20 @@ static void __cpuinit coherency_setup(void)
 	}
 }
 
+#if defined(CONFIG_DMA_NONCOHERENT)
+
+static int __cpuinitdata coherentio;
+
+static int __init setcoherentio(char *str)
+{
+	coherentio = 1;
+
+	return 1;
+}
+
+__setup("coherentio", setcoherentio);
+#endif
+
 void __cpuinit r4k_cache_init(void)
 {
 	extern void build_clear_page(void);
@@ -1307,14 +1347,22 @@ void __cpuinit r4k_cache_init(void)
 	flush_data_cache_page	= r4k_flush_data_cache_page;
 	flush_icache_range	= r4k_flush_icache_range;
 
-#ifdef CONFIG_DMA_NONCOHERENT
-	_dma_cache_wback_inv	= r4k_dma_cache_wback_inv;
-	_dma_cache_wback	= r4k_dma_cache_wback_inv;
-	_dma_cache_inv		= r4k_dma_cache_inv;
+#if defined(CONFIG_DMA_NONCOHERENT)
+	if (coherentio) {
+		_dma_cache_wback_inv	= (void *)cache_noop;
+		_dma_cache_wback	= (void *)cache_noop;
+		_dma_cache_inv		= (void *)cache_noop;
+	} else {
+		_dma_cache_wback_inv	= r4k_dma_cache_wback_inv;
+		_dma_cache_wback	= r4k_dma_cache_wback_inv;
+		_dma_cache_inv		= r4k_dma_cache_inv;
+	}
 #endif
 
 	build_clear_page();
 	build_copy_page();
+#if !defined(CONFIG_MIPS_CMP)
 	local_r4k___flush_cache_all(NULL);
+#endif
 	coherency_setup();
 }
diff --git a/trunk/arch/mips/mm/cache.c b/trunk/arch/mips/mm/cache.c
index f5903679ee6a..034e8506f6ea 100644
--- a/trunk/arch/mips/mm/cache.c
+++ b/trunk/arch/mips/mm/cache.c
@@ -130,8 +130,28 @@ void __update_cache(struct vm_area_struct *vma, unsigned long address,
 	}
 }
 
-static char cache_panic[] __cpuinitdata =
-	"Yeee, unsupported cache architecture.";
+unsigned long _page_cachable_default;
+EXPORT_SYMBOL_GPL(_page_cachable_default);
+
+static inline void setup_protection_map(void)
+{
+	protection_map[0] = PAGE_NONE;
+	protection_map[1] = PAGE_READONLY;
+	protection_map[2] = PAGE_COPY;
+	protection_map[3] = PAGE_COPY;
+	protection_map[4] = PAGE_READONLY;
+	protection_map[5] = PAGE_READONLY;
+	protection_map[6] = PAGE_COPY;
+	protection_map[7] = PAGE_COPY;
+	protection_map[8] = PAGE_NONE;
+	protection_map[9] = PAGE_READONLY;
+	protection_map[10] = PAGE_SHARED;
+	protection_map[11] = PAGE_SHARED;
+	protection_map[12] = PAGE_READONLY;
+	protection_map[13] = PAGE_READONLY;
+	protection_map[14] = PAGE_SHARED;
+	protection_map[15] = PAGE_SHARED;
+}
 
 void __devinit cpu_cache_init(void)
 {
@@ -139,34 +159,29 @@ void __devinit cpu_cache_init(void)
 		extern void __weak r3k_cache_init(void);
 
 		r3k_cache_init();
-		return;
 	}
 	if (cpu_has_6k_cache) {
 		extern void __weak r6k_cache_init(void);
 
 		r6k_cache_init();
-		return;
 	}
 	if (cpu_has_4k_cache) {
 		extern void __weak r4k_cache_init(void);
 
 		r4k_cache_init();
-		return;
 	}
 	if (cpu_has_8k_cache) {
 		extern void __weak r8k_cache_init(void);
 
 		r8k_cache_init();
-		return;
 	}
 	if (cpu_has_tx39_cache) {
 		extern void __weak tx39_cache_init(void);
 
 		tx39_cache_init();
-		return;
 	}
 
-	panic(cache_panic);
+	setup_protection_map();
 }
 
 int __weak __uncached_access(struct file *file, unsigned long addr)
diff --git a/trunk/arch/mips/mm/init.c b/trunk/arch/mips/mm/init.c
index c7aed133d11d..ecd562d2c348 100644
--- a/trunk/arch/mips/mm/init.c
+++ b/trunk/arch/mips/mm/init.c
@@ -142,7 +142,7 @@ void *kmap_coherent(struct page *page, unsigned long addr)
 #endif
 	vaddr = __fix_to_virt(FIX_CMAP_END - idx);
 	pte = mk_pte(page, PAGE_KERNEL);
-#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32_R1)
+#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32)
 	entrylo = pte.pte_high;
 #else
 	entrylo = pte_val(pte) >> 6;
@@ -221,7 +221,7 @@ void copy_user_highpage(struct page *to, struct page *from,
 		copy_page(vto, vfrom);
 		kunmap_atomic(vfrom, KM_USER0);
 	}
-	if (((vma->vm_flags & VM_EXEC) && !cpu_has_ic_fills_f_dc) ||
+	if ((!cpu_has_ic_fills_f_dc) ||
 	    pages_do_alias((unsigned long)vto, vaddr & PAGE_MASK))
 		flush_data_cache_page((unsigned long)vto);
 	kunmap_atomic(vto, KM_USER1);
@@ -229,8 +229,6 @@ void copy_user_highpage(struct page *to, struct page *from,
 	smp_wmb();
 }
 
-EXPORT_SYMBOL(copy_user_highpage);
-
 void copy_to_user_page(struct vm_area_struct *vma,
 	struct page *page, unsigned long vaddr, void *dst, const void *src,
 	unsigned long len)
@@ -249,8 +247,6 @@ void copy_to_user_page(struct vm_area_struct *vma,
 		flush_cache_page(vma, vaddr, page_to_pfn(page));
 }
 
-EXPORT_SYMBOL(copy_to_user_page);
-
 void copy_from_user_page(struct vm_area_struct *vma,
 	struct page *page, unsigned long vaddr, void *dst, const void *src,
 	unsigned long len)
@@ -267,9 +263,6 @@ void copy_from_user_page(struct vm_area_struct *vma,
 	}
 }
 
-EXPORT_SYMBOL(copy_from_user_page);
-
-
 #ifdef CONFIG_HIGHMEM
 unsigned long highstart_pfn, highend_pfn;
 
diff --git a/trunk/arch/mips/mm/page.c b/trunk/arch/mips/mm/page.c
new file mode 100644
index 000000000000..d827d6144369
--- /dev/null
+++ b/trunk/arch/mips/mm/page.c
@@ -0,0 +1,684 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2003, 04, 05 Ralf Baechle (ralf@linux-mips.org)
+ * Copyright (C) 2007  Maciej W. Rozycki
+ * Copyright (C) 2008  Thiemo Seufer
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+
+#include <asm/bugs.h>
+#include <asm/cacheops.h>
+#include <asm/inst.h>
+#include <asm/io.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/prefetch.h>
+#include <asm/system.h>
+#include <asm/bootinfo.h>
+#include <asm/mipsregs.h>
+#include <asm/mmu_context.h>
+#include <asm/cpu.h>
+#include <asm/war.h>
+
+#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
+#include <asm/sibyte/sb1250.h>
+#include <asm/sibyte/sb1250_regs.h>
+#include <asm/sibyte/sb1250_dma.h>
+#endif
+
+#include "uasm.h"
+
+/* Registers used in the assembled routines. */
+#define ZERO 0
+#define AT 2
+#define A0 4
+#define A1 5
+#define A2 6
+#define T0 8
+#define T1 9
+#define T2 10
+#define T3 11
+#define T9 25
+#define RA 31
+
+/* Handle labels (which must be positive integers). */
+enum label_id {
+	label_clear_nopref = 1,
+	label_clear_pref,
+	label_copy_nopref,
+	label_copy_pref_both,
+	label_copy_pref_store,
+};
+
+UASM_L_LA(_clear_nopref)
+UASM_L_LA(_clear_pref)
+UASM_L_LA(_copy_nopref)
+UASM_L_LA(_copy_pref_both)
+UASM_L_LA(_copy_pref_store)
+
+/* We need one branch and therefore one relocation per target label. */
+static struct uasm_label __cpuinitdata labels[5];
+static struct uasm_reloc __cpuinitdata relocs[5];
+
+#define cpu_is_r4600_v1_x()	((read_c0_prid() & 0xfffffff0) == 0x00002010)
+#define cpu_is_r4600_v2_x()	((read_c0_prid() & 0xfffffff0) == 0x00002020)
+
+/*
+ * Maximum sizes:
+ *
+ * R4000 128 bytes S-cache:		0x058 bytes
+ * R4600 v1.7:				0x05c bytes
+ * R4600 v2.0:				0x060 bytes
+ * With prefetching, 16 word strides	0x120 bytes
+ */
+
+static u32 clear_page_array[0x120 / 4];
+
+#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
+void clear_page_cpu(void *page) __attribute__((alias("clear_page_array")));
+#else
+void clear_page(void *page) __attribute__((alias("clear_page_array")));
+#endif
+
+EXPORT_SYMBOL(clear_page);
+
+/*
+ * Maximum sizes:
+ *
+ * R4000 128 bytes S-cache:		0x11c bytes
+ * R4600 v1.7:				0x080 bytes
+ * R4600 v2.0:				0x07c bytes
+ * With prefetching, 16 word strides	0x540 bytes
+ */
+static u32 copy_page_array[0x540 / 4];
+
+#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
+void
+copy_page_cpu(void *to, void *from) __attribute__((alias("copy_page_array")));
+#else
+void copy_page(void *to, void *from) __attribute__((alias("copy_page_array")));
+#endif
+
+EXPORT_SYMBOL(copy_page);
+
+
+static int pref_bias_clear_store __cpuinitdata;
+static int pref_bias_copy_load __cpuinitdata;
+static int pref_bias_copy_store __cpuinitdata;
+
+static u32 pref_src_mode __cpuinitdata;
+static u32 pref_dst_mode __cpuinitdata;
+
+static int clear_word_size __cpuinitdata;
+static int copy_word_size __cpuinitdata;
+
+static int half_clear_loop_size __cpuinitdata;
+static int half_copy_loop_size __cpuinitdata;
+
+static int cache_line_size __cpuinitdata;
+#define cache_line_mask() (cache_line_size - 1)
+
+static inline void __cpuinit
+pg_addiu(u32 **buf, unsigned int reg1, unsigned int reg2, unsigned int off)
+{
+	if (cpu_has_64bit_gp_regs && DADDI_WAR && r4k_daddiu_bug()) {
+		if (off > 0x7fff) {
+			uasm_i_lui(buf, T9, uasm_rel_hi(off));
+			uasm_i_addiu(buf, T9, T9, uasm_rel_lo(off));
+		} else
+			uasm_i_addiu(buf, T9, ZERO, off);
+		uasm_i_daddu(buf, reg1, reg2, T9);
+	} else {
+		if (off > 0x7fff) {
+			uasm_i_lui(buf, T9, uasm_rel_hi(off));
+			uasm_i_addiu(buf, T9, T9, uasm_rel_lo(off));
+			UASM_i_ADDU(buf, reg1, reg2, T9);
+		} else
+			UASM_i_ADDIU(buf, reg1, reg2, off);
+	}
+}
+
+static void __cpuinit set_prefetch_parameters(void)
+{
+	if (cpu_has_64bit_gp_regs || cpu_has_64bit_zero_reg)
+		clear_word_size = 8;
+	else
+		clear_word_size = 4;
+
+	if (cpu_has_64bit_gp_regs)
+		copy_word_size = 8;
+	else
+		copy_word_size = 4;
+
+	/*
+	 * The pref's used here are using "streaming" hints, which cause the
+	 * copied data to be kicked out of the cache sooner.  A page copy often
+	 * ends up copying a lot more data than is commonly used, so this seems
+	 * to make sense in terms of reducing cache pollution, but I've no real
+	 * performance data to back this up.
+	 */
+	if (cpu_has_prefetch) {
+		/*
+		 * XXX: Most prefetch bias values in here are based on
+		 * guesswork.
+		 */
+		cache_line_size = cpu_dcache_line_size();
+		switch (current_cpu_type()) {
+		case CPU_TX49XX:
+			/* TX49 supports only Pref_Load */
+			pref_bias_copy_load = 256;
+			break;
+
+		case CPU_RM9000:
+			/*
+			 * As a workaround for erratum G105 which make the
+			 * PrepareForStore hint unusable we fall back to
+			 * StoreRetained on the RM9000.  Once it is known which
+			 * versions of the RM9000 we'll be able to condition-
+			 * alize this.
+			 */
+
+		case CPU_R10000:
+		case CPU_R12000:
+		case CPU_R14000:
+			/*
+			 * Those values have been experimentally tuned for an
+			 * Origin 200.
+			 */
+			pref_bias_clear_store = 512;
+			pref_bias_copy_load = 256;
+			pref_bias_copy_store = 256;
+			pref_src_mode = Pref_LoadStreamed;
+			pref_dst_mode = Pref_StoreStreamed;
+			break;
+
+		case CPU_SB1:
+		case CPU_SB1A:
+			pref_bias_clear_store = 128;
+			pref_bias_copy_load = 128;
+			pref_bias_copy_store = 128;
+			/*
+			 * SB1 pass1 Pref_LoadStreamed/Pref_StoreStreamed
+			 * hints are broken.
+			 */
+			if (current_cpu_type() == CPU_SB1 &&
+			    (current_cpu_data.processor_id & 0xff) < 0x02) {
+				pref_src_mode = Pref_Load;
+				pref_dst_mode = Pref_Store;
+			} else {
+				pref_src_mode = Pref_LoadStreamed;
+				pref_dst_mode = Pref_StoreStreamed;
+			}
+			break;
+
+		default:
+			pref_bias_clear_store = 128;
+			pref_bias_copy_load = 256;
+			pref_bias_copy_store = 128;
+			pref_src_mode = Pref_LoadStreamed;
+			pref_dst_mode = Pref_PrepareForStore;
+			break;
+		}
+	} else {
+		if (cpu_has_cache_cdex_s)
+			cache_line_size = cpu_scache_line_size();
+		else if (cpu_has_cache_cdex_p)
+			cache_line_size = cpu_dcache_line_size();
+	}
+	/*
+	 * Too much unrolling will overflow the available space in
+	 * clear_space_array / copy_page_array. 8 words sounds generous,
+	 * but a R4000 with 128 byte L2 line length can exceed even that.
+	 */
+	half_clear_loop_size = min(8 * clear_word_size,
+				   max(cache_line_size >> 1,
+				       4 * clear_word_size));
+	half_copy_loop_size = min(8 * copy_word_size,
+				  max(cache_line_size >> 1,
+				      4 * copy_word_size));
+}
+
+static void __cpuinit build_clear_store(u32 **buf, int off)
+{
+	if (cpu_has_64bit_gp_regs || cpu_has_64bit_zero_reg) {
+		uasm_i_sd(buf, ZERO, off, A0);
+	} else {
+		uasm_i_sw(buf, ZERO, off, A0);
+	}
+}
+
+static inline void __cpuinit build_clear_pref(u32 **buf, int off)
+{
+	if (off & cache_line_mask())
+		return;
+
+	if (pref_bias_clear_store) {
+		uasm_i_pref(buf, pref_dst_mode, pref_bias_clear_store + off,
+			    A0);
+	} else if (cpu_has_cache_cdex_s) {
+		uasm_i_cache(buf, Create_Dirty_Excl_SD, off, A0);
+	} else if (cpu_has_cache_cdex_p) {
+		if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) {
+			uasm_i_nop(buf);
+			uasm_i_nop(buf);
+			uasm_i_nop(buf);
+			uasm_i_nop(buf);
+		}
+
+		if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
+			uasm_i_lw(buf, ZERO, ZERO, AT);
+
+		uasm_i_cache(buf, Create_Dirty_Excl_D, off, A0);
+	}
+}
+
+void __cpuinit build_clear_page(void)
+{
+	int off;
+	u32 *buf = (u32 *)&clear_page_array;
+	struct uasm_label *l = labels;
+	struct uasm_reloc *r = relocs;
+	int i;
+
+	memset(labels, 0, sizeof(labels));
+	memset(relocs, 0, sizeof(relocs));
+
+	set_prefetch_parameters();
+
+	/*
+	 * This algorithm makes the following assumptions:
+	 *   - The prefetch bias is a multiple of 2 words.
+	 *   - The prefetch bias is less than one page.
+	 */
+	BUG_ON(pref_bias_clear_store % (2 * clear_word_size));
+	BUG_ON(PAGE_SIZE < pref_bias_clear_store);
+
+	off = PAGE_SIZE - pref_bias_clear_store;
+	if (off > 0xffff || !pref_bias_clear_store)
+		pg_addiu(&buf, A2, A0, off);
+	else
+		uasm_i_ori(&buf, A2, A0, off);
+
+	if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
+		uasm_i_lui(&buf, AT, 0xa000);
+
+	off = min(8, pref_bias_clear_store / cache_line_size) *
+	      cache_line_size;
+	while (off) {
+		build_clear_pref(&buf, -off);
+		off -= cache_line_size;
+	}
+	uasm_l_clear_pref(&l, buf);
+	do {
+		build_clear_pref(&buf, off);
+		build_clear_store(&buf, off);
+		off += clear_word_size;
+	} while (off < half_clear_loop_size);
+	pg_addiu(&buf, A0, A0, 2 * off);
+	off = -off;
+	do {
+		build_clear_pref(&buf, off);
+		if (off == -clear_word_size)
+			uasm_il_bne(&buf, &r, A0, A2, label_clear_pref);
+		build_clear_store(&buf, off);
+		off += clear_word_size;
+	} while (off < 0);
+
+	if (pref_bias_clear_store) {
+		pg_addiu(&buf, A2, A0, pref_bias_clear_store);
+		uasm_l_clear_nopref(&l, buf);
+		off = 0;
+		do {
+			build_clear_store(&buf, off);
+			off += clear_word_size;
+		} while (off < half_clear_loop_size);
+		pg_addiu(&buf, A0, A0, 2 * off);
+		off = -off;
+		do {
+			if (off == -clear_word_size)
+				uasm_il_bne(&buf, &r, A0, A2,
+					    label_clear_nopref);
+			build_clear_store(&buf, off);
+			off += clear_word_size;
+		} while (off < 0);
+	}
+
+	uasm_i_jr(&buf, RA);
+	uasm_i_nop(&buf);
+
+	BUG_ON(buf > clear_page_array + ARRAY_SIZE(clear_page_array));
+
+	uasm_resolve_relocs(relocs, labels);
+
+	pr_debug("Synthesized clear page handler (%u instructions).\n",
+		 (u32)(buf - clear_page_array));
+
+	pr_debug("\t.set push\n");
+	pr_debug("\t.set noreorder\n");
+	for (i = 0; i < (buf - clear_page_array); i++)
+		pr_debug("\t.word 0x%08x\n", clear_page_array[i]);
+	pr_debug("\t.set pop\n");
+}
+
+static void __cpuinit build_copy_load(u32 **buf, int reg, int off)
+{
+	if (cpu_has_64bit_gp_regs) {
+		uasm_i_ld(buf, reg, off, A1);
+	} else {
+		uasm_i_lw(buf, reg, off, A1);
+	}
+}
+
+static void __cpuinit build_copy_store(u32 **buf, int reg, int off)
+{
+	if (cpu_has_64bit_gp_regs) {
+		uasm_i_sd(buf, reg, off, A0);
+	} else {
+		uasm_i_sw(buf, reg, off, A0);
+	}
+}
+
+static inline void build_copy_load_pref(u32 **buf, int off)
+{
+	if (off & cache_line_mask())
+		return;
+
+	if (pref_bias_copy_load)
+		uasm_i_pref(buf, pref_src_mode, pref_bias_copy_load + off, A1);
+}
+
+static inline void build_copy_store_pref(u32 **buf, int off)
+{
+	if (off & cache_line_mask())
+		return;
+
+	if (pref_bias_copy_store) {
+		uasm_i_pref(buf, pref_dst_mode, pref_bias_copy_store + off,
+			    A0);
+	} else if (cpu_has_cache_cdex_s) {
+		uasm_i_cache(buf, Create_Dirty_Excl_SD, off, A0);
+	} else if (cpu_has_cache_cdex_p) {
+		if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) {
+			uasm_i_nop(buf);
+			uasm_i_nop(buf);
+			uasm_i_nop(buf);
+			uasm_i_nop(buf);
+		}
+
+		if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
+			uasm_i_lw(buf, ZERO, ZERO, AT);
+
+		uasm_i_cache(buf, Create_Dirty_Excl_D, off, A0);
+	}
+}
+
+void __cpuinit build_copy_page(void)
+{
+	int off;
+	u32 *buf = (u32 *)&copy_page_array;
+	struct uasm_label *l = labels;
+	struct uasm_reloc *r = relocs;
+	int i;
+
+	memset(labels, 0, sizeof(labels));
+	memset(relocs, 0, sizeof(relocs));
+
+	set_prefetch_parameters();
+
+	/*
+	 * This algorithm makes the following assumptions:
+	 *   - All prefetch biases are multiples of 8 words.
+	 *   - The prefetch biases are less than one page.
+	 *   - The store prefetch bias isn't greater than the load
+	 *     prefetch bias.
+	 */
+	BUG_ON(pref_bias_copy_load % (8 * copy_word_size));
+	BUG_ON(pref_bias_copy_store % (8 * copy_word_size));
+	BUG_ON(PAGE_SIZE < pref_bias_copy_load);
+	BUG_ON(pref_bias_copy_store > pref_bias_copy_load);
+
+	off = PAGE_SIZE - pref_bias_copy_load;
+	if (off > 0xffff || !pref_bias_copy_load)
+		pg_addiu(&buf, A2, A0, off);
+	else
+		uasm_i_ori(&buf, A2, A0, off);
+
+	if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
+		uasm_i_lui(&buf, AT, 0xa000);
+
+	off = min(8, pref_bias_copy_load / cache_line_size) * cache_line_size;
+	while (off) {
+		build_copy_load_pref(&buf, -off);
+		off -= cache_line_size;
+	}
+	off = min(8, pref_bias_copy_store / cache_line_size) * cache_line_size;
+	while (off) {
+		build_copy_store_pref(&buf, -off);
+		off -= cache_line_size;
+	}
+	uasm_l_copy_pref_both(&l, buf);
+	do {
+		build_copy_load_pref(&buf, off);
+		build_copy_load(&buf, T0, off);
+		build_copy_load_pref(&buf, off + copy_word_size);
+		build_copy_load(&buf, T1, off + copy_word_size);
+		build_copy_load_pref(&buf, off + 2 * copy_word_size);
+		build_copy_load(&buf, T2, off + 2 * copy_word_size);
+		build_copy_load_pref(&buf, off + 3 * copy_word_size);
+		build_copy_load(&buf, T3, off + 3 * copy_word_size);
+		build_copy_store_pref(&buf, off);
+		build_copy_store(&buf, T0, off);
+		build_copy_store_pref(&buf, off + copy_word_size);
+		build_copy_store(&buf, T1, off + copy_word_size);
+		build_copy_store_pref(&buf, off + 2 * copy_word_size);
+		build_copy_store(&buf, T2, off + 2 * copy_word_size);
+		build_copy_store_pref(&buf, off + 3 * copy_word_size);
+		build_copy_store(&buf, T3, off + 3 * copy_word_size);
+		off += 4 * copy_word_size;
+	} while (off < half_copy_loop_size);
+	pg_addiu(&buf, A1, A1, 2 * off);
+	pg_addiu(&buf, A0, A0, 2 * off);
+	off = -off;
+	do {
+		build_copy_load_pref(&buf, off);
+		build_copy_load(&buf, T0, off);
+		build_copy_load_pref(&buf, off + copy_word_size);
+		build_copy_load(&buf, T1, off + copy_word_size);
+		build_copy_load_pref(&buf, off + 2 * copy_word_size);
+		build_copy_load(&buf, T2, off + 2 * copy_word_size);
+		build_copy_load_pref(&buf, off + 3 * copy_word_size);
+		build_copy_load(&buf, T3, off + 3 * copy_word_size);
+		build_copy_store_pref(&buf, off);
+		build_copy_store(&buf, T0, off);
+		build_copy_store_pref(&buf, off + copy_word_size);
+		build_copy_store(&buf, T1, off + copy_word_size);
+		build_copy_store_pref(&buf, off + 2 * copy_word_size);
+		build_copy_store(&buf, T2, off + 2 * copy_word_size);
+		build_copy_store_pref(&buf, off + 3 * copy_word_size);
+		if (off == -(4 * copy_word_size))
+			uasm_il_bne(&buf, &r, A2, A0, label_copy_pref_both);
+		build_copy_store(&buf, T3, off + 3 * copy_word_size);
+		off += 4 * copy_word_size;
+	} while (off < 0);
+
+	if (pref_bias_copy_load - pref_bias_copy_store) {
+		pg_addiu(&buf, A2, A0,
+			 pref_bias_copy_load - pref_bias_copy_store);
+		uasm_l_copy_pref_store(&l, buf);
+		off = 0;
+		do {
+			build_copy_load(&buf, T0, off);
+			build_copy_load(&buf, T1, off + copy_word_size);
+			build_copy_load(&buf, T2, off + 2 * copy_word_size);
+			build_copy_load(&buf, T3, off + 3 * copy_word_size);
+			build_copy_store_pref(&buf, off);
+			build_copy_store(&buf, T0, off);
+			build_copy_store_pref(&buf, off + copy_word_size);
+			build_copy_store(&buf, T1, off + copy_word_size);
+			build_copy_store_pref(&buf, off + 2 * copy_word_size);
+			build_copy_store(&buf, T2, off + 2 * copy_word_size);
+			build_copy_store_pref(&buf, off + 3 * copy_word_size);
+			build_copy_store(&buf, T3, off + 3 * copy_word_size);
+			off += 4 * copy_word_size;
+		} while (off < half_copy_loop_size);
+		pg_addiu(&buf, A1, A1, 2 * off);
+		pg_addiu(&buf, A0, A0, 2 * off);
+		off = -off;
+		do {
+			build_copy_load(&buf, T0, off);
+			build_copy_load(&buf, T1, off + copy_word_size);
+			build_copy_load(&buf, T2, off + 2 * copy_word_size);
+			build_copy_load(&buf, T3, off + 3 * copy_word_size);
+			build_copy_store_pref(&buf, off);
+			build_copy_store(&buf, T0, off);
+			build_copy_store_pref(&buf, off + copy_word_size);
+			build_copy_store(&buf, T1, off + copy_word_size);
+			build_copy_store_pref(&buf, off + 2 * copy_word_size);
+			build_copy_store(&buf, T2, off + 2 * copy_word_size);
+			build_copy_store_pref(&buf, off + 3 * copy_word_size);
+			if (off == -(4 * copy_word_size))
+				uasm_il_bne(&buf, &r, A2, A0,
+					    label_copy_pref_store);
+			build_copy_store(&buf, T3, off + 3 * copy_word_size);
+			off += 4 * copy_word_size;
+		} while (off < 0);
+	}
+
+	if (pref_bias_copy_store) {
+		pg_addiu(&buf, A2, A0, pref_bias_copy_store);
+		uasm_l_copy_nopref(&l, buf);
+		off = 0;
+		do {
+			build_copy_load(&buf, T0, off);
+			build_copy_load(&buf, T1, off + copy_word_size);
+			build_copy_load(&buf, T2, off + 2 * copy_word_size);
+			build_copy_load(&buf, T3, off + 3 * copy_word_size);
+			build_copy_store(&buf, T0, off);
+			build_copy_store(&buf, T1, off + copy_word_size);
+			build_copy_store(&buf, T2, off + 2 * copy_word_size);
+			build_copy_store(&buf, T3, off + 3 * copy_word_size);
+			off += 4 * copy_word_size;
+		} while (off < half_copy_loop_size);
+		pg_addiu(&buf, A1, A1, 2 * off);
+		pg_addiu(&buf, A0, A0, 2 * off);
+		off = -off;
+		do {
+			build_copy_load(&buf, T0, off);
+			build_copy_load(&buf, T1, off + copy_word_size);
+			build_copy_load(&buf, T2, off + 2 * copy_word_size);
+			build_copy_load(&buf, T3, off + 3 * copy_word_size);
+			build_copy_store(&buf, T0, off);
+			build_copy_store(&buf, T1, off + copy_word_size);
+			build_copy_store(&buf, T2, off + 2 * copy_word_size);
+			if (off == -(4 * copy_word_size))
+				uasm_il_bne(&buf, &r, A2, A0,
+					    label_copy_nopref);
+			build_copy_store(&buf, T3, off + 3 * copy_word_size);
+			off += 4 * copy_word_size;
+		} while (off < 0);
+	}
+
+	uasm_i_jr(&buf, RA);
+	uasm_i_nop(&buf);
+
+	BUG_ON(buf > copy_page_array + ARRAY_SIZE(copy_page_array));
+
+	uasm_resolve_relocs(relocs, labels);
+
+	pr_debug("Synthesized copy page handler (%u instructions).\n",
+		 (u32)(buf - copy_page_array));
+
+	pr_debug("\t.set push\n");
+	pr_debug("\t.set noreorder\n");
+	for (i = 0; i < (buf - copy_page_array); i++)
+		pr_debug("\t.word 0x%08x\n", copy_page_array[i]);
+	pr_debug("\t.set pop\n");
+}
+
+#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
+
+/*
+ * Pad descriptors to cacheline, since each is exclusively owned by a
+ * particular CPU.
+ */
+struct dmadscr {
+	u64 dscr_a;
+	u64 dscr_b;
+	u64 pad_a;
+	u64 pad_b;
+} ____cacheline_aligned_in_smp page_descr[DM_NUM_CHANNELS];
+
+void sb1_dma_init(void)
+{
+	int i;
+
+	for (i = 0; i < DM_NUM_CHANNELS; i++) {
+		const u64 base_val = CPHYSADDR((unsigned long)&page_descr[i]) |
+				     V_DM_DSCR_BASE_RINGSZ(1);
+		void *base_reg = IOADDR(A_DM_REGISTER(i, R_DM_DSCR_BASE));
+
+		__raw_writeq(base_val, base_reg);
+		__raw_writeq(base_val | M_DM_DSCR_BASE_RESET, base_reg);
+		__raw_writeq(base_val | M_DM_DSCR_BASE_ENABL, base_reg);
+	}
+}
+
+void clear_page(void *page)
+{
+	u64 to_phys = CPHYSADDR((unsigned long)page);
+	unsigned int cpu = smp_processor_id();
+
+	/* if the page is not in KSEG0, use old way */
+	if ((long)KSEGX((unsigned long)page) != (long)CKSEG0)
+		return clear_page_cpu(page);
+
+	page_descr[cpu].dscr_a = to_phys | M_DM_DSCRA_ZERO_MEM |
+				 M_DM_DSCRA_L2C_DEST | M_DM_DSCRA_INTERRUPT;
+	page_descr[cpu].dscr_b = V_DM_DSCRB_SRC_LENGTH(PAGE_SIZE);
+	__raw_writeq(1, IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_COUNT)));
+
+	/*
+	 * Don't really want to do it this way, but there's no
+	 * reliable way to delay completion detection.
+	 */
+	while (!(__raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE_DEBUG)))
+		 & M_DM_DSCR_BASE_INTERRUPT))
+		;
+	__raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE)));
+}
+
+void copy_page(void *to, void *from)
+{
+	u64 from_phys = CPHYSADDR((unsigned long)from);
+	u64 to_phys = CPHYSADDR((unsigned long)to);
+	unsigned int cpu = smp_processor_id();
+
+	/* if any page is not in KSEG0, use old way */
+	if ((long)KSEGX((unsigned long)to) != (long)CKSEG0
+	    || (long)KSEGX((unsigned long)from) != (long)CKSEG0)
+		return copy_page_cpu(to, from);
+
+	page_descr[cpu].dscr_a = to_phys | M_DM_DSCRA_L2C_DEST |
+				 M_DM_DSCRA_INTERRUPT;
+	page_descr[cpu].dscr_b = from_phys | V_DM_DSCRB_SRC_LENGTH(PAGE_SIZE);
+	__raw_writeq(1, IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_COUNT)));
+
+	/*
+	 * Don't really want to do it this way, but there's no
+	 * reliable way to delay completion detection.
+	 */
+	while (!(__raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE_DEBUG)))
+		 & M_DM_DSCR_BASE_INTERRUPT))
+		;
+	__raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE)));
+}
+
+#endif /* CONFIG_SIBYTE_DMA_PAGEOPS */
diff --git a/trunk/arch/mips/mm/pg-r4k.c b/trunk/arch/mips/mm/pg-r4k.c
deleted file mode 100644
index 455dedb5b39e..000000000000
--- a/trunk/arch/mips/mm/pg-r4k.c
+++ /dev/null
@@ -1,534 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2003, 04, 05 Ralf Baechle (ralf@linux-mips.org)
- * Copyright (C) 2007  Maciej W. Rozycki
- */
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/proc_fs.h>
-
-#include <asm/bugs.h>
-#include <asm/cacheops.h>
-#include <asm/inst.h>
-#include <asm/io.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/prefetch.h>
-#include <asm/system.h>
-#include <asm/bootinfo.h>
-#include <asm/mipsregs.h>
-#include <asm/mmu_context.h>
-#include <asm/cpu.h>
-#include <asm/war.h>
-
-#define half_scache_line_size()	(cpu_scache_line_size() >> 1)
-#define cpu_is_r4600_v1_x()	((read_c0_prid() & 0xfffffff0) == 0x00002010)
-#define cpu_is_r4600_v2_x()	((read_c0_prid() & 0xfffffff0) == 0x00002020)
-
-
-/*
- * Maximum sizes:
- *
- * R4000 128 bytes S-cache:		0x58 bytes
- * R4600 v1.7:				0x5c bytes
- * R4600 v2.0:				0x60 bytes
- * With prefetching, 16 byte strides	0xa0 bytes
- */
-
-static unsigned int clear_page_array[0x130 / 4];
-
-void clear_page(void * page) __attribute__((alias("clear_page_array")));
-
-EXPORT_SYMBOL(clear_page);
-
-/*
- * Maximum sizes:
- *
- * R4000 128 bytes S-cache:		0x11c bytes
- * R4600 v1.7:				0x080 bytes
- * R4600 v2.0:				0x07c bytes
- * With prefetching, 16 byte strides	0x0b8 bytes
- */
-static unsigned int copy_page_array[0x148 / 4];
-
-void copy_page(void *to, void *from) __attribute__((alias("copy_page_array")));
-
-EXPORT_SYMBOL(copy_page);
-
-/*
- * This is suboptimal for 32-bit kernels; we assume that R10000 is only used
- * with 64-bit kernels.  The prefetch offsets have been experimentally tuned
- * an Origin 200.
- */
-static int pref_offset_clear __cpuinitdata = 512;
-static int pref_offset_copy  __cpuinitdata = 256;
-
-static unsigned int pref_src_mode __cpuinitdata;
-static unsigned int pref_dst_mode __cpuinitdata;
-
-static int load_offset __cpuinitdata;
-static int store_offset __cpuinitdata;
-
-static unsigned int __cpuinitdata *dest, *epc;
-
-static unsigned int instruction_pending;
-static union mips_instruction delayed_mi;
-
-static void __cpuinit emit_instruction(union mips_instruction mi)
-{
-	if (instruction_pending)
-		*epc++ = delayed_mi.word;
-
-	instruction_pending = 1;
-	delayed_mi = mi;
-}
-
-static inline void flush_delay_slot_or_nop(void)
-{
-	if (instruction_pending) {
-		*epc++ = delayed_mi.word;
-		instruction_pending = 0;
-		return;
-	}
-
-	*epc++ = 0;
-}
-
-static inline unsigned int *label(void)
-{
-	if (instruction_pending) {
-		*epc++ = delayed_mi.word;
-		instruction_pending = 0;
-	}
-
-	return epc;
-}
-
-static inline void build_insn_word(unsigned int word)
-{
-	union mips_instruction mi;
-
-	mi.word		 = word;
-
-	emit_instruction(mi);
-}
-
-static inline void build_nop(void)
-{
-	build_insn_word(0);			/* nop */
-}
-
-static inline void build_src_pref(int advance)
-{
-	if (!(load_offset & (cpu_dcache_line_size() - 1)) && advance) {
-		union mips_instruction mi;
-
-		mi.i_format.opcode     = pref_op;
-		mi.i_format.rs         = 5;		/* $a1 */
-		mi.i_format.rt         = pref_src_mode;
-		mi.i_format.simmediate = load_offset + advance;
-
-		emit_instruction(mi);
-	}
-}
-
-static inline void __build_load_reg(int reg)
-{
-	union mips_instruction mi;
-	unsigned int width;
-
-	if (cpu_has_64bit_gp_regs) {
-		mi.i_format.opcode     = ld_op;
-		width = 8;
-	} else {
-		mi.i_format.opcode     = lw_op;
-		width = 4;
-	}
-	mi.i_format.rs         = 5;		/* $a1 */
-	mi.i_format.rt         = reg;		/* $reg */
-	mi.i_format.simmediate = load_offset;
-
-	load_offset += width;
-	emit_instruction(mi);
-}
-
-static inline void build_load_reg(int reg)
-{
-	if (cpu_has_prefetch)
-		build_src_pref(pref_offset_copy);
-
-	__build_load_reg(reg);
-}
-
-static inline void build_dst_pref(int advance)
-{
-	if (!(store_offset & (cpu_dcache_line_size() - 1)) && advance) {
-		union mips_instruction mi;
-
-		mi.i_format.opcode     = pref_op;
-		mi.i_format.rs         = 4;		/* $a0 */
-		mi.i_format.rt         = pref_dst_mode;
-		mi.i_format.simmediate = store_offset + advance;
-
-		emit_instruction(mi);
-	}
-}
-
-static inline void build_cdex_s(void)
-{
-	union mips_instruction mi;
-
-	if ((store_offset & (cpu_scache_line_size() - 1)))
-		return;
-
-	mi.c_format.opcode     = cache_op;
-	mi.c_format.rs         = 4;		/* $a0 */
-	mi.c_format.c_op       = 3;		/* Create Dirty Exclusive */
-	mi.c_format.cache      = 3;		/* Secondary Data Cache */
-	mi.c_format.simmediate = store_offset;
-
-	emit_instruction(mi);
-}
-
-static inline void build_cdex_p(void)
-{
-	union mips_instruction mi;
-
-	if (store_offset & (cpu_dcache_line_size() - 1))
-		return;
-
-	if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) {
-		build_nop();
-		build_nop();
-		build_nop();
-		build_nop();
-	}
-
-	if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
-		build_insn_word(0x8c200000);	/* lw      $zero, ($at) */
-
-	mi.c_format.opcode     = cache_op;
-	mi.c_format.rs         = 4;		/* $a0 */
-	mi.c_format.c_op       = 3;		/* Create Dirty Exclusive */
-	mi.c_format.cache      = 1;		/* Data Cache */
-	mi.c_format.simmediate = store_offset;
-
-	emit_instruction(mi);
-}
-
-static void __cpuinit __build_store_reg(int reg)
-{
-	union mips_instruction mi;
-	unsigned int width;
-
-	if (cpu_has_64bit_gp_regs ||
-	    (cpu_has_64bit_zero_reg && reg == 0)) {
-		mi.i_format.opcode     = sd_op;
-		width = 8;
-	} else {
-		mi.i_format.opcode     = sw_op;
-		width = 4;
-	}
-	mi.i_format.rs         = 4;		/* $a0 */
-	mi.i_format.rt         = reg;		/* $reg */
-	mi.i_format.simmediate = store_offset;
-
-	store_offset += width;
-	emit_instruction(mi);
-}
-
-static inline void build_store_reg(int reg)
-{
-	int pref_off = cpu_has_prefetch ?
-		(reg ? pref_offset_copy : pref_offset_clear) : 0;
-	if (pref_off)
-		build_dst_pref(pref_off);
-	else if (cpu_has_cache_cdex_s)
-		build_cdex_s();
-	else if (cpu_has_cache_cdex_p)
-		build_cdex_p();
-
-	__build_store_reg(reg);
-}
-
-static inline void build_addiu_rt_rs(unsigned int rt, unsigned int rs,
-				     unsigned long offset)
-{
-	union mips_instruction mi;
-
-	BUG_ON(offset > 0x7fff);
-
-	if (cpu_has_64bit_gp_regs && DADDI_WAR && r4k_daddiu_bug()) {
-		mi.i_format.opcode     = addiu_op;
-		mi.i_format.rs         = 0;	/* $zero */
-		mi.i_format.rt         = 25;	/* $t9 */
-		mi.i_format.simmediate = offset;
-		emit_instruction(mi);
-
-		mi.r_format.opcode     = spec_op;
-		mi.r_format.rs         = rs;
-		mi.r_format.rt         = 25;	/* $t9 */
-		mi.r_format.rd         = rt;
-		mi.r_format.re         = 0;
-		mi.r_format.func       = daddu_op;
-	} else {
-		mi.i_format.opcode     = cpu_has_64bit_gp_regs ?
-					 daddiu_op : addiu_op;
-		mi.i_format.rs         = rs;
-		mi.i_format.rt         = rt;
-		mi.i_format.simmediate = offset;
-	}
-	emit_instruction(mi);
-}
-
-static inline void build_addiu_a2_a0(unsigned long offset)
-{
-	build_addiu_rt_rs(6, 4, offset);	/* $a2, $a0, offset */
-}
-
-static inline void build_addiu_a2(unsigned long offset)
-{
-	build_addiu_rt_rs(6, 6, offset);	/* $a2, $a2, offset */
-}
-
-static inline void build_addiu_a1(unsigned long offset)
-{
-	build_addiu_rt_rs(5, 5, offset);	/* $a1, $a1, offset */
-
-	load_offset -= offset;
-}
-
-static inline void build_addiu_a0(unsigned long offset)
-{
-	build_addiu_rt_rs(4, 4, offset);	/* $a0, $a0, offset */
-
-	store_offset -= offset;
-}
-
-static inline void build_bne(unsigned int *dest)
-{
-	union mips_instruction mi;
-
-	mi.i_format.opcode = bne_op;
-	mi.i_format.rs     = 6;			/* $a2 */
-	mi.i_format.rt     = 4;			/* $a0 */
-	mi.i_format.simmediate = dest - epc - 1;
-
-	*epc++ = mi.word;
-	flush_delay_slot_or_nop();
-}
-
-static inline void build_jr_ra(void)
-{
-	union mips_instruction mi;
-
-	mi.r_format.opcode = spec_op;
-	mi.r_format.rs     = 31;
-	mi.r_format.rt     = 0;
-	mi.r_format.rd     = 0;
-	mi.r_format.re     = 0;
-	mi.r_format.func   = jr_op;
-
-	*epc++ = mi.word;
-	flush_delay_slot_or_nop();
-}
-
-void __cpuinit build_clear_page(void)
-{
-	unsigned int loop_start;
-	unsigned long off;
-	int i;
-
-	epc = (unsigned int *) &clear_page_array;
-	instruction_pending = 0;
-	store_offset = 0;
-
-	if (cpu_has_prefetch) {
-		switch (current_cpu_type()) {
-		case CPU_TX49XX:
-			/* TX49 supports only Pref_Load */
-			pref_offset_clear = 0;
-			pref_offset_copy = 0;
-			break;
-
-		case CPU_RM9000:
-			/*
-			 * As a workaround for erratum G105 which make the
-			 * PrepareForStore hint unusable we fall back to
-			 * StoreRetained on the RM9000.  Once it is known which
-			 * versions of the RM9000 we'll be able to condition-
-			 * alize this.
-			 */
-
-		case CPU_R10000:
-		case CPU_R12000:
-		case CPU_R14000:
-			pref_src_mode = Pref_LoadStreamed;
-			pref_dst_mode = Pref_StoreStreamed;
-			break;
-
-		default:
-			pref_src_mode = Pref_LoadStreamed;
-			pref_dst_mode = Pref_PrepareForStore;
-			break;
-		}
-	}
-
-        off = PAGE_SIZE - (cpu_has_prefetch ? pref_offset_clear : 0);
-	if (off > 0x7fff) {
-		build_addiu_a2_a0(off >> 1);
-		build_addiu_a2(off >> 1);
-	} else
-		build_addiu_a2_a0(off);
-
-	if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
-		build_insn_word(0x3c01a000);	/* lui     $at, 0xa000  */
-
-dest = label();
-	do {
-		build_store_reg(0);
-		build_store_reg(0);
-		build_store_reg(0);
-		build_store_reg(0);
-	} while (store_offset < half_scache_line_size());
-	build_addiu_a0(2 * store_offset);
-	loop_start = store_offset;
-	do {
-		build_store_reg(0);
-		build_store_reg(0);
-		build_store_reg(0);
-		build_store_reg(0);
-	} while ((store_offset - loop_start) < half_scache_line_size());
-	build_bne(dest);
-
-	if (cpu_has_prefetch && pref_offset_clear) {
-		build_addiu_a2_a0(pref_offset_clear);
-	dest = label();
-		loop_start = store_offset;
-		do {
-			__build_store_reg(0);
-			__build_store_reg(0);
-			__build_store_reg(0);
-			__build_store_reg(0);
-		} while ((store_offset - loop_start) < half_scache_line_size());
-		build_addiu_a0(2 * store_offset);
-		loop_start = store_offset;
-		do {
-			__build_store_reg(0);
-			__build_store_reg(0);
-			__build_store_reg(0);
-			__build_store_reg(0);
-		} while ((store_offset - loop_start) < half_scache_line_size());
-		build_bne(dest);
-	}
-
-	build_jr_ra();
-
-	BUG_ON(epc > clear_page_array + ARRAY_SIZE(clear_page_array));
-
-	pr_info("Synthesized clear page handler (%u instructions).\n",
-		(unsigned int)(epc - clear_page_array));
-
-	pr_debug("\t.set push\n");
-	pr_debug("\t.set noreorder\n");
-	for (i = 0; i < (epc - clear_page_array); i++)
-		pr_debug("\t.word 0x%08x\n", clear_page_array[i]);
-	pr_debug("\t.set pop\n");
-}
-
-void __cpuinit build_copy_page(void)
-{
-	unsigned int loop_start;
-	unsigned long off;
-	int i;
-
-	epc = (unsigned int *) &copy_page_array;
-	store_offset = load_offset = 0;
-	instruction_pending = 0;
-
-	off = PAGE_SIZE - (cpu_has_prefetch ? pref_offset_copy : 0);
-	if (off > 0x7fff) {
-		build_addiu_a2_a0(off >> 1);
-		build_addiu_a2(off >> 1);
-	} else
-		build_addiu_a2_a0(off);
-
-	if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
-		build_insn_word(0x3c01a000);	/* lui     $at, 0xa000  */
-
-dest = label();
-	loop_start = store_offset;
-	do {
-		build_load_reg( 8);
-		build_load_reg( 9);
-		build_load_reg(10);
-		build_load_reg(11);
-		build_store_reg( 8);
-		build_store_reg( 9);
-		build_store_reg(10);
-		build_store_reg(11);
-	} while ((store_offset - loop_start) < half_scache_line_size());
-	build_addiu_a0(2 * store_offset);
-	build_addiu_a1(2 * load_offset);
-	loop_start = store_offset;
-	do {
-		build_load_reg( 8);
-		build_load_reg( 9);
-		build_load_reg(10);
-		build_load_reg(11);
-		build_store_reg( 8);
-		build_store_reg( 9);
-		build_store_reg(10);
-		build_store_reg(11);
-	} while ((store_offset - loop_start) < half_scache_line_size());
-	build_bne(dest);
-
-	if (cpu_has_prefetch && pref_offset_copy) {
-		build_addiu_a2_a0(pref_offset_copy);
-	dest = label();
-		loop_start = store_offset;
-		do {
-			__build_load_reg( 8);
-			__build_load_reg( 9);
-			__build_load_reg(10);
-			__build_load_reg(11);
-			__build_store_reg( 8);
-			__build_store_reg( 9);
-			__build_store_reg(10);
-			__build_store_reg(11);
-		} while ((store_offset - loop_start) < half_scache_line_size());
-		build_addiu_a0(2 * store_offset);
-		build_addiu_a1(2 * load_offset);
-		loop_start = store_offset;
-		do {
-			__build_load_reg( 8);
-			__build_load_reg( 9);
-			__build_load_reg(10);
-			__build_load_reg(11);
-			__build_store_reg( 8);
-			__build_store_reg( 9);
-			__build_store_reg(10);
-			__build_store_reg(11);
-		} while ((store_offset - loop_start) < half_scache_line_size());
-		build_bne(dest);
-	}
-
-	build_jr_ra();
-
-	BUG_ON(epc > copy_page_array + ARRAY_SIZE(copy_page_array));
-
-	pr_info("Synthesized copy page handler (%u instructions).\n",
-		(unsigned int)(epc - copy_page_array));
-
-	pr_debug("\t.set push\n");
-	pr_debug("\t.set noreorder\n");
-	for (i = 0; i < (epc - copy_page_array); i++)
-		pr_debug("\t.word 0x%08x\n", copy_page_array[i]);
-	pr_debug("\t.set pop\n");
-}
diff --git a/trunk/arch/mips/mm/pg-sb1.c b/trunk/arch/mips/mm/pg-sb1.c
deleted file mode 100644
index 49e289d05414..000000000000
--- a/trunk/arch/mips/mm/pg-sb1.c
+++ /dev/null
@@ -1,302 +0,0 @@
-/*
- * Copyright (C) 1996 David S. Miller (dm@engr.sgi.com)
- * Copyright (C) 1997, 2001 Ralf Baechle (ralf@gnu.org)
- * Copyright (C) 2000 SiByte, Inc.
- * Copyright (C) 2005 Thiemo Seufer
- *
- * Written by Justin Carlson of SiByte, Inc.
- *         and Kip Walker of Broadcom Corp.
- *
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- */
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/smp.h>
-
-#include <asm/io.h>
-#include <asm/sibyte/sb1250.h>
-#include <asm/sibyte/sb1250_regs.h>
-#include <asm/sibyte/sb1250_dma.h>
-
-#ifdef CONFIG_SB1_PASS_1_WORKAROUNDS
-#define SB1_PREF_LOAD_STREAMED_HINT "0"
-#define SB1_PREF_STORE_STREAMED_HINT "1"
-#else
-#define SB1_PREF_LOAD_STREAMED_HINT "4"
-#define SB1_PREF_STORE_STREAMED_HINT "5"
-#endif
-
-static inline void clear_page_cpu(void *page)
-{
-	unsigned char *addr = (unsigned char *) page;
-	unsigned char *end = addr + PAGE_SIZE;
-
-	/*
-	 * JDCXXX - This should be bottlenecked by the write buffer, but these
-	 * things tend to be mildly unpredictable...should check this on the
-	 * performance model
-	 *
-	 * We prefetch 4 lines ahead.  We're also "cheating" slightly here...
-	 * since we know we're on an SB1, we force the assembler to take
-	 * 64-bit operands to speed things up
-	 */
-	__asm__ __volatile__(
-	"	.set	push		\n"
-	"	.set	mips4		\n"
-	"	.set	noreorder	\n"
-#ifdef CONFIG_CPU_HAS_PREFETCH
-	"	daddiu	%0, %0, 128	\n"
-	"	pref	" SB1_PREF_STORE_STREAMED_HINT ", -128(%0)  \n"
-					     /* Prefetch the first 4 lines */
-	"	pref	" SB1_PREF_STORE_STREAMED_HINT ",  -96(%0)  \n"
-	"	pref	" SB1_PREF_STORE_STREAMED_HINT ",  -64(%0)  \n"
-	"	pref	" SB1_PREF_STORE_STREAMED_HINT ",  -32(%0)  \n"
-	"1:	sd	$0, -128(%0)	\n"  /* Throw out a cacheline of 0's */
-	"	sd	$0, -120(%0)	\n"
-	"	sd	$0, -112(%0)	\n"
-	"	sd	$0, -104(%0)	\n"
-	"	daddiu	%0, %0, 32	\n"
-	"	bnel	%0, %1, 1b	\n"
-	"	 pref	" SB1_PREF_STORE_STREAMED_HINT ",  -32(%0)  \n"
-	"	daddiu	%0, %0, -128	\n"
-#endif
-	"	sd	$0, 0(%0)	\n"  /* Throw out a cacheline of 0's */
-	"1:	sd	$0, 8(%0)	\n"
-	"	sd	$0, 16(%0)	\n"
-	"	sd	$0, 24(%0)	\n"
-	"	daddiu	%0, %0, 32	\n"
-	"	bnel	%0, %1, 1b	\n"
-	"	 sd	$0, 0(%0)	\n"
-	"	.set	pop		\n"
-	: "+r" (addr)
-	: "r" (end)
-	: "memory");
-}
-
-static inline void copy_page_cpu(void *to, void *from)
-{
-	unsigned char *src = (unsigned char *)from;
-	unsigned char *dst = (unsigned char *)to;
-	unsigned char *end = src + PAGE_SIZE;
-
-	/*
-	 * The pref's used here are using "streaming" hints, which cause the
-	 * copied data to be kicked out of the cache sooner.  A page copy often
-	 * ends up copying a lot more data than is commonly used, so this seems
-	 * to make sense in terms of reducing cache pollution, but I've no real
-	 * performance data to back this up
-	 */
-	__asm__ __volatile__(
-	"	.set	push		\n"
-	"	.set	mips4		\n"
-	"	.set	noreorder	\n"
-#ifdef CONFIG_CPU_HAS_PREFETCH
-	"	daddiu	%0, %0, 128	\n"
-	"	daddiu	%1, %1, 128	\n"
-	"	pref	" SB1_PREF_LOAD_STREAMED_HINT  ", -128(%0)\n"
-					     /* Prefetch the first 4 lines */
-	"	pref	" SB1_PREF_STORE_STREAMED_HINT ", -128(%1)\n"
-	"	pref	" SB1_PREF_LOAD_STREAMED_HINT  ",  -96(%0)\n"
-	"	pref	" SB1_PREF_STORE_STREAMED_HINT ",  -96(%1)\n"
-	"	pref	" SB1_PREF_LOAD_STREAMED_HINT  ",  -64(%0)\n"
-	"	pref	" SB1_PREF_STORE_STREAMED_HINT ",  -64(%1)\n"
-	"	pref	" SB1_PREF_LOAD_STREAMED_HINT  ",  -32(%0)\n"
-	"1:	pref	" SB1_PREF_STORE_STREAMED_HINT ",  -32(%1)\n"
-# ifdef CONFIG_64BIT
-	"	ld	$8, -128(%0)	\n"  /* Block copy a cacheline */
-	"	ld	$9, -120(%0)	\n"
-	"	ld	$10, -112(%0)	\n"
-	"	ld	$11, -104(%0)	\n"
-	"	sd	$8, -128(%1)	\n"
-	"	sd	$9, -120(%1)	\n"
-	"	sd	$10, -112(%1)	\n"
-	"	sd	$11, -104(%1)	\n"
-# else
-	"	lw	$2, -128(%0)	\n"  /* Block copy a cacheline */
-	"	lw	$3, -124(%0)	\n"
-	"	lw	$6, -120(%0)	\n"
-	"	lw	$7, -116(%0)	\n"
-	"	lw	$8, -112(%0)	\n"
-	"	lw	$9, -108(%0)	\n"
-	"	lw	$10, -104(%0)	\n"
-	"	lw	$11, -100(%0)	\n"
-	"	sw	$2, -128(%1)	\n"
-	"	sw	$3, -124(%1)	\n"
-	"	sw	$6, -120(%1)	\n"
-	"	sw	$7, -116(%1)	\n"
-	"	sw	$8, -112(%1)	\n"
-	"	sw	$9, -108(%1)	\n"
-	"	sw	$10, -104(%1)	\n"
-	"	sw	$11, -100(%1)	\n"
-# endif
-	"	daddiu	%0, %0, 32	\n"
-	"	daddiu	%1, %1, 32	\n"
-	"	bnel	%0, %2, 1b	\n"
-	"	 pref	" SB1_PREF_LOAD_STREAMED_HINT  ",  -32(%0)\n"
-	"	daddiu	%0, %0, -128	\n"
-	"	daddiu	%1, %1, -128	\n"
-#endif
-#ifdef CONFIG_64BIT
-	"	ld	$8, 0(%0)	\n"  /* Block copy a cacheline */
-	"1:	ld	$9, 8(%0)	\n"
-	"	ld	$10, 16(%0)	\n"
-	"	ld	$11, 24(%0)	\n"
-	"	sd	$8, 0(%1)	\n"
-	"	sd	$9, 8(%1)	\n"
-	"	sd	$10, 16(%1)	\n"
-	"	sd	$11, 24(%1)	\n"
-#else
-	"	lw	$2, 0(%0)	\n"  /* Block copy a cacheline */
-	"1:	lw	$3, 4(%0)	\n"
-	"	lw	$6, 8(%0)	\n"
-	"	lw	$7, 12(%0)	\n"
-	"	lw	$8, 16(%0)	\n"
-	"	lw	$9, 20(%0)	\n"
-	"	lw	$10, 24(%0)	\n"
-	"	lw	$11, 28(%0)	\n"
-	"	sw	$2, 0(%1)	\n"
-	"	sw	$3, 4(%1)	\n"
-	"	sw	$6, 8(%1)	\n"
-	"	sw	$7, 12(%1)	\n"
-	"	sw	$8, 16(%1)	\n"
-	"	sw	$9, 20(%1)	\n"
-	"	sw	$10, 24(%1)	\n"
-	"	sw	$11, 28(%1)	\n"
-#endif
-	"	daddiu	%0, %0, 32	\n"
-	"	daddiu	%1, %1, 32	\n"
-	"	bnel	%0, %2, 1b	\n"
-#ifdef CONFIG_64BIT
-	"	 ld	$8, 0(%0)	\n"
-#else
-	"	 lw	$2, 0(%0)	\n"
-#endif
-	"	.set	pop		\n"
-	: "+r" (src), "+r" (dst)
-	: "r" (end)
-#ifdef CONFIG_64BIT
-	: "$8", "$9", "$10", "$11", "memory");
-#else
-	: "$2", "$3", "$6", "$7", "$8", "$9", "$10", "$11", "memory");
-#endif
-}
-
-
-#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
-
-/*
- * Pad descriptors to cacheline, since each is exclusively owned by a
- * particular CPU.
- */
-typedef struct dmadscr_s {
-	u64 dscr_a;
-	u64 dscr_b;
-	u64 pad_a;
-	u64 pad_b;
-} dmadscr_t;
-
-static dmadscr_t page_descr[DM_NUM_CHANNELS]
-	__attribute__((aligned(SMP_CACHE_BYTES)));
-
-void sb1_dma_init(void)
-{
-	int i;
-
-	for (i = 0; i < DM_NUM_CHANNELS; i++) {
-		const u64 base_val = CPHYSADDR((unsigned long)&page_descr[i]) |
-				     V_DM_DSCR_BASE_RINGSZ(1);
-		void *base_reg = IOADDR(A_DM_REGISTER(i, R_DM_DSCR_BASE));
-
-		__raw_writeq(base_val, base_reg);
-		__raw_writeq(base_val | M_DM_DSCR_BASE_RESET, base_reg);
-		__raw_writeq(base_val | M_DM_DSCR_BASE_ENABL, base_reg);
-	}
-}
-
-void clear_page(void *page)
-{
-	u64 to_phys = CPHYSADDR((unsigned long)page);
-	unsigned int cpu = smp_processor_id();
-
-	/* if the page is not in KSEG0, use old way */
-	if ((long)KSEGX((unsigned long)page) != (long)CKSEG0)
-		return clear_page_cpu(page);
-
-	page_descr[cpu].dscr_a = to_phys | M_DM_DSCRA_ZERO_MEM |
-				 M_DM_DSCRA_L2C_DEST | M_DM_DSCRA_INTERRUPT;
-	page_descr[cpu].dscr_b = V_DM_DSCRB_SRC_LENGTH(PAGE_SIZE);
-	__raw_writeq(1, IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_COUNT)));
-
-	/*
-	 * Don't really want to do it this way, but there's no
-	 * reliable way to delay completion detection.
-	 */
-	while (!(__raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE_DEBUG)))
-		 & M_DM_DSCR_BASE_INTERRUPT))
-		;
-	__raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE)));
-}
-
-void copy_page(void *to, void *from)
-{
-	u64 from_phys = CPHYSADDR((unsigned long)from);
-	u64 to_phys = CPHYSADDR((unsigned long)to);
-	unsigned int cpu = smp_processor_id();
-
-	/* if any page is not in KSEG0, use old way */
-	if ((long)KSEGX((unsigned long)to) != (long)CKSEG0
-	    || (long)KSEGX((unsigned long)from) != (long)CKSEG0)
-		return copy_page_cpu(to, from);
-
-	page_descr[cpu].dscr_a = to_phys | M_DM_DSCRA_L2C_DEST |
-				 M_DM_DSCRA_INTERRUPT;
-	page_descr[cpu].dscr_b = from_phys | V_DM_DSCRB_SRC_LENGTH(PAGE_SIZE);
-	__raw_writeq(1, IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_COUNT)));
-
-	/*
-	 * Don't really want to do it this way, but there's no
-	 * reliable way to delay completion detection.
-	 */
-	while (!(__raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE_DEBUG)))
-		 & M_DM_DSCR_BASE_INTERRUPT))
-		;
-	__raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE)));
-}
-
-#else /* !CONFIG_SIBYTE_DMA_PAGEOPS */
-
-void clear_page(void *page)
-{
-	return clear_page_cpu(page);
-}
-
-void copy_page(void *to, void *from)
-{
-	return copy_page_cpu(to, from);
-}
-
-#endif /* !CONFIG_SIBYTE_DMA_PAGEOPS */
-
-EXPORT_SYMBOL(clear_page);
-EXPORT_SYMBOL(copy_page);
-
-void __cpuinit build_clear_page(void)
-{
-}
-
-void __cpuinit build_copy_page(void)
-{
-}
diff --git a/trunk/arch/mips/mm/pgtable.c b/trunk/arch/mips/mm/pgtable.c
index 57df1c38e303..7dfa579ab24c 100644
--- a/trunk/arch/mips/mm/pgtable.c
+++ b/trunk/arch/mips/mm/pgtable.c
@@ -12,7 +12,6 @@ void show_mem(void)
 
 	printk("Mem-info:\n");
 	show_free_areas();
-	printk("Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
 	pfn = max_mapnr;
 	while (pfn-- > 0) {
 		if (!pfn_valid(pfn))
diff --git a/trunk/arch/mips/mm/tlb-r4k.c b/trunk/arch/mips/mm/tlb-r4k.c
index 63065d6e8063..5ce2fa745626 100644
--- a/trunk/arch/mips/mm/tlb-r4k.c
+++ b/trunk/arch/mips/mm/tlb-r4k.c
@@ -299,7 +299,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte)
 	idx = read_c0_index();
 	ptep = pte_offset_map(pmdp, address);
 
-#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32_R1)
+#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32)
 	write_c0_entrylo0(ptep->pte_high);
 	ptep++;
 	write_c0_entrylo1(ptep->pte_high);
diff --git a/trunk/arch/mips/mm/uasm.c b/trunk/arch/mips/mm/uasm.c
index 1a6f7704cc89..1655aa69e133 100644
--- a/trunk/arch/mips/mm/uasm.c
+++ b/trunk/arch/mips/mm/uasm.c
@@ -58,13 +58,13 @@ enum opcode {
 	insn_invalid,
 	insn_addu, insn_addiu, insn_and, insn_andi, insn_beq,
 	insn_beql, insn_bgez, insn_bgezl, insn_bltz, insn_bltzl,
-	insn_bne, insn_daddu, insn_daddiu, insn_dmfc0, insn_dmtc0,
-	insn_dsll, insn_dsll32, insn_dsra, insn_dsrl, insn_dsrl32,
-	insn_dsubu, insn_eret, insn_j, insn_jal, insn_jr, insn_ld,
-	insn_ll, insn_lld, insn_lui, insn_lw, insn_mfc0, insn_mtc0,
-	insn_ori, insn_rfe, insn_sc, insn_scd, insn_sd, insn_sll,
-	insn_sra, insn_srl, insn_subu, insn_sw, insn_tlbp, insn_tlbwi,
-	insn_tlbwr, insn_xor, insn_xori
+	insn_bne, insn_cache, insn_daddu, insn_daddiu, insn_dmfc0,
+	insn_dmtc0, insn_dsll, insn_dsll32, insn_dsra, insn_dsrl,
+	insn_dsrl32, insn_dsubu, insn_eret, insn_j, insn_jal, insn_jr,
+	insn_ld, insn_ll, insn_lld, insn_lui, insn_lw, insn_mfc0,
+	insn_mtc0, insn_ori, insn_pref, insn_rfe, insn_sc, insn_scd,
+	insn_sd, insn_sll, insn_sra, insn_srl, insn_subu, insn_sw,
+	insn_tlbp, insn_tlbwi, insn_tlbwr, insn_xor, insn_xori
 };
 
 struct insn {
@@ -94,6 +94,7 @@ static struct insn insn_table[] __cpuinitdata = {
 	{ insn_bltz, M(bcond_op, 0, bltz_op, 0, 0, 0), RS | BIMM },
 	{ insn_bltzl, M(bcond_op, 0, bltzl_op, 0, 0, 0), RS | BIMM },
 	{ insn_bne, M(bne_op, 0, 0, 0, 0, 0), RS | RT | BIMM },
+	{ insn_cache,  M(cache_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
 	{ insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD },
 	{ insn_dmfc0, M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET},
@@ -116,6 +117,7 @@ static struct insn insn_table[] __cpuinitdata = {
 	{ insn_mfc0,  M(cop0_op, mfc_op, 0, 0, 0, 0),  RT | RD | SET},
 	{ insn_mtc0,  M(cop0_op, mtc_op, 0, 0, 0, 0),  RT | RD | SET},
 	{ insn_ori,  M(ori_op, 0, 0, 0, 0, 0),  RS | RT | UIMM },
+	{ insn_pref,  M(pref_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_rfe,  M(cop0_op, cop_op, 0, 0, 0, rfe_op),  0 },
 	{ insn_sc,  M(sc_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_scd,  M(scd_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
@@ -337,6 +339,7 @@ I_u1s2(_bgezl)
 I_u1s2(_bltz)
 I_u1s2(_bltzl)
 I_u1u2s3(_bne)
+I_u2s3u1(_cache)
 I_u1u2u3(_dmfc0)
 I_u1u2u3(_dmtc0)
 I_u2u1s3(_daddiu)
@@ -359,6 +362,7 @@ I_u2s3u1(_lw)
 I_u1u2u3(_mfc0)
 I_u1u2u3(_mtc0)
 I_u2u1u3(_ori)
+I_u2s3u1(_pref)
 I_0(_rfe)
 I_u2s3u1(_sc)
 I_u2s3u1(_scd)
@@ -554,6 +558,14 @@ uasm_il_beqzl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid)
 	uasm_i_beqzl(p, reg, 0);
 }
 
+void __cpuinit
+uasm_il_bne(u32 **p, struct uasm_reloc **r, unsigned int reg1,
+	unsigned int reg2, int lid)
+{
+	uasm_r_mips_pc16(r, *p, lid);
+	uasm_i_bne(p, reg1, reg2, 0);
+}
+
 void __cpuinit
 uasm_il_bnez(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid)
 {
diff --git a/trunk/arch/mips/mm/uasm.h b/trunk/arch/mips/mm/uasm.h
index fe0574f6e77d..0d6a66f32030 100644
--- a/trunk/arch/mips/mm/uasm.h
+++ b/trunk/arch/mips/mm/uasm.h
@@ -55,6 +55,7 @@ Ip_u1s2(_bgezl);
 Ip_u1s2(_bltz);
 Ip_u1s2(_bltzl);
 Ip_u1u2s3(_bne);
+Ip_u2s3u1(_cache);
 Ip_u1u2u3(_dmfc0);
 Ip_u1u2u3(_dmtc0);
 Ip_u2u1s3(_daddiu);
@@ -77,6 +78,7 @@ Ip_u2s3u1(_lw);
 Ip_u1u2u3(_mfc0);
 Ip_u1u2u3(_mtc0);
 Ip_u2u1u3(_ori);
+Ip_u2s3u1(_pref);
 Ip_0(_rfe);
 Ip_u2s3u1(_sc);
 Ip_u2s3u1(_scd);
@@ -177,6 +179,8 @@ void uasm_il_bltz(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
 void uasm_il_b(u32 **p, struct uasm_reloc **r, int lid);
 void uasm_il_beqz(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
 void uasm_il_beqzl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
+void uasm_il_bne(u32 **p, struct uasm_reloc **r, unsigned int reg1,
+		 unsigned int reg2, int lid);
 void uasm_il_bnez(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
 void uasm_il_bgezl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
 void uasm_il_bgez(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
diff --git a/trunk/arch/mips/philips/pnx8550/common/Makefile b/trunk/arch/mips/nxp/pnx8550/common/Makefile
similarity index 100%
rename from trunk/arch/mips/philips/pnx8550/common/Makefile
rename to trunk/arch/mips/nxp/pnx8550/common/Makefile
diff --git a/trunk/arch/mips/philips/pnx8550/common/gdb_hook.c b/trunk/arch/mips/nxp/pnx8550/common/gdb_hook.c
similarity index 100%
rename from trunk/arch/mips/philips/pnx8550/common/gdb_hook.c
rename to trunk/arch/mips/nxp/pnx8550/common/gdb_hook.c
diff --git a/trunk/arch/mips/philips/pnx8550/common/int.c b/trunk/arch/mips/nxp/pnx8550/common/int.c
similarity index 100%
rename from trunk/arch/mips/philips/pnx8550/common/int.c
rename to trunk/arch/mips/nxp/pnx8550/common/int.c
diff --git a/trunk/arch/mips/philips/pnx8550/common/pci.c b/trunk/arch/mips/nxp/pnx8550/common/pci.c
similarity index 100%
rename from trunk/arch/mips/philips/pnx8550/common/pci.c
rename to trunk/arch/mips/nxp/pnx8550/common/pci.c
diff --git a/trunk/arch/mips/philips/pnx8550/common/platform.c b/trunk/arch/mips/nxp/pnx8550/common/platform.c
similarity index 98%
rename from trunk/arch/mips/philips/pnx8550/common/platform.c
rename to trunk/arch/mips/nxp/pnx8550/common/platform.c
index c839436bd012..c7c763dbe588 100644
--- a/trunk/arch/mips/philips/pnx8550/common/platform.c
+++ b/trunk/arch/mips/nxp/pnx8550/common/platform.c
@@ -1,5 +1,5 @@
 /*
- * Platform device support for Philips PNX8550 SoCs
+ * Platform device support for NXP PNX8550 SoCs
  *
  * Copyright 2005, Embedded Alley Solutions, Inc
  *
diff --git a/trunk/arch/mips/philips/pnx8550/common/proc.c b/trunk/arch/mips/nxp/pnx8550/common/proc.c
similarity index 100%
rename from trunk/arch/mips/philips/pnx8550/common/proc.c
rename to trunk/arch/mips/nxp/pnx8550/common/proc.c
diff --git a/trunk/arch/mips/philips/pnx8550/common/prom.c b/trunk/arch/mips/nxp/pnx8550/common/prom.c
similarity index 100%
rename from trunk/arch/mips/philips/pnx8550/common/prom.c
rename to trunk/arch/mips/nxp/pnx8550/common/prom.c
diff --git a/trunk/arch/mips/philips/pnx8550/common/reset.c b/trunk/arch/mips/nxp/pnx8550/common/reset.c
similarity index 100%
rename from trunk/arch/mips/philips/pnx8550/common/reset.c
rename to trunk/arch/mips/nxp/pnx8550/common/reset.c
diff --git a/trunk/arch/mips/philips/pnx8550/common/setup.c b/trunk/arch/mips/nxp/pnx8550/common/setup.c
similarity index 100%
rename from trunk/arch/mips/philips/pnx8550/common/setup.c
rename to trunk/arch/mips/nxp/pnx8550/common/setup.c
diff --git a/trunk/arch/mips/philips/pnx8550/common/time.c b/trunk/arch/mips/nxp/pnx8550/common/time.c
similarity index 100%
rename from trunk/arch/mips/philips/pnx8550/common/time.c
rename to trunk/arch/mips/nxp/pnx8550/common/time.c
diff --git a/trunk/arch/mips/philips/pnx8550/jbs/Makefile b/trunk/arch/mips/nxp/pnx8550/jbs/Makefile
similarity index 51%
rename from trunk/arch/mips/philips/pnx8550/jbs/Makefile
rename to trunk/arch/mips/nxp/pnx8550/jbs/Makefile
index e8228dbca8f6..ad6a8ca7d8ce 100644
--- a/trunk/arch/mips/philips/pnx8550/jbs/Makefile
+++ b/trunk/arch/mips/nxp/pnx8550/jbs/Makefile
@@ -1,4 +1,4 @@
 
-# Makefile for the Philips JBS Board.
+# Makefile for the NXP JBS Board.
 
 lib-y := init.o board_setup.o irqmap.o
diff --git a/trunk/arch/mips/philips/pnx8550/jbs/board_setup.c b/trunk/arch/mips/nxp/pnx8550/jbs/board_setup.c
similarity index 100%
rename from trunk/arch/mips/philips/pnx8550/jbs/board_setup.c
rename to trunk/arch/mips/nxp/pnx8550/jbs/board_setup.c
diff --git a/trunk/arch/mips/philips/pnx8550/jbs/init.c b/trunk/arch/mips/nxp/pnx8550/jbs/init.c
similarity index 98%
rename from trunk/arch/mips/philips/pnx8550/jbs/init.c
rename to trunk/arch/mips/nxp/pnx8550/jbs/init.c
index 90b4d35f3ece..d59b4a4e5e8b 100644
--- a/trunk/arch/mips/philips/pnx8550/jbs/init.c
+++ b/trunk/arch/mips/nxp/pnx8550/jbs/init.c
@@ -40,7 +40,7 @@ extern char *prom_getenv(char *envname);
 
 const char *get_system_type(void)
 {
-	return "Philips PNX8550/JBS";
+	return "NXP PNX8550/JBS";
 }
 
 void __init prom_init(void)
diff --git a/trunk/arch/mips/philips/pnx8550/jbs/irqmap.c b/trunk/arch/mips/nxp/pnx8550/jbs/irqmap.c
similarity index 98%
rename from trunk/arch/mips/philips/pnx8550/jbs/irqmap.c
rename to trunk/arch/mips/nxp/pnx8550/jbs/irqmap.c
index 98c3429e6e50..7fc89842002c 100644
--- a/trunk/arch/mips/philips/pnx8550/jbs/irqmap.c
+++ b/trunk/arch/mips/nxp/pnx8550/jbs/irqmap.c
@@ -1,5 +1,5 @@
 /*
- *  Philips JBS board irqmap.
+ *  NXP JBS board irqmap.
  *
  *  Copyright 2005 Embedded Alley Solutions, Inc
  *  source@embeddealley.com
@@ -33,4 +33,3 @@ char pnx8550_irq_tab[][5] __initdata = {
 	[9]	= { -1, PNX8550_INT_PCI_INTA, 0xff, 0xff, 0xff},
 	[17]	= { -1, PNX8550_INT_PCI_INTA, 0xff, 0xff, 0xff},
 };
-
diff --git a/trunk/arch/mips/philips/pnx8550/stb810/Makefile b/trunk/arch/mips/nxp/pnx8550/stb810/Makefile
similarity index 52%
rename from trunk/arch/mips/philips/pnx8550/stb810/Makefile
rename to trunk/arch/mips/nxp/pnx8550/stb810/Makefile
index f14b592af398..ab91d72c5664 100644
--- a/trunk/arch/mips/philips/pnx8550/stb810/Makefile
+++ b/trunk/arch/mips/nxp/pnx8550/stb810/Makefile
@@ -1,4 +1,4 @@
 
-# Makefile for the Philips STB810 Board.
+# Makefile for the NXP STB810 Board.
 
 lib-y := prom_init.o board_setup.o irqmap.o
diff --git a/trunk/arch/mips/philips/pnx8550/stb810/board_setup.c b/trunk/arch/mips/nxp/pnx8550/stb810/board_setup.c
similarity index 95%
rename from trunk/arch/mips/philips/pnx8550/stb810/board_setup.c
rename to trunk/arch/mips/nxp/pnx8550/stb810/board_setup.c
index 345d71e53cf2..1282c27cfcb7 100644
--- a/trunk/arch/mips/philips/pnx8550/stb810/board_setup.c
+++ b/trunk/arch/mips/nxp/pnx8550/stb810/board_setup.c
@@ -1,7 +1,7 @@
 /*
  *  STB810 specific board startup routines.
  *
- *  Based on the arch/mips/philips/pnx8550/jbs/board_setup.c
+ *  Based on the arch/mips/nxp/pnx8550/jbs/board_setup.c
  *
  *  Author: MontaVista Software, Inc.
  *          source@mvista.com
diff --git a/trunk/arch/mips/philips/pnx8550/stb810/irqmap.c b/trunk/arch/mips/nxp/pnx8550/stb810/irqmap.c
similarity index 94%
rename from trunk/arch/mips/philips/pnx8550/stb810/irqmap.c
rename to trunk/arch/mips/nxp/pnx8550/stb810/irqmap.c
index 5ee11e19975e..8c034963ddcd 100644
--- a/trunk/arch/mips/philips/pnx8550/stb810/irqmap.c
+++ b/trunk/arch/mips/nxp/pnx8550/stb810/irqmap.c
@@ -1,5 +1,5 @@
 /*
- *  Philips STB810 board irqmap.
+ *  NXP STB810 board irqmap.
  *
  *  Author: MontaVista Software, Inc.
  *          source@mvista.com
@@ -20,4 +20,3 @@ char pnx8550_irq_tab[][5] __initdata = {
 	[9]	= { -1, PNX8550_INT_PCI_INTA, 0xff, 0xff, 0xff},
 	[10]	= { -1, PNX8550_INT_PCI_INTA, 0xff, 0xff, 0xff},
 };
-
diff --git a/trunk/arch/mips/philips/pnx8550/stb810/prom_init.c b/trunk/arch/mips/nxp/pnx8550/stb810/prom_init.c
similarity index 96%
rename from trunk/arch/mips/philips/pnx8550/stb810/prom_init.c
rename to trunk/arch/mips/nxp/pnx8550/stb810/prom_init.c
index 832dd60b0a7a..ca7f4ada0640 100644
--- a/trunk/arch/mips/philips/pnx8550/stb810/prom_init.c
+++ b/trunk/arch/mips/nxp/pnx8550/stb810/prom_init.c
@@ -28,7 +28,7 @@ extern char *prom_getenv(char *envname);
 
 const char *get_system_type(void)
 {
-	return "Philips PNX8550/STB810";
+	return "NXP PNX8950/STB810";
 }
 
 void __init prom_init(void)
diff --git a/trunk/arch/mips/oprofile/common.c b/trunk/arch/mips/oprofile/common.c
index aa52aa146cea..b5f6f71b27bc 100644
--- a/trunk/arch/mips/oprofile/common.c
+++ b/trunk/arch/mips/oprofile/common.c
@@ -80,6 +80,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	case CPU_24K:
 	case CPU_25KF:
 	case CPU_34K:
+	case CPU_1004K:
 	case CPU_74K:
 	case CPU_SB1:
 	case CPU_SB1A:
diff --git a/trunk/arch/mips/oprofile/op_impl.h b/trunk/arch/mips/oprofile/op_impl.h
index fa6b4aae7523..2bfc17c30106 100644
--- a/trunk/arch/mips/oprofile/op_impl.h
+++ b/trunk/arch/mips/oprofile/op_impl.h
@@ -10,7 +10,6 @@
 #ifndef OP_IMPL_H
 #define OP_IMPL_H 1
 
-extern int null_perf_irq(void);
 extern int (*perf_irq)(void);
 
 /* Per-counter configuration as set via oprofilefs.  */
diff --git a/trunk/arch/mips/oprofile/op_model_mipsxx.c b/trunk/arch/mips/oprofile/op_model_mipsxx.c
index ccbea229a0e6..da8cbb6899dc 100644
--- a/trunk/arch/mips/oprofile/op_model_mipsxx.c
+++ b/trunk/arch/mips/oprofile/op_model_mipsxx.c
@@ -31,9 +31,14 @@
 
 #define M_COUNTER_OVERFLOW		(1UL      << 31)
 
+static int (*save_perf_irq)(void);
+
 #ifdef CONFIG_MIPS_MT_SMP
-#define WHAT		(M_TC_EN_VPE | M_PERFCTL_VPEID(smp_processor_id()))
-#define vpe_id()	smp_processor_id()
+static int cpu_has_mipsmt_pertccounters;
+#define WHAT		(M_TC_EN_VPE | \
+			 M_PERFCTL_VPEID(cpu_data[smp_processor_id()].vpe_id))
+#define vpe_id()	(cpu_has_mipsmt_pertccounters ? \
+			0 : cpu_data[smp_processor_id()].vpe_id)
 
 /*
  * The number of bits to shift to convert between counters per core and
@@ -243,11 +248,11 @@ static inline int __n_counters(void)
 {
 	if (!(read_c0_config1() & M_CONFIG1_PC))
 		return 0;
-	if (!(r_c0_perfctrl0() & M_PERFCTL_MORE))
+	if (!(read_c0_perfctrl0() & M_PERFCTL_MORE))
 		return 1;
-	if (!(r_c0_perfctrl1() & M_PERFCTL_MORE))
+	if (!(read_c0_perfctrl1() & M_PERFCTL_MORE))
 		return 2;
-	if (!(r_c0_perfctrl2() & M_PERFCTL_MORE))
+	if (!(read_c0_perfctrl2() & M_PERFCTL_MORE))
 		return 3;
 
 	return 4;
@@ -274,8 +279,9 @@ static inline int n_counters(void)
 	return counters;
 }
 
-static inline void reset_counters(int counters)
+static void reset_counters(void *arg)
 {
+	int counters = (int)arg;
 	switch (counters) {
 	case 4:
 		w_c0_perfctrl3(0);
@@ -302,9 +308,12 @@ static int __init mipsxx_init(void)
 		return -ENODEV;
 	}
 
-	reset_counters(counters);
-
-	counters = counters_total_to_per_cpu(counters);
+#ifdef CONFIG_MIPS_MT_SMP
+	cpu_has_mipsmt_pertccounters = read_c0_config7() & (1<<19);
+	if (!cpu_has_mipsmt_pertccounters)
+		counters = counters_total_to_per_cpu(counters);
+#endif
+	on_each_cpu(reset_counters, (void *)counters, 0, 1);
 
 	op_model_mipsxx_ops.num_counters = counters;
 	switch (current_cpu_type()) {
@@ -320,6 +329,13 @@ static int __init mipsxx_init(void)
 		op_model_mipsxx_ops.cpu_type = "mips/25K";
 		break;
 
+	case CPU_1004K:
+#if 0
+		/* FIXME: report as 34K for now */
+		op_model_mipsxx_ops.cpu_type = "mips/1004K";
+		break;
+#endif
+
 	case CPU_34K:
 		op_model_mipsxx_ops.cpu_type = "mips/34K";
 		break;
@@ -355,6 +371,7 @@ static int __init mipsxx_init(void)
 		return -ENODEV;
 	}
 
+	save_perf_irq = perf_irq;
 	perf_irq = mipsxx_perfcount_handler;
 
 	return 0;
@@ -365,9 +382,9 @@ static void mipsxx_exit(void)
 	int counters = op_model_mipsxx_ops.num_counters;
 
 	counters = counters_per_cpu_to_total(counters);
-	reset_counters(counters);
+	on_each_cpu(reset_counters, (void *)counters, 0, 1);
 
-	perf_irq = null_perf_irq;
+	perf_irq = save_perf_irq;
 }
 
 struct op_mips_model op_model_mipsxx_ops = {
diff --git a/trunk/arch/mips/pci/fixup-au1000.c b/trunk/arch/mips/pci/fixup-au1000.c
index ca0276c8070a..00c36c9dbe0e 100644
--- a/trunk/arch/mips/pci/fixup-au1000.c
+++ b/trunk/arch/mips/pci/fixup-au1000.c
@@ -26,13 +26,10 @@
  *  with this program; if not, write  to the Free Software Foundation, Inc.,
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/types.h>
+
 #include <linux/pci.h>
-#include <linux/kernel.h>
 #include <linux/init.h>
 
-#include <asm/mach-au1x00/au1000.h>
-
 extern char irq_tab_alchemy[][5];
 
 int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
diff --git a/trunk/arch/mips/pci/ops-pnx8550.c b/trunk/arch/mips/pci/ops-pnx8550.c
index d61064652498..0e160d9f07c3 100644
--- a/trunk/arch/mips/pci/ops-pnx8550.c
+++ b/trunk/arch/mips/pci/ops-pnx8550.c
@@ -90,14 +90,14 @@ config_access(unsigned int pci_cmd, struct pci_bus *bus, unsigned int devfn, int
 
 		loops--;
 		if (loops == 0) {
-			printk("%s : Arbiter Locked.\n", __FUNCTION__);
+			printk("%s : Arbiter Locked.\n", __func__);
 		}
 	}
 
 	clear_status();
 	if ((pci_cmd == PCI_CMD_IOR) || (pci_cmd == PCI_CMD_IOW)) {
 		printk("%s timeout (GPPM_CTRL=%X) ioaddr %lX pci_cmd %X\n",
-		       __FUNCTION__, inl(PCI_BASE | PCI_GPPM_CTRL), ioaddr,
+		       __func__, inl(PCI_BASE | PCI_GPPM_CTRL), ioaddr,
 		       pci_cmd);
 	}
 
diff --git a/trunk/arch/mips/pmc-sierra/yosemite/setup.c b/trunk/arch/mips/pmc-sierra/yosemite/setup.c
index 855977ca51cd..6537d90a25bb 100644
--- a/trunk/arch/mips/pmc-sierra/yosemite/setup.c
+++ b/trunk/arch/mips/pmc-sierra/yosemite/setup.c
@@ -143,9 +143,6 @@ void __init plat_time_init(void)
 mips_hpt_frequency = 33000000 * 3 * 5;
 }
 
-/* No other usable initialization hook than this ...  */
-extern void (*late_time_init)(void);
-
 unsigned long ocd_base;
 
 EXPORT_SYMBOL(ocd_base);
diff --git a/trunk/arch/mips/sgi-ip32/ip32-reset.c b/trunk/arch/mips/sgi-ip32/ip32-reset.c
index 624bbdbff2a8..b6cab089561e 100644
--- a/trunk/arch/mips/sgi-ip32/ip32-reset.c
+++ b/trunk/arch/mips/sgi-ip32/ip32-reset.c
@@ -142,7 +142,7 @@ static irqreturn_t ip32_rtc_int(int irq, void *dev_id)
 	reg_c = CMOS_READ(RTC_INTR_FLAGS);
 	if (!(reg_c & RTC_IRQF)) {
 		printk(KERN_WARNING
-			"%s: RTC IRQ without RTC_IRQF\n", __FUNCTION__);
+			"%s: RTC IRQ without RTC_IRQF\n", __func__);
 	}
 	/* Wait until interrupt goes away */
 	disable_irq(MACEISA_RTC_IRQ);
diff --git a/trunk/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_irq.c b/trunk/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_irq.c
index 3f808b629242..6d31f2a98abf 100644
--- a/trunk/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_irq.c
+++ b/trunk/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_irq.c
@@ -173,7 +173,7 @@ static const u32 toshiba_rbtx4927_irq_debug_flag =
         { \
            char tmp[100]; \
            sprintf( tmp, str ); \
-           printk( "%s(%s:%u)::%s", __FUNCTION__, __FILE__, __LINE__, tmp ); \
+           printk( "%s(%s:%u)::%s", __func__, __FILE__, __LINE__, tmp ); \
         }
 #else
 #define TOSHIBA_RBTX4927_IRQ_DPRINTK(flag, str...)
diff --git a/trunk/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c b/trunk/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c
index e466e5e711d8..2203c77b2ce2 100644
--- a/trunk/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c
+++ b/trunk/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c
@@ -93,7 +93,7 @@ static const u32 toshiba_rbtx4927_setup_debug_flag =
         { \
            char tmp[100]; \
            sprintf( tmp, str ); \
-           printk( "%s(%s:%u)::%s", __FUNCTION__, __FILE__, __LINE__, tmp ); \
+           printk( "%s(%s:%u)::%s", __func__, __FILE__, __LINE__, tmp ); \
         }
 #else
 #define TOSHIBA_RBTX4927_SETUP_DPRINTK(flag, str...)
diff --git a/trunk/arch/mips/tx4938/common/dbgio.c b/trunk/arch/mips/tx4938/common/dbgio.c
index bea59ff1842a..33b9c672a322 100644
--- a/trunk/arch/mips/tx4938/common/dbgio.c
+++ b/trunk/arch/mips/tx4938/common/dbgio.c
@@ -31,9 +31,7 @@
  * Support for TX4938 in 2.6 - Hiroshi DOYU <Hiroshi_DOYU@montavista.co.jp>
  */
 
-#include <asm/mipsregs.h>
-#include <asm/system.h>
-#include <asm/tx4938/tx4938_mips.h>
+#include <linux/types>
 
 extern u8 txx9_sio_kdbg_rd(void);
 extern int txx9_sio_kdbg_wr( u8 ch );
diff --git a/trunk/arch/mips/tx4938/common/prom.c b/trunk/arch/mips/tx4938/common/prom.c
index 3189a65f7d7e..20baeaeba4cd 100644
--- a/trunk/arch/mips/tx4938/common/prom.c
+++ b/trunk/arch/mips/tx4938/common/prom.c
@@ -13,13 +13,8 @@
  */
 
 #include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-
-#include <asm/addrspace.h>
-#include <asm/bootinfo.h>
-#include <asm/tx4938/tx4938.h>
+#include <linux/types.h>
+#include <linux/io.h>
 
 static unsigned int __init
 tx4938_process_sdccr(u64 * addr)
@@ -35,7 +30,7 @@ tx4938_process_sdccr(u64 * addr)
 	unsigned int bc = 4;
 	unsigned int msize = 0;
 
-	val = (*((vu64 *) (addr)));
+	val = ____raw_readq((void __iomem *)addr);
 
 	/* MVMCP -- need #defs for these bits masks */
 	sdccr_ce = ((val & (1 << 10)) >> 10);
diff --git a/trunk/arch/mips/tx4938/toshiba_rbtx4938/irq.c b/trunk/arch/mips/tx4938/toshiba_rbtx4938/irq.c
index f00185017e80..4d6a8dc46c76 100644
--- a/trunk/arch/mips/tx4938/toshiba_rbtx4938/irq.c
+++ b/trunk/arch/mips/tx4938/toshiba_rbtx4938/irq.c
@@ -67,24 +67,7 @@ IRQ  Device
 63 RBTX4938-IOC/07 SWINT
 */
 #include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/ioport.h>
-#include <linux/sched.h>
 #include <linux/interrupt.h>
-#include <linux/pci.h>
-#include <linux/timex.h>
-#include <asm/bootinfo.h>
-#include <asm/page.h>
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/processor.h>
-#include <asm/reboot.h>
-#include <asm/time.h>
-#include <asm/wbflush.h>
-#include <linux/bootmem.h>
 #include <asm/tx4938/rbtx4938.h>
 
 static void toshiba_rbtx4938_irq_ioc_enable(unsigned int irq);
@@ -99,21 +82,16 @@ static struct irq_chip toshiba_rbtx4938_irq_ioc_type = {
 	.unmask = toshiba_rbtx4938_irq_ioc_enable,
 };
 
-#define TOSHIBA_RBTX4938_IOC_INTR_ENAB 0xb7f02000
-#define TOSHIBA_RBTX4938_IOC_INTR_STAT 0xb7f0200a
-
 int
 toshiba_rbtx4938_irq_nested(int sw_irq)
 {
 	u8 level3;
 
-	level3 = reg_rd08(TOSHIBA_RBTX4938_IOC_INTR_STAT) & 0xff;
-	if (level3) {
+	level3 = readb(rbtx4938_imstat_addr);
+	if (level3)
 		/* must use fls so onboard ATA has priority */
 		sw_irq = TOSHIBA_RBTX4938_IRQ_IOC_BEG + fls(level3) - 1;
-	}
 
-	wbflush();
 	return sw_irq;
 }
 
@@ -144,25 +122,23 @@ toshiba_rbtx4938_irq_ioc_init(void)
 static void
 toshiba_rbtx4938_irq_ioc_enable(unsigned int irq)
 {
-	volatile unsigned char v;
+	unsigned char v;
 
-	v = TX4938_RD08(TOSHIBA_RBTX4938_IOC_INTR_ENAB);
+	v = readb(rbtx4938_imask_addr);
 	v |= (1 << (irq - TOSHIBA_RBTX4938_IRQ_IOC_BEG));
-	TX4938_WR08(TOSHIBA_RBTX4938_IOC_INTR_ENAB, v);
+	writeb(v, rbtx4938_imask_addr);
 	mmiowb();
-	TX4938_RD08(TOSHIBA_RBTX4938_IOC_INTR_ENAB);
 }
 
 static void
 toshiba_rbtx4938_irq_ioc_disable(unsigned int irq)
 {
-	volatile unsigned char v;
+	unsigned char v;
 
-	v = TX4938_RD08(TOSHIBA_RBTX4938_IOC_INTR_ENAB);
+	v = readb(rbtx4938_imask_addr);
 	v &= ~(1 << (irq - TOSHIBA_RBTX4938_IRQ_IOC_BEG));
-	TX4938_WR08(TOSHIBA_RBTX4938_IOC_INTR_ENAB, v);
+	writeb(v, rbtx4938_imask_addr);
 	mmiowb();
-	TX4938_RD08(TOSHIBA_RBTX4938_IOC_INTR_ENAB);
 }
 
 void __init arch_init_irq(void)
@@ -174,14 +150,12 @@ void __init arch_init_irq(void)
 	/* all IRC interrupt mode are Low Active. */
 
 	/* mask all IOC interrupts */
-	*rbtx4938_imask_ptr = 0;
+	writeb(0, rbtx4938_imask_addr);
 
 	/* clear SoftInt interrupts */
-	*rbtx4938_softint_ptr = 0;
+	writeb(0, rbtx4938_softint_addr);
 	tx4938_irq_init();
 	toshiba_rbtx4938_irq_ioc_init();
 	/* Onboard 10M Ether: High Active */
 	set_irq_type(RBTX4938_IRQ_ETHER, IRQF_TRIGGER_HIGH);
-
-	wbflush();
 }
diff --git a/trunk/arch/mips/tx4938/toshiba_rbtx4938/setup.c b/trunk/arch/mips/tx4938/toshiba_rbtx4938/setup.c
index 61249f049cd6..3a3659e8633a 100644
--- a/trunk/arch/mips/tx4938/toshiba_rbtx4938/setup.c
+++ b/trunk/arch/mips/tx4938/toshiba_rbtx4938/setup.c
@@ -21,8 +21,8 @@
 #include <linux/pm.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
+#include <linux/gpio.h>
 
-#include <asm/wbflush.h>
 #include <asm/reboot.h>
 #include <asm/time.h>
 #include <asm/txx9tmr.h>
@@ -34,7 +34,7 @@
 #endif
 #include <linux/spi/spi.h>
 #include <asm/tx4938/spi.h>
-#include <asm/gpio.h>
+#include <asm/txx9pio.h>
 
 extern char * __init prom_getcmdline(void);
 static inline void tx4938_report_pcic_status1(struct tx4938_pcic_reg *pcicptr);
@@ -90,12 +90,11 @@ void rbtx4938_machine_restart(char *command)
 	local_irq_disable();
 
 	printk("Rebooting...");
-	*rbtx4938_softresetlock_ptr = 1;
-	*rbtx4938_sfvol_ptr = 1;
-	*rbtx4938_softreset_ptr = 1;
-	wbflush();
-
-	while(1);
+	writeb(1, rbtx4938_softresetlock_addr);
+	writeb(1, rbtx4938_sfvol_addr);
+	writeb(1, rbtx4938_softreset_addr);
+	while(1)
+		;
 }
 
 void __init
@@ -487,7 +486,7 @@ static int __init tx4938_pcibios_init(void)
 	}
 
 	/* Reset PCI Bus */
-	*rbtx4938_pcireset_ptr = 0;
+	writeb(0, rbtx4938_pcireset_addr);
 	/* Reset PCIC */
 	tx4938_ccfgptr->clkctr |= TX4938_CLKCTR_PCIRST;
 	if (txboard_pci66_mode > 0)
@@ -495,8 +494,8 @@ static int __init tx4938_pcibios_init(void)
 	mdelay(10);
 	/* clear PCIC reset */
 	tx4938_ccfgptr->clkctr &= ~TX4938_CLKCTR_PCIRST;
-	*rbtx4938_pcireset_ptr = 1;
-	wbflush();
+	writeb(1, rbtx4938_pcireset_addr);
+	mmiowb();
 	tx4938_report_pcic_status1(tx4938_pcicptr);
 
 	tx4938_report_pciclk();
@@ -504,15 +503,15 @@ static int __init tx4938_pcibios_init(void)
 	if (txboard_pci66_mode == 0 &&
 	    txboard_pci66_check(&tx4938_pci_controller[0], 0, 0)) {
 		/* Reset PCI Bus */
-		*rbtx4938_pcireset_ptr = 0;
+		writeb(0, rbtx4938_pcireset_addr);
 		/* Reset PCIC */
 		tx4938_ccfgptr->clkctr |= TX4938_CLKCTR_PCIRST;
 		tx4938_pciclk66_setup();
 		mdelay(10);
 		/* clear PCIC reset */
 		tx4938_ccfgptr->clkctr &= ~TX4938_CLKCTR_PCIRST;
-		*rbtx4938_pcireset_ptr = 1;
-		wbflush();
+		writeb(1, rbtx4938_pcireset_addr);
+		mmiowb();
 		/* Reinitialize PCIC */
 		tx4938_report_pciclk();
 		tx4938_pcic_setup(tx4938_pcicptr, &tx4938_pci_controller[0], io_base[0], extarb);
@@ -615,9 +614,6 @@ static void __init rbtx4938_spi_setup(void)
 {
 	/* set SPI_SEL */
 	tx4938_ccfgptr->pcfg |= TX4938_PCFG_SPI_SEL;
-	/* chip selects for SPI devices */
-	tx4938_pioptr->dout |= (1 << SEEPROM1_CS);
-	tx4938_pioptr->dir |= (1 << SEEPROM1_CS);
 }
 
 static struct resource rbtx4938_fpga_resource;
@@ -776,12 +772,13 @@ void __init tx4938_board_setup(void)
 		txx9_tmr_init(TX4938_TMR_REG(i) & 0xfffffffffULL);
 
 	/* enable DMA */
-	TX4938_WR64(0xff1fb150, TX4938_DMA_MCR_MSTEN);
-	TX4938_WR64(0xff1fb950, TX4938_DMA_MCR_MSTEN);
+	for (i = 0; i < 2; i++)
+		____raw_writeq(TX4938_DMA_MCR_MSTEN,
+			       (void __iomem *)(TX4938_DMA_REG(i) + 0x50));
 
 	/* PIO */
-	tx4938_pioptr->maskcpu = 0;
-	tx4938_pioptr->maskext = 0;
+	__raw_writel(0, &tx4938_pioptr->maskcpu);
+	__raw_writel(0, &tx4938_pioptr->maskext);
 
 	/* TX4938 internal registers */
 	if (request_resource(&iomem_resource, &tx4938_reg_resource))
@@ -863,10 +860,6 @@ void __init plat_mem_setup(void)
 	if (txx9_master_clock == 0)
 		txx9_master_clock = 25000000; /* 25MHz */
 	tx4938_board_setup();
-	/* setup serial stuff */
-	TX4938_WR(0xff1ff314, 0x00000000);	/* h/w flow control off */
-	TX4938_WR(0xff1ff414, 0x00000000);	/* h/w flow control off */
-
 #ifndef CONFIG_PCI
 	set_io_port_base(RBTX4938_ETHER_BASE);
 #endif
@@ -932,16 +925,16 @@ void __init plat_mem_setup(void)
 	pcfg = tx4938_ccfgptr->pcfg;	/* updated */
 	/* fixup piosel */
 	if ((pcfg & (TX4938_PCFG_ATA_SEL | TX4938_PCFG_NDF_SEL)) ==
-	    TX4938_PCFG_ATA_SEL) {
-		*rbtx4938_piosel_ptr = (*rbtx4938_piosel_ptr & 0x03) | 0x04;
-	}
+	    TX4938_PCFG_ATA_SEL)
+		writeb((readb(rbtx4938_piosel_addr) & 0x03) | 0x04,
+		       rbtx4938_piosel_addr);
 	else if ((pcfg & (TX4938_PCFG_ATA_SEL | TX4938_PCFG_NDF_SEL)) ==
-	    TX4938_PCFG_NDF_SEL) {
-		*rbtx4938_piosel_ptr = (*rbtx4938_piosel_ptr & 0x03) | 0x08;
-	}
-	else {
-		*rbtx4938_piosel_ptr &= ~(0x08 | 0x04);
-	}
+		 TX4938_PCFG_NDF_SEL)
+		writeb((readb(rbtx4938_piosel_addr) & 0x03) | 0x08,
+		       rbtx4938_piosel_addr);
+	else
+		writeb(readb(rbtx4938_piosel_addr) & ~(0x08 | 0x04),
+		       rbtx4938_piosel_addr);
 
 	rbtx4938_fpga_resource.name = "FPGA Registers";
 	rbtx4938_fpga_resource.start = CPHYSADDR(RBTX4938_FPGA_REG_ADDR);
@@ -950,17 +943,14 @@ void __init plat_mem_setup(void)
 	if (request_resource(&iomem_resource, &rbtx4938_fpga_resource))
 		printk("request resource for fpga failed\n");
 
-	/* disable all OnBoard I/O interrupts */
-	*rbtx4938_imask_ptr = 0;
-
 	_machine_restart = rbtx4938_machine_restart;
 	_machine_halt = rbtx4938_machine_halt;
 	pm_power_off = rbtx4938_machine_power_off;
 
-	*rbtx4938_led_ptr = 0xff;
-	printk("RBTX4938 --- FPGA(Rev %02x)", *rbtx4938_fpga_rev_ptr);
-	printk(" DIPSW:%02x,%02x\n",
-	       *rbtx4938_dipsw_ptr, *rbtx4938_bdipsw_ptr);
+	writeb(0xff, rbtx4938_led_addr);
+	printk(KERN_INFO "RBTX4938 --- FPGA(Rev %02x) DIPSW:%02x,%02x\n",
+	       readb(rbtx4938_fpga_rev_addr),
+	       readb(rbtx4938_dipsw_addr), readb(rbtx4938_bdipsw_addr));
 }
 
 static int __init rbtx4938_ne_init(void)
@@ -984,106 +974,48 @@ device_initcall(rbtx4938_ne_init);
 
 /* GPIO support */
 
-static DEFINE_SPINLOCK(rbtx4938_spi_gpio_lock);
-
-static void rbtx4938_spi_gpio_set(unsigned gpio, int value)
+int gpio_to_irq(unsigned gpio)
 {
-	u8 val;
-	unsigned long flags;
-	gpio -= 16;
-	spin_lock_irqsave(&rbtx4938_spi_gpio_lock, flags);
-	val = *rbtx4938_spics_ptr;
-	if (value)
-		val |= 1 << gpio;
-	else
-		val &= ~(1 << gpio);
-	*rbtx4938_spics_ptr = val;
-	mmiowb();
-	spin_unlock_irqrestore(&rbtx4938_spi_gpio_lock, flags);
+	return -EINVAL;
 }
 
-static int rbtx4938_spi_gpio_dir_out(unsigned gpio, int value)
+int irq_to_gpio(unsigned irq)
 {
-	rbtx4938_spi_gpio_set(gpio, value);
-	return 0;
+	return -EINVAL;
 }
 
-static DEFINE_SPINLOCK(tx4938_gpio_lock);
-
-static int tx4938_gpio_get(unsigned gpio)
-{
-	return tx4938_pioptr->din & (1 << gpio);
-}
+static DEFINE_SPINLOCK(rbtx4938_spi_gpio_lock);
 
-static void tx4938_gpio_set_raw(unsigned gpio, int value)
+static void rbtx4938_spi_gpio_set(struct gpio_chip *chip, unsigned int offset,
+				  int value)
 {
-	u32 val;
-	val = tx4938_pioptr->dout;
+	u8 val;
+	unsigned long flags;
+	spin_lock_irqsave(&rbtx4938_spi_gpio_lock, flags);
+	val = readb(rbtx4938_spics_addr);
 	if (value)
-		val |= 1 << gpio;
+		val |= 1 << offset;
 	else
-		val &= ~(1 << gpio);
-	tx4938_pioptr->dout = val;
-}
-
-static void tx4938_gpio_set(unsigned gpio, int value)
-{
-	unsigned long flags;
-	spin_lock_irqsave(&tx4938_gpio_lock, flags);
-	tx4938_gpio_set_raw(gpio, value);
-	mmiowb();
-	spin_unlock_irqrestore(&tx4938_gpio_lock, flags);
-}
-
-static int tx4938_gpio_dir_in(unsigned gpio)
-{
-	spin_lock_irq(&tx4938_gpio_lock);
-	tx4938_pioptr->dir &= ~(1 << gpio);
+		val &= ~(1 << offset);
+	writeb(val, rbtx4938_spics_addr);
 	mmiowb();
-	spin_unlock_irq(&tx4938_gpio_lock);
-	return 0;
-}
-
-static int tx4938_gpio_dir_out(unsigned int gpio, int value)
-{
-	spin_lock_irq(&tx4938_gpio_lock);
-	tx4938_gpio_set_raw(gpio, value);
-	tx4938_pioptr->dir |= 1 << gpio;
-	mmiowb();
-	spin_unlock_irq(&tx4938_gpio_lock);
-	return 0;
-}
-
-int gpio_direction_input(unsigned gpio)
-{
-	if (gpio < 16)
-		return tx4938_gpio_dir_in(gpio);
-	return -EINVAL;
-}
-
-int gpio_direction_output(unsigned gpio, int value)
-{
-	if (gpio < 16)
-		return tx4938_gpio_dir_out(gpio, value);
-	if (gpio < 16 + 3)
-		return rbtx4938_spi_gpio_dir_out(gpio, value);
-	return -EINVAL;
+	spin_unlock_irqrestore(&rbtx4938_spi_gpio_lock, flags);
 }
 
-int gpio_get_value(unsigned gpio)
+static int rbtx4938_spi_gpio_dir_out(struct gpio_chip *chip,
+				     unsigned int offset, int value)
 {
-	if (gpio < 16)
-		return tx4938_gpio_get(gpio);
+	rbtx4938_spi_gpio_set(chip, offset, value);
 	return 0;
 }
 
-void gpio_set_value(unsigned gpio, int value)
-{
-	if (gpio < 16)
-		tx4938_gpio_set(gpio, value);
-	else
-		rbtx4938_spi_gpio_set(gpio, value);
-}
+static struct gpio_chip rbtx4938_spi_gpio_chip = {
+	.set = rbtx4938_spi_gpio_set,
+	.direction_output = rbtx4938_spi_gpio_dir_out,
+	.label = "RBTX4938-SPICS",
+	.base = 16,
+	.ngpio = 3,
+};
 
 /* SPI support */
 
@@ -1094,7 +1026,6 @@ static void __init txx9_spi_init(unsigned long base, int irq)
 			.start	= base,
 			.end	= base + 0x20 - 1,
 			.flags	= IORESOURCE_MEM,
-			.parent	= &tx4938_reg_resource,
 		}, {
 			.start	= irq,
 			.flags	= IORESOURCE_IRQ,
@@ -1118,10 +1049,25 @@ static int __init rbtx4938_spi_init(void)
 	spi_eeprom_register(SEEPROM1_CS);
 	spi_eeprom_register(16 + SEEPROM2_CS);
 	spi_eeprom_register(16 + SEEPROM3_CS);
+	gpio_request(16 + SRTC_CS, "rtc-rs5c348");
+	gpio_direction_output(16 + SRTC_CS, 0);
+	gpio_request(SEEPROM1_CS, "seeprom1");
+	gpio_direction_output(SEEPROM1_CS, 1);
+	gpio_request(16 + SEEPROM2_CS, "seeprom2");
+	gpio_direction_output(16 + SEEPROM2_CS, 1);
+	gpio_request(16 + SEEPROM3_CS, "seeprom3");
+	gpio_direction_output(16 + SEEPROM3_CS, 1);
 	txx9_spi_init(TX4938_SPI_REG & 0xfffffffffULL, RBTX4938_IRQ_IRC_SPI);
 	return 0;
 }
-arch_initcall(rbtx4938_spi_init);
+
+static int __init rbtx4938_arch_init(void)
+{
+	txx9_gpio_init(TX4938_PIO_REG & 0xfffffffffULL, 0, 16);
+	gpiochip_add(&rbtx4938_spi_gpio_chip);
+	return rbtx4938_spi_init();
+}
+arch_initcall(rbtx4938_arch_init);
 
 /* Watchdog support */
 
@@ -1131,7 +1077,6 @@ static int __init txx9_wdt_init(unsigned long base)
 		.start	= base,
 		.end	= base + 0x100 - 1,
 		.flags	= IORESOURCE_MEM,
-		.parent	= &tx4938_reg_resource,
 	};
 	struct platform_device *dev =
 		platform_device_register_simple("txx9wdt", -1, &res, 1);
diff --git a/trunk/arch/mips/vr41xx/common/init.c b/trunk/arch/mips/vr41xx/common/init.c
index 76d4b5ed3fc0..c64995342ba8 100644
--- a/trunk/arch/mips/vr41xx/common/init.c
+++ b/trunk/arch/mips/vr41xx/common/init.c
@@ -1,7 +1,7 @@
 /*
  *  init.c, Common initialization routines for NEC VR4100 series.
  *
- *  Copyright (C) 2003-2005  Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
+ *  Copyright (C) 2003-2008  Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
@@ -53,6 +53,8 @@ void __init plat_time_init(void)
 void __init plat_mem_setup(void)
 {
 	iomem_resource_init();
+
+	vr41xx_siu_setup();
 }
 
 void __init prom_init(void)
diff --git a/trunk/arch/mips/vr41xx/common/siu.c b/trunk/arch/mips/vr41xx/common/siu.c
index b735f45b25f0..654dee6208be 100644
--- a/trunk/arch/mips/vr41xx/common/siu.c
+++ b/trunk/arch/mips/vr41xx/common/siu.c
@@ -1,7 +1,7 @@
 /*
  *  NEC VR4100 series SIU platform device.
  *
- *  Copyright (C) 2007  Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
+ *  Copyright (C) 2007-2008  Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
@@ -118,3 +118,37 @@ static int __init vr41xx_siu_add(void)
 	return retval;
 }
 device_initcall(vr41xx_siu_add);
+
+void __init vr41xx_siu_setup(void)
+{
+	struct uart_port port;
+	struct resource *res;
+	unsigned int *type;
+	int i;
+
+	switch (current_cpu_type()) {
+	case CPU_VR4111:
+	case CPU_VR4121:
+		type = siu_type1_ports;
+		res = siu_type1_resource;
+		break;
+	case CPU_VR4122:
+	case CPU_VR4131:
+	case CPU_VR4133:
+		type = siu_type2_ports;
+		res = siu_type2_resource;
+		break;
+	default:
+		return;
+	}
+
+	for (i = 0; i < SIU_PORTS_MAX; i++) {
+		port.line = i;
+		port.type = type[i];
+		if (port.type == PORT_UNKNOWN)
+			break;
+		port.mapbase = res[i].start;
+		port.membase = (unsigned char __iomem *)KSEG1ADDR(res[i].start);
+		vr41xx_siu_early_setup(&port);
+	}
+}
diff --git a/trunk/arch/mn10300/kernel/asm-offsets.c b/trunk/arch/mn10300/kernel/asm-offsets.c
index ee2d9f8af5ad..2646fcbd7d89 100644
--- a/trunk/arch/mn10300/kernel/asm-offsets.c
+++ b/trunk/arch/mn10300/kernel/asm-offsets.c
@@ -7,6 +7,7 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/personality.h>
+#include <linux/kbuild.h>
 #include <asm/ucontext.h>
 #include <asm/processor.h>
 #include <asm/thread_info.h>
@@ -14,14 +15,6 @@
 #include "sigframe.h"
 #include "mn10300-serial.h"
 
-#define DEFINE(sym, val) \
-	asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->")
-
-#define OFFSET(sym, str, mem) \
-	DEFINE(sym, offsetof(struct str, mem));
-
 void foo(void)
 {
 	OFFSET(SIGCONTEXT_d0, sigcontext, d0);
diff --git a/trunk/arch/mn10300/unit-asb2305/pci-iomap.c b/trunk/arch/mn10300/unit-asb2305/pci-iomap.c
index dbceae4307da..c1a8d8f941fd 100644
--- a/trunk/arch/mn10300/unit-asb2305/pci-iomap.c
+++ b/trunk/arch/mn10300/unit-asb2305/pci-iomap.c
@@ -16,8 +16,8 @@
  */
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
-	unsigned long start = pci_resource_start(dev, bar);
-	unsigned long len = pci_resource_len(dev, bar);
+	resource_size_t start = pci_resource_start(dev, bar);
+	resource_size_t len = pci_resource_len(dev, bar);
 	unsigned long flags = pci_resource_flags(dev, bar);
 
 	if (!len || !start)
diff --git a/trunk/arch/parisc/kernel/asm-offsets.c b/trunk/arch/parisc/kernel/asm-offsets.c
index eaa79bc14d94..3efc0b73e4ff 100644
--- a/trunk/arch/parisc/kernel/asm-offsets.c
+++ b/trunk/arch/parisc/kernel/asm-offsets.c
@@ -32,6 +32,7 @@
 #include <linux/thread_info.h>
 #include <linux/ptrace.h>
 #include <linux/hardirq.h>
+#include <linux/kbuild.h>
 
 #include <asm/pgtable.h>
 #include <asm/ptrace.h>
@@ -39,11 +40,6 @@
 #include <asm/pdc.h>
 #include <asm/uaccess.h>
 
-#define DEFINE(sym, val) \
-	asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
-
 #ifdef CONFIG_64BIT
 #define FRAME_SIZE	128
 #else
diff --git a/trunk/arch/parisc/kernel/pci-dma.c b/trunk/arch/parisc/kernel/pci-dma.c
index 9448d4e91142..ccd61b9567a6 100644
--- a/trunk/arch/parisc/kernel/pci-dma.c
+++ b/trunk/arch/parisc/kernel/pci-dma.c
@@ -397,10 +397,9 @@ pcxl_dma_init(void)
 			"pcxl_dma_init: Unable to create gsc /proc dir entry\n");
 	else {
 		struct proc_dir_entry* ent;
-		ent = create_proc_entry("pcxl_dma", 0, proc_gsc_root);
-		if (ent)
-			ent->proc_fops = &proc_pcxl_dma_ops;
-		else
+		ent = proc_create("pcxl_dma", 0, proc_gsc_root,
+				  &proc_pcxl_dma_ops);
+		if (!ent)
 			printk(KERN_WARNING
 				"pci-dma.c: Unable to create pcxl_dma /proc entry.\n");
 	}
diff --git a/trunk/arch/parisc/lib/iomap.c b/trunk/arch/parisc/lib/iomap.c
index f4a811690ab3..9abed07db7fc 100644
--- a/trunk/arch/parisc/lib/iomap.c
+++ b/trunk/arch/parisc/lib/iomap.c
@@ -438,8 +438,8 @@ void ioport_unmap(void __iomem *addr)
 /* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
-	unsigned long start = pci_resource_start(dev, bar);
-	unsigned long len = pci_resource_len(dev, bar);
+	resource_size_t start = pci_resource_start(dev, bar);
+	resource_size_t len = pci_resource_len(dev, bar);
 	unsigned long flags = pci_resource_flags(dev, bar);
 
 	if (!len || !start)
diff --git a/trunk/arch/parisc/mm/init.c b/trunk/arch/parisc/mm/init.c
index eb80f5e33d7d..1f012843150f 100644
--- a/trunk/arch/parisc/mm/init.c
+++ b/trunk/arch/parisc/mm/init.c
@@ -603,15 +603,18 @@ void show_mem(void)
 #ifdef CONFIG_DISCONTIGMEM
 	{
 		struct zonelist *zl;
-		int i, j, k;
+		int i, j;
 
 		for (i = 0; i < npmem_ranges; i++) {
+			zl = node_zonelist(i);
 			for (j = 0; j < MAX_NR_ZONES; j++) {
-				zl = NODE_DATA(i)->node_zonelists + j;
+				struct zoneref *z;
+				struct zone *zone;
 
 				printk("Zone list for zone %d on node %d: ", j, i);
-				for (k = 0; zl->zones[k] != NULL; k++) 
-					printk("[%d/%s] ", zone_to_nid(zl->zones[k]), zl->zones[k]->name);
+				for_each_zone_zonelist(zone, z, zl, j)
+					printk("[%d/%s] ", zone_to_nid(zone),
+								zone->name);
 				printk("\n");
 			}
 		}
diff --git a/trunk/arch/powerpc/Kconfig b/trunk/arch/powerpc/Kconfig
index 20f45a8b87e3..3934e2659407 100644
--- a/trunk/arch/powerpc/Kconfig
+++ b/trunk/arch/powerpc/Kconfig
@@ -608,6 +608,19 @@ source "drivers/pcmcia/Kconfig"
 
 source "drivers/pci/hotplug/Kconfig"
 
+config HAS_RAPIDIO
+	bool
+	default n
+
+config RAPIDIO
+	bool "RapidIO support"
+	depends on HAS_RAPIDIO
+	help
+	  If you say Y here, the kernel will include drivers and
+	  infrastructure code to support RapidIO interconnect devices.
+
+source "drivers/rapidio/Kconfig"
+
 endmenu
 
 menu "Advanced setup"
@@ -803,3 +816,4 @@ config PPC_CLOCK
 config PPC_LIB_RHEAP
 	bool
 
+source "arch/powerpc/kvm/Kconfig"
diff --git a/trunk/arch/powerpc/Kconfig.debug b/trunk/arch/powerpc/Kconfig.debug
index a86d8d853214..a7d24e692bab 100644
--- a/trunk/arch/powerpc/Kconfig.debug
+++ b/trunk/arch/powerpc/Kconfig.debug
@@ -118,7 +118,6 @@ config XMON_DISASSEMBLY
 
 config IRQSTACKS
 	bool "Use separate kernel stacks when processing interrupts"
-	depends on PPC64
 	help
 	  If you say Y here the kernel will use separate kernel stacks
 	  for handling hard and soft interrupts.  This can help avoid
@@ -151,6 +150,9 @@ config BOOTX_TEXT
 
 config PPC_EARLY_DEBUG
 	bool "Early debugging (dangerous)"
+	# PPC_EARLY_DEBUG on 440 leaves AS=1 mappings above the TLB high water
+	# mark, which doesn't work with current 440 KVM.
+	depends on !KVM
 	help
 	  Say Y to enable some early debugging facilities that may be available
 	  for your processor/board combination. Those facilities are hacks
diff --git a/trunk/arch/powerpc/Makefile b/trunk/arch/powerpc/Makefile
index e2ec4a91ccef..9dcdc036cdf7 100644
--- a/trunk/arch/powerpc/Makefile
+++ b/trunk/arch/powerpc/Makefile
@@ -145,6 +145,7 @@ core-y				+= arch/powerpc/kernel/ \
 				   arch/powerpc/platforms/
 core-$(CONFIG_MATH_EMULATION)	+= arch/powerpc/math-emu/
 core-$(CONFIG_XMON)		+= arch/powerpc/xmon/
+core-$(CONFIG_KVM) 		+= arch/powerpc/kvm/
 
 drivers-$(CONFIG_OPROFILE)	+= arch/powerpc/oprofile/
 
diff --git a/trunk/arch/powerpc/boot/dts/mpc8610_hpcd.dts b/trunk/arch/powerpc/boot/dts/mpc8610_hpcd.dts
index 16c947b8a721..1f2f1e0a5571 100644
--- a/trunk/arch/powerpc/boot/dts/mpc8610_hpcd.dts
+++ b/trunk/arch/powerpc/boot/dts/mpc8610_hpcd.dts
@@ -45,6 +45,11 @@
 		reg = <0x00000000 0x20000000>;	// 512M at 0x0
 	};
 
+	board-control@e8000000 {
+		compatible = "fsl,fpga-pixis";
+		reg = <0xe8000000 32>;		// pixis at 0xe8000000
+	};
+
 	soc@e0000000 {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -104,6 +109,13 @@
 			interrupt-parent = <&mpic>;
 		};
 
+		display@2c000 {
+			compatible = "fsl,diu";
+			reg = <0x2c000 100>;
+			interrupts = <72 2>;
+			interrupt-parent = <&mpic>;
+		};
+
 		mpic: interrupt-controller@40000 {
 			clock-frequency = <0>;
 			interrupt-controller;
diff --git a/trunk/arch/powerpc/boot/dts/mpc8641_hpcn.dts b/trunk/arch/powerpc/boot/dts/mpc8641_hpcn.dts
index 7f9b999843ce..1e4bfe9cadb9 100644
--- a/trunk/arch/powerpc/boot/dts/mpc8641_hpcn.dts
+++ b/trunk/arch/powerpc/boot/dts/mpc8641_hpcn.dts
@@ -26,6 +26,7 @@
 		serial1 = &serial1;
 		pci0 = &pci0;
 		pci1 = &pci1;
+		rapidio0 = &rapidio0;
 	};
 
 	cpus {
@@ -500,4 +501,15 @@
 				  0x0 0x00100000>;
 		};
 	};
+	rapidio0: rapidio@f80c0000 {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		compatible = "fsl,rapidio-delta";
+		reg = <0xf80c0000 0x20000>;
+		ranges = <0 0 0xc0000000 0 0x20000000>;
+		interrupt-parent = <&mpic>;
+		/* err_irq bell_outb_irq bell_inb_irq
+			msg1_tx_irq msg1_rx_irq	msg2_tx_irq msg2_rx_irq */
+		interrupts = <48 2 49 2 50 2 53 2 54 2 55 2 56 2>;
+	};
 };
diff --git a/trunk/arch/powerpc/configs/g5_defconfig b/trunk/arch/powerpc/configs/g5_defconfig
index a20501f89474..88338a9f5e95 100644
--- a/trunk/arch/powerpc/configs/g5_defconfig
+++ b/trunk/arch/powerpc/configs/g5_defconfig
@@ -696,6 +696,7 @@ CONFIG_WINDFARM=y
 CONFIG_WINDFARM_PM81=y
 CONFIG_WINDFARM_PM91=y
 CONFIG_WINDFARM_PM112=y
+CONFIG_WINDFARM_PM121=y
 # CONFIG_PMAC_RACKMETER is not set
 CONFIG_NETDEVICES=y
 # CONFIG_NETDEVICES_MULTIQUEUE is not set
diff --git a/trunk/arch/powerpc/kernel/Makefile b/trunk/arch/powerpc/kernel/Makefile
index 9177b21b1a95..d14cebf62bb0 100644
--- a/trunk/arch/powerpc/kernel/Makefile
+++ b/trunk/arch/powerpc/kernel/Makefile
@@ -73,7 +73,6 @@ pci64-$(CONFIG_PPC64)		+= pci_dn.o isa-bridge.o
 obj-$(CONFIG_PCI)		+= pci_$(CONFIG_WORD_SIZE).o $(pci64-y) \
 				   pci-common.o
 obj-$(CONFIG_PCI_MSI)		+= msi.o
-obj-$(CONFIG_RAPIDIO)		+= rio.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o crash.o \
 				   machine_kexec_$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_AUDIT)		+= audit.o
diff --git a/trunk/arch/powerpc/kernel/asm-offsets.c b/trunk/arch/powerpc/kernel/asm-offsets.c
index adf1d09d726f..ec9228d687b0 100644
--- a/trunk/arch/powerpc/kernel/asm-offsets.c
+++ b/trunk/arch/powerpc/kernel/asm-offsets.c
@@ -23,10 +23,14 @@
 #include <linux/mm.h>
 #include <linux/suspend.h>
 #include <linux/hrtimer.h>
+#ifdef CONFIG_KVM
+#include <linux/kvm_host.h>
+#endif
 #ifdef CONFIG_PPC64
 #include <linux/time.h>
 #include <linux/hardirq.h>
 #endif
+#include <linux/kbuild.h>
 
 #include <asm/io.h>
 #include <asm/page.h>
@@ -48,11 +52,6 @@
 #include <asm/iseries/alpaca.h>
 #endif
 
-#define DEFINE(sym, val) \
-	asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
-
 int main(void)
 {
 	DEFINE(THREAD, offsetof(struct task_struct, thread));
@@ -64,6 +63,7 @@ int main(void)
 #endif /* CONFIG_PPC64 */
 
 	DEFINE(KSP, offsetof(struct thread_struct, ksp));
+	DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
 	DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
 	DEFINE(THREAD_FPEXC_MODE, offsetof(struct thread_struct, fpexc_mode));
 	DEFINE(THREAD_FPR0, offsetof(struct thread_struct, fpr[0]));
@@ -324,5 +324,30 @@ int main(void)
 
 	DEFINE(PGD_TABLE_SIZE, PGD_TABLE_SIZE);
 
+#ifdef CONFIG_KVM
+	DEFINE(TLBE_BYTES, sizeof(struct tlbe));
+
+	DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
+	DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
+	DEFINE(VCPU_HOST_TLB, offsetof(struct kvm_vcpu, arch.host_tlb));
+	DEFINE(VCPU_SHADOW_TLB, offsetof(struct kvm_vcpu, arch.shadow_tlb));
+	DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
+	DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
+	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
+	DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
+	DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
+	DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
+	DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.msr));
+	DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4));
+	DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5));
+	DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));
+	DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7));
+	DEFINE(VCPU_PID, offsetof(struct kvm_vcpu, arch.pid));
+
+	DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
+	DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
+	DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
+#endif
+
 	return 0;
 }
diff --git a/trunk/arch/powerpc/kernel/entry_32.S b/trunk/arch/powerpc/kernel/entry_32.S
index 84c868633068..0c8614d9875c 100644
--- a/trunk/arch/powerpc/kernel/entry_32.S
+++ b/trunk/arch/powerpc/kernel/entry_32.S
@@ -137,11 +137,12 @@ transfer_to_handler:
 2:	/* if from kernel, check interrupted DOZE/NAP mode and
          * check for stack overflow
          */
-	lwz	r9,THREAD_INFO-THREAD(r12)
-	cmplw	r1,r9			/* if r1 <= current->thread_info */
+	lwz	r9,KSP_LIMIT(r12)
+	cmplw	r1,r9			/* if r1 <= ksp_limit */
 	ble-	stack_ovf		/* then the kernel stack overflowed */
 5:
 #ifdef CONFIG_6xx
+	rlwinm	r9,r1,0,0,31-THREAD_SHIFT
 	tophys(r9,r9)			/* check local flags */
 	lwz	r12,TI_LOCAL_FLAGS(r9)
 	mtcrf	0x01,r12
diff --git a/trunk/arch/powerpc/kernel/head_64.S b/trunk/arch/powerpc/kernel/head_64.S
index 215973a2c8d5..024805e1747d 100644
--- a/trunk/arch/powerpc/kernel/head_64.S
+++ b/trunk/arch/powerpc/kernel/head_64.S
@@ -239,6 +239,10 @@ instruction_access_slb_pSeries:
 	.globl	system_call_pSeries
 system_call_pSeries:
 	HMT_MEDIUM
+BEGIN_FTR_SECTION
+	cmpdi	r0,0x1ebe
+	beq-	1f
+END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	mr	r9,r13
 	mfmsr	r10
 	mfspr	r13,SPRN_SPRG3
@@ -253,6 +257,13 @@ system_call_pSeries:
 	rfid
 	b	.	/* prevent speculative execution */
 
+/* Fast LE/BE switch system call */
+1:	mfspr	r12,SPRN_SRR1
+	xori	r12,r12,MSR_LE
+	mtspr	SPRN_SRR1,r12
+	rfid		/* return to userspace */
+	b	.
+
 	STD_EXCEPTION_PSERIES(0xd00, single_step)
 	STD_EXCEPTION_PSERIES(0xe00, trap_0e)
 
diff --git a/trunk/arch/powerpc/kernel/irq.c b/trunk/arch/powerpc/kernel/irq.c
index 425616f92d18..2f73f705d564 100644
--- a/trunk/arch/powerpc/kernel/irq.c
+++ b/trunk/arch/powerpc/kernel/irq.c
@@ -307,6 +307,7 @@ void do_IRQ(struct pt_regs *regs)
 		if (curtp != irqtp) {
 			struct irq_desc *desc = irq_desc + irq;
 			void *handler = desc->handle_irq;
+			unsigned long saved_sp_limit = current->thread.ksp_limit;
 			if (handler == NULL)
 				handler = &__do_IRQ;
 			irqtp->task = curtp->task;
@@ -319,7 +320,10 @@ void do_IRQ(struct pt_regs *regs)
 				(irqtp->preempt_count & ~SOFTIRQ_MASK) |
 				(curtp->preempt_count & SOFTIRQ_MASK);
 
+			current->thread.ksp_limit = (unsigned long)irqtp +
+				_ALIGN_UP(sizeof(struct thread_info), 16);
 			call_handle_irq(irq, desc, irqtp, handler);
+			current->thread.ksp_limit = saved_sp_limit;
 			irqtp->task = NULL;
 
 
@@ -352,9 +356,7 @@ void __init init_IRQ(void)
 {
 	if (ppc_md.init_IRQ)
 		ppc_md.init_IRQ();
-#ifdef CONFIG_PPC64
 	irq_ctx_init();
-#endif
 }
 
 
@@ -383,11 +385,15 @@ void irq_ctx_init(void)
 static inline void do_softirq_onstack(void)
 {
 	struct thread_info *curtp, *irqtp;
+	unsigned long saved_sp_limit = current->thread.ksp_limit;
 
 	curtp = current_thread_info();
 	irqtp = softirq_ctx[smp_processor_id()];
 	irqtp->task = curtp->task;
+	current->thread.ksp_limit = (unsigned long)irqtp +
+				    _ALIGN_UP(sizeof(struct thread_info), 16);
 	call_do_softirq(irqtp);
+	current->thread.ksp_limit = saved_sp_limit;
 	irqtp->task = NULL;
 }
 
diff --git a/trunk/arch/powerpc/kernel/lparcfg.c b/trunk/arch/powerpc/kernel/lparcfg.c
index 1ffacc698ffb..1e656b43ad7f 100644
--- a/trunk/arch/powerpc/kernel/lparcfg.c
+++ b/trunk/arch/powerpc/kernel/lparcfg.c
@@ -591,10 +591,8 @@ int __init lparcfg_init(void)
 			!firmware_has_feature(FW_FEATURE_ISERIES))
 		mode |= S_IWUSR;
 
-	ent = create_proc_entry("ppc64/lparcfg", mode, NULL);
-	if (ent) {
-		ent->proc_fops = &lparcfg_fops;
-	} else {
+	ent = proc_create("ppc64/lparcfg", mode, NULL, &lparcfg_fops);
+	if (!ent) {
 		printk(KERN_ERR "Failed to create ppc64/lparcfg\n");
 		return -EIO;
 	}
diff --git a/trunk/arch/powerpc/kernel/misc_32.S b/trunk/arch/powerpc/kernel/misc_32.S
index 92ccc6fcc5b0..89aaaa6f3561 100644
--- a/trunk/arch/powerpc/kernel/misc_32.S
+++ b/trunk/arch/powerpc/kernel/misc_32.S
@@ -32,6 +32,31 @@
 
 	.text
 
+#ifdef CONFIG_IRQSTACKS
+_GLOBAL(call_do_softirq)
+	mflr	r0
+	stw	r0,4(r1)
+	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
+	mr	r1,r3
+	bl	__do_softirq
+	lwz	r1,0(r1)
+	lwz	r0,4(r1)
+	mtlr	r0
+	blr
+
+_GLOBAL(call_handle_irq)
+	mflr	r0
+	stw	r0,4(r1)
+	mtctr	r6
+	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5)
+	mr	r1,r5
+	bctrl
+	lwz	r1,0(r1)
+	lwz	r0,4(r1)
+	mtlr	r0
+	blr
+#endif /* CONFIG_IRQSTACKS */
+
 /*
  * This returns the high 64 bits of the product of two 64-bit numbers.
  */
diff --git a/trunk/arch/powerpc/kernel/proc_ppc64.c b/trunk/arch/powerpc/kernel/proc_ppc64.c
index f78dfce1b771..c647ddef40dc 100644
--- a/trunk/arch/powerpc/kernel/proc_ppc64.c
+++ b/trunk/arch/powerpc/kernel/proc_ppc64.c
@@ -68,12 +68,11 @@ static int __init proc_ppc64_init(void)
 {
 	struct proc_dir_entry *pde;
 
-	pde = create_proc_entry("ppc64/systemcfg", S_IFREG|S_IRUGO, NULL);
+	pde = proc_create_data("ppc64/systemcfg", S_IFREG|S_IRUGO, NULL,
+			       &page_map_fops, vdso_data);
 	if (!pde)
 		return 1;
-	pde->data = vdso_data;
 	pde->size = PAGE_SIZE;
-	pde->proc_fops = &page_map_fops;
 
 	return 0;
 }
diff --git a/trunk/arch/powerpc/kernel/process.c b/trunk/arch/powerpc/kernel/process.c
index 6caad17ea72e..7de41c3948ec 100644
--- a/trunk/arch/powerpc/kernel/process.c
+++ b/trunk/arch/powerpc/kernel/process.c
@@ -589,6 +589,8 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
 	kregs = (struct pt_regs *) sp;
 	sp -= STACK_FRAME_OVERHEAD;
 	p->thread.ksp = sp;
+	p->thread.ksp_limit = (unsigned long)task_stack_page(p) +
+				_ALIGN_UP(sizeof(struct thread_info), 16);
 
 #ifdef CONFIG_PPC64
 	if (cpu_has_feature(CPU_FTR_SLB)) {
diff --git a/trunk/arch/powerpc/kernel/rio.c b/trunk/arch/powerpc/kernel/rio.c
deleted file mode 100644
index 29487fedfc76..000000000000
--- a/trunk/arch/powerpc/kernel/rio.c
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * RapidIO PPC32 support
- *
- * Copyright 2005 MontaVista Software, Inc.
- * Matt Porter <mporter@kernel.crashing.org>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/rio.h>
-
-#include <asm/rio.h>
-
-/**
- * platform_rio_init - Do platform specific RIO init
- *
- * Any platform specific initialization of RapdIO
- * hardware is done here as well as registration
- * of any active master ports in the system.
- */
-void __attribute__ ((weak))
-    platform_rio_init(void)
-{
-	printk(KERN_WARNING "RIO: No platform_rio_init() present\n");
-}
-
-/**
- * ppc_rio_init - Do PPC32 RIO init
- *
- * Calls platform-specific RIO init code and then calls
- * rio_init_mports() to initialize any master ports that
- * have been registered with the RIO subsystem.
- */
-static int __init ppc_rio_init(void)
-{
-	printk(KERN_INFO "RIO: RapidIO init\n");
-
-	/* Platform specific initialization */
-	platform_rio_init();
-
-	/* Enumerate all registered ports */
-	rio_init_mports();
-
-	return 0;
-}
-
-subsys_initcall(ppc_rio_init);
diff --git a/trunk/arch/powerpc/kernel/rtas-proc.c b/trunk/arch/powerpc/kernel/rtas-proc.c
index f2e3bc714d76..f9c6abc84a94 100644
--- a/trunk/arch/powerpc/kernel/rtas-proc.c
+++ b/trunk/arch/powerpc/kernel/rtas-proc.c
@@ -255,8 +255,6 @@ static void check_location(struct seq_file *m, const char *c);
 
 static int __init proc_rtas_init(void)
 {
-	struct proc_dir_entry *entry;
-
 	if (!machine_is(pseries))
 		return -ENODEV;
 
@@ -264,35 +262,20 @@ static int __init proc_rtas_init(void)
 	if (rtas_node == NULL)
 		return -ENODEV;
 
-	entry = create_proc_entry("ppc64/rtas/progress", S_IRUGO|S_IWUSR, NULL);
-	if (entry)
-		entry->proc_fops = &ppc_rtas_progress_operations;
-
-	entry = create_proc_entry("ppc64/rtas/clock", S_IRUGO|S_IWUSR, NULL);
-	if (entry)
-		entry->proc_fops = &ppc_rtas_clock_operations;
-
-	entry = create_proc_entry("ppc64/rtas/poweron", S_IWUSR|S_IRUGO, NULL);
-	if (entry)
-		entry->proc_fops = &ppc_rtas_poweron_operations;
-
-	entry = create_proc_entry("ppc64/rtas/sensors", S_IRUGO, NULL);
-	if (entry)
-		entry->proc_fops = &ppc_rtas_sensors_operations;
-
-	entry = create_proc_entry("ppc64/rtas/frequency", S_IWUSR|S_IRUGO,
-				  NULL);
-	if (entry)
-		entry->proc_fops = &ppc_rtas_tone_freq_operations;
-
-	entry = create_proc_entry("ppc64/rtas/volume", S_IWUSR|S_IRUGO, NULL);
-	if (entry)
-		entry->proc_fops = &ppc_rtas_tone_volume_operations;
-
-	entry = create_proc_entry("ppc64/rtas/rmo_buffer", S_IRUSR, NULL);
-	if (entry)
-		entry->proc_fops = &ppc_rtas_rmo_buf_ops;
-
+	proc_create("ppc64/rtas/progress", S_IRUGO|S_IWUSR, NULL,
+		    &ppc_rtas_progress_operations);
+	proc_create("ppc64/rtas/clock", S_IRUGO|S_IWUSR, NULL,
+		    &ppc_rtas_clock_operations);
+	proc_create("ppc64/rtas/poweron", S_IWUSR|S_IRUGO, NULL,
+		    &ppc_rtas_poweron_operations);
+	proc_create("ppc64/rtas/sensors", S_IRUGO, NULL,
+		    &ppc_rtas_sensors_operations);
+	proc_create("ppc64/rtas/frequency", S_IWUSR|S_IRUGO, NULL,
+		    &ppc_rtas_tone_freq_operations);
+	proc_create("ppc64/rtas/volume", S_IWUSR|S_IRUGO, NULL,
+		    &ppc_rtas_tone_volume_operations);
+	proc_create("ppc64/rtas/rmo_buffer", S_IRUSR, NULL,
+		    &ppc_rtas_rmo_buf_ops);
 	return 0;
 }
 
diff --git a/trunk/arch/powerpc/kernel/rtas_flash.c b/trunk/arch/powerpc/kernel/rtas_flash.c
index 627f126d1848..0a5e22b22729 100644
--- a/trunk/arch/powerpc/kernel/rtas_flash.c
+++ b/trunk/arch/powerpc/kernel/rtas_flash.c
@@ -704,18 +704,11 @@ static int initialize_flash_pde_data(const char *rtas_call_name,
 static struct proc_dir_entry *create_flash_pde(const char *filename,
 					       const struct file_operations *fops)
 {
-	struct proc_dir_entry *ent = NULL;
-
-	ent = create_proc_entry(filename, S_IRUSR | S_IWUSR, NULL);
-	if (ent != NULL) {
-		ent->proc_fops = fops;
-		ent->owner = THIS_MODULE;
-	}
-
-	return ent;
+	return proc_create(filename, S_IRUSR | S_IWUSR, NULL, fops);
 }
 
 static const struct file_operations rtas_flash_operations = {
+	.owner		= THIS_MODULE,
 	.read		= rtas_flash_read,
 	.write		= rtas_flash_write,
 	.open		= rtas_excl_open,
@@ -723,6 +716,7 @@ static const struct file_operations rtas_flash_operations = {
 };
 
 static const struct file_operations manage_flash_operations = {
+	.owner		= THIS_MODULE,
 	.read		= manage_flash_read,
 	.write		= manage_flash_write,
 	.open		= rtas_excl_open,
@@ -730,6 +724,7 @@ static const struct file_operations manage_flash_operations = {
 };
 
 static const struct file_operations validate_flash_operations = {
+	.owner		= THIS_MODULE,
 	.read		= validate_flash_read,
 	.write		= validate_flash_write,
 	.open		= rtas_excl_open,
diff --git a/trunk/arch/powerpc/kernel/setup_32.c b/trunk/arch/powerpc/kernel/setup_32.c
index 36f6779c88d4..5112a4aa801d 100644
--- a/trunk/arch/powerpc/kernel/setup_32.c
+++ b/trunk/arch/powerpc/kernel/setup_32.c
@@ -16,6 +16,7 @@
 #include <linux/root_dev.h>
 #include <linux/cpu.h>
 #include <linux/console.h>
+#include <linux/lmb.h>
 
 #include <asm/io.h>
 #include <asm/prom.h>
@@ -229,6 +230,24 @@ int __init ppc_init(void)
 
 arch_initcall(ppc_init);
 
+#ifdef CONFIG_IRQSTACKS
+static void __init irqstack_early_init(void)
+{
+	unsigned int i;
+
+	/* interrupt stacks must be in lowmem, we get that for free on ppc32
+	 * as the lmb is limited to lowmem by LMB_REAL_LIMIT */
+	for_each_possible_cpu(i) {
+		softirq_ctx[i] = (struct thread_info *)
+			__va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
+		hardirq_ctx[i] = (struct thread_info *)
+			__va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
+	}
+}
+#else
+#define irqstack_early_init()
+#endif
+
 /* Warning, IO base is not yet inited */
 void __init setup_arch(char **cmdline_p)
 {
@@ -286,6 +305,8 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.end_data = (unsigned long) _edata;
 	init_mm.brk = klimit;
 
+	irqstack_early_init();
+
 	/* set up the bootmem stuff with available memory */
 	do_init_bootmem();
 	if ( ppc_md.progress ) ppc_md.progress("setup_arch: bootmem", 0x3eab);
diff --git a/trunk/arch/powerpc/kvm/44x_tlb.c b/trunk/arch/powerpc/kvm/44x_tlb.c
new file mode 100644
index 000000000000..f5d7a5eab96e
--- /dev/null
+++ b/trunk/arch/powerpc/kvm/44x_tlb.c
@@ -0,0 +1,224 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kvm_host.h>
+#include <linux/highmem.h>
+#include <asm/mmu-44x.h>
+#include <asm/kvm_ppc.h>
+
+#include "44x_tlb.h"
+
+#define PPC44x_TLB_USER_PERM_MASK (PPC44x_TLB_UX|PPC44x_TLB_UR|PPC44x_TLB_UW)
+#define PPC44x_TLB_SUPER_PERM_MASK (PPC44x_TLB_SX|PPC44x_TLB_SR|PPC44x_TLB_SW)
+
+static unsigned int kvmppc_tlb_44x_pos;
+
+static u32 kvmppc_44x_tlb_shadow_attrib(u32 attrib, int usermode)
+{
+	/* Mask off reserved bits. */
+	attrib &= PPC44x_TLB_PERM_MASK|PPC44x_TLB_ATTR_MASK;
+
+	if (!usermode) {
+		/* Guest is in supervisor mode, so we need to translate guest
+		 * supervisor permissions into user permissions. */
+		attrib &= ~PPC44x_TLB_USER_PERM_MASK;
+		attrib |= (attrib & PPC44x_TLB_SUPER_PERM_MASK) << 3;
+	}
+
+	/* Make sure host can always access this memory. */
+	attrib |= PPC44x_TLB_SX|PPC44x_TLB_SR|PPC44x_TLB_SW;
+
+	return attrib;
+}
+
+/* Search the guest TLB for a matching entry. */
+int kvmppc_44x_tlb_index(struct kvm_vcpu *vcpu, gva_t eaddr, unsigned int pid,
+                         unsigned int as)
+{
+	int i;
+
+	/* XXX Replace loop with fancy data structures. */
+	for (i = 0; i < PPC44x_TLB_SIZE; i++) {
+		struct tlbe *tlbe = &vcpu->arch.guest_tlb[i];
+		unsigned int tid;
+
+		if (eaddr < get_tlb_eaddr(tlbe))
+			continue;
+
+		if (eaddr > get_tlb_end(tlbe))
+			continue;
+
+		tid = get_tlb_tid(tlbe);
+		if (tid && (tid != pid))
+			continue;
+
+		if (!get_tlb_v(tlbe))
+			continue;
+
+		if (get_tlb_ts(tlbe) != as)
+			continue;
+
+		return i;
+	}
+
+	return -1;
+}
+
+struct tlbe *kvmppc_44x_itlb_search(struct kvm_vcpu *vcpu, gva_t eaddr)
+{
+	unsigned int as = !!(vcpu->arch.msr & MSR_IS);
+	unsigned int index;
+
+	index = kvmppc_44x_tlb_index(vcpu, eaddr, vcpu->arch.pid, as);
+	if (index == -1)
+		return NULL;
+	return &vcpu->arch.guest_tlb[index];
+}
+
+struct tlbe *kvmppc_44x_dtlb_search(struct kvm_vcpu *vcpu, gva_t eaddr)
+{
+	unsigned int as = !!(vcpu->arch.msr & MSR_DS);
+	unsigned int index;
+
+	index = kvmppc_44x_tlb_index(vcpu, eaddr, vcpu->arch.pid, as);
+	if (index == -1)
+		return NULL;
+	return &vcpu->arch.guest_tlb[index];
+}
+
+static int kvmppc_44x_tlbe_is_writable(struct tlbe *tlbe)
+{
+	return tlbe->word2 & (PPC44x_TLB_SW|PPC44x_TLB_UW);
+}
+
+/* Must be called with mmap_sem locked for writing. */
+static void kvmppc_44x_shadow_release(struct kvm_vcpu *vcpu,
+                                      unsigned int index)
+{
+	struct tlbe *stlbe = &vcpu->arch.shadow_tlb[index];
+	struct page *page = vcpu->arch.shadow_pages[index];
+
+	kunmap(vcpu->arch.shadow_pages[index]);
+
+	if (get_tlb_v(stlbe)) {
+		if (kvmppc_44x_tlbe_is_writable(stlbe))
+			kvm_release_page_dirty(page);
+		else
+			kvm_release_page_clean(page);
+	}
+}
+
+/* Caller must ensure that the specified guest TLB entry is safe to insert into
+ * the shadow TLB. */
+void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gfn_t gfn, u64 asid,
+                    u32 flags)
+{
+	struct page *new_page;
+	struct tlbe *stlbe;
+	hpa_t hpaddr;
+	unsigned int victim;
+
+	/* Future optimization: don't overwrite the TLB entry containing the
+	 * current PC (or stack?). */
+	victim = kvmppc_tlb_44x_pos++;
+	if (kvmppc_tlb_44x_pos > tlb_44x_hwater)
+		kvmppc_tlb_44x_pos = 0;
+	stlbe = &vcpu->arch.shadow_tlb[victim];
+
+	/* Get reference to new page. */
+	down_write(&current->mm->mmap_sem);
+	new_page = gfn_to_page(vcpu->kvm, gfn);
+	if (is_error_page(new_page)) {
+		printk(KERN_ERR "Couldn't get guest page!\n");
+		kvm_release_page_clean(new_page);
+		return;
+	}
+	hpaddr = page_to_phys(new_page);
+
+	/* Drop reference to old page. */
+	kvmppc_44x_shadow_release(vcpu, victim);
+	up_write(&current->mm->mmap_sem);
+
+	vcpu->arch.shadow_pages[victim] = new_page;
+
+	/* XXX Make sure (va, size) doesn't overlap any other
+	 * entries. 440x6 user manual says the result would be
+	 * "undefined." */
+
+	/* XXX what about AS? */
+
+	stlbe->tid = asid & 0xff;
+
+	/* Force TS=1 for all guest mappings. */
+	/* For now we hardcode 4KB mappings, but it will be important to
+	 * use host large pages in the future. */
+	stlbe->word0 = (gvaddr & PAGE_MASK) | PPC44x_TLB_VALID | PPC44x_TLB_TS
+	               | PPC44x_TLB_4K;
+
+	stlbe->word1 = (hpaddr & 0xfffffc00) | ((hpaddr >> 32) & 0xf);
+	stlbe->word2 = kvmppc_44x_tlb_shadow_attrib(flags,
+	                                            vcpu->arch.msr & MSR_PR);
+}
+
+void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, u64 eaddr, u64 asid)
+{
+	unsigned int pid = asid & 0xff;
+	int i;
+
+	/* XXX Replace loop with fancy data structures. */
+	down_write(&current->mm->mmap_sem);
+	for (i = 0; i <= tlb_44x_hwater; i++) {
+		struct tlbe *stlbe = &vcpu->arch.shadow_tlb[i];
+		unsigned int tid;
+
+		if (!get_tlb_v(stlbe))
+			continue;
+
+		if (eaddr < get_tlb_eaddr(stlbe))
+			continue;
+
+		if (eaddr > get_tlb_end(stlbe))
+			continue;
+
+		tid = get_tlb_tid(stlbe);
+		if (tid && (tid != pid))
+			continue;
+
+		kvmppc_44x_shadow_release(vcpu, i);
+		stlbe->word0 = 0;
+	}
+	up_write(&current->mm->mmap_sem);
+}
+
+/* Invalidate all mappings, so that when they fault back in they will get the
+ * proper permission bits. */
+void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode)
+{
+	int i;
+
+	/* XXX Replace loop with fancy data structures. */
+	down_write(&current->mm->mmap_sem);
+	for (i = 0; i <= tlb_44x_hwater; i++) {
+		kvmppc_44x_shadow_release(vcpu, i);
+		vcpu->arch.shadow_tlb[i].word0 = 0;
+	}
+	up_write(&current->mm->mmap_sem);
+}
diff --git a/trunk/arch/powerpc/kvm/44x_tlb.h b/trunk/arch/powerpc/kvm/44x_tlb.h
new file mode 100644
index 000000000000..2ccd46b6f6b7
--- /dev/null
+++ b/trunk/arch/powerpc/kvm/44x_tlb.h
@@ -0,0 +1,91 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#ifndef __KVM_POWERPC_TLB_H__
+#define __KVM_POWERPC_TLB_H__
+
+#include <linux/kvm_host.h>
+#include <asm/mmu-44x.h>
+
+extern int kvmppc_44x_tlb_index(struct kvm_vcpu *vcpu, gva_t eaddr,
+                                unsigned int pid, unsigned int as);
+extern struct tlbe *kvmppc_44x_dtlb_search(struct kvm_vcpu *vcpu, gva_t eaddr);
+extern struct tlbe *kvmppc_44x_itlb_search(struct kvm_vcpu *vcpu, gva_t eaddr);
+
+/* TLB helper functions */
+static inline unsigned int get_tlb_size(const struct tlbe *tlbe)
+{
+	return (tlbe->word0 >> 4) & 0xf;
+}
+
+static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
+{
+	return tlbe->word0 & 0xfffffc00;
+}
+
+static inline gva_t get_tlb_bytes(const struct tlbe *tlbe)
+{
+	unsigned int pgsize = get_tlb_size(tlbe);
+	return 1 << 10 << (pgsize << 1);
+}
+
+static inline gva_t get_tlb_end(const struct tlbe *tlbe)
+{
+	return get_tlb_eaddr(tlbe) + get_tlb_bytes(tlbe) - 1;
+}
+
+static inline u64 get_tlb_raddr(const struct tlbe *tlbe)
+{
+	u64 word1 = tlbe->word1;
+	return ((word1 & 0xf) << 32) | (word1 & 0xfffffc00);
+}
+
+static inline unsigned int get_tlb_tid(const struct tlbe *tlbe)
+{
+	return tlbe->tid & 0xff;
+}
+
+static inline unsigned int get_tlb_ts(const struct tlbe *tlbe)
+{
+	return (tlbe->word0 >> 8) & 0x1;
+}
+
+static inline unsigned int get_tlb_v(const struct tlbe *tlbe)
+{
+	return (tlbe->word0 >> 9) & 0x1;
+}
+
+static inline unsigned int get_mmucr_stid(const struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.mmucr & 0xff;
+}
+
+static inline unsigned int get_mmucr_sts(const struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.mmucr >> 16) & 0x1;
+}
+
+static inline gpa_t tlb_xlate(struct tlbe *tlbe, gva_t eaddr)
+{
+	unsigned int pgmask = get_tlb_bytes(tlbe) - 1;
+
+	return get_tlb_raddr(tlbe) | (eaddr & pgmask);
+}
+
+#endif /* __KVM_POWERPC_TLB_H__ */
diff --git a/trunk/arch/powerpc/kvm/Kconfig b/trunk/arch/powerpc/kvm/Kconfig
new file mode 100644
index 000000000000..6b076010213b
--- /dev/null
+++ b/trunk/arch/powerpc/kvm/Kconfig
@@ -0,0 +1,42 @@
+#
+# KVM configuration
+#
+
+menuconfig VIRTUALIZATION
+	bool "Virtualization"
+	---help---
+	  Say Y here to get to see options for using your Linux host to run
+	  other operating systems inside virtual machines (guests).
+	  This option alone does not add any kernel code.
+
+	  If you say N, all options in this submenu will be skipped and
+	  disabled.
+
+if VIRTUALIZATION
+
+config KVM
+	bool "Kernel-based Virtual Machine (KVM) support"
+	depends on 44x && EXPERIMENTAL
+	select PREEMPT_NOTIFIERS
+	select ANON_INODES
+	# We can only run on Book E hosts so far
+	select KVM_BOOKE_HOST
+	---help---
+	  Support hosting virtualized guest machines. You will also
+	  need to select one or more of the processor modules below.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  If unsure, say N.
+
+config KVM_BOOKE_HOST
+	bool "KVM host support for Book E PowerPC processors"
+	depends on KVM && 44x
+	---help---
+	  Provides host support for KVM on Book E PowerPC processors. Currently
+	  this works on 440 processors only.
+
+source drivers/virtio/Kconfig
+
+endif # VIRTUALIZATION
diff --git a/trunk/arch/powerpc/kvm/Makefile b/trunk/arch/powerpc/kvm/Makefile
new file mode 100644
index 000000000000..d0d358d367ec
--- /dev/null
+++ b/trunk/arch/powerpc/kvm/Makefile
@@ -0,0 +1,15 @@
+#
+# Makefile for Kernel-based Virtual Machine module
+#
+
+EXTRA_CFLAGS += -Ivirt/kvm -Iarch/powerpc/kvm
+
+common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o)
+
+kvm-objs := $(common-objs) powerpc.o emulate.o booke_guest.o
+obj-$(CONFIG_KVM) += kvm.o
+
+AFLAGS_booke_interrupts.o := -I$(obj)
+
+kvm-booke-host-objs := booke_host.o booke_interrupts.o 44x_tlb.o
+obj-$(CONFIG_KVM_BOOKE_HOST) += kvm-booke-host.o
diff --git a/trunk/arch/powerpc/kvm/booke_guest.c b/trunk/arch/powerpc/kvm/booke_guest.c
new file mode 100644
index 000000000000..6d9884a6884a
--- /dev/null
+++ b/trunk/arch/powerpc/kvm/booke_guest.c
@@ -0,0 +1,615 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ *          Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/fs.h>
+#include <asm/cputable.h>
+#include <asm/uaccess.h>
+#include <asm/kvm_ppc.h>
+
+#include "44x_tlb.h"
+
+#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
+#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+
+struct kvm_stats_debugfs_item debugfs_entries[] = {
+	{ "exits",      VCPU_STAT(sum_exits) },
+	{ "mmio",       VCPU_STAT(mmio_exits) },
+	{ "dcr",        VCPU_STAT(dcr_exits) },
+	{ "sig",        VCPU_STAT(signal_exits) },
+	{ "light",      VCPU_STAT(light_exits) },
+	{ "itlb_r",     VCPU_STAT(itlb_real_miss_exits) },
+	{ "itlb_v",     VCPU_STAT(itlb_virt_miss_exits) },
+	{ "dtlb_r",     VCPU_STAT(dtlb_real_miss_exits) },
+	{ "dtlb_v",     VCPU_STAT(dtlb_virt_miss_exits) },
+	{ "sysc",       VCPU_STAT(syscall_exits) },
+	{ "isi",        VCPU_STAT(isi_exits) },
+	{ "dsi",        VCPU_STAT(dsi_exits) },
+	{ "inst_emu",   VCPU_STAT(emulated_inst_exits) },
+	{ "dec",        VCPU_STAT(dec_exits) },
+	{ "ext_intr",   VCPU_STAT(ext_intr_exits) },
+	{ NULL }
+};
+
+static const u32 interrupt_msr_mask[16] = {
+	[BOOKE_INTERRUPT_CRITICAL]      = MSR_ME,
+	[BOOKE_INTERRUPT_MACHINE_CHECK] = 0,
+	[BOOKE_INTERRUPT_DATA_STORAGE]  = MSR_CE|MSR_ME|MSR_DE,
+	[BOOKE_INTERRUPT_INST_STORAGE]  = MSR_CE|MSR_ME|MSR_DE,
+	[BOOKE_INTERRUPT_EXTERNAL]      = MSR_CE|MSR_ME|MSR_DE,
+	[BOOKE_INTERRUPT_ALIGNMENT]     = MSR_CE|MSR_ME|MSR_DE,
+	[BOOKE_INTERRUPT_PROGRAM]       = MSR_CE|MSR_ME|MSR_DE,
+	[BOOKE_INTERRUPT_FP_UNAVAIL]    = MSR_CE|MSR_ME|MSR_DE,
+	[BOOKE_INTERRUPT_SYSCALL]       = MSR_CE|MSR_ME|MSR_DE,
+	[BOOKE_INTERRUPT_AP_UNAVAIL]    = MSR_CE|MSR_ME|MSR_DE,
+	[BOOKE_INTERRUPT_DECREMENTER]   = MSR_CE|MSR_ME|MSR_DE,
+	[BOOKE_INTERRUPT_FIT]           = MSR_CE|MSR_ME|MSR_DE,
+	[BOOKE_INTERRUPT_WATCHDOG]      = MSR_ME,
+	[BOOKE_INTERRUPT_DTLB_MISS]     = MSR_CE|MSR_ME|MSR_DE,
+	[BOOKE_INTERRUPT_ITLB_MISS]     = MSR_CE|MSR_ME|MSR_DE,
+	[BOOKE_INTERRUPT_DEBUG]         = MSR_ME,
+};
+
+const unsigned char exception_priority[] = {
+	[BOOKE_INTERRUPT_DATA_STORAGE] = 0,
+	[BOOKE_INTERRUPT_INST_STORAGE] = 1,
+	[BOOKE_INTERRUPT_ALIGNMENT] = 2,
+	[BOOKE_INTERRUPT_PROGRAM] = 3,
+	[BOOKE_INTERRUPT_FP_UNAVAIL] = 4,
+	[BOOKE_INTERRUPT_SYSCALL] = 5,
+	[BOOKE_INTERRUPT_AP_UNAVAIL] = 6,
+	[BOOKE_INTERRUPT_DTLB_MISS] = 7,
+	[BOOKE_INTERRUPT_ITLB_MISS] = 8,
+	[BOOKE_INTERRUPT_MACHINE_CHECK] = 9,
+	[BOOKE_INTERRUPT_DEBUG] = 10,
+	[BOOKE_INTERRUPT_CRITICAL] = 11,
+	[BOOKE_INTERRUPT_WATCHDOG] = 12,
+	[BOOKE_INTERRUPT_EXTERNAL] = 13,
+	[BOOKE_INTERRUPT_FIT] = 14,
+	[BOOKE_INTERRUPT_DECREMENTER] = 15,
+};
+
+const unsigned char priority_exception[] = {
+	BOOKE_INTERRUPT_DATA_STORAGE,
+	BOOKE_INTERRUPT_INST_STORAGE,
+	BOOKE_INTERRUPT_ALIGNMENT,
+	BOOKE_INTERRUPT_PROGRAM,
+	BOOKE_INTERRUPT_FP_UNAVAIL,
+	BOOKE_INTERRUPT_SYSCALL,
+	BOOKE_INTERRUPT_AP_UNAVAIL,
+	BOOKE_INTERRUPT_DTLB_MISS,
+	BOOKE_INTERRUPT_ITLB_MISS,
+	BOOKE_INTERRUPT_MACHINE_CHECK,
+	BOOKE_INTERRUPT_DEBUG,
+	BOOKE_INTERRUPT_CRITICAL,
+	BOOKE_INTERRUPT_WATCHDOG,
+	BOOKE_INTERRUPT_EXTERNAL,
+	BOOKE_INTERRUPT_FIT,
+	BOOKE_INTERRUPT_DECREMENTER,
+};
+
+
+void kvmppc_dump_tlbs(struct kvm_vcpu *vcpu)
+{
+	struct tlbe *tlbe;
+	int i;
+
+	printk("vcpu %d TLB dump:\n", vcpu->vcpu_id);
+	printk("| %2s | %3s | %8s | %8s | %8s |\n",
+			"nr", "tid", "word0", "word1", "word2");
+
+	for (i = 0; i < PPC44x_TLB_SIZE; i++) {
+		tlbe = &vcpu->arch.guest_tlb[i];
+		if (tlbe->word0 & PPC44x_TLB_VALID)
+			printk(" G%2d |  %02X | %08X | %08X | %08X |\n",
+			       i, tlbe->tid, tlbe->word0, tlbe->word1,
+			       tlbe->word2);
+	}
+
+	for (i = 0; i < PPC44x_TLB_SIZE; i++) {
+		tlbe = &vcpu->arch.shadow_tlb[i];
+		if (tlbe->word0 & PPC44x_TLB_VALID)
+			printk(" S%2d | %02X | %08X | %08X | %08X |\n",
+			       i, tlbe->tid, tlbe->word0, tlbe->word1,
+			       tlbe->word2);
+	}
+}
+
+/* TODO: use vcpu_printf() */
+void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu)
+{
+	int i;
+
+	printk("pc:   %08x msr:  %08x\n", vcpu->arch.pc, vcpu->arch.msr);
+	printk("lr:   %08x ctr:  %08x\n", vcpu->arch.lr, vcpu->arch.ctr);
+	printk("srr0: %08x srr1: %08x\n", vcpu->arch.srr0, vcpu->arch.srr1);
+
+	printk("exceptions: %08lx\n", vcpu->arch.pending_exceptions);
+
+	for (i = 0; i < 32; i += 4) {
+		printk("gpr%02d: %08x %08x %08x %08x\n", i,
+		       vcpu->arch.gpr[i],
+		       vcpu->arch.gpr[i+1],
+		       vcpu->arch.gpr[i+2],
+		       vcpu->arch.gpr[i+3]);
+	}
+}
+
+/* Check if we are ready to deliver the interrupt */
+static int kvmppc_can_deliver_interrupt(struct kvm_vcpu *vcpu, int interrupt)
+{
+	int r;
+
+	switch (interrupt) {
+	case BOOKE_INTERRUPT_CRITICAL:
+		r = vcpu->arch.msr & MSR_CE;
+		break;
+	case BOOKE_INTERRUPT_MACHINE_CHECK:
+		r = vcpu->arch.msr & MSR_ME;
+		break;
+	case BOOKE_INTERRUPT_EXTERNAL:
+		r = vcpu->arch.msr & MSR_EE;
+		break;
+	case BOOKE_INTERRUPT_DECREMENTER:
+		r = vcpu->arch.msr & MSR_EE;
+		break;
+	case BOOKE_INTERRUPT_FIT:
+		r = vcpu->arch.msr & MSR_EE;
+		break;
+	case BOOKE_INTERRUPT_WATCHDOG:
+		r = vcpu->arch.msr & MSR_CE;
+		break;
+	case BOOKE_INTERRUPT_DEBUG:
+		r = vcpu->arch.msr & MSR_DE;
+		break;
+	default:
+		r = 1;
+	}
+
+	return r;
+}
+
+static void kvmppc_deliver_interrupt(struct kvm_vcpu *vcpu, int interrupt)
+{
+	switch (interrupt) {
+	case BOOKE_INTERRUPT_DECREMENTER:
+		vcpu->arch.tsr |= TSR_DIS;
+		break;
+	}
+
+	vcpu->arch.srr0 = vcpu->arch.pc;
+	vcpu->arch.srr1 = vcpu->arch.msr;
+	vcpu->arch.pc = vcpu->arch.ivpr | vcpu->arch.ivor[interrupt];
+	kvmppc_set_msr(vcpu, vcpu->arch.msr & interrupt_msr_mask[interrupt]);
+}
+
+/* Check pending exceptions and deliver one, if possible. */
+void kvmppc_check_and_deliver_interrupts(struct kvm_vcpu *vcpu)
+{
+	unsigned long *pending = &vcpu->arch.pending_exceptions;
+	unsigned int exception;
+	unsigned int priority;
+
+	priority = find_first_bit(pending, BITS_PER_BYTE * sizeof(*pending));
+	while (priority <= BOOKE_MAX_INTERRUPT) {
+		exception = priority_exception[priority];
+		if (kvmppc_can_deliver_interrupt(vcpu, exception)) {
+			kvmppc_clear_exception(vcpu, exception);
+			kvmppc_deliver_interrupt(vcpu, exception);
+			break;
+		}
+
+		priority = find_next_bit(pending,
+		                         BITS_PER_BYTE * sizeof(*pending),
+		                         priority + 1);
+	}
+}
+
+static int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+	enum emulation_result er;
+	int r;
+
+	er = kvmppc_emulate_instruction(run, vcpu);
+	switch (er) {
+	case EMULATE_DONE:
+		/* Future optimization: only reload non-volatiles if they were
+		 * actually modified. */
+		r = RESUME_GUEST_NV;
+		break;
+	case EMULATE_DO_MMIO:
+		run->exit_reason = KVM_EXIT_MMIO;
+		/* We must reload nonvolatiles because "update" load/store
+		 * instructions modify register state. */
+		/* Future optimization: only reload non-volatiles if they were
+		 * actually modified. */
+		r = RESUME_HOST_NV;
+		break;
+	case EMULATE_FAIL:
+		/* XXX Deliver Program interrupt to guest. */
+		printk(KERN_EMERG "%s: emulation failed (%08x)\n", __func__,
+		       vcpu->arch.last_inst);
+		r = RESUME_HOST;
+		break;
+	default:
+		BUG();
+	}
+
+	return r;
+}
+
+/**
+ * kvmppc_handle_exit
+ *
+ * Return value is in the form (errcode<<2 | RESUME_FLAG_HOST | RESUME_FLAG_NV)
+ */
+int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                       unsigned int exit_nr)
+{
+	enum emulation_result er;
+	int r = RESUME_HOST;
+
+	local_irq_enable();
+
+	run->exit_reason = KVM_EXIT_UNKNOWN;
+	run->ready_for_interrupt_injection = 1;
+
+	switch (exit_nr) {
+	case BOOKE_INTERRUPT_MACHINE_CHECK:
+		printk("MACHINE CHECK: %lx\n", mfspr(SPRN_MCSR));
+		kvmppc_dump_vcpu(vcpu);
+		r = RESUME_HOST;
+		break;
+
+	case BOOKE_INTERRUPT_EXTERNAL:
+	case BOOKE_INTERRUPT_DECREMENTER:
+		/* Since we switched IVPR back to the host's value, the host
+		 * handled this interrupt the moment we enabled interrupts.
+		 * Now we just offer it a chance to reschedule the guest. */
+
+		/* XXX At this point the TLB still holds our shadow TLB, so if
+		 * we do reschedule the host will fault over it. Perhaps we
+		 * should politely restore the host's entries to minimize
+		 * misses before ceding control. */
+		if (need_resched())
+			cond_resched();
+		if (exit_nr == BOOKE_INTERRUPT_DECREMENTER)
+			vcpu->stat.dec_exits++;
+		else
+			vcpu->stat.ext_intr_exits++;
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_PROGRAM:
+		if (vcpu->arch.msr & MSR_PR) {
+			/* Program traps generated by user-level software must be handled
+			 * by the guest kernel. */
+			vcpu->arch.esr = vcpu->arch.fault_esr;
+			kvmppc_queue_exception(vcpu, BOOKE_INTERRUPT_PROGRAM);
+			r = RESUME_GUEST;
+			break;
+		}
+
+		er = kvmppc_emulate_instruction(run, vcpu);
+		switch (er) {
+		case EMULATE_DONE:
+			/* Future optimization: only reload non-volatiles if
+			 * they were actually modified by emulation. */
+			vcpu->stat.emulated_inst_exits++;
+			r = RESUME_GUEST_NV;
+			break;
+		case EMULATE_DO_DCR:
+			run->exit_reason = KVM_EXIT_DCR;
+			r = RESUME_HOST;
+			break;
+		case EMULATE_FAIL:
+			/* XXX Deliver Program interrupt to guest. */
+			printk(KERN_CRIT "%s: emulation at %x failed (%08x)\n",
+			       __func__, vcpu->arch.pc, vcpu->arch.last_inst);
+			/* For debugging, encode the failing instruction and
+			 * report it to userspace. */
+			run->hw.hardware_exit_reason = ~0ULL << 32;
+			run->hw.hardware_exit_reason |= vcpu->arch.last_inst;
+			r = RESUME_HOST;
+			break;
+		default:
+			BUG();
+		}
+		break;
+
+	case BOOKE_INTERRUPT_DATA_STORAGE:
+		vcpu->arch.dear = vcpu->arch.fault_dear;
+		vcpu->arch.esr = vcpu->arch.fault_esr;
+		kvmppc_queue_exception(vcpu, exit_nr);
+		vcpu->stat.dsi_exits++;
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_INST_STORAGE:
+		vcpu->arch.esr = vcpu->arch.fault_esr;
+		kvmppc_queue_exception(vcpu, exit_nr);
+		vcpu->stat.isi_exits++;
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_SYSCALL:
+		kvmppc_queue_exception(vcpu, exit_nr);
+		vcpu->stat.syscall_exits++;
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_DTLB_MISS: {
+		struct tlbe *gtlbe;
+		unsigned long eaddr = vcpu->arch.fault_dear;
+		gfn_t gfn;
+
+		/* Check the guest TLB. */
+		gtlbe = kvmppc_44x_dtlb_search(vcpu, eaddr);
+		if (!gtlbe) {
+			/* The guest didn't have a mapping for it. */
+			kvmppc_queue_exception(vcpu, exit_nr);
+			vcpu->arch.dear = vcpu->arch.fault_dear;
+			vcpu->arch.esr = vcpu->arch.fault_esr;
+			vcpu->stat.dtlb_real_miss_exits++;
+			r = RESUME_GUEST;
+			break;
+		}
+
+		vcpu->arch.paddr_accessed = tlb_xlate(gtlbe, eaddr);
+		gfn = vcpu->arch.paddr_accessed >> PAGE_SHIFT;
+
+		if (kvm_is_visible_gfn(vcpu->kvm, gfn)) {
+			/* The guest TLB had a mapping, but the shadow TLB
+			 * didn't, and it is RAM. This could be because:
+			 * a) the entry is mapping the host kernel, or
+			 * b) the guest used a large mapping which we're faking
+			 * Either way, we need to satisfy the fault without
+			 * invoking the guest. */
+			kvmppc_mmu_map(vcpu, eaddr, gfn, gtlbe->tid,
+			               gtlbe->word2);
+			vcpu->stat.dtlb_virt_miss_exits++;
+			r = RESUME_GUEST;
+		} else {
+			/* Guest has mapped and accessed a page which is not
+			 * actually RAM. */
+			r = kvmppc_emulate_mmio(run, vcpu);
+		}
+
+		break;
+	}
+
+	case BOOKE_INTERRUPT_ITLB_MISS: {
+		struct tlbe *gtlbe;
+		unsigned long eaddr = vcpu->arch.pc;
+		gfn_t gfn;
+
+		r = RESUME_GUEST;
+
+		/* Check the guest TLB. */
+		gtlbe = kvmppc_44x_itlb_search(vcpu, eaddr);
+		if (!gtlbe) {
+			/* The guest didn't have a mapping for it. */
+			kvmppc_queue_exception(vcpu, exit_nr);
+			vcpu->stat.itlb_real_miss_exits++;
+			break;
+		}
+
+		vcpu->stat.itlb_virt_miss_exits++;
+
+		gfn = tlb_xlate(gtlbe, eaddr) >> PAGE_SHIFT;
+
+		if (kvm_is_visible_gfn(vcpu->kvm, gfn)) {
+			/* The guest TLB had a mapping, but the shadow TLB
+			 * didn't. This could be because:
+			 * a) the entry is mapping the host kernel, or
+			 * b) the guest used a large mapping which we're faking
+			 * Either way, we need to satisfy the fault without
+			 * invoking the guest. */
+			kvmppc_mmu_map(vcpu, eaddr, gfn, gtlbe->tid,
+			               gtlbe->word2);
+		} else {
+			/* Guest mapped and leaped at non-RAM! */
+			kvmppc_queue_exception(vcpu,
+			                       BOOKE_INTERRUPT_MACHINE_CHECK);
+		}
+
+		break;
+	}
+
+	default:
+		printk(KERN_EMERG "exit_nr %d\n", exit_nr);
+		BUG();
+	}
+
+	local_irq_disable();
+
+	kvmppc_check_and_deliver_interrupts(vcpu);
+
+	/* Do some exit accounting. */
+	vcpu->stat.sum_exits++;
+	if (!(r & RESUME_HOST)) {
+		/* To avoid clobbering exit_reason, only check for signals if
+		 * we aren't already exiting to userspace for some other
+		 * reason. */
+		if (signal_pending(current)) {
+			run->exit_reason = KVM_EXIT_INTR;
+			r = (-EINTR << 2) | RESUME_HOST | (r & RESUME_FLAG_NV);
+
+			vcpu->stat.signal_exits++;
+		} else {
+			vcpu->stat.light_exits++;
+		}
+	} else {
+		switch (run->exit_reason) {
+		case KVM_EXIT_MMIO:
+			vcpu->stat.mmio_exits++;
+			break;
+		case KVM_EXIT_DCR:
+			vcpu->stat.dcr_exits++;
+			break;
+		case KVM_EXIT_INTR:
+			vcpu->stat.signal_exits++;
+			break;
+		}
+	}
+
+	return r;
+}
+
+/* Initial guest state: 16MB mapping 0 -> 0, PC = 0, MSR = 0, R1 = 16MB */
+int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+	struct tlbe *tlbe = &vcpu->arch.guest_tlb[0];
+
+	tlbe->tid = 0;
+	tlbe->word0 = PPC44x_TLB_16M | PPC44x_TLB_VALID;
+	tlbe->word1 = 0;
+	tlbe->word2 = PPC44x_TLB_SX | PPC44x_TLB_SW | PPC44x_TLB_SR;
+
+	tlbe++;
+	tlbe->tid = 0;
+	tlbe->word0 = 0xef600000 | PPC44x_TLB_4K | PPC44x_TLB_VALID;
+	tlbe->word1 = 0xef600000;
+	tlbe->word2 = PPC44x_TLB_SX | PPC44x_TLB_SW | PPC44x_TLB_SR
+	              | PPC44x_TLB_I | PPC44x_TLB_G;
+
+	vcpu->arch.pc = 0;
+	vcpu->arch.msr = 0;
+	vcpu->arch.gpr[1] = (16<<20) - 8; /* -8 for the callee-save LR slot */
+
+	/* Eye-catching number so we know if the guest takes an interrupt
+	 * before it's programmed its own IVPR. */
+	vcpu->arch.ivpr = 0x55550000;
+
+	/* Since the guest can directly access the timebase, it must know the
+	 * real timebase frequency. Accordingly, it must see the state of
+	 * CCR1[TCS]. */
+	vcpu->arch.ccr1 = mfspr(SPRN_CCR1);
+
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+	int i;
+
+	regs->pc = vcpu->arch.pc;
+	regs->cr = vcpu->arch.cr;
+	regs->ctr = vcpu->arch.ctr;
+	regs->lr = vcpu->arch.lr;
+	regs->xer = vcpu->arch.xer;
+	regs->msr = vcpu->arch.msr;
+	regs->srr0 = vcpu->arch.srr0;
+	regs->srr1 = vcpu->arch.srr1;
+	regs->pid = vcpu->arch.pid;
+	regs->sprg0 = vcpu->arch.sprg0;
+	regs->sprg1 = vcpu->arch.sprg1;
+	regs->sprg2 = vcpu->arch.sprg2;
+	regs->sprg3 = vcpu->arch.sprg3;
+	regs->sprg5 = vcpu->arch.sprg4;
+	regs->sprg6 = vcpu->arch.sprg5;
+	regs->sprg7 = vcpu->arch.sprg6;
+
+	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
+		regs->gpr[i] = vcpu->arch.gpr[i];
+
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+	int i;
+
+	vcpu->arch.pc = regs->pc;
+	vcpu->arch.cr = regs->cr;
+	vcpu->arch.ctr = regs->ctr;
+	vcpu->arch.lr = regs->lr;
+	vcpu->arch.xer = regs->xer;
+	vcpu->arch.msr = regs->msr;
+	vcpu->arch.srr0 = regs->srr0;
+	vcpu->arch.srr1 = regs->srr1;
+	vcpu->arch.sprg0 = regs->sprg0;
+	vcpu->arch.sprg1 = regs->sprg1;
+	vcpu->arch.sprg2 = regs->sprg2;
+	vcpu->arch.sprg3 = regs->sprg3;
+	vcpu->arch.sprg5 = regs->sprg4;
+	vcpu->arch.sprg6 = regs->sprg5;
+	vcpu->arch.sprg7 = regs->sprg6;
+
+	for (i = 0; i < ARRAY_SIZE(vcpu->arch.gpr); i++)
+		vcpu->arch.gpr[i] = regs->gpr[i];
+
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+                                  struct kvm_sregs *sregs)
+{
+	return -ENOTSUPP;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+                                  struct kvm_sregs *sregs)
+{
+	return -ENOTSUPP;
+}
+
+int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+	return -ENOTSUPP;
+}
+
+int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+	return -ENOTSUPP;
+}
+
+/* 'linear_address' is actually an encoding of AS|PID|EADDR . */
+int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+                                  struct kvm_translation *tr)
+{
+	struct tlbe *gtlbe;
+	int index;
+	gva_t eaddr;
+	u8 pid;
+	u8 as;
+
+	eaddr = tr->linear_address;
+	pid = (tr->linear_address >> 32) & 0xff;
+	as = (tr->linear_address >> 40) & 0x1;
+
+	index = kvmppc_44x_tlb_index(vcpu, eaddr, pid, as);
+	if (index == -1) {
+		tr->valid = 0;
+		return 0;
+	}
+
+	gtlbe = &vcpu->arch.guest_tlb[index];
+
+	tr->physical_address = tlb_xlate(gtlbe, eaddr);
+	/* XXX what does "writeable" and "usermode" even mean? */
+	tr->valid = 1;
+
+	return 0;
+}
diff --git a/trunk/arch/powerpc/kvm/booke_host.c b/trunk/arch/powerpc/kvm/booke_host.c
new file mode 100644
index 000000000000..b480341bc31e
--- /dev/null
+++ b/trunk/arch/powerpc/kvm/booke_host.c
@@ -0,0 +1,83 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <asm/cacheflush.h>
+#include <asm/kvm_ppc.h>
+
+unsigned long kvmppc_booke_handlers;
+
+static int kvmppc_booke_init(void)
+{
+	unsigned long ivor[16];
+	unsigned long max_ivor = 0;
+	int i;
+
+	/* We install our own exception handlers by hijacking IVPR. IVPR must
+	 * be 16-bit aligned, so we need a 64KB allocation. */
+	kvmppc_booke_handlers = __get_free_pages(GFP_KERNEL | __GFP_ZERO,
+	                                         VCPU_SIZE_ORDER);
+	if (!kvmppc_booke_handlers)
+		return -ENOMEM;
+
+	/* XXX make sure our handlers are smaller than Linux's */
+
+	/* Copy our interrupt handlers to match host IVORs. That way we don't
+	 * have to swap the IVORs on every guest/host transition. */
+	ivor[0] = mfspr(SPRN_IVOR0);
+	ivor[1] = mfspr(SPRN_IVOR1);
+	ivor[2] = mfspr(SPRN_IVOR2);
+	ivor[3] = mfspr(SPRN_IVOR3);
+	ivor[4] = mfspr(SPRN_IVOR4);
+	ivor[5] = mfspr(SPRN_IVOR5);
+	ivor[6] = mfspr(SPRN_IVOR6);
+	ivor[7] = mfspr(SPRN_IVOR7);
+	ivor[8] = mfspr(SPRN_IVOR8);
+	ivor[9] = mfspr(SPRN_IVOR9);
+	ivor[10] = mfspr(SPRN_IVOR10);
+	ivor[11] = mfspr(SPRN_IVOR11);
+	ivor[12] = mfspr(SPRN_IVOR12);
+	ivor[13] = mfspr(SPRN_IVOR13);
+	ivor[14] = mfspr(SPRN_IVOR14);
+	ivor[15] = mfspr(SPRN_IVOR15);
+
+	for (i = 0; i < 16; i++) {
+		if (ivor[i] > max_ivor)
+			max_ivor = ivor[i];
+
+		memcpy((void *)kvmppc_booke_handlers + ivor[i],
+		       kvmppc_handlers_start + i * kvmppc_handler_len,
+		       kvmppc_handler_len);
+	}
+	flush_icache_range(kvmppc_booke_handlers,
+	                   kvmppc_booke_handlers + max_ivor + kvmppc_handler_len);
+
+	return kvm_init(NULL, sizeof(struct kvm_vcpu), THIS_MODULE);
+}
+
+static void __exit kvmppc_booke_exit(void)
+{
+	free_pages(kvmppc_booke_handlers, VCPU_SIZE_ORDER);
+	kvm_exit();
+}
+
+module_init(kvmppc_booke_init)
+module_exit(kvmppc_booke_exit)
diff --git a/trunk/arch/powerpc/kvm/booke_interrupts.S b/trunk/arch/powerpc/kvm/booke_interrupts.S
new file mode 100644
index 000000000000..3b653b5309b8
--- /dev/null
+++ b/trunk/arch/powerpc/kvm/booke_interrupts.S
@@ -0,0 +1,436 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/kvm_asm.h>
+#include <asm/reg.h>
+#include <asm/mmu-44x.h>
+#include <asm/page.h>
+#include <asm/asm-offsets.h>
+
+#define KVMPPC_MSR_MASK (MSR_CE|MSR_EE|MSR_PR|MSR_DE|MSR_ME|MSR_IS|MSR_DS)
+
+#define VCPU_GPR(n)     (VCPU_GPRS + (n * 4))
+
+/* The host stack layout: */
+#define HOST_R1         0 /* Implied by stwu. */
+#define HOST_CALLEE_LR  4
+#define HOST_RUN        8
+/* r2 is special: it holds 'current', and it made nonvolatile in the
+ * kernel with the -ffixed-r2 gcc option. */
+#define HOST_R2         12
+#define HOST_NV_GPRS    16
+#define HOST_NV_GPR(n)  (HOST_NV_GPRS + ((n - 14) * 4))
+#define HOST_MIN_STACK_SIZE (HOST_NV_GPR(31) + 4)
+#define HOST_STACK_SIZE (((HOST_MIN_STACK_SIZE + 15) / 16) * 16) /* Align. */
+#define HOST_STACK_LR   (HOST_STACK_SIZE + 4) /* In caller stack frame. */
+
+#define NEED_INST_MASK ((1<<BOOKE_INTERRUPT_PROGRAM) | \
+                        (1<<BOOKE_INTERRUPT_DTLB_MISS))
+
+#define NEED_DEAR_MASK ((1<<BOOKE_INTERRUPT_DATA_STORAGE) | \
+                        (1<<BOOKE_INTERRUPT_DTLB_MISS))
+
+#define NEED_ESR_MASK ((1<<BOOKE_INTERRUPT_DATA_STORAGE) | \
+                       (1<<BOOKE_INTERRUPT_INST_STORAGE) | \
+                       (1<<BOOKE_INTERRUPT_PROGRAM) | \
+                       (1<<BOOKE_INTERRUPT_DTLB_MISS))
+
+.macro KVM_HANDLER ivor_nr
+_GLOBAL(kvmppc_handler_\ivor_nr)
+	/* Get pointer to vcpu and record exit number. */
+	mtspr	SPRN_SPRG0, r4
+	mfspr	r4, SPRN_SPRG1
+	stw	r5, VCPU_GPR(r5)(r4)
+	stw	r6, VCPU_GPR(r6)(r4)
+	mfctr	r5
+	lis	r6, kvmppc_resume_host@h
+	stw	r5, VCPU_CTR(r4)
+	li	r5, \ivor_nr
+	ori	r6, r6, kvmppc_resume_host@l
+	mtctr	r6
+	bctr
+.endm
+
+_GLOBAL(kvmppc_handlers_start)
+KVM_HANDLER BOOKE_INTERRUPT_CRITICAL
+KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK
+KVM_HANDLER BOOKE_INTERRUPT_DATA_STORAGE
+KVM_HANDLER BOOKE_INTERRUPT_INST_STORAGE
+KVM_HANDLER BOOKE_INTERRUPT_EXTERNAL
+KVM_HANDLER BOOKE_INTERRUPT_ALIGNMENT
+KVM_HANDLER BOOKE_INTERRUPT_PROGRAM
+KVM_HANDLER BOOKE_INTERRUPT_FP_UNAVAIL
+KVM_HANDLER BOOKE_INTERRUPT_SYSCALL
+KVM_HANDLER BOOKE_INTERRUPT_AP_UNAVAIL
+KVM_HANDLER BOOKE_INTERRUPT_DECREMENTER
+KVM_HANDLER BOOKE_INTERRUPT_FIT
+KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG
+KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS
+KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS
+KVM_HANDLER BOOKE_INTERRUPT_DEBUG
+
+_GLOBAL(kvmppc_handler_len)
+	.long kvmppc_handler_1 - kvmppc_handler_0
+
+
+/* Registers:
+ *  SPRG0: guest r4
+ *  r4: vcpu pointer
+ *  r5: KVM exit number
+ */
+_GLOBAL(kvmppc_resume_host)
+	stw	r3, VCPU_GPR(r3)(r4)
+	mfcr	r3
+	stw	r3, VCPU_CR(r4)
+	stw	r7, VCPU_GPR(r7)(r4)
+	stw	r8, VCPU_GPR(r8)(r4)
+	stw	r9, VCPU_GPR(r9)(r4)
+
+	li	r6, 1
+	slw	r6, r6, r5
+
+	/* Save the faulting instruction and all GPRs for emulation. */
+	andi.	r7, r6, NEED_INST_MASK
+	beq	..skip_inst_copy
+	mfspr	r9, SPRN_SRR0
+	mfmsr	r8
+	ori	r7, r8, MSR_DS
+	mtmsr	r7
+	isync
+	lwz	r9, 0(r9)
+	mtmsr	r8
+	isync
+	stw	r9, VCPU_LAST_INST(r4)
+
+	stw	r15, VCPU_GPR(r15)(r4)
+	stw	r16, VCPU_GPR(r16)(r4)
+	stw	r17, VCPU_GPR(r17)(r4)
+	stw	r18, VCPU_GPR(r18)(r4)
+	stw	r19, VCPU_GPR(r19)(r4)
+	stw	r20, VCPU_GPR(r20)(r4)
+	stw	r21, VCPU_GPR(r21)(r4)
+	stw	r22, VCPU_GPR(r22)(r4)
+	stw	r23, VCPU_GPR(r23)(r4)
+	stw	r24, VCPU_GPR(r24)(r4)
+	stw	r25, VCPU_GPR(r25)(r4)
+	stw	r26, VCPU_GPR(r26)(r4)
+	stw	r27, VCPU_GPR(r27)(r4)
+	stw	r28, VCPU_GPR(r28)(r4)
+	stw	r29, VCPU_GPR(r29)(r4)
+	stw	r30, VCPU_GPR(r30)(r4)
+	stw	r31, VCPU_GPR(r31)(r4)
+..skip_inst_copy:
+
+	/* Also grab DEAR and ESR before the host can clobber them. */
+
+	andi.	r7, r6, NEED_DEAR_MASK
+	beq	..skip_dear
+	mfspr	r9, SPRN_DEAR
+	stw	r9, VCPU_FAULT_DEAR(r4)
+..skip_dear:
+
+	andi.	r7, r6, NEED_ESR_MASK
+	beq	..skip_esr
+	mfspr	r9, SPRN_ESR
+	stw	r9, VCPU_FAULT_ESR(r4)
+..skip_esr:
+
+	/* Save remaining volatile guest register state to vcpu. */
+	stw	r0, VCPU_GPR(r0)(r4)
+	stw	r1, VCPU_GPR(r1)(r4)
+	stw	r2, VCPU_GPR(r2)(r4)
+	stw	r10, VCPU_GPR(r10)(r4)
+	stw	r11, VCPU_GPR(r11)(r4)
+	stw	r12, VCPU_GPR(r12)(r4)
+	stw	r13, VCPU_GPR(r13)(r4)
+	stw	r14, VCPU_GPR(r14)(r4) /* We need a NV GPR below. */
+	mflr	r3
+	stw	r3, VCPU_LR(r4)
+	mfxer	r3
+	stw	r3, VCPU_XER(r4)
+	mfspr	r3, SPRN_SPRG0
+	stw	r3, VCPU_GPR(r4)(r4)
+	mfspr	r3, SPRN_SRR0
+	stw	r3, VCPU_PC(r4)
+
+	/* Restore host stack pointer and PID before IVPR, since the host
+	 * exception handlers use them. */
+	lwz	r1, VCPU_HOST_STACK(r4)
+	lwz	r3, VCPU_HOST_PID(r4)
+	mtspr	SPRN_PID, r3
+
+	/* Restore host IVPR before re-enabling interrupts. We cheat and know
+	 * that Linux IVPR is always 0xc0000000. */
+	lis	r3, 0xc000
+	mtspr	SPRN_IVPR, r3
+
+	/* Switch to kernel stack and jump to handler. */
+	LOAD_REG_ADDR(r3, kvmppc_handle_exit)
+	mtctr	r3
+	lwz	r3, HOST_RUN(r1)
+	lwz	r2, HOST_R2(r1)
+	mr	r14, r4 /* Save vcpu pointer. */
+
+	bctrl	/* kvmppc_handle_exit() */
+
+	/* Restore vcpu pointer and the nonvolatiles we used. */
+	mr	r4, r14
+	lwz	r14, VCPU_GPR(r14)(r4)
+
+	/* Sometimes instruction emulation must restore complete GPR state. */
+	andi.	r5, r3, RESUME_FLAG_NV
+	beq	..skip_nv_load
+	lwz	r15, VCPU_GPR(r15)(r4)
+	lwz	r16, VCPU_GPR(r16)(r4)
+	lwz	r17, VCPU_GPR(r17)(r4)
+	lwz	r18, VCPU_GPR(r18)(r4)
+	lwz	r19, VCPU_GPR(r19)(r4)
+	lwz	r20, VCPU_GPR(r20)(r4)
+	lwz	r21, VCPU_GPR(r21)(r4)
+	lwz	r22, VCPU_GPR(r22)(r4)
+	lwz	r23, VCPU_GPR(r23)(r4)
+	lwz	r24, VCPU_GPR(r24)(r4)
+	lwz	r25, VCPU_GPR(r25)(r4)
+	lwz	r26, VCPU_GPR(r26)(r4)
+	lwz	r27, VCPU_GPR(r27)(r4)
+	lwz	r28, VCPU_GPR(r28)(r4)
+	lwz	r29, VCPU_GPR(r29)(r4)
+	lwz	r30, VCPU_GPR(r30)(r4)
+	lwz	r31, VCPU_GPR(r31)(r4)
+..skip_nv_load:
+
+	/* Should we return to the guest? */
+	andi.	r5, r3, RESUME_FLAG_HOST
+	beq	lightweight_exit
+
+	srawi	r3, r3, 2 /* Shift -ERR back down. */
+
+heavyweight_exit:
+	/* Not returning to guest. */
+
+	/* We already saved guest volatile register state; now save the
+	 * non-volatiles. */
+	stw	r15, VCPU_GPR(r15)(r4)
+	stw	r16, VCPU_GPR(r16)(r4)
+	stw	r17, VCPU_GPR(r17)(r4)
+	stw	r18, VCPU_GPR(r18)(r4)
+	stw	r19, VCPU_GPR(r19)(r4)
+	stw	r20, VCPU_GPR(r20)(r4)
+	stw	r21, VCPU_GPR(r21)(r4)
+	stw	r22, VCPU_GPR(r22)(r4)
+	stw	r23, VCPU_GPR(r23)(r4)
+	stw	r24, VCPU_GPR(r24)(r4)
+	stw	r25, VCPU_GPR(r25)(r4)
+	stw	r26, VCPU_GPR(r26)(r4)
+	stw	r27, VCPU_GPR(r27)(r4)
+	stw	r28, VCPU_GPR(r28)(r4)
+	stw	r29, VCPU_GPR(r29)(r4)
+	stw	r30, VCPU_GPR(r30)(r4)
+	stw	r31, VCPU_GPR(r31)(r4)
+
+	/* Load host non-volatile register state from host stack. */
+	lwz	r14, HOST_NV_GPR(r14)(r1)
+	lwz	r15, HOST_NV_GPR(r15)(r1)
+	lwz	r16, HOST_NV_GPR(r16)(r1)
+	lwz	r17, HOST_NV_GPR(r17)(r1)
+	lwz	r18, HOST_NV_GPR(r18)(r1)
+	lwz	r19, HOST_NV_GPR(r19)(r1)
+	lwz	r20, HOST_NV_GPR(r20)(r1)
+	lwz	r21, HOST_NV_GPR(r21)(r1)
+	lwz	r22, HOST_NV_GPR(r22)(r1)
+	lwz	r23, HOST_NV_GPR(r23)(r1)
+	lwz	r24, HOST_NV_GPR(r24)(r1)
+	lwz	r25, HOST_NV_GPR(r25)(r1)
+	lwz	r26, HOST_NV_GPR(r26)(r1)
+	lwz	r27, HOST_NV_GPR(r27)(r1)
+	lwz	r28, HOST_NV_GPR(r28)(r1)
+	lwz	r29, HOST_NV_GPR(r29)(r1)
+	lwz	r30, HOST_NV_GPR(r30)(r1)
+	lwz	r31, HOST_NV_GPR(r31)(r1)
+
+	/* Return to kvm_vcpu_run(). */
+	lwz	r4, HOST_STACK_LR(r1)
+	addi	r1, r1, HOST_STACK_SIZE
+	mtlr	r4
+	/* r3 still contains the return code from kvmppc_handle_exit(). */
+	blr
+
+
+/* Registers:
+ *  r3: kvm_run pointer
+ *  r4: vcpu pointer
+ */
+_GLOBAL(__kvmppc_vcpu_run)
+	stwu	r1, -HOST_STACK_SIZE(r1)
+	stw	r1, VCPU_HOST_STACK(r4)	/* Save stack pointer to vcpu. */
+
+	/* Save host state to stack. */
+	stw	r3, HOST_RUN(r1)
+	mflr	r3
+	stw	r3, HOST_STACK_LR(r1)
+
+	/* Save host non-volatile register state to stack. */
+	stw	r14, HOST_NV_GPR(r14)(r1)
+	stw	r15, HOST_NV_GPR(r15)(r1)
+	stw	r16, HOST_NV_GPR(r16)(r1)
+	stw	r17, HOST_NV_GPR(r17)(r1)
+	stw	r18, HOST_NV_GPR(r18)(r1)
+	stw	r19, HOST_NV_GPR(r19)(r1)
+	stw	r20, HOST_NV_GPR(r20)(r1)
+	stw	r21, HOST_NV_GPR(r21)(r1)
+	stw	r22, HOST_NV_GPR(r22)(r1)
+	stw	r23, HOST_NV_GPR(r23)(r1)
+	stw	r24, HOST_NV_GPR(r24)(r1)
+	stw	r25, HOST_NV_GPR(r25)(r1)
+	stw	r26, HOST_NV_GPR(r26)(r1)
+	stw	r27, HOST_NV_GPR(r27)(r1)
+	stw	r28, HOST_NV_GPR(r28)(r1)
+	stw	r29, HOST_NV_GPR(r29)(r1)
+	stw	r30, HOST_NV_GPR(r30)(r1)
+	stw	r31, HOST_NV_GPR(r31)(r1)
+
+	/* Load guest non-volatiles. */
+	lwz	r14, VCPU_GPR(r14)(r4)
+	lwz	r15, VCPU_GPR(r15)(r4)
+	lwz	r16, VCPU_GPR(r16)(r4)
+	lwz	r17, VCPU_GPR(r17)(r4)
+	lwz	r18, VCPU_GPR(r18)(r4)
+	lwz	r19, VCPU_GPR(r19)(r4)
+	lwz	r20, VCPU_GPR(r20)(r4)
+	lwz	r21, VCPU_GPR(r21)(r4)
+	lwz	r22, VCPU_GPR(r22)(r4)
+	lwz	r23, VCPU_GPR(r23)(r4)
+	lwz	r24, VCPU_GPR(r24)(r4)
+	lwz	r25, VCPU_GPR(r25)(r4)
+	lwz	r26, VCPU_GPR(r26)(r4)
+	lwz	r27, VCPU_GPR(r27)(r4)
+	lwz	r28, VCPU_GPR(r28)(r4)
+	lwz	r29, VCPU_GPR(r29)(r4)
+	lwz	r30, VCPU_GPR(r30)(r4)
+	lwz	r31, VCPU_GPR(r31)(r4)
+
+lightweight_exit:
+	stw	r2, HOST_R2(r1)
+
+	mfspr	r3, SPRN_PID
+	stw	r3, VCPU_HOST_PID(r4)
+	lwz	r3, VCPU_PID(r4)
+	mtspr	SPRN_PID, r3
+
+	/* Prevent all TLB updates. */
+	mfmsr	r5
+	lis	r6, (MSR_EE|MSR_CE|MSR_ME|MSR_DE)@h
+	ori	r6, r6, (MSR_EE|MSR_CE|MSR_ME|MSR_DE)@l
+	andc	r6, r5, r6
+	mtmsr	r6
+
+	/* Save the host's non-pinned TLB mappings, and load the guest mappings
+	 * over them. Leave the host's "pinned" kernel mappings in place. */
+	/* XXX optimization: use generation count to avoid swapping unmodified
+	 * entries. */
+	mfspr	r10, SPRN_MMUCR			/* Save host MMUCR. */
+	lis	r8, tlb_44x_hwater@ha
+	lwz	r8, tlb_44x_hwater@l(r8)
+	addi	r3, r4, VCPU_HOST_TLB - 4
+	addi	r9, r4, VCPU_SHADOW_TLB - 4
+	li	r6, 0
+1:
+	/* Save host entry. */
+	tlbre	r7, r6, PPC44x_TLB_PAGEID
+	mfspr	r5, SPRN_MMUCR
+	stwu	r5, 4(r3)
+	stwu	r7, 4(r3)
+	tlbre	r7, r6, PPC44x_TLB_XLAT
+	stwu	r7, 4(r3)
+	tlbre	r7, r6, PPC44x_TLB_ATTRIB
+	stwu	r7, 4(r3)
+	/* Load guest entry. */
+	lwzu	r7, 4(r9)
+	mtspr	SPRN_MMUCR, r7
+	lwzu	r7, 4(r9)
+	tlbwe	r7, r6, PPC44x_TLB_PAGEID
+	lwzu	r7, 4(r9)
+	tlbwe	r7, r6, PPC44x_TLB_XLAT
+	lwzu	r7, 4(r9)
+	tlbwe	r7, r6, PPC44x_TLB_ATTRIB
+	/* Increment index. */
+	addi	r6, r6, 1
+	cmpw	r6, r8
+	blt	1b
+	mtspr	SPRN_MMUCR, r10			/* Restore host MMUCR. */
+
+	iccci	0, 0 /* XXX hack */
+
+	/* Load some guest volatiles. */
+	lwz	r0, VCPU_GPR(r0)(r4)
+	lwz	r2, VCPU_GPR(r2)(r4)
+	lwz	r9, VCPU_GPR(r9)(r4)
+	lwz	r10, VCPU_GPR(r10)(r4)
+	lwz	r11, VCPU_GPR(r11)(r4)
+	lwz	r12, VCPU_GPR(r12)(r4)
+	lwz	r13, VCPU_GPR(r13)(r4)
+	lwz	r3, VCPU_LR(r4)
+	mtlr	r3
+	lwz	r3, VCPU_XER(r4)
+	mtxer	r3
+
+	/* Switch the IVPR. XXX If we take a TLB miss after this we're screwed,
+	 * so how do we make sure vcpu won't fault? */
+	lis	r8, kvmppc_booke_handlers@ha
+	lwz	r8, kvmppc_booke_handlers@l(r8)
+	mtspr	SPRN_IVPR, r8
+
+	/* Save vcpu pointer for the exception handlers. */
+	mtspr	SPRN_SPRG1, r4
+
+	/* Can't switch the stack pointer until after IVPR is switched,
+	 * because host interrupt handlers would get confused. */
+	lwz	r1, VCPU_GPR(r1)(r4)
+
+	/* XXX handle USPRG0 */
+	/* Host interrupt handlers may have clobbered these guest-readable
+	 * SPRGs, so we need to reload them here with the guest's values. */
+	lwz	r3, VCPU_SPRG4(r4)
+	mtspr	SPRN_SPRG4, r3
+	lwz	r3, VCPU_SPRG5(r4)
+	mtspr	SPRN_SPRG5, r3
+	lwz	r3, VCPU_SPRG6(r4)
+	mtspr	SPRN_SPRG6, r3
+	lwz	r3, VCPU_SPRG7(r4)
+	mtspr	SPRN_SPRG7, r3
+
+	/* Finish loading guest volatiles and jump to guest. */
+	lwz	r3, VCPU_CTR(r4)
+	mtctr	r3
+	lwz	r3, VCPU_CR(r4)
+	mtcr	r3
+	lwz	r5, VCPU_GPR(r5)(r4)
+	lwz	r6, VCPU_GPR(r6)(r4)
+	lwz	r7, VCPU_GPR(r7)(r4)
+	lwz	r8, VCPU_GPR(r8)(r4)
+	lwz	r3, VCPU_PC(r4)
+	mtsrr0	r3
+	lwz	r3, VCPU_MSR(r4)
+	oris	r3, r3, KVMPPC_MSR_MASK@h
+	ori	r3, r3, KVMPPC_MSR_MASK@l
+	mtsrr1	r3
+	lwz	r3, VCPU_GPR(r3)(r4)
+	lwz	r4, VCPU_GPR(r4)(r4)
+	rfi
diff --git a/trunk/arch/powerpc/kvm/emulate.c b/trunk/arch/powerpc/kvm/emulate.c
new file mode 100644
index 000000000000..a03fe0c80698
--- /dev/null
+++ b/trunk/arch/powerpc/kvm/emulate.c
@@ -0,0 +1,760 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#include <linux/jiffies.h>
+#include <linux/timer.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kvm_host.h>
+
+#include <asm/dcr.h>
+#include <asm/dcr-regs.h>
+#include <asm/time.h>
+#include <asm/byteorder.h>
+#include <asm/kvm_ppc.h>
+
+#include "44x_tlb.h"
+
+/* Instruction decoding */
+static inline unsigned int get_op(u32 inst)
+{
+	return inst >> 26;
+}
+
+static inline unsigned int get_xop(u32 inst)
+{
+	return (inst >> 1) & 0x3ff;
+}
+
+static inline unsigned int get_sprn(u32 inst)
+{
+	return ((inst >> 16) & 0x1f) | ((inst >> 6) & 0x3e0);
+}
+
+static inline unsigned int get_dcrn(u32 inst)
+{
+	return ((inst >> 16) & 0x1f) | ((inst >> 6) & 0x3e0);
+}
+
+static inline unsigned int get_rt(u32 inst)
+{
+	return (inst >> 21) & 0x1f;
+}
+
+static inline unsigned int get_rs(u32 inst)
+{
+	return (inst >> 21) & 0x1f;
+}
+
+static inline unsigned int get_ra(u32 inst)
+{
+	return (inst >> 16) & 0x1f;
+}
+
+static inline unsigned int get_rb(u32 inst)
+{
+	return (inst >> 11) & 0x1f;
+}
+
+static inline unsigned int get_rc(u32 inst)
+{
+	return inst & 0x1;
+}
+
+static inline unsigned int get_ws(u32 inst)
+{
+	return (inst >> 11) & 0x1f;
+}
+
+static inline unsigned int get_d(u32 inst)
+{
+	return inst & 0xffff;
+}
+
+static int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
+                             const struct tlbe *tlbe)
+{
+	gpa_t gpa;
+
+	if (!get_tlb_v(tlbe))
+		return 0;
+
+	/* Does it match current guest AS? */
+	/* XXX what about IS != DS? */
+	if (get_tlb_ts(tlbe) != !!(vcpu->arch.msr & MSR_IS))
+		return 0;
+
+	gpa = get_tlb_raddr(tlbe);
+	if (!gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT))
+		/* Mapping is not for RAM. */
+		return 0;
+
+	return 1;
+}
+
+static int kvmppc_emul_tlbwe(struct kvm_vcpu *vcpu, u32 inst)
+{
+	u64 eaddr;
+	u64 raddr;
+	u64 asid;
+	u32 flags;
+	struct tlbe *tlbe;
+	unsigned int ra;
+	unsigned int rs;
+	unsigned int ws;
+	unsigned int index;
+
+	ra = get_ra(inst);
+	rs = get_rs(inst);
+	ws = get_ws(inst);
+
+	index = vcpu->arch.gpr[ra];
+	if (index > PPC44x_TLB_SIZE) {
+		printk("%s: index %d\n", __func__, index);
+		kvmppc_dump_vcpu(vcpu);
+		return EMULATE_FAIL;
+	}
+
+	tlbe = &vcpu->arch.guest_tlb[index];
+
+	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
+	if (tlbe->word0 & PPC44x_TLB_VALID) {
+		eaddr = get_tlb_eaddr(tlbe);
+		asid = (tlbe->word0 & PPC44x_TLB_TS) | tlbe->tid;
+		kvmppc_mmu_invalidate(vcpu, eaddr, asid);
+	}
+
+	switch (ws) {
+	case PPC44x_TLB_PAGEID:
+		tlbe->tid = vcpu->arch.mmucr & 0xff;
+		tlbe->word0 = vcpu->arch.gpr[rs];
+		break;
+
+	case PPC44x_TLB_XLAT:
+		tlbe->word1 = vcpu->arch.gpr[rs];
+		break;
+
+	case PPC44x_TLB_ATTRIB:
+		tlbe->word2 = vcpu->arch.gpr[rs];
+		break;
+
+	default:
+		return EMULATE_FAIL;
+	}
+
+	if (tlbe_is_host_safe(vcpu, tlbe)) {
+		eaddr = get_tlb_eaddr(tlbe);
+		raddr = get_tlb_raddr(tlbe);
+		asid = (tlbe->word0 & PPC44x_TLB_TS) | tlbe->tid;
+		flags = tlbe->word2 & 0xffff;
+
+		/* Create a 4KB mapping on the host. If the guest wanted a
+		 * large page, only the first 4KB is mapped here and the rest
+		 * are mapped on the fly. */
+		kvmppc_mmu_map(vcpu, eaddr, raddr >> PAGE_SHIFT, asid, flags);
+	}
+
+	return EMULATE_DONE;
+}
+
+static void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.tcr & TCR_DIE) {
+		/* The decrementer ticks at the same rate as the timebase, so
+		 * that's how we convert the guest DEC value to the number of
+		 * host ticks. */
+		unsigned long nr_jiffies;
+
+		nr_jiffies = vcpu->arch.dec / tb_ticks_per_jiffy;
+		mod_timer(&vcpu->arch.dec_timer,
+		          get_jiffies_64() + nr_jiffies);
+	} else {
+		del_timer(&vcpu->arch.dec_timer);
+	}
+}
+
+static void kvmppc_emul_rfi(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pc = vcpu->arch.srr0;
+	kvmppc_set_msr(vcpu, vcpu->arch.srr1);
+}
+
+/* XXX to do:
+ * lhax
+ * lhaux
+ * lswx
+ * lswi
+ * stswx
+ * stswi
+ * lha
+ * lhau
+ * lmw
+ * stmw
+ *
+ * XXX is_bigendian should depend on MMU mapping or MSR[LE]
+ */
+int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+	u32 inst = vcpu->arch.last_inst;
+	u32 ea;
+	int ra;
+	int rb;
+	int rc;
+	int rs;
+	int rt;
+	int sprn;
+	int dcrn;
+	enum emulation_result emulated = EMULATE_DONE;
+	int advance = 1;
+
+	switch (get_op(inst)) {
+	case 3:                                                 /* trap */
+		printk("trap!\n");
+		kvmppc_queue_exception(vcpu, BOOKE_INTERRUPT_PROGRAM);
+		advance = 0;
+		break;
+
+	case 19:
+		switch (get_xop(inst)) {
+		case 50:                                        /* rfi */
+			kvmppc_emul_rfi(vcpu);
+			advance = 0;
+			break;
+
+		default:
+			emulated = EMULATE_FAIL;
+			break;
+		}
+		break;
+
+	case 31:
+		switch (get_xop(inst)) {
+
+		case 83:                                        /* mfmsr */
+			rt = get_rt(inst);
+			vcpu->arch.gpr[rt] = vcpu->arch.msr;
+			break;
+
+		case 87:                                        /* lbzx */
+			rt = get_rt(inst);
+			emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
+			break;
+
+		case 131:                                       /* wrtee */
+			rs = get_rs(inst);
+			vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE)
+			                 | (vcpu->arch.gpr[rs] & MSR_EE);
+			break;
+
+		case 146:                                       /* mtmsr */
+			rs = get_rs(inst);
+			kvmppc_set_msr(vcpu, vcpu->arch.gpr[rs]);
+			break;
+
+		case 163:                                       /* wrteei */
+			vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE)
+			                 | (inst & MSR_EE);
+			break;
+
+		case 215:                                       /* stbx */
+			rs = get_rs(inst);
+			emulated = kvmppc_handle_store(run, vcpu,
+			                               vcpu->arch.gpr[rs],
+			                               1, 1);
+			break;
+
+		case 247:                                       /* stbux */
+			rs = get_rs(inst);
+			ra = get_ra(inst);
+			rb = get_rb(inst);
+
+			ea = vcpu->arch.gpr[rb];
+			if (ra)
+				ea += vcpu->arch.gpr[ra];
+
+			emulated = kvmppc_handle_store(run, vcpu,
+			                               vcpu->arch.gpr[rs],
+			                               1, 1);
+			vcpu->arch.gpr[rs] = ea;
+			break;
+
+		case 279:                                       /* lhzx */
+			rt = get_rt(inst);
+			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
+			break;
+
+		case 311:                                       /* lhzux */
+			rt = get_rt(inst);
+			ra = get_ra(inst);
+			rb = get_rb(inst);
+
+			ea = vcpu->arch.gpr[rb];
+			if (ra)
+				ea += vcpu->arch.gpr[ra];
+
+			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
+			vcpu->arch.gpr[ra] = ea;
+			break;
+
+		case 323:                                       /* mfdcr */
+			dcrn = get_dcrn(inst);
+			rt = get_rt(inst);
+
+			/* The guest may access CPR0 registers to determine the timebase
+			 * frequency, and it must know the real host frequency because it
+			 * can directly access the timebase registers.
+			 *
+			 * It would be possible to emulate those accesses in userspace,
+			 * but userspace can really only figure out the end frequency.
+			 * We could decompose that into the factors that compute it, but
+			 * that's tricky math, and it's easier to just report the real
+			 * CPR0 values.
+			 */
+			switch (dcrn) {
+			case DCRN_CPR0_CONFIG_ADDR:
+				vcpu->arch.gpr[rt] = vcpu->arch.cpr0_cfgaddr;
+				break;
+			case DCRN_CPR0_CONFIG_DATA:
+				local_irq_disable();
+				mtdcr(DCRN_CPR0_CONFIG_ADDR,
+				      vcpu->arch.cpr0_cfgaddr);
+				vcpu->arch.gpr[rt] = mfdcr(DCRN_CPR0_CONFIG_DATA);
+				local_irq_enable();
+				break;
+			default:
+				run->dcr.dcrn = dcrn;
+				run->dcr.data =  0;
+				run->dcr.is_write = 0;
+				vcpu->arch.io_gpr = rt;
+				vcpu->arch.dcr_needed = 1;
+				emulated = EMULATE_DO_DCR;
+			}
+
+			break;
+
+		case 339:                                       /* mfspr */
+			sprn = get_sprn(inst);
+			rt = get_rt(inst);
+
+			switch (sprn) {
+			case SPRN_SRR0:
+				vcpu->arch.gpr[rt] = vcpu->arch.srr0; break;
+			case SPRN_SRR1:
+				vcpu->arch.gpr[rt] = vcpu->arch.srr1; break;
+			case SPRN_MMUCR:
+				vcpu->arch.gpr[rt] = vcpu->arch.mmucr; break;
+			case SPRN_PID:
+				vcpu->arch.gpr[rt] = vcpu->arch.pid; break;
+			case SPRN_IVPR:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivpr; break;
+			case SPRN_CCR0:
+				vcpu->arch.gpr[rt] = vcpu->arch.ccr0; break;
+			case SPRN_CCR1:
+				vcpu->arch.gpr[rt] = vcpu->arch.ccr1; break;
+			case SPRN_PVR:
+				vcpu->arch.gpr[rt] = vcpu->arch.pvr; break;
+			case SPRN_DEAR:
+				vcpu->arch.gpr[rt] = vcpu->arch.dear; break;
+			case SPRN_ESR:
+				vcpu->arch.gpr[rt] = vcpu->arch.esr; break;
+			case SPRN_DBCR0:
+				vcpu->arch.gpr[rt] = vcpu->arch.dbcr0; break;
+			case SPRN_DBCR1:
+				vcpu->arch.gpr[rt] = vcpu->arch.dbcr1; break;
+
+			/* Note: mftb and TBRL/TBWL are user-accessible, so
+			 * the guest can always access the real TB anyways.
+			 * In fact, we probably will never see these traps. */
+			case SPRN_TBWL:
+				vcpu->arch.gpr[rt] = mftbl(); break;
+			case SPRN_TBWU:
+				vcpu->arch.gpr[rt] = mftbu(); break;
+
+			case SPRN_SPRG0:
+				vcpu->arch.gpr[rt] = vcpu->arch.sprg0; break;
+			case SPRN_SPRG1:
+				vcpu->arch.gpr[rt] = vcpu->arch.sprg1; break;
+			case SPRN_SPRG2:
+				vcpu->arch.gpr[rt] = vcpu->arch.sprg2; break;
+			case SPRN_SPRG3:
+				vcpu->arch.gpr[rt] = vcpu->arch.sprg3; break;
+			/* Note: SPRG4-7 are user-readable, so we don't get
+			 * a trap. */
+
+			case SPRN_IVOR0:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[0]; break;
+			case SPRN_IVOR1:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[1]; break;
+			case SPRN_IVOR2:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[2]; break;
+			case SPRN_IVOR3:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[3]; break;
+			case SPRN_IVOR4:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[4]; break;
+			case SPRN_IVOR5:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[5]; break;
+			case SPRN_IVOR6:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[6]; break;
+			case SPRN_IVOR7:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[7]; break;
+			case SPRN_IVOR8:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[8]; break;
+			case SPRN_IVOR9:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[9]; break;
+			case SPRN_IVOR10:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[10]; break;
+			case SPRN_IVOR11:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[11]; break;
+			case SPRN_IVOR12:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[12]; break;
+			case SPRN_IVOR13:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[13]; break;
+			case SPRN_IVOR14:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[14]; break;
+			case SPRN_IVOR15:
+				vcpu->arch.gpr[rt] = vcpu->arch.ivor[15]; break;
+
+			default:
+				printk("mfspr: unknown spr %x\n", sprn);
+				vcpu->arch.gpr[rt] = 0;
+				break;
+			}
+			break;
+
+		case 407:                                       /* sthx */
+			rs = get_rs(inst);
+			ra = get_ra(inst);
+			rb = get_rb(inst);
+
+			emulated = kvmppc_handle_store(run, vcpu,
+			                               vcpu->arch.gpr[rs],
+			                               2, 1);
+			break;
+
+		case 439:                                       /* sthux */
+			rs = get_rs(inst);
+			ra = get_ra(inst);
+			rb = get_rb(inst);
+
+			ea = vcpu->arch.gpr[rb];
+			if (ra)
+				ea += vcpu->arch.gpr[ra];
+
+			emulated = kvmppc_handle_store(run, vcpu,
+			                               vcpu->arch.gpr[rs],
+			                               2, 1);
+			vcpu->arch.gpr[ra] = ea;
+			break;
+
+		case 451:                                       /* mtdcr */
+			dcrn = get_dcrn(inst);
+			rs = get_rs(inst);
+
+			/* emulate some access in kernel */
+			switch (dcrn) {
+			case DCRN_CPR0_CONFIG_ADDR:
+				vcpu->arch.cpr0_cfgaddr = vcpu->arch.gpr[rs];
+				break;
+			default:
+				run->dcr.dcrn = dcrn;
+				run->dcr.data = vcpu->arch.gpr[rs];
+				run->dcr.is_write = 1;
+				vcpu->arch.dcr_needed = 1;
+				emulated = EMULATE_DO_DCR;
+			}
+
+			break;
+
+		case 467:                                       /* mtspr */
+			sprn = get_sprn(inst);
+			rs = get_rs(inst);
+			switch (sprn) {
+			case SPRN_SRR0:
+				vcpu->arch.srr0 = vcpu->arch.gpr[rs]; break;
+			case SPRN_SRR1:
+				vcpu->arch.srr1 = vcpu->arch.gpr[rs]; break;
+			case SPRN_MMUCR:
+				vcpu->arch.mmucr = vcpu->arch.gpr[rs]; break;
+			case SPRN_PID:
+				vcpu->arch.pid = vcpu->arch.gpr[rs]; break;
+			case SPRN_CCR0:
+				vcpu->arch.ccr0 = vcpu->arch.gpr[rs]; break;
+			case SPRN_CCR1:
+				vcpu->arch.ccr1 = vcpu->arch.gpr[rs]; break;
+			case SPRN_DEAR:
+				vcpu->arch.dear = vcpu->arch.gpr[rs]; break;
+			case SPRN_ESR:
+				vcpu->arch.esr = vcpu->arch.gpr[rs]; break;
+			case SPRN_DBCR0:
+				vcpu->arch.dbcr0 = vcpu->arch.gpr[rs]; break;
+			case SPRN_DBCR1:
+				vcpu->arch.dbcr1 = vcpu->arch.gpr[rs]; break;
+
+			/* XXX We need to context-switch the timebase for
+			 * watchdog and FIT. */
+			case SPRN_TBWL: break;
+			case SPRN_TBWU: break;
+
+			case SPRN_DEC:
+				vcpu->arch.dec = vcpu->arch.gpr[rs];
+				kvmppc_emulate_dec(vcpu);
+				break;
+
+			case SPRN_TSR:
+				vcpu->arch.tsr &= ~vcpu->arch.gpr[rs]; break;
+
+			case SPRN_TCR:
+				vcpu->arch.tcr = vcpu->arch.gpr[rs];
+				kvmppc_emulate_dec(vcpu);
+				break;
+
+			case SPRN_SPRG0:
+				vcpu->arch.sprg0 = vcpu->arch.gpr[rs]; break;
+			case SPRN_SPRG1:
+				vcpu->arch.sprg1 = vcpu->arch.gpr[rs]; break;
+			case SPRN_SPRG2:
+				vcpu->arch.sprg2 = vcpu->arch.gpr[rs]; break;
+			case SPRN_SPRG3:
+				vcpu->arch.sprg3 = vcpu->arch.gpr[rs]; break;
+
+			/* Note: SPRG4-7 are user-readable. These values are
+			 * loaded into the real SPRGs when resuming the
+			 * guest. */
+			case SPRN_SPRG4:
+				vcpu->arch.sprg4 = vcpu->arch.gpr[rs]; break;
+			case SPRN_SPRG5:
+				vcpu->arch.sprg5 = vcpu->arch.gpr[rs]; break;
+			case SPRN_SPRG6:
+				vcpu->arch.sprg6 = vcpu->arch.gpr[rs]; break;
+			case SPRN_SPRG7:
+				vcpu->arch.sprg7 = vcpu->arch.gpr[rs]; break;
+
+			case SPRN_IVPR:
+				vcpu->arch.ivpr = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR0:
+				vcpu->arch.ivor[0] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR1:
+				vcpu->arch.ivor[1] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR2:
+				vcpu->arch.ivor[2] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR3:
+				vcpu->arch.ivor[3] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR4:
+				vcpu->arch.ivor[4] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR5:
+				vcpu->arch.ivor[5] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR6:
+				vcpu->arch.ivor[6] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR7:
+				vcpu->arch.ivor[7] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR8:
+				vcpu->arch.ivor[8] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR9:
+				vcpu->arch.ivor[9] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR10:
+				vcpu->arch.ivor[10] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR11:
+				vcpu->arch.ivor[11] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR12:
+				vcpu->arch.ivor[12] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR13:
+				vcpu->arch.ivor[13] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR14:
+				vcpu->arch.ivor[14] = vcpu->arch.gpr[rs]; break;
+			case SPRN_IVOR15:
+				vcpu->arch.ivor[15] = vcpu->arch.gpr[rs]; break;
+
+			default:
+				printk("mtspr: unknown spr %x\n", sprn);
+				emulated = EMULATE_FAIL;
+				break;
+			}
+			break;
+
+		case 470:                                       /* dcbi */
+			/* Do nothing. The guest is performing dcbi because
+			 * hardware DMA is not snooped by the dcache, but
+			 * emulated DMA either goes through the dcache as
+			 * normal writes, or the host kernel has handled dcache
+			 * coherence. */
+			break;
+
+		case 534:                                       /* lwbrx */
+			rt = get_rt(inst);
+			emulated = kvmppc_handle_load(run, vcpu, rt, 4, 0);
+			break;
+
+		case 566:                                       /* tlbsync */
+			break;
+
+		case 662:                                       /* stwbrx */
+			rs = get_rs(inst);
+			ra = get_ra(inst);
+			rb = get_rb(inst);
+
+			emulated = kvmppc_handle_store(run, vcpu,
+			                               vcpu->arch.gpr[rs],
+			                               4, 0);
+			break;
+
+		case 978:                                       /* tlbwe */
+			emulated = kvmppc_emul_tlbwe(vcpu, inst);
+			break;
+
+		case 914:       {                               /* tlbsx */
+			int index;
+			unsigned int as = get_mmucr_sts(vcpu);
+			unsigned int pid = get_mmucr_stid(vcpu);
+
+			rt = get_rt(inst);
+			ra = get_ra(inst);
+			rb = get_rb(inst);
+			rc = get_rc(inst);
+
+			ea = vcpu->arch.gpr[rb];
+			if (ra)
+				ea += vcpu->arch.gpr[ra];
+
+			index = kvmppc_44x_tlb_index(vcpu, ea, pid, as);
+			if (rc) {
+				if (index < 0)
+					vcpu->arch.cr &= ~0x20000000;
+				else
+					vcpu->arch.cr |= 0x20000000;
+			}
+			vcpu->arch.gpr[rt] = index;
+
+			}
+			break;
+
+		case 790:                                       /* lhbrx */
+			rt = get_rt(inst);
+			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 0);
+			break;
+
+		case 918:                                       /* sthbrx */
+			rs = get_rs(inst);
+			ra = get_ra(inst);
+			rb = get_rb(inst);
+
+			emulated = kvmppc_handle_store(run, vcpu,
+			                               vcpu->arch.gpr[rs],
+			                               2, 0);
+			break;
+
+		case 966:                                       /* iccci */
+			break;
+
+		default:
+			printk("unknown: op %d xop %d\n", get_op(inst),
+				get_xop(inst));
+			emulated = EMULATE_FAIL;
+			break;
+		}
+		break;
+
+	case 32:                                                /* lwz */
+		rt = get_rt(inst);
+		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
+		break;
+
+	case 33:                                                /* lwzu */
+		ra = get_ra(inst);
+		rt = get_rt(inst);
+		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
+		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+		break;
+
+	case 34:                                                /* lbz */
+		rt = get_rt(inst);
+		emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
+		break;
+
+	case 35:                                                /* lbzu */
+		ra = get_ra(inst);
+		rt = get_rt(inst);
+		emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
+		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+		break;
+
+	case 36:                                                /* stw */
+		rs = get_rs(inst);
+		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+		                               4, 1);
+		break;
+
+	case 37:                                                /* stwu */
+		ra = get_ra(inst);
+		rs = get_rs(inst);
+		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+		                               4, 1);
+		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+		break;
+
+	case 38:                                                /* stb */
+		rs = get_rs(inst);
+		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+		                               1, 1);
+		break;
+
+	case 39:                                                /* stbu */
+		ra = get_ra(inst);
+		rs = get_rs(inst);
+		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+		                               1, 1);
+		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+		break;
+
+	case 40:                                                /* lhz */
+		rt = get_rt(inst);
+		emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
+		break;
+
+	case 41:                                                /* lhzu */
+		ra = get_ra(inst);
+		rt = get_rt(inst);
+		emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
+		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+		break;
+
+	case 44:                                                /* sth */
+		rs = get_rs(inst);
+		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+		                               2, 1);
+		break;
+
+	case 45:                                                /* sthu */
+		ra = get_ra(inst);
+		rs = get_rs(inst);
+		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+		                               2, 1);
+		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+		break;
+
+	default:
+		printk("unknown op %d\n", get_op(inst));
+		emulated = EMULATE_FAIL;
+		break;
+	}
+
+	if (advance)
+		vcpu->arch.pc += 4; /* Advance past emulated instruction. */
+
+	return emulated;
+}
diff --git a/trunk/arch/powerpc/kvm/powerpc.c b/trunk/arch/powerpc/kvm/powerpc.c
new file mode 100644
index 000000000000..bad40bd2d3ac
--- /dev/null
+++ b/trunk/arch/powerpc/kvm/powerpc.c
@@ -0,0 +1,436 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ *          Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/fs.h>
+#include <asm/cputable.h>
+#include <asm/uaccess.h>
+#include <asm/kvm_ppc.h>
+
+
+gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
+{
+	return gfn;
+}
+
+int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
+{
+	/* XXX implement me */
+	return 0;
+}
+
+int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
+{
+	return 1;
+}
+
+
+int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+	enum emulation_result er;
+	int r;
+
+	er = kvmppc_emulate_instruction(run, vcpu);
+	switch (er) {
+	case EMULATE_DONE:
+		/* Future optimization: only reload non-volatiles if they were
+		 * actually modified. */
+		r = RESUME_GUEST_NV;
+		break;
+	case EMULATE_DO_MMIO:
+		run->exit_reason = KVM_EXIT_MMIO;
+		/* We must reload nonvolatiles because "update" load/store
+		 * instructions modify register state. */
+		/* Future optimization: only reload non-volatiles if they were
+		 * actually modified. */
+		r = RESUME_HOST_NV;
+		break;
+	case EMULATE_FAIL:
+		/* XXX Deliver Program interrupt to guest. */
+		printk(KERN_EMERG "%s: emulation failed (%08x)\n", __func__,
+		       vcpu->arch.last_inst);
+		r = RESUME_HOST;
+		break;
+	default:
+		BUG();
+	}
+
+	return r;
+}
+
+void kvm_arch_hardware_enable(void *garbage)
+{
+}
+
+void kvm_arch_hardware_disable(void *garbage)
+{
+}
+
+int kvm_arch_hardware_setup(void)
+{
+	return 0;
+}
+
+void kvm_arch_hardware_unsetup(void)
+{
+}
+
+void kvm_arch_check_processor_compat(void *rtn)
+{
+	int r;
+
+	if (strcmp(cur_cpu_spec->platform, "ppc440") == 0)
+		r = 0;
+	else
+		r = -ENOTSUPP;
+
+	*(int *)rtn = r;
+}
+
+struct kvm *kvm_arch_create_vm(void)
+{
+	struct kvm *kvm;
+
+	kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
+	if (!kvm)
+		return ERR_PTR(-ENOMEM);
+
+	return kvm;
+}
+
+static void kvmppc_free_vcpus(struct kvm *kvm)
+{
+	unsigned int i;
+
+	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+		if (kvm->vcpus[i]) {
+			kvm_arch_vcpu_free(kvm->vcpus[i]);
+			kvm->vcpus[i] = NULL;
+		}
+	}
+}
+
+void kvm_arch_destroy_vm(struct kvm *kvm)
+{
+	kvmppc_free_vcpus(kvm);
+	kvm_free_physmem(kvm);
+	kfree(kvm);
+}
+
+int kvm_dev_ioctl_check_extension(long ext)
+{
+	int r;
+
+	switch (ext) {
+	case KVM_CAP_USER_MEMORY:
+		r = 1;
+		break;
+	default:
+		r = 0;
+		break;
+	}
+	return r;
+
+}
+
+long kvm_arch_dev_ioctl(struct file *filp,
+                        unsigned int ioctl, unsigned long arg)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_set_memory_region(struct kvm *kvm,
+                               struct kvm_userspace_memory_region *mem,
+                               struct kvm_memory_slot old,
+                               int user_alloc)
+{
+	return 0;
+}
+
+struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
+{
+	struct kvm_vcpu *vcpu;
+	int err;
+
+	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+	if (!vcpu) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = kvm_vcpu_init(vcpu, kvm, id);
+	if (err)
+		goto free_vcpu;
+
+	return vcpu;
+
+free_vcpu:
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
+out:
+	return ERR_PTR(err);
+}
+
+void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
+{
+	kvm_vcpu_uninit(vcpu);
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
+}
+
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	kvm_arch_vcpu_free(vcpu);
+}
+
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+	unsigned int priority = exception_priority[BOOKE_INTERRUPT_DECREMENTER];
+
+	return test_bit(priority, &vcpu->arch.pending_exceptions);
+}
+
+static void kvmppc_decrementer_func(unsigned long data)
+{
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
+
+	kvmppc_queue_exception(vcpu, BOOKE_INTERRUPT_DECREMENTER);
+}
+
+int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	setup_timer(&vcpu->arch.dec_timer, kvmppc_decrementer_func,
+	            (unsigned long)vcpu);
+
+	return 0;
+}
+
+void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+}
+
+void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
+void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
+{
+}
+
+void decache_vcpus_on_cpu(int cpu)
+{
+}
+
+int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
+                                    struct kvm_debug_guest *dbg)
+{
+	return -ENOTSUPP;
+}
+
+static void kvmppc_complete_dcr_load(struct kvm_vcpu *vcpu,
+                                     struct kvm_run *run)
+{
+	u32 *gpr = &vcpu->arch.gpr[vcpu->arch.io_gpr];
+	*gpr = run->dcr.data;
+}
+
+static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
+                                      struct kvm_run *run)
+{
+	u32 *gpr = &vcpu->arch.gpr[vcpu->arch.io_gpr];
+
+	if (run->mmio.len > sizeof(*gpr)) {
+		printk(KERN_ERR "bad MMIO length: %d\n", run->mmio.len);
+		return;
+	}
+
+	if (vcpu->arch.mmio_is_bigendian) {
+		switch (run->mmio.len) {
+		case 4: *gpr = *(u32 *)run->mmio.data; break;
+		case 2: *gpr = *(u16 *)run->mmio.data; break;
+		case 1: *gpr = *(u8 *)run->mmio.data; break;
+		}
+	} else {
+		/* Convert BE data from userland back to LE. */
+		switch (run->mmio.len) {
+		case 4: *gpr = ld_le32((u32 *)run->mmio.data); break;
+		case 2: *gpr = ld_le16((u16 *)run->mmio.data); break;
+		case 1: *gpr = *(u8 *)run->mmio.data; break;
+		}
+	}
+}
+
+int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                       unsigned int rt, unsigned int bytes, int is_bigendian)
+{
+	if (bytes > sizeof(run->mmio.data)) {
+		printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__,
+		       run->mmio.len);
+	}
+
+	run->mmio.phys_addr = vcpu->arch.paddr_accessed;
+	run->mmio.len = bytes;
+	run->mmio.is_write = 0;
+
+	vcpu->arch.io_gpr = rt;
+	vcpu->arch.mmio_is_bigendian = is_bigendian;
+	vcpu->mmio_needed = 1;
+	vcpu->mmio_is_write = 0;
+
+	return EMULATE_DO_MMIO;
+}
+
+int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                        u32 val, unsigned int bytes, int is_bigendian)
+{
+	void *data = run->mmio.data;
+
+	if (bytes > sizeof(run->mmio.data)) {
+		printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__,
+		       run->mmio.len);
+	}
+
+	run->mmio.phys_addr = vcpu->arch.paddr_accessed;
+	run->mmio.len = bytes;
+	run->mmio.is_write = 1;
+	vcpu->mmio_needed = 1;
+	vcpu->mmio_is_write = 1;
+
+	/* Store the value at the lowest bytes in 'data'. */
+	if (is_bigendian) {
+		switch (bytes) {
+		case 4: *(u32 *)data = val; break;
+		case 2: *(u16 *)data = val; break;
+		case 1: *(u8  *)data = val; break;
+		}
+	} else {
+		/* Store LE value into 'data'. */
+		switch (bytes) {
+		case 4: st_le32(data, val); break;
+		case 2: st_le16(data, val); break;
+		case 1: *(u8 *)data = val; break;
+		}
+	}
+
+	return EMULATE_DO_MMIO;
+}
+
+int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	int r;
+	sigset_t sigsaved;
+
+	if (vcpu->sigset_active)
+		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+
+	if (vcpu->mmio_needed) {
+		if (!vcpu->mmio_is_write)
+			kvmppc_complete_mmio_load(vcpu, run);
+		vcpu->mmio_needed = 0;
+	} else if (vcpu->arch.dcr_needed) {
+		if (!vcpu->arch.dcr_is_write)
+			kvmppc_complete_dcr_load(vcpu, run);
+		vcpu->arch.dcr_needed = 0;
+	}
+
+	kvmppc_check_and_deliver_interrupts(vcpu);
+
+	local_irq_disable();
+	kvm_guest_enter();
+	r = __kvmppc_vcpu_run(run, vcpu);
+	kvm_guest_exit();
+	local_irq_enable();
+
+	if (vcpu->sigset_active)
+		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+	return r;
+}
+
+int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
+{
+	kvmppc_queue_exception(vcpu, BOOKE_INTERRUPT_EXTERNAL);
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+                                    struct kvm_mp_state *mp_state)
+{
+	return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+                                    struct kvm_mp_state *mp_state)
+{
+	return -EINVAL;
+}
+
+long kvm_arch_vcpu_ioctl(struct file *filp,
+                         unsigned int ioctl, unsigned long arg)
+{
+	struct kvm_vcpu *vcpu = filp->private_data;
+	void __user *argp = (void __user *)arg;
+	long r;
+
+	switch (ioctl) {
+	case KVM_INTERRUPT: {
+		struct kvm_interrupt irq;
+		r = -EFAULT;
+		if (copy_from_user(&irq, argp, sizeof(irq)))
+			goto out;
+		r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
+		break;
+	}
+	default:
+		r = -EINVAL;
+	}
+
+out:
+	return r;
+}
+
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
+{
+	return -ENOTSUPP;
+}
+
+long kvm_arch_vm_ioctl(struct file *filp,
+                       unsigned int ioctl, unsigned long arg)
+{
+	long r;
+
+	switch (ioctl) {
+	default:
+		r = -EINVAL;
+	}
+
+	return r;
+}
+
+int kvm_arch_init(void *opaque)
+{
+	return 0;
+}
+
+void kvm_arch_exit(void)
+{
+}
diff --git a/trunk/arch/powerpc/mm/mem.c b/trunk/arch/powerpc/mm/mem.c
index 5ccb579b81e4..f67e118116fa 100644
--- a/trunk/arch/powerpc/mm/mem.c
+++ b/trunk/arch/powerpc/mm/mem.c
@@ -110,15 +110,6 @@ EXPORT_SYMBOL(phys_mem_access_prot);
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 
-void online_page(struct page *page)
-{
-	ClearPageReserved(page);
-	init_page_count(page);
-	__free_page(page);
-	totalram_pages++;
-	num_physpages++;
-}
-
 #ifdef CONFIG_NUMA
 int memory_add_physaddr_to_nid(u64 start)
 {
@@ -163,19 +154,35 @@ int remove_memory(u64 start, u64 size)
 
 /*
  * walk_memory_resource() needs to make sure there is no holes in a given
- * memory range. On PPC64, since this range comes from /sysfs, the range
- * is guaranteed to be valid, non-overlapping and can not contain any
- * holes. By the time we get here (memory add or remove), /proc/device-tree
- * is updated and correct. Only reason we need to check against device-tree
- * would be if we allow user-land to specify a memory range through a
- * system call/ioctl etc. instead of doing offline/online through /sysfs.
+ * memory range.  PPC64 does not maintain the memory layout in /proc/iomem.
+ * Instead it maintains it in lmb.memory structures.  Walk through the
+ * memory regions, find holes and callback for contiguous regions.
  */
 int
 walk_memory_resource(unsigned long start_pfn, unsigned long nr_pages, void *arg,
 			int (*func)(unsigned long, unsigned long, void *))
 {
-	return  (*func)(start_pfn, nr_pages, arg);
+	struct lmb_property res;
+	unsigned long pfn, len;
+	u64 end;
+	int ret = -1;
+
+	res.base = (u64) start_pfn << PAGE_SHIFT;
+	res.size = (u64) nr_pages << PAGE_SHIFT;
+
+	end = res.base + res.size - 1;
+	while ((res.base < end) && (lmb_find(&res) >= 0)) {
+		pfn = (unsigned long)(res.base >> PAGE_SHIFT);
+		len = (unsigned long)(res.size >> PAGE_SHIFT);
+		ret = (*func)(pfn, len, arg);
+		if (ret)
+			break;
+		res.base += (res.size + 1);
+		res.size = (end - res.base + 1);
+	}
+	return ret;
 }
+EXPORT_SYMBOL_GPL(walk_memory_resource);
 
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
diff --git a/trunk/arch/powerpc/platforms/86xx/Kconfig b/trunk/arch/powerpc/platforms/86xx/Kconfig
index 7442c58d44f5..053f49a1dcae 100644
--- a/trunk/arch/powerpc/platforms/86xx/Kconfig
+++ b/trunk/arch/powerpc/platforms/86xx/Kconfig
@@ -8,6 +8,7 @@ config MPC8641_HPCN
 	select PPC_I8259
 	select DEFAULT_UIMAGE
 	select FSL_ULI1575
+	select HAS_RAPIDIO
 	help
 	  This option enables support for the MPC8641 HPCN board.
 
diff --git a/trunk/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/trunk/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
index 18b8ebe930d5..5e1e8cf14e75 100644
--- a/trunk/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
+++ b/trunk/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
@@ -3,11 +3,12 @@
  *
  * Initial author: Xianghua Xiao <x.xiao@freescale.com>
  * Recode: Jason Jin <jason.jin@freescale.com>
+ *         York Sun <yorksun@freescale.com>
  *
  * Rewrite the interrupt routing. remove the 8259PIC support,
  * All the integrated device in ULI use sideband interrupt.
  *
- * Copyright 2007 Freescale Semiconductor Inc.
+ * Copyright 2008 Freescale Semiconductor Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -38,6 +39,8 @@
 #include <sysdev/fsl_pci.h>
 #include <sysdev/fsl_soc.h>
 
+static unsigned char *pixis_bdcfg0, *pixis_arch;
+
 static struct of_device_id __initdata mpc8610_ids[] = {
 	{ .compatible = "fsl,mpc8610-immr", },
 	{}
@@ -52,8 +55,7 @@ static int __init mpc8610_declare_of_platform_devices(void)
 }
 machine_device_initcall(mpc86xx_hpcd, mpc8610_declare_of_platform_devices);
 
-static void __init
-mpc86xx_hpcd_init_irq(void)
+static void __init mpc86xx_hpcd_init_irq(void)
 {
 	struct mpic *mpic1;
 	struct device_node *np;
@@ -161,12 +163,159 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AL, 0x5229, quirk_uli5229);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, 0x5288, final_uli5288);
 #endif /* CONFIG_PCI */
 
-static void __init
-mpc86xx_hpcd_setup_arch(void)
+#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+
+static u32 get_busfreq(void)
 {
-#ifdef CONFIG_PCI
-	struct device_node *np;
+	struct device_node *node;
+
+	u32 fs_busfreq = 0;
+	node = of_find_node_by_type(NULL, "cpu");
+	if (node) {
+		unsigned int size;
+		const unsigned int *prop =
+			of_get_property(node, "bus-frequency", &size);
+		if (prop)
+			fs_busfreq = *prop;
+		of_node_put(node);
+	};
+	return fs_busfreq;
+}
+
+unsigned int mpc8610hpcd_get_pixel_format(unsigned int bits_per_pixel,
+						int monitor_port)
+{
+	static const unsigned long pixelformat[][3] = {
+		{0x88882317, 0x88083218, 0x65052119},
+		{0x88883316, 0x88082219, 0x65053118},
+	};
+	unsigned int pix_fmt, arch_monitor;
+
+	arch_monitor = ((*pixis_arch == 0x01) && (monitor_port == 0))? 0 : 1;
+		/* DVI port for board version 0x01 */
+
+	if (bits_per_pixel == 32)
+		pix_fmt = pixelformat[arch_monitor][0];
+	else if (bits_per_pixel == 24)
+		pix_fmt = pixelformat[arch_monitor][1];
+	else if (bits_per_pixel == 16)
+		pix_fmt = pixelformat[arch_monitor][2];
+	else
+		pix_fmt = pixelformat[1][0];
+
+	return pix_fmt;
+}
+
+void mpc8610hpcd_set_gamma_table(int monitor_port, char *gamma_table_base)
+{
+	int i;
+	if (monitor_port == 2) {		/* dual link LVDS */
+		for (i = 0; i < 256*3; i++)
+			gamma_table_base[i] = (gamma_table_base[i] << 2) |
+					 ((gamma_table_base[i] >> 6) & 0x03);
+	}
+}
+
+void mpc8610hpcd_set_monitor_port(int monitor_port)
+{
+	static const u8 bdcfg[] = {0xBD, 0xB5, 0xA5};
+	if (monitor_port < 3)
+		*pixis_bdcfg0 = bdcfg[monitor_port];
+}
+
+void mpc8610hpcd_set_pixel_clock(unsigned int pixclock)
+{
+	u32 __iomem *clkdvdr;
+	u32 temp;
+	/* variables for pixel clock calcs */
+	ulong  bestval, bestfreq, speed_ccb, minpixclock, maxpixclock;
+	ulong pixval;
+	long err;
+	int i;
+
+	clkdvdr = ioremap(get_immrbase() + 0xe0800, sizeof(u32));
+	if (!clkdvdr) {
+		printk(KERN_ERR "Err: can't map clock divider register!\n");
+		return;
+	}
+
+	/* Pixel Clock configuration */
+	pr_debug("DIU: Bus Frequency = %d\n", get_busfreq());
+	speed_ccb = get_busfreq();
+
+	/* Calculate the pixel clock with the smallest error */
+	/* calculate the following in steps to avoid overflow */
+	pr_debug("DIU pixclock in ps - %d\n", pixclock);
+	temp = 1000000000/pixclock;
+	temp *= 1000;
+	pixclock = temp;
+	pr_debug("DIU pixclock freq - %u\n", pixclock);
+
+	temp = pixclock * 5 / 100;
+	pr_debug("deviation = %d\n", temp);
+	minpixclock = pixclock - temp;
+	maxpixclock = pixclock + temp;
+	pr_debug("DIU minpixclock - %lu\n", minpixclock);
+	pr_debug("DIU maxpixclock - %lu\n", maxpixclock);
+	pixval = speed_ccb/pixclock;
+	pr_debug("DIU pixval = %lu\n", pixval);
+
+	err = 100000000;
+	bestval = pixval;
+	pr_debug("DIU bestval = %lu\n", bestval);
+
+	bestfreq = 0;
+	for (i = -1; i <= 1; i++) {
+		temp = speed_ccb / ((pixval+i) + 1);
+		pr_debug("DIU test pixval i= %d, pixval=%lu, temp freq. = %u\n",
+							i, pixval, temp);
+		if ((temp < minpixclock) || (temp > maxpixclock))
+			pr_debug("DIU exceeds monitor range (%lu to %lu)\n",
+				minpixclock, maxpixclock);
+		else if (abs(temp - pixclock) < err) {
+		  pr_debug("Entered the else if block %d\n", i);
+			err = abs(temp - pixclock);
+			bestval = pixval+i;
+			bestfreq = temp;
+		}
+	}
+
+	pr_debug("DIU chose = %lx\n", bestval);
+	pr_debug("DIU error = %ld\n NomPixClk ", err);
+	pr_debug("DIU: Best Freq = %lx\n", bestfreq);
+	/* Modify PXCLK in GUTS CLKDVDR */
+	pr_debug("DIU: Current value of CLKDVDR = 0x%08x\n", (*clkdvdr));
+	temp = (*clkdvdr) & 0x2000FFFF;
+	*clkdvdr = temp;		/* turn off clock */
+	*clkdvdr = temp | 0x80000000 | (((bestval) & 0x1F) << 16);
+	pr_debug("DIU: Modified value of CLKDVDR = 0x%08x\n", (*clkdvdr));
+	iounmap(clkdvdr);
+}
+
+ssize_t mpc8610hpcd_show_monitor_port(int monitor_port, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE,
+			"%c0 - DVI\n"
+			"%c1 - Single link LVDS\n"
+			"%c2 - Dual link LVDS\n",
+			monitor_port == 0 ? '*' : ' ',
+			monitor_port == 1 ? '*' : ' ',
+			monitor_port == 2 ? '*' : ' ');
+}
+
+int mpc8610hpcd_set_sysfs_monitor_port(int val)
+{
+	return val < 3 ? val : 0;
+}
+
 #endif
+
+static void __init mpc86xx_hpcd_setup_arch(void)
+{
+	struct resource r;
+	struct device_node *np;
+	unsigned char *pixis;
+
 	if (ppc_md.progress)
 		ppc_md.progress("mpc86xx_hpcd_setup_arch()", 0);
 
@@ -183,6 +332,30 @@ mpc86xx_hpcd_setup_arch(void)
 		}
         }
 #endif
+#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+	preallocate_diu_videomemory();
+	diu_ops.get_pixel_format	= mpc8610hpcd_get_pixel_format;
+	diu_ops.set_gamma_table		= mpc8610hpcd_set_gamma_table;
+	diu_ops.set_monitor_port	= mpc8610hpcd_set_monitor_port;
+	diu_ops.set_pixel_clock		= mpc8610hpcd_set_pixel_clock;
+	diu_ops.show_monitor_port	= mpc8610hpcd_show_monitor_port;
+	diu_ops.set_sysfs_monitor_port	= mpc8610hpcd_set_sysfs_monitor_port;
+#endif
+
+	np = of_find_compatible_node(NULL, NULL, "fsl,fpga-pixis");
+	if (np) {
+		of_address_to_resource(np, 0, &r);
+		of_node_put(np);
+		pixis = ioremap(r.start, 32);
+		if (!pixis) {
+			printk(KERN_ERR "Err: can't map FPGA cfg register!\n");
+			return;
+		}
+		pixis_bdcfg0 = pixis + 8;
+		pixis_arch = pixis + 1;
+	} else
+		printk(KERN_ERR "Err: "
+				"can't find device node 'fsl,fpga-pixis'\n");
 
 	printk("MPC86xx HPCD board from Freescale Semiconductor\n");
 }
@@ -200,8 +373,7 @@ static int __init mpc86xx_hpcd_probe(void)
 	return 0;
 }
 
-static long __init
-mpc86xx_time_init(void)
+static long __init mpc86xx_time_init(void)
 {
 	unsigned int temp;
 
diff --git a/trunk/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/trunk/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index f947f555fd46..f13704aabbea 100644
--- a/trunk/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/trunk/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -221,6 +221,7 @@ mpc86xx_time_init(void)
 
 static __initdata struct of_device_id of_bus_ids[] = {
 	{ .compatible = "simple-bus", },
+	{ .compatible = "fsl,rapidio-delta", },
 	{},
 };
 
diff --git a/trunk/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/trunk/arch/powerpc/platforms/cell/celleb_scc_pciex.c
index ab24d94baab6..31da84c458d2 100644
--- a/trunk/arch/powerpc/platforms/cell/celleb_scc_pciex.c
+++ b/trunk/arch/powerpc/platforms/cell/celleb_scc_pciex.c
@@ -36,8 +36,8 @@
 #include "celleb_scc.h"
 #include "celleb_pci.h"
 
-#define PEX_IN(base, off)	in_be32((void *)(base) + (off))
-#define PEX_OUT(base, off, data) out_be32((void *)(base) + (off), (data))
+#define PEX_IN(base, off)	in_be32((void __iomem *)(base) + (off))
+#define PEX_OUT(base, off, data) out_be32((void __iomem *)(base) + (off), (data))
 
 static void scc_pciex_io_flush(struct iowa_bus *bus)
 {
@@ -304,7 +304,7 @@ static int __init scc_pciex_iowa_init(struct iowa_bus *bus, void *data)
 	((((0x1 << (size))-1) << ((addr) & 0x3)) << PEXDCMND_BYTE_EN_SHIFT)
 #define MK_PEXDCMND(cmd, addr, size) ((cmd) | MK_PEXDCMND_BYTE_EN(addr, size))
 
-static uint32_t config_read_pciex_dev(unsigned int *base,
+static uint32_t config_read_pciex_dev(unsigned int __iomem *base,
 		uint64_t bus_no, uint64_t dev_no, uint64_t func_no,
 		uint64_t off, uint64_t size)
 {
@@ -320,7 +320,7 @@ static uint32_t config_read_pciex_dev(unsigned int *base,
 	return ret;
 }
 
-static void config_write_pciex_dev(unsigned int *base, uint64_t bus_no,
+static void config_write_pciex_dev(unsigned int __iomem *base, uint64_t bus_no,
 	uint64_t dev_no, uint64_t func_no, uint64_t off, uint64_t size,
 	uint32_t data)
 {
@@ -338,7 +338,7 @@ static void config_write_pciex_dev(unsigned int *base, uint64_t bus_no,
 	((((0x1 << (len)) - 1) << ((off) & 0x3)) << PEXCADRS_BYTE_EN_SHIFT)
 #define MK_PEXCADRS(cmd, addr, size) \
 	((cmd) | MK_PEXCADRS_BYTE_EN(addr, size) | ((addr) & ~0x3))
-static uint32_t config_read_pciex_rc(unsigned int *base,
+static uint32_t config_read_pciex_rc(unsigned int __iomem *base,
 				     uint32_t where, uint32_t size)
 {
 	PEX_OUT(base, PEXCADRS, MK_PEXCADRS(PEXCADRS_CMD_READ, where, size));
@@ -346,7 +346,7 @@ static uint32_t config_read_pciex_rc(unsigned int *base,
 		>> ((where & (4 - size)) * 8)) & ((0x1 << (size * 8)) - 1);
 }
 
-static void config_write_pciex_rc(unsigned int *base, uint32_t where,
+static void config_write_pciex_rc(unsigned int __iomem *base, uint32_t where,
 				  uint32_t size, uint32_t val)
 {
 	uint32_t data;
@@ -410,7 +410,7 @@ static struct pci_ops scc_pciex_pci_ops = {
 	scc_pciex_write_config,
 };
 
-static void pciex_clear_intr_all(unsigned int *base)
+static void pciex_clear_intr_all(unsigned int __iomem *base)
 {
 	PEX_OUT(base, PEXAERRSTS, 0xffffffff);
 	PEX_OUT(base, PEXPRERRSTS, 0xffffffff);
@@ -427,7 +427,7 @@ static void pciex_disable_intr_all(unsigned int *base)
 }
 #endif
 
-static void pciex_enable_intr_all(unsigned int *base)
+static void pciex_enable_intr_all(unsigned int __iomem *base)
 {
 	PEX_OUT(base, PEXINTMASK, 0x0000e7f1);
 	PEX_OUT(base, PEXAERRMASK, 0x03ff01ff);
@@ -435,7 +435,7 @@ static void pciex_enable_intr_all(unsigned int *base)
 	PEX_OUT(base, PEXVDMASK, 0x00000001);
 }
 
-static void pciex_check_status(unsigned int *base)
+static void pciex_check_status(unsigned int __iomem *base)
 {
 	uint32_t err = 0;
 	uint32_t intsts, aerr, prerr, rcvcp, lenerr;
diff --git a/trunk/arch/powerpc/platforms/cell/spufs/sched.c b/trunk/arch/powerpc/platforms/cell/spufs/sched.c
index 00528ef84ad2..45dcd2693502 100644
--- a/trunk/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/trunk/arch/powerpc/platforms/cell/spufs/sched.c
@@ -1063,10 +1063,9 @@ int __init spu_sched_init(void)
 
 	mod_timer(&spuloadavg_timer, 0);
 
-	entry = create_proc_entry("spu_loadavg", 0, NULL);
+	entry = proc_create("spu_loadavg", 0, NULL, &spu_loadavg_fops);
 	if (!entry)
 		goto out_stop_kthread;
-	entry->proc_fops = &spu_loadavg_fops;
 
 	pr_debug("spusched: tick: %d, min ticks: %d, default ticks: %d\n",
 			SPUSCHED_TICK, MIN_SPU_TIMESLICE, DEF_SPU_TIMESLICE);
diff --git a/trunk/arch/powerpc/platforms/cell/spufs/sputrace.c b/trunk/arch/powerpc/platforms/cell/spufs/sputrace.c
index 79aa773f3c99..aea5286f1245 100644
--- a/trunk/arch/powerpc/platforms/cell/spufs/sputrace.c
+++ b/trunk/arch/powerpc/platforms/cell/spufs/sputrace.c
@@ -201,10 +201,9 @@ static int __init sputrace_init(void)
 	if (!sputrace_log)
 		goto out;
 
-	entry = create_proc_entry("sputrace", S_IRUSR, NULL);
+	entry = proc_create("sputrace", S_IRUSR, NULL, &sputrace_fops);
 	if (!entry)
 		goto out_free_log;
-	entry->proc_fops = &sputrace_fops;
 
 	for (i = 0; i < ARRAY_SIZE(spu_probes); i++) {
 		struct spu_probe *p = &spu_probes[i];
diff --git a/trunk/arch/powerpc/platforms/iseries/lpevents.c b/trunk/arch/powerpc/platforms/iseries/lpevents.c
index e5b40e3e0082..b0f8a857ec02 100644
--- a/trunk/arch/powerpc/platforms/iseries/lpevents.c
+++ b/trunk/arch/powerpc/platforms/iseries/lpevents.c
@@ -330,15 +330,11 @@ static const struct file_operations proc_lpevents_operations = {
 
 static int __init proc_lpevents_init(void)
 {
-	struct proc_dir_entry *e;
-
 	if (!firmware_has_feature(FW_FEATURE_ISERIES))
 		return 0;
 
-	e = create_proc_entry("iSeries/lpevents", S_IFREG|S_IRUGO, NULL);
-	if (e)
-		e->proc_fops = &proc_lpevents_operations;
-
+	proc_create("iSeries/lpevents", S_IFREG|S_IRUGO, NULL,
+		    &proc_lpevents_operations);
 	return 0;
 }
 __initcall(proc_lpevents_init);
diff --git a/trunk/arch/powerpc/platforms/iseries/mf.c b/trunk/arch/powerpc/platforms/iseries/mf.c
index c0f2433bc16e..1dc7295746da 100644
--- a/trunk/arch/powerpc/platforms/iseries/mf.c
+++ b/trunk/arch/powerpc/platforms/iseries/mf.c
@@ -1255,11 +1255,11 @@ static int __init mf_proc_init(void)
 		if (i == 3)	/* no vmlinux entry for 'D' */
 			continue;
 
-		ent = create_proc_entry("vmlinux", S_IFREG|S_IWUSR, mf);
+		ent = proc_create_data("vmlinux", S_IFREG|S_IWUSR, mf,
+				       &proc_vmlinux_operations,
+				       (void *)(long)i);
 		if (!ent)
 			return 1;
-		ent->data = (void *)(long)i;
-		ent->proc_fops = &proc_vmlinux_operations;
 	}
 
 	ent = create_proc_entry("side", S_IFREG|S_IRUSR|S_IWUSR, mf_proc_root);
diff --git a/trunk/arch/powerpc/platforms/iseries/proc.c b/trunk/arch/powerpc/platforms/iseries/proc.c
index f2cde4180204..91f4c6cd4b99 100644
--- a/trunk/arch/powerpc/platforms/iseries/proc.c
+++ b/trunk/arch/powerpc/platforms/iseries/proc.c
@@ -110,15 +110,11 @@ static const struct file_operations proc_titantod_operations = {
 
 static int __init iseries_proc_init(void)
 {
-	struct proc_dir_entry *e;
-
 	if (!firmware_has_feature(FW_FEATURE_ISERIES))
 		return 0;
 
-	e = create_proc_entry("iSeries/titanTod", S_IFREG|S_IRUGO, NULL);
-	if (e)
-		e->proc_fops = &proc_titantod_operations;
-
+	proc_create("iSeries/titanTod", S_IFREG|S_IRUGO, NULL,
+		    &proc_titantod_operations);
 	return 0;
 }
 __initcall(iseries_proc_init);
diff --git a/trunk/arch/powerpc/platforms/iseries/viopath.c b/trunk/arch/powerpc/platforms/iseries/viopath.c
index df23331eb25c..49ff4dc422b7 100644
--- a/trunk/arch/powerpc/platforms/iseries/viopath.c
+++ b/trunk/arch/powerpc/platforms/iseries/viopath.c
@@ -180,15 +180,10 @@ static const struct file_operations proc_viopath_operations = {
 
 static int __init vio_proc_init(void)
 {
-	struct proc_dir_entry *e;
-
 	if (!firmware_has_feature(FW_FEATURE_ISERIES))
 		return 0;
 
-	e = create_proc_entry("iSeries/config", 0, NULL);
-	if (e)
-		e->proc_fops = &proc_viopath_operations;
-
+	proc_create("iSeries/config", 0, NULL, &proc_viopath_operations);
         return 0;
 }
 __initcall(vio_proc_init);
diff --git a/trunk/arch/powerpc/platforms/powermac/Makefile b/trunk/arch/powerpc/platforms/powermac/Makefile
index 78093d7f97af..4d72c8f72159 100644
--- a/trunk/arch/powerpc/platforms/powermac/Makefile
+++ b/trunk/arch/powerpc/platforms/powermac/Makefile
@@ -6,7 +6,10 @@ obj-y				+= pic.o setup.o time.o feature.o pci.o \
 obj-$(CONFIG_PMAC_BACKLIGHT)	+= backlight.o
 obj-$(CONFIG_CPU_FREQ_PMAC)	+= cpufreq_32.o
 obj-$(CONFIG_CPU_FREQ_PMAC64)	+= cpufreq_64.o
-obj-$(CONFIG_NVRAM)		+= nvram.o
+# CONFIG_NVRAM is an arch. independant tristate symbol, for pmac32 we really
+# need this to be a bool.  Cheat here and pretend CONFIG_NVRAM=m is really
+# CONFIG_NVRAM=y
+obj-$(CONFIG_NVRAM:m=y)		+= nvram.o
 # ppc64 pmac doesn't define CONFIG_NVRAM but needs nvram stuff
 obj-$(CONFIG_PPC64)		+= nvram.o
 obj-$(CONFIG_PPC32)		+= bootx_init.o
diff --git a/trunk/arch/powerpc/platforms/powermac/setup.c b/trunk/arch/powerpc/platforms/powermac/setup.c
index bf44c5441a36..00bd0166d07f 100644
--- a/trunk/arch/powerpc/platforms/powermac/setup.c
+++ b/trunk/arch/powerpc/platforms/powermac/setup.c
@@ -337,7 +337,8 @@ static void __init pmac_setup_arch(void)
 	find_via_pmu();
 	smu_init();
 
-#if defined(CONFIG_NVRAM) || defined(CONFIG_PPC64)
+#if defined(CONFIG_NVRAM) || defined(CONFIG_NVRAM_MODULE) || \
+    defined(CONFIG_PPC64)
 	pmac_nvram_init();
 #endif
 
diff --git a/trunk/arch/powerpc/platforms/pseries/Makefile b/trunk/arch/powerpc/platforms/pseries/Makefile
index bd2593ed28dd..554c6e42ef2a 100644
--- a/trunk/arch/powerpc/platforms/pseries/Makefile
+++ b/trunk/arch/powerpc/platforms/pseries/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_PCI)	+= pci.o pci_dlpar.o
 obj-$(CONFIG_PCI_MSI)	+= msi.o
 
 obj-$(CONFIG_HOTPLUG_CPU)	+= hotplug-cpu.o
+obj-$(CONFIG_MEMORY_HOTPLUG)	+= hotplug-memory.o
 
 obj-$(CONFIG_HVC_CONSOLE)	+= hvconsole.o
 obj-$(CONFIG_HVCS)		+= hvcserver.o
diff --git a/trunk/arch/powerpc/platforms/pseries/eeh.c b/trunk/arch/powerpc/platforms/pseries/eeh.c
index a3fd56b186e6..6f544ba4b37f 100644
--- a/trunk/arch/powerpc/platforms/pseries/eeh.c
+++ b/trunk/arch/powerpc/platforms/pseries/eeh.c
@@ -1259,14 +1259,8 @@ static const struct file_operations proc_eeh_operations = {
 
 static int __init eeh_init_proc(void)
 {
-	struct proc_dir_entry *e;
-
-	if (machine_is(pseries)) {
-		e = create_proc_entry("ppc64/eeh", 0, NULL);
-		if (e)
-			e->proc_fops = &proc_eeh_operations;
-	}
-
+	if (machine_is(pseries))
+		proc_create("ppc64/eeh", 0, NULL, &proc_eeh_operations);
 	return 0;
 }
 __initcall(eeh_init_proc);
diff --git a/trunk/arch/powerpc/platforms/pseries/hotplug-memory.c b/trunk/arch/powerpc/platforms/pseries/hotplug-memory.c
new file mode 100644
index 000000000000..3c5727dd5aa5
--- /dev/null
+++ b/trunk/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -0,0 +1,141 @@
+/*
+ * pseries Memory Hotplug infrastructure.
+ *
+ * Copyright (C) 2008 Badari Pulavarty, IBM Corporation
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/of.h>
+#include <linux/lmb.h>
+#include <asm/firmware.h>
+#include <asm/machdep.h>
+#include <asm/pSeries_reconfig.h>
+
+static int pseries_remove_memory(struct device_node *np)
+{
+	const char *type;
+	const unsigned int *my_index;
+	const unsigned int *regs;
+	u64 start_pfn, start;
+	struct zone *zone;
+	int ret = -EINVAL;
+
+	/*
+	 * Check to see if we are actually removing memory
+	 */
+	type = of_get_property(np, "device_type", NULL);
+	if (type == NULL || strcmp(type, "memory") != 0)
+		return 0;
+
+	/*
+	 * Find the memory index and size of the removing section
+	 */
+	my_index = of_get_property(np, "ibm,my-drc-index", NULL);
+	if (!my_index)
+		return ret;
+
+	regs = of_get_property(np, "reg", NULL);
+	if (!regs)
+		return ret;
+
+	start_pfn = section_nr_to_pfn(*my_index & 0xffff);
+	zone = page_zone(pfn_to_page(start_pfn));
+
+	/*
+	 * Remove section mappings and sysfs entries for the
+	 * section of the memory we are removing.
+	 *
+	 * NOTE: Ideally, this should be done in generic code like
+	 * remove_memory(). But remove_memory() gets called by writing
+	 * to sysfs "state" file and we can't remove sysfs entries
+	 * while writing to it. So we have to defer it to here.
+	 */
+	ret = __remove_pages(zone, start_pfn, regs[3] >> PAGE_SHIFT);
+	if (ret)
+		return ret;
+
+	/*
+	 * Update memory regions for memory remove
+	 */
+	lmb_remove(start_pfn << PAGE_SHIFT, regs[3]);
+
+	/*
+	 * Remove htab bolted mappings for this section of memory
+	 */
+	start = (unsigned long)__va(start_pfn << PAGE_SHIFT);
+	ret = remove_section_mapping(start, start + regs[3]);
+	return ret;
+}
+
+static int pseries_add_memory(struct device_node *np)
+{
+	const char *type;
+	const unsigned int *my_index;
+	const unsigned int *regs;
+	u64 start_pfn;
+	int ret = -EINVAL;
+
+	/*
+	 * Check to see if we are actually adding memory
+	 */
+	type = of_get_property(np, "device_type", NULL);
+	if (type == NULL || strcmp(type, "memory") != 0)
+		return 0;
+
+	/*
+	 * Find the memory index and size of the added section
+	 */
+	my_index = of_get_property(np, "ibm,my-drc-index", NULL);
+	if (!my_index)
+		return ret;
+
+	regs = of_get_property(np, "reg", NULL);
+	if (!regs)
+		return ret;
+
+	start_pfn = section_nr_to_pfn(*my_index & 0xffff);
+
+	/*
+	 * Update memory region to represent the memory add
+	 */
+	lmb_add(start_pfn << PAGE_SHIFT, regs[3]);
+	return 0;
+}
+
+static int pseries_memory_notifier(struct notifier_block *nb,
+				unsigned long action, void *node)
+{
+	int err = NOTIFY_OK;
+
+	switch (action) {
+	case PSERIES_RECONFIG_ADD:
+		if (pseries_add_memory(node))
+			err = NOTIFY_BAD;
+		break;
+	case PSERIES_RECONFIG_REMOVE:
+		if (pseries_remove_memory(node))
+			err = NOTIFY_BAD;
+		break;
+	default:
+		err = NOTIFY_DONE;
+		break;
+	}
+	return err;
+}
+
+static struct notifier_block pseries_mem_nb = {
+	.notifier_call = pseries_memory_notifier,
+};
+
+static int __init pseries_memory_hotplug_init(void)
+{
+	if (firmware_has_feature(FW_FEATURE_LPAR))
+		pSeries_reconfig_notifier_register(&pseries_mem_nb);
+
+	return 0;
+}
+machine_device_initcall(pseries, pseries_memory_hotplug_init);
diff --git a/trunk/arch/powerpc/platforms/pseries/reconfig.c b/trunk/arch/powerpc/platforms/pseries/reconfig.c
index ac75c10de278..75769aae41d5 100644
--- a/trunk/arch/powerpc/platforms/pseries/reconfig.c
+++ b/trunk/arch/powerpc/platforms/pseries/reconfig.c
@@ -512,12 +512,9 @@ static int proc_ppc64_create_ofdt(void)
 	if (!machine_is(pseries))
 		return 0;
 
-	ent = create_proc_entry("ppc64/ofdt", S_IWUSR, NULL);
-	if (ent) {
-		ent->data = NULL;
+	ent = proc_create("ppc64/ofdt", S_IWUSR, NULL, &ofdt_fops);
+	if (ent)
 		ent->size = 0;
-		ent->proc_fops = &ofdt_fops;
-	}
 
 	return 0;
 }
diff --git a/trunk/arch/powerpc/platforms/pseries/rtasd.c b/trunk/arch/powerpc/platforms/pseries/rtasd.c
index befadd4f9524..7d3e2b0bd4d2 100644
--- a/trunk/arch/powerpc/platforms/pseries/rtasd.c
+++ b/trunk/arch/powerpc/platforms/pseries/rtasd.c
@@ -468,10 +468,9 @@ static int __init rtas_init(void)
 		return -ENOMEM;
 	}
 
-	entry = create_proc_entry("ppc64/rtas/error_log", S_IRUSR, NULL);
-	if (entry)
-		entry->proc_fops = &proc_rtas_log_operations;
-	else
+	entry = proc_create("ppc64/rtas/error_log", S_IRUSR, NULL,
+			    &proc_rtas_log_operations);
+	if (!entry)
 		printk(KERN_ERR "Failed to create error_log proc entry\n");
 
 	if (kernel_thread(rtasd, NULL, CLONE_FS) < 0)
diff --git a/trunk/arch/powerpc/sysdev/axonram.c b/trunk/arch/powerpc/sysdev/axonram.c
index d359d6e92975..7f59188cd9a1 100644
--- a/trunk/arch/powerpc/sysdev/axonram.c
+++ b/trunk/arch/powerpc/sysdev/axonram.c
@@ -143,7 +143,7 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
  */
 static int
 axon_ram_direct_access(struct block_device *device, sector_t sector,
-		       unsigned long *data)
+		       void **kaddr, unsigned long *pfn)
 {
 	struct axon_ram_bank *bank = device->bd_disk->private_data;
 	loff_t offset;
@@ -154,7 +154,8 @@ axon_ram_direct_access(struct block_device *device, sector_t sector,
 		return -ERANGE;
 	}
 
-	*data = bank->ph_addr + offset;
+	*kaddr = (void *)(bank->ph_addr + offset);
+	*pfn = virt_to_phys(kaddr) >> PAGE_SHIFT;
 
 	return 0;
 }
diff --git a/trunk/arch/powerpc/sysdev/fsl_rio.c b/trunk/arch/powerpc/sysdev/fsl_rio.c
index af2425e4655f..3d920376f58e 100644
--- a/trunk/arch/powerpc/sysdev/fsl_rio.c
+++ b/trunk/arch/powerpc/sysdev/fsl_rio.c
@@ -1,5 +1,8 @@
 /*
- * MPC85xx RapidIO support
+ * Freescale MPC85xx/MPC86xx RapidIO support
+ *
+ * Copyright (C) 2007, 2008 Freescale Semiconductor, Inc.
+ * Zhang Wei <wei.zhang@freescale.com>
  *
  * Copyright 2005 MontaVista Software, Inc.
  * Matt Porter <mporter@kernel.crashing.org>
@@ -17,12 +20,23 @@
 #include <linux/interrupt.h>
 #include <linux/rio.h>
 #include <linux/rio_drv.h>
+#include <linux/of_platform.h>
+#include <linux/delay.h>
 
 #include <asm/io.h>
 
-#define RIO_REGS_BASE		(CCSRBAR + 0xc0000)
+/* RapidIO definition irq, which read from OF-tree */
+#define IRQ_RIO_BELL(m)		(((struct rio_priv *)(m->priv))->bellirq)
+#define IRQ_RIO_TX(m)		(((struct rio_priv *)(m->priv))->txirq)
+#define IRQ_RIO_RX(m)		(((struct rio_priv *)(m->priv))->rxirq)
+
 #define RIO_ATMU_REGS_OFFSET	0x10c00
-#define RIO_MSG_REGS_OFFSET	0x11000
+#define RIO_P_MSG_REGS_OFFSET	0x11000
+#define RIO_S_MSG_REGS_OFFSET	0x13000
+#define RIO_ESCSR		0x158
+#define RIO_CCSR		0x15c
+#define RIO_ISR_AACR		0x10120
+#define RIO_ISR_AACR_AA		0x1	/* Accept All ID */
 #define RIO_MAINT_WIN_SIZE	0x400000
 #define RIO_DBELL_WIN_SIZE	0x1000
 
@@ -50,18 +64,18 @@
 #define DOORBELL_DSR_TE		0x00000080
 #define DOORBELL_DSR_QFI	0x00000010
 #define DOORBELL_DSR_DIQI	0x00000001
-#define DOORBELL_TID_OFFSET	0x03
-#define DOORBELL_SID_OFFSET	0x05
+#define DOORBELL_TID_OFFSET	0x02
+#define DOORBELL_SID_OFFSET	0x04
 #define DOORBELL_INFO_OFFSET	0x06
 
 #define DOORBELL_MESSAGE_SIZE	0x08
-#define DBELL_SID(x)		(*(u8 *)(x + DOORBELL_SID_OFFSET))
-#define DBELL_TID(x)		(*(u8 *)(x + DOORBELL_TID_OFFSET))
+#define DBELL_SID(x)		(*(u16 *)(x + DOORBELL_SID_OFFSET))
+#define DBELL_TID(x)		(*(u16 *)(x + DOORBELL_TID_OFFSET))
 #define DBELL_INF(x)		(*(u16 *)(x + DOORBELL_INFO_OFFSET))
 
 struct rio_atmu_regs {
 	u32 rowtar;
-	u32 pad1;
+	u32 rowtear;
 	u32 rowbar;
 	u32 pad2;
 	u32 rowar;
@@ -87,7 +101,15 @@ struct rio_msg_regs {
 	u32 ifqdpar;
 	u32 pad6;
 	u32 ifqepar;
-	u32 pad7[250];
+	u32 pad7[226];
+	u32 odmr;
+	u32 odsr;
+	u32 res0[4];
+	u32 oddpr;
+	u32 oddatr;
+	u32 res1[3];
+	u32 odretcr;
+	u32 res2[12];
 	u32 dmr;
 	u32 dsr;
 	u32 pad8;
@@ -112,20 +134,12 @@ struct rio_tx_desc {
 	u32 res4;
 };
 
-static u32 regs_win;
-static struct rio_atmu_regs *atmu_regs;
-static struct rio_atmu_regs *maint_atmu_regs;
-static struct rio_atmu_regs *dbell_atmu_regs;
-static u32 dbell_win;
-static u32 maint_win;
-static struct rio_msg_regs *msg_regs;
-
-static struct rio_dbell_ring {
+struct rio_dbell_ring {
 	void *virt;
 	dma_addr_t phys;
-} dbell_ring;
+};
 
-static struct rio_msg_tx_ring {
+struct rio_msg_tx_ring {
 	void *virt;
 	dma_addr_t phys;
 	void *virt_buffer[RIO_MAX_TX_RING_SIZE];
@@ -133,19 +147,35 @@ static struct rio_msg_tx_ring {
 	int tx_slot;
 	int size;
 	void *dev_id;
-} msg_tx_ring;
+};
 
-static struct rio_msg_rx_ring {
+struct rio_msg_rx_ring {
 	void *virt;
 	dma_addr_t phys;
 	void *virt_buffer[RIO_MAX_RX_RING_SIZE];
 	int rx_slot;
 	int size;
 	void *dev_id;
-} msg_rx_ring;
+};
+
+struct rio_priv {
+	void __iomem *regs_win;
+	struct rio_atmu_regs __iomem *atmu_regs;
+	struct rio_atmu_regs __iomem *maint_atmu_regs;
+	struct rio_atmu_regs __iomem *dbell_atmu_regs;
+	void __iomem *dbell_win;
+	void __iomem *maint_win;
+	struct rio_msg_regs __iomem *msg_regs;
+	struct rio_dbell_ring dbell_ring;
+	struct rio_msg_tx_ring msg_tx_ring;
+	struct rio_msg_rx_ring msg_rx_ring;
+	int bellirq;
+	int txirq;
+	int rxirq;
+};
 
 /**
- * mpc85xx_rio_doorbell_send - Send a MPC85xx doorbell message
+ * fsl_rio_doorbell_send - Send a MPC85xx doorbell message
  * @index: ID of RapidIO interface
  * @destid: Destination ID of target device
  * @data: 16-bit info field of RapidIO doorbell message
@@ -153,18 +183,34 @@ static struct rio_msg_rx_ring {
  * Sends a MPC85xx doorbell message. Returns %0 on success or
  * %-EINVAL on failure.
  */
-static int mpc85xx_rio_doorbell_send(int index, u16 destid, u16 data)
+static int fsl_rio_doorbell_send(struct rio_mport *mport,
+				int index, u16 destid, u16 data)
 {
-	pr_debug("mpc85xx_doorbell_send: index %d destid %4.4x data %4.4x\n",
+	struct rio_priv *priv = mport->priv;
+	pr_debug("fsl_doorbell_send: index %d destid %4.4x data %4.4x\n",
 		 index, destid, data);
-	out_be32((void *)&dbell_atmu_regs->rowtar, destid << 22);
-	out_be16((void *)(dbell_win), data);
+	switch (mport->phy_type) {
+	case RIO_PHY_PARALLEL:
+		out_be32(&priv->dbell_atmu_regs->rowtar, destid << 22);
+		out_be16(priv->dbell_win, data);
+		break;
+	case RIO_PHY_SERIAL:
+		/* In the serial version silicons, such as MPC8548, MPC8641,
+		 * below operations is must be.
+		 */
+		out_be32(&priv->msg_regs->odmr, 0x00000000);
+		out_be32(&priv->msg_regs->odretcr, 0x00000004);
+		out_be32(&priv->msg_regs->oddpr, destid << 16);
+		out_be32(&priv->msg_regs->oddatr, data);
+		out_be32(&priv->msg_regs->odmr, 0x00000001);
+		break;
+	}
 
 	return 0;
 }
 
 /**
- * mpc85xx_local_config_read - Generate a MPC85xx local config space read
+ * fsl_local_config_read - Generate a MPC85xx local config space read
  * @index: ID of RapdiIO interface
  * @offset: Offset into configuration space
  * @len: Length (in bytes) of the maintenance transaction
@@ -173,17 +219,19 @@ static int mpc85xx_rio_doorbell_send(int index, u16 destid, u16 data)
  * Generates a MPC85xx local configuration space read. Returns %0 on
  * success or %-EINVAL on failure.
  */
-static int mpc85xx_local_config_read(int index, u32 offset, int len, u32 * data)
+static int fsl_local_config_read(struct rio_mport *mport,
+				int index, u32 offset, int len, u32 *data)
 {
-	pr_debug("mpc85xx_local_config_read: index %d offset %8.8x\n", index,
+	struct rio_priv *priv = mport->priv;
+	pr_debug("fsl_local_config_read: index %d offset %8.8x\n", index,
 		 offset);
-	*data = in_be32((void *)(regs_win + offset));
+	*data = in_be32(priv->regs_win + offset);
 
 	return 0;
 }
 
 /**
- * mpc85xx_local_config_write - Generate a MPC85xx local config space write
+ * fsl_local_config_write - Generate a MPC85xx local config space write
  * @index: ID of RapdiIO interface
  * @offset: Offset into configuration space
  * @len: Length (in bytes) of the maintenance transaction
@@ -192,18 +240,20 @@ static int mpc85xx_local_config_read(int index, u32 offset, int len, u32 * data)
  * Generates a MPC85xx local configuration space write. Returns %0 on
  * success or %-EINVAL on failure.
  */
-static int mpc85xx_local_config_write(int index, u32 offset, int len, u32 data)
+static int fsl_local_config_write(struct rio_mport *mport,
+				int index, u32 offset, int len, u32 data)
 {
+	struct rio_priv *priv = mport->priv;
 	pr_debug
-	    ("mpc85xx_local_config_write: index %d offset %8.8x data %8.8x\n",
+	    ("fsl_local_config_write: index %d offset %8.8x data %8.8x\n",
 	     index, offset, data);
-	out_be32((void *)(regs_win + offset), data);
+	out_be32(priv->regs_win + offset, data);
 
 	return 0;
 }
 
 /**
- * mpc85xx_rio_config_read - Generate a MPC85xx read maintenance transaction
+ * fsl_rio_config_read - Generate a MPC85xx read maintenance transaction
  * @index: ID of RapdiIO interface
  * @destid: Destination ID of transaction
  * @hopcount: Number of hops to target device
@@ -215,18 +265,19 @@ static int mpc85xx_local_config_write(int index, u32 offset, int len, u32 data)
  * success or %-EINVAL on failure.
  */
 static int
-mpc85xx_rio_config_read(int index, u16 destid, u8 hopcount, u32 offset, int len,
-			u32 * val)
+fsl_rio_config_read(struct rio_mport *mport, int index, u16 destid,
+			u8 hopcount, u32 offset, int len, u32 *val)
 {
+	struct rio_priv *priv = mport->priv;
 	u8 *data;
 
 	pr_debug
-	    ("mpc85xx_rio_config_read: index %d destid %d hopcount %d offset %8.8x len %d\n",
+	    ("fsl_rio_config_read: index %d destid %d hopcount %d offset %8.8x len %d\n",
 	     index, destid, hopcount, offset, len);
-	out_be32((void *)&maint_atmu_regs->rowtar,
+	out_be32(&priv->maint_atmu_regs->rowtar,
 		 (destid << 22) | (hopcount << 12) | ((offset & ~0x3) >> 9));
 
-	data = (u8 *) maint_win + offset;
+	data = (u8 *) priv->maint_win + offset;
 	switch (len) {
 	case 1:
 		*val = in_8((u8 *) data);
@@ -243,7 +294,7 @@ mpc85xx_rio_config_read(int index, u16 destid, u8 hopcount, u32 offset, int len,
 }
 
 /**
- * mpc85xx_rio_config_write - Generate a MPC85xx write maintenance transaction
+ * fsl_rio_config_write - Generate a MPC85xx write maintenance transaction
  * @index: ID of RapdiIO interface
  * @destid: Destination ID of transaction
  * @hopcount: Number of hops to target device
@@ -255,17 +306,18 @@ mpc85xx_rio_config_read(int index, u16 destid, u8 hopcount, u32 offset, int len,
  * success or %-EINVAL on failure.
  */
 static int
-mpc85xx_rio_config_write(int index, u16 destid, u8 hopcount, u32 offset,
-			 int len, u32 val)
+fsl_rio_config_write(struct rio_mport *mport, int index, u16 destid,
+			u8 hopcount, u32 offset, int len, u32 val)
 {
+	struct rio_priv *priv = mport->priv;
 	u8 *data;
 	pr_debug
-	    ("mpc85xx_rio_config_write: index %d destid %d hopcount %d offset %8.8x len %d val %8.8x\n",
+	    ("fsl_rio_config_write: index %d destid %d hopcount %d offset %8.8x len %d val %8.8x\n",
 	     index, destid, hopcount, offset, len, val);
-	out_be32((void *)&maint_atmu_regs->rowtar,
+	out_be32(&priv->maint_atmu_regs->rowtar,
 		 (destid << 22) | (hopcount << 12) | ((offset & ~0x3) >> 9));
 
-	data = (u8 *) maint_win + offset;
+	data = (u8 *) priv->maint_win + offset;
 	switch (len) {
 	case 1:
 		out_8((u8 *) data, val);
@@ -296,9 +348,10 @@ int
 rio_hw_add_outb_message(struct rio_mport *mport, struct rio_dev *rdev, int mbox,
 			void *buffer, size_t len)
 {
+	struct rio_priv *priv = mport->priv;
 	u32 omr;
-	struct rio_tx_desc *desc =
-	    (struct rio_tx_desc *)msg_tx_ring.virt + msg_tx_ring.tx_slot;
+	struct rio_tx_desc *desc = (struct rio_tx_desc *)priv->msg_tx_ring.virt
+					+ priv->msg_tx_ring.tx_slot;
 	int ret = 0;
 
 	pr_debug
@@ -311,31 +364,43 @@ rio_hw_add_outb_message(struct rio_mport *mport, struct rio_dev *rdev, int mbox,
 	}
 
 	/* Copy and clear rest of buffer */
-	memcpy(msg_tx_ring.virt_buffer[msg_tx_ring.tx_slot], buffer, len);
+	memcpy(priv->msg_tx_ring.virt_buffer[priv->msg_tx_ring.tx_slot], buffer,
+			len);
 	if (len < (RIO_MAX_MSG_SIZE - 4))
-		memset((void *)((u32) msg_tx_ring.
-				virt_buffer[msg_tx_ring.tx_slot] + len), 0,
-		       RIO_MAX_MSG_SIZE - len);
+		memset(priv->msg_tx_ring.virt_buffer[priv->msg_tx_ring.tx_slot]
+				+ len, 0, RIO_MAX_MSG_SIZE - len);
 
-	/* Set mbox field for message */
-	desc->dport = mbox & 0x3;
+	switch (mport->phy_type) {
+	case RIO_PHY_PARALLEL:
+		/* Set mbox field for message */
+		desc->dport = mbox & 0x3;
 
-	/* Enable EOMI interrupt, set priority, and set destid */
-	desc->dattr = 0x28000000 | (rdev->destid << 2);
+		/* Enable EOMI interrupt, set priority, and set destid */
+		desc->dattr = 0x28000000 | (rdev->destid << 2);
+		break;
+	case RIO_PHY_SERIAL:
+		/* Set mbox field for message, and set destid */
+		desc->dport = (rdev->destid << 16) | (mbox & 0x3);
+
+		/* Enable EOMI interrupt and priority */
+		desc->dattr = 0x28000000;
+		break;
+	}
 
 	/* Set transfer size aligned to next power of 2 (in double words) */
 	desc->dwcnt = is_power_of_2(len) ? len : 1 << get_bitmask_order(len);
 
 	/* Set snooping and source buffer address */
-	desc->saddr = 0x00000004 | msg_tx_ring.phys_buffer[msg_tx_ring.tx_slot];
+	desc->saddr = 0x00000004
+		| priv->msg_tx_ring.phys_buffer[priv->msg_tx_ring.tx_slot];
 
 	/* Increment enqueue pointer */
-	omr = in_be32((void *)&msg_regs->omr);
-	out_be32((void *)&msg_regs->omr, omr | RIO_MSG_OMR_MUI);
+	omr = in_be32(&priv->msg_regs->omr);
+	out_be32(&priv->msg_regs->omr, omr | RIO_MSG_OMR_MUI);
 
 	/* Go to next descriptor */
-	if (++msg_tx_ring.tx_slot == msg_tx_ring.size)
-		msg_tx_ring.tx_slot = 0;
+	if (++priv->msg_tx_ring.tx_slot == priv->msg_tx_ring.size)
+		priv->msg_tx_ring.tx_slot = 0;
 
       out:
 	return ret;
@@ -344,7 +409,7 @@ rio_hw_add_outb_message(struct rio_mport *mport, struct rio_dev *rdev, int mbox,
 EXPORT_SYMBOL_GPL(rio_hw_add_outb_message);
 
 /**
- * mpc85xx_rio_tx_handler - MPC85xx outbound message interrupt handler
+ * fsl_rio_tx_handler - MPC85xx outbound message interrupt handler
  * @irq: Linux interrupt number
  * @dev_instance: Pointer to interrupt-specific data
  *
@@ -352,32 +417,34 @@ EXPORT_SYMBOL_GPL(rio_hw_add_outb_message);
  * mailbox event handler and acks the interrupt occurrence.
  */
 static irqreturn_t
-mpc85xx_rio_tx_handler(int irq, void *dev_instance)
+fsl_rio_tx_handler(int irq, void *dev_instance)
 {
 	int osr;
 	struct rio_mport *port = (struct rio_mport *)dev_instance;
+	struct rio_priv *priv = port->priv;
 
-	osr = in_be32((void *)&msg_regs->osr);
+	osr = in_be32(&priv->msg_regs->osr);
 
 	if (osr & RIO_MSG_OSR_TE) {
 		pr_info("RIO: outbound message transmission error\n");
-		out_be32((void *)&msg_regs->osr, RIO_MSG_OSR_TE);
+		out_be32(&priv->msg_regs->osr, RIO_MSG_OSR_TE);
 		goto out;
 	}
 
 	if (osr & RIO_MSG_OSR_QOI) {
 		pr_info("RIO: outbound message queue overflow\n");
-		out_be32((void *)&msg_regs->osr, RIO_MSG_OSR_QOI);
+		out_be32(&priv->msg_regs->osr, RIO_MSG_OSR_QOI);
 		goto out;
 	}
 
 	if (osr & RIO_MSG_OSR_EOMI) {
-		u32 dqp = in_be32((void *)&msg_regs->odqdpar);
-		int slot = (dqp - msg_tx_ring.phys) >> 5;
-		port->outb_msg[0].mcback(port, msg_tx_ring.dev_id, -1, slot);
+		u32 dqp = in_be32(&priv->msg_regs->odqdpar);
+		int slot = (dqp - priv->msg_tx_ring.phys) >> 5;
+		port->outb_msg[0].mcback(port, priv->msg_tx_ring.dev_id, -1,
+				slot);
 
 		/* Ack the end-of-message interrupt */
-		out_be32((void *)&msg_regs->osr, RIO_MSG_OSR_EOMI);
+		out_be32(&priv->msg_regs->osr, RIO_MSG_OSR_EOMI);
 	}
 
       out:
@@ -398,6 +465,7 @@ mpc85xx_rio_tx_handler(int irq, void *dev_instance)
 int rio_open_outb_mbox(struct rio_mport *mport, void *dev_id, int mbox, int entries)
 {
 	int i, j, rc = 0;
+	struct rio_priv *priv = mport->priv;
 
 	if ((entries < RIO_MIN_TX_RING_SIZE) ||
 	    (entries > RIO_MAX_TX_RING_SIZE) || (!is_power_of_2(entries))) {
@@ -406,54 +474,53 @@ int rio_open_outb_mbox(struct rio_mport *mport, void *dev_id, int mbox, int entr
 	}
 
 	/* Initialize shadow copy ring */
-	msg_tx_ring.dev_id = dev_id;
-	msg_tx_ring.size = entries;
-
-	for (i = 0; i < msg_tx_ring.size; i++) {
-		if (!
-		    (msg_tx_ring.virt_buffer[i] =
-		     dma_alloc_coherent(NULL, RIO_MSG_BUFFER_SIZE,
-					&msg_tx_ring.phys_buffer[i],
-					GFP_KERNEL))) {
+	priv->msg_tx_ring.dev_id = dev_id;
+	priv->msg_tx_ring.size = entries;
+
+	for (i = 0; i < priv->msg_tx_ring.size; i++) {
+		priv->msg_tx_ring.virt_buffer[i] =
+			dma_alloc_coherent(NULL, RIO_MSG_BUFFER_SIZE,
+				&priv->msg_tx_ring.phys_buffer[i], GFP_KERNEL);
+		if (!priv->msg_tx_ring.virt_buffer[i]) {
 			rc = -ENOMEM;
-			for (j = 0; j < msg_tx_ring.size; j++)
-				if (msg_tx_ring.virt_buffer[j])
+			for (j = 0; j < priv->msg_tx_ring.size; j++)
+				if (priv->msg_tx_ring.virt_buffer[j])
 					dma_free_coherent(NULL,
-							  RIO_MSG_BUFFER_SIZE,
-							  msg_tx_ring.
-							  virt_buffer[j],
-							  msg_tx_ring.
-							  phys_buffer[j]);
+							RIO_MSG_BUFFER_SIZE,
+							priv->msg_tx_ring.
+							virt_buffer[j],
+							priv->msg_tx_ring.
+							phys_buffer[j]);
 			goto out;
 		}
 	}
 
 	/* Initialize outbound message descriptor ring */
-	if (!(msg_tx_ring.virt = dma_alloc_coherent(NULL,
-						    msg_tx_ring.size *
-						    RIO_MSG_DESC_SIZE,
-						    &msg_tx_ring.phys,
-						    GFP_KERNEL))) {
+	priv->msg_tx_ring.virt = dma_alloc_coherent(NULL,
+				priv->msg_tx_ring.size * RIO_MSG_DESC_SIZE,
+				&priv->msg_tx_ring.phys, GFP_KERNEL);
+	if (!priv->msg_tx_ring.virt) {
 		rc = -ENOMEM;
 		goto out_dma;
 	}
-	memset(msg_tx_ring.virt, 0, msg_tx_ring.size * RIO_MSG_DESC_SIZE);
-	msg_tx_ring.tx_slot = 0;
+	memset(priv->msg_tx_ring.virt, 0,
+			priv->msg_tx_ring.size * RIO_MSG_DESC_SIZE);
+	priv->msg_tx_ring.tx_slot = 0;
 
 	/* Point dequeue/enqueue pointers at first entry in ring */
-	out_be32((void *)&msg_regs->odqdpar, msg_tx_ring.phys);
-	out_be32((void *)&msg_regs->odqepar, msg_tx_ring.phys);
+	out_be32(&priv->msg_regs->odqdpar, priv->msg_tx_ring.phys);
+	out_be32(&priv->msg_regs->odqepar, priv->msg_tx_ring.phys);
 
 	/* Configure for snooping */
-	out_be32((void *)&msg_regs->osar, 0x00000004);
+	out_be32(&priv->msg_regs->osar, 0x00000004);
 
 	/* Clear interrupt status */
-	out_be32((void *)&msg_regs->osr, 0x000000b3);
+	out_be32(&priv->msg_regs->osr, 0x000000b3);
 
 	/* Hook up outbound message handler */
-	if ((rc =
-	     request_irq(MPC85xx_IRQ_RIO_TX, mpc85xx_rio_tx_handler, 0,
-			 "msg_tx", (void *)mport)) < 0)
+	rc = request_irq(IRQ_RIO_TX(mport), fsl_rio_tx_handler, 0,
+			 "msg_tx", (void *)mport);
+	if (rc < 0)
 		goto out_irq;
 
 	/*
@@ -463,28 +530,28 @@ int rio_open_outb_mbox(struct rio_mport *mport, void *dev_id, int mbox, int entr
 	 *      Chaining mode
 	 *      Disable
 	 */
-	out_be32((void *)&msg_regs->omr, 0x00100220);
+	out_be32(&priv->msg_regs->omr, 0x00100220);
 
 	/* Set number of entries */
-	out_be32((void *)&msg_regs->omr,
-		 in_be32((void *)&msg_regs->omr) |
+	out_be32(&priv->msg_regs->omr,
+		 in_be32(&priv->msg_regs->omr) |
 		 ((get_bitmask_order(entries) - 2) << 12));
 
 	/* Now enable the unit */
-	out_be32((void *)&msg_regs->omr, in_be32((void *)&msg_regs->omr) | 0x1);
+	out_be32(&priv->msg_regs->omr, in_be32(&priv->msg_regs->omr) | 0x1);
 
       out:
 	return rc;
 
       out_irq:
-	dma_free_coherent(NULL, msg_tx_ring.size * RIO_MSG_DESC_SIZE,
-			  msg_tx_ring.virt, msg_tx_ring.phys);
+	dma_free_coherent(NULL, priv->msg_tx_ring.size * RIO_MSG_DESC_SIZE,
+			  priv->msg_tx_ring.virt, priv->msg_tx_ring.phys);
 
       out_dma:
-	for (i = 0; i < msg_tx_ring.size; i++)
+	for (i = 0; i < priv->msg_tx_ring.size; i++)
 		dma_free_coherent(NULL, RIO_MSG_BUFFER_SIZE,
-				  msg_tx_ring.virt_buffer[i],
-				  msg_tx_ring.phys_buffer[i]);
+				  priv->msg_tx_ring.virt_buffer[i],
+				  priv->msg_tx_ring.phys_buffer[i]);
 
 	return rc;
 }
@@ -499,19 +566,20 @@ int rio_open_outb_mbox(struct rio_mport *mport, void *dev_id, int mbox, int entr
  */
 void rio_close_outb_mbox(struct rio_mport *mport, int mbox)
 {
+	struct rio_priv *priv = mport->priv;
 	/* Disable inbound message unit */
-	out_be32((void *)&msg_regs->omr, 0);
+	out_be32(&priv->msg_regs->omr, 0);
 
 	/* Free ring */
-	dma_free_coherent(NULL, msg_tx_ring.size * RIO_MSG_DESC_SIZE,
-			  msg_tx_ring.virt, msg_tx_ring.phys);
+	dma_free_coherent(NULL, priv->msg_tx_ring.size * RIO_MSG_DESC_SIZE,
+			  priv->msg_tx_ring.virt, priv->msg_tx_ring.phys);
 
 	/* Free interrupt */
-	free_irq(MPC85xx_IRQ_RIO_TX, (void *)mport);
+	free_irq(IRQ_RIO_TX(mport), (void *)mport);
 }
 
 /**
- * mpc85xx_rio_rx_handler - MPC85xx inbound message interrupt handler
+ * fsl_rio_rx_handler - MPC85xx inbound message interrupt handler
  * @irq: Linux interrupt number
  * @dev_instance: Pointer to interrupt-specific data
  *
@@ -519,16 +587,17 @@ void rio_close_outb_mbox(struct rio_mport *mport, int mbox)
  * mailbox event handler and acks the interrupt occurrence.
  */
 static irqreturn_t
-mpc85xx_rio_rx_handler(int irq, void *dev_instance)
+fsl_rio_rx_handler(int irq, void *dev_instance)
 {
 	int isr;
 	struct rio_mport *port = (struct rio_mport *)dev_instance;
+	struct rio_priv *priv = port->priv;
 
-	isr = in_be32((void *)&msg_regs->isr);
+	isr = in_be32(&priv->msg_regs->isr);
 
 	if (isr & RIO_MSG_ISR_TE) {
 		pr_info("RIO: inbound message reception error\n");
-		out_be32((void *)&msg_regs->isr, RIO_MSG_ISR_TE);
+		out_be32((void *)&priv->msg_regs->isr, RIO_MSG_ISR_TE);
 		goto out;
 	}
 
@@ -540,10 +609,10 @@ mpc85xx_rio_rx_handler(int irq, void *dev_instance)
 		 * make the callback with an unknown/invalid mailbox number
 		 * argument.
 		 */
-		port->inb_msg[0].mcback(port, msg_rx_ring.dev_id, -1, -1);
+		port->inb_msg[0].mcback(port, priv->msg_rx_ring.dev_id, -1, -1);
 
 		/* Ack the queueing interrupt */
-		out_be32((void *)&msg_regs->isr, RIO_MSG_ISR_DIQI);
+		out_be32(&priv->msg_regs->isr, RIO_MSG_ISR_DIQI);
 	}
 
       out:
@@ -564,6 +633,7 @@ mpc85xx_rio_rx_handler(int irq, void *dev_instance)
 int rio_open_inb_mbox(struct rio_mport *mport, void *dev_id, int mbox, int entries)
 {
 	int i, rc = 0;
+	struct rio_priv *priv = mport->priv;
 
 	if ((entries < RIO_MIN_RX_RING_SIZE) ||
 	    (entries > RIO_MAX_RX_RING_SIZE) || (!is_power_of_2(entries))) {
@@ -572,36 +642,35 @@ int rio_open_inb_mbox(struct rio_mport *mport, void *dev_id, int mbox, int entri
 	}
 
 	/* Initialize client buffer ring */
-	msg_rx_ring.dev_id = dev_id;
-	msg_rx_ring.size = entries;
-	msg_rx_ring.rx_slot = 0;
-	for (i = 0; i < msg_rx_ring.size; i++)
-		msg_rx_ring.virt_buffer[i] = NULL;
+	priv->msg_rx_ring.dev_id = dev_id;
+	priv->msg_rx_ring.size = entries;
+	priv->msg_rx_ring.rx_slot = 0;
+	for (i = 0; i < priv->msg_rx_ring.size; i++)
+		priv->msg_rx_ring.virt_buffer[i] = NULL;
 
 	/* Initialize inbound message ring */
-	if (!(msg_rx_ring.virt = dma_alloc_coherent(NULL,
-						    msg_rx_ring.size *
-						    RIO_MAX_MSG_SIZE,
-						    &msg_rx_ring.phys,
-						    GFP_KERNEL))) {
+	priv->msg_rx_ring.virt = dma_alloc_coherent(NULL,
+				priv->msg_rx_ring.size * RIO_MAX_MSG_SIZE,
+				&priv->msg_rx_ring.phys, GFP_KERNEL);
+	if (!priv->msg_rx_ring.virt) {
 		rc = -ENOMEM;
 		goto out;
 	}
 
 	/* Point dequeue/enqueue pointers at first entry in ring */
-	out_be32((void *)&msg_regs->ifqdpar, (u32) msg_rx_ring.phys);
-	out_be32((void *)&msg_regs->ifqepar, (u32) msg_rx_ring.phys);
+	out_be32(&priv->msg_regs->ifqdpar, (u32) priv->msg_rx_ring.phys);
+	out_be32(&priv->msg_regs->ifqepar, (u32) priv->msg_rx_ring.phys);
 
 	/* Clear interrupt status */
-	out_be32((void *)&msg_regs->isr, 0x00000091);
+	out_be32(&priv->msg_regs->isr, 0x00000091);
 
 	/* Hook up inbound message handler */
-	if ((rc =
-	     request_irq(MPC85xx_IRQ_RIO_RX, mpc85xx_rio_rx_handler, 0,
-			 "msg_rx", (void *)mport)) < 0) {
+	rc = request_irq(IRQ_RIO_RX(mport), fsl_rio_rx_handler, 0,
+			 "msg_rx", (void *)mport);
+	if (rc < 0) {
 		dma_free_coherent(NULL, RIO_MSG_BUFFER_SIZE,
-				  msg_tx_ring.virt_buffer[i],
-				  msg_tx_ring.phys_buffer[i]);
+				  priv->msg_tx_ring.virt_buffer[i],
+				  priv->msg_tx_ring.phys_buffer[i]);
 		goto out;
 	}
 
@@ -612,15 +681,13 @@ int rio_open_inb_mbox(struct rio_mport *mport, void *dev_id, int mbox, int entri
 	 *      Unmask all interrupt sources
 	 *      Disable
 	 */
-	out_be32((void *)&msg_regs->imr, 0x001b0060);
+	out_be32(&priv->msg_regs->imr, 0x001b0060);
 
 	/* Set number of queue entries */
-	out_be32((void *)&msg_regs->imr,
-		 in_be32((void *)&msg_regs->imr) |
-		 ((get_bitmask_order(entries) - 2) << 12));
+	setbits32(&priv->msg_regs->imr, (get_bitmask_order(entries) - 2) << 12);
 
 	/* Now enable the unit */
-	out_be32((void *)&msg_regs->imr, in_be32((void *)&msg_regs->imr) | 0x1);
+	setbits32(&priv->msg_regs->imr, 0x1);
 
       out:
 	return rc;
@@ -636,15 +703,16 @@ int rio_open_inb_mbox(struct rio_mport *mport, void *dev_id, int mbox, int entri
  */
 void rio_close_inb_mbox(struct rio_mport *mport, int mbox)
 {
+	struct rio_priv *priv = mport->priv;
 	/* Disable inbound message unit */
-	out_be32((void *)&msg_regs->imr, 0);
+	out_be32(&priv->msg_regs->imr, 0);
 
 	/* Free ring */
-	dma_free_coherent(NULL, msg_rx_ring.size * RIO_MAX_MSG_SIZE,
-			  msg_rx_ring.virt, msg_rx_ring.phys);
+	dma_free_coherent(NULL, priv->msg_rx_ring.size * RIO_MAX_MSG_SIZE,
+			  priv->msg_rx_ring.virt, priv->msg_rx_ring.phys);
 
 	/* Free interrupt */
-	free_irq(MPC85xx_IRQ_RIO_RX, (void *)mport);
+	free_irq(IRQ_RIO_RX(mport), (void *)mport);
 }
 
 /**
@@ -659,21 +727,22 @@ void rio_close_inb_mbox(struct rio_mport *mport, int mbox)
 int rio_hw_add_inb_buffer(struct rio_mport *mport, int mbox, void *buf)
 {
 	int rc = 0;
+	struct rio_priv *priv = mport->priv;
 
 	pr_debug("RIO: rio_hw_add_inb_buffer(), msg_rx_ring.rx_slot %d\n",
-		 msg_rx_ring.rx_slot);
+		 priv->msg_rx_ring.rx_slot);
 
-	if (msg_rx_ring.virt_buffer[msg_rx_ring.rx_slot]) {
+	if (priv->msg_rx_ring.virt_buffer[priv->msg_rx_ring.rx_slot]) {
 		printk(KERN_ERR
 		       "RIO: error adding inbound buffer %d, buffer exists\n",
-		       msg_rx_ring.rx_slot);
+		       priv->msg_rx_ring.rx_slot);
 		rc = -EINVAL;
 		goto out;
 	}
 
-	msg_rx_ring.virt_buffer[msg_rx_ring.rx_slot] = buf;
-	if (++msg_rx_ring.rx_slot == msg_rx_ring.size)
-		msg_rx_ring.rx_slot = 0;
+	priv->msg_rx_ring.virt_buffer[priv->msg_rx_ring.rx_slot] = buf;
+	if (++priv->msg_rx_ring.rx_slot == priv->msg_rx_ring.size)
+		priv->msg_rx_ring.rx_slot = 0;
 
       out:
 	return rc;
@@ -691,20 +760,21 @@ EXPORT_SYMBOL_GPL(rio_hw_add_inb_buffer);
  */
 void *rio_hw_get_inb_message(struct rio_mport *mport, int mbox)
 {
-	u32 imr;
+	struct rio_priv *priv = mport->priv;
 	u32 phys_buf, virt_buf;
 	void *buf = NULL;
 	int buf_idx;
 
-	phys_buf = in_be32((void *)&msg_regs->ifqdpar);
+	phys_buf = in_be32(&priv->msg_regs->ifqdpar);
 
 	/* If no more messages, then bail out */
-	if (phys_buf == in_be32((void *)&msg_regs->ifqepar))
+	if (phys_buf == in_be32(&priv->msg_regs->ifqepar))
 		goto out2;
 
-	virt_buf = (u32) msg_rx_ring.virt + (phys_buf - msg_rx_ring.phys);
-	buf_idx = (phys_buf - msg_rx_ring.phys) / RIO_MAX_MSG_SIZE;
-	buf = msg_rx_ring.virt_buffer[buf_idx];
+	virt_buf = (u32) priv->msg_rx_ring.virt + (phys_buf
+						- priv->msg_rx_ring.phys);
+	buf_idx = (phys_buf - priv->msg_rx_ring.phys) / RIO_MAX_MSG_SIZE;
+	buf = priv->msg_rx_ring.virt_buffer[buf_idx];
 
 	if (!buf) {
 		printk(KERN_ERR
@@ -716,11 +786,10 @@ void *rio_hw_get_inb_message(struct rio_mport *mport, int mbox)
 	memcpy(buf, (void *)virt_buf, RIO_MAX_MSG_SIZE);
 
 	/* Clear the available buffer */
-	msg_rx_ring.virt_buffer[buf_idx] = NULL;
+	priv->msg_rx_ring.virt_buffer[buf_idx] = NULL;
 
       out1:
-	imr = in_be32((void *)&msg_regs->imr);
-	out_be32((void *)&msg_regs->imr, imr | RIO_MSG_IMR_MI);
+	setbits32(&priv->msg_regs->imr, RIO_MSG_IMR_MI);
 
       out2:
 	return buf;
@@ -729,7 +798,7 @@ void *rio_hw_get_inb_message(struct rio_mport *mport, int mbox)
 EXPORT_SYMBOL_GPL(rio_hw_get_inb_message);
 
 /**
- * mpc85xx_rio_dbell_handler - MPC85xx doorbell interrupt handler
+ * fsl_rio_dbell_handler - MPC85xx doorbell interrupt handler
  * @irq: Linux interrupt number
  * @dev_instance: Pointer to interrupt-specific data
  *
@@ -737,31 +806,31 @@ EXPORT_SYMBOL_GPL(rio_hw_get_inb_message);
  * doorbell event handlers and executes a matching event handler.
  */
 static irqreturn_t
-mpc85xx_rio_dbell_handler(int irq, void *dev_instance)
+fsl_rio_dbell_handler(int irq, void *dev_instance)
 {
 	int dsr;
 	struct rio_mport *port = (struct rio_mport *)dev_instance;
+	struct rio_priv *priv = port->priv;
 
-	dsr = in_be32((void *)&msg_regs->dsr);
+	dsr = in_be32(&priv->msg_regs->dsr);
 
 	if (dsr & DOORBELL_DSR_TE) {
 		pr_info("RIO: doorbell reception error\n");
-		out_be32((void *)&msg_regs->dsr, DOORBELL_DSR_TE);
+		out_be32(&priv->msg_regs->dsr, DOORBELL_DSR_TE);
 		goto out;
 	}
 
 	if (dsr & DOORBELL_DSR_QFI) {
 		pr_info("RIO: doorbell queue full\n");
-		out_be32((void *)&msg_regs->dsr, DOORBELL_DSR_QFI);
+		out_be32(&priv->msg_regs->dsr, DOORBELL_DSR_QFI);
 		goto out;
 	}
 
 	/* XXX Need to check/dispatch until queue empty */
 	if (dsr & DOORBELL_DSR_DIQI) {
 		u32 dmsg =
-		    (u32) dbell_ring.virt +
-		    (in_be32((void *)&msg_regs->dqdpar) & 0xfff);
-		u32 dmr;
+		    (u32) priv->dbell_ring.virt +
+		    (in_be32(&priv->msg_regs->dqdpar) & 0xfff);
 		struct rio_dbell *dbell;
 		int found = 0;
 
@@ -784,9 +853,8 @@ mpc85xx_rio_dbell_handler(int irq, void *dev_instance)
 			    ("RIO: spurious doorbell, sid %2.2x tid %2.2x info %4.4x\n",
 			     DBELL_SID(dmsg), DBELL_TID(dmsg), DBELL_INF(dmsg));
 		}
-		dmr = in_be32((void *)&msg_regs->dmr);
-		out_be32((void *)&msg_regs->dmr, dmr | DOORBELL_DMR_DI);
-		out_be32((void *)&msg_regs->dsr, DOORBELL_DSR_DIQI);
+		setbits32(&priv->msg_regs->dmr, DOORBELL_DMR_DI);
+		out_be32(&priv->msg_regs->dsr, DOORBELL_DSR_DIQI);
 	}
 
       out:
@@ -794,21 +862,22 @@ mpc85xx_rio_dbell_handler(int irq, void *dev_instance)
 }
 
 /**
- * mpc85xx_rio_doorbell_init - MPC85xx doorbell interface init
+ * fsl_rio_doorbell_init - MPC85xx doorbell interface init
  * @mport: Master port implementing the inbound doorbell unit
  *
  * Initializes doorbell unit hardware and inbound DMA buffer
- * ring. Called from mpc85xx_rio_setup(). Returns %0 on success
+ * ring. Called from fsl_rio_setup(). Returns %0 on success
  * or %-ENOMEM on failure.
  */
-static int mpc85xx_rio_doorbell_init(struct rio_mport *mport)
+static int fsl_rio_doorbell_init(struct rio_mport *mport)
 {
+	struct rio_priv *priv = mport->priv;
 	int rc = 0;
 
 	/* Map outbound doorbell window immediately after maintenance window */
-	if (!(dbell_win =
-	      (u32) ioremap(mport->iores.start + RIO_MAINT_WIN_SIZE,
-			    RIO_DBELL_WIN_SIZE))) {
+	priv->dbell_win = ioremap(mport->iores.start + RIO_MAINT_WIN_SIZE,
+			    RIO_DBELL_WIN_SIZE);
+	if (!priv->dbell_win) {
 		printk(KERN_ERR
 		       "RIO: unable to map outbound doorbell window\n");
 		rc = -ENOMEM;
@@ -816,37 +885,36 @@ static int mpc85xx_rio_doorbell_init(struct rio_mport *mport)
 	}
 
 	/* Initialize inbound doorbells */
-	if (!(dbell_ring.virt = dma_alloc_coherent(NULL,
-						   512 * DOORBELL_MESSAGE_SIZE,
-						   &dbell_ring.phys,
-						   GFP_KERNEL))) {
+	priv->dbell_ring.virt = dma_alloc_coherent(NULL, 512 *
+		    DOORBELL_MESSAGE_SIZE, &priv->dbell_ring.phys, GFP_KERNEL);
+	if (!priv->dbell_ring.virt) {
 		printk(KERN_ERR "RIO: unable allocate inbound doorbell ring\n");
 		rc = -ENOMEM;
-		iounmap((void *)dbell_win);
+		iounmap(priv->dbell_win);
 		goto out;
 	}
 
 	/* Point dequeue/enqueue pointers at first entry in ring */
-	out_be32((void *)&msg_regs->dqdpar, (u32) dbell_ring.phys);
-	out_be32((void *)&msg_regs->dqepar, (u32) dbell_ring.phys);
+	out_be32(&priv->msg_regs->dqdpar, (u32) priv->dbell_ring.phys);
+	out_be32(&priv->msg_regs->dqepar, (u32) priv->dbell_ring.phys);
 
 	/* Clear interrupt status */
-	out_be32((void *)&msg_regs->dsr, 0x00000091);
+	out_be32(&priv->msg_regs->dsr, 0x00000091);
 
 	/* Hook up doorbell handler */
-	if ((rc =
-	     request_irq(MPC85xx_IRQ_RIO_BELL, mpc85xx_rio_dbell_handler, 0,
-			 "dbell_rx", (void *)mport) < 0)) {
-		iounmap((void *)dbell_win);
+	rc = request_irq(IRQ_RIO_BELL(mport), fsl_rio_dbell_handler, 0,
+			 "dbell_rx", (void *)mport);
+	if (rc < 0) {
+		iounmap(priv->dbell_win);
 		dma_free_coherent(NULL, 512 * DOORBELL_MESSAGE_SIZE,
-				  dbell_ring.virt, dbell_ring.phys);
+				  priv->dbell_ring.virt, priv->dbell_ring.phys);
 		printk(KERN_ERR
 		       "MPC85xx RIO: unable to request inbound doorbell irq");
 		goto out;
 	}
 
 	/* Configure doorbells for snooping, 512 entries, and enable */
-	out_be32((void *)&msg_regs->dmr, 0x00108161);
+	out_be32(&priv->msg_regs->dmr, 0x00108161);
 
       out:
 	return rc;
@@ -854,7 +922,7 @@ static int mpc85xx_rio_doorbell_init(struct rio_mport *mport)
 
 static char *cmdline = NULL;
 
-static int mpc85xx_rio_get_hdid(int index)
+static int fsl_rio_get_hdid(int index)
 {
 	/* XXX Need to parse multiple entries in some format */
 	if (!cmdline)
@@ -863,7 +931,7 @@ static int mpc85xx_rio_get_hdid(int index)
 	return simple_strtol(cmdline, NULL, 0);
 }
 
-static int mpc85xx_rio_get_cmdline(char *s)
+static int fsl_rio_get_cmdline(char *s)
 {
 	if (!s)
 		return 0;
@@ -872,61 +940,266 @@ static int mpc85xx_rio_get_cmdline(char *s)
 	return 1;
 }
 
-__setup("riohdid=", mpc85xx_rio_get_cmdline);
+__setup("riohdid=", fsl_rio_get_cmdline);
+
+static inline void fsl_rio_info(struct device *dev, u32 ccsr)
+{
+	const char *str;
+	if (ccsr & 1) {
+		/* Serial phy */
+		switch (ccsr >> 30) {
+		case 0:
+			str = "1";
+			break;
+		case 1:
+			str = "4";
+			break;
+		default:
+			str = "Unknown";
+			break;;
+		}
+		dev_info(dev, "Hardware port width: %s\n", str);
+
+		switch ((ccsr >> 27) & 7) {
+		case 0:
+			str = "Single-lane 0";
+			break;
+		case 1:
+			str = "Single-lane 2";
+			break;
+		case 2:
+			str = "Four-lane";
+			break;
+		default:
+			str = "Unknown";
+			break;
+		}
+		dev_info(dev, "Training connection status: %s\n", str);
+	} else {
+		/* Parallel phy */
+		if (!(ccsr & 0x80000000))
+			dev_info(dev, "Output port operating in 8-bit mode\n");
+		if (!(ccsr & 0x08000000))
+			dev_info(dev, "Input port operating in 8-bit mode\n");
+	}
+}
 
 /**
- * mpc85xx_rio_setup - Setup MPC85xx RapidIO interface
- * @law_start: Starting physical address of RapidIO LAW
- * @law_size: Size of RapidIO LAW
+ * fsl_rio_setup - Setup MPC85xx RapidIO interface
+ * @fsl_rio_setup - Setup Freescale PowerPC RapidIO interface
  *
  * Initializes MPC85xx RapidIO hardware interface, configures
  * master port with system-specific info, and registers the
  * master port with the RapidIO subsystem.
  */
-void mpc85xx_rio_setup(int law_start, int law_size)
+int fsl_rio_setup(struct of_device *dev)
 {
 	struct rio_ops *ops;
 	struct rio_mport *port;
+	struct rio_priv *priv;
+	int rc = 0;
+	const u32 *dt_range, *cell;
+	struct resource regs;
+	int rlen;
+	u32 ccsr;
+	u64 law_start, law_size;
+	int paw, aw, sw;
+
+	if (!dev->node) {
+		dev_err(&dev->dev, "Device OF-Node is NULL");
+		return -EFAULT;
+	}
+
+	rc = of_address_to_resource(dev->node, 0, &regs);
+	if (rc) {
+		dev_err(&dev->dev, "Can't get %s property 'reg'\n",
+				dev->node->full_name);
+		return -EFAULT;
+	}
+	dev_info(&dev->dev, "Of-device full name %s\n", dev->node->full_name);
+	dev_info(&dev->dev, "Regs start 0x%08x size 0x%08x\n",	regs.start,
+						regs.end - regs.start + 1);
+
+	dt_range = of_get_property(dev->node, "ranges", &rlen);
+	if (!dt_range) {
+		dev_err(&dev->dev, "Can't get %s property 'ranges'\n",
+				dev->node->full_name);
+		return -EFAULT;
+	}
+
+	/* Get node address wide */
+	cell = of_get_property(dev->node, "#address-cells", NULL);
+	if (cell)
+		aw = *cell;
+	else
+		aw = of_n_addr_cells(dev->node);
+	/* Get node size wide */
+	cell = of_get_property(dev->node, "#size-cells", NULL);
+	if (cell)
+		sw = *cell;
+	else
+		sw = of_n_size_cells(dev->node);
+	/* Get parent address wide wide */
+	paw = of_n_addr_cells(dev->node);
+
+	law_start = of_read_number(dt_range + aw, paw);
+	law_size = of_read_number(dt_range + aw + paw, sw);
+
+	dev_info(&dev->dev, "LAW start 0x%016llx, size 0x%016llx.\n",
+			law_start, law_size);
 
 	ops = kmalloc(sizeof(struct rio_ops), GFP_KERNEL);
-	ops->lcread = mpc85xx_local_config_read;
-	ops->lcwrite = mpc85xx_local_config_write;
-	ops->cread = mpc85xx_rio_config_read;
-	ops->cwrite = mpc85xx_rio_config_write;
-	ops->dsend = mpc85xx_rio_doorbell_send;
+	ops->lcread = fsl_local_config_read;
+	ops->lcwrite = fsl_local_config_write;
+	ops->cread = fsl_rio_config_read;
+	ops->cwrite = fsl_rio_config_write;
+	ops->dsend = fsl_rio_doorbell_send;
 
-	port = kmalloc(sizeof(struct rio_mport), GFP_KERNEL);
+	port = kzalloc(sizeof(struct rio_mport), GFP_KERNEL);
 	port->id = 0;
 	port->index = 0;
+
+	priv = kzalloc(sizeof(struct rio_priv), GFP_KERNEL);
+	if (!priv) {
+		printk(KERN_ERR "Can't alloc memory for 'priv'\n");
+		rc = -ENOMEM;
+		goto err;
+	}
+
 	INIT_LIST_HEAD(&port->dbells);
 	port->iores.start = law_start;
 	port->iores.end = law_start + law_size;
 	port->iores.flags = IORESOURCE_MEM;
 
+	priv->bellirq = irq_of_parse_and_map(dev->node, 2);
+	priv->txirq = irq_of_parse_and_map(dev->node, 3);
+	priv->rxirq = irq_of_parse_and_map(dev->node, 4);
+	dev_info(&dev->dev, "bellirq: %d, txirq: %d, rxirq %d\n", priv->bellirq,
+				priv->txirq, priv->rxirq);
+
 	rio_init_dbell_res(&port->riores[RIO_DOORBELL_RESOURCE], 0, 0xffff);
 	rio_init_mbox_res(&port->riores[RIO_INB_MBOX_RESOURCE], 0, 0);
 	rio_init_mbox_res(&port->riores[RIO_OUTB_MBOX_RESOURCE], 0, 0);
 	strcpy(port->name, "RIO0 mport");
 
 	port->ops = ops;
-	port->host_deviceid = mpc85xx_rio_get_hdid(port->id);
+	port->host_deviceid = fsl_rio_get_hdid(port->id);
 
+	port->priv = priv;
 	rio_register_mport(port);
 
-	regs_win = (u32) ioremap(RIO_REGS_BASE, 0x20000);
-	atmu_regs = (struct rio_atmu_regs *)(regs_win + RIO_ATMU_REGS_OFFSET);
-	maint_atmu_regs = atmu_regs + 1;
-	dbell_atmu_regs = atmu_regs + 2;
-	msg_regs = (struct rio_msg_regs *)(regs_win + RIO_MSG_REGS_OFFSET);
+	priv->regs_win = ioremap(regs.start, regs.end - regs.start + 1);
+
+	/* Probe the master port phy type */
+	ccsr = in_be32(priv->regs_win + RIO_CCSR);
+	port->phy_type = (ccsr & 1) ? RIO_PHY_SERIAL : RIO_PHY_PARALLEL;
+	dev_info(&dev->dev, "RapidIO PHY type: %s\n",
+			(port->phy_type == RIO_PHY_PARALLEL) ? "parallel" :
+			((port->phy_type == RIO_PHY_SERIAL) ? "serial" :
+			 "unknown"));
+	/* Checking the port training status */
+	if (in_be32((priv->regs_win + RIO_ESCSR)) & 1) {
+		dev_err(&dev->dev, "Port is not ready. "
+				   "Try to restart connection...\n");
+		switch (port->phy_type) {
+		case RIO_PHY_SERIAL:
+			/* Disable ports */
+			out_be32(priv->regs_win + RIO_CCSR, 0);
+			/* Set 1x lane */
+			setbits32(priv->regs_win + RIO_CCSR, 0x02000000);
+			/* Enable ports */
+			setbits32(priv->regs_win + RIO_CCSR, 0x00600000);
+			break;
+		case RIO_PHY_PARALLEL:
+			/* Disable ports */
+			out_be32(priv->regs_win + RIO_CCSR, 0x22000000);
+			/* Enable ports */
+			out_be32(priv->regs_win + RIO_CCSR, 0x44000000);
+			break;
+		}
+		msleep(100);
+		if (in_be32((priv->regs_win + RIO_ESCSR)) & 1) {
+			dev_err(&dev->dev, "Port restart failed.\n");
+			rc = -ENOLINK;
+			goto err;
+		}
+		dev_info(&dev->dev, "Port restart success!\n");
+	}
+	fsl_rio_info(&dev->dev, ccsr);
+
+	port->sys_size = (in_be32((priv->regs_win + RIO_PEF_CAR))
+					& RIO_PEF_CTLS) >> 4;
+	dev_info(&dev->dev, "RapidIO Common Transport System size: %d\n",
+			port->sys_size ? 65536 : 256);
+
+	priv->atmu_regs = (struct rio_atmu_regs *)(priv->regs_win
+					+ RIO_ATMU_REGS_OFFSET);
+	priv->maint_atmu_regs = priv->atmu_regs + 1;
+	priv->dbell_atmu_regs = priv->atmu_regs + 2;
+	priv->msg_regs = (struct rio_msg_regs *)(priv->regs_win +
+				((port->phy_type == RIO_PHY_SERIAL) ?
+				RIO_S_MSG_REGS_OFFSET : RIO_P_MSG_REGS_OFFSET));
+
+	/* Set to receive any dist ID for serial RapidIO controller. */
+	if (port->phy_type == RIO_PHY_SERIAL)
+		out_be32((priv->regs_win + RIO_ISR_AACR), RIO_ISR_AACR_AA);
 
 	/* Configure maintenance transaction window */
-	out_be32((void *)&maint_atmu_regs->rowbar, 0x000c0000);
-	out_be32((void *)&maint_atmu_regs->rowar, 0x80077015);
+	out_be32(&priv->maint_atmu_regs->rowbar, 0x000c0000);
+	out_be32(&priv->maint_atmu_regs->rowar, 0x80077015);
 
-	maint_win = (u32) ioremap(law_start, RIO_MAINT_WIN_SIZE);
+	priv->maint_win = ioremap(law_start, RIO_MAINT_WIN_SIZE);
 
 	/* Configure outbound doorbell window */
-	out_be32((void *)&dbell_atmu_regs->rowbar, 0x000c0400);
-	out_be32((void *)&dbell_atmu_regs->rowar, 0x8004200b);
-	mpc85xx_rio_doorbell_init(port);
+	out_be32(&priv->dbell_atmu_regs->rowbar, 0x000c0400);
+	out_be32(&priv->dbell_atmu_regs->rowar, 0x8004200b);
+	fsl_rio_doorbell_init(port);
+
+	return 0;
+err:
+	if (priv)
+		iounmap(priv->regs_win);
+	kfree(ops);
+	kfree(priv);
+	kfree(port);
+	return rc;
+}
+
+/* The probe function for RapidIO peer-to-peer network.
+ */
+static int __devinit fsl_of_rio_rpn_probe(struct of_device *dev,
+				     const struct of_device_id *match)
+{
+	int rc;
+	printk(KERN_INFO "Setting up RapidIO peer-to-peer network %s\n",
+			dev->node->full_name);
+
+	rc = fsl_rio_setup(dev);
+	if (rc)
+		goto out;
+
+	/* Enumerate all registered ports */
+	rc = rio_init_mports();
+out:
+	return rc;
+};
+
+static const struct of_device_id fsl_of_rio_rpn_ids[] = {
+	{
+		.compatible = "fsl,rapidio-delta",
+	},
+	{},
+};
+
+static struct of_platform_driver fsl_of_rio_rpn_driver = {
+	.name = "fsl-of-rio",
+	.match_table = fsl_of_rio_rpn_ids,
+	.probe = fsl_of_rio_rpn_probe,
+};
+
+static __init int fsl_of_rio_rpn_init(void)
+{
+	return of_register_platform_driver(&fsl_of_rio_rpn_driver);
 }
+
+subsys_initcall(fsl_of_rio_rpn_init);
diff --git a/trunk/arch/powerpc/sysdev/fsl_rio.h b/trunk/arch/powerpc/sysdev/fsl_rio.h
deleted file mode 100644
index 6d3ff30b1579..000000000000
--- a/trunk/arch/powerpc/sysdev/fsl_rio.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * MPC85xx RapidIO definitions
- *
- * Copyright 2005 MontaVista Software, Inc.
- * Matt Porter <mporter@kernel.crashing.org>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#ifndef __PPC_SYSLIB_PPC85XX_RIO_H
-#define __PPC_SYSLIB_PPC85XX_RIO_H
-
-#include <linux/init.h>
-
-extern void mpc85xx_rio_setup(int law_start, int law_size);
-
-#endif				/* __PPC_SYSLIB_PPC85XX_RIO_H */
diff --git a/trunk/arch/powerpc/sysdev/fsl_soc.c b/trunk/arch/powerpc/sysdev/fsl_soc.c
index 5c1b246aaccc..7b45670c7af3 100644
--- a/trunk/arch/powerpc/sysdev/fsl_soc.c
+++ b/trunk/arch/powerpc/sysdev/fsl_soc.c
@@ -892,3 +892,44 @@ void fsl_rstcr_restart(char *cmd)
 	while (1) ;
 }
 #endif
+
+#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+struct platform_diu_data_ops diu_ops = {
+	.diu_size = 1280 * 1024 * 4,	/* default one 1280x1024 buffer */
+};
+EXPORT_SYMBOL(diu_ops);
+
+int __init preallocate_diu_videomemory(void)
+{
+	pr_debug("diu_size=%lu\n", diu_ops.diu_size);
+
+	diu_ops.diu_mem = __alloc_bootmem(diu_ops.diu_size, 8, 0);
+	if (!diu_ops.diu_mem) {
+		printk(KERN_ERR "fsl-diu: cannot allocate %lu bytes\n",
+			diu_ops.diu_size);
+		return -ENOMEM;
+	}
+
+	pr_debug("diu_mem=%p\n", diu_ops.diu_mem);
+
+	rh_init(&diu_ops.diu_rh_info, 4096, ARRAY_SIZE(diu_ops.diu_rh_block),
+		diu_ops.diu_rh_block);
+	return rh_attach_region(&diu_ops.diu_rh_info,
+				(unsigned long) diu_ops.diu_mem,
+				diu_ops.diu_size);
+}
+
+static int __init early_parse_diufb(char *p)
+{
+	if (!p)
+		return 1;
+
+	diu_ops.diu_size = _ALIGN_UP(memparse(p, &p), 8);
+
+	pr_debug("diu_size=%lu\n", diu_ops.diu_size);
+
+	return 0;
+}
+early_param("diufb", early_parse_diufb);
+
+#endif
diff --git a/trunk/arch/powerpc/sysdev/fsl_soc.h b/trunk/arch/powerpc/sysdev/fsl_soc.h
index 74c4a9657b33..52c831fa1886 100644
--- a/trunk/arch/powerpc/sysdev/fsl_soc.h
+++ b/trunk/arch/powerpc/sysdev/fsl_soc.h
@@ -17,5 +17,28 @@ extern int fsl_spi_init(struct spi_board_info *board_infos,
 			void (*deactivate_cs)(u8 cs, u8 polarity));
 
 extern void fsl_rstcr_restart(char *cmd);
+
+#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+#include <linux/bootmem.h>
+#include <asm/rheap.h>
+struct platform_diu_data_ops {
+	rh_block_t diu_rh_block[16];
+	rh_info_t diu_rh_info;
+	unsigned long diu_size;
+	void *diu_mem;
+
+	unsigned int (*get_pixel_format) (unsigned int bits_per_pixel,
+		int monitor_port);
+	void (*set_gamma_table) (int monitor_port, char *gamma_table_base);
+	void (*set_monitor_port) (int monitor_port);
+	void (*set_pixel_clock) (unsigned int pixclock);
+	ssize_t (*show_monitor_port) (int monitor_port, char *buf);
+	int (*set_sysfs_monitor_port) (int val);
+};
+
+extern struct platform_diu_data_ops diu_ops;
+int __init preallocate_diu_videomemory(void);
+#endif
+
 #endif
 #endif
diff --git a/trunk/arch/ppc/kernel/asm-offsets.c b/trunk/arch/ppc/kernel/asm-offsets.c
index a51a17714231..8dcbdd6c2d2c 100644
--- a/trunk/arch/ppc/kernel/asm-offsets.c
+++ b/trunk/arch/ppc/kernel/asm-offsets.c
@@ -18,6 +18,8 @@
 #include <linux/suspend.h>
 #include <linux/mman.h>
 #include <linux/mm.h>
+#include <linux/kbuild.h>
+
 #include <asm/io.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -26,11 +28,6 @@
 #include <asm/thread_info.h>
 #include <asm/vdso_datapage.h>
 
-#define DEFINE(sym, val) \
-	asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
-
 int
 main(void)
 {
diff --git a/trunk/arch/ppc/kernel/pci.c b/trunk/arch/ppc/kernel/pci.c
index 50ce83f20adb..df3ef6db072c 100644
--- a/trunk/arch/ppc/kernel/pci.c
+++ b/trunk/arch/ppc/kernel/pci.c
@@ -1121,8 +1121,8 @@ void __init pci_init_resource(struct resource *res, resource_size_t start,
 
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max)
 {
-	unsigned long start = pci_resource_start(dev, bar);
-	unsigned long len = pci_resource_len(dev, bar);
+	resource_size_t start = pci_resource_start(dev, bar);
+	resource_size_t len = pci_resource_len(dev, bar);
 	unsigned long flags = pci_resource_flags(dev, bar);
 
 	if (!len)
diff --git a/trunk/arch/ppc/platforms/sbc82xx.c b/trunk/arch/ppc/platforms/sbc82xx.c
index 0df6aacb8237..24f6e0694ac1 100644
--- a/trunk/arch/ppc/platforms/sbc82xx.c
+++ b/trunk/arch/ppc/platforms/sbc82xx.c
@@ -30,8 +30,6 @@ static void (*callback_init_IRQ)(void);
 
 extern unsigned char __res[sizeof(bd_t)];
 
-extern void (*late_time_init)(void);
-
 #ifdef CONFIG_GEN_RTC
 TODC_ALLOC();
 
diff --git a/trunk/arch/s390/Kconfig b/trunk/arch/s390/Kconfig
index f6a68e178fc5..8f5f02160ffc 100644
--- a/trunk/arch/s390/Kconfig
+++ b/trunk/arch/s390/Kconfig
@@ -62,6 +62,10 @@ config GENERIC_LOCKBREAK
 	default y
 	depends on SMP && PREEMPT
 
+config PGSTE
+	bool
+	default y if KVM
+
 mainmenu "Linux Kernel Configuration"
 
 config S390
@@ -69,6 +73,7 @@ config S390
 	select HAVE_OPROFILE
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
+	select HAVE_KVM if 64BIT
 
 source "init/Kconfig"
 
@@ -515,6 +520,13 @@ config ZFCPDUMP
 	  Select this option if you want to build an zfcpdump enabled kernel.
 	  Refer to <file:Documentation/s390/zfcpdump.txt> for more details on this.
 
+config S390_GUEST
+bool "s390 guest support (EXPERIMENTAL)"
+	depends on 64BIT && EXPERIMENTAL
+	select VIRTIO
+	select VIRTIO_RING
+	help
+	  Select this option if you want to run the kernel under s390 linux
 endmenu
 
 source "net/Kconfig"
@@ -536,3 +548,5 @@ source "security/Kconfig"
 source "crypto/Kconfig"
 
 source "lib/Kconfig"
+
+source "arch/s390/kvm/Kconfig"
diff --git a/trunk/arch/s390/Makefile b/trunk/arch/s390/Makefile
index f708be367b03..792a4e7743ce 100644
--- a/trunk/arch/s390/Makefile
+++ b/trunk/arch/s390/Makefile
@@ -87,7 +87,7 @@ LDFLAGS_vmlinux := -e start
 head-y		:= arch/s390/kernel/head.o arch/s390/kernel/init_task.o
 
 core-y		+= arch/s390/mm/ arch/s390/kernel/ arch/s390/crypto/ \
-		   arch/s390/appldata/ arch/s390/hypfs/
+		   arch/s390/appldata/ arch/s390/hypfs/ arch/s390/kvm/
 libs-y		+= arch/s390/lib/
 drivers-y	+= drivers/s390/
 drivers-$(CONFIG_MATHEMU) += arch/s390/math-emu/
diff --git a/trunk/arch/s390/kernel/asm-offsets.c b/trunk/arch/s390/kernel/asm-offsets.c
index 1375f8a4469e..fa28ecae636b 100644
--- a/trunk/arch/s390/kernel/asm-offsets.c
+++ b/trunk/arch/s390/kernel/asm-offsets.c
@@ -5,44 +5,38 @@
  */
 
 #include <linux/sched.h>
-
-/* Use marker if you need to separate the values later */
-
-#define DEFINE(sym, val, marker) \
-	asm volatile("\n->" #sym " %0 " #val " " #marker : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
+#include <linux/kbuild.h>
 
 int main(void)
 {
-	DEFINE(__THREAD_info, offsetof(struct task_struct, stack),);
-	DEFINE(__THREAD_ksp, offsetof(struct task_struct, thread.ksp),);
-	DEFINE(__THREAD_per, offsetof(struct task_struct, thread.per_info),);
+	DEFINE(__THREAD_info, offsetof(struct task_struct, stack));
+	DEFINE(__THREAD_ksp, offsetof(struct task_struct, thread.ksp));
+	DEFINE(__THREAD_per, offsetof(struct task_struct, thread.per_info));
 	DEFINE(__THREAD_mm_segment,
-	       offsetof(struct task_struct, thread.mm_segment),);
+	       offsetof(struct task_struct, thread.mm_segment));
 	BLANK();
-	DEFINE(__TASK_pid, offsetof(struct task_struct, pid),);
+	DEFINE(__TASK_pid, offsetof(struct task_struct, pid));
 	BLANK();
-	DEFINE(__PER_atmid, offsetof(per_struct, lowcore.words.perc_atmid),);
-	DEFINE(__PER_address, offsetof(per_struct, lowcore.words.address),);
-	DEFINE(__PER_access_id, offsetof(per_struct, lowcore.words.access_id),);
+	DEFINE(__PER_atmid, offsetof(per_struct, lowcore.words.perc_atmid));
+	DEFINE(__PER_address, offsetof(per_struct, lowcore.words.address));
+	DEFINE(__PER_access_id, offsetof(per_struct, lowcore.words.access_id));
 	BLANK();
-	DEFINE(__TI_task, offsetof(struct thread_info, task),);
-	DEFINE(__TI_domain, offsetof(struct thread_info, exec_domain),);
-	DEFINE(__TI_flags, offsetof(struct thread_info, flags),);
-	DEFINE(__TI_cpu, offsetof(struct thread_info, cpu),);
-	DEFINE(__TI_precount, offsetof(struct thread_info, preempt_count),);
+	DEFINE(__TI_task, offsetof(struct thread_info, task));
+	DEFINE(__TI_domain, offsetof(struct thread_info, exec_domain));
+	DEFINE(__TI_flags, offsetof(struct thread_info, flags));
+	DEFINE(__TI_cpu, offsetof(struct thread_info, cpu));
+	DEFINE(__TI_precount, offsetof(struct thread_info, preempt_count));
 	BLANK();
-	DEFINE(__PT_ARGS, offsetof(struct pt_regs, args),);
-	DEFINE(__PT_PSW, offsetof(struct pt_regs, psw),);
-	DEFINE(__PT_GPRS, offsetof(struct pt_regs, gprs),);
-	DEFINE(__PT_ORIG_GPR2, offsetof(struct pt_regs, orig_gpr2),);
-	DEFINE(__PT_ILC, offsetof(struct pt_regs, ilc),);
-	DEFINE(__PT_TRAP, offsetof(struct pt_regs, trap),);
-	DEFINE(__PT_SIZE, sizeof(struct pt_regs),);
+	DEFINE(__PT_ARGS, offsetof(struct pt_regs, args));
+	DEFINE(__PT_PSW, offsetof(struct pt_regs, psw));
+	DEFINE(__PT_GPRS, offsetof(struct pt_regs, gprs));
+	DEFINE(__PT_ORIG_GPR2, offsetof(struct pt_regs, orig_gpr2));
+	DEFINE(__PT_ILC, offsetof(struct pt_regs, ilc));
+	DEFINE(__PT_TRAP, offsetof(struct pt_regs, trap));
+	DEFINE(__PT_SIZE, sizeof(struct pt_regs));
 	BLANK();
-	DEFINE(__SF_BACKCHAIN, offsetof(struct stack_frame, back_chain),);
-	DEFINE(__SF_GPRS, offsetof(struct stack_frame, gprs),);
-	DEFINE(__SF_EMPTY, offsetof(struct stack_frame, empty1),);
+	DEFINE(__SF_BACKCHAIN, offsetof(struct stack_frame, back_chain));
+	DEFINE(__SF_GPRS, offsetof(struct stack_frame, gprs));
+	DEFINE(__SF_EMPTY, offsetof(struct stack_frame, empty1));
 	return 0;
 }
diff --git a/trunk/arch/s390/kernel/early.c b/trunk/arch/s390/kernel/early.c
index 540a67f979b6..68ec4083bf73 100644
--- a/trunk/arch/s390/kernel/early.c
+++ b/trunk/arch/s390/kernel/early.c
@@ -144,6 +144,10 @@ static noinline __init void detect_machine_type(void)
 	/* Running on a P/390 ? */
 	if (cpuinfo->cpu_id.machine == 0x7490)
 		machine_flags |= 4;
+
+	/* Running under KVM ? */
+	if (cpuinfo->cpu_id.version == 0xfe)
+		machine_flags |= 64;
 }
 
 #ifdef CONFIG_64BIT
diff --git a/trunk/arch/s390/kernel/irq.c b/trunk/arch/s390/kernel/irq.c
index c36d8123ca14..c59a86dca584 100644
--- a/trunk/arch/s390/kernel/irq.c
+++ b/trunk/arch/s390/kernel/irq.c
@@ -60,8 +60,6 @@ init_IRQ(void)
 /*
  * Switch to the asynchronous interrupt stack for softirq execution.
  */
-extern void __do_softirq(void);
-
 asmlinkage void do_softirq(void)
 {
 	unsigned long flags, old, new;
diff --git a/trunk/arch/s390/kernel/setup.c b/trunk/arch/s390/kernel/setup.c
index 7141147e6b63..a9d18aafa5f4 100644
--- a/trunk/arch/s390/kernel/setup.c
+++ b/trunk/arch/s390/kernel/setup.c
@@ -316,7 +316,11 @@ static int __init early_parse_ipldelay(char *p)
 early_param("ipldelay", early_parse_ipldelay);
 
 #ifdef CONFIG_S390_SWITCH_AMODE
+#ifdef CONFIG_PGSTE
+unsigned int switch_amode = 1;
+#else
 unsigned int switch_amode = 0;
+#endif
 EXPORT_SYMBOL_GPL(switch_amode);
 
 static void set_amode_and_uaccess(unsigned long user_amode,
@@ -797,9 +801,13 @@ setup_arch(char **cmdline_p)
 	       "This machine has an IEEE fpu\n" :
 	       "This machine has no IEEE fpu\n");
 #else /* CONFIG_64BIT */
-	printk((MACHINE_IS_VM) ?
-	       "We are running under VM (64 bit mode)\n" :
-	       "We are running native (64 bit mode)\n");
+	if (MACHINE_IS_VM)
+		printk("We are running under VM (64 bit mode)\n");
+	else if (MACHINE_IS_KVM) {
+		printk("We are running under KVM (64 bit mode)\n");
+		add_preferred_console("ttyS", 1, NULL);
+	} else
+		printk("We are running native (64 bit mode)\n");
 #endif /* CONFIG_64BIT */
 
 	/* Save unparsed command line copy for /proc/cmdline */
diff --git a/trunk/arch/s390/kernel/vtime.c b/trunk/arch/s390/kernel/vtime.c
index c5f05b3fb2c3..ca90ee3f930e 100644
--- a/trunk/arch/s390/kernel/vtime.c
+++ b/trunk/arch/s390/kernel/vtime.c
@@ -110,6 +110,7 @@ void account_system_vtime(struct task_struct *tsk)
 	S390_lowcore.steal_clock -= cputime << 12;
 	account_system_time(tsk, 0, cputime);
 }
+EXPORT_SYMBOL_GPL(account_system_vtime);
 
 static inline void set_vtimer(__u64 expires)
 {
diff --git a/trunk/arch/s390/kvm/Kconfig b/trunk/arch/s390/kvm/Kconfig
new file mode 100644
index 000000000000..1761b74d639b
--- /dev/null
+++ b/trunk/arch/s390/kvm/Kconfig
@@ -0,0 +1,46 @@
+#
+# KVM configuration
+#
+config HAVE_KVM
+       bool
+
+menuconfig VIRTUALIZATION
+	bool "Virtualization"
+	default y
+	---help---
+	  Say Y here to get to see options for using your Linux host to run other
+	  operating systems inside virtual machines (guests).
+	  This option alone does not add any kernel code.
+
+	  If you say N, all options in this submenu will be skipped and disabled.
+
+if VIRTUALIZATION
+
+config KVM
+	tristate "Kernel-based Virtual Machine (KVM) support"
+	depends on HAVE_KVM && EXPERIMENTAL
+	select PREEMPT_NOTIFIERS
+	select ANON_INODES
+	select S390_SWITCH_AMODE
+	select PREEMPT
+	---help---
+	  Support hosting paravirtualized guest machines using the SIE
+	  virtualization capability on the mainframe. This should work
+	  on any 64bit machine.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  To compile this as a module, choose M here: the module
+	  will be called kvm.
+
+	  If unsure, say N.
+
+config KVM_TRACE
+       bool
+
+# OK, it's a little counter-intuitive to do this, but it puts it neatly under
+# the virtualization menu.
+source drivers/virtio/Kconfig
+
+endif # VIRTUALIZATION
diff --git a/trunk/arch/s390/kvm/Makefile b/trunk/arch/s390/kvm/Makefile
new file mode 100644
index 000000000000..e5221ec0b8e3
--- /dev/null
+++ b/trunk/arch/s390/kvm/Makefile
@@ -0,0 +1,14 @@
+# Makefile for kernel virtual machines on s390
+#
+# Copyright IBM Corp. 2008
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License (version 2 only)
+# as published by the Free Software Foundation.
+
+common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o)
+
+EXTRA_CFLAGS += -Ivirt/kvm -Iarch/s390/kvm
+
+kvm-objs := $(common-objs) kvm-s390.o sie64a.o intercept.o interrupt.o priv.o sigp.o diag.o
+obj-$(CONFIG_KVM) += kvm.o
diff --git a/trunk/arch/s390/kvm/diag.c b/trunk/arch/s390/kvm/diag.c
new file mode 100644
index 000000000000..f639a152869f
--- /dev/null
+++ b/trunk/arch/s390/kvm/diag.c
@@ -0,0 +1,67 @@
+/*
+ * diag.c - handling diagnose instructions
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include "kvm-s390.h"
+
+static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
+{
+	VCPU_EVENT(vcpu, 5, "%s", "diag time slice end");
+	vcpu->stat.diagnose_44++;
+	vcpu_put(vcpu);
+	schedule();
+	vcpu_load(vcpu);
+	return 0;
+}
+
+static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
+{
+	unsigned int reg = vcpu->arch.sie_block->ipa & 0xf;
+	unsigned long subcode = vcpu->arch.guest_gprs[reg] & 0xffff;
+
+	VCPU_EVENT(vcpu, 5, "diag ipl functions, subcode %lx", subcode);
+	switch (subcode) {
+	case 3:
+		vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR;
+		break;
+	case 4:
+		vcpu->run->s390_reset_flags = 0;
+		break;
+	default:
+		return -ENOTSUPP;
+	}
+
+	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM;
+	vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL;
+	vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT;
+	vcpu->run->exit_reason = KVM_EXIT_S390_RESET;
+	VCPU_EVENT(vcpu, 3, "requesting userspace resets %lx",
+	  vcpu->run->s390_reset_flags);
+	return -EREMOTE;
+}
+
+int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
+{
+	int code = (vcpu->arch.sie_block->ipb & 0xfff0000) >> 16;
+
+	switch (code) {
+	case 0x44:
+		return __diag_time_slice_end(vcpu);
+	case 0x308:
+		return __diag_ipl_functions(vcpu);
+	default:
+		return -ENOTSUPP;
+	}
+}
diff --git a/trunk/arch/s390/kvm/gaccess.h b/trunk/arch/s390/kvm/gaccess.h
new file mode 100644
index 000000000000..4e0633c413f3
--- /dev/null
+++ b/trunk/arch/s390/kvm/gaccess.h
@@ -0,0 +1,274 @@
+/*
+ * gaccess.h -  access guest memory
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ */
+
+#ifndef __KVM_S390_GACCESS_H
+#define __KVM_S390_GACCESS_H
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+#include <asm/uaccess.h>
+
+static inline void __user *__guestaddr_to_user(struct kvm_vcpu *vcpu,
+					       u64 guestaddr)
+{
+	u64 prefix  = vcpu->arch.sie_block->prefix;
+	u64 origin  = vcpu->kvm->arch.guest_origin;
+	u64 memsize = vcpu->kvm->arch.guest_memsize;
+
+	if (guestaddr < 2 * PAGE_SIZE)
+		guestaddr += prefix;
+	else if ((guestaddr >= prefix) && (guestaddr < prefix + 2 * PAGE_SIZE))
+		guestaddr -= prefix;
+
+	if (guestaddr > memsize)
+		return (void __user __force *) ERR_PTR(-EFAULT);
+
+	guestaddr += origin;
+
+	return (void __user *) guestaddr;
+}
+
+static inline int get_guest_u64(struct kvm_vcpu *vcpu, u64 guestaddr,
+				u64 *result)
+{
+	void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+	BUG_ON(guestaddr & 7);
+
+	if (IS_ERR((void __force *) uptr))
+		return PTR_ERR((void __force *) uptr);
+
+	return get_user(*result, (u64 __user *) uptr);
+}
+
+static inline int get_guest_u32(struct kvm_vcpu *vcpu, u64 guestaddr,
+				u32 *result)
+{
+	void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+	BUG_ON(guestaddr & 3);
+
+	if (IS_ERR((void __force *) uptr))
+		return PTR_ERR((void __force *) uptr);
+
+	return get_user(*result, (u32 __user *) uptr);
+}
+
+static inline int get_guest_u16(struct kvm_vcpu *vcpu, u64 guestaddr,
+				u16 *result)
+{
+	void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+	BUG_ON(guestaddr & 1);
+
+	if (IS_ERR(uptr))
+		return PTR_ERR(uptr);
+
+	return get_user(*result, (u16 __user *) uptr);
+}
+
+static inline int get_guest_u8(struct kvm_vcpu *vcpu, u64 guestaddr,
+			       u8 *result)
+{
+	void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+	if (IS_ERR((void __force *) uptr))
+		return PTR_ERR((void __force *) uptr);
+
+	return get_user(*result, (u8 __user *) uptr);
+}
+
+static inline int put_guest_u64(struct kvm_vcpu *vcpu, u64 guestaddr,
+				u64 value)
+{
+	void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+	BUG_ON(guestaddr & 7);
+
+	if (IS_ERR((void __force *) uptr))
+		return PTR_ERR((void __force *) uptr);
+
+	return put_user(value, (u64 __user *) uptr);
+}
+
+static inline int put_guest_u32(struct kvm_vcpu *vcpu, u64 guestaddr,
+				u32 value)
+{
+	void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+	BUG_ON(guestaddr & 3);
+
+	if (IS_ERR((void __force *) uptr))
+		return PTR_ERR((void __force *) uptr);
+
+	return put_user(value, (u32 __user *) uptr);
+}
+
+static inline int put_guest_u16(struct kvm_vcpu *vcpu, u64 guestaddr,
+				u16 value)
+{
+	void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+	BUG_ON(guestaddr & 1);
+
+	if (IS_ERR((void __force *) uptr))
+		return PTR_ERR((void __force *) uptr);
+
+	return put_user(value, (u16 __user *) uptr);
+}
+
+static inline int put_guest_u8(struct kvm_vcpu *vcpu, u64 guestaddr,
+			       u8 value)
+{
+	void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+	if (IS_ERR((void __force *) uptr))
+		return PTR_ERR((void __force *) uptr);
+
+	return put_user(value, (u8 __user *) uptr);
+}
+
+
+static inline int __copy_to_guest_slow(struct kvm_vcpu *vcpu, u64 guestdest,
+				       const void *from, unsigned long n)
+{
+	int rc;
+	unsigned long i;
+	const u8 *data = from;
+
+	for (i = 0; i < n; i++) {
+		rc = put_guest_u8(vcpu, guestdest++, *(data++));
+		if (rc < 0)
+			return rc;
+	}
+	return 0;
+}
+
+static inline int copy_to_guest(struct kvm_vcpu *vcpu, u64 guestdest,
+				const void *from, unsigned long n)
+{
+	u64 prefix  = vcpu->arch.sie_block->prefix;
+	u64 origin  = vcpu->kvm->arch.guest_origin;
+	u64 memsize = vcpu->kvm->arch.guest_memsize;
+
+	if ((guestdest < 2 * PAGE_SIZE) && (guestdest + n > 2 * PAGE_SIZE))
+		goto slowpath;
+
+	if ((guestdest < prefix) && (guestdest + n > prefix))
+		goto slowpath;
+
+	if ((guestdest < prefix + 2 * PAGE_SIZE)
+	    && (guestdest + n > prefix + 2 * PAGE_SIZE))
+		goto slowpath;
+
+	if (guestdest < 2 * PAGE_SIZE)
+		guestdest += prefix;
+	else if ((guestdest >= prefix) && (guestdest < prefix + 2 * PAGE_SIZE))
+		guestdest -= prefix;
+
+	if (guestdest + n > memsize)
+		return -EFAULT;
+
+	if (guestdest + n < guestdest)
+		return -EFAULT;
+
+	guestdest += origin;
+
+	return copy_to_user((void __user *) guestdest, from, n);
+slowpath:
+	return __copy_to_guest_slow(vcpu, guestdest, from, n);
+}
+
+static inline int __copy_from_guest_slow(struct kvm_vcpu *vcpu, void *to,
+					 u64 guestsrc, unsigned long n)
+{
+	int rc;
+	unsigned long i;
+	u8 *data = to;
+
+	for (i = 0; i < n; i++) {
+		rc = get_guest_u8(vcpu, guestsrc++, data++);
+		if (rc < 0)
+			return rc;
+	}
+	return 0;
+}
+
+static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to,
+				  u64 guestsrc, unsigned long n)
+{
+	u64 prefix  = vcpu->arch.sie_block->prefix;
+	u64 origin  = vcpu->kvm->arch.guest_origin;
+	u64 memsize = vcpu->kvm->arch.guest_memsize;
+
+	if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE))
+		goto slowpath;
+
+	if ((guestsrc < prefix) && (guestsrc + n > prefix))
+		goto slowpath;
+
+	if ((guestsrc < prefix + 2 * PAGE_SIZE)
+	    && (guestsrc + n > prefix + 2 * PAGE_SIZE))
+		goto slowpath;
+
+	if (guestsrc < 2 * PAGE_SIZE)
+		guestsrc += prefix;
+	else if ((guestsrc >= prefix) && (guestsrc < prefix + 2 * PAGE_SIZE))
+		guestsrc -= prefix;
+
+	if (guestsrc + n > memsize)
+		return -EFAULT;
+
+	if (guestsrc + n < guestsrc)
+		return -EFAULT;
+
+	guestsrc += origin;
+
+	return copy_from_user(to, (void __user *) guestsrc, n);
+slowpath:
+	return __copy_from_guest_slow(vcpu, to, guestsrc, n);
+}
+
+static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu, u64 guestdest,
+					 const void *from, unsigned long n)
+{
+	u64 origin  = vcpu->kvm->arch.guest_origin;
+	u64 memsize = vcpu->kvm->arch.guest_memsize;
+
+	if (guestdest + n > memsize)
+		return -EFAULT;
+
+	if (guestdest + n < guestdest)
+		return -EFAULT;
+
+	guestdest += origin;
+
+	return copy_to_user((void __user *) guestdest, from, n);
+}
+
+static inline int copy_from_guest_absolute(struct kvm_vcpu *vcpu, void *to,
+					   u64 guestsrc, unsigned long n)
+{
+	u64 origin  = vcpu->kvm->arch.guest_origin;
+	u64 memsize = vcpu->kvm->arch.guest_memsize;
+
+	if (guestsrc + n > memsize)
+		return -EFAULT;
+
+	if (guestsrc + n < guestsrc)
+		return -EFAULT;
+
+	guestsrc += origin;
+
+	return copy_from_user(to, (void __user *) guestsrc, n);
+}
+#endif
diff --git a/trunk/arch/s390/kvm/intercept.c b/trunk/arch/s390/kvm/intercept.c
new file mode 100644
index 000000000000..349581a26103
--- /dev/null
+++ b/trunk/arch/s390/kvm/intercept.c
@@ -0,0 +1,216 @@
+/*
+ * intercept.c - in-kernel handling for sie intercepts
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/errno.h>
+#include <linux/pagemap.h>
+
+#include <asm/kvm_host.h>
+
+#include "kvm-s390.h"
+#include "gaccess.h"
+
+static int handle_lctg(struct kvm_vcpu *vcpu)
+{
+	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
+	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
+	int base2 = vcpu->arch.sie_block->ipb >> 28;
+	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
+			((vcpu->arch.sie_block->ipb & 0xff00) << 4);
+	u64 useraddr;
+	int reg, rc;
+
+	vcpu->stat.instruction_lctg++;
+	if ((vcpu->arch.sie_block->ipb & 0xff) != 0x2f)
+		return -ENOTSUPP;
+
+	useraddr = disp2;
+	if (base2)
+		useraddr += vcpu->arch.guest_gprs[base2];
+
+	reg = reg1;
+
+	VCPU_EVENT(vcpu, 5, "lctg r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2,
+		   disp2);
+
+	do {
+		rc = get_guest_u64(vcpu, useraddr,
+				   &vcpu->arch.sie_block->gcr[reg]);
+		if (rc == -EFAULT) {
+			kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+			break;
+		}
+		useraddr += 8;
+		if (reg == reg3)
+			break;
+		reg = (reg + 1) % 16;
+	} while (1);
+	return 0;
+}
+
+static int handle_lctl(struct kvm_vcpu *vcpu)
+{
+	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
+	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
+	int base2 = vcpu->arch.sie_block->ipb >> 28;
+	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+	u64 useraddr;
+	u32 val = 0;
+	int reg, rc;
+
+	vcpu->stat.instruction_lctl++;
+
+	useraddr = disp2;
+	if (base2)
+		useraddr += vcpu->arch.guest_gprs[base2];
+
+	VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2,
+		   disp2);
+
+	reg = reg1;
+	do {
+		rc = get_guest_u32(vcpu, useraddr, &val);
+		if (rc == -EFAULT) {
+			kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+			break;
+		}
+		vcpu->arch.sie_block->gcr[reg] &= 0xffffffff00000000ul;
+		vcpu->arch.sie_block->gcr[reg] |= val;
+		useraddr += 4;
+		if (reg == reg3)
+			break;
+		reg = (reg + 1) % 16;
+	} while (1);
+	return 0;
+}
+
+static intercept_handler_t instruction_handlers[256] = {
+	[0x83] = kvm_s390_handle_diag,
+	[0xae] = kvm_s390_handle_sigp,
+	[0xb2] = kvm_s390_handle_priv,
+	[0xb7] = handle_lctl,
+	[0xeb] = handle_lctg,
+};
+
+static int handle_noop(struct kvm_vcpu *vcpu)
+{
+	switch (vcpu->arch.sie_block->icptcode) {
+	case 0x10:
+		vcpu->stat.exit_external_request++;
+		break;
+	case 0x14:
+		vcpu->stat.exit_external_interrupt++;
+		break;
+	default:
+		break; /* nothing */
+	}
+	return 0;
+}
+
+static int handle_stop(struct kvm_vcpu *vcpu)
+{
+	int rc;
+
+	vcpu->stat.exit_stop_request++;
+	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	spin_lock_bh(&vcpu->arch.local_int.lock);
+	if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
+		vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
+		rc = __kvm_s390_vcpu_store_status(vcpu,
+						  KVM_S390_STORE_STATUS_NOADDR);
+		if (rc >= 0)
+			rc = -ENOTSUPP;
+	}
+
+	if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) {
+		vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP;
+		VCPU_EVENT(vcpu, 3, "%s", "cpu stopped");
+		rc = -ENOTSUPP;
+	} else
+		rc = 0;
+	spin_unlock_bh(&vcpu->arch.local_int.lock);
+	return rc;
+}
+
+static int handle_validity(struct kvm_vcpu *vcpu)
+{
+	int viwhy = vcpu->arch.sie_block->ipb >> 16;
+	vcpu->stat.exit_validity++;
+	if (viwhy == 0x37) {
+		fault_in_pages_writeable((char __user *)
+					 vcpu->kvm->arch.guest_origin +
+					 vcpu->arch.sie_block->prefix,
+					 PAGE_SIZE);
+		return 0;
+	}
+	VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d",
+		   viwhy);
+	return -ENOTSUPP;
+}
+
+static int handle_instruction(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	vcpu->stat.exit_instruction++;
+	handler = instruction_handlers[vcpu->arch.sie_block->ipa >> 8];
+	if (handler)
+		return handler(vcpu);
+	return -ENOTSUPP;
+}
+
+static int handle_prog(struct kvm_vcpu *vcpu)
+{
+	vcpu->stat.exit_program_interruption++;
+	return kvm_s390_inject_program_int(vcpu, vcpu->arch.sie_block->iprcc);
+}
+
+static int handle_instruction_and_prog(struct kvm_vcpu *vcpu)
+{
+	int rc, rc2;
+
+	vcpu->stat.exit_instr_and_program++;
+	rc = handle_instruction(vcpu);
+	rc2 = handle_prog(vcpu);
+
+	if (rc == -ENOTSUPP)
+		vcpu->arch.sie_block->icptcode = 0x04;
+	if (rc)
+		return rc;
+	return rc2;
+}
+
+static const intercept_handler_t intercept_funcs[0x48 >> 2] = {
+	[0x00 >> 2] = handle_noop,
+	[0x04 >> 2] = handle_instruction,
+	[0x08 >> 2] = handle_prog,
+	[0x0C >> 2] = handle_instruction_and_prog,
+	[0x10 >> 2] = handle_noop,
+	[0x14 >> 2] = handle_noop,
+	[0x1C >> 2] = kvm_s390_handle_wait,
+	[0x20 >> 2] = handle_validity,
+	[0x28 >> 2] = handle_stop,
+};
+
+int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t func;
+	u8 code = vcpu->arch.sie_block->icptcode;
+
+	if (code & 3 || code > 0x48)
+		return -ENOTSUPP;
+	func = intercept_funcs[code >> 2];
+	if (func)
+		return func(vcpu);
+	return -ENOTSUPP;
+}
diff --git a/trunk/arch/s390/kvm/interrupt.c b/trunk/arch/s390/kvm/interrupt.c
new file mode 100644
index 000000000000..fcd1ed8015c1
--- /dev/null
+++ b/trunk/arch/s390/kvm/interrupt.c
@@ -0,0 +1,592 @@
+/*
+ * interrupt.c - handling kvm guest interrupts
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ */
+
+#include <asm/lowcore.h>
+#include <asm/uaccess.h>
+#include <linux/kvm_host.h>
+#include "kvm-s390.h"
+#include "gaccess.h"
+
+static int psw_extint_disabled(struct kvm_vcpu *vcpu)
+{
+	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
+}
+
+static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
+{
+	if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) ||
+	    (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO) ||
+	    (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT))
+		return 0;
+	return 1;
+}
+
+static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
+				      struct interrupt_info *inti)
+{
+	switch (inti->type) {
+	case KVM_S390_INT_EMERGENCY:
+		if (psw_extint_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[0] & 0x4000ul)
+			return 1;
+		return 0;
+	case KVM_S390_INT_SERVICE:
+		if (psw_extint_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[0] & 0x200ul)
+			return 1;
+		return 0;
+	case KVM_S390_INT_VIRTIO:
+		if (psw_extint_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[0] & 0x200ul)
+			return 1;
+		return 0;
+	case KVM_S390_PROGRAM_INT:
+	case KVM_S390_SIGP_STOP:
+	case KVM_S390_SIGP_SET_PREFIX:
+	case KVM_S390_RESTART:
+		return 1;
+	default:
+		BUG();
+	}
+	return 0;
+}
+
+static void __set_cpu_idle(struct kvm_vcpu *vcpu)
+{
+	BUG_ON(vcpu->vcpu_id > KVM_MAX_VCPUS - 1);
+	atomic_set_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+	set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
+}
+
+static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
+{
+	BUG_ON(vcpu->vcpu_id > KVM_MAX_VCPUS - 1);
+	atomic_clear_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+	clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
+}
+
+static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
+{
+	atomic_clear_mask(CPUSTAT_ECALL_PEND |
+		CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
+		&vcpu->arch.sie_block->cpuflags);
+	vcpu->arch.sie_block->lctl = 0x0000;
+}
+
+static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
+{
+	atomic_set_mask(flag, &vcpu->arch.sie_block->cpuflags);
+}
+
+static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
+				      struct interrupt_info *inti)
+{
+	switch (inti->type) {
+	case KVM_S390_INT_EMERGENCY:
+	case KVM_S390_INT_SERVICE:
+	case KVM_S390_INT_VIRTIO:
+		if (psw_extint_disabled(vcpu))
+			__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
+		else
+			vcpu->arch.sie_block->lctl |= LCTL_CR0;
+		break;
+	case KVM_S390_SIGP_STOP:
+		__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
+		break;
+	default:
+		BUG();
+	}
+}
+
+static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
+				   struct interrupt_info *inti)
+{
+	const unsigned short table[] = { 2, 4, 4, 6 };
+	int rc, exception = 0;
+
+	switch (inti->type) {
+	case KVM_S390_INT_EMERGENCY:
+		VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
+		vcpu->stat.deliver_emergency_signal++;
+		rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1201);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+			 &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+			__LC_EXT_NEW_PSW, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+		break;
+
+	case KVM_S390_INT_SERVICE:
+		VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x",
+			   inti->ext.ext_params);
+		vcpu->stat.deliver_service_signal++;
+		rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x2401);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+			 &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+			__LC_EXT_NEW_PSW, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = put_guest_u32(vcpu, __LC_EXT_PARAMS, inti->ext.ext_params);
+		if (rc == -EFAULT)
+			exception = 1;
+		break;
+
+	case KVM_S390_INT_VIRTIO:
+		VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%lx",
+			   inti->ext.ext_params, inti->ext.ext_params2);
+		vcpu->stat.deliver_virtio_interrupt++;
+		rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x2603);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = put_guest_u16(vcpu, __LC_CPU_ADDRESS, 0x0d00);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+			 &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+			__LC_EXT_NEW_PSW, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = put_guest_u32(vcpu, __LC_EXT_PARAMS, inti->ext.ext_params);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = put_guest_u64(vcpu, __LC_PFAULT_INTPARM,
+			inti->ext.ext_params2);
+		if (rc == -EFAULT)
+			exception = 1;
+		break;
+
+	case KVM_S390_SIGP_STOP:
+		VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop");
+		vcpu->stat.deliver_stop_signal++;
+		__set_intercept_indicator(vcpu, inti);
+		break;
+
+	case KVM_S390_SIGP_SET_PREFIX:
+		VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x",
+			   inti->prefix.address);
+		vcpu->stat.deliver_prefix_signal++;
+		vcpu->arch.sie_block->prefix = inti->prefix.address;
+		vcpu->arch.sie_block->ihcpu = 0xffff;
+		break;
+
+	case KVM_S390_RESTART:
+		VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart");
+		vcpu->stat.deliver_restart_signal++;
+		rc = copy_to_guest(vcpu, offsetof(struct _lowcore,
+		  restart_old_psw), &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+			offsetof(struct _lowcore, restart_psw), sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+		break;
+
+	case KVM_S390_PROGRAM_INT:
+		VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x",
+			   inti->pgm.code,
+			   table[vcpu->arch.sie_block->ipa >> 14]);
+		vcpu->stat.deliver_program_int++;
+		rc = put_guest_u16(vcpu, __LC_PGM_INT_CODE, inti->pgm.code);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = put_guest_u16(vcpu, __LC_PGM_ILC,
+			table[vcpu->arch.sie_block->ipa >> 14]);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_to_guest(vcpu, __LC_PGM_OLD_PSW,
+			 &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+			__LC_PGM_NEW_PSW, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+		break;
+
+	default:
+		BUG();
+	}
+
+	if (exception) {
+		VCPU_EVENT(vcpu, 1, "%s", "program exception while delivering"
+			   " interrupt");
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		if (inti->type == KVM_S390_PROGRAM_INT) {
+			printk(KERN_WARNING "kvm: recursive program check\n");
+			BUG();
+		}
+	}
+}
+
+static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu)
+{
+	int rc, exception = 0;
+
+	if (psw_extint_disabled(vcpu))
+		return 0;
+	if (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))
+		return 0;
+	rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1004);
+	if (rc == -EFAULT)
+		exception = 1;
+	rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+		 &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+	if (rc == -EFAULT)
+		exception = 1;
+	rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+		__LC_EXT_NEW_PSW, sizeof(psw_t));
+	if (rc == -EFAULT)
+		exception = 1;
+
+	if (exception) {
+		VCPU_EVENT(vcpu, 1, "%s", "program exception while delivering" \
+			   " ckc interrupt");
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		return 0;
+	}
+
+	return 1;
+}
+
+int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
+{
+	struct local_interrupt *li = &vcpu->arch.local_int;
+	struct float_interrupt *fi = vcpu->arch.local_int.float_int;
+	struct interrupt_info  *inti;
+	int rc = 0;
+
+	if (atomic_read(&li->active)) {
+		spin_lock_bh(&li->lock);
+		list_for_each_entry(inti, &li->list, list)
+			if (__interrupt_is_deliverable(vcpu, inti)) {
+				rc = 1;
+				break;
+			}
+		spin_unlock_bh(&li->lock);
+	}
+
+	if ((!rc) && atomic_read(&fi->active)) {
+		spin_lock_bh(&fi->lock);
+		list_for_each_entry(inti, &fi->list, list)
+			if (__interrupt_is_deliverable(vcpu, inti)) {
+				rc = 1;
+				break;
+			}
+		spin_unlock_bh(&fi->lock);
+	}
+
+	if ((!rc) && (vcpu->arch.sie_block->ckc <
+		get_clock() + vcpu->arch.sie_block->epoch)) {
+		if ((!psw_extint_disabled(vcpu)) &&
+			(vcpu->arch.sie_block->gcr[0] & 0x800ul))
+			rc = 1;
+	}
+
+	return rc;
+}
+
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
+{
+	u64 now, sltime;
+	DECLARE_WAITQUEUE(wait, current);
+
+	vcpu->stat.exit_wait_state++;
+	if (kvm_cpu_has_interrupt(vcpu))
+		return 0;
+
+	if (psw_interrupts_disabled(vcpu)) {
+		VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
+		__unset_cpu_idle(vcpu);
+		return -ENOTSUPP; /* disabled wait */
+	}
+
+	if (psw_extint_disabled(vcpu) ||
+	    (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))) {
+		VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
+		goto no_timer;
+	}
+
+	now = get_clock() + vcpu->arch.sie_block->epoch;
+	if (vcpu->arch.sie_block->ckc < now) {
+		__unset_cpu_idle(vcpu);
+		return 0;
+	}
+
+	sltime = (vcpu->arch.sie_block->ckc - now) / (0xf4240000ul / HZ) + 1;
+
+	vcpu->arch.ckc_timer.expires = jiffies + sltime;
+
+	add_timer(&vcpu->arch.ckc_timer);
+	VCPU_EVENT(vcpu, 5, "enabled wait timer:%lx jiffies", sltime);
+no_timer:
+	spin_lock_bh(&vcpu->arch.local_int.float_int->lock);
+	spin_lock_bh(&vcpu->arch.local_int.lock);
+	__set_cpu_idle(vcpu);
+	vcpu->arch.local_int.timer_due = 0;
+	add_wait_queue(&vcpu->arch.local_int.wq, &wait);
+	while (list_empty(&vcpu->arch.local_int.list) &&
+		list_empty(&vcpu->arch.local_int.float_int->list) &&
+		(!vcpu->arch.local_int.timer_due) &&
+		!signal_pending(current)) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		spin_unlock_bh(&vcpu->arch.local_int.lock);
+		spin_unlock_bh(&vcpu->arch.local_int.float_int->lock);
+		vcpu_put(vcpu);
+		schedule();
+		vcpu_load(vcpu);
+		spin_lock_bh(&vcpu->arch.local_int.float_int->lock);
+		spin_lock_bh(&vcpu->arch.local_int.lock);
+	}
+	__unset_cpu_idle(vcpu);
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&vcpu->wq, &wait);
+	spin_unlock_bh(&vcpu->arch.local_int.lock);
+	spin_unlock_bh(&vcpu->arch.local_int.float_int->lock);
+	del_timer(&vcpu->arch.ckc_timer);
+	return 0;
+}
+
+void kvm_s390_idle_wakeup(unsigned long data)
+{
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
+
+	spin_lock_bh(&vcpu->arch.local_int.lock);
+	vcpu->arch.local_int.timer_due = 1;
+	if (waitqueue_active(&vcpu->arch.local_int.wq))
+		wake_up_interruptible(&vcpu->arch.local_int.wq);
+	spin_unlock_bh(&vcpu->arch.local_int.lock);
+}
+
+
+void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
+{
+	struct local_interrupt *li = &vcpu->arch.local_int;
+	struct float_interrupt *fi = vcpu->arch.local_int.float_int;
+	struct interrupt_info  *n, *inti = NULL;
+	int deliver;
+
+	__reset_intercept_indicators(vcpu);
+	if (atomic_read(&li->active)) {
+		do {
+			deliver = 0;
+			spin_lock_bh(&li->lock);
+			list_for_each_entry_safe(inti, n, &li->list, list) {
+				if (__interrupt_is_deliverable(vcpu, inti)) {
+					list_del(&inti->list);
+					deliver = 1;
+					break;
+				}
+				__set_intercept_indicator(vcpu, inti);
+			}
+			if (list_empty(&li->list))
+				atomic_set(&li->active, 0);
+			spin_unlock_bh(&li->lock);
+			if (deliver) {
+				__do_deliver_interrupt(vcpu, inti);
+				kfree(inti);
+			}
+		} while (deliver);
+	}
+
+	if ((vcpu->arch.sie_block->ckc <
+		get_clock() + vcpu->arch.sie_block->epoch))
+		__try_deliver_ckc_interrupt(vcpu);
+
+	if (atomic_read(&fi->active)) {
+		do {
+			deliver = 0;
+			spin_lock_bh(&fi->lock);
+			list_for_each_entry_safe(inti, n, &fi->list, list) {
+				if (__interrupt_is_deliverable(vcpu, inti)) {
+					list_del(&inti->list);
+					deliver = 1;
+					break;
+				}
+				__set_intercept_indicator(vcpu, inti);
+			}
+			if (list_empty(&fi->list))
+				atomic_set(&fi->active, 0);
+			spin_unlock_bh(&fi->lock);
+			if (deliver) {
+				__do_deliver_interrupt(vcpu, inti);
+				kfree(inti);
+			}
+		} while (deliver);
+	}
+}
+
+int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
+{
+	struct local_interrupt *li = &vcpu->arch.local_int;
+	struct interrupt_info *inti;
+
+	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	if (!inti)
+		return -ENOMEM;
+
+	inti->type = KVM_S390_PROGRAM_INT;;
+	inti->pgm.code = code;
+
+	VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code);
+	spin_lock_bh(&li->lock);
+	list_add(&inti->list, &li->list);
+	atomic_set(&li->active, 1);
+	BUG_ON(waitqueue_active(&li->wq));
+	spin_unlock_bh(&li->lock);
+	return 0;
+}
+
+int kvm_s390_inject_vm(struct kvm *kvm,
+		       struct kvm_s390_interrupt *s390int)
+{
+	struct local_interrupt *li;
+	struct float_interrupt *fi;
+	struct interrupt_info *inti;
+	int sigcpu;
+
+	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	if (!inti)
+		return -ENOMEM;
+
+	switch (s390int->type) {
+	case KVM_S390_INT_VIRTIO:
+		VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%lx",
+			 s390int->parm, s390int->parm64);
+		inti->type = s390int->type;
+		inti->ext.ext_params = s390int->parm;
+		inti->ext.ext_params2 = s390int->parm64;
+		break;
+	case KVM_S390_INT_SERVICE:
+		VM_EVENT(kvm, 5, "inject: sclp parm:%x", s390int->parm);
+		inti->type = s390int->type;
+		inti->ext.ext_params = s390int->parm;
+		break;
+	case KVM_S390_PROGRAM_INT:
+	case KVM_S390_SIGP_STOP:
+	case KVM_S390_INT_EMERGENCY:
+	default:
+		kfree(inti);
+		return -EINVAL;
+	}
+
+	mutex_lock(&kvm->lock);
+	fi = &kvm->arch.float_int;
+	spin_lock_bh(&fi->lock);
+	list_add_tail(&inti->list, &fi->list);
+	atomic_set(&fi->active, 1);
+	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
+	if (sigcpu == KVM_MAX_VCPUS) {
+		do {
+			sigcpu = fi->next_rr_cpu++;
+			if (sigcpu == KVM_MAX_VCPUS)
+				sigcpu = fi->next_rr_cpu = 0;
+		} while (fi->local_int[sigcpu] == NULL);
+	}
+	li = fi->local_int[sigcpu];
+	spin_lock_bh(&li->lock);
+	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	if (waitqueue_active(&li->wq))
+		wake_up_interruptible(&li->wq);
+	spin_unlock_bh(&li->lock);
+	spin_unlock_bh(&fi->lock);
+	mutex_unlock(&kvm->lock);
+	return 0;
+}
+
+int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
+			 struct kvm_s390_interrupt *s390int)
+{
+	struct local_interrupt *li;
+	struct interrupt_info *inti;
+
+	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	if (!inti)
+		return -ENOMEM;
+
+	switch (s390int->type) {
+	case KVM_S390_PROGRAM_INT:
+		if (s390int->parm & 0xffff0000) {
+			kfree(inti);
+			return -EINVAL;
+		}
+		inti->type = s390int->type;
+		inti->pgm.code = s390int->parm;
+		VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)",
+			   s390int->parm);
+		break;
+	case KVM_S390_SIGP_STOP:
+	case KVM_S390_RESTART:
+	case KVM_S390_SIGP_SET_PREFIX:
+	case KVM_S390_INT_EMERGENCY:
+		VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type);
+		inti->type = s390int->type;
+		break;
+	case KVM_S390_INT_VIRTIO:
+	case KVM_S390_INT_SERVICE:
+	default:
+		kfree(inti);
+		return -EINVAL;
+	}
+
+	mutex_lock(&vcpu->kvm->lock);
+	li = &vcpu->arch.local_int;
+	spin_lock_bh(&li->lock);
+	if (inti->type == KVM_S390_PROGRAM_INT)
+		list_add(&inti->list, &li->list);
+	else
+		list_add_tail(&inti->list, &li->list);
+	atomic_set(&li->active, 1);
+	if (inti->type == KVM_S390_SIGP_STOP)
+		li->action_bits |= ACTION_STOP_ON_STOP;
+	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	if (waitqueue_active(&li->wq))
+		wake_up_interruptible(&vcpu->arch.local_int.wq);
+	spin_unlock_bh(&li->lock);
+	mutex_unlock(&vcpu->kvm->lock);
+	return 0;
+}
diff --git a/trunk/arch/s390/kvm/kvm-s390.c b/trunk/arch/s390/kvm/kvm-s390.c
new file mode 100644
index 000000000000..98d1e73e01f1
--- /dev/null
+++ b/trunk/arch/s390/kvm/kvm-s390.c
@@ -0,0 +1,685 @@
+/*
+ * s390host.c --  hosting zSeries kernel virtual machines
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ *               Heiko Carstens <heiko.carstens@de.ibm.com>
+ */
+
+#include <linux/compiler.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/timer.h>
+#include <asm/lowcore.h>
+#include <asm/pgtable.h>
+
+#include "kvm-s390.h"
+#include "gaccess.h"
+
+#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+
+struct kvm_stats_debugfs_item debugfs_entries[] = {
+	{ "userspace_handled", VCPU_STAT(exit_userspace) },
+	{ "exit_validity", VCPU_STAT(exit_validity) },
+	{ "exit_stop_request", VCPU_STAT(exit_stop_request) },
+	{ "exit_external_request", VCPU_STAT(exit_external_request) },
+	{ "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
+	{ "exit_instruction", VCPU_STAT(exit_instruction) },
+	{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
+	{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
+	{ "instruction_lctg", VCPU_STAT(instruction_lctg) },
+	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
+	{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
+	{ "deliver_service_signal", VCPU_STAT(deliver_service_signal) },
+	{ "deliver_virtio_interrupt", VCPU_STAT(deliver_virtio_interrupt) },
+	{ "deliver_stop_signal", VCPU_STAT(deliver_stop_signal) },
+	{ "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) },
+	{ "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
+	{ "deliver_program_interruption", VCPU_STAT(deliver_program_int) },
+	{ "exit_wait_state", VCPU_STAT(exit_wait_state) },
+	{ "instruction_stidp", VCPU_STAT(instruction_stidp) },
+	{ "instruction_spx", VCPU_STAT(instruction_spx) },
+	{ "instruction_stpx", VCPU_STAT(instruction_stpx) },
+	{ "instruction_stap", VCPU_STAT(instruction_stap) },
+	{ "instruction_storage_key", VCPU_STAT(instruction_storage_key) },
+	{ "instruction_stsch", VCPU_STAT(instruction_stsch) },
+	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
+	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
+	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
+	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
+	{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
+	{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
+	{ "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) },
+	{ "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) },
+	{ "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
+	{ "diagnose_44", VCPU_STAT(diagnose_44) },
+	{ NULL }
+};
+
+
+/* Section: not file related */
+void kvm_arch_hardware_enable(void *garbage)
+{
+	/* every s390 is virtualization enabled ;-) */
+}
+
+void kvm_arch_hardware_disable(void *garbage)
+{
+}
+
+void decache_vcpus_on_cpu(int cpu)
+{
+}
+
+int kvm_arch_hardware_setup(void)
+{
+	return 0;
+}
+
+void kvm_arch_hardware_unsetup(void)
+{
+}
+
+void kvm_arch_check_processor_compat(void *rtn)
+{
+}
+
+int kvm_arch_init(void *opaque)
+{
+	return 0;
+}
+
+void kvm_arch_exit(void)
+{
+}
+
+/* Section: device related */
+long kvm_arch_dev_ioctl(struct file *filp,
+			unsigned int ioctl, unsigned long arg)
+{
+	if (ioctl == KVM_S390_ENABLE_SIE)
+		return s390_enable_sie();
+	return -EINVAL;
+}
+
+int kvm_dev_ioctl_check_extension(long ext)
+{
+	return 0;
+}
+
+/* Section: vm related */
+/*
+ * Get (and clear) the dirty memory log for a memory slot.
+ */
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
+			       struct kvm_dirty_log *log)
+{
+	return 0;
+}
+
+long kvm_arch_vm_ioctl(struct file *filp,
+		       unsigned int ioctl, unsigned long arg)
+{
+	struct kvm *kvm = filp->private_data;
+	void __user *argp = (void __user *)arg;
+	int r;
+
+	switch (ioctl) {
+	case KVM_S390_INTERRUPT: {
+		struct kvm_s390_interrupt s390int;
+
+		r = -EFAULT;
+		if (copy_from_user(&s390int, argp, sizeof(s390int)))
+			break;
+		r = kvm_s390_inject_vm(kvm, &s390int);
+		break;
+	}
+	default:
+		r = -EINVAL;
+	}
+
+	return r;
+}
+
+struct kvm *kvm_arch_create_vm(void)
+{
+	struct kvm *kvm;
+	int rc;
+	char debug_name[16];
+
+	rc = s390_enable_sie();
+	if (rc)
+		goto out_nokvm;
+
+	rc = -ENOMEM;
+	kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
+	if (!kvm)
+		goto out_nokvm;
+
+	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
+	if (!kvm->arch.sca)
+		goto out_nosca;
+
+	sprintf(debug_name, "kvm-%u", current->pid);
+
+	kvm->arch.dbf = debug_register(debug_name, 8, 2, 8 * sizeof(long));
+	if (!kvm->arch.dbf)
+		goto out_nodbf;
+
+	spin_lock_init(&kvm->arch.float_int.lock);
+	INIT_LIST_HEAD(&kvm->arch.float_int.list);
+
+	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
+	VM_EVENT(kvm, 3, "%s", "vm created");
+
+	try_module_get(THIS_MODULE);
+
+	return kvm;
+out_nodbf:
+	free_page((unsigned long)(kvm->arch.sca));
+out_nosca:
+	kfree(kvm);
+out_nokvm:
+	return ERR_PTR(rc);
+}
+
+void kvm_arch_destroy_vm(struct kvm *kvm)
+{
+	debug_unregister(kvm->arch.dbf);
+	free_page((unsigned long)(kvm->arch.sca));
+	kfree(kvm);
+	module_put(THIS_MODULE);
+}
+
+/* Section: vcpu related */
+int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+	/* kvm common code refers to this, but does'nt call it */
+	BUG();
+}
+
+void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	save_fp_regs(&vcpu->arch.host_fpregs);
+	save_access_regs(vcpu->arch.host_acrs);
+	vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK;
+	restore_fp_regs(&vcpu->arch.guest_fpregs);
+	restore_access_regs(vcpu->arch.guest_acrs);
+
+	if (signal_pending(current))
+		atomic_set_mask(CPUSTAT_STOP_INT,
+			&vcpu->arch.sie_block->cpuflags);
+}
+
+void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	save_fp_regs(&vcpu->arch.guest_fpregs);
+	save_access_regs(vcpu->arch.guest_acrs);
+	restore_fp_regs(&vcpu->arch.host_fpregs);
+	restore_access_regs(vcpu->arch.host_acrs);
+}
+
+static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
+{
+	/* this equals initial cpu reset in pop, but we don't switch to ESA */
+	vcpu->arch.sie_block->gpsw.mask = 0UL;
+	vcpu->arch.sie_block->gpsw.addr = 0UL;
+	vcpu->arch.sie_block->prefix    = 0UL;
+	vcpu->arch.sie_block->ihcpu     = 0xffff;
+	vcpu->arch.sie_block->cputm     = 0UL;
+	vcpu->arch.sie_block->ckc       = 0UL;
+	vcpu->arch.sie_block->todpr     = 0;
+	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
+	vcpu->arch.sie_block->gcr[0]  = 0xE0UL;
+	vcpu->arch.sie_block->gcr[14] = 0xC2000000UL;
+	vcpu->arch.guest_fpregs.fpc = 0;
+	asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
+	vcpu->arch.sie_block->gbea = 1;
+}
+
+int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH);
+	vcpu->arch.sie_block->gmslm = 0xffffffffffUL;
+	vcpu->arch.sie_block->gmsor = 0x000000000000;
+	vcpu->arch.sie_block->ecb   = 2;
+	vcpu->arch.sie_block->eca   = 0xC1002001U;
+	setup_timer(&vcpu->arch.ckc_timer, kvm_s390_idle_wakeup,
+		 (unsigned long) vcpu);
+	get_cpu_id(&vcpu->arch.cpu_id);
+	vcpu->arch.cpu_id.version = 0xfe;
+	return 0;
+}
+
+struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
+				      unsigned int id)
+{
+	struct kvm_vcpu *vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
+	int rc = -ENOMEM;
+
+	if (!vcpu)
+		goto out_nomem;
+
+	vcpu->arch.sie_block = (struct sie_block *) get_zeroed_page(GFP_KERNEL);
+
+	if (!vcpu->arch.sie_block)
+		goto out_free_cpu;
+
+	vcpu->arch.sie_block->icpua = id;
+	BUG_ON(!kvm->arch.sca);
+	BUG_ON(kvm->arch.sca->cpu[id].sda);
+	kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
+	vcpu->arch.sie_block->scaoh = (__u32)(((__u64)kvm->arch.sca) >> 32);
+	vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
+
+	spin_lock_init(&vcpu->arch.local_int.lock);
+	INIT_LIST_HEAD(&vcpu->arch.local_int.list);
+	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
+	spin_lock_bh(&kvm->arch.float_int.lock);
+	kvm->arch.float_int.local_int[id] = &vcpu->arch.local_int;
+	init_waitqueue_head(&vcpu->arch.local_int.wq);
+	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
+	spin_unlock_bh(&kvm->arch.float_int.lock);
+
+	rc = kvm_vcpu_init(vcpu, kvm, id);
+	if (rc)
+		goto out_free_cpu;
+	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
+		 vcpu->arch.sie_block);
+
+	try_module_get(THIS_MODULE);
+
+	return vcpu;
+out_free_cpu:
+	kfree(vcpu);
+out_nomem:
+	return ERR_PTR(rc);
+}
+
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	VCPU_EVENT(vcpu, 3, "%s", "destroy cpu");
+	free_page((unsigned long)(vcpu->arch.sie_block));
+	kfree(vcpu);
+	module_put(THIS_MODULE);
+}
+
+int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
+{
+	/* kvm common code refers to this, but never calls it */
+	BUG();
+	return 0;
+}
+
+static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
+{
+	vcpu_load(vcpu);
+	kvm_s390_vcpu_initial_reset(vcpu);
+	vcpu_put(vcpu);
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+	vcpu_load(vcpu);
+	memcpy(&vcpu->arch.guest_gprs, &regs->gprs, sizeof(regs->gprs));
+	vcpu_put(vcpu);
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+	vcpu_load(vcpu);
+	memcpy(&regs->gprs, &vcpu->arch.guest_gprs, sizeof(regs->gprs));
+	vcpu_put(vcpu);
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+				  struct kvm_sregs *sregs)
+{
+	vcpu_load(vcpu);
+	memcpy(&vcpu->arch.guest_acrs, &sregs->acrs, sizeof(sregs->acrs));
+	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
+	vcpu_put(vcpu);
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+				  struct kvm_sregs *sregs)
+{
+	vcpu_load(vcpu);
+	memcpy(&sregs->acrs, &vcpu->arch.guest_acrs, sizeof(sregs->acrs));
+	memcpy(&sregs->crs, &vcpu->arch.sie_block->gcr, sizeof(sregs->crs));
+	vcpu_put(vcpu);
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+	vcpu_load(vcpu);
+	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
+	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
+	vcpu_put(vcpu);
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+	vcpu_load(vcpu);
+	memcpy(&fpu->fprs, &vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs));
+	fpu->fpc = vcpu->arch.guest_fpregs.fpc;
+	vcpu_put(vcpu);
+	return 0;
+}
+
+static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw)
+{
+	int rc = 0;
+
+	vcpu_load(vcpu);
+	if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING)
+		rc = -EBUSY;
+	else
+		vcpu->arch.sie_block->gpsw = psw;
+	vcpu_put(vcpu);
+	return rc;
+}
+
+int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+				  struct kvm_translation *tr)
+{
+	return -EINVAL; /* not implemented yet */
+}
+
+int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
+				    struct kvm_debug_guest *dbg)
+{
+	return -EINVAL; /* not implemented yet */
+}
+
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state)
+{
+	return -EINVAL; /* not implemented yet */
+}
+
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state)
+{
+	return -EINVAL; /* not implemented yet */
+}
+
+static void __vcpu_run(struct kvm_vcpu *vcpu)
+{
+	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->arch.guest_gprs[14], 16);
+
+	if (need_resched())
+		schedule();
+
+	vcpu->arch.sie_block->icptcode = 0;
+	local_irq_disable();
+	kvm_guest_enter();
+	local_irq_enable();
+	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
+		   atomic_read(&vcpu->arch.sie_block->cpuflags));
+	sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs);
+	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
+		   vcpu->arch.sie_block->icptcode);
+	local_irq_disable();
+	kvm_guest_exit();
+	local_irq_enable();
+
+	memcpy(&vcpu->arch.guest_gprs[14], &vcpu->arch.sie_block->gg14, 16);
+}
+
+int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	int rc;
+	sigset_t sigsaved;
+
+	vcpu_load(vcpu);
+
+	if (vcpu->sigset_active)
+		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+
+	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+
+	BUG_ON(vcpu->kvm->arch.float_int.local_int[vcpu->vcpu_id] == NULL);
+
+	switch (kvm_run->exit_reason) {
+	case KVM_EXIT_S390_SIEIC:
+		vcpu->arch.sie_block->gpsw.mask = kvm_run->s390_sieic.mask;
+		vcpu->arch.sie_block->gpsw.addr = kvm_run->s390_sieic.addr;
+		break;
+	case KVM_EXIT_UNKNOWN:
+	case KVM_EXIT_S390_RESET:
+		break;
+	default:
+		BUG();
+	}
+
+	might_sleep();
+
+	do {
+		kvm_s390_deliver_pending_interrupts(vcpu);
+		__vcpu_run(vcpu);
+		rc = kvm_handle_sie_intercept(vcpu);
+	} while (!signal_pending(current) && !rc);
+
+	if (signal_pending(current) && !rc)
+		rc = -EINTR;
+
+	if (rc == -ENOTSUPP) {
+		/* intercept cannot be handled in-kernel, prepare kvm-run */
+		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
+		kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
+		kvm_run->s390_sieic.mask     = vcpu->arch.sie_block->gpsw.mask;
+		kvm_run->s390_sieic.addr     = vcpu->arch.sie_block->gpsw.addr;
+		kvm_run->s390_sieic.ipa      = vcpu->arch.sie_block->ipa;
+		kvm_run->s390_sieic.ipb      = vcpu->arch.sie_block->ipb;
+		rc = 0;
+	}
+
+	if (rc == -EREMOTE) {
+		/* intercept was handled, but userspace support is needed
+		 * kvm_run has been prepared by the handler */
+		rc = 0;
+	}
+
+	if (vcpu->sigset_active)
+		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+	vcpu_put(vcpu);
+
+	vcpu->stat.exit_userspace++;
+	return rc;
+}
+
+static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, const void *from,
+		       unsigned long n, int prefix)
+{
+	if (prefix)
+		return copy_to_guest(vcpu, guestdest, from, n);
+	else
+		return copy_to_guest_absolute(vcpu, guestdest, from, n);
+}
+
+/*
+ * store status at address
+ * we use have two special cases:
+ * KVM_S390_STORE_STATUS_NOADDR: -> 0x1200 on 64 bit
+ * KVM_S390_STORE_STATUS_PREFIXED: -> prefix
+ */
+int __kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
+{
+	const unsigned char archmode = 1;
+	int prefix;
+
+	if (addr == KVM_S390_STORE_STATUS_NOADDR) {
+		if (copy_to_guest_absolute(vcpu, 163ul, &archmode, 1))
+			return -EFAULT;
+		addr = SAVE_AREA_BASE;
+		prefix = 0;
+	} else if (addr == KVM_S390_STORE_STATUS_PREFIXED) {
+		if (copy_to_guest(vcpu, 163ul, &archmode, 1))
+			return -EFAULT;
+		addr = SAVE_AREA_BASE;
+		prefix = 1;
+	} else
+		prefix = 0;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, fp_regs),
+			vcpu->arch.guest_fpregs.fprs, 128, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, gp_regs),
+			vcpu->arch.guest_gprs, 128, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, psw),
+			&vcpu->arch.sie_block->gpsw, 16, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, pref_reg),
+			&vcpu->arch.sie_block->prefix, 4, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu,
+			addr + offsetof(struct save_area_s390x, fp_ctrl_reg),
+			&vcpu->arch.guest_fpregs.fpc, 4, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, tod_reg),
+			&vcpu->arch.sie_block->todpr, 4, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, timer),
+			&vcpu->arch.sie_block->cputm, 8, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, clk_cmp),
+			&vcpu->arch.sie_block->ckc, 8, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, acc_regs),
+			&vcpu->arch.guest_acrs, 64, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu,
+			addr + offsetof(struct save_area_s390x, ctrl_regs),
+			&vcpu->arch.sie_block->gcr, 128, prefix))
+		return -EFAULT;
+	return 0;
+}
+
+static int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
+{
+	int rc;
+
+	vcpu_load(vcpu);
+	rc = __kvm_s390_vcpu_store_status(vcpu, addr);
+	vcpu_put(vcpu);
+	return rc;
+}
+
+long kvm_arch_vcpu_ioctl(struct file *filp,
+			 unsigned int ioctl, unsigned long arg)
+{
+	struct kvm_vcpu *vcpu = filp->private_data;
+	void __user *argp = (void __user *)arg;
+
+	switch (ioctl) {
+	case KVM_S390_INTERRUPT: {
+		struct kvm_s390_interrupt s390int;
+
+		if (copy_from_user(&s390int, argp, sizeof(s390int)))
+			return -EFAULT;
+		return kvm_s390_inject_vcpu(vcpu, &s390int);
+	}
+	case KVM_S390_STORE_STATUS:
+		return kvm_s390_vcpu_store_status(vcpu, arg);
+	case KVM_S390_SET_INITIAL_PSW: {
+		psw_t psw;
+
+		if (copy_from_user(&psw, argp, sizeof(psw)))
+			return -EFAULT;
+		return kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
+	}
+	case KVM_S390_INITIAL_RESET:
+		return kvm_arch_vcpu_ioctl_initial_reset(vcpu);
+	default:
+		;
+	}
+	return -EINVAL;
+}
+
+/* Section: memory related */
+int kvm_arch_set_memory_region(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem,
+				struct kvm_memory_slot old,
+				int user_alloc)
+{
+	/* A few sanity checks. We can have exactly one memory slot which has
+	   to start at guest virtual zero and which has to be located at a
+	   page boundary in userland and which has to end at a page boundary.
+	   The memory in userland is ok to be fragmented into various different
+	   vmas. It is okay to mmap() and munmap() stuff in this slot after
+	   doing this call at any time */
+
+	if (mem->slot)
+		return -EINVAL;
+
+	if (mem->guest_phys_addr)
+		return -EINVAL;
+
+	if (mem->userspace_addr & (PAGE_SIZE - 1))
+		return -EINVAL;
+
+	if (mem->memory_size & (PAGE_SIZE - 1))
+		return -EINVAL;
+
+	kvm->arch.guest_origin = mem->userspace_addr;
+	kvm->arch.guest_memsize = mem->memory_size;
+
+	/* FIXME: we do want to interrupt running CPUs and update their memory
+	   configuration now to avoid race conditions. But hey, changing the
+	   memory layout while virtual CPUs are running is usually bad
+	   programming practice. */
+
+	return 0;
+}
+
+gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
+{
+	return gfn;
+}
+
+static int __init kvm_s390_init(void)
+{
+	return kvm_init(NULL, sizeof(struct kvm_vcpu), THIS_MODULE);
+}
+
+static void __exit kvm_s390_exit(void)
+{
+	kvm_exit();
+}
+
+module_init(kvm_s390_init);
+module_exit(kvm_s390_exit);
diff --git a/trunk/arch/s390/kvm/kvm-s390.h b/trunk/arch/s390/kvm/kvm-s390.h
new file mode 100644
index 000000000000..3893cf12eacf
--- /dev/null
+++ b/trunk/arch/s390/kvm/kvm-s390.h
@@ -0,0 +1,64 @@
+/*
+ * kvm_s390.h -  definition for kvm on s390
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#ifndef ARCH_S390_KVM_S390_H
+#define ARCH_S390_KVM_S390_H
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+
+typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
+
+int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
+
+#define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\
+do { \
+	debug_sprintf_event(d_kvm->arch.dbf, d_loglevel, d_string "\n", \
+	  d_args); \
+} while (0)
+
+#define VCPU_EVENT(d_vcpu, d_loglevel, d_string, d_args...)\
+do { \
+	debug_sprintf_event(d_vcpu->kvm->arch.dbf, d_loglevel, \
+	  "%02d[%016lx-%016lx]: " d_string "\n", d_vcpu->vcpu_id, \
+	  d_vcpu->arch.sie_block->gpsw.mask, d_vcpu->arch.sie_block->gpsw.addr,\
+	  d_args); \
+} while (0)
+
+static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu)
+{
+	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOP_INT;
+}
+
+int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
+void kvm_s390_idle_wakeup(unsigned long data);
+void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu);
+int kvm_s390_inject_vm(struct kvm *kvm,
+		struct kvm_s390_interrupt *s390int);
+int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
+		struct kvm_s390_interrupt *s390int);
+int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
+
+/* implemented in priv.c */
+int kvm_s390_handle_priv(struct kvm_vcpu *vcpu);
+
+/* implemented in sigp.c */
+int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
+
+/* implemented in kvm-s390.c */
+int __kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu,
+				 unsigned long addr);
+/* implemented in diag.c */
+int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
+
+#endif
diff --git a/trunk/arch/s390/kvm/priv.c b/trunk/arch/s390/kvm/priv.c
new file mode 100644
index 000000000000..1465946325c5
--- /dev/null
+++ b/trunk/arch/s390/kvm/priv.c
@@ -0,0 +1,323 @@
+/*
+ * priv.c - handling privileged instructions
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#include <linux/kvm.h>
+#include <linux/errno.h>
+#include <asm/current.h>
+#include <asm/debug.h>
+#include <asm/ebcdic.h>
+#include <asm/sysinfo.h>
+#include "gaccess.h"
+#include "kvm-s390.h"
+
+static int handle_set_prefix(struct kvm_vcpu *vcpu)
+{
+	int base2 = vcpu->arch.sie_block->ipb >> 28;
+	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+	u64 operand2;
+	u32 address = 0;
+	u8 tmp;
+
+	vcpu->stat.instruction_spx++;
+
+	operand2 = disp2;
+	if (base2)
+		operand2 += vcpu->arch.guest_gprs[base2];
+
+	/* must be word boundary */
+	if (operand2 & 3) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	/* get the value */
+	if (get_guest_u32(vcpu, operand2, &address)) {
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		goto out;
+	}
+
+	address = address & 0x7fffe000u;
+
+	/* make sure that the new value is valid memory */
+	if (copy_from_guest_absolute(vcpu, &tmp, address, 1) ||
+	   (copy_from_guest_absolute(vcpu, &tmp, address + PAGE_SIZE, 1))) {
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		goto out;
+	}
+
+	vcpu->arch.sie_block->prefix = address;
+	vcpu->arch.sie_block->ihcpu = 0xffff;
+
+	VCPU_EVENT(vcpu, 5, "setting prefix to %x", address);
+out:
+	return 0;
+}
+
+static int handle_store_prefix(struct kvm_vcpu *vcpu)
+{
+	int base2 = vcpu->arch.sie_block->ipb >> 28;
+	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+	u64 operand2;
+	u32 address;
+
+	vcpu->stat.instruction_stpx++;
+	operand2 = disp2;
+	if (base2)
+		operand2 += vcpu->arch.guest_gprs[base2];
+
+	/* must be word boundary */
+	if (operand2 & 3) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	address = vcpu->arch.sie_block->prefix;
+	address = address & 0x7fffe000u;
+
+	/* get the value */
+	if (put_guest_u32(vcpu, operand2, address)) {
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		goto out;
+	}
+
+	VCPU_EVENT(vcpu, 5, "storing prefix to %x", address);
+out:
+	return 0;
+}
+
+static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
+{
+	int base2 = vcpu->arch.sie_block->ipb >> 28;
+	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+	u64 useraddr;
+	int rc;
+
+	vcpu->stat.instruction_stap++;
+	useraddr = disp2;
+	if (base2)
+		useraddr += vcpu->arch.guest_gprs[base2];
+
+	if (useraddr & 1) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	rc = put_guest_u16(vcpu, useraddr, vcpu->vcpu_id);
+	if (rc == -EFAULT) {
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		goto out;
+	}
+
+	VCPU_EVENT(vcpu, 5, "storing cpu address to %lx", useraddr);
+out:
+	return 0;
+}
+
+static int handle_skey(struct kvm_vcpu *vcpu)
+{
+	vcpu->stat.instruction_storage_key++;
+	vcpu->arch.sie_block->gpsw.addr -= 4;
+	VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
+	return 0;
+}
+
+static int handle_stsch(struct kvm_vcpu *vcpu)
+{
+	vcpu->stat.instruction_stsch++;
+	VCPU_EVENT(vcpu, 4, "%s", "store subchannel - CC3");
+	/* condition code 3 */
+	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+	vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
+	return 0;
+}
+
+static int handle_chsc(struct kvm_vcpu *vcpu)
+{
+	vcpu->stat.instruction_chsc++;
+	VCPU_EVENT(vcpu, 4, "%s", "channel subsystem call - CC3");
+	/* condition code 3 */
+	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+	vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
+	return 0;
+}
+
+static unsigned int kvm_stfl(void)
+{
+	asm volatile(
+		"	.insn	s,0xb2b10000,0(0)\n" /* stfl */
+		"0:\n"
+		EX_TABLE(0b, 0b));
+	return S390_lowcore.stfl_fac_list;
+}
+
+static int handle_stfl(struct kvm_vcpu *vcpu)
+{
+	unsigned int facility_list = kvm_stfl();
+	int rc;
+
+	vcpu->stat.instruction_stfl++;
+	facility_list &= ~(1UL<<24); /* no stfle */
+
+	rc = copy_to_guest(vcpu, offsetof(struct _lowcore, stfl_fac_list),
+			   &facility_list, sizeof(facility_list));
+	if (rc == -EFAULT)
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	else
+		VCPU_EVENT(vcpu, 5, "store facility list value %x",
+			   facility_list);
+	return 0;
+}
+
+static int handle_stidp(struct kvm_vcpu *vcpu)
+{
+	int base2 = vcpu->arch.sie_block->ipb >> 28;
+	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+	u64 operand2;
+	int rc;
+
+	vcpu->stat.instruction_stidp++;
+	operand2 = disp2;
+	if (base2)
+		operand2 += vcpu->arch.guest_gprs[base2];
+
+	if (operand2 & 7) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	rc = put_guest_u64(vcpu, operand2, vcpu->arch.stidp_data);
+	if (rc == -EFAULT) {
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		goto out;
+	}
+
+	VCPU_EVENT(vcpu, 5, "%s", "store cpu id");
+out:
+	return 0;
+}
+
+static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
+{
+	struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	int cpus = 0;
+	int n;
+
+	spin_lock_bh(&fi->lock);
+	for (n = 0; n < KVM_MAX_VCPUS; n++)
+		if (fi->local_int[n])
+			cpus++;
+	spin_unlock_bh(&fi->lock);
+
+	/* deal with other level 3 hypervisors */
+	if (stsi(mem, 3, 2, 2) == -ENOSYS)
+		mem->count = 0;
+	if (mem->count < 8)
+		mem->count++;
+	for (n = mem->count - 1; n > 0 ; n--)
+		memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0]));
+
+	mem->vm[0].cpus_total = cpus;
+	mem->vm[0].cpus_configured = cpus;
+	mem->vm[0].cpus_standby = 0;
+	mem->vm[0].cpus_reserved = 0;
+	mem->vm[0].caf = 1000;
+	memcpy(mem->vm[0].name, "KVMguest", 8);
+	ASCEBC(mem->vm[0].name, 8);
+	memcpy(mem->vm[0].cpi, "KVM/Linux       ", 16);
+	ASCEBC(mem->vm[0].cpi, 16);
+}
+
+static int handle_stsi(struct kvm_vcpu *vcpu)
+{
+	int fc = (vcpu->arch.guest_gprs[0] & 0xf0000000) >> 28;
+	int sel1 = vcpu->arch.guest_gprs[0] & 0xff;
+	int sel2 = vcpu->arch.guest_gprs[1] & 0xffff;
+	int base2 = vcpu->arch.sie_block->ipb >> 28;
+	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+	u64 operand2;
+	unsigned long mem;
+
+	vcpu->stat.instruction_stsi++;
+	VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2);
+
+	operand2 = disp2;
+	if (base2)
+		operand2 += vcpu->arch.guest_gprs[base2];
+
+	if (operand2 & 0xfff && fc > 0)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	switch (fc) {
+	case 0:
+		vcpu->arch.guest_gprs[0] = 3 << 28;
+		vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+		return 0;
+	case 1: /* same handling for 1 and 2 */
+	case 2:
+		mem = get_zeroed_page(GFP_KERNEL);
+		if (!mem)
+			goto out_fail;
+		if (stsi((void *) mem, fc, sel1, sel2) == -ENOSYS)
+			goto out_mem;
+		break;
+	case 3:
+		if (sel1 != 2 || sel2 != 2)
+			goto out_fail;
+		mem = get_zeroed_page(GFP_KERNEL);
+		if (!mem)
+			goto out_fail;
+		handle_stsi_3_2_2(vcpu, (void *) mem);
+		break;
+	default:
+		goto out_fail;
+	}
+
+	if (copy_to_guest_absolute(vcpu, operand2, (void *) mem, PAGE_SIZE)) {
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		goto out_mem;
+	}
+	free_page(mem);
+	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+	vcpu->arch.guest_gprs[0] = 0;
+	return 0;
+out_mem:
+	free_page(mem);
+out_fail:
+	/* condition code 3 */
+	vcpu->arch.sie_block->gpsw.mask |= 3ul << 44;
+	return 0;
+}
+
+static intercept_handler_t priv_handlers[256] = {
+	[0x02] = handle_stidp,
+	[0x10] = handle_set_prefix,
+	[0x11] = handle_store_prefix,
+	[0x12] = handle_store_cpu_address,
+	[0x29] = handle_skey,
+	[0x2a] = handle_skey,
+	[0x2b] = handle_skey,
+	[0x34] = handle_stsch,
+	[0x5f] = handle_chsc,
+	[0x7d] = handle_stsi,
+	[0xb1] = handle_stfl,
+};
+
+int kvm_s390_handle_priv(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	handler = priv_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
+	if (handler)
+		return handler(vcpu);
+	return -ENOTSUPP;
+}
diff --git a/trunk/arch/s390/kvm/sie64a.S b/trunk/arch/s390/kvm/sie64a.S
new file mode 100644
index 000000000000..934fd6a885f6
--- /dev/null
+++ b/trunk/arch/s390/kvm/sie64a.S
@@ -0,0 +1,47 @@
+/*
+ * sie64a.S - low level sie call
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
+ */
+
+#include <linux/errno.h>
+#include <asm/asm-offsets.h>
+
+SP_R5 =	5 * 8	# offset into stackframe
+SP_R6 =	6 * 8
+
+/*
+ * sie64a calling convention:
+ * %r2 pointer to sie control block
+ * %r3 guest register save area
+ */
+	.globl	sie64a
+sie64a:
+	lgr	%r5,%r3
+	stmg	%r5,%r14,SP_R5(%r15)	# save register on entry
+	lgr	%r14,%r2		# pointer to sie control block
+	lmg	%r0,%r13,0(%r3)		# load guest gprs 0-13
+sie_inst:
+	sie	0(%r14)
+	lg	%r14,SP_R5(%r15)
+	stmg	%r0,%r13,0(%r14)	# save guest gprs 0-13
+	lghi	%r2,0
+	lmg	%r6,%r14,SP_R6(%r15)
+	br	%r14
+
+sie_err:
+	lg	%r14,SP_R5(%r15)
+	stmg	%r0,%r13,0(%r14)	# save guest gprs 0-13
+	lghi	%r2,-EFAULT
+	lmg	%r6,%r14,SP_R6(%r15)
+	br	%r14
+
+	.section __ex_table,"a"
+	.quad	sie_inst,sie_err
+	.previous
diff --git a/trunk/arch/s390/kvm/sigp.c b/trunk/arch/s390/kvm/sigp.c
new file mode 100644
index 000000000000..0a236acfb5f6
--- /dev/null
+++ b/trunk/arch/s390/kvm/sigp.c
@@ -0,0 +1,288 @@
+/*
+ * sigp.c - handlinge interprocessor communication
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include "gaccess.h"
+#include "kvm-s390.h"
+
+/* sigp order codes */
+#define SIGP_SENSE             0x01
+#define SIGP_EXTERNAL_CALL     0x02
+#define SIGP_EMERGENCY         0x03
+#define SIGP_START             0x04
+#define SIGP_STOP              0x05
+#define SIGP_RESTART           0x06
+#define SIGP_STOP_STORE_STATUS 0x09
+#define SIGP_INITIAL_CPU_RESET 0x0b
+#define SIGP_CPU_RESET         0x0c
+#define SIGP_SET_PREFIX        0x0d
+#define SIGP_STORE_STATUS_ADDR 0x0e
+#define SIGP_SET_ARCH          0x12
+
+/* cpu status bits */
+#define SIGP_STAT_EQUIPMENT_CHECK   0x80000000UL
+#define SIGP_STAT_INCORRECT_STATE   0x00000200UL
+#define SIGP_STAT_INVALID_PARAMETER 0x00000100UL
+#define SIGP_STAT_EXT_CALL_PENDING  0x00000080UL
+#define SIGP_STAT_STOPPED           0x00000040UL
+#define SIGP_STAT_OPERATOR_INTERV   0x00000020UL
+#define SIGP_STAT_CHECK_STOP        0x00000010UL
+#define SIGP_STAT_INOPERATIVE       0x00000004UL
+#define SIGP_STAT_INVALID_ORDER     0x00000002UL
+#define SIGP_STAT_RECEIVER_CHECK    0x00000001UL
+
+
+static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, u64 *reg)
+{
+	struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	int rc;
+
+	if (cpu_addr >= KVM_MAX_VCPUS)
+		return 3; /* not operational */
+
+	spin_lock_bh(&fi->lock);
+	if (fi->local_int[cpu_addr] == NULL)
+		rc = 3; /* not operational */
+	else if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
+		 & CPUSTAT_RUNNING) {
+		*reg &= 0xffffffff00000000UL;
+		rc = 1; /* status stored */
+	} else {
+		*reg &= 0xffffffff00000000UL;
+		*reg |= SIGP_STAT_STOPPED;
+		rc = 1; /* status stored */
+	}
+	spin_unlock_bh(&fi->lock);
+
+	VCPU_EVENT(vcpu, 4, "sensed status of cpu %x rc %x", cpu_addr, rc);
+	return rc;
+}
+
+static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
+{
+	struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct local_interrupt *li;
+	struct interrupt_info *inti;
+	int rc;
+
+	if (cpu_addr >= KVM_MAX_VCPUS)
+		return 3; /* not operational */
+
+	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	if (!inti)
+		return -ENOMEM;
+
+	inti->type = KVM_S390_INT_EMERGENCY;
+
+	spin_lock_bh(&fi->lock);
+	li = fi->local_int[cpu_addr];
+	if (li == NULL) {
+		rc = 3; /* not operational */
+		kfree(inti);
+		goto unlock;
+	}
+	spin_lock_bh(&li->lock);
+	list_add_tail(&inti->list, &li->list);
+	atomic_set(&li->active, 1);
+	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	if (waitqueue_active(&li->wq))
+		wake_up_interruptible(&li->wq);
+	spin_unlock_bh(&li->lock);
+	rc = 0; /* order accepted */
+unlock:
+	spin_unlock_bh(&fi->lock);
+	VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr);
+	return rc;
+}
+
+static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int store)
+{
+	struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct local_interrupt *li;
+	struct interrupt_info *inti;
+	int rc;
+
+	if (cpu_addr >= KVM_MAX_VCPUS)
+		return 3; /* not operational */
+
+	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	if (!inti)
+		return -ENOMEM;
+
+	inti->type = KVM_S390_SIGP_STOP;
+
+	spin_lock_bh(&fi->lock);
+	li = fi->local_int[cpu_addr];
+	if (li == NULL) {
+		rc = 3; /* not operational */
+		kfree(inti);
+		goto unlock;
+	}
+	spin_lock_bh(&li->lock);
+	list_add_tail(&inti->list, &li->list);
+	atomic_set(&li->active, 1);
+	atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
+	if (store)
+		li->action_bits |= ACTION_STORE_ON_STOP;
+	li->action_bits |= ACTION_STOP_ON_STOP;
+	if (waitqueue_active(&li->wq))
+		wake_up_interruptible(&li->wq);
+	spin_unlock_bh(&li->lock);
+	rc = 0; /* order accepted */
+unlock:
+	spin_unlock_bh(&fi->lock);
+	VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", cpu_addr);
+	return rc;
+}
+
+static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
+{
+	int rc;
+
+	switch (parameter & 0xff) {
+	case 0:
+		printk(KERN_WARNING "kvm: request to switch to ESA/390 mode"
+							" not supported");
+		rc = 3; /* not operational */
+		break;
+	case 1:
+	case 2:
+		rc = 0; /* order accepted */
+		break;
+	default:
+		rc = -ENOTSUPP;
+	}
+	return rc;
+}
+
+static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
+			     u64 *reg)
+{
+	struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct local_interrupt *li;
+	struct interrupt_info *inti;
+	int rc;
+	u8 tmp;
+
+	/* make sure that the new value is valid memory */
+	address = address & 0x7fffe000u;
+	if ((copy_from_guest(vcpu, &tmp,
+		(u64) (address + vcpu->kvm->arch.guest_origin) , 1)) ||
+	   (copy_from_guest(vcpu, &tmp, (u64) (address +
+			vcpu->kvm->arch.guest_origin + PAGE_SIZE), 1))) {
+		*reg |= SIGP_STAT_INVALID_PARAMETER;
+		return 1; /* invalid parameter */
+	}
+
+	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	if (!inti)
+		return 2; /* busy */
+
+	spin_lock_bh(&fi->lock);
+	li = fi->local_int[cpu_addr];
+
+	if ((cpu_addr >= KVM_MAX_VCPUS) || (li == NULL)) {
+		rc = 1; /* incorrect state */
+		*reg &= SIGP_STAT_INCORRECT_STATE;
+		kfree(inti);
+		goto out_fi;
+	}
+
+	spin_lock_bh(&li->lock);
+	/* cpu must be in stopped state */
+	if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) {
+		rc = 1; /* incorrect state */
+		*reg &= SIGP_STAT_INCORRECT_STATE;
+		kfree(inti);
+		goto out_li;
+	}
+
+	inti->type = KVM_S390_SIGP_SET_PREFIX;
+	inti->prefix.address = address;
+
+	list_add_tail(&inti->list, &li->list);
+	atomic_set(&li->active, 1);
+	if (waitqueue_active(&li->wq))
+		wake_up_interruptible(&li->wq);
+	rc = 0; /* order accepted */
+
+	VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", cpu_addr, address);
+out_li:
+	spin_unlock_bh(&li->lock);
+out_fi:
+	spin_unlock_bh(&fi->lock);
+	return rc;
+}
+
+int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
+{
+	int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
+	int r3 = vcpu->arch.sie_block->ipa & 0x000f;
+	int base2 = vcpu->arch.sie_block->ipb >> 28;
+	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+	u32 parameter;
+	u16 cpu_addr = vcpu->arch.guest_gprs[r3];
+	u8 order_code;
+	int rc;
+
+	order_code = disp2;
+	if (base2)
+		order_code += vcpu->arch.guest_gprs[base2];
+
+	if (r1 % 2)
+		parameter = vcpu->arch.guest_gprs[r1];
+	else
+		parameter = vcpu->arch.guest_gprs[r1 + 1];
+
+	switch (order_code) {
+	case SIGP_SENSE:
+		vcpu->stat.instruction_sigp_sense++;
+		rc = __sigp_sense(vcpu, cpu_addr,
+				  &vcpu->arch.guest_gprs[r1]);
+		break;
+	case SIGP_EMERGENCY:
+		vcpu->stat.instruction_sigp_emergency++;
+		rc = __sigp_emergency(vcpu, cpu_addr);
+		break;
+	case SIGP_STOP:
+		vcpu->stat.instruction_sigp_stop++;
+		rc = __sigp_stop(vcpu, cpu_addr, 0);
+		break;
+	case SIGP_STOP_STORE_STATUS:
+		vcpu->stat.instruction_sigp_stop++;
+		rc = __sigp_stop(vcpu, cpu_addr, 1);
+		break;
+	case SIGP_SET_ARCH:
+		vcpu->stat.instruction_sigp_arch++;
+		rc = __sigp_set_arch(vcpu, parameter);
+		break;
+	case SIGP_SET_PREFIX:
+		vcpu->stat.instruction_sigp_prefix++;
+		rc = __sigp_set_prefix(vcpu, cpu_addr, parameter,
+				       &vcpu->arch.guest_gprs[r1]);
+		break;
+	case SIGP_RESTART:
+		vcpu->stat.instruction_sigp_restart++;
+		/* user space must know about restart */
+	default:
+		return -ENOTSUPP;
+	}
+
+	if (rc < 0)
+		return rc;
+
+	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+	vcpu->arch.sie_block->gpsw.mask |= (rc & 3ul) << 44;
+	return 0;
+}
diff --git a/trunk/arch/s390/mm/pgtable.c b/trunk/arch/s390/mm/pgtable.c
index fd072013f88c..5c1aea97cd12 100644
--- a/trunk/arch/s390/mm/pgtable.c
+++ b/trunk/arch/s390/mm/pgtable.c
@@ -30,11 +30,27 @@
 #define TABLES_PER_PAGE	4
 #define FRAG_MASK	15UL
 #define SECOND_HALVES	10UL
+
+void clear_table_pgstes(unsigned long *table)
+{
+	clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/4);
+	memset(table + 256, 0, PAGE_SIZE/4);
+	clear_table(table + 512, _PAGE_TYPE_EMPTY, PAGE_SIZE/4);
+	memset(table + 768, 0, PAGE_SIZE/4);
+}
+
 #else
 #define ALLOC_ORDER	2
 #define TABLES_PER_PAGE	2
 #define FRAG_MASK	3UL
 #define SECOND_HALVES	2UL
+
+void clear_table_pgstes(unsigned long *table)
+{
+	clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2);
+	memset(table + 256, 0, PAGE_SIZE/2);
+}
+
 #endif
 
 unsigned long *crst_table_alloc(struct mm_struct *mm, int noexec)
@@ -153,7 +169,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
 	unsigned long *table;
 	unsigned long bits;
 
-	bits = mm->context.noexec ? 3UL : 1UL;
+	bits = (mm->context.noexec || mm->context.pgstes) ? 3UL : 1UL;
 	spin_lock(&mm->page_table_lock);
 	page = NULL;
 	if (!list_empty(&mm->context.pgtable_list)) {
@@ -170,7 +186,10 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
 		pgtable_page_ctor(page);
 		page->flags &= ~FRAG_MASK;
 		table = (unsigned long *) page_to_phys(page);
-		clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
+		if (mm->context.pgstes)
+			clear_table_pgstes(table);
+		else
+			clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
 		spin_lock(&mm->page_table_lock);
 		list_add(&page->lru, &mm->context.pgtable_list);
 	}
@@ -191,7 +210,7 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
 	struct page *page;
 	unsigned long bits;
 
-	bits = mm->context.noexec ? 3UL : 1UL;
+	bits = (mm->context.noexec || mm->context.pgstes) ? 3UL : 1UL;
 	bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	spin_lock(&mm->page_table_lock);
@@ -228,3 +247,43 @@ void disable_noexec(struct mm_struct *mm, struct task_struct *tsk)
 	mm->context.noexec = 0;
 	update_mm(mm, tsk);
 }
+
+/*
+ * switch on pgstes for its userspace process (for kvm)
+ */
+int s390_enable_sie(void)
+{
+	struct task_struct *tsk = current;
+	struct mm_struct *mm;
+	int rc;
+
+	task_lock(tsk);
+
+	rc = 0;
+	if (tsk->mm->context.pgstes)
+		goto unlock;
+
+	rc = -EINVAL;
+	if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||
+	    tsk->mm != tsk->active_mm || tsk->mm->ioctx_list)
+		goto unlock;
+
+	tsk->mm->context.pgstes = 1;	/* dirty little tricks .. */
+	mm = dup_mm(tsk);
+	tsk->mm->context.pgstes = 0;
+
+	rc = -ENOMEM;
+	if (!mm)
+		goto unlock;
+	mmput(tsk->mm);
+	tsk->mm = tsk->active_mm = mm;
+	preempt_disable();
+	update_mm(mm, tsk);
+	cpu_set(smp_processor_id(), mm->cpu_vm_mask);
+	preempt_enable();
+	rc = 0;
+unlock:
+	task_unlock(tsk);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(s390_enable_sie);
diff --git a/trunk/arch/sh/drivers/pci/pci.c b/trunk/arch/sh/drivers/pci/pci.c
index 49b435c3a57a..08d2e7325252 100644
--- a/trunk/arch/sh/drivers/pci/pci.c
+++ b/trunk/arch/sh/drivers/pci/pci.c
@@ -191,8 +191,8 @@ void __init pcibios_update_irq(struct pci_dev *dev, int irq)
 
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
-	unsigned long start = pci_resource_start(dev, bar);
-	unsigned long len = pci_resource_len(dev, bar);
+	resource_size_t start = pci_resource_start(dev, bar);
+	resource_size_t len = pci_resource_len(dev, bar);
 	unsigned long flags = pci_resource_flags(dev, bar);
 
 	if (unlikely(!len || !start))
diff --git a/trunk/arch/sh/kernel/asm-offsets.c b/trunk/arch/sh/kernel/asm-offsets.c
index dc6725c51a89..57cf0e0680f3 100644
--- a/trunk/arch/sh/kernel/asm-offsets.c
+++ b/trunk/arch/sh/kernel/asm-offsets.c
@@ -11,12 +11,9 @@
 #include <linux/stddef.h>
 #include <linux/types.h>
 #include <linux/mm.h>
-#include <asm/thread_info.h>
-
-#define DEFINE(sym, val) \
-        asm volatile("\n->" #sym " %0 " #val : : "i" (val))
+#include <linux/kbuild.h>
 
-#define BLANK() asm volatile("\n->" : : )
+#include <asm/thread_info.h>
 
 int main(void)
 {
diff --git a/trunk/arch/sh/kernel/irq.c b/trunk/arch/sh/kernel/irq.c
index 9bf19b00696a..a2a99e487e33 100644
--- a/trunk/arch/sh/kernel/irq.c
+++ b/trunk/arch/sh/kernel/irq.c
@@ -200,8 +200,6 @@ void irq_ctx_exit(int cpu)
 	hardirq_ctx[cpu] = NULL;
 }
 
-extern asmlinkage void __do_softirq(void);
-
 asmlinkage void do_softirq(void)
 {
 	unsigned long flags;
diff --git a/trunk/arch/sh/mm/init.c b/trunk/arch/sh/mm/init.c
index 53dde0607362..d7df26bd1e54 100644
--- a/trunk/arch/sh/mm/init.c
+++ b/trunk/arch/sh/mm/init.c
@@ -307,15 +307,6 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 #endif
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-void online_page(struct page *page)
-{
-	ClearPageReserved(page);
-	init_page_count(page);
-	__free_page(page);
-	totalram_pages++;
-	num_physpages++;
-}
-
 int arch_add_memory(int nid, u64 start, u64 size)
 {
 	pg_data_t *pgdat;
diff --git a/trunk/arch/sparc/kernel/asm-offsets.c b/trunk/arch/sparc/kernel/asm-offsets.c
index 6773ed76e414..cd3f7694e9b9 100644
--- a/trunk/arch/sparc/kernel/asm-offsets.c
+++ b/trunk/arch/sparc/kernel/asm-offsets.c
@@ -12,11 +12,7 @@
 
 #include <linux/sched.h>
 // #include <linux/mm.h>
-
-#define DEFINE(sym, val) \
-	asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
+#include <linux/kbuild.h>
 
 int foo(void)
 {
diff --git a/trunk/arch/sparc/kernel/process.c b/trunk/arch/sparc/kernel/process.c
index 70c0dd22491d..e7f35198ae34 100644
--- a/trunk/arch/sparc/kernel/process.c
+++ b/trunk/arch/sparc/kernel/process.c
@@ -357,8 +357,6 @@ void flush_thread(void)
 {
 	current_thread_info()->w_saved = 0;
 
-	/* No new signal delivery by default */
-	current->thread.new_signal = 0;
 #ifndef CONFIG_SMP
 	if(last_task_used_math == current) {
 #else
diff --git a/trunk/arch/sparc/kernel/signal.c b/trunk/arch/sparc/kernel/signal.c
index 3e849e8e3480..3c312290c3c2 100644
--- a/trunk/arch/sparc/kernel/signal.c
+++ b/trunk/arch/sparc/kernel/signal.c
@@ -1,5 +1,4 @@
-/*  $Id: signal.c,v 1.110 2002/02/08 03:57:14 davem Exp $
- *  linux/arch/sparc/kernel/signal.c
+/*  linux/arch/sparc/kernel/signal.c
  *
  *  Copyright (C) 1991, 1992  Linus Torvalds
  *  Copyright (C) 1995 David S. Miller (davem@caip.rutgers.edu)
@@ -32,37 +31,7 @@ extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
 		   void *fpqueue, unsigned long *fpqdepth);
 extern void fpload(unsigned long *fpregs, unsigned long *fsr);
 
-/* Signal frames: the original one (compatible with SunOS):
- *
- * Set up a signal frame... Make the stack look the way SunOS
- * expects it to look which is basically:
- *
- * ---------------------------------- <-- %sp at signal time
- * Struct sigcontext
- * Signal address
- * Ptr to sigcontext area above
- * Signal code
- * The signal number itself
- * One register window
- * ---------------------------------- <-- New %sp
- */
-struct signal_sframe {
-	struct reg_window	sig_window;
-	int			sig_num;
-	int			sig_code;
-	struct sigcontext __user *sig_scptr;
-	int			sig_address;
-	struct sigcontext	sig_context;
-	unsigned int		extramask[_NSIG_WORDS - 1];
-};
-
-/* 
- * And the new one, intended to be used for Linux applications only
- * (we have enough in there to work with clone).
- * All the interesting bits are in the info field.
- */
-
-struct new_signal_frame {
+struct signal_frame {
 	struct sparc_stackf	ss;
 	__siginfo_t		info;
 	__siginfo_fpu_t __user	*fpu_save;
@@ -85,8 +54,7 @@ struct rt_signal_frame {
 };
 
 /* Align macros */
-#define SF_ALIGNEDSZ  (((sizeof(struct signal_sframe) + 7) & (~7)))
-#define NF_ALIGNEDSZ  (((sizeof(struct new_signal_frame) + 7) & (~7)))
+#define SF_ALIGNEDSZ  (((sizeof(struct signal_frame) + 7) & (~7)))
 #define RT_ALIGNEDSZ  (((sizeof(struct rt_signal_frame) + 7) & (~7)))
 
 static int _sigpause_common(old_sigset_t set)
@@ -141,15 +109,20 @@ restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 	return err;
 }
 
-static inline void do_new_sigreturn (struct pt_regs *regs)
+asmlinkage void do_sigreturn(struct pt_regs *regs)
 {
-	struct new_signal_frame __user *sf;
+	struct signal_frame __user *sf;
 	unsigned long up_psr, pc, npc;
 	sigset_t set;
 	__siginfo_fpu_t __user *fpu_save;
 	int err;
 
-	sf = (struct new_signal_frame __user *) regs->u_regs[UREG_FP];
+	/* Always make any pending restarted system calls return -EINTR */
+	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
+	synchronize_user_stack();
+
+	sf = (struct signal_frame __user *) regs->u_regs[UREG_FP];
 
 	/* 1. Make sure we are not getting garbage from the user */
 	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)))
@@ -198,73 +171,6 @@ static inline void do_new_sigreturn (struct pt_regs *regs)
 	force_sig(SIGSEGV, current);
 }
 
-asmlinkage void do_sigreturn(struct pt_regs *regs)
-{
-	struct sigcontext __user *scptr;
-	unsigned long pc, npc, psr;
-	sigset_t set;
-	int err;
-
-	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
-
-	synchronize_user_stack();
-
-	if (current->thread.new_signal) {
-		do_new_sigreturn(regs);
-		return;
-	}
-
-	scptr = (struct sigcontext __user *) regs->u_regs[UREG_I0];
-
-	/* Check sanity of the user arg. */
-	if (!access_ok(VERIFY_READ, scptr, sizeof(struct sigcontext)) ||
-	    (((unsigned long) scptr) & 3))
-		goto segv_and_exit;
-
-	err = __get_user(pc, &scptr->sigc_pc);
-	err |= __get_user(npc, &scptr->sigc_npc);
-
-	if ((pc | npc) & 3)
-		goto segv_and_exit;
-
-	/* This is pretty much atomic, no amount locking would prevent
-	 * the races which exist anyways.
-	 */
-	err |= __get_user(set.sig[0], &scptr->sigc_mask);
-	/* Note that scptr + 1 points to extramask */
-	err |= __copy_from_user(&set.sig[1], scptr + 1,
-				(_NSIG_WORDS - 1) * sizeof(unsigned int));
-	
-	if (err)
-		goto segv_and_exit;
-
-	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
-
-	regs->pc = pc;
-	regs->npc = npc;
-
-	err = __get_user(regs->u_regs[UREG_FP], &scptr->sigc_sp);
-	err |= __get_user(regs->u_regs[UREG_I0], &scptr->sigc_o0);
-	err |= __get_user(regs->u_regs[UREG_G1], &scptr->sigc_g1);
-
-	/* User can only change condition codes in %psr. */
-	err |= __get_user(psr, &scptr->sigc_psr);
-	if (err)
-		goto segv_and_exit;
-		
-	regs->psr &= ~(PSR_ICC);
-	regs->psr |= (psr & PSR_ICC);
-	return;
-
-segv_and_exit:
-	force_sig(SIGSEGV, current);
-}
-
 asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 {
 	struct rt_signal_frame __user *sf;
@@ -351,128 +257,6 @@ static inline void __user *get_sigframe(struct sigaction *sa, struct pt_regs *re
 	return (void __user *)(sp - framesize);
 }
 
-static inline void
-setup_frame(struct sigaction *sa, struct pt_regs *regs, int signr, sigset_t *oldset, siginfo_t *info)
-{
-	struct signal_sframe __user *sframep;
-	struct sigcontext __user *sc;
-	int window = 0, err;
-	unsigned long pc = regs->pc;
-	unsigned long npc = regs->npc;
-	struct thread_info *tp = current_thread_info();
-	void __user *sig_address;
-	int sig_code;
-
-	synchronize_user_stack();
-	sframep = (struct signal_sframe __user *)
-		get_sigframe(sa, regs, SF_ALIGNEDSZ);
-	if (invalid_frame_pointer(sframep, sizeof(*sframep))){
-		/* Don't change signal code and address, so that
-		 * post mortem debuggers can have a look.
-		 */
-		goto sigill_and_return;
-	}
-
-	sc = &sframep->sig_context;
-
-	/* We've already made sure frame pointer isn't in kernel space... */
-	err  = __put_user((sas_ss_flags(regs->u_regs[UREG_FP]) == SS_ONSTACK),
-			 &sc->sigc_onstack);
-	err |= __put_user(oldset->sig[0], &sc->sigc_mask);
-	err |= __copy_to_user(sframep->extramask, &oldset->sig[1],
-			      (_NSIG_WORDS - 1) * sizeof(unsigned int));
-	err |= __put_user(regs->u_regs[UREG_FP], &sc->sigc_sp);
-	err |= __put_user(pc, &sc->sigc_pc);
-	err |= __put_user(npc, &sc->sigc_npc);
-	err |= __put_user(regs->psr, &sc->sigc_psr);
-	err |= __put_user(regs->u_regs[UREG_G1], &sc->sigc_g1);
-	err |= __put_user(regs->u_regs[UREG_I0], &sc->sigc_o0);
-	err |= __put_user(tp->w_saved, &sc->sigc_oswins);
-	if (tp->w_saved)
-		for (window = 0; window < tp->w_saved; window++) {
-			put_user((char *)tp->rwbuf_stkptrs[window],
-				 &sc->sigc_spbuf[window]);
-			err |= __copy_to_user(&sc->sigc_wbuf[window],
-					      &tp->reg_window[window],
-					      sizeof(struct reg_window));
-		}
-	else
-		err |= __copy_to_user(sframep, (char *) regs->u_regs[UREG_FP],
-				      sizeof(struct reg_window));
-
-	tp->w_saved = 0; /* So process is allowed to execute. */
-
-	err |= __put_user(signr, &sframep->sig_num);
-	sig_address = NULL;
-	sig_code = 0;
-	if (SI_FROMKERNEL (info) && (info->si_code & __SI_MASK) == __SI_FAULT) {
-		sig_address = info->si_addr;
-		switch (signr) {
-		case SIGSEGV:
-			switch (info->si_code) {
-			case SEGV_MAPERR: sig_code = SUBSIG_NOMAPPING; break;
-			default: sig_code = SUBSIG_PROTECTION; break;
-			}
-			break;
-		case SIGILL:
-			switch (info->si_code) {
-			case ILL_ILLOPC: sig_code = SUBSIG_ILLINST; break;
-			case ILL_PRVOPC: sig_code = SUBSIG_PRIVINST; break;
-			case ILL_ILLTRP: sig_code = SUBSIG_BADTRAP(info->si_trapno); break;
-			default: sig_code = SUBSIG_STACK; break;
-			}
-			break;
-		case SIGFPE:
-			switch (info->si_code) {
-			case FPE_INTDIV: sig_code = SUBSIG_IDIVZERO; break;
-			case FPE_INTOVF: sig_code = SUBSIG_FPINTOVFL; break;
-			case FPE_FLTDIV: sig_code = SUBSIG_FPDIVZERO; break;
-			case FPE_FLTOVF: sig_code = SUBSIG_FPOVFLOW; break;
-			case FPE_FLTUND: sig_code = SUBSIG_FPUNFLOW; break;
-			case FPE_FLTRES: sig_code = SUBSIG_FPINEXACT; break;
-			case FPE_FLTINV: sig_code = SUBSIG_FPOPERROR; break;
-			default: sig_code = SUBSIG_FPERROR; break;
-			}
-			break;
-		case SIGBUS:
-			switch (info->si_code) {
-			case BUS_ADRALN: sig_code = SUBSIG_ALIGNMENT; break;
-			case BUS_ADRERR: sig_code = SUBSIG_MISCERROR; break;
-			default: sig_code = SUBSIG_BUSTIMEOUT; break;
-			}
-			break;
-		case SIGEMT:
-			switch (info->si_code) {
-			case EMT_TAGOVF: sig_code = SUBSIG_TAG; break;
-			}
-			break;
-		case SIGSYS:
-			if (info->si_code == (__SI_FAULT|0x100)) {
-				sig_code = info->si_trapno;
-				break;
-			}
-		default:
-			sig_address = NULL;
-		}
-	}
-	err |= __put_user((unsigned long)sig_address, &sframep->sig_address);
-	err |= __put_user(sig_code, &sframep->sig_code);
-	err |= __put_user(sc, &sframep->sig_scptr);
-	if (err)
-		goto sigsegv;
-
-	regs->u_regs[UREG_FP] = (unsigned long) sframep;
-	regs->pc = (unsigned long) sa->sa_handler;
-	regs->npc = (regs->pc + 4);
-	return;
-
-sigill_and_return:
-	do_exit(SIGILL);
-sigsegv:
-	force_sigsegv(signr, current);
-}
-
-
 static inline int
 save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 {
@@ -508,21 +292,20 @@ save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 	return err;
 }
 
-static inline void
-new_setup_frame(struct k_sigaction *ka, struct pt_regs *regs,
-		int signo, sigset_t *oldset)
+static void setup_frame(struct k_sigaction *ka, struct pt_regs *regs,
+			int signo, sigset_t *oldset)
 {
-	struct new_signal_frame __user *sf;
+	struct signal_frame __user *sf;
 	int sigframe_size, err;
 
 	/* 1. Make sure everything is clean */
 	synchronize_user_stack();
 
-	sigframe_size = NF_ALIGNEDSZ;
+	sigframe_size = SF_ALIGNEDSZ;
 	if (!used_math())
 		sigframe_size -= sizeof(__siginfo_fpu_t);
 
-	sf = (struct new_signal_frame __user *)
+	sf = (struct signal_frame __user *)
 		get_sigframe(&ka->sa, regs, sigframe_size);
 
 	if (invalid_frame_pointer(sf, sigframe_size))
@@ -586,9 +369,8 @@ new_setup_frame(struct k_sigaction *ka, struct pt_regs *regs,
 	force_sigsegv(signo, current);
 }
 
-static inline void
-new_setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
-		   int signo, sigset_t *oldset, siginfo_t *info)
+static void setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
+			   int signo, sigset_t *oldset, siginfo_t *info)
 {
 	struct rt_signal_frame __user *sf;
 	int sigframe_size;
@@ -674,11 +456,9 @@ handle_signal(unsigned long signr, struct k_sigaction *ka,
 	      siginfo_t *info, sigset_t *oldset, struct pt_regs *regs)
 {
 	if (ka->sa.sa_flags & SA_SIGINFO)
-		new_setup_rt_frame(ka, regs, signr, oldset, info);
-	else if (current->thread.new_signal)
-		new_setup_frame(ka, regs, signr, oldset);
+		setup_rt_frame(ka, regs, signr, oldset, info);
 	else
-		setup_frame(&ka->sa, regs, signr, oldset, info);
+		setup_frame(ka, regs, signr, oldset);
 
 	spin_lock_irq(&current->sighand->siglock);
 	sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
diff --git a/trunk/arch/sparc/kernel/sys_sparc.c b/trunk/arch/sparc/kernel/sys_sparc.c
index 42bf09db9a81..f188b5dc9fd0 100644
--- a/trunk/arch/sparc/kernel/sys_sparc.c
+++ b/trunk/arch/sparc/kernel/sys_sparc.c
@@ -1,5 +1,4 @@
-/* $Id: sys_sparc.c,v 1.70 2001/04/14 01:12:02 davem Exp $
- * linux/arch/sparc/kernel/sys_sparc.c
+/* linux/arch/sparc/kernel/sys_sparc.c
  *
  * This file contains various random system calls that
  * have a non-standard calling sequence on the Linux/sparc
@@ -395,10 +394,8 @@ sparc_sigaction (int sig, const struct old_sigaction __user *act,
 	struct k_sigaction new_ka, old_ka;
 	int ret;
 
-	if (sig < 0) {
-		current->thread.new_signal = 1;
-		sig = -sig;
-	}
+	WARN_ON_ONCE(sig >= 0);
+	sig = -sig;
 
 	if (act) {
 		unsigned long mask;
@@ -446,11 +443,6 @@ sys_rt_sigaction(int sig,
 	if (sigsetsize != sizeof(sigset_t))
 		return -EINVAL;
 
-	/* All tasks which use RT signals (effectively) use
-	 * new style signals.
-	 */
-	current->thread.new_signal = 1;
-
 	if (act) {
 		new_ka.ka_restorer = restorer;
 		if (copy_from_user(&new_ka.sa, act, sizeof(*act)))
diff --git a/trunk/arch/sparc/lib/iomap.c b/trunk/arch/sparc/lib/iomap.c
index 54501c1ca785..9ef37e13a920 100644
--- a/trunk/arch/sparc/lib/iomap.c
+++ b/trunk/arch/sparc/lib/iomap.c
@@ -21,8 +21,8 @@ EXPORT_SYMBOL(ioport_unmap);
 /* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
-	unsigned long start = pci_resource_start(dev, bar);
-	unsigned long len = pci_resource_len(dev, bar);
+	resource_size_t start = pci_resource_start(dev, bar);
+	resource_size_t len = pci_resource_len(dev, bar);
 	unsigned long flags = pci_resource_flags(dev, bar);
 
 	if (!len || !start)
diff --git a/trunk/arch/sparc64/Kconfig b/trunk/arch/sparc64/Kconfig
index 8acc5cc38621..edbe71e3fab9 100644
--- a/trunk/arch/sparc64/Kconfig
+++ b/trunk/arch/sparc64/Kconfig
@@ -1,9 +1,5 @@
-# $Id: config.in,v 1.158 2002/01/24 22:14:44 davem Exp $
-# For a description of the syntax of this configuration file,
-# see the Configure script.
-#
-
-mainmenu "Linux/UltraSPARC Kernel Configuration"
+# sparc64 configuration
+mainmenu "Linux Kernel Configuration for 64-bit SPARC"
 
 config SPARC
 	bool
@@ -17,12 +13,6 @@ config SPARC64
 	default y
 	select HAVE_IDE
 	select HAVE_LMB
-	help
-	  SPARC is a family of RISC microprocessors designed and marketed by
-	  Sun Microsystems, incorporated.  This port covers the newer 64-bit
-	  UltraSPARC.  The UltraLinux project maintains both the SPARC32 and
-	  SPARC64 ports; its web page is available at
-	  <http://www.ultralinux.org/>.
 
 config GENERIC_TIME
 	bool
@@ -97,7 +87,7 @@ config SPARC64_PAGE_SIZE_8KB
 	help
 	  This lets you select the page size of the kernel.
 
-	  8KB and 64KB work quite well, since Sparc ELF sections
+	  8KB and 64KB work quite well, since SPARC ELF sections
 	  provide for up to 64KB alignment.
 
 	  Therefore, 512KB and 4MB are for expert hackers only.
@@ -138,7 +128,7 @@ config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs"
 	depends on SMP
 	select HOTPLUG
-	---help---
+	help
 	  Say Y here to experiment with turning CPUs off and on.  CPUs
 	  can be controlled through /sys/devices/system/cpu/cpu#.
 	  Say N if you want to disable CPU hotplug.
@@ -155,23 +145,16 @@ source "kernel/time/Kconfig"
 
 config SMP
 	bool "Symmetric multi-processing support"
-	---help---
+	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, say N. If you have a system with more than
 	  one CPU, say Y.
 
 	  If you say N here, the kernel will run on single and multiprocessor
 	  machines, but will use only one CPU of a multiprocessor machine. If
-	  you say Y here, the kernel will run on many, but not all,
-	  singleprocessor machines. On a singleprocessor machine, the kernel
-	  will run faster if you say N here.
-
-	  People using multiprocessor machines who say Y here should also say
-	  Y to "Enhanced Real Time Clock Support", below. The "Advanced Power
-	  Management" code will be disabled if you say Y here.
-
-	  See also <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO
-	  available at <http://www.tldp.org/docs.html#howto>.
+	  you say Y here, the kernel will run on single-processor machines.
+	  On a single-processor machine, the kernel will run faster if you say
+	  N here.
 
 	  If you don't know what to do here, say N.
 
@@ -284,50 +267,19 @@ source "mm/Kconfig"
 
 config ISA
 	bool
-	help
-	  Find out whether you have ISA slots on your motherboard.  ISA is the
-	  name of a bus system, i.e. the way the CPU talks to the other stuff
-	  inside your box.  Other bus systems are PCI, EISA, MicroChannel
-	  (MCA) or VESA.  ISA is an older system, now being displaced by PCI;
-	  newer boards don't support it.  If you have ISA, say Y, otherwise N.
 
 config ISAPNP
 	bool
-	help
-	  Say Y here if you would like support for ISA Plug and Play devices.
-	  Some information is in <file:Documentation/isapnp.txt>.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called isapnp.
-
-	  If unsure, say Y.
 
 config EISA
 	bool
-	---help---
-	  The Extended Industry Standard Architecture (EISA) bus was
-	  developed as an open alternative to the IBM MicroChannel bus.
-
-	  The EISA bus provided some of the features of the IBM MicroChannel
-	  bus while maintaining backward compatibility with cards made for
-	  the older ISA bus.  The EISA bus saw limited use between 1988 and
-	  1995 when it was made obsolete by the PCI bus.
-
-	  Say Y here if you are building a kernel for an EISA-based machine.
-
-	  Otherwise, say N.
 
 config MCA
 	bool
-	help
-	  MicroChannel Architecture is found in some IBM PS/2 machines and
-	  laptops.  It is a bus system similar to PCI or ISA. See
-	  <file:Documentation/mca.txt> (and especially the web page given
-	  there) before attempting to build an MCA bus kernel.
 
 config PCMCIA
 	tristate
-	---help---
+	help
 	  Say Y here if you want to attach PCMCIA- or PC-cards to your Linux
 	  computer.  These are credit-card size devices such as network cards,
 	  modems or hard drives often used with laptops computers.  There are
@@ -369,10 +321,10 @@ config PCI
 	bool "PCI support"
 	select ARCH_SUPPORTS_MSI
 	help
-	  Find out whether you have a PCI motherboard. PCI is the name of a
-	  bus system, i.e. the way the CPU talks to the other stuff inside
-	  your box. Other bus systems are ISA, EISA, MicroChannel (MCA) or
-	  VESA. If you have PCI, say Y, otherwise N.
+	  Find out whether your system includes a PCI bus. PCI is the name of
+	  a bus system, i.e. the way the CPU talks to the other stuff inside
+	  your box.  If you say Y here, the kernel will include drivers and
+	  infrastructure code to support PCI bus devices.
 
 config PCI_DOMAINS
 	def_bool PCI
@@ -396,15 +348,8 @@ menu "Executable file formats"
 
 source "fs/Kconfig.binfmt"
 
-config SPARC32_COMPAT
-	bool "Kernel support for Linux/Sparc 32bit binary compatibility"
-	help
-	  This allows you to run 32-bit binaries on your Ultra.
-	  Everybody wants this; say Y.
-
 config COMPAT
 	bool
-	depends on SPARC32_COMPAT
 	default y
 	select COMPAT_BINFMT_ELF
 
@@ -421,8 +366,8 @@ config SCHED_SMT
 	default y
 	help
 	  SMT scheduler support improves the CPU scheduler's decision making
-	  when dealing with UltraSPARC cpus at a cost of slightly increased
-	  overhead in some places. If unsure say N here.
+	  when dealing with SPARC cpus at a cost of slightly increased overhead
+	  in some places. If unsure say N here.
 
 config SCHED_MC
 	bool "Multi-core scheduler support"
diff --git a/trunk/arch/sparc64/defconfig b/trunk/arch/sparc64/defconfig
index 92f79680f70d..aff93c9d13f4 100644
--- a/trunk/arch/sparc64/defconfig
+++ b/trunk/arch/sparc64/defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.25-numa
-# Wed Apr 23 04:49:08 2008
+# Linux kernel version: 2.6.25
+# Sat Apr 26 03:11:06 2008
 #
 CONFIG_SPARC=y
 CONFIG_SPARC64=y
@@ -152,7 +152,9 @@ CONFIG_GENERIC_CALIBRATE_DELAY=y
 CONFIG_HUGETLB_PAGE_SIZE_4MB=y
 # CONFIG_HUGETLB_PAGE_SIZE_512K is not set
 # CONFIG_HUGETLB_PAGE_SIZE_64K is not set
-# CONFIG_NUMA is not set
+CONFIG_NUMA=y
+CONFIG_NODES_SHIFT=4
+CONFIG_NODES_SPAN_OTHER_NODES=y
 CONFIG_ARCH_POPULATES_NODE_MAP=y
 CONFIG_ARCH_SELECT_MEMORY_MODEL=y
 CONFIG_ARCH_SPARSEMEM_ENABLE=y
@@ -162,12 +164,14 @@ CONFIG_SELECT_MEMORY_MODEL=y
 # CONFIG_DISCONTIGMEM_MANUAL is not set
 CONFIG_SPARSEMEM_MANUAL=y
 CONFIG_SPARSEMEM=y
+CONFIG_NEED_MULTIPLE_NODES=y
 CONFIG_HAVE_MEMORY_PRESENT=y
 # CONFIG_SPARSEMEM_STATIC is not set
 CONFIG_SPARSEMEM_EXTREME=y
 CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y
 CONFIG_SPARSEMEM_VMEMMAP=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
+CONFIG_MIGRATION=y
 CONFIG_RESOURCES_64BIT=y
 CONFIG_ZONE_DMA_FLAG=0
 CONFIG_NR_QUICK=1
@@ -191,7 +195,6 @@ CONFIG_SUN_OPENPROMFS=m
 CONFIG_BINFMT_ELF=y
 CONFIG_COMPAT_BINFMT_ELF=y
 CONFIG_BINFMT_MISC=m
-CONFIG_SPARC32_COMPAT=y
 CONFIG_COMPAT=y
 CONFIG_SYSVIPC_COMPAT=y
 CONFIG_SCHED_SMT=y
@@ -746,13 +749,7 @@ CONFIG_DEVPORT=y
 CONFIG_I2C=y
 CONFIG_I2C_BOARDINFO=y
 # CONFIG_I2C_CHARDEV is not set
-
-#
-# I2C Algorithms
-#
 CONFIG_I2C_ALGOBIT=y
-# CONFIG_I2C_ALGOPCF is not set
-# CONFIG_I2C_ALGOPCA is not set
 
 #
 # I2C Hardware Bus support
@@ -780,6 +777,7 @@ CONFIG_I2C_ALGOBIT=y
 # CONFIG_I2C_VIA is not set
 # CONFIG_I2C_VIAPRO is not set
 # CONFIG_I2C_VOODOO3 is not set
+# CONFIG_I2C_PCA_PLATFORM is not set
 
 #
 # Miscellaneous I2C Chip support
@@ -1026,6 +1024,7 @@ CONFIG_SND_ALI5451=m
 # CONFIG_SND_AU8810 is not set
 # CONFIG_SND_AU8820 is not set
 # CONFIG_SND_AU8830 is not set
+# CONFIG_SND_AW2 is not set
 # CONFIG_SND_AZT3328 is not set
 # CONFIG_SND_BT87X is not set
 # CONFIG_SND_CA0106 is not set
@@ -1096,10 +1095,6 @@ CONFIG_SND_SUN_CS4231=m
 #
 # CONFIG_SND_SOC is not set
 
-#
-# SoC Audio support for SuperH
-#
-
 #
 # ALSA SoC audio for Freescale SOCs
 #
diff --git a/trunk/arch/sparc64/kernel/Makefile b/trunk/arch/sparc64/kernel/Makefile
index 63c6ae0dd273..2bd0340b743d 100644
--- a/trunk/arch/sparc64/kernel/Makefile
+++ b/trunk/arch/sparc64/kernel/Makefile
@@ -15,17 +15,17 @@ obj-y		:= process.o setup.o cpu.o idprom.o \
 		   visemul.o prom.o of_device.o hvapi.o sstate.o mdesc.o
 
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
-obj-$(CONFIG_PCI)	 += ebus.o isa.o pci_common.o \
+obj-$(CONFIG_PCI)	 += ebus.o pci_common.o \
 			    pci_psycho.o pci_sabre.o pci_schizo.o \
 			    pci_sun4v.o pci_sun4v_asm.o pci_fire.o
 obj-$(CONFIG_PCI_MSI)	+= pci_msi.o
 obj-$(CONFIG_SMP)	 += smp.o trampoline.o hvtramp.o
-obj-$(CONFIG_SPARC32_COMPAT) += sys32.o sys_sparc32.o signal32.o
+obj-$(CONFIG_COMPAT) += sys32.o sys_sparc32.o signal32.o
 obj-$(CONFIG_MODULES) += module.o
 obj-$(CONFIG_US3_FREQ) += us3_cpufreq.o
 obj-$(CONFIG_US2E_FREQ) += us2e_cpufreq.o
 obj-$(CONFIG_KPROBES) += kprobes.o
 obj-$(CONFIG_SUN_LDOMS) += ldc.o vio.o viohs.o ds.o
 obj-$(CONFIG_AUDIT) += audit.o
-obj-$(CONFIG_AUDIT)$(CONFIG_SPARC32_COMPAT) += compat_audit.o
+obj-$(CONFIG_AUDIT)$(CONFIG_COMPAT) += compat_audit.o
 obj-y += $(obj-yy)
diff --git a/trunk/arch/sparc64/kernel/audit.c b/trunk/arch/sparc64/kernel/audit.c
index 24d7f4b4178a..8fff0ac63d56 100644
--- a/trunk/arch/sparc64/kernel/audit.c
+++ b/trunk/arch/sparc64/kernel/audit.c
@@ -30,7 +30,7 @@ static unsigned signal_class[] = {
 
 int audit_classify_arch(int arch)
 {
-#ifdef CONFIG_SPARC32_COMPAT
+#ifdef CONFIG_COMPAT
 	if (arch == AUDIT_ARCH_SPARC)
 		return 1;
 #endif
@@ -39,7 +39,7 @@ int audit_classify_arch(int arch)
 
 int audit_classify_syscall(int abi, unsigned syscall)
 {
-#ifdef CONFIG_SPARC32_COMPAT
+#ifdef CONFIG_COMPAT
 	extern int sparc32_classify_syscall(unsigned);
 	if (abi == AUDIT_ARCH_SPARC)
 		return sparc32_classify_syscall(syscall);
@@ -60,7 +60,7 @@ int audit_classify_syscall(int abi, unsigned syscall)
 
 static int __init audit_classes_init(void)
 {
-#ifdef CONFIG_SPARC32_COMPAT
+#ifdef CONFIG_COMPAT
 	extern __u32 sparc32_dir_class[];
 	extern __u32 sparc32_write_class[];
 	extern __u32 sparc32_read_class[];
diff --git a/trunk/arch/sparc64/kernel/irq.c b/trunk/arch/sparc64/kernel/irq.c
index eb88bd6e674e..b441a26b73b0 100644
--- a/trunk/arch/sparc64/kernel/irq.c
+++ b/trunk/arch/sparc64/kernel/irq.c
@@ -1,6 +1,6 @@
 /* irq.c: UltraSparc IRQ handling/init/registry.
  *
- * Copyright (C) 1997, 2007  David S. Miller  (davem@davemloft.net)
+ * Copyright (C) 1997, 2007, 2008 David S. Miller (davem@davemloft.net)
  * Copyright (C) 1998  Eddie C. Dost    (ecd@skynet.be)
  * Copyright (C) 1998  Jakub Jelinek    (jj@ultra.linux.cz)
  */
@@ -308,6 +308,7 @@ static void sun4u_irq_enable(unsigned int virt_irq)
 			 IMAP_AID_SAFARI | IMAP_NID_SAFARI);
 		val |= tid | IMAP_VALID;
 		upa_writeq(val, imap);
+		upa_writeq(ICLR_IDLE, data->iclr);
 	}
 }
 
diff --git a/trunk/arch/sparc64/kernel/isa.c b/trunk/arch/sparc64/kernel/isa.c
deleted file mode 100644
index a2af5ed784c9..000000000000
--- a/trunk/arch/sparc64/kernel/isa.c
+++ /dev/null
@@ -1,191 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/pci.h>
-#include <linux/slab.h>
-#include <asm/oplib.h>
-#include <asm/prom.h>
-#include <asm/of_device.h>
-#include <asm/isa.h>
-
-struct sparc_isa_bridge *isa_chain;
-
-static void __init fatal_err(const char *reason)
-{
-	prom_printf("ISA: fatal error, %s.\n", reason);
-}
-
-static void __init report_dev(struct sparc_isa_device *isa_dev, int child)
-{
-	if (child)
-		printk(" (%s)", isa_dev->prom_node->name);
-	else
-		printk(" [%s", isa_dev->prom_node->name);
-}
-
-static void __init isa_dev_get_resource(struct sparc_isa_device *isa_dev)
-{
-	struct of_device *op = of_find_device_by_node(isa_dev->prom_node);
-
-	memcpy(&isa_dev->resource, &op->resource[0], sizeof(struct resource));
-}
-
-static void __init isa_dev_get_irq(struct sparc_isa_device *isa_dev)
-{
-	struct of_device *op = of_find_device_by_node(isa_dev->prom_node);
-
-	if (!op || !op->num_irqs) {
-		isa_dev->irq = PCI_IRQ_NONE;
-	} else {
-		isa_dev->irq = op->irqs[0];
-	}
-}
-
-static void __init isa_fill_children(struct sparc_isa_device *parent_isa_dev)
-{
-	struct device_node *dp = parent_isa_dev->prom_node->child;
-
-	if (!dp)
-		return;
-
-	printk(" ->");
-	while (dp) {
-		struct sparc_isa_device *isa_dev;
-
-		isa_dev = kzalloc(sizeof(*isa_dev), GFP_KERNEL);
-		if (!isa_dev) {
-			fatal_err("cannot allocate child isa_dev");
-			prom_halt();
-		}
-
-		/* Link it in to parent. */
-		isa_dev->next = parent_isa_dev->child;
-		parent_isa_dev->child = isa_dev;
-
-		isa_dev->bus = parent_isa_dev->bus;
-		isa_dev->prom_node = dp;
-
-		isa_dev_get_resource(isa_dev);
-		isa_dev_get_irq(isa_dev);
-
-		report_dev(isa_dev, 1);
-
-		dp = dp->sibling;
-	}
-}
-
-static void __init isa_fill_devices(struct sparc_isa_bridge *isa_br)
-{
-	struct device_node *dp = isa_br->prom_node->child;
-
-	while (dp) {
-		struct sparc_isa_device *isa_dev;
-		struct dev_archdata *sd;
-
-		isa_dev = kzalloc(sizeof(*isa_dev), GFP_KERNEL);
-		if (!isa_dev) {
-			printk(KERN_DEBUG "ISA: cannot allocate isa_dev");
-			return;
-		}
-
-		sd = &isa_dev->ofdev.dev.archdata;
-		sd->prom_node = dp;
-		sd->op = &isa_dev->ofdev;
-		sd->iommu = isa_br->ofdev.dev.parent->archdata.iommu;
-		sd->stc = isa_br->ofdev.dev.parent->archdata.stc;
-		sd->numa_node = isa_br->ofdev.dev.parent->archdata.numa_node;
-
-		isa_dev->ofdev.node = dp;
-		isa_dev->ofdev.dev.parent = &isa_br->ofdev.dev;
-		isa_dev->ofdev.dev.bus = &isa_bus_type;
-		sprintf(isa_dev->ofdev.dev.bus_id, "isa[%08x]", dp->node);
-
-		/* Register with core */
-		if (of_device_register(&isa_dev->ofdev) != 0) {
-			printk(KERN_DEBUG "isa: device registration error for %s!\n",
-			       dp->path_component_name);
-			kfree(isa_dev);
-			goto next_sibling;
-		}
-
-		/* Link it in. */
-		isa_dev->next = NULL;
-		if (isa_br->devices == NULL) {
-			isa_br->devices = isa_dev;
-		} else {
-			struct sparc_isa_device *tmp = isa_br->devices;
-
-			while (tmp->next)
-				tmp = tmp->next;
-
-			tmp->next = isa_dev;
-		}
-
-		isa_dev->bus = isa_br;
-		isa_dev->prom_node = dp;
-
-		isa_dev_get_resource(isa_dev);
-		isa_dev_get_irq(isa_dev);
-
-		report_dev(isa_dev, 0);
-
-		isa_fill_children(isa_dev);
-
-		printk("]");
-
-	next_sibling:
-		dp = dp->sibling;
-	}
-}
-
-void __init isa_init(void)
-{
-	struct pci_dev *pdev;
-	unsigned short vendor, device;
-	int index = 0;
-
-	vendor = PCI_VENDOR_ID_AL;
-	device = PCI_DEVICE_ID_AL_M1533;
-
-	pdev = NULL;
-	while ((pdev = pci_get_device(vendor, device, pdev)) != NULL) {
-		struct sparc_isa_bridge *isa_br;
-		struct device_node *dp;
-
-		dp = pci_device_to_OF_node(pdev);
-
-		isa_br = kzalloc(sizeof(*isa_br), GFP_KERNEL);
-		if (!isa_br) {
-			printk(KERN_DEBUG "isa: cannot allocate sparc_isa_bridge");
-			pci_dev_put(pdev);
-			return;
-		}
-
-		isa_br->ofdev.node = dp;
-		isa_br->ofdev.dev.parent = &pdev->dev;
-		isa_br->ofdev.dev.bus = &isa_bus_type;
-		sprintf(isa_br->ofdev.dev.bus_id, "isa%d", index);
-
-		/* Register with core */
-		if (of_device_register(&isa_br->ofdev) != 0) {
-			printk(KERN_DEBUG "isa: device registration error for %s!\n",
-			       dp->path_component_name);
-			kfree(isa_br);
-			pci_dev_put(pdev);
-			return;
-		}
-
-		/* Link it in. */
-		isa_br->next = isa_chain;
-		isa_chain = isa_br;
-
-		isa_br->self = pdev;
-		isa_br->index = index++;
-		isa_br->prom_node = dp;
-
-		printk("isa%d:", isa_br->index);
-
-		isa_fill_devices(isa_br);
-
-		printk("\n");
-	}
-}
diff --git a/trunk/arch/sparc64/kernel/of_device.c b/trunk/arch/sparc64/kernel/of_device.c
index 9e58e8cba1c3..d569f60c24b8 100644
--- a/trunk/arch/sparc64/kernel/of_device.c
+++ b/trunk/arch/sparc64/kernel/of_device.c
@@ -412,12 +412,6 @@ static int __init build_one_resource(struct device_node *parent,
 
 static int __init use_1to1_mapping(struct device_node *pp)
 {
-	/* If this is on the PMU bus, don't try to translate it even
-	 * if a ranges property exists.
-	 */
-	if (!strcmp(pp->name, "pmu"))
-		return 1;
-
 	/* If we have a ranges property in the parent, use it.  */
 	if (of_find_property(pp, "ranges", NULL) != NULL)
 		return 0;
diff --git a/trunk/arch/sparc64/kernel/pci.c b/trunk/arch/sparc64/kernel/pci.c
index 49f912766519..dbf2fc2f4d87 100644
--- a/trunk/arch/sparc64/kernel/pci.c
+++ b/trunk/arch/sparc64/kernel/pci.c
@@ -23,7 +23,6 @@
 #include <asm/pgtable.h>
 #include <asm/irq.h>
 #include <asm/ebus.h>
-#include <asm/isa.h>
 #include <asm/prom.h>
 #include <asm/apb.h>
 
@@ -885,7 +884,6 @@ static int __init pcibios_init(void)
 
 	pci_scan_each_controller_bus();
 
-	isa_init();
 	ebus_init();
 	power_init();
 
diff --git a/trunk/arch/sparc64/kernel/process.c b/trunk/arch/sparc64/kernel/process.c
index acf8c5250aa9..056013749157 100644
--- a/trunk/arch/sparc64/kernel/process.c
+++ b/trunk/arch/sparc64/kernel/process.c
@@ -1,5 +1,4 @@
-/*  $Id: process.c,v 1.131 2002/02/09 19:49:30 davem Exp $
- *  arch/sparc64/kernel/process.c
+/*  arch/sparc64/kernel/process.c
  *
  *  Copyright (C) 1995, 1996 David S. Miller (davem@caip.rutgers.edu)
  *  Copyright (C) 1996       Eddie C. Dost   (ecd@skynet.be)
@@ -368,9 +367,6 @@ void flush_thread(void)
 	
 	if (get_thread_current_ds() != ASI_AIUS)
 		set_fs(USER_DS);
-
-	/* Init new signal delivery disposition. */
-	clear_thread_flag(TIF_NEWSIGNALS);
 }
 
 /* It's a bit more tricky when 64-bit tasks are involved... */
@@ -595,6 +591,12 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
 	if (clone_flags & CLONE_SETTLS)
 		t->kregs->u_regs[UREG_G7] = regs->u_regs[UREG_I3];
 
+	/* We do not want to accidently trigger system call restart
+	 * handling in the new thread.  Therefore, clear out the trap
+	 * type, which will make pt_regs_regs_is_syscall() return false.
+	 */
+	pt_regs_clear_trap_type(t->kregs);
+
 	return 0;
 }
 
diff --git a/trunk/arch/sparc64/kernel/signal.c b/trunk/arch/sparc64/kernel/signal.c
index 77a3e8592cbc..f2d88d8f7a42 100644
--- a/trunk/arch/sparc64/kernel/signal.c
+++ b/trunk/arch/sparc64/kernel/signal.c
@@ -8,7 +8,7 @@
  *  Copyright (C) 1997,1998 Jakub Jelinek   (jj@sunsite.mff.cuni.cz)
  */
 
-#ifdef CONFIG_SPARC32_COMPAT
+#ifdef CONFIG_COMPAT
 #include <linux/compat.h>	/* for compat_old_sigset_t */
 #endif
 #include <linux/sched.h>
@@ -236,9 +236,6 @@ struct rt_signal_frame {
 	__siginfo_fpu_t		fpu_state;
 };
 
-/* Align macros */
-#define RT_ALIGNEDSZ  (((sizeof(struct rt_signal_frame) + 7) & (~7)))
-
 static long _sigpause_common(old_sigset_t set)
 {
 	set &= _BLOCKABLE;
@@ -400,7 +397,7 @@ setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
 	synchronize_user_stack();
 	save_and_clear_fpu();
 	
-	sigframe_size = RT_ALIGNEDSZ;
+	sigframe_size = sizeof(struct rt_signal_frame);
 	if (!(current_thread_info()->fpsaved[0] & FPRS_FEF))
 		sigframe_size -= sizeof(__siginfo_fpu_t);
 
@@ -516,11 +513,10 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 	struct k_sigaction ka;
 	sigset_t *oldset;
 	siginfo_t info;
-	int signr, tt;
+	int signr;
 	
-	tt = regs->magic & 0x1ff;
-	if (tt == 0x110 || tt == 0x111 || tt == 0x16d) {
-		regs->magic &= ~0x1ff;
+	if (pt_regs_is_syscall(regs)) {
+		pt_regs_clear_trap_type(regs);
 		cookie.restart_syscall = 1;
 	} else
 		cookie.restart_syscall = 0;
@@ -531,7 +527,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 	else
 		oldset = &current->blocked;
 
-#ifdef CONFIG_SPARC32_COMPAT
+#ifdef CONFIG_COMPAT
 	if (test_thread_flag(TIF_32BIT)) {
 		extern void do_signal32(sigset_t *, struct pt_regs *,
 					struct signal_deliver_cookie *);
diff --git a/trunk/arch/sparc64/kernel/signal32.c b/trunk/arch/sparc64/kernel/signal32.c
index 43cdec64d9c9..91f8d0826db1 100644
--- a/trunk/arch/sparc64/kernel/signal32.c
+++ b/trunk/arch/sparc64/kernel/signal32.c
@@ -1,5 +1,4 @@
-/*  $Id: signal32.c,v 1.74 2002/02/09 19:49:30 davem Exp $
- *  arch/sparc64/kernel/signal32.c
+/*  arch/sparc64/kernel/signal32.c
  *
  *  Copyright (C) 1991, 1992  Linus Torvalds
  *  Copyright (C) 1995 David S. Miller (davem@caip.rutgers.edu)
@@ -31,30 +30,6 @@
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
-/* Signal frames: the original one (compatible with SunOS):
- *
- * Set up a signal frame... Make the stack look the way SunOS
- * expects it to look which is basically:
- *
- * ---------------------------------- <-- %sp at signal time
- * Struct sigcontext
- * Signal address
- * Ptr to sigcontext area above
- * Signal code
- * The signal number itself
- * One register window
- * ---------------------------------- <-- New %sp
- */
-struct signal_sframe32 {
-	struct reg_window32 sig_window;
-	int sig_num;
-	int sig_code;
-	/* struct sigcontext32 * */ u32 sig_scptr;
-	int sig_address;
-	struct sigcontext32 sig_context;
-	unsigned int extramask[_COMPAT_NSIG_WORDS - 1];
-};
-
 /* This magic should be in g_upper[0] for all upper parts
  * to be valid.
  */
@@ -65,12 +40,7 @@ typedef struct {
 	unsigned int asi;
 } siginfo_extra_v8plus_t;
 
-/* 
- * And the new one, intended to be used for Linux applications only
- * (we have enough in there to work with clone).
- * All the interesting bits are in the info field.
- */
-struct new_signal_frame32 {
+struct signal_frame32 {
 	struct sparc_stackf32	ss;
 	__siginfo32_t		info;
 	/* __siginfo_fpu32_t * */ u32 fpu_save;
@@ -149,8 +119,7 @@ struct rt_signal_frame32 {
 };
 
 /* Align macros */
-#define SF_ALIGNEDSZ  (((sizeof(struct signal_sframe32) + 7) & (~7)))
-#define NF_ALIGNEDSZ  (((sizeof(struct new_signal_frame32) + 7) & (~7)))
+#define SF_ALIGNEDSZ  (((sizeof(struct signal_frame32) + 7) & (~7)))
 #define RT_ALIGNEDSZ  (((sizeof(struct rt_signal_frame32) + 7) & (~7)))
 
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
@@ -241,17 +210,22 @@ static int restore_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu
 	return err;
 }
 
-void do_new_sigreturn32(struct pt_regs *regs)
+void do_sigreturn32(struct pt_regs *regs)
 {
-	struct new_signal_frame32 __user *sf;
+	struct signal_frame32 __user *sf;
 	unsigned int psr;
 	unsigned pc, npc, fpu_save;
 	sigset_t set;
 	unsigned seta[_COMPAT_NSIG_WORDS];
 	int err, i;
 	
+	/* Always make any pending restarted system calls return -EINTR */
+	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
+	synchronize_user_stack();
+
 	regs->u_regs[UREG_FP] &= 0x00000000ffffffffUL;
-	sf = (struct new_signal_frame32 __user *) regs->u_regs[UREG_FP];
+	sf = (struct signal_frame32 __user *) regs->u_regs[UREG_FP];
 
 	/* 1. Make sure we are not getting garbage from the user */
 	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
@@ -319,76 +293,6 @@ void do_new_sigreturn32(struct pt_regs *regs)
 	force_sig(SIGSEGV, current);
 }
 
-asmlinkage void do_sigreturn32(struct pt_regs *regs)
-{
-	struct sigcontext32 __user *scptr;
-	unsigned int pc, npc, psr;
-	sigset_t set;
-	unsigned int seta[_COMPAT_NSIG_WORDS];
-	int err;
-
-	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
-
-	synchronize_user_stack();
-	if (test_thread_flag(TIF_NEWSIGNALS)) {
-		do_new_sigreturn32(regs);
-		return;
-	}
-
-	scptr = (struct sigcontext32 __user *)
-		(regs->u_regs[UREG_I0] & 0x00000000ffffffffUL);
-	/* Check sanity of the user arg. */
-	if (!access_ok(VERIFY_READ, scptr, sizeof(struct sigcontext32)) ||
-	    (((unsigned long) scptr) & 3))
-		goto segv;
-
-	err = __get_user(pc, &scptr->sigc_pc);
-	err |= __get_user(npc, &scptr->sigc_npc);
-
-	if ((pc | npc) & 3)
-		goto segv; /* Nice try. */
-
-	err |= __get_user(seta[0], &scptr->sigc_mask);
-	/* Note that scptr + 1 points to extramask */
-	err |= copy_from_user(seta+1, scptr + 1,
-			      (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int));
-	if (err)
-	    	goto segv;
-	switch (_NSIG_WORDS) {
-		case 4: set.sig[3] = seta[6] + (((long)seta[7]) << 32);
-		case 3: set.sig[2] = seta[4] + (((long)seta[5]) << 32);
-		case 2: set.sig[1] = seta[2] + (((long)seta[3]) << 32);
-		case 1: set.sig[0] = seta[0] + (((long)seta[1]) << 32);
-	}
-	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
-	
-	if (test_thread_flag(TIF_32BIT)) {
-		pc &= 0xffffffff;
-		npc &= 0xffffffff;
-	}
-	regs->tpc = pc;
-	regs->tnpc = npc;
-	err = __get_user(regs->u_regs[UREG_FP], &scptr->sigc_sp);
-	err |= __get_user(regs->u_regs[UREG_I0], &scptr->sigc_o0);
-	err |= __get_user(regs->u_regs[UREG_G1], &scptr->sigc_g1);
-
-	/* User can only change condition codes in %tstate. */
-	err |= __get_user(psr, &scptr->sigc_psr);
-	if (err)
-		goto segv;
-	regs->tstate &= ~(TSTATE_ICC|TSTATE_XCC);
-	regs->tstate |= psr_to_tstate_icc(psr);
-	return;
-
-segv:
-	force_sig(SIGSEGV, current);
-}
-
 asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 {
 	struct rt_signal_frame32 __user *sf;
@@ -504,145 +408,6 @@ static void __user *get_sigframe(struct sigaction *sa, struct pt_regs *regs, uns
 	return (void __user *)(sp - framesize);
 }
 
-static void
-setup_frame32(struct sigaction *sa, struct pt_regs *regs, int signr, sigset_t *oldset, siginfo_t *info)
-{
-	struct signal_sframe32 __user *sframep;
-	struct sigcontext32 __user *sc;
-	unsigned int seta[_COMPAT_NSIG_WORDS];
-	int err = 0;
-	void __user *sig_address;
-	int sig_code;
-	unsigned long pc = regs->tpc;
-	unsigned long npc = regs->tnpc;
-	unsigned int psr;
-
-	if (test_thread_flag(TIF_32BIT)) {
-		pc &= 0xffffffff;
-		npc &= 0xffffffff;
-	}
-
-	synchronize_user_stack();
-	save_and_clear_fpu();
-
-	sframep = (struct signal_sframe32 __user *)
-		get_sigframe(sa, regs, SF_ALIGNEDSZ);
-	if (invalid_frame_pointer(sframep, sizeof(*sframep))){
-		/* Don't change signal code and address, so that
-		 * post mortem debuggers can have a look.
-		 */
-		do_exit(SIGILL);
-	}
-
-	sc = &sframep->sig_context;
-
-	/* We've already made sure frame pointer isn't in kernel space... */
-	err = __put_user((sas_ss_flags(regs->u_regs[UREG_FP]) == SS_ONSTACK),
-			 &sc->sigc_onstack);
-	
-	switch (_NSIG_WORDS) {
-	case 4: seta[7] = (oldset->sig[3] >> 32);
-	        seta[6] = oldset->sig[3];
-	case 3: seta[5] = (oldset->sig[2] >> 32);
-	        seta[4] = oldset->sig[2];
-	case 2: seta[3] = (oldset->sig[1] >> 32);
-	        seta[2] = oldset->sig[1];
-	case 1: seta[1] = (oldset->sig[0] >> 32);
-	        seta[0] = oldset->sig[0];
-	}
-	err |= __put_user(seta[0], &sc->sigc_mask);
-	err |= __copy_to_user(sframep->extramask, seta + 1,
-			      (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int));
-	err |= __put_user(regs->u_regs[UREG_FP], &sc->sigc_sp);
-	err |= __put_user(pc, &sc->sigc_pc);
-	err |= __put_user(npc, &sc->sigc_npc);
-	psr = tstate_to_psr(regs->tstate);
-	if (current_thread_info()->fpsaved[0] & FPRS_FEF)
-		psr |= PSR_EF;
-	err |= __put_user(psr, &sc->sigc_psr);
-	err |= __put_user(regs->u_regs[UREG_G1], &sc->sigc_g1);
-	err |= __put_user(regs->u_regs[UREG_I0], &sc->sigc_o0);
-	err |= __put_user(get_thread_wsaved(), &sc->sigc_oswins);
-
-	err |= copy_in_user((u32 __user *)sframep,
-			    (u32 __user *)(regs->u_regs[UREG_FP]),
-			    sizeof(struct reg_window32));
-		       
-	set_thread_wsaved(0); /* So process is allowed to execute. */
-	err |= __put_user(signr, &sframep->sig_num);
-	sig_address = NULL;
-	sig_code = 0;
-	if (SI_FROMKERNEL (info) && (info->si_code & __SI_MASK) == __SI_FAULT) {
-		sig_address = info->si_addr;
-		switch (signr) {
-		case SIGSEGV:
-			switch (info->si_code) {
-			case SEGV_MAPERR: sig_code = SUBSIG_NOMAPPING; break;
-			default: sig_code = SUBSIG_PROTECTION; break;
-			}
-			break;
-		case SIGILL:
-			switch (info->si_code) {
-			case ILL_ILLOPC: sig_code = SUBSIG_ILLINST; break;
-			case ILL_PRVOPC: sig_code = SUBSIG_PRIVINST; break;
-			case ILL_ILLTRP: sig_code = SUBSIG_BADTRAP(info->si_trapno); break;
-			default: sig_code = SUBSIG_STACK; break;
-			}
-			break;
-		case SIGFPE:
-			switch (info->si_code) {
-			case FPE_INTDIV: sig_code = SUBSIG_IDIVZERO; break;
-			case FPE_INTOVF: sig_code = SUBSIG_FPINTOVFL; break;
-			case FPE_FLTDIV: sig_code = SUBSIG_FPDIVZERO; break;
-			case FPE_FLTOVF: sig_code = SUBSIG_FPOVFLOW; break;
-			case FPE_FLTUND: sig_code = SUBSIG_FPUNFLOW; break;
-			case FPE_FLTRES: sig_code = SUBSIG_FPINEXACT; break;
-			case FPE_FLTINV: sig_code = SUBSIG_FPOPERROR; break;
-			default: sig_code = SUBSIG_FPERROR; break;
-			}
-			break;
-		case SIGBUS:
-			switch (info->si_code) {
-			case BUS_ADRALN: sig_code = SUBSIG_ALIGNMENT; break;
-			case BUS_ADRERR: sig_code = SUBSIG_MISCERROR; break;
-			default: sig_code = SUBSIG_BUSTIMEOUT; break;
-			}
-			break;
-		case SIGEMT:
-			switch (info->si_code) {
-			case EMT_TAGOVF: sig_code = SUBSIG_TAG; break;
-			}
-			break;
-		case SIGSYS:
-			if (info->si_code == (__SI_FAULT|0x100)) {
-				/* See sys_sunos32.c */
-				sig_code = info->si_trapno;
-				break;
-			}
-		default:
-			sig_address = NULL;
-		}
-	}
-	err |= __put_user(ptr_to_compat(sig_address), &sframep->sig_address);
-	err |= __put_user(sig_code, &sframep->sig_code);
-	err |= __put_user(ptr_to_compat(sc), &sframep->sig_scptr);
-	if (err)
-		goto sigsegv;
-
-	regs->u_regs[UREG_FP] = (unsigned long) sframep;
-	regs->tpc = (unsigned long) sa->sa_handler;
-	regs->tnpc = (regs->tpc + 4);
-	if (test_thread_flag(TIF_32BIT)) {
-		regs->tpc &= 0xffffffff;
-		regs->tnpc &= 0xffffffff;
-	}
-	return;
-
-sigsegv:
-	force_sigsegv(signr, current);
-}
-
-
 static int save_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 {
 	unsigned long *fpregs = current_thread_info()->fpregs;
@@ -663,10 +428,10 @@ static int save_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 	return err;
 }
 
-static void new_setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
-			      int signo, sigset_t *oldset)
+static void setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
+			  int signo, sigset_t *oldset)
 {
-	struct new_signal_frame32 __user *sf;
+	struct signal_frame32 __user *sf;
 	int sigframe_size;
 	u32 psr;
 	int i, err;
@@ -676,11 +441,11 @@ static void new_setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
 	synchronize_user_stack();
 	save_and_clear_fpu();
 	
-	sigframe_size = NF_ALIGNEDSZ;
+	sigframe_size = SF_ALIGNEDSZ;
 	if (!(current_thread_info()->fpsaved[0] & FPRS_FEF))
 		sigframe_size -= sizeof(__siginfo_fpu_t);
 
-	sf = (struct new_signal_frame32 __user *)
+	sf = (struct signal_frame32 __user *)
 		get_sigframe(&ka->sa, regs, sigframe_size);
 	
 	if (invalid_frame_pointer(sf, sigframe_size))
@@ -944,10 +709,9 @@ static inline void handle_signal32(unsigned long signr, struct k_sigaction *ka,
 {
 	if (ka->sa.sa_flags & SA_SIGINFO)
 		setup_rt_frame32(ka, regs, signr, oldset, info);
-	else if (test_thread_flag(TIF_NEWSIGNALS))
-		new_setup_frame32(ka, regs, signr, oldset);
 	else
-		setup_frame32(&ka->sa, regs, signr, oldset, info);
+		setup_frame32(ka, regs, signr, oldset);
+
 	spin_lock_irq(&current->sighand->siglock);
 	sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
 	if (!(ka->sa.sa_flags & SA_NOMASK))
diff --git a/trunk/arch/sparc64/kernel/sparc64_ksyms.c b/trunk/arch/sparc64/kernel/sparc64_ksyms.c
index 66336590e830..8ac0b99f2c55 100644
--- a/trunk/arch/sparc64/kernel/sparc64_ksyms.c
+++ b/trunk/arch/sparc64/kernel/sparc64_ksyms.c
@@ -49,7 +49,6 @@
 #endif
 #ifdef CONFIG_PCI
 #include <asm/ebus.h>
-#include <asm/isa.h>
 #endif
 #include <asm/ns87303.h>
 #include <asm/timer.h>
@@ -187,7 +186,6 @@ EXPORT_SYMBOL(insw);
 EXPORT_SYMBOL(insl);
 #ifdef CONFIG_PCI
 EXPORT_SYMBOL(ebus_chain);
-EXPORT_SYMBOL(isa_chain);
 EXPORT_SYMBOL(pci_alloc_consistent);
 EXPORT_SYMBOL(pci_free_consistent);
 EXPORT_SYMBOL(pci_map_single);
diff --git a/trunk/arch/sparc64/kernel/sys_sparc32.c b/trunk/arch/sparc64/kernel/sys_sparc32.c
index c1a61e98899a..161ce4710fe7 100644
--- a/trunk/arch/sparc64/kernel/sys_sparc32.c
+++ b/trunk/arch/sparc64/kernel/sys_sparc32.c
@@ -554,10 +554,8 @@ asmlinkage long compat_sys_sigaction(int sig, struct old_sigaction32 __user *act
         struct k_sigaction new_ka, old_ka;
         int ret;
 
-	if (sig < 0) {
-		set_thread_flag(TIF_NEWSIGNALS);
-		sig = -sig;
-	}
+	WARN_ON_ONCE(sig >= 0);
+	sig = -sig;
 
         if (act) {
 		compat_old_sigset_t mask;
@@ -601,11 +599,6 @@ asmlinkage long compat_sys_rt_sigaction(int sig,
         if (sigsetsize != sizeof(compat_sigset_t))
                 return -EINVAL;
 
-	/* All tasks which use RT signals (effectively) use
-	 * new style signals.
-	 */
-	set_thread_flag(TIF_NEWSIGNALS);
-
         if (act) {
 		u32 u_handler, u_restorer;
 
diff --git a/trunk/arch/sparc64/lib/iomap.c b/trunk/arch/sparc64/lib/iomap.c
index ac556db06973..7120ebbd4d03 100644
--- a/trunk/arch/sparc64/lib/iomap.c
+++ b/trunk/arch/sparc64/lib/iomap.c
@@ -21,8 +21,8 @@ EXPORT_SYMBOL(ioport_unmap);
 /* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
-	unsigned long start = pci_resource_start(dev, bar);
-	unsigned long len = pci_resource_len(dev, bar);
+	resource_size_t start = pci_resource_start(dev, bar);
+	resource_size_t len = pci_resource_len(dev, bar);
 	unsigned long flags = pci_resource_flags(dev, bar);
 
 	if (!len || !start)
diff --git a/trunk/arch/sparc64/mm/init.c b/trunk/arch/sparc64/mm/init.c
index 177d8aaeec42..8c2b50e8abc6 100644
--- a/trunk/arch/sparc64/mm/init.c
+++ b/trunk/arch/sparc64/mm/init.c
@@ -1699,9 +1699,21 @@ void __init paging_init(void)
 	 * functions like clear_dcache_dirty_cpu use the cpu mask
 	 * in 13-bit signed-immediate instruction fields.
 	 */
-	BUILD_BUG_ON(FLAGS_RESERVED != 32);
+
+	/*
+	 * Page flags must not reach into upper 32 bits that are used
+	 * for the cpu number
+	 */
+	BUILD_BUG_ON(NR_PAGEFLAGS > 32);
+
+	/*
+	 * The bit fields placed in the high range must not reach below
+	 * the 32 bit boundary. Otherwise we cannot place the cpu field
+	 * at the 32 bit boundary.
+	 */
 	BUILD_BUG_ON(SECTIONS_WIDTH + NODES_WIDTH + ZONES_WIDTH +
-		     ilog2(roundup_pow_of_two(NR_CPUS)) > FLAGS_RESERVED);
+		ilog2(roundup_pow_of_two(NR_CPUS)) > 32);
+
 	BUILD_BUG_ON(NR_CPUS > 4096);
 
 	kern_base = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
diff --git a/trunk/arch/um/drivers/chan_kern.c b/trunk/arch/um/drivers/chan_kern.c
index db3082b4da46..6e51424745ab 100644
--- a/trunk/arch/um/drivers/chan_kern.c
+++ b/trunk/arch/um/drivers/chan_kern.c
@@ -125,7 +125,7 @@ static int open_one_chan(struct chan *chan)
 	return 0;
 }
 
-int open_chan(struct list_head *chans)
+static int open_chan(struct list_head *chans)
 {
 	struct list_head *ele;
 	struct chan *chan;
@@ -583,19 +583,6 @@ int parse_chan_pair(char *str, struct line *line, int device,
 	return 0;
 }
 
-int chan_out_fd(struct list_head *chans)
-{
-	struct list_head *ele;
-	struct chan *chan;
-
-	list_for_each(ele, chans) {
-		chan = list_entry(ele, struct chan, list);
-		if (chan->primary && chan->output)
-			return chan->fd;
-	}
-	return -1;
-}
-
 void chan_interrupt(struct list_head *chans, struct delayed_work *task,
 		    struct tty_struct *tty, int irq)
 {
diff --git a/trunk/arch/um/drivers/line.c b/trunk/arch/um/drivers/line.c
index 2c898c4d6b6a..10b86e1cc659 100644
--- a/trunk/arch/um/drivers/line.c
+++ b/trunk/arch/um/drivers/line.c
@@ -304,7 +304,7 @@ int line_ioctl(struct tty_struct *tty, struct file * file,
 				break;
 		if (i == ARRAY_SIZE(tty_ioctls)) {
 			printk(KERN_ERR "%s: %s: unknown ioctl: 0x%x\n",
-			       __FUNCTION__, tty->name, cmd);
+			       __func__, tty->name, cmd);
 		}
 		ret = -ENOIOCTLCMD;
 		break;
diff --git a/trunk/arch/um/drivers/mcast_kern.c b/trunk/arch/um/drivers/mcast_kern.c
index 822092f149be..8c4378a76d63 100644
--- a/trunk/arch/um/drivers/mcast_kern.c
+++ b/trunk/arch/um/drivers/mcast_kern.c
@@ -58,7 +58,7 @@ static const struct net_kern_info mcast_kern_info = {
 	.write			= mcast_write,
 };
 
-int mcast_setup(char *str, char **mac_out, void *data)
+static int mcast_setup(char *str, char **mac_out, void *data)
 {
 	struct mcast_init *init = data;
 	char *port_str = NULL, *ttl_str = NULL, *remain;
diff --git a/trunk/arch/um/drivers/mconsole_user.c b/trunk/arch/um/drivers/mconsole_user.c
index 13af2f03ed84..f8cf4c8bedef 100644
--- a/trunk/arch/um/drivers/mconsole_user.c
+++ b/trunk/arch/um/drivers/mconsole_user.c
@@ -39,7 +39,7 @@ static struct mconsole_command commands[] = {
 /* Initialized in mconsole_init, which is an initcall */
 char mconsole_socket_name[256];
 
-int mconsole_reply_v0(struct mc_request *req, char *reply)
+static int mconsole_reply_v0(struct mc_request *req, char *reply)
 {
 	struct iovec iov;
 	struct msghdr msg;
diff --git a/trunk/arch/um/drivers/net_kern.c b/trunk/arch/um/drivers/net_kern.c
index 1d43bdfc20c4..5b4ca8d93682 100644
--- a/trunk/arch/um/drivers/net_kern.c
+++ b/trunk/arch/um/drivers/net_kern.c
@@ -116,7 +116,7 @@ static void uml_dev_close(struct work_struct *work)
 	dev_close(lp->dev);
 }
 
-irqreturn_t uml_net_interrupt(int irq, void *dev_id)
+static irqreturn_t uml_net_interrupt(int irq, void *dev_id)
 {
 	struct net_device *dev = dev_id;
 	struct uml_net_private *lp = dev->priv;
@@ -296,7 +296,7 @@ static struct ethtool_ops uml_net_ethtool_ops = {
 	.get_link	= ethtool_op_get_link,
 };
 
-void uml_net_user_timer_expire(unsigned long _conn)
+static void uml_net_user_timer_expire(unsigned long _conn)
 {
 #ifdef undef
 	struct connection *conn = (struct connection *)_conn;
@@ -786,7 +786,7 @@ static int uml_inetaddr_event(struct notifier_block *this, unsigned long event,
 }
 
 /* uml_net_init shouldn't be called twice on two CPUs at the same time */
-struct notifier_block uml_inetaddr_notifier = {
+static struct notifier_block uml_inetaddr_notifier = {
 	.notifier_call		= uml_inetaddr_event,
 };
 
diff --git a/trunk/arch/um/drivers/port_user.c b/trunk/arch/um/drivers/port_user.c
index addd75902656..d269ca387f10 100644
--- a/trunk/arch/um/drivers/port_user.c
+++ b/trunk/arch/um/drivers/port_user.c
@@ -153,7 +153,7 @@ struct port_pre_exec_data {
 	int pipe_fd;
 };
 
-void port_pre_exec(void *arg)
+static void port_pre_exec(void *arg)
 {
 	struct port_pre_exec_data *data = arg;
 
diff --git a/trunk/arch/um/drivers/slip_kern.c b/trunk/arch/um/drivers/slip_kern.c
index 6b4a0f9e38de..d19faec7046e 100644
--- a/trunk/arch/um/drivers/slip_kern.c
+++ b/trunk/arch/um/drivers/slip_kern.c
@@ -13,7 +13,7 @@ struct slip_init {
 	char *gate_addr;
 };
 
-void slip_init(struct net_device *dev, void *data)
+static void slip_init(struct net_device *dev, void *data)
 {
 	struct uml_net_private *private;
 	struct slip_data *spri;
@@ -57,7 +57,7 @@ static int slip_write(int fd, struct sk_buff *skb, struct uml_net_private *lp)
 			       (struct slip_data *) &lp->user);
 }
 
-const struct net_kern_info slip_kern_info = {
+static const struct net_kern_info slip_kern_info = {
 	.init			= slip_init,
 	.protocol		= slip_protocol,
 	.read			= slip_read,
diff --git a/trunk/arch/um/drivers/stdio_console.c b/trunk/arch/um/drivers/stdio_console.c
index cec0c33cdd39..49266f6108c4 100644
--- a/trunk/arch/um/drivers/stdio_console.c
+++ b/trunk/arch/um/drivers/stdio_console.c
@@ -34,7 +34,7 @@
 
 static struct tty_driver *console_driver;
 
-void stdio_announce(char *dev_name, int dev)
+static void stdio_announce(char *dev_name, int dev)
 {
 	printk(KERN_INFO "Virtual console %d assigned device '%s'\n", dev,
 	       dev_name);
@@ -158,7 +158,7 @@ static struct console stdiocons = {
 	.index		= -1,
 };
 
-int stdio_init(void)
+static int stdio_init(void)
 {
 	char *new_title;
 
diff --git a/trunk/arch/um/drivers/ubd_kern.c b/trunk/arch/um/drivers/ubd_kern.c
index be3a2797dac4..5e45e39a8a8d 100644
--- a/trunk/arch/um/drivers/ubd_kern.c
+++ b/trunk/arch/um/drivers/ubd_kern.c
@@ -72,18 +72,6 @@ struct io_thread_req {
 	int error;
 };
 
-extern int open_ubd_file(char *file, struct openflags *openflags, int shared,
-			 char **backing_file_out, int *bitmap_offset_out,
-			 unsigned long *bitmap_len_out, int *data_offset_out,
-			 int *create_cow_out);
-extern int create_cow_file(char *cow_file, char *backing_file,
-			   struct openflags flags, int sectorsize,
-			   int alignment, int *bitmap_offset_out,
-			   unsigned long *bitmap_len_out,
-			   int *data_offset_out);
-extern int read_cow_bitmap(int fd, void *buf, int offset, int len);
-extern void do_io(struct io_thread_req *req);
-
 static inline int ubd_test_bit(__u64 bit, unsigned char *data)
 {
 	__u64 n;
@@ -200,7 +188,7 @@ struct ubd {
 }
 
 /* Protected by ubd_lock */
-struct ubd ubd_devs[MAX_DEV] = { [ 0 ... MAX_DEV - 1 ] = DEFAULT_UBD };
+static struct ubd ubd_devs[MAX_DEV] = { [0 ... MAX_DEV - 1] = DEFAULT_UBD };
 
 /* Only changed by fake_ide_setup which is a setup */
 static int fake_ide = 0;
@@ -463,7 +451,7 @@ __uml_help(udb_setup,
 static void do_ubd_request(struct request_queue * q);
 
 /* Only changed by ubd_init, which is an initcall. */
-int thread_fd = -1;
+static int thread_fd = -1;
 
 static void ubd_end_request(struct request *req, int bytes, int error)
 {
@@ -531,7 +519,7 @@ static irqreturn_t ubd_intr(int irq, void *dev)
 /* Only changed by ubd_init, which is an initcall. */
 static int io_pid = -1;
 
-void kill_io_thread(void)
+static void kill_io_thread(void)
 {
 	if(io_pid != -1)
 		os_kill_process(io_pid, 1);
@@ -547,6 +535,192 @@ static inline int ubd_file_size(struct ubd *ubd_dev, __u64 *size_out)
 	return os_file_size(file, size_out);
 }
 
+static int read_cow_bitmap(int fd, void *buf, int offset, int len)
+{
+	int err;
+
+	err = os_seek_file(fd, offset);
+	if (err < 0)
+		return err;
+
+	err = os_read_file(fd, buf, len);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int backing_file_mismatch(char *file, __u64 size, time_t mtime)
+{
+	unsigned long modtime;
+	unsigned long long actual;
+	int err;
+
+	err = os_file_modtime(file, &modtime);
+	if (err < 0) {
+		printk(KERN_ERR "Failed to get modification time of backing "
+		       "file \"%s\", err = %d\n", file, -err);
+		return err;
+	}
+
+	err = os_file_size(file, &actual);
+	if (err < 0) {
+		printk(KERN_ERR "Failed to get size of backing file \"%s\", "
+		       "err = %d\n", file, -err);
+		return err;
+	}
+
+	if (actual != size) {
+		/*__u64 can be a long on AMD64 and with %lu GCC complains; so
+		 * the typecast.*/
+		printk(KERN_ERR "Size mismatch (%llu vs %llu) of COW header "
+		       "vs backing file\n", (unsigned long long) size, actual);
+		return -EINVAL;
+	}
+	if (modtime != mtime) {
+		printk(KERN_ERR "mtime mismatch (%ld vs %ld) of COW header vs "
+		       "backing file\n", mtime, modtime);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int path_requires_switch(char *from_cmdline, char *from_cow, char *cow)
+{
+	struct uml_stat buf1, buf2;
+	int err;
+
+	if (from_cmdline == NULL)
+		return 0;
+	if (!strcmp(from_cmdline, from_cow))
+		return 0;
+
+	err = os_stat_file(from_cmdline, &buf1);
+	if (err < 0) {
+		printk(KERN_ERR "Couldn't stat '%s', err = %d\n", from_cmdline,
+		       -err);
+		return 0;
+	}
+	err = os_stat_file(from_cow, &buf2);
+	if (err < 0) {
+		printk(KERN_ERR "Couldn't stat '%s', err = %d\n", from_cow,
+		       -err);
+		return 1;
+	}
+	if ((buf1.ust_dev == buf2.ust_dev) && (buf1.ust_ino == buf2.ust_ino))
+		return 0;
+
+	printk(KERN_ERR "Backing file mismatch - \"%s\" requested, "
+	       "\"%s\" specified in COW header of \"%s\"\n",
+	       from_cmdline, from_cow, cow);
+	return 1;
+}
+
+static int open_ubd_file(char *file, struct openflags *openflags, int shared,
+		  char **backing_file_out, int *bitmap_offset_out,
+		  unsigned long *bitmap_len_out, int *data_offset_out,
+		  int *create_cow_out)
+{
+	time_t mtime;
+	unsigned long long size;
+	__u32 version, align;
+	char *backing_file;
+	int fd, err, sectorsize, asked_switch, mode = 0644;
+
+	fd = os_open_file(file, *openflags, mode);
+	if (fd < 0) {
+		if ((fd == -ENOENT) && (create_cow_out != NULL))
+			*create_cow_out = 1;
+		if (!openflags->w ||
+		    ((fd != -EROFS) && (fd != -EACCES)))
+			return fd;
+		openflags->w = 0;
+		fd = os_open_file(file, *openflags, mode);
+		if (fd < 0)
+			return fd;
+	}
+
+	if (shared)
+		printk(KERN_INFO "Not locking \"%s\" on the host\n", file);
+	else {
+		err = os_lock_file(fd, openflags->w);
+		if (err < 0) {
+			printk(KERN_ERR "Failed to lock '%s', err = %d\n",
+			       file, -err);
+			goto out_close;
+		}
+	}
+
+	/* Successful return case! */
+	if (backing_file_out == NULL)
+		return fd;
+
+	err = read_cow_header(file_reader, &fd, &version, &backing_file, &mtime,
+			      &size, &sectorsize, &align, bitmap_offset_out);
+	if (err && (*backing_file_out != NULL)) {
+		printk(KERN_ERR "Failed to read COW header from COW file "
+		       "\"%s\", errno = %d\n", file, -err);
+		goto out_close;
+	}
+	if (err)
+		return fd;
+
+	asked_switch = path_requires_switch(*backing_file_out, backing_file,
+					    file);
+
+	/* Allow switching only if no mismatch. */
+	if (asked_switch && !backing_file_mismatch(*backing_file_out, size,
+						   mtime)) {
+		printk(KERN_ERR "Switching backing file to '%s'\n",
+		       *backing_file_out);
+		err = write_cow_header(file, fd, *backing_file_out,
+				       sectorsize, align, &size);
+		if (err) {
+			printk(KERN_ERR "Switch failed, errno = %d\n", -err);
+			goto out_close;
+		}
+	} else {
+		*backing_file_out = backing_file;
+		err = backing_file_mismatch(*backing_file_out, size, mtime);
+		if (err)
+			goto out_close;
+	}
+
+	cow_sizes(version, size, sectorsize, align, *bitmap_offset_out,
+		  bitmap_len_out, data_offset_out);
+
+	return fd;
+ out_close:
+	os_close_file(fd);
+	return err;
+}
+
+static int create_cow_file(char *cow_file, char *backing_file,
+		    struct openflags flags,
+		    int sectorsize, int alignment, int *bitmap_offset_out,
+		    unsigned long *bitmap_len_out, int *data_offset_out)
+{
+	int err, fd;
+
+	flags.c = 1;
+	fd = open_ubd_file(cow_file, &flags, 0, NULL, NULL, NULL, NULL, NULL);
+	if (fd < 0) {
+		err = fd;
+		printk(KERN_ERR "Open of COW file '%s' failed, errno = %d\n",
+		       cow_file, -err);
+		goto out;
+	}
+
+	err = init_cow_file(fd, cow_file, backing_file, sectorsize, alignment,
+			    bitmap_offset_out, bitmap_len_out,
+			    data_offset_out);
+	if (!err)
+		return fd;
+	os_close_file(fd);
+ out:
+	return err;
+}
+
 static void ubd_close_dev(struct ubd *ubd_dev)
 {
 	os_close_file(ubd_dev->fd);
@@ -1166,185 +1340,6 @@ static int ubd_ioctl(struct inode * inode, struct file * file,
 	return -EINVAL;
 }
 
-static int path_requires_switch(char *from_cmdline, char *from_cow, char *cow)
-{
-	struct uml_stat buf1, buf2;
-	int err;
-
-	if(from_cmdline == NULL)
-		return 0;
-	if(!strcmp(from_cmdline, from_cow))
-		return 0;
-
-	err = os_stat_file(from_cmdline, &buf1);
-	if(err < 0){
-		printk("Couldn't stat '%s', err = %d\n", from_cmdline, -err);
-		return 0;
-	}
-	err = os_stat_file(from_cow, &buf2);
-	if(err < 0){
-		printk("Couldn't stat '%s', err = %d\n", from_cow, -err);
-		return 1;
-	}
-	if((buf1.ust_dev == buf2.ust_dev) && (buf1.ust_ino == buf2.ust_ino))
-		return 0;
-
-	printk("Backing file mismatch - \"%s\" requested,\n"
-	       "\"%s\" specified in COW header of \"%s\"\n",
-	       from_cmdline, from_cow, cow);
-	return 1;
-}
-
-static int backing_file_mismatch(char *file, __u64 size, time_t mtime)
-{
-	unsigned long modtime;
-	unsigned long long actual;
-	int err;
-
-	err = os_file_modtime(file, &modtime);
-	if(err < 0){
-		printk("Failed to get modification time of backing file "
-		       "\"%s\", err = %d\n", file, -err);
-		return err;
-	}
-
-	err = os_file_size(file, &actual);
-	if(err < 0){
-		printk("Failed to get size of backing file \"%s\", "
-		       "err = %d\n", file, -err);
-		return err;
-	}
-
-	if(actual != size){
-		/*__u64 can be a long on AMD64 and with %lu GCC complains; so
-		 * the typecast.*/
-		printk("Size mismatch (%llu vs %llu) of COW header vs backing "
-		       "file\n", (unsigned long long) size, actual);
-		return -EINVAL;
-	}
-	if(modtime != mtime){
-		printk("mtime mismatch (%ld vs %ld) of COW header vs backing "
-		       "file\n", mtime, modtime);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-int read_cow_bitmap(int fd, void *buf, int offset, int len)
-{
-	int err;
-
-	err = os_seek_file(fd, offset);
-	if(err < 0)
-		return err;
-
-	err = os_read_file(fd, buf, len);
-	if(err < 0)
-		return err;
-
-	return 0;
-}
-
-int open_ubd_file(char *file, struct openflags *openflags, int shared,
-		  char **backing_file_out, int *bitmap_offset_out,
-		  unsigned long *bitmap_len_out, int *data_offset_out,
-		  int *create_cow_out)
-{
-	time_t mtime;
-	unsigned long long size;
-	__u32 version, align;
-	char *backing_file;
-	int fd, err, sectorsize, asked_switch, mode = 0644;
-
-	fd = os_open_file(file, *openflags, mode);
-	if (fd < 0) {
-		if ((fd == -ENOENT) && (create_cow_out != NULL))
-			*create_cow_out = 1;
-		if (!openflags->w ||
-		    ((fd != -EROFS) && (fd != -EACCES)))
-			return fd;
-		openflags->w = 0;
-		fd = os_open_file(file, *openflags, mode);
-		if (fd < 0)
-			return fd;
-	}
-
-	if(shared)
-		printk("Not locking \"%s\" on the host\n", file);
-	else {
-		err = os_lock_file(fd, openflags->w);
-		if(err < 0){
-			printk("Failed to lock '%s', err = %d\n", file, -err);
-			goto out_close;
-		}
-	}
-
-	/* Successful return case! */
-	if(backing_file_out == NULL)
-		return fd;
-
-	err = read_cow_header(file_reader, &fd, &version, &backing_file, &mtime,
-			      &size, &sectorsize, &align, bitmap_offset_out);
-	if(err && (*backing_file_out != NULL)){
-		printk("Failed to read COW header from COW file \"%s\", "
-		       "errno = %d\n", file, -err);
-		goto out_close;
-	}
-	if(err)
-		return fd;
-
-	asked_switch = path_requires_switch(*backing_file_out, backing_file, file);
-
-	/* Allow switching only if no mismatch. */
-	if (asked_switch && !backing_file_mismatch(*backing_file_out, size, mtime)) {
-		printk("Switching backing file to '%s'\n", *backing_file_out);
-		err = write_cow_header(file, fd, *backing_file_out,
-				       sectorsize, align, &size);
-		if (err) {
-			printk("Switch failed, errno = %d\n", -err);
-			goto out_close;
-		}
-	} else {
-		*backing_file_out = backing_file;
-		err = backing_file_mismatch(*backing_file_out, size, mtime);
-		if (err)
-			goto out_close;
-	}
-
-	cow_sizes(version, size, sectorsize, align, *bitmap_offset_out,
-		  bitmap_len_out, data_offset_out);
-
-	return fd;
- out_close:
-	os_close_file(fd);
-	return err;
-}
-
-int create_cow_file(char *cow_file, char *backing_file, struct openflags flags,
-		    int sectorsize, int alignment, int *bitmap_offset_out,
-		    unsigned long *bitmap_len_out, int *data_offset_out)
-{
-	int err, fd;
-
-	flags.c = 1;
-	fd = open_ubd_file(cow_file, &flags, 0, NULL, NULL, NULL, NULL, NULL);
-	if(fd < 0){
-		err = fd;
-		printk("Open of COW file '%s' failed, errno = %d\n", cow_file,
-		       -err);
-		goto out;
-	}
-
-	err = init_cow_file(fd, cow_file, backing_file, sectorsize, alignment,
-			    bitmap_offset_out, bitmap_len_out,
-			    data_offset_out);
-	if(!err)
-		return fd;
-	os_close_file(fd);
- out:
-	return err;
-}
-
 static int update_bitmap(struct io_thread_req *req)
 {
 	int n;
@@ -1369,7 +1364,7 @@ static int update_bitmap(struct io_thread_req *req)
 	return 0;
 }
 
-void do_io(struct io_thread_req *req)
+static void do_io(struct io_thread_req *req)
 {
 	char *buf;
 	unsigned long len;
diff --git a/trunk/arch/um/include/chan_kern.h b/trunk/arch/um/include/chan_kern.h
index 624b5100a3cd..1e651457e049 100644
--- a/trunk/arch/um/include/chan_kern.h
+++ b/trunk/arch/um/include/chan_kern.h
@@ -31,7 +31,6 @@ extern void chan_interrupt(struct list_head *chans, struct delayed_work *task,
 			   struct tty_struct *tty, int irq);
 extern int parse_chan_pair(char *str, struct line *line, int device,
 			   const struct chan_opts *opts, char **error_out);
-extern int open_chan(struct list_head *chans);
 extern int write_chan(struct list_head *chans, const char *buf, int len,
 			     int write_irq);
 extern int console_write_chan(struct list_head *chans, const char *buf, 
@@ -45,7 +44,6 @@ extern void close_chan(struct list_head *chans, int delay_free_irq);
 extern int chan_window_size(struct list_head *chans, 
 			     unsigned short *rows_out, 
 			     unsigned short *cols_out);
-extern int chan_out_fd(struct list_head *chans);
 extern int chan_config_string(struct list_head *chans, char *str, int size,
 			      char **error_out);
 
diff --git a/trunk/arch/um/kernel/exitcode.c b/trunk/arch/um/kernel/exitcode.c
index 984f80e668ca..6540d2c9fbb7 100644
--- a/trunk/arch/um/kernel/exitcode.c
+++ b/trunk/arch/um/kernel/exitcode.c
@@ -59,7 +59,7 @@ static int make_proc_exitcode(void)
 {
 	struct proc_dir_entry *ent;
 
-	ent = create_proc_entry("exitcode", 0600, &proc_root);
+	ent = create_proc_entry("exitcode", 0600, NULL);
 	if (ent == NULL) {
 		printk(KERN_WARNING "make_proc_exitcode : Failed to register "
 		       "/proc/exitcode\n");
diff --git a/trunk/arch/um/kernel/process.c b/trunk/arch/um/kernel/process.c
index e8cb9ff183e9..83603cfbde81 100644
--- a/trunk/arch/um/kernel/process.c
+++ b/trunk/arch/um/kernel/process.c
@@ -364,7 +364,7 @@ int __init make_proc_sysemu(void)
 	if (!sysemu_supported)
 		return 0;
 
-	ent = create_proc_entry("sysemu", 0600, &proc_root);
+	ent = create_proc_entry("sysemu", 0600, NULL);
 
 	if (ent == NULL)
 	{
diff --git a/trunk/arch/um/kernel/time.c b/trunk/arch/um/kernel/time.c
index e066e84493b1..0d0cea2ac98d 100644
--- a/trunk/arch/um/kernel/time.c
+++ b/trunk/arch/um/kernel/time.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/clockchips.h>
+#include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/jiffies.h>
 #include <linux/threads.h>
@@ -109,8 +110,6 @@ static void __init setup_itimer(void)
 	clockevents_register_device(&itimer_clockevent);
 }
 
-extern void (*late_time_init)(void);
-
 void __init time_init(void)
 {
 	long long nsecs;
diff --git a/trunk/arch/um/kernel/um_arch.c b/trunk/arch/um/kernel/um_arch.c
index a6c1dd1cf5a1..56deed623446 100644
--- a/trunk/arch/um/kernel/um_arch.c
+++ b/trunk/arch/um/kernel/um_arch.c
@@ -115,7 +115,7 @@ static int have_root __initdata = 0;
 /* Set in uml_mem_setup and modified in linux_main */
 long long physmem_size = 32 * 1024 * 1024;
 
-static char *usage_string =
+static const char *usage_string =
 "User Mode Linux v%s\n"
 "	available at http://user-mode-linux.sourceforge.net/\n\n";
 
@@ -202,7 +202,7 @@ static void __init uml_checksetup(char *line, int *add)
 
 	p = &__uml_setup_start;
 	while (p < &__uml_setup_end) {
-		int n;
+		size_t n;
 
 		n = strlen(p->str);
 		if (!strncmp(line, p->str, n) && p->setup_func(line + n, add))
@@ -258,7 +258,8 @@ int __init linux_main(int argc, char **argv)
 {
 	unsigned long avail, diff;
 	unsigned long virtmem_size, max_physmem;
-	unsigned int i, add;
+	unsigned int i;
+	int add;
 	char * mode;
 
 	for (i = 1; i < argc; i++) {
diff --git a/trunk/arch/um/os-Linux/start_up.c b/trunk/arch/um/os-Linux/start_up.c
index b616e15638fb..997d01944f91 100644
--- a/trunk/arch/um/os-Linux/start_up.c
+++ b/trunk/arch/um/os-Linux/start_up.c
@@ -25,15 +25,15 @@
 #include "registers.h"
 #include "skas_ptrace.h"
 
-static int ptrace_child(void)
+static void ptrace_child(void)
 {
 	int ret;
 	/* Calling os_getpid because some libcs cached getpid incorrectly */
 	int pid = os_getpid(), ppid = getppid();
 	int sc_result;
 
-	change_sig(SIGWINCH, 0);
-	if (ptrace(PTRACE_TRACEME, 0, 0, 0) < 0) {
+	if (change_sig(SIGWINCH, 0) < 0 ||
+	    ptrace(PTRACE_TRACEME, 0, 0, 0) < 0) {
 		perror("ptrace");
 		kill(pid, SIGKILL);
 	}
@@ -75,9 +75,8 @@ static void fatal(char *fmt, ...)
 	va_list list;
 
 	va_start(list, fmt);
-	vprintf(fmt, list);
+	vfprintf(stderr, fmt, list);
 	va_end(list);
-	fflush(stdout);
 
 	exit(1);
 }
@@ -87,9 +86,8 @@ static void non_fatal(char *fmt, ...)
 	va_list list;
 
 	va_start(list, fmt);
-	vprintf(fmt, list);
+	vfprintf(stderr, fmt, list);
 	va_end(list);
-	fflush(stdout);
 }
 
 static int start_ptraced_child(void)
@@ -495,7 +493,7 @@ int __init parse_iomem(char *str, int *add)
 	driver = str;
 	file = strchr(str,',');
 	if (file == NULL) {
-		printf("parse_iomem : failed to parse iomem\n");
+		fprintf(stderr, "parse_iomem : failed to parse iomem\n");
 		goto out;
 	}
 	*file = '\0';
diff --git a/trunk/arch/um/os-Linux/sys-i386/task_size.c b/trunk/arch/um/os-Linux/sys-i386/task_size.c
index 48d211b3d9a1..ccb49b0aff59 100644
--- a/trunk/arch/um/os-Linux/sys-i386/task_size.c
+++ b/trunk/arch/um/os-Linux/sys-i386/task_size.c
@@ -88,7 +88,10 @@ unsigned long os_get_task_size(void)
 	sa.sa_handler = segfault;
 	sigemptyset(&sa.sa_mask);
 	sa.sa_flags = SA_NODEFER;
-	sigaction(SIGSEGV, &sa, &old);
+	if (sigaction(SIGSEGV, &sa, &old)) {
+		perror("os_get_task_size");
+		exit(1);
+	}
 
 	if (!page_ok(bottom)) {
 		fprintf(stderr, "Address 0x%x no good?\n",
@@ -110,11 +113,12 @@ unsigned long os_get_task_size(void)
 
 out:
 	/* Restore the old SIGSEGV handling */
-	sigaction(SIGSEGV, &old, NULL);
-
+	if (sigaction(SIGSEGV, &old, NULL)) {
+		perror("os_get_task_size");
+		exit(1);
+	}
 	top <<= UM_KERN_PAGE_SHIFT;
 	printf("0x%x\n", top);
-	fflush(stdout);
 
 	return top;
 }
diff --git a/trunk/arch/v850/kernel/asm-offsets.c b/trunk/arch/v850/kernel/asm-offsets.c
index cee5c3142d41..581e6986a776 100644
--- a/trunk/arch/v850/kernel/asm-offsets.c
+++ b/trunk/arch/v850/kernel/asm-offsets.c
@@ -13,14 +13,11 @@
 #include <linux/kernel_stat.h>
 #include <linux/ptrace.h>
 #include <linux/hardirq.h>
+#include <linux/kbuild.h>
+
 #include <asm/irq.h>
 #include <asm/errno.h>
 
-#define DEFINE(sym, val) \
-	asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
-
 int main (void)
 {
 	/* offsets into the task struct */
diff --git a/trunk/arch/v850/kernel/rte_mb_a_pci.c b/trunk/arch/v850/kernel/rte_mb_a_pci.c
index 7165478824e7..687e367d8b64 100644
--- a/trunk/arch/v850/kernel/rte_mb_a_pci.c
+++ b/trunk/arch/v850/kernel/rte_mb_a_pci.c
@@ -790,8 +790,8 @@ pci_free_consistent (struct pci_dev *pdev, size_t size, void *cpu_addr,
 
 void __iomem *pci_iomap (struct pci_dev *dev, int bar, unsigned long max)
 {
-	unsigned long start = pci_resource_start (dev, bar);
-	unsigned long len = pci_resource_len (dev, bar);
+	resource_size_t start = pci_resource_start (dev, bar);
+	resource_size_t len = pci_resource_len (dev, bar);
 
 	if (!start || len == 0)
 		return 0;
diff --git a/trunk/arch/x86/Kconfig b/trunk/arch/x86/Kconfig
index 2fadf794483d..f70e3e3a9fa7 100644
--- a/trunk/arch/x86/Kconfig
+++ b/trunk/arch/x86/Kconfig
@@ -86,9 +86,6 @@ config GENERIC_GPIO
 config ARCH_MAY_HAVE_PC_FDC
 	def_bool y
 
-config DMI
-	def_bool y
-
 config RWSEM_GENERIC_SPINLOCK
 	def_bool !X86_XADD
 
@@ -114,6 +111,9 @@ config GENERIC_TIME_VSYSCALL
 config ARCH_HAS_CPU_RELAX
 	def_bool y
 
+config ARCH_HAS_CACHE_LINE_SIZE
+	def_bool y
+
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool X86_64 || (X86_SMP && !X86_VOYAGER)
 
@@ -373,6 +373,25 @@ config VMI
 	  at the moment), by linking the kernel to a GPL-ed ROM module
 	  provided by the hypervisor.
 
+config KVM_CLOCK
+	bool "KVM paravirtualized clock"
+	select PARAVIRT
+	depends on !(X86_VISWS || X86_VOYAGER)
+	help
+	  Turning on this option will allow you to run a paravirtualized clock
+	  when running over the KVM hypervisor. Instead of relying on a PIT
+	  (or probably other) emulation by the underlying device model, the host
+	  provides the guest with timing infrastructure such as time of day, and
+	  system time
+
+config KVM_GUEST
+	bool "KVM Guest support"
+	select PARAVIRT
+	depends on !(X86_VISWS || X86_VOYAGER)
+	help
+	 This option enables various optimizations for running under the KVM
+	 hypervisor.
+
 source "arch/x86/lguest/Kconfig"
 
 config PARAVIRT
@@ -463,6 +482,15 @@ config HPET_EMULATE_RTC
 
 # Mark as embedded because too many people got it wrong.
 # The code disables itself when not needed.
+config DMI
+	default y
+	bool "Enable DMI scanning" if EMBEDDED
+	help
+	  Enabled scanning of DMI to identify machine quirks. Say Y
+	  here unless you have verified that your setup is not
+	  affected by entries in the DMI blacklist. Required by PNP
+	  BIOS code.
+
 config GART_IOMMU
 	bool "GART IOMMU support" if EMBEDDED
 	default y
@@ -509,9 +537,6 @@ config CALGARY_IOMMU_ENABLED_BY_DEFAULT
 	  Calgary anyway, pass 'iommu=calgary' on the kernel command line.
 	  If unsure, say Y.
 
-config IOMMU_HELPER
-	def_bool (CALGARY_IOMMU || GART_IOMMU)
-
 # need this always selected by IOMMU for the VIA workaround
 config SWIOTLB
 	bool
@@ -522,6 +547,8 @@ config SWIOTLB
 	  access 32-bits of memory can be used on systems with more than
 	  3 GB of memory. If unsure, say Y.
 
+config IOMMU_HELPER
+	def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB)
 
 config NR_CPUS
 	int "Maximum number of CPUs (2-255)"
@@ -1477,6 +1504,10 @@ config PCI_GODIRECT
 config PCI_GOANY
 	bool "Any"
 
+config PCI_GOOLPC
+	bool "OLPC"
+	depends on OLPC
+
 endchoice
 
 config PCI_BIOS
@@ -1486,12 +1517,17 @@ config PCI_BIOS
 # x86-64 doesn't support PCI BIOS access from long mode so always go direct.
 config PCI_DIRECT
 	def_bool y
-	depends on PCI && (X86_64 || (PCI_GODIRECT || PCI_GOANY) || X86_VISWS)
+	depends on PCI && (X86_64 || (PCI_GODIRECT || PCI_GOANY || PCI_GOOLPC) || X86_VISWS)
 
 config PCI_MMCONFIG
 	def_bool y
 	depends on X86_32 && PCI && ACPI && (PCI_GOMMCONFIG || PCI_GOANY)
 
+config PCI_OLPC
+	bool
+	depends on PCI && PCI_GOOLPC
+	default y
+
 config PCI_DOMAINS
 	def_bool y
 	depends on PCI
@@ -1611,6 +1647,13 @@ config GEODE_MFGPT_TIMER
 	  MFGPTs have a better resolution and max interval than the
 	  generic PIT, and are suitable for use as high-res timers.
 
+config OLPC
+	bool "One Laptop Per Child support"
+	default n
+	help
+	  Add support for detecting the unique features of the OLPC
+	  XO hardware.
+
 endif # X86_32
 
 config K8_NB
diff --git a/trunk/arch/x86/boot/edd.c b/trunk/arch/x86/boot/edd.c
index d84a48ece785..03399d64013b 100644
--- a/trunk/arch/x86/boot/edd.c
+++ b/trunk/arch/x86/boot/edd.c
@@ -126,17 +126,25 @@ void query_edd(void)
 {
 	char eddarg[8];
 	int do_mbr = 1;
+#ifdef CONFIG_EDD_OFF
+	int do_edd = 0;
+#else
 	int do_edd = 1;
+#endif
 	int be_quiet;
 	int devno;
 	struct edd_info ei, *edp;
 	u32 *mbrptr;
 
 	if (cmdline_find_option("edd", eddarg, sizeof eddarg) > 0) {
-		if (!strcmp(eddarg, "skipmbr") || !strcmp(eddarg, "skip"))
+		if (!strcmp(eddarg, "skipmbr") || !strcmp(eddarg, "skip")) {
+			do_edd = 1;
 			do_mbr = 0;
+		}
 		else if (!strcmp(eddarg, "off"))
 			do_edd = 0;
+		else if (!strcmp(eddarg, "on"))
+			do_edd = 1;
 	}
 
 	be_quiet = cmdline_find_option_bool("quiet");
diff --git a/trunk/arch/x86/kernel/Makefile b/trunk/arch/x86/kernel/Makefile
index 815b650977b4..30d54ed27e55 100644
--- a/trunk/arch/x86/kernel/Makefile
+++ b/trunk/arch/x86/kernel/Makefile
@@ -80,6 +80,8 @@ obj-$(CONFIG_DEBUG_RODATA_TEST)	+= test_rodata.o
 obj-$(CONFIG_DEBUG_NX_TEST)	+= test_nx.o
 
 obj-$(CONFIG_VMI)		+= vmi_32.o vmiclock_32.o
+obj-$(CONFIG_KVM_GUEST)		+= kvm.o
+obj-$(CONFIG_KVM_CLOCK)		+= kvmclock.o
 obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch_$(BITS).o
 
 ifdef CONFIG_INPUT_PCSPKR
@@ -89,6 +91,8 @@ endif
 obj-$(CONFIG_SCx200)		+= scx200.o
 scx200-y			+= scx200_32.o
 
+obj-$(CONFIG_OLPC)		+= olpc.o
+
 ###
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
diff --git a/trunk/arch/x86/kernel/apm_32.c b/trunk/arch/x86/kernel/apm_32.c
index f0030a0999c7..e4ea362e8480 100644
--- a/trunk/arch/x86/kernel/apm_32.c
+++ b/trunk/arch/x86/kernel/apm_32.c
@@ -904,6 +904,7 @@ static void apm_cpu_idle(void)
 			original_pm_idle();
 		else
 			default_idle();
+		local_irq_disable();
 		jiffies_since_last_check = jiffies - last_jiffies;
 		if (jiffies_since_last_check > idle_period)
 			goto recalc;
@@ -911,6 +912,8 @@ static void apm_cpu_idle(void)
 
 	if (apm_idle_done)
 		apm_do_busy();
+
+	local_irq_enable();
 }
 
 /**
diff --git a/trunk/arch/x86/kernel/asm-offsets_32.c b/trunk/arch/x86/kernel/asm-offsets_32.c
index 670c3c311289..92588083950f 100644
--- a/trunk/arch/x86/kernel/asm-offsets_32.c
+++ b/trunk/arch/x86/kernel/asm-offsets_32.c
@@ -9,6 +9,7 @@
 #include <linux/signal.h>
 #include <linux/personality.h>
 #include <linux/suspend.h>
+#include <linux/kbuild.h>
 #include <asm/ucontext.h>
 #include "sigframe.h"
 #include <asm/pgtable.h>
@@ -23,14 +24,6 @@
 #include <linux/lguest.h>
 #include "../../../drivers/lguest/lg.h"
 
-#define DEFINE(sym, val) \
-        asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
-
-#define OFFSET(sym, str, mem) \
-	DEFINE(sym, offsetof(struct str, mem));
-
 /* workaround for a warning with -Wmissing-prototypes */
 void foo(void);
 
diff --git a/trunk/arch/x86/kernel/asm-offsets_64.c b/trunk/arch/x86/kernel/asm-offsets_64.c
index 494e1e096ee6..f126c05d6170 100644
--- a/trunk/arch/x86/kernel/asm-offsets_64.c
+++ b/trunk/arch/x86/kernel/asm-offsets_64.c
@@ -10,6 +10,7 @@
 #include <linux/errno.h> 
 #include <linux/hardirq.h>
 #include <linux/suspend.h>
+#include <linux/kbuild.h>
 #include <asm/pda.h>
 #include <asm/processor.h>
 #include <asm/segment.h>
@@ -17,14 +18,6 @@
 #include <asm/ia32.h>
 #include <asm/bootparam.h>
 
-#define DEFINE(sym, val) \
-        asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
-
-#define OFFSET(sym, str, mem) \
-	DEFINE(sym, offsetof(struct str, mem))
-
 #define __NO_STUBS 1
 #undef __SYSCALL
 #undef _ASM_X86_64_UNISTD_H_
diff --git a/trunk/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/trunk/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index e2d870de837c..b0c8208df9fa 100644
--- a/trunk/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/trunk/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -339,6 +339,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 {
 	struct acpi_cpufreq_data *data = per_cpu(drv_data, cpu);
 	unsigned int freq;
+	unsigned int cached_freq;
 
 	dprintk("get_cur_freq_on_cpu (%d)\n", cpu);
 
@@ -347,7 +348,16 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 		return 0;
 	}
 
+	cached_freq = data->freq_table[data->acpi_data->state].frequency;
 	freq = extract_freq(get_cur_val(&cpumask_of_cpu(cpu)), data);
+	if (freq != cached_freq) {
+		/*
+		 * The dreaded BIOS frequency change behind our back.
+		 * Force set the frequency on next target call.
+		 */
+		data->resume = 1;
+	}
+
 	dprintk("cur freq = %u\n", freq);
 
 	return freq;
@@ -591,6 +601,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	    policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
 		policy->cpus = perf->shared_cpu_map;
 	}
+	policy->related_cpus = perf->shared_cpu_map;
 
 #ifdef CONFIG_SMP
 	dmi_check_system(sw_any_bug_dmi_table);
diff --git a/trunk/arch/x86/kernel/cpu/mtrr/if.c b/trunk/arch/x86/kernel/cpu/mtrr/if.c
index 1960f1985e5e..84c480bb3715 100644
--- a/trunk/arch/x86/kernel/cpu/mtrr/if.c
+++ b/trunk/arch/x86/kernel/cpu/mtrr/if.c
@@ -424,7 +424,7 @@ static int __init mtrr_if_init(void)
 		return -ENODEV;
 
 	proc_root_mtrr =
-		proc_create("mtrr", S_IWUSR | S_IRUGO, &proc_root, &mtrr_fops);
+		proc_create("mtrr", S_IWUSR | S_IRUGO, NULL, &mtrr_fops);
 
 	if (proc_root_mtrr)
 		proc_root_mtrr->owner = THIS_MODULE;
diff --git a/trunk/arch/x86/kernel/crash.c b/trunk/arch/x86/kernel/crash.c
index 2251d0ae9570..268553817909 100644
--- a/trunk/arch/x86/kernel/crash.c
+++ b/trunk/arch/x86/kernel/crash.c
@@ -25,6 +25,7 @@
 #include <asm/hpet.h>
 #include <linux/kdebug.h>
 #include <asm/smp.h>
+#include <asm/reboot.h>
 
 #include <mach_ipi.h>
 
@@ -117,7 +118,7 @@ static void nmi_shootdown_cpus(void)
 }
 #endif
 
-void machine_crash_shutdown(struct pt_regs *regs)
+void native_machine_crash_shutdown(struct pt_regs *regs)
 {
 	/* This function is only called after the system
 	 * has panicked or is otherwise in a critical state.
diff --git a/trunk/arch/x86/kernel/io_apic_32.c b/trunk/arch/x86/kernel/io_apic_32.c
index 696b8e4e66bb..a40d54fc1fdd 100644
--- a/trunk/arch/x86/kernel/io_apic_32.c
+++ b/trunk/arch/x86/kernel/io_apic_32.c
@@ -2444,6 +2444,7 @@ void destroy_irq(unsigned int irq)
 	dynamic_irq_cleanup(irq);
 
 	spin_lock_irqsave(&vector_lock, flags);
+	clear_bit(irq_vector[irq], used_vectors);
 	irq_vector[irq] = 0;
 	spin_unlock_irqrestore(&vector_lock, flags);
 }
diff --git a/trunk/arch/x86/kernel/irq_32.c b/trunk/arch/x86/kernel/irq_32.c
index 00bda7bcda63..147352df28b9 100644
--- a/trunk/arch/x86/kernel/irq_32.c
+++ b/trunk/arch/x86/kernel/irq_32.c
@@ -190,8 +190,6 @@ void irq_ctx_exit(int cpu)
 	hardirq_ctx[cpu] = NULL;
 }
 
-extern asmlinkage void __do_softirq(void);
-
 asmlinkage void do_softirq(void)
 {
 	unsigned long flags;
diff --git a/trunk/arch/x86/kernel/kvm.c b/trunk/arch/x86/kernel/kvm.c
new file mode 100644
index 000000000000..8b7a3cf37d2b
--- /dev/null
+++ b/trunk/arch/x86/kernel/kvm.c
@@ -0,0 +1,248 @@
+/*
+ * KVM paravirt_ops implementation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) 2007, Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ * Copyright IBM Corporation, 2007
+ *   Authors: Anthony Liguori <aliguori@us.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/kvm_para.h>
+#include <linux/cpu.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/hardirq.h>
+
+#define MMU_QUEUE_SIZE 1024
+
+struct kvm_para_state {
+	u8 mmu_queue[MMU_QUEUE_SIZE];
+	int mmu_queue_len;
+	enum paravirt_lazy_mode mode;
+};
+
+static DEFINE_PER_CPU(struct kvm_para_state, para_state);
+
+static struct kvm_para_state *kvm_para_state(void)
+{
+	return &per_cpu(para_state, raw_smp_processor_id());
+}
+
+/*
+ * No need for any "IO delay" on KVM
+ */
+static void kvm_io_delay(void)
+{
+}
+
+static void kvm_mmu_op(void *buffer, unsigned len)
+{
+	int r;
+	unsigned long a1, a2;
+
+	do {
+		a1 = __pa(buffer);
+		a2 = 0;   /* on i386 __pa() always returns <4G */
+		r = kvm_hypercall3(KVM_HC_MMU_OP, len, a1, a2);
+		buffer += r;
+		len -= r;
+	} while (len);
+}
+
+static void mmu_queue_flush(struct kvm_para_state *state)
+{
+	if (state->mmu_queue_len) {
+		kvm_mmu_op(state->mmu_queue, state->mmu_queue_len);
+		state->mmu_queue_len = 0;
+	}
+}
+
+static void kvm_deferred_mmu_op(void *buffer, int len)
+{
+	struct kvm_para_state *state = kvm_para_state();
+
+	if (state->mode != PARAVIRT_LAZY_MMU) {
+		kvm_mmu_op(buffer, len);
+		return;
+	}
+	if (state->mmu_queue_len + len > sizeof state->mmu_queue)
+		mmu_queue_flush(state);
+	memcpy(state->mmu_queue + state->mmu_queue_len, buffer, len);
+	state->mmu_queue_len += len;
+}
+
+static void kvm_mmu_write(void *dest, u64 val)
+{
+	__u64 pte_phys;
+	struct kvm_mmu_op_write_pte wpte;
+
+#ifdef CONFIG_HIGHPTE
+	struct page *page;
+	unsigned long dst = (unsigned long) dest;
+
+	page = kmap_atomic_to_page(dest);
+	pte_phys = page_to_pfn(page);
+	pte_phys <<= PAGE_SHIFT;
+	pte_phys += (dst & ~(PAGE_MASK));
+#else
+	pte_phys = (unsigned long)__pa(dest);
+#endif
+	wpte.header.op = KVM_MMU_OP_WRITE_PTE;
+	wpte.pte_val = val;
+	wpte.pte_phys = pte_phys;
+
+	kvm_deferred_mmu_op(&wpte, sizeof wpte);
+}
+
+/*
+ * We only need to hook operations that are MMU writes.  We hook these so that
+ * we can use lazy MMU mode to batch these operations.  We could probably
+ * improve the performance of the host code if we used some of the information
+ * here to simplify processing of batched writes.
+ */
+static void kvm_set_pte(pte_t *ptep, pte_t pte)
+{
+	kvm_mmu_write(ptep, pte_val(pte));
+}
+
+static void kvm_set_pte_at(struct mm_struct *mm, unsigned long addr,
+			   pte_t *ptep, pte_t pte)
+{
+	kvm_mmu_write(ptep, pte_val(pte));
+}
+
+static void kvm_set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+	kvm_mmu_write(pmdp, pmd_val(pmd));
+}
+
+#if PAGETABLE_LEVELS >= 3
+#ifdef CONFIG_X86_PAE
+static void kvm_set_pte_atomic(pte_t *ptep, pte_t pte)
+{
+	kvm_mmu_write(ptep, pte_val(pte));
+}
+
+static void kvm_set_pte_present(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte)
+{
+	kvm_mmu_write(ptep, pte_val(pte));
+}
+
+static void kvm_pte_clear(struct mm_struct *mm,
+			  unsigned long addr, pte_t *ptep)
+{
+	kvm_mmu_write(ptep, 0);
+}
+
+static void kvm_pmd_clear(pmd_t *pmdp)
+{
+	kvm_mmu_write(pmdp, 0);
+}
+#endif
+
+static void kvm_set_pud(pud_t *pudp, pud_t pud)
+{
+	kvm_mmu_write(pudp, pud_val(pud));
+}
+
+#if PAGETABLE_LEVELS == 4
+static void kvm_set_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	kvm_mmu_write(pgdp, pgd_val(pgd));
+}
+#endif
+#endif /* PAGETABLE_LEVELS >= 3 */
+
+static void kvm_flush_tlb(void)
+{
+	struct kvm_mmu_op_flush_tlb ftlb = {
+		.header.op = KVM_MMU_OP_FLUSH_TLB,
+	};
+
+	kvm_deferred_mmu_op(&ftlb, sizeof ftlb);
+}
+
+static void kvm_release_pt(u32 pfn)
+{
+	struct kvm_mmu_op_release_pt rpt = {
+		.header.op = KVM_MMU_OP_RELEASE_PT,
+		.pt_phys = (u64)pfn << PAGE_SHIFT,
+	};
+
+	kvm_mmu_op(&rpt, sizeof rpt);
+}
+
+static void kvm_enter_lazy_mmu(void)
+{
+	struct kvm_para_state *state = kvm_para_state();
+
+	paravirt_enter_lazy_mmu();
+	state->mode = paravirt_get_lazy_mode();
+}
+
+static void kvm_leave_lazy_mmu(void)
+{
+	struct kvm_para_state *state = kvm_para_state();
+
+	mmu_queue_flush(state);
+	paravirt_leave_lazy(paravirt_get_lazy_mode());
+	state->mode = paravirt_get_lazy_mode();
+}
+
+static void paravirt_ops_setup(void)
+{
+	pv_info.name = "KVM";
+	pv_info.paravirt_enabled = 1;
+
+	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
+		pv_cpu_ops.io_delay = kvm_io_delay;
+
+	if (kvm_para_has_feature(KVM_FEATURE_MMU_OP)) {
+		pv_mmu_ops.set_pte = kvm_set_pte;
+		pv_mmu_ops.set_pte_at = kvm_set_pte_at;
+		pv_mmu_ops.set_pmd = kvm_set_pmd;
+#if PAGETABLE_LEVELS >= 3
+#ifdef CONFIG_X86_PAE
+		pv_mmu_ops.set_pte_atomic = kvm_set_pte_atomic;
+		pv_mmu_ops.set_pte_present = kvm_set_pte_present;
+		pv_mmu_ops.pte_clear = kvm_pte_clear;
+		pv_mmu_ops.pmd_clear = kvm_pmd_clear;
+#endif
+		pv_mmu_ops.set_pud = kvm_set_pud;
+#if PAGETABLE_LEVELS == 4
+		pv_mmu_ops.set_pgd = kvm_set_pgd;
+#endif
+#endif
+		pv_mmu_ops.flush_tlb_user = kvm_flush_tlb;
+		pv_mmu_ops.release_pte = kvm_release_pt;
+		pv_mmu_ops.release_pmd = kvm_release_pt;
+		pv_mmu_ops.release_pud = kvm_release_pt;
+
+		pv_mmu_ops.lazy_mode.enter = kvm_enter_lazy_mmu;
+		pv_mmu_ops.lazy_mode.leave = kvm_leave_lazy_mmu;
+	}
+}
+
+void __init kvm_guest_init(void)
+{
+	if (!kvm_para_available())
+		return;
+
+	paravirt_ops_setup();
+}
diff --git a/trunk/arch/x86/kernel/kvmclock.c b/trunk/arch/x86/kernel/kvmclock.c
new file mode 100644
index 000000000000..ddee04043aeb
--- /dev/null
+++ b/trunk/arch/x86/kernel/kvmclock.c
@@ -0,0 +1,187 @@
+/*  KVM paravirtual clock driver. A clocksource implementation
+    Copyright (C) 2008 Glauber de Oliveira Costa, Red Hat Inc.
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+*/
+
+#include <linux/clocksource.h>
+#include <linux/kvm_para.h>
+#include <asm/arch_hooks.h>
+#include <asm/msr.h>
+#include <asm/apic.h>
+#include <linux/percpu.h>
+#include <asm/reboot.h>
+
+#define KVM_SCALE 22
+
+static int kvmclock = 1;
+
+static int parse_no_kvmclock(char *arg)
+{
+	kvmclock = 0;
+	return 0;
+}
+early_param("no-kvmclock", parse_no_kvmclock);
+
+/* The hypervisor will put information about time periodically here */
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct kvm_vcpu_time_info, hv_clock);
+#define get_clock(cpu, field) per_cpu(hv_clock, cpu).field
+
+static inline u64 kvm_get_delta(u64 last_tsc)
+{
+	int cpu = smp_processor_id();
+	u64 delta = native_read_tsc() - last_tsc;
+	return (delta * get_clock(cpu, tsc_to_system_mul)) >> KVM_SCALE;
+}
+
+static struct kvm_wall_clock wall_clock;
+static cycle_t kvm_clock_read(void);
+/*
+ * The wallclock is the time of day when we booted. Since then, some time may
+ * have elapsed since the hypervisor wrote the data. So we try to account for
+ * that with system time
+ */
+unsigned long kvm_get_wallclock(void)
+{
+	u32 wc_sec, wc_nsec;
+	u64 delta;
+	struct timespec ts;
+	int version, nsec;
+	int low, high;
+
+	low = (int)__pa(&wall_clock);
+	high = ((u64)__pa(&wall_clock) >> 32);
+
+	delta = kvm_clock_read();
+
+	native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
+	do {
+		version = wall_clock.wc_version;
+		rmb();
+		wc_sec = wall_clock.wc_sec;
+		wc_nsec = wall_clock.wc_nsec;
+		rmb();
+	} while ((wall_clock.wc_version != version) || (version & 1));
+
+	delta = kvm_clock_read() - delta;
+	delta += wc_nsec;
+	nsec = do_div(delta, NSEC_PER_SEC);
+	set_normalized_timespec(&ts, wc_sec + delta, nsec);
+	/*
+	 * Of all mechanisms of time adjustment I've tested, this one
+	 * was the champion!
+	 */
+	return ts.tv_sec + 1;
+}
+
+int kvm_set_wallclock(unsigned long now)
+{
+	return 0;
+}
+
+/*
+ * This is our read_clock function. The host puts an tsc timestamp each time
+ * it updates a new time. Without the tsc adjustment, we can have a situation
+ * in which a vcpu starts to run earlier (smaller system_time), but probes
+ * time later (compared to another vcpu), leading to backwards time
+ */
+static cycle_t kvm_clock_read(void)
+{
+	u64 last_tsc, now;
+	int cpu;
+
+	preempt_disable();
+	cpu = smp_processor_id();
+
+	last_tsc = get_clock(cpu, tsc_timestamp);
+	now = get_clock(cpu, system_time);
+
+	now += kvm_get_delta(last_tsc);
+	preempt_enable();
+
+	return now;
+}
+static struct clocksource kvm_clock = {
+	.name = "kvm-clock",
+	.read = kvm_clock_read,
+	.rating = 400,
+	.mask = CLOCKSOURCE_MASK(64),
+	.mult = 1 << KVM_SCALE,
+	.shift = KVM_SCALE,
+	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static int kvm_register_clock(void)
+{
+	int cpu = smp_processor_id();
+	int low, high;
+	low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1;
+	high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32);
+
+	return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high);
+}
+
+static void kvm_setup_secondary_clock(void)
+{
+	/*
+	 * Now that the first cpu already had this clocksource initialized,
+	 * we shouldn't fail.
+	 */
+	WARN_ON(kvm_register_clock());
+	/* ok, done with our trickery, call native */
+	setup_secondary_APIC_clock();
+}
+
+/*
+ * After the clock is registered, the host will keep writing to the
+ * registered memory location. If the guest happens to shutdown, this memory
+ * won't be valid. In cases like kexec, in which you install a new kernel, this
+ * means a random memory location will be kept being written. So before any
+ * kind of shutdown from our side, we unregister the clock by writting anything
+ * that does not have the 'enable' bit set in the msr
+ */
+#ifdef CONFIG_KEXEC
+static void kvm_crash_shutdown(struct pt_regs *regs)
+{
+	native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+	native_machine_crash_shutdown(regs);
+}
+#endif
+
+static void kvm_shutdown(void)
+{
+	native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+	native_machine_shutdown();
+}
+
+void __init kvmclock_init(void)
+{
+	if (!kvm_para_available())
+		return;
+
+	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
+		if (kvm_register_clock())
+			return;
+		pv_time_ops.get_wallclock = kvm_get_wallclock;
+		pv_time_ops.set_wallclock = kvm_set_wallclock;
+		pv_time_ops.sched_clock = kvm_clock_read;
+		pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock;
+		machine_ops.shutdown  = kvm_shutdown;
+#ifdef CONFIG_KEXEC
+		machine_ops.crash_shutdown  = kvm_crash_shutdown;
+#endif
+		clocksource_register(&kvm_clock);
+	}
+}
diff --git a/trunk/arch/x86/kernel/mfgpt_32.c b/trunk/arch/x86/kernel/mfgpt_32.c
index cfc2648d25ff..3cad17fe026b 100644
--- a/trunk/arch/x86/kernel/mfgpt_32.c
+++ b/trunk/arch/x86/kernel/mfgpt_32.c
@@ -63,7 +63,7 @@ static int __init mfgpt_fix(char *s)
 
 	/* The following udocumented bit resets the MFGPT timers */
 	val = 0xFF; dummy = 0;
-	wrmsr(0x5140002B, val, dummy);
+	wrmsr(MSR_MFGPT_SETUP, val, dummy);
 	return 1;
 }
 __setup("mfgptfix", mfgpt_fix);
@@ -127,17 +127,17 @@ int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable)
 		 * 6; that is, resets for 7 and 8 will be ignored.  Is this
 		 * a problem?   -dilinger
 		 */
-		msr = MFGPT_NR_MSR;
+		msr = MSR_MFGPT_NR;
 		mask = 1 << (timer + 24);
 		break;
 
 	case MFGPT_EVENT_NMI:
-		msr = MFGPT_NR_MSR;
+		msr = MSR_MFGPT_NR;
 		mask = 1 << (timer + shift);
 		break;
 
 	case MFGPT_EVENT_IRQ:
-		msr = MFGPT_IRQ_MSR;
+		msr = MSR_MFGPT_IRQ;
 		mask = 1 << (timer + shift);
 		break;
 
diff --git a/trunk/arch/x86/kernel/olpc.c b/trunk/arch/x86/kernel/olpc.c
new file mode 100644
index 000000000000..3e6672274807
--- /dev/null
+++ b/trunk/arch/x86/kernel/olpc.c
@@ -0,0 +1,260 @@
+/*
+ * Support for the OLPC DCON and OLPC EC access
+ *
+ * Copyright © 2006  Advanced Micro Devices, Inc.
+ * Copyright © 2007-2008  Andres Salomon <dilinger@debian.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/io.h>
+#include <linux/string.h>
+#include <asm/geode.h>
+#include <asm/olpc.h>
+
+#ifdef CONFIG_OPEN_FIRMWARE
+#include <asm/ofw.h>
+#endif
+
+struct olpc_platform_t olpc_platform_info;
+EXPORT_SYMBOL_GPL(olpc_platform_info);
+
+static DEFINE_SPINLOCK(ec_lock);
+
+/* what the timeout *should* be (in ms) */
+#define EC_BASE_TIMEOUT 20
+
+/* the timeout that bugs in the EC might force us to actually use */
+static int ec_timeout = EC_BASE_TIMEOUT;
+
+static int __init olpc_ec_timeout_set(char *str)
+{
+	if (get_option(&str, &ec_timeout) != 1) {
+		ec_timeout = EC_BASE_TIMEOUT;
+		printk(KERN_ERR "olpc-ec:  invalid argument to "
+				"'olpc_ec_timeout=', ignoring!\n");
+	}
+	printk(KERN_DEBUG "olpc-ec:  using %d ms delay for EC commands.\n",
+			ec_timeout);
+	return 1;
+}
+__setup("olpc_ec_timeout=", olpc_ec_timeout_set);
+
+/*
+ * These {i,o}bf_status functions return whether the buffers are full or not.
+ */
+
+static inline unsigned int ibf_status(unsigned int port)
+{
+	return !!(inb(port) & 0x02);
+}
+
+static inline unsigned int obf_status(unsigned int port)
+{
+	return inb(port) & 0x01;
+}
+
+#define wait_on_ibf(p, d) __wait_on_ibf(__LINE__, (p), (d))
+static int __wait_on_ibf(unsigned int line, unsigned int port, int desired)
+{
+	unsigned int timeo;
+	int state = ibf_status(port);
+
+	for (timeo = ec_timeout; state != desired && timeo; timeo--) {
+		mdelay(1);
+		state = ibf_status(port);
+	}
+
+	if ((state == desired) && (ec_timeout > EC_BASE_TIMEOUT) &&
+			timeo < (ec_timeout - EC_BASE_TIMEOUT)) {
+		printk(KERN_WARNING "olpc-ec:  %d: waited %u ms for IBF!\n",
+				line, ec_timeout - timeo);
+	}
+
+	return !(state == desired);
+}
+
+#define wait_on_obf(p, d) __wait_on_obf(__LINE__, (p), (d))
+static int __wait_on_obf(unsigned int line, unsigned int port, int desired)
+{
+	unsigned int timeo;
+	int state = obf_status(port);
+
+	for (timeo = ec_timeout; state != desired && timeo; timeo--) {
+		mdelay(1);
+		state = obf_status(port);
+	}
+
+	if ((state == desired) && (ec_timeout > EC_BASE_TIMEOUT) &&
+			timeo < (ec_timeout - EC_BASE_TIMEOUT)) {
+		printk(KERN_WARNING "olpc-ec:  %d: waited %u ms for OBF!\n",
+				line, ec_timeout - timeo);
+	}
+
+	return !(state == desired);
+}
+
+/*
+ * This allows the kernel to run Embedded Controller commands.  The EC is
+ * documented at <http://wiki.laptop.org/go/Embedded_controller>, and the
+ * available EC commands are here:
+ * <http://wiki.laptop.org/go/Ec_specification>.  Unfortunately, while
+ * OpenFirmware's source is available, the EC's is not.
+ */
+int olpc_ec_cmd(unsigned char cmd, unsigned char *inbuf, size_t inlen,
+		unsigned char *outbuf,  size_t outlen)
+{
+	unsigned long flags;
+	int ret = -EIO;
+	int i;
+
+	spin_lock_irqsave(&ec_lock, flags);
+
+	/* Clear OBF */
+	for (i = 0; i < 10 && (obf_status(0x6c) == 1); i++)
+		inb(0x68);
+	if (i == 10) {
+		printk(KERN_ERR "olpc-ec:  timeout while attempting to "
+				"clear OBF flag!\n");
+		goto err;
+	}
+
+	if (wait_on_ibf(0x6c, 0)) {
+		printk(KERN_ERR "olpc-ec:  timeout waiting for EC to "
+				"quiesce!\n");
+		goto err;
+	}
+
+restart:
+	/*
+	 * Note that if we time out during any IBF checks, that's a failure;
+	 * we have to return.  There's no way for the kernel to clear that.
+	 *
+	 * If we time out during an OBF check, we can restart the command;
+	 * reissuing it will clear the OBF flag, and we should be alright.
+	 * The OBF flag will sometimes misbehave due to what we believe
+	 * is a hardware quirk..
+	 */
+	printk(KERN_DEBUG "olpc-ec:  running cmd 0x%x\n", cmd);
+	outb(cmd, 0x6c);
+
+	if (wait_on_ibf(0x6c, 0)) {
+		printk(KERN_ERR "olpc-ec:  timeout waiting for EC to read "
+				"command!\n");
+		goto err;
+	}
+
+	if (inbuf && inlen) {
+		/* write data to EC */
+		for (i = 0; i < inlen; i++) {
+			if (wait_on_ibf(0x6c, 0)) {
+				printk(KERN_ERR "olpc-ec:  timeout waiting for"
+						" EC accept data!\n");
+				goto err;
+			}
+			printk(KERN_DEBUG "olpc-ec:  sending cmd arg 0x%x\n",
+					inbuf[i]);
+			outb(inbuf[i], 0x68);
+		}
+	}
+	if (outbuf && outlen) {
+		/* read data from EC */
+		for (i = 0; i < outlen; i++) {
+			if (wait_on_obf(0x6c, 1)) {
+				printk(KERN_ERR "olpc-ec:  timeout waiting for"
+						" EC to provide data!\n");
+				goto restart;
+			}
+			outbuf[i] = inb(0x68);
+			printk(KERN_DEBUG "olpc-ec:  received 0x%x\n",
+					outbuf[i]);
+		}
+	}
+
+	ret = 0;
+err:
+	spin_unlock_irqrestore(&ec_lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(olpc_ec_cmd);
+
+#ifdef CONFIG_OPEN_FIRMWARE
+static void __init platform_detect(void)
+{
+	size_t propsize;
+	u32 rev;
+
+	if (ofw("getprop", 4, 1, NULL, "board-revision-int", &rev, 4,
+			&propsize) || propsize != 4) {
+		printk(KERN_ERR "ofw: getprop call failed!\n");
+		rev = 0;
+	}
+	olpc_platform_info.boardrev = be32_to_cpu(rev);
+}
+#else
+static void __init platform_detect(void)
+{
+	/* stopgap until OFW support is added to the kernel */
+	olpc_platform_info.boardrev = be32_to_cpu(0xc2);
+}
+#endif
+
+static int __init olpc_init(void)
+{
+	unsigned char *romsig;
+
+	/* The ioremap check is dangerous; limit what we run it on */
+	if (!is_geode() || geode_has_vsa2())
+		return 0;
+
+	spin_lock_init(&ec_lock);
+
+	romsig = ioremap(0xffffffc0, 16);
+	if (!romsig)
+		return 0;
+
+	if (strncmp(romsig, "CL1   Q", 7))
+		goto unmap;
+	if (strncmp(romsig+6, romsig+13, 3)) {
+		printk(KERN_INFO "OLPC BIOS signature looks invalid.  "
+				"Assuming not OLPC\n");
+		goto unmap;
+	}
+
+	printk(KERN_INFO "OLPC board with OpenFirmware %.16s\n", romsig);
+	olpc_platform_info.flags |= OLPC_F_PRESENT;
+
+	/* get the platform revision */
+	platform_detect();
+
+	/* assume B1 and above models always have a DCON */
+	if (olpc_board_at_least(olpc_board(0xb1)))
+		olpc_platform_info.flags |= OLPC_F_DCON;
+
+	/* get the EC revision */
+	olpc_ec_cmd(EC_FIRMWARE_REV, NULL, 0,
+			(unsigned char *) &olpc_platform_info.ecver, 1);
+
+	/* check to see if the VSA exists */
+	if (geode_has_vsa2())
+		olpc_platform_info.flags |= OLPC_F_VSA;
+
+	printk(KERN_INFO "OLPC board revision %s%X (EC=%x)\n",
+			((olpc_platform_info.boardrev & 0xf) < 8) ? "pre" : "",
+			olpc_platform_info.boardrev >> 4,
+			olpc_platform_info.ecver);
+
+unmap:
+	iounmap(romsig);
+	return 0;
+}
+
+postcore_initcall(olpc_init);
diff --git a/trunk/arch/x86/kernel/process.c b/trunk/arch/x86/kernel/process.c
index 3004d716539d..67e9b4a1e89d 100644
--- a/trunk/arch/x86/kernel/process.c
+++ b/trunk/arch/x86/kernel/process.c
@@ -4,6 +4,8 @@
 #include <linux/smp.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/pm.h>
 
 struct kmem_cache *task_xstate_cachep;
 
@@ -42,3 +44,118 @@ void arch_task_cache_init(void)
 				  __alignof__(union thread_xstate),
 				  SLAB_PANIC, NULL);
 }
+
+static void do_nothing(void *unused)
+{
+}
+
+/*
+ * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
+ * pm_idle and update to new pm_idle value. Required while changing pm_idle
+ * handler on SMP systems.
+ *
+ * Caller must have changed pm_idle to the new value before the call. Old
+ * pm_idle value will not be used by any CPU after the return of this function.
+ */
+void cpu_idle_wait(void)
+{
+	smp_mb();
+	/* kick all the CPUs so that they exit out of pm_idle */
+	smp_call_function(do_nothing, NULL, 0, 1);
+}
+EXPORT_SYMBOL_GPL(cpu_idle_wait);
+
+/*
+ * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
+ * which can obviate IPI to trigger checking of need_resched.
+ * We execute MONITOR against need_resched and enter optimized wait state
+ * through MWAIT. Whenever someone changes need_resched, we would be woken
+ * up from MWAIT (without an IPI).
+ *
+ * New with Core Duo processors, MWAIT can take some hints based on CPU
+ * capability.
+ */
+void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
+{
+	if (!need_resched()) {
+		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		smp_mb();
+		if (!need_resched())
+			__mwait(ax, cx);
+	}
+}
+
+/* Default MONITOR/MWAIT with no hints, used for default C1 state */
+static void mwait_idle(void)
+{
+	if (!need_resched()) {
+		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		smp_mb();
+		if (!need_resched())
+			__sti_mwait(0, 0);
+		else
+			local_irq_enable();
+	} else
+		local_irq_enable();
+}
+
+
+static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
+{
+	if (force_mwait)
+		return 1;
+	/* Any C1 states supported? */
+	return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0;
+}
+
+/*
+ * On SMP it's slightly faster (but much more power-consuming!)
+ * to poll the ->work.need_resched flag instead of waiting for the
+ * cross-CPU IPI to arrive. Use this option with caution.
+ */
+static void poll_idle(void)
+{
+	local_irq_enable();
+	cpu_relax();
+}
+
+void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
+{
+	static int selected;
+
+	if (selected)
+		return;
+#ifdef CONFIG_X86_SMP
+	if (pm_idle == poll_idle && smp_num_siblings > 1) {
+		printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
+			" performance may degrade.\n");
+	}
+#endif
+	if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
+		/*
+		 * Skip, if setup has overridden idle.
+		 * One CPU supports mwait => All CPUs supports mwait
+		 */
+		if (!pm_idle) {
+			printk(KERN_INFO "using mwait in idle threads.\n");
+			pm_idle = mwait_idle;
+		}
+	}
+	selected = 1;
+}
+
+static int __init idle_setup(char *str)
+{
+	if (!strcmp(str, "poll")) {
+		printk("using polling idle threads.\n");
+		pm_idle = poll_idle;
+	} else if (!strcmp(str, "mwait"))
+		force_mwait = 1;
+	else
+		return -1;
+
+	boot_option_idle_override = 1;
+	return 0;
+}
+early_param("idle", idle_setup);
+
diff --git a/trunk/arch/x86/kernel/process_32.c b/trunk/arch/x86/kernel/process_32.c
index 77de848bd1fb..f8476dfbb60d 100644
--- a/trunk/arch/x86/kernel/process_32.c
+++ b/trunk/arch/x86/kernel/process_32.c
@@ -111,12 +111,10 @@ void default_idle(void)
 		 */
 		smp_mb();
 
-		local_irq_disable();
-		if (!need_resched()) {
+		if (!need_resched())
 			safe_halt();	/* enables interrupts racelessly */
-			local_irq_disable();
-		}
-		local_irq_enable();
+		else
+			local_irq_enable();
 		current_thread_info()->status |= TS_POLLING;
 	} else {
 		local_irq_enable();
@@ -128,17 +126,6 @@ void default_idle(void)
 EXPORT_SYMBOL(default_idle);
 #endif
 
-/*
- * On SMP it's slightly faster (but much more power-consuming!)
- * to poll the ->work.need_resched flag instead of waiting for the
- * cross-CPU IPI to arrive. Use this option with caution.
- */
-static void poll_idle(void)
-{
-	local_irq_enable();
-	cpu_relax();
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 #include <asm/nmi.h>
 /* We don't actually take CPU down, just spin without interrupts. */
@@ -196,6 +183,7 @@ void cpu_idle(void)
 			if (cpu_is_offline(cpu))
 				play_dead();
 
+			local_irq_disable();
 			__get_cpu_var(irq_stat).idle_timestamp = jiffies;
 			idle();
 		}
@@ -206,104 +194,6 @@ void cpu_idle(void)
 	}
 }
 
-static void do_nothing(void *unused)
-{
-}
-
-/*
- * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
- * pm_idle and update to new pm_idle value. Required while changing pm_idle
- * handler on SMP systems.
- *
- * Caller must have changed pm_idle to the new value before the call. Old
- * pm_idle value will not be used by any CPU after the return of this function.
- */
-void cpu_idle_wait(void)
-{
-	smp_mb();
-	/* kick all the CPUs so that they exit out of pm_idle */
-	smp_call_function(do_nothing, NULL, 0, 1);
-}
-EXPORT_SYMBOL_GPL(cpu_idle_wait);
-
-/*
- * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
- * which can obviate IPI to trigger checking of need_resched.
- * We execute MONITOR against need_resched and enter optimized wait state
- * through MWAIT. Whenever someone changes need_resched, we would be woken
- * up from MWAIT (without an IPI).
- *
- * New with Core Duo processors, MWAIT can take some hints based on CPU
- * capability.
- */
-void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
-{
-	if (!need_resched()) {
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		smp_mb();
-		if (!need_resched())
-			__sti_mwait(ax, cx);
-		else
-			local_irq_enable();
-	} else
-		local_irq_enable();
-}
-
-/* Default MONITOR/MWAIT with no hints, used for default C1 state */
-static void mwait_idle(void)
-{
-	local_irq_enable();
-	mwait_idle_with_hints(0, 0);
-}
-
-static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
-{
-	if (force_mwait)
-		return 1;
-	/* Any C1 states supported? */
-	return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0;
-}
-
-void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
-{
-	static int selected;
-
-	if (selected)
-		return;
-#ifdef CONFIG_X86_SMP
-	if (pm_idle == poll_idle && smp_num_siblings > 1) {
-		printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
-			" performance may degrade.\n");
-	}
-#endif
-	if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
-		/*
-		 * Skip, if setup has overridden idle.
-		 * One CPU supports mwait => All CPUs supports mwait
-		 */
-		if (!pm_idle) {
-			printk(KERN_INFO "using mwait in idle threads.\n");
-			pm_idle = mwait_idle;
-		}
-	}
-	selected = 1;
-}
-
-static int __init idle_setup(char *str)
-{
-	if (!strcmp(str, "poll")) {
-		printk("using polling idle threads.\n");
-		pm_idle = poll_idle;
-	} else if (!strcmp(str, "mwait"))
-		force_mwait = 1;
-	else
-		return -1;
-
-	boot_option_idle_override = 1;
-	return 0;
-}
-early_param("idle", idle_setup);
-
 void __show_registers(struct pt_regs *regs, int all)
 {
 	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
diff --git a/trunk/arch/x86/kernel/process_64.c b/trunk/arch/x86/kernel/process_64.c
index 131c2ee7ac56..e2319f39988b 100644
--- a/trunk/arch/x86/kernel/process_64.c
+++ b/trunk/arch/x86/kernel/process_64.c
@@ -106,26 +106,13 @@ void default_idle(void)
 	 * test NEED_RESCHED:
 	 */
 	smp_mb();
-	local_irq_disable();
-	if (!need_resched()) {
+	if (!need_resched())
 		safe_halt();	/* enables interrupts racelessly */
-		local_irq_disable();
-	}
-	local_irq_enable();
+	else
+		local_irq_enable();
 	current_thread_info()->status |= TS_POLLING;
 }
 
-/*
- * On SMP it's slightly faster (but much more power-consuming!)
- * to poll the ->need_resched flag instead of waiting for the
- * cross-CPU IPI to arrive. Use this option with caution.
- */
-static void poll_idle(void)
-{
-	local_irq_enable();
-	cpu_relax();
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 DECLARE_PER_CPU(int, cpu_state);
 
@@ -192,110 +179,6 @@ void cpu_idle(void)
 	}
 }
 
-static void do_nothing(void *unused)
-{
-}
-
-/*
- * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
- * pm_idle and update to new pm_idle value. Required while changing pm_idle
- * handler on SMP systems.
- *
- * Caller must have changed pm_idle to the new value before the call. Old
- * pm_idle value will not be used by any CPU after the return of this function.
- */
-void cpu_idle_wait(void)
-{
-	smp_mb();
-	/* kick all the CPUs so that they exit out of pm_idle */
-	smp_call_function(do_nothing, NULL, 0, 1);
-}
-EXPORT_SYMBOL_GPL(cpu_idle_wait);
-
-/*
- * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
- * which can obviate IPI to trigger checking of need_resched.
- * We execute MONITOR against need_resched and enter optimized wait state
- * through MWAIT. Whenever someone changes need_resched, we would be woken
- * up from MWAIT (without an IPI).
- *
- * New with Core Duo processors, MWAIT can take some hints based on CPU
- * capability.
- */
-void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
-{
-	if (!need_resched()) {
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		smp_mb();
-		if (!need_resched())
-			__mwait(ax, cx);
-	}
-}
-
-/* Default MONITOR/MWAIT with no hints, used for default C1 state */
-static void mwait_idle(void)
-{
-	if (!need_resched()) {
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		smp_mb();
-		if (!need_resched())
-			__sti_mwait(0, 0);
-		else
-			local_irq_enable();
-	} else {
-		local_irq_enable();
-	}
-}
-
-
-static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
-{
-	if (force_mwait)
-		return 1;
-	/* Any C1 states supported? */
-	return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0;
-}
-
-void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
-{
-	static int selected;
-
-	if (selected)
-		return;
-#ifdef CONFIG_X86_SMP
-	if (pm_idle == poll_idle && smp_num_siblings > 1) {
-		printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
-			" performance may degrade.\n");
-	}
-#endif
-	if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
-		/*
-		 * Skip, if setup has overridden idle.
-		 * One CPU supports mwait => All CPUs supports mwait
-		 */
-		if (!pm_idle) {
-			printk(KERN_INFO "using mwait in idle threads.\n");
-			pm_idle = mwait_idle;
-		}
-	}
-	selected = 1;
-}
-
-static int __init idle_setup(char *str)
-{
-	if (!strcmp(str, "poll")) {
-		printk("using polling idle threads.\n");
-		pm_idle = poll_idle;
-	} else if (!strcmp(str, "mwait"))
-		force_mwait = 1;
-	else
-		return -1;
-
-	boot_option_idle_override = 1;
-	return 0;
-}
-early_param("idle", idle_setup);
-
 /* Prints also some state that isn't saved in the pt_regs */
 void __show_regs(struct pt_regs * regs)
 {
diff --git a/trunk/arch/x86/kernel/reboot.c b/trunk/arch/x86/kernel/reboot.c
index 1791a751a772..a4a838306b2c 100644
--- a/trunk/arch/x86/kernel/reboot.c
+++ b/trunk/arch/x86/kernel/reboot.c
@@ -399,7 +399,7 @@ static void native_machine_emergency_restart(void)
 	}
 }
 
-static void native_machine_shutdown(void)
+void native_machine_shutdown(void)
 {
 	/* Stop the cpus and apics */
 #ifdef CONFIG_SMP
@@ -470,7 +470,10 @@ struct machine_ops machine_ops = {
 	.shutdown = native_machine_shutdown,
 	.emergency_restart = native_machine_emergency_restart,
 	.restart = native_machine_restart,
-	.halt = native_machine_halt
+	.halt = native_machine_halt,
+#ifdef CONFIG_KEXEC
+	.crash_shutdown = native_machine_crash_shutdown,
+#endif
 };
 
 void machine_power_off(void)
@@ -498,3 +501,9 @@ void machine_halt(void)
 	machine_ops.halt();
 }
 
+#ifdef CONFIG_KEXEC
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+	machine_ops.crash_shutdown(regs);
+}
+#endif
diff --git a/trunk/arch/x86/kernel/setup_32.c b/trunk/arch/x86/kernel/setup_32.c
index 44cc9b933932..2283422af794 100644
--- a/trunk/arch/x86/kernel/setup_32.c
+++ b/trunk/arch/x86/kernel/setup_32.c
@@ -47,6 +47,7 @@
 #include <linux/pfn.h>
 #include <linux/pci.h>
 #include <linux/init_ohci1394_dma.h>
+#include <linux/kvm_para.h>
 
 #include <video/edid.h>
 
@@ -820,6 +821,10 @@ void __init setup_arch(char **cmdline_p)
 
 	max_low_pfn = setup_memory();
 
+#ifdef CONFIG_KVM_CLOCK
+	kvmclock_init();
+#endif
+
 #ifdef CONFIG_VMI
 	/*
 	 * Must be after max_low_pfn is determined, and before kernel
@@ -827,6 +832,7 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	vmi_init();
 #endif
+	kvm_guest_init();
 
 	/*
 	 * NOTE: before this point _nobody_ is allowed to allocate
diff --git a/trunk/arch/x86/kernel/setup_64.c b/trunk/arch/x86/kernel/setup_64.c
index 2f5c488aad0b..22c14e21c97c 100644
--- a/trunk/arch/x86/kernel/setup_64.c
+++ b/trunk/arch/x86/kernel/setup_64.c
@@ -44,6 +44,7 @@
 #include <linux/sort.h>
 #include <linux/uaccess.h>
 #include <linux/init_ohci1394_dma.h>
+#include <linux/kvm_para.h>
 
 #include <asm/mtrr.h>
 #include <asm/uaccess.h>
@@ -398,6 +399,10 @@ void __init setup_arch(char **cmdline_p)
 
 	io_delay_init();
 
+#ifdef CONFIG_KVM_CLOCK
+	kvmclock_init();
+#endif
+
 #ifdef CONFIG_SMP
 	/* setup to use the early static init tables during kernel startup */
 	x86_cpu_to_apicid_early_ptr = (void *)x86_cpu_to_apicid_init;
@@ -502,6 +507,8 @@ void __init setup_arch(char **cmdline_p)
 	init_apic_mappings();
 	ioapic_init_mappings();
 
+	kvm_guest_init();
+
 	/*
 	 * We trust e820 completely. No explicit ROM probing in memory.
 	 */
diff --git a/trunk/arch/x86/kernel/time_32.c b/trunk/arch/x86/kernel/time_32.c
index 1a89e93f3f1c..2ff21f398934 100644
--- a/trunk/arch/x86/kernel/time_32.c
+++ b/trunk/arch/x86/kernel/time_32.c
@@ -115,7 +115,6 @@ irqreturn_t timer_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-extern void (*late_time_init)(void);
 /* Duplicate of time_init() below, with hpet_enable part added */
 void __init hpet_time_init(void)
 {
diff --git a/trunk/arch/x86/kernel/vmlinux_64.lds.S b/trunk/arch/x86/kernel/vmlinux_64.lds.S
index b7ab3c335fae..fad3674b06a5 100644
--- a/trunk/arch/x86/kernel/vmlinux_64.lds.S
+++ b/trunk/arch/x86/kernel/vmlinux_64.lds.S
@@ -209,12 +209,6 @@ SECTIONS
 	EXIT_DATA
   }
 
-/* vdso blob that is mapped into user space */
-  vdso_start = . ;
-  .vdso  : AT(ADDR(.vdso) - LOAD_OFFSET) { *(.vdso) }
-  . = ALIGN(PAGE_SIZE);
-  vdso_end = .;
-
 #ifdef CONFIG_BLK_DEV_INITRD
   . = ALIGN(PAGE_SIZE);
   __initramfs_start = .;
diff --git a/trunk/arch/x86/kvm/Kconfig b/trunk/arch/x86/kvm/Kconfig
index 41962e793c0f..8d45fabc5f3b 100644
--- a/trunk/arch/x86/kvm/Kconfig
+++ b/trunk/arch/x86/kvm/Kconfig
@@ -19,7 +19,7 @@ if VIRTUALIZATION
 
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
-	depends on HAVE_KVM && EXPERIMENTAL
+	depends on HAVE_KVM
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	---help---
@@ -50,6 +50,17 @@ config KVM_AMD
 	  Provides support for KVM on AMD processors equipped with the AMD-V
 	  (SVM) extensions.
 
+config KVM_TRACE
+	bool "KVM trace support"
+	depends on KVM && MARKERS && SYSFS
+	select RELAY
+	select DEBUG_FS
+	default n
+	---help---
+	  This option allows reading a trace of kvm-related events through
+	  relayfs.  Note the ABI is not considered stable and will be
+	  modified in future updates.
+
 # OK, it's a little counter-intuitive to do this, but it puts it neatly under
 # the virtualization menu.
 source drivers/lguest/Kconfig
diff --git a/trunk/arch/x86/kvm/Makefile b/trunk/arch/x86/kvm/Makefile
index ffdd0b310784..c97d35c218db 100644
--- a/trunk/arch/x86/kvm/Makefile
+++ b/trunk/arch/x86/kvm/Makefile
@@ -3,10 +3,14 @@
 #
 
 common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o)
+ifeq ($(CONFIG_KVM_TRACE),y)
+common-objs += $(addprefix ../../../virt/kvm/, kvm_trace.o)
+endif
 
 EXTRA_CFLAGS += -Ivirt/kvm -Iarch/x86/kvm
 
-kvm-objs := $(common-objs) x86.o mmu.o x86_emulate.o i8259.o irq.o lapic.o
+kvm-objs := $(common-objs) x86.o mmu.o x86_emulate.o i8259.o irq.o lapic.o \
+	i8254.o
 obj-$(CONFIG_KVM) += kvm.o
 kvm-intel-objs = vmx.o
 obj-$(CONFIG_KVM_INTEL) += kvm-intel.o
diff --git a/trunk/arch/x86/kvm/i8254.c b/trunk/arch/x86/kvm/i8254.c
new file mode 100644
index 000000000000..361e31611276
--- /dev/null
+++ b/trunk/arch/x86/kvm/i8254.c
@@ -0,0 +1,611 @@
+/*
+ * 8253/8254 interval timer emulation
+ *
+ * Copyright (c) 2003-2004 Fabrice Bellard
+ * Copyright (c) 2006 Intel Corporation
+ * Copyright (c) 2007 Keir Fraser, XenSource Inc
+ * Copyright (c) 2008 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ *
+ * Authors:
+ *   Sheng Yang <sheng.yang@intel.com>
+ *   Based on QEMU and Xen.
+ */
+
+#include <linux/kvm_host.h>
+
+#include "irq.h"
+#include "i8254.h"
+
+#ifndef CONFIG_X86_64
+#define mod_64(x, y) ((x) - (y) * div64_64(x, y))
+#else
+#define mod_64(x, y) ((x) % (y))
+#endif
+
+#define RW_STATE_LSB 1
+#define RW_STATE_MSB 2
+#define RW_STATE_WORD0 3
+#define RW_STATE_WORD1 4
+
+/* Compute with 96 bit intermediate result: (a*b)/c */
+static u64 muldiv64(u64 a, u32 b, u32 c)
+{
+	union {
+		u64 ll;
+		struct {
+			u32 low, high;
+		} l;
+	} u, res;
+	u64 rl, rh;
+
+	u.ll = a;
+	rl = (u64)u.l.low * (u64)b;
+	rh = (u64)u.l.high * (u64)b;
+	rh += (rl >> 32);
+	res.l.high = div64_64(rh, c);
+	res.l.low = div64_64(((mod_64(rh, c) << 32) + (rl & 0xffffffff)), c);
+	return res.ll;
+}
+
+static void pit_set_gate(struct kvm *kvm, int channel, u32 val)
+{
+	struct kvm_kpit_channel_state *c =
+		&kvm->arch.vpit->pit_state.channels[channel];
+
+	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+
+	switch (c->mode) {
+	default:
+	case 0:
+	case 4:
+		/* XXX: just disable/enable counting */
+		break;
+	case 1:
+	case 2:
+	case 3:
+	case 5:
+		/* Restart counting on rising edge. */
+		if (c->gate < val)
+			c->count_load_time = ktime_get();
+		break;
+	}
+
+	c->gate = val;
+}
+
+int pit_get_gate(struct kvm *kvm, int channel)
+{
+	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+
+	return kvm->arch.vpit->pit_state.channels[channel].gate;
+}
+
+static int pit_get_count(struct kvm *kvm, int channel)
+{
+	struct kvm_kpit_channel_state *c =
+		&kvm->arch.vpit->pit_state.channels[channel];
+	s64 d, t;
+	int counter;
+
+	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+
+	t = ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time));
+	d = muldiv64(t, KVM_PIT_FREQ, NSEC_PER_SEC);
+
+	switch (c->mode) {
+	case 0:
+	case 1:
+	case 4:
+	case 5:
+		counter = (c->count - d) & 0xffff;
+		break;
+	case 3:
+		/* XXX: may be incorrect for odd counts */
+		counter = c->count - (mod_64((2 * d), c->count));
+		break;
+	default:
+		counter = c->count - mod_64(d, c->count);
+		break;
+	}
+	return counter;
+}
+
+static int pit_get_out(struct kvm *kvm, int channel)
+{
+	struct kvm_kpit_channel_state *c =
+		&kvm->arch.vpit->pit_state.channels[channel];
+	s64 d, t;
+	int out;
+
+	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+
+	t = ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time));
+	d = muldiv64(t, KVM_PIT_FREQ, NSEC_PER_SEC);
+
+	switch (c->mode) {
+	default:
+	case 0:
+		out = (d >= c->count);
+		break;
+	case 1:
+		out = (d < c->count);
+		break;
+	case 2:
+		out = ((mod_64(d, c->count) == 0) && (d != 0));
+		break;
+	case 3:
+		out = (mod_64(d, c->count) < ((c->count + 1) >> 1));
+		break;
+	case 4:
+	case 5:
+		out = (d == c->count);
+		break;
+	}
+
+	return out;
+}
+
+static void pit_latch_count(struct kvm *kvm, int channel)
+{
+	struct kvm_kpit_channel_state *c =
+		&kvm->arch.vpit->pit_state.channels[channel];
+
+	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+
+	if (!c->count_latched) {
+		c->latched_count = pit_get_count(kvm, channel);
+		c->count_latched = c->rw_mode;
+	}
+}
+
+static void pit_latch_status(struct kvm *kvm, int channel)
+{
+	struct kvm_kpit_channel_state *c =
+		&kvm->arch.vpit->pit_state.channels[channel];
+
+	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+
+	if (!c->status_latched) {
+		/* TODO: Return NULL COUNT (bit 6). */
+		c->status = ((pit_get_out(kvm, channel) << 7) |
+				(c->rw_mode << 4) |
+				(c->mode << 1) |
+				c->bcd);
+		c->status_latched = 1;
+	}
+}
+
+int __pit_timer_fn(struct kvm_kpit_state *ps)
+{
+	struct kvm_vcpu *vcpu0 = ps->pit->kvm->vcpus[0];
+	struct kvm_kpit_timer *pt = &ps->pit_timer;
+
+	atomic_inc(&pt->pending);
+	smp_mb__after_atomic_inc();
+	/* FIXME: handle case where the guest is in guest mode */
+	if (vcpu0 && waitqueue_active(&vcpu0->wq)) {
+		vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+		wake_up_interruptible(&vcpu0->wq);
+	}
+
+	pt->timer.expires = ktime_add_ns(pt->timer.expires, pt->period);
+	pt->scheduled = ktime_to_ns(pt->timer.expires);
+
+	return (pt->period == 0 ? 0 : 1);
+}
+
+int pit_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
+
+	if (pit && vcpu->vcpu_id == 0)
+		return atomic_read(&pit->pit_state.pit_timer.pending);
+
+	return 0;
+}
+
+static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
+{
+	struct kvm_kpit_state *ps;
+	int restart_timer = 0;
+
+	ps = container_of(data, struct kvm_kpit_state, pit_timer.timer);
+
+	restart_timer = __pit_timer_fn(ps);
+
+	if (restart_timer)
+		return HRTIMER_RESTART;
+	else
+		return HRTIMER_NORESTART;
+}
+
+static void destroy_pit_timer(struct kvm_kpit_timer *pt)
+{
+	pr_debug("pit: execute del timer!\n");
+	hrtimer_cancel(&pt->timer);
+}
+
+static void create_pit_timer(struct kvm_kpit_timer *pt, u32 val, int is_period)
+{
+	s64 interval;
+
+	interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ);
+
+	pr_debug("pit: create pit timer, interval is %llu nsec\n", interval);
+
+	/* TODO The new value only affected after the retriggered */
+	hrtimer_cancel(&pt->timer);
+	pt->period = (is_period == 0) ? 0 : interval;
+	pt->timer.function = pit_timer_fn;
+	atomic_set(&pt->pending, 0);
+
+	hrtimer_start(&pt->timer, ktime_add_ns(ktime_get(), interval),
+		      HRTIMER_MODE_ABS);
+}
+
+static void pit_load_count(struct kvm *kvm, int channel, u32 val)
+{
+	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
+
+	WARN_ON(!mutex_is_locked(&ps->lock));
+
+	pr_debug("pit: load_count val is %d, channel is %d\n", val, channel);
+
+	/*
+	 * Though spec said the state of 8254 is undefined after power-up,
+	 * seems some tricky OS like Windows XP depends on IRQ0 interrupt
+	 * when booting up.
+	 * So here setting initialize rate for it, and not a specific number
+	 */
+	if (val == 0)
+		val = 0x10000;
+
+	ps->channels[channel].count_load_time = ktime_get();
+	ps->channels[channel].count = val;
+
+	if (channel != 0)
+		return;
+
+	/* Two types of timer
+	 * mode 1 is one shot, mode 2 is period, otherwise del timer */
+	switch (ps->channels[0].mode) {
+	case 1:
+		create_pit_timer(&ps->pit_timer, val, 0);
+		break;
+	case 2:
+		create_pit_timer(&ps->pit_timer, val, 1);
+		break;
+	default:
+		destroy_pit_timer(&ps->pit_timer);
+	}
+}
+
+void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val)
+{
+	mutex_lock(&kvm->arch.vpit->pit_state.lock);
+	pit_load_count(kvm, channel, val);
+	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+}
+
+static void pit_ioport_write(struct kvm_io_device *this,
+			     gpa_t addr, int len, const void *data)
+{
+	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_kpit_state *pit_state = &pit->pit_state;
+	struct kvm *kvm = pit->kvm;
+	int channel, access;
+	struct kvm_kpit_channel_state *s;
+	u32 val = *(u32 *) data;
+
+	val  &= 0xff;
+	addr &= KVM_PIT_CHANNEL_MASK;
+
+	mutex_lock(&pit_state->lock);
+
+	if (val != 0)
+		pr_debug("pit: write addr is 0x%x, len is %d, val is 0x%x\n",
+			  (unsigned int)addr, len, val);
+
+	if (addr == 3) {
+		channel = val >> 6;
+		if (channel == 3) {
+			/* Read-Back Command. */
+			for (channel = 0; channel < 3; channel++) {
+				s = &pit_state->channels[channel];
+				if (val & (2 << channel)) {
+					if (!(val & 0x20))
+						pit_latch_count(kvm, channel);
+					if (!(val & 0x10))
+						pit_latch_status(kvm, channel);
+				}
+			}
+		} else {
+			/* Select Counter <channel>. */
+			s = &pit_state->channels[channel];
+			access = (val >> 4) & KVM_PIT_CHANNEL_MASK;
+			if (access == 0) {
+				pit_latch_count(kvm, channel);
+			} else {
+				s->rw_mode = access;
+				s->read_state = access;
+				s->write_state = access;
+				s->mode = (val >> 1) & 7;
+				if (s->mode > 5)
+					s->mode -= 4;
+				s->bcd = val & 1;
+			}
+		}
+	} else {
+		/* Write Count. */
+		s = &pit_state->channels[addr];
+		switch (s->write_state) {
+		default:
+		case RW_STATE_LSB:
+			pit_load_count(kvm, addr, val);
+			break;
+		case RW_STATE_MSB:
+			pit_load_count(kvm, addr, val << 8);
+			break;
+		case RW_STATE_WORD0:
+			s->write_latch = val;
+			s->write_state = RW_STATE_WORD1;
+			break;
+		case RW_STATE_WORD1:
+			pit_load_count(kvm, addr, s->write_latch | (val << 8));
+			s->write_state = RW_STATE_WORD0;
+			break;
+		}
+	}
+
+	mutex_unlock(&pit_state->lock);
+}
+
+static void pit_ioport_read(struct kvm_io_device *this,
+			    gpa_t addr, int len, void *data)
+{
+	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_kpit_state *pit_state = &pit->pit_state;
+	struct kvm *kvm = pit->kvm;
+	int ret, count;
+	struct kvm_kpit_channel_state *s;
+
+	addr &= KVM_PIT_CHANNEL_MASK;
+	s = &pit_state->channels[addr];
+
+	mutex_lock(&pit_state->lock);
+
+	if (s->status_latched) {
+		s->status_latched = 0;
+		ret = s->status;
+	} else if (s->count_latched) {
+		switch (s->count_latched) {
+		default:
+		case RW_STATE_LSB:
+			ret = s->latched_count & 0xff;
+			s->count_latched = 0;
+			break;
+		case RW_STATE_MSB:
+			ret = s->latched_count >> 8;
+			s->count_latched = 0;
+			break;
+		case RW_STATE_WORD0:
+			ret = s->latched_count & 0xff;
+			s->count_latched = RW_STATE_MSB;
+			break;
+		}
+	} else {
+		switch (s->read_state) {
+		default:
+		case RW_STATE_LSB:
+			count = pit_get_count(kvm, addr);
+			ret = count & 0xff;
+			break;
+		case RW_STATE_MSB:
+			count = pit_get_count(kvm, addr);
+			ret = (count >> 8) & 0xff;
+			break;
+		case RW_STATE_WORD0:
+			count = pit_get_count(kvm, addr);
+			ret = count & 0xff;
+			s->read_state = RW_STATE_WORD1;
+			break;
+		case RW_STATE_WORD1:
+			count = pit_get_count(kvm, addr);
+			ret = (count >> 8) & 0xff;
+			s->read_state = RW_STATE_WORD0;
+			break;
+		}
+	}
+
+	if (len > sizeof(ret))
+		len = sizeof(ret);
+	memcpy(data, (char *)&ret, len);
+
+	mutex_unlock(&pit_state->lock);
+}
+
+static int pit_in_range(struct kvm_io_device *this, gpa_t addr)
+{
+	return ((addr >= KVM_PIT_BASE_ADDRESS) &&
+		(addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH));
+}
+
+static void speaker_ioport_write(struct kvm_io_device *this,
+				 gpa_t addr, int len, const void *data)
+{
+	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_kpit_state *pit_state = &pit->pit_state;
+	struct kvm *kvm = pit->kvm;
+	u32 val = *(u32 *) data;
+
+	mutex_lock(&pit_state->lock);
+	pit_state->speaker_data_on = (val >> 1) & 1;
+	pit_set_gate(kvm, 2, val & 1);
+	mutex_unlock(&pit_state->lock);
+}
+
+static void speaker_ioport_read(struct kvm_io_device *this,
+				gpa_t addr, int len, void *data)
+{
+	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_kpit_state *pit_state = &pit->pit_state;
+	struct kvm *kvm = pit->kvm;
+	unsigned int refresh_clock;
+	int ret;
+
+	/* Refresh clock toggles at about 15us. We approximate as 2^14ns. */
+	refresh_clock = ((unsigned int)ktime_to_ns(ktime_get()) >> 14) & 1;
+
+	mutex_lock(&pit_state->lock);
+	ret = ((pit_state->speaker_data_on << 1) | pit_get_gate(kvm, 2) |
+		(pit_get_out(kvm, 2) << 5) | (refresh_clock << 4));
+	if (len > sizeof(ret))
+		len = sizeof(ret);
+	memcpy(data, (char *)&ret, len);
+	mutex_unlock(&pit_state->lock);
+}
+
+static int speaker_in_range(struct kvm_io_device *this, gpa_t addr)
+{
+	return (addr == KVM_SPEAKER_BASE_ADDRESS);
+}
+
+void kvm_pit_reset(struct kvm_pit *pit)
+{
+	int i;
+	struct kvm_kpit_channel_state *c;
+
+	mutex_lock(&pit->pit_state.lock);
+	for (i = 0; i < 3; i++) {
+		c = &pit->pit_state.channels[i];
+		c->mode = 0xff;
+		c->gate = (i != 2);
+		pit_load_count(pit->kvm, i, 0);
+	}
+	mutex_unlock(&pit->pit_state.lock);
+
+	atomic_set(&pit->pit_state.pit_timer.pending, 0);
+	pit->pit_state.inject_pending = 1;
+}
+
+struct kvm_pit *kvm_create_pit(struct kvm *kvm)
+{
+	struct kvm_pit *pit;
+	struct kvm_kpit_state *pit_state;
+
+	pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL);
+	if (!pit)
+		return NULL;
+
+	mutex_init(&pit->pit_state.lock);
+	mutex_lock(&pit->pit_state.lock);
+
+	/* Initialize PIO device */
+	pit->dev.read = pit_ioport_read;
+	pit->dev.write = pit_ioport_write;
+	pit->dev.in_range = pit_in_range;
+	pit->dev.private = pit;
+	kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev);
+
+	pit->speaker_dev.read = speaker_ioport_read;
+	pit->speaker_dev.write = speaker_ioport_write;
+	pit->speaker_dev.in_range = speaker_in_range;
+	pit->speaker_dev.private = pit;
+	kvm_io_bus_register_dev(&kvm->pio_bus, &pit->speaker_dev);
+
+	kvm->arch.vpit = pit;
+	pit->kvm = kvm;
+
+	pit_state = &pit->pit_state;
+	pit_state->pit = pit;
+	hrtimer_init(&pit_state->pit_timer.timer,
+		     CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	mutex_unlock(&pit->pit_state.lock);
+
+	kvm_pit_reset(pit);
+
+	return pit;
+}
+
+void kvm_free_pit(struct kvm *kvm)
+{
+	struct hrtimer *timer;
+
+	if (kvm->arch.vpit) {
+		mutex_lock(&kvm->arch.vpit->pit_state.lock);
+		timer = &kvm->arch.vpit->pit_state.pit_timer.timer;
+		hrtimer_cancel(timer);
+		mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+		kfree(kvm->arch.vpit);
+	}
+}
+
+void __inject_pit_timer_intr(struct kvm *kvm)
+{
+	mutex_lock(&kvm->lock);
+	kvm_ioapic_set_irq(kvm->arch.vioapic, 0, 1);
+	kvm_ioapic_set_irq(kvm->arch.vioapic, 0, 0);
+	kvm_pic_set_irq(pic_irqchip(kvm), 0, 1);
+	kvm_pic_set_irq(pic_irqchip(kvm), 0, 0);
+	mutex_unlock(&kvm->lock);
+}
+
+void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_kpit_state *ps;
+
+	if (vcpu && pit) {
+		ps = &pit->pit_state;
+
+		/* Try to inject pending interrupts when:
+		 * 1. Pending exists
+		 * 2. Last interrupt was accepted or waited for too long time*/
+		if (atomic_read(&ps->pit_timer.pending) &&
+		    (ps->inject_pending ||
+		    (jiffies - ps->last_injected_time
+				>= KVM_MAX_PIT_INTR_INTERVAL))) {
+			ps->inject_pending = 0;
+			__inject_pit_timer_intr(kvm);
+			ps->last_injected_time = jiffies;
+		}
+	}
+}
+
+void kvm_pit_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
+{
+	struct kvm_arch *arch = &vcpu->kvm->arch;
+	struct kvm_kpit_state *ps;
+
+	if (vcpu && arch->vpit) {
+		ps = &arch->vpit->pit_state;
+		if (atomic_read(&ps->pit_timer.pending) &&
+		(((arch->vpic->pics[0].imr & 1) == 0 &&
+		  arch->vpic->pics[0].irq_base == vec) ||
+		  (arch->vioapic->redirtbl[0].fields.vector == vec &&
+		  arch->vioapic->redirtbl[0].fields.mask != 1))) {
+			ps->inject_pending = 1;
+			atomic_dec(&ps->pit_timer.pending);
+			ps->channels[0].count_load_time = ktime_get();
+		}
+	}
+}
diff --git a/trunk/arch/x86/kvm/i8254.h b/trunk/arch/x86/kvm/i8254.h
new file mode 100644
index 000000000000..db25c2a6c8c4
--- /dev/null
+++ b/trunk/arch/x86/kvm/i8254.h
@@ -0,0 +1,63 @@
+#ifndef __I8254_H
+#define __I8254_H
+
+#include "iodev.h"
+
+struct kvm_kpit_timer {
+	struct hrtimer timer;
+	int irq;
+	s64 period; /* unit: ns */
+	s64 scheduled;
+	ktime_t last_update;
+	atomic_t pending;
+};
+
+struct kvm_kpit_channel_state {
+	u32 count; /* can be 65536 */
+	u16 latched_count;
+	u8 count_latched;
+	u8 status_latched;
+	u8 status;
+	u8 read_state;
+	u8 write_state;
+	u8 write_latch;
+	u8 rw_mode;
+	u8 mode;
+	u8 bcd; /* not supported */
+	u8 gate; /* timer start */
+	ktime_t count_load_time;
+};
+
+struct kvm_kpit_state {
+	struct kvm_kpit_channel_state channels[3];
+	struct kvm_kpit_timer pit_timer;
+	u32    speaker_data_on;
+	struct mutex lock;
+	struct kvm_pit *pit;
+	bool inject_pending; /* if inject pending interrupts */
+	unsigned long last_injected_time;
+};
+
+struct kvm_pit {
+	unsigned long base_addresss;
+	struct kvm_io_device dev;
+	struct kvm_io_device speaker_dev;
+	struct kvm *kvm;
+	struct kvm_kpit_state pit_state;
+};
+
+#define KVM_PIT_BASE_ADDRESS	    0x40
+#define KVM_SPEAKER_BASE_ADDRESS    0x61
+#define KVM_PIT_MEM_LENGTH	    4
+#define KVM_PIT_FREQ		    1193181
+#define KVM_MAX_PIT_INTR_INTERVAL   HZ / 100
+#define KVM_PIT_CHANNEL_MASK	    0x3
+
+void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu);
+void kvm_pit_timer_intr_post(struct kvm_vcpu *vcpu, int vec);
+void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val);
+struct kvm_pit *kvm_create_pit(struct kvm *kvm);
+void kvm_free_pit(struct kvm *kvm);
+void kvm_pit_reset(struct kvm_pit *pit);
+
+#endif
diff --git a/trunk/arch/x86/kvm/irq.c b/trunk/arch/x86/kvm/irq.c
index e5714759e97f..ce1f583459b1 100644
--- a/trunk/arch/x86/kvm/irq.c
+++ b/trunk/arch/x86/kvm/irq.c
@@ -23,6 +23,22 @@
 #include <linux/kvm_host.h>
 
 #include "irq.h"
+#include "i8254.h"
+
+/*
+ * check if there are pending timer events
+ * to be processed.
+ */
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	ret = pit_has_pending_timer(vcpu);
+	ret |= apic_has_pending_timer(vcpu);
+
+	return ret;
+}
+EXPORT_SYMBOL(kvm_cpu_has_pending_timer);
 
 /*
  * check if there is pending interrupt without
@@ -66,6 +82,7 @@ EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt);
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
 {
 	kvm_inject_apic_timer_irqs(vcpu);
+	kvm_inject_pit_timer_irqs(vcpu);
 	/* TODO: PIT, RTC etc. */
 }
 EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs);
@@ -73,6 +90,7 @@ EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs);
 void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
 {
 	kvm_apic_timer_intr_post(vcpu, vec);
+	kvm_pit_timer_intr_post(vcpu, vec);
 	/* TODO: PIT, RTC etc. */
 }
 EXPORT_SYMBOL_GPL(kvm_timer_intr_post);
diff --git a/trunk/arch/x86/kvm/irq.h b/trunk/arch/x86/kvm/irq.h
index fa5ed5d59b5d..1802134b836f 100644
--- a/trunk/arch/x86/kvm/irq.h
+++ b/trunk/arch/x86/kvm/irq.h
@@ -85,4 +85,7 @@ void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
 void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu);
 
+int pit_has_pending_timer(struct kvm_vcpu *vcpu);
+int apic_has_pending_timer(struct kvm_vcpu *vcpu);
+
 #endif
diff --git a/trunk/arch/x86/kvm/kvm_svm.h b/trunk/arch/x86/kvm/kvm_svm.h
index ecdfe97e4635..65ef0fc2c036 100644
--- a/trunk/arch/x86/kvm/kvm_svm.h
+++ b/trunk/arch/x86/kvm/kvm_svm.h
@@ -39,6 +39,8 @@ struct vcpu_svm {
 	unsigned long host_db_regs[NUM_DB_REGS];
 	unsigned long host_dr6;
 	unsigned long host_dr7;
+
+	u32 *msrpm;
 };
 
 #endif
diff --git a/trunk/arch/x86/kvm/lapic.c b/trunk/arch/x86/kvm/lapic.c
index 68a6b1511934..57ac4e4c556a 100644
--- a/trunk/arch/x86/kvm/lapic.c
+++ b/trunk/arch/x86/kvm/lapic.c
@@ -338,10 +338,10 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 		} else
 			apic_clear_vector(vector, apic->regs + APIC_TMR);
 
-		if (vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE)
+		if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
 			kvm_vcpu_kick(vcpu);
-		else if (vcpu->arch.mp_state == VCPU_MP_STATE_HALTED) {
-			vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
+		else if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) {
+			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 			if (waitqueue_active(&vcpu->wq))
 				wake_up_interruptible(&vcpu->wq);
 		}
@@ -362,11 +362,11 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 
 	case APIC_DM_INIT:
 		if (level) {
-			if (vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE)
+			if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
 				printk(KERN_DEBUG
 				       "INIT on a runnable vcpu %d\n",
 				       vcpu->vcpu_id);
-			vcpu->arch.mp_state = VCPU_MP_STATE_INIT_RECEIVED;
+			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
 			kvm_vcpu_kick(vcpu);
 		} else {
 			printk(KERN_DEBUG
@@ -379,9 +379,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 	case APIC_DM_STARTUP:
 		printk(KERN_DEBUG "SIPI to vcpu %d vector 0x%02x\n",
 		       vcpu->vcpu_id, vector);
-		if (vcpu->arch.mp_state == VCPU_MP_STATE_INIT_RECEIVED) {
+		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
 			vcpu->arch.sipi_vector = vector;
-			vcpu->arch.mp_state = VCPU_MP_STATE_SIPI_RECEIVED;
+			vcpu->arch.mp_state = KVM_MP_STATE_SIPI_RECEIVED;
 			if (waitqueue_active(&vcpu->wq))
 				wake_up_interruptible(&vcpu->wq);
 		}
@@ -658,7 +658,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 	apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016"
 			   PRIx64 ", "
 			   "timer initial count 0x%x, period %lldns, "
-			   "expire @ 0x%016" PRIx64 ".\n", __FUNCTION__,
+			   "expire @ 0x%016" PRIx64 ".\n", __func__,
 			   APIC_BUS_CYCLE_NS, ktime_to_ns(now),
 			   apic_get_reg(apic, APIC_TMICT),
 			   apic->timer.period,
@@ -691,7 +691,7 @@ static void apic_mmio_write(struct kvm_io_device *this,
 	/* too common printing */
 	if (offset != APIC_EOI)
 		apic_debug("%s: offset 0x%x with length 0x%x, and value is "
-			   "0x%x\n", __FUNCTION__, offset, len, val);
+			   "0x%x\n", __func__, offset, len, val);
 
 	offset &= 0xff0;
 
@@ -822,6 +822,7 @@ void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8)
 	apic_set_tpr(apic, ((cr8 & 0x0f) << 4)
 		     | (apic_get_reg(apic, APIC_TASKPRI) & 4));
 }
+EXPORT_SYMBOL_GPL(kvm_lapic_set_tpr);
 
 u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
 {
@@ -869,7 +870,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic;
 	int i;
 
-	apic_debug("%s\n", __FUNCTION__);
+	apic_debug("%s\n", __func__);
 
 	ASSERT(vcpu);
 	apic = vcpu->arch.apic;
@@ -907,7 +908,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 	apic_update_ppr(apic);
 
 	apic_debug(KERN_INFO "%s: vcpu=%p, id=%d, base_msr="
-		   "0x%016" PRIx64 ", base_address=0x%0lx.\n", __FUNCTION__,
+		   "0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__,
 		   vcpu, kvm_apic_id(apic),
 		   vcpu->arch.apic_base, apic->base_address);
 }
@@ -940,7 +941,7 @@ static int __apic_timer_fn(struct kvm_lapic *apic)
 
 	atomic_inc(&apic->timer.pending);
 	if (waitqueue_active(q)) {
-		apic->vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
+		apic->vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 		wake_up_interruptible(q);
 	}
 	if (apic_lvtt_period(apic)) {
@@ -952,6 +953,16 @@ static int __apic_timer_fn(struct kvm_lapic *apic)
 	return result;
 }
 
+int apic_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *lapic = vcpu->arch.apic;
+
+	if (lapic)
+		return atomic_read(&lapic->timer.pending);
+
+	return 0;
+}
+
 static int __inject_apic_timer_irq(struct kvm_lapic *apic)
 {
 	int vector;
diff --git a/trunk/arch/x86/kvm/mmu.c b/trunk/arch/x86/kvm/mmu.c
index e55af12e11b7..2ad6f5481671 100644
--- a/trunk/arch/x86/kvm/mmu.c
+++ b/trunk/arch/x86/kvm/mmu.c
@@ -27,11 +27,22 @@
 #include <linux/highmem.h>
 #include <linux/module.h>
 #include <linux/swap.h>
+#include <linux/hugetlb.h>
+#include <linux/compiler.h>
 
 #include <asm/page.h>
 #include <asm/cmpxchg.h>
 #include <asm/io.h>
 
+/*
+ * When setting this variable to true it enables Two-Dimensional-Paging
+ * where the hardware walks 2 page tables:
+ * 1. the guest-virtual to guest-physical
+ * 2. while doing 1. it walks guest-physical to host-physical
+ * If the hardware supports that we don't need to do shadow paging.
+ */
+bool tdp_enabled = false;
+
 #undef MMU_DEBUG
 
 #undef AUDIT
@@ -101,8 +112,6 @@ static int dbg = 1;
 #define PT_FIRST_AVAIL_BITS_SHIFT 9
 #define PT64_SECOND_AVAIL_BITS_SHIFT 52
 
-#define PT_SHADOW_IO_MARK (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
-
 #define VALID_PAGE(x) ((x) != INVALID_PAGE)
 
 #define PT64_LEVEL_BITS 9
@@ -159,6 +168,13 @@ static int dbg = 1;
 #define ACC_USER_MASK    PT_USER_MASK
 #define ACC_ALL          (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK)
 
+struct kvm_pv_mmu_op_buffer {
+	void *ptr;
+	unsigned len;
+	unsigned processed;
+	char buf[512] __aligned(sizeof(long));
+};
+
 struct kvm_rmap_desc {
 	u64 *shadow_ptes[RMAP_EXT];
 	struct kvm_rmap_desc *more;
@@ -200,11 +216,15 @@ static int is_present_pte(unsigned long pte)
 
 static int is_shadow_present_pte(u64 pte)
 {
-	pte &= ~PT_SHADOW_IO_MARK;
 	return pte != shadow_trap_nonpresent_pte
 		&& pte != shadow_notrap_nonpresent_pte;
 }
 
+static int is_large_pte(u64 pte)
+{
+	return pte & PT_PAGE_SIZE_MASK;
+}
+
 static int is_writeble_pte(unsigned long pte)
 {
 	return pte & PT_WRITABLE_MASK;
@@ -215,14 +235,14 @@ static int is_dirty_pte(unsigned long pte)
 	return pte & PT_DIRTY_MASK;
 }
 
-static int is_io_pte(unsigned long pte)
+static int is_rmap_pte(u64 pte)
 {
-	return pte & PT_SHADOW_IO_MARK;
+	return is_shadow_present_pte(pte);
 }
 
-static int is_rmap_pte(u64 pte)
+static pfn_t spte_to_pfn(u64 pte)
 {
-	return is_shadow_present_pte(pte);
+	return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
 }
 
 static gfn_t pse36_gfn_delta(u32 gpte)
@@ -348,17 +368,101 @@ static void mmu_free_rmap_desc(struct kvm_rmap_desc *rd)
 	kfree(rd);
 }
 
+/*
+ * Return the pointer to the largepage write count for a given
+ * gfn, handling slots that are not large page aligned.
+ */
+static int *slot_largepage_idx(gfn_t gfn, struct kvm_memory_slot *slot)
+{
+	unsigned long idx;
+
+	idx = (gfn / KVM_PAGES_PER_HPAGE) -
+	      (slot->base_gfn / KVM_PAGES_PER_HPAGE);
+	return &slot->lpage_info[idx].write_count;
+}
+
+static void account_shadowed(struct kvm *kvm, gfn_t gfn)
+{
+	int *write_count;
+
+	write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn));
+	*write_count += 1;
+	WARN_ON(*write_count > KVM_PAGES_PER_HPAGE);
+}
+
+static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
+{
+	int *write_count;
+
+	write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn));
+	*write_count -= 1;
+	WARN_ON(*write_count < 0);
+}
+
+static int has_wrprotected_page(struct kvm *kvm, gfn_t gfn)
+{
+	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
+	int *largepage_idx;
+
+	if (slot) {
+		largepage_idx = slot_largepage_idx(gfn, slot);
+		return *largepage_idx;
+	}
+
+	return 1;
+}
+
+static int host_largepage_backed(struct kvm *kvm, gfn_t gfn)
+{
+	struct vm_area_struct *vma;
+	unsigned long addr;
+
+	addr = gfn_to_hva(kvm, gfn);
+	if (kvm_is_error_hva(addr))
+		return 0;
+
+	vma = find_vma(current->mm, addr);
+	if (vma && is_vm_hugetlb_page(vma))
+		return 1;
+
+	return 0;
+}
+
+static int is_largepage_backed(struct kvm_vcpu *vcpu, gfn_t large_gfn)
+{
+	struct kvm_memory_slot *slot;
+
+	if (has_wrprotected_page(vcpu->kvm, large_gfn))
+		return 0;
+
+	if (!host_largepage_backed(vcpu->kvm, large_gfn))
+		return 0;
+
+	slot = gfn_to_memslot(vcpu->kvm, large_gfn);
+	if (slot && slot->dirty_bitmap)
+		return 0;
+
+	return 1;
+}
+
 /*
  * Take gfn and return the reverse mapping to it.
  * Note: gfn must be unaliased before this function get called
  */
 
-static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn)
+static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int lpage)
 {
 	struct kvm_memory_slot *slot;
+	unsigned long idx;
 
 	slot = gfn_to_memslot(kvm, gfn);
-	return &slot->rmap[gfn - slot->base_gfn];
+	if (!lpage)
+		return &slot->rmap[gfn - slot->base_gfn];
+
+	idx = (gfn / KVM_PAGES_PER_HPAGE) -
+	      (slot->base_gfn / KVM_PAGES_PER_HPAGE);
+
+	return &slot->lpage_info[idx].rmap_pde;
 }
 
 /*
@@ -370,7 +474,7 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn)
  * If rmapp bit zero is one, (then rmap & ~1) points to a struct kvm_rmap_desc
  * containing more mappings.
  */
-static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
+static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage)
 {
 	struct kvm_mmu_page *sp;
 	struct kvm_rmap_desc *desc;
@@ -382,7 +486,7 @@ static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 	gfn = unalias_gfn(vcpu->kvm, gfn);
 	sp = page_header(__pa(spte));
 	sp->gfns[spte - sp->spt] = gfn;
-	rmapp = gfn_to_rmap(vcpu->kvm, gfn);
+	rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage);
 	if (!*rmapp) {
 		rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte);
 		*rmapp = (unsigned long)spte;
@@ -435,20 +539,21 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
 	struct kvm_rmap_desc *desc;
 	struct kvm_rmap_desc *prev_desc;
 	struct kvm_mmu_page *sp;
-	struct page *page;
+	pfn_t pfn;
 	unsigned long *rmapp;
 	int i;
 
 	if (!is_rmap_pte(*spte))
 		return;
 	sp = page_header(__pa(spte));
-	page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT);
-	mark_page_accessed(page);
+	pfn = spte_to_pfn(*spte);
+	if (*spte & PT_ACCESSED_MASK)
+		kvm_set_pfn_accessed(pfn);
 	if (is_writeble_pte(*spte))
-		kvm_release_page_dirty(page);
+		kvm_release_pfn_dirty(pfn);
 	else
-		kvm_release_page_clean(page);
-	rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt]);
+		kvm_release_pfn_clean(pfn);
+	rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], is_large_pte(*spte));
 	if (!*rmapp) {
 		printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte);
 		BUG();
@@ -514,7 +619,7 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn)
 	int write_protected = 0;
 
 	gfn = unalias_gfn(kvm, gfn);
-	rmapp = gfn_to_rmap(kvm, gfn);
+	rmapp = gfn_to_rmap(kvm, gfn, 0);
 
 	spte = rmap_next(kvm, rmapp, NULL);
 	while (spte) {
@@ -527,8 +632,35 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn)
 		}
 		spte = rmap_next(kvm, rmapp, spte);
 	}
+	if (write_protected) {
+		pfn_t pfn;
+
+		spte = rmap_next(kvm, rmapp, NULL);
+		pfn = spte_to_pfn(*spte);
+		kvm_set_pfn_dirty(pfn);
+	}
+
+	/* check for huge page mappings */
+	rmapp = gfn_to_rmap(kvm, gfn, 1);
+	spte = rmap_next(kvm, rmapp, NULL);
+	while (spte) {
+		BUG_ON(!spte);
+		BUG_ON(!(*spte & PT_PRESENT_MASK));
+		BUG_ON((*spte & (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)) != (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK));
+		pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn);
+		if (is_writeble_pte(*spte)) {
+			rmap_remove(kvm, spte);
+			--kvm->stat.lpages;
+			set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+			write_protected = 1;
+		}
+		spte = rmap_next(kvm, rmapp, spte);
+	}
+
 	if (write_protected)
 		kvm_flush_remote_tlbs(kvm);
+
+	account_shadowed(kvm, gfn);
 }
 
 #ifdef MMU_DEBUG
@@ -538,8 +670,8 @@ static int is_empty_shadow_page(u64 *spt)
 	u64 *end;
 
 	for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
-		if ((*pos & ~PT_SHADOW_IO_MARK) != shadow_trap_nonpresent_pte) {
-			printk(KERN_ERR "%s: %p %llx\n", __FUNCTION__,
+		if (*pos != shadow_trap_nonpresent_pte) {
+			printk(KERN_ERR "%s: %p %llx\n", __func__,
 			       pos, *pos);
 			return 0;
 		}
@@ -559,7 +691,7 @@ static void kvm_mmu_free_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 
 static unsigned kvm_page_table_hashfn(gfn_t gfn)
 {
-	return gfn;
+	return gfn & ((1 << KVM_MMU_HASH_SHIFT) - 1);
 }
 
 static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
@@ -662,13 +794,14 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
 	struct kvm_mmu_page *sp;
 	struct hlist_node *node;
 
-	pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn);
-	index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+	pgprintk("%s: looking for gfn %lx\n", __func__, gfn);
+	index = kvm_page_table_hashfn(gfn);
 	bucket = &kvm->arch.mmu_page_hash[index];
 	hlist_for_each_entry(sp, node, bucket, hash_link)
-		if (sp->gfn == gfn && !sp->role.metaphysical) {
+		if (sp->gfn == gfn && !sp->role.metaphysical
+		    && !sp->role.invalid) {
 			pgprintk("%s: found role %x\n",
-				 __FUNCTION__, sp->role.word);
+				 __func__, sp->role.word);
 			return sp;
 		}
 	return NULL;
@@ -699,27 +832,27 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 		quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
 		role.quadrant = quadrant;
 	}
-	pgprintk("%s: looking gfn %lx role %x\n", __FUNCTION__,
+	pgprintk("%s: looking gfn %lx role %x\n", __func__,
 		 gfn, role.word);
-	index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+	index = kvm_page_table_hashfn(gfn);
 	bucket = &vcpu->kvm->arch.mmu_page_hash[index];
 	hlist_for_each_entry(sp, node, bucket, hash_link)
 		if (sp->gfn == gfn && sp->role.word == role.word) {
 			mmu_page_add_parent_pte(vcpu, sp, parent_pte);
-			pgprintk("%s: found\n", __FUNCTION__);
+			pgprintk("%s: found\n", __func__);
 			return sp;
 		}
 	++vcpu->kvm->stat.mmu_cache_miss;
 	sp = kvm_mmu_alloc_page(vcpu, parent_pte);
 	if (!sp)
 		return sp;
-	pgprintk("%s: adding gfn %lx role %x\n", __FUNCTION__, gfn, role.word);
+	pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word);
 	sp->gfn = gfn;
 	sp->role = role;
 	hlist_add_head(&sp->hash_link, bucket);
-	vcpu->arch.mmu.prefetch_page(vcpu, sp);
 	if (!metaphysical)
 		rmap_write_protect(vcpu->kvm, gfn);
+	vcpu->arch.mmu.prefetch_page(vcpu, sp);
 	return sp;
 }
 
@@ -745,11 +878,17 @@ static void kvm_mmu_page_unlink_children(struct kvm *kvm,
 	for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
 		ent = pt[i];
 
+		if (is_shadow_present_pte(ent)) {
+			if (!is_large_pte(ent)) {
+				ent &= PT64_BASE_ADDR_MASK;
+				mmu_page_remove_parent_pte(page_header(ent),
+							   &pt[i]);
+			} else {
+				--kvm->stat.lpages;
+				rmap_remove(kvm, &pt[i]);
+			}
+		}
 		pt[i] = shadow_trap_nonpresent_pte;
-		if (!is_shadow_present_pte(ent))
-			continue;
-		ent &= PT64_BASE_ADDR_MASK;
-		mmu_page_remove_parent_pte(page_header(ent), &pt[i]);
 	}
 	kvm_flush_remote_tlbs(kvm);
 }
@@ -789,10 +928,15 @@ static void kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 	}
 	kvm_mmu_page_unlink_children(kvm, sp);
 	if (!sp->root_count) {
+		if (!sp->role.metaphysical)
+			unaccount_shadowed(kvm, sp->gfn);
 		hlist_del(&sp->hash_link);
 		kvm_mmu_free_page(kvm, sp);
-	} else
+	} else {
 		list_move(&sp->link, &kvm->arch.active_mmu_pages);
+		sp->role.invalid = 1;
+		kvm_reload_remote_mmus(kvm);
+	}
 	kvm_mmu_reset_last_pte_updated(kvm);
 }
 
@@ -838,13 +982,13 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 	struct hlist_node *node, *n;
 	int r;
 
-	pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn);
+	pgprintk("%s: looking for gfn %lx\n", __func__, gfn);
 	r = 0;
-	index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+	index = kvm_page_table_hashfn(gfn);
 	bucket = &kvm->arch.mmu_page_hash[index];
 	hlist_for_each_entry_safe(sp, node, n, bucket, hash_link)
 		if (sp->gfn == gfn && !sp->role.metaphysical) {
-			pgprintk("%s: gfn %lx role %x\n", __FUNCTION__, gfn,
+			pgprintk("%s: gfn %lx role %x\n", __func__, gfn,
 				 sp->role.word);
 			kvm_mmu_zap_page(kvm, sp);
 			r = 1;
@@ -857,7 +1001,7 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
 	struct kvm_mmu_page *sp;
 
 	while ((sp = kvm_mmu_lookup_page(kvm, gfn)) != NULL) {
-		pgprintk("%s: zap %lx %x\n", __FUNCTION__, gfn, sp->role.word);
+		pgprintk("%s: zap %lx %x\n", __func__, gfn, sp->role.word);
 		kvm_mmu_zap_page(kvm, sp);
 	}
 }
@@ -889,26 +1033,39 @@ struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva)
 static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 			 unsigned pt_access, unsigned pte_access,
 			 int user_fault, int write_fault, int dirty,
-			 int *ptwrite, gfn_t gfn, struct page *page)
+			 int *ptwrite, int largepage, gfn_t gfn,
+			 pfn_t pfn, bool speculative)
 {
 	u64 spte;
 	int was_rmapped = 0;
 	int was_writeble = is_writeble_pte(*shadow_pte);
-	hfn_t host_pfn = (*shadow_pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
 
 	pgprintk("%s: spte %llx access %x write_fault %d"
 		 " user_fault %d gfn %lx\n",
-		 __FUNCTION__, *shadow_pte, pt_access,
+		 __func__, *shadow_pte, pt_access,
 		 write_fault, user_fault, gfn);
 
 	if (is_rmap_pte(*shadow_pte)) {
-		if (host_pfn != page_to_pfn(page)) {
+		/*
+		 * If we overwrite a PTE page pointer with a 2MB PMD, unlink
+		 * the parent of the now unreachable PTE.
+		 */
+		if (largepage && !is_large_pte(*shadow_pte)) {
+			struct kvm_mmu_page *child;
+			u64 pte = *shadow_pte;
+
+			child = page_header(pte & PT64_BASE_ADDR_MASK);
+			mmu_page_remove_parent_pte(child, shadow_pte);
+		} else if (pfn != spte_to_pfn(*shadow_pte)) {
 			pgprintk("hfn old %lx new %lx\n",
-				 host_pfn, page_to_pfn(page));
+				 spte_to_pfn(*shadow_pte), pfn);
 			rmap_remove(vcpu->kvm, shadow_pte);
+		} else {
+			if (largepage)
+				was_rmapped = is_large_pte(*shadow_pte);
+			else
+				was_rmapped = 1;
 		}
-		else
-			was_rmapped = 1;
 	}
 
 	/*
@@ -917,6 +1074,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 	 * demand paging).
 	 */
 	spte = PT_PRESENT_MASK | PT_DIRTY_MASK;
+	if (!speculative)
+		pte_access |= PT_ACCESSED_MASK;
 	if (!dirty)
 		pte_access &= ~ACC_WRITE_MASK;
 	if (!(pte_access & ACC_EXEC_MASK))
@@ -925,15 +1084,10 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 	spte |= PT_PRESENT_MASK;
 	if (pte_access & ACC_USER_MASK)
 		spte |= PT_USER_MASK;
+	if (largepage)
+		spte |= PT_PAGE_SIZE_MASK;
 
-	if (is_error_page(page)) {
-		set_shadow_pte(shadow_pte,
-			       shadow_trap_nonpresent_pte | PT_SHADOW_IO_MARK);
-		kvm_release_page_clean(page);
-		return;
-	}
-
-	spte |= page_to_phys(page);
+	spte |= (u64)pfn << PAGE_SHIFT;
 
 	if ((pte_access & ACC_WRITE_MASK)
 	    || (write_fault && !is_write_protection(vcpu) && !user_fault)) {
@@ -946,9 +1100,10 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 		}
 
 		shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn);
-		if (shadow) {
+		if (shadow ||
+		   (largepage && has_wrprotected_page(vcpu->kvm, gfn))) {
 			pgprintk("%s: found shadow page for %lx, marking ro\n",
-				 __FUNCTION__, gfn);
+				 __func__, gfn);
 			pte_access &= ~ACC_WRITE_MASK;
 			if (is_writeble_pte(spte)) {
 				spte &= ~PT_WRITABLE_MASK;
@@ -964,18 +1119,25 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 	if (pte_access & ACC_WRITE_MASK)
 		mark_page_dirty(vcpu->kvm, gfn);
 
-	pgprintk("%s: setting spte %llx\n", __FUNCTION__, spte);
+	pgprintk("%s: setting spte %llx\n", __func__, spte);
+	pgprintk("instantiating %s PTE (%s) at %d (%llx) addr %llx\n",
+		 (spte&PT_PAGE_SIZE_MASK)? "2MB" : "4kB",
+		 (spte&PT_WRITABLE_MASK)?"RW":"R", gfn, spte, shadow_pte);
 	set_shadow_pte(shadow_pte, spte);
+	if (!was_rmapped && (spte & PT_PAGE_SIZE_MASK)
+	    && (spte & PT_PRESENT_MASK))
+		++vcpu->kvm->stat.lpages;
+
 	page_header_update_slot(vcpu->kvm, shadow_pte, gfn);
 	if (!was_rmapped) {
-		rmap_add(vcpu, shadow_pte, gfn);
+		rmap_add(vcpu, shadow_pte, gfn, largepage);
 		if (!is_rmap_pte(*shadow_pte))
-			kvm_release_page_clean(page);
+			kvm_release_pfn_clean(pfn);
 	} else {
 		if (was_writeble)
-			kvm_release_page_dirty(page);
+			kvm_release_pfn_dirty(pfn);
 		else
-			kvm_release_page_clean(page);
+			kvm_release_pfn_clean(pfn);
 	}
 	if (!ptwrite || !*ptwrite)
 		vcpu->arch.last_pte_updated = shadow_pte;
@@ -985,10 +1147,10 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
 {
 }
 
-static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write,
-			   gfn_t gfn, struct page *page)
+static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
+			   int largepage, gfn_t gfn, pfn_t pfn,
+			   int level)
 {
-	int level = PT32E_ROOT_LEVEL;
 	hpa_t table_addr = vcpu->arch.mmu.root_hpa;
 	int pt_write = 0;
 
@@ -1001,8 +1163,14 @@ static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write,
 
 		if (level == 1) {
 			mmu_set_spte(vcpu, &table[index], ACC_ALL, ACC_ALL,
-				     0, write, 1, &pt_write, gfn, page);
-			return pt_write || is_io_pte(table[index]);
+				     0, write, 1, &pt_write, 0, gfn, pfn, false);
+			return pt_write;
+		}
+
+		if (largepage && level == 2) {
+			mmu_set_spte(vcpu, &table[index], ACC_ALL, ACC_ALL,
+				     0, write, 1, &pt_write, 1, gfn, pfn, false);
+			return pt_write;
 		}
 
 		if (table[index] == shadow_trap_nonpresent_pte) {
@@ -1016,7 +1184,7 @@ static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write,
 						     1, ACC_ALL, &table[index]);
 			if (!new_table) {
 				pgprintk("nonpaging_map: ENOMEM\n");
-				kvm_release_page_clean(page);
+				kvm_release_pfn_clean(pfn);
 				return -ENOMEM;
 			}
 
@@ -1030,21 +1198,30 @@ static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write,
 static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
 {
 	int r;
-
-	struct page *page;
-
-	down_read(&vcpu->kvm->slots_lock);
+	int largepage = 0;
+	pfn_t pfn;
 
 	down_read(&current->mm->mmap_sem);
-	page = gfn_to_page(vcpu->kvm, gfn);
+	if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
+		gfn &= ~(KVM_PAGES_PER_HPAGE-1);
+		largepage = 1;
+	}
+
+	pfn = gfn_to_pfn(vcpu->kvm, gfn);
 	up_read(&current->mm->mmap_sem);
 
+	/* mmio */
+	if (is_error_pfn(pfn)) {
+		kvm_release_pfn_clean(pfn);
+		return 1;
+	}
+
 	spin_lock(&vcpu->kvm->mmu_lock);
 	kvm_mmu_free_some_pages(vcpu);
-	r = __nonpaging_map(vcpu, v, write, gfn, page);
+	r = __direct_map(vcpu, v, write, largepage, gfn, pfn,
+			 PT32E_ROOT_LEVEL);
 	spin_unlock(&vcpu->kvm->mmu_lock);
 
-	up_read(&vcpu->kvm->slots_lock);
 
 	return r;
 }
@@ -1073,6 +1250,8 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu)
 
 		sp = page_header(root);
 		--sp->root_count;
+		if (!sp->root_count && sp->role.invalid)
+			kvm_mmu_zap_page(vcpu->kvm, sp);
 		vcpu->arch.mmu.root_hpa = INVALID_PAGE;
 		spin_unlock(&vcpu->kvm->mmu_lock);
 		return;
@@ -1085,6 +1264,8 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu)
 			root &= PT64_BASE_ADDR_MASK;
 			sp = page_header(root);
 			--sp->root_count;
+			if (!sp->root_count && sp->role.invalid)
+				kvm_mmu_zap_page(vcpu->kvm, sp);
 		}
 		vcpu->arch.mmu.pae_root[i] = INVALID_PAGE;
 	}
@@ -1097,6 +1278,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
 	int i;
 	gfn_t root_gfn;
 	struct kvm_mmu_page *sp;
+	int metaphysical = 0;
 
 	root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT;
 
@@ -1105,14 +1287,20 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
 		hpa_t root = vcpu->arch.mmu.root_hpa;
 
 		ASSERT(!VALID_PAGE(root));
+		if (tdp_enabled)
+			metaphysical = 1;
 		sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
-				      PT64_ROOT_LEVEL, 0, ACC_ALL, NULL);
+				      PT64_ROOT_LEVEL, metaphysical,
+				      ACC_ALL, NULL);
 		root = __pa(sp->spt);
 		++sp->root_count;
 		vcpu->arch.mmu.root_hpa = root;
 		return;
 	}
 #endif
+	metaphysical = !is_paging(vcpu);
+	if (tdp_enabled)
+		metaphysical = 1;
 	for (i = 0; i < 4; ++i) {
 		hpa_t root = vcpu->arch.mmu.pae_root[i];
 
@@ -1126,7 +1314,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
 		} else if (vcpu->arch.mmu.root_level == 0)
 			root_gfn = 0;
 		sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
-				      PT32_ROOT_LEVEL, !is_paging(vcpu),
+				      PT32_ROOT_LEVEL, metaphysical,
 				      ACC_ALL, NULL);
 		root = __pa(sp->spt);
 		++sp->root_count;
@@ -1146,7 +1334,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
 	gfn_t gfn;
 	int r;
 
-	pgprintk("%s: gva %lx error %x\n", __FUNCTION__, gva, error_code);
+	pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
 	r = mmu_topup_memory_caches(vcpu);
 	if (r)
 		return r;
@@ -1160,6 +1348,41 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
 			     error_code & PFERR_WRITE_MASK, gfn);
 }
 
+static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
+				u32 error_code)
+{
+	pfn_t pfn;
+	int r;
+	int largepage = 0;
+	gfn_t gfn = gpa >> PAGE_SHIFT;
+
+	ASSERT(vcpu);
+	ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa));
+
+	r = mmu_topup_memory_caches(vcpu);
+	if (r)
+		return r;
+
+	down_read(&current->mm->mmap_sem);
+	if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
+		gfn &= ~(KVM_PAGES_PER_HPAGE-1);
+		largepage = 1;
+	}
+	pfn = gfn_to_pfn(vcpu->kvm, gfn);
+	up_read(&current->mm->mmap_sem);
+	if (is_error_pfn(pfn)) {
+		kvm_release_pfn_clean(pfn);
+		return 1;
+	}
+	spin_lock(&vcpu->kvm->mmu_lock);
+	kvm_mmu_free_some_pages(vcpu);
+	r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK,
+			 largepage, gfn, pfn, TDP_ROOT_LEVEL);
+	spin_unlock(&vcpu->kvm->mmu_lock);
+
+	return r;
+}
+
 static void nonpaging_free(struct kvm_vcpu *vcpu)
 {
 	mmu_free_roots(vcpu);
@@ -1188,7 +1411,7 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
 
 static void paging_new_cr3(struct kvm_vcpu *vcpu)
 {
-	pgprintk("%s: cr3 %lx\n", __FUNCTION__, vcpu->arch.cr3);
+	pgprintk("%s: cr3 %lx\n", __func__, vcpu->arch.cr3);
 	mmu_free_roots(vcpu);
 }
 
@@ -1253,7 +1476,35 @@ static int paging32E_init_context(struct kvm_vcpu *vcpu)
 	return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL);
 }
 
-static int init_kvm_mmu(struct kvm_vcpu *vcpu)
+static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
+{
+	struct kvm_mmu *context = &vcpu->arch.mmu;
+
+	context->new_cr3 = nonpaging_new_cr3;
+	context->page_fault = tdp_page_fault;
+	context->free = nonpaging_free;
+	context->prefetch_page = nonpaging_prefetch_page;
+	context->shadow_root_level = TDP_ROOT_LEVEL;
+	context->root_hpa = INVALID_PAGE;
+
+	if (!is_paging(vcpu)) {
+		context->gva_to_gpa = nonpaging_gva_to_gpa;
+		context->root_level = 0;
+	} else if (is_long_mode(vcpu)) {
+		context->gva_to_gpa = paging64_gva_to_gpa;
+		context->root_level = PT64_ROOT_LEVEL;
+	} else if (is_pae(vcpu)) {
+		context->gva_to_gpa = paging64_gva_to_gpa;
+		context->root_level = PT32E_ROOT_LEVEL;
+	} else {
+		context->gva_to_gpa = paging32_gva_to_gpa;
+		context->root_level = PT32_ROOT_LEVEL;
+	}
+
+	return 0;
+}
+
+static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
 {
 	ASSERT(vcpu);
 	ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
@@ -1268,6 +1519,16 @@ static int init_kvm_mmu(struct kvm_vcpu *vcpu)
 		return paging32_init_context(vcpu);
 }
 
+static int init_kvm_mmu(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.update_pte.pfn = bad_pfn;
+
+	if (tdp_enabled)
+		return init_kvm_tdp_mmu(vcpu);
+	else
+		return init_kvm_softmmu(vcpu);
+}
+
 static void destroy_kvm_mmu(struct kvm_vcpu *vcpu)
 {
 	ASSERT(vcpu);
@@ -1316,7 +1577,8 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu,
 
 	pte = *spte;
 	if (is_shadow_present_pte(pte)) {
-		if (sp->role.level == PT_PAGE_TABLE_LEVEL)
+		if (sp->role.level == PT_PAGE_TABLE_LEVEL ||
+		    is_large_pte(pte))
 			rmap_remove(vcpu->kvm, spte);
 		else {
 			child = page_header(pte & PT64_BASE_ADDR_MASK);
@@ -1324,24 +1586,26 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu,
 		}
 	}
 	set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+	if (is_large_pte(pte))
+		--vcpu->kvm->stat.lpages;
 }
 
 static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
 				  struct kvm_mmu_page *sp,
 				  u64 *spte,
-				  const void *new, int bytes,
-				  int offset_in_pte)
+				  const void *new)
 {
-	if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
+	if ((sp->role.level != PT_PAGE_TABLE_LEVEL)
+	    && !vcpu->arch.update_pte.largepage) {
 		++vcpu->kvm->stat.mmu_pde_zapped;
 		return;
 	}
 
 	++vcpu->kvm->stat.mmu_pte_updated;
 	if (sp->role.glevels == PT32_ROOT_LEVEL)
-		paging32_update_pte(vcpu, sp, spte, new, bytes, offset_in_pte);
+		paging32_update_pte(vcpu, sp, spte, new);
 	else
-		paging64_update_pte(vcpu, sp, spte, new, bytes, offset_in_pte);
+		paging64_update_pte(vcpu, sp, spte, new);
 }
 
 static bool need_remote_flush(u64 old, u64 new)
@@ -1378,7 +1642,9 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	gfn_t gfn;
 	int r;
 	u64 gpte = 0;
-	struct page *page;
+	pfn_t pfn;
+
+	vcpu->arch.update_pte.largepage = 0;
 
 	if (bytes != 4 && bytes != 8)
 		return;
@@ -1408,11 +1674,19 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
 
 	down_read(&current->mm->mmap_sem);
-	page = gfn_to_page(vcpu->kvm, gfn);
+	if (is_large_pte(gpte) && is_largepage_backed(vcpu, gfn)) {
+		gfn &= ~(KVM_PAGES_PER_HPAGE-1);
+		vcpu->arch.update_pte.largepage = 1;
+	}
+	pfn = gfn_to_pfn(vcpu->kvm, gfn);
 	up_read(&current->mm->mmap_sem);
 
+	if (is_error_pfn(pfn)) {
+		kvm_release_pfn_clean(pfn);
+		return;
+	}
 	vcpu->arch.update_pte.gfn = gfn;
-	vcpu->arch.update_pte.page = page;
+	vcpu->arch.update_pte.pfn = pfn;
 }
 
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
@@ -1423,7 +1697,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	struct hlist_node *node, *n;
 	struct hlist_head *bucket;
 	unsigned index;
-	u64 entry;
+	u64 entry, gentry;
 	u64 *spte;
 	unsigned offset = offset_in_page(gpa);
 	unsigned pte_size;
@@ -1433,8 +1707,9 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	int level;
 	int flooded = 0;
 	int npte;
+	int r;
 
-	pgprintk("%s: gpa %llx bytes %d\n", __FUNCTION__, gpa, bytes);
+	pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
 	mmu_guess_page_from_pte_write(vcpu, gpa, new, bytes);
 	spin_lock(&vcpu->kvm->mmu_lock);
 	kvm_mmu_free_some_pages(vcpu);
@@ -1450,7 +1725,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		vcpu->arch.last_pt_write_count = 1;
 		vcpu->arch.last_pte_updated = NULL;
 	}
-	index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+	index = kvm_page_table_hashfn(gfn);
 	bucket = &vcpu->kvm->arch.mmu_page_hash[index];
 	hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) {
 		if (sp->gfn != gfn || sp->role.metaphysical)
@@ -1496,20 +1771,29 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 				continue;
 		}
 		spte = &sp->spt[page_offset / sizeof(*spte)];
+		if ((gpa & (pte_size - 1)) || (bytes < pte_size)) {
+			gentry = 0;
+			r = kvm_read_guest_atomic(vcpu->kvm,
+						  gpa & ~(u64)(pte_size - 1),
+						  &gentry, pte_size);
+			new = (const void *)&gentry;
+			if (r < 0)
+				new = NULL;
+		}
 		while (npte--) {
 			entry = *spte;
 			mmu_pte_write_zap_pte(vcpu, sp, spte);
-			mmu_pte_write_new_pte(vcpu, sp, spte, new, bytes,
-					      page_offset & (pte_size - 1));
+			if (new)
+				mmu_pte_write_new_pte(vcpu, sp, spte, new);
 			mmu_pte_write_flush_tlb(vcpu, entry, *spte);
 			++spte;
 		}
 	}
 	kvm_mmu_audit(vcpu, "post pte write");
 	spin_unlock(&vcpu->kvm->mmu_lock);
-	if (vcpu->arch.update_pte.page) {
-		kvm_release_page_clean(vcpu->arch.update_pte.page);
-		vcpu->arch.update_pte.page = NULL;
+	if (!is_error_pfn(vcpu->arch.update_pte.pfn)) {
+		kvm_release_pfn_clean(vcpu->arch.update_pte.pfn);
+		vcpu->arch.update_pte.pfn = bad_pfn;
 	}
 }
 
@@ -1518,9 +1802,7 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
 	gpa_t gpa;
 	int r;
 
-	down_read(&vcpu->kvm->slots_lock);
 	gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva);
-	up_read(&vcpu->kvm->slots_lock);
 
 	spin_lock(&vcpu->kvm->mmu_lock);
 	r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
@@ -1577,6 +1859,12 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
 
+void kvm_enable_tdp(void)
+{
+	tdp_enabled = true;
+}
+EXPORT_SYMBOL_GPL(kvm_enable_tdp);
+
 static void free_mmu_pages(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu_page *sp;
@@ -1677,7 +1965,53 @@ void kvm_mmu_zap_all(struct kvm *kvm)
 	kvm_flush_remote_tlbs(kvm);
 }
 
-void kvm_mmu_module_exit(void)
+void kvm_mmu_remove_one_alloc_mmu_page(struct kvm *kvm)
+{
+	struct kvm_mmu_page *page;
+
+	page = container_of(kvm->arch.active_mmu_pages.prev,
+			    struct kvm_mmu_page, link);
+	kvm_mmu_zap_page(kvm, page);
+}
+
+static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
+{
+	struct kvm *kvm;
+	struct kvm *kvm_freed = NULL;
+	int cache_count = 0;
+
+	spin_lock(&kvm_lock);
+
+	list_for_each_entry(kvm, &vm_list, vm_list) {
+		int npages;
+
+		spin_lock(&kvm->mmu_lock);
+		npages = kvm->arch.n_alloc_mmu_pages -
+			 kvm->arch.n_free_mmu_pages;
+		cache_count += npages;
+		if (!kvm_freed && nr_to_scan > 0 && npages > 0) {
+			kvm_mmu_remove_one_alloc_mmu_page(kvm);
+			cache_count--;
+			kvm_freed = kvm;
+		}
+		nr_to_scan--;
+
+		spin_unlock(&kvm->mmu_lock);
+	}
+	if (kvm_freed)
+		list_move_tail(&kvm_freed->vm_list, &vm_list);
+
+	spin_unlock(&kvm_lock);
+
+	return cache_count;
+}
+
+static struct shrinker mmu_shrinker = {
+	.shrink = mmu_shrink,
+	.seeks = DEFAULT_SEEKS * 10,
+};
+
+void mmu_destroy_caches(void)
 {
 	if (pte_chain_cache)
 		kmem_cache_destroy(pte_chain_cache);
@@ -1687,6 +2021,12 @@ void kvm_mmu_module_exit(void)
 		kmem_cache_destroy(mmu_page_header_cache);
 }
 
+void kvm_mmu_module_exit(void)
+{
+	mmu_destroy_caches();
+	unregister_shrinker(&mmu_shrinker);
+}
+
 int kvm_mmu_module_init(void)
 {
 	pte_chain_cache = kmem_cache_create("kvm_pte_chain",
@@ -1706,10 +2046,12 @@ int kvm_mmu_module_init(void)
 	if (!mmu_page_header_cache)
 		goto nomem;
 
+	register_shrinker(&mmu_shrinker);
+
 	return 0;
 
 nomem:
-	kvm_mmu_module_exit();
+	mmu_destroy_caches();
 	return -ENOMEM;
 }
 
@@ -1732,6 +2074,127 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
 	return nr_mmu_pages;
 }
 
+static void *pv_mmu_peek_buffer(struct kvm_pv_mmu_op_buffer *buffer,
+				unsigned len)
+{
+	if (len > buffer->len)
+		return NULL;
+	return buffer->ptr;
+}
+
+static void *pv_mmu_read_buffer(struct kvm_pv_mmu_op_buffer *buffer,
+				unsigned len)
+{
+	void *ret;
+
+	ret = pv_mmu_peek_buffer(buffer, len);
+	if (!ret)
+		return ret;
+	buffer->ptr += len;
+	buffer->len -= len;
+	buffer->processed += len;
+	return ret;
+}
+
+static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu,
+			     gpa_t addr, gpa_t value)
+{
+	int bytes = 8;
+	int r;
+
+	if (!is_long_mode(vcpu) && !is_pae(vcpu))
+		bytes = 4;
+
+	r = mmu_topup_memory_caches(vcpu);
+	if (r)
+		return r;
+
+	if (!emulator_write_phys(vcpu, addr, &value, bytes))
+		return -EFAULT;
+
+	return 1;
+}
+
+static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu)
+{
+	kvm_x86_ops->tlb_flush(vcpu);
+	return 1;
+}
+
+static int kvm_pv_mmu_release_pt(struct kvm_vcpu *vcpu, gpa_t addr)
+{
+	spin_lock(&vcpu->kvm->mmu_lock);
+	mmu_unshadow(vcpu->kvm, addr >> PAGE_SHIFT);
+	spin_unlock(&vcpu->kvm->mmu_lock);
+	return 1;
+}
+
+static int kvm_pv_mmu_op_one(struct kvm_vcpu *vcpu,
+			     struct kvm_pv_mmu_op_buffer *buffer)
+{
+	struct kvm_mmu_op_header *header;
+
+	header = pv_mmu_peek_buffer(buffer, sizeof *header);
+	if (!header)
+		return 0;
+	switch (header->op) {
+	case KVM_MMU_OP_WRITE_PTE: {
+		struct kvm_mmu_op_write_pte *wpte;
+
+		wpte = pv_mmu_read_buffer(buffer, sizeof *wpte);
+		if (!wpte)
+			return 0;
+		return kvm_pv_mmu_write(vcpu, wpte->pte_phys,
+					wpte->pte_val);
+	}
+	case KVM_MMU_OP_FLUSH_TLB: {
+		struct kvm_mmu_op_flush_tlb *ftlb;
+
+		ftlb = pv_mmu_read_buffer(buffer, sizeof *ftlb);
+		if (!ftlb)
+			return 0;
+		return kvm_pv_mmu_flush_tlb(vcpu);
+	}
+	case KVM_MMU_OP_RELEASE_PT: {
+		struct kvm_mmu_op_release_pt *rpt;
+
+		rpt = pv_mmu_read_buffer(buffer, sizeof *rpt);
+		if (!rpt)
+			return 0;
+		return kvm_pv_mmu_release_pt(vcpu, rpt->pt_phys);
+	}
+	default: return 0;
+	}
+}
+
+int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
+		  gpa_t addr, unsigned long *ret)
+{
+	int r;
+	struct kvm_pv_mmu_op_buffer buffer;
+
+	buffer.ptr = buffer.buf;
+	buffer.len = min_t(unsigned long, bytes, sizeof buffer.buf);
+	buffer.processed = 0;
+
+	r = kvm_read_guest(vcpu->kvm, addr, buffer.buf, buffer.len);
+	if (r)
+		goto out;
+
+	while (buffer.len) {
+		r = kvm_pv_mmu_op_one(vcpu, &buffer);
+		if (r < 0)
+			goto out;
+		if (r == 0)
+			break;
+	}
+
+	r = 1;
+out:
+	*ret = buffer.processed;
+	return r;
+}
+
 #ifdef AUDIT
 
 static const char *audit_msg;
@@ -1768,8 +2231,7 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte,
 			audit_mappings_page(vcpu, ent, va, level - 1);
 		} else {
 			gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, va);
-			struct page *page = gpa_to_page(vcpu, gpa);
-			hpa_t hpa = page_to_phys(page);
+			hpa_t hpa = (hpa_t)gpa_to_pfn(vcpu, gpa) << PAGE_SHIFT;
 
 			if (is_shadow_present_pte(ent)
 			    && (ent & PT64_BASE_ADDR_MASK) != hpa)
@@ -1782,7 +2244,7 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte,
 				 && !is_error_hpa(hpa))
 				printk(KERN_ERR "audit: (%s) notrap shadow,"
 				       " valid guest gva %lx\n", audit_msg, va);
-			kvm_release_page_clean(page);
+			kvm_release_pfn_clean(pfn);
 
 		}
 	}
@@ -1867,7 +2329,7 @@ static void audit_rmap(struct kvm_vcpu *vcpu)
 
 	if (n_rmap != n_actual)
 		printk(KERN_ERR "%s: (%s) rmap %d actual %d\n",
-		       __FUNCTION__, audit_msg, n_rmap, n_actual);
+		       __func__, audit_msg, n_rmap, n_actual);
 }
 
 static void audit_write_protection(struct kvm_vcpu *vcpu)
@@ -1887,7 +2349,7 @@ static void audit_write_protection(struct kvm_vcpu *vcpu)
 		if (*rmapp)
 			printk(KERN_ERR "%s: (%s) shadow page has writable"
 			       " mappings: gfn %lx role %x\n",
-			       __FUNCTION__, audit_msg, sp->gfn,
+			       __func__, audit_msg, sp->gfn,
 			       sp->role.word);
 	}
 }
diff --git a/trunk/arch/x86/kvm/mmu.h b/trunk/arch/x86/kvm/mmu.h
index 1fce19ec7a23..e64e9f56a65e 100644
--- a/trunk/arch/x86/kvm/mmu.h
+++ b/trunk/arch/x86/kvm/mmu.h
@@ -3,6 +3,12 @@
 
 #include <linux/kvm_host.h>
 
+#ifdef CONFIG_X86_64
+#define TDP_ROOT_LEVEL PT64_ROOT_LEVEL
+#else
+#define TDP_ROOT_LEVEL PT32E_ROOT_LEVEL
+#endif
+
 static inline void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
 {
 	if (unlikely(vcpu->kvm->arch.n_free_mmu_pages < KVM_MIN_FREE_MMU_PAGES))
diff --git a/trunk/arch/x86/kvm/paging_tmpl.h b/trunk/arch/x86/kvm/paging_tmpl.h
index ecc0856268c4..156fe10288ae 100644
--- a/trunk/arch/x86/kvm/paging_tmpl.h
+++ b/trunk/arch/x86/kvm/paging_tmpl.h
@@ -130,7 +130,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker,
 	unsigned index, pt_access, pte_access;
 	gpa_t pte_gpa;
 
-	pgprintk("%s: addr %lx\n", __FUNCTION__, addr);
+	pgprintk("%s: addr %lx\n", __func__, addr);
 walk:
 	walker->level = vcpu->arch.mmu.root_level;
 	pte = vcpu->arch.cr3;
@@ -155,7 +155,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker,
 		pte_gpa += index * sizeof(pt_element_t);
 		walker->table_gfn[walker->level - 1] = table_gfn;
 		walker->pte_gpa[walker->level - 1] = pte_gpa;
-		pgprintk("%s: table_gfn[%d] %lx\n", __FUNCTION__,
+		pgprintk("%s: table_gfn[%d] %lx\n", __func__,
 			 walker->level - 1, table_gfn);
 
 		kvm_read_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte));
@@ -222,7 +222,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker,
 	walker->pt_access = pt_access;
 	walker->pte_access = pte_access;
 	pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
-		 __FUNCTION__, (u64)pte, pt_access, pte_access);
+		 __func__, (u64)pte, pt_access, pte_access);
 	return 1;
 
 not_present:
@@ -243,31 +243,30 @@ static int FNAME(walk_addr)(struct guest_walker *walker,
 }
 
 static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
-			      u64 *spte, const void *pte, int bytes,
-			      int offset_in_pte)
+			      u64 *spte, const void *pte)
 {
 	pt_element_t gpte;
 	unsigned pte_access;
-	struct page *npage;
+	pfn_t pfn;
+	int largepage = vcpu->arch.update_pte.largepage;
 
 	gpte = *(const pt_element_t *)pte;
 	if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) {
-		if (!offset_in_pte && !is_present_pte(gpte))
+		if (!is_present_pte(gpte))
 			set_shadow_pte(spte, shadow_notrap_nonpresent_pte);
 		return;
 	}
-	if (bytes < sizeof(pt_element_t))
-		return;
-	pgprintk("%s: gpte %llx spte %p\n", __FUNCTION__, (u64)gpte, spte);
+	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
 	pte_access = page->role.access & FNAME(gpte_access)(vcpu, gpte);
 	if (gpte_to_gfn(gpte) != vcpu->arch.update_pte.gfn)
 		return;
-	npage = vcpu->arch.update_pte.page;
-	if (!npage)
+	pfn = vcpu->arch.update_pte.pfn;
+	if (is_error_pfn(pfn))
 		return;
-	get_page(npage);
+	kvm_get_pfn(pfn);
 	mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0,
-		     gpte & PT_DIRTY_MASK, NULL, gpte_to_gfn(gpte), npage);
+		     gpte & PT_DIRTY_MASK, NULL, largepage, gpte_to_gfn(gpte),
+		     pfn, true);
 }
 
 /*
@@ -275,8 +274,8 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
  */
 static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			 struct guest_walker *walker,
-			 int user_fault, int write_fault, int *ptwrite,
-			 struct page *page)
+			 int user_fault, int write_fault, int largepage,
+			 int *ptwrite, pfn_t pfn)
 {
 	hpa_t shadow_addr;
 	int level;
@@ -304,11 +303,19 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 		shadow_ent = ((u64 *)__va(shadow_addr)) + index;
 		if (level == PT_PAGE_TABLE_LEVEL)
 			break;
-		if (is_shadow_present_pte(*shadow_ent)) {
+
+		if (largepage && level == PT_DIRECTORY_LEVEL)
+			break;
+
+		if (is_shadow_present_pte(*shadow_ent)
+		    && !is_large_pte(*shadow_ent)) {
 			shadow_addr = *shadow_ent & PT64_BASE_ADDR_MASK;
 			continue;
 		}
 
+		if (is_large_pte(*shadow_ent))
+			rmap_remove(vcpu->kvm, shadow_ent);
+
 		if (level - 1 == PT_PAGE_TABLE_LEVEL
 		    && walker->level == PT_DIRECTORY_LEVEL) {
 			metaphysical = 1;
@@ -329,7 +336,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 						  walker->pte_gpa[level - 2],
 						  &curr_pte, sizeof(curr_pte));
 			if (r || curr_pte != walker->ptes[level - 2]) {
-				kvm_release_page_clean(page);
+				kvm_release_pfn_clean(pfn);
 				return NULL;
 			}
 		}
@@ -342,7 +349,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 	mmu_set_spte(vcpu, shadow_ent, access, walker->pte_access & access,
 		     user_fault, write_fault,
 		     walker->ptes[walker->level-1] & PT_DIRTY_MASK,
-		     ptwrite, walker->gfn, page);
+		     ptwrite, largepage, walker->gfn, pfn, false);
 
 	return shadow_ent;
 }
@@ -371,16 +378,16 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 	u64 *shadow_pte;
 	int write_pt = 0;
 	int r;
-	struct page *page;
+	pfn_t pfn;
+	int largepage = 0;
 
-	pgprintk("%s: addr %lx err %x\n", __FUNCTION__, addr, error_code);
+	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
 	kvm_mmu_audit(vcpu, "pre page fault");
 
 	r = mmu_topup_memory_caches(vcpu);
 	if (r)
 		return r;
 
-	down_read(&vcpu->kvm->slots_lock);
 	/*
 	 * Look up the shadow pte for the faulting address.
 	 */
@@ -391,40 +398,45 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 	 * The page is not mapped by the guest.  Let the guest handle it.
 	 */
 	if (!r) {
-		pgprintk("%s: guest page fault\n", __FUNCTION__);
+		pgprintk("%s: guest page fault\n", __func__);
 		inject_page_fault(vcpu, addr, walker.error_code);
 		vcpu->arch.last_pt_write_count = 0; /* reset fork detector */
-		up_read(&vcpu->kvm->slots_lock);
 		return 0;
 	}
 
 	down_read(&current->mm->mmap_sem);
-	page = gfn_to_page(vcpu->kvm, walker.gfn);
+	if (walker.level == PT_DIRECTORY_LEVEL) {
+		gfn_t large_gfn;
+		large_gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE-1);
+		if (is_largepage_backed(vcpu, large_gfn)) {
+			walker.gfn = large_gfn;
+			largepage = 1;
+		}
+	}
+	pfn = gfn_to_pfn(vcpu->kvm, walker.gfn);
 	up_read(&current->mm->mmap_sem);
 
+	/* mmio */
+	if (is_error_pfn(pfn)) {
+		pgprintk("gfn %x is mmio\n", walker.gfn);
+		kvm_release_pfn_clean(pfn);
+		return 1;
+	}
+
 	spin_lock(&vcpu->kvm->mmu_lock);
 	kvm_mmu_free_some_pages(vcpu);
 	shadow_pte = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
-				  &write_pt, page);
-	pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __FUNCTION__,
+				  largepage, &write_pt, pfn);
+
+	pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __func__,
 		 shadow_pte, *shadow_pte, write_pt);
 
 	if (!write_pt)
 		vcpu->arch.last_pt_write_count = 0; /* reset fork detector */
 
-	/*
-	 * mmio: emulate if accessible, otherwise its a guest fault.
-	 */
-	if (shadow_pte && is_io_pte(*shadow_pte)) {
-		spin_unlock(&vcpu->kvm->mmu_lock);
-		up_read(&vcpu->kvm->slots_lock);
-		return 1;
-	}
-
 	++vcpu->stat.pf_fixed;
 	kvm_mmu_audit(vcpu, "post page fault (fixed)");
 	spin_unlock(&vcpu->kvm->mmu_lock);
-	up_read(&vcpu->kvm->slots_lock);
 
 	return write_pt;
 }
diff --git a/trunk/arch/x86/kvm/segment_descriptor.h b/trunk/arch/x86/kvm/segment_descriptor.h
deleted file mode 100644
index 56fc4c873389..000000000000
--- a/trunk/arch/x86/kvm/segment_descriptor.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef __SEGMENT_DESCRIPTOR_H
-#define __SEGMENT_DESCRIPTOR_H
-
-struct segment_descriptor {
-	u16 limit_low;
-	u16 base_low;
-	u8  base_mid;
-	u8  type : 4;
-	u8  system : 1;
-	u8  dpl : 2;
-	u8  present : 1;
-	u8  limit_high : 4;
-	u8  avl : 1;
-	u8  long_mode : 1;
-	u8  default_op : 1;
-	u8  granularity : 1;
-	u8  base_high;
-} __attribute__((packed));
-
-#ifdef CONFIG_X86_64
-/* LDT or TSS descriptor in the GDT. 16 bytes. */
-struct segment_descriptor_64 {
-	struct segment_descriptor s;
-	u32 base_higher;
-	u32 pad_zero;
-};
-
-#endif
-#endif
diff --git a/trunk/arch/x86/kvm/svm.c b/trunk/arch/x86/kvm/svm.c
index 1a582f1090e8..89e0be2c10d0 100644
--- a/trunk/arch/x86/kvm/svm.c
+++ b/trunk/arch/x86/kvm/svm.c
@@ -47,6 +47,18 @@ MODULE_LICENSE("GPL");
 #define SVM_FEATURE_LBRV (1 << 1)
 #define SVM_DEATURE_SVML (1 << 2)
 
+#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
+
+/* enable NPT for AMD64 and X86 with PAE */
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+static bool npt_enabled = true;
+#else
+static bool npt_enabled = false;
+#endif
+static int npt = 1;
+
+module_param(npt, int, S_IRUGO);
+
 static void kvm_reput_irq(struct vcpu_svm *svm);
 
 static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
@@ -54,8 +66,7 @@ static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
 	return container_of(vcpu, struct vcpu_svm, vcpu);
 }
 
-unsigned long iopm_base;
-unsigned long msrpm_base;
+static unsigned long iopm_base;
 
 struct kvm_ldttss_desc {
 	u16 limit0;
@@ -182,7 +193,7 @@ static inline void flush_guest_tlb(struct kvm_vcpu *vcpu)
 
 static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
-	if (!(efer & EFER_LMA))
+	if (!npt_enabled && !(efer & EFER_LMA))
 		efer &= ~EFER_LME;
 
 	to_svm(vcpu)->vmcb->save.efer = efer | MSR_EFER_SVME_MASK;
@@ -219,12 +230,12 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (!svm->next_rip) {
-		printk(KERN_DEBUG "%s: NOP\n", __FUNCTION__);
+		printk(KERN_DEBUG "%s: NOP\n", __func__);
 		return;
 	}
 	if (svm->next_rip - svm->vmcb->save.rip > MAX_INST_SIZE)
 		printk(KERN_ERR "%s: ip 0x%llx next 0x%llx\n",
-		       __FUNCTION__,
+		       __func__,
 		       svm->vmcb->save.rip,
 		       svm->next_rip);
 
@@ -279,11 +290,7 @@ static void svm_hardware_enable(void *garbage)
 
 	struct svm_cpu_data *svm_data;
 	uint64_t efer;
-#ifdef CONFIG_X86_64
-	struct desc_ptr gdt_descr;
-#else
 	struct desc_ptr gdt_descr;
-#endif
 	struct desc_struct *gdt;
 	int me = raw_smp_processor_id();
 
@@ -302,7 +309,6 @@ static void svm_hardware_enable(void *garbage)
 	svm_data->asid_generation = 1;
 	svm_data->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
 	svm_data->next_asid = svm_data->max_asid + 1;
-	svm_features = cpuid_edx(SVM_CPUID_FUNC);
 
 	asm volatile ("sgdt %0" : "=m"(gdt_descr));
 	gdt = (struct desc_struct *)gdt_descr.address;
@@ -361,12 +367,51 @@ static void set_msr_interception(u32 *msrpm, unsigned msr,
 	BUG();
 }
 
+static void svm_vcpu_init_msrpm(u32 *msrpm)
+{
+	memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
+
+#ifdef CONFIG_X86_64
+	set_msr_interception(msrpm, MSR_GS_BASE, 1, 1);
+	set_msr_interception(msrpm, MSR_FS_BASE, 1, 1);
+	set_msr_interception(msrpm, MSR_KERNEL_GS_BASE, 1, 1);
+	set_msr_interception(msrpm, MSR_LSTAR, 1, 1);
+	set_msr_interception(msrpm, MSR_CSTAR, 1, 1);
+	set_msr_interception(msrpm, MSR_SYSCALL_MASK, 1, 1);
+#endif
+	set_msr_interception(msrpm, MSR_K6_STAR, 1, 1);
+	set_msr_interception(msrpm, MSR_IA32_SYSENTER_CS, 1, 1);
+	set_msr_interception(msrpm, MSR_IA32_SYSENTER_ESP, 1, 1);
+	set_msr_interception(msrpm, MSR_IA32_SYSENTER_EIP, 1, 1);
+}
+
+static void svm_enable_lbrv(struct vcpu_svm *svm)
+{
+	u32 *msrpm = svm->msrpm;
+
+	svm->vmcb->control.lbr_ctl = 1;
+	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
+	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
+	set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
+	set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
+}
+
+static void svm_disable_lbrv(struct vcpu_svm *svm)
+{
+	u32 *msrpm = svm->msrpm;
+
+	svm->vmcb->control.lbr_ctl = 0;
+	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
+	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
+	set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
+	set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
+}
+
 static __init int svm_hardware_setup(void)
 {
 	int cpu;
 	struct page *iopm_pages;
-	struct page *msrpm_pages;
-	void *iopm_va, *msrpm_va;
+	void *iopm_va;
 	int r;
 
 	iopm_pages = alloc_pages(GFP_KERNEL, IOPM_ALLOC_ORDER);
@@ -379,41 +424,33 @@ static __init int svm_hardware_setup(void)
 	clear_bit(0x80, iopm_va); /* allow direct access to PC debug port */
 	iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT;
 
+	if (boot_cpu_has(X86_FEATURE_NX))
+		kvm_enable_efer_bits(EFER_NX);
 
-	msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
+	for_each_online_cpu(cpu) {
+		r = svm_cpu_init(cpu);
+		if (r)
+			goto err;
+	}
 
-	r = -ENOMEM;
-	if (!msrpm_pages)
-		goto err_1;
+	svm_features = cpuid_edx(SVM_CPUID_FUNC);
 
-	msrpm_va = page_address(msrpm_pages);
-	memset(msrpm_va, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
-	msrpm_base = page_to_pfn(msrpm_pages) << PAGE_SHIFT;
+	if (!svm_has(SVM_FEATURE_NPT))
+		npt_enabled = false;
 
-#ifdef CONFIG_X86_64
-	set_msr_interception(msrpm_va, MSR_GS_BASE, 1, 1);
-	set_msr_interception(msrpm_va, MSR_FS_BASE, 1, 1);
-	set_msr_interception(msrpm_va, MSR_KERNEL_GS_BASE, 1, 1);
-	set_msr_interception(msrpm_va, MSR_LSTAR, 1, 1);
-	set_msr_interception(msrpm_va, MSR_CSTAR, 1, 1);
-	set_msr_interception(msrpm_va, MSR_SYSCALL_MASK, 1, 1);
-#endif
-	set_msr_interception(msrpm_va, MSR_K6_STAR, 1, 1);
-	set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_CS, 1, 1);
-	set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_ESP, 1, 1);
-	set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_EIP, 1, 1);
+	if (npt_enabled && !npt) {
+		printk(KERN_INFO "kvm: Nested Paging disabled\n");
+		npt_enabled = false;
+	}
 
-	for_each_online_cpu(cpu) {
-		r = svm_cpu_init(cpu);
-		if (r)
-			goto err_2;
+	if (npt_enabled) {
+		printk(KERN_INFO "kvm: Nested Paging enabled\n");
+		kvm_enable_tdp();
 	}
+
 	return 0;
 
-err_2:
-	__free_pages(msrpm_pages, MSRPM_ALLOC_ORDER);
-	msrpm_base = 0;
-err_1:
+err:
 	__free_pages(iopm_pages, IOPM_ALLOC_ORDER);
 	iopm_base = 0;
 	return r;
@@ -421,9 +458,8 @@ static __init int svm_hardware_setup(void)
 
 static __exit void svm_hardware_unsetup(void)
 {
-	__free_pages(pfn_to_page(msrpm_base >> PAGE_SHIFT), MSRPM_ALLOC_ORDER);
 	__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
-	iopm_base = msrpm_base = 0;
+	iopm_base = 0;
 }
 
 static void init_seg(struct vmcb_seg *seg)
@@ -443,15 +479,14 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type)
 	seg->base = 0;
 }
 
-static void init_vmcb(struct vmcb *vmcb)
+static void init_vmcb(struct vcpu_svm *svm)
 {
-	struct vmcb_control_area *control = &vmcb->control;
-	struct vmcb_save_area *save = &vmcb->save;
+	struct vmcb_control_area *control = &svm->vmcb->control;
+	struct vmcb_save_area *save = &svm->vmcb->save;
 
 	control->intercept_cr_read = 	INTERCEPT_CR0_MASK |
 					INTERCEPT_CR3_MASK |
-					INTERCEPT_CR4_MASK |
-					INTERCEPT_CR8_MASK;
+					INTERCEPT_CR4_MASK;
 
 	control->intercept_cr_write = 	INTERCEPT_CR0_MASK |
 					INTERCEPT_CR3_MASK |
@@ -471,23 +506,13 @@ static void init_vmcb(struct vmcb *vmcb)
 					INTERCEPT_DR7_MASK;
 
 	control->intercept_exceptions = (1 << PF_VECTOR) |
-					(1 << UD_VECTOR);
+					(1 << UD_VECTOR) |
+					(1 << MC_VECTOR);
 
 
 	control->intercept = 	(1ULL << INTERCEPT_INTR) |
 				(1ULL << INTERCEPT_NMI) |
 				(1ULL << INTERCEPT_SMI) |
-		/*
-		 * selective cr0 intercept bug?
-		 *    	0:   0f 22 d8                mov    %eax,%cr3
-		 *	3:   0f 20 c0                mov    %cr0,%eax
-		 *	6:   0d 00 00 00 80          or     $0x80000000,%eax
-		 *	b:   0f 22 c0                mov    %eax,%cr0
-		 * set cr3 ->interception
-		 * get cr0 ->interception
-		 * set cr0 -> no interception
-		 */
-		/*              (1ULL << INTERCEPT_SELECTIVE_CR0) | */
 				(1ULL << INTERCEPT_CPUID) |
 				(1ULL << INTERCEPT_INVD) |
 				(1ULL << INTERCEPT_HLT) |
@@ -508,7 +533,7 @@ static void init_vmcb(struct vmcb *vmcb)
 				(1ULL << INTERCEPT_MWAIT);
 
 	control->iopm_base_pa = iopm_base;
-	control->msrpm_base_pa = msrpm_base;
+	control->msrpm_base_pa = __pa(svm->msrpm);
 	control->tsc_offset = 0;
 	control->int_ctl = V_INTR_MASKING_MASK;
 
@@ -550,13 +575,30 @@ static void init_vmcb(struct vmcb *vmcb)
 	save->cr0 = 0x00000010 | X86_CR0_PG | X86_CR0_WP;
 	save->cr4 = X86_CR4_PAE;
 	/* rdx = ?? */
+
+	if (npt_enabled) {
+		/* Setup VMCB for Nested Paging */
+		control->nested_ctl = 1;
+		control->intercept &= ~(1ULL << INTERCEPT_TASK_SWITCH);
+		control->intercept_exceptions &= ~(1 << PF_VECTOR);
+		control->intercept_cr_read &= ~(INTERCEPT_CR0_MASK|
+						INTERCEPT_CR3_MASK);
+		control->intercept_cr_write &= ~(INTERCEPT_CR0_MASK|
+						 INTERCEPT_CR3_MASK);
+		save->g_pat = 0x0007040600070406ULL;
+		/* enable caching because the QEMU Bios doesn't enable it */
+		save->cr0 = X86_CR0_ET;
+		save->cr3 = 0;
+		save->cr4 = 0;
+	}
+	force_new_asid(&svm->vcpu);
 }
 
 static int svm_vcpu_reset(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	init_vmcb(svm->vmcb);
+	init_vmcb(svm);
 
 	if (vcpu->vcpu_id != 0) {
 		svm->vmcb->save.rip = 0;
@@ -571,6 +613,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 {
 	struct vcpu_svm *svm;
 	struct page *page;
+	struct page *msrpm_pages;
 	int err;
 
 	svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
@@ -589,12 +632,19 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 		goto uninit;
 	}
 
+	err = -ENOMEM;
+	msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
+	if (!msrpm_pages)
+		goto uninit;
+	svm->msrpm = page_address(msrpm_pages);
+	svm_vcpu_init_msrpm(svm->msrpm);
+
 	svm->vmcb = page_address(page);
 	clear_page(svm->vmcb);
 	svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT;
 	svm->asid_generation = 0;
 	memset(svm->db_regs, 0, sizeof(svm->db_regs));
-	init_vmcb(svm->vmcb);
+	init_vmcb(svm);
 
 	fx_init(&svm->vcpu);
 	svm->vcpu.fpu_active = 1;
@@ -617,6 +667,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	__free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT));
+	__free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, svm);
 }
@@ -731,6 +782,13 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
 	var->unusable = !var->present;
 }
 
+static int svm_get_cpl(struct kvm_vcpu *vcpu)
+{
+	struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save;
+
+	return save->cpl;
+}
+
 static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -784,6 +842,9 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 		}
 	}
 #endif
+	if (npt_enabled)
+		goto set;
+
 	if ((vcpu->arch.cr0 & X86_CR0_TS) && !(cr0 & X86_CR0_TS)) {
 		svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
 		vcpu->fpu_active = 1;
@@ -791,18 +852,29 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 	vcpu->arch.cr0 = cr0;
 	cr0 |= X86_CR0_PG | X86_CR0_WP;
-	cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
 	if (!vcpu->fpu_active) {
 		svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR);
 		cr0 |= X86_CR0_TS;
 	}
+set:
+	/*
+	 * re-enable caching here because the QEMU bios
+	 * does not do it - this results in some delay at
+	 * reboot
+	 */
+	cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
 	svm->vmcb->save.cr0 = cr0;
 }
 
 static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-       vcpu->arch.cr4 = cr4;
-       to_svm(vcpu)->vmcb->save.cr4 = cr4 | X86_CR4_PAE;
+	unsigned long host_cr4_mce = read_cr4() & X86_CR4_MCE;
+
+	vcpu->arch.cr4 = cr4;
+	if (!npt_enabled)
+		cr4 |= X86_CR4_PAE;
+	cr4 |= host_cr4_mce;
+	to_svm(vcpu)->vmcb->save.cr4 = cr4;
 }
 
 static void svm_set_segment(struct kvm_vcpu *vcpu,
@@ -833,13 +905,6 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
 
 }
 
-/* FIXME:
-
-	svm(vcpu)->vmcb->control.int_ctl &= ~V_TPR_MASK;
-	svm(vcpu)->vmcb->control.int_ctl |= (sregs->cr8 & V_TPR_MASK);
-
-*/
-
 static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg)
 {
 	return -EOPNOTSUPP;
@@ -920,7 +985,7 @@ static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value,
 	}
 	default:
 		printk(KERN_DEBUG "%s: unexpected dr %u\n",
-		       __FUNCTION__, dr);
+		       __func__, dr);
 		*exception = UD_VECTOR;
 		return;
 	}
@@ -962,6 +1027,19 @@ static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
+static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+	/*
+	 * On an #MC intercept the MCE handler is not called automatically in
+	 * the host. So do it by hand here.
+	 */
+	asm volatile (
+		"int $0x12\n");
+	/* not sure if we ever come back to this point */
+
+	return 1;
+}
+
 static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 {
 	/*
@@ -969,7 +1047,7 @@ static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	 * so reinitialize it.
 	 */
 	clear_page(svm->vmcb);
-	init_vmcb(svm->vmcb);
+	init_vmcb(svm);
 
 	kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
 	return 0;
@@ -1033,9 +1111,18 @@ static int invalid_op_interception(struct vcpu_svm *svm,
 static int task_switch_interception(struct vcpu_svm *svm,
 				    struct kvm_run *kvm_run)
 {
-	pr_unimpl(&svm->vcpu, "%s: task switch is unsupported\n", __FUNCTION__);
-	kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
-	return 0;
+	u16 tss_selector;
+
+	tss_selector = (u16)svm->vmcb->control.exit_info_1;
+	if (svm->vmcb->control.exit_info_2 &
+	    (1ULL << SVM_EXITINFOSHIFT_TS_REASON_IRET))
+		return kvm_task_switch(&svm->vcpu, tss_selector,
+				       TASK_SWITCH_IRET);
+	if (svm->vmcb->control.exit_info_2 &
+	    (1ULL << SVM_EXITINFOSHIFT_TS_REASON_JMP))
+		return kvm_task_switch(&svm->vcpu, tss_selector,
+				       TASK_SWITCH_JMP);
+	return kvm_task_switch(&svm->vcpu, tss_selector, TASK_SWITCH_CALL);
 }
 
 static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
@@ -1049,7 +1136,7 @@ static int emulate_on_interception(struct vcpu_svm *svm,
 				   struct kvm_run *kvm_run)
 {
 	if (emulate_instruction(&svm->vcpu, NULL, 0, 0, 0) != EMULATE_DONE)
-		pr_unimpl(&svm->vcpu, "%s: failed\n", __FUNCTION__);
+		pr_unimpl(&svm->vcpu, "%s: failed\n", __func__);
 	return 1;
 }
 
@@ -1179,8 +1266,19 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 		svm->vmcb->save.sysenter_esp = data;
 		break;
 	case MSR_IA32_DEBUGCTLMSR:
-		pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
-				__FUNCTION__, data);
+		if (!svm_has(SVM_FEATURE_LBRV)) {
+			pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n",
+					__func__, data);
+			break;
+		}
+		if (data & DEBUGCTL_RESERVED_BITS)
+			return 1;
+
+		svm->vmcb->save.dbgctl = data;
+		if (data & (1ULL<<0))
+			svm_enable_lbrv(svm);
+		else
+			svm_disable_lbrv(svm);
 		break;
 	case MSR_K7_EVNTSEL0:
 	case MSR_K7_EVNTSEL1:
@@ -1265,6 +1363,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
 	[SVM_EXIT_EXCP_BASE + UD_VECTOR]	= ud_interception,
 	[SVM_EXIT_EXCP_BASE + PF_VECTOR] 	= pf_interception,
 	[SVM_EXIT_EXCP_BASE + NM_VECTOR] 	= nm_interception,
+	[SVM_EXIT_EXCP_BASE + MC_VECTOR] 	= mc_interception,
 	[SVM_EXIT_INTR] 			= nop_on_interception,
 	[SVM_EXIT_NMI]				= nop_on_interception,
 	[SVM_EXIT_SMI]				= nop_on_interception,
@@ -1290,14 +1389,34 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
 	[SVM_EXIT_WBINVD]                       = emulate_on_interception,
 	[SVM_EXIT_MONITOR]			= invalid_op_interception,
 	[SVM_EXIT_MWAIT]			= invalid_op_interception,
+	[SVM_EXIT_NPF]				= pf_interception,
 };
 
-
 static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u32 exit_code = svm->vmcb->control.exit_code;
 
+	if (npt_enabled) {
+		int mmu_reload = 0;
+		if ((vcpu->arch.cr0 ^ svm->vmcb->save.cr0) & X86_CR0_PG) {
+			svm_set_cr0(vcpu, svm->vmcb->save.cr0);
+			mmu_reload = 1;
+		}
+		vcpu->arch.cr0 = svm->vmcb->save.cr0;
+		vcpu->arch.cr3 = svm->vmcb->save.cr3;
+		if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
+			if (!load_pdptrs(vcpu, vcpu->arch.cr3)) {
+				kvm_inject_gp(vcpu, 0);
+				return 1;
+			}
+		}
+		if (mmu_reload) {
+			kvm_mmu_reset_context(vcpu);
+			kvm_mmu_load(vcpu);
+		}
+	}
+
 	kvm_reput_irq(svm);
 
 	if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) {
@@ -1308,10 +1427,11 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	}
 
 	if (is_external_interrupt(svm->vmcb->control.exit_int_info) &&
-	    exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR)
+	    exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR &&
+	    exit_code != SVM_EXIT_NPF)
 		printk(KERN_ERR "%s: unexpected exit_ini_info 0x%x "
 		       "exit_code 0x%x\n",
-		       __FUNCTION__, svm->vmcb->control.exit_int_info,
+		       __func__, svm->vmcb->control.exit_int_info,
 		       exit_code);
 
 	if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
@@ -1364,6 +1484,27 @@ static void svm_set_irq(struct kvm_vcpu *vcpu, int irq)
 	svm_inject_irq(svm, irq);
 }
 
+static void update_cr8_intercept(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	struct vmcb *vmcb = svm->vmcb;
+	int max_irr, tpr;
+
+	if (!irqchip_in_kernel(vcpu->kvm) || vcpu->arch.apic->vapic_addr)
+		return;
+
+	vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK;
+
+	max_irr = kvm_lapic_find_highest_irr(vcpu);
+	if (max_irr == -1)
+		return;
+
+	tpr = kvm_lapic_get_cr8(vcpu) << 4;
+
+	if (tpr >= (max_irr & 0xf0))
+		vmcb->control.intercept_cr_write |= INTERCEPT_CR8_MASK;
+}
+
 static void svm_intr_assist(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -1376,14 +1517,14 @@ static void svm_intr_assist(struct kvm_vcpu *vcpu)
 			      SVM_EVTINJ_VEC_MASK;
 		vmcb->control.exit_int_info = 0;
 		svm_inject_irq(svm, intr_vector);
-		return;
+		goto out;
 	}
 
 	if (vmcb->control.int_ctl & V_IRQ_MASK)
-		return;
+		goto out;
 
 	if (!kvm_cpu_has_interrupt(vcpu))
-		return;
+		goto out;
 
 	if (!(vmcb->save.rflags & X86_EFLAGS_IF) ||
 	    (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) ||
@@ -1391,12 +1532,14 @@ static void svm_intr_assist(struct kvm_vcpu *vcpu)
 		/* unable to deliver irq, set pending irq */
 		vmcb->control.intercept |= (1ULL << INTERCEPT_VINTR);
 		svm_inject_irq(svm, 0x0);
-		return;
+		goto out;
 	}
 	/* Okay, we can deliver the interrupt: grab it and update PIC state. */
 	intr_vector = kvm_cpu_get_interrupt(vcpu);
 	svm_inject_irq(svm, intr_vector);
 	kvm_timer_intr_post(vcpu, intr_vector);
+out:
+	update_cr8_intercept(vcpu);
 }
 
 static void kvm_reput_irq(struct vcpu_svm *svm)
@@ -1482,6 +1625,29 @@ static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu)
 {
 }
 
+static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR8_MASK)) {
+		int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK;
+		kvm_lapic_set_tpr(vcpu, cr8);
+	}
+}
+
+static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	u64 cr8;
+
+	if (!irqchip_in_kernel(vcpu->kvm))
+		return;
+
+	cr8 = kvm_get_cr8(vcpu);
+	svm->vmcb->control.int_ctl &= ~V_TPR_MASK;
+	svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK;
+}
+
 static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -1491,6 +1657,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	pre_svm_run(svm);
 
+	sync_lapic_to_cr8(vcpu);
+
 	save_host_msrs(vcpu);
 	fs_selector = read_fs();
 	gs_selector = read_gs();
@@ -1499,6 +1667,9 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	svm->host_dr6 = read_dr6();
 	svm->host_dr7 = read_dr7();
 	svm->vmcb->save.cr2 = vcpu->arch.cr2;
+	/* required for live migration with NPT */
+	if (npt_enabled)
+		svm->vmcb->save.cr3 = vcpu->arch.cr3;
 
 	if (svm->vmcb->save.dr7 & 0xff) {
 		write_dr7(0);
@@ -1635,6 +1806,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	stgi();
 
+	sync_cr8_to_lapic(vcpu);
+
 	svm->next_rip = 0;
 }
 
@@ -1642,6 +1815,12 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	if (npt_enabled) {
+		svm->vmcb->control.nested_cr3 = root;
+		force_new_asid(vcpu);
+		return;
+	}
+
 	svm->vmcb->save.cr3 = root;
 	force_new_asid(vcpu);
 
@@ -1709,6 +1888,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.get_segment_base = svm_get_segment_base,
 	.get_segment = svm_get_segment,
 	.set_segment = svm_set_segment,
+	.get_cpl = svm_get_cpl,
 	.get_cs_db_l_bits = kvm_get_cs_db_l_bits,
 	.decache_cr4_guest_bits = svm_decache_cr4_guest_bits,
 	.set_cr0 = svm_set_cr0,
diff --git a/trunk/arch/x86/kvm/svm.h b/trunk/arch/x86/kvm/svm.h
index 5fd50491b555..1b8afa78e869 100644
--- a/trunk/arch/x86/kvm/svm.h
+++ b/trunk/arch/x86/kvm/svm.h
@@ -238,6 +238,9 @@ struct __attribute__ ((__packed__)) vmcb {
 #define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID
 #define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR
 
+#define SVM_EXITINFOSHIFT_TS_REASON_IRET 36
+#define SVM_EXITINFOSHIFT_TS_REASON_JMP 38
+
 #define	SVM_EXIT_READ_CR0 	0x000
 #define	SVM_EXIT_READ_CR3 	0x003
 #define	SVM_EXIT_READ_CR4 	0x004
diff --git a/trunk/arch/x86/kvm/tss.h b/trunk/arch/x86/kvm/tss.h
new file mode 100644
index 000000000000..622aa10f692f
--- /dev/null
+++ b/trunk/arch/x86/kvm/tss.h
@@ -0,0 +1,59 @@
+#ifndef __TSS_SEGMENT_H
+#define __TSS_SEGMENT_H
+
+struct tss_segment_32 {
+	u32 prev_task_link;
+	u32 esp0;
+	u32 ss0;
+	u32 esp1;
+	u32 ss1;
+	u32 esp2;
+	u32 ss2;
+	u32 cr3;
+	u32 eip;
+	u32 eflags;
+	u32 eax;
+	u32 ecx;
+	u32 edx;
+	u32 ebx;
+	u32 esp;
+	u32 ebp;
+	u32 esi;
+	u32 edi;
+	u32 es;
+	u32 cs;
+	u32 ss;
+	u32 ds;
+	u32 fs;
+	u32 gs;
+	u32 ldt_selector;
+	u16 t;
+	u16 io_map;
+};
+
+struct tss_segment_16 {
+	u16 prev_task_link;
+	u16 sp0;
+	u16 ss0;
+	u16 sp1;
+	u16 ss1;
+	u16 sp2;
+	u16 ss2;
+	u16 ip;
+	u16 flag;
+	u16 ax;
+	u16 cx;
+	u16 dx;
+	u16 bx;
+	u16 sp;
+	u16 bp;
+	u16 si;
+	u16 di;
+	u16 es;
+	u16 cs;
+	u16 ss;
+	u16 ds;
+	u16 ldt;
+};
+
+#endif
diff --git a/trunk/arch/x86/kvm/vmx.c b/trunk/arch/x86/kvm/vmx.c
index 8e1462880d1f..8e5d6645b90d 100644
--- a/trunk/arch/x86/kvm/vmx.c
+++ b/trunk/arch/x86/kvm/vmx.c
@@ -17,7 +17,6 @@
 
 #include "irq.h"
 #include "vmx.h"
-#include "segment_descriptor.h"
 #include "mmu.h"
 
 #include <linux/kvm_host.h>
@@ -37,6 +36,12 @@ MODULE_LICENSE("GPL");
 static int bypass_guest_pf = 1;
 module_param(bypass_guest_pf, bool, 0);
 
+static int enable_vpid = 1;
+module_param(enable_vpid, bool, 0);
+
+static int flexpriority_enabled = 1;
+module_param(flexpriority_enabled, bool, 0);
+
 struct vmcs {
 	u32 revision_id;
 	u32 abort;
@@ -71,6 +76,7 @@ struct vcpu_vmx {
 			unsigned rip;
 		} irq;
 	} rmode;
+	int vpid;
 };
 
 static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
@@ -85,6 +91,10 @@ static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
 
 static struct page *vmx_io_bitmap_a;
 static struct page *vmx_io_bitmap_b;
+static struct page *vmx_msr_bitmap;
+
+static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
+static DEFINE_SPINLOCK(vmx_vpid_lock);
 
 static struct vmcs_config {
 	int size;
@@ -176,6 +186,11 @@ static inline int is_external_interrupt(u32 intr_info)
 		== (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
 }
 
+static inline int cpu_has_vmx_msr_bitmap(void)
+{
+	return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS);
+}
+
 static inline int cpu_has_vmx_tpr_shadow(void)
 {
 	return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW);
@@ -194,8 +209,9 @@ static inline int cpu_has_secondary_exec_ctrls(void)
 
 static inline bool cpu_has_vmx_virtualize_apic_accesses(void)
 {
-	return (vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
+	return flexpriority_enabled
+		&& (vmcs_config.cpu_based_2nd_exec_ctrl &
+		    SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
 }
 
 static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
@@ -204,6 +220,12 @@ static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
 		(irqchip_in_kernel(kvm)));
 }
 
+static inline int cpu_has_vmx_vpid(void)
+{
+	return (vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_ENABLE_VPID);
+}
+
 static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
 {
 	int i;
@@ -214,6 +236,20 @@ static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
 	return -1;
 }
 
+static inline void __invvpid(int ext, u16 vpid, gva_t gva)
+{
+    struct {
+	u64 vpid : 16;
+	u64 rsvd : 48;
+	u64 gva;
+    } operand = { vpid, 0, gva };
+
+    asm volatile (ASM_VMX_INVVPID
+		  /* CF==1 or ZF==1 --> rc = -1 */
+		  "; ja 1f ; ud2 ; 1:"
+		  : : "a"(&operand), "c"(ext) : "cc", "memory");
+}
+
 static struct kvm_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
 {
 	int i;
@@ -257,6 +293,14 @@ static void vcpu_clear(struct vcpu_vmx *vmx)
 	vmx->launched = 0;
 }
 
+static inline void vpid_sync_vcpu_all(struct vcpu_vmx *vmx)
+{
+	if (vmx->vpid == 0)
+		return;
+
+	__invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0);
+}
+
 static unsigned long vmcs_readl(unsigned long field)
 {
 	unsigned long value;
@@ -353,7 +397,7 @@ static void reload_tss(void)
 	 * VT restores TR but not its size.  Useless.
 	 */
 	struct descriptor_table gdt;
-	struct segment_descriptor *descs;
+	struct desc_struct *descs;
 
 	get_gdt(&gdt);
 	descs = (void *)gdt.base;
@@ -485,11 +529,12 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u64 phys_addr = __pa(vmx->vmcs);
-	u64 tsc_this, delta;
+	u64 tsc_this, delta, new_offset;
 
 	if (vcpu->cpu != cpu) {
 		vcpu_clear(vmx);
 		kvm_migrate_apic_timer(vcpu);
+		vpid_sync_vcpu_all(vmx);
 	}
 
 	if (per_cpu(current_vmcs, cpu) != vmx->vmcs) {
@@ -524,8 +569,11 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		 * Make sure the time stamp counter is monotonous.
 		 */
 		rdtscll(tsc_this);
-		delta = vcpu->arch.host_tsc - tsc_this;
-		vmcs_write64(TSC_OFFSET, vmcs_read64(TSC_OFFSET) + delta);
+		if (tsc_this < vcpu->arch.host_tsc) {
+			delta = vcpu->arch.host_tsc - tsc_this;
+			new_offset = vmcs_read64(TSC_OFFSET) + delta;
+			vmcs_write64(TSC_OFFSET, new_offset);
+		}
 	}
 }
 
@@ -596,7 +644,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 {
 	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
 		     nr | INTR_TYPE_EXCEPTION
-		     | (has_error_code ? INTR_INFO_DELIEVER_CODE_MASK : 0)
+		     | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0)
 		     | INTR_INFO_VALID_MASK);
 	if (has_error_code)
 		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
@@ -959,6 +1007,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 	      CPU_BASED_MOV_DR_EXITING |
 	      CPU_BASED_USE_TSC_OFFSETING;
 	opt = CPU_BASED_TPR_SHADOW |
+	      CPU_BASED_USE_MSR_BITMAPS |
 	      CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
 	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS,
 				&_cpu_based_exec_control) < 0)
@@ -971,7 +1020,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 	if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) {
 		min = 0;
 		opt = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
-			SECONDARY_EXEC_WBINVD_EXITING;
+			SECONDARY_EXEC_WBINVD_EXITING |
+			SECONDARY_EXEC_ENABLE_VPID;
 		if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS2,
 					&_cpu_based_2nd_exec_control) < 0)
 			return -EIO;
@@ -1080,6 +1130,10 @@ static __init int hardware_setup(void)
 {
 	if (setup_vmcs_config(&vmcs_config) < 0)
 		return -EIO;
+
+	if (boot_cpu_has(X86_FEATURE_NX))
+		kvm_enable_efer_bits(EFER_NX);
+
 	return alloc_kvm_area();
 }
 
@@ -1214,7 +1268,7 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
 	guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES);
 	if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) {
 		printk(KERN_DEBUG "%s: tss fixup for long mode. \n",
-		       __FUNCTION__);
+		       __func__);
 		vmcs_write32(GUEST_TR_AR_BYTES,
 			     (guest_tr_ar & ~AR_TYPE_MASK)
 			     | AR_TYPE_BUSY_64_TSS);
@@ -1239,6 +1293,11 @@ static void exit_lmode(struct kvm_vcpu *vcpu)
 
 #endif
 
+static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
+{
+	vpid_sync_vcpu_all(to_vmx(vcpu));
+}
+
 static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.cr4 &= KVM_GUEST_CR4_MASK;
@@ -1275,6 +1334,7 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
+	vmx_flush_tlb(vcpu);
 	vmcs_writel(GUEST_CR3, cr3);
 	if (vcpu->arch.cr0 & X86_CR0_PE)
 		vmx_fpu_deactivate(vcpu);
@@ -1288,14 +1348,14 @@ static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	vcpu->arch.cr4 = cr4;
 }
 
-#ifdef CONFIG_X86_64
-
 static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
 
 	vcpu->arch.shadow_efer = efer;
+	if (!msr)
+		return;
 	if (efer & EFER_LMA) {
 		vmcs_write32(VM_ENTRY_CONTROLS,
 				     vmcs_read32(VM_ENTRY_CONTROLS) |
@@ -1312,8 +1372,6 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	setup_msrs(vmx);
 }
 
-#endif
-
 static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
 {
 	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
@@ -1344,6 +1402,20 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
 	var->unusable = (ar >> 16) & 1;
 }
 
+static int vmx_get_cpl(struct kvm_vcpu *vcpu)
+{
+	struct kvm_segment kvm_seg;
+
+	if (!(vcpu->arch.cr0 & X86_CR0_PE)) /* if real mode */
+		return 0;
+
+	if (vmx_get_rflags(vcpu) & X86_EFLAGS_VM) /* if virtual 8086 */
+		return 3;
+
+	vmx_get_segment(vcpu, &kvm_seg, VCPU_SREG_CS);
+	return kvm_seg.selector & 3;
+}
+
 static u32 vmx_segment_access_rights(struct kvm_segment *var)
 {
 	u32 ar;
@@ -1433,7 +1505,6 @@ static int init_rmode_tss(struct kvm *kvm)
 	int ret = 0;
 	int r;
 
-	down_read(&kvm->slots_lock);
 	r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
 	if (r < 0)
 		goto out;
@@ -1456,7 +1527,6 @@ static int init_rmode_tss(struct kvm *kvm)
 
 	ret = 1;
 out:
-	up_read(&kvm->slots_lock);
 	return ret;
 }
 
@@ -1494,6 +1564,46 @@ static int alloc_apic_access_page(struct kvm *kvm)
 	return r;
 }
 
+static void allocate_vpid(struct vcpu_vmx *vmx)
+{
+	int vpid;
+
+	vmx->vpid = 0;
+	if (!enable_vpid || !cpu_has_vmx_vpid())
+		return;
+	spin_lock(&vmx_vpid_lock);
+	vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
+	if (vpid < VMX_NR_VPIDS) {
+		vmx->vpid = vpid;
+		__set_bit(vpid, vmx_vpid_bitmap);
+	}
+	spin_unlock(&vmx_vpid_lock);
+}
+
+void vmx_disable_intercept_for_msr(struct page *msr_bitmap, u32 msr)
+{
+	void *va;
+
+	if (!cpu_has_vmx_msr_bitmap())
+		return;
+
+	/*
+	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
+	 * have the write-low and read-high bitmap offsets the wrong way round.
+	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
+	 */
+	va = kmap(msr_bitmap);
+	if (msr <= 0x1fff) {
+		__clear_bit(msr, va + 0x000); /* read-low */
+		__clear_bit(msr, va + 0x800); /* write-low */
+	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+		msr &= 0x1fff;
+		__clear_bit(msr, va + 0x400); /* read-high */
+		__clear_bit(msr, va + 0xc00); /* write-high */
+	}
+	kunmap(msr_bitmap);
+}
+
 /*
  * Sets up the vmcs for emulated real mode.
  */
@@ -1511,6 +1621,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	vmcs_write64(IO_BITMAP_A, page_to_phys(vmx_io_bitmap_a));
 	vmcs_write64(IO_BITMAP_B, page_to_phys(vmx_io_bitmap_b));
 
+	if (cpu_has_vmx_msr_bitmap())
+		vmcs_write64(MSR_BITMAP, page_to_phys(vmx_msr_bitmap));
+
 	vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */
 
 	/* Control */
@@ -1532,6 +1645,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		if (!vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))
 			exec_control &=
 				~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+		if (vmx->vpid == 0)
+			exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
 	}
 
@@ -1613,6 +1728,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	u64 msr;
 	int ret;
 
+	down_read(&vcpu->kvm->slots_lock);
 	if (!init_rmode_tss(vmx->vcpu.kvm)) {
 		ret = -ENOMEM;
 		goto out;
@@ -1621,7 +1737,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	vmx->vcpu.arch.rmode.active = 0;
 
 	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
-	set_cr8(&vmx->vcpu, 0);
+	kvm_set_cr8(&vmx->vcpu, 0);
 	msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
 	if (vmx->vcpu.vcpu_id == 0)
 		msr |= MSR_IA32_APICBASE_BSP;
@@ -1704,18 +1820,22 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 		vmcs_write64(APIC_ACCESS_ADDR,
 			     page_to_phys(vmx->vcpu.kvm->arch.apic_access_page));
 
+	if (vmx->vpid != 0)
+		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
+
 	vmx->vcpu.arch.cr0 = 0x60000010;
 	vmx_set_cr0(&vmx->vcpu, vmx->vcpu.arch.cr0); /* enter rmode */
 	vmx_set_cr4(&vmx->vcpu, 0);
-#ifdef CONFIG_X86_64
 	vmx_set_efer(&vmx->vcpu, 0);
-#endif
 	vmx_fpu_activate(&vmx->vcpu);
 	update_exception_bitmap(&vmx->vcpu);
 
-	return 0;
+	vpid_sync_vcpu_all(vmx);
+
+	ret = 0;
 
 out:
+	up_read(&vcpu->kvm->slots_lock);
 	return ret;
 }
 
@@ -1723,6 +1843,8 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	KVMTRACE_1D(INJ_VIRQ, vcpu, (u32)irq, handler);
+
 	if (vcpu->arch.rmode.active) {
 		vmx->rmode.irq.pending = true;
 		vmx->rmode.irq.vector = irq;
@@ -1844,7 +1966,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if ((vect_info & VECTORING_INFO_VALID_MASK) &&
 						!is_page_fault(intr_info))
 		printk(KERN_ERR "%s: unexpected, vectoring info 0x%x "
-		       "intr info 0x%x\n", __FUNCTION__, vect_info, intr_info);
+		       "intr info 0x%x\n", __func__, vect_info, intr_info);
 
 	if (!irqchip_in_kernel(vcpu->kvm) && is_external_interrupt(vect_info)) {
 		int irq = vect_info & VECTORING_INFO_VECTOR_MASK;
@@ -1869,10 +1991,12 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	error_code = 0;
 	rip = vmcs_readl(GUEST_RIP);
-	if (intr_info & INTR_INFO_DELIEVER_CODE_MASK)
+	if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
 		error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
 	if (is_page_fault(intr_info)) {
 		cr2 = vmcs_readl(EXIT_QUALIFICATION);
+		KVMTRACE_3D(PAGE_FAULT, vcpu, error_code, (u32)cr2,
+			    (u32)((u64)cr2 >> 32), handler);
 		return kvm_mmu_page_fault(vcpu, cr2, error_code);
 	}
 
@@ -1901,6 +2025,7 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu,
 				     struct kvm_run *kvm_run)
 {
 	++vcpu->stat.irq_exits;
+	KVMTRACE_1D(INTR, vcpu, vmcs_read32(VM_EXIT_INTR_INFO), handler);
 	return 1;
 }
 
@@ -1958,25 +2083,27 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	reg = (exit_qualification >> 8) & 15;
 	switch ((exit_qualification >> 4) & 3) {
 	case 0: /* mov to cr */
+		KVMTRACE_3D(CR_WRITE, vcpu, (u32)cr, (u32)vcpu->arch.regs[reg],
+			    (u32)((u64)vcpu->arch.regs[reg] >> 32), handler);
 		switch (cr) {
 		case 0:
 			vcpu_load_rsp_rip(vcpu);
-			set_cr0(vcpu, vcpu->arch.regs[reg]);
+			kvm_set_cr0(vcpu, vcpu->arch.regs[reg]);
 			skip_emulated_instruction(vcpu);
 			return 1;
 		case 3:
 			vcpu_load_rsp_rip(vcpu);
-			set_cr3(vcpu, vcpu->arch.regs[reg]);
+			kvm_set_cr3(vcpu, vcpu->arch.regs[reg]);
 			skip_emulated_instruction(vcpu);
 			return 1;
 		case 4:
 			vcpu_load_rsp_rip(vcpu);
-			set_cr4(vcpu, vcpu->arch.regs[reg]);
+			kvm_set_cr4(vcpu, vcpu->arch.regs[reg]);
 			skip_emulated_instruction(vcpu);
 			return 1;
 		case 8:
 			vcpu_load_rsp_rip(vcpu);
-			set_cr8(vcpu, vcpu->arch.regs[reg]);
+			kvm_set_cr8(vcpu, vcpu->arch.regs[reg]);
 			skip_emulated_instruction(vcpu);
 			if (irqchip_in_kernel(vcpu->kvm))
 				return 1;
@@ -1990,6 +2117,7 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		vcpu->arch.cr0 &= ~X86_CR0_TS;
 		vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
 		vmx_fpu_activate(vcpu);
+		KVMTRACE_0D(CLTS, vcpu, handler);
 		skip_emulated_instruction(vcpu);
 		return 1;
 	case 1: /*mov from cr*/
@@ -1998,18 +2126,24 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 			vcpu_load_rsp_rip(vcpu);
 			vcpu->arch.regs[reg] = vcpu->arch.cr3;
 			vcpu_put_rsp_rip(vcpu);
+			KVMTRACE_3D(CR_READ, vcpu, (u32)cr,
+				    (u32)vcpu->arch.regs[reg],
+				    (u32)((u64)vcpu->arch.regs[reg] >> 32),
+				    handler);
 			skip_emulated_instruction(vcpu);
 			return 1;
 		case 8:
 			vcpu_load_rsp_rip(vcpu);
-			vcpu->arch.regs[reg] = get_cr8(vcpu);
+			vcpu->arch.regs[reg] = kvm_get_cr8(vcpu);
 			vcpu_put_rsp_rip(vcpu);
+			KVMTRACE_2D(CR_READ, vcpu, (u32)cr,
+				    (u32)vcpu->arch.regs[reg], handler);
 			skip_emulated_instruction(vcpu);
 			return 1;
 		}
 		break;
 	case 3: /* lmsw */
-		lmsw(vcpu, (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f);
+		kvm_lmsw(vcpu, (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f);
 
 		skip_emulated_instruction(vcpu);
 		return 1;
@@ -2049,6 +2183,7 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 			val = 0;
 		}
 		vcpu->arch.regs[reg] = val;
+		KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler);
 	} else {
 		/* mov to dr */
 	}
@@ -2073,6 +2208,9 @@ static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		return 1;
 	}
 
+	KVMTRACE_3D(MSR_READ, vcpu, ecx, (u32)data, (u32)(data >> 32),
+		    handler);
+
 	/* FIXME: handling of bits 32:63 of rax, rdx */
 	vcpu->arch.regs[VCPU_REGS_RAX] = data & -1u;
 	vcpu->arch.regs[VCPU_REGS_RDX] = (data >> 32) & -1u;
@@ -2086,6 +2224,9 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u)
 		| ((u64)(vcpu->arch.regs[VCPU_REGS_RDX] & -1u) << 32);
 
+	KVMTRACE_3D(MSR_WRITE, vcpu, ecx, (u32)data, (u32)(data >> 32),
+		    handler);
+
 	if (vmx_set_msr(vcpu, ecx, data) != 0) {
 		kvm_inject_gp(vcpu, 0);
 		return 1;
@@ -2110,6 +2251,9 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu,
 	cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
 	cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
 	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+
+	KVMTRACE_0D(PEND_INTR, vcpu, handler);
+
 	/*
 	 * If the user space waits to inject interrupts, exit as soon as
 	 * possible
@@ -2152,6 +2296,8 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
 	offset = exit_qualification & 0xffful;
 
+	KVMTRACE_1D(APIC_ACCESS, vcpu, (u32)offset, handler);
+
 	er = emulate_instruction(vcpu, kvm_run, 0, 0, 0);
 
 	if (er !=  EMULATE_DONE) {
@@ -2163,6 +2309,20 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	return 1;
 }
 
+static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	unsigned long exit_qualification;
+	u16 tss_selector;
+	int reason;
+
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+	reason = (u32)exit_qualification >> 30;
+	tss_selector = exit_qualification;
+
+	return kvm_task_switch(vcpu, tss_selector, reason);
+}
+
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -2185,6 +2345,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu,
 	[EXIT_REASON_TPR_BELOW_THRESHOLD]     = handle_tpr_below_threshold,
 	[EXIT_REASON_APIC_ACCESS]             = handle_apic_access,
 	[EXIT_REASON_WBINVD]                  = handle_wbinvd,
+	[EXIT_REASON_TASK_SWITCH]             = handle_task_switch,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -2200,6 +2361,9 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 vectoring_info = vmx->idt_vectoring_info;
 
+	KVMTRACE_3D(VMEXIT, vcpu, exit_reason, (u32)vmcs_readl(GUEST_RIP),
+		    (u32)((u64)vmcs_readl(GUEST_RIP) >> 32), entryexit);
+
 	if (unlikely(vmx->fail)) {
 		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
 		kvm_run->fail_entry.hardware_entry_failure_reason
@@ -2210,7 +2374,7 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
 				exit_reason != EXIT_REASON_EXCEPTION_NMI)
 		printk(KERN_WARNING "%s: unexpected, valid vectoring info and "
-		       "exit reason is 0x%x\n", __FUNCTION__, exit_reason);
+		       "exit reason is 0x%x\n", __func__, exit_reason);
 	if (exit_reason < kvm_vmx_max_exit_handlers
 	    && kvm_vmx_exit_handlers[exit_reason])
 		return kvm_vmx_exit_handlers[exit_reason](vcpu, kvm_run);
@@ -2221,10 +2385,6 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
-{
-}
-
 static void update_tpr_threshold(struct kvm_vcpu *vcpu)
 {
 	int max_irr, tpr;
@@ -2285,11 +2445,13 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu)
 			return;
 		}
 
+		KVMTRACE_1D(REDELIVER_EVT, vcpu, idtv_info_field, handler);
+
 		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, idtv_info_field);
 		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
 				vmcs_read32(VM_EXIT_INSTRUCTION_LEN));
 
-		if (unlikely(idtv_info_field & INTR_INFO_DELIEVER_CODE_MASK))
+		if (unlikely(idtv_info_field & INTR_INFO_DELIVER_CODE_MASK))
 			vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
 				vmcs_read32(IDT_VECTORING_ERROR_CODE));
 		if (unlikely(has_ext_irq))
@@ -2470,8 +2632,10 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
 
 	/* We need to handle NMIs before interrupts are enabled */
-	if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) /* nmi */
+	if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) { /* nmi */
+		KVMTRACE_0D(NMI, vcpu, handler);
 		asm("int $2");
+	}
 }
 
 static void vmx_free_vmcs(struct kvm_vcpu *vcpu)
@@ -2489,6 +2653,10 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	spin_lock(&vmx_vpid_lock);
+	if (vmx->vpid != 0)
+		__clear_bit(vmx->vpid, vmx_vpid_bitmap);
+	spin_unlock(&vmx_vpid_lock);
 	vmx_free_vmcs(vcpu);
 	kfree(vmx->host_msrs);
 	kfree(vmx->guest_msrs);
@@ -2505,6 +2673,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (!vmx)
 		return ERR_PTR(-ENOMEM);
 
+	allocate_vpid(vmx);
+
 	err = kvm_vcpu_init(&vmx->vcpu, kvm, id);
 	if (err)
 		goto free_vcpu;
@@ -2591,14 +2761,13 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.get_segment_base = vmx_get_segment_base,
 	.get_segment = vmx_get_segment,
 	.set_segment = vmx_set_segment,
+	.get_cpl = vmx_get_cpl,
 	.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
 	.decache_cr4_guest_bits = vmx_decache_cr4_guest_bits,
 	.set_cr0 = vmx_set_cr0,
 	.set_cr3 = vmx_set_cr3,
 	.set_cr4 = vmx_set_cr4,
-#ifdef CONFIG_X86_64
 	.set_efer = vmx_set_efer,
-#endif
 	.get_idt = vmx_get_idt,
 	.set_idt = vmx_set_idt,
 	.get_gdt = vmx_get_gdt,
@@ -2626,7 +2795,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 
 static int __init vmx_init(void)
 {
-	void *iova;
+	void *va;
 	int r;
 
 	vmx_io_bitmap_a = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
@@ -2639,28 +2808,48 @@ static int __init vmx_init(void)
 		goto out;
 	}
 
+	vmx_msr_bitmap = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
+	if (!vmx_msr_bitmap) {
+		r = -ENOMEM;
+		goto out1;
+	}
+
 	/*
 	 * Allow direct access to the PC debug port (it is often used for I/O
 	 * delays, but the vmexits simply slow things down).
 	 */
-	iova = kmap(vmx_io_bitmap_a);
-	memset(iova, 0xff, PAGE_SIZE);
-	clear_bit(0x80, iova);
+	va = kmap(vmx_io_bitmap_a);
+	memset(va, 0xff, PAGE_SIZE);
+	clear_bit(0x80, va);
 	kunmap(vmx_io_bitmap_a);
 
-	iova = kmap(vmx_io_bitmap_b);
-	memset(iova, 0xff, PAGE_SIZE);
+	va = kmap(vmx_io_bitmap_b);
+	memset(va, 0xff, PAGE_SIZE);
 	kunmap(vmx_io_bitmap_b);
 
+	va = kmap(vmx_msr_bitmap);
+	memset(va, 0xff, PAGE_SIZE);
+	kunmap(vmx_msr_bitmap);
+
+	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
+
 	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE);
 	if (r)
-		goto out1;
+		goto out2;
+
+	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_FS_BASE);
+	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_GS_BASE);
+	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_CS);
+	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_ESP);
+	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_EIP);
 
 	if (bypass_guest_pf)
 		kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull);
 
 	return 0;
 
+out2:
+	__free_page(vmx_msr_bitmap);
 out1:
 	__free_page(vmx_io_bitmap_b);
 out:
@@ -2670,6 +2859,7 @@ static int __init vmx_init(void)
 
 static void __exit vmx_exit(void)
 {
+	__free_page(vmx_msr_bitmap);
 	__free_page(vmx_io_bitmap_b);
 	__free_page(vmx_io_bitmap_a);
 
diff --git a/trunk/arch/x86/kvm/vmx.h b/trunk/arch/x86/kvm/vmx.h
index d52ae8d7303d..5dff4606b988 100644
--- a/trunk/arch/x86/kvm/vmx.h
+++ b/trunk/arch/x86/kvm/vmx.h
@@ -49,6 +49,7 @@
  * Definitions of Secondary Processor-Based VM-Execution Controls.
  */
 #define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
+#define SECONDARY_EXEC_ENABLE_VPID              0x00000020
 #define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
 
 
@@ -65,6 +66,7 @@
 
 /* VMCS Encodings */
 enum vmcs_field {
+	VIRTUAL_PROCESSOR_ID            = 0x00000000,
 	GUEST_ES_SELECTOR               = 0x00000800,
 	GUEST_CS_SELECTOR               = 0x00000802,
 	GUEST_SS_SELECTOR               = 0x00000804,
@@ -231,12 +233,12 @@ enum vmcs_field {
  */
 #define INTR_INFO_VECTOR_MASK           0xff            /* 7:0 */
 #define INTR_INFO_INTR_TYPE_MASK        0x700           /* 10:8 */
-#define INTR_INFO_DELIEVER_CODE_MASK    0x800           /* 11 */
+#define INTR_INFO_DELIVER_CODE_MASK     0x800           /* 11 */
 #define INTR_INFO_VALID_MASK            0x80000000      /* 31 */
 
 #define VECTORING_INFO_VECTOR_MASK           	INTR_INFO_VECTOR_MASK
 #define VECTORING_INFO_TYPE_MASK        	INTR_INFO_INTR_TYPE_MASK
-#define VECTORING_INFO_DELIEVER_CODE_MASK    	INTR_INFO_DELIEVER_CODE_MASK
+#define VECTORING_INFO_DELIVER_CODE_MASK    	INTR_INFO_DELIVER_CODE_MASK
 #define VECTORING_INFO_VALID_MASK       	INTR_INFO_VALID_MASK
 
 #define INTR_TYPE_EXT_INTR              (0 << 8) /* external interrupt */
@@ -321,4 +323,8 @@ enum vmcs_field {
 
 #define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT	9
 
+#define VMX_NR_VPIDS				(1 << 16)
+#define VMX_VPID_EXTENT_SINGLE_CONTEXT		1
+#define VMX_VPID_EXTENT_ALL_CONTEXT		2
+
 #endif
diff --git a/trunk/arch/x86/kvm/x86.c b/trunk/arch/x86/kvm/x86.c
index 6b01552bd1f1..0ce556372a4d 100644
--- a/trunk/arch/x86/kvm/x86.c
+++ b/trunk/arch/x86/kvm/x86.c
@@ -15,10 +15,12 @@
  */
 
 #include <linux/kvm_host.h>
-#include "segment_descriptor.h"
 #include "irq.h"
 #include "mmu.h"
+#include "i8254.h"
+#include "tss.h"
 
+#include <linux/clocksource.h>
 #include <linux/kvm.h>
 #include <linux/fs.h>
 #include <linux/vmalloc.h>
@@ -28,6 +30,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/msr.h>
+#include <asm/desc.h>
 
 #define MAX_IO_MSRS 256
 #define CR0_RESERVED_BITS						\
@@ -41,7 +44,15 @@
 			  | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
 
 #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
-#define EFER_RESERVED_BITS 0xfffffffffffff2fe
+/* EFER defaults:
+ * - enable syscall per default because its emulated by KVM
+ * - enable LME and LMA per default on 64 bit KVM
+ */
+#ifdef CONFIG_X86_64
+static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffafeULL;
+#else
+static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffffeULL;
+#endif
 
 #define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
 #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
@@ -63,6 +74,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "irq_window", VCPU_STAT(irq_window_exits) },
 	{ "halt_exits", VCPU_STAT(halt_exits) },
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
+	{ "hypercalls", VCPU_STAT(hypercalls) },
 	{ "request_irq", VCPU_STAT(request_irq_exits) },
 	{ "irq_exits", VCPU_STAT(irq_exits) },
 	{ "host_state_reload", VCPU_STAT(host_state_reload) },
@@ -78,6 +90,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "mmu_recycled", VM_STAT(mmu_recycled) },
 	{ "mmu_cache_miss", VM_STAT(mmu_cache_miss) },
 	{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
+	{ "largepages", VM_STAT(lpages) },
 	{ NULL }
 };
 
@@ -85,7 +98,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 unsigned long segment_base(u16 selector)
 {
 	struct descriptor_table gdt;
-	struct segment_descriptor *d;
+	struct desc_struct *d;
 	unsigned long table_base;
 	unsigned long v;
 
@@ -101,13 +114,12 @@ unsigned long segment_base(u16 selector)
 		asm("sldt %0" : "=g"(ldt_selector));
 		table_base = segment_base(ldt_selector);
 	}
-	d = (struct segment_descriptor *)(table_base + (selector & ~7));
-	v = d->base_low | ((unsigned long)d->base_mid << 16) |
-		((unsigned long)d->base_high << 24);
+	d = (struct desc_struct *)(table_base + (selector & ~7));
+	v = d->base0 | ((unsigned long)d->base1 << 16) |
+		((unsigned long)d->base2 << 24);
 #ifdef CONFIG_X86_64
-	if (d->system == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
-		v |= ((unsigned long) \
-		      ((struct segment_descriptor_64 *)d)->base_higher) << 32;
+	if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
+		v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32;
 #endif
 	return v;
 }
@@ -145,11 +157,16 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr,
 			   u32 error_code)
 {
 	++vcpu->stat.pf_guest;
-	if (vcpu->arch.exception.pending && vcpu->arch.exception.nr == PF_VECTOR) {
-		printk(KERN_DEBUG "kvm: inject_page_fault:"
-		       " double fault 0x%lx\n", addr);
-		vcpu->arch.exception.nr = DF_VECTOR;
-		vcpu->arch.exception.error_code = 0;
+	if (vcpu->arch.exception.pending) {
+		if (vcpu->arch.exception.nr == PF_VECTOR) {
+			printk(KERN_DEBUG "kvm: inject_page_fault:"
+					" double fault 0x%lx\n", addr);
+			vcpu->arch.exception.nr = DF_VECTOR;
+			vcpu->arch.exception.error_code = 0;
+		} else if (vcpu->arch.exception.nr == DF_VECTOR) {
+			/* triple fault -> shutdown */
+			set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
+		}
 		return;
 	}
 	vcpu->arch.cr2 = addr;
@@ -184,7 +201,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3)
 	int ret;
 	u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)];
 
-	down_read(&vcpu->kvm->slots_lock);
 	ret = kvm_read_guest_page(vcpu->kvm, pdpt_gfn, pdpte,
 				  offset * sizeof(u64), sizeof(pdpte));
 	if (ret < 0) {
@@ -201,10 +217,10 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 	memcpy(vcpu->arch.pdptrs, pdpte, sizeof(vcpu->arch.pdptrs));
 out:
-	up_read(&vcpu->kvm->slots_lock);
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(load_pdptrs);
 
 static bool pdptrs_changed(struct kvm_vcpu *vcpu)
 {
@@ -215,18 +231,16 @@ static bool pdptrs_changed(struct kvm_vcpu *vcpu)
 	if (is_long_mode(vcpu) || !is_pae(vcpu))
 		return false;
 
-	down_read(&vcpu->kvm->slots_lock);
 	r = kvm_read_guest(vcpu->kvm, vcpu->arch.cr3 & ~31u, pdpte, sizeof(pdpte));
 	if (r < 0)
 		goto out;
 	changed = memcmp(pdpte, vcpu->arch.pdptrs, sizeof(pdpte)) != 0;
 out:
-	up_read(&vcpu->kvm->slots_lock);
 
 	return changed;
 }
 
-void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
+void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 {
 	if (cr0 & CR0_RESERVED_BITS) {
 		printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n",
@@ -284,15 +298,18 @@ void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	kvm_mmu_reset_context(vcpu);
 	return;
 }
-EXPORT_SYMBOL_GPL(set_cr0);
+EXPORT_SYMBOL_GPL(kvm_set_cr0);
 
-void lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
+void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
 {
-	set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f));
+	kvm_set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f));
+	KVMTRACE_1D(LMSW, vcpu,
+		    (u32)((vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f)),
+		    handler);
 }
-EXPORT_SYMBOL_GPL(lmsw);
+EXPORT_SYMBOL_GPL(kvm_lmsw);
 
-void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	if (cr4 & CR4_RESERVED_BITS) {
 		printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n");
@@ -323,9 +340,9 @@ void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	vcpu->arch.cr4 = cr4;
 	kvm_mmu_reset_context(vcpu);
 }
-EXPORT_SYMBOL_GPL(set_cr4);
+EXPORT_SYMBOL_GPL(kvm_set_cr4);
 
-void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
+void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
 	if (cr3 == vcpu->arch.cr3 && !pdptrs_changed(vcpu)) {
 		kvm_mmu_flush_tlb(vcpu);
@@ -359,7 +376,6 @@ void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 		 */
 	}
 
-	down_read(&vcpu->kvm->slots_lock);
 	/*
 	 * Does the new cr3 value map to physical memory? (Note, we
 	 * catch an invalid cr3 even in real-mode, because it would
@@ -375,11 +391,10 @@ void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 		vcpu->arch.cr3 = cr3;
 		vcpu->arch.mmu.new_cr3(vcpu);
 	}
-	up_read(&vcpu->kvm->slots_lock);
 }
-EXPORT_SYMBOL_GPL(set_cr3);
+EXPORT_SYMBOL_GPL(kvm_set_cr3);
 
-void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
+void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
 {
 	if (cr8 & CR8_RESERVED_BITS) {
 		printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8);
@@ -391,16 +406,16 @@ void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
 	else
 		vcpu->arch.cr8 = cr8;
 }
-EXPORT_SYMBOL_GPL(set_cr8);
+EXPORT_SYMBOL_GPL(kvm_set_cr8);
 
-unsigned long get_cr8(struct kvm_vcpu *vcpu)
+unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
 {
 	if (irqchip_in_kernel(vcpu->kvm))
 		return kvm_lapic_get_cr8(vcpu);
 	else
 		return vcpu->arch.cr8;
 }
-EXPORT_SYMBOL_GPL(get_cr8);
+EXPORT_SYMBOL_GPL(kvm_get_cr8);
 
 /*
  * List of msr numbers which we expose to userspace through KVM_GET_MSRS
@@ -415,7 +430,8 @@ static u32 msrs_to_save[] = {
 #ifdef CONFIG_X86_64
 	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
-	MSR_IA32_TIME_STAMP_COUNTER,
+	MSR_IA32_TIME_STAMP_COUNTER, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
+	MSR_IA32_PERF_STATUS,
 };
 
 static unsigned num_msrs_to_save;
@@ -424,11 +440,9 @@ static u32 emulated_msrs[] = {
 	MSR_IA32_MISC_ENABLE,
 };
 
-#ifdef CONFIG_X86_64
-
 static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
-	if (efer & EFER_RESERVED_BITS) {
+	if (efer & efer_reserved_bits) {
 		printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n",
 		       efer);
 		kvm_inject_gp(vcpu, 0);
@@ -450,7 +464,12 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	vcpu->arch.shadow_efer = efer;
 }
 
-#endif
+void kvm_enable_efer_bits(u64 mask)
+{
+       efer_reserved_bits &= ~mask;
+}
+EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
+
 
 /*
  * Writes msr value into into the appropriate "register".
@@ -470,26 +489,86 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 	return kvm_set_msr(vcpu, index, *data);
 }
 
+static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
+{
+	static int version;
+	struct kvm_wall_clock wc;
+	struct timespec wc_ts;
+
+	if (!wall_clock)
+		return;
+
+	version++;
+
+	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
+
+	wc_ts = current_kernel_time();
+	wc.wc_sec = wc_ts.tv_sec;
+	wc.wc_nsec = wc_ts.tv_nsec;
+	wc.wc_version = version;
+
+	kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc));
+
+	version++;
+	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
+}
+
+static void kvm_write_guest_time(struct kvm_vcpu *v)
+{
+	struct timespec ts;
+	unsigned long flags;
+	struct kvm_vcpu_arch *vcpu = &v->arch;
+	void *shared_kaddr;
+
+	if ((!vcpu->time_page))
+		return;
+
+	/* Keep irq disabled to prevent changes to the clock */
+	local_irq_save(flags);
+	kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER,
+			  &vcpu->hv_clock.tsc_timestamp);
+	ktime_get_ts(&ts);
+	local_irq_restore(flags);
+
+	/* With all the info we got, fill in the values */
+
+	vcpu->hv_clock.system_time = ts.tv_nsec +
+				     (NSEC_PER_SEC * (u64)ts.tv_sec);
+	/*
+	 * The interface expects us to write an even number signaling that the
+	 * update is finished. Since the guest won't see the intermediate
+	 * state, we just write "2" at the end
+	 */
+	vcpu->hv_clock.version = 2;
+
+	shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);
+
+	memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
+		sizeof(vcpu->hv_clock));
+
+	kunmap_atomic(shared_kaddr, KM_USER0);
+
+	mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
+}
+
 
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	switch (msr) {
-#ifdef CONFIG_X86_64
 	case MSR_EFER:
 		set_efer(vcpu, data);
 		break;
-#endif
 	case MSR_IA32_MC0_STATUS:
 		pr_unimpl(vcpu, "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n",
-		       __FUNCTION__, data);
+		       __func__, data);
 		break;
 	case MSR_IA32_MCG_STATUS:
 		pr_unimpl(vcpu, "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n",
-			__FUNCTION__, data);
+			__func__, data);
 		break;
 	case MSR_IA32_MCG_CTL:
 		pr_unimpl(vcpu, "%s: MSR_IA32_MCG_CTL 0x%llx, nop\n",
-			__FUNCTION__, data);
+			__func__, data);
 		break;
 	case MSR_IA32_UCODE_REV:
 	case MSR_IA32_UCODE_WRITE:
@@ -501,6 +580,42 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	case MSR_IA32_MISC_ENABLE:
 		vcpu->arch.ia32_misc_enable_msr = data;
 		break;
+	case MSR_KVM_WALL_CLOCK:
+		vcpu->kvm->arch.wall_clock = data;
+		kvm_write_wall_clock(vcpu->kvm, data);
+		break;
+	case MSR_KVM_SYSTEM_TIME: {
+		if (vcpu->arch.time_page) {
+			kvm_release_page_dirty(vcpu->arch.time_page);
+			vcpu->arch.time_page = NULL;
+		}
+
+		vcpu->arch.time = data;
+
+		/* we verify if the enable bit is set... */
+		if (!(data & 1))
+			break;
+
+		/* ...but clean it before doing the actual write */
+		vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
+
+		vcpu->arch.hv_clock.tsc_to_system_mul =
+					clocksource_khz2mult(tsc_khz, 22);
+		vcpu->arch.hv_clock.tsc_shift = 22;
+
+		down_read(&current->mm->mmap_sem);
+		vcpu->arch.time_page =
+				gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
+		up_read(&current->mm->mmap_sem);
+
+		if (is_error_page(vcpu->arch.time_page)) {
+			kvm_release_page_clean(vcpu->arch.time_page);
+			vcpu->arch.time_page = NULL;
+		}
+
+		kvm_write_guest_time(vcpu);
+		break;
+	}
 	default:
 		pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data);
 		return 1;
@@ -540,7 +655,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_IA32_MC0_MISC+12:
 	case MSR_IA32_MC0_MISC+16:
 	case MSR_IA32_UCODE_REV:
-	case MSR_IA32_PERF_STATUS:
 	case MSR_IA32_EBL_CR_POWERON:
 		/* MTRR registers */
 	case 0xfe:
@@ -556,11 +670,21 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_IA32_MISC_ENABLE:
 		data = vcpu->arch.ia32_misc_enable_msr;
 		break;
-#ifdef CONFIG_X86_64
+	case MSR_IA32_PERF_STATUS:
+		/* TSC increment by tick */
+		data = 1000ULL;
+		/* CPU multiplier */
+		data |= (((uint64_t)4ULL) << 40);
+		break;
 	case MSR_EFER:
 		data = vcpu->arch.shadow_efer;
 		break;
-#endif
+	case MSR_KVM_WALL_CLOCK:
+		data = vcpu->kvm->arch.wall_clock;
+		break;
+	case MSR_KVM_SYSTEM_TIME:
+		data = vcpu->arch.time;
+		break;
 	default:
 		pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
 		return 1;
@@ -584,9 +708,11 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs,
 
 	vcpu_load(vcpu);
 
+	down_read(&vcpu->kvm->slots_lock);
 	for (i = 0; i < msrs->nmsrs; ++i)
 		if (do_msr(vcpu, entries[i].index, &entries[i].data))
 			break;
+	up_read(&vcpu->kvm->slots_lock);
 
 	vcpu_put(vcpu);
 
@@ -688,11 +814,24 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_SET_TSS_ADDR:
 	case KVM_CAP_EXT_CPUID:
+	case KVM_CAP_CLOCKSOURCE:
+	case KVM_CAP_PIT:
+	case KVM_CAP_NOP_IO_DELAY:
+	case KVM_CAP_MP_STATE:
 		r = 1;
 		break;
 	case KVM_CAP_VAPIC:
 		r = !kvm_x86_ops->cpu_has_accelerated_tpr();
 		break;
+	case KVM_CAP_NR_VCPUS:
+		r = KVM_MAX_VCPUS;
+		break;
+	case KVM_CAP_NR_MEMSLOTS:
+		r = KVM_MEMORY_SLOTS;
+		break;
+	case KVM_CAP_PV_MMU:
+		r = !tdp_enabled;
+		break;
 	default:
 		r = 0;
 		break;
@@ -763,6 +902,7 @@ long kvm_arch_dev_ioctl(struct file *filp,
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	kvm_x86_ops->vcpu_load(vcpu, cpu);
+	kvm_write_guest_time(vcpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -958,32 +1098,32 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	}
 	/* function 4 and 0xb have additional index. */
 	case 4: {
-		int index, cache_type;
+		int i, cache_type;
 
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
 		/* read more entries until cache_type is zero */
-		for (index = 1; *nent < maxnent; ++index) {
-			cache_type = entry[index - 1].eax & 0x1f;
+		for (i = 1; *nent < maxnent; ++i) {
+			cache_type = entry[i - 1].eax & 0x1f;
 			if (!cache_type)
 				break;
-			do_cpuid_1_ent(&entry[index], function, index);
-			entry[index].flags |=
+			do_cpuid_1_ent(&entry[i], function, i);
+			entry[i].flags |=
 			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
 			++*nent;
 		}
 		break;
 	}
 	case 0xb: {
-		int index, level_type;
+		int i, level_type;
 
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
 		/* read more entries until level_type is zero */
-		for (index = 1; *nent < maxnent; ++index) {
-			level_type = entry[index - 1].ecx & 0xff;
+		for (i = 1; *nent < maxnent; ++i) {
+			level_type = entry[i - 1].ecx & 0xff;
 			if (!level_type)
 				break;
-			do_cpuid_1_ent(&entry[index], function, index);
-			entry[index].flags |=
+			do_cpuid_1_ent(&entry[i], function, i);
+			entry[i].flags |=
 			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
 			++*nent;
 		}
@@ -1365,6 +1505,23 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
 	return r;
 }
 
+static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
+{
+	int r = 0;
+
+	memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state));
+	return r;
+}
+
+static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
+{
+	int r = 0;
+
+	memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
+	kvm_pit_load_count(kvm, 0, ps->channels[0].count);
+	return r;
+}
+
 /*
  * Get (and clear) the dirty memory log for a memory slot.
  */
@@ -1457,6 +1614,12 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		} else
 			goto out;
 		break;
+	case KVM_CREATE_PIT:
+		r = -ENOMEM;
+		kvm->arch.vpit = kvm_create_pit(kvm);
+		if (kvm->arch.vpit)
+			r = 0;
+		break;
 	case KVM_IRQ_LINE: {
 		struct kvm_irq_level irq_event;
 
@@ -1512,6 +1675,37 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
+	case KVM_GET_PIT: {
+		struct kvm_pit_state ps;
+		r = -EFAULT;
+		if (copy_from_user(&ps, argp, sizeof ps))
+			goto out;
+		r = -ENXIO;
+		if (!kvm->arch.vpit)
+			goto out;
+		r = kvm_vm_ioctl_get_pit(kvm, &ps);
+		if (r)
+			goto out;
+		r = -EFAULT;
+		if (copy_to_user(argp, &ps, sizeof ps))
+			goto out;
+		r = 0;
+		break;
+	}
+	case KVM_SET_PIT: {
+		struct kvm_pit_state ps;
+		r = -EFAULT;
+		if (copy_from_user(&ps, argp, sizeof ps))
+			goto out;
+		r = -ENXIO;
+		if (!kvm->arch.vpit)
+			goto out;
+		r = kvm_vm_ioctl_set_pit(kvm, &ps);
+		if (r)
+			goto out;
+		r = 0;
+		break;
+	}
 	default:
 		;
 	}
@@ -1570,7 +1764,6 @@ int emulator_read_std(unsigned long addr,
 	void *data = val;
 	int r = X86EMUL_CONTINUE;
 
-	down_read(&vcpu->kvm->slots_lock);
 	while (bytes) {
 		gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
 		unsigned offset = addr & (PAGE_SIZE-1);
@@ -1592,7 +1785,6 @@ int emulator_read_std(unsigned long addr,
 		addr += tocopy;
 	}
 out:
-	up_read(&vcpu->kvm->slots_lock);
 	return r;
 }
 EXPORT_SYMBOL_GPL(emulator_read_std);
@@ -1611,9 +1803,7 @@ static int emulator_read_emulated(unsigned long addr,
 		return X86EMUL_CONTINUE;
 	}
 
-	down_read(&vcpu->kvm->slots_lock);
 	gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
-	up_read(&vcpu->kvm->slots_lock);
 
 	/* For APIC access vmexit */
 	if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
@@ -1646,19 +1836,15 @@ static int emulator_read_emulated(unsigned long addr,
 	return X86EMUL_UNHANDLEABLE;
 }
 
-static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
-			       const void *val, int bytes)
+int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
+			  const void *val, int bytes)
 {
 	int ret;
 
-	down_read(&vcpu->kvm->slots_lock);
 	ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes);
-	if (ret < 0) {
-		up_read(&vcpu->kvm->slots_lock);
+	if (ret < 0)
 		return 0;
-	}
 	kvm_mmu_pte_write(vcpu, gpa, val, bytes);
-	up_read(&vcpu->kvm->slots_lock);
 	return 1;
 }
 
@@ -1670,9 +1856,7 @@ static int emulator_write_emulated_onepage(unsigned long addr,
 	struct kvm_io_device *mmio_dev;
 	gpa_t                 gpa;
 
-	down_read(&vcpu->kvm->slots_lock);
 	gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
-	up_read(&vcpu->kvm->slots_lock);
 
 	if (gpa == UNMAPPED_GVA) {
 		kvm_inject_page_fault(vcpu, addr, 2);
@@ -1749,7 +1933,6 @@ static int emulator_cmpxchg_emulated(unsigned long addr,
 		char *kaddr;
 		u64 val;
 
-		down_read(&vcpu->kvm->slots_lock);
 		gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
 
 		if (gpa == UNMAPPED_GVA ||
@@ -1769,9 +1952,8 @@ static int emulator_cmpxchg_emulated(unsigned long addr,
 		set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val);
 		kunmap_atomic(kaddr, KM_USER0);
 		kvm_release_page_dirty(page);
-	emul_write:
-		up_read(&vcpu->kvm->slots_lock);
 	}
+emul_write:
 #endif
 
 	return emulator_write_emulated(addr, new, bytes, vcpu);
@@ -1802,7 +1984,7 @@ int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest)
 		*dest = kvm_x86_ops->get_dr(vcpu, dr);
 		return X86EMUL_CONTINUE;
 	default:
-		pr_unimpl(vcpu, "%s: unexpected dr %u\n", __FUNCTION__, dr);
+		pr_unimpl(vcpu, "%s: unexpected dr %u\n", __func__, dr);
 		return X86EMUL_UNHANDLEABLE;
 	}
 }
@@ -1840,7 +2022,7 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
 }
 EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);
 
-struct x86_emulate_ops emulate_ops = {
+static struct x86_emulate_ops emulate_ops = {
 	.read_std            = emulator_read_std,
 	.read_emulated       = emulator_read_emulated,
 	.write_emulated      = emulator_write_emulated,
@@ -2091,6 +2273,13 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 	vcpu->arch.pio.guest_page_offset = 0;
 	vcpu->arch.pio.rep = 0;
 
+	if (vcpu->run->io.direction == KVM_EXIT_IO_IN)
+		KVMTRACE_2D(IO_READ, vcpu, vcpu->run->io.port, (u32)size,
+			    handler);
+	else
+		KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size,
+			    handler);
+
 	kvm_x86_ops->cache_regs(vcpu);
 	memcpy(vcpu->arch.pio_data, &vcpu->arch.regs[VCPU_REGS_RAX], 4);
 	kvm_x86_ops->decache_regs(vcpu);
@@ -2129,6 +2318,13 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 	vcpu->arch.pio.guest_page_offset = offset_in_page(address);
 	vcpu->arch.pio.rep = rep;
 
+	if (vcpu->run->io.direction == KVM_EXIT_IO_IN)
+		KVMTRACE_2D(IO_READ, vcpu, vcpu->run->io.port, (u32)size,
+			    handler);
+	else
+		KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size,
+			    handler);
+
 	if (!count) {
 		kvm_x86_ops->skip_emulated_instruction(vcpu);
 		return 1;
@@ -2163,10 +2359,8 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 		kvm_x86_ops->skip_emulated_instruction(vcpu);
 
 	for (i = 0; i < nr_pages; ++i) {
-		down_read(&vcpu->kvm->slots_lock);
 		page = gva_to_page(vcpu, address + i * PAGE_SIZE);
 		vcpu->arch.pio.guest_pages[i] = page;
-		up_read(&vcpu->kvm->slots_lock);
 		if (!page) {
 			kvm_inject_gp(vcpu, 0);
 			free_pio_guest_pages(vcpu);
@@ -2238,10 +2432,13 @@ void kvm_arch_exit(void)
 int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 {
 	++vcpu->stat.halt_exits;
+	KVMTRACE_0D(HLT, vcpu, handler);
 	if (irqchip_in_kernel(vcpu->kvm)) {
-		vcpu->arch.mp_state = VCPU_MP_STATE_HALTED;
+		vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
+		up_read(&vcpu->kvm->slots_lock);
 		kvm_vcpu_block(vcpu);
-		if (vcpu->arch.mp_state != VCPU_MP_STATE_RUNNABLE)
+		down_read(&vcpu->kvm->slots_lock);
+		if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
 			return -EINTR;
 		return 1;
 	} else {
@@ -2251,9 +2448,19 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_halt);
 
+static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0,
+			   unsigned long a1)
+{
+	if (is_long_mode(vcpu))
+		return a0;
+	else
+		return a0 | ((gpa_t)a1 << 32);
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
+	int r = 1;
 
 	kvm_x86_ops->cache_regs(vcpu);
 
@@ -2263,6 +2470,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	a2 = vcpu->arch.regs[VCPU_REGS_RDX];
 	a3 = vcpu->arch.regs[VCPU_REGS_RSI];
 
+	KVMTRACE_1D(VMMCALL, vcpu, (u32)nr, handler);
+
 	if (!is_long_mode(vcpu)) {
 		nr &= 0xFFFFFFFF;
 		a0 &= 0xFFFFFFFF;
@@ -2275,13 +2484,17 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	case KVM_HC_VAPIC_POLL_IRQ:
 		ret = 0;
 		break;
+	case KVM_HC_MMU_OP:
+		r = kvm_pv_mmu_op(vcpu, a0, hc_gpa(vcpu, a1, a2), &ret);
+		break;
 	default:
 		ret = -KVM_ENOSYS;
 		break;
 	}
 	vcpu->arch.regs[VCPU_REGS_RAX] = ret;
 	kvm_x86_ops->decache_regs(vcpu);
-	return 0;
+	++vcpu->stat.hypercalls;
+	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
 
@@ -2329,7 +2542,7 @@ void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
 void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
 		   unsigned long *rflags)
 {
-	lmsw(vcpu, msw);
+	kvm_lmsw(vcpu, msw);
 	*rflags = kvm_x86_ops->get_rflags(vcpu);
 }
 
@@ -2346,9 +2559,9 @@ unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
 	case 4:
 		return vcpu->arch.cr4;
 	case 8:
-		return get_cr8(vcpu);
+		return kvm_get_cr8(vcpu);
 	default:
-		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr);
+		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
 		return 0;
 	}
 }
@@ -2358,23 +2571,23 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
 {
 	switch (cr) {
 	case 0:
-		set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val));
+		kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val));
 		*rflags = kvm_x86_ops->get_rflags(vcpu);
 		break;
 	case 2:
 		vcpu->arch.cr2 = val;
 		break;
 	case 3:
-		set_cr3(vcpu, val);
+		kvm_set_cr3(vcpu, val);
 		break;
 	case 4:
-		set_cr4(vcpu, mk_cr_64(vcpu->arch.cr4, val));
+		kvm_set_cr4(vcpu, mk_cr_64(vcpu->arch.cr4, val));
 		break;
 	case 8:
-		set_cr8(vcpu, val & 0xfUL);
+		kvm_set_cr8(vcpu, val & 0xfUL);
 		break;
 	default:
-		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr);
+		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
 	}
 }
 
@@ -2447,6 +2660,11 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
 	}
 	kvm_x86_ops->decache_regs(vcpu);
 	kvm_x86_ops->skip_emulated_instruction(vcpu);
+	KVMTRACE_5D(CPUID, vcpu, function,
+		    (u32)vcpu->arch.regs[VCPU_REGS_RAX],
+		    (u32)vcpu->arch.regs[VCPU_REGS_RBX],
+		    (u32)vcpu->arch.regs[VCPU_REGS_RCX],
+		    (u32)vcpu->arch.regs[VCPU_REGS_RDX], handler);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);
 
@@ -2469,7 +2687,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu,
 			      struct kvm_run *kvm_run)
 {
 	kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
-	kvm_run->cr8 = get_cr8(vcpu);
+	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
 	if (irqchip_in_kernel(vcpu->kvm))
 		kvm_run->ready_for_interrupt_injection = 1;
@@ -2509,16 +2727,17 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	int r;
 
-	if (unlikely(vcpu->arch.mp_state == VCPU_MP_STATE_SIPI_RECEIVED)) {
+	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) {
 		pr_debug("vcpu %d received sipi with vector # %x\n",
 		       vcpu->vcpu_id, vcpu->arch.sipi_vector);
 		kvm_lapic_reset(vcpu);
 		r = kvm_x86_ops->vcpu_reset(vcpu);
 		if (r)
 			return r;
-		vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
+		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 	}
 
+	down_read(&vcpu->kvm->slots_lock);
 	vapic_enter(vcpu);
 
 preempted:
@@ -2526,6 +2745,10 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		kvm_x86_ops->guest_debug_pre(vcpu);
 
 again:
+	if (vcpu->requests)
+		if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
+			kvm_mmu_unload(vcpu);
+
 	r = kvm_mmu_reload(vcpu);
 	if (unlikely(r))
 		goto out;
@@ -2539,6 +2762,11 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 			r = 0;
 			goto out;
 		}
+		if (test_and_clear_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests)) {
+			kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
+			r = 0;
+			goto out;
+		}
 	}
 
 	kvm_inject_pending_timer_irqs(vcpu);
@@ -2557,6 +2785,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		goto out;
 	}
 
+	if (vcpu->requests)
+		if (test_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) {
+			local_irq_enable();
+			preempt_enable();
+			r = 1;
+			goto out;
+		}
+
 	if (signal_pending(current)) {
 		local_irq_enable();
 		preempt_enable();
@@ -2566,6 +2802,13 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		goto out;
 	}
 
+	vcpu->guest_mode = 1;
+	/*
+	 * Make sure that guest_mode assignment won't happen after
+	 * testing the pending IRQ vector bitmap.
+	 */
+	smp_wmb();
+
 	if (vcpu->arch.exception.pending)
 		__queue_exception(vcpu);
 	else if (irqchip_in_kernel(vcpu->kvm))
@@ -2575,13 +2818,15 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	kvm_lapic_sync_to_vapic(vcpu);
 
-	vcpu->guest_mode = 1;
+	up_read(&vcpu->kvm->slots_lock);
+
 	kvm_guest_enter();
 
 	if (vcpu->requests)
 		if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
 			kvm_x86_ops->tlb_flush(vcpu);
 
+	KVMTRACE_0D(VMENTRY, vcpu, entryexit);
 	kvm_x86_ops->run(vcpu, kvm_run);
 
 	vcpu->guest_mode = 0;
@@ -2601,6 +2846,8 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	preempt_enable();
 
+	down_read(&vcpu->kvm->slots_lock);
+
 	/*
 	 * Profile KVM exit RIPs:
 	 */
@@ -2628,14 +2875,18 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 
 out:
+	up_read(&vcpu->kvm->slots_lock);
 	if (r > 0) {
 		kvm_resched(vcpu);
+		down_read(&vcpu->kvm->slots_lock);
 		goto preempted;
 	}
 
 	post_kvm_run_save(vcpu, kvm_run);
 
+	down_read(&vcpu->kvm->slots_lock);
 	vapic_exit(vcpu);
+	up_read(&vcpu->kvm->slots_lock);
 
 	return r;
 }
@@ -2647,7 +2898,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	vcpu_load(vcpu);
 
-	if (unlikely(vcpu->arch.mp_state == VCPU_MP_STATE_UNINITIALIZED)) {
+	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
 		kvm_vcpu_block(vcpu);
 		vcpu_put(vcpu);
 		return -EAGAIN;
@@ -2658,7 +2909,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	/* re-sync apic's tpr */
 	if (!irqchip_in_kernel(vcpu->kvm))
-		set_cr8(vcpu, kvm_run->cr8);
+		kvm_set_cr8(vcpu, kvm_run->cr8);
 
 	if (vcpu->arch.pio.cur_count) {
 		r = complete_pio(vcpu);
@@ -2670,9 +2921,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
 		vcpu->mmio_read_completed = 1;
 		vcpu->mmio_needed = 0;
+
+		down_read(&vcpu->kvm->slots_lock);
 		r = emulate_instruction(vcpu, kvm_run,
 					vcpu->arch.mmio_fault_cr2, 0,
 					EMULTYPE_NO_DECODE);
+		up_read(&vcpu->kvm->slots_lock);
 		if (r == EMULATE_DO_MMIO) {
 			/*
 			 * Read-modify-write.  Back to userspace.
@@ -2773,7 +3027,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 static void get_segment(struct kvm_vcpu *vcpu,
 			struct kvm_segment *var, int seg)
 {
-	return kvm_x86_ops->get_segment(vcpu, var, seg);
+	kvm_x86_ops->get_segment(vcpu, var, seg);
 }
 
 void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
@@ -2816,7 +3070,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	sregs->cr2 = vcpu->arch.cr2;
 	sregs->cr3 = vcpu->arch.cr3;
 	sregs->cr4 = vcpu->arch.cr4;
-	sregs->cr8 = get_cr8(vcpu);
+	sregs->cr8 = kvm_get_cr8(vcpu);
 	sregs->efer = vcpu->arch.shadow_efer;
 	sregs->apic_base = kvm_get_apic_base(vcpu);
 
@@ -2836,12 +3090,438 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state)
+{
+	vcpu_load(vcpu);
+	mp_state->mp_state = vcpu->arch.mp_state;
+	vcpu_put(vcpu);
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state)
+{
+	vcpu_load(vcpu);
+	vcpu->arch.mp_state = mp_state->mp_state;
+	vcpu_put(vcpu);
+	return 0;
+}
+
 static void set_segment(struct kvm_vcpu *vcpu,
 			struct kvm_segment *var, int seg)
 {
-	return kvm_x86_ops->set_segment(vcpu, var, seg);
+	kvm_x86_ops->set_segment(vcpu, var, seg);
+}
+
+static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector,
+				   struct kvm_segment *kvm_desct)
+{
+	kvm_desct->base = seg_desc->base0;
+	kvm_desct->base |= seg_desc->base1 << 16;
+	kvm_desct->base |= seg_desc->base2 << 24;
+	kvm_desct->limit = seg_desc->limit0;
+	kvm_desct->limit |= seg_desc->limit << 16;
+	kvm_desct->selector = selector;
+	kvm_desct->type = seg_desc->type;
+	kvm_desct->present = seg_desc->p;
+	kvm_desct->dpl = seg_desc->dpl;
+	kvm_desct->db = seg_desc->d;
+	kvm_desct->s = seg_desc->s;
+	kvm_desct->l = seg_desc->l;
+	kvm_desct->g = seg_desc->g;
+	kvm_desct->avl = seg_desc->avl;
+	if (!selector)
+		kvm_desct->unusable = 1;
+	else
+		kvm_desct->unusable = 0;
+	kvm_desct->padding = 0;
+}
+
+static void get_segment_descritptor_dtable(struct kvm_vcpu *vcpu,
+					   u16 selector,
+					   struct descriptor_table *dtable)
+{
+	if (selector & 1 << 2) {
+		struct kvm_segment kvm_seg;
+
+		get_segment(vcpu, &kvm_seg, VCPU_SREG_LDTR);
+
+		if (kvm_seg.unusable)
+			dtable->limit = 0;
+		else
+			dtable->limit = kvm_seg.limit;
+		dtable->base = kvm_seg.base;
+	}
+	else
+		kvm_x86_ops->get_gdt(vcpu, dtable);
+}
+
+/* allowed just for 8 bytes segments */
+static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
+					 struct desc_struct *seg_desc)
+{
+	struct descriptor_table dtable;
+	u16 index = selector >> 3;
+
+	get_segment_descritptor_dtable(vcpu, selector, &dtable);
+
+	if (dtable.limit < index * 8 + 7) {
+		kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc);
+		return 1;
+	}
+	return kvm_read_guest(vcpu->kvm, dtable.base + index * 8, seg_desc, 8);
+}
+
+/* allowed just for 8 bytes segments */
+static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
+					 struct desc_struct *seg_desc)
+{
+	struct descriptor_table dtable;
+	u16 index = selector >> 3;
+
+	get_segment_descritptor_dtable(vcpu, selector, &dtable);
+
+	if (dtable.limit < index * 8 + 7)
+		return 1;
+	return kvm_write_guest(vcpu->kvm, dtable.base + index * 8, seg_desc, 8);
+}
+
+static u32 get_tss_base_addr(struct kvm_vcpu *vcpu,
+			     struct desc_struct *seg_desc)
+{
+	u32 base_addr;
+
+	base_addr = seg_desc->base0;
+	base_addr |= (seg_desc->base1 << 16);
+	base_addr |= (seg_desc->base2 << 24);
+
+	return base_addr;
+}
+
+static int load_tss_segment32(struct kvm_vcpu *vcpu,
+			      struct desc_struct *seg_desc,
+			      struct tss_segment_32 *tss)
+{
+	u32 base_addr;
+
+	base_addr = get_tss_base_addr(vcpu, seg_desc);
+
+	return kvm_read_guest(vcpu->kvm, base_addr, tss,
+			      sizeof(struct tss_segment_32));
+}
+
+static int save_tss_segment32(struct kvm_vcpu *vcpu,
+			      struct desc_struct *seg_desc,
+			      struct tss_segment_32 *tss)
+{
+	u32 base_addr;
+
+	base_addr = get_tss_base_addr(vcpu, seg_desc);
+
+	return kvm_write_guest(vcpu->kvm, base_addr, tss,
+			       sizeof(struct tss_segment_32));
+}
+
+static int load_tss_segment16(struct kvm_vcpu *vcpu,
+			      struct desc_struct *seg_desc,
+			      struct tss_segment_16 *tss)
+{
+	u32 base_addr;
+
+	base_addr = get_tss_base_addr(vcpu, seg_desc);
+
+	return kvm_read_guest(vcpu->kvm, base_addr, tss,
+			      sizeof(struct tss_segment_16));
+}
+
+static int save_tss_segment16(struct kvm_vcpu *vcpu,
+			      struct desc_struct *seg_desc,
+			      struct tss_segment_16 *tss)
+{
+	u32 base_addr;
+
+	base_addr = get_tss_base_addr(vcpu, seg_desc);
+
+	return kvm_write_guest(vcpu->kvm, base_addr, tss,
+			       sizeof(struct tss_segment_16));
+}
+
+static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg)
+{
+	struct kvm_segment kvm_seg;
+
+	get_segment(vcpu, &kvm_seg, seg);
+	return kvm_seg.selector;
+}
+
+static int load_segment_descriptor_to_kvm_desct(struct kvm_vcpu *vcpu,
+						u16 selector,
+						struct kvm_segment *kvm_seg)
+{
+	struct desc_struct seg_desc;
+
+	if (load_guest_segment_descriptor(vcpu, selector, &seg_desc))
+		return 1;
+	seg_desct_to_kvm_desct(&seg_desc, selector, kvm_seg);
+	return 0;
+}
+
+static int load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
+				   int type_bits, int seg)
+{
+	struct kvm_segment kvm_seg;
+
+	if (load_segment_descriptor_to_kvm_desct(vcpu, selector, &kvm_seg))
+		return 1;
+	kvm_seg.type |= type_bits;
+
+	if (seg != VCPU_SREG_SS && seg != VCPU_SREG_CS &&
+	    seg != VCPU_SREG_LDTR)
+		if (!kvm_seg.s)
+			kvm_seg.unusable = 1;
+
+	set_segment(vcpu, &kvm_seg, seg);
+	return 0;
+}
+
+static void save_state_to_tss32(struct kvm_vcpu *vcpu,
+				struct tss_segment_32 *tss)
+{
+	tss->cr3 = vcpu->arch.cr3;
+	tss->eip = vcpu->arch.rip;
+	tss->eflags = kvm_x86_ops->get_rflags(vcpu);
+	tss->eax = vcpu->arch.regs[VCPU_REGS_RAX];
+	tss->ecx = vcpu->arch.regs[VCPU_REGS_RCX];
+	tss->edx = vcpu->arch.regs[VCPU_REGS_RDX];
+	tss->ebx = vcpu->arch.regs[VCPU_REGS_RBX];
+	tss->esp = vcpu->arch.regs[VCPU_REGS_RSP];
+	tss->ebp = vcpu->arch.regs[VCPU_REGS_RBP];
+	tss->esi = vcpu->arch.regs[VCPU_REGS_RSI];
+	tss->edi = vcpu->arch.regs[VCPU_REGS_RDI];
+
+	tss->es = get_segment_selector(vcpu, VCPU_SREG_ES);
+	tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS);
+	tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS);
+	tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS);
+	tss->fs = get_segment_selector(vcpu, VCPU_SREG_FS);
+	tss->gs = get_segment_selector(vcpu, VCPU_SREG_GS);
+	tss->ldt_selector = get_segment_selector(vcpu, VCPU_SREG_LDTR);
+	tss->prev_task_link = get_segment_selector(vcpu, VCPU_SREG_TR);
+}
+
+static int load_state_from_tss32(struct kvm_vcpu *vcpu,
+				  struct tss_segment_32 *tss)
+{
+	kvm_set_cr3(vcpu, tss->cr3);
+
+	vcpu->arch.rip = tss->eip;
+	kvm_x86_ops->set_rflags(vcpu, tss->eflags | 2);
+
+	vcpu->arch.regs[VCPU_REGS_RAX] = tss->eax;
+	vcpu->arch.regs[VCPU_REGS_RCX] = tss->ecx;
+	vcpu->arch.regs[VCPU_REGS_RDX] = tss->edx;
+	vcpu->arch.regs[VCPU_REGS_RBX] = tss->ebx;
+	vcpu->arch.regs[VCPU_REGS_RSP] = tss->esp;
+	vcpu->arch.regs[VCPU_REGS_RBP] = tss->ebp;
+	vcpu->arch.regs[VCPU_REGS_RSI] = tss->esi;
+	vcpu->arch.regs[VCPU_REGS_RDI] = tss->edi;
+
+	if (load_segment_descriptor(vcpu, tss->ldt_selector, 0, VCPU_SREG_LDTR))
+		return 1;
+
+	if (load_segment_descriptor(vcpu, tss->es, 1, VCPU_SREG_ES))
+		return 1;
+
+	if (load_segment_descriptor(vcpu, tss->cs, 9, VCPU_SREG_CS))
+		return 1;
+
+	if (load_segment_descriptor(vcpu, tss->ss, 1, VCPU_SREG_SS))
+		return 1;
+
+	if (load_segment_descriptor(vcpu, tss->ds, 1, VCPU_SREG_DS))
+		return 1;
+
+	if (load_segment_descriptor(vcpu, tss->fs, 1, VCPU_SREG_FS))
+		return 1;
+
+	if (load_segment_descriptor(vcpu, tss->gs, 1, VCPU_SREG_GS))
+		return 1;
+	return 0;
+}
+
+static void save_state_to_tss16(struct kvm_vcpu *vcpu,
+				struct tss_segment_16 *tss)
+{
+	tss->ip = vcpu->arch.rip;
+	tss->flag = kvm_x86_ops->get_rflags(vcpu);
+	tss->ax = vcpu->arch.regs[VCPU_REGS_RAX];
+	tss->cx = vcpu->arch.regs[VCPU_REGS_RCX];
+	tss->dx = vcpu->arch.regs[VCPU_REGS_RDX];
+	tss->bx = vcpu->arch.regs[VCPU_REGS_RBX];
+	tss->sp = vcpu->arch.regs[VCPU_REGS_RSP];
+	tss->bp = vcpu->arch.regs[VCPU_REGS_RBP];
+	tss->si = vcpu->arch.regs[VCPU_REGS_RSI];
+	tss->di = vcpu->arch.regs[VCPU_REGS_RDI];
+
+	tss->es = get_segment_selector(vcpu, VCPU_SREG_ES);
+	tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS);
+	tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS);
+	tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS);
+	tss->ldt = get_segment_selector(vcpu, VCPU_SREG_LDTR);
+	tss->prev_task_link = get_segment_selector(vcpu, VCPU_SREG_TR);
+}
+
+static int load_state_from_tss16(struct kvm_vcpu *vcpu,
+				 struct tss_segment_16 *tss)
+{
+	vcpu->arch.rip = tss->ip;
+	kvm_x86_ops->set_rflags(vcpu, tss->flag | 2);
+	vcpu->arch.regs[VCPU_REGS_RAX] = tss->ax;
+	vcpu->arch.regs[VCPU_REGS_RCX] = tss->cx;
+	vcpu->arch.regs[VCPU_REGS_RDX] = tss->dx;
+	vcpu->arch.regs[VCPU_REGS_RBX] = tss->bx;
+	vcpu->arch.regs[VCPU_REGS_RSP] = tss->sp;
+	vcpu->arch.regs[VCPU_REGS_RBP] = tss->bp;
+	vcpu->arch.regs[VCPU_REGS_RSI] = tss->si;
+	vcpu->arch.regs[VCPU_REGS_RDI] = tss->di;
+
+	if (load_segment_descriptor(vcpu, tss->ldt, 0, VCPU_SREG_LDTR))
+		return 1;
+
+	if (load_segment_descriptor(vcpu, tss->es, 1, VCPU_SREG_ES))
+		return 1;
+
+	if (load_segment_descriptor(vcpu, tss->cs, 9, VCPU_SREG_CS))
+		return 1;
+
+	if (load_segment_descriptor(vcpu, tss->ss, 1, VCPU_SREG_SS))
+		return 1;
+
+	if (load_segment_descriptor(vcpu, tss->ds, 1, VCPU_SREG_DS))
+		return 1;
+	return 0;
+}
+
+int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector,
+		       struct desc_struct *cseg_desc,
+		       struct desc_struct *nseg_desc)
+{
+	struct tss_segment_16 tss_segment_16;
+	int ret = 0;
+
+	if (load_tss_segment16(vcpu, cseg_desc, &tss_segment_16))
+		goto out;
+
+	save_state_to_tss16(vcpu, &tss_segment_16);
+	save_tss_segment16(vcpu, cseg_desc, &tss_segment_16);
+
+	if (load_tss_segment16(vcpu, nseg_desc, &tss_segment_16))
+		goto out;
+	if (load_state_from_tss16(vcpu, &tss_segment_16))
+		goto out;
+
+	ret = 1;
+out:
+	return ret;
+}
+
+int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector,
+		       struct desc_struct *cseg_desc,
+		       struct desc_struct *nseg_desc)
+{
+	struct tss_segment_32 tss_segment_32;
+	int ret = 0;
+
+	if (load_tss_segment32(vcpu, cseg_desc, &tss_segment_32))
+		goto out;
+
+	save_state_to_tss32(vcpu, &tss_segment_32);
+	save_tss_segment32(vcpu, cseg_desc, &tss_segment_32);
+
+	if (load_tss_segment32(vcpu, nseg_desc, &tss_segment_32))
+		goto out;
+	if (load_state_from_tss32(vcpu, &tss_segment_32))
+		goto out;
+
+	ret = 1;
+out:
+	return ret;
 }
 
+int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
+{
+	struct kvm_segment tr_seg;
+	struct desc_struct cseg_desc;
+	struct desc_struct nseg_desc;
+	int ret = 0;
+
+	get_segment(vcpu, &tr_seg, VCPU_SREG_TR);
+
+	if (load_guest_segment_descriptor(vcpu, tss_selector, &nseg_desc))
+		goto out;
+
+	if (load_guest_segment_descriptor(vcpu, tr_seg.selector, &cseg_desc))
+		goto out;
+
+
+	if (reason != TASK_SWITCH_IRET) {
+		int cpl;
+
+		cpl = kvm_x86_ops->get_cpl(vcpu);
+		if ((tss_selector & 3) > nseg_desc.dpl || cpl > nseg_desc.dpl) {
+			kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+			return 1;
+		}
+	}
+
+	if (!nseg_desc.p || (nseg_desc.limit0 | nseg_desc.limit << 16) < 0x67) {
+		kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc);
+		return 1;
+	}
+
+	if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) {
+		cseg_desc.type &= ~(1 << 8); //clear the B flag
+		save_guest_segment_descriptor(vcpu, tr_seg.selector,
+					      &cseg_desc);
+	}
+
+	if (reason == TASK_SWITCH_IRET) {
+		u32 eflags = kvm_x86_ops->get_rflags(vcpu);
+		kvm_x86_ops->set_rflags(vcpu, eflags & ~X86_EFLAGS_NT);
+	}
+
+	kvm_x86_ops->skip_emulated_instruction(vcpu);
+	kvm_x86_ops->cache_regs(vcpu);
+
+	if (nseg_desc.type & 8)
+		ret = kvm_task_switch_32(vcpu, tss_selector, &cseg_desc,
+					 &nseg_desc);
+	else
+		ret = kvm_task_switch_16(vcpu, tss_selector, &cseg_desc,
+					 &nseg_desc);
+
+	if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) {
+		u32 eflags = kvm_x86_ops->get_rflags(vcpu);
+		kvm_x86_ops->set_rflags(vcpu, eflags | X86_EFLAGS_NT);
+	}
+
+	if (reason != TASK_SWITCH_IRET) {
+		nseg_desc.type |= (1 << 8);
+		save_guest_segment_descriptor(vcpu, tss_selector,
+					      &nseg_desc);
+	}
+
+	kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 | X86_CR0_TS);
+	seg_desct_to_kvm_desct(&nseg_desc, tss_selector, &tr_seg);
+	tr_seg.type = 11;
+	set_segment(vcpu, &tr_seg, VCPU_SREG_TR);
+out:
+	kvm_x86_ops->decache_regs(vcpu);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kvm_task_switch);
+
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
@@ -2862,12 +3542,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	mmu_reset_needed |= vcpu->arch.cr3 != sregs->cr3;
 	vcpu->arch.cr3 = sregs->cr3;
 
-	set_cr8(vcpu, sregs->cr8);
+	kvm_set_cr8(vcpu, sregs->cr8);
 
 	mmu_reset_needed |= vcpu->arch.shadow_efer != sregs->efer;
-#ifdef CONFIG_X86_64
 	kvm_x86_ops->set_efer(vcpu, sregs->efer);
-#endif
 	kvm_set_apic_base(vcpu, sregs->apic_base);
 
 	kvm_x86_ops->decache_cr4_guest_bits(vcpu);
@@ -3141,9 +3819,9 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.mmu.root_hpa = INVALID_PAGE;
 	if (!irqchip_in_kernel(kvm) || vcpu->vcpu_id == 0)
-		vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
+		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 	else
-		vcpu->arch.mp_state = VCPU_MP_STATE_UNINITIALIZED;
+		vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED;
 
 	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	if (!page) {
@@ -3175,7 +3853,9 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
 	kvm_free_lapic(vcpu);
+	down_read(&vcpu->kvm->slots_lock);
 	kvm_mmu_destroy(vcpu);
+	up_read(&vcpu->kvm->slots_lock);
 	free_page((unsigned long)vcpu->arch.pio_data);
 }
 
@@ -3219,10 +3899,13 @@ static void kvm_free_vcpus(struct kvm *kvm)
 
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
+	kvm_free_pit(kvm);
 	kfree(kvm->arch.vpic);
 	kfree(kvm->arch.vioapic);
 	kvm_free_vcpus(kvm);
 	kvm_free_physmem(kvm);
+	if (kvm->arch.apic_access_page)
+		put_page(kvm->arch.apic_access_page);
 	kfree(kvm);
 }
 
@@ -3278,8 +3961,8 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE
-	       || vcpu->arch.mp_state == VCPU_MP_STATE_SIPI_RECEIVED;
+	return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE
+	       || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED;
 }
 
 static void vcpu_kick_intr(void *info)
@@ -3293,11 +3976,17 @@ static void vcpu_kick_intr(void *info)
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 {
 	int ipi_pcpu = vcpu->cpu;
+	int cpu = get_cpu();
 
 	if (waitqueue_active(&vcpu->wq)) {
 		wake_up_interruptible(&vcpu->wq);
 		++vcpu->stat.halt_wakeup;
 	}
-	if (vcpu->guest_mode)
+	/*
+	 * We may be called synchronously with irqs disabled in guest mode,
+	 * So need not to call smp_call_function_single() in that case.
+	 */
+	if (vcpu->guest_mode && vcpu->cpu != cpu)
 		smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0, 0);
+	put_cpu();
 }
diff --git a/trunk/arch/x86/kvm/x86_emulate.c b/trunk/arch/x86/kvm/x86_emulate.c
index 79586003397a..2ca08386f993 100644
--- a/trunk/arch/x86/kvm/x86_emulate.c
+++ b/trunk/arch/x86/kvm/x86_emulate.c
@@ -65,6 +65,14 @@
 #define MemAbs      (1<<9)      /* Memory operand is absolute displacement */
 #define String      (1<<10)     /* String instruction (rep capable) */
 #define Stack       (1<<11)     /* Stack instruction (push/pop) */
+#define Group       (1<<14)     /* Bits 3:5 of modrm byte extend opcode */
+#define GroupDual   (1<<15)     /* Alternate decoding of mod == 3 */
+#define GroupMask   0xff        /* Group number stored in bits 0:7 */
+
+enum {
+	Group1_80, Group1_81, Group1_82, Group1_83,
+	Group1A, Group3_Byte, Group3, Group4, Group5, Group7,
+};
 
 static u16 opcode_table[256] = {
 	/* 0x00 - 0x07 */
@@ -123,14 +131,14 @@ static u16 opcode_table[256] = {
 	ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
 	ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
 	/* 0x80 - 0x87 */
-	ByteOp | DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM,
-	ByteOp | DstMem | SrcImm | ModRM, DstMem | SrcImmByte | ModRM,
+	Group | Group1_80, Group | Group1_81,
+	Group | Group1_82, Group | Group1_83,
 	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
 	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
 	/* 0x88 - 0x8F */
 	ByteOp | DstMem | SrcReg | ModRM | Mov, DstMem | SrcReg | ModRM | Mov,
 	ByteOp | DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov,
-	0, ModRM | DstReg, 0, DstMem | SrcNone | ModRM | Mov | Stack,
+	0, ModRM | DstReg, 0, Group | Group1A,
 	/* 0x90 - 0x9F */
 	0, 0, 0, 0, 0, 0, 0, 0,
 	0, 0, 0, 0, ImplicitOps | Stack, ImplicitOps | Stack, 0, 0,
@@ -164,16 +172,15 @@ static u16 opcode_table[256] = {
 	0, 0, 0, 0,
 	/* 0xF0 - 0xF7 */
 	0, 0, 0, 0,
-	ImplicitOps, ImplicitOps,
-	ByteOp | DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM,
+	ImplicitOps, ImplicitOps, Group | Group3_Byte, Group | Group3,
 	/* 0xF8 - 0xFF */
 	ImplicitOps, 0, ImplicitOps, ImplicitOps,
-	0, 0, ByteOp | DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM
+	0, 0, Group | Group4, Group | Group5,
 };
 
 static u16 twobyte_table[256] = {
 	/* 0x00 - 0x0F */
-	0, SrcMem | ModRM | DstReg, 0, 0, 0, 0, ImplicitOps, 0,
+	0, Group | GroupDual | Group7, 0, 0, 0, 0, ImplicitOps, 0,
 	ImplicitOps, ImplicitOps, 0, 0, 0, ImplicitOps | ModRM, 0, 0,
 	/* 0x10 - 0x1F */
 	0, 0, 0, 0, 0, 0, 0, 0, ImplicitOps | ModRM, 0, 0, 0, 0, 0, 0, 0,
@@ -229,6 +236,56 @@ static u16 twobyte_table[256] = {
 	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
 };
 
+static u16 group_table[] = {
+	[Group1_80*8] =
+	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+	[Group1_81*8] =
+	DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM,
+	DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM,
+	DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM,
+	DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM,
+	[Group1_82*8] =
+	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+	[Group1_83*8] =
+	DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM,
+	DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM,
+	DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM,
+	DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM,
+	[Group1A*8] =
+	DstMem | SrcNone | ModRM | Mov | Stack, 0, 0, 0, 0, 0, 0, 0,
+	[Group3_Byte*8] =
+	ByteOp | SrcImm | DstMem | ModRM, 0,
+	ByteOp | DstMem | SrcNone | ModRM, ByteOp | DstMem | SrcNone | ModRM,
+	0, 0, 0, 0,
+	[Group3*8] =
+	DstMem | SrcImm | ModRM | SrcImm, 0,
+	DstMem | SrcNone | ModRM, ByteOp | DstMem | SrcNone | ModRM,
+	0, 0, 0, 0,
+	[Group4*8] =
+	ByteOp | DstMem | SrcNone | ModRM, ByteOp | DstMem | SrcNone | ModRM,
+	0, 0, 0, 0, 0, 0,
+	[Group5*8] =
+	DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM, 0, 0,
+	SrcMem | ModRM, 0, SrcMem | ModRM | Stack, 0,
+	[Group7*8] =
+	0, 0, ModRM | SrcMem, ModRM | SrcMem,
+	SrcNone | ModRM | DstMem | Mov, 0,
+	SrcMem16 | ModRM | Mov, SrcMem | ModRM | ByteOp,
+};
+
+static u16 group2_table[] = {
+	[Group7*8] =
+	SrcNone | ModRM, 0, 0, 0,
+	SrcNone | ModRM | DstMem | Mov, 0,
+	SrcMem16 | ModRM | Mov, 0,
+};
+
 /* EFLAGS bit definitions. */
 #define EFLG_OF (1<<11)
 #define EFLG_DF (1<<10)
@@ -317,7 +374,7 @@ static u16 twobyte_table[256] = {
 
 #define __emulate_2op(_op,_src,_dst,_eflags,_bx,_by,_wx,_wy,_lx,_ly,_qx,_qy) \
 	do {								     \
-		unsigned long _tmp;					     \
+		unsigned long __tmp;					     \
 		switch ((_dst).bytes) {				             \
 		case 1:							     \
 			__asm__ __volatile__ (				     \
@@ -325,7 +382,7 @@ static u16 twobyte_table[256] = {
 				_op"b %"_bx"3,%1; "			     \
 				_POST_EFLAGS("0", "4", "2")		     \
 				: "=m" (_eflags), "=m" ((_dst).val),	     \
-				  "=&r" (_tmp)				     \
+				  "=&r" (__tmp)				     \
 				: _by ((_src).val), "i" (EFLAGS_MASK));      \
 			break;						     \
 		default:						     \
@@ -426,29 +483,40 @@ static u16 twobyte_table[256] = {
 	(_type)_x;							\
 })
 
+static inline unsigned long ad_mask(struct decode_cache *c)
+{
+	return (1UL << (c->ad_bytes << 3)) - 1;
+}
+
 /* Access/update address held in a register, based on addressing mode. */
-#define address_mask(reg)						\
-	((c->ad_bytes == sizeof(unsigned long)) ? 			\
-		(reg) :	((reg) & ((1UL << (c->ad_bytes << 3)) - 1)))
-#define register_address(base, reg)                                     \
-	((base) + address_mask(reg))
-#define register_address_increment(reg, inc)                            \
-	do {								\
-		/* signed type ensures sign extension to long */        \
-		int _inc = (inc);					\
-		if (c->ad_bytes == sizeof(unsigned long))		\
-			(reg) += _inc;					\
-		else							\
-			(reg) = ((reg) & 				\
-				 ~((1UL << (c->ad_bytes << 3)) - 1)) |	\
-				(((reg) + _inc) &			\
-				 ((1UL << (c->ad_bytes << 3)) - 1));	\
-	} while (0)
+static inline unsigned long
+address_mask(struct decode_cache *c, unsigned long reg)
+{
+	if (c->ad_bytes == sizeof(unsigned long))
+		return reg;
+	else
+		return reg & ad_mask(c);
+}
 
-#define JMP_REL(rel) 							\
-	do {								\
-		register_address_increment(c->eip, rel);		\
-	} while (0)
+static inline unsigned long
+register_address(struct decode_cache *c, unsigned long base, unsigned long reg)
+{
+	return base + address_mask(c, reg);
+}
+
+static inline void
+register_address_increment(struct decode_cache *c, unsigned long *reg, int inc)
+{
+	if (c->ad_bytes == sizeof(unsigned long))
+		*reg += inc;
+	else
+		*reg = (*reg & ~ad_mask(c)) | ((*reg + inc) & ad_mask(c));
+}
+
+static inline void jmp_rel(struct decode_cache *c, int rel)
+{
+	register_address_increment(c, &c->eip, rel);
+}
 
 static int do_fetch_insn_byte(struct x86_emulate_ctxt *ctxt,
 			      struct x86_emulate_ops *ops,
@@ -763,7 +831,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	struct decode_cache *c = &ctxt->decode;
 	int rc = 0;
 	int mode = ctxt->mode;
-	int def_op_bytes, def_ad_bytes;
+	int def_op_bytes, def_ad_bytes, group;
 
 	/* Shadow copy of register state. Committed on successful emulation. */
 
@@ -864,12 +932,24 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 			c->b = insn_fetch(u8, 1, c->eip);
 			c->d = twobyte_table[c->b];
 		}
+	}
 
-		/* Unrecognised? */
-		if (c->d == 0) {
-			DPRINTF("Cannot emulate %02x\n", c->b);
-			return -1;
-		}
+	if (c->d & Group) {
+		group = c->d & GroupMask;
+		c->modrm = insn_fetch(u8, 1, c->eip);
+		--c->eip;
+
+		group = (group << 3) + ((c->modrm >> 3) & 7);
+		if ((c->d & GroupDual) && (c->modrm >> 6) == 3)
+			c->d = group2_table[group];
+		else
+			c->d = group_table[group];
+	}
+
+	/* Unrecognised? */
+	if (c->d == 0) {
+		DPRINTF("Cannot emulate %02x\n", c->b);
+		return -1;
 	}
 
 	if (mode == X86EMUL_MODE_PROT64 && (c->d & Stack))
@@ -924,6 +1004,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		 */
 		if ((c->d & ModRM) && c->modrm_mod == 3) {
 			c->src.type = OP_REG;
+			c->src.val = c->modrm_val;
 			break;
 		}
 		c->src.type = OP_MEM;
@@ -967,6 +1048,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	case DstMem:
 		if ((c->d & ModRM) && c->modrm_mod == 3) {
 			c->dst.type = OP_REG;
+			c->dst.val = c->dst.orig_val = c->modrm_val;
 			break;
 		}
 		c->dst.type = OP_MEM;
@@ -984,8 +1066,8 @@ static inline void emulate_push(struct x86_emulate_ctxt *ctxt)
 	c->dst.type  = OP_MEM;
 	c->dst.bytes = c->op_bytes;
 	c->dst.val = c->src.val;
-	register_address_increment(c->regs[VCPU_REGS_RSP], -c->op_bytes);
-	c->dst.ptr = (void *) register_address(ctxt->ss_base,
+	register_address_increment(c, &c->regs[VCPU_REGS_RSP], -c->op_bytes);
+	c->dst.ptr = (void *) register_address(c, ctxt->ss_base,
 					       c->regs[VCPU_REGS_RSP]);
 }
 
@@ -995,13 +1077,13 @@ static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt,
 	struct decode_cache *c = &ctxt->decode;
 	int rc;
 
-	rc = ops->read_std(register_address(ctxt->ss_base,
+	rc = ops->read_std(register_address(c, ctxt->ss_base,
 					    c->regs[VCPU_REGS_RSP]),
 			   &c->dst.val, c->dst.bytes, ctxt->vcpu);
 	if (rc != 0)
 		return rc;
 
-	register_address_increment(c->regs[VCPU_REGS_RSP], c->dst.bytes);
+	register_address_increment(c, &c->regs[VCPU_REGS_RSP], c->dst.bytes);
 
 	return 0;
 }
@@ -1043,26 +1125,6 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt,
 
 	switch (c->modrm_reg) {
 	case 0 ... 1:	/* test */
-		/*
-		 * Special case in Grp3: test has an immediate
-		 * source operand.
-		 */
-		c->src.type = OP_IMM;
-		c->src.ptr = (unsigned long *)c->eip;
-		c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		if (c->src.bytes == 8)
-			c->src.bytes = 4;
-		switch (c->src.bytes) {
-		case 1:
-			c->src.val = insn_fetch(s8, 1, c->eip);
-			break;
-		case 2:
-			c->src.val = insn_fetch(s16, 2, c->eip);
-			break;
-		case 4:
-			c->src.val = insn_fetch(s32, 4, c->eip);
-			break;
-		}
 		emulate_2op_SrcV("test", c->src, c->dst, ctxt->eflags);
 		break;
 	case 2:	/* not */
@@ -1076,7 +1138,6 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt,
 		rc = X86EMUL_UNHANDLEABLE;
 		break;
 	}
-done:
 	return rc;
 }
 
@@ -1084,7 +1145,6 @@ static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt,
 			       struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	int rc;
 
 	switch (c->modrm_reg) {
 	case 0:	/* inc */
@@ -1094,36 +1154,11 @@ static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt,
 		emulate_1op("dec", c->dst, ctxt->eflags);
 		break;
 	case 4: /* jmp abs */
-		if (c->b == 0xff)
-			c->eip = c->dst.val;
-		else {
-			DPRINTF("Cannot emulate %02x\n", c->b);
-			return X86EMUL_UNHANDLEABLE;
-		}
+		c->eip = c->src.val;
 		break;
 	case 6:	/* push */
-
-		/* 64-bit mode: PUSH always pushes a 64-bit operand. */
-
-		if (ctxt->mode == X86EMUL_MODE_PROT64) {
-			c->dst.bytes = 8;
-			rc = ops->read_std((unsigned long)c->dst.ptr,
-					   &c->dst.val, 8, ctxt->vcpu);
-			if (rc != 0)
-				return rc;
-		}
-		register_address_increment(c->regs[VCPU_REGS_RSP],
-					   -c->dst.bytes);
-		rc = ops->write_emulated(register_address(ctxt->ss_base,
-				    c->regs[VCPU_REGS_RSP]), &c->dst.val,
-				    c->dst.bytes, ctxt->vcpu);
-		if (rc != 0)
-			return rc;
-		c->dst.type = OP_NONE;
+		emulate_push(ctxt);
 		break;
-	default:
-		DPRINTF("Cannot emulate %02x\n", c->b);
-		return X86EMUL_UNHANDLEABLE;
 	}
 	return 0;
 }
@@ -1361,19 +1396,19 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		c->dst.type  = OP_MEM;
 		c->dst.bytes = c->op_bytes;
 		c->dst.val = c->src.val;
-		register_address_increment(c->regs[VCPU_REGS_RSP],
+		register_address_increment(c, &c->regs[VCPU_REGS_RSP],
 					   -c->op_bytes);
 		c->dst.ptr = (void *) register_address(
-			ctxt->ss_base, c->regs[VCPU_REGS_RSP]);
+			c, ctxt->ss_base, c->regs[VCPU_REGS_RSP]);
 		break;
 	case 0x58 ... 0x5f: /* pop reg */
 	pop_instruction:
-		if ((rc = ops->read_std(register_address(ctxt->ss_base,
+		if ((rc = ops->read_std(register_address(c, ctxt->ss_base,
 			c->regs[VCPU_REGS_RSP]), c->dst.ptr,
 			c->op_bytes, ctxt->vcpu)) != 0)
 			goto done;
 
-		register_address_increment(c->regs[VCPU_REGS_RSP],
+		register_address_increment(c, &c->regs[VCPU_REGS_RSP],
 					   c->op_bytes);
 		c->dst.type = OP_NONE;	/* Disable writeback. */
 		break;
@@ -1393,9 +1428,9 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 				1,
 				(c->d & ByteOp) ? 1 : c->op_bytes,
 				c->rep_prefix ?
-				address_mask(c->regs[VCPU_REGS_RCX]) : 1,
+				address_mask(c, c->regs[VCPU_REGS_RCX]) : 1,
 				(ctxt->eflags & EFLG_DF),
-				register_address(ctxt->es_base,
+				register_address(c, ctxt->es_base,
 						 c->regs[VCPU_REGS_RDI]),
 				c->rep_prefix,
 				c->regs[VCPU_REGS_RDX]) == 0) {
@@ -1409,9 +1444,9 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 				0,
 				(c->d & ByteOp) ? 1 : c->op_bytes,
 				c->rep_prefix ?
-				address_mask(c->regs[VCPU_REGS_RCX]) : 1,
+				address_mask(c, c->regs[VCPU_REGS_RCX]) : 1,
 				(ctxt->eflags & EFLG_DF),
-				register_address(c->override_base ?
+				register_address(c, c->override_base ?
 							*c->override_base :
 							ctxt->ds_base,
 						 c->regs[VCPU_REGS_RSI]),
@@ -1425,7 +1460,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		int rel = insn_fetch(s8, 1, c->eip);
 
 		if (test_cc(c->b, ctxt->eflags))
-			JMP_REL(rel);
+			jmp_rel(c, rel);
 		break;
 	}
 	case 0x80 ... 0x83:	/* Grp1 */
@@ -1477,7 +1512,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	case 0x88 ... 0x8b:	/* mov */
 		goto mov;
 	case 0x8d: /* lea r16/r32, m */
-		c->dst.val = c->modrm_val;
+		c->dst.val = c->modrm_ea;
 		break;
 	case 0x8f:		/* pop (sole member of Grp1a) */
 		rc = emulate_grp1a(ctxt, ops);
@@ -1501,27 +1536,27 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	case 0xa4 ... 0xa5:	/* movs */
 		c->dst.type = OP_MEM;
 		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->dst.ptr = (unsigned long *)register_address(
+		c->dst.ptr = (unsigned long *)register_address(c,
 						   ctxt->es_base,
 						   c->regs[VCPU_REGS_RDI]);
-		if ((rc = ops->read_emulated(register_address(
+		if ((rc = ops->read_emulated(register_address(c,
 		      c->override_base ? *c->override_base :
 					ctxt->ds_base,
 					c->regs[VCPU_REGS_RSI]),
 					&c->dst.val,
 					c->dst.bytes, ctxt->vcpu)) != 0)
 			goto done;
-		register_address_increment(c->regs[VCPU_REGS_RSI],
+		register_address_increment(c, &c->regs[VCPU_REGS_RSI],
 				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
 							   : c->dst.bytes);
-		register_address_increment(c->regs[VCPU_REGS_RDI],
+		register_address_increment(c, &c->regs[VCPU_REGS_RDI],
 				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
 							   : c->dst.bytes);
 		break;
 	case 0xa6 ... 0xa7:	/* cmps */
 		c->src.type = OP_NONE; /* Disable writeback. */
 		c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->src.ptr = (unsigned long *)register_address(
+		c->src.ptr = (unsigned long *)register_address(c,
 				c->override_base ? *c->override_base :
 						   ctxt->ds_base,
 						   c->regs[VCPU_REGS_RSI]);
@@ -1533,7 +1568,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 
 		c->dst.type = OP_NONE; /* Disable writeback. */
 		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->dst.ptr = (unsigned long *)register_address(
+		c->dst.ptr = (unsigned long *)register_address(c,
 						   ctxt->es_base,
 						   c->regs[VCPU_REGS_RDI]);
 		if ((rc = ops->read_emulated((unsigned long)c->dst.ptr,
@@ -1546,10 +1581,10 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 
 		emulate_2op_SrcV("cmp", c->src, c->dst, ctxt->eflags);
 
-		register_address_increment(c->regs[VCPU_REGS_RSI],
+		register_address_increment(c, &c->regs[VCPU_REGS_RSI],
 				       (ctxt->eflags & EFLG_DF) ? -c->src.bytes
 								  : c->src.bytes);
-		register_address_increment(c->regs[VCPU_REGS_RDI],
+		register_address_increment(c, &c->regs[VCPU_REGS_RDI],
 				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
 								  : c->dst.bytes);
 
@@ -1557,11 +1592,11 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	case 0xaa ... 0xab:	/* stos */
 		c->dst.type = OP_MEM;
 		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->dst.ptr = (unsigned long *)register_address(
+		c->dst.ptr = (unsigned long *)register_address(c,
 						   ctxt->es_base,
 						   c->regs[VCPU_REGS_RDI]);
 		c->dst.val = c->regs[VCPU_REGS_RAX];
-		register_address_increment(c->regs[VCPU_REGS_RDI],
+		register_address_increment(c, &c->regs[VCPU_REGS_RDI],
 				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
 							   : c->dst.bytes);
 		break;
@@ -1569,7 +1604,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		c->dst.type = OP_REG;
 		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
 		c->dst.ptr = (unsigned long *)&c->regs[VCPU_REGS_RAX];
-		if ((rc = ops->read_emulated(register_address(
+		if ((rc = ops->read_emulated(register_address(c,
 				c->override_base ? *c->override_base :
 						   ctxt->ds_base,
 						 c->regs[VCPU_REGS_RSI]),
@@ -1577,7 +1612,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 						 c->dst.bytes,
 						 ctxt->vcpu)) != 0)
 			goto done;
-		register_address_increment(c->regs[VCPU_REGS_RSI],
+		register_address_increment(c, &c->regs[VCPU_REGS_RSI],
 				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
 							   : c->dst.bytes);
 		break;
@@ -1616,14 +1651,14 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 			goto cannot_emulate;
 		}
 		c->src.val = (unsigned long) c->eip;
-		JMP_REL(rel);
+		jmp_rel(c, rel);
 		c->op_bytes = c->ad_bytes;
 		emulate_push(ctxt);
 		break;
 	}
 	case 0xe9: /* jmp rel */
 	case 0xeb: /* jmp rel short */
-		JMP_REL(c->src.val);
+		jmp_rel(c, c->src.val);
 		c->dst.type = OP_NONE; /* Disable writeback. */
 		break;
 	case 0xf4:              /* hlt */
@@ -1690,6 +1725,8 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 				goto done;
 
 			kvm_emulate_hypercall(ctxt->vcpu);
+			/* Disable writeback. */
+			c->dst.type = OP_NONE;
 			break;
 		case 2: /* lgdt */
 			rc = read_descriptor(ctxt, ops, c->src.ptr,
@@ -1697,6 +1734,8 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 			if (rc)
 				goto done;
 			realmode_lgdt(ctxt->vcpu, size, address);
+			/* Disable writeback. */
+			c->dst.type = OP_NONE;
 			break;
 		case 3: /* lidt/vmmcall */
 			if (c->modrm_mod == 3 && c->modrm_rm == 1) {
@@ -1712,27 +1751,25 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 					goto done;
 				realmode_lidt(ctxt->vcpu, size, address);
 			}
+			/* Disable writeback. */
+			c->dst.type = OP_NONE;
 			break;
 		case 4: /* smsw */
-			if (c->modrm_mod != 3)
-				goto cannot_emulate;
-			*(u16 *)&c->regs[c->modrm_rm]
-				= realmode_get_cr(ctxt->vcpu, 0);
+			c->dst.bytes = 2;
+			c->dst.val = realmode_get_cr(ctxt->vcpu, 0);
 			break;
 		case 6: /* lmsw */
-			if (c->modrm_mod != 3)
-				goto cannot_emulate;
-			realmode_lmsw(ctxt->vcpu, (u16)c->modrm_val,
-						  &ctxt->eflags);
+			realmode_lmsw(ctxt->vcpu, (u16)c->src.val,
+				      &ctxt->eflags);
 			break;
 		case 7: /* invlpg*/
 			emulate_invlpg(ctxt->vcpu, memop);
+			/* Disable writeback. */
+			c->dst.type = OP_NONE;
 			break;
 		default:
 			goto cannot_emulate;
 		}
-		/* Disable writeback. */
-		c->dst.type = OP_NONE;
 		break;
 	case 0x06:
 		emulate_clts(ctxt->vcpu);
@@ -1823,7 +1860,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 			goto cannot_emulate;
 		}
 		if (test_cc(c->b, ctxt->eflags))
-			JMP_REL(rel);
+			jmp_rel(c, rel);
 		c->dst.type = OP_NONE;
 		break;
 	}
diff --git a/trunk/arch/x86/mm/init_32.c b/trunk/arch/x86/mm/init_32.c
index 4a4761892951..de236e419cb5 100644
--- a/trunk/arch/x86/mm/init_32.c
+++ b/trunk/arch/x86/mm/init_32.c
@@ -287,47 +287,17 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base)
 	pkmap_page_table = pte;
 }
 
-static void __meminit free_new_highpage(struct page *page)
-{
-	init_page_count(page);
-	__free_page(page);
-	totalhigh_pages++;
-}
-
 void __init add_one_highpage_init(struct page *page, int pfn, int bad_ppro)
 {
 	if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) {
 		ClearPageReserved(page);
-		free_new_highpage(page);
+		init_page_count(page);
+		__free_page(page);
+		totalhigh_pages++;
 	} else
 		SetPageReserved(page);
 }
 
-static int __meminit
-add_one_highpage_hotplug(struct page *page, unsigned long pfn)
-{
-	free_new_highpage(page);
-	totalram_pages++;
-#ifdef CONFIG_FLATMEM
-	max_mapnr = max(pfn, max_mapnr);
-#endif
-	num_physpages++;
-
-	return 0;
-}
-
-/*
- * Not currently handling the NUMA case.
- * Assuming single node and all memory that
- * has been added dynamically that would be
- * onlined here is in HIGHMEM.
- */
-void __meminit online_page(struct page *page)
-{
-	ClearPageReserved(page);
-	add_one_highpage_hotplug(page, page_to_pfn(page));
-}
-
 #ifndef CONFIG_NUMA
 static void __init set_highmem_pages_init(int bad_ppro)
 {
diff --git a/trunk/arch/x86/mm/init_64.c b/trunk/arch/x86/mm/init_64.c
index 5fbb8652cf59..32ba13b0f818 100644
--- a/trunk/arch/x86/mm/init_64.c
+++ b/trunk/arch/x86/mm/init_64.c
@@ -620,15 +620,6 @@ void __init paging_init(void)
 /*
  * Memory hotplug specific functions
  */
-void online_page(struct page *page)
-{
-	ClearPageReserved(page);
-	init_page_count(page);
-	__free_page(page);
-	totalram_pages++;
-	num_physpages++;
-}
-
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * Memory is added always to NORMAL zone. This means you will never get
diff --git a/trunk/arch/x86/mm/ioremap.c b/trunk/arch/x86/mm/ioremap.c
index d176b23110cc..804de18abcc2 100644
--- a/trunk/arch/x86/mm/ioremap.c
+++ b/trunk/arch/x86/mm/ioremap.c
@@ -117,8 +117,8 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size,
  * have to convert them into an offset in a page-aligned mapping, but the
  * caller shouldn't need to know that small detail.
  */
-static void __iomem *__ioremap(resource_size_t phys_addr, unsigned long size,
-			       unsigned long prot_val)
+static void __iomem *__ioremap_caller(resource_size_t phys_addr,
+		unsigned long size, unsigned long prot_val, void *caller)
 {
 	unsigned long pfn, offset, vaddr;
 	resource_size_t last_addr;
@@ -212,7 +212,7 @@ static void __iomem *__ioremap(resource_size_t phys_addr, unsigned long size,
 	/*
 	 * Ok, go for it..
 	 */
-	area = get_vm_area(size, VM_IOREMAP);
+	area = get_vm_area_caller(size, VM_IOREMAP, caller);
 	if (!area)
 		return NULL;
 	area->phys_addr = phys_addr;
@@ -255,7 +255,8 @@ static void __iomem *__ioremap(resource_size_t phys_addr, unsigned long size,
  */
 void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
 {
-	return __ioremap(phys_addr, size, _PAGE_CACHE_UC);
+	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_UC,
+				__builtin_return_address(0));
 }
 EXPORT_SYMBOL(ioremap_nocache);
 
@@ -272,7 +273,8 @@ EXPORT_SYMBOL(ioremap_nocache);
 void __iomem *ioremap_wc(unsigned long phys_addr, unsigned long size)
 {
 	if (pat_wc_enabled)
-		return __ioremap(phys_addr, size, _PAGE_CACHE_WC);
+		return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WC,
+					__builtin_return_address(0));
 	else
 		return ioremap_nocache(phys_addr, size);
 }
@@ -280,7 +282,8 @@ EXPORT_SYMBOL(ioremap_wc);
 
 void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
 {
-	return __ioremap(phys_addr, size, _PAGE_CACHE_WB);
+	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WB,
+				__builtin_return_address(0));
 }
 EXPORT_SYMBOL(ioremap_cache);
 
diff --git a/trunk/arch/x86/mm/pat.c b/trunk/arch/x86/mm/pat.c
index e7ca7fc48d12..277446cd30b6 100644
--- a/trunk/arch/x86/mm/pat.c
+++ b/trunk/arch/x86/mm/pat.c
@@ -387,8 +387,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 				break;
 			}
 
-			printk(KERN_INFO "Overlap at 0x%Lx-0x%Lx\n",
-			       saved_ptr->start, saved_ptr->end);
+			pr_debug(KERN_INFO "Overlap at 0x%Lx-0x%Lx\n",
+				 saved_ptr->start, saved_ptr->end);
 			/* No conflict. Go ahead and add this new entry */
 			list_add(&new_entry->nd, &saved_ptr->nd);
 			new_entry = NULL;
@@ -510,7 +510,6 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 {
 	u64 offset = ((u64) pfn) << PAGE_SHIFT;
 	unsigned long flags = _PAGE_CACHE_UC_MINUS;
-	unsigned long ret_flags;
 	int retval;
 
 	if (!range_is_allowed(pfn, size))
@@ -549,14 +548,12 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 	if (flags != _PAGE_CACHE_UC_MINUS) {
 		retval = reserve_memtype(offset, offset + size, flags, NULL);
 	} else {
-		retval = reserve_memtype(offset, offset + size, -1, &ret_flags);
+		retval = reserve_memtype(offset, offset + size, -1, &flags);
 	}
 
 	if (retval < 0)
 		return 0;
 
-	flags = ret_flags;
-
 	if (pfn <= max_pfn_mapped &&
             ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) {
 		free_memtype(offset, offset + size);
diff --git a/trunk/arch/x86/pci/Makefile_32 b/trunk/arch/x86/pci/Makefile_32
index e9c5caf54e59..2a1516efb542 100644
--- a/trunk/arch/x86/pci/Makefile_32
+++ b/trunk/arch/x86/pci/Makefile_32
@@ -3,6 +3,7 @@ obj-y				:= i386.o init.o
 obj-$(CONFIG_PCI_BIOS)		+= pcbios.o
 obj-$(CONFIG_PCI_MMCONFIG)	+= mmconfig_32.o direct.o mmconfig-shared.o
 obj-$(CONFIG_PCI_DIRECT)	+= direct.o
+obj-$(CONFIG_PCI_OLPC)		+= olpc.o
 
 pci-y				:= fixup.o
 pci-$(CONFIG_ACPI)		+= acpi.o
diff --git a/trunk/arch/x86/pci/init.c b/trunk/arch/x86/pci/init.c
index 343c36337e69..dd30c6076b5d 100644
--- a/trunk/arch/x86/pci/init.c
+++ b/trunk/arch/x86/pci/init.c
@@ -11,8 +11,12 @@ static __init int pci_access_init(void)
 
 	type = pci_direct_probe();
 #endif
+
 	pci_mmcfg_early_init();
 
+#ifdef CONFIG_PCI_OLPC
+	pci_olpc_init();
+#endif
 #ifdef CONFIG_PCI_BIOS
 	pci_pcbios_init();
 #endif
diff --git a/trunk/arch/x86/pci/olpc.c b/trunk/arch/x86/pci/olpc.c
new file mode 100644
index 000000000000..5e7636558c02
--- /dev/null
+++ b/trunk/arch/x86/pci/olpc.c
@@ -0,0 +1,313 @@
+/*
+ * Low-level PCI config space access for OLPC systems who lack the VSA
+ * PCI virtualization software.
+ *
+ * Copyright © 2006  Advanced Micro Devices, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * The AMD Geode chipset (ie: GX2 processor, cs5536 I/O companion device)
+ * has some I/O functions (display, southbridge, sound, USB HCIs, etc)
+ * that more or less behave like PCI devices, but the hardware doesn't
+ * directly implement the PCI configuration space headers.  AMD provides
+ * "VSA" (Virtual System Architecture) software that emulates PCI config
+ * space for these devices, by trapping I/O accesses to PCI config register
+ * (CF8/CFC) and running some code in System Management Mode interrupt state.
+ * On the OLPC platform, we don't want to use that VSA code because
+ * (a) it slows down suspend/resume, and (b) recompiling it requires special
+ * compilers that are hard to get.  So instead of letting the complex VSA
+ * code simulate the PCI config registers for the on-chip devices, we
+ * just simulate them the easy way, by inserting the code into the
+ * pci_write_config and pci_read_config path.  Most of the config registers
+ * are read-only anyway, so the bulk of the simulation is just table lookup.
+ */
+
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <asm/olpc.h>
+#include <asm/geode.h>
+#include "pci.h"
+
+/*
+ * In the tables below, the first two line (8 longwords) are the
+ * size masks that are used when the higher level PCI code determines
+ * the size of the region by writing ~0 to a base address register
+ * and reading back the result.
+ *
+ * The following lines are the values that are read during normal
+ * PCI config access cycles, i.e. not after just having written
+ * ~0 to a base address register.
+ */
+
+static const uint32_t lxnb_hdr[] = {  /* dev 1 function 0 - devfn = 8 */
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+
+	0x281022, 0x2200005, 0x6000021, 0x80f808,	/* AMD Vendor ID */
+	0x0,	0x0,	0x0,	0x0,   /* No virtual registers, hence no BAR */
+	0x0,	0x0,	0x0,	0x28100b,
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+};
+
+static const uint32_t gxnb_hdr[] = {  /* dev 1 function 0 - devfn = 8 */
+	0xfffffffd, 0x0, 0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+
+	0x28100b, 0x2200005, 0x6000021, 0x80f808,	/* NSC Vendor ID */
+	0xac1d,	0x0,	0x0,	0x0,  /* I/O BAR - base of virtual registers */
+	0x0,	0x0,	0x0,	0x28100b,
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+};
+
+static const uint32_t lxfb_hdr[] = {  /* dev 1 function 1 - devfn = 9 */
+	0xff000008, 0xffffc000, 0xffffc000, 0xffffc000,
+	0xffffc000,	0x0,	0x0,	0x0,
+
+	0x20811022, 0x2200003, 0x3000000, 0x0,		/* AMD Vendor ID */
+	0xfd000000, 0xfe000000, 0xfe004000, 0xfe008000, /* FB, GP, VG, DF */
+	0xfe00c000, 0x0, 0x0,	0x30100b,		/* VIP */
+	0x0,	0x0,	0x0,	0x10e,	   /* INTA, IRQ14 for graphics accel */
+	0x0,	0x0,	0x0,	0x0,
+	0x3d0,	0x3c0,	0xa0000, 0x0,	    /* VG IO, VG IO, EGA FB, MONO FB */
+	0x0,	0x0,	0x0,	0x0,
+};
+
+static const uint32_t gxfb_hdr[] = {  /* dev 1 function 1 - devfn = 9 */
+	0xff800008, 0xffffc000, 0xffffc000, 0xffffc000,
+	0x0,	0x0,	0x0,	0x0,
+
+	0x30100b, 0x2200003, 0x3000000, 0x0,		/* NSC Vendor ID */
+	0xfd000000, 0xfe000000, 0xfe004000, 0xfe008000,	/* FB, GP, VG, DF */
+	0x0,	0x0,	0x0,	0x30100b,
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+	0x3d0,	0x3c0,	0xa0000, 0x0,  	    /* VG IO, VG IO, EGA FB, MONO FB */
+	0x0,	0x0,	0x0,	0x0,
+};
+
+static const uint32_t aes_hdr[] = {	/* dev 1 function 2 - devfn = 0xa */
+	0xffffc000, 0x0, 0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+
+	0x20821022, 0x2a00006, 0x10100000, 0x8,		/* NSC Vendor ID */
+	0xfe010000, 0x0, 0x0,	0x0,			/* AES registers */
+	0x0,	0x0,	0x0,	0x20821022,
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+};
+
+
+static const uint32_t isa_hdr[] = {  /* dev f function 0 - devfn = 78 */
+	0xfffffff9, 0xffffff01, 0xffffffc1, 0xffffffe1,
+	0xffffff81, 0xffffffc1, 0x0, 0x0,
+
+	0x20901022, 0x2a00049, 0x6010003, 0x802000,
+	0x18b1,	0x1001,	0x1801,	0x1881,	/* SMB-8   GPIO-256 MFGPT-64  IRQ-32 */
+	0x1401,	0x1841,	0x0,	0x20901022,		/* PMS-128 ACPI-64 */
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0xaa5b,			/* IRQ steering */
+	0x0,	0x0,	0x0,	0x0,
+};
+
+static const uint32_t ac97_hdr[] = {  /* dev f function 3 - devfn = 7b */
+	0xffffff81, 0x0, 0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+
+	0x20931022, 0x2a00041, 0x4010001, 0x0,
+	0x1481,	0x0,	0x0,	0x0,			/* I/O BAR-128 */
+	0x0,	0x0,	0x0,	0x20931022,
+	0x0,	0x0,	0x0,	0x205,			/* IntB, IRQ5 */
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+};
+
+static const uint32_t ohci_hdr[] = {  /* dev f function 4 - devfn = 7c */
+	0xfffff000, 0x0, 0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+
+	0x20941022, 0x2300006, 0xc031002, 0x0,
+	0xfe01a000, 0x0, 0x0,	0x0,			/* MEMBAR-1000 */
+	0x0,	0x0,	0x0,	0x20941022,
+	0x0,	0x40,	0x0,	0x40a,			/* CapPtr INT-D, IRQA */
+	0xc8020001, 0x0, 0x0,	0x0,	/* Capabilities - 40 is R/O,
+					   44 is mask 8103 (power control) */
+	0x0,	0x0,	0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+};
+
+static const uint32_t ehci_hdr[] = {  /* dev f function 4 - devfn = 7d */
+	0xfffff000, 0x0, 0x0,	0x0,
+	0x0,	0x0,	0x0,	0x0,
+
+	0x20951022, 0x2300006, 0xc032002, 0x0,
+	0xfe01b000, 0x0, 0x0,	0x0,			/* MEMBAR-1000 */
+	0x0,	0x0,	0x0,	0x20951022,
+	0x0,	0x40,	0x0,	0x40a,			/* CapPtr INT-D, IRQA */
+	0xc8020001, 0x0, 0x0,	0x0,	/* Capabilities - 40 is R/O, 44 is
+					   mask 8103 (power control) */
+#if 0
+	0x1,	0x40080000, 0x0, 0x0,	/* EECP - see EHCI spec section 2.1.7 */
+#endif
+	0x01000001, 0x0, 0x0,	0x0,	/* EECP - see EHCI spec section 2.1.7 */
+	0x2020,	0x0,	0x0,	0x0,	/* (EHCI page 8) 60 SBRN (R/O),
+					   61 FLADJ (R/W), PORTWAKECAP  */
+};
+
+static uint32_t ff_loc = ~0;
+static uint32_t zero_loc;
+static int bar_probing;		/* Set after a write of ~0 to a BAR */
+static int is_lx;
+
+#define NB_SLOT 0x1	/* Northbridge - GX chip - Device 1 */
+#define SB_SLOT 0xf	/* Southbridge - CS5536 chip - Device F */
+
+static int is_simulated(unsigned int bus, unsigned int devfn)
+{
+	return (!bus && ((PCI_SLOT(devfn) == NB_SLOT) ||
+			(PCI_SLOT(devfn) == SB_SLOT)));
+}
+
+static uint32_t *hdr_addr(const uint32_t *hdr, int reg)
+{
+	uint32_t addr;
+
+	/*
+	 * This is a little bit tricky.  The header maps consist of
+	 * 0x20 bytes of size masks, followed by 0x70 bytes of header data.
+	 * In the normal case, when not probing a BAR's size, we want
+	 * to access the header data, so we add 0x20 to the reg offset,
+	 * thus skipping the size mask area.
+	 * In the BAR probing case, we want to access the size mask for
+	 * the BAR, so we subtract 0x10 (the config header offset for
+	 * BAR0), and don't skip the size mask area.
+	 */
+
+	addr = (uint32_t)hdr + reg + (bar_probing ? -0x10 : 0x20);
+
+	bar_probing = 0;
+	return (uint32_t *)addr;
+}
+
+static int pci_olpc_read(unsigned int seg, unsigned int bus,
+		unsigned int devfn, int reg, int len, uint32_t *value)
+{
+	uint32_t *addr;
+
+	/* Use the hardware mechanism for non-simulated devices */
+	if (!is_simulated(bus, devfn))
+		return pci_direct_conf1.read(seg, bus, devfn, reg, len, value);
+
+	/*
+	 * No device has config registers past 0x70, so we save table space
+	 * by not storing entries for the nonexistent registers
+	 */
+	if (reg >= 0x70)
+		addr = &zero_loc;
+	else {
+		switch (devfn) {
+		case  0x8:
+			addr = hdr_addr(is_lx ? lxnb_hdr : gxnb_hdr, reg);
+			break;
+		case  0x9:
+			addr = hdr_addr(is_lx ? lxfb_hdr : gxfb_hdr, reg);
+			break;
+		case  0xa:
+			addr = is_lx ? hdr_addr(aes_hdr, reg) : &ff_loc;
+			break;
+		case 0x78:
+			addr = hdr_addr(isa_hdr, reg);
+			break;
+		case 0x7b:
+			addr = hdr_addr(ac97_hdr, reg);
+			break;
+		case 0x7c:
+			addr = hdr_addr(ohci_hdr, reg);
+			break;
+		case 0x7d:
+			addr = hdr_addr(ehci_hdr, reg);
+			break;
+		default:
+			addr = &ff_loc;
+			break;
+		}
+	}
+	switch (len) {
+	case 1:
+		*value = *(uint8_t *)addr;
+		break;
+	case 2:
+		*value = *(uint16_t *)addr;
+		break;
+	case 4:
+		*value = *addr;
+		break;
+	default:
+		BUG();
+	}
+
+	return 0;
+}
+
+static int pci_olpc_write(unsigned int seg, unsigned int bus,
+		unsigned int devfn, int reg, int len, uint32_t value)
+{
+	/* Use the hardware mechanism for non-simulated devices */
+	if (!is_simulated(bus, devfn))
+		return pci_direct_conf1.write(seg, bus, devfn, reg, len, value);
+
+	/* XXX we may want to extend this to simulate EHCI power management */
+
+	/*
+	 * Mostly we just discard writes, but if the write is a size probe
+	 * (i.e. writing ~0 to a BAR), we remember it and arrange to return
+	 * the appropriate size mask on the next read.  This is cheating
+	 * to some extent, because it depends on the fact that the next
+	 * access after such a write will always be a read to the same BAR.
+	 */
+
+	if ((reg >= 0x10) && (reg < 0x2c)) {
+		/* write is to a BAR */
+		if (value == ~0)
+			bar_probing = 1;
+	} else {
+		/*
+		 * No warning on writes to ROM BAR, CMD, LATENCY_TIMER,
+		 * CACHE_LINE_SIZE, or PM registers.
+		 */
+		if ((reg != PCI_ROM_ADDRESS) && (reg != PCI_COMMAND_MASTER) &&
+				(reg != PCI_LATENCY_TIMER) &&
+				(reg != PCI_CACHE_LINE_SIZE) && (reg != 0x44))
+			printk(KERN_WARNING "OLPC PCI: Config write to devfn"
+				" %x reg %x value %x\n", devfn, reg, value);
+	}
+
+	return 0;
+}
+
+static struct pci_raw_ops pci_olpc_conf = {
+	.read =	pci_olpc_read,
+	.write = pci_olpc_write,
+};
+
+void __init pci_olpc_init(void)
+{
+	if (!machine_is_olpc() || olpc_has_vsa())
+		return;
+
+	printk(KERN_INFO "PCI: Using configuration type OLPC\n");
+	raw_pci_ops = &pci_olpc_conf;
+	is_lx = is_geode_lx();
+}
diff --git a/trunk/arch/x86/pci/pci.h b/trunk/arch/x86/pci/pci.h
index 8ef86b5c37c8..c58805a92db5 100644
--- a/trunk/arch/x86/pci/pci.h
+++ b/trunk/arch/x86/pci/pci.h
@@ -98,6 +98,7 @@ extern struct pci_raw_ops pci_direct_conf1;
 extern int pci_direct_probe(void);
 extern void pci_direct_init(int type);
 extern void pci_pcbios_init(void);
+extern void pci_olpc_init(void);
 
 /* pci-mmconfig.c */
 
diff --git a/trunk/arch/x86/vdso/vdso.S b/trunk/arch/x86/vdso/vdso.S
index 4b1620a1529e..1d3aa6b87181 100644
--- a/trunk/arch/x86/vdso/vdso.S
+++ b/trunk/arch/x86/vdso/vdso.S
@@ -1,2 +1,10 @@
-	.section ".vdso","a"
+#include <linux/init.h>
+
+__INITDATA
+
+	.globl vdso_start, vdso_end
+vdso_start:
 	.incbin "arch/x86/vdso/vdso.so"
+vdso_end:
+
+__FINIT
diff --git a/trunk/arch/x86/xen/mmu.c b/trunk/arch/x86/xen/mmu.c
index 6cbcf65609ad..126766d43aea 100644
--- a/trunk/arch/x86/xen/mmu.c
+++ b/trunk/arch/x86/xen/mmu.c
@@ -387,7 +387,7 @@ static void xen_do_pin(unsigned level, unsigned long pfn)
 
 static int pin_page(struct page *page, enum pt_level level)
 {
-	unsigned pgfl = test_and_set_bit(PG_pinned, &page->flags);
+	unsigned pgfl = TestSetPagePinned(page);
 	int flush;
 
 	if (pgfl)
@@ -468,7 +468,7 @@ void __init xen_mark_init_mm_pinned(void)
 
 static int unpin_page(struct page *page, enum pt_level level)
 {
-	unsigned pgfl = test_and_clear_bit(PG_pinned, &page->flags);
+	unsigned pgfl = TestClearPagePinned(page);
 
 	if (pgfl && !PageHighMem(page)) {
 		void *pt = lowmem_page_address(page);
diff --git a/trunk/arch/xtensa/kernel/asm-offsets.c b/trunk/arch/xtensa/kernel/asm-offsets.c
index ef63adadf7f4..070ff8af3a21 100644
--- a/trunk/arch/xtensa/kernel/asm-offsets.c
+++ b/trunk/arch/xtensa/kernel/asm-offsets.c
@@ -19,12 +19,11 @@
 #include <linux/thread_info.h>
 #include <linux/ptrace.h>
 #include <linux/mm.h>
+#include <linux/kbuild.h>
 
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
 
-#define DEFINE(sym, val) asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
 int main(void)
 {
 	/* struct pt_regs */
diff --git a/trunk/block/blk-barrier.c b/trunk/block/blk-barrier.c
index 55c5f1fc4f1f..66e55288178c 100644
--- a/trunk/block/blk-barrier.c
+++ b/trunk/block/blk-barrier.c
@@ -53,7 +53,7 @@ EXPORT_SYMBOL(blk_queue_ordered);
 /*
  * Cache flushing for ordered writes handling
  */
-inline unsigned blk_ordered_cur_seq(struct request_queue *q)
+unsigned blk_ordered_cur_seq(struct request_queue *q)
 {
 	if (!q->ordseq)
 		return 0;
@@ -143,10 +143,8 @@ static void queue_flush(struct request_queue *q, unsigned which)
 		end_io = post_flush_end_io;
 	}
 
+	blk_rq_init(q, rq);
 	rq->cmd_flags = REQ_HARDBARRIER;
-	rq_init(q, rq);
-	rq->elevator_private = NULL;
-	rq->elevator_private2 = NULL;
 	rq->rq_disk = q->bar_rq.rq_disk;
 	rq->end_io = end_io;
 	q->prepare_flush_fn(q, rq);
@@ -167,14 +165,11 @@ static inline struct request *start_ordered(struct request_queue *q,
 	blkdev_dequeue_request(rq);
 	q->orig_bar_rq = rq;
 	rq = &q->bar_rq;
-	rq->cmd_flags = 0;
-	rq_init(q, rq);
+	blk_rq_init(q, rq);
 	if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
 		rq->cmd_flags |= REQ_RW;
 	if (q->ordered & QUEUE_ORDERED_FUA)
 		rq->cmd_flags |= REQ_FUA;
-	rq->elevator_private = NULL;
-	rq->elevator_private2 = NULL;
 	init_request_from_bio(rq, q->orig_bar_rq->bio);
 	rq->end_io = bar_end_io;
 
diff --git a/trunk/block/blk-core.c b/trunk/block/blk-core.c
index 2a438a93f723..5d09f8c56024 100644
--- a/trunk/block/blk-core.c
+++ b/trunk/block/blk-core.c
@@ -107,41 +107,21 @@ struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
 }
 EXPORT_SYMBOL(blk_get_backing_dev_info);
 
-/*
- * We can't just memset() the structure, since the allocation path
- * already stored some information in the request.
- */
-void rq_init(struct request_queue *q, struct request *rq)
+void blk_rq_init(struct request_queue *q, struct request *rq)
 {
+	memset(rq, 0, sizeof(*rq));
+
 	INIT_LIST_HEAD(&rq->queuelist);
 	INIT_LIST_HEAD(&rq->donelist);
 	rq->q = q;
 	rq->sector = rq->hard_sector = (sector_t) -1;
-	rq->nr_sectors = rq->hard_nr_sectors = 0;
-	rq->current_nr_sectors = rq->hard_cur_sectors = 0;
-	rq->bio = rq->biotail = NULL;
 	INIT_HLIST_NODE(&rq->hash);
 	RB_CLEAR_NODE(&rq->rb_node);
-	rq->rq_disk = NULL;
-	rq->nr_phys_segments = 0;
-	rq->nr_hw_segments = 0;
-	rq->ioprio = 0;
-	rq->special = NULL;
-	rq->buffer = NULL;
+	rq->cmd = rq->__cmd;
 	rq->tag = -1;
-	rq->errors = 0;
 	rq->ref_count = 1;
-	rq->cmd_len = 0;
-	memset(rq->cmd, 0, sizeof(rq->cmd));
-	rq->data_len = 0;
-	rq->extra_len = 0;
-	rq->sense_len = 0;
-	rq->data = NULL;
-	rq->sense = NULL;
-	rq->end_io = NULL;
-	rq->end_io_data = NULL;
-	rq->next_rq = NULL;
 }
+EXPORT_SYMBOL(blk_rq_init);
 
 static void req_bio_endio(struct request *rq, struct bio *bio,
 			  unsigned int nbytes, int error)
@@ -194,7 +174,7 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 
 	if (blk_pc_request(rq)) {
 		printk(KERN_INFO "  cdb: ");
-		for (bit = 0; bit < sizeof(rq->cmd); bit++)
+		for (bit = 0; bit < BLK_MAX_CDB; bit++)
 			printk("%02x ", rq->cmd[bit]);
 		printk("\n");
 	}
@@ -220,7 +200,8 @@ void blk_plug_device(struct request_queue *q)
 	if (blk_queue_stopped(q))
 		return;
 
-	if (!test_and_set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags)) {
+	if (!test_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags)) {
+		__set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags);
 		mod_timer(&q->unplug_timer, jiffies + q->unplug_delay);
 		blk_add_trace_generic(q, NULL, 0, BLK_TA_PLUG);
 	}
@@ -235,9 +216,10 @@ int blk_remove_plug(struct request_queue *q)
 {
 	WARN_ON(!irqs_disabled());
 
-	if (!test_and_clear_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags))
+	if (!test_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags))
 		return 0;
 
+	queue_flag_clear(QUEUE_FLAG_PLUGGED, q);
 	del_timer(&q->unplug_timer);
 	return 1;
 }
@@ -333,15 +315,16 @@ void blk_start_queue(struct request_queue *q)
 {
 	WARN_ON(!irqs_disabled());
 
-	clear_bit(QUEUE_FLAG_STOPPED, &q->queue_flags);
+	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
 
 	/*
 	 * one level of recursion is ok and is much faster than kicking
 	 * the unplug handling
 	 */
-	if (!test_and_set_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
+	if (!test_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
+		queue_flag_set(QUEUE_FLAG_REENTER, q);
 		q->request_fn(q);
-		clear_bit(QUEUE_FLAG_REENTER, &q->queue_flags);
+		queue_flag_clear(QUEUE_FLAG_REENTER, q);
 	} else {
 		blk_plug_device(q);
 		kblockd_schedule_work(&q->unplug_work);
@@ -366,7 +349,7 @@ EXPORT_SYMBOL(blk_start_queue);
 void blk_stop_queue(struct request_queue *q)
 {
 	blk_remove_plug(q);
-	set_bit(QUEUE_FLAG_STOPPED, &q->queue_flags);
+	queue_flag_set(QUEUE_FLAG_STOPPED, q);
 }
 EXPORT_SYMBOL(blk_stop_queue);
 
@@ -395,11 +378,8 @@ EXPORT_SYMBOL(blk_sync_queue);
  * blk_run_queue - run a single device queue
  * @q:	The queue to run
  */
-void blk_run_queue(struct request_queue *q)
+void __blk_run_queue(struct request_queue *q)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(q->queue_lock, flags);
 	blk_remove_plug(q);
 
 	/*
@@ -407,15 +387,28 @@ void blk_run_queue(struct request_queue *q)
 	 * handling reinvoke the handler shortly if we already got there.
 	 */
 	if (!elv_queue_empty(q)) {
-		if (!test_and_set_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
+		if (!test_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
+			queue_flag_set(QUEUE_FLAG_REENTER, q);
 			q->request_fn(q);
-			clear_bit(QUEUE_FLAG_REENTER, &q->queue_flags);
+			queue_flag_clear(QUEUE_FLAG_REENTER, q);
 		} else {
 			blk_plug_device(q);
 			kblockd_schedule_work(&q->unplug_work);
 		}
 	}
+}
+EXPORT_SYMBOL(__blk_run_queue);
+
+/**
+ * blk_run_queue - run a single device queue
+ * @q: The queue to run
+ */
+void blk_run_queue(struct request_queue *q)
+{
+	unsigned long flags;
 
+	spin_lock_irqsave(q->queue_lock, flags);
+	__blk_run_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(blk_run_queue);
@@ -428,7 +421,7 @@ void blk_put_queue(struct request_queue *q)
 void blk_cleanup_queue(struct request_queue *q)
 {
 	mutex_lock(&q->sysfs_lock);
-	set_bit(QUEUE_FLAG_DEAD, &q->queue_flags);
+	queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
 	mutex_unlock(&q->sysfs_lock);
 
 	if (q->elevator)
@@ -607,6 +600,8 @@ blk_alloc_request(struct request_queue *q, int rw, int priv, gfp_t gfp_mask)
 	if (!rq)
 		return NULL;
 
+	blk_rq_init(q, rq);
+
 	/*
 	 * first three bits are identical in rq->cmd_flags and bio->bi_rw,
 	 * see bio.h and blkdev.h
@@ -789,8 +784,6 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 	if (ioc_batching(q, ioc))
 		ioc->nr_batch_requests--;
 
-	rq_init(q, rq);
-
 	blk_add_trace_generic(q, bio, rw, BLK_TA_GETRQ);
 out:
 	return rq;
diff --git a/trunk/block/blk-map.c b/trunk/block/blk-map.c
index 3c942bd6422a..0b1af5a3537c 100644
--- a/trunk/block/blk-map.c
+++ b/trunk/block/blk-map.c
@@ -255,10 +255,18 @@ EXPORT_SYMBOL(blk_rq_unmap_user);
  * @kbuf:	the kernel buffer
  * @len:	length of user data
  * @gfp_mask:	memory allocation flags
+ *
+ * Description:
+ *    Data will be mapped directly if possible. Otherwise a bounce
+ *    buffer is used.
  */
 int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 		    unsigned int len, gfp_t gfp_mask)
 {
+	unsigned long kaddr;
+	unsigned int alignment;
+	int reading = rq_data_dir(rq) == READ;
+	int do_copy = 0;
 	struct bio *bio;
 
 	if (len > (q->max_hw_sectors << 9))
@@ -266,13 +274,24 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	if (!len || !kbuf)
 		return -EINVAL;
 
-	bio = bio_map_kern(q, kbuf, len, gfp_mask);
+	kaddr = (unsigned long)kbuf;
+	alignment = queue_dma_alignment(q) | q->dma_pad_mask;
+	do_copy = ((kaddr & alignment) || (len & alignment));
+
+	if (do_copy)
+		bio = bio_copy_kern(q, kbuf, len, gfp_mask, reading);
+	else
+		bio = bio_map_kern(q, kbuf, len, gfp_mask);
+
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
 	if (rq_data_dir(rq) == WRITE)
 		bio->bi_rw |= (1 << BIO_RW);
 
+	if (do_copy)
+		rq->cmd_flags |= REQ_COPY_USER;
+
 	blk_rq_bio_prep(q, rq, bio);
 	blk_queue_bounce(q, &rq->bio);
 	rq->buffer = rq->data = NULL;
diff --git a/trunk/block/blk-merge.c b/trunk/block/blk-merge.c
index b5c5c4a9e3f0..73b23562af20 100644
--- a/trunk/block/blk-merge.c
+++ b/trunk/block/blk-merge.c
@@ -55,7 +55,7 @@ void blk_recalc_rq_segments(struct request *rq)
 	if (!rq->bio)
 		return;
 
-	cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
+	cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
 	hw_seg_size = seg_size = 0;
 	phys_size = hw_size = nr_phys_segs = nr_hw_segs = 0;
 	rq_for_each_segment(bv, rq, iter) {
@@ -128,7 +128,7 @@ EXPORT_SYMBOL(blk_recount_segments);
 static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 				   struct bio *nxt)
 {
-	if (!(q->queue_flags & (1 << QUEUE_FLAG_CLUSTER)))
+	if (!test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
 		return 0;
 
 	if (!BIOVEC_PHYS_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)))
@@ -175,7 +175,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	int nsegs, cluster;
 
 	nsegs = 0;
-	cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
+	cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
 
 	/*
 	 * for each bio in rq
diff --git a/trunk/block/blk-settings.c b/trunk/block/blk-settings.c
index 5713f7e5cbd2..6089384ab064 100644
--- a/trunk/block/blk-settings.c
+++ b/trunk/block/blk-settings.c
@@ -14,7 +14,6 @@ unsigned long blk_max_low_pfn;
 EXPORT_SYMBOL(blk_max_low_pfn);
 
 unsigned long blk_max_pfn;
-EXPORT_SYMBOL(blk_max_pfn);
 
 /**
  * blk_queue_prep_rq - set a prepare_request function for queue
@@ -288,7 +287,7 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 	t->max_segment_size = min(t->max_segment_size, b->max_segment_size);
 	t->hardsect_size = max(t->hardsect_size, b->hardsect_size);
 	if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags))
-		clear_bit(QUEUE_FLAG_CLUSTER, &t->queue_flags);
+		queue_flag_clear(QUEUE_FLAG_CLUSTER, t);
 }
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
diff --git a/trunk/block/blk-sysfs.c b/trunk/block/blk-sysfs.c
index fc41d83be22b..e85c4013e8a2 100644
--- a/trunk/block/blk-sysfs.c
+++ b/trunk/block/blk-sysfs.c
@@ -135,6 +135,25 @@ static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
 	return queue_var_show(max_hw_sectors_kb, (page));
 }
 
+static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(blk_queue_nomerges(q), page);
+}
+
+static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
+				    size_t count)
+{
+	unsigned long nm;
+	ssize_t ret = queue_var_store(&nm, page, count);
+
+	if (nm)
+	       set_bit(QUEUE_FLAG_NOMERGES, &q->queue_flags);
+	else
+	       clear_bit(QUEUE_FLAG_NOMERGES, &q->queue_flags);
+
+	return ret;
+}
+
 
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
@@ -170,6 +189,12 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = {
 	.show = queue_hw_sector_size_show,
 };
 
+static struct queue_sysfs_entry queue_nomerges_entry = {
+	.attr = {.name = "nomerges", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_nomerges_show,
+	.store = queue_nomerges_store,
+};
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -177,6 +202,7 @@ static struct attribute *default_attrs[] = {
 	&queue_max_sectors_entry.attr,
 	&queue_iosched_entry.attr,
 	&queue_hw_sector_size_entry.attr,
+	&queue_nomerges_entry.attr,
 	NULL,
 };
 
diff --git a/trunk/block/blk-tag.c b/trunk/block/blk-tag.c
index 4780a46ce234..e176ddbe599e 100644
--- a/trunk/block/blk-tag.c
+++ b/trunk/block/blk-tag.c
@@ -70,7 +70,7 @@ void __blk_queue_free_tags(struct request_queue *q)
 	__blk_free_tags(bqt);
 
 	q->queue_tags = NULL;
-	q->queue_flags &= ~(1 << QUEUE_FLAG_QUEUED);
+	queue_flag_clear(QUEUE_FLAG_QUEUED, q);
 }
 
 /**
@@ -98,7 +98,7 @@ EXPORT_SYMBOL(blk_free_tags);
  **/
 void blk_queue_free_tags(struct request_queue *q)
 {
-	clear_bit(QUEUE_FLAG_QUEUED, &q->queue_flags);
+	queue_flag_clear(QUEUE_FLAG_QUEUED, q);
 }
 EXPORT_SYMBOL(blk_queue_free_tags);
 
@@ -188,7 +188,7 @@ int blk_queue_init_tags(struct request_queue *q, int depth,
 		rc = blk_queue_resize_tags(q, depth);
 		if (rc)
 			return rc;
-		set_bit(QUEUE_FLAG_QUEUED, &q->queue_flags);
+		queue_flag_set(QUEUE_FLAG_QUEUED, q);
 		return 0;
 	} else
 		atomic_inc(&tags->refcnt);
@@ -197,7 +197,7 @@ int blk_queue_init_tags(struct request_queue *q, int depth,
 	 * assign it, all done
 	 */
 	q->queue_tags = tags;
-	q->queue_flags |= (1 << QUEUE_FLAG_QUEUED);
+	queue_flag_set(QUEUE_FLAG_QUEUED, q);
 	INIT_LIST_HEAD(&q->tag_busy_list);
 	return 0;
 fail:
diff --git a/trunk/block/blk.h b/trunk/block/blk.h
index ec9120fb789a..59776ab4742a 100644
--- a/trunk/block/blk.h
+++ b/trunk/block/blk.h
@@ -10,7 +10,6 @@
 extern struct kmem_cache *blk_requestq_cachep;
 extern struct kobj_type blk_queue_ktype;
 
-void rq_init(struct request_queue *q, struct request *rq);
 void init_request_from_bio(struct request *req, struct bio *bio);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 			struct bio *bio);
diff --git a/trunk/block/bsg.c b/trunk/block/bsg.c
index f51172ed27c2..23ea4fd1a66d 100644
--- a/trunk/block/bsg.c
+++ b/trunk/block/bsg.c
@@ -699,14 +699,26 @@ static struct bsg_device *bsg_alloc_device(void)
 	return bd;
 }
 
+static void bsg_kref_release_function(struct kref *kref)
+{
+	struct bsg_class_device *bcd =
+		container_of(kref, struct bsg_class_device, ref);
+
+	if (bcd->release)
+		bcd->release(bcd->parent);
+
+	put_device(bcd->parent);
+}
+
 static int bsg_put_device(struct bsg_device *bd)
 {
-	int ret = 0;
-	struct device *dev = bd->queue->bsg_dev.dev;
+	int ret = 0, do_free;
+	struct request_queue *q = bd->queue;
 
 	mutex_lock(&bsg_mutex);
 
-	if (!atomic_dec_and_test(&bd->ref_count))
+	do_free = atomic_dec_and_test(&bd->ref_count);
+	if (!do_free)
 		goto out;
 
 	dprintk("%s: tearing down\n", bd->name);
@@ -723,12 +735,13 @@ static int bsg_put_device(struct bsg_device *bd)
 	 */
 	ret = bsg_complete_all_commands(bd);
 
-	blk_put_queue(bd->queue);
 	hlist_del(&bd->dev_list);
 	kfree(bd);
 out:
 	mutex_unlock(&bsg_mutex);
-	put_device(dev);
+	kref_put(&q->bsg_dev.ref, bsg_kref_release_function);
+	if (do_free)
+		blk_put_queue(q);
 	return ret;
 }
 
@@ -796,7 +809,7 @@ static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file)
 	mutex_lock(&bsg_mutex);
 	bcd = idr_find(&bsg_minor_idr, iminor(inode));
 	if (bcd)
-		get_device(bcd->dev);
+		kref_get(&bcd->ref);
 	mutex_unlock(&bsg_mutex);
 
 	if (!bcd)
@@ -808,7 +821,7 @@ static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file)
 
 	bd = bsg_add_device(inode, bcd->queue, file);
 	if (IS_ERR(bd))
-		put_device(bcd->dev);
+		kref_put(&bcd->ref, bsg_kref_release_function);
 
 	return bd;
 }
@@ -947,14 +960,14 @@ void bsg_unregister_queue(struct request_queue *q)
 	idr_remove(&bsg_minor_idr, bcd->minor);
 	sysfs_remove_link(&q->kobj, "bsg");
 	device_unregister(bcd->class_dev);
-	put_device(bcd->dev);
 	bcd->class_dev = NULL;
+	kref_put(&bcd->ref, bsg_kref_release_function);
 	mutex_unlock(&bsg_mutex);
 }
 EXPORT_SYMBOL_GPL(bsg_unregister_queue);
 
-int bsg_register_queue(struct request_queue *q, struct device *gdev,
-		       const char *name)
+int bsg_register_queue(struct request_queue *q, struct device *parent,
+		       const char *name, void (*release)(struct device *))
 {
 	struct bsg_class_device *bcd;
 	dev_t dev;
@@ -965,7 +978,7 @@ int bsg_register_queue(struct request_queue *q, struct device *gdev,
 	if (name)
 		devname = name;
 	else
-		devname = gdev->bus_id;
+		devname = parent->bus_id;
 
 	/*
 	 * we need a proper transport to send commands, not a stacked device
@@ -996,9 +1009,11 @@ int bsg_register_queue(struct request_queue *q, struct device *gdev,
 
 	bcd->minor = minor;
 	bcd->queue = q;
-	bcd->dev = get_device(gdev);
+	bcd->parent = get_device(parent);
+	bcd->release = release;
+	kref_init(&bcd->ref);
 	dev = MKDEV(bsg_major, bcd->minor);
-	class_dev = device_create(bsg_class, gdev, dev, "%s", devname);
+	class_dev = device_create(bsg_class, parent, dev, "%s", devname);
 	if (IS_ERR(class_dev)) {
 		ret = PTR_ERR(class_dev);
 		goto put_dev;
@@ -1017,7 +1032,7 @@ int bsg_register_queue(struct request_queue *q, struct device *gdev,
 unregister_class_dev:
 	device_unregister(class_dev);
 put_dev:
-	put_device(gdev);
+	put_device(parent);
 remove_idr:
 	idr_remove(&bsg_minor_idr, minor);
 unlock:
diff --git a/trunk/block/elevator.c b/trunk/block/elevator.c
index 88318c383608..ac5310ef8270 100644
--- a/trunk/block/elevator.c
+++ b/trunk/block/elevator.c
@@ -69,7 +69,7 @@ static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
 /*
  * can we safely merge with this request?
  */
-inline int elv_rq_merge_ok(struct request *rq, struct bio *bio)
+int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 {
 	if (!rq_mergeable(rq))
 		return 0;
@@ -488,6 +488,9 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 		}
 	}
 
+	if (blk_queue_nomerges(q))
+		return ELEVATOR_NO_MERGE;
+
 	/*
 	 * See if our hash lookup can find a potential backmerge.
 	 */
@@ -1070,7 +1073,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	 */
 	spin_lock_irq(q->queue_lock);
 
-	set_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
+	queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
 
 	elv_drain_elevator(q);
 
@@ -1104,7 +1107,10 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	 * finally exit old elevator and turn off BYPASS.
 	 */
 	elevator_exit(old_elevator);
-	clear_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
+	spin_lock_irq(q->queue_lock);
+	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
+	spin_unlock_irq(q->queue_lock);
+
 	return 1;
 
 fail_register:
@@ -1115,7 +1121,11 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	elevator_exit(e);
 	q->elevator = old_elevator;
 	elv_register_queue(q);
-	clear_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
+
+	spin_lock_irq(q->queue_lock);
+	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
+	spin_unlock_irq(q->queue_lock);
+
 	return 0;
 }
 
diff --git a/trunk/block/scsi_ioctl.c b/trunk/block/scsi_ioctl.c
index a2c3a936ebf9..ffa3720e6ca0 100644
--- a/trunk/block/scsi_ioctl.c
+++ b/trunk/block/scsi_ioctl.c
@@ -217,8 +217,6 @@ EXPORT_SYMBOL_GPL(blk_verify_command);
 static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 			     struct sg_io_hdr *hdr, int has_write_perm)
 {
-	memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */
-
 	if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len))
 		return -EFAULT;
 	if (blk_verify_command(rq->cmd, has_write_perm))
@@ -531,7 +529,6 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	rq->data_len = 0;
 	rq->extra_len = 0;
 	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
-	memset(rq->cmd, 0, sizeof(rq->cmd));
 	rq->cmd[0] = cmd;
 	rq->cmd[4] = data;
 	rq->cmd_len = 6;
diff --git a/trunk/drivers/acpi/ac.c b/trunk/drivers/acpi/ac.c
index 43a95e5640de..5b73f6a2cd86 100644
--- a/trunk/drivers/acpi/ac.c
+++ b/trunk/drivers/acpi/ac.c
@@ -92,6 +92,7 @@ struct acpi_ac {
 
 #ifdef CONFIG_ACPI_PROCFS_POWER
 static const struct file_operations acpi_ac_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_ac_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -195,16 +196,11 @@ static int acpi_ac_add_fs(struct acpi_device *device)
 	}
 
 	/* 'state' [R] */
-	entry = create_proc_entry(ACPI_AC_FILE_STATE,
-				  S_IRUGO, acpi_device_dir(device));
+	entry = proc_create_data(ACPI_AC_FILE_STATE,
+				 S_IRUGO, acpi_device_dir(device),
+				 &acpi_ac_fops, acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		entry->proc_fops = &acpi_ac_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
-
 	return 0;
 }
 
diff --git a/trunk/drivers/acpi/battery.c b/trunk/drivers/acpi/battery.c
index d5729d5dc190..b1c723f9f58d 100644
--- a/trunk/drivers/acpi/battery.c
+++ b/trunk/drivers/acpi/battery.c
@@ -741,15 +741,13 @@ static int acpi_battery_add_fs(struct acpi_device *device)
 	}
 
 	for (i = 0; i < ACPI_BATTERY_NUMFILES; ++i) {
-		entry = create_proc_entry(acpi_battery_file[i].name,
-				  acpi_battery_file[i].mode, acpi_device_dir(device));
+		entry = proc_create_data(acpi_battery_file[i].name,
+					 acpi_battery_file[i].mode,
+					 acpi_device_dir(device),
+					 &acpi_battery_file[i].ops,
+					 acpi_driver_data(device));
 		if (!entry)
 			return -ENODEV;
-		else {
-			entry->proc_fops = &acpi_battery_file[i].ops;
-			entry->data = acpi_driver_data(device);
-			entry->owner = THIS_MODULE;
-		}
 	}
 	return 0;
 }
diff --git a/trunk/drivers/acpi/button.c b/trunk/drivers/acpi/button.c
index 6c5da83cdb68..1dfec413588c 100644
--- a/trunk/drivers/acpi/button.c
+++ b/trunk/drivers/acpi/button.c
@@ -102,6 +102,7 @@ struct acpi_button {
 };
 
 static const struct file_operations acpi_button_info_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_button_info_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -109,6 +110,7 @@ static const struct file_operations acpi_button_info_fops = {
 };
 
 static const struct file_operations acpi_button_state_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_button_state_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -207,27 +209,21 @@ static int acpi_button_add_fs(struct acpi_device *device)
 	acpi_device_dir(device)->owner = THIS_MODULE;
 
 	/* 'info' [R] */
-	entry = create_proc_entry(ACPI_BUTTON_FILE_INFO,
-				  S_IRUGO, acpi_device_dir(device));
+	entry = proc_create_data(ACPI_BUTTON_FILE_INFO,
+				 S_IRUGO, acpi_device_dir(device),
+				 &acpi_button_info_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		entry->proc_fops = &acpi_button_info_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	/* show lid state [R] */
 	if (button->type == ACPI_BUTTON_TYPE_LID) {
-		entry = create_proc_entry(ACPI_BUTTON_FILE_STATE,
-					  S_IRUGO, acpi_device_dir(device));
+		entry = proc_create_data(ACPI_BUTTON_FILE_STATE,
+					 S_IRUGO, acpi_device_dir(device),
+					 &acpi_button_state_fops,
+					 acpi_driver_data(device));
 		if (!entry)
 			return -ENODEV;
-		else {
-			entry->proc_fops = &acpi_button_state_fops;
-			entry->data = acpi_driver_data(device);
-			entry->owner = THIS_MODULE;
-		}
 	}
 
 	return 0;
diff --git a/trunk/drivers/acpi/ec.c b/trunk/drivers/acpi/ec.c
index 7222a18a0319..e3f04b272f3f 100644
--- a/trunk/drivers/acpi/ec.c
+++ b/trunk/drivers/acpi/ec.c
@@ -669,16 +669,11 @@ static int acpi_ec_add_fs(struct acpi_device *device)
 			return -ENODEV;
 	}
 
-	entry = create_proc_entry(ACPI_EC_FILE_INFO, S_IRUGO,
-				  acpi_device_dir(device));
+	entry = proc_create_data(ACPI_EC_FILE_INFO, S_IRUGO,
+				 acpi_device_dir(device),
+				 &acpi_ec_info_ops, acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		entry->proc_fops = &acpi_ec_info_ops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
-
 	return 0;
 }
 
diff --git a/trunk/drivers/acpi/event.c b/trunk/drivers/acpi/event.c
index abec1ca94cf4..0c24bd4d6562 100644
--- a/trunk/drivers/acpi/event.c
+++ b/trunk/drivers/acpi/event.c
@@ -102,6 +102,7 @@ static unsigned int acpi_system_poll_event(struct file *file, poll_table * wait)
 }
 
 static const struct file_operations acpi_system_event_ops = {
+	.owner = THIS_MODULE,
 	.open = acpi_system_open_event,
 	.read = acpi_system_read_event,
 	.release = acpi_system_close_event,
@@ -294,10 +295,9 @@ static int __init acpi_event_init(void)
 
 #ifdef CONFIG_ACPI_PROC_EVENT
 	/* 'event' [R] */
-	entry = create_proc_entry("event", S_IRUSR, acpi_root_dir);
-	if (entry)
-		entry->proc_fops = &acpi_system_event_ops;
-	else
+	entry = proc_create("event", S_IRUSR, acpi_root_dir,
+			    &acpi_system_event_ops);
+	if (!entry)
 		return -ENODEV;
 #endif
 
diff --git a/trunk/drivers/acpi/fan.c b/trunk/drivers/acpi/fan.c
index c8e3cba423ef..194077ab9b85 100644
--- a/trunk/drivers/acpi/fan.c
+++ b/trunk/drivers/acpi/fan.c
@@ -192,17 +192,13 @@ static int acpi_fan_add_fs(struct acpi_device *device)
 	}
 
 	/* 'status' [R/W] */
-	entry = create_proc_entry(ACPI_FAN_FILE_STATE,
-				  S_IFREG | S_IRUGO | S_IWUSR,
-				  acpi_device_dir(device));
+	entry = proc_create_data(ACPI_FAN_FILE_STATE,
+				 S_IFREG | S_IRUGO | S_IWUSR,
+				 acpi_device_dir(device),
+				 &acpi_fan_state_ops,
+				 device);
 	if (!entry)
 		return -ENODEV;
-	else {
-		entry->proc_fops = &acpi_fan_state_ops;
-		entry->data = device;
-		entry->owner = THIS_MODULE;
-	}
-
 	return 0;
 }
 
diff --git a/trunk/drivers/acpi/power.c b/trunk/drivers/acpi/power.c
index 76bf6d90c700..21fc8bf0d31f 100644
--- a/trunk/drivers/acpi/power.c
+++ b/trunk/drivers/acpi/power.c
@@ -93,6 +93,7 @@ struct acpi_power_resource {
 static struct list_head acpi_power_resource_list;
 
 static const struct file_operations acpi_power_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_power_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -543,15 +544,11 @@ static int acpi_power_add_fs(struct acpi_device *device)
 	}
 
 	/* 'status' [R] */
-	entry = create_proc_entry(ACPI_POWER_FILE_STATUS,
-				  S_IRUGO, acpi_device_dir(device));
+	entry = proc_create_data(ACPI_POWER_FILE_STATUS,
+				 S_IRUGO, acpi_device_dir(device),
+				 &acpi_power_fops, acpi_driver_data(device));
 	if (!entry)
 		return -EIO;
-	else {
-		entry->proc_fops = &acpi_power_fops;
-		entry->data = acpi_driver_data(device);
-	}
-
 	return 0;
 }
 
diff --git a/trunk/drivers/acpi/processor_core.c b/trunk/drivers/acpi/processor_core.c
index a825b431b64f..dd28c912e84f 100644
--- a/trunk/drivers/acpi/processor_core.c
+++ b/trunk/drivers/acpi/processor_core.c
@@ -112,6 +112,7 @@ static struct acpi_driver acpi_processor_driver = {
 #define UNINSTALL_NOTIFY_HANDLER	2
 
 static const struct file_operations acpi_processor_info_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_processor_info_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -326,40 +327,30 @@ static int acpi_processor_add_fs(struct acpi_device *device)
 	acpi_device_dir(device)->owner = THIS_MODULE;
 
 	/* 'info' [R] */
-	entry = create_proc_entry(ACPI_PROCESSOR_FILE_INFO,
-				  S_IRUGO, acpi_device_dir(device));
+	entry = proc_create_data(ACPI_PROCESSOR_FILE_INFO,
+				 S_IRUGO, acpi_device_dir(device),
+				 &acpi_processor_info_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -EIO;
-	else {
-		entry->proc_fops = &acpi_processor_info_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	/* 'throttling' [R/W] */
-	entry = create_proc_entry(ACPI_PROCESSOR_FILE_THROTTLING,
-				  S_IFREG | S_IRUGO | S_IWUSR,
-				  acpi_device_dir(device));
+	entry = proc_create_data(ACPI_PROCESSOR_FILE_THROTTLING,
+				 S_IFREG | S_IRUGO | S_IWUSR,
+				 acpi_device_dir(device),
+				 &acpi_processor_throttling_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -EIO;
-	else {
-		entry->proc_fops = &acpi_processor_throttling_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	/* 'limit' [R/W] */
-	entry = create_proc_entry(ACPI_PROCESSOR_FILE_LIMIT,
-				  S_IFREG | S_IRUGO | S_IWUSR,
-				  acpi_device_dir(device));
+	entry = proc_create_data(ACPI_PROCESSOR_FILE_LIMIT,
+				 S_IFREG | S_IRUGO | S_IWUSR,
+				 acpi_device_dir(device),
+				 &acpi_processor_limit_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -EIO;
-	else {
-		entry->proc_fops = &acpi_processor_limit_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
-
 	return 0;
 }
 
diff --git a/trunk/drivers/acpi/processor_idle.c b/trunk/drivers/acpi/processor_idle.c
index 788da9781f80..789d4947ed31 100644
--- a/trunk/drivers/acpi/processor_idle.c
+++ b/trunk/drivers/acpi/processor_idle.c
@@ -418,13 +418,12 @@ static void acpi_processor_idle(void)
 
 	cx = pr->power.state;
 	if (!cx || acpi_idle_suspend) {
-		if (pm_idle_save)
-			pm_idle_save();
-		else
+		if (pm_idle_save) {
+			pm_idle_save(); /* enables IRQs */
+		} else {
 			acpi_safe_halt();
-
-		if (irqs_disabled())
 			local_irq_enable();
+		}
 
 		return;
 	}
@@ -520,10 +519,12 @@ static void acpi_processor_idle(void)
 		 * Use the appropriate idle routine, the one that would
 		 * be used without acpi C-states.
 		 */
-		if (pm_idle_save)
-			pm_idle_save();
-		else
+		if (pm_idle_save) {
+			pm_idle_save(); /* enables IRQs */
+		} else {
 			acpi_safe_halt();
+			local_irq_enable();
+		}
 
 		/*
 		 * TBD: Can't get time duration while in C1, as resumes
@@ -534,8 +535,6 @@ static void acpi_processor_idle(void)
 		 *       skew otherwise.
 		 */
 		sleep_ticks = 0xFFFFFFFF;
-		if (irqs_disabled())
-			local_irq_enable();
 
 		break;
 
@@ -1283,6 +1282,7 @@ static int acpi_processor_power_open_fs(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations acpi_processor_power_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_processor_power_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -1823,16 +1823,12 @@ int __cpuinit acpi_processor_power_init(struct acpi_processor *pr,
 	}
 
 	/* 'power' [R] */
-	entry = create_proc_entry(ACPI_PROCESSOR_FILE_POWER,
-				  S_IRUGO, acpi_device_dir(device));
+	entry = proc_create_data(ACPI_PROCESSOR_FILE_POWER,
+				 S_IRUGO, acpi_device_dir(device),
+				 &acpi_processor_power_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -EIO;
-	else {
-		entry->proc_fops = &acpi_processor_power_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
-
 	return 0;
 }
 
diff --git a/trunk/drivers/acpi/processor_perflib.c b/trunk/drivers/acpi/processor_perflib.c
index b477a4be8a69..d80b2d1441af 100644
--- a/trunk/drivers/acpi/processor_perflib.c
+++ b/trunk/drivers/acpi/processor_perflib.c
@@ -411,6 +411,7 @@ EXPORT_SYMBOL(acpi_processor_notify_smm);
 
 static int acpi_processor_perf_open_fs(struct inode *inode, struct file *file);
 static struct file_operations acpi_processor_perf_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_processor_perf_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -456,7 +457,6 @@ static int acpi_processor_perf_open_fs(struct inode *inode, struct file *file)
 
 static void acpi_cpufreq_add_file(struct acpi_processor *pr)
 {
-	struct proc_dir_entry *entry = NULL;
 	struct acpi_device *device = NULL;
 
 
@@ -464,14 +464,9 @@ static void acpi_cpufreq_add_file(struct acpi_processor *pr)
 		return;
 
 	/* add file 'performance' [R/W] */
-	entry = create_proc_entry(ACPI_PROCESSOR_FILE_PERFORMANCE,
-				  S_IFREG | S_IRUGO,
-				  acpi_device_dir(device));
-	if (entry){
-		entry->proc_fops = &acpi_processor_perf_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
+	proc_create_data(ACPI_PROCESSOR_FILE_PERFORMANCE, S_IFREG | S_IRUGO,
+			 acpi_device_dir(device),
+			 &acpi_processor_perf_fops, acpi_driver_data(device));
 	return;
 }
 
diff --git a/trunk/drivers/acpi/processor_thermal.c b/trunk/drivers/acpi/processor_thermal.c
index 9cb43f52f7b6..ef34b18f95ca 100644
--- a/trunk/drivers/acpi/processor_thermal.c
+++ b/trunk/drivers/acpi/processor_thermal.c
@@ -97,7 +97,7 @@ static int acpi_processor_apply_limit(struct acpi_processor *pr)
 #define CPUFREQ_THERMAL_MIN_STEP 0
 #define CPUFREQ_THERMAL_MAX_STEP 3
 
-static unsigned int cpufreq_thermal_reduction_pctg[NR_CPUS];
+static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_pctg);
 static unsigned int acpi_thermal_cpufreq_is_init = 0;
 
 static int cpu_has_cpufreq(unsigned int cpu)
@@ -113,9 +113,9 @@ static int acpi_thermal_cpufreq_increase(unsigned int cpu)
 	if (!cpu_has_cpufreq(cpu))
 		return -ENODEV;
 
-	if (cpufreq_thermal_reduction_pctg[cpu] <
+	if (per_cpu(cpufreq_thermal_reduction_pctg, cpu) <
 		CPUFREQ_THERMAL_MAX_STEP) {
-		cpufreq_thermal_reduction_pctg[cpu]++;
+		per_cpu(cpufreq_thermal_reduction_pctg, cpu)++;
 		cpufreq_update_policy(cpu);
 		return 0;
 	}
@@ -128,14 +128,14 @@ static int acpi_thermal_cpufreq_decrease(unsigned int cpu)
 	if (!cpu_has_cpufreq(cpu))
 		return -ENODEV;
 
-	if (cpufreq_thermal_reduction_pctg[cpu] >
+	if (per_cpu(cpufreq_thermal_reduction_pctg, cpu) >
 		(CPUFREQ_THERMAL_MIN_STEP + 1))
-		cpufreq_thermal_reduction_pctg[cpu]--;
+		per_cpu(cpufreq_thermal_reduction_pctg, cpu)--;
 	else
-		cpufreq_thermal_reduction_pctg[cpu] = 0;
+		per_cpu(cpufreq_thermal_reduction_pctg, cpu) = 0;
 	cpufreq_update_policy(cpu);
 	/* We reached max freq again and can leave passive mode */
-	return !cpufreq_thermal_reduction_pctg[cpu];
+	return !per_cpu(cpufreq_thermal_reduction_pctg, cpu);
 }
 
 static int acpi_thermal_cpufreq_notifier(struct notifier_block *nb,
@@ -147,9 +147,10 @@ static int acpi_thermal_cpufreq_notifier(struct notifier_block *nb,
 	if (event != CPUFREQ_ADJUST)
 		goto out;
 
-	max_freq =
-	    (policy->cpuinfo.max_freq *
-	     (100 - cpufreq_thermal_reduction_pctg[policy->cpu] * 20)) / 100;
+	max_freq = (
+	    policy->cpuinfo.max_freq *
+	    (100 - per_cpu(cpufreq_thermal_reduction_pctg, policy->cpu) * 20)
+	) / 100;
 
 	cpufreq_verify_within_limits(policy, 0, max_freq);
 
@@ -174,7 +175,7 @@ static int cpufreq_get_cur_state(unsigned int cpu)
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	return cpufreq_thermal_reduction_pctg[cpu];
+	return per_cpu(cpufreq_thermal_reduction_pctg, cpu);
 }
 
 static int cpufreq_set_cur_state(unsigned int cpu, int state)
@@ -182,7 +183,7 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	cpufreq_thermal_reduction_pctg[cpu] = state;
+	per_cpu(cpufreq_thermal_reduction_pctg, cpu) = state;
 	cpufreq_update_policy(cpu);
 	return 0;
 }
@@ -191,8 +192,9 @@ void acpi_thermal_cpufreq_init(void)
 {
 	int i;
 
-	for (i = 0; i < NR_CPUS; i++)
-		cpufreq_thermal_reduction_pctg[i] = 0;
+	for (i = 0; i < nr_cpu_ids; i++)
+		if (cpu_present(i))
+			per_cpu(cpufreq_thermal_reduction_pctg, i) = 0;
 
 	i = cpufreq_register_notifier(&acpi_thermal_cpufreq_notifier_block,
 				      CPUFREQ_POLICY_NOTIFIER);
@@ -507,6 +509,7 @@ static ssize_t acpi_processor_write_limit(struct file * file,
 }
 
 struct file_operations acpi_processor_limit_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_processor_limit_open_fs,
 	.read = seq_read,
 	.write = acpi_processor_write_limit,
diff --git a/trunk/drivers/acpi/processor_throttling.c b/trunk/drivers/acpi/processor_throttling.c
index 0bba3a914e86..bb06738860c4 100644
--- a/trunk/drivers/acpi/processor_throttling.c
+++ b/trunk/drivers/acpi/processor_throttling.c
@@ -1252,6 +1252,7 @@ static ssize_t acpi_processor_write_throttling(struct file *file,
 }
 
 struct file_operations acpi_processor_throttling_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_processor_throttling_open_fs,
 	.read = seq_read,
 	.write = acpi_processor_write_throttling,
diff --git a/trunk/drivers/acpi/sbs.c b/trunk/drivers/acpi/sbs.c
index 585ae3c9c8ea..10a36512647c 100644
--- a/trunk/drivers/acpi/sbs.c
+++ b/trunk/drivers/acpi/sbs.c
@@ -483,8 +483,6 @@ acpi_sbs_add_fs(struct proc_dir_entry **dir,
 		struct file_operations *state_fops,
 		struct file_operations *alarm_fops, void *data)
 {
-	struct proc_dir_entry *entry = NULL;
-
 	if (!*dir) {
 		*dir = proc_mkdir(dir_name, parent_dir);
 		if (!*dir) {
@@ -494,34 +492,19 @@ acpi_sbs_add_fs(struct proc_dir_entry **dir,
 	}
 
 	/* 'info' [R] */
-	if (info_fops) {
-		entry = create_proc_entry(ACPI_SBS_FILE_INFO, S_IRUGO, *dir);
-		if (entry) {
-			entry->proc_fops = info_fops;
-			entry->data = data;
-			entry->owner = THIS_MODULE;
-		}
-	}
+	if (info_fops)
+		proc_create_data(ACPI_SBS_FILE_INFO, S_IRUGO, *dir,
+				 info_fops, data);
 
 	/* 'state' [R] */
-	if (state_fops) {
-		entry = create_proc_entry(ACPI_SBS_FILE_STATE, S_IRUGO, *dir);
-		if (entry) {
-			entry->proc_fops = state_fops;
-			entry->data = data;
-			entry->owner = THIS_MODULE;
-		}
-	}
+	if (state_fops)
+		proc_create_data(ACPI_SBS_FILE_STATE, S_IRUGO, *dir,
+				 state_fops, data);
 
 	/* 'alarm' [R/W] */
-	if (alarm_fops) {
-		entry = create_proc_entry(ACPI_SBS_FILE_ALARM, S_IRUGO, *dir);
-		if (entry) {
-			entry->proc_fops = alarm_fops;
-			entry->data = data;
-			entry->owner = THIS_MODULE;
-		}
-	}
+	if (alarm_fops)
+		proc_create_data(ACPI_SBS_FILE_ALARM, S_IRUGO, *dir,
+				 alarm_fops, data);
 	return 0;
 }
 
diff --git a/trunk/drivers/acpi/sleep/proc.c b/trunk/drivers/acpi/sleep/proc.c
index f8df5217d477..8a5fe8710513 100644
--- a/trunk/drivers/acpi/sleep/proc.c
+++ b/trunk/drivers/acpi/sleep/proc.c
@@ -440,6 +440,7 @@ acpi_system_wakeup_device_open_fs(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations acpi_system_wakeup_device_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_system_wakeup_device_open_fs,
 	.read = seq_read,
 	.write = acpi_system_write_wakeup_device,
@@ -449,6 +450,7 @@ static const struct file_operations acpi_system_wakeup_device_fops = {
 
 #ifdef	CONFIG_ACPI_PROCFS
 static const struct file_operations acpi_system_sleep_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_system_sleep_open_fs,
 	.read = seq_read,
 	.write = acpi_system_write_sleep,
@@ -459,6 +461,7 @@ static const struct file_operations acpi_system_sleep_fops = {
 
 #ifdef	HAVE_ACPI_LEGACY_ALARM
 static const struct file_operations acpi_system_alarm_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_system_alarm_open_fs,
 	.read = seq_read,
 	.write = acpi_system_write_alarm,
@@ -477,37 +480,26 @@ static u32 rtc_handler(void *context)
 
 static int __init acpi_sleep_proc_init(void)
 {
-	struct proc_dir_entry *entry = NULL;
-
 	if (acpi_disabled)
 		return 0;
 
 #ifdef	CONFIG_ACPI_PROCFS
 	/* 'sleep' [R/W] */
-	entry =
-	    create_proc_entry("sleep", S_IFREG | S_IRUGO | S_IWUSR,
-			      acpi_root_dir);
-	if (entry)
-		entry->proc_fops = &acpi_system_sleep_fops;
+	proc_create("sleep", S_IFREG | S_IRUGO | S_IWUSR,
+		    acpi_root_dir, &acpi_system_sleep_fops);
 #endif				/* CONFIG_ACPI_PROCFS */
 
 #ifdef	HAVE_ACPI_LEGACY_ALARM
 	/* 'alarm' [R/W] */
-	entry =
-	    create_proc_entry("alarm", S_IFREG | S_IRUGO | S_IWUSR,
-			      acpi_root_dir);
-	if (entry)
-		entry->proc_fops = &acpi_system_alarm_fops;
+	proc_create("alarm", S_IFREG | S_IRUGO | S_IWUSR,
+		    acpi_root_dir, &acpi_system_alarm_fops);
 
 	acpi_install_fixed_event_handler(ACPI_EVENT_RTC, rtc_handler, NULL);
 #endif				/* HAVE_ACPI_LEGACY_ALARM */
 
 	/* 'wakeup device' [R/W] */
-	entry =
-	    create_proc_entry("wakeup", S_IFREG | S_IRUGO | S_IWUSR,
-			      acpi_root_dir);
-	if (entry)
-		entry->proc_fops = &acpi_system_wakeup_device_fops;
+	proc_create("wakeup", S_IFREG | S_IRUGO | S_IWUSR,
+		    acpi_root_dir, &acpi_system_wakeup_device_fops);
 
 	return 0;
 }
diff --git a/trunk/drivers/acpi/system.c b/trunk/drivers/acpi/system.c
index 4749f379a915..769f24855eb6 100644
--- a/trunk/drivers/acpi/system.c
+++ b/trunk/drivers/acpi/system.c
@@ -396,6 +396,7 @@ static int acpi_system_info_open_fs(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations acpi_system_info_ops = {
+	.owner = THIS_MODULE,
 	.open = acpi_system_info_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -406,6 +407,7 @@ static ssize_t acpi_system_read_dsdt(struct file *, char __user *, size_t,
 				     loff_t *);
 
 static const struct file_operations acpi_system_dsdt_ops = {
+	.owner = THIS_MODULE,
 	.read = acpi_system_read_dsdt,
 };
 
@@ -430,6 +432,7 @@ static ssize_t acpi_system_read_fadt(struct file *, char __user *, size_t,
 				     loff_t *);
 
 static const struct file_operations acpi_system_fadt_ops = {
+	.owner = THIS_MODULE,
 	.read = acpi_system_read_fadt,
 };
 
@@ -454,31 +457,23 @@ static int acpi_system_procfs_init(void)
 {
 	struct proc_dir_entry *entry;
 	int error = 0;
-	char *name;
 
 	/* 'info' [R] */
-	name = ACPI_SYSTEM_FILE_INFO;
-	entry = create_proc_entry(name, S_IRUGO, acpi_root_dir);
+	entry = proc_create(ACPI_SYSTEM_FILE_INFO, S_IRUGO, acpi_root_dir,
+			    &acpi_system_info_ops);
 	if (!entry)
 		goto Error;
-	else {
-		entry->proc_fops = &acpi_system_info_ops;
-	}
 
 	/* 'dsdt' [R] */
-	name = ACPI_SYSTEM_FILE_DSDT;
-	entry = create_proc_entry(name, S_IRUSR, acpi_root_dir);
-	if (entry)
-		entry->proc_fops = &acpi_system_dsdt_ops;
-	else
+	entry = proc_create(ACPI_SYSTEM_FILE_DSDT, S_IRUSR, acpi_root_dir,
+			    &acpi_system_dsdt_ops);
+	if (!entry)
 		goto Error;
 
 	/* 'fadt' [R] */
-	name = ACPI_SYSTEM_FILE_FADT;
-	entry = create_proc_entry(name, S_IRUSR, acpi_root_dir);
-	if (entry)
-		entry->proc_fops = &acpi_system_fadt_ops;
-	else
+	entry = proc_create(ACPI_SYSTEM_FILE_FADT, S_IRUSR, acpi_root_dir,
+			    &acpi_system_fadt_ops);
+	if (!entry)
 		goto Error;
 
       Done:
diff --git a/trunk/drivers/acpi/thermal.c b/trunk/drivers/acpi/thermal.c
index 1bcecc7dd2ca..0815ac3ae3d6 100644
--- a/trunk/drivers/acpi/thermal.c
+++ b/trunk/drivers/acpi/thermal.c
@@ -198,6 +198,7 @@ struct acpi_thermal {
 };
 
 static const struct file_operations acpi_thermal_state_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_thermal_state_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -205,6 +206,7 @@ static const struct file_operations acpi_thermal_state_fops = {
 };
 
 static const struct file_operations acpi_thermal_temp_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_thermal_temp_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -212,6 +214,7 @@ static const struct file_operations acpi_thermal_temp_fops = {
 };
 
 static const struct file_operations acpi_thermal_trip_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_thermal_trip_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -219,6 +222,7 @@ static const struct file_operations acpi_thermal_trip_fops = {
 };
 
 static const struct file_operations acpi_thermal_cooling_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_thermal_cooling_open_fs,
 	.read = seq_read,
 	.write = acpi_thermal_write_cooling_mode,
@@ -227,6 +231,7 @@ static const struct file_operations acpi_thermal_cooling_fops = {
 };
 
 static const struct file_operations acpi_thermal_polling_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_thermal_polling_open_fs,
 	.read = seq_read,
 	.write = acpi_thermal_write_polling,
@@ -1419,63 +1424,47 @@ static int acpi_thermal_add_fs(struct acpi_device *device)
 	}
 
 	/* 'state' [R] */
-	entry = create_proc_entry(ACPI_THERMAL_FILE_STATE,
-				  S_IRUGO, acpi_device_dir(device));
+	entry = proc_create_data(ACPI_THERMAL_FILE_STATE,
+				 S_IRUGO, acpi_device_dir(device),
+				 &acpi_thermal_state_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		entry->proc_fops = &acpi_thermal_state_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	/* 'temperature' [R] */
-	entry = create_proc_entry(ACPI_THERMAL_FILE_TEMPERATURE,
-				  S_IRUGO, acpi_device_dir(device));
+	entry = proc_create_data(ACPI_THERMAL_FILE_TEMPERATURE,
+				 S_IRUGO, acpi_device_dir(device),
+				 &acpi_thermal_temp_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		entry->proc_fops = &acpi_thermal_temp_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	/* 'trip_points' [R] */
-	entry = create_proc_entry(ACPI_THERMAL_FILE_TRIP_POINTS,
-				  S_IRUGO,
-				  acpi_device_dir(device));
+	entry = proc_create_data(ACPI_THERMAL_FILE_TRIP_POINTS,
+				 S_IRUGO,
+				 acpi_device_dir(device),
+				 &acpi_thermal_trip_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		entry->proc_fops = &acpi_thermal_trip_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	/* 'cooling_mode' [R/W] */
-	entry = create_proc_entry(ACPI_THERMAL_FILE_COOLING_MODE,
-				  S_IFREG | S_IRUGO | S_IWUSR,
-				  acpi_device_dir(device));
+	entry = proc_create_data(ACPI_THERMAL_FILE_COOLING_MODE,
+				 S_IFREG | S_IRUGO | S_IWUSR,
+				 acpi_device_dir(device),
+				 &acpi_thermal_cooling_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		entry->proc_fops = &acpi_thermal_cooling_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	/* 'polling_frequency' [R/W] */
-	entry = create_proc_entry(ACPI_THERMAL_FILE_POLLING_FREQ,
-				  S_IFREG | S_IRUGO | S_IWUSR,
-				  acpi_device_dir(device));
+	entry = proc_create_data(ACPI_THERMAL_FILE_POLLING_FREQ,
+				 S_IFREG | S_IRUGO | S_IWUSR,
+				 acpi_device_dir(device),
+				 &acpi_thermal_polling_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		entry->proc_fops = &acpi_thermal_polling_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
-
 	return 0;
 }
 
@@ -1710,7 +1699,6 @@ static int acpi_thermal_resume(struct acpi_device *device)
 	return AE_OK;
 }
 
-#ifdef CONFIG_DMI
 static int thermal_act(const struct dmi_system_id *d) {
 
 	if (act == 0) {
@@ -1785,7 +1773,6 @@ static struct dmi_system_id thermal_dmi_table[] __initdata = {
 	},
 	{}
 };
-#endif /* CONFIG_DMI */
 
 static int __init acpi_thermal_init(void)
 {
diff --git a/trunk/drivers/acpi/video.c b/trunk/drivers/acpi/video.c
index 980a74188781..43b228314a86 100644
--- a/trunk/drivers/acpi/video.c
+++ b/trunk/drivers/acpi/video.c
@@ -192,6 +192,7 @@ struct acpi_video_device {
 /* bus */
 static int acpi_video_bus_info_open_fs(struct inode *inode, struct file *file);
 static struct file_operations acpi_video_bus_info_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_video_bus_info_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -200,6 +201,7 @@ static struct file_operations acpi_video_bus_info_fops = {
 
 static int acpi_video_bus_ROM_open_fs(struct inode *inode, struct file *file);
 static struct file_operations acpi_video_bus_ROM_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_video_bus_ROM_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -209,6 +211,7 @@ static struct file_operations acpi_video_bus_ROM_fops = {
 static int acpi_video_bus_POST_info_open_fs(struct inode *inode,
 					    struct file *file);
 static struct file_operations acpi_video_bus_POST_info_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_video_bus_POST_info_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -217,6 +220,7 @@ static struct file_operations acpi_video_bus_POST_info_fops = {
 
 static int acpi_video_bus_POST_open_fs(struct inode *inode, struct file *file);
 static struct file_operations acpi_video_bus_POST_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_video_bus_POST_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -225,6 +229,7 @@ static struct file_operations acpi_video_bus_POST_fops = {
 
 static int acpi_video_bus_DOS_open_fs(struct inode *inode, struct file *file);
 static struct file_operations acpi_video_bus_DOS_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_video_bus_DOS_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -235,6 +240,7 @@ static struct file_operations acpi_video_bus_DOS_fops = {
 static int acpi_video_device_info_open_fs(struct inode *inode,
 					  struct file *file);
 static struct file_operations acpi_video_device_info_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_video_device_info_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -244,6 +250,7 @@ static struct file_operations acpi_video_device_info_fops = {
 static int acpi_video_device_state_open_fs(struct inode *inode,
 					   struct file *file);
 static struct file_operations acpi_video_device_state_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_video_device_state_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -253,6 +260,7 @@ static struct file_operations acpi_video_device_state_fops = {
 static int acpi_video_device_brightness_open_fs(struct inode *inode,
 						struct file *file);
 static struct file_operations acpi_video_device_brightness_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_video_device_brightness_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -262,6 +270,7 @@ static struct file_operations acpi_video_device_brightness_fops = {
 static int acpi_video_device_EDID_open_fs(struct inode *inode,
 					  struct file *file);
 static struct file_operations acpi_video_device_EDID_fops = {
+	.owner = THIS_MODULE,
 	.open = acpi_video_device_EDID_open_fs,
 	.read = seq_read,
 	.llseek = seq_lseek,
@@ -1070,51 +1079,36 @@ static int acpi_video_device_add_fs(struct acpi_device *device)
 	}
 
 	/* 'info' [R] */
-	entry = create_proc_entry("info", S_IRUGO, acpi_device_dir(device));
+	entry = proc_create_data("info", S_IRUGO, acpi_device_dir(device),
+			&acpi_video_device_info_fops, acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		entry->proc_fops = &acpi_video_device_info_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	/* 'state' [R/W] */
-	entry =
-	    create_proc_entry("state", S_IFREG | S_IRUGO | S_IWUSR,
-			      acpi_device_dir(device));
+	acpi_video_device_state_fops.write = acpi_video_device_write_state;
+	entry = proc_create_data("state", S_IFREG | S_IRUGO | S_IWUSR,
+				 acpi_device_dir(device),
+				 &acpi_video_device_state_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		acpi_video_device_state_fops.write = acpi_video_device_write_state;
-		entry->proc_fops = &acpi_video_device_state_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	/* 'brightness' [R/W] */
-	entry =
-	    create_proc_entry("brightness", S_IFREG | S_IRUGO | S_IWUSR,
-			      acpi_device_dir(device));
+	acpi_video_device_brightness_fops.write =
+		acpi_video_device_write_brightness;
+	entry = proc_create_data("brightness", S_IFREG | S_IRUGO | S_IWUSR,
+				 acpi_device_dir(device),
+				 &acpi_video_device_brightness_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		acpi_video_device_brightness_fops.write = acpi_video_device_write_brightness;
-		entry->proc_fops = &acpi_video_device_brightness_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	/* 'EDID' [R] */
-	entry = create_proc_entry("EDID", S_IRUGO, acpi_device_dir(device));
+	entry = proc_create_data("EDID", S_IRUGO, acpi_device_dir(device),
+				 &acpi_video_device_EDID_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		entry->proc_fops = &acpi_video_device_EDID_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
-
 	return 0;
 }
 
@@ -1353,61 +1347,43 @@ static int acpi_video_bus_add_fs(struct acpi_device *device)
 	}
 
 	/* 'info' [R] */
-	entry = create_proc_entry("info", S_IRUGO, acpi_device_dir(device));
+	entry = proc_create_data("info", S_IRUGO, acpi_device_dir(device),
+				 &acpi_video_bus_info_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		entry->proc_fops = &acpi_video_bus_info_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	/* 'ROM' [R] */
-	entry = create_proc_entry("ROM", S_IRUGO, acpi_device_dir(device));
+	entry = proc_create_data("ROM", S_IRUGO, acpi_device_dir(device),
+				 &acpi_video_bus_ROM_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		entry->proc_fops = &acpi_video_bus_ROM_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	/* 'POST_info' [R] */
-	entry =
-	    create_proc_entry("POST_info", S_IRUGO, acpi_device_dir(device));
+	entry = proc_create_data("POST_info", S_IRUGO, acpi_device_dir(device),
+				 &acpi_video_bus_POST_info_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		entry->proc_fops = &acpi_video_bus_POST_info_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	/* 'POST' [R/W] */
-	entry =
-	    create_proc_entry("POST", S_IFREG | S_IRUGO | S_IRUSR,
-			      acpi_device_dir(device));
+	acpi_video_bus_POST_fops.write = acpi_video_bus_write_POST;
+	entry = proc_create_data("POST", S_IFREG | S_IRUGO | S_IRUSR,
+				 acpi_device_dir(device),
+				 &acpi_video_bus_POST_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		acpi_video_bus_POST_fops.write = acpi_video_bus_write_POST;
-		entry->proc_fops = &acpi_video_bus_POST_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	/* 'DOS' [R/W] */
-	entry =
-	    create_proc_entry("DOS", S_IFREG | S_IRUGO | S_IRUSR,
-			      acpi_device_dir(device));
+	acpi_video_bus_DOS_fops.write = acpi_video_bus_write_DOS;
+	entry = proc_create_data("DOS", S_IFREG | S_IRUGO | S_IRUSR,
+				 acpi_device_dir(device),
+				 &acpi_video_bus_DOS_fops,
+				 acpi_driver_data(device));
 	if (!entry)
 		return -ENODEV;
-	else {
-		acpi_video_bus_DOS_fops.write = acpi_video_bus_write_DOS;
-		entry->proc_fops = &acpi_video_bus_DOS_fops;
-		entry->data = acpi_driver_data(device);
-		entry->owner = THIS_MODULE;
-	}
 
 	return 0;
 }
diff --git a/trunk/drivers/ata/sata_fsl.c b/trunk/drivers/ata/sata_fsl.c
index fddd346b1d57..853559e32315 100644
--- a/trunk/drivers/ata/sata_fsl.c
+++ b/trunk/drivers/ata/sata_fsl.c
@@ -678,7 +678,7 @@ static unsigned int sata_fsl_dev_classify(struct ata_port *ap)
 	return ata_dev_classify(&tf);
 }
 
-static int sata_fsl_prereset(struct ata_linke *link, unsigned long deadline)
+static int sata_fsl_prereset(struct ata_link *link, unsigned long deadline)
 {
 	/* FIXME: Never skip softreset, sata_fsl_softreset() is
 	 * combination of soft and hard resets.  sata_fsl_softreset()
diff --git a/trunk/drivers/atm/nicstar.c b/trunk/drivers/atm/nicstar.c
index 38c769f8d2b7..3da804b1627d 100644
--- a/trunk/drivers/atm/nicstar.c
+++ b/trunk/drivers/atm/nicstar.c
@@ -415,7 +415,7 @@ static int __devinit ns_init_card(int i, struct pci_dev *pcidev)
    card->pcidev = pcidev;
    membase = pci_resource_start(pcidev, 1);
    card->membase = ioremap(membase, NS_IOREMAP_SIZE);
-   if (card->membase == 0)
+   if (!card->membase)
    {
       printk("nicstar%d: can't ioremap() membase.\n",i);
       error = 3;
diff --git a/trunk/drivers/base/firmware_class.c b/trunk/drivers/base/firmware_class.c
index 1fef7df8c9d6..9fd4a8534146 100644
--- a/trunk/drivers/base/firmware_class.c
+++ b/trunk/drivers/base/firmware_class.c
@@ -396,6 +396,8 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 	if (!firmware_p)
 		return -EINVAL;
 
+	printk(KERN_INFO "firmware: requesting %s\n", name);
+
 	*firmware_p = firmware = kzalloc(sizeof(*firmware), GFP_KERNEL);
 	if (!firmware) {
 		printk(KERN_ERR "%s: kmalloc(struct firmware) failed\n",
diff --git a/trunk/drivers/block/aoe/aoe.h b/trunk/drivers/block/aoe/aoe.h
index 280e71ee744c..5b4c6e649c11 100644
--- a/trunk/drivers/block/aoe/aoe.h
+++ b/trunk/drivers/block/aoe/aoe.h
@@ -195,7 +195,6 @@ void aoedev_exit(void);
 struct aoedev *aoedev_by_aoeaddr(int maj, int min);
 struct aoedev *aoedev_by_sysminor_m(ulong sysminor);
 void aoedev_downdev(struct aoedev *d);
-int aoedev_isbusy(struct aoedev *d);
 int aoedev_flush(const char __user *str, size_t size);
 
 int aoenet_init(void);
diff --git a/trunk/drivers/block/aoe/aoecmd.c b/trunk/drivers/block/aoe/aoecmd.c
index d00293ba3b45..8fc429cf82b6 100644
--- a/trunk/drivers/block/aoe/aoecmd.c
+++ b/trunk/drivers/block/aoe/aoecmd.c
@@ -668,16 +668,16 @@ ataid_complete(struct aoedev *d, struct aoetgt *t, unsigned char *id)
 	u16 n;
 
 	/* word 83: command set supported */
-	n = le16_to_cpu(get_unaligned((__le16 *) &id[83<<1]));
+	n = get_unaligned_le16(&id[83 << 1]);
 
 	/* word 86: command set/feature enabled */
-	n |= le16_to_cpu(get_unaligned((__le16 *) &id[86<<1]));
+	n |= get_unaligned_le16(&id[86 << 1]);
 
 	if (n & (1<<10)) {	/* bit 10: LBA 48 */
 		d->flags |= DEVFL_EXT;
 
 		/* word 100: number lba48 sectors */
-		ssize = le64_to_cpu(get_unaligned((__le64 *) &id[100<<1]));
+		ssize = get_unaligned_le64(&id[100 << 1]);
 
 		/* set as in ide-disk.c:init_idedisk_capacity */
 		d->geo.cylinders = ssize;
@@ -688,12 +688,12 @@ ataid_complete(struct aoedev *d, struct aoetgt *t, unsigned char *id)
 		d->flags &= ~DEVFL_EXT;
 
 		/* number lba28 sectors */
-		ssize = le32_to_cpu(get_unaligned((__le32 *) &id[60<<1]));
+		ssize = get_unaligned_le32(&id[60 << 1]);
 
 		/* NOTE: obsolete in ATA 6 */
-		d->geo.cylinders = le16_to_cpu(get_unaligned((__le16 *) &id[54<<1]));
-		d->geo.heads = le16_to_cpu(get_unaligned((__le16 *) &id[55<<1]));
-		d->geo.sectors = le16_to_cpu(get_unaligned((__le16 *) &id[56<<1]));
+		d->geo.cylinders = get_unaligned_le16(&id[54 << 1]);
+		d->geo.heads = get_unaligned_le16(&id[55 << 1]);
+		d->geo.sectors = get_unaligned_le16(&id[56 << 1]);
 	}
 
 	if (d->ssize != ssize)
@@ -779,7 +779,7 @@ aoecmd_ata_rsp(struct sk_buff *skb)
 	u16 aoemajor;
 
 	hin = (struct aoe_hdr *) skb_mac_header(skb);
-	aoemajor = be16_to_cpu(get_unaligned(&hin->major));
+	aoemajor = get_unaligned_be16(&hin->major);
 	d = aoedev_by_aoeaddr(aoemajor, hin->minor);
 	if (d == NULL) {
 		snprintf(ebuf, sizeof ebuf, "aoecmd_ata_rsp: ata response "
@@ -791,7 +791,7 @@ aoecmd_ata_rsp(struct sk_buff *skb)
 
 	spin_lock_irqsave(&d->lock, flags);
 
-	n = be32_to_cpu(get_unaligned(&hin->tag));
+	n = get_unaligned_be32(&hin->tag);
 	t = gettgt(d, hin->src);
 	if (t == NULL) {
 		printk(KERN_INFO "aoe: can't find target e%ld.%d:%012llx\n",
@@ -806,9 +806,9 @@ aoecmd_ata_rsp(struct sk_buff *skb)
 		snprintf(ebuf, sizeof ebuf,
 			"%15s e%d.%d    tag=%08x@%08lx\n",
 			"unexpected rsp",
-			be16_to_cpu(get_unaligned(&hin->major)),
+			get_unaligned_be16(&hin->major),
 			hin->minor,
-			be32_to_cpu(get_unaligned(&hin->tag)),
+			get_unaligned_be32(&hin->tag),
 			jiffies);
 		aoechr_error(ebuf);
 		return;
@@ -873,7 +873,7 @@ aoecmd_ata_rsp(struct sk_buff *skb)
 			printk(KERN_INFO
 				"aoe: unrecognized ata command %2.2Xh for %d.%d\n",
 				ahout->cmdstat,
-				be16_to_cpu(get_unaligned(&hin->major)),
+				get_unaligned_be16(&hin->major),
 				hin->minor);
 		}
 	}
diff --git a/trunk/drivers/block/aoe/aoedev.c b/trunk/drivers/block/aoe/aoedev.c
index f9a1cd9edb77..a1d813ab0d6b 100644
--- a/trunk/drivers/block/aoe/aoedev.c
+++ b/trunk/drivers/block/aoe/aoedev.c
@@ -18,24 +18,6 @@ static void skbpoolfree(struct aoedev *d);
 static struct aoedev *devlist;
 static DEFINE_SPINLOCK(devlist_lock);
 
-int
-aoedev_isbusy(struct aoedev *d)
-{
-	struct aoetgt **t, **te;
-	struct frame *f, *e;
-
-	t = d->targets;
-	te = t + NTARGETS;
-	for (; t < te && *t; t++) {
-		f = (*t)->frames;
-		e = f + (*t)->nframes;
-		for (; f < e; f++)
-			if (f->tag != FREETAG)
-				return 1;
-	}
-	return 0;
-}
-
 struct aoedev *
 aoedev_by_aoeaddr(int maj, int min)
 {
diff --git a/trunk/drivers/block/aoe/aoenet.c b/trunk/drivers/block/aoe/aoenet.c
index 18d243c73eee..d625169c8e48 100644
--- a/trunk/drivers/block/aoe/aoenet.c
+++ b/trunk/drivers/block/aoe/aoenet.c
@@ -128,7 +128,7 @@ aoenet_rcv(struct sk_buff *skb, struct net_device *ifp, struct packet_type *pt,
 	skb_push(skb, ETH_HLEN);	/* (1) */
 
 	h = (struct aoe_hdr *) skb_mac_header(skb);
-	n = be32_to_cpu(get_unaligned(&h->tag));
+	n = get_unaligned_be32(&h->tag);
 	if ((h->verfl & AOEFL_RSP) == 0 || (n & 1<<31))
 		goto exit;
 
@@ -140,7 +140,7 @@ aoenet_rcv(struct sk_buff *skb, struct net_device *ifp, struct packet_type *pt,
 			printk(KERN_ERR
 				"%s%d.%d@%s; ecode=%d '%s'\n",
 				"aoe: error packet from ",
-				be16_to_cpu(get_unaligned(&h->major)),
+				get_unaligned_be16(&h->major),
 				h->minor, skb->dev->name,
 				h->err, aoe_errlist[n]);
 		goto exit;
diff --git a/trunk/drivers/block/brd.c b/trunk/drivers/block/brd.c
index 7bd76639544c..e8e38faeafd8 100644
--- a/trunk/drivers/block/brd.c
+++ b/trunk/drivers/block/brd.c
@@ -319,7 +319,7 @@ static int brd_make_request(struct request_queue *q, struct bio *bio)
 
 #ifdef CONFIG_BLK_DEV_XIP
 static int brd_direct_access (struct block_device *bdev, sector_t sector,
-			unsigned long *data)
+			void **kaddr, unsigned long *pfn)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	struct page *page;
@@ -333,7 +333,8 @@ static int brd_direct_access (struct block_device *bdev, sector_t sector,
 	page = brd_insert_page(brd, sector);
 	if (!page)
 		return -ENOMEM;
-	*data = (unsigned long)page_address(page);
+	*kaddr = page_address(page);
+	*pfn = page_to_pfn(page);
 
 	return 0;
 }
diff --git a/trunk/drivers/block/cciss.c b/trunk/drivers/block/cciss.c
index cf6083a1f928..e539be5750dc 100644
--- a/trunk/drivers/block/cciss.c
+++ b/trunk/drivers/block/cciss.c
@@ -425,7 +425,7 @@ static void __devinit cciss_procinit(int i)
 	struct proc_dir_entry *pde;
 
 	if (proc_cciss == NULL)
-		proc_cciss = proc_mkdir("cciss", proc_root_driver);
+		proc_cciss = proc_mkdir("driver/cciss", NULL);
 	if (!proc_cciss)
 		return;
 	pde = proc_create(hba[i]->devname, S_IWUSR | S_IRUSR | S_IRGRP |
@@ -3700,7 +3700,7 @@ static void __exit cciss_cleanup(void)
 			cciss_remove_one(hba[i]->pdev);
 		}
 	}
-	remove_proc_entry("cciss", proc_root_driver);
+	remove_proc_entry("driver/cciss", NULL);
 }
 
 static void fail_all_cmds(unsigned long ctlr)
diff --git a/trunk/drivers/block/cpqarray.c b/trunk/drivers/block/cpqarray.c
index 69199185ff4b..09c14341e6e3 100644
--- a/trunk/drivers/block/cpqarray.c
+++ b/trunk/drivers/block/cpqarray.c
@@ -214,7 +214,7 @@ static struct proc_dir_entry *proc_array;
 static void __init ida_procinit(int i)
 {
 	if (proc_array == NULL) {
-		proc_array = proc_mkdir("cpqarray", proc_root_driver);
+		proc_array = proc_mkdir("driver/cpqarray", NULL);
 		if (!proc_array) return;
 	}
 
@@ -1796,7 +1796,7 @@ static void __exit cpqarray_exit(void)
 		}
 	}
 
-	remove_proc_entry("cpqarray", proc_root_driver);
+	remove_proc_entry("driver/cpqarray", NULL);
 }
 
 module_init(cpqarray_init)
diff --git a/trunk/drivers/block/floppy.c b/trunk/drivers/block/floppy.c
index 7652e87d60c5..395f8ea7981c 100644
--- a/trunk/drivers/block/floppy.c
+++ b/trunk/drivers/block/floppy.c
@@ -4526,14 +4526,15 @@ static void __init parse_floppy_cfg_string(char *cfg)
 	}
 }
 
-int __init init_module(void)
+static int __init floppy_module_init(void)
 {
 	if (floppy)
 		parse_floppy_cfg_string(floppy);
 	return floppy_init();
 }
+module_init(floppy_module_init);
 
-void cleanup_module(void)
+static void __exit floppy_module_exit(void)
 {
 	int drive;
 
@@ -4562,6 +4563,7 @@ void cleanup_module(void)
 	/* eject disk, if any */
 	fd_eject(0);
 }
+module_exit(floppy_module_exit);
 
 module_param(floppy, charp, 0);
 module_param(FLOPPY_IRQ, int, 0);
diff --git a/trunk/drivers/block/loop.c b/trunk/drivers/block/loop.c
index f7f163557aa0..d3a25b027ff9 100644
--- a/trunk/drivers/block/loop.c
+++ b/trunk/drivers/block/loop.c
@@ -546,7 +546,7 @@ static void loop_unplug(struct request_queue *q)
 {
 	struct loop_device *lo = q->queuedata;
 
-	clear_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags);
+	queue_flag_clear_unlocked(QUEUE_FLAG_PLUGGED, q);
 	blk_run_address_space(lo->lo_backing_file->f_mapping);
 }
 
diff --git a/trunk/drivers/block/nbd.c b/trunk/drivers/block/nbd.c
index 60cc54368b66..ad98dda6037d 100644
--- a/trunk/drivers/block/nbd.c
+++ b/trunk/drivers/block/nbd.c
@@ -29,6 +29,7 @@
 #include <linux/kernel.h>
 #include <net/sock.h>
 #include <linux/net.h>
+#include <linux/kthread.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -55,6 +56,7 @@ static unsigned int debugflags;
 
 static unsigned int nbds_max = 16;
 static struct nbd_device *nbd_dev;
+static int max_part;
 
 /*
  * Use just one lock (or at most 1 per NIC). Two arguments for this:
@@ -337,7 +339,7 @@ static struct request *nbd_read_stat(struct nbd_device *lo)
 	}
 
 	req = nbd_find_request(lo, *(struct request **)reply.handle);
-	if (unlikely(IS_ERR(req))) {
+	if (IS_ERR(req)) {
 		result = PTR_ERR(req);
 		if (result != -ENOENT)
 			goto harderror;
@@ -441,6 +443,85 @@ static void nbd_clear_que(struct nbd_device *lo)
 }
 
 
+static void nbd_handle_req(struct nbd_device *lo, struct request *req)
+{
+	if (!blk_fs_request(req))
+		goto error_out;
+
+	nbd_cmd(req) = NBD_CMD_READ;
+	if (rq_data_dir(req) == WRITE) {
+		nbd_cmd(req) = NBD_CMD_WRITE;
+		if (lo->flags & NBD_READ_ONLY) {
+			printk(KERN_ERR "%s: Write on read-only\n",
+					lo->disk->disk_name);
+			goto error_out;
+		}
+	}
+
+	req->errors = 0;
+
+	mutex_lock(&lo->tx_lock);
+	if (unlikely(!lo->sock)) {
+		mutex_unlock(&lo->tx_lock);
+		printk(KERN_ERR "%s: Attempted send on closed socket\n",
+		       lo->disk->disk_name);
+		req->errors++;
+		nbd_end_request(req);
+		return;
+	}
+
+	lo->active_req = req;
+
+	if (nbd_send_req(lo, req) != 0) {
+		printk(KERN_ERR "%s: Request send failed\n",
+				lo->disk->disk_name);
+		req->errors++;
+		nbd_end_request(req);
+	} else {
+		spin_lock(&lo->queue_lock);
+		list_add(&req->queuelist, &lo->queue_head);
+		spin_unlock(&lo->queue_lock);
+	}
+
+	lo->active_req = NULL;
+	mutex_unlock(&lo->tx_lock);
+	wake_up_all(&lo->active_wq);
+
+	return;
+
+error_out:
+	req->errors++;
+	nbd_end_request(req);
+}
+
+static int nbd_thread(void *data)
+{
+	struct nbd_device *lo = data;
+	struct request *req;
+
+	set_user_nice(current, -20);
+	while (!kthread_should_stop() || !list_empty(&lo->waiting_queue)) {
+		/* wait for something to do */
+		wait_event_interruptible(lo->waiting_wq,
+					 kthread_should_stop() ||
+					 !list_empty(&lo->waiting_queue));
+
+		/* extract request */
+		if (list_empty(&lo->waiting_queue))
+			continue;
+
+		spin_lock_irq(&lo->queue_lock);
+		req = list_entry(lo->waiting_queue.next, struct request,
+				 queuelist);
+		list_del_init(&req->queuelist);
+		spin_unlock_irq(&lo->queue_lock);
+
+		/* handle request */
+		nbd_handle_req(lo, req);
+	}
+	return 0;
+}
+
 /*
  * We always wait for result of write, for now. It would be nice to make it optional
  * in future
@@ -456,65 +537,23 @@ static void do_nbd_request(struct request_queue * q)
 		struct nbd_device *lo;
 
 		blkdev_dequeue_request(req);
+
+		spin_unlock_irq(q->queue_lock);
+
 		dprintk(DBG_BLKDEV, "%s: request %p: dequeued (flags=%x)\n",
 				req->rq_disk->disk_name, req, req->cmd_type);
 
-		if (!blk_fs_request(req))
-			goto error_out;
-
 		lo = req->rq_disk->private_data;
 
 		BUG_ON(lo->magic != LO_MAGIC);
 
-		nbd_cmd(req) = NBD_CMD_READ;
-		if (rq_data_dir(req) == WRITE) {
-			nbd_cmd(req) = NBD_CMD_WRITE;
-			if (lo->flags & NBD_READ_ONLY) {
-				printk(KERN_ERR "%s: Write on read-only\n",
-						lo->disk->disk_name);
-				goto error_out;
-			}
-		}
-
-		req->errors = 0;
-		spin_unlock_irq(q->queue_lock);
-
-		mutex_lock(&lo->tx_lock);
-		if (unlikely(!lo->sock)) {
-			mutex_unlock(&lo->tx_lock);
-			printk(KERN_ERR "%s: Attempted send on closed socket\n",
-			       lo->disk->disk_name);
-			req->errors++;
-			nbd_end_request(req);
-			spin_lock_irq(q->queue_lock);
-			continue;
-		}
-
-		lo->active_req = req;
+		spin_lock_irq(&lo->queue_lock);
+		list_add_tail(&req->queuelist, &lo->waiting_queue);
+		spin_unlock_irq(&lo->queue_lock);
 
-		if (nbd_send_req(lo, req) != 0) {
-			printk(KERN_ERR "%s: Request send failed\n",
-					lo->disk->disk_name);
-			req->errors++;
-			nbd_end_request(req);
-		} else {
-			spin_lock(&lo->queue_lock);
-			list_add(&req->queuelist, &lo->queue_head);
-			spin_unlock(&lo->queue_lock);
-		}
-
-		lo->active_req = NULL;
-		mutex_unlock(&lo->tx_lock);
-		wake_up_all(&lo->active_wq);
+		wake_up(&lo->waiting_wq);
 
 		spin_lock_irq(q->queue_lock);
-		continue;
-
-error_out:
-		req->errors++;
-		spin_unlock(q->queue_lock);
-		nbd_end_request(req);
-		spin_lock(q->queue_lock);
 	}
 }
 
@@ -524,6 +563,7 @@ static int nbd_ioctl(struct inode *inode, struct file *file,
 	struct nbd_device *lo = inode->i_bdev->bd_disk->private_data;
 	int error;
 	struct request sreq ;
+	struct task_struct *thread;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -537,6 +577,7 @@ static int nbd_ioctl(struct inode *inode, struct file *file,
 	switch (cmd) {
 	case NBD_DISCONNECT:
 	        printk(KERN_INFO "%s: NBD_DISCONNECT\n", lo->disk->disk_name);
+		blk_rq_init(NULL, &sreq);
 		sreq.cmd_type = REQ_TYPE_SPECIAL;
 		nbd_cmd(&sreq) = NBD_CMD_DISC;
 		/*
@@ -571,10 +612,13 @@ static int nbd_ioctl(struct inode *inode, struct file *file,
 		error = -EINVAL;
 		file = fget(arg);
 		if (file) {
+			struct block_device *bdev = inode->i_bdev;
 			inode = file->f_path.dentry->d_inode;
 			if (S_ISSOCK(inode->i_mode)) {
 				lo->file = file;
 				lo->sock = SOCKET_I(inode);
+				if (max_part > 0)
+					bdev->bd_invalidated = 1;
 				error = 0;
 			} else {
 				fput(file);
@@ -606,7 +650,12 @@ static int nbd_ioctl(struct inode *inode, struct file *file,
 	case NBD_DO_IT:
 		if (!lo->file)
 			return -EINVAL;
+		thread = kthread_create(nbd_thread, lo, lo->disk->disk_name);
+		if (IS_ERR(thread))
+			return PTR_ERR(thread);
+		wake_up_process(thread);
 		error = nbd_do_it(lo);
+		kthread_stop(thread);
 		if (error)
 			return error;
 		sock_shutdown(lo, 1);
@@ -619,6 +668,8 @@ static int nbd_ioctl(struct inode *inode, struct file *file,
 		lo->bytesize = 0;
 		inode->i_bdev->bd_inode->i_size = 0;
 		set_capacity(lo->disk, 0);
+		if (max_part > 0)
+			ioctl_by_bdev(inode->i_bdev, BLKRRPART, 0);
 		return lo->harderror;
 	case NBD_CLEAR_QUE:
 		/*
@@ -652,6 +703,7 @@ static int __init nbd_init(void)
 {
 	int err = -ENOMEM;
 	int i;
+	int part_shift;
 
 	BUILD_BUG_ON(sizeof(struct nbd_request) != 28);
 
@@ -659,8 +711,17 @@ static int __init nbd_init(void)
 	if (!nbd_dev)
 		return -ENOMEM;
 
+	if (max_part < 0) {
+		printk(KERN_CRIT "nbd: max_part must be >= 0\n");
+		return -EINVAL;
+	}
+
+	part_shift = 0;
+	if (max_part > 0)
+		part_shift = fls(max_part);
+
 	for (i = 0; i < nbds_max; i++) {
-		struct gendisk *disk = alloc_disk(1);
+		struct gendisk *disk = alloc_disk(1 << part_shift);
 		elevator_t *old_e;
 		if (!disk)
 			goto out;
@@ -695,17 +756,18 @@ static int __init nbd_init(void)
 		nbd_dev[i].file = NULL;
 		nbd_dev[i].magic = LO_MAGIC;
 		nbd_dev[i].flags = 0;
+		INIT_LIST_HEAD(&nbd_dev[i].waiting_queue);
 		spin_lock_init(&nbd_dev[i].queue_lock);
 		INIT_LIST_HEAD(&nbd_dev[i].queue_head);
 		mutex_init(&nbd_dev[i].tx_lock);
 		init_waitqueue_head(&nbd_dev[i].active_wq);
+		init_waitqueue_head(&nbd_dev[i].waiting_wq);
 		nbd_dev[i].blksize = 1024;
 		nbd_dev[i].bytesize = 0;
 		disk->major = NBD_MAJOR;
-		disk->first_minor = i;
+		disk->first_minor = i << part_shift;
 		disk->fops = &nbd_fops;
 		disk->private_data = &nbd_dev[i];
-		disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
 		sprintf(disk->disk_name, "nbd%d", i);
 		set_capacity(disk, 0);
 		add_disk(disk);
@@ -743,7 +805,9 @@ MODULE_DESCRIPTION("Network Block Device");
 MODULE_LICENSE("GPL");
 
 module_param(nbds_max, int, 0444);
-MODULE_PARM_DESC(nbds_max, "How many network block devices to initialize.");
+MODULE_PARM_DESC(nbds_max, "number of network block devices to initialize (default: 16)");
+module_param(max_part, int, 0444);
+MODULE_PARM_DESC(max_part, "number of partitions per device (default: 0)");
 #ifndef NDEBUG
 module_param(debugflags, int, 0644);
 MODULE_PARM_DESC(debugflags, "flags for controlling debug output");
diff --git a/trunk/drivers/block/paride/pd.c b/trunk/drivers/block/paride/pd.c
index df819f8a95a6..570f3b70dce7 100644
--- a/trunk/drivers/block/paride/pd.c
+++ b/trunk/drivers/block/paride/pd.c
@@ -716,10 +716,8 @@ static int pd_special_command(struct pd_unit *disk,
 	struct request rq;
 	int err = 0;
 
-	memset(&rq, 0, sizeof(rq));
-	rq.errors = 0;
+	blk_rq_init(NULL, &rq);
 	rq.rq_disk = disk->gd;
-	rq.ref_count = 1;
 	rq.end_io_data = &wait;
 	rq.end_io = blk_end_sync_rq;
 	blk_insert_request(disk->gd->queue, &rq, 0, func);
diff --git a/trunk/drivers/block/pktcdvd.c b/trunk/drivers/block/pktcdvd.c
index 18feb1c7c33b..3ba1df93e9e3 100644
--- a/trunk/drivers/block/pktcdvd.c
+++ b/trunk/drivers/block/pktcdvd.c
@@ -776,8 +776,6 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 
 	rq->cmd_len = COMMAND_SIZE(cgc->cmd[0]);
 	memcpy(rq->cmd, cgc->cmd, CDROM_PACKET_SIZE);
-	if (sizeof(rq->cmd) > CDROM_PACKET_SIZE)
-		memset(rq->cmd + CDROM_PACKET_SIZE, 0, sizeof(rq->cmd) - CDROM_PACKET_SIZE);
 
 	rq->timeout = 60*HZ;
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
@@ -2744,7 +2742,6 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	int i;
 	int ret = 0;
 	char b[BDEVNAME_SIZE];
-	struct proc_dir_entry *proc;
 	struct block_device *bdev;
 
 	if (pd->pkt_dev == dev) {
@@ -2788,11 +2785,7 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 		goto out_mem;
 	}
 
-	proc = create_proc_entry(pd->name, 0, pkt_proc);
-	if (proc) {
-		proc->data = pd;
-		proc->proc_fops = &pkt_proc_fops;
-	}
+	proc_create_data(pd->name, 0, pkt_proc, &pkt_proc_fops, pd);
 	DPRINTK(DRIVER_NAME": writer %s mapped to %s\n", pd->name, bdevname(bdev, b));
 	return 0;
 
@@ -3101,7 +3094,7 @@ static int __init pkt_init(void)
 		goto out_misc;
 	}
 
-	pkt_proc = proc_mkdir(DRIVER_NAME, proc_root_driver);
+	pkt_proc = proc_mkdir("driver/"DRIVER_NAME, NULL);
 
 	return 0;
 
@@ -3117,7 +3110,7 @@ static int __init pkt_init(void)
 
 static void __exit pkt_exit(void)
 {
-	remove_proc_entry(DRIVER_NAME, proc_root_driver);
+	remove_proc_entry("driver/"DRIVER_NAME, NULL);
 	misc_deregister(&pkt_misc);
 
 	pkt_debugfs_cleanup();
diff --git a/trunk/drivers/block/ps3disk.c b/trunk/drivers/block/ps3disk.c
index 7483f947f0e9..d797e209951d 100644
--- a/trunk/drivers/block/ps3disk.c
+++ b/trunk/drivers/block/ps3disk.c
@@ -102,8 +102,7 @@ static void ps3disk_scatter_gather(struct ps3_storage_device *dev,
 		dev_dbg(&dev->sbd.core,
 			"%s:%u: bio %u: %u segs %u sectors from %lu\n",
 			__func__, __LINE__, i, bio_segments(iter.bio),
-			bio_sectors(iter.bio),
-			(unsigned long)iter.bio->bi_sector);
+			bio_sectors(iter.bio), iter.bio->bi_sector);
 
 		size = bvec->bv_len;
 		buf = bvec_kmap_irq(bvec, &flags);
@@ -406,7 +405,6 @@ static void ps3disk_prepare_flush(struct request_queue *q, struct request *req)
 
 	dev_dbg(&dev->sbd.core, "%s:%u\n", __func__, __LINE__);
 
-	memset(req->cmd, 0, sizeof(req->cmd));
 	req->cmd_type = REQ_TYPE_FLUSH;
 }
 
diff --git a/trunk/drivers/block/ub.c b/trunk/drivers/block/ub.c
index 27bfe72aab59..e322cce8c12d 100644
--- a/trunk/drivers/block/ub.c
+++ b/trunk/drivers/block/ub.c
@@ -2399,7 +2399,7 @@ static void ub_disconnect(struct usb_interface *intf)
 		del_gendisk(lun->disk);
 		/*
 		 * I wish I could do:
-		 *    set_bit(QUEUE_FLAG_DEAD, &q->queue_flags);
+		 *    queue_flag_set(QUEUE_FLAG_DEAD, q);
 		 * As it is, we rely on our internal poisoning and let
 		 * the upper levels to spin furiously failing all the I/O.
 		 */
diff --git a/trunk/drivers/block/xen-blkfront.c b/trunk/drivers/block/xen-blkfront.c
index d771da816d95..f2fff5799ddf 100644
--- a/trunk/drivers/block/xen-blkfront.c
+++ b/trunk/drivers/block/xen-blkfront.c
@@ -137,7 +137,7 @@ static void blkif_restart_queue_callback(void *arg)
 	schedule_work(&info->work);
 }
 
-int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg)
+static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg)
 {
 	/* We don't have real geometry info, but let's at least return
 	   values consistent with the size of the device */
diff --git a/trunk/drivers/cdrom/cdrom.c b/trunk/drivers/cdrom/cdrom.c
index ac3829030ac5..69f26eb6415b 100644
--- a/trunk/drivers/cdrom/cdrom.c
+++ b/trunk/drivers/cdrom/cdrom.c
@@ -2194,7 +2194,6 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 		if (ret)
 			break;
 
-		memset(rq->cmd, 0, sizeof(rq->cmd));
 		rq->cmd[0] = GPCMD_READ_CD;
 		rq->cmd[1] = 1 << 2;
 		rq->cmd[2] = (lba >> 24) & 0xff;
diff --git a/trunk/drivers/cdrom/viocd.c b/trunk/drivers/cdrom/viocd.c
index b74b6c2768a8..5245a4a0ba74 100644
--- a/trunk/drivers/cdrom/viocd.c
+++ b/trunk/drivers/cdrom/viocd.c
@@ -144,6 +144,7 @@ static int proc_viocd_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations proc_viocd_operations = {
+	.owner		= THIS_MODULE,
 	.open		= proc_viocd_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -679,7 +680,6 @@ static struct vio_driver viocd_driver = {
 
 static int __init viocd_init(void)
 {
-	struct proc_dir_entry *e;
 	int ret = 0;
 
 	if (!firmware_has_feature(FW_FEATURE_ISERIES))
@@ -719,12 +719,8 @@ static int __init viocd_init(void)
 	if (ret)
 		goto out_free_info;
 
-	e = create_proc_entry("iSeries/viocd", S_IFREG|S_IRUGO, NULL);
-	if (e) {
-		e->owner = THIS_MODULE;
-		e->proc_fops = &proc_viocd_operations;
-	}
-
+	proc_create("iSeries/viocd", S_IFREG|S_IRUGO, NULL,
+		    &proc_viocd_operations);
 	return 0;
 
 out_free_info:
diff --git a/trunk/drivers/char/Kconfig b/trunk/drivers/char/Kconfig
index 2906ee7bd298..5dce3877eee5 100644
--- a/trunk/drivers/char/Kconfig
+++ b/trunk/drivers/char/Kconfig
@@ -80,6 +80,15 @@ config VT_HW_CONSOLE_BINDING
 	 information. For framebuffer console users, please refer to
 	 <file:Documentation/fb/fbcon.txt>.
 
+config DEVKMEM
+	bool "/dev/kmem virtual device support"
+	default y
+	help
+	  Say Y here if you want to support the /dev/kmem device. The
+	  /dev/kmem device is rarely used, but can be used for certain
+	  kind of kernel debugging operations.
+	  When in doubt, say "N".
+
 config SERIAL_NONSTANDARD
 	bool "Non-standard serial port support"
 	depends on HAS_IOMEM
@@ -732,9 +741,16 @@ config NVRAM
 	  To compile this driver as a module, choose M here: the
 	  module will be called nvram.
 
+#
+# These legacy RTC drivers just cause too many conflicts with the generic
+# RTC framework ... let's not even try to coexist any more.
+#
+if RTC_LIB=n
+
 config RTC
 	tristate "Enhanced Real Time Clock Support"
-	depends on !PPC && !PARISC && !IA64 && !M68K && !SPARC && !FRV && !ARM && !SUPERH && !S390 && !AVR32
+	depends on !PPC && !PARISC && !IA64 && !M68K && !SPARC && !FRV \
+			&& !ARM && !SUPERH && !S390 && !AVR32
 	---help---
 	  If you say Y here and create a character special file /dev/rtc with
 	  major number 10 and minor number 135 using mknod ("man mknod"), you
@@ -840,6 +856,8 @@ config DS1302
 	  will get access to the real time clock (or hardware clock) built
 	  into your computer.
 
+endif # RTC_LIB
+
 config COBALT_LCD
 	bool "Support for Cobalt LCD"
 	depends on MIPS_COBALT
diff --git a/trunk/drivers/char/apm-emulation.c b/trunk/drivers/char/apm-emulation.c
index 17d54315e146..cdd876dbb2b0 100644
--- a/trunk/drivers/char/apm-emulation.c
+++ b/trunk/drivers/char/apm-emulation.c
@@ -14,6 +14,7 @@
 #include <linux/poll.h>
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/miscdevice.h>
 #include <linux/apm_bios.h>
 #include <linux/capability.h>
@@ -493,11 +494,10 @@ static struct miscdevice apm_device = {
  *	-1: Unknown
  *   8) min = minutes; sec = seconds
  */
-static int apm_get_info(char *buf, char **start, off_t fpos, int length)
+static int proc_apm_show(struct seq_file *m, void *v)
 {
 	struct apm_power_info info;
 	char *units;
-	int ret;
 
 	info.ac_line_status = 0xff;
 	info.battery_status = 0xff;
@@ -515,14 +515,27 @@ static int apm_get_info(char *buf, char **start, off_t fpos, int length)
 	case 1: 	units = "sec";	break;
 	}
 
-	ret = sprintf(buf, "%s 1.2 0x%02x 0x%02x 0x%02x 0x%02x %d%% %d %s\n",
+	seq_printf(m, "%s 1.2 0x%02x 0x%02x 0x%02x 0x%02x %d%% %d %s\n",
 		     driver_version, APM_32_BIT_SUPPORT,
 		     info.ac_line_status, info.battery_status,
 		     info.battery_flag, info.battery_life,
 		     info.time, units);
 
-	return ret;
+	return 0;
 }
+
+static int proc_apm_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, proc_apm_show, NULL);
+}
+
+static const struct file_operations apm_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= proc_apm_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
 #endif
 
 static int kapmd(void *arg)
@@ -593,7 +606,7 @@ static int __init apm_init(void)
 	wake_up_process(kapmd_tsk);
 
 #ifdef CONFIG_PROC_FS
-	create_proc_info_entry("apm", 0, NULL, apm_get_info);
+	proc_create("apm", 0, NULL, &apm_proc_fops);
 #endif
 
 	ret = misc_register(&apm_device);
diff --git a/trunk/drivers/char/cs5535_gpio.c b/trunk/drivers/char/cs5535_gpio.c
index c2d23cae9515..c0a4a0bb509e 100644
--- a/trunk/drivers/char/cs5535_gpio.c
+++ b/trunk/drivers/char/cs5535_gpio.c
@@ -215,7 +215,7 @@ static int __init cs5535_gpio_init(void)
 	else
 		mask = 0x0b003c66;
 
-	if (request_region(gpio_base, CS5535_GPIO_SIZE, NAME) == 0) {
+	if (!request_region(gpio_base, CS5535_GPIO_SIZE, NAME)) {
 		printk(KERN_ERR NAME ": can't allocate I/O for GPIO\n");
 		return -ENODEV;
 	}
diff --git a/trunk/drivers/char/drm/r128_cce.c b/trunk/drivers/char/drm/r128_cce.c
index f36adbd3aaf5..c31afbde62e7 100644
--- a/trunk/drivers/char/drm/r128_cce.c
+++ b/trunk/drivers/char/drm/r128_cce.c
@@ -817,7 +817,7 @@ static struct drm_buf *r128_freelist_get(struct drm_device * dev)
 	for (i = 0; i < dma->buf_count; i++) {
 		buf = dma->buflist[i];
 		buf_priv = buf->dev_private;
-		if (buf->file_priv == 0)
+		if (!buf->file_priv)
 			return buf;
 	}
 
diff --git a/trunk/drivers/char/i8k.c b/trunk/drivers/char/i8k.c
index 8609b8236c67..f49037b744f9 100644
--- a/trunk/drivers/char/i8k.c
+++ b/trunk/drivers/char/i8k.c
@@ -82,6 +82,7 @@ static int i8k_ioctl(struct inode *, struct file *, unsigned int,
 		     unsigned long);
 
 static const struct file_operations i8k_fops = {
+	.owner		= THIS_MODULE,
 	.open		= i8k_open_fs,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -554,13 +555,10 @@ static int __init i8k_init(void)
 		return -ENODEV;
 
 	/* Register the proc entry */
-	proc_i8k = create_proc_entry("i8k", 0, NULL);
+	proc_i8k = proc_create("i8k", 0, NULL, &i8k_fops);
 	if (!proc_i8k)
 		return -ENOENT;
 
-	proc_i8k->proc_fops = &i8k_fops;
-	proc_i8k->owner = THIS_MODULE;
-
 	printk(KERN_INFO
 	       "Dell laptop SMM driver v%s Massimo Dal Zotto (dz@debian.org)\n",
 	       I8K_VERSION);
diff --git a/trunk/drivers/char/ip2/ip2main.c b/trunk/drivers/char/ip2/ip2main.c
index b1d6cad84282..0a61856c631f 100644
--- a/trunk/drivers/char/ip2/ip2main.c
+++ b/trunk/drivers/char/ip2/ip2main.c
@@ -133,8 +133,9 @@
  *****************/
 
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 
-static int ip2_read_procmem(char *, char **, off_t, int);
+static const struct file_operations ip2mem_proc_fops;
 static int ip2_read_proc(char *, char **, off_t, int, int *, void * );
 
 /********************/
@@ -423,7 +424,7 @@ cleanup_module(void)
 	}
 	put_tty_driver(ip2_tty_driver);
 	unregister_chrdev(IP2_IPL_MAJOR, pcIpl);
-	remove_proc_entry("ip2mem", &proc_root);
+	remove_proc_entry("ip2mem", NULL);
 
 	// free memory
 	for (i = 0; i < IP2_MAX_BOARDS; i++) {
@@ -695,7 +696,7 @@ ip2_loadmain(int *iop, int *irqp, unsigned char *firmware, int firmsize)
 		}
 	}
 	/* Register the read_procmem thing */
-	if (!create_proc_info_entry("ip2mem",0,&proc_root,ip2_read_procmem)) {
+	if (!proc_create("ip2mem",0,NULL,&ip2mem_proc_fops)) {
 		printk(KERN_ERR "IP2: failed to register read_procmem\n");
 	} else {
 
@@ -2967,65 +2968,61 @@ ip2_ipl_open( struct inode *pInode, struct file *pFile )
 	}
 	return 0;
 }
-/******************************************************************************/
-/* Function:   ip2_read_procmem                                               */
-/* Parameters:                                                                */
-/*                                                                            */
-/* Returns: Length of output                                                  */
-/*                                                                            */
-/* Description:                                                               */
-/*   Supplies some driver operating parameters                                */
-/*	Not real useful unless your debugging the fifo							  */
-/*                                                                            */
-/******************************************************************************/
-
-#define LIMIT  (PAGE_SIZE - 120)
 
 static int
-ip2_read_procmem(char *buf, char **start, off_t offset, int len)
+proc_ip2mem_show(struct seq_file *m, void *v)
 {
 	i2eBordStrPtr  pB;
 	i2ChanStrPtr  pCh;
 	PTTY tty;
 	int i;
 
-	len = 0;
-
 #define FMTLINE	"%3d: 0x%08x 0x%08x 0%011o 0%011o\n"
 #define FMTLIN2	"     0x%04x 0x%04x tx flow 0x%x\n"
 #define FMTLIN3	"     0x%04x 0x%04x rc flow\n"
 
-	len += sprintf(buf+len,"\n");
+	seq_printf(m,"\n");
 
 	for( i = 0; i < IP2_MAX_BOARDS; ++i ) {
 		pB = i2BoardPtrTable[i];
 		if ( pB ) {
-			len += sprintf(buf+len,"board %d:\n",i);
-			len += sprintf(buf+len,"\tFifo rem: %d mty: %x outM %x\n",
+			seq_printf(m,"board %d:\n",i);
+			seq_printf(m,"\tFifo rem: %d mty: %x outM %x\n",
 				pB->i2eFifoRemains,pB->i2eWaitingForEmptyFifo,pB->i2eOutMailWaiting);
 		}
 	}
 
-	len += sprintf(buf+len,"#: tty flags, port flags,     cflags,     iflags\n");
+	seq_printf(m,"#: tty flags, port flags,     cflags,     iflags\n");
 	for (i=0; i < IP2_MAX_PORTS; i++) {
-		if (len > LIMIT)
-			break;
 		pCh = DevTable[i];
 		if (pCh) {
 			tty = pCh->pTTY;
 			if (tty && tty->count) {
-				len += sprintf(buf+len,FMTLINE,i,(int)tty->flags,pCh->flags,
+				seq_printf(m,FMTLINE,i,(int)tty->flags,pCh->flags,
 									tty->termios->c_cflag,tty->termios->c_iflag);
 
-				len += sprintf(buf+len,FMTLIN2,
+				seq_printf(m,FMTLIN2,
 						pCh->outfl.asof,pCh->outfl.room,pCh->channelNeeds);
-				len += sprintf(buf+len,FMTLIN3,pCh->infl.asof,pCh->infl.room);
+				seq_printf(m,FMTLIN3,pCh->infl.asof,pCh->infl.room);
 			}
 		}
 	}
-	return len;
+	return 0;
+}
+
+static int proc_ip2mem_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, proc_ip2mem_show, NULL);
 }
 
+static const struct file_operations ip2mem_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= proc_ip2mem_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 /*
  * This is the handler for /proc/tty/driver/ip2
  *
diff --git a/trunk/drivers/char/ipmi/Makefile b/trunk/drivers/char/ipmi/Makefile
index 553f0a408eda..eb8a1a8c188e 100644
--- a/trunk/drivers/char/ipmi/Makefile
+++ b/trunk/drivers/char/ipmi/Makefile
@@ -9,7 +9,3 @@ obj-$(CONFIG_IPMI_DEVICE_INTERFACE) += ipmi_devintf.o
 obj-$(CONFIG_IPMI_SI) += ipmi_si.o
 obj-$(CONFIG_IPMI_WATCHDOG) += ipmi_watchdog.o
 obj-$(CONFIG_IPMI_POWEROFF) += ipmi_poweroff.o
-
-ipmi_si.o:	$(ipmi_si-objs)
-	$(LD) -r -o $@ $(ipmi_si-objs)
-
diff --git a/trunk/drivers/char/ipmi/ipmi_bt_sm.c b/trunk/drivers/char/ipmi/ipmi_bt_sm.c
index e736119b6497..7b98c067190a 100644
--- a/trunk/drivers/char/ipmi/ipmi_bt_sm.c
+++ b/trunk/drivers/char/ipmi/ipmi_bt_sm.c
@@ -37,26 +37,32 @@
 #define BT_DEBUG_ENABLE	1	/* Generic messages */
 #define BT_DEBUG_MSG	2	/* Prints all request/response buffers */
 #define BT_DEBUG_STATES	4	/* Verbose look at state changes */
-/* BT_DEBUG_OFF must be zero to correspond to the default uninitialized
-   value */
+/*
+ * BT_DEBUG_OFF must be zero to correspond to the default uninitialized
+ * value
+ */
 
 static int bt_debug; /* 0 == BT_DEBUG_OFF */
 
 module_param(bt_debug, int, 0644);
 MODULE_PARM_DESC(bt_debug, "debug bitmask, 1=enable, 2=messages, 4=states");
 
-/* Typical "Get BT Capabilities" values are 2-3 retries, 5-10 seconds,
-   and 64 byte buffers.  However, one HP implementation wants 255 bytes of
-   buffer (with a documented message of 160 bytes) so go for the max.
-   Since the Open IPMI architecture is single-message oriented at this
-   stage, the queue depth of BT is of no concern. */
+/*
+ * Typical "Get BT Capabilities" values are 2-3 retries, 5-10 seconds,
+ * and 64 byte buffers.  However, one HP implementation wants 255 bytes of
+ * buffer (with a documented message of 160 bytes) so go for the max.
+ * Since the Open IPMI architecture is single-message oriented at this
+ * stage, the queue depth of BT is of no concern.
+ */
 
 #define BT_NORMAL_TIMEOUT	5	/* seconds */
 #define BT_NORMAL_RETRY_LIMIT	2
 #define BT_RESET_DELAY		6	/* seconds after warm reset */
 
-/* States are written in chronological order and usually cover
-   multiple rows of the state table discussion in the IPMI spec. */
+/*
+ * States are written in chronological order and usually cover
+ * multiple rows of the state table discussion in the IPMI spec.
+ */
 
 enum bt_states {
 	BT_STATE_IDLE = 0,	/* Order is critical in this list */
@@ -76,10 +82,12 @@ enum bt_states {
 	BT_STATE_LONG_BUSY	/* BT doesn't get hosed :-) */
 };
 
-/* Macros seen at the end of state "case" blocks.  They help with legibility
-   and debugging. */
+/*
+ * Macros seen at the end of state "case" blocks.  They help with legibility
+ * and debugging.
+ */
 
-#define BT_STATE_CHANGE(X,Y) { bt->state = X; return Y; }
+#define BT_STATE_CHANGE(X, Y) { bt->state = X; return Y; }
 
 #define BT_SI_SM_RETURN(Y)   { last_printed = BT_STATE_PRINTME; return Y; }
 
@@ -110,11 +118,13 @@ struct si_sm_data {
 #define BT_H_BUSY	0x40
 #define BT_B_BUSY	0x80
 
-/* Some bits are toggled on each write: write once to set it, once
-   more to clear it; writing a zero does nothing.  To absolutely
-   clear it, check its state and write if set.  This avoids the "get
-   current then use as mask" scheme to modify one bit.  Note that the
-   variable "bt" is hardcoded into these macros. */
+/*
+ * Some bits are toggled on each write: write once to set it, once
+ * more to clear it; writing a zero does nothing.  To absolutely
+ * clear it, check its state and write if set.  This avoids the "get
+ * current then use as mask" scheme to modify one bit.  Note that the
+ * variable "bt" is hardcoded into these macros.
+ */
 
 #define BT_STATUS	bt->io->inputb(bt->io, 0)
 #define BT_CONTROL(x)	bt->io->outputb(bt->io, 0, x)
@@ -125,8 +135,10 @@ struct si_sm_data {
 #define BT_INTMASK_R	bt->io->inputb(bt->io, 2)
 #define BT_INTMASK_W(x)	bt->io->outputb(bt->io, 2, x)
 
-/* Convenience routines for debugging.  These are not multi-open safe!
-   Note the macros have hardcoded variables in them. */
+/*
+ * Convenience routines for debugging.  These are not multi-open safe!
+ * Note the macros have hardcoded variables in them.
+ */
 
 static char *state2txt(unsigned char state)
 {
@@ -182,7 +194,8 @@ static char *status2txt(unsigned char status)
 static unsigned int bt_init_data(struct si_sm_data *bt, struct si_sm_io *io)
 {
 	memset(bt, 0, sizeof(struct si_sm_data));
-	if (bt->io != io) {		/* external: one-time only things */
+	if (bt->io != io) {
+		/* external: one-time only things */
 		bt->io = io;
 		bt->seq = 0;
 	}
@@ -229,7 +242,7 @@ static int bt_start_transaction(struct si_sm_data *bt,
 		printk(KERN_WARNING "BT: +++++++++++++++++ New command\n");
 		printk(KERN_WARNING "BT: NetFn/LUN CMD [%d data]:", size - 2);
 		for (i = 0; i < size; i ++)
-			printk (" %02x", data[i]);
+			printk(" %02x", data[i]);
 		printk("\n");
 	}
 	bt->write_data[0] = size + 1;	/* all data plus seq byte */
@@ -246,8 +259,10 @@ static int bt_start_transaction(struct si_sm_data *bt,
 	return 0;
 }
 
-/* After the upper state machine has been told SI_SM_TRANSACTION_COMPLETE
-   it calls this.  Strip out the length and seq bytes. */
+/*
+ * After the upper state machine has been told SI_SM_TRANSACTION_COMPLETE
+ * it calls this.  Strip out the length and seq bytes.
+ */
 
 static int bt_get_result(struct si_sm_data *bt,
 			 unsigned char *data,
@@ -269,10 +284,10 @@ static int bt_get_result(struct si_sm_data *bt,
 		memcpy(data + 2, bt->read_data + 4, msg_len - 2);
 
 	if (bt_debug & BT_DEBUG_MSG) {
-		printk (KERN_WARNING "BT: result %d bytes:", msg_len);
+		printk(KERN_WARNING "BT: result %d bytes:", msg_len);
 		for (i = 0; i < msg_len; i++)
 			printk(" %02x", data[i]);
-		printk ("\n");
+		printk("\n");
 	}
 	return msg_len;
 }
@@ -292,8 +307,10 @@ static void reset_flags(struct si_sm_data *bt)
 	BT_INTMASK_W(BT_BMC_HWRST);
 }
 
-/* Get rid of an unwanted/stale response.  This should only be needed for
-   BMCs that support multiple outstanding requests. */
+/*
+ * Get rid of an unwanted/stale response.  This should only be needed for
+ * BMCs that support multiple outstanding requests.
+ */
 
 static void drain_BMC2HOST(struct si_sm_data *bt)
 {
@@ -326,8 +343,8 @@ static inline void write_all_bytes(struct si_sm_data *bt)
 		printk(KERN_WARNING "BT: write %d bytes seq=0x%02X",
 			bt->write_count, bt->seq);
 		for (i = 0; i < bt->write_count; i++)
-			printk (" %02x", bt->write_data[i]);
-		printk ("\n");
+			printk(" %02x", bt->write_data[i]);
+		printk("\n");
 	}
 	for (i = 0; i < bt->write_count; i++)
 		HOST2BMC(bt->write_data[i]);
@@ -337,8 +354,10 @@ static inline int read_all_bytes(struct si_sm_data *bt)
 {
 	unsigned char i;
 
-	/* length is "framing info", minimum = 4: NetFn, Seq, Cmd, cCode.
-	   Keep layout of first four bytes aligned with write_data[] */
+	/*
+	 * length is "framing info", minimum = 4: NetFn, Seq, Cmd, cCode.
+	 * Keep layout of first four bytes aligned with write_data[]
+	 */
 
 	bt->read_data[0] = BMC2HOST;
 	bt->read_count = bt->read_data[0];
@@ -362,8 +381,8 @@ static inline int read_all_bytes(struct si_sm_data *bt)
 		if (max > 16)
 			max = 16;
 		for (i = 0; i < max; i++)
-			printk (" %02x", bt->read_data[i]);
-		printk ("%s\n", bt->read_count == max ? "" : " ...");
+			printk(KERN_CONT " %02x", bt->read_data[i]);
+		printk(KERN_CONT "%s\n", bt->read_count == max ? "" : " ...");
 	}
 
 	/* per the spec, the (NetFn[1], Seq[2], Cmd[3]) tuples must match */
@@ -402,8 +421,10 @@ static enum si_sm_result error_recovery(struct si_sm_data *bt,
 	printk(KERN_WARNING "IPMI BT: %s in %s %s ", 	/* open-ended line */
 		reason, STATE2TXT, STATUS2TXT);
 
-	/* Per the IPMI spec, retries are based on the sequence number
-	   known only to this module, so manage a restart here. */
+	/*
+	 * Per the IPMI spec, retries are based on the sequence number
+	 * known only to this module, so manage a restart here.
+	 */
 	(bt->error_retries)++;
 	if (bt->error_retries < bt->BT_CAP_retries) {
 		printk("%d retries left\n",
@@ -412,8 +433,8 @@ static enum si_sm_result error_recovery(struct si_sm_data *bt,
 		return SI_SM_CALL_WITHOUT_DELAY;
 	}
 
-	printk("failed %d retries, sending error response\n",
-		bt->BT_CAP_retries);
+	printk(KERN_WARNING "failed %d retries, sending error response\n",
+	       bt->BT_CAP_retries);
 	if (!bt->nonzero_status)
 		printk(KERN_ERR "IPMI BT: stuck, try power cycle\n");
 
@@ -424,8 +445,10 @@ static enum si_sm_result error_recovery(struct si_sm_data *bt,
 		return SI_SM_CALL_WITHOUT_DELAY;
 	}
 
-	/* Concoct a useful error message, set up the next state, and
-	   be done with this sequence. */
+	/*
+	 * Concoct a useful error message, set up the next state, and
+	 * be done with this sequence.
+	 */
 
 	bt->state = BT_STATE_IDLE;
 	switch (cCode) {
@@ -461,10 +484,12 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time)
 		last_printed = bt->state;
 	}
 
-	/* Commands that time out may still (eventually) provide a response.
-	   This stale response will get in the way of a new response so remove
-	   it if possible (hopefully during IDLE).  Even if it comes up later
-	   it will be rejected by its (now-forgotten) seq number. */
+	/*
+	 * Commands that time out may still (eventually) provide a response.
+	 * This stale response will get in the way of a new response so remove
+	 * it if possible (hopefully during IDLE).  Even if it comes up later
+	 * it will be rejected by its (now-forgotten) seq number.
+	 */
 
 	if ((bt->state < BT_STATE_WRITE_BYTES) && (status & BT_B2H_ATN)) {
 		drain_BMC2HOST(bt);
@@ -472,7 +497,8 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time)
 	}
 
 	if ((bt->state != BT_STATE_IDLE) &&
-	    (bt->state <  BT_STATE_PRINTME)) {		/* check timeout */
+	    (bt->state <  BT_STATE_PRINTME)) {
+		/* check timeout */
 		bt->timeout -= time;
 		if ((bt->timeout < 0) && (bt->state < BT_STATE_RESET1))
 			return error_recovery(bt,
@@ -482,8 +508,10 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time)
 
 	switch (bt->state) {
 
-	/* Idle state first checks for asynchronous messages from another
-	   channel, then does some opportunistic housekeeping. */
+	/*
+	 * Idle state first checks for asynchronous messages from another
+	 * channel, then does some opportunistic housekeeping.
+	 */
 
 	case BT_STATE_IDLE:
 		if (status & BT_SMS_ATN) {
@@ -531,16 +559,19 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time)
 			BT_SI_SM_RETURN(SI_SM_CALL_WITH_DELAY);
 		BT_CONTROL(BT_H_BUSY);		/* set */
 
-		/* Uncached, ordered writes should just proceeed serially but
-		   some BMCs don't clear B2H_ATN with one hit.  Fast-path a
-		   workaround without too much penalty to the general case. */
+		/*
+		 * Uncached, ordered writes should just proceeed serially but
+		 * some BMCs don't clear B2H_ATN with one hit.  Fast-path a
+		 * workaround without too much penalty to the general case.
+		 */
 
 		BT_CONTROL(BT_B2H_ATN);		/* clear it to ACK the BMC */
 		BT_STATE_CHANGE(BT_STATE_CLEAR_B2H,
 				SI_SM_CALL_WITHOUT_DELAY);
 
 	case BT_STATE_CLEAR_B2H:
-		if (status & BT_B2H_ATN) {	/* keep hitting it */
+		if (status & BT_B2H_ATN) {
+			/* keep hitting it */
 			BT_CONTROL(BT_B2H_ATN);
 			BT_SI_SM_RETURN(SI_SM_CALL_WITH_DELAY);
 		}
@@ -548,7 +579,8 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time)
 				SI_SM_CALL_WITHOUT_DELAY);
 
 	case BT_STATE_READ_BYTES:
-		if (!(status & BT_H_BUSY))	/* check in case of retry */
+		if (!(status & BT_H_BUSY))
+			/* check in case of retry */
 			BT_CONTROL(BT_H_BUSY);
 		BT_CONTROL(BT_CLR_RD_PTR);	/* start of BMC2HOST buffer */
 		i = read_all_bytes(bt);		/* true == packet seq match */
@@ -599,8 +631,10 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time)
 		BT_STATE_CHANGE(BT_STATE_XACTION_START,
 				SI_SM_CALL_WITH_DELAY);
 
-	/* Get BT Capabilities, using timing of upper level state machine.
-	   Set outreqs to prevent infinite loop on timeout. */
+	/*
+	 * Get BT Capabilities, using timing of upper level state machine.
+	 * Set outreqs to prevent infinite loop on timeout.
+	 */
 	case BT_STATE_CAPABILITIES_BEGIN:
 		bt->BT_CAP_outreqs = 1;
 		{
@@ -638,10 +672,12 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time)
 
 static int bt_detect(struct si_sm_data *bt)
 {
-	/* It's impossible for the BT status and interrupt registers to be
-	   all 1's, (assuming a properly functioning, self-initialized BMC)
-	   but that's what you get from reading a bogus address, so we
-	   test that first.  The calling routine uses negative logic. */
+	/*
+	 * It's impossible for the BT status and interrupt registers to be
+	 * all 1's, (assuming a properly functioning, self-initialized BMC)
+	 * but that's what you get from reading a bogus address, so we
+	 * test that first.  The calling routine uses negative logic.
+	 */
 
 	if ((BT_STATUS == 0xFF) && (BT_INTMASK_R == 0xFF))
 		return 1;
@@ -658,8 +694,7 @@ static int bt_size(void)
 	return sizeof(struct si_sm_data);
 }
 
-struct si_sm_handlers bt_smi_handlers =
-{
+struct si_sm_handlers bt_smi_handlers = {
 	.init_data		= bt_init_data,
 	.start_transaction	= bt_start_transaction,
 	.get_result		= bt_get_result,
diff --git a/trunk/drivers/char/ipmi/ipmi_kcs_sm.c b/trunk/drivers/char/ipmi/ipmi_kcs_sm.c
index c1b8228cb7b6..80704875794c 100644
--- a/trunk/drivers/char/ipmi/ipmi_kcs_sm.c
+++ b/trunk/drivers/char/ipmi/ipmi_kcs_sm.c
@@ -60,37 +60,58 @@ MODULE_PARM_DESC(kcs_debug, "debug bitmask, 1=enable, 2=messages, 4=states");
 
 /* The states the KCS driver may be in. */
 enum kcs_states {
-	KCS_IDLE,		/* The KCS interface is currently
-                                   doing nothing. */
-	KCS_START_OP,		/* We are starting an operation.  The
-				   data is in the output buffer, but
-				   nothing has been done to the
-				   interface yet.  This was added to
-				   the state machine in the spec to
-				   wait for the initial IBF. */
-	KCS_WAIT_WRITE_START,	/* We have written a write cmd to the
-				   interface. */
-	KCS_WAIT_WRITE,		/* We are writing bytes to the
-                                   interface. */
-	KCS_WAIT_WRITE_END,	/* We have written the write end cmd
-                                   to the interface, and still need to
-                                   write the last byte. */
-	KCS_WAIT_READ,		/* We are waiting to read data from
-				   the interface. */
-	KCS_ERROR0,		/* State to transition to the error
-				   handler, this was added to the
-				   state machine in the spec to be
-				   sure IBF was there. */
-	KCS_ERROR1,		/* First stage error handler, wait for
-                                   the interface to respond. */
-	KCS_ERROR2,		/* The abort cmd has been written,
-				   wait for the interface to
-				   respond. */
-	KCS_ERROR3,		/* We wrote some data to the
-				   interface, wait for it to switch to
-				   read mode. */
-	KCS_HOSED		/* The hardware failed to follow the
-				   state machine. */
+	/* The KCS interface is currently doing nothing. */
+	KCS_IDLE,
+
+	/*
+	 * We are starting an operation.  The data is in the output
+	 * buffer, but nothing has been done to the interface yet.  This
+	 * was added to the state machine in the spec to wait for the
+	 * initial IBF.
+	 */
+	KCS_START_OP,
+
+	/* We have written a write cmd to the interface. */
+	KCS_WAIT_WRITE_START,
+
+	/* We are writing bytes to the interface. */
+	KCS_WAIT_WRITE,
+
+	/*
+	 * We have written the write end cmd to the interface, and
+	 * still need to write the last byte.
+	 */
+	KCS_WAIT_WRITE_END,
+
+	/* We are waiting to read data from the interface. */
+	KCS_WAIT_READ,
+
+	/*
+	 * State to transition to the error handler, this was added to
+	 * the state machine in the spec to be sure IBF was there.
+	 */
+	KCS_ERROR0,
+
+	/*
+	 * First stage error handler, wait for the interface to
+	 * respond.
+	 */
+	KCS_ERROR1,
+
+	/*
+	 * The abort cmd has been written, wait for the interface to
+	 * respond.
+	 */
+	KCS_ERROR2,
+
+	/*
+	 * We wrote some data to the interface, wait for it to switch
+	 * to read mode.
+	 */
+	KCS_ERROR3,
+
+	/* The hardware failed to follow the state machine. */
+	KCS_HOSED
 };
 
 #define MAX_KCS_READ_SIZE IPMI_MAX_MSG_LENGTH
@@ -102,8 +123,7 @@ enum kcs_states {
 #define MAX_ERROR_RETRIES 10
 #define ERROR0_OBF_WAIT_JIFFIES (2*HZ)
 
-struct si_sm_data
-{
+struct si_sm_data {
 	enum kcs_states  state;
 	struct si_sm_io *io;
 	unsigned char    write_data[MAX_KCS_WRITE_SIZE];
@@ -187,7 +207,8 @@ static inline void start_error_recovery(struct si_sm_data *kcs, char *reason)
 	(kcs->error_retries)++;
 	if (kcs->error_retries > MAX_ERROR_RETRIES) {
 		if (kcs_debug & KCS_DEBUG_ENABLE)
-			printk(KERN_DEBUG "ipmi_kcs_sm: kcs hosed: %s\n", reason);
+			printk(KERN_DEBUG "ipmi_kcs_sm: kcs hosed: %s\n",
+			       reason);
 		kcs->state = KCS_HOSED;
 	} else {
 		kcs->error0_timeout = jiffies + ERROR0_OBF_WAIT_JIFFIES;
@@ -271,10 +292,9 @@ static int start_kcs_transaction(struct si_sm_data *kcs, unsigned char *data,
 
 	if (kcs_debug & KCS_DEBUG_MSG) {
 		printk(KERN_DEBUG "start_kcs_transaction -");
-		for (i = 0; i < size; i ++) {
+		for (i = 0; i < size; i++)
 			printk(" %02x", (unsigned char) (data [i]));
-		}
-		printk ("\n");
+		printk("\n");
 	}
 	kcs->error_retries = 0;
 	memcpy(kcs->write_data, data, size);
@@ -305,9 +325,11 @@ static int get_kcs_result(struct si_sm_data *kcs, unsigned char *data,
 		kcs->read_pos = 3;
 	}
 	if (kcs->truncated) {
-		/* Report a truncated error.  We might overwrite
-		   another error, but that's too bad, the user needs
-		   to know it was truncated. */
+		/*
+		 * Report a truncated error.  We might overwrite
+		 * another error, but that's too bad, the user needs
+		 * to know it was truncated.
+		 */
 		data[2] = IPMI_ERR_MSG_TRUNCATED;
 		kcs->truncated = 0;
 	}
@@ -315,9 +337,11 @@ static int get_kcs_result(struct si_sm_data *kcs, unsigned char *data,
 	return kcs->read_pos;
 }
 
-/* This implements the state machine defined in the IPMI manual, see
-   that for details on how this works.  Divide that flowchart into
-   sections delimited by "Wait for IBF" and this will become clear. */
+/*
+ * This implements the state machine defined in the IPMI manual, see
+ * that for details on how this works.  Divide that flowchart into
+ * sections delimited by "Wait for IBF" and this will become clear.
+ */
 static enum si_sm_result kcs_event(struct si_sm_data *kcs, long time)
 {
 	unsigned char status;
@@ -388,11 +412,12 @@ static enum si_sm_result kcs_event(struct si_sm_data *kcs, long time)
 			write_next_byte(kcs);
 		}
 		break;
-		
+
 	case KCS_WAIT_WRITE_END:
 		if (state != KCS_WRITE_STATE) {
 			start_error_recovery(kcs,
-					     "Not in write state for write end");
+					     "Not in write state"
+					     " for write end");
 			break;
 		}
 		clear_obf(kcs, status);
@@ -413,13 +438,15 @@ static enum si_sm_result kcs_event(struct si_sm_data *kcs, long time)
 				return SI_SM_CALL_WITH_DELAY;
 			read_next_byte(kcs);
 		} else {
-			/* We don't implement this exactly like the state
-			   machine in the spec.  Some broken hardware
-			   does not write the final dummy byte to the
-			   read register.  Thus obf will never go high
-			   here.  We just go straight to idle, and we
-			   handle clearing out obf in idle state if it
-			   happens to come in. */
+			/*
+			 * We don't implement this exactly like the state
+			 * machine in the spec.  Some broken hardware
+			 * does not write the final dummy byte to the
+			 * read register.  Thus obf will never go high
+			 * here.  We just go straight to idle, and we
+			 * handle clearing out obf in idle state if it
+			 * happens to come in.
+			 */
 			clear_obf(kcs, status);
 			kcs->orig_write_count = 0;
 			kcs->state = KCS_IDLE;
@@ -430,7 +457,8 @@ static enum si_sm_result kcs_event(struct si_sm_data *kcs, long time)
 	case KCS_ERROR0:
 		clear_obf(kcs, status);
 		status = read_status(kcs);
-		if  (GET_STATUS_OBF(status)) /* controller isn't responding */
+		if (GET_STATUS_OBF(status))
+			/* controller isn't responding */
 			if (time_before(jiffies, kcs->error0_timeout))
 				return SI_SM_CALL_WITH_TICK_DELAY;
 		write_cmd(kcs, KCS_GET_STATUS_ABORT);
@@ -442,7 +470,7 @@ static enum si_sm_result kcs_event(struct si_sm_data *kcs, long time)
 		write_data(kcs, 0);
 		kcs->state = KCS_ERROR2;
 		break;
-		
+
 	case KCS_ERROR2:
 		if (state != KCS_READ_STATE) {
 			start_error_recovery(kcs,
@@ -456,7 +484,7 @@ static enum si_sm_result kcs_event(struct si_sm_data *kcs, long time)
 		write_data(kcs, KCS_READ_BYTE);
 		kcs->state = KCS_ERROR3;
 		break;
-		
+
 	case KCS_ERROR3:
 		if (state != KCS_IDLE_STATE) {
 			start_error_recovery(kcs,
@@ -475,7 +503,7 @@ static enum si_sm_result kcs_event(struct si_sm_data *kcs, long time)
 			return SI_SM_TRANSACTION_COMPLETE;
 		}
 		break;
-			
+
 	case KCS_HOSED:
 		break;
 	}
@@ -495,10 +523,12 @@ static int kcs_size(void)
 
 static int kcs_detect(struct si_sm_data *kcs)
 {
-	/* It's impossible for the KCS status register to be all 1's,
-	   (assuming a properly functioning, self-initialized BMC)
-	   but that's what you get from reading a bogus address, so we
-	   test that first. */
+	/*
+	 * It's impossible for the KCS status register to be all 1's,
+	 * (assuming a properly functioning, self-initialized BMC)
+	 * but that's what you get from reading a bogus address, so we
+	 * test that first.
+	 */
 	if (read_status(kcs) == 0xff)
 		return 1;
 
@@ -509,8 +539,7 @@ static void kcs_cleanup(struct si_sm_data *kcs)
 {
 }
 
-struct si_sm_handlers kcs_smi_handlers =
-{
+struct si_sm_handlers kcs_smi_handlers = {
 	.init_data         = init_kcs_data,
 	.start_transaction = start_kcs_transaction,
 	.get_result        = get_kcs_result,
diff --git a/trunk/drivers/char/ipmi/ipmi_msghandler.c b/trunk/drivers/char/ipmi/ipmi_msghandler.c
index 32b2b22996dc..8a59aaa21be5 100644
--- a/trunk/drivers/char/ipmi/ipmi_msghandler.c
+++ b/trunk/drivers/char/ipmi/ipmi_msghandler.c
@@ -47,7 +47,7 @@
 
 #define PFX "IPMI message handler: "
 
-#define IPMI_DRIVER_VERSION "39.1"
+#define IPMI_DRIVER_VERSION "39.2"
 
 static struct ipmi_recv_msg *ipmi_alloc_recv_msg(void);
 static int ipmi_init_msghandler(void);
@@ -63,16 +63,16 @@ static struct proc_dir_entry *proc_ipmi_root;
 
 #define MAX_EVENTS_IN_QUEUE	25
 
-/* Don't let a message sit in a queue forever, always time it with at lest
-   the max message timer.  This is in milliseconds. */
+/*
+ * Don't let a message sit in a queue forever, always time it with at lest
+ * the max message timer.  This is in milliseconds.
+ */
 #define MAX_MSG_TIMEOUT		60000
 
-
 /*
  * The main "user" data structure.
  */
-struct ipmi_user
-{
+struct ipmi_user {
 	struct list_head link;
 
 	/* Set to "0" when the user is destroyed. */
@@ -91,8 +91,7 @@ struct ipmi_user
 	int gets_events;
 };
 
-struct cmd_rcvr
-{
+struct cmd_rcvr {
 	struct list_head link;
 
 	ipmi_user_t   user;
@@ -106,12 +105,12 @@ struct cmd_rcvr
 	 * or change any data until the RCU period completes.  So we
 	 * use this next variable during mass deletion so we can have
 	 * a list and don't have to wait and restart the search on
-	 * every individual deletion of a command. */
+	 * every individual deletion of a command.
+	 */
 	struct cmd_rcvr *next;
 };
 
-struct seq_table
-{
+struct seq_table {
 	unsigned int         inuse : 1;
 	unsigned int         broadcast : 1;
 
@@ -119,53 +118,60 @@ struct seq_table
 	unsigned long        orig_timeout;
 	unsigned int         retries_left;
 
-	/* To verify on an incoming send message response that this is
-           the message that the response is for, we keep a sequence id
-           and increment it every time we send a message. */
+	/*
+	 * To verify on an incoming send message response that this is
+	 * the message that the response is for, we keep a sequence id
+	 * and increment it every time we send a message.
+	 */
 	long                 seqid;
 
-	/* This is held so we can properly respond to the message on a
-           timeout, and it is used to hold the temporary data for
-           retransmission, too. */
+	/*
+	 * This is held so we can properly respond to the message on a
+	 * timeout, and it is used to hold the temporary data for
+	 * retransmission, too.
+	 */
 	struct ipmi_recv_msg *recv_msg;
 };
 
-/* Store the information in a msgid (long) to allow us to find a
-   sequence table entry from the msgid. */
+/*
+ * Store the information in a msgid (long) to allow us to find a
+ * sequence table entry from the msgid.
+ */
 #define STORE_SEQ_IN_MSGID(seq, seqid) (((seq&0xff)<<26) | (seqid&0x3ffffff))
 
 #define GET_SEQ_FROM_MSGID(msgid, seq, seqid) \
 	do {								\
 		seq = ((msgid >> 26) & 0x3f);				\
 		seqid = (msgid & 0x3fffff);				\
-        } while (0)
+	} while (0)
 
 #define NEXT_SEQID(seqid) (((seqid) + 1) & 0x3fffff)
 
-struct ipmi_channel
-{
+struct ipmi_channel {
 	unsigned char medium;
 	unsigned char protocol;
 
-	/* My slave address.  This is initialized to IPMI_BMC_SLAVE_ADDR,
-	   but may be changed by the user. */
+	/*
+	 * My slave address.  This is initialized to IPMI_BMC_SLAVE_ADDR,
+	 * but may be changed by the user.
+	 */
 	unsigned char address;
 
-	/* My LUN.  This should generally stay the SMS LUN, but just in
-	   case... */
+	/*
+	 * My LUN.  This should generally stay the SMS LUN, but just in
+	 * case...
+	 */
 	unsigned char lun;
 };
 
 #ifdef CONFIG_PROC_FS
-struct ipmi_proc_entry
-{
+struct ipmi_proc_entry {
 	char                   *name;
 	struct ipmi_proc_entry *next;
 };
 #endif
 
-struct bmc_device
-{
+struct bmc_device {
 	struct platform_device *dev;
 	struct ipmi_device_id  id;
 	unsigned char          guid[16];
@@ -186,10 +192,108 @@ struct bmc_device
 	struct device_attribute aux_firmware_rev_attr;
 };
 
+/*
+ * Various statistics for IPMI, these index stats[] in the ipmi_smi
+ * structure.
+ */
+enum ipmi_stat_indexes {
+	/* Commands we got from the user that were invalid. */
+	IPMI_STAT_sent_invalid_commands = 0,
+
+	/* Commands we sent to the MC. */
+	IPMI_STAT_sent_local_commands,
+
+	/* Responses from the MC that were delivered to a user. */
+	IPMI_STAT_handled_local_responses,
+
+	/* Responses from the MC that were not delivered to a user. */
+	IPMI_STAT_unhandled_local_responses,
+
+	/* Commands we sent out to the IPMB bus. */
+	IPMI_STAT_sent_ipmb_commands,
+
+	/* Commands sent on the IPMB that had errors on the SEND CMD */
+	IPMI_STAT_sent_ipmb_command_errs,
+
+	/* Each retransmit increments this count. */
+	IPMI_STAT_retransmitted_ipmb_commands,
+
+	/*
+	 * When a message times out (runs out of retransmits) this is
+	 * incremented.
+	 */
+	IPMI_STAT_timed_out_ipmb_commands,
+
+	/*
+	 * This is like above, but for broadcasts.  Broadcasts are
+	 * *not* included in the above count (they are expected to
+	 * time out).
+	 */
+	IPMI_STAT_timed_out_ipmb_broadcasts,
+
+	/* Responses I have sent to the IPMB bus. */
+	IPMI_STAT_sent_ipmb_responses,
+
+	/* The response was delivered to the user. */
+	IPMI_STAT_handled_ipmb_responses,
+
+	/* The response had invalid data in it. */
+	IPMI_STAT_invalid_ipmb_responses,
+
+	/* The response didn't have anyone waiting for it. */
+	IPMI_STAT_unhandled_ipmb_responses,
+
+	/* Commands we sent out to the IPMB bus. */
+	IPMI_STAT_sent_lan_commands,
+
+	/* Commands sent on the IPMB that had errors on the SEND CMD */
+	IPMI_STAT_sent_lan_command_errs,
+
+	/* Each retransmit increments this count. */
+	IPMI_STAT_retransmitted_lan_commands,
+
+	/*
+	 * When a message times out (runs out of retransmits) this is
+	 * incremented.
+	 */
+	IPMI_STAT_timed_out_lan_commands,
+
+	/* Responses I have sent to the IPMB bus. */
+	IPMI_STAT_sent_lan_responses,
+
+	/* The response was delivered to the user. */
+	IPMI_STAT_handled_lan_responses,
+
+	/* The response had invalid data in it. */
+	IPMI_STAT_invalid_lan_responses,
+
+	/* The response didn't have anyone waiting for it. */
+	IPMI_STAT_unhandled_lan_responses,
+
+	/* The command was delivered to the user. */
+	IPMI_STAT_handled_commands,
+
+	/* The command had invalid data in it. */
+	IPMI_STAT_invalid_commands,
+
+	/* The command didn't have anyone waiting for it. */
+	IPMI_STAT_unhandled_commands,
+
+	/* Invalid data in an event. */
+	IPMI_STAT_invalid_events,
+
+	/* Events that were received with the proper format. */
+	IPMI_STAT_events,
+
+
+	/* This *must* remain last, add new values above this. */
+	IPMI_NUM_STATS
+};
+
+
 #define IPMI_IPMB_NUM_SEQ	64
 #define IPMI_MAX_CHANNELS       16
-struct ipmi_smi
-{
+struct ipmi_smi {
 	/* What interface number are we? */
 	int intf_num;
 
@@ -198,8 +302,10 @@ struct ipmi_smi
 	/* Used for a list of interfaces. */
 	struct list_head link;
 
-	/* The list of upper layers that are using me.  seq_lock
-	 * protects this. */
+	/*
+	 * The list of upper layers that are using me.  seq_lock
+	 * protects this.
+	 */
 	struct list_head users;
 
 	/* Information to supply to users. */
@@ -213,10 +319,12 @@ struct ipmi_smi
 	char *my_dev_name;
 	char *sysfs_name;
 
-	/* This is the lower-layer's sender routine.  Note that you
+	/*
+	 * This is the lower-layer's sender routine.  Note that you
 	 * must either be holding the ipmi_interfaces_mutex or be in
 	 * an umpreemptible region to use this.  You must fetch the
-	 * value into a local variable and make sure it is not NULL. */
+	 * value into a local variable and make sure it is not NULL.
+	 */
 	struct ipmi_smi_handlers *handlers;
 	void                     *send_info;
 
@@ -229,34 +337,45 @@ struct ipmi_smi
 	/* Driver-model device for the system interface. */
 	struct device          *si_dev;
 
-	/* A table of sequence numbers for this interface.  We use the
-           sequence numbers for IPMB messages that go out of the
-           interface to match them up with their responses.  A routine
-           is called periodically to time the items in this list. */
+	/*
+	 * A table of sequence numbers for this interface.  We use the
+	 * sequence numbers for IPMB messages that go out of the
+	 * interface to match them up with their responses.  A routine
+	 * is called periodically to time the items in this list.
+	 */
 	spinlock_t       seq_lock;
 	struct seq_table seq_table[IPMI_IPMB_NUM_SEQ];
 	int curr_seq;
 
-	/* Messages that were delayed for some reason (out of memory,
-           for instance), will go in here to be processed later in a
-           periodic timer interrupt. */
+	/*
+	 * Messages that were delayed for some reason (out of memory,
+	 * for instance), will go in here to be processed later in a
+	 * periodic timer interrupt.
+	 */
 	spinlock_t       waiting_msgs_lock;
 	struct list_head waiting_msgs;
 
-	/* The list of command receivers that are registered for commands
-	   on this interface. */
+	/*
+	 * The list of command receivers that are registered for commands
+	 * on this interface.
+	 */
 	struct mutex     cmd_rcvrs_mutex;
 	struct list_head cmd_rcvrs;
 
-	/* Events that were queues because no one was there to receive
-           them. */
+	/*
+	 * Events that were queues because no one was there to receive
+	 * them.
+	 */
 	spinlock_t       events_lock; /* For dealing with event stuff. */
 	struct list_head waiting_events;
 	unsigned int     waiting_events_count; /* How many events in queue? */
-	int              delivering_events;
+	char             delivering_events;
+	char             event_msg_printed;
 
-	/* The event receiver for my BMC, only really used at panic
-	   shutdown as a place to store this. */
+	/*
+	 * The event receiver for my BMC, only really used at panic
+	 * shutdown as a place to store this.
+	 */
 	unsigned char event_receiver;
 	unsigned char event_receiver_lun;
 	unsigned char local_sel_device;
@@ -268,14 +387,18 @@ struct ipmi_smi
 	int auto_maintenance_timeout;
 	spinlock_t maintenance_mode_lock; /* Used in a timer... */
 
-	/* A cheap hack, if this is non-null and a message to an
-	   interface comes in with a NULL user, call this routine with
-	   it.  Note that the message will still be freed by the
-	   caller.  This only works on the system interface. */
+	/*
+	 * A cheap hack, if this is non-null and a message to an
+	 * interface comes in with a NULL user, call this routine with
+	 * it.  Note that the message will still be freed by the
+	 * caller.  This only works on the system interface.
+	 */
 	void (*null_user_handler)(ipmi_smi_t intf, struct ipmi_recv_msg *msg);
 
-	/* When we are scanning the channels for an SMI, this will
-	   tell which channel we are scanning. */
+	/*
+	 * When we are scanning the channels for an SMI, this will
+	 * tell which channel we are scanning.
+	 */
 	int curr_channel;
 
 	/* Channel information */
@@ -285,74 +408,14 @@ struct ipmi_smi
 	struct proc_dir_entry *proc_dir;
 	char                  proc_dir_name[10];
 
-	spinlock_t   counter_lock; /* For making counters atomic. */
-
-	/* Commands we got that were invalid. */
-	unsigned int sent_invalid_commands;
-
-	/* Commands we sent to the MC. */
-	unsigned int sent_local_commands;
-	/* Responses from the MC that were delivered to a user. */
-	unsigned int handled_local_responses;
-	/* Responses from the MC that were not delivered to a user. */
-	unsigned int unhandled_local_responses;
-
-	/* Commands we sent out to the IPMB bus. */
-	unsigned int sent_ipmb_commands;
-	/* Commands sent on the IPMB that had errors on the SEND CMD */
-	unsigned int sent_ipmb_command_errs;
-	/* Each retransmit increments this count. */
-	unsigned int retransmitted_ipmb_commands;
-	/* When a message times out (runs out of retransmits) this is
-           incremented. */
-	unsigned int timed_out_ipmb_commands;
-
-	/* This is like above, but for broadcasts.  Broadcasts are
-           *not* included in the above count (they are expected to
-           time out). */
-	unsigned int timed_out_ipmb_broadcasts;
+	atomic_t stats[IPMI_NUM_STATS];
 
-	/* Responses I have sent to the IPMB bus. */
-	unsigned int sent_ipmb_responses;
-
-	/* The response was delivered to the user. */
-	unsigned int handled_ipmb_responses;
-	/* The response had invalid data in it. */
-	unsigned int invalid_ipmb_responses;
-	/* The response didn't have anyone waiting for it. */
-	unsigned int unhandled_ipmb_responses;
-
-	/* Commands we sent out to the IPMB bus. */
-	unsigned int sent_lan_commands;
-	/* Commands sent on the IPMB that had errors on the SEND CMD */
-	unsigned int sent_lan_command_errs;
-	/* Each retransmit increments this count. */
-	unsigned int retransmitted_lan_commands;
-	/* When a message times out (runs out of retransmits) this is
-           incremented. */
-	unsigned int timed_out_lan_commands;
-
-	/* Responses I have sent to the IPMB bus. */
-	unsigned int sent_lan_responses;
-
-	/* The response was delivered to the user. */
-	unsigned int handled_lan_responses;
-	/* The response had invalid data in it. */
-	unsigned int invalid_lan_responses;
-	/* The response didn't have anyone waiting for it. */
-	unsigned int unhandled_lan_responses;
-
-	/* The command was delivered to the user. */
-	unsigned int handled_commands;
-	/* The command had invalid data in it. */
-	unsigned int invalid_commands;
-	/* The command didn't have anyone waiting for it. */
-	unsigned int unhandled_commands;
-
-	/* Invalid data in an event. */
-	unsigned int invalid_events;
-	/* Events that were received with the proper format. */
-	unsigned int events;
+	/*
+	 * run_to_completion duplicate of smb_info, smi_info
+	 * and ipmi_serial_info structures. Used to decrease numbers of
+	 * parameters passed by "low" level IPMI code.
+	 */
+	int run_to_completion;
 };
 #define to_si_intf_from_dev(device) container_of(device, struct ipmi_smi, dev)
 
@@ -368,12 +431,19 @@ static DEFINE_MUTEX(ipmidriver_mutex);
 static LIST_HEAD(ipmi_interfaces);
 static DEFINE_MUTEX(ipmi_interfaces_mutex);
 
-/* List of watchers that want to know when smi's are added and
-   deleted. */
+/*
+ * List of watchers that want to know when smi's are added and deleted.
+ */
 static LIST_HEAD(smi_watchers);
 static DEFINE_MUTEX(smi_watchers_mutex);
 
 
+#define ipmi_inc_stat(intf, stat) \
+	atomic_inc(&(intf)->stats[IPMI_STAT_ ## stat])
+#define ipmi_get_stat(intf, stat) \
+	((unsigned int) atomic_read(&(intf)->stats[IPMI_STAT_ ## stat]))
+
+
 static void free_recv_msg_list(struct list_head *q)
 {
 	struct ipmi_recv_msg *msg, *msg2;
@@ -417,10 +487,8 @@ static void clean_up_interface_data(ipmi_smi_t intf)
 
 	for (i = 0; i < IPMI_IPMB_NUM_SEQ; i++) {
 		if ((intf->seq_table[i].inuse)
-		    && (intf->seq_table[i].recv_msg))
-		{
+					&& (intf->seq_table[i].recv_msg))
 			ipmi_free_recv_msg(intf->seq_table[i].recv_msg);
-		}
 	}
 }
 
@@ -487,6 +555,7 @@ int ipmi_smi_watcher_register(struct ipmi_smi_watcher *watcher)
 	}
 	return -ENOMEM;
 }
+EXPORT_SYMBOL(ipmi_smi_watcher_register);
 
 int ipmi_smi_watcher_unregister(struct ipmi_smi_watcher *watcher)
 {
@@ -495,6 +564,7 @@ int ipmi_smi_watcher_unregister(struct ipmi_smi_watcher *watcher)
 	mutex_unlock(&smi_watchers_mutex);
 	return 0;
 }
+EXPORT_SYMBOL(ipmi_smi_watcher_unregister);
 
 /*
  * Must be called with smi_watchers_mutex held.
@@ -530,8 +600,7 @@ ipmi_addr_equal(struct ipmi_addr *addr1, struct ipmi_addr *addr2)
 	}
 
 	if ((addr1->addr_type == IPMI_IPMB_ADDR_TYPE)
-	    || (addr1->addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE))
-	{
+	    || (addr1->addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE)) {
 		struct ipmi_ipmb_addr *ipmb_addr1
 		    = (struct ipmi_ipmb_addr *) addr1;
 		struct ipmi_ipmb_addr *ipmb_addr2
@@ -559,9 +628,8 @@ ipmi_addr_equal(struct ipmi_addr *addr1, struct ipmi_addr *addr2)
 
 int ipmi_validate_addr(struct ipmi_addr *addr, int len)
 {
-	if (len < sizeof(struct ipmi_system_interface_addr)) {
+	if (len < sizeof(struct ipmi_system_interface_addr))
 		return -EINVAL;
-	}
 
 	if (addr->addr_type == IPMI_SYSTEM_INTERFACE_ADDR_TYPE) {
 		if (addr->channel != IPMI_BMC_CHANNEL)
@@ -575,23 +643,21 @@ int ipmi_validate_addr(struct ipmi_addr *addr, int len)
 		return -EINVAL;
 
 	if ((addr->addr_type == IPMI_IPMB_ADDR_TYPE)
-	    || (addr->addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE))
-	{
-		if (len < sizeof(struct ipmi_ipmb_addr)) {
+	    || (addr->addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE)) {
+		if (len < sizeof(struct ipmi_ipmb_addr))
 			return -EINVAL;
-		}
 		return 0;
 	}
 
 	if (addr->addr_type == IPMI_LAN_ADDR_TYPE) {
-		if (len < sizeof(struct ipmi_lan_addr)) {
+		if (len < sizeof(struct ipmi_lan_addr))
 			return -EINVAL;
-		}
 		return 0;
 	}
 
 	return -EINVAL;
 }
+EXPORT_SYMBOL(ipmi_validate_addr);
 
 unsigned int ipmi_addr_length(int addr_type)
 {
@@ -599,34 +665,28 @@ unsigned int ipmi_addr_length(int addr_type)
 		return sizeof(struct ipmi_system_interface_addr);
 
 	if ((addr_type == IPMI_IPMB_ADDR_TYPE)
-	    || (addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE))
-	{
+			|| (addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE))
 		return sizeof(struct ipmi_ipmb_addr);
-	}
 
 	if (addr_type == IPMI_LAN_ADDR_TYPE)
 		return sizeof(struct ipmi_lan_addr);
 
 	return 0;
 }
+EXPORT_SYMBOL(ipmi_addr_length);
 
 static void deliver_response(struct ipmi_recv_msg *msg)
 {
 	if (!msg->user) {
 		ipmi_smi_t    intf = msg->user_msg_data;
-		unsigned long flags;
 
 		/* Special handling for NULL users. */
 		if (intf->null_user_handler) {
 			intf->null_user_handler(intf, msg);
-			spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->handled_local_responses++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+			ipmi_inc_stat(intf, handled_local_responses);
 		} else {
 			/* No handler, so give up. */
-			spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->unhandled_local_responses++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+			ipmi_inc_stat(intf, unhandled_local_responses);
 		}
 		ipmi_free_recv_msg(msg);
 	} else {
@@ -646,9 +706,11 @@ deliver_err_response(struct ipmi_recv_msg *msg, int err)
 	deliver_response(msg);
 }
 
-/* Find the next sequence number not being used and add the given
-   message with the given timeout to the sequence table.  This must be
-   called with the interface's seq_lock held. */
+/*
+ * Find the next sequence number not being used and add the given
+ * message with the given timeout to the sequence table.  This must be
+ * called with the interface's seq_lock held.
+ */
 static int intf_next_seq(ipmi_smi_t           intf,
 			 struct ipmi_recv_msg *recv_msg,
 			 unsigned long        timeout,
@@ -660,10 +722,8 @@ static int intf_next_seq(ipmi_smi_t           intf,
 	int          rv = 0;
 	unsigned int i;
 
-	for (i = intf->curr_seq;
-	     (i+1)%IPMI_IPMB_NUM_SEQ != intf->curr_seq;
-	     i = (i+1)%IPMI_IPMB_NUM_SEQ)
-	{
+	for (i = intf->curr_seq; (i+1)%IPMI_IPMB_NUM_SEQ != intf->curr_seq;
+					i = (i+1)%IPMI_IPMB_NUM_SEQ) {
 		if (!intf->seq_table[i].inuse)
 			break;
 	}
@@ -671,8 +731,10 @@ static int intf_next_seq(ipmi_smi_t           intf,
 	if (!intf->seq_table[i].inuse) {
 		intf->seq_table[i].recv_msg = recv_msg;
 
-		/* Start with the maximum timeout, when the send response
-		   comes in we will start the real timer. */
+		/*
+		 * Start with the maximum timeout, when the send response
+		 * comes in we will start the real timer.
+		 */
 		intf->seq_table[i].timeout = MAX_MSG_TIMEOUT;
 		intf->seq_table[i].orig_timeout = timeout;
 		intf->seq_table[i].retries_left = retries;
@@ -685,15 +747,17 @@ static int intf_next_seq(ipmi_smi_t           intf,
 	} else {
 		rv = -EAGAIN;
 	}
-	
+
 	return rv;
 }
 
-/* Return the receive message for the given sequence number and
-   release the sequence number so it can be reused.  Some other data
-   is passed in to be sure the message matches up correctly (to help
-   guard against message coming in after their timeout and the
-   sequence number being reused). */
+/*
+ * Return the receive message for the given sequence number and
+ * release the sequence number so it can be reused.  Some other data
+ * is passed in to be sure the message matches up correctly (to help
+ * guard against message coming in after their timeout and the
+ * sequence number being reused).
+ */
 static int intf_find_seq(ipmi_smi_t           intf,
 			 unsigned char        seq,
 			 short                channel,
@@ -712,11 +776,9 @@ static int intf_find_seq(ipmi_smi_t           intf,
 	if (intf->seq_table[seq].inuse) {
 		struct ipmi_recv_msg *msg = intf->seq_table[seq].recv_msg;
 
-		if ((msg->addr.channel == channel)
-		    && (msg->msg.cmd == cmd)
-		    && (msg->msg.netfn == netfn)
-		    && (ipmi_addr_equal(addr, &(msg->addr))))
-		{
+		if ((msg->addr.channel == channel) && (msg->msg.cmd == cmd)
+				&& (msg->msg.netfn == netfn)
+				&& (ipmi_addr_equal(addr, &(msg->addr)))) {
 			*recv_msg = msg;
 			intf->seq_table[seq].inuse = 0;
 			rv = 0;
@@ -741,11 +803,12 @@ static int intf_start_seq_timer(ipmi_smi_t intf,
 	GET_SEQ_FROM_MSGID(msgid, seq, seqid);
 
 	spin_lock_irqsave(&(intf->seq_lock), flags);
-	/* We do this verification because the user can be deleted
-           while a message is outstanding. */
+	/*
+	 * We do this verification because the user can be deleted
+	 * while a message is outstanding.
+	 */
 	if ((intf->seq_table[seq].inuse)
-	    && (intf->seq_table[seq].seqid == seqid))
-	{
+				&& (intf->seq_table[seq].seqid == seqid)) {
 		struct seq_table *ent = &(intf->seq_table[seq]);
 		ent->timeout = ent->orig_timeout;
 		rv = 0;
@@ -770,11 +833,12 @@ static int intf_err_seq(ipmi_smi_t   intf,
 	GET_SEQ_FROM_MSGID(msgid, seq, seqid);
 
 	spin_lock_irqsave(&(intf->seq_lock), flags);
-	/* We do this verification because the user can be deleted
-           while a message is outstanding. */
+	/*
+	 * We do this verification because the user can be deleted
+	 * while a message is outstanding.
+	 */
 	if ((intf->seq_table[seq].inuse)
-	    && (intf->seq_table[seq].seqid == seqid))
-	{
+				&& (intf->seq_table[seq].seqid == seqid)) {
 		struct seq_table *ent = &(intf->seq_table[seq]);
 
 		ent->inuse = 0;
@@ -800,24 +864,30 @@ int ipmi_create_user(unsigned int          if_num,
 	int           rv = 0;
 	ipmi_smi_t    intf;
 
-	/* There is no module usecount here, because it's not
-           required.  Since this can only be used by and called from
-           other modules, they will implicitly use this module, and
-           thus this can't be removed unless the other modules are
-           removed. */
+	/*
+	 * There is no module usecount here, because it's not
+	 * required.  Since this can only be used by and called from
+	 * other modules, they will implicitly use this module, and
+	 * thus this can't be removed unless the other modules are
+	 * removed.
+	 */
 
 	if (handler == NULL)
 		return -EINVAL;
 
-	/* Make sure the driver is actually initialized, this handles
-	   problems with initialization order. */
+	/*
+	 * Make sure the driver is actually initialized, this handles
+	 * problems with initialization order.
+	 */
 	if (!initialized) {
 		rv = ipmi_init_msghandler();
 		if (rv)
 			return rv;
 
-		/* The init code doesn't return an error if it was turned
-		   off, but it won't initialize.  Check that. */
+		/*
+		 * The init code doesn't return an error if it was turned
+		 * off, but it won't initialize.  Check that.
+		 */
 		if (!initialized)
 			return -ENODEV;
 	}
@@ -858,8 +928,10 @@ int ipmi_create_user(unsigned int          if_num,
 		}
 	}
 
-	/* Hold the lock so intf->handlers is guaranteed to be good
-	 * until now */
+	/*
+	 * Hold the lock so intf->handlers is guaranteed to be good
+	 * until now
+	 */
 	mutex_unlock(&ipmi_interfaces_mutex);
 
 	new_user->valid = 1;
@@ -876,6 +948,7 @@ int ipmi_create_user(unsigned int          if_num,
 	kfree(new_user);
 	return rv;
 }
+EXPORT_SYMBOL(ipmi_create_user);
 
 static void free_user(struct kref *ref)
 {
@@ -899,8 +972,7 @@ int ipmi_destroy_user(ipmi_user_t user)
 
 	for (i = 0; i < IPMI_IPMB_NUM_SEQ; i++) {
 		if (intf->seq_table[i].inuse
-		    && (intf->seq_table[i].recv_msg->user == user))
-		{
+		    && (intf->seq_table[i].recv_msg->user == user)) {
 			intf->seq_table[i].inuse = 0;
 			ipmi_free_recv_msg(intf->seq_table[i].recv_msg);
 		}
@@ -943,6 +1015,7 @@ int ipmi_destroy_user(ipmi_user_t user)
 
 	return 0;
 }
+EXPORT_SYMBOL(ipmi_destroy_user);
 
 void ipmi_get_version(ipmi_user_t   user,
 		      unsigned char *major,
@@ -951,6 +1024,7 @@ void ipmi_get_version(ipmi_user_t   user,
 	*major = user->intf->ipmi_version_major;
 	*minor = user->intf->ipmi_version_minor;
 }
+EXPORT_SYMBOL(ipmi_get_version);
 
 int ipmi_set_my_address(ipmi_user_t   user,
 			unsigned int  channel,
@@ -961,6 +1035,7 @@ int ipmi_set_my_address(ipmi_user_t   user,
 	user->intf->channels[channel].address = address;
 	return 0;
 }
+EXPORT_SYMBOL(ipmi_set_my_address);
 
 int ipmi_get_my_address(ipmi_user_t   user,
 			unsigned int  channel,
@@ -971,6 +1046,7 @@ int ipmi_get_my_address(ipmi_user_t   user,
 	*address = user->intf->channels[channel].address;
 	return 0;
 }
+EXPORT_SYMBOL(ipmi_get_my_address);
 
 int ipmi_set_my_LUN(ipmi_user_t   user,
 		    unsigned int  channel,
@@ -981,6 +1057,7 @@ int ipmi_set_my_LUN(ipmi_user_t   user,
 	user->intf->channels[channel].lun = LUN & 0x3;
 	return 0;
 }
+EXPORT_SYMBOL(ipmi_set_my_LUN);
 
 int ipmi_get_my_LUN(ipmi_user_t   user,
 		    unsigned int  channel,
@@ -991,6 +1068,7 @@ int ipmi_get_my_LUN(ipmi_user_t   user,
 	*address = user->intf->channels[channel].lun;
 	return 0;
 }
+EXPORT_SYMBOL(ipmi_get_my_LUN);
 
 int ipmi_get_maintenance_mode(ipmi_user_t user)
 {
@@ -1075,6 +1153,11 @@ int ipmi_set_gets_events(ipmi_user_t user, int val)
 		list_for_each_entry_safe(msg, msg2, &intf->waiting_events, link)
 			list_move_tail(&msg->link, &msgs);
 		intf->waiting_events_count = 0;
+		if (intf->event_msg_printed) {
+			printk(KERN_WARNING PFX "Event queue no longer"
+			       " full\n");
+			intf->event_msg_printed = 0;
+		}
 
 		intf->delivering_events = 1;
 		spin_unlock_irqrestore(&intf->events_lock, flags);
@@ -1094,6 +1177,7 @@ int ipmi_set_gets_events(ipmi_user_t user, int val)
 
 	return 0;
 }
+EXPORT_SYMBOL(ipmi_set_gets_events);
 
 static struct cmd_rcvr *find_cmd_rcvr(ipmi_smi_t    intf,
 				      unsigned char netfn,
@@ -1159,6 +1243,7 @@ int ipmi_register_for_cmd(ipmi_user_t   user,
 
 	return rv;
 }
+EXPORT_SYMBOL(ipmi_register_for_cmd);
 
 int ipmi_unregister_for_cmd(ipmi_user_t   user,
 			    unsigned char netfn,
@@ -1196,19 +1281,13 @@ int ipmi_unregister_for_cmd(ipmi_user_t   user,
 	}
 	return rv;
 }
-
-void ipmi_user_set_run_to_completion(ipmi_user_t user, int val)
-{
-	ipmi_smi_t intf = user->intf;
-	if (intf->handlers)
-		intf->handlers->set_run_to_completion(intf->send_info, val);
-}
+EXPORT_SYMBOL(ipmi_unregister_for_cmd);
 
 static unsigned char
 ipmb_checksum(unsigned char *data, int size)
 {
 	unsigned char csum = 0;
-	
+
 	for (; size > 0; size--, data++)
 		csum += *data;
 
@@ -1250,8 +1329,10 @@ static inline void format_ipmb_msg(struct ipmi_smi_msg   *smi_msg,
 		= ipmb_checksum(&(smi_msg->data[i+6]),
 				smi_msg->data_size-6);
 
-	/* Add on the checksum size and the offset from the
-	   broadcast. */
+	/*
+	 * Add on the checksum size and the offset from the
+	 * broadcast.
+	 */
 	smi_msg->data_size += 1 + i;
 
 	smi_msg->msgid = msgid;
@@ -1287,17 +1368,21 @@ static inline void format_lan_msg(struct ipmi_smi_msg   *smi_msg,
 		= ipmb_checksum(&(smi_msg->data[7]),
 				smi_msg->data_size-7);
 
-	/* Add on the checksum size and the offset from the
-	   broadcast. */
+	/*
+	 * Add on the checksum size and the offset from the
+	 * broadcast.
+	 */
 	smi_msg->data_size += 1;
 
 	smi_msg->msgid = msgid;
 }
 
-/* Separate from ipmi_request so that the user does not have to be
-   supplied in certain circumstances (mainly at panic time).  If
-   messages are supplied, they will be freed, even if an error
-   occurs. */
+/*
+ * Separate from ipmi_request so that the user does not have to be
+ * supplied in certain circumstances (mainly at panic time).  If
+ * messages are supplied, they will be freed, even if an error
+ * occurs.
+ */
 static int i_ipmi_request(ipmi_user_t          user,
 			  ipmi_smi_t           intf,
 			  struct ipmi_addr     *addr,
@@ -1319,19 +1404,18 @@ static int i_ipmi_request(ipmi_user_t          user,
 	struct ipmi_smi_handlers *handlers;
 
 
-	if (supplied_recv) {
+	if (supplied_recv)
 		recv_msg = supplied_recv;
-	} else {
+	else {
 		recv_msg = ipmi_alloc_recv_msg();
-		if (recv_msg == NULL) {
+		if (recv_msg == NULL)
 			return -ENOMEM;
-		}
 	}
 	recv_msg->user_msg_data = user_msg_data;
 
-	if (supplied_smi) {
+	if (supplied_smi)
 		smi_msg = (struct ipmi_smi_msg *) supplied_smi;
-	} else {
+	else {
 		smi_msg = ipmi_alloc_smi_msg();
 		if (smi_msg == NULL) {
 			ipmi_free_recv_msg(recv_msg);
@@ -1350,8 +1434,10 @@ static int i_ipmi_request(ipmi_user_t          user,
 	if (user)
 		kref_get(&user->refcount);
 	recv_msg->msgid = msgid;
-	/* Store the message to send in the receive message so timeout
-	   responses can get the proper response data. */
+	/*
+	 * Store the message to send in the receive message so timeout
+	 * responses can get the proper response data.
+	 */
 	recv_msg->msg = *msg;
 
 	if (addr->addr_type == IPMI_SYSTEM_INTERFACE_ADDR_TYPE) {
@@ -1365,9 +1451,7 @@ static int i_ipmi_request(ipmi_user_t          user,
 
 		smi_addr = (struct ipmi_system_interface_addr *) addr;
 		if (smi_addr->lun > 3) {
-			spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->sent_invalid_commands++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+			ipmi_inc_stat(intf, sent_invalid_commands);
 			rv = -EINVAL;
 			goto out_err;
 		}
@@ -1377,13 +1461,12 @@ static int i_ipmi_request(ipmi_user_t          user,
 		if ((msg->netfn == IPMI_NETFN_APP_REQUEST)
 		    && ((msg->cmd == IPMI_SEND_MSG_CMD)
 			|| (msg->cmd == IPMI_GET_MSG_CMD)
-			|| (msg->cmd == IPMI_READ_EVENT_MSG_BUFFER_CMD)))
-		{
-			/* We don't let the user do these, since we manage
-			   the sequence numbers. */
-			spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->sent_invalid_commands++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+			|| (msg->cmd == IPMI_READ_EVENT_MSG_BUFFER_CMD))) {
+			/*
+			 * We don't let the user do these, since we manage
+			 * the sequence numbers.
+			 */
+			ipmi_inc_stat(intf, sent_invalid_commands);
 			rv = -EINVAL;
 			goto out_err;
 		}
@@ -1391,14 +1474,12 @@ static int i_ipmi_request(ipmi_user_t          user,
 		if (((msg->netfn == IPMI_NETFN_APP_REQUEST)
 		      && ((msg->cmd == IPMI_COLD_RESET_CMD)
 			  || (msg->cmd == IPMI_WARM_RESET_CMD)))
-		     || (msg->netfn == IPMI_NETFN_FIRMWARE_REQUEST))
-		{
+		     || (msg->netfn == IPMI_NETFN_FIRMWARE_REQUEST)) {
 			spin_lock_irqsave(&intf->maintenance_mode_lock, flags);
 			intf->auto_maintenance_timeout
 				= IPMI_MAINTENANCE_MODE_TIMEOUT;
 			if (!intf->maintenance_mode
-			    && !intf->maintenance_mode_enable)
-			{
+			    && !intf->maintenance_mode_enable) {
 				intf->maintenance_mode_enable = 1;
 				maintenance_mode_update(intf);
 			}
@@ -1407,9 +1488,7 @@ static int i_ipmi_request(ipmi_user_t          user,
 		}
 
 		if ((msg->data_len + 2) > IPMI_MAX_MSG_LENGTH) {
-			spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->sent_invalid_commands++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+			ipmi_inc_stat(intf, sent_invalid_commands);
 			rv = -EMSGSIZE;
 			goto out_err;
 		}
@@ -1421,31 +1500,23 @@ static int i_ipmi_request(ipmi_user_t          user,
 		if (msg->data_len > 0)
 			memcpy(&(smi_msg->data[2]), msg->data, msg->data_len);
 		smi_msg->data_size = msg->data_len + 2;
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->sent_local_commands++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+		ipmi_inc_stat(intf, sent_local_commands);
 	} else if ((addr->addr_type == IPMI_IPMB_ADDR_TYPE)
-		   || (addr->addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE))
-	{
+		   || (addr->addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE)) {
 		struct ipmi_ipmb_addr *ipmb_addr;
 		unsigned char         ipmb_seq;
 		long                  seqid;
 		int                   broadcast = 0;
 
 		if (addr->channel >= IPMI_MAX_CHANNELS) {
-		        spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->sent_invalid_commands++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+			ipmi_inc_stat(intf, sent_invalid_commands);
 			rv = -EINVAL;
 			goto out_err;
 		}
 
 		if (intf->channels[addr->channel].medium
-		    != IPMI_CHANNEL_MEDIUM_IPMB)
-		{
-			spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->sent_invalid_commands++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+					!= IPMI_CHANNEL_MEDIUM_IPMB) {
+			ipmi_inc_stat(intf, sent_invalid_commands);
 			rv = -EINVAL;
 			goto out_err;
 		}
@@ -1457,9 +1528,11 @@ static int i_ipmi_request(ipmi_user_t          user,
 			retries = 4;
 		}
 		if (addr->addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE) {
-		    /* Broadcasts add a zero at the beginning of the
-		       message, but otherwise is the same as an IPMB
-		       address. */
+		    /*
+		     * Broadcasts add a zero at the beginning of the
+		     * message, but otherwise is the same as an IPMB
+		     * address.
+		     */
 		    addr->addr_type = IPMI_IPMB_ADDR_TYPE;
 		    broadcast = 1;
 		}
@@ -1469,21 +1542,19 @@ static int i_ipmi_request(ipmi_user_t          user,
 		if (retry_time_ms == 0)
 		    retry_time_ms = 1000;
 
-		/* 9 for the header and 1 for the checksum, plus
-                   possibly one for the broadcast. */
+		/*
+		 * 9 for the header and 1 for the checksum, plus
+		 * possibly one for the broadcast.
+		 */
 		if ((msg->data_len + 10 + broadcast) > IPMI_MAX_MSG_LENGTH) {
-			spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->sent_invalid_commands++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+			ipmi_inc_stat(intf, sent_invalid_commands);
 			rv = -EMSGSIZE;
 			goto out_err;
 		}
 
 		ipmb_addr = (struct ipmi_ipmb_addr *) addr;
 		if (ipmb_addr->lun > 3) {
-			spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->sent_invalid_commands++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+			ipmi_inc_stat(intf, sent_invalid_commands);
 			rv = -EINVAL;
 			goto out_err;
 		}
@@ -1491,29 +1562,31 @@ static int i_ipmi_request(ipmi_user_t          user,
 		memcpy(&recv_msg->addr, ipmb_addr, sizeof(*ipmb_addr));
 
 		if (recv_msg->msg.netfn & 0x1) {
-			/* It's a response, so use the user's sequence
-                           from msgid. */
-			spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->sent_ipmb_responses++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+			/*
+			 * It's a response, so use the user's sequence
+			 * from msgid.
+			 */
+			ipmi_inc_stat(intf, sent_ipmb_responses);
 			format_ipmb_msg(smi_msg, msg, ipmb_addr, msgid,
 					msgid, broadcast,
 					source_address, source_lun);
 
-			/* Save the receive message so we can use it
-			   to deliver the response. */
+			/*
+			 * Save the receive message so we can use it
+			 * to deliver the response.
+			 */
 			smi_msg->user_data = recv_msg;
 		} else {
 			/* It's a command, so get a sequence for it. */
 
 			spin_lock_irqsave(&(intf->seq_lock), flags);
 
-			spin_lock(&intf->counter_lock);
-			intf->sent_ipmb_commands++;
-			spin_unlock(&intf->counter_lock);
+			ipmi_inc_stat(intf, sent_ipmb_commands);
 
-			/* Create a sequence number with a 1 second
-                           timeout and 4 retries. */
+			/*
+			 * Create a sequence number with a 1 second
+			 * timeout and 4 retries.
+			 */
 			rv = intf_next_seq(intf,
 					   recv_msg,
 					   retry_time_ms,
@@ -1522,34 +1595,42 @@ static int i_ipmi_request(ipmi_user_t          user,
 					   &ipmb_seq,
 					   &seqid);
 			if (rv) {
-				/* We have used up all the sequence numbers,
-				   probably, so abort. */
+				/*
+				 * We have used up all the sequence numbers,
+				 * probably, so abort.
+				 */
 				spin_unlock_irqrestore(&(intf->seq_lock),
 						       flags);
 				goto out_err;
 			}
 
-			/* Store the sequence number in the message,
-                           so that when the send message response
-                           comes back we can start the timer. */
+			/*
+			 * Store the sequence number in the message,
+			 * so that when the send message response
+			 * comes back we can start the timer.
+			 */
 			format_ipmb_msg(smi_msg, msg, ipmb_addr,
 					STORE_SEQ_IN_MSGID(ipmb_seq, seqid),
 					ipmb_seq, broadcast,
 					source_address, source_lun);
 
-			/* Copy the message into the recv message data, so we
-			   can retransmit it later if necessary. */
+			/*
+			 * Copy the message into the recv message data, so we
+			 * can retransmit it later if necessary.
+			 */
 			memcpy(recv_msg->msg_data, smi_msg->data,
 			       smi_msg->data_size);
 			recv_msg->msg.data = recv_msg->msg_data;
 			recv_msg->msg.data_len = smi_msg->data_size;
 
-			/* We don't unlock until here, because we need
-                           to copy the completed message into the
-                           recv_msg before we release the lock.
-                           Otherwise, race conditions may bite us.  I
-                           know that's pretty paranoid, but I prefer
-                           to be correct. */
+			/*
+			 * We don't unlock until here, because we need
+			 * to copy the completed message into the
+			 * recv_msg before we release the lock.
+			 * Otherwise, race conditions may bite us.  I
+			 * know that's pretty paranoid, but I prefer
+			 * to be correct.
+			 */
 			spin_unlock_irqrestore(&(intf->seq_lock), flags);
 		}
 	} else if (addr->addr_type == IPMI_LAN_ADDR_TYPE) {
@@ -1558,21 +1639,16 @@ static int i_ipmi_request(ipmi_user_t          user,
 		long                  seqid;
 
 		if (addr->channel >= IPMI_MAX_CHANNELS) {
-			spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->sent_invalid_commands++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+			ipmi_inc_stat(intf, sent_invalid_commands);
 			rv = -EINVAL;
 			goto out_err;
 		}
 
 		if ((intf->channels[addr->channel].medium
-		    != IPMI_CHANNEL_MEDIUM_8023LAN)
+				!= IPMI_CHANNEL_MEDIUM_8023LAN)
 		    && (intf->channels[addr->channel].medium
-			!= IPMI_CHANNEL_MEDIUM_ASYNC))
-		{
-			spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->sent_invalid_commands++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+				!= IPMI_CHANNEL_MEDIUM_ASYNC)) {
+			ipmi_inc_stat(intf, sent_invalid_commands);
 			rv = -EINVAL;
 			goto out_err;
 		}
@@ -1585,18 +1661,14 @@ static int i_ipmi_request(ipmi_user_t          user,
 
 		/* 11 for the header and 1 for the checksum. */
 		if ((msg->data_len + 12) > IPMI_MAX_MSG_LENGTH) {
-			spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->sent_invalid_commands++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+			ipmi_inc_stat(intf, sent_invalid_commands);
 			rv = -EMSGSIZE;
 			goto out_err;
 		}
 
 		lan_addr = (struct ipmi_lan_addr *) addr;
 		if (lan_addr->lun > 3) {
-			spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->sent_invalid_commands++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+			ipmi_inc_stat(intf, sent_invalid_commands);
 			rv = -EINVAL;
 			goto out_err;
 		}
@@ -1604,28 +1676,30 @@ static int i_ipmi_request(ipmi_user_t          user,
 		memcpy(&recv_msg->addr, lan_addr, sizeof(*lan_addr));
 
 		if (recv_msg->msg.netfn & 0x1) {
-			/* It's a response, so use the user's sequence
-                           from msgid. */
-			spin_lock_irqsave(&intf->counter_lock, flags);
-			intf->sent_lan_responses++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+			/*
+			 * It's a response, so use the user's sequence
+			 * from msgid.
+			 */
+			ipmi_inc_stat(intf, sent_lan_responses);
 			format_lan_msg(smi_msg, msg, lan_addr, msgid,
 				       msgid, source_lun);
 
-			/* Save the receive message so we can use it
-			   to deliver the response. */
+			/*
+			 * Save the receive message so we can use it
+			 * to deliver the response.
+			 */
 			smi_msg->user_data = recv_msg;
 		} else {
 			/* It's a command, so get a sequence for it. */
 
 			spin_lock_irqsave(&(intf->seq_lock), flags);
 
-			spin_lock(&intf->counter_lock);
-			intf->sent_lan_commands++;
-			spin_unlock(&intf->counter_lock);
+			ipmi_inc_stat(intf, sent_lan_commands);
 
-			/* Create a sequence number with a 1 second
-                           timeout and 4 retries. */
+			/*
+			 * Create a sequence number with a 1 second
+			 * timeout and 4 retries.
+			 */
 			rv = intf_next_seq(intf,
 					   recv_msg,
 					   retry_time_ms,
@@ -1634,40 +1708,46 @@ static int i_ipmi_request(ipmi_user_t          user,
 					   &ipmb_seq,
 					   &seqid);
 			if (rv) {
-				/* We have used up all the sequence numbers,
-				   probably, so abort. */
+				/*
+				 * We have used up all the sequence numbers,
+				 * probably, so abort.
+				 */
 				spin_unlock_irqrestore(&(intf->seq_lock),
 						       flags);
 				goto out_err;
 			}
 
-			/* Store the sequence number in the message,
-                           so that when the send message response
-                           comes back we can start the timer. */
+			/*
+			 * Store the sequence number in the message,
+			 * so that when the send message response
+			 * comes back we can start the timer.
+			 */
 			format_lan_msg(smi_msg, msg, lan_addr,
 				       STORE_SEQ_IN_MSGID(ipmb_seq, seqid),
 				       ipmb_seq, source_lun);
 
-			/* Copy the message into the recv message data, so we
-			   can retransmit it later if necessary. */
+			/*
+			 * Copy the message into the recv message data, so we
+			 * can retransmit it later if necessary.
+			 */
 			memcpy(recv_msg->msg_data, smi_msg->data,
 			       smi_msg->data_size);
 			recv_msg->msg.data = recv_msg->msg_data;
 			recv_msg->msg.data_len = smi_msg->data_size;
 
-			/* We don't unlock until here, because we need
-                           to copy the completed message into the
-                           recv_msg before we release the lock.
-                           Otherwise, race conditions may bite us.  I
-                           know that's pretty paranoid, but I prefer
-                           to be correct. */
+			/*
+			 * We don't unlock until here, because we need
+			 * to copy the completed message into the
+			 * recv_msg before we release the lock.
+			 * Otherwise, race conditions may bite us.  I
+			 * know that's pretty paranoid, but I prefer
+			 * to be correct.
+			 */
 			spin_unlock_irqrestore(&(intf->seq_lock), flags);
 		}
 	} else {
 	    /* Unknown address type. */
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->sent_invalid_commands++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+		ipmi_inc_stat(intf, sent_invalid_commands);
 		rv = -EINVAL;
 		goto out_err;
 	}
@@ -1735,6 +1815,7 @@ int ipmi_request_settime(ipmi_user_t      user,
 			      retries,
 			      retry_time_ms);
 }
+EXPORT_SYMBOL(ipmi_request_settime);
 
 int ipmi_request_supply_msgs(ipmi_user_t          user,
 			     struct ipmi_addr     *addr,
@@ -1766,6 +1847,7 @@ int ipmi_request_supply_msgs(ipmi_user_t          user,
 			      lun,
 			      -1, 0);
 }
+EXPORT_SYMBOL(ipmi_request_supply_msgs);
 
 #ifdef CONFIG_PROC_FS
 static int ipmb_file_read_proc(char *page, char **start, off_t off,
@@ -1790,7 +1872,7 @@ static int version_file_read_proc(char *page, char **start, off_t off,
 	char       *out = (char *) page;
 	ipmi_smi_t intf = data;
 
-	return sprintf(out, "%d.%d\n",
+	return sprintf(out, "%u.%u\n",
 		       ipmi_version_major(&intf->bmc->id),
 		       ipmi_version_minor(&intf->bmc->id));
 }
@@ -1801,65 +1883,65 @@ static int stat_file_read_proc(char *page, char **start, off_t off,
 	char       *out = (char *) page;
 	ipmi_smi_t intf = data;
 
-	out += sprintf(out, "sent_invalid_commands:       %d\n",
-		       intf->sent_invalid_commands);
-	out += sprintf(out, "sent_local_commands:         %d\n",
-		       intf->sent_local_commands);
-	out += sprintf(out, "handled_local_responses:     %d\n",
-		       intf->handled_local_responses);
-	out += sprintf(out, "unhandled_local_responses:   %d\n",
-		       intf->unhandled_local_responses);
-	out += sprintf(out, "sent_ipmb_commands:          %d\n",
-		       intf->sent_ipmb_commands);
-	out += sprintf(out, "sent_ipmb_command_errs:      %d\n",
-		       intf->sent_ipmb_command_errs);
-	out += sprintf(out, "retransmitted_ipmb_commands: %d\n",
-		       intf->retransmitted_ipmb_commands);
-	out += sprintf(out, "timed_out_ipmb_commands:     %d\n",
-		       intf->timed_out_ipmb_commands);
-	out += sprintf(out, "timed_out_ipmb_broadcasts:   %d\n",
-		       intf->timed_out_ipmb_broadcasts);
-	out += sprintf(out, "sent_ipmb_responses:         %d\n",
-		       intf->sent_ipmb_responses);
-	out += sprintf(out, "handled_ipmb_responses:      %d\n",
-		       intf->handled_ipmb_responses);
-	out += sprintf(out, "invalid_ipmb_responses:      %d\n",
-		       intf->invalid_ipmb_responses);
-	out += sprintf(out, "unhandled_ipmb_responses:    %d\n",
-		       intf->unhandled_ipmb_responses);
-	out += sprintf(out, "sent_lan_commands:           %d\n",
-		       intf->sent_lan_commands);
-	out += sprintf(out, "sent_lan_command_errs:       %d\n",
-		       intf->sent_lan_command_errs);
-	out += sprintf(out, "retransmitted_lan_commands:  %d\n",
-		       intf->retransmitted_lan_commands);
-	out += sprintf(out, "timed_out_lan_commands:      %d\n",
-		       intf->timed_out_lan_commands);
-	out += sprintf(out, "sent_lan_responses:          %d\n",
-		       intf->sent_lan_responses);
-	out += sprintf(out, "handled_lan_responses:       %d\n",
-		       intf->handled_lan_responses);
-	out += sprintf(out, "invalid_lan_responses:       %d\n",
-		       intf->invalid_lan_responses);
-	out += sprintf(out, "unhandled_lan_responses:     %d\n",
-		       intf->unhandled_lan_responses);
-	out += sprintf(out, "handled_commands:            %d\n",
-		       intf->handled_commands);
-	out += sprintf(out, "invalid_commands:            %d\n",
-		       intf->invalid_commands);
-	out += sprintf(out, "unhandled_commands:          %d\n",
-		       intf->unhandled_commands);
-	out += sprintf(out, "invalid_events:              %d\n",
-		       intf->invalid_events);
-	out += sprintf(out, "events:                      %d\n",
-		       intf->events);
+	out += sprintf(out, "sent_invalid_commands:       %u\n",
+		       ipmi_get_stat(intf, sent_invalid_commands));
+	out += sprintf(out, "sent_local_commands:         %u\n",
+		       ipmi_get_stat(intf, sent_local_commands));
+	out += sprintf(out, "handled_local_responses:     %u\n",
+		       ipmi_get_stat(intf, handled_local_responses));
+	out += sprintf(out, "unhandled_local_responses:   %u\n",
+		       ipmi_get_stat(intf, unhandled_local_responses));
+	out += sprintf(out, "sent_ipmb_commands:          %u\n",
+		       ipmi_get_stat(intf, sent_ipmb_commands));
+	out += sprintf(out, "sent_ipmb_command_errs:      %u\n",
+		       ipmi_get_stat(intf, sent_ipmb_command_errs));
+	out += sprintf(out, "retransmitted_ipmb_commands: %u\n",
+		       ipmi_get_stat(intf, retransmitted_ipmb_commands));
+	out += sprintf(out, "timed_out_ipmb_commands:     %u\n",
+		       ipmi_get_stat(intf, timed_out_ipmb_commands));
+	out += sprintf(out, "timed_out_ipmb_broadcasts:   %u\n",
+		       ipmi_get_stat(intf, timed_out_ipmb_broadcasts));
+	out += sprintf(out, "sent_ipmb_responses:         %u\n",
+		       ipmi_get_stat(intf, sent_ipmb_responses));
+	out += sprintf(out, "handled_ipmb_responses:      %u\n",
+		       ipmi_get_stat(intf, handled_ipmb_responses));
+	out += sprintf(out, "invalid_ipmb_responses:      %u\n",
+		       ipmi_get_stat(intf, invalid_ipmb_responses));
+	out += sprintf(out, "unhandled_ipmb_responses:    %u\n",
+		       ipmi_get_stat(intf, unhandled_ipmb_responses));
+	out += sprintf(out, "sent_lan_commands:           %u\n",
+		       ipmi_get_stat(intf, sent_lan_commands));
+	out += sprintf(out, "sent_lan_command_errs:       %u\n",
+		       ipmi_get_stat(intf, sent_lan_command_errs));
+	out += sprintf(out, "retransmitted_lan_commands:  %u\n",
+		       ipmi_get_stat(intf, retransmitted_lan_commands));
+	out += sprintf(out, "timed_out_lan_commands:      %u\n",
+		       ipmi_get_stat(intf, timed_out_lan_commands));
+	out += sprintf(out, "sent_lan_responses:          %u\n",
+		       ipmi_get_stat(intf, sent_lan_responses));
+	out += sprintf(out, "handled_lan_responses:       %u\n",
+		       ipmi_get_stat(intf, handled_lan_responses));
+	out += sprintf(out, "invalid_lan_responses:       %u\n",
+		       ipmi_get_stat(intf, invalid_lan_responses));
+	out += sprintf(out, "unhandled_lan_responses:     %u\n",
+		       ipmi_get_stat(intf, unhandled_lan_responses));
+	out += sprintf(out, "handled_commands:            %u\n",
+		       ipmi_get_stat(intf, handled_commands));
+	out += sprintf(out, "invalid_commands:            %u\n",
+		       ipmi_get_stat(intf, invalid_commands));
+	out += sprintf(out, "unhandled_commands:          %u\n",
+		       ipmi_get_stat(intf, unhandled_commands));
+	out += sprintf(out, "invalid_events:              %u\n",
+		       ipmi_get_stat(intf, invalid_events));
+	out += sprintf(out, "events:                      %u\n",
+		       ipmi_get_stat(intf, events));
 
 	return (out - ((char *) page));
 }
 #endif /* CONFIG_PROC_FS */
 
 int ipmi_smi_add_proc_entry(ipmi_smi_t smi, char *name,
-			    read_proc_t *read_proc, write_proc_t *write_proc,
+			    read_proc_t *read_proc,
 			    void *data, struct module *owner)
 {
 	int                    rv = 0;
@@ -1886,7 +1968,6 @@ int ipmi_smi_add_proc_entry(ipmi_smi_t smi, char *name,
 	} else {
 		file->data = data;
 		file->read_proc = read_proc;
-		file->write_proc = write_proc;
 		file->owner = owner;
 
 		mutex_lock(&smi->proc_entry_lock);
@@ -1899,6 +1980,7 @@ int ipmi_smi_add_proc_entry(ipmi_smi_t smi, char *name,
 
 	return rv;
 }
+EXPORT_SYMBOL(ipmi_smi_add_proc_entry);
 
 static int add_proc_entries(ipmi_smi_t smi, int num)
 {
@@ -1909,23 +1991,22 @@ static int add_proc_entries(ipmi_smi_t smi, int num)
 	smi->proc_dir = proc_mkdir(smi->proc_dir_name, proc_ipmi_root);
 	if (!smi->proc_dir)
 		rv = -ENOMEM;
-	else {
+	else
 		smi->proc_dir->owner = THIS_MODULE;
-	}
 
 	if (rv == 0)
 		rv = ipmi_smi_add_proc_entry(smi, "stats",
-					     stat_file_read_proc, NULL,
+					     stat_file_read_proc,
 					     smi, THIS_MODULE);
 
 	if (rv == 0)
 		rv = ipmi_smi_add_proc_entry(smi, "ipmb",
-					     ipmb_file_read_proc, NULL,
+					     ipmb_file_read_proc,
 					     smi, THIS_MODULE);
 
 	if (rv == 0)
 		rv = ipmi_smi_add_proc_entry(smi, "version",
-					     version_file_read_proc, NULL,
+					     version_file_read_proc,
 					     smi, THIS_MODULE);
 #endif /* CONFIG_PROC_FS */
 
@@ -2210,37 +2291,47 @@ static int create_files(struct bmc_device *bmc)
 
 	err = device_create_file(&bmc->dev->dev,
 			   &bmc->device_id_attr);
-	if (err) goto out;
+	if (err)
+		goto out;
 	err = device_create_file(&bmc->dev->dev,
 			   &bmc->provides_dev_sdrs_attr);
-	if (err) goto out_devid;
+	if (err)
+		goto out_devid;
 	err = device_create_file(&bmc->dev->dev,
 			   &bmc->revision_attr);
-	if (err) goto out_sdrs;
+	if (err)
+		goto out_sdrs;
 	err = device_create_file(&bmc->dev->dev,
 			   &bmc->firmware_rev_attr);
-	if (err) goto out_rev;
+	if (err)
+		goto out_rev;
 	err = device_create_file(&bmc->dev->dev,
 			   &bmc->version_attr);
-	if (err) goto out_firm;
+	if (err)
+		goto out_firm;
 	err = device_create_file(&bmc->dev->dev,
 			   &bmc->add_dev_support_attr);
-	if (err) goto out_version;
+	if (err)
+		goto out_version;
 	err = device_create_file(&bmc->dev->dev,
 			   &bmc->manufacturer_id_attr);
-	if (err) goto out_add_dev;
+	if (err)
+		goto out_add_dev;
 	err = device_create_file(&bmc->dev->dev,
 			   &bmc->product_id_attr);
-	if (err) goto out_manu;
+	if (err)
+		goto out_manu;
 	if (bmc->id.aux_firmware_revision_set) {
 		err = device_create_file(&bmc->dev->dev,
 				   &bmc->aux_firmware_rev_attr);
-		if (err) goto out_prod_id;
+		if (err)
+			goto out_prod_id;
 	}
 	if (bmc->guid_set) {
 		err = device_create_file(&bmc->dev->dev,
 				   &bmc->guid_attr);
-		if (err) goto out_aux_firm;
+		if (err)
+			goto out_aux_firm;
 	}
 
 	return 0;
@@ -2368,8 +2459,10 @@ static int ipmi_bmc_register(ipmi_smi_t intf, int ifnum,
 			       "ipmi_msghandler:"
 			       " Unable to register bmc device: %d\n",
 			       rv);
-			/* Don't go to out_err, you can only do that if
-			   the device is registered already. */
+			/*
+			 * Don't go to out_err, you can only do that if
+			 * the device is registered already.
+			 */
 			return rv;
 		}
 
@@ -2560,17 +2653,18 @@ channel_handler(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
 
 	if ((msg->addr.addr_type == IPMI_SYSTEM_INTERFACE_ADDR_TYPE)
 	    && (msg->msg.netfn == IPMI_NETFN_APP_RESPONSE)
-	    && (msg->msg.cmd == IPMI_GET_CHANNEL_INFO_CMD))
-	{
+	    && (msg->msg.cmd == IPMI_GET_CHANNEL_INFO_CMD)) {
 		/* It's the one we want */
 		if (msg->msg.data[0] != 0) {
 			/* Got an error from the channel, just go on. */
 
 			if (msg->msg.data[0] == IPMI_INVALID_COMMAND_ERR) {
-				/* If the MC does not support this
-				   command, that is legal.  We just
-				   assume it has one IPMB at channel
-				   zero. */
+				/*
+				 * If the MC does not support this
+				 * command, that is legal.  We just
+				 * assume it has one IPMB at channel
+				 * zero.
+				 */
 				intf->channels[0].medium
 					= IPMI_CHANNEL_MEDIUM_IPMB;
 				intf->channels[0].protocol
@@ -2591,7 +2685,7 @@ channel_handler(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
 		intf->channels[chan].medium = msg->msg.data[2] & 0x7f;
 		intf->channels[chan].protocol = msg->msg.data[3] & 0x1f;
 
-	next_channel:
+ next_channel:
 		intf->curr_channel++;
 		if (intf->curr_channel >= IPMI_MAX_CHANNELS)
 			wake_up(&intf->waitq);
@@ -2619,6 +2713,7 @@ void ipmi_poll_interface(ipmi_user_t user)
 	if (intf->handlers->poll)
 		intf->handlers->poll(intf->send_info);
 }
+EXPORT_SYMBOL(ipmi_poll_interface);
 
 int ipmi_register_smi(struct ipmi_smi_handlers *handlers,
 		      void		       *send_info,
@@ -2633,14 +2728,18 @@ int ipmi_register_smi(struct ipmi_smi_handlers *handlers,
 	ipmi_smi_t       tintf;
 	struct list_head *link;
 
-	/* Make sure the driver is actually initialized, this handles
-	   problems with initialization order. */
+	/*
+	 * Make sure the driver is actually initialized, this handles
+	 * problems with initialization order.
+	 */
 	if (!initialized) {
 		rv = ipmi_init_msghandler();
 		if (rv)
 			return rv;
-		/* The init code doesn't return an error if it was turned
-		   off, but it won't initialize.  Check that. */
+		/*
+		 * The init code doesn't return an error if it was turned
+		 * off, but it won't initialize.  Check that.
+		 */
 		if (!initialized)
 			return -ENODEV;
 	}
@@ -2688,8 +2787,9 @@ int ipmi_register_smi(struct ipmi_smi_handlers *handlers,
 	spin_lock_init(&intf->maintenance_mode_lock);
 	INIT_LIST_HEAD(&intf->cmd_rcvrs);
 	init_waitqueue_head(&intf->waitq);
+	for (i = 0; i < IPMI_NUM_STATS; i++)
+		atomic_set(&intf->stats[i], 0);
 
-	spin_lock_init(&intf->counter_lock);
 	intf->proc_dir = NULL;
 
 	mutex_lock(&smi_watchers_mutex);
@@ -2717,11 +2817,12 @@ int ipmi_register_smi(struct ipmi_smi_handlers *handlers,
 	get_guid(intf);
 
 	if ((intf->ipmi_version_major > 1)
-	    || ((intf->ipmi_version_major == 1)
-		&& (intf->ipmi_version_minor >= 5)))
-	{
-		/* Start scanning the channels to see what is
-		   available. */
+			|| ((intf->ipmi_version_major == 1)
+			    && (intf->ipmi_version_minor >= 5))) {
+		/*
+		 * Start scanning the channels to see what is
+		 * available.
+		 */
 		intf->null_user_handler = channel_handler;
 		intf->curr_channel = 0;
 		rv = send_channel_info_cmd(intf, 0);
@@ -2769,6 +2870,7 @@ int ipmi_register_smi(struct ipmi_smi_handlers *handlers,
 
 	return rv;
 }
+EXPORT_SYMBOL(ipmi_register_smi);
 
 static void cleanup_smi_msgs(ipmi_smi_t intf)
 {
@@ -2803,8 +2905,10 @@ int ipmi_unregister_smi(ipmi_smi_t intf)
 
 	remove_proc_entries(intf);
 
-	/* Call all the watcher interfaces to tell them that
-	   an interface is gone. */
+	/*
+	 * Call all the watcher interfaces to tell them that
+	 * an interface is gone.
+	 */
 	list_for_each_entry(w, &smi_watchers, link)
 		w->smi_gone(intf_num);
 	mutex_unlock(&smi_watchers_mutex);
@@ -2812,22 +2916,21 @@ int ipmi_unregister_smi(ipmi_smi_t intf)
 	kref_put(&intf->refcount, intf_free);
 	return 0;
 }
+EXPORT_SYMBOL(ipmi_unregister_smi);
 
 static int handle_ipmb_get_msg_rsp(ipmi_smi_t          intf,
 				   struct ipmi_smi_msg *msg)
 {
 	struct ipmi_ipmb_addr ipmb_addr;
 	struct ipmi_recv_msg  *recv_msg;
-	unsigned long         flags;
 
-	
-	/* This is 11, not 10, because the response must contain a
-	 * completion code. */
+	/*
+	 * This is 11, not 10, because the response must contain a
+	 * completion code.
+	 */
 	if (msg->rsp_size < 11) {
 		/* Message not big enough, just ignore it. */
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->invalid_ipmb_responses++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+		ipmi_inc_stat(intf, invalid_ipmb_responses);
 		return 0;
 	}
 
@@ -2841,37 +2944,38 @@ static int handle_ipmb_get_msg_rsp(ipmi_smi_t          intf,
 	ipmb_addr.channel = msg->rsp[3] & 0x0f;
 	ipmb_addr.lun = msg->rsp[7] & 3;
 
-	/* It's a response from a remote entity.  Look up the sequence
-	   number and handle the response. */
+	/*
+	 * It's a response from a remote entity.  Look up the sequence
+	 * number and handle the response.
+	 */
 	if (intf_find_seq(intf,
 			  msg->rsp[7] >> 2,
 			  msg->rsp[3] & 0x0f,
 			  msg->rsp[8],
 			  (msg->rsp[4] >> 2) & (~1),
 			  (struct ipmi_addr *) &(ipmb_addr),
-			  &recv_msg))
-	{
-		/* We were unable to find the sequence number,
-		   so just nuke the message. */
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->unhandled_ipmb_responses++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+			  &recv_msg)) {
+		/*
+		 * We were unable to find the sequence number,
+		 * so just nuke the message.
+		 */
+		ipmi_inc_stat(intf, unhandled_ipmb_responses);
 		return 0;
 	}
 
 	memcpy(recv_msg->msg_data,
 	       &(msg->rsp[9]),
 	       msg->rsp_size - 9);
-	/* THe other fields matched, so no need to set them, except
-           for netfn, which needs to be the response that was
-           returned, not the request value. */
+	/*
+	 * The other fields matched, so no need to set them, except
+	 * for netfn, which needs to be the response that was
+	 * returned, not the request value.
+	 */
 	recv_msg->msg.netfn = msg->rsp[4] >> 2;
 	recv_msg->msg.data = recv_msg->msg_data;
 	recv_msg->msg.data_len = msg->rsp_size - 10;
 	recv_msg->recv_type = IPMI_RESPONSE_RECV_TYPE;
-	spin_lock_irqsave(&intf->counter_lock, flags);
-	intf->handled_ipmb_responses++;
-	spin_unlock_irqrestore(&intf->counter_lock, flags);
+	ipmi_inc_stat(intf, handled_ipmb_responses);
 	deliver_response(recv_msg);
 
 	return 0;
@@ -2888,14 +2992,11 @@ static int handle_ipmb_get_msg_cmd(ipmi_smi_t          intf,
 	ipmi_user_t              user = NULL;
 	struct ipmi_ipmb_addr    *ipmb_addr;
 	struct ipmi_recv_msg     *recv_msg;
-	unsigned long            flags;
 	struct ipmi_smi_handlers *handlers;
 
 	if (msg->rsp_size < 10) {
 		/* Message not big enough, just ignore it. */
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->invalid_commands++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+		ipmi_inc_stat(intf, invalid_commands);
 		return 0;
 	}
 
@@ -2919,19 +3020,17 @@ static int handle_ipmb_get_msg_cmd(ipmi_smi_t          intf,
 
 	if (user == NULL) {
 		/* We didn't find a user, deliver an error response. */
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->unhandled_commands++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+		ipmi_inc_stat(intf, unhandled_commands);
 
 		msg->data[0] = (IPMI_NETFN_APP_REQUEST << 2);
 		msg->data[1] = IPMI_SEND_MSG_CMD;
 		msg->data[2] = msg->rsp[3];
 		msg->data[3] = msg->rsp[6];
-                msg->data[4] = ((netfn + 1) << 2) | (msg->rsp[7] & 0x3);
+		msg->data[4] = ((netfn + 1) << 2) | (msg->rsp[7] & 0x3);
 		msg->data[5] = ipmb_checksum(&(msg->data[3]), 2);
 		msg->data[6] = intf->channels[msg->rsp[3] & 0xf].address;
-                /* rqseq/lun */
-                msg->data[7] = (msg->rsp[7] & 0xfc) | (msg->rsp[4] & 0x3);
+		/* rqseq/lun */
+		msg->data[7] = (msg->rsp[7] & 0xfc) | (msg->rsp[4] & 0x3);
 		msg->data[8] = msg->rsp[8]; /* cmd */
 		msg->data[9] = IPMI_INVALID_CMD_COMPLETION_CODE;
 		msg->data[10] = ipmb_checksum(&(msg->data[6]), 4);
@@ -2950,23 +3049,25 @@ static int handle_ipmb_get_msg_cmd(ipmi_smi_t          intf,
 		handlers = intf->handlers;
 		if (handlers) {
 			handlers->sender(intf->send_info, msg, 0);
-			/* We used the message, so return the value
-			   that causes it to not be freed or
-			   queued. */
+			/*
+			 * We used the message, so return the value
+			 * that causes it to not be freed or
+			 * queued.
+			 */
 			rv = -1;
 		}
 		rcu_read_unlock();
 	} else {
 		/* Deliver the message to the user. */
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->handled_commands++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+		ipmi_inc_stat(intf, handled_commands);
 
 		recv_msg = ipmi_alloc_recv_msg();
 		if (!recv_msg) {
-			/* We couldn't allocate memory for the
-                           message, so requeue it for handling
-                           later. */
+			/*
+			 * We couldn't allocate memory for the
+			 * message, so requeue it for handling
+			 * later.
+			 */
 			rv = 1;
 			kref_put(&user->refcount, free_user);
 		} else {
@@ -2977,8 +3078,10 @@ static int handle_ipmb_get_msg_cmd(ipmi_smi_t          intf,
 			ipmb_addr->lun = msg->rsp[7] & 3;
 			ipmb_addr->channel = msg->rsp[3] & 0xf;
 
-			/* Extract the rest of the message information
-			   from the IPMB header.*/
+			/*
+			 * Extract the rest of the message information
+			 * from the IPMB header.
+			 */
 			recv_msg->user = user;
 			recv_msg->recv_type = IPMI_CMD_RECV_TYPE;
 			recv_msg->msgid = msg->rsp[7] >> 2;
@@ -2986,8 +3089,10 @@ static int handle_ipmb_get_msg_cmd(ipmi_smi_t          intf,
 			recv_msg->msg.cmd = msg->rsp[8];
 			recv_msg->msg.data = recv_msg->msg_data;
 
-			/* We chop off 10, not 9 bytes because the checksum
-			   at the end also needs to be removed. */
+			/*
+			 * We chop off 10, not 9 bytes because the checksum
+			 * at the end also needs to be removed.
+			 */
 			recv_msg->msg.data_len = msg->rsp_size - 10;
 			memcpy(recv_msg->msg_data,
 			       &(msg->rsp[9]),
@@ -3004,16 +3109,15 @@ static int handle_lan_get_msg_rsp(ipmi_smi_t          intf,
 {
 	struct ipmi_lan_addr  lan_addr;
 	struct ipmi_recv_msg  *recv_msg;
-	unsigned long         flags;
 
 
-	/* This is 13, not 12, because the response must contain a
-	 * completion code. */
+	/*
+	 * This is 13, not 12, because the response must contain a
+	 * completion code.
+	 */
 	if (msg->rsp_size < 13) {
 		/* Message not big enough, just ignore it. */
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->invalid_lan_responses++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+		ipmi_inc_stat(intf, invalid_lan_responses);
 		return 0;
 	}
 
@@ -3030,37 +3134,38 @@ static int handle_lan_get_msg_rsp(ipmi_smi_t          intf,
 	lan_addr.privilege = msg->rsp[3] >> 4;
 	lan_addr.lun = msg->rsp[9] & 3;
 
-	/* It's a response from a remote entity.  Look up the sequence
-	   number and handle the response. */
+	/*
+	 * It's a response from a remote entity.  Look up the sequence
+	 * number and handle the response.
+	 */
 	if (intf_find_seq(intf,
 			  msg->rsp[9] >> 2,
 			  msg->rsp[3] & 0x0f,
 			  msg->rsp[10],
 			  (msg->rsp[6] >> 2) & (~1),
 			  (struct ipmi_addr *) &(lan_addr),
-			  &recv_msg))
-	{
-		/* We were unable to find the sequence number,
-		   so just nuke the message. */
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->unhandled_lan_responses++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+			  &recv_msg)) {
+		/*
+		 * We were unable to find the sequence number,
+		 * so just nuke the message.
+		 */
+		ipmi_inc_stat(intf, unhandled_lan_responses);
 		return 0;
 	}
 
 	memcpy(recv_msg->msg_data,
 	       &(msg->rsp[11]),
 	       msg->rsp_size - 11);
-	/* The other fields matched, so no need to set them, except
-           for netfn, which needs to be the response that was
-           returned, not the request value. */
+	/*
+	 * The other fields matched, so no need to set them, except
+	 * for netfn, which needs to be the response that was
+	 * returned, not the request value.
+	 */
 	recv_msg->msg.netfn = msg->rsp[6] >> 2;
 	recv_msg->msg.data = recv_msg->msg_data;
 	recv_msg->msg.data_len = msg->rsp_size - 12;
 	recv_msg->recv_type = IPMI_RESPONSE_RECV_TYPE;
-	spin_lock_irqsave(&intf->counter_lock, flags);
-	intf->handled_lan_responses++;
-	spin_unlock_irqrestore(&intf->counter_lock, flags);
+	ipmi_inc_stat(intf, handled_lan_responses);
 	deliver_response(recv_msg);
 
 	return 0;
@@ -3077,13 +3182,10 @@ static int handle_lan_get_msg_cmd(ipmi_smi_t          intf,
 	ipmi_user_t              user = NULL;
 	struct ipmi_lan_addr     *lan_addr;
 	struct ipmi_recv_msg     *recv_msg;
-	unsigned long            flags;
 
 	if (msg->rsp_size < 12) {
 		/* Message not big enough, just ignore it. */
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->invalid_commands++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+		ipmi_inc_stat(intf, invalid_commands);
 		return 0;
 	}
 
@@ -3107,23 +3209,23 @@ static int handle_lan_get_msg_cmd(ipmi_smi_t          intf,
 
 	if (user == NULL) {
 		/* We didn't find a user, just give up. */
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->unhandled_commands++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+		ipmi_inc_stat(intf, unhandled_commands);
 
-		rv = 0; /* Don't do anything with these messages, just
-			   allow them to be freed. */
+		/*
+		 * Don't do anything with these messages, just allow
+		 * them to be freed.
+		 */
+		rv = 0;
 	} else {
 		/* Deliver the message to the user. */
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->handled_commands++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+		ipmi_inc_stat(intf, handled_commands);
 
 		recv_msg = ipmi_alloc_recv_msg();
 		if (!recv_msg) {
-			/* We couldn't allocate memory for the
-                           message, so requeue it for handling
-                           later. */
+			/*
+			 * We couldn't allocate memory for the
+			 * message, so requeue it for handling later.
+			 */
 			rv = 1;
 			kref_put(&user->refcount, free_user);
 		} else {
@@ -3137,8 +3239,10 @@ static int handle_lan_get_msg_cmd(ipmi_smi_t          intf,
 			lan_addr->channel = msg->rsp[3] & 0xf;
 			lan_addr->privilege = msg->rsp[3] >> 4;
 
-			/* Extract the rest of the message information
-			   from the IPMB header.*/
+			/*
+			 * Extract the rest of the message information
+			 * from the IPMB header.
+			 */
 			recv_msg->user = user;
 			recv_msg->recv_type = IPMI_CMD_RECV_TYPE;
 			recv_msg->msgid = msg->rsp[9] >> 2;
@@ -3146,8 +3250,10 @@ static int handle_lan_get_msg_cmd(ipmi_smi_t          intf,
 			recv_msg->msg.cmd = msg->rsp[10];
 			recv_msg->msg.data = recv_msg->msg_data;
 
-			/* We chop off 12, not 11 bytes because the checksum
-			   at the end also needs to be removed. */
+			/*
+			 * We chop off 12, not 11 bytes because the checksum
+			 * at the end also needs to be removed.
+			 */
 			recv_msg->msg.data_len = msg->rsp_size - 12;
 			memcpy(recv_msg->msg_data,
 			       &(msg->rsp[11]),
@@ -3163,7 +3269,7 @@ static void copy_event_into_recv_msg(struct ipmi_recv_msg *recv_msg,
 				     struct ipmi_smi_msg  *msg)
 {
 	struct ipmi_system_interface_addr *smi_addr;
-	
+
 	recv_msg->msgid = 0;
 	smi_addr = (struct ipmi_system_interface_addr *) &(recv_msg->addr);
 	smi_addr->addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
@@ -3189,9 +3295,7 @@ static int handle_read_event_rsp(ipmi_smi_t          intf,
 
 	if (msg->rsp_size < 19) {
 		/* Message is too small to be an IPMB event. */
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->invalid_events++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+		ipmi_inc_stat(intf, invalid_events);
 		return 0;
 	}
 
@@ -3204,12 +3308,12 @@ static int handle_read_event_rsp(ipmi_smi_t          intf,
 
 	spin_lock_irqsave(&intf->events_lock, flags);
 
-	spin_lock(&intf->counter_lock);
-	intf->events++;
-	spin_unlock(&intf->counter_lock);
+	ipmi_inc_stat(intf, events);
 
-	/* Allocate and fill in one message for every user that is getting
-	   events. */
+	/*
+	 * Allocate and fill in one message for every user that is
+	 * getting events.
+	 */
 	rcu_read_lock();
 	list_for_each_entry_rcu(user, &intf->users, link) {
 		if (!user->gets_events)
@@ -3223,9 +3327,11 @@ static int handle_read_event_rsp(ipmi_smi_t          intf,
 				list_del(&recv_msg->link);
 				ipmi_free_recv_msg(recv_msg);
 			}
-			/* We couldn't allocate memory for the
-                           message, so requeue it for handling
-                           later. */
+			/*
+			 * We couldn't allocate memory for the
+			 * message, so requeue it for handling
+			 * later.
+			 */
 			rv = 1;
 			goto out;
 		}
@@ -3246,13 +3352,17 @@ static int handle_read_event_rsp(ipmi_smi_t          intf,
 			deliver_response(recv_msg);
 		}
 	} else if (intf->waiting_events_count < MAX_EVENTS_IN_QUEUE) {
-		/* No one to receive the message, put it in queue if there's
-		   not already too many things in the queue. */
+		/*
+		 * No one to receive the message, put it in queue if there's
+		 * not already too many things in the queue.
+		 */
 		recv_msg = ipmi_alloc_recv_msg();
 		if (!recv_msg) {
-			/* We couldn't allocate memory for the
-                           message, so requeue it for handling
-                           later. */
+			/*
+			 * We couldn't allocate memory for the
+			 * message, so requeue it for handling
+			 * later.
+			 */
 			rv = 1;
 			goto out;
 		}
@@ -3260,11 +3370,14 @@ static int handle_read_event_rsp(ipmi_smi_t          intf,
 		copy_event_into_recv_msg(recv_msg, msg);
 		list_add_tail(&(recv_msg->link), &(intf->waiting_events));
 		intf->waiting_events_count++;
-	} else {
-		/* There's too many things in the queue, discard this
-		   message. */
-		printk(KERN_WARNING PFX "Event queue full, discarding an"
-		       " incoming event\n");
+	} else if (!intf->event_msg_printed) {
+		/*
+		 * There's too many things in the queue, discard this
+		 * message.
+		 */
+		printk(KERN_WARNING PFX "Event queue full, discarding"
+		       " incoming events\n");
+		intf->event_msg_printed = 1;
 	}
 
  out:
@@ -3277,16 +3390,15 @@ static int handle_bmc_rsp(ipmi_smi_t          intf,
 			  struct ipmi_smi_msg *msg)
 {
 	struct ipmi_recv_msg *recv_msg;
-	unsigned long        flags;
 	struct ipmi_user     *user;
 
 	recv_msg = (struct ipmi_recv_msg *) msg->user_data;
-	if (recv_msg == NULL)
-	{
-		printk(KERN_WARNING"IPMI message received with no owner. This\n"
-			"could be because of a malformed message, or\n"
-			"because of a hardware error.  Contact your\n"
-			"hardware vender for assistance\n");
+	if (recv_msg == NULL) {
+		printk(KERN_WARNING
+		       "IPMI message received with no owner. This\n"
+		       "could be because of a malformed message, or\n"
+		       "because of a hardware error.  Contact your\n"
+		       "hardware vender for assistance\n");
 		return 0;
 	}
 
@@ -3294,16 +3406,12 @@ static int handle_bmc_rsp(ipmi_smi_t          intf,
 	/* Make sure the user still exists. */
 	if (user && !user->valid) {
 		/* The user for the message went away, so give up. */
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->unhandled_local_responses++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+		ipmi_inc_stat(intf, unhandled_local_responses);
 		ipmi_free_recv_msg(recv_msg);
 	} else {
 		struct ipmi_system_interface_addr *smi_addr;
 
-		spin_lock_irqsave(&intf->counter_lock, flags);
-		intf->handled_local_responses++;
-		spin_unlock_irqrestore(&intf->counter_lock, flags);
+		ipmi_inc_stat(intf, handled_local_responses);
 		recv_msg->recv_type = IPMI_RESPONSE_RECV_TYPE;
 		recv_msg->msgid = msg->msgid;
 		smi_addr = ((struct ipmi_system_interface_addr *)
@@ -3324,9 +3432,11 @@ static int handle_bmc_rsp(ipmi_smi_t          intf,
 	return 0;
 }
 
-/* Handle a new message.  Return 1 if the message should be requeued,
-   0 if the message should be freed, or -1 if the message should not
-   be freed or requeued. */
+/*
+ * Handle a new message.  Return 1 if the message should be requeued,
+ * 0 if the message should be freed, or -1 if the message should not
+ * be freed or requeued.
+ */
 static int handle_new_recv_msg(ipmi_smi_t          intf,
 			       struct ipmi_smi_msg *msg)
 {
@@ -3351,10 +3461,12 @@ static int handle_new_recv_msg(ipmi_smi_t          intf,
 		msg->rsp[1] = msg->data[1];
 		msg->rsp[2] = IPMI_ERR_UNSPECIFIED;
 		msg->rsp_size = 3;
-	} else if (((msg->rsp[0] >> 2) != ((msg->data[0] >> 2) | 1))/* Netfn */
-		   || (msg->rsp[1] != msg->data[1]))		  /* Command */
-	{
-		/* The response is not even marginally correct. */
+	} else if (((msg->rsp[0] >> 2) != ((msg->data[0] >> 2) | 1))
+		   || (msg->rsp[1] != msg->data[1])) {
+		/*
+		 * The NetFN and Command in the response is not even
+		 * marginally correct.
+		 */
 		printk(KERN_WARNING PFX "BMC returned incorrect response,"
 		       " expected netfn %x cmd %x, got netfn %x cmd %x\n",
 		       (msg->data[0] >> 2) | 1, msg->data[1],
@@ -3369,10 +3481,11 @@ static int handle_new_recv_msg(ipmi_smi_t          intf,
 
 	if ((msg->rsp[0] == ((IPMI_NETFN_APP_REQUEST|1) << 2))
 	    && (msg->rsp[1] == IPMI_SEND_MSG_CMD)
-	    && (msg->user_data != NULL))
-	{
-		/* It's a response to a response we sent.  For this we
-		   deliver a send message response to the user. */
+	    && (msg->user_data != NULL)) {
+		/*
+		 * It's a response to a response we sent.  For this we
+		 * deliver a send message response to the user.
+		 */
 		struct ipmi_recv_msg     *recv_msg = msg->user_data;
 
 		requeue = 0;
@@ -3398,8 +3511,7 @@ static int handle_new_recv_msg(ipmi_smi_t          intf,
 		recv_msg->msg_data[0] = msg->rsp[2];
 		deliver_response(recv_msg);
 	} else if ((msg->rsp[0] == ((IPMI_NETFN_APP_REQUEST|1) << 2))
-		   && (msg->rsp[1] == IPMI_GET_MSG_CMD))
-	{
+		   && (msg->rsp[1] == IPMI_GET_MSG_CMD)) {
 		/* It's from the receive queue. */
 		chan = msg->rsp[3] & 0xf;
 		if (chan >= IPMI_MAX_CHANNELS) {
@@ -3411,12 +3523,16 @@ static int handle_new_recv_msg(ipmi_smi_t          intf,
 		switch (intf->channels[chan].medium) {
 		case IPMI_CHANNEL_MEDIUM_IPMB:
 			if (msg->rsp[4] & 0x04) {
-				/* It's a response, so find the
-				   requesting message and send it up. */
+				/*
+				 * It's a response, so find the
+				 * requesting message and send it up.
+				 */
 				requeue = handle_ipmb_get_msg_rsp(intf, msg);
 			} else {
-				/* It's a command to the SMS from some other
-				   entity.  Handle that. */
+				/*
+				 * It's a command to the SMS from some other
+				 * entity.  Handle that.
+				 */
 				requeue = handle_ipmb_get_msg_cmd(intf, msg);
 			}
 			break;
@@ -3424,25 +3540,30 @@ static int handle_new_recv_msg(ipmi_smi_t          intf,
 		case IPMI_CHANNEL_MEDIUM_8023LAN:
 		case IPMI_CHANNEL_MEDIUM_ASYNC:
 			if (msg->rsp[6] & 0x04) {
-				/* It's a response, so find the
-				   requesting message and send it up. */
+				/*
+				 * It's a response, so find the
+				 * requesting message and send it up.
+				 */
 				requeue = handle_lan_get_msg_rsp(intf, msg);
 			} else {
-				/* It's a command to the SMS from some other
-				   entity.  Handle that. */
+				/*
+				 * It's a command to the SMS from some other
+				 * entity.  Handle that.
+				 */
 				requeue = handle_lan_get_msg_cmd(intf, msg);
 			}
 			break;
 
 		default:
-			/* We don't handle the channel type, so just
-			 * free the message. */
+			/*
+			 * We don't handle the channel type, so just
+			 * free the message.
+			 */
 			requeue = 0;
 		}
 
 	} else if ((msg->rsp[0] == ((IPMI_NETFN_APP_REQUEST|1) << 2))
-		   && (msg->rsp[1] == IPMI_READ_EVENT_MSG_BUFFER_CMD))
-	{
+		   && (msg->rsp[1] == IPMI_READ_EVENT_MSG_BUFFER_CMD)) {
 		/* It's an asyncronous event. */
 		requeue = handle_read_event_rsp(intf, msg);
 	} else {
@@ -3458,71 +3579,82 @@ static int handle_new_recv_msg(ipmi_smi_t          intf,
 void ipmi_smi_msg_received(ipmi_smi_t          intf,
 			   struct ipmi_smi_msg *msg)
 {
-	unsigned long flags;
+	unsigned long flags = 0; /* keep us warning-free. */
 	int           rv;
+	int           run_to_completion;
 
 
 	if ((msg->data_size >= 2)
 	    && (msg->data[0] == (IPMI_NETFN_APP_REQUEST << 2))
 	    && (msg->data[1] == IPMI_SEND_MSG_CMD)
-	    && (msg->user_data == NULL))
-	{
-		/* This is the local response to a command send, start
-                   the timer for these.  The user_data will not be
-                   NULL if this is a response send, and we will let
-                   response sends just go through. */
-
-		/* Check for errors, if we get certain errors (ones
-                   that mean basically we can try again later), we
-                   ignore them and start the timer.  Otherwise we
-                   report the error immediately. */
+	    && (msg->user_data == NULL)) {
+		/*
+		 * This is the local response to a command send, start
+		 * the timer for these.  The user_data will not be
+		 * NULL if this is a response send, and we will let
+		 * response sends just go through.
+		 */
+
+		/*
+		 * Check for errors, if we get certain errors (ones
+		 * that mean basically we can try again later), we
+		 * ignore them and start the timer.  Otherwise we
+		 * report the error immediately.
+		 */
 		if ((msg->rsp_size >= 3) && (msg->rsp[2] != 0)
 		    && (msg->rsp[2] != IPMI_NODE_BUSY_ERR)
 		    && (msg->rsp[2] != IPMI_LOST_ARBITRATION_ERR)
 		    && (msg->rsp[2] != IPMI_BUS_ERR)
-		    && (msg->rsp[2] != IPMI_NAK_ON_WRITE_ERR))
-		{
+		    && (msg->rsp[2] != IPMI_NAK_ON_WRITE_ERR)) {
 			int chan = msg->rsp[3] & 0xf;
 
 			/* Got an error sending the message, handle it. */
-			spin_lock_irqsave(&intf->counter_lock, flags);
 			if (chan >= IPMI_MAX_CHANNELS)
 				; /* This shouldn't happen */
 			else if ((intf->channels[chan].medium
 				  == IPMI_CHANNEL_MEDIUM_8023LAN)
 				 || (intf->channels[chan].medium
 				     == IPMI_CHANNEL_MEDIUM_ASYNC))
-				intf->sent_lan_command_errs++;
+				ipmi_inc_stat(intf, sent_lan_command_errs);
 			else
-				intf->sent_ipmb_command_errs++;
-			spin_unlock_irqrestore(&intf->counter_lock, flags);
+				ipmi_inc_stat(intf, sent_ipmb_command_errs);
 			intf_err_seq(intf, msg->msgid, msg->rsp[2]);
-		} else {
+		} else
 			/* The message was sent, start the timer. */
 			intf_start_seq_timer(intf, msg->msgid);
-		}
 
 		ipmi_free_smi_msg(msg);
 		goto out;
 	}
 
-	/* To preserve message order, if the list is not empty, we
-           tack this message onto the end of the list. */
-	spin_lock_irqsave(&intf->waiting_msgs_lock, flags);
+	/*
+	 * To preserve message order, if the list is not empty, we
+	 * tack this message onto the end of the list.
+	 */
+	run_to_completion = intf->run_to_completion;
+	if (!run_to_completion)
+		spin_lock_irqsave(&intf->waiting_msgs_lock, flags);
 	if (!list_empty(&intf->waiting_msgs)) {
 		list_add_tail(&msg->link, &intf->waiting_msgs);
-		spin_unlock_irqrestore(&intf->waiting_msgs_lock, flags);
+		if (!run_to_completion)
+			spin_unlock_irqrestore(&intf->waiting_msgs_lock, flags);
 		goto out;
 	}
-	spin_unlock_irqrestore(&intf->waiting_msgs_lock, flags);
-		
+	if (!run_to_completion)
+		spin_unlock_irqrestore(&intf->waiting_msgs_lock, flags);
+
 	rv = handle_new_recv_msg(intf, msg);
 	if (rv > 0) {
-		/* Could not handle the message now, just add it to a
-                   list to handle later. */
-		spin_lock_irqsave(&intf->waiting_msgs_lock, flags);
+		/*
+		 * Could not handle the message now, just add it to a
+		 * list to handle later.
+		 */
+		run_to_completion = intf->run_to_completion;
+		if (!run_to_completion)
+			spin_lock_irqsave(&intf->waiting_msgs_lock, flags);
 		list_add_tail(&msg->link, &intf->waiting_msgs);
-		spin_unlock_irqrestore(&intf->waiting_msgs_lock, flags);
+		if (!run_to_completion)
+			spin_unlock_irqrestore(&intf->waiting_msgs_lock, flags);
 	} else if (rv == 0) {
 		ipmi_free_smi_msg(msg);
 	}
@@ -3530,6 +3662,7 @@ void ipmi_smi_msg_received(ipmi_smi_t          intf,
  out:
 	return;
 }
+EXPORT_SYMBOL(ipmi_smi_msg_received);
 
 void ipmi_smi_watchdog_pretimeout(ipmi_smi_t intf)
 {
@@ -3544,7 +3677,7 @@ void ipmi_smi_watchdog_pretimeout(ipmi_smi_t intf)
 	}
 	rcu_read_unlock();
 }
-
+EXPORT_SYMBOL(ipmi_smi_watchdog_pretimeout);
 
 static struct ipmi_smi_msg *
 smi_from_recv_msg(ipmi_smi_t intf, struct ipmi_recv_msg *recv_msg,
@@ -3552,14 +3685,16 @@ smi_from_recv_msg(ipmi_smi_t intf, struct ipmi_recv_msg *recv_msg,
 {
 	struct ipmi_smi_msg *smi_msg = ipmi_alloc_smi_msg();
 	if (!smi_msg)
-		/* If we can't allocate the message, then just return, we
-		   get 4 retries, so this should be ok. */
+		/*
+		 * If we can't allocate the message, then just return, we
+		 * get 4 retries, so this should be ok.
+		 */
 		return NULL;
 
 	memcpy(smi_msg->data, recv_msg->msg.data, recv_msg->msg.data_len);
 	smi_msg->data_size = recv_msg->msg.data_len;
 	smi_msg->msgid = STORE_SEQ_IN_MSGID(seq, seqid);
-		
+
 #ifdef DEBUG_MSGING
 	{
 		int m;
@@ -3594,28 +3729,26 @@ static void check_msg_timeout(ipmi_smi_t intf, struct seq_table *ent,
 		ent->inuse = 0;
 		msg = ent->recv_msg;
 		list_add_tail(&msg->link, timeouts);
-		spin_lock(&intf->counter_lock);
 		if (ent->broadcast)
-			intf->timed_out_ipmb_broadcasts++;
+			ipmi_inc_stat(intf, timed_out_ipmb_broadcasts);
 		else if (ent->recv_msg->addr.addr_type == IPMI_LAN_ADDR_TYPE)
-			intf->timed_out_lan_commands++;
+			ipmi_inc_stat(intf, timed_out_lan_commands);
 		else
-			intf->timed_out_ipmb_commands++;
-		spin_unlock(&intf->counter_lock);
+			ipmi_inc_stat(intf, timed_out_ipmb_commands);
 	} else {
 		struct ipmi_smi_msg *smi_msg;
 		/* More retries, send again. */
 
-		/* Start with the max timer, set to normal
-		   timer after the message is sent. */
+		/*
+		 * Start with the max timer, set to normal timer after
+		 * the message is sent.
+		 */
 		ent->timeout = MAX_MSG_TIMEOUT;
 		ent->retries_left--;
-		spin_lock(&intf->counter_lock);
 		if (ent->recv_msg->addr.addr_type == IPMI_LAN_ADDR_TYPE)
-			intf->retransmitted_lan_commands++;
+			ipmi_inc_stat(intf, retransmitted_lan_commands);
 		else
-			intf->retransmitted_ipmb_commands++;
-		spin_unlock(&intf->counter_lock);
+			ipmi_inc_stat(intf, retransmitted_ipmb_commands);
 
 		smi_msg = smi_from_recv_msg(intf, ent->recv_msg, slot,
 					    ent->seqid);
@@ -3624,11 +3757,13 @@ static void check_msg_timeout(ipmi_smi_t intf, struct seq_table *ent,
 
 		spin_unlock_irqrestore(&intf->seq_lock, *flags);
 
-		/* Send the new message.  We send with a zero
-		 * priority.  It timed out, I doubt time is
-		 * that critical now, and high priority
-		 * messages are really only for messages to the
-		 * local MC, which don't get resent. */
+		/*
+		 * Send the new message.  We send with a zero
+		 * priority.  It timed out, I doubt time is that
+		 * critical now, and high priority messages are really
+		 * only for messages to the local MC, which don't get
+		 * resent.
+		 */
 		handlers = intf->handlers;
 		if (handlers)
 			intf->handlers->sender(intf->send_info,
@@ -3659,16 +3794,20 @@ static void ipmi_timeout_handler(long timeout_period)
 				list_del(&smi_msg->link);
 				ipmi_free_smi_msg(smi_msg);
 			} else {
-				/* To preserve message order, quit if we
-				   can't handle a message. */
+				/*
+				 * To preserve message order, quit if we
+				 * can't handle a message.
+				 */
 				break;
 			}
 		}
 		spin_unlock_irqrestore(&intf->waiting_msgs_lock, flags);
 
-		/* Go through the seq table and find any messages that
-		   have timed out, putting them in the timeouts
-		   list. */
+		/*
+		 * Go through the seq table and find any messages that
+		 * have timed out, putting them in the timeouts
+		 * list.
+		 */
 		INIT_LIST_HEAD(&timeouts);
 		spin_lock_irqsave(&intf->seq_lock, flags);
 		for (i = 0; i < IPMI_IPMB_NUM_SEQ; i++)
@@ -3694,8 +3833,7 @@ static void ipmi_timeout_handler(long timeout_period)
 				intf->auto_maintenance_timeout
 					-= timeout_period;
 				if (!intf->maintenance_mode
-				    && (intf->auto_maintenance_timeout <= 0))
-				{
+				    && (intf->auto_maintenance_timeout <= 0)) {
 					intf->maintenance_mode_enable = 0;
 					maintenance_mode_update(intf);
 				}
@@ -3713,8 +3851,10 @@ static void ipmi_request_event(void)
 	struct ipmi_smi_handlers *handlers;
 
 	rcu_read_lock();
-	/* Called from the timer, no need to check if handlers is
-	 * valid. */
+	/*
+	 * Called from the timer, no need to check if handlers is
+	 * valid.
+	 */
 	list_for_each_entry_rcu(intf, &ipmi_interfaces, link) {
 		/* No event requests when in maintenance mode. */
 		if (intf->maintenance_mode_enable)
@@ -3735,10 +3875,12 @@ static struct timer_list ipmi_timer;
 /* How many jiffies does it take to get to the timeout time. */
 #define IPMI_TIMEOUT_JIFFIES	((IPMI_TIMEOUT_TIME * HZ) / 1000)
 
-/* Request events from the queue every second (this is the number of
-   IPMI_TIMEOUT_TIMES between event requests).  Hopefully, in the
-   future, IPMI will add a way to know immediately if an event is in
-   the queue and this silliness can go away. */
+/*
+ * Request events from the queue every second (this is the number of
+ * IPMI_TIMEOUT_TIMES between event requests).  Hopefully, in the
+ * future, IPMI will add a way to know immediately if an event is in
+ * the queue and this silliness can go away.
+ */
 #define IPMI_REQUEST_EV_TIME	(1000 / (IPMI_TIMEOUT_TIME))
 
 static atomic_t stop_operation;
@@ -3782,6 +3924,7 @@ struct ipmi_smi_msg *ipmi_alloc_smi_msg(void)
 	}
 	return rv;
 }
+EXPORT_SYMBOL(ipmi_alloc_smi_msg);
 
 static void free_recv_msg(struct ipmi_recv_msg *msg)
 {
@@ -3789,7 +3932,7 @@ static void free_recv_msg(struct ipmi_recv_msg *msg)
 	kfree(msg);
 }
 
-struct ipmi_recv_msg *ipmi_alloc_recv_msg(void)
+static struct ipmi_recv_msg *ipmi_alloc_recv_msg(void)
 {
 	struct ipmi_recv_msg *rv;
 
@@ -3808,6 +3951,7 @@ void ipmi_free_recv_msg(struct ipmi_recv_msg *msg)
 		kref_put(&msg->user->refcount, free_user);
 	msg->done(msg);
 }
+EXPORT_SYMBOL(ipmi_free_recv_msg);
 
 #ifdef CONFIG_IPMI_PANIC_EVENT
 
@@ -3825,8 +3969,7 @@ static void event_receiver_fetcher(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
 	if ((msg->addr.addr_type == IPMI_SYSTEM_INTERFACE_ADDR_TYPE)
 	    && (msg->msg.netfn == IPMI_NETFN_SENSOR_EVENT_RESPONSE)
 	    && (msg->msg.cmd == IPMI_GET_EVENT_RECEIVER_CMD)
-	    && (msg->msg.data[0] == IPMI_CC_NO_ERROR))
-	{
+	    && (msg->msg.data[0] == IPMI_CC_NO_ERROR)) {
 		/* A get event receiver command, save it. */
 		intf->event_receiver = msg->msg.data[1];
 		intf->event_receiver_lun = msg->msg.data[2] & 0x3;
@@ -3838,10 +3981,11 @@ static void device_id_fetcher(ipmi_smi_t intf, struct ipmi_recv_msg *msg)
 	if ((msg->addr.addr_type == IPMI_SYSTEM_INTERFACE_ADDR_TYPE)
 	    && (msg->msg.netfn == IPMI_NETFN_APP_RESPONSE)
 	    && (msg->msg.cmd == IPMI_GET_DEVICE_ID_CMD)
-	    && (msg->msg.data[0] == IPMI_CC_NO_ERROR))
-	{
-		/* A get device id command, save if we are an event
-		   receiver or generator. */
+	    && (msg->msg.data[0] == IPMI_CC_NO_ERROR)) {
+		/*
+		 * A get device id command, save if we are an event
+		 * receiver or generator.
+		 */
 		intf->local_sel_device = (msg->msg.data[6] >> 2) & 1;
 		intf->local_event_generator = (msg->msg.data[6] >> 5) & 1;
 	}
@@ -3874,8 +4018,10 @@ static void send_panic_events(char *str)
 	data[4] = 0x6f; /* Sensor specific, IPMI table 36-1 */
 	data[5] = 0xa1; /* Runtime stop OEM bytes 2 & 3. */
 
-	/* Put a few breadcrumbs in.  Hopefully later we can add more things
-	   to make the panic events more useful. */
+	/*
+	 * Put a few breadcrumbs in.  Hopefully later we can add more things
+	 * to make the panic events more useful.
+	 */
 	if (str) {
 		data[3] = str[0];
 		data[6] = str[1];
@@ -3891,6 +4037,7 @@ static void send_panic_events(char *str)
 			/* Interface is not ready. */
 			continue;
 
+		intf->run_to_completion = 1;
 		/* Send the event announcing the panic. */
 		intf->handlers->set_run_to_completion(intf->send_info, 1);
 		i_ipmi_request(NULL,
@@ -3908,9 +4055,11 @@ static void send_panic_events(char *str)
 	}
 
 #ifdef CONFIG_IPMI_PANIC_STRING
-	/* On every interface, dump a bunch of OEM event holding the
-	   string. */
-	if (!str) 
+	/*
+	 * On every interface, dump a bunch of OEM event holding the
+	 * string.
+	 */
+	if (!str)
 		return;
 
 	/* For every registered interface, send the event. */
@@ -3931,11 +4080,13 @@ static void send_panic_events(char *str)
 		 */
 		smp_rmb();
 
-		/* First job here is to figure out where to send the
-		   OEM events.  There's no way in IPMI to send OEM
-		   events using an event send command, so we have to
-		   find the SEL to put them in and stick them in
-		   there. */
+		/*
+		 * First job here is to figure out where to send the
+		 * OEM events.  There's no way in IPMI to send OEM
+		 * events using an event send command, so we have to
+		 * find the SEL to put them in and stick them in
+		 * there.
+		 */
 
 		/* Get capabilities from the get device id. */
 		intf->local_sel_device = 0;
@@ -3983,24 +4134,29 @@ static void send_panic_events(char *str)
 		}
 		intf->null_user_handler = NULL;
 
-		/* Validate the event receiver.  The low bit must not
-		   be 1 (it must be a valid IPMB address), it cannot
-		   be zero, and it must not be my address. */
-                if (((intf->event_receiver & 1) == 0)
+		/*
+		 * Validate the event receiver.  The low bit must not
+		 * be 1 (it must be a valid IPMB address), it cannot
+		 * be zero, and it must not be my address.
+		 */
+		if (((intf->event_receiver & 1) == 0)
 		    && (intf->event_receiver != 0)
-		    && (intf->event_receiver != intf->channels[0].address))
-		{
-			/* The event receiver is valid, send an IPMB
-			   message. */
+		    && (intf->event_receiver != intf->channels[0].address)) {
+			/*
+			 * The event receiver is valid, send an IPMB
+			 * message.
+			 */
 			ipmb = (struct ipmi_ipmb_addr *) &addr;
 			ipmb->addr_type = IPMI_IPMB_ADDR_TYPE;
 			ipmb->channel = 0; /* FIXME - is this right? */
 			ipmb->lun = intf->event_receiver_lun;
 			ipmb->slave_addr = intf->event_receiver;
 		} else if (intf->local_sel_device) {
-			/* The event receiver was not valid (or was
-			   me), but I am an SEL device, just dump it
-			   in my SEL. */
+			/*
+			 * The event receiver was not valid (or was
+			 * me), but I am an SEL device, just dump it
+			 * in my SEL.
+			 */
 			si = (struct ipmi_system_interface_addr *) &addr;
 			si->addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
 			si->channel = IPMI_BMC_CHANNEL;
@@ -4008,7 +4164,6 @@ static void send_panic_events(char *str)
 		} else
 			continue; /* No where to send the event. */
 
-		
 		msg.netfn = IPMI_NETFN_STORAGE_REQUEST; /* Storage. */
 		msg.cmd = IPMI_ADD_SEL_ENTRY_CMD;
 		msg.data = data;
@@ -4025,8 +4180,10 @@ static void send_panic_events(char *str)
 			data[2] = 0xf0; /* OEM event without timestamp. */
 			data[3] = intf->channels[0].address;
 			data[4] = j++; /* sequence # */
-			/* Always give 11 bytes, so strncpy will fill
-			   it with zeroes for me. */
+			/*
+			 * Always give 11 bytes, so strncpy will fill
+			 * it with zeroes for me.
+			 */
 			strncpy(data+5, p, 11);
 			p += size;
 
@@ -4043,7 +4200,7 @@ static void send_panic_events(char *str)
 				       intf->channels[0].lun,
 				       0, 1); /* no retry, and no wait. */
 		}
-	}	
+	}
 #endif /* CONFIG_IPMI_PANIC_STRING */
 }
 #endif /* CONFIG_IPMI_PANIC_EVENT */
@@ -4052,7 +4209,7 @@ static int has_panicked;
 
 static int panic_event(struct notifier_block *this,
 		       unsigned long         event,
-                       void                  *ptr)
+		       void                  *ptr)
 {
 	ipmi_smi_t intf;
 
@@ -4066,6 +4223,7 @@ static int panic_event(struct notifier_block *this,
 			/* Interface is not ready. */
 			continue;
 
+		intf->run_to_completion = 1;
 		intf->handlers->set_run_to_completion(intf->send_info, 1);
 	}
 
@@ -4133,11 +4291,16 @@ static __exit void cleanup_ipmi(void)
 
 	atomic_notifier_chain_unregister(&panic_notifier_list, &panic_block);
 
-	/* This can't be called if any interfaces exist, so no worry about
-	   shutting down the interfaces. */
+	/*
+	 * This can't be called if any interfaces exist, so no worry
+	 * about shutting down the interfaces.
+	 */
 
-	/* Tell the timer to stop, then wait for it to stop.  This avoids
-	   problems with race conditions removing the timer here. */
+	/*
+	 * Tell the timer to stop, then wait for it to stop.  This
+	 * avoids problems with race conditions removing the timer
+	 * here.
+	 */
 	atomic_inc(&stop_operation);
 	del_timer_sync(&ipmi_timer);
 
@@ -4164,31 +4327,6 @@ module_exit(cleanup_ipmi);
 module_init(ipmi_init_msghandler_mod);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Corey Minyard <minyard@mvista.com>");
-MODULE_DESCRIPTION("Incoming and outgoing message routing for an IPMI interface.");
+MODULE_DESCRIPTION("Incoming and outgoing message routing for an IPMI"
+		   " interface.");
 MODULE_VERSION(IPMI_DRIVER_VERSION);
-
-EXPORT_SYMBOL(ipmi_create_user);
-EXPORT_SYMBOL(ipmi_destroy_user);
-EXPORT_SYMBOL(ipmi_get_version);
-EXPORT_SYMBOL(ipmi_request_settime);
-EXPORT_SYMBOL(ipmi_request_supply_msgs);
-EXPORT_SYMBOL(ipmi_poll_interface);
-EXPORT_SYMBOL(ipmi_register_smi);
-EXPORT_SYMBOL(ipmi_unregister_smi);
-EXPORT_SYMBOL(ipmi_register_for_cmd);
-EXPORT_SYMBOL(ipmi_unregister_for_cmd);
-EXPORT_SYMBOL(ipmi_smi_msg_received);
-EXPORT_SYMBOL(ipmi_smi_watchdog_pretimeout);
-EXPORT_SYMBOL(ipmi_alloc_smi_msg);
-EXPORT_SYMBOL(ipmi_addr_length);
-EXPORT_SYMBOL(ipmi_validate_addr);
-EXPORT_SYMBOL(ipmi_set_gets_events);
-EXPORT_SYMBOL(ipmi_smi_watcher_register);
-EXPORT_SYMBOL(ipmi_smi_watcher_unregister);
-EXPORT_SYMBOL(ipmi_set_my_address);
-EXPORT_SYMBOL(ipmi_get_my_address);
-EXPORT_SYMBOL(ipmi_set_my_LUN);
-EXPORT_SYMBOL(ipmi_get_my_LUN);
-EXPORT_SYMBOL(ipmi_smi_add_proc_entry);
-EXPORT_SYMBOL(ipmi_user_set_run_to_completion);
-EXPORT_SYMBOL(ipmi_free_recv_msg);
diff --git a/trunk/drivers/char/ipmi/ipmi_poweroff.c b/trunk/drivers/char/ipmi/ipmi_poweroff.c
index b86186de7f07..a261bd735dfb 100644
--- a/trunk/drivers/char/ipmi/ipmi_poweroff.c
+++ b/trunk/drivers/char/ipmi/ipmi_poweroff.c
@@ -87,7 +87,10 @@ MODULE_PARM_DESC(ifnum_to_use, "The interface number to use for the watchdog "
 
 /* parameter definition to allow user to flag power cycle */
 module_param(poweroff_powercycle, int, 0644);
-MODULE_PARM_DESC(poweroff_powercycle, " Set to non-zero to enable power cycle instead of power down. Power cycle is contingent on hardware support, otherwise it defaults back to power down.");
+MODULE_PARM_DESC(poweroff_powercycle,
+		 " Set to non-zero to enable power cycle instead of power"
+		 " down. Power cycle is contingent on hardware support,"
+		 " otherwise it defaults back to power down.");
 
 /* Stuff from the get device id command. */
 static unsigned int mfg_id;
@@ -95,22 +98,25 @@ static unsigned int prod_id;
 static unsigned char capabilities;
 static unsigned char ipmi_version;
 
-/* We use our own messages for this operation, we don't let the system
-   allocate them, since we may be in a panic situation.  The whole
-   thing is single-threaded, anyway, so multiple messages are not
-   required. */
+/*
+ * We use our own messages for this operation, we don't let the system
+ * allocate them, since we may be in a panic situation.  The whole
+ * thing is single-threaded, anyway, so multiple messages are not
+ * required.
+ */
+static atomic_t dummy_count = ATOMIC_INIT(0);
 static void dummy_smi_free(struct ipmi_smi_msg *msg)
 {
+	atomic_dec(&dummy_count);
 }
 static void dummy_recv_free(struct ipmi_recv_msg *msg)
 {
+	atomic_dec(&dummy_count);
 }
-static struct ipmi_smi_msg halt_smi_msg =
-{
+static struct ipmi_smi_msg halt_smi_msg = {
 	.done = dummy_smi_free
 };
-static struct ipmi_recv_msg halt_recv_msg =
-{
+static struct ipmi_recv_msg halt_recv_msg = {
 	.done = dummy_recv_free
 };
 
@@ -127,8 +133,7 @@ static void receive_handler(struct ipmi_recv_msg *recv_msg, void *handler_data)
 		complete(comp);
 }
 
-static struct ipmi_user_hndl ipmi_poweroff_handler =
-{
+static struct ipmi_user_hndl ipmi_poweroff_handler = {
 	.ipmi_recv_hndl = receive_handler
 };
 
@@ -152,17 +157,28 @@ static int ipmi_request_wait_for_response(ipmi_user_t            user,
 	return halt_recv_msg.msg.data[0];
 }
 
-/* We are in run-to-completion mode, no completion is desired. */
+/* Wait for message to complete, spinning. */
 static int ipmi_request_in_rc_mode(ipmi_user_t            user,
 				   struct ipmi_addr       *addr,
 				   struct kernel_ipmi_msg *send_msg)
 {
 	int rv;
 
+	atomic_set(&dummy_count, 2);
 	rv = ipmi_request_supply_msgs(user, addr, 0, send_msg, NULL,
 				      &halt_smi_msg, &halt_recv_msg, 0);
-	if (rv)
+	if (rv) {
+		atomic_set(&dummy_count, 0);
 		return rv;
+	}
+
+	/*
+	 * Spin until our message is done.
+	 */
+	while (atomic_read(&dummy_count) > 0) {
+		ipmi_poll_interface(user);
+		cpu_relax();
+	}
 
 	return halt_recv_msg.msg.data[0];
 }
@@ -184,47 +200,47 @@ static int ipmi_request_in_rc_mode(ipmi_user_t            user,
 
 static void (*atca_oem_poweroff_hook)(ipmi_user_t user);
 
-static void pps_poweroff_atca (ipmi_user_t user)
+static void pps_poweroff_atca(ipmi_user_t user)
 {
-        struct ipmi_system_interface_addr smi_addr;
-        struct kernel_ipmi_msg            send_msg;
-        int                               rv;
-        /*
-         * Configure IPMI address for local access
-         */
-        smi_addr.addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
-        smi_addr.channel = IPMI_BMC_CHANNEL;
-        smi_addr.lun = 0;
-
-        printk(KERN_INFO PFX "PPS powerdown hook used");
-
-        send_msg.netfn = IPMI_NETFN_OEM;
-        send_msg.cmd = IPMI_ATCA_PPS_GRACEFUL_RESTART;
-        send_msg.data = IPMI_ATCA_PPS_IANA;
-        send_msg.data_len = 3;
-        rv = ipmi_request_in_rc_mode(user,
-                                  (struct ipmi_addr *) &smi_addr,
-                                   &send_msg);
-        if (rv && rv != IPMI_UNKNOWN_ERR_COMPLETION_CODE) {
-                printk(KERN_ERR PFX "Unable to send ATCA ,"
-                       " IPMI error 0x%x\n", rv);
-        }
+	struct ipmi_system_interface_addr smi_addr;
+	struct kernel_ipmi_msg            send_msg;
+	int                               rv;
+	/*
+	 * Configure IPMI address for local access
+	 */
+	smi_addr.addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
+	smi_addr.channel = IPMI_BMC_CHANNEL;
+	smi_addr.lun = 0;
+
+	printk(KERN_INFO PFX "PPS powerdown hook used");
+
+	send_msg.netfn = IPMI_NETFN_OEM;
+	send_msg.cmd = IPMI_ATCA_PPS_GRACEFUL_RESTART;
+	send_msg.data = IPMI_ATCA_PPS_IANA;
+	send_msg.data_len = 3;
+	rv = ipmi_request_in_rc_mode(user,
+				     (struct ipmi_addr *) &smi_addr,
+				     &send_msg);
+	if (rv && rv != IPMI_UNKNOWN_ERR_COMPLETION_CODE) {
+		printk(KERN_ERR PFX "Unable to send ATCA ,"
+		       " IPMI error 0x%x\n", rv);
+	}
 	return;
 }
 
-static int ipmi_atca_detect (ipmi_user_t user)
+static int ipmi_atca_detect(ipmi_user_t user)
 {
 	struct ipmi_system_interface_addr smi_addr;
 	struct kernel_ipmi_msg            send_msg;
 	int                               rv;
 	unsigned char                     data[1];
 
-        /*
-         * Configure IPMI address for local access
-         */
-        smi_addr.addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
-        smi_addr.channel = IPMI_BMC_CHANNEL;
-        smi_addr.lun = 0;
+	/*
+	 * Configure IPMI address for local access
+	 */
+	smi_addr.addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
+	smi_addr.channel = IPMI_BMC_CHANNEL;
+	smi_addr.lun = 0;
 
 	/*
 	 * Use get address info to check and see if we are ATCA
@@ -238,28 +254,30 @@ static int ipmi_atca_detect (ipmi_user_t user)
 					    (struct ipmi_addr *) &smi_addr,
 					    &send_msg);
 
-        printk(KERN_INFO PFX "ATCA Detect mfg 0x%X prod 0x%X\n", mfg_id, prod_id);
-        if((mfg_id == IPMI_MOTOROLA_MANUFACTURER_ID)
-            && (prod_id == IPMI_MOTOROLA_PPS_IPMC_PRODUCT_ID)) {
-		printk(KERN_INFO PFX "Installing Pigeon Point Systems Poweroff Hook\n");
+	printk(KERN_INFO PFX "ATCA Detect mfg 0x%X prod 0x%X\n",
+	       mfg_id, prod_id);
+	if ((mfg_id == IPMI_MOTOROLA_MANUFACTURER_ID)
+	    && (prod_id == IPMI_MOTOROLA_PPS_IPMC_PRODUCT_ID)) {
+		printk(KERN_INFO PFX
+		       "Installing Pigeon Point Systems Poweroff Hook\n");
 		atca_oem_poweroff_hook = pps_poweroff_atca;
 	}
 	return !rv;
 }
 
-static void ipmi_poweroff_atca (ipmi_user_t user)
+static void ipmi_poweroff_atca(ipmi_user_t user)
 {
 	struct ipmi_system_interface_addr smi_addr;
 	struct kernel_ipmi_msg            send_msg;
 	int                               rv;
 	unsigned char                     data[4];
 
-        /*
-         * Configure IPMI address for local access
-         */
-        smi_addr.addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
-        smi_addr.channel = IPMI_BMC_CHANNEL;
-        smi_addr.lun = 0;
+	/*
+	 * Configure IPMI address for local access
+	 */
+	smi_addr.addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
+	smi_addr.channel = IPMI_BMC_CHANNEL;
+	smi_addr.lun = 0;
 
 	printk(KERN_INFO PFX "Powering down via ATCA power command\n");
 
@@ -273,23 +291,24 @@ static void ipmi_poweroff_atca (ipmi_user_t user)
 	data[2] = 0; /* Power Level */
 	data[3] = 0; /* Don't change saved presets */
 	send_msg.data = data;
-	send_msg.data_len = sizeof (data);
+	send_msg.data_len = sizeof(data);
 	rv = ipmi_request_in_rc_mode(user,
 				     (struct ipmi_addr *) &smi_addr,
 				     &send_msg);
-        /** At this point, the system may be shutting down, and most
-         ** serial drivers (if used) will have interrupts turned off
-         ** it may be better to ignore IPMI_UNKNOWN_ERR_COMPLETION_CODE
-         ** return code
-         **/
-        if (rv && rv != IPMI_UNKNOWN_ERR_COMPLETION_CODE) {
+	/*
+	 * At this point, the system may be shutting down, and most
+	 * serial drivers (if used) will have interrupts turned off
+	 * it may be better to ignore IPMI_UNKNOWN_ERR_COMPLETION_CODE
+	 * return code
+	 */
+	if (rv && rv != IPMI_UNKNOWN_ERR_COMPLETION_CODE) {
 		printk(KERN_ERR PFX "Unable to send ATCA powerdown message,"
 		       " IPMI error 0x%x\n", rv);
 		goto out;
 	}
 
-	if(atca_oem_poweroff_hook)
-		return atca_oem_poweroff_hook(user);
+	if (atca_oem_poweroff_hook)
+		atca_oem_poweroff_hook(user);
  out:
 	return;
 }
@@ -310,13 +329,13 @@ static void ipmi_poweroff_atca (ipmi_user_t user)
 #define IPMI_CPI1_PRODUCT_ID		0x000157
 #define IPMI_CPI1_MANUFACTURER_ID	0x0108
 
-static int ipmi_cpi1_detect (ipmi_user_t user)
+static int ipmi_cpi1_detect(ipmi_user_t user)
 {
 	return ((mfg_id == IPMI_CPI1_MANUFACTURER_ID)
 		&& (prod_id == IPMI_CPI1_PRODUCT_ID));
 }
 
-static void ipmi_poweroff_cpi1 (ipmi_user_t user)
+static void ipmi_poweroff_cpi1(ipmi_user_t user)
 {
 	struct ipmi_system_interface_addr smi_addr;
 	struct ipmi_ipmb_addr             ipmb_addr;
@@ -328,12 +347,12 @@ static void ipmi_poweroff_cpi1 (ipmi_user_t user)
 	unsigned char                     aer_addr;
 	unsigned char                     aer_lun;
 
-        /*
-         * Configure IPMI address for local access
-         */
-        smi_addr.addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
-        smi_addr.channel = IPMI_BMC_CHANNEL;
-        smi_addr.lun = 0;
+	/*
+	 * Configure IPMI address for local access
+	 */
+	smi_addr.addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
+	smi_addr.channel = IPMI_BMC_CHANNEL;
+	smi_addr.lun = 0;
 
 	printk(KERN_INFO PFX "Powering down via CPI1 power command\n");
 
@@ -425,7 +444,7 @@ static void ipmi_poweroff_cpi1 (ipmi_user_t user)
  */
 
 #define DELL_IANA_MFR_ID {0xA2, 0x02, 0x00}
-static int ipmi_dell_chassis_detect (ipmi_user_t user)
+static int ipmi_dell_chassis_detect(ipmi_user_t user)
 {
 	const char ipmi_version_major = ipmi_version & 0xF;
 	const char ipmi_version_minor = (ipmi_version >> 4) & 0xF;
@@ -444,25 +463,25 @@ static int ipmi_dell_chassis_detect (ipmi_user_t user)
 #define IPMI_NETFN_CHASSIS_REQUEST	0
 #define IPMI_CHASSIS_CONTROL_CMD	0x02
 
-static int ipmi_chassis_detect (ipmi_user_t user)
+static int ipmi_chassis_detect(ipmi_user_t user)
 {
 	/* Chassis support, use it. */
 	return (capabilities & 0x80);
 }
 
-static void ipmi_poweroff_chassis (ipmi_user_t user)
+static void ipmi_poweroff_chassis(ipmi_user_t user)
 {
 	struct ipmi_system_interface_addr smi_addr;
 	struct kernel_ipmi_msg            send_msg;
 	int                               rv;
 	unsigned char                     data[1];
 
-        /*
-         * Configure IPMI address for local access
-         */
-        smi_addr.addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
-        smi_addr.channel = IPMI_BMC_CHANNEL;
-        smi_addr.lun = 0;
+	/*
+	 * Configure IPMI address for local access
+	 */
+	smi_addr.addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
+	smi_addr.channel = IPMI_BMC_CHANNEL;
+	smi_addr.lun = 0;
 
  powercyclefailed:
 	printk(KERN_INFO PFX "Powering %s via IPMI chassis control command\n",
@@ -525,15 +544,13 @@ static struct poweroff_function poweroff_functions[] = {
 
 
 /* Called on a powerdown request. */
-static void ipmi_poweroff_function (void)
+static void ipmi_poweroff_function(void)
 {
 	if (!ready)
 		return;
 
 	/* Use run-to-completion mode, since interrupts may be off. */
-	ipmi_user_set_run_to_completion(ipmi_user, 1);
 	specific_poweroff_func(ipmi_user);
-	ipmi_user_set_run_to_completion(ipmi_user, 0);
 }
 
 /* Wait for an IPMI interface to be installed, the first one installed
@@ -561,13 +578,13 @@ static void ipmi_po_new_smi(int if_num, struct device *device)
 
 	ipmi_ifnum = if_num;
 
-        /*
-         * Do a get device ide and store some results, since this is
+	/*
+	 * Do a get device ide and store some results, since this is
 	 * used by several functions.
-         */
-        smi_addr.addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
-        smi_addr.channel = IPMI_BMC_CHANNEL;
-        smi_addr.lun = 0;
+	 */
+	smi_addr.addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
+	smi_addr.channel = IPMI_BMC_CHANNEL;
+	smi_addr.lun = 0;
 
 	send_msg.netfn = IPMI_NETFN_APP_REQUEST;
 	send_msg.cmd = IPMI_GET_DEVICE_ID_CMD;
@@ -632,8 +649,7 @@ static void ipmi_po_smi_gone(int if_num)
 	pm_power_off = old_poweroff_func;
 }
 
-static struct ipmi_smi_watcher smi_watcher =
-{
+static struct ipmi_smi_watcher smi_watcher = {
 	.owner    = THIS_MODULE,
 	.new_smi  = ipmi_po_new_smi,
 	.smi_gone = ipmi_po_smi_gone
@@ -675,12 +691,12 @@ static struct ctl_table_header *ipmi_table_header;
 /*
  * Startup and shutdown functions.
  */
-static int ipmi_poweroff_init (void)
+static int ipmi_poweroff_init(void)
 {
 	int rv;
 
-	printk (KERN_INFO "Copyright (C) 2004 MontaVista Software -"
-		" IPMI Powerdown via sys_reboot.\n");
+	printk(KERN_INFO "Copyright (C) 2004 MontaVista Software -"
+	       " IPMI Powerdown via sys_reboot.\n");
 
 	if (poweroff_powercycle)
 		printk(KERN_INFO PFX "Power cycle is enabled.\n");
diff --git a/trunk/drivers/char/ipmi/ipmi_si_intf.c b/trunk/drivers/char/ipmi/ipmi_si_intf.c
index 4f560d0bb808..5a5455585c1d 100644
--- a/trunk/drivers/char/ipmi/ipmi_si_intf.c
+++ b/trunk/drivers/char/ipmi/ipmi_si_intf.c
@@ -80,7 +80,7 @@
 #define SI_USEC_PER_JIFFY	(1000000/HZ)
 #define SI_TIMEOUT_JIFFIES	(SI_TIMEOUT_TIME_USEC/SI_USEC_PER_JIFFY)
 #define SI_SHORT_TIMEOUT_USEC  250 /* .25ms when the SM request a
-                                       short timeout */
+				      short timeout */
 
 /* Bit for BMC global enables. */
 #define IPMI_BMC_RCV_MSG_INTR     0x01
@@ -114,14 +114,61 @@ static char *si_to_str[] = { "kcs", "smic", "bt" };
 
 #define DEVICE_NAME "ipmi_si"
 
-static struct device_driver ipmi_driver =
-{
+static struct device_driver ipmi_driver = {
 	.name = DEVICE_NAME,
 	.bus = &platform_bus_type
 };
 
-struct smi_info
-{
+
+/*
+ * Indexes into stats[] in smi_info below.
+ */
+enum si_stat_indexes {
+	/*
+	 * Number of times the driver requested a timer while an operation
+	 * was in progress.
+	 */
+	SI_STAT_short_timeouts = 0,
+
+	/*
+	 * Number of times the driver requested a timer while nothing was in
+	 * progress.
+	 */
+	SI_STAT_long_timeouts,
+
+	/* Number of times the interface was idle while being polled. */
+	SI_STAT_idles,
+
+	/* Number of interrupts the driver handled. */
+	SI_STAT_interrupts,
+
+	/* Number of time the driver got an ATTN from the hardware. */
+	SI_STAT_attentions,
+
+	/* Number of times the driver requested flags from the hardware. */
+	SI_STAT_flag_fetches,
+
+	/* Number of times the hardware didn't follow the state machine. */
+	SI_STAT_hosed_count,
+
+	/* Number of completed messages. */
+	SI_STAT_complete_transactions,
+
+	/* Number of IPMI events received from the hardware. */
+	SI_STAT_events,
+
+	/* Number of watchdog pretimeouts. */
+	SI_STAT_watchdog_pretimeouts,
+
+	/* Number of asyncronous messages received. */
+	SI_STAT_incoming_messages,
+
+
+	/* This *must* remain last, add new values above this. */
+	SI_NUM_STATS
+};
+
+struct smi_info {
 	int                    intf_num;
 	ipmi_smi_t             intf;
 	struct si_sm_data      *si_sm;
@@ -134,8 +181,10 @@ struct smi_info
 	struct ipmi_smi_msg    *curr_msg;
 	enum si_intf_state     si_state;
 
-	/* Used to handle the various types of I/O that can occur with
-           IPMI */
+	/*
+	 * Used to handle the various types of I/O that can occur with
+	 * IPMI
+	 */
 	struct si_sm_io io;
 	int (*io_setup)(struct smi_info *info);
 	void (*io_cleanup)(struct smi_info *info);
@@ -146,15 +195,18 @@ struct smi_info
 	void (*addr_source_cleanup)(struct smi_info *info);
 	void *addr_source_data;
 
-	/* Per-OEM handler, called from handle_flags().
-	   Returns 1 when handle_flags() needs to be re-run
-	   or 0 indicating it set si_state itself.
-	*/
+	/*
+	 * Per-OEM handler, called from handle_flags().  Returns 1
+	 * when handle_flags() needs to be re-run or 0 indicating it
+	 * set si_state itself.
+	 */
 	int (*oem_data_avail_handler)(struct smi_info *smi_info);
 
-	/* Flags from the last GET_MSG_FLAGS command, used when an ATTN
-	   is set to hold the flags until we are done handling everything
-	   from the flags. */
+	/*
+	 * Flags from the last GET_MSG_FLAGS command, used when an ATTN
+	 * is set to hold the flags until we are done handling everything
+	 * from the flags.
+	 */
 #define RECEIVE_MSG_AVAIL	0x01
 #define EVENT_MSG_BUFFER_FULL	0x02
 #define WDT_PRE_TIMEOUT_INT	0x08
@@ -162,25 +214,31 @@ struct smi_info
 #define OEM1_DATA_AVAIL     0x40
 #define OEM2_DATA_AVAIL     0x80
 #define OEM_DATA_AVAIL      (OEM0_DATA_AVAIL | \
-                             OEM1_DATA_AVAIL | \
-                             OEM2_DATA_AVAIL)
+			     OEM1_DATA_AVAIL | \
+			     OEM2_DATA_AVAIL)
 	unsigned char       msg_flags;
 
-	/* If set to true, this will request events the next time the
-	   state machine is idle. */
+	/*
+	 * If set to true, this will request events the next time the
+	 * state machine is idle.
+	 */
 	atomic_t            req_events;
 
-	/* If true, run the state machine to completion on every send
-	   call.  Generally used after a panic to make sure stuff goes
-	   out. */
+	/*
+	 * If true, run the state machine to completion on every send
+	 * call.  Generally used after a panic to make sure stuff goes
+	 * out.
+	 */
 	int                 run_to_completion;
 
 	/* The I/O port of an SI interface. */
 	int                 port;
 
-	/* The space between start addresses of the two ports.  For
-	   instance, if the first port is 0xca2 and the spacing is 4, then
-	   the second port is 0xca6. */
+	/*
+	 * The space between start addresses of the two ports.  For
+	 * instance, if the first port is 0xca2 and the spacing is 4, then
+	 * the second port is 0xca6.
+	 */
 	unsigned int        spacing;
 
 	/* zero if no irq; */
@@ -195,10 +253,12 @@ struct smi_info
 	/* Used to gracefully stop the timer without race conditions. */
 	atomic_t            stop_operation;
 
-	/* The driver will disable interrupts when it gets into a
-	   situation where it cannot handle messages due to lack of
-	   memory.  Once that situation clears up, it will re-enable
-	   interrupts. */
+	/*
+	 * The driver will disable interrupts when it gets into a
+	 * situation where it cannot handle messages due to lack of
+	 * memory.  Once that situation clears up, it will re-enable
+	 * interrupts.
+	 */
 	int interrupt_disabled;
 
 	/* From the get device id response... */
@@ -208,33 +268,28 @@ struct smi_info
 	struct device *dev;
 	struct platform_device *pdev;
 
-	 /* True if we allocated the device, false if it came from
-	  * someplace else (like PCI). */
+	/*
+	 * True if we allocated the device, false if it came from
+	 * someplace else (like PCI).
+	 */
 	int dev_registered;
 
 	/* Slave address, could be reported from DMI. */
 	unsigned char slave_addr;
 
 	/* Counters and things for the proc filesystem. */
-	spinlock_t count_lock;
-	unsigned long short_timeouts;
-	unsigned long long_timeouts;
-	unsigned long timeout_restarts;
-	unsigned long idles;
-	unsigned long interrupts;
-	unsigned long attentions;
-	unsigned long flag_fetches;
-	unsigned long hosed_count;
-	unsigned long complete_transactions;
-	unsigned long events;
-	unsigned long watchdog_pretimeouts;
-	unsigned long incoming_messages;
-
-        struct task_struct *thread;
+	atomic_t stats[SI_NUM_STATS];
+
+	struct task_struct *thread;
 
 	struct list_head link;
 };
 
+#define smi_inc_stat(smi, stat) \
+	atomic_inc(&(smi)->stats[SI_STAT_ ## stat])
+#define smi_get_stat(smi, stat) \
+	((unsigned int) atomic_read(&(smi)->stats[SI_STAT_ ## stat]))
+
 #define SI_MAX_PARMS 4
 
 static int force_kipmid[SI_MAX_PARMS];
@@ -246,7 +301,7 @@ static int try_smi_init(struct smi_info *smi);
 static void cleanup_one_si(struct smi_info *to_clean);
 
 static ATOMIC_NOTIFIER_HEAD(xaction_notifier_list);
-static int register_xaction_notifier(struct notifier_block * nb)
+static int register_xaction_notifier(struct notifier_block *nb)
 {
 	return atomic_notifier_chain_register(&xaction_notifier_list, nb);
 }
@@ -255,7 +310,7 @@ static void deliver_recv_msg(struct smi_info *smi_info,
 			     struct ipmi_smi_msg *msg)
 {
 	/* Deliver the message to the upper layer with the lock
-           released. */
+	   released. */
 	spin_unlock(&(smi_info->si_lock));
 	ipmi_smi_msg_received(smi_info->intf, msg);
 	spin_lock(&(smi_info->si_lock));
@@ -287,9 +342,12 @@ static enum si_sm_result start_next_msg(struct smi_info *smi_info)
 	struct timeval t;
 #endif
 
-	/* No need to save flags, we aleady have interrupts off and we
-	   already hold the SMI lock. */
-	spin_lock(&(smi_info->msg_lock));
+	/*
+	 * No need to save flags, we aleady have interrupts off and we
+	 * already hold the SMI lock.
+	 */
+	if (!smi_info->run_to_completion)
+		spin_lock(&(smi_info->msg_lock));
 
 	/* Pick the high priority queue first. */
 	if (!list_empty(&(smi_info->hp_xmit_msgs))) {
@@ -310,7 +368,7 @@ static enum si_sm_result start_next_msg(struct smi_info *smi_info)
 						link);
 #ifdef DEBUG_TIMING
 		do_gettimeofday(&t);
-		printk("**Start2: %d.%9.9d\n", t.tv_sec, t.tv_usec);
+		printk(KERN_DEBUG "**Start2: %d.%9.9d\n", t.tv_sec, t.tv_usec);
 #endif
 		err = atomic_notifier_call_chain(&xaction_notifier_list,
 				0, smi_info);
@@ -322,14 +380,14 @@ static enum si_sm_result start_next_msg(struct smi_info *smi_info)
 			smi_info->si_sm,
 			smi_info->curr_msg->data,
 			smi_info->curr_msg->data_size);
-		if (err) {
+		if (err)
 			return_hosed_msg(smi_info, err);
-		}
 
 		rv = SI_SM_CALL_WITHOUT_DELAY;
 	}
-	out:
-	spin_unlock(&(smi_info->msg_lock));
+ out:
+	if (!smi_info->run_to_completion)
+		spin_unlock(&(smi_info->msg_lock));
 
 	return rv;
 }
@@ -338,8 +396,10 @@ static void start_enable_irq(struct smi_info *smi_info)
 {
 	unsigned char msg[2];
 
-	/* If we are enabling interrupts, we have to tell the
-	   BMC to use them. */
+	/*
+	 * If we are enabling interrupts, we have to tell the
+	 * BMC to use them.
+	 */
 	msg[0] = (IPMI_NETFN_APP_REQUEST << 2);
 	msg[1] = IPMI_GET_BMC_GLOBAL_ENABLES_CMD;
 
@@ -371,10 +431,12 @@ static void start_clear_flags(struct smi_info *smi_info)
 	smi_info->si_state = SI_CLEARING_FLAGS;
 }
 
-/* When we have a situtaion where we run out of memory and cannot
-   allocate messages, we just leave them in the BMC and run the system
-   polled until we can allocate some memory.  Once we have some
-   memory, we will re-enable the interrupt. */
+/*
+ * When we have a situtaion where we run out of memory and cannot
+ * allocate messages, we just leave them in the BMC and run the system
+ * polled until we can allocate some memory.  Once we have some
+ * memory, we will re-enable the interrupt.
+ */
 static inline void disable_si_irq(struct smi_info *smi_info)
 {
 	if ((smi_info->irq) && (!smi_info->interrupt_disabled)) {
@@ -396,9 +458,7 @@ static void handle_flags(struct smi_info *smi_info)
  retry:
 	if (smi_info->msg_flags & WDT_PRE_TIMEOUT_INT) {
 		/* Watchdog pre-timeout */
-		spin_lock(&smi_info->count_lock);
-		smi_info->watchdog_pretimeouts++;
-		spin_unlock(&smi_info->count_lock);
+		smi_inc_stat(smi_info, watchdog_pretimeouts);
 
 		start_clear_flags(smi_info);
 		smi_info->msg_flags &= ~WDT_PRE_TIMEOUT_INT;
@@ -444,12 +504,11 @@ static void handle_flags(struct smi_info *smi_info)
 			smi_info->curr_msg->data_size);
 		smi_info->si_state = SI_GETTING_EVENTS;
 	} else if (smi_info->msg_flags & OEM_DATA_AVAIL &&
-	           smi_info->oem_data_avail_handler) {
+		   smi_info->oem_data_avail_handler) {
 		if (smi_info->oem_data_avail_handler(smi_info))
 			goto retry;
-	} else {
+	} else
 		smi_info->si_state = SI_NORMAL;
-	}
 }
 
 static void handle_transaction_done(struct smi_info *smi_info)
@@ -459,7 +518,7 @@ static void handle_transaction_done(struct smi_info *smi_info)
 	struct timeval t;
 
 	do_gettimeofday(&t);
-	printk("**Done: %d.%9.9d\n", t.tv_sec, t.tv_usec);
+	printk(KERN_DEBUG "**Done: %d.%9.9d\n", t.tv_sec, t.tv_usec);
 #endif
 	switch (smi_info->si_state) {
 	case SI_NORMAL:
@@ -472,9 +531,11 @@ static void handle_transaction_done(struct smi_info *smi_info)
 				smi_info->curr_msg->rsp,
 				IPMI_MAX_MSG_LENGTH);
 
-		/* Do this here becase deliver_recv_msg() releases the
-		   lock, and a new message can be put in during the
-		   time the lock is released. */
+		/*
+		 * Do this here becase deliver_recv_msg() releases the
+		 * lock, and a new message can be put in during the
+		 * time the lock is released.
+		 */
 		msg = smi_info->curr_msg;
 		smi_info->curr_msg = NULL;
 		deliver_recv_msg(smi_info, msg);
@@ -488,12 +549,13 @@ static void handle_transaction_done(struct smi_info *smi_info)
 		/* We got the flags from the SMI, now handle them. */
 		len = smi_info->handlers->get_result(smi_info->si_sm, msg, 4);
 		if (msg[2] != 0) {
-			/* Error fetching flags, just give up for
-			   now. */
+			/* Error fetching flags, just give up for now. */
 			smi_info->si_state = SI_NORMAL;
 		} else if (len < 4) {
-			/* Hmm, no flags.  That's technically illegal, but
-			   don't use uninitialized data. */
+			/*
+			 * Hmm, no flags.  That's technically illegal, but
+			 * don't use uninitialized data.
+			 */
 			smi_info->si_state = SI_NORMAL;
 		} else {
 			smi_info->msg_flags = msg[3];
@@ -530,9 +592,11 @@ static void handle_transaction_done(struct smi_info *smi_info)
 				smi_info->curr_msg->rsp,
 				IPMI_MAX_MSG_LENGTH);
 
-		/* Do this here becase deliver_recv_msg() releases the
-		   lock, and a new message can be put in during the
-		   time the lock is released. */
+		/*
+		 * Do this here becase deliver_recv_msg() releases the
+		 * lock, and a new message can be put in during the
+		 * time the lock is released.
+		 */
 		msg = smi_info->curr_msg;
 		smi_info->curr_msg = NULL;
 		if (msg->rsp[2] != 0) {
@@ -543,14 +607,14 @@ static void handle_transaction_done(struct smi_info *smi_info)
 			smi_info->msg_flags &= ~EVENT_MSG_BUFFER_FULL;
 			handle_flags(smi_info);
 		} else {
-			spin_lock(&smi_info->count_lock);
-			smi_info->events++;
-			spin_unlock(&smi_info->count_lock);
-
-			/* Do this before we deliver the message
-			   because delivering the message releases the
-			   lock and something else can mess with the
-			   state. */
+			smi_inc_stat(smi_info, events);
+
+			/*
+			 * Do this before we deliver the message
+			 * because delivering the message releases the
+			 * lock and something else can mess with the
+			 * state.
+			 */
 			handle_flags(smi_info);
 
 			deliver_recv_msg(smi_info, msg);
@@ -566,9 +630,11 @@ static void handle_transaction_done(struct smi_info *smi_info)
 				smi_info->curr_msg->rsp,
 				IPMI_MAX_MSG_LENGTH);
 
-		/* Do this here becase deliver_recv_msg() releases the
-		   lock, and a new message can be put in during the
-		   time the lock is released. */
+		/*
+		 * Do this here becase deliver_recv_msg() releases the
+		 * lock, and a new message can be put in during the
+		 * time the lock is released.
+		 */
 		msg = smi_info->curr_msg;
 		smi_info->curr_msg = NULL;
 		if (msg->rsp[2] != 0) {
@@ -579,14 +645,14 @@ static void handle_transaction_done(struct smi_info *smi_info)
 			smi_info->msg_flags &= ~RECEIVE_MSG_AVAIL;
 			handle_flags(smi_info);
 		} else {
-			spin_lock(&smi_info->count_lock);
-			smi_info->incoming_messages++;
-			spin_unlock(&smi_info->count_lock);
-
-			/* Do this before we deliver the message
-			   because delivering the message releases the
-			   lock and something else can mess with the
-			   state. */
+			smi_inc_stat(smi_info, incoming_messages);
+
+			/*
+			 * Do this before we deliver the message
+			 * because delivering the message releases the
+			 * lock and something else can mess with the
+			 * state.
+			 */
 			handle_flags(smi_info);
 
 			deliver_recv_msg(smi_info, msg);
@@ -674,69 +740,70 @@ static void handle_transaction_done(struct smi_info *smi_info)
 	}
 }
 
-/* Called on timeouts and events.  Timeouts should pass the elapsed
-   time, interrupts should pass in zero.  Must be called with
-   si_lock held and interrupts disabled. */
+/*
+ * Called on timeouts and events.  Timeouts should pass the elapsed
+ * time, interrupts should pass in zero.  Must be called with
+ * si_lock held and interrupts disabled.
+ */
 static enum si_sm_result smi_event_handler(struct smi_info *smi_info,
 					   int time)
 {
 	enum si_sm_result si_sm_result;
 
  restart:
-	/* There used to be a loop here that waited a little while
-	   (around 25us) before giving up.  That turned out to be
-	   pointless, the minimum delays I was seeing were in the 300us
-	   range, which is far too long to wait in an interrupt.  So
-	   we just run until the state machine tells us something
-	   happened or it needs a delay. */
+	/*
+	 * There used to be a loop here that waited a little while
+	 * (around 25us) before giving up.  That turned out to be
+	 * pointless, the minimum delays I was seeing were in the 300us
+	 * range, which is far too long to wait in an interrupt.  So
+	 * we just run until the state machine tells us something
+	 * happened or it needs a delay.
+	 */
 	si_sm_result = smi_info->handlers->event(smi_info->si_sm, time);
 	time = 0;
 	while (si_sm_result == SI_SM_CALL_WITHOUT_DELAY)
-	{
 		si_sm_result = smi_info->handlers->event(smi_info->si_sm, 0);
-	}
 
-	if (si_sm_result == SI_SM_TRANSACTION_COMPLETE)
-	{
-		spin_lock(&smi_info->count_lock);
-		smi_info->complete_transactions++;
-		spin_unlock(&smi_info->count_lock);
+	if (si_sm_result == SI_SM_TRANSACTION_COMPLETE) {
+		smi_inc_stat(smi_info, complete_transactions);
 
 		handle_transaction_done(smi_info);
 		si_sm_result = smi_info->handlers->event(smi_info->si_sm, 0);
-	}
-	else if (si_sm_result == SI_SM_HOSED)
-	{
-		spin_lock(&smi_info->count_lock);
-		smi_info->hosed_count++;
-		spin_unlock(&smi_info->count_lock);
+	} else if (si_sm_result == SI_SM_HOSED) {
+		smi_inc_stat(smi_info, hosed_count);
 
-		/* Do the before return_hosed_msg, because that
-		   releases the lock. */
+		/*
+		 * Do the before return_hosed_msg, because that
+		 * releases the lock.
+		 */
 		smi_info->si_state = SI_NORMAL;
 		if (smi_info->curr_msg != NULL) {
-			/* If we were handling a user message, format
-                           a response to send to the upper layer to
-                           tell it about the error. */
+			/*
+			 * If we were handling a user message, format
+			 * a response to send to the upper layer to
+			 * tell it about the error.
+			 */
 			return_hosed_msg(smi_info, IPMI_ERR_UNSPECIFIED);
 		}
 		si_sm_result = smi_info->handlers->event(smi_info->si_sm, 0);
 	}
 
-	/* We prefer handling attn over new messages. */
-	if (si_sm_result == SI_SM_ATTN)
-	{
+	/*
+	 * We prefer handling attn over new messages.  But don't do
+	 * this if there is not yet an upper layer to handle anything.
+	 */
+	if (likely(smi_info->intf) && si_sm_result == SI_SM_ATTN) {
 		unsigned char msg[2];
 
-		spin_lock(&smi_info->count_lock);
-		smi_info->attentions++;
-		spin_unlock(&smi_info->count_lock);
+		smi_inc_stat(smi_info, attentions);
 
-		/* Got a attn, send down a get message flags to see
-                   what's causing it.  It would be better to handle
-                   this in the upper layer, but due to the way
-                   interrupts work with the SMI, that's not really
-                   possible. */
+		/*
+		 * Got a attn, send down a get message flags to see
+		 * what's causing it.  It would be better to handle
+		 * this in the upper layer, but due to the way
+		 * interrupts work with the SMI, that's not really
+		 * possible.
+		 */
 		msg[0] = (IPMI_NETFN_APP_REQUEST << 2);
 		msg[1] = IPMI_GET_MSG_FLAGS_CMD;
 
@@ -748,20 +815,19 @@ static enum si_sm_result smi_event_handler(struct smi_info *smi_info,
 
 	/* If we are currently idle, try to start the next message. */
 	if (si_sm_result == SI_SM_IDLE) {
-		spin_lock(&smi_info->count_lock);
-		smi_info->idles++;
-		spin_unlock(&smi_info->count_lock);
+		smi_inc_stat(smi_info, idles);
 
 		si_sm_result = start_next_msg(smi_info);
 		if (si_sm_result != SI_SM_IDLE)
 			goto restart;
-        }
+	}
 
 	if ((si_sm_result == SI_SM_IDLE)
-	    && (atomic_read(&smi_info->req_events)))
-	{
-		/* We are idle and the upper layer requested that I fetch
-		   events, so do so. */
+	    && (atomic_read(&smi_info->req_events))) {
+		/*
+		 * We are idle and the upper layer requested that I fetch
+		 * events, so do so.
+		 */
 		atomic_set(&smi_info->req_events, 0);
 
 		smi_info->curr_msg = ipmi_alloc_smi_msg();
@@ -803,56 +869,50 @@ static void sender(void                *send_info,
 		return;
 	}
 
-	spin_lock_irqsave(&(smi_info->msg_lock), flags);
 #ifdef DEBUG_TIMING
 	do_gettimeofday(&t);
 	printk("**Enqueue: %d.%9.9d\n", t.tv_sec, t.tv_usec);
 #endif
 
 	if (smi_info->run_to_completion) {
-		/* If we are running to completion, then throw it in
-		   the list and run transactions until everything is
-		   clear.  Priority doesn't matter here. */
+		/*
+		 * If we are running to completion, then throw it in
+		 * the list and run transactions until everything is
+		 * clear.  Priority doesn't matter here.
+		 */
+
+		/*
+		 * Run to completion means we are single-threaded, no
+		 * need for locks.
+		 */
 		list_add_tail(&(msg->link), &(smi_info->xmit_msgs));
 
-		/* We have to release the msg lock and claim the smi
-		   lock in this case, because of race conditions. */
-		spin_unlock_irqrestore(&(smi_info->msg_lock), flags);
-
-		spin_lock_irqsave(&(smi_info->si_lock), flags);
 		result = smi_event_handler(smi_info, 0);
 		while (result != SI_SM_IDLE) {
 			udelay(SI_SHORT_TIMEOUT_USEC);
 			result = smi_event_handler(smi_info,
 						   SI_SHORT_TIMEOUT_USEC);
 		}
-		spin_unlock_irqrestore(&(smi_info->si_lock), flags);
 		return;
-	} else {
-		if (priority > 0) {
-			list_add_tail(&(msg->link), &(smi_info->hp_xmit_msgs));
-		} else {
-			list_add_tail(&(msg->link), &(smi_info->xmit_msgs));
-		}
 	}
-	spin_unlock_irqrestore(&(smi_info->msg_lock), flags);
 
-	spin_lock_irqsave(&(smi_info->si_lock), flags);
-	if ((smi_info->si_state == SI_NORMAL)
-	    && (smi_info->curr_msg == NULL))
-	{
+	spin_lock_irqsave(&smi_info->msg_lock, flags);
+	if (priority > 0)
+		list_add_tail(&msg->link, &smi_info->hp_xmit_msgs);
+	else
+		list_add_tail(&msg->link, &smi_info->xmit_msgs);
+	spin_unlock_irqrestore(&smi_info->msg_lock, flags);
+
+	spin_lock_irqsave(&smi_info->si_lock, flags);
+	if (smi_info->si_state == SI_NORMAL && smi_info->curr_msg == NULL)
 		start_next_msg(smi_info);
-	}
-	spin_unlock_irqrestore(&(smi_info->si_lock), flags);
+	spin_unlock_irqrestore(&smi_info->si_lock, flags);
 }
 
 static void set_run_to_completion(void *send_info, int i_run_to_completion)
 {
 	struct smi_info   *smi_info = send_info;
 	enum si_sm_result result;
-	unsigned long     flags;
-
-	spin_lock_irqsave(&(smi_info->si_lock), flags);
 
 	smi_info->run_to_completion = i_run_to_completion;
 	if (i_run_to_completion) {
@@ -863,8 +923,6 @@ static void set_run_to_completion(void *send_info, int i_run_to_completion)
 						   SI_SHORT_TIMEOUT_USEC);
 		}
 	}
-
-	spin_unlock_irqrestore(&(smi_info->si_lock), flags);
 }
 
 static int ipmi_thread(void *data)
@@ -878,9 +936,8 @@ static int ipmi_thread(void *data)
 		spin_lock_irqsave(&(smi_info->si_lock), flags);
 		smi_result = smi_event_handler(smi_info, 0);
 		spin_unlock_irqrestore(&(smi_info->si_lock), flags);
-		if (smi_result == SI_SM_CALL_WITHOUT_DELAY) {
-			/* do nothing */
-		}
+		if (smi_result == SI_SM_CALL_WITHOUT_DELAY)
+			; /* do nothing */
 		else if (smi_result == SI_SM_CALL_WITH_DELAY)
 			schedule();
 		else
@@ -931,7 +988,7 @@ static void smi_timeout(unsigned long data)
 	spin_lock_irqsave(&(smi_info->si_lock), flags);
 #ifdef DEBUG_TIMING
 	do_gettimeofday(&t);
-	printk("**Timer: %d.%9.9d\n", t.tv_sec, t.tv_usec);
+	printk(KERN_DEBUG "**Timer: %d.%9.9d\n", t.tv_sec, t.tv_usec);
 #endif
 	jiffies_now = jiffies;
 	time_diff = (((long)jiffies_now - (long)smi_info->last_timeout_jiffies)
@@ -945,23 +1002,19 @@ static void smi_timeout(unsigned long data)
 	if ((smi_info->irq) && (!smi_info->interrupt_disabled)) {
 		/* Running with interrupts, only do long timeouts. */
 		smi_info->si_timer.expires = jiffies + SI_TIMEOUT_JIFFIES;
-		spin_lock_irqsave(&smi_info->count_lock, flags);
-		smi_info->long_timeouts++;
-		spin_unlock_irqrestore(&smi_info->count_lock, flags);
+		smi_inc_stat(smi_info, long_timeouts);
 		goto do_add_timer;
 	}
 
-	/* If the state machine asks for a short delay, then shorten
-           the timer timeout. */
+	/*
+	 * If the state machine asks for a short delay, then shorten
+	 * the timer timeout.
+	 */
 	if (smi_result == SI_SM_CALL_WITH_DELAY) {
-		spin_lock_irqsave(&smi_info->count_lock, flags);
-		smi_info->short_timeouts++;
-		spin_unlock_irqrestore(&smi_info->count_lock, flags);
+		smi_inc_stat(smi_info, short_timeouts);
 		smi_info->si_timer.expires = jiffies + 1;
 	} else {
-		spin_lock_irqsave(&smi_info->count_lock, flags);
-		smi_info->long_timeouts++;
-		spin_unlock_irqrestore(&smi_info->count_lock, flags);
+		smi_inc_stat(smi_info, long_timeouts);
 		smi_info->si_timer.expires = jiffies + SI_TIMEOUT_JIFFIES;
 	}
 
@@ -979,13 +1032,11 @@ static irqreturn_t si_irq_handler(int irq, void *data)
 
 	spin_lock_irqsave(&(smi_info->si_lock), flags);
 
-	spin_lock(&smi_info->count_lock);
-	smi_info->interrupts++;
-	spin_unlock(&smi_info->count_lock);
+	smi_inc_stat(smi_info, interrupts);
 
 #ifdef DEBUG_TIMING
 	do_gettimeofday(&t);
-	printk("**Interrupt: %d.%9.9d\n", t.tv_sec, t.tv_usec);
+	printk(KERN_DEBUG "**Interrupt: %d.%9.9d\n", t.tv_sec, t.tv_usec);
 #endif
 	smi_event_handler(smi_info, 0);
 	spin_unlock_irqrestore(&(smi_info->si_lock), flags);
@@ -1028,7 +1079,7 @@ static int smi_start_processing(void       *send_info,
 	 * The BT interface is efficient enough to not need a thread,
 	 * and there is no need for a thread if we have interrupts.
 	 */
- 	else if ((new_smi->si_type != SI_BT) && (!new_smi->irq))
+	else if ((new_smi->si_type != SI_BT) && (!new_smi->irq))
 		enable = 1;
 
 	if (enable) {
@@ -1054,8 +1105,7 @@ static void set_maintenance_mode(void *send_info, int enable)
 		atomic_set(&smi_info->req_events, 0);
 }
 
-static struct ipmi_smi_handlers handlers =
-{
+static struct ipmi_smi_handlers handlers = {
 	.owner                  = THIS_MODULE,
 	.start_processing       = smi_start_processing,
 	.sender			= sender,
@@ -1065,8 +1115,10 @@ static struct ipmi_smi_handlers handlers =
 	.poll			= poll,
 };
 
-/* There can be 4 IO ports passed in (with or without IRQs), 4 addresses,
-   a default IO port, and 1 ACPI/SPMI address.  That sets SI_MAX_DRIVERS */
+/*
+ * There can be 4 IO ports passed in (with or without IRQs), 4 addresses,
+ * a default IO port, and 1 ACPI/SPMI address.  That sets SI_MAX_DRIVERS.
+ */
 
 static LIST_HEAD(smi_infos);
 static DEFINE_MUTEX(smi_infos_lock);
@@ -1257,10 +1309,9 @@ static void port_cleanup(struct smi_info *info)
 	int          idx;
 
 	if (addr) {
-	  	for (idx = 0; idx < info->io_size; idx++) {
+		for (idx = 0; idx < info->io_size; idx++)
 			release_region(addr + idx * info->io.regspacing,
 				       info->io.regsize);
-		}
 	}
 }
 
@@ -1274,8 +1325,10 @@ static int port_setup(struct smi_info *info)
 
 	info->io_cleanup = port_cleanup;
 
-	/* Figure out the actual inb/inw/inl/etc routine to use based
-	   upon the register size. */
+	/*
+	 * Figure out the actual inb/inw/inl/etc routine to use based
+	 * upon the register size.
+	 */
 	switch (info->io.regsize) {
 	case 1:
 		info->io.inputb = port_inb;
@@ -1290,17 +1343,18 @@ static int port_setup(struct smi_info *info)
 		info->io.outputb = port_outl;
 		break;
 	default:
-		printk("ipmi_si: Invalid register size: %d\n",
+		printk(KERN_WARNING "ipmi_si: Invalid register size: %d\n",
 		       info->io.regsize);
 		return -EINVAL;
 	}
 
-	/* Some BIOSes reserve disjoint I/O regions in their ACPI
+	/*
+	 * Some BIOSes reserve disjoint I/O regions in their ACPI
 	 * tables.  This causes problems when trying to register the
 	 * entire I/O region.  Therefore we must register each I/O
 	 * port separately.
 	 */
-  	for (idx = 0; idx < info->io_size; idx++) {
+	for (idx = 0; idx < info->io_size; idx++) {
 		if (request_region(addr + idx * info->io.regspacing,
 				   info->io.regsize, DEVICE_NAME) == NULL) {
 			/* Undo allocations */
@@ -1388,8 +1442,10 @@ static int mem_setup(struct smi_info *info)
 
 	info->io_cleanup = mem_cleanup;
 
-	/* Figure out the actual readb/readw/readl/etc routine to use based
-	   upon the register size. */
+	/*
+	 * Figure out the actual readb/readw/readl/etc routine to use based
+	 * upon the register size.
+	 */
 	switch (info->io.regsize) {
 	case 1:
 		info->io.inputb = intf_mem_inb;
@@ -1410,16 +1466,18 @@ static int mem_setup(struct smi_info *info)
 		break;
 #endif
 	default:
-		printk("ipmi_si: Invalid register size: %d\n",
+		printk(KERN_WARNING "ipmi_si: Invalid register size: %d\n",
 		       info->io.regsize);
 		return -EINVAL;
 	}
 
-	/* Calculate the total amount of memory to claim.  This is an
+	/*
+	 * Calculate the total amount of memory to claim.  This is an
 	 * unusual looking calculation, but it avoids claiming any
 	 * more memory than it has to.  It will claim everything
 	 * between the first address to the end of the last full
-	 * register. */
+	 * register.
+	 */
 	mapsize = ((info->io_size * info->io.regspacing)
 		   - (info->io.regspacing - info->io.regsize));
 
@@ -1749,9 +1807,11 @@ static __devinit void hardcode_find_bmc(void)
 
 #include <linux/acpi.h>
 
-/* Once we get an ACPI failure, we don't try any more, because we go
-   through the tables sequentially.  Once we don't find a table, there
-   are no more. */
+/*
+ * Once we get an ACPI failure, we don't try any more, because we go
+ * through the tables sequentially.  Once we don't find a table, there
+ * are no more.
+ */
 static int acpi_failure;
 
 /* For GPE-type interrupts. */
@@ -1765,9 +1825,7 @@ static u32 ipmi_acpi_gpe(void *context)
 
 	spin_lock_irqsave(&(smi_info->si_lock), flags);
 
-	spin_lock(&smi_info->count_lock);
-	smi_info->interrupts++;
-	spin_unlock(&smi_info->count_lock);
+	smi_inc_stat(smi_info, interrupts);
 
 #ifdef DEBUG_TIMING
 	do_gettimeofday(&t);
@@ -1816,7 +1874,8 @@ static int acpi_gpe_irq_setup(struct smi_info *info)
 
 /*
  * Defined at
- * http://h21007.www2.hp.com/dspp/files/unprotected/devresource/Docs/TechPapers/IA64/hpspmi.pdf
+ * http://h21007.www2.hp.com/dspp/files/unprotected/devresource/
+ * Docs/TechPapers/IA64/hpspmi.pdf
  */
 struct SPMITable {
 	s8	Signature[4];
@@ -1838,14 +1897,18 @@ struct SPMITable {
 	 */
 	u8	InterruptType;
 
-	/* If bit 0 of InterruptType is set, then this is the SCI
-           interrupt in the GPEx_STS register. */
+	/*
+	 * If bit 0 of InterruptType is set, then this is the SCI
+	 * interrupt in the GPEx_STS register.
+	 */
 	u8	GPE;
 
 	s16	Reserved;
 
-	/* If bit 1 of InterruptType is set, then this is the I/O
-           APIC/SAPIC interrupt. */
+	/*
+	 * If bit 1 of InterruptType is set, then this is the I/O
+	 * APIC/SAPIC interrupt.
+	 */
 	u32	GlobalSystemInterrupt;
 
 	/* The actual register address. */
@@ -1863,7 +1926,7 @@ static __devinit int try_init_acpi(struct SPMITable *spmi)
 
 	if (spmi->IPMIlegacy != 1) {
 	    printk(KERN_INFO "IPMI: Bad SPMI legacy %d\n", spmi->IPMIlegacy);
-  	    return -ENODEV;
+	    return -ENODEV;
 	}
 
 	if (spmi->addr.space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
@@ -1880,8 +1943,7 @@ static __devinit int try_init_acpi(struct SPMITable *spmi)
 	info->addr_source = "ACPI";
 
 	/* Figure out the interface type. */
-	switch (spmi->InterfaceType)
-	{
+	switch (spmi->InterfaceType) {
 	case 1:	/* KCS */
 		info->si_type = SI_KCS;
 		break;
@@ -1929,7 +1991,8 @@ static __devinit int try_init_acpi(struct SPMITable *spmi)
 		info->io.addr_type = IPMI_IO_ADDR_SPACE;
 	} else {
 		kfree(info);
-		printk("ipmi_si: Unknown ACPI I/O Address type\n");
+		printk(KERN_WARNING
+		       "ipmi_si: Unknown ACPI I/O Address type\n");
 		return -EIO;
 	}
 	info->io.addr_data = spmi->addr.address;
@@ -1963,8 +2026,7 @@ static __devinit void acpi_find_bmc(void)
 #endif
 
 #ifdef CONFIG_DMI
-struct dmi_ipmi_data
-{
+struct dmi_ipmi_data {
 	u8   		type;
 	u8   		addr_space;
 	unsigned long	base_addr;
@@ -1989,11 +2051,10 @@ static int __devinit decode_dmi(const struct dmi_header *dm,
 			/* I/O */
 			base_addr &= 0xFFFE;
 			dmi->addr_space = IPMI_IO_ADDR_SPACE;
-		}
-		else {
+		} else
 			/* Memory */
 			dmi->addr_space = IPMI_MEM_ADDR_SPACE;
-		}
+
 		/* If bit 4 of byte 0x10 is set, then the lsb for the address
 		   is odd. */
 		dmi->base_addr = base_addr | ((data[0x10] & 0x10) >> 4);
@@ -2002,7 +2063,7 @@ static int __devinit decode_dmi(const struct dmi_header *dm,
 
 		/* The top two bits of byte 0x10 hold the register spacing. */
 		reg_spacing = (data[0x10] & 0xC0) >> 6;
-		switch(reg_spacing){
+		switch (reg_spacing) {
 		case 0x00: /* Byte boundaries */
 		    dmi->offset = 1;
 		    break;
@@ -2018,12 +2079,14 @@ static int __devinit decode_dmi(const struct dmi_header *dm,
 		}
 	} else {
 		/* Old DMI spec. */
-		/* Note that technically, the lower bit of the base
+		/*
+		 * Note that technically, the lower bit of the base
 		 * address should be 1 if the address is I/O and 0 if
 		 * the address is in memory.  So many systems get that
 		 * wrong (and all that I have seen are I/O) so we just
 		 * ignore that bit and assume I/O.  Systems that use
-		 * memory should use the newer spec, anyway. */
+		 * memory should use the newer spec, anyway.
+		 */
 		dmi->base_addr = base_addr & 0xfffe;
 		dmi->addr_space = IPMI_IO_ADDR_SPACE;
 		dmi->offset = 1;
@@ -2230,13 +2293,13 @@ static struct pci_device_id ipmi_pci_devices[] = {
 MODULE_DEVICE_TABLE(pci, ipmi_pci_devices);
 
 static struct pci_driver ipmi_pci_driver = {
-        .name =         DEVICE_NAME,
-        .id_table =     ipmi_pci_devices,
-        .probe =        ipmi_pci_probe,
-        .remove =       __devexit_p(ipmi_pci_remove),
+	.name =         DEVICE_NAME,
+	.id_table =     ipmi_pci_devices,
+	.probe =        ipmi_pci_probe,
+	.remove =       __devexit_p(ipmi_pci_remove),
 #ifdef CONFIG_PM
-        .suspend =      ipmi_pci_suspend,
-        .resume =       ipmi_pci_resume,
+	.suspend =      ipmi_pci_suspend,
+	.resume =       ipmi_pci_resume,
 #endif
 };
 #endif /* CONFIG_PCI */
@@ -2306,7 +2369,7 @@ static int __devinit ipmi_of_probe(struct of_device *dev,
 		info->io.addr_data, info->io.regsize, info->io.regspacing,
 		info->irq);
 
-	dev->dev.driver_data = (void*) info;
+	dev->dev.driver_data = (void *) info;
 
 	return try_smi_init(info);
 }
@@ -2319,14 +2382,16 @@ static int __devexit ipmi_of_remove(struct of_device *dev)
 
 static struct of_device_id ipmi_match[] =
 {
-	{ .type = "ipmi", .compatible = "ipmi-kcs",  .data = (void *)(unsigned long) SI_KCS },
-	{ .type = "ipmi", .compatible = "ipmi-smic", .data = (void *)(unsigned long) SI_SMIC },
-	{ .type = "ipmi", .compatible = "ipmi-bt",   .data = (void *)(unsigned long) SI_BT },
+	{ .type = "ipmi", .compatible = "ipmi-kcs",
+	  .data = (void *)(unsigned long) SI_KCS },
+	{ .type = "ipmi", .compatible = "ipmi-smic",
+	  .data = (void *)(unsigned long) SI_SMIC },
+	{ .type = "ipmi", .compatible = "ipmi-bt",
+	  .data = (void *)(unsigned long) SI_BT },
 	{},
 };
 
-static struct of_platform_driver ipmi_of_platform_driver =
-{
+static struct of_platform_driver ipmi_of_platform_driver = {
 	.name		= "ipmi",
 	.match_table	= ipmi_match,
 	.probe		= ipmi_of_probe,
@@ -2347,32 +2412,32 @@ static int try_get_dev_id(struct smi_info *smi_info)
 	if (!resp)
 		return -ENOMEM;
 
-	/* Do a Get Device ID command, since it comes back with some
-	   useful info. */
+	/*
+	 * Do a Get Device ID command, since it comes back with some
+	 * useful info.
+	 */
 	msg[0] = IPMI_NETFN_APP_REQUEST << 2;
 	msg[1] = IPMI_GET_DEVICE_ID_CMD;
 	smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2);
 
 	smi_result = smi_info->handlers->event(smi_info->si_sm, 0);
-	for (;;)
-	{
+	for (;;) {
 		if (smi_result == SI_SM_CALL_WITH_DELAY ||
 		    smi_result == SI_SM_CALL_WITH_TICK_DELAY) {
 			schedule_timeout_uninterruptible(1);
 			smi_result = smi_info->handlers->event(
 				smi_info->si_sm, 100);
-		}
-		else if (smi_result == SI_SM_CALL_WITHOUT_DELAY)
-		{
+		} else if (smi_result == SI_SM_CALL_WITHOUT_DELAY) {
 			smi_result = smi_info->handlers->event(
 				smi_info->si_sm, 0);
-		}
-		else
+		} else
 			break;
 	}
 	if (smi_result == SI_SM_HOSED) {
-		/* We couldn't get the state machine to run, so whatever's at
-		   the port is probably not an IPMI SMI interface. */
+		/*
+		 * We couldn't get the state machine to run, so whatever's at
+		 * the port is probably not an IPMI SMI interface.
+		 */
 		rv = -ENODEV;
 		goto out;
 	}
@@ -2405,30 +2470,28 @@ static int stat_file_read_proc(char *page, char **start, off_t off,
 
 	out += sprintf(out, "interrupts_enabled:    %d\n",
 		       smi->irq && !smi->interrupt_disabled);
-	out += sprintf(out, "short_timeouts:        %ld\n",
-		       smi->short_timeouts);
-	out += sprintf(out, "long_timeouts:         %ld\n",
-		       smi->long_timeouts);
-	out += sprintf(out, "timeout_restarts:      %ld\n",
-		       smi->timeout_restarts);
-	out += sprintf(out, "idles:                 %ld\n",
-		       smi->idles);
-	out += sprintf(out, "interrupts:            %ld\n",
-		       smi->interrupts);
-	out += sprintf(out, "attentions:            %ld\n",
-		       smi->attentions);
-	out += sprintf(out, "flag_fetches:          %ld\n",
-		       smi->flag_fetches);
-	out += sprintf(out, "hosed_count:           %ld\n",
-		       smi->hosed_count);
-	out += sprintf(out, "complete_transactions: %ld\n",
-		       smi->complete_transactions);
-	out += sprintf(out, "events:                %ld\n",
-		       smi->events);
-	out += sprintf(out, "watchdog_pretimeouts:  %ld\n",
-		       smi->watchdog_pretimeouts);
-	out += sprintf(out, "incoming_messages:     %ld\n",
-		       smi->incoming_messages);
+	out += sprintf(out, "short_timeouts:        %u\n",
+		       smi_get_stat(smi, short_timeouts));
+	out += sprintf(out, "long_timeouts:         %u\n",
+		       smi_get_stat(smi, long_timeouts));
+	out += sprintf(out, "idles:                 %u\n",
+		       smi_get_stat(smi, idles));
+	out += sprintf(out, "interrupts:            %u\n",
+		       smi_get_stat(smi, interrupts));
+	out += sprintf(out, "attentions:            %u\n",
+		       smi_get_stat(smi, attentions));
+	out += sprintf(out, "flag_fetches:          %u\n",
+		       smi_get_stat(smi, flag_fetches));
+	out += sprintf(out, "hosed_count:           %u\n",
+		       smi_get_stat(smi, hosed_count));
+	out += sprintf(out, "complete_transactions: %u\n",
+		       smi_get_stat(smi, complete_transactions));
+	out += sprintf(out, "events:                %u\n",
+		       smi_get_stat(smi, events));
+	out += sprintf(out, "watchdog_pretimeouts:  %u\n",
+		       smi_get_stat(smi, watchdog_pretimeouts));
+	out += sprintf(out, "incoming_messages:     %u\n",
+		       smi_get_stat(smi, incoming_messages));
 
 	return out - page;
 }
@@ -2460,7 +2523,7 @@ static int param_read_proc(char *page, char **start, off_t off,
 static int oem_data_avail_to_receive_msg_avail(struct smi_info *smi_info)
 {
 	smi_info->msg_flags = ((smi_info->msg_flags & ~OEM_DATA_AVAIL) |
-			      	RECEIVE_MSG_AVAIL);
+			       RECEIVE_MSG_AVAIL);
 	return 1;
 }
 
@@ -2502,10 +2565,9 @@ static void setup_dell_poweredge_oem_data_handler(struct smi_info *smi_info)
 		    id->ipmi_version   == DELL_POWEREDGE_8G_BMC_IPMI_VERSION) {
 			smi_info->oem_data_avail_handler =
 				oem_data_avail_to_receive_msg_avail;
-		}
-		else if (ipmi_version_major(id) < 1 ||
-			 (ipmi_version_major(id) == 1 &&
-			  ipmi_version_minor(id) < 5)) {
+		} else if (ipmi_version_major(id) < 1 ||
+			   (ipmi_version_major(id) == 1 &&
+			    ipmi_version_minor(id) < 5)) {
 			smi_info->oem_data_avail_handler =
 				oem_data_avail_to_receive_msg_avail;
 		}
@@ -2597,8 +2659,10 @@ static void setup_xaction_handlers(struct smi_info *smi_info)
 static inline void wait_for_timer_and_thread(struct smi_info *smi_info)
 {
 	if (smi_info->intf) {
-		/* The timer and thread are only running if the
-		   interface has been started up and registered. */
+		/*
+		 * The timer and thread are only running if the
+		 * interface has been started up and registered.
+		 */
 		if (smi_info->thread != NULL)
 			kthread_stop(smi_info->thread);
 		del_timer_sync(&smi_info->si_timer);
@@ -2676,6 +2740,7 @@ static int is_new_interface(struct smi_info *info)
 static int try_smi_init(struct smi_info *new_smi)
 {
 	int rv;
+	int i;
 
 	if (new_smi->addr_source) {
 		printk(KERN_INFO "ipmi_si: Trying %s-specified %s state"
@@ -2722,7 +2787,7 @@ static int try_smi_init(struct smi_info *new_smi)
 	/* Allocate the state machine's data and initialize it. */
 	new_smi->si_sm = kmalloc(new_smi->handlers->size(), GFP_KERNEL);
 	if (!new_smi->si_sm) {
-		printk(" Could not allocate state machine memory\n");
+		printk(KERN_ERR "Could not allocate state machine memory\n");
 		rv = -ENOMEM;
 		goto out_err;
 	}
@@ -2732,13 +2797,12 @@ static int try_smi_init(struct smi_info *new_smi)
 	/* Now that we know the I/O size, we can set up the I/O. */
 	rv = new_smi->io_setup(new_smi);
 	if (rv) {
-		printk(" Could not set up I/O space\n");
+		printk(KERN_ERR "Could not set up I/O space\n");
 		goto out_err;
 	}
 
 	spin_lock_init(&(new_smi->si_lock));
 	spin_lock_init(&(new_smi->msg_lock));
-	spin_lock_init(&(new_smi->count_lock));
 
 	/* Do low-level detection first. */
 	if (new_smi->handlers->detect(new_smi->si_sm)) {
@@ -2749,8 +2813,10 @@ static int try_smi_init(struct smi_info *new_smi)
 		goto out_err;
 	}
 
-	/* Attempt a get device id command.  If it fails, we probably
-           don't have a BMC here. */
+	/*
+	 * Attempt a get device id command.  If it fails, we probably
+	 * don't have a BMC here.
+	 */
 	rv = try_get_dev_id(new_smi);
 	if (rv) {
 		if (new_smi->addr_source)
@@ -2767,22 +2833,28 @@ static int try_smi_init(struct smi_info *new_smi)
 	new_smi->curr_msg = NULL;
 	atomic_set(&new_smi->req_events, 0);
 	new_smi->run_to_completion = 0;
+	for (i = 0; i < SI_NUM_STATS; i++)
+		atomic_set(&new_smi->stats[i], 0);
 
 	new_smi->interrupt_disabled = 0;
 	atomic_set(&new_smi->stop_operation, 0);
 	new_smi->intf_num = smi_num;
 	smi_num++;
 
-	/* Start clearing the flags before we enable interrupts or the
-	   timer to avoid racing with the timer. */
+	/*
+	 * Start clearing the flags before we enable interrupts or the
+	 * timer to avoid racing with the timer.
+	 */
 	start_clear_flags(new_smi);
 	/* IRQ is defined to be set when non-zero. */
 	if (new_smi->irq)
 		new_smi->si_state = SI_CLEARING_FLAGS_THEN_SET_IRQ;
 
 	if (!new_smi->dev) {
-		/* If we don't already have a device from something
-		 * else (like PCI), then register a new one. */
+		/*
+		 * If we don't already have a device from something
+		 * else (like PCI), then register a new one.
+		 */
 		new_smi->pdev = platform_device_alloc("ipmi_si",
 						      new_smi->intf_num);
 		if (rv) {
@@ -2820,7 +2892,7 @@ static int try_smi_init(struct smi_info *new_smi)
 	}
 
 	rv = ipmi_smi_add_proc_entry(new_smi->intf, "type",
-				     type_file_read_proc, NULL,
+				     type_file_read_proc,
 				     new_smi, THIS_MODULE);
 	if (rv) {
 		printk(KERN_ERR
@@ -2830,7 +2902,7 @@ static int try_smi_init(struct smi_info *new_smi)
 	}
 
 	rv = ipmi_smi_add_proc_entry(new_smi->intf, "si_stats",
-				     stat_file_read_proc, NULL,
+				     stat_file_read_proc,
 				     new_smi, THIS_MODULE);
 	if (rv) {
 		printk(KERN_ERR
@@ -2840,7 +2912,7 @@ static int try_smi_init(struct smi_info *new_smi)
 	}
 
 	rv = ipmi_smi_add_proc_entry(new_smi->intf, "params",
-				     param_read_proc, NULL,
+				     param_read_proc,
 				     new_smi, THIS_MODULE);
 	if (rv) {
 		printk(KERN_ERR
@@ -2853,7 +2925,8 @@ static int try_smi_init(struct smi_info *new_smi)
 
 	mutex_unlock(&smi_infos_lock);
 
-	printk(KERN_INFO "IPMI %s interface initialized\n",si_to_str[new_smi->si_type]);
+	printk(KERN_INFO "IPMI %s interface initialized\n",
+	       si_to_str[new_smi->si_type]);
 
 	return 0;
 
@@ -2868,9 +2941,11 @@ static int try_smi_init(struct smi_info *new_smi)
 	if (new_smi->irq_cleanup)
 		new_smi->irq_cleanup(new_smi);
 
-	/* Wait until we know that we are out of any interrupt
-	   handlers might have been running before we freed the
-	   interrupt. */
+	/*
+	 * Wait until we know that we are out of any interrupt
+	 * handlers might have been running before we freed the
+	 * interrupt.
+	 */
 	synchronize_sched();
 
 	if (new_smi->si_sm) {
@@ -2942,11 +3017,10 @@ static __devinit int init_ipmi_si(void)
 
 #ifdef CONFIG_PCI
 	rv = pci_register_driver(&ipmi_pci_driver);
-	if (rv){
+	if (rv)
 		printk(KERN_ERR
 		       "init_ipmi_si: Unable to register PCI driver: %d\n",
 		       rv);
-	}
 #endif
 
 #ifdef CONFIG_PPC_OF
@@ -2975,7 +3049,8 @@ static __devinit int init_ipmi_si(void)
 		of_unregister_platform_driver(&ipmi_of_platform_driver);
 #endif
 		driver_unregister(&ipmi_driver);
-		printk("ipmi_si: Unable to find any System Interface(s)\n");
+		printk(KERN_WARNING
+		       "ipmi_si: Unable to find any System Interface(s)\n");
 		return -ENODEV;
 	} else {
 		mutex_unlock(&smi_infos_lock);
@@ -2997,13 +3072,17 @@ static void cleanup_one_si(struct smi_info *to_clean)
 	/* Tell the driver that we are shutting down. */
 	atomic_inc(&to_clean->stop_operation);
 
-	/* Make sure the timer and thread are stopped and will not run
-	   again. */
+	/*
+	 * Make sure the timer and thread are stopped and will not run
+	 * again.
+	 */
 	wait_for_timer_and_thread(to_clean);
 
-	/* Timeouts are stopped, now make sure the interrupts are off
-	   for the device.  A little tricky with locks to make sure
-	   there are no races. */
+	/*
+	 * Timeouts are stopped, now make sure the interrupts are off
+	 * for the device.  A little tricky with locks to make sure
+	 * there are no races.
+	 */
 	spin_lock_irqsave(&to_clean->si_lock, flags);
 	while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) {
 		spin_unlock_irqrestore(&to_clean->si_lock, flags);
@@ -3074,4 +3153,5 @@ module_exit(cleanup_ipmi_si);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Corey Minyard <minyard@mvista.com>");
-MODULE_DESCRIPTION("Interface to the IPMI driver for the KCS, SMIC, and BT system interfaces.");
+MODULE_DESCRIPTION("Interface to the IPMI driver for the KCS, SMIC, and BT"
+		   " system interfaces.");
diff --git a/trunk/drivers/char/ipmi/ipmi_si_sm.h b/trunk/drivers/char/ipmi/ipmi_si_sm.h
index 4b731b24dc16..df89f73475fb 100644
--- a/trunk/drivers/char/ipmi/ipmi_si_sm.h
+++ b/trunk/drivers/char/ipmi/ipmi_si_sm.h
@@ -34,22 +34,27 @@
  *  675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-/* This is defined by the state machines themselves, it is an opaque
-   data type for them to use. */
+/*
+ * This is defined by the state machines themselves, it is an opaque
+ * data type for them to use.
+ */
 struct si_sm_data;
 
-/* The structure for doing I/O in the state machine.  The state
-   machine doesn't have the actual I/O routines, they are done through
-   this interface. */
-struct si_sm_io
-{
+/*
+ * The structure for doing I/O in the state machine.  The state
+ * machine doesn't have the actual I/O routines, they are done through
+ * this interface.
+ */
+struct si_sm_io {
 	unsigned char (*inputb)(struct si_sm_io *io, unsigned int offset);
 	void (*outputb)(struct si_sm_io *io,
 			unsigned int  offset,
 			unsigned char b);
 
-	/* Generic info used by the actual handling routines, the
-           state machine shouldn't touch these. */
+	/*
+	 * Generic info used by the actual handling routines, the
+	 * state machine shouldn't touch these.
+	 */
 	void __iomem *addr;
 	int  regspacing;
 	int  regsize;
@@ -59,53 +64,67 @@ struct si_sm_io
 };
 
 /* Results of SMI events. */
-enum si_sm_result
-{
+enum si_sm_result {
 	SI_SM_CALL_WITHOUT_DELAY, /* Call the driver again immediately */
 	SI_SM_CALL_WITH_DELAY,	/* Delay some before calling again. */
-	SI_SM_CALL_WITH_TICK_DELAY,	/* Delay at least 1 tick before calling again. */
+	SI_SM_CALL_WITH_TICK_DELAY,/* Delay >=1 tick before calling again. */
 	SI_SM_TRANSACTION_COMPLETE, /* A transaction is finished. */
 	SI_SM_IDLE,		/* The SM is in idle state. */
 	SI_SM_HOSED,		/* The hardware violated the state machine. */
-	SI_SM_ATTN		/* The hardware is asserting attn and the
-				   state machine is idle. */
+
+	/*
+	 * The hardware is asserting attn and the state machine is
+	 * idle.
+	 */
+	SI_SM_ATTN
 };
 
 /* Handlers for the SMI state machine. */
-struct si_sm_handlers
-{
-	/* Put the version number of the state machine here so the
-           upper layer can print it. */
+struct si_sm_handlers {
+	/*
+	 * Put the version number of the state machine here so the
+	 * upper layer can print it.
+	 */
 	char *version;
 
-	/* Initialize the data and return the amount of I/O space to
-           reserve for the space. */
+	/*
+	 * Initialize the data and return the amount of I/O space to
+	 * reserve for the space.
+	 */
 	unsigned int (*init_data)(struct si_sm_data *smi,
 				  struct si_sm_io   *io);
 
-	/* Start a new transaction in the state machine.  This will
-	   return -2 if the state machine is not idle, -1 if the size
-	   is invalid (to large or too small), or 0 if the transaction
-	   is successfully completed. */
+	/*
+	 * Start a new transaction in the state machine.  This will
+	 * return -2 if the state machine is not idle, -1 if the size
+	 * is invalid (to large or too small), or 0 if the transaction
+	 * is successfully completed.
+	 */
 	int (*start_transaction)(struct si_sm_data *smi,
 				 unsigned char *data, unsigned int size);
 
-	/* Return the results after the transaction.  This will return
-	   -1 if the buffer is too small, zero if no transaction is
-	   present, or the actual length of the result data. */
+	/*
+	 * Return the results after the transaction.  This will return
+	 * -1 if the buffer is too small, zero if no transaction is
+	 * present, or the actual length of the result data.
+	 */
 	int (*get_result)(struct si_sm_data *smi,
 			  unsigned char *data, unsigned int length);
 
-	/* Call this periodically (for a polled interface) or upon
-	   receiving an interrupt (for a interrupt-driven interface).
-	   If interrupt driven, you should probably poll this
-	   periodically when not in idle state.  This should be called
-	   with the time that passed since the last call, if it is
-	   significant.  Time is in microseconds. */
+	/*
+	 * Call this periodically (for a polled interface) or upon
+	 * receiving an interrupt (for a interrupt-driven interface).
+	 * If interrupt driven, you should probably poll this
+	 * periodically when not in idle state.  This should be called
+	 * with the time that passed since the last call, if it is
+	 * significant.  Time is in microseconds.
+	 */
 	enum si_sm_result (*event)(struct si_sm_data *smi, long time);
 
-	/* Attempt to detect an SMI.  Returns 0 on success or nonzero
-           on failure. */
+	/*
+	 * Attempt to detect an SMI.  Returns 0 on success or nonzero
+	 * on failure.
+	 */
 	int (*detect)(struct si_sm_data *smi);
 
 	/* The interface is shutting down, so clean it up. */
diff --git a/trunk/drivers/char/ipmi/ipmi_smic_sm.c b/trunk/drivers/char/ipmi/ipmi_smic_sm.c
index e64ea7d25d24..faed92971907 100644
--- a/trunk/drivers/char/ipmi/ipmi_smic_sm.c
+++ b/trunk/drivers/char/ipmi/ipmi_smic_sm.c
@@ -85,6 +85,7 @@ enum smic_states {
 /* SMIC Flags Register Bits */
 #define SMIC_RX_DATA_READY	0x80
 #define SMIC_TX_DATA_READY	0x40
+
 /*
  * SMIC_SMI and SMIC_EVM_DATA_AVAIL are only used by
  * a few systems, and then only by Systems Management
@@ -104,23 +105,22 @@ enum smic_states {
 #define	EC_ILLEGAL_COMMAND	0x04
 #define	EC_BUFFER_FULL		0x05
 
-struct si_sm_data
-{
+struct si_sm_data {
 	enum smic_states state;
 	struct si_sm_io *io;
-        unsigned char	 write_data[MAX_SMIC_WRITE_SIZE];
-        int		 write_pos;
-        int		 write_count;
-        int		 orig_write_count;
-        unsigned char	 read_data[MAX_SMIC_READ_SIZE];
-        int		 read_pos;
-        int		 truncated;
-        unsigned int	 error_retries;
-        long		 smic_timeout;
+	unsigned char	 write_data[MAX_SMIC_WRITE_SIZE];
+	int		 write_pos;
+	int		 write_count;
+	int		 orig_write_count;
+	unsigned char	 read_data[MAX_SMIC_READ_SIZE];
+	int		 read_pos;
+	int		 truncated;
+	unsigned int	 error_retries;
+	long		 smic_timeout;
 };
 
-static unsigned int init_smic_data (struct si_sm_data *smic,
-				    struct si_sm_io *io)
+static unsigned int init_smic_data(struct si_sm_data *smic,
+				   struct si_sm_io *io)
 {
 	smic->state = SMIC_IDLE;
 	smic->io = io;
@@ -150,11 +150,10 @@ static int start_smic_transaction(struct si_sm_data *smic,
 		return IPMI_NOT_IN_MY_STATE_ERR;
 
 	if (smic_debug & SMIC_DEBUG_MSG) {
-		printk(KERN_INFO "start_smic_transaction -");
-		for (i = 0; i < size; i ++) {
-			printk (" %02x", (unsigned char) (data [i]));
-		}
-		printk ("\n");
+		printk(KERN_DEBUG "start_smic_transaction -");
+		for (i = 0; i < size; i++)
+			printk(" %02x", (unsigned char) data[i]);
+		printk("\n");
 	}
 	smic->error_retries = 0;
 	memcpy(smic->write_data, data, size);
@@ -173,11 +172,10 @@ static int smic_get_result(struct si_sm_data *smic,
 	int i;
 
 	if (smic_debug & SMIC_DEBUG_MSG) {
-		printk (KERN_INFO "smic_get result -");
-		for (i = 0; i < smic->read_pos; i ++) {
-			printk (" %02x", (smic->read_data [i]));
-		}
-		printk ("\n");
+		printk(KERN_DEBUG "smic_get result -");
+		for (i = 0; i < smic->read_pos; i++)
+			printk(" %02x", smic->read_data[i]);
+		printk("\n");
 	}
 	if (length < smic->read_pos) {
 		smic->read_pos = length;
@@ -223,8 +221,8 @@ static inline void write_smic_control(struct si_sm_data *smic,
 	smic->io->outputb(smic->io, 1, control);
 }
 
-static inline void write_si_sm_data (struct si_sm_data *smic,
-				   unsigned char   data)
+static inline void write_si_sm_data(struct si_sm_data *smic,
+				    unsigned char   data)
 {
 	smic->io->outputb(smic->io, 0, data);
 }
@@ -233,10 +231,9 @@ static inline void start_error_recovery(struct si_sm_data *smic, char *reason)
 {
 	(smic->error_retries)++;
 	if (smic->error_retries > SMIC_MAX_ERROR_RETRIES) {
-		if (smic_debug & SMIC_DEBUG_ENABLE) {
+		if (smic_debug & SMIC_DEBUG_ENABLE)
 			printk(KERN_WARNING
 			       "ipmi_smic_drv: smic hosed: %s\n", reason);
-		}
 		smic->state = SMIC_HOSED;
 	} else {
 		smic->write_count = smic->orig_write_count;
@@ -254,14 +251,14 @@ static inline void write_next_byte(struct si_sm_data *smic)
 	(smic->write_count)--;
 }
 
-static inline void read_next_byte (struct si_sm_data *smic)
+static inline void read_next_byte(struct si_sm_data *smic)
 {
 	if (smic->read_pos >= MAX_SMIC_READ_SIZE) {
-		read_smic_data (smic);
+		read_smic_data(smic);
 		smic->truncated = 1;
 	} else {
 		smic->read_data[smic->read_pos] = read_smic_data(smic);
-		(smic->read_pos)++;
+		smic->read_pos++;
 	}
 }
 
@@ -336,7 +333,7 @@ static inline void read_next_byte (struct si_sm_data *smic)
 	SMIC_SC_SMS_RD_END	0xC6
 */
 
-static enum si_sm_result smic_event (struct si_sm_data *smic, long time)
+static enum si_sm_result smic_event(struct si_sm_data *smic, long time)
 {
 	unsigned char status;
 	unsigned char flags;
@@ -347,13 +344,15 @@ static enum si_sm_result smic_event (struct si_sm_data *smic, long time)
 		return SI_SM_HOSED;
 	}
 	if (smic->state != SMIC_IDLE) {
-		if (smic_debug & SMIC_DEBUG_STATES) {
-			printk(KERN_INFO
+		if (smic_debug & SMIC_DEBUG_STATES)
+			printk(KERN_DEBUG
 			       "smic_event - smic->smic_timeout = %ld,"
 			       " time = %ld\n",
 			       smic->smic_timeout, time);
-		}
-/* FIXME: smic_event is sometimes called with time > SMIC_RETRY_TIMEOUT */
+		/*
+		 * FIXME: smic_event is sometimes called with time >
+		 * SMIC_RETRY_TIMEOUT
+		 */
 		if (time < SMIC_RETRY_TIMEOUT) {
 			smic->smic_timeout -= time;
 			if (smic->smic_timeout < 0) {
@@ -366,9 +365,9 @@ static enum si_sm_result smic_event (struct si_sm_data *smic, long time)
 	if (flags & SMIC_FLAG_BSY)
 		return SI_SM_CALL_WITH_DELAY;
 
-	status = read_smic_status (smic);
+	status = read_smic_status(smic);
 	if (smic_debug & SMIC_DEBUG_STATES)
-		printk(KERN_INFO
+		printk(KERN_DEBUG
 		       "smic_event - state = %d, flags = 0x%02x,"
 		       " status = 0x%02x\n",
 		       smic->state, flags, status);
@@ -377,9 +376,7 @@ static enum si_sm_result smic_event (struct si_sm_data *smic, long time)
 	case SMIC_IDLE:
 		/* in IDLE we check for available messages */
 		if (flags & SMIC_SMS_DATA_AVAIL)
-		{
 			return SI_SM_ATTN;
-		}
 		return SI_SM_IDLE;
 
 	case SMIC_START_OP:
@@ -391,7 +388,7 @@ static enum si_sm_result smic_event (struct si_sm_data *smic, long time)
 
 	case SMIC_OP_OK:
 		if (status != SMIC_SC_SMS_READY) {
-				/* this should not happen */
+			/* this should not happen */
 			start_error_recovery(smic,
 					     "state = SMIC_OP_OK,"
 					     " status != SMIC_SC_SMS_READY");
@@ -411,8 +408,10 @@ static enum si_sm_result smic_event (struct si_sm_data *smic, long time)
 					     "status != SMIC_SC_SMS_WR_START");
 			return SI_SM_CALL_WITH_DELAY;
 		}
-		/* we must not issue WR_(NEXT|END) unless
-                   TX_DATA_READY is set */
+		/*
+		 * we must not issue WR_(NEXT|END) unless
+		 * TX_DATA_READY is set
+		 * */
 		if (flags & SMIC_TX_DATA_READY) {
 			if (smic->write_count == 1) {
 				/* last byte */
@@ -424,10 +423,8 @@ static enum si_sm_result smic_event (struct si_sm_data *smic, long time)
 			}
 			write_next_byte(smic);
 			write_smic_flags(smic, flags | SMIC_FLAG_BSY);
-		}
-		else {
+		} else
 			return SI_SM_CALL_WITH_DELAY;
-		}
 		break;
 
 	case SMIC_WRITE_NEXT:
@@ -442,52 +439,48 @@ static enum si_sm_result smic_event (struct si_sm_data *smic, long time)
 			if (smic->write_count == 1) {
 				write_smic_control(smic, SMIC_CC_SMS_WR_END);
 				smic->state = SMIC_WRITE_END;
-			}
-			else {
+			} else {
 				write_smic_control(smic, SMIC_CC_SMS_WR_NEXT);
 				smic->state = SMIC_WRITE_NEXT;
 			}
 			write_next_byte(smic);
 			write_smic_flags(smic, flags | SMIC_FLAG_BSY);
-		}
-		else {
+		} else
 			return SI_SM_CALL_WITH_DELAY;
-		}
 		break;
 
 	case SMIC_WRITE_END:
 		if (status != SMIC_SC_SMS_WR_END) {
-			start_error_recovery (smic,
-					      "state = SMIC_WRITE_END, "
-					      "status != SMIC_SC_SMS_WR_END");
+			start_error_recovery(smic,
+					     "state = SMIC_WRITE_END, "
+					     "status != SMIC_SC_SMS_WR_END");
 			return SI_SM_CALL_WITH_DELAY;
 		}
 		/* data register holds an error code */
 		data = read_smic_data(smic);
 		if (data != 0) {
-			if (smic_debug & SMIC_DEBUG_ENABLE) {
-				printk(KERN_INFO
+			if (smic_debug & SMIC_DEBUG_ENABLE)
+				printk(KERN_DEBUG
 				       "SMIC_WRITE_END: data = %02x\n", data);
-			}
 			start_error_recovery(smic,
 					     "state = SMIC_WRITE_END, "
 					     "data != SUCCESS");
 			return SI_SM_CALL_WITH_DELAY;
-		} else {
+		} else
 			smic->state = SMIC_WRITE2READ;
-		}
 		break;
 
 	case SMIC_WRITE2READ:
-		/* we must wait for RX_DATA_READY to be set before we
-                   can continue */
+		/*
+		 * we must wait for RX_DATA_READY to be set before we
+		 * can continue
+		 */
 		if (flags & SMIC_RX_DATA_READY) {
 			write_smic_control(smic, SMIC_CC_SMS_RD_START);
 			write_smic_flags(smic, flags | SMIC_FLAG_BSY);
 			smic->state = SMIC_READ_START;
-		} else {
+		} else
 			return SI_SM_CALL_WITH_DELAY;
-		}
 		break;
 
 	case SMIC_READ_START:
@@ -502,15 +495,16 @@ static enum si_sm_result smic_event (struct si_sm_data *smic, long time)
 			write_smic_control(smic, SMIC_CC_SMS_RD_NEXT);
 			write_smic_flags(smic, flags | SMIC_FLAG_BSY);
 			smic->state = SMIC_READ_NEXT;
-		} else {
+		} else
 			return SI_SM_CALL_WITH_DELAY;
-		}
 		break;
 
 	case SMIC_READ_NEXT:
 		switch (status) {
-		/* smic tells us that this is the last byte to be read
-                   --> clean up */
+		/*
+		 * smic tells us that this is the last byte to be read
+		 * --> clean up
+		 */
 		case SMIC_SC_SMS_RD_END:
 			read_next_byte(smic);
 			write_smic_control(smic, SMIC_CC_SMS_RD_END);
@@ -523,9 +517,8 @@ static enum si_sm_result smic_event (struct si_sm_data *smic, long time)
 				write_smic_control(smic, SMIC_CC_SMS_RD_NEXT);
 				write_smic_flags(smic, flags | SMIC_FLAG_BSY);
 				smic->state = SMIC_READ_NEXT;
-			} else {
+			} else
 				return SI_SM_CALL_WITH_DELAY;
-			}
 			break;
 		default:
 			start_error_recovery(
@@ -546,10 +539,9 @@ static enum si_sm_result smic_event (struct si_sm_data *smic, long time)
 		data = read_smic_data(smic);
 		/* data register holds an error code */
 		if (data != 0) {
-			if (smic_debug & SMIC_DEBUG_ENABLE) {
-				printk(KERN_INFO
+			if (smic_debug & SMIC_DEBUG_ENABLE)
+				printk(KERN_DEBUG
 				       "SMIC_READ_END: data = %02x\n", data);
-			}
 			start_error_recovery(smic,
 					     "state = SMIC_READ_END, "
 					     "data != SUCCESS");
@@ -565,7 +557,7 @@ static enum si_sm_result smic_event (struct si_sm_data *smic, long time)
 
 	default:
 		if (smic_debug & SMIC_DEBUG_ENABLE) {
-			printk(KERN_WARNING "smic->state = %d\n", smic->state);
+			printk(KERN_DEBUG "smic->state = %d\n", smic->state);
 			start_error_recovery(smic, "state = UNKNOWN");
 			return SI_SM_CALL_WITH_DELAY;
 		}
@@ -576,10 +568,12 @@ static enum si_sm_result smic_event (struct si_sm_data *smic, long time)
 
 static int smic_detect(struct si_sm_data *smic)
 {
-	/* It's impossible for the SMIC fnags register to be all 1's,
-	   (assuming a properly functioning, self-initialized BMC)
-	   but that's what you get from reading a bogus address, so we
-	   test that first. */
+	/*
+	 * It's impossible for the SMIC fnags register to be all 1's,
+	 * (assuming a properly functioning, self-initialized BMC)
+	 * but that's what you get from reading a bogus address, so we
+	 * test that first.
+	 */
 	if (read_smic_flags(smic) == 0xff)
 		return 1;
 
@@ -595,8 +589,7 @@ static int smic_size(void)
 	return sizeof(struct si_sm_data);
 }
 
-struct si_sm_handlers smic_smi_handlers =
-{
+struct si_sm_handlers smic_smi_handlers = {
 	.init_data         = init_smic_data,
 	.start_transaction = start_smic_transaction,
 	.get_result        = smic_get_result,
diff --git a/trunk/drivers/char/ipmi/ipmi_watchdog.c b/trunk/drivers/char/ipmi/ipmi_watchdog.c
index 8f45ca9235ad..1b9a87047817 100644
--- a/trunk/drivers/char/ipmi/ipmi_watchdog.c
+++ b/trunk/drivers/char/ipmi/ipmi_watchdog.c
@@ -54,13 +54,15 @@
 #include <asm/atomic.h>
 
 #ifdef CONFIG_X86
-/* This is ugly, but I've determined that x86 is the only architecture
-   that can reasonably support the IPMI NMI watchdog timeout at this
-   time.  If another architecture adds this capability somehow, it
-   will have to be a somewhat different mechanism and I have no idea
-   how it will work.  So in the unlikely event that another
-   architecture supports this, we can figure out a good generic
-   mechanism for it at that time. */
+/*
+ * This is ugly, but I've determined that x86 is the only architecture
+ * that can reasonably support the IPMI NMI watchdog timeout at this
+ * time.  If another architecture adds this capability somehow, it
+ * will have to be a somewhat different mechanism and I have no idea
+ * how it will work.  So in the unlikely event that another
+ * architecture supports this, we can figure out a good generic
+ * mechanism for it at that time.
+ */
 #include <asm/kdebug.h>
 #define HAVE_DIE_NMI
 #endif
@@ -95,9 +97,8 @@
 /* Operations that can be performed on a pretimout. */
 #define WDOG_PREOP_NONE		0
 #define WDOG_PREOP_PANIC	1
-#define WDOG_PREOP_GIVE_DATA	2 /* Cause data to be available to
-                                     read.  Doesn't work in NMI
-                                     mode. */
+/* Cause data to be available to read.  Doesn't work in NMI mode. */
+#define WDOG_PREOP_GIVE_DATA	2
 
 /* Actions to perform on a full timeout. */
 #define WDOG_SET_TIMEOUT_ACT(byte, use) \
@@ -108,8 +109,10 @@
 #define WDOG_TIMEOUT_POWER_DOWN		2
 #define WDOG_TIMEOUT_POWER_CYCLE	3
 
-/* Byte 3 of the get command, byte 4 of the get response is the
-   pre-timeout in seconds. */
+/*
+ * Byte 3 of the get command, byte 4 of the get response is the
+ * pre-timeout in seconds.
+ */
 
 /* Bits for setting byte 4 of the set command, byte 5 of the get response. */
 #define WDOG_EXPIRE_CLEAR_BIOS_FRB2	(1 << 1)
@@ -118,11 +121,13 @@
 #define WDOG_EXPIRE_CLEAR_SMS_OS	(1 << 4)
 #define WDOG_EXPIRE_CLEAR_OEM		(1 << 5)
 
-/* Setting/getting the watchdog timer value.  This is for bytes 5 and
-   6 (the timeout time) of the set command, and bytes 6 and 7 (the
-   timeout time) and 8 and 9 (the current countdown value) of the
-   response.  The timeout value is given in seconds (in the command it
-   is 100ms intervals). */
+/*
+ * Setting/getting the watchdog timer value.  This is for bytes 5 and
+ * 6 (the timeout time) of the set command, and bytes 6 and 7 (the
+ * timeout time) and 8 and 9 (the current countdown value) of the
+ * response.  The timeout value is given in seconds (in the command it
+ * is 100ms intervals).
+ */
 #define WDOG_SET_TIMEOUT(byte1, byte2, val) \
 	(byte1) = (((val) * 10) & 0xff), (byte2) = (((val) * 10) >> 8)
 #define WDOG_GET_TIMEOUT(byte1, byte2) \
@@ -184,8 +189,10 @@ static int ipmi_set_timeout(int do_heartbeat);
 static void ipmi_register_watchdog(int ipmi_intf);
 static void ipmi_unregister_watchdog(int ipmi_intf);
 
-/* If true, the driver will start running as soon as it is configured
-   and ready. */
+/*
+ * If true, the driver will start running as soon as it is configured
+ * and ready.
+ */
 static int start_now;
 
 static int set_param_int(const char *val, struct kernel_param *kp)
@@ -309,10 +316,12 @@ static int ipmi_ignore_heartbeat;
 /* Is someone using the watchdog?  Only one user is allowed. */
 static unsigned long ipmi_wdog_open;
 
-/* If set to 1, the heartbeat command will set the state to reset and
-   start the timer.  The timer doesn't normally run when the driver is
-   first opened until the heartbeat is set the first time, this
-   variable is used to accomplish this. */
+/*
+ * If set to 1, the heartbeat command will set the state to reset and
+ * start the timer.  The timer doesn't normally run when the driver is
+ * first opened until the heartbeat is set the first time, this
+ * variable is used to accomplish this.
+ */
 static int ipmi_start_timer_on_heartbeat;
 
 /* IPMI version of the BMC. */
@@ -329,10 +338,12 @@ static int nmi_handler_registered;
 
 static int ipmi_heartbeat(void);
 
-/* We use a mutex to make sure that only one thing can send a set
-   timeout at one time, because we only have one copy of the data.
-   The mutex is claimed when the set_timeout is sent and freed
-   when both messages are free. */
+/*
+ * We use a mutex to make sure that only one thing can send a set
+ * timeout at one time, because we only have one copy of the data.
+ * The mutex is claimed when the set_timeout is sent and freed
+ * when both messages are free.
+ */
 static atomic_t set_timeout_tofree = ATOMIC_INIT(0);
 static DEFINE_MUTEX(set_timeout_lock);
 static DECLARE_COMPLETION(set_timeout_wait);
@@ -346,15 +357,13 @@ static void set_timeout_free_recv(struct ipmi_recv_msg *msg)
     if (atomic_dec_and_test(&set_timeout_tofree))
 	    complete(&set_timeout_wait);
 }
-static struct ipmi_smi_msg set_timeout_smi_msg =
-{
+static struct ipmi_smi_msg set_timeout_smi_msg = {
 	.done = set_timeout_free_smi
 };
-static struct ipmi_recv_msg set_timeout_recv_msg =
-{
+static struct ipmi_recv_msg set_timeout_recv_msg = {
 	.done = set_timeout_free_recv
 };
- 
+
 static int i_ipmi_set_timeout(struct ipmi_smi_msg  *smi_msg,
 			      struct ipmi_recv_msg *recv_msg,
 			      int                  *send_heartbeat_now)
@@ -373,13 +382,14 @@ static int i_ipmi_set_timeout(struct ipmi_smi_msg  *smi_msg,
 	WDOG_SET_TIMER_USE(data[0], WDOG_TIMER_USE_SMS_OS);
 
 	if ((ipmi_version_major > 1)
-	    || ((ipmi_version_major == 1) && (ipmi_version_minor >= 5)))
-	{
+	    || ((ipmi_version_major == 1) && (ipmi_version_minor >= 5))) {
 		/* This is an IPMI 1.5-only feature. */
 		data[0] |= WDOG_DONT_STOP_ON_SET;
 	} else if (ipmi_watchdog_state != WDOG_TIMEOUT_NONE) {
-		/* In ipmi 1.0, setting the timer stops the watchdog, we
-		   need to start it back up again. */
+		/*
+		 * In ipmi 1.0, setting the timer stops the watchdog, we
+		 * need to start it back up again.
+		 */
 		hbnow = 1;
 	}
 
@@ -465,12 +475,10 @@ static void panic_recv_free(struct ipmi_recv_msg *msg)
 	atomic_dec(&panic_done_count);
 }
 
-static struct ipmi_smi_msg panic_halt_heartbeat_smi_msg =
-{
+static struct ipmi_smi_msg panic_halt_heartbeat_smi_msg = {
 	.done = panic_smi_free
 };
-static struct ipmi_recv_msg panic_halt_heartbeat_recv_msg =
-{
+static struct ipmi_recv_msg panic_halt_heartbeat_recv_msg = {
 	.done = panic_recv_free
 };
 
@@ -480,8 +488,10 @@ static void panic_halt_ipmi_heartbeat(void)
 	struct ipmi_system_interface_addr addr;
 	int rv;
 
-	/* Don't reset the timer if we have the timer turned off, that
-           re-enables the watchdog. */
+	/*
+	 * Don't reset the timer if we have the timer turned off, that
+	 * re-enables the watchdog.
+	 */
 	if (ipmi_watchdog_state == WDOG_TIMEOUT_NONE)
 		return;
 
@@ -505,19 +515,19 @@ static void panic_halt_ipmi_heartbeat(void)
 		atomic_add(2, &panic_done_count);
 }
 
-static struct ipmi_smi_msg panic_halt_smi_msg =
-{
+static struct ipmi_smi_msg panic_halt_smi_msg = {
 	.done = panic_smi_free
 };
-static struct ipmi_recv_msg panic_halt_recv_msg =
-{
+static struct ipmi_recv_msg panic_halt_recv_msg = {
 	.done = panic_recv_free
 };
 
-/* Special call, doesn't claim any locks.  This is only to be called
-   at panic or halt time, in run-to-completion mode, when the caller
-   is the only CPU and the only thing that will be going is these IPMI
-   calls. */
+/*
+ * Special call, doesn't claim any locks.  This is only to be called
+ * at panic or halt time, in run-to-completion mode, when the caller
+ * is the only CPU and the only thing that will be going is these IPMI
+ * calls.
+ */
 static void panic_halt_ipmi_set_timeout(void)
 {
 	int send_heartbeat_now;
@@ -540,10 +550,12 @@ static void panic_halt_ipmi_set_timeout(void)
 		ipmi_poll_interface(watchdog_user);
 }
 
-/* We use a semaphore to make sure that only one thing can send a
-   heartbeat at one time, because we only have one copy of the data.
-   The semaphore is claimed when the set_timeout is sent and freed
-   when both messages are free. */
+/*
+ * We use a mutex to make sure that only one thing can send a
+ * heartbeat at one time, because we only have one copy of the data.
+ * The semaphore is claimed when the set_timeout is sent and freed
+ * when both messages are free.
+ */
 static atomic_t heartbeat_tofree = ATOMIC_INIT(0);
 static DEFINE_MUTEX(heartbeat_lock);
 static DECLARE_COMPLETION(heartbeat_wait);
@@ -557,15 +569,13 @@ static void heartbeat_free_recv(struct ipmi_recv_msg *msg)
     if (atomic_dec_and_test(&heartbeat_tofree))
 	    complete(&heartbeat_wait);
 }
-static struct ipmi_smi_msg heartbeat_smi_msg =
-{
+static struct ipmi_smi_msg heartbeat_smi_msg = {
 	.done = heartbeat_free_smi
 };
-static struct ipmi_recv_msg heartbeat_recv_msg =
-{
+static struct ipmi_recv_msg heartbeat_recv_msg = {
 	.done = heartbeat_free_recv
 };
- 
+
 static int ipmi_heartbeat(void)
 {
 	struct kernel_ipmi_msg            msg;
@@ -580,10 +590,12 @@ static int ipmi_heartbeat(void)
 		ipmi_watchdog_state = action_val;
 		return ipmi_set_timeout(IPMI_SET_TIMEOUT_FORCE_HB);
 	} else if (pretimeout_since_last_heartbeat) {
-		/* A pretimeout occurred, make sure we set the timeout.
-		   We don't want to set the action, though, we want to
-		   leave that alone (thus it can't be combined with the
-		   above operation. */
+		/*
+		 * A pretimeout occurred, make sure we set the timeout.
+		 * We don't want to set the action, though, we want to
+		 * leave that alone (thus it can't be combined with the
+		 * above operation.
+		 */
 		return ipmi_set_timeout(IPMI_SET_TIMEOUT_HB_IF_NECESSARY);
 	}
 
@@ -591,8 +603,10 @@ static int ipmi_heartbeat(void)
 
 	atomic_set(&heartbeat_tofree, 2);
 
-	/* Don't reset the timer if we have the timer turned off, that
-           re-enables the watchdog. */
+	/*
+	 * Don't reset the timer if we have the timer turned off, that
+	 * re-enables the watchdog.
+	 */
 	if (ipmi_watchdog_state == WDOG_TIMEOUT_NONE) {
 		mutex_unlock(&heartbeat_lock);
 		return 0;
@@ -625,10 +639,12 @@ static int ipmi_heartbeat(void)
 	wait_for_completion(&heartbeat_wait);
 
 	if (heartbeat_recv_msg.msg.data[0] != 0) {
-	    /* Got an error in the heartbeat response.  It was already
-	       reported in ipmi_wdog_msg_handler, but we should return
-	       an error here. */
-	    rv = -EINVAL;
+		/*
+		 * Got an error in the heartbeat response.  It was already
+		 * reported in ipmi_wdog_msg_handler, but we should return
+		 * an error here.
+		 */
+		rv = -EINVAL;
 	}
 
 	mutex_unlock(&heartbeat_lock);
@@ -636,8 +652,7 @@ static int ipmi_heartbeat(void)
 	return rv;
 }
 
-static struct watchdog_info ident =
-{
+static struct watchdog_info ident = {
 	.options	= 0,	/* WDIOF_SETTIMEOUT, */
 	.firmware_version = 1,
 	.identity	= "IPMI"
@@ -650,7 +665,7 @@ static int ipmi_ioctl(struct inode *inode, struct file *file,
 	int i;
 	int val;
 
-	switch(cmd) {
+	switch (cmd) {
 	case WDIOC_GETSUPPORT:
 		i = copy_to_user(argp, &ident, sizeof(ident));
 		return i ? -EFAULT : 0;
@@ -690,15 +705,13 @@ static int ipmi_ioctl(struct inode *inode, struct file *file,
 		i = copy_from_user(&val, argp, sizeof(int));
 		if (i)
 			return -EFAULT;
-		if (val & WDIOS_DISABLECARD)
-		{
+		if (val & WDIOS_DISABLECARD) {
 			ipmi_watchdog_state = WDOG_TIMEOUT_NONE;
 			ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB);
 			ipmi_start_timer_on_heartbeat = 0;
 		}
 
-		if (val & WDIOS_ENABLECARD)
-		{
+		if (val & WDIOS_ENABLECARD) {
 			ipmi_watchdog_state = action_val;
 			ipmi_set_timeout(IPMI_SET_TIMEOUT_FORCE_HB);
 		}
@@ -724,13 +737,13 @@ static ssize_t ipmi_write(struct file *file,
 	int rv;
 
 	if (len) {
-	    	if (!nowayout) {
-		    	size_t i;
+		if (!nowayout) {
+			size_t i;
 
 			/* In case it was set long ago */
 			expect_close = 0;
 
-    			for (i = 0; i != len; i++) {
+			for (i = 0; i != len; i++) {
 				char c;
 
 				if (get_user(c, buf + i))
@@ -758,15 +771,17 @@ static ssize_t ipmi_read(struct file *file,
 	if (count <= 0)
 		return 0;
 
-	/* Reading returns if the pretimeout has gone off, and it only does
-	   it once per pretimeout. */
+	/*
+	 * Reading returns if the pretimeout has gone off, and it only does
+	 * it once per pretimeout.
+	 */
 	spin_lock(&ipmi_read_lock);
 	if (!data_to_read) {
 		if (file->f_flags & O_NONBLOCK) {
 			rv = -EAGAIN;
 			goto out;
 		}
-		
+
 		init_waitqueue_entry(&wait, current);
 		add_wait_queue(&read_q, &wait);
 		while (!data_to_read) {
@@ -776,7 +791,7 @@ static ssize_t ipmi_read(struct file *file,
 			spin_lock(&ipmi_read_lock);
 		}
 		remove_wait_queue(&read_q, &wait);
-	    
+
 		if (signal_pending(current)) {
 			rv = -ERESTARTSYS;
 			goto out;
@@ -799,25 +814,27 @@ static ssize_t ipmi_read(struct file *file,
 
 static int ipmi_open(struct inode *ino, struct file *filep)
 {
-        switch (iminor(ino)) {
-        case WATCHDOG_MINOR:
+	switch (iminor(ino)) {
+	case WATCHDOG_MINOR:
 		if (test_and_set_bit(0, &ipmi_wdog_open))
-                        return -EBUSY;
+			return -EBUSY;
 
-		/* Don't start the timer now, let it start on the
-		   first heartbeat. */
+		/*
+		 * Don't start the timer now, let it start on the
+		 * first heartbeat.
+		 */
 		ipmi_start_timer_on_heartbeat = 1;
 		return nonseekable_open(ino, filep);
 
 	default:
 		return (-ENODEV);
-        }
+	}
 }
 
 static unsigned int ipmi_poll(struct file *file, poll_table *wait)
 {
 	unsigned int mask = 0;
-	
+
 	poll_wait(file, &read_q, wait);
 
 	spin_lock(&ipmi_read_lock);
@@ -851,7 +868,7 @@ static int ipmi_close(struct inode *ino, struct file *filep)
 		clear_bit(0, &ipmi_wdog_open);
 	}
 
-	ipmi_fasync (-1, filep, 0);
+	ipmi_fasync(-1, filep, 0);
 	expect_close = 0;
 
 	return 0;
@@ -882,7 +899,7 @@ static void ipmi_wdog_msg_handler(struct ipmi_recv_msg *msg,
 		       msg->msg.data[0],
 		       msg->msg.cmd);
 	}
-	
+
 	ipmi_free_recv_msg(msg);
 }
 
@@ -902,14 +919,14 @@ static void ipmi_wdog_pretimeout_handler(void *handler_data)
 		}
 	}
 
-	/* On some machines, the heartbeat will give
-	   an error and not work unless we re-enable
-	   the timer.   So do so. */
+	/*
+	 * On some machines, the heartbeat will give an error and not
+	 * work unless we re-enable the timer.  So do so.
+	 */
 	pretimeout_since_last_heartbeat = 1;
 }
 
-static struct ipmi_user_hndl ipmi_hndlrs =
-{
+static struct ipmi_user_hndl ipmi_hndlrs = {
 	.ipmi_recv_hndl           = ipmi_wdog_msg_handler,
 	.ipmi_watchdog_pretimeout = ipmi_wdog_pretimeout_handler
 };
@@ -949,8 +966,10 @@ static void ipmi_register_watchdog(int ipmi_intf)
 		int old_timeout = timeout;
 		int old_preop_val = preop_val;
 
-		/* Set the pretimeout to go off in a second and give
-		   ourselves plenty of time to stop the timer. */
+		/*
+		 * Set the pretimeout to go off in a second and give
+		 * ourselves plenty of time to stop the timer.
+		 */
 		ipmi_watchdog_state = WDOG_TIMEOUT_RESET;
 		preop_val = WDOG_PREOP_NONE; /* Make sure nothing happens */
 		pretimeout = 99;
@@ -974,7 +993,7 @@ static void ipmi_register_watchdog(int ipmi_intf)
 			       " occur.  The NMI pretimeout will"
 			       " likely not work\n");
 		}
-	out_restore:
+ out_restore:
 		testing_nmi = 0;
 		preop_val = old_preop_val;
 		pretimeout = old_pretimeout;
@@ -1009,9 +1028,11 @@ static void ipmi_unregister_watchdog(int ipmi_intf)
 	/* Make sure no one can call us any more. */
 	misc_deregister(&ipmi_wdog_miscdev);
 
-	/* Wait to make sure the message makes it out.  The lower layer has
-	   pointers to our buffers, we want to make sure they are done before
-	   we release our memory. */
+	/*
+	 * Wait to make sure the message makes it out.  The lower layer has
+	 * pointers to our buffers, we want to make sure they are done before
+	 * we release our memory.
+	 */
 	while (atomic_read(&set_timeout_tofree))
 		schedule_timeout_uninterruptible(1);
 
@@ -1052,15 +1073,17 @@ ipmi_nmi(struct notifier_block *self, unsigned long val, void *data)
 		return NOTIFY_STOP;
 	}
 
-        /* If we are not expecting a timeout, ignore it. */
+	/* If we are not expecting a timeout, ignore it. */
 	if (ipmi_watchdog_state == WDOG_TIMEOUT_NONE)
 		return NOTIFY_OK;
 
 	if (preaction_val != WDOG_PRETIMEOUT_NMI)
 		return NOTIFY_OK;
 
-	/* If no one else handled the NMI, we assume it was the IPMI
-           watchdog. */
+	/*
+	 * If no one else handled the NMI, we assume it was the IPMI
+	 * watchdog.
+	 */
 	if (preop_val == WDOG_PREOP_PANIC) {
 		/* On some machines, the heartbeat will give
 		   an error and not work unless we re-enable
@@ -1082,7 +1105,7 @@ static int wdog_reboot_handler(struct notifier_block *this,
 			       unsigned long         code,
 			       void                  *unused)
 {
-	static int reboot_event_handled = 0;
+	static int reboot_event_handled;
 
 	if ((watchdog_user) && (!reboot_event_handled)) {
 		/* Make sure we only do this once. */
@@ -1115,7 +1138,7 @@ static int wdog_panic_handler(struct notifier_block *this,
 			      unsigned long         event,
 			      void                  *unused)
 {
-	static int panic_event_handled = 0;
+	static int panic_event_handled;
 
 	/* On a panic, if we have a panic timeout, make sure to extend
 	   the watchdog timer to a reasonable value to complete the
@@ -1125,7 +1148,7 @@ static int wdog_panic_handler(struct notifier_block *this,
 	    ipmi_watchdog_state != WDOG_TIMEOUT_NONE) {
 		/* Make sure we do this only once. */
 		panic_event_handled = 1;
-	    
+
 		timeout = 255;
 		pretimeout = 0;
 		panic_halt_ipmi_set_timeout();
@@ -1151,8 +1174,7 @@ static void ipmi_smi_gone(int if_num)
 	ipmi_unregister_watchdog(if_num);
 }
 
-static struct ipmi_smi_watcher smi_watcher =
-{
+static struct ipmi_smi_watcher smi_watcher = {
 	.owner    = THIS_MODULE,
 	.new_smi  = ipmi_new_smi,
 	.smi_gone = ipmi_smi_gone
diff --git a/trunk/drivers/char/mem.c b/trunk/drivers/char/mem.c
index e83623ead441..934ffafedaea 100644
--- a/trunk/drivers/char/mem.c
+++ b/trunk/drivers/char/mem.c
@@ -364,6 +364,7 @@ static int mmap_mem(struct file * file, struct vm_area_struct * vma)
 	return 0;
 }
 
+#ifdef CONFIG_DEVKMEM
 static int mmap_kmem(struct file * file, struct vm_area_struct * vma)
 {
 	unsigned long pfn;
@@ -384,6 +385,7 @@ static int mmap_kmem(struct file * file, struct vm_area_struct * vma)
 	vma->vm_pgoff = pfn;
 	return mmap_mem(file, vma);
 }
+#endif
 
 #ifdef CONFIG_CRASH_DUMP
 /*
@@ -422,6 +424,7 @@ static ssize_t read_oldmem(struct file *file, char __user *buf,
 extern long vread(char *buf, char *addr, unsigned long count);
 extern long vwrite(char *buf, char *addr, unsigned long count);
 
+#ifdef CONFIG_DEVKMEM
 /*
  * This function reads the *virtual* memory as seen by the kernel.
  */
@@ -626,6 +629,7 @@ static ssize_t write_kmem(struct file * file, const char __user * buf,
  	*ppos = p;
  	return virtr + wrote;
 }
+#endif
 
 #ifdef CONFIG_DEVPORT
 static ssize_t read_port(struct file * file, char __user * buf,
@@ -803,6 +807,7 @@ static const struct file_operations mem_fops = {
 	.get_unmapped_area = get_unmapped_area_mem,
 };
 
+#ifdef CONFIG_DEVKMEM
 static const struct file_operations kmem_fops = {
 	.llseek		= memory_lseek,
 	.read		= read_kmem,
@@ -811,6 +816,7 @@ static const struct file_operations kmem_fops = {
 	.open		= open_kmem,
 	.get_unmapped_area = get_unmapped_area_mem,
 };
+#endif
 
 static const struct file_operations null_fops = {
 	.llseek		= null_lseek,
@@ -889,11 +895,13 @@ static int memory_open(struct inode * inode, struct file * filp)
 			filp->f_mapping->backing_dev_info =
 				&directly_mappable_cdev_bdi;
 			break;
+#ifdef CONFIG_DEVKMEM
 		case 2:
 			filp->f_op = &kmem_fops;
 			filp->f_mapping->backing_dev_info =
 				&directly_mappable_cdev_bdi;
 			break;
+#endif
 		case 3:
 			filp->f_op = &null_fops;
 			break;
@@ -942,7 +950,9 @@ static const struct {
 	const struct file_operations	*fops;
 } devlist[] = { /* list of minor devices */
 	{1, "mem",     S_IRUSR | S_IWUSR | S_IRGRP, &mem_fops},
+#ifdef CONFIG_DEVKMEM
 	{2, "kmem",    S_IRUSR | S_IWUSR | S_IRGRP, &kmem_fops},
+#endif
 	{3, "null",    S_IRUGO | S_IWUGO,           &null_fops},
 #ifdef CONFIG_DEVPORT
 	{4, "port",    S_IRUSR | S_IWUSR | S_IRGRP, &port_fops},
diff --git a/trunk/drivers/char/misc.c b/trunk/drivers/char/misc.c
index 4d058dadbfcc..eaace0db0ff4 100644
--- a/trunk/drivers/char/misc.c
+++ b/trunk/drivers/char/misc.c
@@ -263,23 +263,26 @@ EXPORT_SYMBOL(misc_deregister);
 
 static int __init misc_init(void)
 {
-#ifdef CONFIG_PROC_FS
-	struct proc_dir_entry *ent;
+	int err;
 
-	ent = create_proc_entry("misc", 0, NULL);
-	if (ent)
-		ent->proc_fops = &misc_proc_fops;
+#ifdef CONFIG_PROC_FS
+	proc_create("misc", 0, NULL, &misc_proc_fops);
 #endif
 	misc_class = class_create(THIS_MODULE, "misc");
+	err = PTR_ERR(misc_class);
 	if (IS_ERR(misc_class))
-		return PTR_ERR(misc_class);
+		goto fail_remove;
 
-	if (register_chrdev(MISC_MAJOR,"misc",&misc_fops)) {
-		printk("unable to get major %d for misc devices\n",
-		       MISC_MAJOR);
-		class_destroy(misc_class);
-		return -EIO;
-	}
+	err = -EIO;
+	if (register_chrdev(MISC_MAJOR,"misc",&misc_fops))
+		goto fail_printk;
 	return 0;
+
+fail_printk:
+	printk("unable to get major %d for misc devices\n", MISC_MAJOR);
+	class_destroy(misc_class);
+fail_remove:
+	remove_proc_entry("misc", NULL);
+	return err;
 }
 subsys_initcall(misc_init);
diff --git a/trunk/drivers/char/n_hdlc.c b/trunk/drivers/char/n_hdlc.c
index 82bcfb9c839a..06803ed5568c 100644
--- a/trunk/drivers/char/n_hdlc.c
+++ b/trunk/drivers/char/n_hdlc.c
@@ -501,7 +501,7 @@ static void n_hdlc_tty_receive(struct tty_struct *tty, const __u8 *data,
 			__FILE__,__LINE__, count);
 		
 	/* This can happen if stuff comes in on the backup tty */
-	if (n_hdlc == 0 || tty != n_hdlc->tty)
+	if (!n_hdlc || tty != n_hdlc->tty)
 		return;
 		
 	/* verify line is using HDLC discipline */
diff --git a/trunk/drivers/char/pcmcia/ipwireless/hardware.c b/trunk/drivers/char/pcmcia/ipwireless/hardware.c
index 1f978ff87fa8..fa9d3c945f31 100644
--- a/trunk/drivers/char/pcmcia/ipwireless/hardware.c
+++ b/trunk/drivers/char/pcmcia/ipwireless/hardware.c
@@ -354,32 +354,6 @@ struct ipw_rx_packet {
 	unsigned int channel_idx;
 };
 
-#ifdef IPWIRELESS_STATE_DEBUG
-int ipwireless_dump_hardware_state(char *p, size_t limit,
-				   struct ipw_hardware *hw)
-{
-	return snprintf(p, limit,
-			"debug: initializing=%d\n"
-			"debug: tx_ready=%d\n"
-			"debug: tx_queued=%d\n"
-			"debug: rx_ready=%d\n"
-			"debug: rx_bytes_queued=%d\n"
-			"debug: blocking_rx=%d\n"
-			"debug: removed=%d\n"
-			"debug: hardware.shutting_down=%d\n"
-			"debug: to_setup=%d\n",
-			hw->initializing,
-			hw->tx_ready,
-			hw->tx_queued,
-			hw->rx_ready,
-			hw->rx_bytes_queued,
-			hw->blocking_rx,
-			hw->removed,
-			hw->shutting_down,
-			hw->to_setup);
-}
-#endif
-
 static char *data_type(const unsigned char *buf, unsigned length)
 {
 	struct nl_packet_header *hdr = (struct nl_packet_header *) buf;
diff --git a/trunk/drivers/char/pcmcia/ipwireless/hardware.h b/trunk/drivers/char/pcmcia/ipwireless/hardware.h
index c83190ffb0e7..19ce5eb266b1 100644
--- a/trunk/drivers/char/pcmcia/ipwireless/hardware.h
+++ b/trunk/drivers/char/pcmcia/ipwireless/hardware.h
@@ -58,7 +58,5 @@ void ipwireless_init_hardware_v1(struct ipw_hardware *hw,
 				 void *reboot_cb_data);
 void ipwireless_init_hardware_v2_v3(struct ipw_hardware *hw);
 void ipwireless_sleep(unsigned int tenths);
-int ipwireless_dump_hardware_state(char *p, size_t limit,
-				   struct ipw_hardware *hw);
 
 #endif
diff --git a/trunk/drivers/char/pcmcia/ipwireless/network.c b/trunk/drivers/char/pcmcia/ipwireless/network.c
index d793e68b3e0d..fe914d34f7f6 100644
--- a/trunk/drivers/char/pcmcia/ipwireless/network.c
+++ b/trunk/drivers/char/pcmcia/ipwireless/network.c
@@ -63,21 +63,6 @@ struct ipw_network {
 	struct work_struct work_go_offline;
 };
 
-
-#ifdef IPWIRELESS_STATE_DEBUG
-int ipwireless_dump_network_state(char *p, size_t limit,
-				  struct ipw_network *network)
-{
-	return snprintf(p, limit,
-			"debug: ppp_blocked=%d\n"
-			"debug: outgoing_packets_queued=%d\n"
-			"debug: network.shutting_down=%d\n",
-			network->ppp_blocked,
-			network->outgoing_packets_queued,
-			network->shutting_down);
-}
-#endif
-
 static void notify_packet_sent(void *callback_data, unsigned int packet_length)
 {
 	struct ipw_network *network = callback_data;
diff --git a/trunk/drivers/char/pcmcia/ipwireless/network.h b/trunk/drivers/char/pcmcia/ipwireless/network.h
index b0e1e952fd14..ccacd26fc7ef 100644
--- a/trunk/drivers/char/pcmcia/ipwireless/network.h
+++ b/trunk/drivers/char/pcmcia/ipwireless/network.h
@@ -49,7 +49,4 @@ void ipwireless_ppp_close(struct ipw_network *net);
 int ipwireless_ppp_channel_index(struct ipw_network *net);
 int ipwireless_ppp_unit_number(struct ipw_network *net);
 
-int ipwireless_dump_network_state(char *p, size_t limit,
-				  struct ipw_network *net);
-
 #endif
diff --git a/trunk/drivers/char/pcmcia/synclink_cs.c b/trunk/drivers/char/pcmcia/synclink_cs.c
index 4e84d233e5a2..583356426dfb 100644
--- a/trunk/drivers/char/pcmcia/synclink_cs.c
+++ b/trunk/drivers/char/pcmcia/synclink_cs.c
@@ -189,20 +189,20 @@ typedef struct _mgslpc_info {
 
 	u32 pending_bh;
 
-	int bh_running;
-	int bh_requested;
+	bool bh_running;
+	bool bh_requested;
 
 	int dcd_chkcount; /* check counts to prevent */
 	int cts_chkcount; /* too many IRQs if a signal */
 	int dsr_chkcount; /* is floating */
 	int ri_chkcount;
 
-	int rx_enabled;
-	int rx_overflow;
+	bool rx_enabled;
+	bool rx_overflow;
 
-	int tx_enabled;
-	int tx_active;
-	int tx_aborting;
+	bool tx_enabled;
+	bool tx_active;
+	bool tx_aborting;
 	u32 idle_mode;
 
 	int if_mode; /* serial interface selection (RS-232, v.35 etc) */
@@ -216,12 +216,12 @@ typedef struct _mgslpc_info {
 
 	unsigned char serial_signals;	/* current serial signal states */
 
-	char irq_occurred;		/* for diagnostics use */
+	bool irq_occurred;		/* for diagnostics use */
 	char testing_irq;
 	unsigned int init_error;	/* startup error (DIAGS)	*/
 
 	char flag_buf[MAX_ASYNC_BUFFER_SIZE];
-	BOOLEAN drop_rts_on_tx_done;
+	bool drop_rts_on_tx_done;
 
 	struct	_input_signal_events	input_signal_events;
 
@@ -402,8 +402,8 @@ static void hdlcdev_exit(MGSLPC_INFO *info);
 
 static void trace_block(MGSLPC_INFO *info,const char* data, int count, int xmit);
 
-static BOOLEAN register_test(MGSLPC_INFO *info);
-static BOOLEAN irq_test(MGSLPC_INFO *info);
+static bool register_test(MGSLPC_INFO *info);
+static bool irq_test(MGSLPC_INFO *info);
 static int adapter_test(MGSLPC_INFO *info);
 
 static int claim_resources(MGSLPC_INFO *info);
@@ -411,7 +411,7 @@ static void release_resources(MGSLPC_INFO *info);
 static void mgslpc_add_device(MGSLPC_INFO *info);
 static void mgslpc_remove_device(MGSLPC_INFO *info);
 
-static int  rx_get_frame(MGSLPC_INFO *info);
+static bool rx_get_frame(MGSLPC_INFO *info);
 static void rx_reset_buffers(MGSLPC_INFO *info);
 static int  rx_alloc_buffers(MGSLPC_INFO *info);
 static void rx_free_buffers(MGSLPC_INFO *info);
@@ -719,7 +719,7 @@ static int mgslpc_resume(struct pcmcia_device *link)
 }
 
 
-static inline int mgslpc_paranoia_check(MGSLPC_INFO *info,
+static inline bool mgslpc_paranoia_check(MGSLPC_INFO *info,
 					char *name, const char *routine)
 {
 #ifdef MGSLPC_PARANOIA_CHECK
@@ -730,17 +730,17 @@ static inline int mgslpc_paranoia_check(MGSLPC_INFO *info,
 
 	if (!info) {
 		printk(badinfo, name, routine);
-		return 1;
+		return true;
 	}
 	if (info->magic != MGSLPC_MAGIC) {
 		printk(badmagic, name, routine);
-		return 1;
+		return true;
 	}
 #else
 	if (!info)
-		return 1;
+		return true;
 #endif
-	return 0;
+	return false;
 }
 
 
@@ -752,16 +752,16 @@ static inline int mgslpc_paranoia_check(MGSLPC_INFO *info,
 #define CMD_TXEOM       BIT1	// transmit end message
 #define CMD_TXRESET     BIT0	// transmit reset
 
-static BOOLEAN wait_command_complete(MGSLPC_INFO *info, unsigned char channel)
+static bool wait_command_complete(MGSLPC_INFO *info, unsigned char channel)
 {
 	int i = 0;
 	/* wait for command completion */
 	while (read_reg(info, (unsigned char)(channel+STAR)) & BIT2) {
 		udelay(1);
 		if (i++ == 1000)
-			return FALSE;
+			return false;
 	}
-	return TRUE;
+	return true;
 }
 
 static void issue_command(MGSLPC_INFO *info, unsigned char channel, unsigned char cmd)
@@ -825,8 +825,8 @@ static int bh_action(MGSLPC_INFO *info)
 
 	if (!rc) {
 		/* Mark BH routine as complete */
-		info->bh_running   = 0;
-		info->bh_requested = 0;
+		info->bh_running = false;
+		info->bh_requested = false;
 	}
 
 	spin_unlock_irqrestore(&info->lock,flags);
@@ -846,7 +846,7 @@ static void bh_handler(struct work_struct *work)
 		printk( "%s(%d):bh_handler(%s) entry\n",
 			__FILE__,__LINE__,info->device_name);
 
-	info->bh_running = 1;
+	info->bh_running = true;
 
 	while((action = bh_action(info)) != 0) {
 
@@ -913,7 +913,7 @@ static void rx_ready_hdlc(MGSLPC_INFO *info, int eom)
 		/* no more free buffers */
 		issue_command(info, CHA, CMD_RXRESET);
 		info->pending_bh |= BH_RECEIVE;
-		info->rx_overflow = 1;
+		info->rx_overflow = true;
 		info->icount.buf_overrun++;
 		return;
 	}
@@ -1032,8 +1032,8 @@ static void tx_done(MGSLPC_INFO *info)
 	if (!info->tx_active)
 		return;
 
-	info->tx_active = 0;
-	info->tx_aborting = 0;
+	info->tx_active = false;
+	info->tx_aborting = false;
 
 	if (info->params.mode == MGSL_MODE_ASYNC)
 		return;
@@ -1047,7 +1047,7 @@ static void tx_done(MGSLPC_INFO *info)
 			info->serial_signals &= ~SerialSignal_RTS;
 			set_signals(info);
 		}
-		info->drop_rts_on_tx_done = 0;
+		info->drop_rts_on_tx_done = false;
 	}
 
 #if SYNCLINK_GENERIC_HDLC
@@ -1081,7 +1081,7 @@ static void tx_ready(MGSLPC_INFO *info)
 			return;
 		}
 		if (!info->tx_count)
-			info->tx_active = 0;
+			info->tx_active = false;
 	}
 
 	if (!info->tx_count)
@@ -1261,7 +1261,7 @@ static irqreturn_t mgslpc_isr(int dummy, void *dev_id)
 		{
 			isr = read_reg16(info, CHA + ISR);
 			if (isr & IRQ_TIMER) {
-				info->irq_occurred = 1;
+				info->irq_occurred = true;
 				irq_disable(info, CHA, IRQ_TIMER);
 			}
 
@@ -1318,7 +1318,7 @@ static irqreturn_t mgslpc_isr(int dummy, void *dev_id)
 			printk("%s(%d):%s queueing bh task.\n",
 				__FILE__,__LINE__,info->device_name);
 		schedule_work(&info->task);
-		info->bh_requested = 1;
+		info->bh_requested = true;
 	}
 
 	spin_unlock(&info->lock);
@@ -1990,7 +1990,7 @@ static int tx_abort(MGSLPC_INFO * info)
 		 * This results in underrun and abort transmission.
 		 */
 		info->tx_count = info->tx_put = info->tx_get = 0;
-		info->tx_aborting = TRUE;
+		info->tx_aborting = true;
 	}
 	spin_unlock_irqrestore(&info->lock,flags);
 	return 0;
@@ -2589,7 +2589,8 @@ static int block_til_ready(struct tty_struct *tty, struct file *filp,
 {
 	DECLARE_WAITQUEUE(wait, current);
 	int		retval;
-	int		do_clocal = 0, extra_count = 0;
+	bool		do_clocal = false;
+	bool		extra_count = false;
 	unsigned long	flags;
 
 	if (debug_level >= DEBUG_LEVEL_INFO)
@@ -2604,7 +2605,7 @@ static int block_til_ready(struct tty_struct *tty, struct file *filp,
 	}
 
 	if (tty->termios->c_cflag & CLOCAL)
-		do_clocal = 1;
+		do_clocal = true;
 
 	/* Wait for carrier detect and the line to become
 	 * free (i.e., not in use by the callout).  While we are in
@@ -2622,7 +2623,7 @@ static int block_til_ready(struct tty_struct *tty, struct file *filp,
 
 	spin_lock_irqsave(&info->lock, flags);
 	if (!tty_hung_up_p(filp)) {
-		extra_count = 1;
+		extra_count = true;
 		info->count--;
 	}
 	spin_unlock_irqrestore(&info->lock, flags);
@@ -3493,8 +3494,8 @@ static void rx_stop(MGSLPC_INFO *info)
 	/* MODE:03 RAC Receiver Active, 0=inactive */
 	clear_reg_bits(info, CHA + MODE, BIT3);
 
-	info->rx_enabled = 0;
-	info->rx_overflow = 0;
+	info->rx_enabled = false;
+	info->rx_overflow = false;
 }
 
 static void rx_start(MGSLPC_INFO *info)
@@ -3504,13 +3505,13 @@ static void rx_start(MGSLPC_INFO *info)
 			 __FILE__,__LINE__, info->device_name );
 
 	rx_reset_buffers(info);
-	info->rx_enabled = 0;
-	info->rx_overflow = 0;
+	info->rx_enabled = false;
+	info->rx_overflow = false;
 
 	/* MODE:03 RAC Receiver Active, 1=active */
 	set_reg_bits(info, CHA + MODE, BIT3);
 
-	info->rx_enabled = 1;
+	info->rx_enabled = true;
 }
 
 static void tx_start(MGSLPC_INFO *info)
@@ -3523,24 +3524,24 @@ static void tx_start(MGSLPC_INFO *info)
 		/* If auto RTS enabled and RTS is inactive, then assert */
 		/* RTS and set a flag indicating that the driver should */
 		/* negate RTS when the transmission completes. */
-		info->drop_rts_on_tx_done = 0;
+		info->drop_rts_on_tx_done = false;
 
 		if (info->params.flags & HDLC_FLAG_AUTO_RTS) {
 			get_signals(info);
 			if (!(info->serial_signals & SerialSignal_RTS)) {
 				info->serial_signals |= SerialSignal_RTS;
 				set_signals(info);
-				info->drop_rts_on_tx_done = 1;
+				info->drop_rts_on_tx_done = true;
 			}
 		}
 
 		if (info->params.mode == MGSL_MODE_ASYNC) {
 			if (!info->tx_active) {
-				info->tx_active = 1;
+				info->tx_active = true;
 				tx_ready(info);
 			}
 		} else {
-			info->tx_active = 1;
+			info->tx_active = true;
 			tx_ready(info);
 			mod_timer(&info->tx_timer, jiffies +
 					msecs_to_jiffies(5000));
@@ -3548,7 +3549,7 @@ static void tx_start(MGSLPC_INFO *info)
 	}
 
 	if (!info->tx_enabled)
-		info->tx_enabled = 1;
+		info->tx_enabled = true;
 }
 
 static void tx_stop(MGSLPC_INFO *info)
@@ -3559,8 +3560,8 @@ static void tx_stop(MGSLPC_INFO *info)
 
 	del_timer(&info->tx_timer);
 
-	info->tx_enabled = 0;
-	info->tx_active  = 0;
+	info->tx_enabled = false;
+	info->tx_active = false;
 }
 
 /* Reset the adapter to a known state and prepare it for further use.
@@ -3860,19 +3861,19 @@ static void rx_reset_buffers(MGSLPC_INFO *info)
 /* Attempt to return a received HDLC frame
  * Only frames received without errors are returned.
  *
- * Returns 1 if frame returned, otherwise 0
+ * Returns true if frame returned, otherwise false
  */
-static int rx_get_frame(MGSLPC_INFO *info)
+static bool rx_get_frame(MGSLPC_INFO *info)
 {
 	unsigned short status;
 	RXBUF *buf;
 	unsigned int framesize = 0;
 	unsigned long flags;
 	struct tty_struct *tty = info->tty;
-	int return_frame = 0;
+	bool return_frame = false;
 
 	if (info->rx_frame_count == 0)
-		return 0;
+		return false;
 
 	buf = (RXBUF*)(info->rx_buf + (info->rx_get * info->rx_buf_size));
 
@@ -3891,7 +3892,7 @@ static int rx_get_frame(MGSLPC_INFO *info)
 		else if (!(status & BIT5)) {
 			info->icount.rxcrc++;
 			if (info->params.crc_type & HDLC_CRC_RETURN_EX)
-				return_frame = 1;
+				return_frame = true;
 		}
 		framesize = 0;
 #if SYNCLINK_GENERIC_HDLC
@@ -3902,7 +3903,7 @@ static int rx_get_frame(MGSLPC_INFO *info)
 		}
 #endif
 	} else
-		return_frame = 1;
+		return_frame = true;
 
 	if (return_frame)
 		framesize = buf->count;
@@ -3945,16 +3946,16 @@ static int rx_get_frame(MGSLPC_INFO *info)
 		info->rx_get = 0;
 	spin_unlock_irqrestore(&info->lock,flags);
 
-	return 1;
+	return true;
 }
 
-static BOOLEAN register_test(MGSLPC_INFO *info)
+static bool register_test(MGSLPC_INFO *info)
 {
 	static unsigned char patterns[] =
 	    { 0x00, 0xff, 0xaa, 0x55, 0x69, 0x96, 0x0f };
 	static unsigned int count = ARRAY_SIZE(patterns);
 	unsigned int i;
-	BOOLEAN rc = TRUE;
+	bool rc = true;
 	unsigned long flags;
 
 	spin_lock_irqsave(&info->lock,flags);
@@ -3965,7 +3966,7 @@ static BOOLEAN register_test(MGSLPC_INFO *info)
 		write_reg(info, XAD2, patterns[(i + 1) % count]);
 		if ((read_reg(info, XAD1) != patterns[i]) ||
 		    (read_reg(info, XAD2) != patterns[(i + 1) % count])) {
-			rc = FALSE;
+			rc = false;
 			break;
 		}
 	}
@@ -3974,7 +3975,7 @@ static BOOLEAN register_test(MGSLPC_INFO *info)
 	return rc;
 }
 
-static BOOLEAN irq_test(MGSLPC_INFO *info)
+static bool irq_test(MGSLPC_INFO *info)
 {
 	unsigned long end_time;
 	unsigned long flags;
@@ -3982,10 +3983,10 @@ static BOOLEAN irq_test(MGSLPC_INFO *info)
 	spin_lock_irqsave(&info->lock,flags);
 	reset_device(info);
 
-	info->testing_irq = TRUE;
+	info->testing_irq = true;
 	hdlc_mode(info);
 
-	info->irq_occurred = FALSE;
+	info->irq_occurred = false;
 
 	/* init hdlc mode */
 
@@ -4000,13 +4001,13 @@ static BOOLEAN irq_test(MGSLPC_INFO *info)
 		msleep_interruptible(10);
 	}
 
-	info->testing_irq = FALSE;
+	info->testing_irq = false;
 
 	spin_lock_irqsave(&info->lock,flags);
 	reset_device(info);
 	spin_unlock_irqrestore(&info->lock,flags);
 
-	return info->irq_occurred ? TRUE : FALSE;
+	return info->irq_occurred;
 }
 
 static int adapter_test(MGSLPC_INFO *info)
@@ -4079,7 +4080,7 @@ static void tx_timeout(unsigned long context)
 		info->icount.txtimeout++;
 	}
 	spin_lock_irqsave(&info->lock,flags);
-	info->tx_active = 0;
+	info->tx_active = false;
 	info->tx_count = info->tx_put = info->tx_get = 0;
 
 	spin_unlock_irqrestore(&info->lock,flags);
diff --git a/trunk/drivers/char/random.c b/trunk/drivers/char/random.c
index f43c89f7c449..0cf98bd4f2d2 100644
--- a/trunk/drivers/char/random.c
+++ b/trunk/drivers/char/random.c
@@ -272,7 +272,7 @@ static int random_write_wakeup_thresh = 128;
 
 static int trickle_thresh __read_mostly = INPUT_POOL_WORDS * 28;
 
-static DEFINE_PER_CPU(int, trickle_count) = 0;
+static DEFINE_PER_CPU(int, trickle_count);
 
 /*
  * A pool of size .poolwords is stirred with a primitive polynomial
@@ -370,17 +370,19 @@ static struct poolinfo {
  */
 static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
 static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
+static struct fasync_struct *fasync;
 
 #if 0
-static int debug = 0;
+static int debug;
 module_param(debug, bool, 0644);
-#define DEBUG_ENT(fmt, arg...) do { if (debug) \
-	printk(KERN_DEBUG "random %04d %04d %04d: " \
-	fmt,\
-	input_pool.entropy_count,\
-	blocking_pool.entropy_count,\
-	nonblocking_pool.entropy_count,\
-	## arg); } while (0)
+#define DEBUG_ENT(fmt, arg...) do { \
+	if (debug) \
+		printk(KERN_DEBUG "random %04d %04d %04d: " \
+		fmt,\
+		input_pool.entropy_count,\
+		blocking_pool.entropy_count,\
+		nonblocking_pool.entropy_count,\
+		## arg); } while (0)
 #else
 #define DEBUG_ENT(fmt, arg...) do {} while (0)
 #endif
@@ -394,7 +396,7 @@ module_param(debug, bool, 0644);
 
 struct entropy_store;
 struct entropy_store {
-	/* mostly-read data: */
+	/* read-only data: */
 	struct poolinfo *poolinfo;
 	__u32 *pool;
 	const char *name;
@@ -402,7 +404,7 @@ struct entropy_store {
 	struct entropy_store *pull;
 
 	/* read-write data: */
-	spinlock_t lock ____cacheline_aligned_in_smp;
+	spinlock_t lock;
 	unsigned add_ptr;
 	int entropy_count;
 	int input_rotate;
@@ -438,25 +440,26 @@ static struct entropy_store nonblocking_pool = {
 };
 
 /*
- * This function adds a byte into the entropy "pool".  It does not
+ * This function adds bytes into the entropy "pool".  It does not
  * update the entropy estimate.  The caller should call
- * credit_entropy_store if this is appropriate.
+ * credit_entropy_bits if this is appropriate.
  *
  * The pool is stirred with a primitive polynomial of the appropriate
  * degree, and then twisted.  We twist by three bits at a time because
  * it's cheap to do so and helps slightly in the expected case where
  * the entropy is concentrated in the low-order bits.
  */
-static void __add_entropy_words(struct entropy_store *r, const __u32 *in,
-				int nwords, __u32 out[16])
+static void mix_pool_bytes_extract(struct entropy_store *r, const void *in,
+				   int nbytes, __u8 out[64])
 {
 	static __u32 const twist_table[8] = {
 		0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158,
 		0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 };
-	unsigned long i, add_ptr, tap1, tap2, tap3, tap4, tap5;
-	int new_rotate, input_rotate;
+	unsigned long i, j, tap1, tap2, tap3, tap4, tap5;
+	int input_rotate;
 	int wordmask = r->poolinfo->poolwords - 1;
-	__u32 w, next_w;
+	const char *bytes = in;
+	__u32 w;
 	unsigned long flags;
 
 	/* Taps are constant, so we can load them without holding r->lock.  */
@@ -465,78 +468,76 @@ static void __add_entropy_words(struct entropy_store *r, const __u32 *in,
 	tap3 = r->poolinfo->tap3;
 	tap4 = r->poolinfo->tap4;
 	tap5 = r->poolinfo->tap5;
-	next_w = *in++;
 
 	spin_lock_irqsave(&r->lock, flags);
-	prefetch_range(r->pool, wordmask);
 	input_rotate = r->input_rotate;
-	add_ptr = r->add_ptr;
+	i = r->add_ptr;
 
-	while (nwords--) {
-		w = rol32(next_w, input_rotate);
-		if (nwords > 0)
-			next_w = *in++;
-		i = add_ptr = (add_ptr - 1) & wordmask;
-		/*
-		 * Normally, we add 7 bits of rotation to the pool.
-		 * At the beginning of the pool, add an extra 7 bits
-		 * rotation, so that successive passes spread the
-		 * input bits across the pool evenly.
-		 */
-		new_rotate = input_rotate + 14;
-		if (i)
-			new_rotate = input_rotate + 7;
-		input_rotate = new_rotate & 31;
+	/* mix one byte at a time to simplify size handling and churn faster */
+	while (nbytes--) {
+		w = rol32(*bytes++, input_rotate & 31);
+		i = (i - 1) & wordmask;
 
 		/* XOR in the various taps */
+		w ^= r->pool[i];
 		w ^= r->pool[(i + tap1) & wordmask];
 		w ^= r->pool[(i + tap2) & wordmask];
 		w ^= r->pool[(i + tap3) & wordmask];
 		w ^= r->pool[(i + tap4) & wordmask];
 		w ^= r->pool[(i + tap5) & wordmask];
-		w ^= r->pool[i];
+
+		/* Mix the result back in with a twist */
 		r->pool[i] = (w >> 3) ^ twist_table[w & 7];
+
+		/*
+		 * Normally, we add 7 bits of rotation to the pool.
+		 * At the beginning of the pool, add an extra 7 bits
+		 * rotation, so that successive passes spread the
+		 * input bits across the pool evenly.
+		 */
+		input_rotate += i ? 7 : 14;
 	}
 
 	r->input_rotate = input_rotate;
-	r->add_ptr = add_ptr;
+	r->add_ptr = i;
 
-	if (out) {
-		for (i = 0; i < 16; i++) {
-			out[i] = r->pool[add_ptr];
-			add_ptr = (add_ptr - 1) & wordmask;
-		}
-	}
+	if (out)
+		for (j = 0; j < 16; j++)
+			((__u32 *)out)[j] = r->pool[(i - j) & wordmask];
 
 	spin_unlock_irqrestore(&r->lock, flags);
 }
 
-static inline void add_entropy_words(struct entropy_store *r, const __u32 *in,
-				     int nwords)
+static void mix_pool_bytes(struct entropy_store *r, const void *in, int bytes)
 {
-	__add_entropy_words(r, in, nwords, NULL);
+       mix_pool_bytes_extract(r, in, bytes, NULL);
 }
 
 /*
  * Credit (or debit) the entropy store with n bits of entropy
  */
-static void credit_entropy_store(struct entropy_store *r, int nbits)
+static void credit_entropy_bits(struct entropy_store *r, int nbits)
 {
 	unsigned long flags;
 
+	if (!nbits)
+		return;
+
 	spin_lock_irqsave(&r->lock, flags);
 
-	if (r->entropy_count + nbits < 0) {
-		DEBUG_ENT("negative entropy/overflow (%d+%d)\n",
-			  r->entropy_count, nbits);
+	DEBUG_ENT("added %d entropy credits to %s\n", nbits, r->name);
+	r->entropy_count += nbits;
+	if (r->entropy_count < 0) {
+		DEBUG_ENT("negative entropy/overflow\n");
 		r->entropy_count = 0;
-	} else if (r->entropy_count + nbits > r->poolinfo->POOLBITS) {
+	} else if (r->entropy_count > r->poolinfo->POOLBITS)
 		r->entropy_count = r->poolinfo->POOLBITS;
-	} else {
-		r->entropy_count += nbits;
-		if (nbits)
-			DEBUG_ENT("added %d entropy credits to %s\n",
-				  nbits, r->name);
+
+	/* should we wake readers? */
+	if (r == &input_pool &&
+	    r->entropy_count >= random_read_wakeup_thresh) {
+		wake_up_interruptible(&random_read_wait);
+		kill_fasync(&fasync, SIGIO, POLL_IN);
 	}
 
 	spin_unlock_irqrestore(&r->lock, flags);
@@ -551,7 +552,7 @@ static void credit_entropy_store(struct entropy_store *r, int nbits)
 /* There is one of these per entropy source */
 struct timer_rand_state {
 	cycles_t last_time;
-	long last_delta,last_delta2;
+	long last_delta, last_delta2;
 	unsigned dont_count_entropy:1;
 };
 
@@ -586,7 +587,7 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 	sample.jiffies = jiffies;
 	sample.cycles = get_cycles();
 	sample.num = num;
-	add_entropy_words(&input_pool, (u32 *)&sample, sizeof(sample)/4);
+	mix_pool_bytes(&input_pool, &sample, sizeof(sample));
 
 	/*
 	 * Calculate number of bits of randomness we probably added.
@@ -620,13 +621,9 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 		 * Round down by 1 bit on general principles,
 		 * and limit entropy entimate to 12 bits.
 		 */
-		credit_entropy_store(&input_pool,
-				     min_t(int, fls(delta>>1), 11));
+		credit_entropy_bits(&input_pool,
+				    min_t(int, fls(delta>>1), 11));
 	}
-
-	if(input_pool.entropy_count >= random_read_wakeup_thresh)
-		wake_up_interruptible(&random_read_wait);
-
 out:
 	preempt_enable();
 }
@@ -677,7 +674,7 @@ void add_disk_randomness(struct gendisk *disk)
  *
  *********************************************************************/
 
-static ssize_t extract_entropy(struct entropy_store *r, void * buf,
+static ssize_t extract_entropy(struct entropy_store *r, void *buf,
 			       size_t nbytes, int min, int rsvd);
 
 /*
@@ -704,10 +701,10 @@ static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 			  "(%d of %d requested)\n",
 			  r->name, bytes * 8, nbytes * 8, r->entropy_count);
 
-		bytes=extract_entropy(r->pull, tmp, bytes,
-				      random_read_wakeup_thresh / 8, rsvd);
-		add_entropy_words(r, tmp, (bytes + 3) / 4);
-		credit_entropy_store(r, bytes*8);
+		bytes = extract_entropy(r->pull, tmp, bytes,
+					random_read_wakeup_thresh / 8, rsvd);
+		mix_pool_bytes(r, tmp, bytes);
+		credit_entropy_bits(r, bytes*8);
 	}
 }
 
@@ -744,13 +741,15 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min,
 		if (r->limit && nbytes + reserved >= r->entropy_count / 8)
 			nbytes = r->entropy_count/8 - reserved;
 
-		if(r->entropy_count / 8 >= nbytes + reserved)
+		if (r->entropy_count / 8 >= nbytes + reserved)
 			r->entropy_count -= nbytes*8;
 		else
 			r->entropy_count = reserved;
 
-		if (r->entropy_count < random_write_wakeup_thresh)
+		if (r->entropy_count < random_write_wakeup_thresh) {
 			wake_up_interruptible(&random_write_wait);
+			kill_fasync(&fasync, SIGIO, POLL_OUT);
+		}
 	}
 
 	DEBUG_ENT("debiting %d entropy credits from %s%s\n",
@@ -764,45 +763,46 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min,
 static void extract_buf(struct entropy_store *r, __u8 *out)
 {
 	int i;
-	__u32 data[16], buf[5 + SHA_WORKSPACE_WORDS];
+	__u32 hash[5], workspace[SHA_WORKSPACE_WORDS];
+	__u8 extract[64];
+
+	/* Generate a hash across the pool, 16 words (512 bits) at a time */
+	sha_init(hash);
+	for (i = 0; i < r->poolinfo->poolwords; i += 16)
+		sha_transform(hash, (__u8 *)(r->pool + i), workspace);
 
-	sha_init(buf);
 	/*
-	 * As we hash the pool, we mix intermediate values of
-	 * the hash back into the pool.  This eliminates
-	 * backtracking attacks (where the attacker knows
-	 * the state of the pool plus the current outputs, and
-	 * attempts to find previous ouputs), unless the hash
-	 * function can be inverted.
+	 * We mix the hash back into the pool to prevent backtracking
+	 * attacks (where the attacker knows the state of the pool
+	 * plus the current outputs, and attempts to find previous
+	 * ouputs), unless the hash function can be inverted. By
+	 * mixing at least a SHA1 worth of hash data back, we make
+	 * brute-forcing the feedback as hard as brute-forcing the
+	 * hash.
 	 */
-	for (i = 0; i < r->poolinfo->poolwords; i += 16) {
-		/* hash blocks of 16 words = 512 bits */
-		sha_transform(buf, (__u8 *)(r->pool + i), buf + 5);
-		/* feed back portion of the resulting hash */
-		add_entropy_words(r, &buf[i % 5], 1);
-	}
+	mix_pool_bytes_extract(r, hash, sizeof(hash), extract);
 
 	/*
-	 * To avoid duplicates, we atomically extract a
-	 * portion of the pool while mixing, and hash one
-	 * final time.
+	 * To avoid duplicates, we atomically extract a portion of the
+	 * pool while mixing, and hash one final time.
 	 */
-	__add_entropy_words(r, &buf[i % 5], 1, data);
-	sha_transform(buf, (__u8 *)data, buf + 5);
+	sha_transform(hash, extract, workspace);
+	memset(extract, 0, sizeof(extract));
+	memset(workspace, 0, sizeof(workspace));
 
 	/*
-	 * In case the hash function has some recognizable
-	 * output pattern, we fold it in half.
+	 * In case the hash function has some recognizable output
+	 * pattern, we fold it in half. Thus, we always feed back
+	 * twice as much data as we output.
 	 */
-
-	buf[0] ^= buf[3];
-	buf[1] ^= buf[4];
-	buf[2] ^= rol32(buf[2], 16);
-	memcpy(out, buf, EXTRACT_SIZE);
-	memset(buf, 0, sizeof(buf));
+	hash[0] ^= hash[3];
+	hash[1] ^= hash[4];
+	hash[2] ^= rol32(hash[2], 16);
+	memcpy(out, hash, EXTRACT_SIZE);
+	memset(hash, 0, sizeof(hash));
 }
 
-static ssize_t extract_entropy(struct entropy_store *r, void * buf,
+static ssize_t extract_entropy(struct entropy_store *r, void *buf,
 			       size_t nbytes, int min, int reserved)
 {
 	ssize_t ret = 0, i;
@@ -872,7 +872,6 @@ void get_random_bytes(void *buf, int nbytes)
 {
 	extract_entropy(&nonblocking_pool, buf, nbytes, 0, 0);
 }
-
 EXPORT_SYMBOL(get_random_bytes);
 
 /*
@@ -894,12 +893,11 @@ static void init_std_data(struct entropy_store *r)
 	spin_unlock_irqrestore(&r->lock, flags);
 
 	now = ktime_get_real();
-	add_entropy_words(r, (__u32 *)&now, sizeof(now)/4);
-	add_entropy_words(r, (__u32 *)utsname(),
-			  sizeof(*(utsname()))/4);
+	mix_pool_bytes(r, &now, sizeof(now));
+	mix_pool_bytes(r, utsname(), sizeof(*(utsname())));
 }
 
-static int __init rand_initialize(void)
+static int rand_initialize(void)
 {
 	init_std_data(&input_pool);
 	init_std_data(&blocking_pool);
@@ -940,7 +938,7 @@ void rand_initialize_disk(struct gendisk *disk)
 #endif
 
 static ssize_t
-random_read(struct file * file, char __user * buf, size_t nbytes, loff_t *ppos)
+random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 {
 	ssize_t n, retval = 0, count = 0;
 
@@ -1002,8 +1000,7 @@ random_read(struct file * file, char __user * buf, size_t nbytes, loff_t *ppos)
 }
 
 static ssize_t
-urandom_read(struct file * file, char __user * buf,
-		      size_t nbytes, loff_t *ppos)
+urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 {
 	return extract_entropy_user(&nonblocking_pool, buf, nbytes);
 }
@@ -1038,16 +1035,15 @@ write_pool(struct entropy_store *r, const char __user *buffer, size_t count)
 		count -= bytes;
 		p += bytes;
 
-		add_entropy_words(r, buf, (bytes + 3) / 4);
+		mix_pool_bytes(r, buf, bytes);
 		cond_resched();
 	}
 
 	return 0;
 }
 
-static ssize_t
-random_write(struct file * file, const char __user * buffer,
-	     size_t count, loff_t *ppos)
+static ssize_t random_write(struct file *file, const char __user *buffer,
+			    size_t count, loff_t *ppos)
 {
 	size_t ret;
 	struct inode *inode = file->f_path.dentry->d_inode;
@@ -1064,9 +1060,7 @@ random_write(struct file * file, const char __user * buffer,
 	return (ssize_t)count;
 }
 
-static int
-random_ioctl(struct inode * inode, struct file * file,
-	     unsigned int cmd, unsigned long arg)
+static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 {
 	int size, ent_count;
 	int __user *p = (int __user *)arg;
@@ -1074,8 +1068,8 @@ random_ioctl(struct inode * inode, struct file * file,
 
 	switch (cmd) {
 	case RNDGETENTCNT:
-		ent_count = input_pool.entropy_count;
-		if (put_user(ent_count, p))
+		/* inherently racy, no point locking */
+		if (put_user(input_pool.entropy_count, p))
 			return -EFAULT;
 		return 0;
 	case RNDADDTOENTCNT:
@@ -1083,13 +1077,7 @@ random_ioctl(struct inode * inode, struct file * file,
 			return -EPERM;
 		if (get_user(ent_count, p))
 			return -EFAULT;
-		credit_entropy_store(&input_pool, ent_count);
-		/*
-		 * Wake up waiting processes if we have enough
-		 * entropy.
-		 */
-		if (input_pool.entropy_count >= random_read_wakeup_thresh)
-			wake_up_interruptible(&random_read_wait);
+		credit_entropy_bits(&input_pool, ent_count);
 		return 0;
 	case RNDADDENTROPY:
 		if (!capable(CAP_SYS_ADMIN))
@@ -1104,39 +1092,45 @@ random_ioctl(struct inode * inode, struct file * file,
 				    size);
 		if (retval < 0)
 			return retval;
-		credit_entropy_store(&input_pool, ent_count);
-		/*
-		 * Wake up waiting processes if we have enough
-		 * entropy.
-		 */
-		if (input_pool.entropy_count >= random_read_wakeup_thresh)
-			wake_up_interruptible(&random_read_wait);
+		credit_entropy_bits(&input_pool, ent_count);
 		return 0;
 	case RNDZAPENTCNT:
 	case RNDCLEARPOOL:
 		/* Clear the entropy pool counters. */
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
-		init_std_data(&input_pool);
-		init_std_data(&blocking_pool);
-		init_std_data(&nonblocking_pool);
+		rand_initialize();
 		return 0;
 	default:
 		return -EINVAL;
 	}
 }
 
+static int random_fasync(int fd, struct file *filp, int on)
+{
+	return fasync_helper(fd, filp, on, &fasync);
+}
+
+static int random_release(struct inode *inode, struct file *filp)
+{
+	return fasync_helper(-1, filp, 0, &fasync);
+}
+
 const struct file_operations random_fops = {
 	.read  = random_read,
 	.write = random_write,
 	.poll  = random_poll,
-	.ioctl = random_ioctl,
+	.unlocked_ioctl = random_ioctl,
+	.fasync = random_fasync,
+	.release = random_release,
 };
 
 const struct file_operations urandom_fops = {
 	.read  = urandom_read,
 	.write = random_write,
-	.ioctl = random_ioctl,
+	.unlocked_ioctl = random_ioctl,
+	.fasync = random_fasync,
+	.release = random_release,
 };
 
 /***************************************************************
@@ -1157,7 +1151,6 @@ void generate_random_uuid(unsigned char uuid_out[16])
 	/* Set the UUID variant to DCE */
 	uuid_out[8] = (uuid_out[8] & 0x3F) | 0x80;
 }
-
 EXPORT_SYMBOL(generate_random_uuid);
 
 /********************************************************************
@@ -1339,7 +1332,7 @@ ctl_table random_table[] = {
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 
-static __u32 twothirdsMD4Transform (__u32 const buf[4], __u32 const in[12])
+static __u32 twothirdsMD4Transform(__u32 const buf[4], __u32 const in[12])
 {
 	__u32 a = buf[0], b = buf[1], c = buf[2], d = buf[3];
 
@@ -1487,8 +1480,8 @@ __u32 secure_tcpv6_sequence_number(__be32 *saddr, __be32 *daddr,
 	 */
 
 	memcpy(hash, saddr, 16);
-	hash[4]=((__force u16)sport << 16) + (__force u16)dport;
-	memcpy(&hash[5],keyptr->secret,sizeof(__u32) * 7);
+	hash[4] = ((__force u16)sport << 16) + (__force u16)dport;
+	memcpy(&hash[5], keyptr->secret, sizeof(__u32) * 7);
 
 	seq = twothirdsMD4Transform((const __u32 *)daddr, hash) & HASH_MASK;
 	seq += keyptr->count;
@@ -1538,10 +1531,10 @@ __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
 	 *  Note that the words are placed into the starting vector, which is
 	 *  then mixed with a partial MD4 over random data.
 	 */
-	hash[0]=(__force u32)saddr;
-	hash[1]=(__force u32)daddr;
-	hash[2]=((__force u16)sport << 16) + (__force u16)dport;
-	hash[3]=keyptr->secret[11];
+	hash[0] = (__force u32)saddr;
+	hash[1] = (__force u32)daddr;
+	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
+	hash[3] = keyptr->secret[11];
 
 	seq = half_md4_transform(hash, keyptr->secret) & HASH_MASK;
 	seq += keyptr->count;
@@ -1556,10 +1549,7 @@ __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
 	 *	Choosing a clock of 64 ns period is OK. (period of 274 s)
 	 */
 	seq += ktime_to_ns(ktime_get_real()) >> 6;
-#if 0
-	printk("init_seq(%lx, %lx, %d, %d) = %d\n",
-	       saddr, daddr, sport, dport, seq);
-#endif
+
 	return seq;
 }
 
@@ -1582,14 +1572,15 @@ u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
 }
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport)
+u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
+			       __be16 dport)
 {
 	struct keydata *keyptr = get_keyptr();
 	u32 hash[12];
 
 	memcpy(hash, saddr, 16);
 	hash[4] = (__force u32)dport;
-	memcpy(&hash[5],keyptr->secret,sizeof(__u32) * 7);
+	memcpy(&hash[5], keyptr->secret, sizeof(__u32) * 7);
 
 	return twothirdsMD4Transform((const __u32 *)daddr, hash);
 }
@@ -1617,13 +1608,9 @@ u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
 
 	seq += ktime_to_ns(ktime_get_real());
 	seq &= (1ull << 48) - 1;
-#if 0
-	printk("dccp init_seq(%lx, %lx, %d, %d) = %d\n",
-	       saddr, daddr, sport, dport, seq);
-#endif
+
 	return seq;
 }
-
 EXPORT_SYMBOL(secure_dccp_sequence_number);
 #endif
 
diff --git a/trunk/drivers/char/rio/rioroute.c b/trunk/drivers/char/rio/rioroute.c
index 85091ff74d96..7a9df7dcf9a8 100644
--- a/trunk/drivers/char/rio/rioroute.c
+++ b/trunk/drivers/char/rio/rioroute.c
@@ -526,7 +526,7 @@ void RIOFixPhbs(struct rio_info *p, struct Host *HostP, unsigned int unit)
 			 ** If RTA is not powered on, the tx packets will be
 			 ** unset, so go no further.
 			 */
-			if (PortP->TxStart == 0) {
+			if (!PortP->TxStart) {
 				rio_dprintk(RIO_DEBUG_ROUTE, "Tx pkts not set up yet\n");
 				rio_spin_unlock_irqrestore(&PortP->portSem, flags);
 				break;
diff --git a/trunk/drivers/char/rocket_int.h b/trunk/drivers/char/rocket_int.h
index b01d38125a8f..143cc432fdb2 100644
--- a/trunk/drivers/char/rocket_int.h
+++ b/trunk/drivers/char/rocket_int.h
@@ -55,7 +55,7 @@ static inline void sOutW(unsigned short port, unsigned short value)
 
 static inline void out32(unsigned short port, Byte_t *p)
 {
-	u32 value = le32_to_cpu(get_unaligned((__le32 *)p));
+	u32 value = get_unaligned_le32(p);
 #ifdef ROCKET_DEBUG_IO
 	printk(KERN_DEBUG "out32(%x, %lx)...\n", port, value);
 #endif
diff --git a/trunk/drivers/char/rtc.c b/trunk/drivers/char/rtc.c
index 5c3142b6f1fc..5f80a9dff573 100644
--- a/trunk/drivers/char/rtc.c
+++ b/trunk/drivers/char/rtc.c
@@ -88,6 +88,7 @@
 
 #ifdef CONFIG_SPARC32
 #include <linux/pci.h>
+#include <linux/jiffies.h>
 #include <asm/ebus.h>
 
 static unsigned long rtc_port;
@@ -1068,10 +1069,8 @@ static int __init rtc_init(void)
 	}
 
 #ifdef CONFIG_PROC_FS
-	ent = create_proc_entry("driver/rtc", 0, NULL);
-	if (ent)
-		ent->proc_fops = &rtc_proc_fops;
-	else
+	ent = proc_create("driver/rtc", 0, NULL, &rtc_proc_fops);
+	if (!ent)
 		printk(KERN_WARNING "rtc: Failed to register with procfs.\n");
 #endif
 
@@ -1316,7 +1315,8 @@ void rtc_get_rtc_time(struct rtc_time *rtc_tm)
 	 * Once the read clears, read the RTC time (again via ioctl). Easy.
 	 */
 
-	while (rtc_is_updating() != 0 && jiffies - uip_watchdog < 2*HZ/100)
+	while (rtc_is_updating() != 0 &&
+	       time_before(jiffies, uip_watchdog + 2*HZ/100))
 		cpu_relax();
 
 	/*
diff --git a/trunk/drivers/char/snsc_event.c b/trunk/drivers/char/snsc_event.c
index 1b75b0b7d542..31a7765eaf73 100644
--- a/trunk/drivers/char/snsc_event.c
+++ b/trunk/drivers/char/snsc_event.c
@@ -63,16 +63,13 @@ static int
 scdrv_parse_event(char *event, int *src, int *code, int *esp_code, char *desc)
 {
 	char *desc_end;
-	__be32 from_buf;
 
 	/* record event source address */
-	from_buf = get_unaligned((__be32 *)event);
-	*src = be32_to_cpup(&from_buf);
+	*src = get_unaligned_be32(event);
 	event += 4; 			/* move on to event code */
 
 	/* record the system controller's event code */
-	from_buf = get_unaligned((__be32 *)event);
-	*code = be32_to_cpup(&from_buf);
+	*code = get_unaligned_be32(event);
 	event += 4;			/* move on to event arguments */
 
 	/* how many arguments are in the packet? */
@@ -86,8 +83,7 @@ scdrv_parse_event(char *event, int *src, int *code, int *esp_code, char *desc)
 		/* not an integer argument, so give up */
 		return -1;
 	}
-	from_buf = get_unaligned((__be32 *)event);
-	*esp_code = be32_to_cpup(&from_buf);
+	*esp_code = get_unaligned_be32(event);
 	event += 4;
 
 	/* parse out the event description */
diff --git a/trunk/drivers/char/synclink.c b/trunk/drivers/char/synclink.c
index a3237d48a584..fadab1d9510f 100644
--- a/trunk/drivers/char/synclink.c
+++ b/trunk/drivers/char/synclink.c
@@ -218,9 +218,9 @@ struct mgsl_struct {
 
 	u32 pending_bh;
 
-	int bh_running;		/* Protection from multiple */
+	bool bh_running;		/* Protection from multiple */
 	int isr_overflow;
-	int bh_requested;
+	bool bh_requested;
 	
 	int dcd_chkcount;		/* check counts to prevent */
 	int cts_chkcount;		/* too many IRQs if a signal */
@@ -250,12 +250,12 @@ struct mgsl_struct {
 	int tx_holding_count;		/* number of tx holding buffers waiting */
 	struct tx_holding_buffer tx_holding_buffers[MAX_TX_HOLDING_BUFFERS];
 
-	int rx_enabled;
-	int rx_overflow;
-	int rx_rcc_underrun;
+	bool rx_enabled;
+	bool rx_overflow;
+	bool rx_rcc_underrun;
 
-	int tx_enabled;
-	int tx_active;
+	bool tx_enabled;
+	bool tx_active;
 	u32 idle_mode;
 
 	u16 cmr_value;
@@ -269,14 +269,14 @@ struct mgsl_struct {
 
 	unsigned int io_base;		/* base I/O address of adapter */
 	unsigned int io_addr_size;	/* size of the I/O address range */
-	int io_addr_requested;		/* nonzero if I/O address requested */
+	bool io_addr_requested;		/* true if I/O address requested */
 	
 	unsigned int irq_level;		/* interrupt level */
 	unsigned long irq_flags;
-	int irq_requested;		/* nonzero if IRQ requested */
+	bool irq_requested;		/* true if IRQ requested */
 	
 	unsigned int dma_level;		/* DMA channel */
-	int dma_requested;		/* nonzero if dma channel requested */
+	bool dma_requested;		/* true if dma channel requested */
 
 	u16 mbre_bit;
 	u16 loopback_bits;
@@ -286,27 +286,27 @@ struct mgsl_struct {
 
 	unsigned char serial_signals;	/* current serial signal states */
 
-	int irq_occurred;		/* for diagnostics use */
+	bool irq_occurred;		/* for diagnostics use */
 	unsigned int init_error;	/* Initialization startup error 		(DIAGS)	*/
 	int	fDiagnosticsmode;	/* Driver in Diagnostic mode?			(DIAGS)	*/
 
 	u32 last_mem_alloc;
 	unsigned char* memory_base;	/* shared memory address (PCI only) */
 	u32 phys_memory_base;
-	int shared_mem_requested;
+	bool shared_mem_requested;
 
 	unsigned char* lcr_base;	/* local config registers (PCI only) */
 	u32 phys_lcr_base;
 	u32 lcr_offset;
-	int lcr_mem_requested;
+	bool lcr_mem_requested;
 
 	u32 misc_ctrl_value;
 	char flag_buf[MAX_ASYNC_BUFFER_SIZE];
 	char char_buf[MAX_ASYNC_BUFFER_SIZE];	
-	BOOLEAN drop_rts_on_tx_done;
+	bool drop_rts_on_tx_done;
 
-	BOOLEAN loopmode_insert_requested;
-	BOOLEAN	loopmode_send_done_requested;
+	bool loopmode_insert_requested;
+	bool loopmode_send_done_requested;
 	
 	struct	_input_signal_events	input_signal_events;
 
@@ -752,10 +752,10 @@ static void mgsl_trace_block(struct mgsl_struct *info,const char* data, int coun
 /*
  * Adapter diagnostic routines
  */
-static BOOLEAN mgsl_register_test( struct mgsl_struct *info );
-static BOOLEAN mgsl_irq_test( struct mgsl_struct *info );
-static BOOLEAN mgsl_dma_test( struct mgsl_struct *info );
-static BOOLEAN mgsl_memory_test( struct mgsl_struct *info );
+static bool mgsl_register_test( struct mgsl_struct *info );
+static bool mgsl_irq_test( struct mgsl_struct *info );
+static bool mgsl_dma_test( struct mgsl_struct *info );
+static bool mgsl_memory_test( struct mgsl_struct *info );
 static int mgsl_adapter_test( struct mgsl_struct *info );
 
 /*
@@ -770,8 +770,8 @@ static struct mgsl_struct* mgsl_allocate_device(void);
  * DMA buffer manupulation functions.
  */
 static void mgsl_free_rx_frame_buffers( struct mgsl_struct *info, unsigned int StartIndex, unsigned int EndIndex );
-static int  mgsl_get_rx_frame( struct mgsl_struct *info );
-static int  mgsl_get_raw_rx_frame( struct mgsl_struct *info );
+static bool mgsl_get_rx_frame( struct mgsl_struct *info );
+static bool mgsl_get_raw_rx_frame( struct mgsl_struct *info );
 static void mgsl_reset_rx_dma_buffers( struct mgsl_struct *info );
 static void mgsl_reset_tx_dma_buffers( struct mgsl_struct *info );
 static int num_free_tx_dma_buffers(struct mgsl_struct *info);
@@ -791,7 +791,7 @@ static int mgsl_alloc_intermediate_rxbuffer_memory(struct mgsl_struct *info);
 static void mgsl_free_intermediate_rxbuffer_memory(struct mgsl_struct *info);
 static int mgsl_alloc_intermediate_txbuffer_memory(struct mgsl_struct *info);
 static void mgsl_free_intermediate_txbuffer_memory(struct mgsl_struct *info);
-static int load_next_tx_holding_buffer(struct mgsl_struct *info);
+static bool load_next_tx_holding_buffer(struct mgsl_struct *info);
 static int save_tx_buffer_request(struct mgsl_struct *info,const char *Buffer, unsigned int BufferSize);
 
 /*
@@ -847,7 +847,7 @@ static int mgsl_wait_event(struct mgsl_struct * info, int __user *mask);
 static int mgsl_loopmode_send_done( struct mgsl_struct * info );
 
 /* set non-zero on successful registration with PCI subsystem */
-static int pci_registered;
+static bool pci_registered;
 
 /*
  * Global linked list of SyncLink devices
@@ -1054,8 +1054,8 @@ static int mgsl_bh_action(struct mgsl_struct *info)
 
 	if (!rc) {
 		/* Mark BH routine as complete */
-		info->bh_running   = 0;
-		info->bh_requested = 0;
+		info->bh_running = false;
+		info->bh_requested = false;
 	}
 	
 	spin_unlock_irqrestore(&info->irq_spinlock,flags);
@@ -1079,7 +1079,7 @@ static void mgsl_bh_handler(struct work_struct *work)
 		printk( "%s(%d):mgsl_bh_handler(%s) entry\n",
 			__FILE__,__LINE__,info->device_name);
 	
-	info->bh_running = 1;
+	info->bh_running = true;
 
 	while((action = mgsl_bh_action(info)) != 0) {
 	
@@ -1113,7 +1113,7 @@ static void mgsl_bh_handler(struct work_struct *work)
 
 static void mgsl_bh_receive(struct mgsl_struct *info)
 {
-	int (*get_rx_frame)(struct mgsl_struct *info) =
+	bool (*get_rx_frame)(struct mgsl_struct *info) =
 		(info->params.mode == MGSL_MODE_HDLC ? mgsl_get_rx_frame : mgsl_get_raw_rx_frame);
 
 	if ( debug_level >= DEBUG_LEVEL_BH )
@@ -1187,7 +1187,7 @@ static void mgsl_isr_receive_status( struct mgsl_struct *info )
  		usc_loopmode_active(info) )
  	{
 		++info->icount.rxabort;
-	 	info->loopmode_insert_requested = FALSE;
+	 	info->loopmode_insert_requested = false;
  
  		/* clear CMR:13 to start echoing RxD to TxD */
 		info->cmr_value &= ~BIT13;
@@ -1257,7 +1257,7 @@ static void mgsl_isr_transmit_status( struct mgsl_struct *info )
 	else
 		info->icount.txunder++;
 			
-	info->tx_active = 0;
+	info->tx_active = false;
 	info->xmit_cnt = info->xmit_head = info->xmit_tail = 0;
 	del_timer(&info->tx_timer);	
 	
@@ -1267,7 +1267,7 @@ static void mgsl_isr_transmit_status( struct mgsl_struct *info )
 			info->serial_signals &= ~SerialSignal_RTS;
 			usc_set_serial_signals( info );
 		}
-		info->drop_rts_on_tx_done = 0;
+		info->drop_rts_on_tx_done = false;
 	}
 
 #if SYNCLINK_GENERIC_HDLC
@@ -1403,7 +1403,7 @@ static void mgsl_isr_io_pin( struct mgsl_struct *info )
 		usc_OutReg( info, SICR,
 			(unsigned short)(usc_InReg(info,SICR) & ~(SICR_TXC_ACTIVE+SICR_TXC_INACTIVE)) );
 		usc_UnlatchIostatusBits( info, MISCSTATUS_TXC_LATCHED );
-		info->irq_occurred = 1;
+		info->irq_occurred = true;
 	}
 
 }	/* end of mgsl_isr_io_pin() */
@@ -1431,7 +1431,7 @@ static void mgsl_isr_transmit_data( struct mgsl_struct *info )
 	if ( info->xmit_cnt )
 		usc_load_txfifo( info );
 	else
-		info->tx_active = 0;
+		info->tx_active = false;
 		
 	if (info->xmit_cnt < WAKEUP_CHARS)
 		info->pending_bh |= BH_TRANSMIT;
@@ -1568,7 +1568,7 @@ static void mgsl_isr_misc( struct mgsl_struct *info )
 
 		/* schedule BH handler to restart receiver */
 		info->pending_bh |= BH_RECEIVE;
-		info->rx_rcc_underrun = 1;
+		info->rx_rcc_underrun = true;
 	}
 
 	usc_ClearIrqPendingBits( info, MISC );
@@ -1626,7 +1626,7 @@ static void mgsl_isr_receive_dma( struct mgsl_struct *info )
 	info->pending_bh |= BH_RECEIVE;
 	
 	if ( status & BIT3 ) {
-		info->rx_overflow = 1;
+		info->rx_overflow = true;
 		info->icount.buf_overrun++;
 	}
 
@@ -1745,7 +1745,7 @@ static irqreturn_t mgsl_interrupt(int dummy, void *dev_id)
 			printk("%s(%d):%s queueing bh task.\n",
 				__FILE__,__LINE__,info->device_name);
 		schedule_work(&info->task);
-		info->bh_requested = 1;
+		info->bh_requested = true;
 	}
 
 	spin_unlock(&info->irq_spinlock);
@@ -3303,7 +3303,8 @@ static int block_til_ready(struct tty_struct *tty, struct file * filp,
 {
 	DECLARE_WAITQUEUE(wait, current);
 	int		retval;
-	int		do_clocal = 0, extra_count = 0;
+	bool		do_clocal = false;
+	bool		extra_count = false;
 	unsigned long	flags;
 	
 	if (debug_level >= DEBUG_LEVEL_INFO)
@@ -3317,7 +3318,7 @@ static int block_til_ready(struct tty_struct *tty, struct file * filp,
 	}
 
 	if (tty->termios->c_cflag & CLOCAL)
-		do_clocal = 1;
+		do_clocal = true;
 
 	/* Wait for carrier detect and the line to become
 	 * free (i.e., not in use by the callout).  While we are in
@@ -3335,7 +3336,7 @@ static int block_til_ready(struct tty_struct *tty, struct file * filp,
 
 	spin_lock_irqsave(&info->irq_spinlock, flags);
 	if (!tty_hung_up_p(filp)) {
-		extra_count = 1;
+		extra_count = true;
 		info->count--;
 	}
 	spin_unlock_irqrestore(&info->irq_spinlock, flags);
@@ -4043,13 +4044,13 @@ static void mgsl_free_intermediate_txbuffer_memory(struct mgsl_struct *info)
  *
  *	info		pointer to device instance data
  *
- * Return Value:	1 if next buffered tx request loaded
+ * Return Value:	true if next buffered tx request loaded
  * 			into adapter's tx dma buffer,
- * 			0 otherwise
+ * 			false otherwise
  */
-static int load_next_tx_holding_buffer(struct mgsl_struct *info)
+static bool load_next_tx_holding_buffer(struct mgsl_struct *info)
 {
-	int ret = 0;
+	bool ret = false;
 
 	if ( info->tx_holding_count ) {
 		/* determine if we have enough tx dma buffers
@@ -4073,7 +4074,7 @@ static int load_next_tx_holding_buffer(struct mgsl_struct *info)
 			/* restart transmit timer */
 			mod_timer(&info->tx_timer, jiffies + msecs_to_jiffies(5000));
 
-			ret = 1;
+			ret = true;
 		}
 	}
 
@@ -4119,7 +4120,7 @@ static int mgsl_claim_resources(struct mgsl_struct *info)
 			__FILE__,__LINE__,info->device_name, info->io_base);
 		return -ENODEV;
 	}
-	info->io_addr_requested = 1;
+	info->io_addr_requested = true;
 	
 	if ( request_irq(info->irq_level,mgsl_interrupt,info->irq_flags,
 		info->device_name, info ) < 0 ) {
@@ -4127,7 +4128,7 @@ static int mgsl_claim_resources(struct mgsl_struct *info)
 			__FILE__,__LINE__,info->device_name, info->irq_level );
 		goto errout;
 	}
-	info->irq_requested = 1;
+	info->irq_requested = true;
 	
 	if ( info->bus_type == MGSL_BUS_TYPE_PCI ) {
 		if (request_mem_region(info->phys_memory_base,0x40000,"synclink") == NULL) {
@@ -4135,13 +4136,13 @@ static int mgsl_claim_resources(struct mgsl_struct *info)
 				__FILE__,__LINE__,info->device_name, info->phys_memory_base);
 			goto errout;
 		}
-		info->shared_mem_requested = 1;
+		info->shared_mem_requested = true;
 		if (request_mem_region(info->phys_lcr_base + info->lcr_offset,128,"synclink") == NULL) {
 			printk( "%s(%d):lcr mem addr conflict device %s Addr=%08X\n",
 				__FILE__,__LINE__,info->device_name, info->phys_lcr_base + info->lcr_offset);
 			goto errout;
 		}
-		info->lcr_mem_requested = 1;
+		info->lcr_mem_requested = true;
 
 		info->memory_base = ioremap(info->phys_memory_base,0x40000);
 		if (!info->memory_base) {
@@ -4172,7 +4173,7 @@ static int mgsl_claim_resources(struct mgsl_struct *info)
 			mgsl_release_resources( info );
 			return -ENODEV;
 		}
-		info->dma_requested = 1;
+		info->dma_requested = true;
 
 		/* ISA adapter uses bus master DMA */		
 		set_dma_mode(info->dma_level,DMA_MODE_CASCADE);
@@ -4200,12 +4201,12 @@ static void mgsl_release_resources(struct mgsl_struct *info)
 			
 	if ( info->irq_requested ) {
 		free_irq(info->irq_level, info);
-		info->irq_requested = 0;
+		info->irq_requested = false;
 	}
 	if ( info->dma_requested ) {
 		disable_dma(info->dma_level);
 		free_dma(info->dma_level);
-		info->dma_requested = 0;
+		info->dma_requested = false;
 	}
 	mgsl_free_dma_buffers(info);
 	mgsl_free_intermediate_rxbuffer_memory(info);
@@ -4213,15 +4214,15 @@ static void mgsl_release_resources(struct mgsl_struct *info)
 	
 	if ( info->io_addr_requested ) {
 		release_region(info->io_base,info->io_addr_size);
-		info->io_addr_requested = 0;
+		info->io_addr_requested = false;
 	}
 	if ( info->shared_mem_requested ) {
 		release_mem_region(info->phys_memory_base,0x40000);
-		info->shared_mem_requested = 0;
+		info->shared_mem_requested = false;
 	}
 	if ( info->lcr_mem_requested ) {
 		release_mem_region(info->phys_lcr_base + info->lcr_offset,128);
-		info->lcr_mem_requested = 0;
+		info->lcr_mem_requested = false;
 	}
 	if (info->memory_base){
 		iounmap(info->memory_base);
@@ -4486,7 +4487,7 @@ static int __init synclink_init(void)
 	if ((rc = pci_register_driver(&synclink_pci_driver)) < 0)
 		printk("%s:failed to register PCI driver, error=%d\n",__FILE__,rc);
 	else
-		pci_registered = 1;
+		pci_registered = true;
 
 	if ((rc = mgsl_init_tty()) < 0)
 		goto error;
@@ -4679,7 +4680,7 @@ static u16 usc_InReg( struct mgsl_struct *info, u16 RegAddr )
 static void usc_set_sdlc_mode( struct mgsl_struct *info )
 {
 	u16 RegValue;
-	int PreSL1660;
+	bool PreSL1660;
 	
 	/*
 	 * determine if the IUSC on the adapter is pre-SL1660. If
@@ -4692,11 +4693,7 @@ static void usc_set_sdlc_mode( struct mgsl_struct *info )
 	 */
 	usc_OutReg(info,TMCR,0x1f);
 	RegValue=usc_InReg(info,TMDR);
-	if ( RegValue == IUSC_PRE_SL1660 )
-		PreSL1660 = 1;
-	else
-		PreSL1660 = 0;
-	
+	PreSL1660 = (RegValue == IUSC_PRE_SL1660);
 
  	if ( info->params.flags & HDLC_FLAG_HDLC_LOOPMODE )
  	{
@@ -5382,9 +5379,9 @@ static void usc_process_rxoverrun_sync( struct mgsl_struct *info )
 	int start_index;
 	int end_index;
 	int frame_start_index;
-	int start_of_frame_found = FALSE;
-	int end_of_frame_found = FALSE;
-	int reprogram_dma = FALSE;
+	bool start_of_frame_found = false;
+	bool end_of_frame_found = false;
+	bool reprogram_dma = false;
 
 	DMABUFFERENTRY *buffer_list = info->rx_buffer_list;
 	u32 phys_addr;
@@ -5410,9 +5407,9 @@ static void usc_process_rxoverrun_sync( struct mgsl_struct *info )
 
 		if ( !start_of_frame_found )
 		{
-			start_of_frame_found = TRUE;
+			start_of_frame_found = true;
 			frame_start_index = end_index;
-			end_of_frame_found = FALSE;
+			end_of_frame_found = false;
 		}
 
 		if ( buffer_list[end_index].status )
@@ -5423,8 +5420,8 @@ static void usc_process_rxoverrun_sync( struct mgsl_struct *info )
 			/* We want to leave the buffers for this frame intact. */
 			/* Move on to next possible frame. */
 
-			start_of_frame_found = FALSE;
-			end_of_frame_found = TRUE;
+			start_of_frame_found = false;
+			end_of_frame_found = true;
 		}
 
   		/* advance to next buffer entry in linked list */
@@ -5439,8 +5436,8 @@ static void usc_process_rxoverrun_sync( struct mgsl_struct *info )
 			/* completely screwed, reset all receive buffers! */
 			mgsl_reset_rx_dma_buffers( info );
 			frame_start_index = 0;
-			start_of_frame_found = FALSE;
-			reprogram_dma = TRUE;
+			start_of_frame_found = false;
+			reprogram_dma = true;
 			break;
 		}
 	}
@@ -5466,7 +5463,7 @@ static void usc_process_rxoverrun_sync( struct mgsl_struct *info )
 
 		} while( start_index != end_index );
 
-		reprogram_dma = TRUE;
+		reprogram_dma = true;
 	}
 
 	if ( reprogram_dma )
@@ -5536,9 +5533,9 @@ static void usc_stop_receiver( struct mgsl_struct *info )
 	usc_OutReg( info, CCSR, (u16)(usc_InReg(info,CCSR) | BIT13) );
 	usc_RTCmd( info, RTCmd_PurgeRxFifo );
 
-	info->rx_enabled = 0;
-	info->rx_overflow = 0;
-	info->rx_rcc_underrun = 0;
+	info->rx_enabled = false;
+	info->rx_overflow = false;
+	info->rx_rcc_underrun = false;
 	
 }	/* end of stop_receiver() */
 
@@ -5601,7 +5598,7 @@ static void usc_start_receiver( struct mgsl_struct *info )
 
 	usc_OutReg( info, CCSR, 0x1020 );
 
-	info->rx_enabled = 1;
+	info->rx_enabled = true;
 
 }	/* end of usc_start_receiver() */
 
@@ -5628,14 +5625,14 @@ static void usc_start_transmitter( struct mgsl_struct *info )
 		/* RTS and set a flag indicating that the driver should */
 		/* negate RTS when the transmission completes. */
 
-		info->drop_rts_on_tx_done = 0;
+		info->drop_rts_on_tx_done = false;
 
 		if ( info->params.flags & HDLC_FLAG_AUTO_RTS ) {
 			usc_get_serial_signals( info );
 			if ( !(info->serial_signals & SerialSignal_RTS) ) {
 				info->serial_signals |= SerialSignal_RTS;
 				usc_set_serial_signals( info );
-				info->drop_rts_on_tx_done = 1;
+				info->drop_rts_on_tx_done = true;
 			}
 		}
 
@@ -5699,11 +5696,11 @@ static void usc_start_transmitter( struct mgsl_struct *info )
 			mod_timer(&info->tx_timer, jiffies +
 					msecs_to_jiffies(5000));
 		}
-		info->tx_active = 1;
+		info->tx_active = true;
 	}
 
 	if ( !info->tx_enabled ) {
-		info->tx_enabled = 1;
+		info->tx_enabled = true;
 		if ( info->params.flags & HDLC_FLAG_AUTO_CTS )
 			usc_EnableTransmitter(info,ENABLE_AUTO_CTS);
 		else
@@ -5735,8 +5732,8 @@ static void usc_stop_transmitter( struct mgsl_struct *info )
 	usc_DmaCmd( info, DmaCmd_ResetTxChannel );
 	usc_RTCmd( info, RTCmd_PurgeTxFifo );
 
-	info->tx_enabled = 0;
-	info->tx_active  = 0;
+	info->tx_enabled = false;
+	info->tx_active = false;
 
 }	/* end of usc_stop_transmitter() */
 
@@ -6520,7 +6517,7 @@ static void mgsl_reset_rx_dma_buffers( struct mgsl_struct *info )
  */
 static void mgsl_free_rx_frame_buffers( struct mgsl_struct *info, unsigned int StartIndex, unsigned int EndIndex )
 {
-	int Done = 0;
+	bool Done = false;
 	DMABUFFERENTRY *pBufEntry;
 	unsigned int Index;
 
@@ -6534,7 +6531,7 @@ static void mgsl_free_rx_frame_buffers( struct mgsl_struct *info, unsigned int S
 
 		if ( Index == EndIndex ) {
 			/* This is the last buffer of the frame! */
-			Done = 1;
+			Done = true;
 		}
 
 		/* reset current buffer for reuse */
@@ -6559,18 +6556,18 @@ static void mgsl_free_rx_frame_buffers( struct mgsl_struct *info, unsigned int S
  * 	receive DMA buffers. Only frames received without errors are returned.
  *
  * Arguments:	 	info	pointer to device extension
- * Return Value:	1 if frame returned, otherwise 0
+ * Return Value:	true if frame returned, otherwise false
  */
-static int mgsl_get_rx_frame(struct mgsl_struct *info)
+static bool mgsl_get_rx_frame(struct mgsl_struct *info)
 {
 	unsigned int StartIndex, EndIndex;	/* index of 1st and last buffers of Rx frame */
 	unsigned short status;
 	DMABUFFERENTRY *pBufEntry;
 	unsigned int framesize = 0;
-	int ReturnCode = 0;
+	bool ReturnCode = false;
 	unsigned long flags;
 	struct tty_struct *tty = info->tty;
-	int return_frame = 0;
+	bool return_frame = false;
 	
 	/*
 	 * current_rx_buffer points to the 1st buffer of the next available
@@ -6629,7 +6626,7 @@ static int mgsl_get_rx_frame(struct mgsl_struct *info)
 		else {
 			info->icount.rxcrc++;
 			if ( info->params.crc_type & HDLC_CRC_RETURN_EX )
-				return_frame = 1;
+				return_frame = true;
 		}
 		framesize = 0;
 #if SYNCLINK_GENERIC_HDLC
@@ -6640,7 +6637,7 @@ static int mgsl_get_rx_frame(struct mgsl_struct *info)
 		}
 #endif
 	} else
-		return_frame = 1;
+		return_frame = true;
 
 	if ( return_frame ) {
 		/* receive frame has no errors, get frame size.
@@ -6719,7 +6716,7 @@ static int mgsl_get_rx_frame(struct mgsl_struct *info)
 	/* Free the buffers used by this frame. */
 	mgsl_free_rx_frame_buffers( info, StartIndex, EndIndex );
 
-	ReturnCode = 1;
+	ReturnCode = true;
 
 Cleanup:
 
@@ -6758,15 +6755,15 @@ static int mgsl_get_rx_frame(struct mgsl_struct *info)
  *	last Rx DMA buffer and return that last portion of the frame.
  *
  * Arguments:	 	info	pointer to device extension
- * Return Value:	1 if frame returned, otherwise 0
+ * Return Value:	true if frame returned, otherwise false
  */
-static int mgsl_get_raw_rx_frame(struct mgsl_struct *info)
+static bool mgsl_get_raw_rx_frame(struct mgsl_struct *info)
 {
 	unsigned int CurrentIndex, NextIndex;
 	unsigned short status;
 	DMABUFFERENTRY *pBufEntry;
 	unsigned int framesize = 0;
-	int ReturnCode = 0;
+	bool ReturnCode = false;
 	unsigned long flags;
 	struct tty_struct *tty = info->tty;
 
@@ -6891,7 +6888,7 @@ static int mgsl_get_raw_rx_frame(struct mgsl_struct *info)
 		/* Free the buffers used by this frame. */
 		mgsl_free_rx_frame_buffers( info, CurrentIndex, CurrentIndex );
 
-		ReturnCode = 1;
+		ReturnCode = true;
 	}
 
 
@@ -7000,15 +6997,15 @@ static void mgsl_load_tx_dma_buffer(struct mgsl_struct *info,
  * 	Performs a register test of the 16C32.
  * 	
  * Arguments:		info	pointer to device instance data
- * Return Value:		TRUE if test passed, otherwise FALSE
+ * Return Value:		true if test passed, otherwise false
  */
-static BOOLEAN mgsl_register_test( struct mgsl_struct *info )
+static bool mgsl_register_test( struct mgsl_struct *info )
 {
 	static unsigned short BitPatterns[] =
 		{ 0x0000, 0xffff, 0xaaaa, 0x5555, 0x1234, 0x6969, 0x9696, 0x0f0f };
 	static unsigned int Patterncount = ARRAY_SIZE(BitPatterns);
 	unsigned int i;
-	BOOLEAN rc = TRUE;
+	bool rc = true;
 	unsigned long flags;
 
 	spin_lock_irqsave(&info->irq_spinlock,flags);
@@ -7019,10 +7016,10 @@ static BOOLEAN mgsl_register_test( struct mgsl_struct *info )
 	if ( (usc_InReg( info, SICR ) != 0) ||
 		  (usc_InReg( info, IVR  ) != 0) ||
 		  (usc_InDmaReg( info, DIVR ) != 0) ){
-		rc = FALSE;
+		rc = false;
 	}
 
-	if ( rc == TRUE ){
+	if ( rc ){
 		/* Write bit patterns to various registers but do it out of */
 		/* sync, then read back and verify values. */
 
@@ -7040,7 +7037,7 @@ static BOOLEAN mgsl_register_test( struct mgsl_struct *info )
 				  (usc_InReg( info, RCLR ) != BitPatterns[(i+3)%Patterncount]) ||
 				  (usc_InReg( info, RSR )  != BitPatterns[(i+4)%Patterncount]) ||
 				  (usc_InDmaReg( info, TBCR ) != BitPatterns[(i+5)%Patterncount]) ){
-				rc = FALSE;
+				rc = false;
 				break;
 			}
 		}
@@ -7056,9 +7053,9 @@ static BOOLEAN mgsl_register_test( struct mgsl_struct *info )
 /* mgsl_irq_test() 	Perform interrupt test of the 16C32.
  * 
  * Arguments:		info	pointer to device instance data
- * Return Value:	TRUE if test passed, otherwise FALSE
+ * Return Value:	true if test passed, otherwise false
  */
-static BOOLEAN mgsl_irq_test( struct mgsl_struct *info )
+static bool mgsl_irq_test( struct mgsl_struct *info )
 {
 	unsigned long EndTime;
 	unsigned long flags;
@@ -7068,10 +7065,10 @@ static BOOLEAN mgsl_irq_test( struct mgsl_struct *info )
 
 	/*
 	 * Setup 16C32 to interrupt on TxC pin (14MHz clock) transition. 
-	 * The ISR sets irq_occurred to 1. 
+	 * The ISR sets irq_occurred to true.
 	 */
 
-	info->irq_occurred = FALSE;
+	info->irq_occurred = false;
 
 	/* Enable INTEN gate for ISA adapter (Port 6, Bit12) */
 	/* Enable INTEN (Port 6, Bit12) */
@@ -7097,10 +7094,7 @@ static BOOLEAN mgsl_irq_test( struct mgsl_struct *info )
 	usc_reset(info);
 	spin_unlock_irqrestore(&info->irq_spinlock,flags);
 	
-	if ( !info->irq_occurred ) 
-		return FALSE;
-	else
-		return TRUE;
+	return info->irq_occurred;
 
 }	/* end of mgsl_irq_test() */
 
@@ -7111,16 +7105,16 @@ static BOOLEAN mgsl_irq_test( struct mgsl_struct *info )
  * 	using single buffer DMA mode.
  * 	
  * Arguments:		info	pointer to device instance data
- * Return Value:	TRUE if test passed, otherwise FALSE
+ * Return Value:	true if test passed, otherwise false
  */
-static BOOLEAN mgsl_dma_test( struct mgsl_struct *info )
+static bool mgsl_dma_test( struct mgsl_struct *info )
 {
 	unsigned short FifoLevel;
 	unsigned long phys_addr;
 	unsigned int FrameSize;
 	unsigned int i;
 	char *TmpPtr;
-	BOOLEAN rc = TRUE;
+	bool rc = true;
 	unsigned short status=0;
 	unsigned long EndTime;
 	unsigned long flags;
@@ -7233,7 +7227,7 @@ static BOOLEAN mgsl_dma_test( struct mgsl_struct *info )
 
 	for(;;) {
 		if (time_after(jiffies, EndTime)) {
-			rc = FALSE;
+			rc = false;
 			break;
 		}
 
@@ -7289,7 +7283,7 @@ static BOOLEAN mgsl_dma_test( struct mgsl_struct *info )
 
 	for(;;) {
 		if (time_after(jiffies, EndTime)) {
-			rc = FALSE;
+			rc = false;
 			break;
 		}
 
@@ -7309,7 +7303,7 @@ static BOOLEAN mgsl_dma_test( struct mgsl_struct *info )
 	}
 
 
-	if ( rc == TRUE )
+	if ( rc )
 	{
 		/* Enable 16C32 transmitter. */
 
@@ -7337,7 +7331,7 @@ static BOOLEAN mgsl_dma_test( struct mgsl_struct *info )
 
 		while ( !(status & (BIT6+BIT5+BIT4+BIT2+BIT1)) ) {
 			if (time_after(jiffies, EndTime)) {
-				rc = FALSE;
+				rc = false;
 				break;
 			}
 
@@ -7348,13 +7342,13 @@ static BOOLEAN mgsl_dma_test( struct mgsl_struct *info )
 	}
 
 
-	if ( rc == TRUE ){
+	if ( rc ){
 		/* CHECK FOR TRANSMIT ERRORS */
 		if ( status & (BIT5 + BIT1) ) 
-			rc = FALSE;
+			rc = false;
 	}
 
-	if ( rc == TRUE ) {
+	if ( rc ) {
 		/* WAIT FOR RECEIVE COMPLETE */
 
 		/* Wait 100ms */
@@ -7364,7 +7358,7 @@ static BOOLEAN mgsl_dma_test( struct mgsl_struct *info )
 		status=info->rx_buffer_list[0].status;
 		while ( status == 0 ) {
 			if (time_after(jiffies, EndTime)) {
-				rc = FALSE;
+				rc = false;
 				break;
 			}
 			status=info->rx_buffer_list[0].status;
@@ -7372,17 +7366,17 @@ static BOOLEAN mgsl_dma_test( struct mgsl_struct *info )
 	}
 
 
-	if ( rc == TRUE ) {
+	if ( rc ) {
 		/* CHECK FOR RECEIVE ERRORS */
 		status = info->rx_buffer_list[0].status;
 
 		if ( status & (BIT8 + BIT3 + BIT1) ) {
 			/* receive error has occurred */
-			rc = FALSE;
+			rc = false;
 		} else {
 			if ( memcmp( info->tx_buffer_list[0].virt_addr ,
 				info->rx_buffer_list[0].virt_addr, FrameSize ) ){
-				rc = FALSE;
+				rc = false;
 			}
 		}
 	}
@@ -7445,9 +7439,9 @@ static int mgsl_adapter_test( struct mgsl_struct *info )
  * 	Test the shared memory on a PCI adapter.
  * 
  * Arguments:		info	pointer to device instance data
- * Return Value:	TRUE if test passed, otherwise FALSE
+ * Return Value:	true if test passed, otherwise false
  */
-static BOOLEAN mgsl_memory_test( struct mgsl_struct *info )
+static bool mgsl_memory_test( struct mgsl_struct *info )
 {
 	static unsigned long BitPatterns[] =
 		{ 0x0, 0x55555555, 0xaaaaaaaa, 0x66666666, 0x99999999, 0xffffffff, 0x12345678 };
@@ -7457,7 +7451,7 @@ static BOOLEAN mgsl_memory_test( struct mgsl_struct *info )
 	unsigned long * TestAddr;
 
 	if ( info->bus_type != MGSL_BUS_TYPE_PCI )
-		return TRUE;
+		return true;
 
 	TestAddr = (unsigned long *)info->memory_base;
 
@@ -7466,7 +7460,7 @@ static BOOLEAN mgsl_memory_test( struct mgsl_struct *info )
 	for ( i = 0 ; i < Patterncount ; i++ ) {
 		*TestAddr = BitPatterns[i];
 		if ( *TestAddr != BitPatterns[i] )
-			return FALSE;
+			return false;
 	}
 
 	/* Test address lines with incrementing pattern over */
@@ -7481,13 +7475,13 @@ static BOOLEAN mgsl_memory_test( struct mgsl_struct *info )
 
 	for ( i = 0 ; i < TestLimit ; i++ ) {
 		if ( *TestAddr != i * 4 )
-			return FALSE;
+			return false;
 		TestAddr++;
 	}
 
 	memset( info->memory_base, 0, SHARED_MEM_ADDRESS_SIZE );
 
-	return TRUE;
+	return true;
 
 }	/* End Of mgsl_memory_test() */
 
@@ -7604,7 +7598,7 @@ static void mgsl_tx_timeout(unsigned long context)
 		info->icount.txtimeout++;
 	}
 	spin_lock_irqsave(&info->irq_spinlock,flags);
-	info->tx_active = 0;
+	info->tx_active = false;
 	info->xmit_cnt = info->xmit_head = info->xmit_tail = 0;
 
 	if ( info->params.flags & HDLC_FLAG_HDLC_LOOPMODE )
@@ -7632,7 +7626,7 @@ static int mgsl_loopmode_send_done( struct mgsl_struct * info )
 	spin_lock_irqsave(&info->irq_spinlock,flags);
 	if (info->params.flags & HDLC_FLAG_HDLC_LOOPMODE) {
 		if (info->tx_active)
-			info->loopmode_send_done_requested = TRUE;
+			info->loopmode_send_done_requested = true;
 		else
 			usc_loopmode_send_done(info);
 	}
@@ -7646,7 +7640,7 @@ static int mgsl_loopmode_send_done( struct mgsl_struct * info )
  */
 static void usc_loopmode_send_done( struct mgsl_struct * info )
 {
- 	info->loopmode_send_done_requested = FALSE;
+ 	info->loopmode_send_done_requested = false;
  	/* clear CMR:13 to 0 to start echoing RxData to TxData */
  	info->cmr_value &= ~BIT13;			  
  	usc_OutReg(info, CMR, info->cmr_value);
@@ -7668,7 +7662,7 @@ static void usc_loopmode_cancel_transmit( struct mgsl_struct * info )
  */
 static void usc_loopmode_insert_request( struct mgsl_struct * info )
 {
- 	info->loopmode_insert_requested = TRUE;
+ 	info->loopmode_insert_requested = true;
  
  	/* enable RxAbort irq. On next RxAbort, clear CMR:13 to
  	 * begin repeating TxData on RxData (complete insertion)
diff --git a/trunk/drivers/char/synclink_gt.c b/trunk/drivers/char/synclink_gt.c
index 3c89266c8255..f3d8d72e5ea4 100644
--- a/trunk/drivers/char/synclink_gt.c
+++ b/trunk/drivers/char/synclink_gt.c
@@ -117,7 +117,7 @@ static struct pci_driver pci_driver = {
 	.remove		= __devexit_p(remove_one),
 };
 
-static int pci_registered;
+static bool pci_registered;
 
 /*
  * module configuration and status
@@ -289,12 +289,12 @@ struct slgt_info {
 
 	struct work_struct task;
 	u32 pending_bh;
-	int bh_requested;
-	int bh_running;
+	bool bh_requested;
+	bool bh_running;
 
 	int isr_overflow;
-	int irq_requested;	/* nonzero if IRQ requested */
-	int irq_occurred;	/* for diagnostics use */
+	bool irq_requested;	/* true if IRQ requested */
+	bool irq_occurred;	/* for diagnostics use */
 
 	/* device configuration */
 
@@ -304,7 +304,7 @@ struct slgt_info {
 
 	unsigned char __iomem * reg_addr;  /* memory mapped registers address */
 	u32 phys_reg_addr;
-	int reg_addr_requested;
+	bool reg_addr_requested;
 
 	MGSL_PARAMS params;       /* communications parameters */
 	u32 idle_mode;
@@ -315,11 +315,11 @@ struct slgt_info {
 
 	/* device status */
 
-	int rx_enabled;
-	int rx_restart;
+	bool rx_enabled;
+	bool rx_restart;
 
-	int tx_enabled;
-	int tx_active;
+	bool tx_enabled;
+	bool tx_active;
 
 	unsigned char signals;    /* serial signal states */
 	int init_error;  /* initialization error */
@@ -329,7 +329,7 @@ struct slgt_info {
 
 	char flag_buf[MAX_ASYNC_BUFFER_SIZE];
 	char char_buf[MAX_ASYNC_BUFFER_SIZE];
-	BOOLEAN drop_rts_on_tx_done;
+	bool drop_rts_on_tx_done;
 	struct	_input_signal_events	input_signal_events;
 
 	int dcd_chkcount;	/* check counts to prevent */
@@ -467,8 +467,8 @@ static void rx_start(struct slgt_info *info);
 static void reset_rbufs(struct slgt_info *info);
 static void free_rbufs(struct slgt_info *info, unsigned int first, unsigned int last);
 static void rdma_reset(struct slgt_info *info);
-static int  rx_get_frame(struct slgt_info *info);
-static int  rx_get_buf(struct slgt_info *info);
+static bool rx_get_frame(struct slgt_info *info);
+static bool rx_get_buf(struct slgt_info *info);
 
 static void tx_start(struct slgt_info *info);
 static void tx_stop(struct slgt_info *info);
@@ -1968,8 +1968,8 @@ static int bh_action(struct slgt_info *info)
 		rc = BH_STATUS;
 	} else {
 		/* Mark BH routine as complete */
-		info->bh_running   = 0;
-		info->bh_requested = 0;
+		info->bh_running = false;
+		info->bh_requested = false;
 		rc = 0;
 	}
 
@@ -1988,7 +1988,7 @@ static void bh_handler(struct work_struct *work)
 
 	if (!info)
 		return;
-	info->bh_running = 1;
+	info->bh_running = true;
 
 	while((action = bh_action(info))) {
 		switch (action) {
@@ -2158,7 +2158,7 @@ static void isr_serial(struct slgt_info *info)
 
 	wr_reg16(info, SSR, status); /* clear pending */
 
-	info->irq_occurred = 1;
+	info->irq_occurred = true;
 
 	if (info->params.mode == MGSL_MODE_ASYNC) {
 		if (status & IRQ_TXIDLE) {
@@ -2225,7 +2225,7 @@ static void isr_rdma(struct slgt_info *info)
 
 	if (status & (BIT5 + BIT4)) {
 		DBGISR(("%s isr_rdma rx_restart=1\n", info->device_name));
-		info->rx_restart = 1;
+		info->rx_restart = true;
 	}
 	info->pending_bh |= BH_RECEIVE;
 }
@@ -2276,14 +2276,14 @@ static void isr_txeom(struct slgt_info *info, unsigned short status)
 				info->icount.txok++;
 		}
 
-		info->tx_active = 0;
+		info->tx_active = false;
 		info->tx_count = 0;
 
 		del_timer(&info->tx_timer);
 
 		if (info->params.mode != MGSL_MODE_ASYNC && info->drop_rts_on_tx_done) {
 			info->signals &= ~SerialSignal_RTS;
-			info->drop_rts_on_tx_done = 0;
+			info->drop_rts_on_tx_done = false;
 			set_signals(info);
 		}
 
@@ -2337,7 +2337,7 @@ static irqreturn_t slgt_interrupt(int dummy, void *dev_id)
 
 	while((gsr = rd_reg32(info, GSR) & 0xffffff00)) {
 		DBGISR(("%s gsr=%08x\n", info->device_name, gsr));
-		info->irq_occurred = 1;
+		info->irq_occurred = true;
 		for(i=0; i < info->port_count ; i++) {
 			if (info->port_array[i] == NULL)
 				continue;
@@ -2374,7 +2374,7 @@ static irqreturn_t slgt_interrupt(int dummy, void *dev_id)
 		    !port->bh_requested) {
 			DBGISR(("%s bh queued\n", port->device_name));
 			schedule_work(&port->task);
-			port->bh_requested = 1;
+			port->bh_requested = true;
 		}
 	}
 
@@ -3110,7 +3110,8 @@ static int block_til_ready(struct tty_struct *tty, struct file *filp,
 {
 	DECLARE_WAITQUEUE(wait, current);
 	int		retval;
-	int		do_clocal = 0, extra_count = 0;
+	bool		do_clocal = false;
+	bool		extra_count = false;
 	unsigned long	flags;
 
 	DBGINFO(("%s block_til_ready\n", tty->driver->name));
@@ -3122,7 +3123,7 @@ static int block_til_ready(struct tty_struct *tty, struct file *filp,
 	}
 
 	if (tty->termios->c_cflag & CLOCAL)
-		do_clocal = 1;
+		do_clocal = true;
 
 	/* Wait for carrier detect and the line to become
 	 * free (i.e., not in use by the callout).  While we are in
@@ -3136,7 +3137,7 @@ static int block_til_ready(struct tty_struct *tty, struct file *filp,
 
 	spin_lock_irqsave(&info->lock, flags);
 	if (!tty_hung_up_p(filp)) {
-		extra_count = 1;
+		extra_count = true;
 		info->count--;
 	}
 	spin_unlock_irqrestore(&info->lock, flags);
@@ -3321,7 +3322,7 @@ static int claim_resources(struct slgt_info *info)
 		goto errout;
 	}
 	else
-		info->reg_addr_requested = 1;
+		info->reg_addr_requested = true;
 
 	info->reg_addr = ioremap(info->phys_reg_addr, SLGT_REG_SIZE);
 	if (!info->reg_addr) {
@@ -3341,12 +3342,12 @@ static void release_resources(struct slgt_info *info)
 {
 	if (info->irq_requested) {
 		free_irq(info->irq_level, info);
-		info->irq_requested = 0;
+		info->irq_requested = false;
 	}
 
 	if (info->reg_addr_requested) {
 		release_mem_region(info->phys_reg_addr, SLGT_REG_SIZE);
-		info->reg_addr_requested = 0;
+		info->reg_addr_requested = false;
 	}
 
 	if (info->reg_addr) {
@@ -3511,7 +3512,7 @@ static void device_init(int adapter_num, struct pci_dev *pdev)
 				port_array[0]->device_name,
 				port_array[0]->irq_level));
 		} else {
-			port_array[0]->irq_requested = 1;
+			port_array[0]->irq_requested = true;
 			adapter_test(port_array[0]);
 			for (i=1 ; i < port_count ; i++) {
 				port_array[i]->init_error = port_array[0]->init_error;
@@ -3654,7 +3655,7 @@ static int __init slgt_init(void)
 		printk("%s pci_register_driver error=%d\n", driver_name, rc);
 		goto error;
 	}
-	pci_registered = 1;
+	pci_registered = true;
 
 	if (!slgt_device_list)
 		printk("%s no devices found\n",driver_name);
@@ -3812,8 +3813,8 @@ static void rx_stop(struct slgt_info *info)
 
 	rdma_reset(info);
 
-	info->rx_enabled = 0;
-	info->rx_restart = 0;
+	info->rx_enabled = false;
+	info->rx_restart = false;
 }
 
 static void rx_start(struct slgt_info *info)
@@ -3849,8 +3850,8 @@ static void rx_start(struct slgt_info *info)
 	/* enable receiver */
 	wr_reg16(info, RCR, (unsigned short)(rd_reg16(info, RCR) | BIT1));
 
-	info->rx_restart = 0;
-	info->rx_enabled = 1;
+	info->rx_restart = false;
+	info->rx_enabled = true;
 }
 
 static void tx_start(struct slgt_info *info)
@@ -3858,11 +3859,11 @@ static void tx_start(struct slgt_info *info)
 	if (!info->tx_enabled) {
 		wr_reg16(info, TCR,
 			 (unsigned short)((rd_reg16(info, TCR) | BIT1) & ~BIT2));
-		info->tx_enabled = TRUE;
+		info->tx_enabled = true;
 	}
 
 	if (info->tx_count) {
-		info->drop_rts_on_tx_done = 0;
+		info->drop_rts_on_tx_done = false;
 
 		if (info->params.mode != MGSL_MODE_ASYNC) {
 			if (info->params.flags & HDLC_FLAG_AUTO_RTS) {
@@ -3870,7 +3871,7 @@ static void tx_start(struct slgt_info *info)
 				if (!(info->signals & SerialSignal_RTS)) {
 					info->signals |= SerialSignal_RTS;
 					set_signals(info);
-					info->drop_rts_on_tx_done = 1;
+					info->drop_rts_on_tx_done = true;
 				}
 			}
 
@@ -3888,7 +3889,7 @@ static void tx_start(struct slgt_info *info)
 			wr_reg16(info, SSR, IRQ_TXIDLE);
 		}
 		tdma_start(info);
-		info->tx_active = 1;
+		info->tx_active = true;
 	}
 }
 
@@ -3949,8 +3950,8 @@ static void tx_stop(struct slgt_info *info)
 
 	reset_tbufs(info);
 
-	info->tx_enabled = 0;
-	info->tx_active  = 0;
+	info->tx_enabled = false;
+	info->tx_active = false;
 }
 
 static void reset_port(struct slgt_info *info)
@@ -4470,14 +4471,13 @@ static void reset_rbufs(struct slgt_info *info)
 /*
  * pass receive HDLC frame to upper layer
  *
- * return 1 if frame available, otherwise 0
+ * return true if frame available, otherwise false
  */
-static int rx_get_frame(struct slgt_info *info)
+static bool rx_get_frame(struct slgt_info *info)
 {
 	unsigned int start, end;
 	unsigned short status;
 	unsigned int framesize = 0;
-	int rc = 0;
 	unsigned long flags;
 	struct tty_struct *tty = info->tty;
 	unsigned char addr_field = 0xff;
@@ -4601,23 +4601,23 @@ static int rx_get_frame(struct slgt_info *info)
 		}
 	}
 	free_rbufs(info, start, end);
-	rc = 1;
+	return true;
 
 cleanup:
-	return rc;
+	return false;
 }
 
 /*
  * pass receive buffer (RAW synchronous mode) to tty layer
- * return 1 if buffer available, otherwise 0
+ * return true if buffer available, otherwise false
  */
-static int rx_get_buf(struct slgt_info *info)
+static bool rx_get_buf(struct slgt_info *info)
 {
 	unsigned int i = info->rbuf_current;
 	unsigned int count;
 
 	if (!desc_complete(info->rbufs[i]))
-		return 0;
+		return false;
 	count = desc_count(info->rbufs[i]);
 	switch(info->params.mode) {
 	case MGSL_MODE_MONOSYNC:
@@ -4633,7 +4633,7 @@ static int rx_get_buf(struct slgt_info *info)
 		ldisc_receive_buf(info->tty, info->rbufs[i].buf,
 				  info->flag_buf, count);
 	free_rbufs(info, i, i);
-	return 1;
+	return true;
 }
 
 static void reset_tbufs(struct slgt_info *info)
@@ -4758,7 +4758,7 @@ static int irq_test(struct slgt_info *info)
 
 	/* assume failure */
 	info->init_error = DiagStatus_IrqFailure;
-	info->irq_occurred = FALSE;
+	info->irq_occurred = false;
 
 	spin_unlock_irqrestore(&info->lock, flags);
 
@@ -4891,7 +4891,7 @@ static void tx_timeout(unsigned long context)
 		info->icount.txtimeout++;
 	}
 	spin_lock_irqsave(&info->lock,flags);
-	info->tx_active = 0;
+	info->tx_active = false;
 	info->tx_count = 0;
 	spin_unlock_irqrestore(&info->lock,flags);
 
diff --git a/trunk/drivers/char/synclinkmp.c b/trunk/drivers/char/synclinkmp.c
index c96062ea72b4..e98c3e6f8216 100644
--- a/trunk/drivers/char/synclinkmp.c
+++ b/trunk/drivers/char/synclinkmp.c
@@ -188,9 +188,9 @@ typedef struct _synclinkmp_info {
 
 	u32 pending_bh;
 
-	int bh_running;				/* Protection from multiple */
+	bool bh_running;				/* Protection from multiple */
 	int isr_overflow;
-	int bh_requested;
+	bool bh_requested;
 
 	int dcd_chkcount;			/* check counts to prevent */
 	int cts_chkcount;			/* too many IRQs if a signal */
@@ -213,11 +213,11 @@ typedef struct _synclinkmp_info {
 	unsigned char *tmp_rx_buf;
 	unsigned int tmp_rx_buf_count;
 
-	int rx_enabled;
-	int rx_overflow;
+	bool rx_enabled;
+	bool rx_overflow;
 
-	int tx_enabled;
-	int tx_active;
+	bool tx_enabled;
+	bool tx_active;
 	u32 idle_mode;
 
 	unsigned char ie0_value;
@@ -238,13 +238,13 @@ typedef struct _synclinkmp_info {
 
 	unsigned int irq_level;			/* interrupt level */
 	unsigned long irq_flags;
-	int irq_requested;			/* nonzero if IRQ requested */
+	bool irq_requested;			/* true if IRQ requested */
 
 	MGSL_PARAMS params;			/* communications parameters */
 
 	unsigned char serial_signals;		/* current serial signal states */
 
-	int irq_occurred;			/* for diagnostics use */
+	bool irq_occurred;			/* for diagnostics use */
 	unsigned int init_error;		/* Initialization startup error */
 
 	u32 last_mem_alloc;
@@ -255,7 +255,7 @@ typedef struct _synclinkmp_info {
 	unsigned char* sca_base;		/* HD64570 SCA Memory address */
 	u32 phys_sca_base;
 	u32 sca_offset;
-	int sca_base_requested;
+	bool sca_base_requested;
 
 	unsigned char* lcr_base;		/* local config registers (PCI only) */
 	u32 phys_lcr_base;
@@ -265,12 +265,12 @@ typedef struct _synclinkmp_info {
 	unsigned char* statctrl_base;		/* status/control register memory */
 	u32 phys_statctrl_base;
 	u32 statctrl_offset;
-	int sca_statctrl_requested;
+	bool sca_statctrl_requested;
 
 	u32 misc_ctrl_value;
 	char flag_buf[MAX_ASYNC_BUFFER_SIZE];
 	char char_buf[MAX_ASYNC_BUFFER_SIZE];
-	BOOLEAN drop_rts_on_tx_done;
+	bool drop_rts_on_tx_done;
 
 	struct	_input_signal_events	input_signal_events;
 
@@ -571,12 +571,12 @@ static void shutdown(SLMP_INFO *info);
 static void program_hw(SLMP_INFO *info);
 static void change_params(SLMP_INFO *info);
 
-static int  init_adapter(SLMP_INFO *info);
-static int  register_test(SLMP_INFO *info);
-static int  irq_test(SLMP_INFO *info);
-static int  loopback_test(SLMP_INFO *info);
+static bool init_adapter(SLMP_INFO *info);
+static bool register_test(SLMP_INFO *info);
+static bool irq_test(SLMP_INFO *info);
+static bool loopback_test(SLMP_INFO *info);
 static int  adapter_test(SLMP_INFO *info);
-static int  memory_test(SLMP_INFO *info);
+static bool memory_test(SLMP_INFO *info);
 
 static void reset_adapter(SLMP_INFO *info);
 static void reset_port(SLMP_INFO *info);
@@ -587,7 +587,7 @@ static void rx_stop(SLMP_INFO *info);
 static void rx_start(SLMP_INFO *info);
 static void rx_reset_buffers(SLMP_INFO *info);
 static void rx_free_frame_buffers(SLMP_INFO *info, unsigned int first, unsigned int last);
-static int  rx_get_frame(SLMP_INFO *info);
+static bool rx_get_frame(SLMP_INFO *info);
 
 static void tx_start(SLMP_INFO *info);
 static void tx_stop(SLMP_INFO *info);
@@ -1473,7 +1473,7 @@ static inline int line_info(char *buf, SLMP_INFO *info)
 
 /* Called to print information about devices
  */
-int read_proc(char *page, char **start, off_t off, int count,
+static int read_proc(char *page, char **start, off_t off, int count,
 	      int *eof, void *data)
 {
 	int len = 0, l;
@@ -2024,7 +2024,7 @@ static void hdlcdev_exit(SLMP_INFO *info)
 /* Return next bottom half action to perform.
  * Return Value:	BH action code or 0 if nothing to do.
  */
-int bh_action(SLMP_INFO *info)
+static int bh_action(SLMP_INFO *info)
 {
 	unsigned long flags;
 	int rc = 0;
@@ -2044,8 +2044,8 @@ int bh_action(SLMP_INFO *info)
 
 	if (!rc) {
 		/* Mark BH routine as complete */
-		info->bh_running   = 0;
-		info->bh_requested = 0;
+		info->bh_running = false;
+		info->bh_requested = false;
 	}
 
 	spin_unlock_irqrestore(&info->lock,flags);
@@ -2055,7 +2055,7 @@ int bh_action(SLMP_INFO *info)
 
 /* Perform bottom half processing of work items queued by ISR.
  */
-void bh_handler(struct work_struct *work)
+static void bh_handler(struct work_struct *work)
 {
 	SLMP_INFO *info = container_of(work, SLMP_INFO, task);
 	int action;
@@ -2067,7 +2067,7 @@ void bh_handler(struct work_struct *work)
 		printk( "%s(%d):%s bh_handler() entry\n",
 			__FILE__,__LINE__,info->device_name);
 
-	info->bh_running = 1;
+	info->bh_running = true;
 
 	while((action = bh_action(info)) != 0) {
 
@@ -2100,7 +2100,7 @@ void bh_handler(struct work_struct *work)
 			__FILE__,__LINE__,info->device_name);
 }
 
-void bh_receive(SLMP_INFO *info)
+static void bh_receive(SLMP_INFO *info)
 {
 	if ( debug_level >= DEBUG_LEVEL_BH )
 		printk( "%s(%d):%s bh_receive()\n",
@@ -2109,7 +2109,7 @@ void bh_receive(SLMP_INFO *info)
 	while( rx_get_frame(info) );
 }
 
-void bh_transmit(SLMP_INFO *info)
+static void bh_transmit(SLMP_INFO *info)
 {
 	struct tty_struct *tty = info->tty;
 
@@ -2121,7 +2121,7 @@ void bh_transmit(SLMP_INFO *info)
 		tty_wakeup(tty);
 }
 
-void bh_status(SLMP_INFO *info)
+static void bh_status(SLMP_INFO *info)
 {
 	if ( debug_level >= DEBUG_LEVEL_BH )
 		printk( "%s(%d):%s bh_status() entry\n",
@@ -2133,7 +2133,7 @@ void bh_status(SLMP_INFO *info)
 	info->cts_chkcount = 0;
 }
 
-void isr_timer(SLMP_INFO * info)
+static void isr_timer(SLMP_INFO * info)
 {
 	unsigned char timer = (info->port_num & 1) ? TIMER2 : TIMER0;
 
@@ -2152,14 +2152,14 @@ void isr_timer(SLMP_INFO * info)
 	 */
 	write_reg(info, (unsigned char)(timer + TMCS), 0);
 
-	info->irq_occurred = TRUE;
+	info->irq_occurred = true;
 
 	if ( debug_level >= DEBUG_LEVEL_ISR )
 		printk("%s(%d):%s isr_timer()\n",
 			__FILE__,__LINE__,info->device_name);
 }
 
-void isr_rxint(SLMP_INFO * info)
+static void isr_rxint(SLMP_INFO * info)
 {
  	struct tty_struct *tty = info->tty;
  	struct	mgsl_icount *icount = &info->icount;
@@ -2218,7 +2218,7 @@ void isr_rxint(SLMP_INFO * info)
 /*
  * handle async rx data interrupts
  */
-void isr_rxrdy(SLMP_INFO * info)
+static void isr_rxrdy(SLMP_INFO * info)
 {
 	u16 status;
 	unsigned char DataByte;
@@ -2232,7 +2232,7 @@ void isr_rxrdy(SLMP_INFO * info)
 	while((status = read_reg(info,CST0)) & BIT0)
 	{
 		int flag = 0;
-		int over = 0;
+		bool over = false;
 		DataByte = read_reg(info,TRB);
 
 		icount->rx++;
@@ -2265,7 +2265,7 @@ void isr_rxrdy(SLMP_INFO * info)
 					 * reported immediately, and doesn't
 					 * affect the current character
 					 */
-					over = 1;
+					over = true;
 				}
 			}
 		}	/* end of if (error) */
@@ -2318,14 +2318,14 @@ static void isr_txeom(SLMP_INFO * info, unsigned char status)
 				info->icount.txok++;
 		}
 
-		info->tx_active = 0;
+		info->tx_active = false;
 		info->tx_count = info->tx_put = info->tx_get = 0;
 
 		del_timer(&info->tx_timer);
 
 		if (info->params.mode != MGSL_MODE_ASYNC && info->drop_rts_on_tx_done ) {
 			info->serial_signals &= ~SerialSignal_RTS;
-			info->drop_rts_on_tx_done = 0;
+			info->drop_rts_on_tx_done = false;
 			set_signals(info);
 		}
 
@@ -2348,7 +2348,7 @@ static void isr_txeom(SLMP_INFO * info, unsigned char status)
 /*
  * handle tx status interrupts
  */
-void isr_txint(SLMP_INFO * info)
+static void isr_txint(SLMP_INFO * info)
 {
 	unsigned char status = read_reg(info, SR1) & info->ie1_value & (UDRN + IDLE + CCTS);
 
@@ -2376,7 +2376,7 @@ void isr_txint(SLMP_INFO * info)
 /*
  * handle async tx data interrupts
  */
-void isr_txrdy(SLMP_INFO * info)
+static void isr_txrdy(SLMP_INFO * info)
 {
 	if ( debug_level >= DEBUG_LEVEL_ISR )
 		printk("%s(%d):%s isr_txrdy() tx_count=%d\n",
@@ -2398,7 +2398,7 @@ void isr_txrdy(SLMP_INFO * info)
 	if ( info->tx_count )
 		tx_load_fifo( info );
 	else {
-		info->tx_active = 0;
+		info->tx_active = false;
 		info->ie0_value &= ~TXRDYE;
 		write_reg(info, IE0, info->ie0_value);
 	}
@@ -2407,7 +2407,7 @@ void isr_txrdy(SLMP_INFO * info)
 		info->pending_bh |= BH_TRANSMIT;
 }
 
-void isr_rxdmaok(SLMP_INFO * info)
+static void isr_rxdmaok(SLMP_INFO * info)
 {
 	/* BIT7 = EOT (end of transfer)
 	 * BIT6 = EOM (end of message/frame)
@@ -2424,7 +2424,7 @@ void isr_rxdmaok(SLMP_INFO * info)
 	info->pending_bh |= BH_RECEIVE;
 }
 
-void isr_rxdmaerror(SLMP_INFO * info)
+static void isr_rxdmaerror(SLMP_INFO * info)
 {
 	/* BIT5 = BOF (buffer overflow)
 	 * BIT4 = COF (counter overflow)
@@ -2438,11 +2438,11 @@ void isr_rxdmaerror(SLMP_INFO * info)
 		printk("%s(%d):%s isr_rxdmaerror(), status=%02x\n",
 			__FILE__,__LINE__,info->device_name,status);
 
-	info->rx_overflow = TRUE;
+	info->rx_overflow = true;
 	info->pending_bh |= BH_RECEIVE;
 }
 
-void isr_txdmaok(SLMP_INFO * info)
+static void isr_txdmaok(SLMP_INFO * info)
 {
 	unsigned char status_reg1 = read_reg(info, SR1);
 
@@ -2460,7 +2460,7 @@ void isr_txdmaok(SLMP_INFO * info)
 	write_reg(info, IE0, info->ie0_value);
 }
 
-void isr_txdmaerror(SLMP_INFO * info)
+static void isr_txdmaerror(SLMP_INFO * info)
 {
 	/* BIT5 = BOF (buffer overflow)
 	 * BIT4 = COF (counter overflow)
@@ -2477,7 +2477,7 @@ void isr_txdmaerror(SLMP_INFO * info)
 
 /* handle input serial signal changes
  */
-void isr_io_pin( SLMP_INFO *info, u16 status )
+static void isr_io_pin( SLMP_INFO *info, u16 status )
 {
  	struct	mgsl_icount *icount;
 
@@ -2691,7 +2691,7 @@ static irqreturn_t synclinkmp_interrupt(int dummy, void *dev_id)
 				printk("%s(%d):%s queueing bh task.\n",
 					__FILE__,__LINE__,port->device_name);
 			schedule_work(&port->task);
-			port->bh_requested = 1;
+			port->bh_requested = true;
 		}
 	}
 
@@ -3320,7 +3320,8 @@ static int block_til_ready(struct tty_struct *tty, struct file *filp,
 {
 	DECLARE_WAITQUEUE(wait, current);
 	int		retval;
-	int		do_clocal = 0, extra_count = 0;
+	bool		do_clocal = false;
+	bool		extra_count = false;
 	unsigned long	flags;
 
 	if (debug_level >= DEBUG_LEVEL_INFO)
@@ -3335,7 +3336,7 @@ static int block_til_ready(struct tty_struct *tty, struct file *filp,
 	}
 
 	if (tty->termios->c_cflag & CLOCAL)
-		do_clocal = 1;
+		do_clocal = true;
 
 	/* Wait for carrier detect and the line to become
 	 * free (i.e., not in use by the callout).  While we are in
@@ -3353,7 +3354,7 @@ static int block_til_ready(struct tty_struct *tty, struct file *filp,
 
 	spin_lock_irqsave(&info->lock, flags);
 	if (!tty_hung_up_p(filp)) {
-		extra_count = 1;
+		extra_count = true;
 		info->count--;
 	}
 	spin_unlock_irqrestore(&info->lock, flags);
@@ -3413,7 +3414,7 @@ static int block_til_ready(struct tty_struct *tty, struct file *filp,
 	return retval;
 }
 
-int alloc_dma_bufs(SLMP_INFO *info)
+static int alloc_dma_bufs(SLMP_INFO *info)
 {
 	unsigned short BuffersPerFrame;
 	unsigned short BufferCount;
@@ -3487,7 +3488,7 @@ int alloc_dma_bufs(SLMP_INFO *info)
 
 /* Allocate DMA buffers for the transmit and receive descriptor lists.
  */
-int alloc_buf_list(SLMP_INFO *info)
+static int alloc_buf_list(SLMP_INFO *info)
 {
 	unsigned int i;
 
@@ -3546,7 +3547,7 @@ int alloc_buf_list(SLMP_INFO *info)
 
 /* Allocate the frame DMA buffers used by the specified buffer list.
  */
-int alloc_frame_bufs(SLMP_INFO *info, SCADESC *buf_list,SCADESC_EX *buf_list_ex,int count)
+static int alloc_frame_bufs(SLMP_INFO *info, SCADESC *buf_list,SCADESC_EX *buf_list_ex,int count)
 {
 	int i;
 	unsigned long phys_addr;
@@ -3563,7 +3564,7 @@ int alloc_frame_bufs(SLMP_INFO *info, SCADESC *buf_list,SCADESC_EX *buf_list_ex,
 	return 0;
 }
 
-void free_dma_bufs(SLMP_INFO *info)
+static void free_dma_bufs(SLMP_INFO *info)
 {
 	info->buffer_list = NULL;
 	info->rx_buf_list = NULL;
@@ -3573,7 +3574,7 @@ void free_dma_bufs(SLMP_INFO *info)
 /* allocate buffer large enough to hold max_frame_size.
  * This buffer is used to pass an assembled frame to the line discipline.
  */
-int alloc_tmp_rx_buf(SLMP_INFO *info)
+static int alloc_tmp_rx_buf(SLMP_INFO *info)
 {
 	info->tmp_rx_buf = kmalloc(info->max_frame_size, GFP_KERNEL);
 	if (info->tmp_rx_buf == NULL)
@@ -3581,13 +3582,13 @@ int alloc_tmp_rx_buf(SLMP_INFO *info)
 	return 0;
 }
 
-void free_tmp_rx_buf(SLMP_INFO *info)
+static void free_tmp_rx_buf(SLMP_INFO *info)
 {
 	kfree(info->tmp_rx_buf);
 	info->tmp_rx_buf = NULL;
 }
 
-int claim_resources(SLMP_INFO *info)
+static int claim_resources(SLMP_INFO *info)
 {
 	if (request_mem_region(info->phys_memory_base,SCA_MEM_SIZE,"synclinkmp") == NULL) {
 		printk( "%s(%d):%s mem addr conflict, Addr=%08X\n",
@@ -3596,7 +3597,7 @@ int claim_resources(SLMP_INFO *info)
 		goto errout;
 	}
 	else
-		info->shared_mem_requested = 1;
+		info->shared_mem_requested = true;
 
 	if (request_mem_region(info->phys_lcr_base + info->lcr_offset,128,"synclinkmp") == NULL) {
 		printk( "%s(%d):%s lcr mem addr conflict, Addr=%08X\n",
@@ -3605,7 +3606,7 @@ int claim_resources(SLMP_INFO *info)
 		goto errout;
 	}
 	else
-		info->lcr_mem_requested = 1;
+		info->lcr_mem_requested = true;
 
 	if (request_mem_region(info->phys_sca_base + info->sca_offset,SCA_BASE_SIZE,"synclinkmp") == NULL) {
 		printk( "%s(%d):%s sca mem addr conflict, Addr=%08X\n",
@@ -3614,7 +3615,7 @@ int claim_resources(SLMP_INFO *info)
 		goto errout;
 	}
 	else
-		info->sca_base_requested = 1;
+		info->sca_base_requested = true;
 
 	if (request_mem_region(info->phys_statctrl_base + info->statctrl_offset,SCA_REG_SIZE,"synclinkmp") == NULL) {
 		printk( "%s(%d):%s stat/ctrl mem addr conflict, Addr=%08X\n",
@@ -3623,7 +3624,7 @@ int claim_resources(SLMP_INFO *info)
 		goto errout;
 	}
 	else
-		info->sca_statctrl_requested = 1;
+		info->sca_statctrl_requested = true;
 
 	info->memory_base = ioremap(info->phys_memory_base,SCA_MEM_SIZE);
 	if (!info->memory_base) {
@@ -3674,7 +3675,7 @@ int claim_resources(SLMP_INFO *info)
 	return -ENODEV;
 }
 
-void release_resources(SLMP_INFO *info)
+static void release_resources(SLMP_INFO *info)
 {
 	if ( debug_level >= DEBUG_LEVEL_INFO )
 		printk( "%s(%d):%s release_resources() entry\n",
@@ -3682,24 +3683,24 @@ void release_resources(SLMP_INFO *info)
 
 	if ( info->irq_requested ) {
 		free_irq(info->irq_level, info);
-		info->irq_requested = 0;
+		info->irq_requested = false;
 	}
 
 	if ( info->shared_mem_requested ) {
 		release_mem_region(info->phys_memory_base,SCA_MEM_SIZE);
-		info->shared_mem_requested = 0;
+		info->shared_mem_requested = false;
 	}
 	if ( info->lcr_mem_requested ) {
 		release_mem_region(info->phys_lcr_base + info->lcr_offset,128);
-		info->lcr_mem_requested = 0;
+		info->lcr_mem_requested = false;
 	}
 	if ( info->sca_base_requested ) {
 		release_mem_region(info->phys_sca_base + info->sca_offset,SCA_BASE_SIZE);
-		info->sca_base_requested = 0;
+		info->sca_base_requested = false;
 	}
 	if ( info->sca_statctrl_requested ) {
 		release_mem_region(info->phys_statctrl_base + info->statctrl_offset,SCA_REG_SIZE);
-		info->sca_statctrl_requested = 0;
+		info->sca_statctrl_requested = false;
 	}
 
 	if (info->memory_base){
@@ -3730,7 +3731,7 @@ void release_resources(SLMP_INFO *info)
 /* Add the specified device instance data structure to the
  * global linked list of devices and increment the device count.
  */
-void add_device(SLMP_INFO *info)
+static void add_device(SLMP_INFO *info)
 {
 	info->next_device = NULL;
 	info->line = synclinkmp_device_count;
@@ -3853,7 +3854,7 @@ static SLMP_INFO *alloc_dev(int adapter_num, int port_num, struct pci_dev *pdev)
 	return info;
 }
 
-void device_init(int adapter_num, struct pci_dev *pdev)
+static void device_init(int adapter_num, struct pci_dev *pdev)
 {
 	SLMP_INFO *port_array[SCA_MAX_PORTS];
 	int port;
@@ -3902,7 +3903,7 @@ void device_init(int adapter_num, struct pci_dev *pdev)
 				port_array[0]->irq_level );
 		}
 		else {
-			port_array[0]->irq_requested = 1;
+			port_array[0]->irq_requested = true;
 			adapter_test(port_array[0]);
 		}
 	}
@@ -4047,7 +4048,7 @@ module_exit(synclinkmp_exit);
  * The TxCLK and RxCLK signals are generated from the BRG and
  * the TxD is looped back to the RxD internally.
  */
-void enable_loopback(SLMP_INFO *info, int enable)
+static void enable_loopback(SLMP_INFO *info, int enable)
 {
 	if (enable) {
 		/* MD2 (Mode Register 2)
@@ -4094,7 +4095,7 @@ void enable_loopback(SLMP_INFO *info, int enable)
  *	data_rate	data rate of clock in bits per second
  *			A data rate of 0 disables the AUX clock.
  */
-void set_rate( SLMP_INFO *info, u32 data_rate )
+static void set_rate( SLMP_INFO *info, u32 data_rate )
 {
        	u32 TMCValue;
        	unsigned char BRValue;
@@ -4140,7 +4141,7 @@ void set_rate( SLMP_INFO *info, u32 data_rate )
 
 /* Disable receiver
  */
-void rx_stop(SLMP_INFO *info)
+static void rx_stop(SLMP_INFO *info)
 {
 	if (debug_level >= DEBUG_LEVEL_ISR)
 		printk("%s(%d):%s rx_stop()\n",
@@ -4155,13 +4156,13 @@ void rx_stop(SLMP_INFO *info)
 	write_reg(info, RXDMA + DCMD, SWABORT);	/* reset/init Rx DMA */
 	write_reg(info, RXDMA + DIR, 0);	/* disable Rx DMA interrupts */
 
-	info->rx_enabled = 0;
-	info->rx_overflow = 0;
+	info->rx_enabled = false;
+	info->rx_overflow = false;
 }
 
 /* enable the receiver
  */
-void rx_start(SLMP_INFO *info)
+static void rx_start(SLMP_INFO *info)
 {
 	int i;
 
@@ -4211,14 +4212,14 @@ void rx_start(SLMP_INFO *info)
 
 	write_reg(info, CMD, RXENABLE);
 
-	info->rx_overflow = FALSE;
-	info->rx_enabled = 1;
+	info->rx_overflow = false;
+	info->rx_enabled = true;
 }
 
 /* Enable the transmitter and send a transmit frame if
  * one is loaded in the DMA buffers.
  */
-void tx_start(SLMP_INFO *info)
+static void tx_start(SLMP_INFO *info)
 {
 	if (debug_level >= DEBUG_LEVEL_ISR)
 		printk("%s(%d):%s tx_start() tx_count=%d\n",
@@ -4227,7 +4228,7 @@ void tx_start(SLMP_INFO *info)
 	if (!info->tx_enabled ) {
 		write_reg(info, CMD, TXRESET);
 		write_reg(info, CMD, TXENABLE);
-		info->tx_enabled = TRUE;
+		info->tx_enabled = true;
 	}
 
 	if ( info->tx_count ) {
@@ -4236,7 +4237,7 @@ void tx_start(SLMP_INFO *info)
 		/* RTS and set a flag indicating that the driver should */
 		/* negate RTS when the transmission completes. */
 
-		info->drop_rts_on_tx_done = 0;
+		info->drop_rts_on_tx_done = false;
 
 		if (info->params.mode != MGSL_MODE_ASYNC) {
 
@@ -4245,7 +4246,7 @@ void tx_start(SLMP_INFO *info)
 				if ( !(info->serial_signals & SerialSignal_RTS) ) {
 					info->serial_signals |= SerialSignal_RTS;
 					set_signals( info );
-					info->drop_rts_on_tx_done = 1;
+					info->drop_rts_on_tx_done = true;
 				}
 			}
 
@@ -4282,13 +4283,13 @@ void tx_start(SLMP_INFO *info)
 			write_reg(info, IE0, info->ie0_value);
 		}
 
-		info->tx_active = 1;
+		info->tx_active = true;
 	}
 }
 
 /* stop the transmitter and DMA
  */
-void tx_stop( SLMP_INFO *info )
+static void tx_stop( SLMP_INFO *info )
 {
 	if (debug_level >= DEBUG_LEVEL_ISR)
 		printk("%s(%d):%s tx_stop()\n",
@@ -4308,14 +4309,14 @@ void tx_stop( SLMP_INFO *info )
 	info->ie0_value &= ~TXRDYE;
 	write_reg(info, IE0, info->ie0_value);	/* disable tx data interrupts */
 
-	info->tx_enabled = 0;
-	info->tx_active  = 0;
+	info->tx_enabled = false;
+	info->tx_active = false;
 }
 
 /* Fill the transmit FIFO until the FIFO is full or
  * there is no more data to load.
  */
-void tx_load_fifo(SLMP_INFO *info)
+static void tx_load_fifo(SLMP_INFO *info)
 {
 	u8 TwoBytes[2];
 
@@ -4364,7 +4365,7 @@ void tx_load_fifo(SLMP_INFO *info)
 
 /* Reset a port to a known state
  */
-void reset_port(SLMP_INFO *info)
+static void reset_port(SLMP_INFO *info)
 {
 	if (info->sca_base) {
 
@@ -4388,7 +4389,7 @@ void reset_port(SLMP_INFO *info)
 
 /* Reset all the ports to a known state.
  */
-void reset_adapter(SLMP_INFO *info)
+static void reset_adapter(SLMP_INFO *info)
 {
 	int i;
 
@@ -4400,7 +4401,7 @@ void reset_adapter(SLMP_INFO *info)
 
 /* Program port for asynchronous communications.
  */
-void async_mode(SLMP_INFO *info)
+static void async_mode(SLMP_INFO *info)
 {
 
   	unsigned char RegValue;
@@ -4539,7 +4540,7 @@ void async_mode(SLMP_INFO *info)
 
 /* Program the SCA for HDLC communications.
  */
-void hdlc_mode(SLMP_INFO *info)
+static void hdlc_mode(SLMP_INFO *info)
 {
 	unsigned char RegValue;
 	u32 DpllDivisor;
@@ -4741,7 +4742,7 @@ void hdlc_mode(SLMP_INFO *info)
 
 /* Set the transmit HDLC idle mode
  */
-void tx_set_idle(SLMP_INFO *info)
+static void tx_set_idle(SLMP_INFO *info)
 {
 	unsigned char RegValue = 0xff;
 
@@ -4761,7 +4762,7 @@ void tx_set_idle(SLMP_INFO *info)
 
 /* Query the adapter for the state of the V24 status (input) signals.
  */
-void get_signals(SLMP_INFO *info)
+static void get_signals(SLMP_INFO *info)
 {
 	u16 status = read_reg(info, SR3);
 	u16 gpstatus = read_status_reg(info);
@@ -4790,7 +4791,7 @@ void get_signals(SLMP_INFO *info)
 /* Set the state of DTR and RTS based on contents of
  * serial_signals member of device context.
  */
-void set_signals(SLMP_INFO *info)
+static void set_signals(SLMP_INFO *info)
 {
 	unsigned char RegValue;
 	u16 EnableBit;
@@ -4819,7 +4820,7 @@ void set_signals(SLMP_INFO *info)
  * and set the current buffer to the first buffer. This effectively
  * makes all buffers free and discards any data in buffers.
  */
-void rx_reset_buffers(SLMP_INFO *info)
+static void rx_reset_buffers(SLMP_INFO *info)
 {
 	rx_free_frame_buffers(info, 0, info->rx_buf_count - 1);
 }
@@ -4830,16 +4831,16 @@ void rx_reset_buffers(SLMP_INFO *info)
  * first  index of 1st receive buffer of frame
  * last   index of last receive buffer of frame
  */
-void rx_free_frame_buffers(SLMP_INFO *info, unsigned int first, unsigned int last)
+static void rx_free_frame_buffers(SLMP_INFO *info, unsigned int first, unsigned int last)
 {
-	int done = 0;
+	bool done = false;
 
 	while(!done) {
 	        /* reset current buffer for reuse */
 		info->rx_buf_list[first].status = 0xff;
 
 	        if (first == last) {
-	                done = 1;
+	                done = true;
 	                /* set new last rx descriptor address */
 			write_reg16(info, RXDMA + EDA, info->rx_buf_list_ex[first].phys_entry);
 	        }
@@ -4856,14 +4857,14 @@ void rx_free_frame_buffers(SLMP_INFO *info, unsigned int first, unsigned int las
 /* Return a received frame from the receive DMA buffers.
  * Only frames received without errors are returned.
  *
- * Return Value:	1 if frame returned, otherwise 0
+ * Return Value:	true if frame returned, otherwise false
  */
-int rx_get_frame(SLMP_INFO *info)
+static bool rx_get_frame(SLMP_INFO *info)
 {
 	unsigned int StartIndex, EndIndex;	/* index of 1st and last buffers of Rx frame */
 	unsigned short status;
 	unsigned int framesize = 0;
-	int ReturnCode = 0;
+	bool ReturnCode = false;
 	unsigned long flags;
 	struct tty_struct *tty = info->tty;
 	unsigned char addr_field = 0xff;
@@ -5014,7 +5015,7 @@ int rx_get_frame(SLMP_INFO *info)
 	/* Free the buffers used by this frame. */
 	rx_free_frame_buffers( info, StartIndex, EndIndex );
 
-	ReturnCode = 1;
+	ReturnCode = true;
 
 Cleanup:
 	if ( info->rx_enabled && info->rx_overflow ) {
@@ -5033,7 +5034,7 @@ int rx_get_frame(SLMP_INFO *info)
 
 /* load the transmit DMA buffer with data
  */
-void tx_load_dma_buffer(SLMP_INFO *info, const char *buf, unsigned int count)
+static void tx_load_dma_buffer(SLMP_INFO *info, const char *buf, unsigned int count)
 {
 	unsigned short copy_count;
 	unsigned int i = 0;
@@ -5073,12 +5074,12 @@ void tx_load_dma_buffer(SLMP_INFO *info, const char *buf, unsigned int count)
 	info->last_tx_buf = ++i;
 }
 
-int register_test(SLMP_INFO *info)
+static bool register_test(SLMP_INFO *info)
 {
 	static unsigned char testval[] = {0x00, 0xff, 0xaa, 0x55, 0x69, 0x96};
 	static unsigned int count = ARRAY_SIZE(testval);
 	unsigned int i;
-	int rc = TRUE;
+	bool rc = true;
 	unsigned long flags;
 
 	spin_lock_irqsave(&info->lock,flags);
@@ -5101,7 +5102,7 @@ int register_test(SLMP_INFO *info)
 			  (read_reg(info, SA0) != testval[(i+2)%count]) ||
 			  (read_reg(info, SA1) != testval[(i+3)%count]) )
 		{
-			rc = FALSE;
+			rc = false;
 			break;
 		}
 	}
@@ -5112,7 +5113,7 @@ int register_test(SLMP_INFO *info)
 	return rc;
 }
 
-int irq_test(SLMP_INFO *info)
+static bool irq_test(SLMP_INFO *info)
 {
 	unsigned long timeout;
 	unsigned long flags;
@@ -5124,7 +5125,7 @@ int irq_test(SLMP_INFO *info)
 
 	/* assume failure */
 	info->init_error = DiagStatus_IrqFailure;
-	info->irq_occurred = FALSE;
+	info->irq_occurred = false;
 
 	/* setup timer0 on SCA0 to interrupt */
 
@@ -5163,7 +5164,7 @@ int irq_test(SLMP_INFO *info)
 
 /* initialize individual SCA device (2 ports)
  */
-static int sca_init(SLMP_INFO *info)
+static bool sca_init(SLMP_INFO *info)
 {
 	/* set wait controller to single mem partition (low), no wait states */
 	write_reg(info, PABR0, 0);	/* wait controller addr boundary 0 */
@@ -5199,12 +5200,12 @@ static int sca_init(SLMP_INFO *info)
 	 */
 	write_reg(info, ITCR, 0);
 
-	return TRUE;
+	return true;
 }
 
 /* initialize adapter hardware
  */
-int init_adapter(SLMP_INFO *info)
+static bool init_adapter(SLMP_INFO *info)
 {
 	int i;
 
@@ -5257,20 +5258,20 @@ int init_adapter(SLMP_INFO *info)
 	sca_init(info->port_array[0]);
 	sca_init(info->port_array[2]);
 
-	return TRUE;
+	return true;
 }
 
 /* Loopback an HDLC frame to test the hardware
  * interrupt and DMA functions.
  */
-int loopback_test(SLMP_INFO *info)
+static bool loopback_test(SLMP_INFO *info)
 {
 #define TESTFRAMESIZE 20
 
 	unsigned long timeout;
 	u16 count = TESTFRAMESIZE;
 	unsigned char buf[TESTFRAMESIZE];
-	int rc = FALSE;
+	bool rc = false;
 	unsigned long flags;
 
 	struct tty_struct *oldtty = info->tty;
@@ -5304,16 +5305,16 @@ int loopback_test(SLMP_INFO *info)
 		msleep_interruptible(10);
 
 		if (rx_get_frame(info)) {
-			rc = TRUE;
+			rc = true;
 			break;
 		}
 	}
 
 	/* verify received frame length and contents */
-	if (rc == TRUE &&
-		( info->tmp_rx_buf_count != count ||
-		  memcmp(buf, info->tmp_rx_buf,count))) {
-		rc = FALSE;
+	if (rc &&
+	    ( info->tmp_rx_buf_count != count ||
+	      memcmp(buf, info->tmp_rx_buf,count))) {
+		rc = false;
 	}
 
 	spin_lock_irqsave(&info->lock,flags);
@@ -5328,7 +5329,7 @@ int loopback_test(SLMP_INFO *info)
 
 /* Perform diagnostics on hardware
  */
-int adapter_test( SLMP_INFO *info )
+static int adapter_test( SLMP_INFO *info )
 {
 	unsigned long flags;
 	if ( debug_level >= DEBUG_LEVEL_INFO )
@@ -5390,7 +5391,7 @@ int adapter_test( SLMP_INFO *info )
 
 /* Test the shared memory on a PCI adapter.
  */
-int memory_test(SLMP_INFO *info)
+static bool memory_test(SLMP_INFO *info)
 {
 	static unsigned long testval[] = { 0x0, 0x55555555, 0xaaaaaaaa,
 		0x66666666, 0x99999999, 0xffffffff, 0x12345678 };
@@ -5404,7 +5405,7 @@ int memory_test(SLMP_INFO *info)
 	for ( i = 0 ; i < count ; i++ ) {
 		*addr = testval[i];
 		if ( *addr != testval[i] )
-			return FALSE;
+			return false;
 	}
 
 	/* Test address lines with incrementing pattern over */
@@ -5419,12 +5420,12 @@ int memory_test(SLMP_INFO *info)
 
 	for ( i = 0 ; i < limit ; i++ ) {
 		if ( *addr != i * 4 )
-			return FALSE;
+			return false;
 		addr++;
 	}
 
 	memset( info->memory_base, 0, SCA_MEM_SIZE );
-	return TRUE;
+	return true;
 }
 
 /* Load data into PCI adapter shared memory.
@@ -5442,7 +5443,7 @@ int memory_test(SLMP_INFO *info)
  * the write transation. This allows any pending DMA request to gain control
  * of the local bus in a timely fasion.
  */
-void load_pci_memory(SLMP_INFO *info, char* dest, const char* src, unsigned short count)
+static void load_pci_memory(SLMP_INFO *info, char* dest, const char* src, unsigned short count)
 {
 	/* A load interval of 16 allows for 4 32-bit writes at */
 	/* 136ns each for a maximum latency of 542ns on the local bus.*/
@@ -5461,7 +5462,7 @@ void load_pci_memory(SLMP_INFO *info, char* dest, const char* src, unsigned shor
 	memcpy(dest, src, count % sca_pci_load_interval);
 }
 
-void trace_block(SLMP_INFO *info,const char* data, int count, int xmit)
+static void trace_block(SLMP_INFO *info,const char* data, int count, int xmit)
 {
 	int i;
 	int linecount;
@@ -5496,7 +5497,7 @@ void trace_block(SLMP_INFO *info,const char* data, int count, int xmit)
 /* called when HDLC frame times out
  * update stats and do tx completion processing
  */
-void tx_timeout(unsigned long context)
+static void tx_timeout(unsigned long context)
 {
 	SLMP_INFO *info = (SLMP_INFO*)context;
 	unsigned long flags;
@@ -5508,7 +5509,7 @@ void tx_timeout(unsigned long context)
 		info->icount.txtimeout++;
 	}
 	spin_lock_irqsave(&info->lock,flags);
-	info->tx_active = 0;
+	info->tx_active = false;
 	info->tx_count = info->tx_put = info->tx_get = 0;
 
 	spin_unlock_irqrestore(&info->lock,flags);
@@ -5523,7 +5524,7 @@ void tx_timeout(unsigned long context)
 
 /* called to periodically check the DSR/RI modem signal input status
  */
-void status_timeout(unsigned long context)
+static void status_timeout(unsigned long context)
 {
 	u16 status = 0;
 	SLMP_INFO *info = (SLMP_INFO*)context;
@@ -5574,36 +5575,36 @@ void status_timeout(unsigned long context)
 	}
 
 
-unsigned char read_reg(SLMP_INFO * info, unsigned char Addr)
+static unsigned char read_reg(SLMP_INFO * info, unsigned char Addr)
 {
 	CALC_REGADDR();
 	return *RegAddr;
 }
-void write_reg(SLMP_INFO * info, unsigned char Addr, unsigned char Value)
+static void write_reg(SLMP_INFO * info, unsigned char Addr, unsigned char Value)
 {
 	CALC_REGADDR();
 	*RegAddr = Value;
 }
 
-u16 read_reg16(SLMP_INFO * info, unsigned char Addr)
+static u16 read_reg16(SLMP_INFO * info, unsigned char Addr)
 {
 	CALC_REGADDR();
 	return *((u16 *)RegAddr);
 }
 
-void write_reg16(SLMP_INFO * info, unsigned char Addr, u16 Value)
+static void write_reg16(SLMP_INFO * info, unsigned char Addr, u16 Value)
 {
 	CALC_REGADDR();
 	*((u16 *)RegAddr) = Value;
 }
 
-unsigned char read_status_reg(SLMP_INFO * info)
+static unsigned char read_status_reg(SLMP_INFO * info)
 {
 	unsigned char *RegAddr = (unsigned char *)info->statctrl_base;
 	return *RegAddr;
 }
 
-void write_control_reg(SLMP_INFO * info)
+static void write_control_reg(SLMP_INFO * info)
 {
 	unsigned char *RegAddr = (unsigned char *)info->statctrl_base;
 	*RegAddr = info->port_array[0]->ctrlreg_value;
diff --git a/trunk/drivers/char/sysrq.c b/trunk/drivers/char/sysrq.c
index de60e1ea4fb3..9e9bad8bdcf4 100644
--- a/trunk/drivers/char/sysrq.c
+++ b/trunk/drivers/char/sysrq.c
@@ -196,6 +196,48 @@ static struct sysrq_key_op sysrq_showlocks_op = {
 #define sysrq_showlocks_op (*(struct sysrq_key_op *)0)
 #endif
 
+#ifdef CONFIG_SMP
+static DEFINE_SPINLOCK(show_lock);
+
+static void showacpu(void *dummy)
+{
+	unsigned long flags;
+
+	/* Idle CPUs have no interesting backtrace. */
+	if (idle_cpu(smp_processor_id()))
+		return;
+
+	spin_lock_irqsave(&show_lock, flags);
+	printk(KERN_INFO "CPU%d:\n", smp_processor_id());
+	show_stack(NULL, NULL);
+	spin_unlock_irqrestore(&show_lock, flags);
+}
+
+static void sysrq_showregs_othercpus(struct work_struct *dummy)
+{
+	smp_call_function(showacpu, NULL, 0, 0);
+}
+
+static DECLARE_WORK(sysrq_showallcpus, sysrq_showregs_othercpus);
+
+static void sysrq_handle_showallcpus(int key, struct tty_struct *tty)
+{
+	struct pt_regs *regs = get_irq_regs();
+	if (regs) {
+		printk(KERN_INFO "CPU%d:\n", smp_processor_id());
+		show_regs(regs);
+	}
+	schedule_work(&sysrq_showallcpus);
+}
+
+static struct sysrq_key_op sysrq_showallcpus_op = {
+	.handler	= sysrq_handle_showallcpus,
+	.help_msg	= "aLlcpus",
+	.action_msg	= "Show backtrace of all active CPUs",
+	.enable_mask	= SYSRQ_ENABLE_DUMP,
+};
+#endif
+
 static void sysrq_handle_showregs(int key, struct tty_struct *tty)
 {
 	struct pt_regs *regs = get_irq_regs();
@@ -271,8 +313,7 @@ static struct sysrq_key_op sysrq_term_op = {
 
 static void moom_callback(struct work_struct *ignored)
 {
-	out_of_memory(&NODE_DATA(0)->node_zonelists[ZONE_NORMAL],
-			GFP_KERNEL, 0);
+	out_of_memory(node_zonelist(0, GFP_KERNEL), GFP_KERNEL, 0);
 }
 
 static DECLARE_WORK(moom_work, moom_callback);
@@ -341,7 +382,11 @@ static struct sysrq_key_op *sysrq_key_table[36] = {
 	&sysrq_kill_op,			/* i */
 	NULL,				/* j */
 	&sysrq_SAK_op,			/* k */
+#ifdef CONFIG_SMP
+	&sysrq_showallcpus_op,		/* l */
+#else
 	NULL,				/* l */
+#endif
 	&sysrq_showmem_op,		/* m */
 	&sysrq_unrt_op,			/* n */
 	/* o: This will often be registered as 'Off' at init time */
diff --git a/trunk/drivers/char/toshiba.c b/trunk/drivers/char/toshiba.c
index ce5ebe3b168f..64f1ceed0b2c 100644
--- a/trunk/drivers/char/toshiba.c
+++ b/trunk/drivers/char/toshiba.c
@@ -520,12 +520,11 @@ static int __init toshiba_init(void)
 	{
 		struct proc_dir_entry *pde;
 
-		pde = create_proc_entry("toshiba", 0, NULL);
+		pde = proc_create("toshiba", 0, NULL, &proc_toshiba_fops);
 		if (!pde) {
 			misc_deregister(&tosh_device);
 			return -ENOMEM;
 		}
-		pde->proc_fops = &proc_toshiba_fops;
 	}
 #endif
 
diff --git a/trunk/drivers/char/tpm/Kconfig b/trunk/drivers/char/tpm/Kconfig
index 8f3f7620f95a..3738cfa209ff 100644
--- a/trunk/drivers/char/tpm/Kconfig
+++ b/trunk/drivers/char/tpm/Kconfig
@@ -23,7 +23,7 @@ if TCG_TPM
 
 config TCG_TIS
 	tristate "TPM Interface Specification 1.2 Interface"
-	depends on PNPACPI
+	depends on PNP
 	---help---
 	  If you have a TPM security chip that is compliant with the
 	  TCG TIS 1.2 TPM specification say Yes and it will be accessible
@@ -32,7 +32,6 @@ config TCG_TIS
 
 config TCG_NSC
 	tristate "National Semiconductor TPM Interface"
-	depends on PNPACPI
 	---help---
 	  If you have a TPM security chip from National Semiconductor 
 	  say Yes and it will be accessible from within Linux.  To 
@@ -48,7 +47,7 @@ config TCG_ATMEL
 
 config TCG_INFINEON
 	tristate "Infineon Technologies TPM Interface"
-	depends on PNPACPI
+	depends on PNP
 	---help---
 	  If you have a TPM security chip from Infineon Technologies
 	  (either SLD 9630 TT 1.1 or SLB 9635 TT 1.2) say Yes and it
diff --git a/trunk/drivers/char/tpm/tpm_nsc.c b/trunk/drivers/char/tpm/tpm_nsc.c
index 6313326bc41f..ab18c1e7b115 100644
--- a/trunk/drivers/char/tpm/tpm_nsc.c
+++ b/trunk/drivers/char/tpm/tpm_nsc.c
@@ -264,7 +264,7 @@ static const struct tpm_vendor_specific tpm_nsc = {
 
 static struct platform_device *pdev = NULL;
 
-static void __devexit tpm_nsc_remove(struct device *dev)
+static void tpm_nsc_remove(struct device *dev)
 {
 	struct tpm_chip *chip = dev_get_drvdata(dev);
 	if ( chip ) {
diff --git a/trunk/drivers/char/tty_io.c b/trunk/drivers/char/tty_io.c
index 4d3c7018f0c3..98b65a230994 100644
--- a/trunk/drivers/char/tty_io.c
+++ b/trunk/drivers/char/tty_io.c
@@ -1180,7 +1180,7 @@ struct tty_driver *tty_find_polling_driver(char *name, int *line)
 		if (*str == ',')
 			str++;
 		if (*str == '\0')
-			str = 0;
+			str = NULL;
 
 		if (tty_line >= 0 && tty_line <= p->num && p->poll_init &&
 				!p->poll_init(p, tty_line, str)) {
diff --git a/trunk/drivers/char/viotape.c b/trunk/drivers/char/viotape.c
index db7a731e2362..58aad63831f4 100644
--- a/trunk/drivers/char/viotape.c
+++ b/trunk/drivers/char/viotape.c
@@ -249,6 +249,7 @@ static int proc_viotape_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations proc_viotape_operations = {
+	.owner		= THIS_MODULE,
 	.open		= proc_viotape_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -915,7 +916,6 @@ static struct vio_driver viotape_driver = {
 int __init viotap_init(void)
 {
 	int ret;
-	struct proc_dir_entry *e;
 
 	if (!firmware_has_feature(FW_FEATURE_ISERIES))
 		return -ENODEV;
@@ -968,11 +968,8 @@ int __init viotap_init(void)
 	if (ret)
 		goto unreg_class;
 
-	e = create_proc_entry("iSeries/viotape", S_IFREG|S_IRUGO, NULL);
-	if (e) {
-		e->owner = THIS_MODULE;
-		e->proc_fops = &proc_viotape_operations;
-	}
+	proc_create("iSeries/viotape", S_IFREG|S_IRUGO, NULL,
+		    &proc_viotape_operations);
 
 	return 0;
 
diff --git a/trunk/drivers/char/vt.c b/trunk/drivers/char/vt.c
index 9b58b894f823..1c2660477135 100644
--- a/trunk/drivers/char/vt.c
+++ b/trunk/drivers/char/vt.c
@@ -301,7 +301,7 @@ static void scrup(struct vc_data *vc, unsigned int t, unsigned int b, int nr)
 	d = (unsigned short *)(vc->vc_origin + vc->vc_size_row * t);
 	s = (unsigned short *)(vc->vc_origin + vc->vc_size_row * (t + nr));
 	scr_memmovew(d, s, (b - t - nr) * vc->vc_size_row);
-	scr_memsetw(d + (b - t - nr) * vc->vc_cols, vc->vc_video_erase_char,
+	scr_memsetw(d + (b - t - nr) * vc->vc_cols, vc->vc_scrl_erase_char,
 		    vc->vc_size_row * nr);
 }
 
@@ -319,7 +319,7 @@ static void scrdown(struct vc_data *vc, unsigned int t, unsigned int b, int nr)
 	s = (unsigned short *)(vc->vc_origin + vc->vc_size_row * t);
 	step = vc->vc_cols * nr;
 	scr_memmovew(s + step, s, (b - t - nr) * vc->vc_size_row);
-	scr_memsetw(s, vc->vc_video_erase_char, 2 * step);
+	scr_memsetw(s, vc->vc_scrl_erase_char, 2 * step);
 }
 
 static void do_update_region(struct vc_data *vc, unsigned long start, int count)
@@ -400,7 +400,7 @@ static u8 build_attr(struct vc_data *vc, u8 _color, u8 _intensity, u8 _blink,
  *  Bit 7   : blink
  */
 	{
-	u8 a = vc->vc_color;
+	u8 a = _color;
 	if (!vc->vc_can_do_color)
 		return _intensity |
 		       (_italic ? 2 : 0) |
@@ -434,6 +434,7 @@ static void update_attr(struct vc_data *vc)
 	              vc->vc_blink, vc->vc_underline,
 	              vc->vc_reverse ^ vc->vc_decscnm, vc->vc_italic);
 	vc->vc_video_erase_char = (build_attr(vc, vc->vc_color, 1, vc->vc_blink, 0, vc->vc_decscnm, 0) << 8) | ' ';
+	vc->vc_scrl_erase_char = (build_attr(vc, vc->vc_def_color, 1, false, false, false, false) << 8) | ' ';
 }
 
 /* Note: inverting the screen twice should revert to the original state */
@@ -2054,6 +2055,7 @@ static int do_con_write(struct tty_struct *tty, const unsigned char *buf, int co
 	unsigned long draw_from = 0, draw_to = 0;
 	struct vc_data *vc;
 	unsigned char vc_attr;
+	struct vt_notifier_param param;
 	uint8_t rescan;
 	uint8_t inverse;
 	uint8_t width;
@@ -2113,6 +2115,8 @@ static int do_con_write(struct tty_struct *tty, const unsigned char *buf, int co
 	if (IS_FG(vc))
 		hide_cursor(vc);
 
+	param.vc = vc;
+
 	while (!tty->stopped && count) {
 		int orig = *buf;
 		c = orig;
@@ -2201,6 +2205,11 @@ static int do_con_write(struct tty_struct *tty, const unsigned char *buf, int co
 		    tc = vc->vc_translate[vc->vc_toggle_meta ? (c | 0x80) : c];
 		}
 
+		param.c = tc;
+		if (atomic_notifier_call_chain(&vt_notifier_list, VT_PREWRITE,
+					&param) == NOTIFY_STOP)
+			continue;
+
                 /* If the original code was a control character we
                  * only allow a glyph to be displayed if the code is
                  * not normally used (such as for cursor movement) or
diff --git a/trunk/drivers/cpufreq/Kconfig b/trunk/drivers/cpufreq/Kconfig
index c159ae64eeb2..5f076aef74fa 100644
--- a/trunk/drivers/cpufreq/Kconfig
+++ b/trunk/drivers/cpufreq/Kconfig
@@ -69,6 +69,15 @@ config CPU_FREQ_DEFAULT_GOV_PERFORMANCE
 	  the frequency statically to the highest frequency supported by
 	  the CPU.
 
+config CPU_FREQ_DEFAULT_GOV_POWERSAVE
+	bool "powersave"
+	depends on EMBEDDED
+	select CPU_FREQ_GOV_POWERSAVE
+	help
+	  Use the CPUFreq governor 'powersave' as default. This sets
+	  the frequency statically to the lowest frequency supported by
+	  the CPU.
+
 config CPU_FREQ_DEFAULT_GOV_USERSPACE
 	bool "userspace"
 	select CPU_FREQ_GOV_USERSPACE
diff --git a/trunk/drivers/cpufreq/cpufreq.c b/trunk/drivers/cpufreq/cpufreq.c
index 35a26a3e5f68..7fce038fa57e 100644
--- a/trunk/drivers/cpufreq/cpufreq.c
+++ b/trunk/drivers/cpufreq/cpufreq.c
@@ -118,9 +118,11 @@ static void handle_update(struct work_struct *work);
 static BLOCKING_NOTIFIER_HEAD(cpufreq_policy_notifier_list);
 static struct srcu_notifier_head cpufreq_transition_notifier_list;
 
+static bool init_cpufreq_transition_notifier_list_called;
 static int __init init_cpufreq_transition_notifier_list(void)
 {
 	srcu_init_notifier_head(&cpufreq_transition_notifier_list);
+	init_cpufreq_transition_notifier_list_called = true;
 	return 0;
 }
 pure_initcall(init_cpufreq_transition_notifier_list);
@@ -216,7 +218,7 @@ static void cpufreq_debug_disable_ratelimit(void)
 }
 
 void cpufreq_debug_printk(unsigned int type, const char *prefix,
-							const char *fmt, ...)
+			const char *fmt, ...)
 {
 	char s[256];
 	va_list args;
@@ -378,7 +380,7 @@ static struct cpufreq_governor *__find_governor(const char *str_governor)
 /**
  * cpufreq_parse_governor - parse a governor string
  */
-static int cpufreq_parse_governor (char *str_governor, unsigned int *policy,
+static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
 				struct cpufreq_governor **governor)
 {
 	int err = -EINVAL;
@@ -446,7 +448,7 @@ extern struct sysdev_class cpu_sysdev_class;
 
 #define show_one(file_name, object)			\
 static ssize_t show_##file_name				\
-(struct cpufreq_policy * policy, char *buf)		\
+(struct cpufreq_policy *policy, char *buf)		\
 {							\
 	return sprintf (buf, "%u\n", policy->object);	\
 }
@@ -465,7 +467,7 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data,
  */
 #define store_one(file_name, object)			\
 static ssize_t store_##file_name					\
-(struct cpufreq_policy * policy, const char *buf, size_t count)		\
+(struct cpufreq_policy *policy, const char *buf, size_t count)		\
 {									\
 	unsigned int ret = -EINVAL;					\
 	struct cpufreq_policy new_policy;				\
@@ -490,8 +492,8 @@ store_one(scaling_max_freq,max);
 /**
  * show_cpuinfo_cur_freq - current CPU frequency as detected by hardware
  */
-static ssize_t show_cpuinfo_cur_freq (struct cpufreq_policy * policy,
-							char *buf)
+static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy,
+					char *buf)
 {
 	unsigned int cur_freq = __cpufreq_get(policy->cpu);
 	if (!cur_freq)
@@ -503,8 +505,7 @@ static ssize_t show_cpuinfo_cur_freq (struct cpufreq_policy * policy,
 /**
  * show_scaling_governor - show the current policy for the specified CPU
  */
-static ssize_t show_scaling_governor (struct cpufreq_policy * policy,
-							char *buf)
+static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf)
 {
 	if(policy->policy == CPUFREQ_POLICY_POWERSAVE)
 		return sprintf(buf, "powersave\n");
@@ -519,8 +520,8 @@ static ssize_t show_scaling_governor (struct cpufreq_policy * policy,
 /**
  * store_scaling_governor - store policy for the specified CPU
  */
-static ssize_t store_scaling_governor (struct cpufreq_policy * policy,
-				       const char *buf, size_t count)
+static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
+					const char *buf, size_t count)
 {
 	unsigned int ret = -EINVAL;
 	char	str_governor[16];
@@ -554,7 +555,7 @@ static ssize_t store_scaling_governor (struct cpufreq_policy * policy,
 /**
  * show_scaling_driver - show the cpufreq driver currently loaded
  */
-static ssize_t show_scaling_driver (struct cpufreq_policy * policy, char *buf)
+static ssize_t show_scaling_driver(struct cpufreq_policy *policy, char *buf)
 {
 	return scnprintf(buf, CPUFREQ_NAME_LEN, "%s\n", cpufreq_driver->name);
 }
@@ -562,8 +563,8 @@ static ssize_t show_scaling_driver (struct cpufreq_policy * policy, char *buf)
 /**
  * show_scaling_available_governors - show the available CPUfreq governors
  */
-static ssize_t show_scaling_available_governors (struct cpufreq_policy *policy,
-				char *buf)
+static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy,
+						char *buf)
 {
 	ssize_t i = 0;
 	struct cpufreq_governor *t;
@@ -582,15 +583,13 @@ static ssize_t show_scaling_available_governors (struct cpufreq_policy *policy,
 	i += sprintf(&buf[i], "\n");
 	return i;
 }
-/**
- * show_affected_cpus - show the CPUs affected by each transition
- */
-static ssize_t show_affected_cpus (struct cpufreq_policy * policy, char *buf)
+
+static ssize_t show_cpus(cpumask_t mask, char *buf)
 {
 	ssize_t i = 0;
 	unsigned int cpu;
 
-	for_each_cpu_mask(cpu, policy->cpus) {
+	for_each_cpu_mask(cpu, mask) {
 		if (i)
 			i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), " ");
 		i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), "%u", cpu);
@@ -601,8 +600,27 @@ static ssize_t show_affected_cpus (struct cpufreq_policy * policy, char *buf)
 	return i;
 }
 
+/**
+ * show_related_cpus - show the CPUs affected by each transition even if
+ * hw coordination is in use
+ */
+static ssize_t show_related_cpus(struct cpufreq_policy *policy, char *buf)
+{
+	if (cpus_empty(policy->related_cpus))
+		return show_cpus(policy->cpus, buf);
+	return show_cpus(policy->related_cpus, buf);
+}
+
+/**
+ * show_affected_cpus - show the CPUs affected by each transition
+ */
+static ssize_t show_affected_cpus(struct cpufreq_policy *policy, char *buf)
+{
+	return show_cpus(policy->cpus, buf);
+}
+
 static ssize_t store_scaling_setspeed(struct cpufreq_policy *policy,
-		const char *buf, size_t count)
+					const char *buf, size_t count)
 {
 	unsigned int freq = 0;
 	unsigned int ret;
@@ -645,18 +663,20 @@ define_one_ro(cpuinfo_max_freq);
 define_one_ro(scaling_available_governors);
 define_one_ro(scaling_driver);
 define_one_ro(scaling_cur_freq);
+define_one_ro(related_cpus);
 define_one_ro(affected_cpus);
 define_one_rw(scaling_min_freq);
 define_one_rw(scaling_max_freq);
 define_one_rw(scaling_governor);
 define_one_rw(scaling_setspeed);
 
-static struct attribute * default_attrs[] = {
+static struct attribute *default_attrs[] = {
 	&cpuinfo_min_freq.attr,
 	&cpuinfo_max_freq.attr,
 	&scaling_min_freq.attr,
 	&scaling_max_freq.attr,
 	&affected_cpus.attr,
+	&related_cpus.attr,
 	&scaling_governor.attr,
 	&scaling_driver.attr,
 	&scaling_available_governors.attr,
@@ -667,10 +687,10 @@ static struct attribute * default_attrs[] = {
 #define to_policy(k) container_of(k,struct cpufreq_policy,kobj)
 #define to_attr(a) container_of(a,struct freq_attr,attr)
 
-static ssize_t show(struct kobject * kobj, struct attribute * attr ,char * buf)
+static ssize_t show(struct kobject *kobj, struct attribute *attr ,char *buf)
 {
-	struct cpufreq_policy * policy = to_policy(kobj);
-	struct freq_attr * fattr = to_attr(attr);
+	struct cpufreq_policy *policy = to_policy(kobj);
+	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret = -EINVAL;
 	policy = cpufreq_cpu_get(policy->cpu);
 	if (!policy)
@@ -691,11 +711,11 @@ static ssize_t show(struct kobject * kobj, struct attribute * attr ,char * buf)
 	return ret;
 }
 
-static ssize_t store(struct kobject * kobj, struct attribute * attr,
-		     const char * buf, size_t count)
+static ssize_t store(struct kobject *kobj, struct attribute *attr,
+		     const char *buf, size_t count)
 {
-	struct cpufreq_policy * policy = to_policy(kobj);
-	struct freq_attr * fattr = to_attr(attr);
+	struct cpufreq_policy *policy = to_policy(kobj);
+	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret = -EINVAL;
 	policy = cpufreq_cpu_get(policy->cpu);
 	if (!policy)
@@ -716,9 +736,9 @@ static ssize_t store(struct kobject * kobj, struct attribute * attr,
 	return ret;
 }
 
-static void cpufreq_sysfs_release(struct kobject * kobj)
+static void cpufreq_sysfs_release(struct kobject *kobj)
 {
-	struct cpufreq_policy * policy = to_policy(kobj);
+	struct cpufreq_policy *policy = to_policy(kobj);
 	dprintk("last reference is dropped\n");
 	complete(&policy->kobj_unregister);
 }
@@ -740,7 +760,7 @@ static struct kobj_type ktype_cpufreq = {
  *
  * Adds the cpufreq interface for a CPU device.
  */
-static int cpufreq_add_dev (struct sys_device * sys_dev)
+static int cpufreq_add_dev(struct sys_device *sys_dev)
 {
 	unsigned int cpu = sys_dev->id;
 	int ret = 0;
@@ -800,7 +820,6 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 	ret = cpufreq_driver->init(policy);
 	if (ret) {
 		dprintk("initialization failed\n");
-		unlock_policy_rwsem_write(cpu);
 		goto err_out;
 	}
 	policy->user_policy.min = policy->cpuinfo.min_freq;
@@ -823,7 +842,7 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 		/* check for existing affected CPUs.  They may not be aware
 		 * of it due to CPU Hotplug.
 		 */
-		managed_policy = cpufreq_cpu_get(j);
+		managed_policy = cpufreq_cpu_get(j);		// FIXME: Where is this released?  What about error paths?
 		if (unlikely(managed_policy)) {
 
 			/* Set proper policy_cpu */
@@ -842,14 +861,11 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 			ret = sysfs_create_link(&sys_dev->kobj,
 						&managed_policy->kobj,
 						"cpufreq");
-			if (ret) {
-				unlock_policy_rwsem_write(cpu);
+			if (ret)
 				goto err_out_driver_exit;
-			}
 
 			cpufreq_debug_enable_ratelimit();
 			ret = 0;
-			unlock_policy_rwsem_write(cpu);
 			goto err_out_driver_exit; /* call driver->exit() */
 		}
 	}
@@ -859,33 +875,26 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 	/* prepare interface data */
 	ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, &sys_dev->kobj,
 				   "cpufreq");
-	if (ret) {
-		unlock_policy_rwsem_write(cpu);
+	if (ret)
 		goto err_out_driver_exit;
-	}
+
 	/* set up files for this cpu device */
 	drv_attr = cpufreq_driver->attr;
 	while ((drv_attr) && (*drv_attr)) {
 		ret = sysfs_create_file(&policy->kobj, &((*drv_attr)->attr));
-		if (ret) {
-			unlock_policy_rwsem_write(cpu);
+		if (ret)
 			goto err_out_driver_exit;
-		}
 		drv_attr++;
 	}
-	if (cpufreq_driver->get){
+	if (cpufreq_driver->get) {
 		ret = sysfs_create_file(&policy->kobj, &cpuinfo_cur_freq.attr);
-		if (ret) {
-			unlock_policy_rwsem_write(cpu);
+		if (ret)
 			goto err_out_driver_exit;
-		}
 	}
-	if (cpufreq_driver->target){
+	if (cpufreq_driver->target) {
 		ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
-		if (ret) {
-			unlock_policy_rwsem_write(cpu);
+		if (ret)
 			goto err_out_driver_exit;
-		}
 	}
 
 	spin_lock_irqsave(&cpufreq_driver_lock, flags);
@@ -907,10 +916,8 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 		cpu_sys_dev = get_cpu_sysdev(j);
 		ret = sysfs_create_link(&cpu_sys_dev->kobj, &policy->kobj,
 					"cpufreq");
-		if (ret) {
-			unlock_policy_rwsem_write(cpu);
+		if (ret)
 			goto err_out_unregister;
-		}
 	}
 
 	policy->governor = NULL; /* to assure that the starting sequence is
@@ -950,6 +957,7 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
 		cpufreq_driver->exit(policy);
 
 err_out:
+	unlock_policy_rwsem_write(cpu);
 	kfree(policy);
 
 nomem_out:
@@ -967,7 +975,7 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
  * Caller should already have policy_rwsem in write mode for this CPU.
  * This routine frees the rwsem before returning.
  */
-static int __cpufreq_remove_dev (struct sys_device * sys_dev)
+static int __cpufreq_remove_dev(struct sys_device *sys_dev)
 {
 	unsigned int cpu = sys_dev->id;
 	unsigned long flags;
@@ -1071,7 +1079,7 @@ static int __cpufreq_remove_dev (struct sys_device * sys_dev)
 }
 
 
-static int cpufreq_remove_dev (struct sys_device * sys_dev)
+static int cpufreq_remove_dev(struct sys_device *sys_dev)
 {
 	unsigned int cpu = sys_dev->id;
 	int retval;
@@ -1138,7 +1146,7 @@ unsigned int cpufreq_quick_get(unsigned int cpu)
 		cpufreq_cpu_put(policy);
 	}
 
-	return (ret_freq);
+	return ret_freq;
 }
 EXPORT_SYMBOL(cpufreq_quick_get);
 
@@ -1149,7 +1157,7 @@ static unsigned int __cpufreq_get(unsigned int cpu)
 	unsigned int ret_freq = 0;
 
 	if (!cpufreq_driver->get)
-		return (ret_freq);
+		return ret_freq;
 
 	ret_freq = cpufreq_driver->get(cpu);
 
@@ -1163,7 +1171,7 @@ static unsigned int __cpufreq_get(unsigned int cpu)
 		}
 	}
 
-	return (ret_freq);
+	return ret_freq;
 }
 
 /**
@@ -1190,7 +1198,7 @@ unsigned int cpufreq_get(unsigned int cpu)
 out_policy:
 	cpufreq_cpu_put(policy);
 out:
-	return (ret_freq);
+	return ret_freq;
 }
 EXPORT_SYMBOL(cpufreq_get);
 
@@ -1199,7 +1207,7 @@ EXPORT_SYMBOL(cpufreq_get);
  *	cpufreq_suspend - let the low level driver prepare for suspend
  */
 
-static int cpufreq_suspend(struct sys_device * sysdev, pm_message_t pmsg)
+static int cpufreq_suspend(struct sys_device *sysdev, pm_message_t pmsg)
 {
 	int cpu = sysdev->id;
 	int ret = 0;
@@ -1221,22 +1229,18 @@ static int cpufreq_suspend(struct sys_device * sysdev, pm_message_t pmsg)
 		return -EINVAL;
 
 	/* only handle each CPU group once */
-	if (unlikely(cpu_policy->cpu != cpu)) {
-		cpufreq_cpu_put(cpu_policy);
-		return 0;
-	}
+	if (unlikely(cpu_policy->cpu != cpu))
+		goto out;
 
 	if (cpufreq_driver->suspend) {
 		ret = cpufreq_driver->suspend(cpu_policy, pmsg);
 		if (ret) {
 			printk(KERN_ERR "cpufreq: suspend failed in ->suspend "
 					"step on CPU %u\n", cpu_policy->cpu);
-			cpufreq_cpu_put(cpu_policy);
-			return ret;
+			goto out;
 		}
 	}
 
-
 	if (cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)
 		goto out;
 
@@ -1270,7 +1274,7 @@ static int cpufreq_suspend(struct sys_device * sysdev, pm_message_t pmsg)
 
 out:
 	cpufreq_cpu_put(cpu_policy);
-	return 0;
+	return ret;
 }
 
 /**
@@ -1281,7 +1285,7 @@ static int cpufreq_suspend(struct sys_device * sysdev, pm_message_t pmsg)
  *	3.) schedule call cpufreq_update_policy() ASAP as interrupts are
  *	    restored.
  */
-static int cpufreq_resume(struct sys_device * sysdev)
+static int cpufreq_resume(struct sys_device *sysdev)
 {
 	int cpu = sysdev->id;
 	int ret = 0;
@@ -1302,18 +1306,15 @@ static int cpufreq_resume(struct sys_device * sysdev)
 		return -EINVAL;
 
 	/* only handle each CPU group once */
-	if (unlikely(cpu_policy->cpu != cpu)) {
-		cpufreq_cpu_put(cpu_policy);
-		return 0;
-	}
+	if (unlikely(cpu_policy->cpu != cpu))
+		goto fail;
 
 	if (cpufreq_driver->resume) {
 		ret = cpufreq_driver->resume(cpu_policy);
 		if (ret) {
 			printk(KERN_ERR "cpufreq: resume failed in ->resume "
 					"step on CPU %u\n", cpu_policy->cpu);
-			cpufreq_cpu_put(cpu_policy);
-			return ret;
+			goto fail;
 		}
 	}
 
@@ -1353,6 +1354,7 @@ static int cpufreq_resume(struct sys_device * sysdev)
 
 out:
 	schedule_work(&cpu_policy->update);
+fail:
 	cpufreq_cpu_put(cpu_policy);
 	return ret;
 }
@@ -1386,6 +1388,8 @@ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list)
 {
 	int ret;
 
+	WARN_ON(!init_cpufreq_transition_notifier_list_called);
+
 	switch (list) {
 	case CPUFREQ_TRANSITION_NOTIFIER:
 		ret = srcu_notifier_chain_register(
@@ -1848,7 +1852,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 		cpufreq_debug_enable_ratelimit();
 	}
 
-	return (ret);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(cpufreq_register_driver);
 
diff --git a/trunk/drivers/cpufreq/cpufreq_powersave.c b/trunk/drivers/cpufreq/cpufreq_powersave.c
index 13fe06b94b0a..88d2f44fba48 100644
--- a/trunk/drivers/cpufreq/cpufreq_powersave.c
+++ b/trunk/drivers/cpufreq/cpufreq_powersave.c
@@ -35,12 +35,12 @@ static int cpufreq_governor_powersave(struct cpufreq_policy *policy,
 	return 0;
 }
 
-static struct cpufreq_governor cpufreq_gov_powersave = {
+struct cpufreq_governor cpufreq_gov_powersave = {
 	.name		= "powersave",
 	.governor	= cpufreq_governor_powersave,
 	.owner		= THIS_MODULE,
 };
-
+EXPORT_SYMBOL(cpufreq_gov_powersave);
 
 static int __init cpufreq_gov_powersave_init(void)
 {
@@ -58,5 +58,9 @@ MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
 MODULE_DESCRIPTION("CPUfreq policy governor 'powersave'");
 MODULE_LICENSE("GPL");
 
+#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE
+fs_initcall(cpufreq_gov_powersave_init);
+#else
 module_init(cpufreq_gov_powersave_init);
+#endif
 module_exit(cpufreq_gov_powersave_exit);
diff --git a/trunk/drivers/cpufreq/cpufreq_stats.c b/trunk/drivers/cpufreq/cpufreq_stats.c
index 070421a5480e..ae70d63a8b26 100644
--- a/trunk/drivers/cpufreq/cpufreq_stats.c
+++ b/trunk/drivers/cpufreq/cpufreq_stats.c
@@ -114,7 +114,7 @@ show_trans_table(struct cpufreq_policy *policy, char *buf)
 				stat->freq_table[i]);
 	}
 	if (len >= PAGE_SIZE)
-		return len;
+		return PAGE_SIZE;
 
 	len += snprintf(buf + len, PAGE_SIZE - len, "\n");
 
@@ -131,8 +131,12 @@ show_trans_table(struct cpufreq_policy *policy, char *buf)
 			len += snprintf(buf + len, PAGE_SIZE - len, "%9u ",
 					stat->trans_table[i*stat->max_state+j]);
 		}
+		if (len >= PAGE_SIZE)
+			break;
 		len += snprintf(buf + len, PAGE_SIZE - len, "\n");
 	}
+	if (len >= PAGE_SIZE)
+		return PAGE_SIZE;
 	return len;
 }
 CPUFREQ_STATDEVICE_ATTR(trans_table,0444,show_trans_table);
@@ -284,7 +288,7 @@ cpufreq_stat_notifier_trans (struct notifier_block *nb, unsigned long val,
 	if (!stat)
 		return 0;
 
-	old_index = freq_table_get_index(stat, freq->old);
+	old_index = stat->last_index;
 	new_index = freq_table_get_index(stat, freq->new);
 
 	cpufreq_stats_update(freq->cpu);
diff --git a/trunk/drivers/edac/Kconfig b/trunk/drivers/edac/Kconfig
index 2b382990fe58..6e6c3c4aea6b 100644
--- a/trunk/drivers/edac/Kconfig
+++ b/trunk/drivers/edac/Kconfig
@@ -67,7 +67,7 @@ config EDAC_E7XXX
 	  E7205, E7500, E7501 and E7505 server chipsets.
 
 config EDAC_E752X
-	tristate "Intel e752x (e7520, e7525, e7320)"
+	tristate "Intel e752x (e7520, e7525, e7320) and 3100"
 	depends on EDAC_MM_EDAC && PCI && X86 && HOTPLUG
 	help
 	  Support for error detection and correction on the Intel
diff --git a/trunk/drivers/edac/amd76x_edac.c b/trunk/drivers/edac/amd76x_edac.c
index f22075410591..2b95f1a3edfc 100644
--- a/trunk/drivers/edac/amd76x_edac.c
+++ b/trunk/drivers/edac/amd76x_edac.c
@@ -17,6 +17,7 @@
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
 #include <linux/slab.h>
+#include <linux/edac.h>
 #include "edac_core.h"
 
 #define AMD76X_REVISION	" Ver: 2.0.2 "  __DATE__
@@ -344,6 +345,9 @@ static struct pci_driver amd76x_driver = {
 
 static int __init amd76x_init(void)
 {
+       /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+       opstate_init();
+
 	return pci_register_driver(&amd76x_driver);
 }
 
@@ -358,3 +362,6 @@ module_exit(amd76x_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Linux Networx (http://lnxi.com) Thayne Harbaugh");
 MODULE_DESCRIPTION("MC support for AMD 76x memory controllers");
+
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
diff --git a/trunk/drivers/edac/e752x_edac.c b/trunk/drivers/edac/e752x_edac.c
index 6eb434749cd5..c94a0eb492cb 100644
--- a/trunk/drivers/edac/e752x_edac.c
+++ b/trunk/drivers/edac/e752x_edac.c
@@ -29,6 +29,7 @@
 #define EDAC_MOD_STR	"e752x_edac"
 
 static int force_function_unhide;
+static int sysbus_parity = -1;
 
 static struct edac_pci_ctl_info *e752x_pci;
 
@@ -62,6 +63,14 @@ static struct edac_pci_ctl_info *e752x_pci;
 #define PCI_DEVICE_ID_INTEL_7320_1_ERR	0x3593
 #endif				/* PCI_DEVICE_ID_INTEL_7320_1_ERR */
 
+#ifndef PCI_DEVICE_ID_INTEL_3100_0
+#define PCI_DEVICE_ID_INTEL_3100_0	0x35B0
+#endif				/* PCI_DEVICE_ID_INTEL_3100_0 */
+
+#ifndef PCI_DEVICE_ID_INTEL_3100_1_ERR
+#define PCI_DEVICE_ID_INTEL_3100_1_ERR	0x35B1
+#endif				/* PCI_DEVICE_ID_INTEL_3100_1_ERR */
+
 #define E752X_NR_CSROWS		8	/* number of csrows */
 
 /* E752X register addresses - device 0 function 0 */
@@ -152,6 +161,12 @@ static struct edac_pci_ctl_info *e752x_pci;
 					/*     error syndrome register (16b) */
 #define E752X_DEVPRES1		0xF4	/* Device Present 1 register (8b) */
 
+/* 3100 IMCH specific register addresses - device 0 function 1 */
+#define I3100_NSI_FERR		0x48	/* NSI first error reg (32b) */
+#define I3100_NSI_NERR		0x4C	/* NSI next error reg (32b) */
+#define I3100_NSI_SMICMD	0x54	/* NSI SMI command register (32b) */
+#define I3100_NSI_EMASK		0x90	/* NSI error mask register (32b) */
+
 /* ICH5R register addresses - device 30 function 0 */
 #define ICH5R_PCI_STAT		0x06	/* PCI status register (16b) */
 #define ICH5R_PCI_2ND_STAT	0x1E	/* PCI status secondary reg (16b) */
@@ -160,7 +175,8 @@ static struct edac_pci_ctl_info *e752x_pci;
 enum e752x_chips {
 	E7520 = 0,
 	E7525 = 1,
-	E7320 = 2
+	E7320 = 2,
+	I3100 = 3
 };
 
 struct e752x_pvt {
@@ -185,8 +201,10 @@ struct e752x_dev_info {
 struct e752x_error_info {
 	u32 ferr_global;
 	u32 nerr_global;
-	u8 hi_ferr;
-	u8 hi_nerr;
+	u32 nsi_ferr;	/* 3100 only */
+	u32 nsi_nerr;	/* 3100 only */
+	u8 hi_ferr;	/* all but 3100 */
+	u8 hi_nerr;	/* all but 3100 */
 	u16 sysbus_ferr;
 	u16 sysbus_nerr;
 	u8 buf_ferr;
@@ -215,6 +233,10 @@ static const struct e752x_dev_info e752x_devs[] = {
 		.err_dev = PCI_DEVICE_ID_INTEL_7320_1_ERR,
 		.ctl_dev = PCI_DEVICE_ID_INTEL_7320_0,
 		.ctl_name = "E7320"},
+	[I3100] = {
+		.err_dev = PCI_DEVICE_ID_INTEL_3100_1_ERR,
+		.ctl_dev = PCI_DEVICE_ID_INTEL_3100_0,
+		.ctl_name = "3100"},
 };
 
 static unsigned long ctl_page_to_phys(struct mem_ctl_info *mci,
@@ -402,7 +424,7 @@ static inline void process_threshold_ce(struct mem_ctl_info *mci, u16 error,
 static char *global_message[11] = {
 	"PCI Express C1", "PCI Express C", "PCI Express B1",
 	"PCI Express B", "PCI Express A1", "PCI Express A",
-	"DMA Controler", "HUB Interface", "System Bus",
+	"DMA Controler", "HUB or NS Interface", "System Bus",
 	"DRAM Controler", "Internal Buffer"
 };
 
@@ -455,6 +477,63 @@ static inline void hub_error(int fatal, u8 errors, int *error_found,
 		do_hub_error(fatal, errors);
 }
 
+#define NSI_FATAL_MASK		0x0c080081
+#define NSI_NON_FATAL_MASK	0x23a0ba64
+#define NSI_ERR_MASK		(NSI_FATAL_MASK | NSI_NON_FATAL_MASK)
+
+static char *nsi_message[30] = {
+	"NSI Link Down",	/* NSI_FERR/NSI_NERR bit 0, fatal error */
+	"",						/* reserved */
+	"NSI Parity Error",				/* bit 2, non-fatal */
+	"",						/* reserved */
+	"",						/* reserved */
+	"Correctable Error Message",			/* bit 5, non-fatal */
+	"Non-Fatal Error Message",			/* bit 6, non-fatal */
+	"Fatal Error Message",				/* bit 7, fatal */
+	"",						/* reserved */
+	"Receiver Error",				/* bit 9, non-fatal */
+	"",						/* reserved */
+	"Bad TLP",					/* bit 11, non-fatal */
+	"Bad DLLP",					/* bit 12, non-fatal */
+	"REPLAY_NUM Rollover",				/* bit 13, non-fatal */
+	"",						/* reserved */
+	"Replay Timer Timeout",				/* bit 15, non-fatal */
+	"",						/* reserved */
+	"",						/* reserved */
+	"",						/* reserved */
+	"Data Link Protocol Error",			/* bit 19, fatal */
+	"",						/* reserved */
+	"Poisoned TLP",					/* bit 21, non-fatal */
+	"",						/* reserved */
+	"Completion Timeout",				/* bit 23, non-fatal */
+	"Completer Abort",				/* bit 24, non-fatal */
+	"Unexpected Completion",			/* bit 25, non-fatal */
+	"Receiver Overflow",				/* bit 26, fatal */
+	"Malformed TLP",				/* bit 27, fatal */
+	"",						/* reserved */
+	"Unsupported Request"				/* bit 29, non-fatal */
+};
+
+static void do_nsi_error(int fatal, u32 errors)
+{
+	int i;
+
+	for (i = 0; i < 30; i++) {
+		if (errors & (1 << i))
+			printk(KERN_WARNING "%sError %s\n",
+			       fatal_message[fatal], nsi_message[i]);
+	}
+}
+
+static inline void nsi_error(int fatal, u32 errors, int *error_found,
+		int handle_error)
+{
+	*error_found = 1;
+
+	if (handle_error)
+		do_nsi_error(fatal, errors);
+}
+
 static char *membuf_message[4] = {
 	"Internal PMWB to DRAM parity",
 	"Internal PMWB to System Bus Parity",
@@ -546,6 +625,31 @@ static void e752x_check_hub_interface(struct e752x_error_info *info,
 	}
 }
 
+static void e752x_check_ns_interface(struct e752x_error_info *info,
+				int *error_found, int handle_error)
+{
+	u32 stat32;
+
+	stat32 = info->nsi_ferr;
+	if (stat32 & NSI_ERR_MASK) { /* Error, so process */
+		if (stat32 & NSI_FATAL_MASK)	/* check for fatal errors */
+			nsi_error(1, stat32 & NSI_FATAL_MASK, error_found,
+				  handle_error);
+		if (stat32 & NSI_NON_FATAL_MASK) /* check for non-fatal ones */
+			nsi_error(0, stat32 & NSI_NON_FATAL_MASK, error_found,
+				  handle_error);
+	}
+	stat32 = info->nsi_nerr;
+	if (stat32 & NSI_ERR_MASK) {
+		if (stat32 & NSI_FATAL_MASK)
+			nsi_error(1, stat32 & NSI_FATAL_MASK, error_found,
+				  handle_error);
+		if (stat32 & NSI_NON_FATAL_MASK)
+			nsi_error(0, stat32 & NSI_NON_FATAL_MASK, error_found,
+				  handle_error);
+	}
+}
+
 static void e752x_check_sysbus(struct e752x_error_info *info,
 			int *error_found, int handle_error)
 {
@@ -653,7 +757,15 @@ static void e752x_get_error_info(struct mem_ctl_info *mci,
 	pci_read_config_dword(dev, E752X_FERR_GLOBAL, &info->ferr_global);
 
 	if (info->ferr_global) {
-		pci_read_config_byte(dev, E752X_HI_FERR, &info->hi_ferr);
+		if (pvt->dev_info->err_dev == PCI_DEVICE_ID_INTEL_3100_1_ERR) {
+			pci_read_config_dword(dev, I3100_NSI_FERR,
+					     &info->nsi_ferr);
+			info->hi_ferr = 0;
+		} else {
+			pci_read_config_byte(dev, E752X_HI_FERR,
+					     &info->hi_ferr);
+			info->nsi_ferr = 0;
+		}
 		pci_read_config_word(dev, E752X_SYSBUS_FERR,
 				&info->sysbus_ferr);
 		pci_read_config_byte(dev, E752X_BUF_FERR, &info->buf_ferr);
@@ -669,10 +781,15 @@ static void e752x_get_error_info(struct mem_ctl_info *mci,
 		pci_read_config_dword(dev, E752X_DRAM_RETR_ADD,
 				&info->dram_retr_add);
 
+		/* ignore the reserved bits just in case */
 		if (info->hi_ferr & 0x7f)
 			pci_write_config_byte(dev, E752X_HI_FERR,
 					info->hi_ferr);
 
+		if (info->nsi_ferr & NSI_ERR_MASK)
+			pci_write_config_dword(dev, I3100_NSI_FERR,
+					info->nsi_ferr);
+
 		if (info->sysbus_ferr)
 			pci_write_config_word(dev, E752X_SYSBUS_FERR,
 					info->sysbus_ferr);
@@ -692,7 +809,15 @@ static void e752x_get_error_info(struct mem_ctl_info *mci,
 	pci_read_config_dword(dev, E752X_NERR_GLOBAL, &info->nerr_global);
 
 	if (info->nerr_global) {
-		pci_read_config_byte(dev, E752X_HI_NERR, &info->hi_nerr);
+		if (pvt->dev_info->err_dev == PCI_DEVICE_ID_INTEL_3100_1_ERR) {
+			pci_read_config_dword(dev, I3100_NSI_NERR,
+					     &info->nsi_nerr);
+			info->hi_nerr = 0;
+		} else {
+			pci_read_config_byte(dev, E752X_HI_NERR,
+					     &info->hi_nerr);
+			info->nsi_nerr = 0;
+		}
 		pci_read_config_word(dev, E752X_SYSBUS_NERR,
 				&info->sysbus_nerr);
 		pci_read_config_byte(dev, E752X_BUF_NERR, &info->buf_nerr);
@@ -706,6 +831,10 @@ static void e752x_get_error_info(struct mem_ctl_info *mci,
 			pci_write_config_byte(dev, E752X_HI_NERR,
 					info->hi_nerr);
 
+		if (info->nsi_nerr & NSI_ERR_MASK)
+			pci_write_config_dword(dev, I3100_NSI_NERR,
+					info->nsi_nerr);
+
 		if (info->sysbus_nerr)
 			pci_write_config_word(dev, E752X_SYSBUS_NERR,
 					info->sysbus_nerr);
@@ -750,6 +879,7 @@ static int e752x_process_error_info(struct mem_ctl_info *mci,
 		global_error(0, stat32, &error_found, handle_errors);
 
 	e752x_check_hub_interface(info, &error_found, handle_errors);
+	e752x_check_ns_interface(info, &error_found, handle_errors);
 	e752x_check_sysbus(info, &error_found, handle_errors);
 	e752x_check_membuf(info, &error_found, handle_errors);
 	e752x_check_dram(mci, info, &error_found, handle_errors);
@@ -920,15 +1050,53 @@ static int e752x_get_devs(struct pci_dev *pdev, int dev_idx,
 	return 1;
 }
 
+/* Setup system bus parity mask register.
+ * Sysbus parity supported on:
+ *   e7320/e7520/e7525 + Xeon
+ *   i3100 + Xeon/Celeron
+ * Sysbus parity not supported on:
+ *   i3100 + Pentium M/Celeron M/Core Duo/Core2 Duo
+ */
+static void e752x_init_sysbus_parity_mask(struct e752x_pvt *pvt)
+{
+	char *cpu_id = cpu_data(0).x86_model_id;
+	struct pci_dev *dev = pvt->dev_d0f1;
+	int enable = 1;
+
+	/* Allow module paramter override, else see if CPU supports parity */
+	if (sysbus_parity != -1) {
+		enable = sysbus_parity;
+	} else if (cpu_id[0] &&
+		   ((strstr(cpu_id, "Pentium") && strstr(cpu_id, " M ")) ||
+		    (strstr(cpu_id, "Celeron") && strstr(cpu_id, " M ")) ||
+		    (strstr(cpu_id, "Core") && strstr(cpu_id, "Duo")))) {
+		e752x_printk(KERN_INFO, "System Bus Parity not "
+			     "supported by CPU, disabling\n");
+		enable = 0;
+	}
+
+	if (enable)
+		pci_write_config_word(dev, E752X_SYSBUS_ERRMASK, 0x0000);
+	else
+		pci_write_config_word(dev, E752X_SYSBUS_ERRMASK, 0x0309);
+}
+
 static void e752x_init_error_reporting_regs(struct e752x_pvt *pvt)
 {
 	struct pci_dev *dev;
 
 	dev = pvt->dev_d0f1;
 	/* Turn off error disable & SMI in case the BIOS turned it on */
-	pci_write_config_byte(dev, E752X_HI_ERRMASK, 0x00);
-	pci_write_config_byte(dev, E752X_HI_SMICMD, 0x00);
-	pci_write_config_word(dev, E752X_SYSBUS_ERRMASK, 0x00);
+	if (pvt->dev_info->err_dev == PCI_DEVICE_ID_INTEL_3100_1_ERR) {
+		pci_write_config_dword(dev, I3100_NSI_EMASK, 0);
+		pci_write_config_dword(dev, I3100_NSI_SMICMD, 0);
+	} else {
+		pci_write_config_byte(dev, E752X_HI_ERRMASK, 0x00);
+		pci_write_config_byte(dev, E752X_HI_SMICMD, 0x00);
+	}
+
+	e752x_init_sysbus_parity_mask(pvt);
+
 	pci_write_config_word(dev, E752X_SYSBUS_SMICMD, 0x00);
 	pci_write_config_byte(dev, E752X_BUF_ERRMASK, 0x00);
 	pci_write_config_byte(dev, E752X_BUF_SMICMD, 0x00);
@@ -949,16 +1117,6 @@ static int e752x_probe1(struct pci_dev *pdev, int dev_idx)
 	debugf0("%s(): mci\n", __func__);
 	debugf0("Starting Probe1\n");
 
-	/* make sure error reporting method is sane */
-	switch (edac_op_state) {
-	case EDAC_OPSTATE_POLL:
-	case EDAC_OPSTATE_NMI:
-		break;
-	default:
-		edac_op_state = EDAC_OPSTATE_POLL;
-		break;
-	}
-
 	/* check to see if device 0 function 1 is enabled; if it isn't, we
 	 * assume the BIOS has reserved it for a reason and is expecting
 	 * exclusive access, we take care not to violate that assumption and
@@ -985,8 +1143,9 @@ static int e752x_probe1(struct pci_dev *pdev, int dev_idx)
 
 	debugf3("%s(): init mci\n", __func__);
 	mci->mtype_cap = MEM_FLAG_RDDR;
-	mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_SECDED |
-		EDAC_FLAG_S4ECD4ED;
+	/* 3100 IMCH supports SECDEC only */
+	mci->edac_ctl_cap = (dev_idx == I3100) ? EDAC_FLAG_SECDED :
+		(EDAC_FLAG_NONE | EDAC_FLAG_SECDED | EDAC_FLAG_S4ECD4ED);
 	/* FIXME - what if different memory types are in different csrows? */
 	mci->mod_name = EDAC_MOD_STR;
 	mci->mod_ver = E752X_REVISION;
@@ -1018,7 +1177,10 @@ static int e752x_probe1(struct pci_dev *pdev, int dev_idx)
 	e752x_init_csrows(mci, pdev, ddrcsr);
 	e752x_init_mem_map_table(pdev, pvt);
 
-	mci->edac_cap |= EDAC_FLAG_NONE;
+	if (dev_idx == I3100)
+		mci->edac_cap = EDAC_FLAG_SECDED; /* the only mode supported */
+	else
+		mci->edac_cap |= EDAC_FLAG_NONE;
 	debugf3("%s(): tolm, remapbase, remaplimit\n", __func__);
 
 	/* load the top of low memory, remap base, and remap limit vars */
@@ -1109,6 +1271,9 @@ static const struct pci_device_id e752x_pci_tbl[] __devinitdata = {
 	{
 	 PCI_VEND_DEV(INTEL, 7320_0), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 	 E7320},
+	{
+	 PCI_VEND_DEV(INTEL, 3100_0), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+	 I3100},
 	{
 	 0,
 	 }			/* 0 terminated list. */
@@ -1128,6 +1293,10 @@ static int __init e752x_init(void)
 	int pci_rc;
 
 	debugf3("%s()\n", __func__);
+
+       /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+       opstate_init();
+
 	pci_rc = pci_register_driver(&e752x_driver);
 	return (pci_rc < 0) ? pci_rc : 0;
 }
@@ -1143,10 +1312,15 @@ module_exit(e752x_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Linux Networx (http://lnxi.com) Tom Zimmerman\n");
-MODULE_DESCRIPTION("MC support for Intel e752x memory controllers");
+MODULE_DESCRIPTION("MC support for Intel e752x/3100 memory controllers");
 
 module_param(force_function_unhide, int, 0444);
 MODULE_PARM_DESC(force_function_unhide, "if BIOS sets Dev0:Fun1 up as hidden:"
 		 " 1=force unhide and hope BIOS doesn't fight driver for Dev0:Fun1 access");
+
 module_param(edac_op_state, int, 0444);
 MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
+
+module_param(sysbus_parity, int, 0444);
+MODULE_PARM_DESC(sysbus_parity, "0=disable system bus parity checking,"
+		" 1=enable system bus parity checking, default=auto-detect");
diff --git a/trunk/drivers/edac/e7xxx_edac.c b/trunk/drivers/edac/e7xxx_edac.c
index 96ecc4926641..c7d11cc4e21a 100644
--- a/trunk/drivers/edac/e7xxx_edac.c
+++ b/trunk/drivers/edac/e7xxx_edac.c
@@ -414,16 +414,6 @@ static int e7xxx_probe1(struct pci_dev *pdev, int dev_idx)
 
 	debugf0("%s(): mci\n", __func__);
 
-	/* make sure error reporting method is sane */
-	switch (edac_op_state) {
-	case EDAC_OPSTATE_POLL:
-	case EDAC_OPSTATE_NMI:
-		break;
-	default:
-		edac_op_state = EDAC_OPSTATE_POLL;
-		break;
-	}
-
 	pci_read_config_dword(pdev, E7XXX_DRC, &drc);
 
 	drc_chan = dual_channel_active(drc, dev_idx);
@@ -565,6 +555,9 @@ static struct pci_driver e7xxx_driver = {
 
 static int __init e7xxx_init(void)
 {
+       /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+       opstate_init();
+
 	return pci_register_driver(&e7xxx_driver);
 }
 
diff --git a/trunk/drivers/edac/edac_device.c b/trunk/drivers/edac/edac_device.c
index b9552bc03dea..63372fa7ecfe 100644
--- a/trunk/drivers/edac/edac_device.c
+++ b/trunk/drivers/edac/edac_device.c
@@ -36,7 +36,7 @@
  * is protected by the 'device_ctls_mutex' lock
  */
 static DEFINE_MUTEX(device_ctls_mutex);
-static struct list_head edac_device_list = LIST_HEAD_INIT(edac_device_list);
+static LIST_HEAD(edac_device_list);
 
 #ifdef CONFIG_EDAC_DEBUG
 static void edac_device_dump_device(struct edac_device_ctl_info *edac_dev)
@@ -375,37 +375,6 @@ static void del_edac_device_from_global_list(struct edac_device_ctl_info
 	wait_for_completion(&edac_device->removal_complete);
 }
 
-/**
- * edac_device_find
- *	Search for a edac_device_ctl_info structure whose index is 'idx'.
- *
- * If found, return a pointer to the structure.
- * Else return NULL.
- *
- * Caller must hold device_ctls_mutex.
- */
-struct edac_device_ctl_info *edac_device_find(int idx)
-{
-	struct list_head *item;
-	struct edac_device_ctl_info *edac_dev;
-
-	/* Iterate over list, looking for exact match of ID */
-	list_for_each(item, &edac_device_list) {
-		edac_dev = list_entry(item, struct edac_device_ctl_info, link);
-
-		if (edac_dev->dev_idx >= idx) {
-			if (edac_dev->dev_idx == idx)
-				return edac_dev;
-
-			/* not on list, so terminate early */
-			break;
-		}
-	}
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(edac_device_find);
-
 /*
  * edac_device_workq_function
  *	performs the operation scheduled by a workq request
diff --git a/trunk/drivers/edac/edac_mc.c b/trunk/drivers/edac/edac_mc.c
index 063a1bffe38b..a4cf1645f588 100644
--- a/trunk/drivers/edac/edac_mc.c
+++ b/trunk/drivers/edac/edac_mc.c
@@ -36,7 +36,7 @@
 
 /* lock to memory controller's control array */
 static DEFINE_MUTEX(mem_ctls_mutex);
-static struct list_head mc_devices = LIST_HEAD_INIT(mc_devices);
+static LIST_HEAD(mc_devices);
 
 #ifdef CONFIG_EDAC_DEBUG
 
@@ -886,24 +886,3 @@ void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci,
 	mci->csrows[csrow].channels[channel].ce_count++;
 }
 EXPORT_SYMBOL(edac_mc_handle_fbd_ce);
-
-/*
- * Iterate over all MC instances and check for ECC, et al, errors
- */
-void edac_check_mc_devices(void)
-{
-	struct list_head *item;
-	struct mem_ctl_info *mci;
-
-	debugf3("%s()\n", __func__);
-	mutex_lock(&mem_ctls_mutex);
-
-	list_for_each(item, &mc_devices) {
-		mci = list_entry(item, struct mem_ctl_info, link);
-
-		if (mci->edac_check != NULL)
-			mci->edac_check(mci);
-	}
-
-	mutex_unlock(&mem_ctls_mutex);
-}
diff --git a/trunk/drivers/edac/edac_module.h b/trunk/drivers/edac/edac_module.h
index cbc419c8ebc1..233d4798c3aa 100644
--- a/trunk/drivers/edac/edac_module.h
+++ b/trunk/drivers/edac/edac_module.h
@@ -27,7 +27,6 @@ extern int edac_mc_register_sysfs_main_kobj(struct mem_ctl_info *mci);
 extern void edac_mc_unregister_sysfs_main_kobj(struct mem_ctl_info *mci);
 extern int edac_create_sysfs_mci_device(struct mem_ctl_info *mci);
 extern void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci);
-extern void edac_check_mc_devices(void);
 extern int edac_get_log_ue(void);
 extern int edac_get_log_ce(void);
 extern int edac_get_panic_on_ue(void);
diff --git a/trunk/drivers/edac/edac_pci.c b/trunk/drivers/edac/edac_pci.c
index 32be43576a8e..9b24340b52e1 100644
--- a/trunk/drivers/edac/edac_pci.c
+++ b/trunk/drivers/edac/edac_pci.c
@@ -29,7 +29,7 @@
 #include "edac_module.h"
 
 static DEFINE_MUTEX(edac_pci_ctls_mutex);
-static struct list_head edac_pci_list = LIST_HEAD_INIT(edac_pci_list);
+static LIST_HEAD(edac_pci_list);
 
 /*
  * edac_pci_alloc_ctl_info
@@ -189,6 +189,9 @@ static void del_edac_pci_from_global_list(struct edac_pci_ctl_info *pci)
 	wait_for_completion(&pci->complete);
 }
 
+#if 0
+/* Older code, but might use in the future */
+
 /*
  * edac_pci_find()
  * 	Search for an edac_pci_ctl_info structure whose index is 'idx'
@@ -219,6 +222,7 @@ struct edac_pci_ctl_info *edac_pci_find(int idx)
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(edac_pci_find);
+#endif
 
 /*
  * edac_pci_workq_function()
@@ -422,7 +426,7 @@ EXPORT_SYMBOL_GPL(edac_pci_del_device);
  *
  *	a Generic parity check API
  */
-void edac_pci_generic_check(struct edac_pci_ctl_info *pci)
+static void edac_pci_generic_check(struct edac_pci_ctl_info *pci)
 {
 	debugf4("%s()\n", __func__);
 	edac_pci_do_parity_check();
diff --git a/trunk/drivers/edac/edac_pci_sysfs.c b/trunk/drivers/edac/edac_pci_sysfs.c
index 71c3195d3704..2c1fa1bb6df2 100644
--- a/trunk/drivers/edac/edac_pci_sysfs.c
+++ b/trunk/drivers/edac/edac_pci_sysfs.c
@@ -37,17 +37,17 @@ int edac_pci_get_check_errors(void)
 	return check_pci_errors;
 }
 
-int edac_pci_get_log_pe(void)
+static int edac_pci_get_log_pe(void)
 {
 	return edac_pci_log_pe;
 }
 
-int edac_pci_get_log_npe(void)
+static int edac_pci_get_log_npe(void)
 {
 	return edac_pci_log_npe;
 }
 
-int edac_pci_get_panic_on_pe(void)
+static int edac_pci_get_panic_on_pe(void)
 {
 	return edac_pci_panic_on_pe;
 }
@@ -197,7 +197,8 @@ static int edac_pci_create_instance_kobj(struct edac_pci_ctl_info *pci, int idx)
  *
  *	unregister the kobj for the EDAC PCI instance
  */
-void edac_pci_unregister_sysfs_instance_kobj(struct edac_pci_ctl_info *pci)
+static void edac_pci_unregister_sysfs_instance_kobj(
+			struct edac_pci_ctl_info *pci)
 {
 	debugf0("%s()\n", __func__);
 
@@ -337,7 +338,7 @@ static struct kobj_type ktype_edac_pci_main_kobj = {
  *	setup the sysfs for EDAC PCI attributes
  *	assumes edac_class has already been initialized
  */
-int edac_pci_main_kobj_setup(void)
+static int edac_pci_main_kobj_setup(void)
 {
 	int err;
 	struct sysdev_class *edac_class;
diff --git a/trunk/drivers/edac/i3000_edac.c b/trunk/drivers/edac/i3000_edac.c
index 5d4292811c14..6c9a0f2a593c 100644
--- a/trunk/drivers/edac/i3000_edac.c
+++ b/trunk/drivers/edac/i3000_edac.c
@@ -326,15 +326,6 @@ static int i3000_probe1(struct pci_dev *pdev, int dev_idx)
 		return -ENODEV;
 	}
 
-	switch (edac_op_state) {
-	case EDAC_OPSTATE_POLL:
-	case EDAC_OPSTATE_NMI:
-		break;
-	default:
-		edac_op_state = EDAC_OPSTATE_POLL;
-		break;
-	}
-
 	c0dra[0] = readb(window + I3000_C0DRA + 0);	/* ranks 0,1 */
 	c0dra[1] = readb(window + I3000_C0DRA + 1);	/* ranks 2,3 */
 	c1dra[0] = readb(window + I3000_C1DRA + 0);	/* ranks 0,1 */
@@ -503,6 +494,10 @@ static int __init i3000_init(void)
 	int pci_rc;
 
 	debugf3("MC: %s()\n", __func__);
+
+       /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+       opstate_init();
+
 	pci_rc = pci_register_driver(&i3000_driver);
 	if (pci_rc < 0)
 		goto fail0;
diff --git a/trunk/drivers/edac/i5000_edac.c b/trunk/drivers/edac/i5000_edac.c
index 5a852017c17a..4a16b5b61cfb 100644
--- a/trunk/drivers/edac/i5000_edac.c
+++ b/trunk/drivers/edac/i5000_edac.c
@@ -1286,16 +1286,6 @@ static int i5000_probe1(struct pci_dev *pdev, int dev_idx)
 	if (PCI_FUNC(pdev->devfn) != 0)
 		return -ENODEV;
 
-	/* make sure error reporting method is sane */
-	switch (edac_op_state) {
-	case EDAC_OPSTATE_POLL:
-	case EDAC_OPSTATE_NMI:
-		break;
-	default:
-		edac_op_state = EDAC_OPSTATE_POLL;
-		break;
-	}
-
 	/* Ask the devices for the number of CSROWS and CHANNELS so
 	 * that we can calculate the memory resources, etc
 	 *
@@ -1478,6 +1468,9 @@ static int __init i5000_init(void)
 
 	debugf2("MC: " __FILE__ ": %s()\n", __func__);
 
+       /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+       opstate_init();
+
 	pci_rc = pci_register_driver(&i5000_driver);
 
 	return (pci_rc < 0) ? pci_rc : 0;
@@ -1501,5 +1494,6 @@ MODULE_AUTHOR
     ("Linux Networx (http://lnxi.com) Doug Thompson <norsk5@xmission.com>");
 MODULE_DESCRIPTION("MC Driver for Intel I5000 memory controllers - "
 		I5000_REVISION);
+
 module_param(edac_op_state, int, 0444);
 MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
diff --git a/trunk/drivers/edac/i82443bxgx_edac.c b/trunk/drivers/edac/i82443bxgx_edac.c
index 83bfe37c4bbb..c5305e3ee434 100644
--- a/trunk/drivers/edac/i82443bxgx_edac.c
+++ b/trunk/drivers/edac/i82443bxgx_edac.c
@@ -29,6 +29,7 @@
 
 #include <linux/slab.h>
 
+#include <linux/edac.h>
 #include "edac_core.h"
 
 #define I82443_REVISION	"0.1"
@@ -386,6 +387,9 @@ static struct pci_driver i82443bxgx_edacmc_driver = {
 
 static int __init i82443bxgx_edacmc_init(void)
 {
+       /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+       opstate_init();
+
 	return pci_register_driver(&i82443bxgx_edacmc_driver);
 }
 
@@ -400,3 +404,6 @@ module_exit(i82443bxgx_edacmc_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Tim Small <tim@buttersideup.com> - WPAD");
 MODULE_DESCRIPTION("EDAC MC support for Intel 82443BX/GX memory controllers");
+
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
diff --git a/trunk/drivers/edac/i82860_edac.c b/trunk/drivers/edac/i82860_edac.c
index f5ecd2c4d813..c0088ba9672b 100644
--- a/trunk/drivers/edac/i82860_edac.c
+++ b/trunk/drivers/edac/i82860_edac.c
@@ -14,6 +14,7 @@
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
 #include <linux/slab.h>
+#include <linux/edac.h>
 #include "edac_core.h"
 
 #define  I82860_REVISION " Ver: 2.0.2 " __DATE__
@@ -294,6 +295,9 @@ static int __init i82860_init(void)
 
 	debugf3("%s()\n", __func__);
 
+       /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+       opstate_init();
+
 	if ((pci_rc = pci_register_driver(&i82860_driver)) < 0)
 		goto fail0;
 
@@ -345,3 +349,6 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Red Hat Inc. (http://www.redhat.com) "
 		"Ben Woodard <woodard@redhat.com>");
 MODULE_DESCRIPTION("ECC support for Intel 82860 memory hub controllers");
+
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
diff --git a/trunk/drivers/edac/i82875p_edac.c b/trunk/drivers/edac/i82875p_edac.c
index 031abadc439a..e43bdc43a1bf 100644
--- a/trunk/drivers/edac/i82875p_edac.c
+++ b/trunk/drivers/edac/i82875p_edac.c
@@ -18,6 +18,7 @@
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
 #include <linux/slab.h>
+#include <linux/edac.h>
 #include "edac_core.h"
 
 #define I82875P_REVISION	" Ver: 2.0.2 " __DATE__
@@ -393,6 +394,7 @@ static int i82875p_probe1(struct pci_dev *pdev, int dev_idx)
 	struct i82875p_error_info discard;
 
 	debugf0("%s()\n", __func__);
+
 	ovrfl_pdev = pci_get_device(PCI_VEND_DEV(INTEL, 82875_6), NULL);
 
 	if (i82875p_setup_overfl_dev(pdev, &ovrfl_pdev, &ovrfl_window))
@@ -532,6 +534,10 @@ static int __init i82875p_init(void)
 	int pci_rc;
 
 	debugf3("%s()\n", __func__);
+
+       /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+       opstate_init();
+
 	pci_rc = pci_register_driver(&i82875p_driver);
 
 	if (pci_rc < 0)
@@ -586,3 +592,6 @@ module_exit(i82875p_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Linux Networx (http://lnxi.com) Thayne Harbaugh");
 MODULE_DESCRIPTION("MC support for Intel 82875 memory hub controllers");
+
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
diff --git a/trunk/drivers/edac/i82975x_edac.c b/trunk/drivers/edac/i82975x_edac.c
index 0ee888456932..2eed3ea2cf62 100644
--- a/trunk/drivers/edac/i82975x_edac.c
+++ b/trunk/drivers/edac/i82975x_edac.c
@@ -14,7 +14,7 @@
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
 #include <linux/slab.h>
-
+#include <linux/edac.h>
 #include "edac_core.h"
 
 #define I82975X_REVISION	" Ver: 1.0.0 " __DATE__
@@ -611,6 +611,9 @@ static int __init i82975x_init(void)
 
 	debugf3("%s()\n", __func__);
 
+       /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+       opstate_init();
+
 	pci_rc = pci_register_driver(&i82975x_driver);
 	if (pci_rc < 0)
 		goto fail0;
@@ -664,3 +667,6 @@ module_exit(i82975x_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arvind R. <arvind@acarlab.com>");
 MODULE_DESCRIPTION("MC support for Intel 82975 memory hub controllers");
+
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
diff --git a/trunk/drivers/edac/pasemi_edac.c b/trunk/drivers/edac/pasemi_edac.c
index 90320917be28..3fd65a563848 100644
--- a/trunk/drivers/edac/pasemi_edac.c
+++ b/trunk/drivers/edac/pasemi_edac.c
@@ -284,6 +284,9 @@ static struct pci_driver pasemi_edac_driver = {
 
 static int __init pasemi_edac_init(void)
 {
+       /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+       opstate_init();
+
 	return pci_register_driver(&pasemi_edac_driver);
 }
 
@@ -298,3 +301,6 @@ module_exit(pasemi_edac_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Egor Martovetsky <egor@pasemi.com>");
 MODULE_DESCRIPTION("MC support for PA Semi PWRficient memory controller");
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
+
diff --git a/trunk/drivers/edac/r82600_edac.c b/trunk/drivers/edac/r82600_edac.c
index e25f712f2dc3..9900675e9598 100644
--- a/trunk/drivers/edac/r82600_edac.c
+++ b/trunk/drivers/edac/r82600_edac.c
@@ -20,6 +20,7 @@
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
 #include <linux/slab.h>
+#include <linux/edac.h>
 #include "edac_core.h"
 
 #define R82600_REVISION	" Ver: 2.0.2 " __DATE__
@@ -393,6 +394,9 @@ static struct pci_driver r82600_driver = {
 
 static int __init r82600_init(void)
 {
+       /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+       opstate_init();
+
 	return pci_register_driver(&r82600_driver);
 }
 
@@ -412,3 +416,6 @@ MODULE_DESCRIPTION("MC support for Radisys 82600 memory controllers");
 module_param(disable_hardware_scrub, bool, 0644);
 MODULE_PARM_DESC(disable_hardware_scrub,
 		 "If set, disable the chipset's automatic scrub for CEs");
+
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
diff --git a/trunk/drivers/firmware/Kconfig b/trunk/drivers/firmware/Kconfig
index 40ffd767647d..dc2cec6127d1 100644
--- a/trunk/drivers/firmware/Kconfig
+++ b/trunk/drivers/firmware/Kconfig
@@ -17,6 +17,15 @@ config EDD
           obscure configurations. Most disk controller BIOS vendors do
           not yet implement this feature.
 
+config EDD_OFF
+	bool "Sets default behavior for EDD detection to off"
+	depends on EDD
+	default n
+	help
+	  Say Y if you want EDD disabled by default, even though it is compiled into the
+	  kernel. Say N if you want EDD enabled by default. EDD can be dynamically set
+	  using the kernel parameter 'edd={on|skipmbr|off}'.
+
 config EFI_VARS
 	tristate "EFI Variable Support via sysfs"
 	depends on EFI
diff --git a/trunk/drivers/firmware/dcdbas.c b/trunk/drivers/firmware/dcdbas.c
index f235940719e7..25918f7dfd0f 100644
--- a/trunk/drivers/firmware/dcdbas.c
+++ b/trunk/drivers/firmware/dcdbas.c
@@ -63,7 +63,7 @@ static void smi_data_buf_free(void)
 		return;
 
 	dev_dbg(&dcdbas_pdev->dev, "%s: phys: %x size: %lu\n",
-		__FUNCTION__, smi_data_buf_phys_addr, smi_data_buf_size);
+		__func__, smi_data_buf_phys_addr, smi_data_buf_size);
 
 	dma_free_coherent(&dcdbas_pdev->dev, smi_data_buf_size, smi_data_buf,
 			  smi_data_buf_handle);
@@ -92,7 +92,7 @@ static int smi_data_buf_realloc(unsigned long size)
 	if (!buf) {
 		dev_dbg(&dcdbas_pdev->dev,
 			"%s: failed to allocate memory size %lu\n",
-			__FUNCTION__, size);
+			__func__, size);
 		return -ENOMEM;
 	}
 	/* memory zeroed by dma_alloc_coherent */
@@ -110,7 +110,7 @@ static int smi_data_buf_realloc(unsigned long size)
 	smi_data_buf_size = size;
 
 	dev_dbg(&dcdbas_pdev->dev, "%s: phys: %x size: %lu\n",
-		__FUNCTION__, smi_data_buf_phys_addr, smi_data_buf_size);
+		__func__, smi_data_buf_phys_addr, smi_data_buf_size);
 
 	return 0;
 }
@@ -258,7 +258,7 @@ static int smi_request(struct smi_cmd *smi_cmd)
 
 	if (smi_cmd->magic != SMI_CMD_MAGIC) {
 		dev_info(&dcdbas_pdev->dev, "%s: invalid magic value\n",
-			 __FUNCTION__);
+			 __func__);
 		return -EBADR;
 	}
 
@@ -267,7 +267,7 @@ static int smi_request(struct smi_cmd *smi_cmd)
 	set_cpus_allowed_ptr(current, &cpumask_of_cpu(0));
 	if (smp_processor_id() != 0) {
 		dev_dbg(&dcdbas_pdev->dev, "%s: failed to get CPU 0\n",
-			__FUNCTION__);
+			__func__);
 		ret = -EBUSY;
 		goto out;
 	}
@@ -428,7 +428,7 @@ static int host_control_smi(void)
 
 	default:
 		dev_dbg(&dcdbas_pdev->dev, "%s: invalid SMI type %u\n",
-			__FUNCTION__, host_control_smi_type);
+			__func__, host_control_smi_type);
 		return -ENOSYS;
 	}
 
@@ -456,13 +456,13 @@ static void dcdbas_host_control(void)
 	host_control_action = HC_ACTION_NONE;
 
 	if (!smi_data_buf) {
-		dev_dbg(&dcdbas_pdev->dev, "%s: no SMI buffer\n", __FUNCTION__);
+		dev_dbg(&dcdbas_pdev->dev, "%s: no SMI buffer\n", __func__);
 		return;
 	}
 
 	if (smi_data_buf_size < sizeof(struct apm_cmd)) {
 		dev_dbg(&dcdbas_pdev->dev, "%s: SMI buffer too small\n",
-			__FUNCTION__);
+			__func__);
 		return;
 	}
 
diff --git a/trunk/drivers/firmware/dell_rbu.c b/trunk/drivers/firmware/dell_rbu.c
index 477a3d0e3caf..6a8b1e037e07 100644
--- a/trunk/drivers/firmware/dell_rbu.c
+++ b/trunk/drivers/firmware/dell_rbu.c
@@ -123,7 +123,7 @@ static int create_packet(void *data, size_t length)
 	if (!newpacket) {
 		printk(KERN_WARNING
 			"dell_rbu:%s: failed to allocate new "
-			"packet\n", __FUNCTION__);
+			"packet\n", __func__);
 		retval = -ENOMEM;
 		spin_lock(&rbu_data.lock);
 		goto out_noalloc;
@@ -152,7 +152,7 @@ static int create_packet(void *data, size_t length)
 		printk(KERN_WARNING
 			"dell_rbu:%s: failed to allocate "
 			"invalid_addr_packet_array \n",
-			__FUNCTION__);
+			__func__);
 		retval = -ENOMEM;
 		spin_lock(&rbu_data.lock);
 		goto out_alloc_packet;
@@ -164,7 +164,7 @@ static int create_packet(void *data, size_t length)
 		if (!packet_data_temp_buf) {
 			printk(KERN_WARNING
 				"dell_rbu:%s: failed to allocate new "
-				"packet\n", __FUNCTION__);
+				"packet\n", __func__);
 			retval = -ENOMEM;
 			spin_lock(&rbu_data.lock);
 			goto out_alloc_packet_array;
@@ -416,7 +416,7 @@ static int img_update_realloc(unsigned long size)
 		 */
 		if ((size != 0) && (rbu_data.image_update_buffer == NULL)) {
 			printk(KERN_ERR "dell_rbu:%s: corruption "
-				"check failed\n", __FUNCTION__);
+				"check failed\n", __func__);
 			return -EINVAL;
 		}
 		/*
@@ -642,7 +642,7 @@ static ssize_t write_rbu_image_type(struct kobject *kobj,
 			if (req_firm_rc) {
 				printk(KERN_ERR
 					"dell_rbu:%s request_firmware_nowait"
-					" failed %d\n", __FUNCTION__, rc);
+					" failed %d\n", __func__, rc);
 				rc = -EIO;
 			} else
 				rbu_data.entry_created = 1;
@@ -718,7 +718,7 @@ static int __init dcdrbu_init(void)
 	if (IS_ERR(rbu_device)) {
 		printk(KERN_ERR
 			"dell_rbu:%s:platform_device_register_simple "
-			"failed\n", __FUNCTION__);
+			"failed\n", __func__);
 		return PTR_ERR(rbu_device);
 	}
 
diff --git a/trunk/drivers/firmware/iscsi_ibft_find.c b/trunk/drivers/firmware/iscsi_ibft_find.c
index d0e5fa4ea51b..11f17440fea6 100644
--- a/trunk/drivers/firmware/iscsi_ibft_find.c
+++ b/trunk/drivers/firmware/iscsi_ibft_find.c
@@ -58,7 +58,7 @@ void __init reserve_ibft_region(void)
 	unsigned int len = 0;
 	void *virt;
 
-	ibft_addr = 0;
+	ibft_addr = NULL;
 
 	for (pos = IBFT_START; pos < IBFT_END; pos += 16) {
 		/* The table can't be inside the VGA BIOS reserved space,
diff --git a/trunk/drivers/gpio/gpiolib.c b/trunk/drivers/gpio/gpiolib.c
index d8db2f8ee411..24c62b848bf9 100644
--- a/trunk/drivers/gpio/gpiolib.c
+++ b/trunk/drivers/gpio/gpiolib.c
@@ -43,6 +43,7 @@ struct gpio_desc {
 /* flag symbols are bit numbers */
 #define FLAG_REQUESTED	0
 #define FLAG_IS_OUT	1
+#define FLAG_RESERVED	2
 
 #ifdef CONFIG_DEBUG_FS
 	const char		*label;
@@ -68,6 +69,9 @@ static void gpio_ensure_requested(struct gpio_desc *desc)
 	if (test_and_set_bit(FLAG_REQUESTED, &desc->flags) == 0) {
 		pr_warning("GPIO-%d autorequested\n", (int)(desc - gpio_desc));
 		desc_set_label(desc, "[auto]");
+		if (!try_module_get(desc->chip->owner))
+			pr_err("GPIO-%d: module can't be gotten \n",
+					(int)(desc - gpio_desc));
 	}
 }
 
@@ -77,6 +81,76 @@ static inline struct gpio_chip *gpio_to_chip(unsigned gpio)
 	return gpio_desc[gpio].chip;
 }
 
+/* dynamic allocation of GPIOs, e.g. on a hotplugged device */
+static int gpiochip_find_base(int ngpio)
+{
+	int i;
+	int spare = 0;
+	int base = -ENOSPC;
+
+	for (i = ARCH_NR_GPIOS - 1; i >= 0 ; i--) {
+		struct gpio_desc *desc = &gpio_desc[i];
+		struct gpio_chip *chip = desc->chip;
+
+		if (!chip && !test_bit(FLAG_RESERVED, &desc->flags)) {
+			spare++;
+			if (spare == ngpio) {
+				base = i;
+				break;
+			}
+		} else {
+			spare = 0;
+			if (chip)
+				i -= chip->ngpio - 1;
+		}
+	}
+
+	if (gpio_is_valid(base))
+		pr_debug("%s: found new base at %d\n", __func__, base);
+	return base;
+}
+
+/**
+ * gpiochip_reserve() - reserve range of gpios to use with platform code only
+ * @start: starting gpio number
+ * @ngpio: number of gpios to reserve
+ * Context: platform init, potentially before irqs or kmalloc will work
+ *
+ * Returns a negative errno if any gpio within the range is already reserved
+ * or registered, else returns zero as a success code.  Use this function
+ * to mark a range of gpios as unavailable for dynamic gpio number allocation,
+ * for example because its driver support is not yet loaded.
+ */
+int __init gpiochip_reserve(int start, int ngpio)
+{
+	int ret = 0;
+	unsigned long flags;
+	int i;
+
+	if (!gpio_is_valid(start) || !gpio_is_valid(start + ngpio))
+		return -EINVAL;
+
+	spin_lock_irqsave(&gpio_lock, flags);
+
+	for (i = start; i < start + ngpio; i++) {
+		struct gpio_desc *desc = &gpio_desc[i];
+
+		if (desc->chip || test_bit(FLAG_RESERVED, &desc->flags)) {
+			ret = -EBUSY;
+			goto err;
+		}
+
+		set_bit(FLAG_RESERVED, &desc->flags);
+	}
+
+	pr_debug("%s: reserved gpios from %d to %d\n",
+		 __func__, start, start + ngpio - 1);
+err:
+	spin_unlock_irqrestore(&gpio_lock, flags);
+
+	return ret;
+}
+
 /**
  * gpiochip_add() - register a gpio_chip
  * @chip: the chip to register, with chip->base initialized
@@ -85,38 +159,49 @@ static inline struct gpio_chip *gpio_to_chip(unsigned gpio)
  * Returns a negative errno if the chip can't be registered, such as
  * because the chip->base is invalid or already associated with a
  * different chip.  Otherwise it returns zero as a success code.
+ *
+ * If chip->base is negative, this requests dynamic assignment of
+ * a range of valid GPIOs.
  */
 int gpiochip_add(struct gpio_chip *chip)
 {
 	unsigned long	flags;
 	int		status = 0;
 	unsigned	id;
+	int		base = chip->base;
 
-	/* NOTE chip->base negative is reserved to mean a request for
-	 * dynamic allocation.  We don't currently support that.
-	 */
-
-	if (chip->base < 0 || (chip->base  + chip->ngpio) >= ARCH_NR_GPIOS) {
+	if ((!gpio_is_valid(base) || !gpio_is_valid(base + chip->ngpio))
+			&& base >= 0) {
 		status = -EINVAL;
 		goto fail;
 	}
 
 	spin_lock_irqsave(&gpio_lock, flags);
 
+	if (base < 0) {
+		base = gpiochip_find_base(chip->ngpio);
+		if (base < 0) {
+			status = base;
+			goto fail_unlock;
+		}
+		chip->base = base;
+	}
+
 	/* these GPIO numbers must not be managed by another gpio_chip */
-	for (id = chip->base; id < chip->base + chip->ngpio; id++) {
+	for (id = base; id < base + chip->ngpio; id++) {
 		if (gpio_desc[id].chip != NULL) {
 			status = -EBUSY;
 			break;
 		}
 	}
 	if (status == 0) {
-		for (id = chip->base; id < chip->base + chip->ngpio; id++) {
+		for (id = base; id < base + chip->ngpio; id++) {
 			gpio_desc[id].chip = chip;
 			gpio_desc[id].flags = 0;
 		}
 	}
 
+fail_unlock:
 	spin_unlock_irqrestore(&gpio_lock, flags);
 fail:
 	/* failures here can mean systems won't boot... */
@@ -171,12 +256,15 @@ int gpio_request(unsigned gpio, const char *label)
 
 	spin_lock_irqsave(&gpio_lock, flags);
 
-	if (gpio >= ARCH_NR_GPIOS)
+	if (!gpio_is_valid(gpio))
 		goto done;
 	desc = &gpio_desc[gpio];
 	if (desc->chip == NULL)
 		goto done;
 
+	if (!try_module_get(desc->chip->owner))
+		goto done;
+
 	/* NOTE:  gpio_request() can be called in early boot,
 	 * before IRQs are enabled.
 	 */
@@ -184,8 +272,10 @@ int gpio_request(unsigned gpio, const char *label)
 	if (test_and_set_bit(FLAG_REQUESTED, &desc->flags) == 0) {
 		desc_set_label(desc, label ? : "?");
 		status = 0;
-	} else
+	} else {
 		status = -EBUSY;
+		module_put(desc->chip->owner);
+	}
 
 done:
 	if (status)
@@ -201,7 +291,7 @@ void gpio_free(unsigned gpio)
 	unsigned long		flags;
 	struct gpio_desc	*desc;
 
-	if (gpio >= ARCH_NR_GPIOS) {
+	if (!gpio_is_valid(gpio)) {
 		WARN_ON(extra_checks);
 		return;
 	}
@@ -209,9 +299,10 @@ void gpio_free(unsigned gpio)
 	spin_lock_irqsave(&gpio_lock, flags);
 
 	desc = &gpio_desc[gpio];
-	if (desc->chip && test_and_clear_bit(FLAG_REQUESTED, &desc->flags))
+	if (desc->chip && test_and_clear_bit(FLAG_REQUESTED, &desc->flags)) {
 		desc_set_label(desc, NULL);
-	else
+		module_put(desc->chip->owner);
+	} else
 		WARN_ON(extra_checks);
 
 	spin_unlock_irqrestore(&gpio_lock, flags);
@@ -236,7 +327,7 @@ const char *gpiochip_is_requested(struct gpio_chip *chip, unsigned offset)
 {
 	unsigned gpio = chip->base + offset;
 
-	if (gpio >= ARCH_NR_GPIOS || gpio_desc[gpio].chip != chip)
+	if (!gpio_is_valid(gpio) || gpio_desc[gpio].chip != chip)
 		return NULL;
 	if (test_bit(FLAG_REQUESTED, &gpio_desc[gpio].flags) == 0)
 		return NULL;
@@ -267,7 +358,7 @@ int gpio_direction_input(unsigned gpio)
 
 	spin_lock_irqsave(&gpio_lock, flags);
 
-	if (gpio >= ARCH_NR_GPIOS)
+	if (!gpio_is_valid(gpio))
 		goto fail;
 	chip = desc->chip;
 	if (!chip || !chip->get || !chip->direction_input)
@@ -305,7 +396,7 @@ int gpio_direction_output(unsigned gpio, int value)
 
 	spin_lock_irqsave(&gpio_lock, flags);
 
-	if (gpio >= ARCH_NR_GPIOS)
+	if (!gpio_is_valid(gpio))
 		goto fail;
 	chip = desc->chip;
 	if (!chip || !chip->set || !chip->direction_output)
@@ -522,7 +613,7 @@ static int gpiolib_show(struct seq_file *s, void *unused)
 
 	/* REVISIT this isn't locked against gpio_chip removal ... */
 
-	for (gpio = 0; gpio < ARCH_NR_GPIOS; gpio++) {
+	for (gpio = 0; gpio_is_valid(gpio); gpio++) {
 		if (chip == gpio_desc[gpio].chip)
 			continue;
 		chip = gpio_desc[gpio].chip;
diff --git a/trunk/drivers/gpio/mcp23s08.c b/trunk/drivers/gpio/mcp23s08.c
index bb60e8c1a1f0..7fb5b9d009d4 100644
--- a/trunk/drivers/gpio/mcp23s08.c
+++ b/trunk/drivers/gpio/mcp23s08.c
@@ -239,6 +239,7 @@ static int mcp23s08_probe(struct spi_device *spi)
 	mcp->chip.base = pdata->base;
 	mcp->chip.ngpio = 8;
 	mcp->chip.can_sleep = 1;
+	mcp->chip.owner = THIS_MODULE;
 
 	spi_set_drvdata(spi, mcp);
 
diff --git a/trunk/drivers/gpio/pca953x.c b/trunk/drivers/gpio/pca953x.c
index 6e72fd31184d..e0e0af536108 100644
--- a/trunk/drivers/gpio/pca953x.c
+++ b/trunk/drivers/gpio/pca953x.c
@@ -189,6 +189,7 @@ static void pca953x_setup_gpio(struct pca953x_chip *chip, int gpios)
 	gc->base = chip->gpio_start;
 	gc->ngpio = gpios;
 	gc->label = chip->client->name;
+	gc->owner = THIS_MODULE;
 }
 
 static int __devinit pca953x_probe(struct i2c_client *client)
diff --git a/trunk/drivers/gpio/pcf857x.c b/trunk/drivers/gpio/pcf857x.c
index c6b3b5378384..1106aa15ac79 100644
--- a/trunk/drivers/gpio/pcf857x.c
+++ b/trunk/drivers/gpio/pcf857x.c
@@ -159,6 +159,7 @@ static int pcf857x_probe(struct i2c_client *client)
 
 	gpio->chip.base = pdata->gpio_base;
 	gpio->chip.can_sleep = 1;
+	gpio->chip.owner = THIS_MODULE;
 
 	/* NOTE:  the OnSemi jlc1562b is also largely compatible with
 	 * these parts, notably for output.  It has a low-resolution
diff --git a/trunk/drivers/hid/hid-core.c b/trunk/drivers/hid/hid-core.c
index e03c67dd3e63..f43d6d3cf2fa 100644
--- a/trunk/drivers/hid/hid-core.c
+++ b/trunk/drivers/hid/hid-core.c
@@ -606,7 +606,7 @@ static u8 *fetch_item(__u8 *start, __u8 *end, struct hid_item *item)
 		case 2:
 			if ((end - start) < 2)
 				return NULL;
-			item->data.u16 = le16_to_cpu(get_unaligned((__le16*)start));
+			item->data.u16 = get_unaligned_le16(start);
 			start = (__u8 *)((__le16 *)start + 1);
 			return start;
 
@@ -614,7 +614,7 @@ static u8 *fetch_item(__u8 *start, __u8 *end, struct hid_item *item)
 			item->size++;
 			if ((end - start) < 4)
 				return NULL;
-			item->data.u32 = le32_to_cpu(get_unaligned((__le32*)start));
+			item->data.u32 = get_unaligned_le32(start);
 			start = (__u8 *)((__le32 *)start + 1);
 			return start;
 	}
@@ -765,7 +765,7 @@ static __inline__ __u32 extract(__u8 *report, unsigned offset, unsigned n)
 
 	report += offset >> 3;  /* adjust byte index */
 	offset &= 7;            /* now only need bit offset into one byte */
-	x = le64_to_cpu(get_unaligned((__le64 *) report));
+	x = get_unaligned_le64(report);
 	x = (x >> offset) & ((1ULL << n) - 1);  /* extract bit field */
 	return (u32) x;
 }
diff --git a/trunk/drivers/hid/usbhid/hid-core.c b/trunk/drivers/hid/usbhid/hid-core.c
index e0d805f1b2bf..01427c51c7cc 100644
--- a/trunk/drivers/hid/usbhid/hid-core.c
+++ b/trunk/drivers/hid/usbhid/hid-core.c
@@ -654,7 +654,7 @@ static int usbhid_output_raw_report(struct hid_device *hid, __u8 *buf, size_t co
 	ret = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
 		HID_REQ_SET_REPORT,
 		USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE,
-		cpu_to_le16(((HID_OUTPUT_REPORT + 1) << 8) | *buf),
+		((HID_OUTPUT_REPORT + 1) << 8) | *buf,
 		interface->desc.bInterfaceNumber, buf + 1, count - 1,
 		USB_CTRL_SET_TIMEOUT);
 
diff --git a/trunk/drivers/ide/Kconfig b/trunk/drivers/ide/Kconfig
index 3f9e10001e19..f702f9152ce6 100644
--- a/trunk/drivers/ide/Kconfig
+++ b/trunk/drivers/ide/Kconfig
@@ -862,40 +862,6 @@ config BLK_DEV_IDE_BAST
 	  Say Y here if you want to support the onboard IDE channels on the
 	  Simtec BAST or the Thorcom VR1000
 
-config ETRAX_IDE
-	tristate "ETRAX IDE support"
-	depends on CRIS && BROKEN
-	select BLK_DEV_IDEDMA
-	help
-	  Enables the ETRAX IDE driver.
-
-	  You can't use parallel ports or SCSI ports at the same time.
-
-config ETRAX_IDE_DELAY
-	int "Delay for drives to regain consciousness"
-	depends on ETRAX_IDE && ETRAX_ARCH_V10
-	default 15
-	help
-	  Number of seconds to wait for IDE drives to spin up after an IDE
-	  reset.
-
-choice
-	prompt "IDE reset pin"
-	depends on ETRAX_IDE && ETRAX_ARCH_V10
-	default ETRAX_IDE_PB7_RESET
-
-config ETRAX_IDE_PB7_RESET
-	bool "Port_PB_Bit_7"
-	help
-	  IDE reset on pin 7 on port B
-
-config ETRAX_IDE_G27_RESET
-	bool "Port_G_Bit_27"
-	help
-	  IDE reset on pin 27 on port G
-
-endchoice
-
 config IDE_H8300
 	tristate "H8300 IDE support"
 	depends on H8300
diff --git a/trunk/drivers/ide/Makefile b/trunk/drivers/ide/Makefile
index 571544c37bb2..f94b679b611e 100644
--- a/trunk/drivers/ide/Makefile
+++ b/trunk/drivers/ide/Makefile
@@ -35,7 +35,7 @@ ifeq ($(CONFIG_BLK_DEV_CMD640), y)
 	obj-y += cmd640-core.o
 endif
 
-obj-$(CONFIG_BLK_DEV_IDE)		+= cris/ ppc/
+obj-$(CONFIG_BLK_DEV_IDE)		+= ppc/
 obj-$(CONFIG_IDE_H8300)			+= h8300/
 obj-$(CONFIG_IDE_GENERIC)		+= ide-generic.o
 obj-$(CONFIG_BLK_DEV_IDEPNP)		+= ide-pnp.o
diff --git a/trunk/drivers/ide/arm/bast-ide.c b/trunk/drivers/ide/arm/bast-ide.c
index d158f579bde2..713cef20622e 100644
--- a/trunk/drivers/ide/arm/bast-ide.c
+++ b/trunk/drivers/ide/arm/bast-ide.c
@@ -35,12 +35,12 @@ static int __init bastide_register(unsigned int base, unsigned int aux, int irq)
 	base += BAST_IDE_CS;
 	aux  += BAST_IDE_CS;
 
-	for (i = IDE_DATA_OFFSET; i <= IDE_STATUS_OFFSET; i++) {
-		hw.io_ports[i] = (unsigned long)base;
+	for (i = 0; i <= 7; i++) {
+		hw.io_ports_array[i] = (unsigned long)base;
 		base += 0x20;
 	}
 
-	hw.io_ports[IDE_CONTROL_OFFSET] = aux + (6 * 0x20);
+	hw.io_ports.ctl_addr = aux + (6 * 0x20);
 	hw.irq = irq;
 
 	hwif = ide_find_port();
@@ -49,11 +49,7 @@ static int __init bastide_register(unsigned int base, unsigned int aux, int irq)
 
 	i = hwif->index;
 
-	if (hwif->present)
-		ide_unregister(i);
-	else
-		ide_init_port_data(hwif, i);
-
+	ide_init_port_data(hwif, i);
 	ide_init_port_hw(hwif, &hw);
 	hwif->port_ops = NULL;
 
diff --git a/trunk/drivers/ide/arm/icside.c b/trunk/drivers/ide/arm/icside.c
index 7d642f44e35b..061456914ca3 100644
--- a/trunk/drivers/ide/arm/icside.c
+++ b/trunk/drivers/ide/arm/icside.c
@@ -419,18 +419,21 @@ icside_setup(void __iomem *base, struct cardinfo *info, struct expansion_card *e
 
 	hwif = ide_find_port();
 	if (hwif) {
-		int i;
-
 		/*
 		 * Ensure we're using MMIO
 		 */
 		default_hwif_mmiops(hwif);
 
-		for (i = IDE_DATA_OFFSET; i <= IDE_STATUS_OFFSET; i++) {
-			hwif->io_ports[i] = port;
-			port += 1 << info->stepping;
-		}
-		hwif->io_ports[IDE_CONTROL_OFFSET] = (unsigned long)base + info->ctrloffset;
+		hwif->io_ports.data_addr = port;
+		hwif->io_ports.error_addr = port + (1 << info->stepping);
+		hwif->io_ports.nsect_addr = port + (2 << info->stepping);
+		hwif->io_ports.lbal_addr = port + (3 << info->stepping);
+		hwif->io_ports.lbam_addr = port + (4 << info->stepping);
+		hwif->io_ports.lbah_addr = port + (5 << info->stepping);
+		hwif->io_ports.device_addr = port + (6 << info->stepping);
+		hwif->io_ports.status_addr = port + (7 << info->stepping);
+		hwif->io_ports.ctl_addr =
+			(unsigned long)base + info->ctrloffset;
 		hwif->irq     = ec->irq;
 		hwif->chipset = ide_acorn;
 		hwif->gendev.parent = &ec->dev;
@@ -480,8 +483,7 @@ static const struct ide_port_info icside_v6_port_info __initdata = {
 	.init_dma		= icside_dma_off_init,
 	.port_ops		= &icside_v6_no_dma_port_ops,
 	.dma_ops		= &icside_v6_dma_ops,
-	.host_flags		= IDE_HFLAG_SERIALIZE |
-				  IDE_HFLAG_NO_AUTOTUNE,
+	.host_flags		= IDE_HFLAG_SERIALIZE | IDE_HFLAG_MMIO,
 	.mwdma_mask		= ATA_MWDMA2,
 	.swdma_mask		= ATA_SWDMA2,
 };
@@ -547,14 +549,13 @@ icside_register_v6(struct icside_state *state, struct expansion_card *ec)
 	hwif->config_data = (unsigned long)ioc_base;
 	hwif->select_data = sel;
 
-	mate->maskproc    = icside_maskproc;
 	mate->hwif_data   = state;
 	mate->config_data = (unsigned long)ioc_base;
 	mate->select_data = sel | 1;
 
 	if (ec->dma != NO_DMA && !request_dma(ec->dma, hwif->name)) {
 		d.init_dma = icside_dma_init;
-		d.port_ops = &icside_v6_dma_port_ops;
+		d.port_ops = &icside_v6_port_ops;
 		d.dma_ops = NULL;
 	}
 
diff --git a/trunk/drivers/ide/arm/palm_bk3710.c b/trunk/drivers/ide/arm/palm_bk3710.c
index 8fa34e26443a..96378ebfb31f 100644
--- a/trunk/drivers/ide/arm/palm_bk3710.c
+++ b/trunk/drivers/ide/arm/palm_bk3710.c
@@ -321,7 +321,7 @@ static int __devinit palm_bk3710_init_dma(ide_hwif_t *hwif,
 					  const struct ide_port_info *d)
 {
 	unsigned long base =
-		hwif->io_ports[IDE_DATA_OFFSET] - IDE_PALM_ATA_PRI_REG_OFFSET;
+		hwif->io_ports.data_addr - IDE_PALM_ATA_PRI_REG_OFFSET;
 
 	printk(KERN_INFO "    %s: MMIO-DMA\n", hwif->name);
 
@@ -342,6 +342,7 @@ static const struct ide_port_ops palm_bk3710_ports_ops = {
 static const struct ide_port_info __devinitdata palm_bk3710_port_info = {
 	.init_dma		= palm_bk3710_init_dma,
 	.port_ops		= &palm_bk3710_ports_ops,
+	.host_flags		= IDE_HFLAG_MMIO,
 	.pio_mask		= ATA_PIO4,
 	.udma_mask		= ATA_UDMA4,	/* (input clk 99MHz) */
 	.mwdma_mask		= ATA_MWDMA2,
@@ -386,8 +387,8 @@ static int __devinit palm_bk3710_probe(struct platform_device *pdev)
 
 	pribase = mem->start + IDE_PALM_ATA_PRI_REG_OFFSET;
 	for (i = 0; i < IDE_NR_PORTS - 2; i++)
-		hw.io_ports[i] = pribase + i;
-	hw.io_ports[IDE_CONTROL_OFFSET] = mem->start +
+		hw.io_ports_array[i] = pribase + i;
+	hw.io_ports.ctl_addr = mem->start +
 			IDE_PALM_ATA_PRI_CTL_OFFSET;
 	hw.irq = irq->start;
 	hw.chipset = ide_palm3710;
@@ -398,11 +399,7 @@ static int __devinit palm_bk3710_probe(struct platform_device *pdev)
 
 	i = hwif->index;
 
-	if (hwif->present)
-		ide_unregister(i);
-	else
-		ide_init_port_data(hwif, i);
-
+	ide_init_port_data(hwif, i);
 	ide_init_port_hw(hwif, &hw);
 
 	hwif->mmio = 1;
diff --git a/trunk/drivers/ide/arm/rapide.c b/trunk/drivers/ide/arm/rapide.c
index c0581bd98d0d..1747b2358775 100644
--- a/trunk/drivers/ide/arm/rapide.c
+++ b/trunk/drivers/ide/arm/rapide.c
@@ -17,11 +17,11 @@ static void rapide_setup_ports(hw_regs_t *hw, void __iomem *base,
 	unsigned long port = (unsigned long)base;
 	int i;
 
-	for (i = IDE_DATA_OFFSET; i <= IDE_STATUS_OFFSET; i++) {
-		hw->io_ports[i] = port;
+	for (i = 0; i <= 7; i++) {
+		hw->io_ports_array[i] = port;
 		port += sz;
 	}
-	hw->io_ports[IDE_CONTROL_OFFSET] = (unsigned long)ctrl;
+	hw->io_ports.ctl_addr = (unsigned long)ctrl;
 	hw->irq = irq;
 }
 
@@ -53,6 +53,7 @@ rapide_probe(struct expansion_card *ec, const struct ecard_id *id)
 
 		ide_init_port_hw(hwif, &hw);
 
+		hwif->host_flags = IDE_HFLAG_MMIO;
 		default_hwif_mmiops(hwif);
 
 		idx[0] = hwif->index;
@@ -75,7 +76,7 @@ static void __devexit rapide_remove(struct expansion_card *ec)
 
 	ecard_set_drvdata(ec, NULL);
 
-	ide_unregister(hwif->index);
+	ide_unregister(hwif);
 
 	ecard_release_resources(ec);
 }
diff --git a/trunk/drivers/ide/cris/Makefile b/trunk/drivers/ide/cris/Makefile
deleted file mode 100644
index 20b95960531f..000000000000
--- a/trunk/drivers/ide/cris/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-EXTRA_CFLAGS				+= -Idrivers/ide
-
-obj-$(CONFIG_IDE_ETRAX)			+= ide-cris.o
diff --git a/trunk/drivers/ide/cris/ide-cris.c b/trunk/drivers/ide/cris/ide-cris.c
deleted file mode 100644
index a62ca75c7e28..000000000000
--- a/trunk/drivers/ide/cris/ide-cris.c
+++ /dev/null
@@ -1,1086 +0,0 @@
-/*
- * Etrax specific IDE functions, like init and PIO-mode setting etc.
- * Almost the entire ide.c is used for the rest of the Etrax ATA driver.
- * Copyright (c) 2000-2005 Axis Communications AB
- *
- * Authors:    Bjorn Wesen        (initial version)
- *             Mikael Starvik     (crisv32 port)
- */
-
-/* Regarding DMA:
- *
- * There are two forms of DMA - "DMA handshaking" between the interface and the drive,
- * and DMA between the memory and the interface. We can ALWAYS use the latter, since it's
- * something built-in in the Etrax. However only some drives support the DMA-mode handshaking
- * on the ATA-bus. The normal PC driver and Triton interface disables memory-if DMA when the
- * device can't do DMA handshaking for some stupid reason. We don't need to do that.
- */
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/timer.h>
-#include <linux/mm.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/blkdev.h>
-#include <linux/hdreg.h>
-#include <linux/ide.h>
-#include <linux/init.h>
-
-#include <asm/io.h>
-#include <asm/dma.h>
-
-/* number of DMA descriptors */
-#define MAX_DMA_DESCRS 64
-
-/* number of times to retry busy-flags when reading/writing IDE-registers
- * this can't be too high because a hung harddisk might cause the watchdog
- * to trigger (sometimes INB and OUTB are called with irq's disabled)
- */
-
-#define IDE_REGISTER_TIMEOUT 300
-
-#define LOWDB(x)
-#define D(x)
-
-enum /* Transfer types */
-{
-	TYPE_PIO,
-	TYPE_DMA,
-	TYPE_UDMA
-};
-
-/* CRISv32 specifics */
-#ifdef CONFIG_ETRAX_ARCH_V32
-#include <asm/arch/hwregs/ata_defs.h>
-#include <asm/arch/hwregs/dma_defs.h>
-#include <asm/arch/hwregs/dma.h>
-#include <asm/arch/pinmux.h>
-
-#define ATA_UDMA2_CYC    2
-#define ATA_UDMA2_DVS    3
-#define ATA_UDMA1_CYC    2
-#define ATA_UDMA1_DVS    4
-#define ATA_UDMA0_CYC    4
-#define ATA_UDMA0_DVS    6
-#define ATA_DMA2_STROBE  7
-#define ATA_DMA2_HOLD    1
-#define ATA_DMA1_STROBE  8
-#define ATA_DMA1_HOLD    3
-#define ATA_DMA0_STROBE 25
-#define ATA_DMA0_HOLD   19
-#define ATA_PIO4_SETUP   3
-#define ATA_PIO4_STROBE  7
-#define ATA_PIO4_HOLD    1
-#define ATA_PIO3_SETUP   3
-#define ATA_PIO3_STROBE  9
-#define ATA_PIO3_HOLD    3
-#define ATA_PIO2_SETUP   3
-#define ATA_PIO2_STROBE 13
-#define ATA_PIO2_HOLD    5
-#define ATA_PIO1_SETUP   5
-#define ATA_PIO1_STROBE 23
-#define ATA_PIO1_HOLD    9
-#define ATA_PIO0_SETUP   9
-#define ATA_PIO0_STROBE 39
-#define ATA_PIO0_HOLD    9
-
-int
-cris_ide_ack_intr(ide_hwif_t* hwif)
-{
-	reg_ata_rw_ctrl2 ctrl2 = REG_TYPE_CONV(reg_ata_rw_ctrl2,
-	                         int, hwif->io_ports[0]);
-	REG_WR_INT(ata, regi_ata, rw_ack_intr, 1 << ctrl2.sel);
-	return 1;
-}
-
-static inline int
-cris_ide_busy(void)
-{
-	reg_ata_rs_stat_data stat_data;
-	stat_data = REG_RD(ata, regi_ata, rs_stat_data);
-	return stat_data.busy;
-}
-
-static inline int
-cris_ide_ready(void)
-{
-	return !cris_ide_busy();
-}
-
-static inline int
-cris_ide_data_available(unsigned short* data)
-{
-	reg_ata_rs_stat_data stat_data;
-	stat_data = REG_RD(ata, regi_ata, rs_stat_data);
-	*data = stat_data.data;
-	return stat_data.dav;
-}
-
-static void
-cris_ide_write_command(unsigned long command)
-{
-	REG_WR_INT(ata, regi_ata, rw_ctrl2, command); /* write data to the drive's register */
-}
-
-static void
-cris_ide_set_speed(int type, int setup, int strobe, int hold)
-{
-	reg_ata_rw_ctrl0 ctrl0 = REG_RD(ata, regi_ata, rw_ctrl0);
-	reg_ata_rw_ctrl1 ctrl1 = REG_RD(ata, regi_ata, rw_ctrl1);
-
-	if (type == TYPE_PIO) {
-		ctrl0.pio_setup = setup;
-		ctrl0.pio_strb = strobe;
-		ctrl0.pio_hold = hold;
-	} else if (type == TYPE_DMA) {
-		ctrl0.dma_strb = strobe;
-		ctrl0.dma_hold = hold;
-	} else if (type == TYPE_UDMA) {
-		ctrl1.udma_tcyc = setup;
-		ctrl1.udma_tdvs = strobe;
-	}
-	REG_WR(ata, regi_ata, rw_ctrl0, ctrl0);
-	REG_WR(ata, regi_ata, rw_ctrl1, ctrl1);
-}
-
-static unsigned long
-cris_ide_base_address(int bus)
-{
-	reg_ata_rw_ctrl2 ctrl2 = {0};
-	ctrl2.sel = bus;
-	return REG_TYPE_CONV(int, reg_ata_rw_ctrl2, ctrl2);
-}
-
-static unsigned long
-cris_ide_reg_addr(unsigned long addr, int cs0, int cs1)
-{
-	reg_ata_rw_ctrl2 ctrl2 = {0};
-	ctrl2.addr = addr;
-	ctrl2.cs1 = cs1;
-	ctrl2.cs0 = cs0;
-	return REG_TYPE_CONV(int, reg_ata_rw_ctrl2, ctrl2);
-}
-
-static __init void
-cris_ide_reset(unsigned val)
-{
-	reg_ata_rw_ctrl0 ctrl0 = {0};
-	ctrl0.rst = val ? regk_ata_active : regk_ata_inactive;
-	REG_WR(ata, regi_ata, rw_ctrl0, ctrl0);
-}
-
-static __init void
-cris_ide_init(void)
-{
-	reg_ata_rw_ctrl0 ctrl0 = {0};
-	reg_ata_rw_intr_mask intr_mask = {0};
-
-	ctrl0.en = regk_ata_yes;
-	REG_WR(ata, regi_ata, rw_ctrl0, ctrl0);
-
-	intr_mask.bus0 = regk_ata_yes;
-	intr_mask.bus1 = regk_ata_yes;
-	intr_mask.bus2 = regk_ata_yes;
-	intr_mask.bus3 = regk_ata_yes;
-
-	REG_WR(ata, regi_ata, rw_intr_mask, intr_mask);
-
-	crisv32_request_dma(2, "ETRAX FS built-in ATA", DMA_VERBOSE_ON_ERROR, 0, dma_ata);
-	crisv32_request_dma(3, "ETRAX FS built-in ATA", DMA_VERBOSE_ON_ERROR, 0, dma_ata);
-
-	crisv32_pinmux_alloc_fixed(pinmux_ata);
-	crisv32_pinmux_alloc_fixed(pinmux_ata0);
-	crisv32_pinmux_alloc_fixed(pinmux_ata1);
-	crisv32_pinmux_alloc_fixed(pinmux_ata2);
-	crisv32_pinmux_alloc_fixed(pinmux_ata3);
-
-	DMA_RESET(regi_dma2);
-	DMA_ENABLE(regi_dma2);
-	DMA_RESET(regi_dma3);
-	DMA_ENABLE(regi_dma3);
-
-	DMA_WR_CMD (regi_dma2, regk_dma_set_w_size2);
-	DMA_WR_CMD (regi_dma3, regk_dma_set_w_size2);
-}
-
-static dma_descr_context mycontext __attribute__ ((__aligned__(32)));
-
-#define cris_dma_descr_type dma_descr_data
-#define cris_pio_read regk_ata_rd
-#define cris_ultra_mask 0x7
-#define MAX_DESCR_SIZE 0xffffffffUL
-
-static unsigned long
-cris_ide_get_reg(unsigned long reg)
-{
-	return (reg & 0x0e000000) >> 25;
-}
-
-static void
-cris_ide_fill_descriptor(cris_dma_descr_type *d, void* buf, unsigned int len, int last)
-{
-	d->buf = (char*)virt_to_phys(buf);
-	d->after = d->buf + len;
-	d->eol = last;
-}
-
-static void
-cris_ide_start_dma(ide_drive_t *drive, cris_dma_descr_type *d, int dir,int type,int len)
-{
-	ide_hwif_t *hwif = drive->hwif;
-
-	reg_ata_rw_ctrl2 ctrl2 = REG_TYPE_CONV(reg_ata_rw_ctrl2, int,
-					       hwif->io_ports[IDE_DATA_OFFSET]);
-	reg_ata_rw_trf_cnt trf_cnt = {0};
-
-	mycontext.saved_data = (dma_descr_data*)virt_to_phys(d);
-	mycontext.saved_data_buf = d->buf;
-	/* start the dma channel */
-	DMA_START_CONTEXT(dir ? regi_dma3 : regi_dma2, virt_to_phys(&mycontext));
-
-	/* initiate a multi word dma read using PIO handshaking */
-	trf_cnt.cnt = len >> 1;
-	/* Due to a "feature" the transfer count has to be one extra word for UDMA. */
-	if (type == TYPE_UDMA)
-		trf_cnt.cnt++;
-	REG_WR(ata, regi_ata, rw_trf_cnt, trf_cnt);
-
-	ctrl2.rw = dir ? regk_ata_rd : regk_ata_wr;
-	ctrl2.trf_mode = regk_ata_dma;
-	ctrl2.hsh = type == TYPE_PIO ? regk_ata_pio :
-	            type == TYPE_DMA ? regk_ata_dma : regk_ata_udma;
-	ctrl2.multi = regk_ata_yes;
-	ctrl2.dma_size = regk_ata_word;
-	REG_WR(ata, regi_ata, rw_ctrl2, ctrl2);
-}
-
-static void
-cris_ide_wait_dma(int dir)
-{
-	reg_dma_rw_stat status;
-	do
-	{
-		status = REG_RD(dma, dir ? regi_dma3 : regi_dma2, rw_stat);
-	} while(status.list_state != regk_dma_data_at_eol);
-}
-
-static int cris_dma_test_irq(ide_drive_t *drive)
-{
-	ide_hwif_t *hwif = drive->hwif;
-	int intr = REG_RD_INT(ata, regi_ata, r_intr);
-
-	reg_ata_rw_ctrl2 ctrl2 = REG_TYPE_CONV(reg_ata_rw_ctrl2, int,
-					       hwif->io_ports[IDE_DATA_OFFSET]);
-
-	return intr & (1 << ctrl2.sel) ? 1 : 0;
-}
-
-static void cris_ide_initialize_dma(int dir)
-{
-}
-
-#else
-/* CRISv10 specifics */
-#include <asm/arch/svinto.h>
-#include <asm/arch/io_interface_mux.h>
-
-/* PIO timing (in R_ATA_CONFIG)
- *
- *                        _____________________________
- * ADDRESS :     ________/
- *
- *                            _______________
- * DIOR    :     ____________/               \__________
- *
- *                               _______________
- * DATA    :     XXXXXXXXXXXXXXXX_______________XXXXXXXX
- *
- *
- * DIOR is unbuffered while address and data is buffered.
- * This creates two problems:
- * 1. The DIOR pulse is to early (because it is unbuffered)
- * 2. The rise time of DIOR is long
- *
- * There are at least three different plausible solutions
- * 1. Use a pad capable of larger currents in Etrax
- * 2. Use an external buffer
- * 3. Make the strobe pulse longer
- *
- * Some of the strobe timings below are modified to compensate
- * for this. This implies a slight performance decrease.
- *
- * THIS SHOULD NEVER BE CHANGED!
- *
- * TODO: Is this true for the latest LX boards still ?
- */
-
-#define ATA_UDMA2_CYC    0 /* No UDMA supported, just to make it compile. */
-#define ATA_UDMA2_DVS    0
-#define ATA_UDMA1_CYC    0
-#define ATA_UDMA1_DVS    0
-#define ATA_UDMA0_CYC    0
-#define ATA_UDMA0_DVS    0
-#define ATA_DMA2_STROBE  4
-#define ATA_DMA2_HOLD    0
-#define ATA_DMA1_STROBE  4
-#define ATA_DMA1_HOLD    1
-#define ATA_DMA0_STROBE 12
-#define ATA_DMA0_HOLD    9
-#define ATA_PIO4_SETUP   1
-#define ATA_PIO4_STROBE  5
-#define ATA_PIO4_HOLD    0
-#define ATA_PIO3_SETUP   1
-#define ATA_PIO3_STROBE  5
-#define ATA_PIO3_HOLD    1
-#define ATA_PIO2_SETUP   1
-#define ATA_PIO2_STROBE  6
-#define ATA_PIO2_HOLD    2
-#define ATA_PIO1_SETUP   2
-#define ATA_PIO1_STROBE 11
-#define ATA_PIO1_HOLD    4
-#define ATA_PIO0_SETUP   4
-#define ATA_PIO0_STROBE 19
-#define ATA_PIO0_HOLD    4
-
-int
-cris_ide_ack_intr(ide_hwif_t* hwif)
-{
-	return 1;
-}
-
-static inline int
-cris_ide_busy(void)
-{
-	return *R_ATA_STATUS_DATA & IO_MASK(R_ATA_STATUS_DATA, busy) ;
-}
-
-static inline int
-cris_ide_ready(void)
-{
-	return *R_ATA_STATUS_DATA & IO_MASK(R_ATA_STATUS_DATA, tr_rdy) ;
-}
-
-static inline int
-cris_ide_data_available(unsigned short* data)
-{
-	unsigned long status = *R_ATA_STATUS_DATA;
-	*data = (unsigned short)status;
-	return status & IO_MASK(R_ATA_STATUS_DATA, dav);
-}
-
-static void
-cris_ide_write_command(unsigned long command)
-{
-	*R_ATA_CTRL_DATA = command;
-}
-
-static void
-cris_ide_set_speed(int type, int setup, int strobe, int hold)
-{
-	static int pio_setup = ATA_PIO4_SETUP;
-	static int pio_strobe = ATA_PIO4_STROBE;
-	static int pio_hold = ATA_PIO4_HOLD;
-	static int dma_strobe = ATA_DMA2_STROBE;
-	static int dma_hold = ATA_DMA2_HOLD;
-
-	if (type == TYPE_PIO) {
-		pio_setup = setup;
-		pio_strobe = strobe;
-		pio_hold = hold;
-	} else if (type == TYPE_DMA) {
-		dma_strobe = strobe;
-	  dma_hold = hold;
-	}
-	*R_ATA_CONFIG = ( IO_FIELD( R_ATA_CONFIG, enable, 1 ) |
-	  IO_FIELD( R_ATA_CONFIG, dma_strobe, dma_strobe ) |
-		IO_FIELD( R_ATA_CONFIG, dma_hold,   dma_hold ) |
-		IO_FIELD( R_ATA_CONFIG, pio_setup,  pio_setup ) |
-		IO_FIELD( R_ATA_CONFIG, pio_strobe, pio_strobe ) |
-		IO_FIELD( R_ATA_CONFIG, pio_hold,   pio_hold ) );
-}
-
-static unsigned long
-cris_ide_base_address(int bus)
-{
-	return IO_FIELD(R_ATA_CTRL_DATA, sel, bus);
-}
-
-static unsigned long
-cris_ide_reg_addr(unsigned long addr, int cs0, int cs1)
-{
-	return IO_FIELD(R_ATA_CTRL_DATA, addr, addr) |
-	       IO_FIELD(R_ATA_CTRL_DATA, cs0, cs0) |
-	       IO_FIELD(R_ATA_CTRL_DATA, cs1, cs1);
-}
-
-static __init void
-cris_ide_reset(unsigned val)
-{
-#ifdef CONFIG_ETRAX_IDE_G27_RESET
-	REG_SHADOW_SET(R_PORT_G_DATA, port_g_data_shadow, 27, val);
-#endif
-#ifdef CONFIG_ETRAX_IDE_PB7_RESET
-	port_pb_dir_shadow = port_pb_dir_shadow |
-		IO_STATE(R_PORT_PB_DIR, dir7, output);
-	*R_PORT_PB_DIR = port_pb_dir_shadow;
-	REG_SHADOW_SET(R_PORT_PB_DATA, port_pb_data_shadow, 7, val);
-#endif
-}
-
-static __init void
-cris_ide_init(void)
-{
-	volatile unsigned int dummy;
-
-	*R_ATA_CTRL_DATA = 0;
-	*R_ATA_TRANSFER_CNT = 0;
-	*R_ATA_CONFIG = 0;
-
-	if (cris_request_io_interface(if_ata, "ETRAX100LX IDE")) {
-		printk(KERN_CRIT "ide: Failed to get IO interface\n");
-		return;
-	} else if (cris_request_dma(ATA_TX_DMA_NBR,
-		                          "ETRAX100LX IDE TX",
-		                          DMA_VERBOSE_ON_ERROR,
-		                          dma_ata)) {
-		cris_free_io_interface(if_ata);
-		printk(KERN_CRIT "ide: Failed to get Tx DMA channel\n");
-		return;
-	} else if (cris_request_dma(ATA_RX_DMA_NBR,
-		                          "ETRAX100LX IDE RX",
-		                          DMA_VERBOSE_ON_ERROR,
-		                          dma_ata)) {
-		cris_free_dma(ATA_TX_DMA_NBR, "ETRAX100LX IDE Tx");
-		cris_free_io_interface(if_ata);
-		printk(KERN_CRIT "ide: Failed to get Rx DMA channel\n");
-		return;
-	}
-
-	/* make a dummy read to set the ata controller in a proper state */
-	dummy = *R_ATA_STATUS_DATA;
-
-	*R_ATA_CONFIG = ( IO_FIELD( R_ATA_CONFIG, enable, 1 ));
-	*R_ATA_CTRL_DATA = ( IO_STATE( R_ATA_CTRL_DATA, rw,   read) |
-	                     IO_FIELD( R_ATA_CTRL_DATA, addr, 1   ) );
-
-	while(*R_ATA_STATUS_DATA & IO_MASK(R_ATA_STATUS_DATA, busy)); /* wait for busy flag*/
-
-	*R_IRQ_MASK0_SET = ( IO_STATE( R_IRQ_MASK0_SET, ata_irq0, set ) |
-	                     IO_STATE( R_IRQ_MASK0_SET, ata_irq1, set ) |
-	                     IO_STATE( R_IRQ_MASK0_SET, ata_irq2, set ) |
-	                     IO_STATE( R_IRQ_MASK0_SET, ata_irq3, set ) );
-
-	/* reset the dma channels we will use */
-
-	RESET_DMA(ATA_TX_DMA_NBR);
-	RESET_DMA(ATA_RX_DMA_NBR);
-	WAIT_DMA(ATA_TX_DMA_NBR);
-	WAIT_DMA(ATA_RX_DMA_NBR);
-}
-
-#define cris_dma_descr_type etrax_dma_descr
-#define cris_pio_read IO_STATE(R_ATA_CTRL_DATA, rw, read)
-#define cris_ultra_mask 0x0
-#define MAX_DESCR_SIZE 0x10000UL
-
-static unsigned long
-cris_ide_get_reg(unsigned long reg)
-{
-	return (reg & 0x0e000000) >> 25;
-}
-
-static void
-cris_ide_fill_descriptor(cris_dma_descr_type *d, void* buf, unsigned int len, int last)
-{
-	d->buf = virt_to_phys(buf);
-	d->sw_len = len == MAX_DESCR_SIZE ? 0 : len;
-	if (last)
-		d->ctrl |= d_eol;
-}
-
-static void cris_ide_start_dma(ide_drive_t *drive, cris_dma_descr_type *d, int dir, int type, int len)
-{
-	unsigned long cmd;
-
-	if (dir) {
-		/* need to do this before RX DMA due to a chip bug
-		 * it is enough to just flush the part of the cache that
-		 * corresponds to the buffers we start, but since HD transfers
-		 * usually are more than 8 kB, it is easier to optimize for the
-		 * normal case and just flush the entire cache. its the only
-		 * way to be sure! (OB movie quote)
-		 */
-		flush_etrax_cache();
-		*R_DMA_CH3_FIRST = virt_to_phys(d);
-		*R_DMA_CH3_CMD   = IO_STATE(R_DMA_CH3_CMD, cmd, start);
-
-	} else {
-		*R_DMA_CH2_FIRST = virt_to_phys(d);
-		*R_DMA_CH2_CMD   = IO_STATE(R_DMA_CH2_CMD, cmd, start);
-	}
-
-	/* initiate a multi word dma read using DMA handshaking */
-
-	*R_ATA_TRANSFER_CNT =
-		IO_FIELD(R_ATA_TRANSFER_CNT, count, len >> 1);
-
-	cmd = dir ? IO_STATE(R_ATA_CTRL_DATA, rw, read) : IO_STATE(R_ATA_CTRL_DATA, rw, write);
-	cmd |= type == TYPE_PIO ? IO_STATE(R_ATA_CTRL_DATA, handsh, pio) :
-	                          IO_STATE(R_ATA_CTRL_DATA, handsh, dma);
-	*R_ATA_CTRL_DATA =
-		cmd |
-		IO_FIELD(R_ATA_CTRL_DATA, data,
-			 drive->hwif->io_ports[IDE_DATA_OFFSET]) |
-		IO_STATE(R_ATA_CTRL_DATA, src_dst,  dma)  |
-		IO_STATE(R_ATA_CTRL_DATA, multi,    on)   |
-		IO_STATE(R_ATA_CTRL_DATA, dma_size, word);
-}
-
-static void
-cris_ide_wait_dma(int dir)
-{
-	if (dir)
-		WAIT_DMA(ATA_RX_DMA_NBR);
-	else
-		WAIT_DMA(ATA_TX_DMA_NBR);
-}
-
-static int cris_dma_test_irq(ide_drive_t *drive)
-{
-	int intr = *R_IRQ_MASK0_RD;
-	int bus = IO_EXTRACT(R_ATA_CTRL_DATA, sel,
-			     drive->hwif->io_ports[IDE_DATA_OFFSET]);
-
-	return intr & (1 << (bus + IO_BITNR(R_IRQ_MASK0_RD, ata_irq0))) ? 1 : 0;
-}
-
-
-static void cris_ide_initialize_dma(int dir)
-{
-	if (dir)
-	{
-		RESET_DMA(ATA_RX_DMA_NBR); /* sometimes the DMA channel get stuck so we need to do this */
-		WAIT_DMA(ATA_RX_DMA_NBR);
-	}
-	else
-	{
-		RESET_DMA(ATA_TX_DMA_NBR); /* sometimes the DMA channel get stuck so we need to do this */
-		WAIT_DMA(ATA_TX_DMA_NBR);
-	}
-}
-
-#endif
-
-void
-cris_ide_outw(unsigned short data, unsigned long reg) {
-	int timeleft;
-
-	LOWDB(printk("ow: data 0x%x, reg 0x%x\n", data, reg));
-
-	/* note the lack of handling any timeouts. we stop waiting, but we don't
-	 * really notify anybody.
-	 */
-
-	timeleft = IDE_REGISTER_TIMEOUT;
-	/* wait for busy flag */
-	do {
-		timeleft--;
-	} while(timeleft && cris_ide_busy());
-
-	/*
-	 * Fall through at a timeout, so the ongoing command will be
-	 * aborted by the write below, which is expected to be a dummy
-	 * command to the command register.  This happens when a faulty
-	 * drive times out on a command.  See comment on timeout in
-	 * INB.
-	 */
-	if(!timeleft)
-		printk("ATA timeout reg 0x%lx := 0x%x\n", reg, data);
-
-	cris_ide_write_command(reg|data); /* write data to the drive's register */
-
-	timeleft = IDE_REGISTER_TIMEOUT;
-	/* wait for transmitter ready */
-	do {
-		timeleft--;
-	} while(timeleft && !cris_ide_ready());
-}
-
-void
-cris_ide_outb(unsigned char data, unsigned long reg)
-{
-	cris_ide_outw(data, reg);
-}
-
-void
-cris_ide_outbsync(ide_drive_t *drive, u8 addr, unsigned long port)
-{
-	cris_ide_outw(addr, port);
-}
-
-unsigned short
-cris_ide_inw(unsigned long reg) {
-	int timeleft;
-	unsigned short val;
-
-	timeleft = IDE_REGISTER_TIMEOUT;
-	/* wait for busy flag */
-	do {
-		timeleft--;
-	} while(timeleft && cris_ide_busy());
-
-	if(!timeleft) {
-		/*
-		 * If we're asked to read the status register, like for
-		 * example when a command does not complete for an
-		 * extended time, but the ATA interface is stuck in a
-		 * busy state at the *ETRAX* ATA interface level (as has
-		 * happened repeatedly with at least one bad disk), then
-		 * the best thing to do is to pretend that we read
-		 * "busy" in the status register, so the IDE driver will
-		 * time-out, abort the ongoing command and perform a
-		 * reset sequence.  Note that the subsequent OUT_BYTE
-		 * call will also timeout on busy, but as long as the
-		 * write is still performed, everything will be fine.
-		 */
-		if (cris_ide_get_reg(reg) == IDE_STATUS_OFFSET)
-			return BUSY_STAT;
-		else
-			/* For other rare cases we assume 0 is good enough.  */
-			return 0;
-	}
-
-	cris_ide_write_command(reg | cris_pio_read);
-
-	timeleft = IDE_REGISTER_TIMEOUT;
-	/* wait for available */
-	do {
-		timeleft--;
-	} while(timeleft && !cris_ide_data_available(&val));
-
-	if(!timeleft)
-		return 0;
-
-	LOWDB(printk("inb: 0x%x from reg 0x%x\n", val & 0xff, reg));
-
-	return val;
-}
-
-unsigned char
-cris_ide_inb(unsigned long reg)
-{
-	return (unsigned char)cris_ide_inw(reg);
-}
-
-static void cris_ide_input_data (ide_drive_t *drive, void *, unsigned int);
-static void cris_ide_output_data (ide_drive_t *drive, void *, unsigned int);
-static void cris_atapi_input_bytes(ide_drive_t *drive, void *, unsigned int);
-static void cris_atapi_output_bytes(ide_drive_t *drive, void *, unsigned int);
-
-static void cris_dma_host_set(ide_drive_t *drive, int on)
-{
-}
-
-static void cris_set_pio_mode(ide_drive_t *drive, const u8 pio)
-{
-	int setup, strobe, hold;
-
-	switch(pio)
-	{
-		case 0:
-			setup = ATA_PIO0_SETUP;
-			strobe = ATA_PIO0_STROBE;
-			hold = ATA_PIO0_HOLD;
-			break;
-		case 1:
-			setup = ATA_PIO1_SETUP;
-			strobe = ATA_PIO1_STROBE;
-			hold = ATA_PIO1_HOLD;
-			break;
-		case 2:
-			setup = ATA_PIO2_SETUP;
-			strobe = ATA_PIO2_STROBE;
-			hold = ATA_PIO2_HOLD;
-			break;
-		case 3:
-			setup = ATA_PIO3_SETUP;
-			strobe = ATA_PIO3_STROBE;
-			hold = ATA_PIO3_HOLD;
-			break;
-		case 4:
-			setup = ATA_PIO4_SETUP;
-			strobe = ATA_PIO4_STROBE;
-			hold = ATA_PIO4_HOLD;
-			break;
-		default:
-			return;
-	}
-
-	cris_ide_set_speed(TYPE_PIO, setup, strobe, hold);
-}
-
-static void cris_set_dma_mode(ide_drive_t *drive, const u8 speed)
-{
-	int cyc = 0, dvs = 0, strobe = 0, hold = 0;
-
-	switch(speed)
-	{
-		case XFER_UDMA_0:
-			cyc = ATA_UDMA0_CYC;
-			dvs = ATA_UDMA0_DVS;
-			break;
-		case XFER_UDMA_1:
-			cyc = ATA_UDMA1_CYC;
-			dvs = ATA_UDMA1_DVS;
-			break;
-		case XFER_UDMA_2:
-			cyc = ATA_UDMA2_CYC;
-			dvs = ATA_UDMA2_DVS;
-			break;
-		case XFER_MW_DMA_0:
-			strobe = ATA_DMA0_STROBE;
-			hold = ATA_DMA0_HOLD;
-			break;
-		case XFER_MW_DMA_1:
-			strobe = ATA_DMA1_STROBE;
-			hold = ATA_DMA1_HOLD;
-			break;
-		case XFER_MW_DMA_2:
-			strobe = ATA_DMA2_STROBE;
-			hold = ATA_DMA2_HOLD;
-			break;
-	}
-
-	if (speed >= XFER_UDMA_0)
-		cris_ide_set_speed(TYPE_UDMA, cyc, dvs, 0);
-	else
-		cris_ide_set_speed(TYPE_DMA, 0, strobe, hold);
-}
-
-static void __init cris_setup_ports(hw_regs_t *hw, unsigned long base)
-{
-	int i;
-
-	memset(hw, 0, sizeof(*hw));
-
-	for (i = 0; i <= 7; i++)
-		hw->io_ports[i] = base + cris_ide_reg_addr(i, 0, 1);
-
-	/*
-	 * the IDE control register is at ATA address 6,
-	 * with CS1 active instead of CS0
-	 */
-	hw->io_ports[IDE_CONTROL_OFFSET] = base + cris_ide_reg_addr(6, 1, 0);
-
-	hw->irq = ide_default_irq(0);
-	hw->ack_intr = cris_ide_ack_intr;
-}
-
-static const struct ide_port_ops cris_port_ops = {
-	.set_pio_mode		= cris_set_pio_mode,
-	.set_dma_mode		= cris_set_dma_mode,
-};
-
-static const struct ide_dma_ops cris_dma_ops;
-
-static const struct ide_port_info cris_port_info __initdata = {
-	.chipset		= ide_etrax100,
-	.port_ops		= &cris_port_ops,
-	.dma_ops		= &cris_dma_ops,
-	.host_flags		= IDE_HFLAG_NO_ATAPI_DMA |
-				  IDE_HFLAG_NO_DMA, /* no SFF-style DMA */
-	.pio_mask		= ATA_PIO4,
-	.udma_mask		= cris_ultra_mask,
-	.mwdma_mask		= ATA_MWDMA2,
-};
-
-static int __init init_e100_ide(void)
-{
-	hw_regs_t hw;
-	int h;
-	u8 idx[4] = { 0xff, 0xff, 0xff, 0xff };
-
-	printk("ide: ETRAX FS built-in ATA DMA controller\n");
-
-	for (h = 0; h < 4; h++) {
-		ide_hwif_t *hwif = NULL;
-
-		cris_setup_ports(&hw, cris_ide_base_address(h));
-
-		hwif = ide_find_port();
-		if (hwif == NULL)
-			continue;
-		ide_init_port_data(hwif, hwif->index);
-		ide_init_port_hw(hwif, &hw);
-
-		hwif->ata_input_data = &cris_ide_input_data;
-		hwif->ata_output_data = &cris_ide_output_data;
-		hwif->atapi_input_bytes = &cris_atapi_input_bytes;
-		hwif->atapi_output_bytes = &cris_atapi_output_bytes;
-		hwif->OUTB = &cris_ide_outb;
-		hwif->OUTW = &cris_ide_outw;
-		hwif->OUTBSYNC = &cris_ide_outbsync;
-		hwif->INB = &cris_ide_inb;
-		hwif->INW = &cris_ide_inw;
-		hwif->cbl = ATA_CBL_PATA40;
-
-		idx[h] = hwif->index;
-	}
-
-	/* Reset pulse */
-	cris_ide_reset(0);
-	udelay(25);
-	cris_ide_reset(1);
-
-	cris_ide_init();
-
-	cris_ide_set_speed(TYPE_PIO, ATA_PIO4_SETUP, ATA_PIO4_STROBE, ATA_PIO4_HOLD);
-	cris_ide_set_speed(TYPE_DMA, 0, ATA_DMA2_STROBE, ATA_DMA2_HOLD);
-	cris_ide_set_speed(TYPE_UDMA, ATA_UDMA2_CYC, ATA_UDMA2_DVS, 0);
-
-	ide_device_add(idx, &cris_port_info);
-
-	return 0;
-}
-
-static cris_dma_descr_type mydescr __attribute__ ((__aligned__(16)));
-
-/*
- * The following routines are mainly used by the ATAPI drivers.
- *
- * These routines will round up any request for an odd number of bytes,
- * so if an odd bytecount is specified, be sure that there's at least one
- * extra byte allocated for the buffer.
- */
-static void
-cris_atapi_input_bytes (ide_drive_t *drive, void *buffer, unsigned int bytecount)
-{
-	D(printk("atapi_input_bytes, buffer 0x%x, count %d\n",
-	         buffer, bytecount));
-
-	if(bytecount & 1) {
-		printk("warning, odd bytecount in cdrom_in_bytes = %d.\n", bytecount);
-		bytecount++; /* to round off */
-	}
-
-	/* setup DMA and start transfer */
-
-	cris_ide_fill_descriptor(&mydescr, buffer, bytecount, 1);
-	cris_ide_start_dma(drive, &mydescr, 1, TYPE_PIO, bytecount);
-
-	/* wait for completion */
-	LED_DISK_READ(1);
-	cris_ide_wait_dma(1);
-	LED_DISK_READ(0);
-}
-
-static void
-cris_atapi_output_bytes (ide_drive_t *drive, void *buffer, unsigned int bytecount)
-{
-	D(printk("atapi_output_bytes, buffer 0x%x, count %d\n",
-	         buffer, bytecount));
-
-	if(bytecount & 1) {
-		printk("odd bytecount %d in atapi_out_bytes!\n", bytecount);
-		bytecount++;
-	}
-
-	cris_ide_fill_descriptor(&mydescr, buffer, bytecount, 1);
-	cris_ide_start_dma(drive, &mydescr, 0, TYPE_PIO, bytecount);
-
-	/* wait for completion */
-
-	LED_DISK_WRITE(1);
-	LED_DISK_READ(1);
-	cris_ide_wait_dma(0);
-	LED_DISK_WRITE(0);
-}
-
-/*
- * This is used for most PIO data transfers *from* the IDE interface
- */
-static void
-cris_ide_input_data (ide_drive_t *drive, void *buffer, unsigned int wcount)
-{
-	cris_atapi_input_bytes(drive, buffer, wcount << 2);
-}
-
-/*
- * This is used for most PIO data transfers *to* the IDE interface
- */
-static void
-cris_ide_output_data (ide_drive_t *drive, void *buffer, unsigned int wcount)
-{
-	cris_atapi_output_bytes(drive, buffer, wcount << 2);
-}
-
-/* we only have one DMA channel on the chip for ATA, so we can keep these statically */
-static cris_dma_descr_type ata_descrs[MAX_DMA_DESCRS] __attribute__ ((__aligned__(16)));
-static unsigned int ata_tot_size;
-
-/*
- * cris_ide_build_dmatable() prepares a dma request.
- * Returns 0 if all went okay, returns 1 otherwise.
- */
-static int cris_ide_build_dmatable (ide_drive_t *drive)
-{
-	ide_hwif_t *hwif = drive->hwif;
-	struct scatterlist* sg;
-	struct request *rq  = drive->hwif->hwgroup->rq;
-	unsigned long size, addr;
-	unsigned int count = 0;
-	int i = 0;
-
-	sg = hwif->sg_table;
-
-	ata_tot_size = 0;
-
-	ide_map_sg(drive, rq);
-	i = hwif->sg_nents;
-
-	while(i) {
-		/*
-		 * Determine addr and size of next buffer area.  We assume that
-		 * individual virtual buffers are always composed linearly in
-		 * physical memory.  For example, we assume that any 8kB buffer
-		 * is always composed of two adjacent physical 4kB pages rather
-		 * than two possibly non-adjacent physical 4kB pages.
-		 */
-		/* group sequential buffers into one large buffer */
-		addr = sg_phys(sg);
-		size = sg_dma_len(sg);
-		while (--i) {
-			sg = sg_next(sg);
-			if ((addr + size) != sg_phys(sg))
-				break;
-			size += sg_dma_len(sg);
-		}
-
-		/* did we run out of descriptors? */
-
-		if(count >= MAX_DMA_DESCRS) {
-			printk("%s: too few DMA descriptors\n", drive->name);
-			return 1;
-		}
-
-		/* however, this case is more difficult - rw_trf_cnt cannot be more
-		   than 65536 words per transfer, so in that case we need to either
-		   1) use a DMA interrupt to re-trigger rw_trf_cnt and continue with
-		      the descriptors, or
-		   2) simply do the request here, and get dma_intr to only ide_end_request on
-		      those blocks that were actually set-up for transfer.
-		*/
-
-		if(ata_tot_size + size > 131072) {
-			printk("too large total ATA DMA request, %d + %d!\n", ata_tot_size, (int)size);
-			return 1;
-		}
-
-		/* If size > MAX_DESCR_SIZE it has to be splitted into new descriptors. Since we
-                   don't handle size > 131072 only one split is necessary */
-
-		if(size > MAX_DESCR_SIZE) {
-			cris_ide_fill_descriptor(&ata_descrs[count], (void*)addr, MAX_DESCR_SIZE, 0);
-			count++;
-			ata_tot_size += MAX_DESCR_SIZE;
-			size -= MAX_DESCR_SIZE;
-			addr += MAX_DESCR_SIZE;
-		}
-
-		cris_ide_fill_descriptor(&ata_descrs[count], (void*)addr, size,i ? 0 : 1);
-		count++;
-		ata_tot_size += size;
-	}
-
-	if (count) {
-		/* return and say all is ok */
-		return 0;
-	}
-
-	printk("%s: empty DMA table?\n", drive->name);
-	return 1;	/* let the PIO routines handle this weirdness */
-}
-
-/*
- * cris_dma_intr() is the handler for disk read/write DMA interrupts
- */
-static ide_startstop_t cris_dma_intr (ide_drive_t *drive)
-{
-	LED_DISK_READ(0);
-	LED_DISK_WRITE(0);
-
-	return ide_dma_intr(drive);
-}
-
-/*
- * Functions below initiates/aborts DMA read/write operations on a drive.
- *
- * The caller is assumed to have selected the drive and programmed the drive's
- * sector address using CHS or LBA.  All that remains is to prepare for DMA
- * and then issue the actual read/write DMA/PIO command to the drive.
- *
- * For ATAPI devices, we just prepare for DMA and return. The caller should
- * then issue the packet command to the drive and call us again with
- * cris_dma_start afterwards.
- *
- * Returns 0 if all went well.
- * Returns 1 if DMA read/write could not be started, in which case
- * the caller should revert to PIO for the current request.
- */
-
-static int cris_dma_end(ide_drive_t *drive)
-{
-	drive->waiting_for_dma = 0;
-	return 0;
-}
-
-static int cris_dma_setup(ide_drive_t *drive)
-{
-	struct request *rq = drive->hwif->hwgroup->rq;
-
-	cris_ide_initialize_dma(!rq_data_dir(rq));
-	if (cris_ide_build_dmatable (drive)) {
-		ide_map_sg(drive, rq);
-		return 1;
-	}
-
-	drive->waiting_for_dma = 1;
-	return 0;
-}
-
-static void cris_dma_exec_cmd(ide_drive_t *drive, u8 command)
-{
-	ide_execute_command(drive, command, &cris_dma_intr, WAIT_CMD, NULL);
-}
-
-static void cris_dma_start(ide_drive_t *drive)
-{
-	struct request *rq = drive->hwif->hwgroup->rq;
-	int writing = rq_data_dir(rq);
-	int type = TYPE_DMA;
-
-	if (drive->current_speed >= XFER_UDMA_0)
-		type = TYPE_UDMA;
-
-	cris_ide_start_dma(drive, &ata_descrs[0], writing ? 0 : 1, type, ata_tot_size);
-
-	if (writing) {
-		LED_DISK_WRITE(1);
-	} else {
-		LED_DISK_READ(1);
-	}
-}
-
-static const struct ide_dma_ops cris_dma_ops = {
-	.dma_host_set		= cris_dma_host_set,
-	.dma_setup		= cris_dma_setup,
-	.dma_exec_cmd		= cris_dma_exec_cmd,
-	.dma_start		= cris_dma_start,
-	.dma_end		= cris_dma_end,
-	.dma_test_irq		= cris_dma_test_irq,
-};
-
-module_init(init_e100_ide);
-
-MODULE_LICENSE("GPL");
diff --git a/trunk/drivers/ide/h8300/ide-h8300.c b/trunk/drivers/ide/h8300/ide-h8300.c
index 0708b29cdb17..ecf53bb0d2aa 100644
--- a/trunk/drivers/ide/h8300/ide-h8300.c
+++ b/trunk/drivers/ide/h8300/ide-h8300.c
@@ -42,6 +42,91 @@ static u16 mm_inw(unsigned long a)
 	return r;
 }
 
+static void h8300_tf_load(ide_drive_t *drive, ide_task_t *task)
+{
+	ide_hwif_t *hwif = drive->hwif;
+	struct ide_io_ports *io_ports = &hwif->io_ports;
+	struct ide_taskfile *tf = &task->tf;
+	u8 HIHI = (task->tf_flags & IDE_TFLAG_LBA48) ? 0xE0 : 0xEF;
+
+	if (task->tf_flags & IDE_TFLAG_FLAGGED)
+		HIHI = 0xFF;
+
+	ide_set_irq(drive, 1);
+
+	if (task->tf_flags & IDE_TFLAG_OUT_DATA)
+		mm_outw((tf->hob_data << 8) | tf->data, io_ports->data_addr);
+
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_FEATURE)
+		outb(tf->hob_feature, io_ports->feature_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_NSECT)
+		outb(tf->hob_nsect, io_ports->nsect_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAL)
+		outb(tf->hob_lbal, io_ports->lbal_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAM)
+		outb(tf->hob_lbam, io_ports->lbam_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAH)
+		outb(tf->hob_lbah, io_ports->lbah_addr);
+
+	if (task->tf_flags & IDE_TFLAG_OUT_FEATURE)
+		outb(tf->feature, io_ports->feature_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_NSECT)
+		outb(tf->nsect, io_ports->nsect_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_LBAL)
+		outb(tf->lbal, io_ports->lbal_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_LBAM)
+		outb(tf->lbam, io_ports->lbam_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_LBAH)
+		outb(tf->lbah, io_ports->lbah_addr);
+
+	if (task->tf_flags & IDE_TFLAG_OUT_DEVICE)
+		outb((tf->device & HIHI) | drive->select.all,
+		     io_ports->device_addr);
+}
+
+static void h8300_tf_read(ide_drive_t *drive, ide_task_t *task)
+{
+	ide_hwif_t *hwif = drive->hwif;
+	struct ide_io_ports *io_ports = &hwif->io_ports;
+	struct ide_taskfile *tf = &task->tf;
+
+	if (task->tf_flags & IDE_TFLAG_IN_DATA) {
+		u16 data = mm_inw(io_ports->data_addr);
+
+		tf->data = data & 0xff;
+		tf->hob_data = (data >> 8) & 0xff;
+	}
+
+	/* be sure we're looking at the low order bits */
+	outb(drive->ctl & ~0x80, io_ports->ctl_addr);
+
+	if (task->tf_flags & IDE_TFLAG_IN_NSECT)
+		tf->nsect  = inb(io_ports->nsect_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_LBAL)
+		tf->lbal   = inb(io_ports->lbal_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_LBAM)
+		tf->lbam   = inb(io_ports->lbam_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_LBAH)
+		tf->lbah   = inb(io_ports->lbah_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_DEVICE)
+		tf->device = inb(io_ports->device_addr);
+
+	if (task->tf_flags & IDE_TFLAG_LBA48) {
+		outb(drive->ctl | 0x80, io_ports->ctl_addr);
+
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_FEATURE)
+			tf->hob_feature = inb(io_ports->feature_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_NSECT)
+			tf->hob_nsect   = inb(io_ports->nsect_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAL)
+			tf->hob_lbal    = inb(io_ports->lbal_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAM)
+			tf->hob_lbam    = inb(io_ports->lbam_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAH)
+			tf->hob_lbah    = inb(io_ports->lbah_addr);
+	}
+}
+
 static void mm_outsw(unsigned long addr, void *buf, u32 len)
 {
 	unsigned short *bp = (unsigned short *)buf;
@@ -56,6 +141,18 @@ static void mm_insw(unsigned long addr, void *buf, u32 len)
 		*bp = bswap(*(volatile u16 *)addr);
 }
 
+static void h8300_input_data(ide_drive_t *drive, struct request *rq,
+			     void *buf, unsigned int len)
+{
+	mm_insw(drive->hwif->io_ports.data_addr, buf, (len + 1) / 2);
+}
+
+static void h8300_output_data(ide_drive_t *drive, struct request *rq,
+			      void *buf, unsigned int len)
+{
+	mm_outsw(drive->hwif->io_ports.data_addr, buf, (len + 1) / 2);
+}
+
 #define H8300_IDE_GAP (2)
 
 static inline void hw_setup(hw_regs_t *hw)
@@ -63,9 +160,9 @@ static inline void hw_setup(hw_regs_t *hw)
 	int i;
 
 	memset(hw, 0, sizeof(hw_regs_t));
-	for (i = 0; i <= IDE_STATUS_OFFSET; i++)
-		hw->io_ports[i] = CONFIG_H8300_IDE_BASE + H8300_IDE_GAP*i;
-	hw->io_ports[IDE_CONTROL_OFFSET] = CONFIG_H8300_IDE_ALT;
+	for (i = 0; i <= 7; i++)
+		hw->io_ports_array[i] = CONFIG_H8300_IDE_BASE + H8300_IDE_GAP*i;
+	hw->io_ports.ctl_addr = CONFIG_H8300_IDE_ALT;
 	hw->irq = EXT_IRQ0 + CONFIG_H8300_IDE_IRQ;
 	hw->chipset = ide_generic;
 }
@@ -74,12 +171,11 @@ static inline void hwif_setup(ide_hwif_t *hwif)
 {
 	default_hwif_iops(hwif);
 
-	hwif->OUTW  = mm_outw;
-	hwif->OUTSW = mm_outsw;
-	hwif->INW   = mm_inw;
-	hwif->INSW  = mm_insw;
-	hwif->OUTSL = NULL;
-	hwif->INSL  = NULL;
+	hwif->tf_load = h8300_tf_load;
+	hwif->tf_read = h8300_tf_read;
+
+	hwif->input_data  = h8300_input_data;
+	hwif->output_data = h8300_output_data;
 }
 
 static int __init h8300_ide_init(void)
diff --git a/trunk/drivers/ide/ide-acpi.c b/trunk/drivers/ide/ide-acpi.c
index e4ad26e4fce7..9d3601fa5680 100644
--- a/trunk/drivers/ide/ide-acpi.c
+++ b/trunk/drivers/ide/ide-acpi.c
@@ -60,9 +60,17 @@ struct ide_acpi_hwif_link {
 #define DEBPRINT(fmt, args...)	do {} while (0)
 #endif	/* DEBUGGING */
 
-extern int ide_noacpi;
-extern int ide_noacpitfs;
-extern int ide_noacpionboot;
+int ide_noacpi;
+module_param_named(noacpi, ide_noacpi, bool, 0);
+MODULE_PARM_DESC(noacpi, "disable IDE ACPI support");
+
+int ide_acpigtf;
+module_param_named(acpigtf, ide_acpigtf, bool, 0);
+MODULE_PARM_DESC(acpigtf, "enable IDE ACPI _GTF support");
+
+int ide_acpionboot;
+module_param_named(acpionboot, ide_acpionboot, bool, 0);
+MODULE_PARM_DESC(acpionboot, "call IDE ACPI methods on boot");
 
 static bool ide_noacpi_psx;
 static int no_acpi_psx(const struct dmi_system_id *id)
@@ -376,7 +384,7 @@ static int taskfile_load_raw(ide_drive_t *drive,
 	memcpy(&args.tf_array[7], &gtf->tfa, 7);
 	args.tf_flags = IDE_TFLAG_TF | IDE_TFLAG_DEVICE;
 
-	if (ide_noacpitfs) {
+	if (!ide_acpigtf) {
 		DEBPRINT("_GTF execution disabled\n");
 		return err;
 	}
@@ -721,7 +729,7 @@ void ide_acpi_port_init_devices(ide_hwif_t *hwif)
 				 drive->name, err);
 	}
 
-	if (ide_noacpionboot) {
+	if (!ide_acpionboot) {
 		DEBPRINT("ACPI methods disabled on boot\n");
 		return;
 	}
diff --git a/trunk/drivers/ide/ide-cd.c b/trunk/drivers/ide/ide-cd.c
index ad984322da94..68e7f19dc036 100644
--- a/trunk/drivers/ide/ide-cd.c
+++ b/trunk/drivers/ide/ide-cd.c
@@ -142,7 +142,6 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
 {
 	unsigned long sector;
 	unsigned long bio_sectors;
-	unsigned long valid;
 	struct cdrom_info *info = drive->driver_data;
 
 	if (!cdrom_log_sense(drive, failed_command, sense))
@@ -173,17 +172,13 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
 				 (sense->information[2] <<  8) |
 				 (sense->information[3]);
 
-			bio_sectors = bio_sectors(failed_command->bio);
-			if (bio_sectors < 4)
-				bio_sectors = 4;
 			if (drive->queue->hardsect_size == 2048)
 				/* device sector size is 2K */
 				sector <<= 2;
+
+			bio_sectors = max(bio_sectors(failed_command->bio), 4U);
 			sector &= ~(bio_sectors - 1);
-			valid = (sector - failed_command->sector) << 9;
 
-			if (valid < 0)
-				valid = 0;
 			if (sector < get_capacity(info->disk) &&
 			    drive->probed_capacity - sector < 4 * 75)
 				set_capacity(info->disk, sector);
@@ -555,14 +550,7 @@ static ide_startstop_t cdrom_start_packet_command(ide_drive_t *drive,
 				    ATAPI_WAIT_PC, cdrom_timer_expiry);
 		return ide_started;
 	} else {
-		unsigned long flags;
-
-		/* packet command */
-		spin_lock_irqsave(&ide_lock, flags);
-		hwif->OUTBSYNC(drive, WIN_PACKETCMD,
-			       hwif->io_ports[IDE_COMMAND_OFFSET]);
-		ndelay(400);
-		spin_unlock_irqrestore(&ide_lock, flags);
+		ide_execute_pkt_cmd(drive);
 
 		return (*handler) (drive);
 	}
@@ -613,7 +601,7 @@ static ide_startstop_t cdrom_transfer_packet_command(ide_drive_t *drive,
 		cmd_len = ATAPI_MIN_CDB_BYTES;
 
 	/* send the command to the device */
-	HWIF(drive)->atapi_output_bytes(drive, rq->cmd, cmd_len);
+	hwif->output_data(drive, NULL, rq->cmd, cmd_len);
 
 	/* start the DMA if need be */
 	if (info->dma)
@@ -629,7 +617,7 @@ static void ide_cd_pad_transfer(ide_drive_t *drive, xfer_func_t *xf, int len)
 {
 	while (len > 0) {
 		int dum = 0;
-		xf(drive, &dum, sizeof(dum));
+		xf(drive, NULL, &dum, sizeof(dum));
 		len -= sizeof(dum);
 	}
 }
@@ -639,7 +627,7 @@ static void ide_cd_drain_data(ide_drive_t *drive, int nsects)
 	while (nsects > 0) {
 		static char dum[SECTOR_SIZE];
 
-		drive->hwif->atapi_input_bytes(drive, dum, sizeof(dum));
+		drive->hwif->input_data(drive, NULL, dum, sizeof(dum));
 		nsects--;
 	}
 }
@@ -666,7 +654,7 @@ static int ide_cd_check_ireason(ide_drive_t *drive, struct request *rq,
 		printk(KERN_ERR "%s: %s: wrong transfer direction!\n",
 				drive->name, __func__);
 
-		xf = rw ? hwif->atapi_output_bytes : hwif->atapi_input_bytes;
+		xf = rw ? hwif->output_data : hwif->input_data;
 		ide_cd_pad_transfer(drive, xf, len);
 	} else  if (rw == 0 && ireason == 1) {
 		/*
@@ -794,7 +782,7 @@ static ide_startstop_t cdrom_start_seek_continuation(ide_drive_t *drive)
 
 	sector_div(frame, queue_hardsect_size(drive->queue) >> SECTOR_BITS);
 
-	memset(rq->cmd, 0, sizeof(rq->cmd));
+	memset(rq->cmd, 0, BLK_MAX_CDB);
 	rq->cmd[0] = GPCMD_SEEK;
 	put_unaligned(cpu_to_be32(frame), (unsigned int *) &rq->cmd[2]);
 
@@ -952,9 +940,9 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 	}
 
 	/* ok we fall to pio :/ */
-	ireason = hwif->INB(hwif->io_ports[IDE_IREASON_OFFSET]) & 0x3;
-	lowcyl  = hwif->INB(hwif->io_ports[IDE_BCOUNTL_OFFSET]);
-	highcyl = hwif->INB(hwif->io_ports[IDE_BCOUNTH_OFFSET]);
+	ireason = hwif->INB(hwif->io_ports.nsect_addr) & 0x3;
+	lowcyl  = hwif->INB(hwif->io_ports.lbam_addr);
+	highcyl = hwif->INB(hwif->io_ports.lbah_addr);
 
 	len = lowcyl + (256 * highcyl);
 
@@ -1019,10 +1007,10 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 
 	if (ireason == 0) {
 		write = 1;
-		xferfunc = HWIF(drive)->atapi_output_bytes;
+		xferfunc = hwif->output_data;
 	} else {
 		write = 0;
-		xferfunc = HWIF(drive)->atapi_input_bytes;
+		xferfunc = hwif->input_data;
 	}
 
 	/* transfer data */
@@ -1061,7 +1049,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 		if (blen > thislen)
 			blen = thislen;
 
-		xferfunc(drive, ptr, blen);
+		xferfunc(drive, NULL, ptr, blen);
 
 		thislen -= blen;
 		len -= blen;
@@ -1706,7 +1694,7 @@ static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq)
 	long block = (long)rq->hard_sector / (hard_sect >> 9);
 	unsigned long blocks = rq->hard_nr_sectors / (hard_sect >> 9);
 
-	memset(rq->cmd, 0, sizeof(rq->cmd));
+	memset(rq->cmd, 0, BLK_MAX_CDB);
 
 	if (rq_data_dir(rq) == READ)
 		rq->cmd[0] = GPCMD_READ_10;
@@ -1909,9 +1897,7 @@ static int ide_cdrom_setup(ide_drive_t *drive)
 	/* set correct block size */
 	blk_queue_hardsect_size(drive->queue, CD_FRAMESIZE);
 
-	if (drive->autotune == IDE_TUNE_DEFAULT ||
-	    drive->autotune == IDE_TUNE_AUTO)
-		drive->dsc_overlap = (drive->next != drive);
+	drive->dsc_overlap = (drive->next != drive);
 
 	if (ide_cdrom_register(drive, nslots)) {
 		printk(KERN_ERR "%s: %s failed to register device with the"
diff --git a/trunk/drivers/ide/ide-cd_verbose.c b/trunk/drivers/ide/ide-cd_verbose.c
index 6ed7ca071331..6490a2dea96b 100644
--- a/trunk/drivers/ide/ide-cd_verbose.c
+++ b/trunk/drivers/ide/ide-cd_verbose.c
@@ -326,7 +326,7 @@ void ide_cd_log_error(const char *name, struct request *failed_command,
 
 		printk(KERN_ERR "  The failed \"%s\" packet command "
 				"was: \n  \"", s);
-		for (i = 0; i < sizeof(failed_command->cmd); i++)
+		for (i = 0; i < BLK_MAX_CDB; i++)
 			printk(KERN_CONT "%02x ", failed_command->cmd[i]);
 		printk(KERN_CONT "\"\n");
 	}
diff --git a/trunk/drivers/ide/ide-dma.c b/trunk/drivers/ide/ide-dma.c
index c352cf27b6e7..653b1ade13d3 100644
--- a/trunk/drivers/ide/ide-dma.c
+++ b/trunk/drivers/ide/ide-dma.c
@@ -464,9 +464,10 @@ int ide_dma_setup(ide_drive_t *drive)
 
 	/* PRD table */
 	if (hwif->mmio)
-		writel(hwif->dmatable_dma, (void __iomem *)hwif->dma_prdtable);
+		writel(hwif->dmatable_dma,
+		       (void __iomem *)(hwif->dma_base + ATA_DMA_TABLE_OFS));
 	else
-		outl(hwif->dmatable_dma, hwif->dma_prdtable);
+		outl(hwif->dmatable_dma, hwif->dma_base + ATA_DMA_TABLE_OFS);
 
 	/* specify r/w */
 	hwif->OUTB(reading, hwif->dma_command);
@@ -858,14 +859,8 @@ void ide_setup_dma(ide_hwif_t *hwif, unsigned long base)
 
 	if (!hwif->dma_command)
 		hwif->dma_command	= hwif->dma_base + 0;
-	if (!hwif->dma_vendor1)
-		hwif->dma_vendor1	= hwif->dma_base + 1;
 	if (!hwif->dma_status)
 		hwif->dma_status	= hwif->dma_base + 2;
-	if (!hwif->dma_vendor3)
-		hwif->dma_vendor3	= hwif->dma_base + 3;
-	if (!hwif->dma_prdtable)
-		hwif->dma_prdtable	= hwif->dma_base + 4;
 
 	hwif->dma_ops = &sff_dma_ops;
 }
diff --git a/trunk/drivers/ide/ide-floppy.c b/trunk/drivers/ide/ide-floppy.c
index 6e891bccd052..f05fbc2bd7a8 100644
--- a/trunk/drivers/ide/ide-floppy.c
+++ b/trunk/drivers/ide/ide-floppy.c
@@ -231,6 +231,7 @@ static int idefloppy_end_request(ide_drive_t *drive, int uptodate, int nsecs)
 static void ide_floppy_io_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
 				  unsigned int bcount, int direction)
 {
+	ide_hwif_t *hwif = drive->hwif;
 	struct request *rq = pc->rq;
 	struct req_iterator iter;
 	struct bio_vec *bvec;
@@ -246,9 +247,9 @@ static void ide_floppy_io_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
 
 		data = bvec_kmap_irq(bvec, &flags);
 		if (direction)
-			drive->hwif->atapi_output_bytes(drive, data, count);
+			hwif->output_data(drive, NULL, data, count);
 		else
-			drive->hwif->atapi_input_bytes(drive, data, count);
+			hwif->input_data(drive, NULL, data, count);
 		bvec_kunmap_irq(data, &flags);
 
 		bcount -= count;
@@ -261,10 +262,7 @@ static void ide_floppy_io_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
 	if (bcount) {
 		printk(KERN_ERR "%s: leftover data in %s, bcount == %d\n",
 				drive->name, __func__, bcount);
-		if (direction)
-			ide_atapi_write_zeros(drive, bcount);
-		else
-			ide_atapi_discard_data(drive, bcount);
+		ide_pad_transfer(drive, direction, bcount);
 	}
 }
 
@@ -465,10 +463,10 @@ static ide_startstop_t idefloppy_pc_intr(ide_drive_t *drive)
 	}
 
 	/* Get the number of bytes to transfer */
-	bcount = (hwif->INB(hwif->io_ports[IDE_BCOUNTH_OFFSET]) << 8) |
-		  hwif->INB(hwif->io_ports[IDE_BCOUNTL_OFFSET]);
+	bcount = (hwif->INB(hwif->io_ports.lbah_addr) << 8) |
+		  hwif->INB(hwif->io_ports.lbam_addr);
 	/* on this interrupt */
-	ireason = hwif->INB(hwif->io_ports[IDE_IREASON_OFFSET]);
+	ireason = hwif->INB(hwif->io_ports.nsect_addr);
 
 	if (ireason & CD) {
 		printk(KERN_ERR "ide-floppy: CoD != 0 in %s\n", __func__);
@@ -490,7 +488,7 @@ static ide_startstop_t idefloppy_pc_intr(ide_drive_t *drive)
 				printk(KERN_ERR "ide-floppy: The floppy wants "
 					"to send us more data than expected "
 					"- discarding data\n");
-				ide_atapi_discard_data(drive, bcount);
+				ide_pad_transfer(drive, 0, bcount);
 
 				ide_set_handler(drive,
 						&idefloppy_pc_intr,
@@ -503,12 +501,12 @@ static ide_startstop_t idefloppy_pc_intr(ide_drive_t *drive)
 		}
 	}
 	if (pc->flags & PC_FLAG_WRITING)
-		xferfunc = hwif->atapi_output_bytes;
+		xferfunc = hwif->output_data;
 	else
-		xferfunc = hwif->atapi_input_bytes;
+		xferfunc = hwif->input_data;
 
 	if (pc->buf)
-		xferfunc(drive, pc->cur_pos, bcount);
+		xferfunc(drive, NULL, pc->cur_pos, bcount);
 	else
 		ide_floppy_io_buffers(drive, pc, bcount,
 				      !!(pc->flags & PC_FLAG_WRITING));
@@ -539,7 +537,7 @@ static ide_startstop_t idefloppy_transfer_pc(ide_drive_t *drive)
 				"initiated yet DRQ isn't asserted\n");
 		return startstop;
 	}
-	ireason = hwif->INB(hwif->io_ports[IDE_IREASON_OFFSET]);
+	ireason = hwif->INB(hwif->io_ports.nsect_addr);
 	if ((ireason & CD) == 0 || (ireason & IO)) {
 		printk(KERN_ERR "ide-floppy: (IO,CoD) != (0,1) while "
 				"issuing a packet command\n");
@@ -548,8 +546,10 @@ static ide_startstop_t idefloppy_transfer_pc(ide_drive_t *drive)
 
 	/* Set the interrupt routine */
 	ide_set_handler(drive, &idefloppy_pc_intr, IDEFLOPPY_WAIT_CMD, NULL);
+
 	/* Send the actual packet */
-	HWIF(drive)->atapi_output_bytes(drive, floppy->pc->c, 12);
+	hwif->output_data(drive, NULL, floppy->pc->c, 12);
+
 	return ide_started;
 }
 
@@ -569,7 +569,8 @@ static int idefloppy_transfer_pc2(ide_drive_t *drive)
 	idefloppy_floppy_t *floppy = drive->driver_data;
 
 	/* Send the actual packet */
-	HWIF(drive)->atapi_output_bytes(drive, floppy->pc->c, 12);
+	drive->hwif->output_data(drive, NULL, floppy->pc->c, 12);
+
 	/* Timeout for the packet command */
 	return IDEFLOPPY_WAIT_CMD;
 }
@@ -586,7 +587,7 @@ static ide_startstop_t idefloppy_transfer_pc1(ide_drive_t *drive)
 				"initiated yet DRQ isn't asserted\n");
 		return startstop;
 	}
-	ireason = hwif->INB(hwif->io_ports[IDE_IREASON_OFFSET]);
+	ireason = hwif->INB(hwif->io_ports.nsect_addr);
 	if ((ireason & CD) == 0 || (ireason & IO)) {
 		printk(KERN_ERR "ide-floppy: (IO,CoD) != (0,1) "
 				"while issuing a packet command\n");
@@ -692,7 +693,7 @@ static ide_startstop_t idefloppy_issue_pc(ide_drive_t *drive,
 		return ide_started;
 	} else {
 		/* Issue the packet command */
-		hwif->OUTB(WIN_PACKETCMD, hwif->io_ports[IDE_COMMAND_OFFSET]);
+		ide_execute_pkt_cmd(drive);
 		return (*pkt_xfer_routine) (drive);
 	}
 }
diff --git a/trunk/drivers/ide/ide-io.c b/trunk/drivers/ide/ide-io.c
index 0fe89a599275..696525342e9a 100644
--- a/trunk/drivers/ide/ide-io.c
+++ b/trunk/drivers/ide/ide-io.c
@@ -295,54 +295,6 @@ static void ide_complete_pm_request (ide_drive_t *drive, struct request *rq)
 	spin_unlock_irqrestore(&ide_lock, flags);
 }
 
-void ide_tf_read(ide_drive_t *drive, ide_task_t *task)
-{
-	ide_hwif_t *hwif = drive->hwif;
-	struct ide_taskfile *tf = &task->tf;
-
-	if (task->tf_flags & IDE_TFLAG_IN_DATA) {
-		u16 data = hwif->INW(hwif->io_ports[IDE_DATA_OFFSET]);
-
-		tf->data = data & 0xff;
-		tf->hob_data = (data >> 8) & 0xff;
-	}
-
-	/* be sure we're looking at the low order bits */
-	hwif->OUTB(drive->ctl & ~0x80, hwif->io_ports[IDE_CONTROL_OFFSET]);
-
-	if (task->tf_flags & IDE_TFLAG_IN_NSECT)
-		tf->nsect  = hwif->INB(hwif->io_ports[IDE_NSECTOR_OFFSET]);
-	if (task->tf_flags & IDE_TFLAG_IN_LBAL)
-		tf->lbal   = hwif->INB(hwif->io_ports[IDE_SECTOR_OFFSET]);
-	if (task->tf_flags & IDE_TFLAG_IN_LBAM)
-		tf->lbam   = hwif->INB(hwif->io_ports[IDE_LCYL_OFFSET]);
-	if (task->tf_flags & IDE_TFLAG_IN_LBAH)
-		tf->lbah   = hwif->INB(hwif->io_ports[IDE_HCYL_OFFSET]);
-	if (task->tf_flags & IDE_TFLAG_IN_DEVICE)
-		tf->device = hwif->INB(hwif->io_ports[IDE_SELECT_OFFSET]);
-
-	if (task->tf_flags & IDE_TFLAG_LBA48) {
-		hwif->OUTB(drive->ctl | 0x80,
-			   hwif->io_ports[IDE_CONTROL_OFFSET]);
-
-		if (task->tf_flags & IDE_TFLAG_IN_HOB_FEATURE)
-			tf->hob_feature =
-				hwif->INB(hwif->io_ports[IDE_FEATURE_OFFSET]);
-		if (task->tf_flags & IDE_TFLAG_IN_HOB_NSECT)
-			tf->hob_nsect   =
-				hwif->INB(hwif->io_ports[IDE_NSECTOR_OFFSET]);
-		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAL)
-			tf->hob_lbal    =
-				hwif->INB(hwif->io_ports[IDE_SECTOR_OFFSET]);
-		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAM)
-			tf->hob_lbam    =
-				hwif->INB(hwif->io_ports[IDE_LCYL_OFFSET]);
-		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAH)
-			tf->hob_lbah    =
-				hwif->INB(hwif->io_ports[IDE_HCYL_OFFSET]);
-	}
-}
-
 /**
  *	ide_end_drive_cmd	-	end an explicit drive command
  *	@drive: command 
@@ -378,7 +330,7 @@ void ide_end_drive_cmd (ide_drive_t *drive, u8 stat, u8 err)
 			tf->error = err;
 			tf->status = stat;
 
-			ide_tf_read(drive, task);
+			drive->hwif->tf_read(drive, task);
 
 			if (task->tf_flags & IDE_TFLAG_DYN)
 				kfree(task);
@@ -427,7 +379,7 @@ static void try_to_flush_leftover_data (ide_drive_t *drive)
 		u32 wcount = (i > 16) ? 16 : i;
 
 		i -= wcount;
-		HWIF(drive)->ata_input_data(drive, buffer, wcount);
+		drive->hwif->input_data(drive, NULL, buffer, wcount * 4);
 	}
 }
 
@@ -454,7 +406,7 @@ static ide_startstop_t ide_ata_error(ide_drive_t *drive, struct request *rq, u8
 		if (err == ABRT_ERR) {
 			if (drive->select.b.lba &&
 			    /* some newer drives don't support WIN_SPECIFY */
-			    hwif->INB(hwif->io_ports[IDE_COMMAND_OFFSET]) ==
+			    hwif->INB(hwif->io_ports.command_addr) ==
 				WIN_SPECIFY)
 				return ide_stopped;
 		} else if ((err & BAD_CRC) == BAD_CRC) {
@@ -507,8 +459,8 @@ static ide_startstop_t ide_atapi_error(ide_drive_t *drive, struct request *rq, u
 
 	if (ide_read_status(drive) & (BUSY_STAT | DRQ_STAT))
 		/* force an abort */
-		hwif->OUTB(WIN_IDLEIMMEDIATE,
-			   hwif->io_ports[IDE_COMMAND_OFFSET]);
+		hwif->OUTBSYNC(drive, WIN_IDLEIMMEDIATE,
+			       hwif->io_ports.command_addr);
 
 	if (rq->errors >= ERROR_MAX) {
 		ide_kill_rq(drive, rq);
@@ -1421,7 +1373,7 @@ static void unexpected_intr (int irq, ide_hwgroup_t *hwgroup)
 	 */
 	do {
 		if (hwif->irq == irq) {
-			stat = hwif->INB(hwif->io_ports[IDE_STATUS_OFFSET]);
+			stat = hwif->INB(hwif->io_ports.status_addr);
 			if (!OK_STAT(stat, READY_STAT, BAD_STAT)) {
 				/* Try to not flood the console with msgs */
 				static unsigned long last_msgtime, count;
@@ -1511,7 +1463,7 @@ irqreturn_t ide_intr (int irq, void *dev_id)
 			 * Whack the status register, just in case
 			 * we have a leftover pending IRQ.
 			 */
-			(void) hwif->INB(hwif->io_ports[IDE_STATUS_OFFSET]);
+			(void) hwif->INB(hwif->io_ports.status_addr);
 #endif /* CONFIG_BLK_DEV_IDEPCI */
 		}
 		spin_unlock_irqrestore(&ide_lock, flags);
@@ -1598,8 +1550,7 @@ irqreturn_t ide_intr (int irq, void *dev_id)
 
 void ide_init_drive_cmd (struct request *rq)
 {
-	memset(rq, 0, sizeof(*rq));
-	rq->ref_count = 1;
+	blk_rq_init(NULL, rq);
 }
 
 EXPORT_SYMBOL(ide_init_drive_cmd);
@@ -1685,7 +1636,23 @@ void ide_pktcmd_tf_load(ide_drive_t *drive, u32 tf_flags, u16 bcount, u8 dma)
 	task.tf.lbam    = bcount & 0xff;
 	task.tf.lbah    = (bcount >> 8) & 0xff;
 
-	ide_tf_load(drive, &task);
+	ide_tf_dump(drive->name, &task.tf);
+	drive->hwif->tf_load(drive, &task);
 }
 
 EXPORT_SYMBOL_GPL(ide_pktcmd_tf_load);
+
+void ide_pad_transfer(ide_drive_t *drive, int write, int len)
+{
+	ide_hwif_t *hwif = drive->hwif;
+	u8 buf[4] = { 0 };
+
+	while (len > 0) {
+		if (write)
+			hwif->output_data(drive, NULL, buf, min(4, len));
+		else
+			hwif->input_data(drive, NULL, buf, min(4, len));
+		len -= 4;
+	}
+}
+EXPORT_SYMBOL_GPL(ide_pad_transfer);
diff --git a/trunk/drivers/ide/ide-iops.c b/trunk/drivers/ide/ide-iops.c
index 9c646bd63549..57d9a9a79a6f 100644
--- a/trunk/drivers/ide/ide-iops.c
+++ b/trunk/drivers/ide/ide-iops.c
@@ -37,21 +37,6 @@ static u8 ide_inb (unsigned long port)
 	return (u8) inb(port);
 }
 
-static u16 ide_inw (unsigned long port)
-{
-	return (u16) inw(port);
-}
-
-static void ide_insw (unsigned long port, void *addr, u32 count)
-{
-	insw(port, addr, count);
-}
-
-static void ide_insl (unsigned long port, void *addr, u32 count)
-{
-	insl(port, addr, count);
-}
-
 static void ide_outb (u8 val, unsigned long port)
 {
 	outb(val, port);
@@ -62,32 +47,11 @@ static void ide_outbsync (ide_drive_t *drive, u8 addr, unsigned long port)
 	outb(addr, port);
 }
 
-static void ide_outw (u16 val, unsigned long port)
-{
-	outw(val, port);
-}
-
-static void ide_outsw (unsigned long port, void *addr, u32 count)
-{
-	outsw(port, addr, count);
-}
-
-static void ide_outsl (unsigned long port, void *addr, u32 count)
-{
-	outsl(port, addr, count);
-}
-
 void default_hwif_iops (ide_hwif_t *hwif)
 {
 	hwif->OUTB	= ide_outb;
 	hwif->OUTBSYNC	= ide_outbsync;
-	hwif->OUTW	= ide_outw;
-	hwif->OUTSW	= ide_outsw;
-	hwif->OUTSL	= ide_outsl;
 	hwif->INB	= ide_inb;
-	hwif->INW	= ide_inw;
-	hwif->INSW	= ide_insw;
-	hwif->INSL	= ide_insl;
 }
 
 /*
@@ -99,21 +63,6 @@ static u8 ide_mm_inb (unsigned long port)
 	return (u8) readb((void __iomem *) port);
 }
 
-static u16 ide_mm_inw (unsigned long port)
-{
-	return (u16) readw((void __iomem *) port);
-}
-
-static void ide_mm_insw (unsigned long port, void *addr, u32 count)
-{
-	__ide_mm_insw((void __iomem *) port, addr, count);
-}
-
-static void ide_mm_insl (unsigned long port, void *addr, u32 count)
-{
-	__ide_mm_insl((void __iomem *) port, addr, count);
-}
-
 static void ide_mm_outb (u8 value, unsigned long port)
 {
 	writeb(value, (void __iomem *) port);
@@ -124,34 +73,13 @@ static void ide_mm_outbsync (ide_drive_t *drive, u8 value, unsigned long port)
 	writeb(value, (void __iomem *) port);
 }
 
-static void ide_mm_outw (u16 value, unsigned long port)
-{
-	writew(value, (void __iomem *) port);
-}
-
-static void ide_mm_outsw (unsigned long port, void *addr, u32 count)
-{
-	__ide_mm_outsw((void __iomem *) port, addr, count);
-}
-
-static void ide_mm_outsl (unsigned long port, void *addr, u32 count)
-{
-	__ide_mm_outsl((void __iomem *) port, addr, count);
-}
-
 void default_hwif_mmiops (ide_hwif_t *hwif)
 {
 	hwif->OUTB	= ide_mm_outb;
 	/* Most systems will need to override OUTBSYNC, alas however
 	   this one is controller specific! */
 	hwif->OUTBSYNC	= ide_mm_outbsync;
-	hwif->OUTW	= ide_mm_outw;
-	hwif->OUTSW	= ide_mm_outsw;
-	hwif->OUTSL	= ide_mm_outsl;
 	hwif->INB	= ide_mm_inb;
-	hwif->INW	= ide_mm_inw;
-	hwif->INSW	= ide_mm_insw;
-	hwif->INSL	= ide_mm_insl;
 }
 
 EXPORT_SYMBOL(default_hwif_mmiops);
@@ -164,7 +92,7 @@ void SELECT_DRIVE (ide_drive_t *drive)
 	if (port_ops && port_ops->selectproc)
 		port_ops->selectproc(drive);
 
-	hwif->OUTB(drive->select.all, hwif->io_ports[IDE_SELECT_OFFSET]);
+	hwif->OUTB(drive->select.all, hwif->io_ports.device_addr);
 }
 
 void SELECT_MASK (ide_drive_t *drive, int mask)
@@ -175,6 +103,123 @@ void SELECT_MASK (ide_drive_t *drive, int mask)
 		port_ops->maskproc(drive, mask);
 }
 
+static void ide_tf_load(ide_drive_t *drive, ide_task_t *task)
+{
+	ide_hwif_t *hwif = drive->hwif;
+	struct ide_io_ports *io_ports = &hwif->io_ports;
+	struct ide_taskfile *tf = &task->tf;
+	void (*tf_outb)(u8 addr, unsigned long port);
+	u8 mmio = (hwif->host_flags & IDE_HFLAG_MMIO) ? 1 : 0;
+	u8 HIHI = (task->tf_flags & IDE_TFLAG_LBA48) ? 0xE0 : 0xEF;
+
+	if (mmio)
+		tf_outb = ide_mm_outb;
+	else
+		tf_outb = ide_outb;
+
+	if (task->tf_flags & IDE_TFLAG_FLAGGED)
+		HIHI = 0xFF;
+
+	ide_set_irq(drive, 1);
+
+	if ((task->tf_flags & IDE_TFLAG_NO_SELECT_MASK) == 0)
+		SELECT_MASK(drive, 0);
+
+	if (task->tf_flags & IDE_TFLAG_OUT_DATA) {
+		u16 data = (tf->hob_data << 8) | tf->data;
+
+		if (mmio)
+			writew(data, (void __iomem *)io_ports->data_addr);
+		else
+			outw(data, io_ports->data_addr);
+	}
+
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_FEATURE)
+		tf_outb(tf->hob_feature, io_ports->feature_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_NSECT)
+		tf_outb(tf->hob_nsect, io_ports->nsect_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAL)
+		tf_outb(tf->hob_lbal, io_ports->lbal_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAM)
+		tf_outb(tf->hob_lbam, io_ports->lbam_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAH)
+		tf_outb(tf->hob_lbah, io_ports->lbah_addr);
+
+	if (task->tf_flags & IDE_TFLAG_OUT_FEATURE)
+		tf_outb(tf->feature, io_ports->feature_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_NSECT)
+		tf_outb(tf->nsect, io_ports->nsect_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_LBAL)
+		tf_outb(tf->lbal, io_ports->lbal_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_LBAM)
+		tf_outb(tf->lbam, io_ports->lbam_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_LBAH)
+		tf_outb(tf->lbah, io_ports->lbah_addr);
+
+	if (task->tf_flags & IDE_TFLAG_OUT_DEVICE)
+		tf_outb((tf->device & HIHI) | drive->select.all,
+			 io_ports->device_addr);
+}
+
+static void ide_tf_read(ide_drive_t *drive, ide_task_t *task)
+{
+	ide_hwif_t *hwif = drive->hwif;
+	struct ide_io_ports *io_ports = &hwif->io_ports;
+	struct ide_taskfile *tf = &task->tf;
+	void (*tf_outb)(u8 addr, unsigned long port);
+	u8 (*tf_inb)(unsigned long port);
+	u8 mmio = (hwif->host_flags & IDE_HFLAG_MMIO) ? 1 : 0;
+
+	if (mmio) {
+		tf_outb = ide_mm_outb;
+		tf_inb  = ide_mm_inb;
+	} else {
+		tf_outb = ide_outb;
+		tf_inb  = ide_inb;
+	}
+
+	if (task->tf_flags & IDE_TFLAG_IN_DATA) {
+		u16 data;
+
+		if (mmio)
+			data = readw((void __iomem *)io_ports->data_addr);
+		else
+			data = inw(io_ports->data_addr);
+
+		tf->data = data & 0xff;
+		tf->hob_data = (data >> 8) & 0xff;
+	}
+
+	/* be sure we're looking at the low order bits */
+	tf_outb(drive->ctl & ~0x80, io_ports->ctl_addr);
+
+	if (task->tf_flags & IDE_TFLAG_IN_NSECT)
+		tf->nsect  = tf_inb(io_ports->nsect_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_LBAL)
+		tf->lbal   = tf_inb(io_ports->lbal_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_LBAM)
+		tf->lbam   = tf_inb(io_ports->lbam_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_LBAH)
+		tf->lbah   = tf_inb(io_ports->lbah_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_DEVICE)
+		tf->device = tf_inb(io_ports->device_addr);
+
+	if (task->tf_flags & IDE_TFLAG_LBA48) {
+		tf_outb(drive->ctl | 0x80, io_ports->ctl_addr);
+
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_FEATURE)
+			tf->hob_feature = tf_inb(io_ports->feature_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_NSECT)
+			tf->hob_nsect   = tf_inb(io_ports->nsect_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAL)
+			tf->hob_lbal    = tf_inb(io_ports->lbal_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAM)
+			tf->hob_lbam    = tf_inb(io_ports->lbam_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAH)
+			tf->hob_lbah    = tf_inb(io_ports->lbah_addr);
+	}
+}
+
 /*
  * Some localbus EIDE interfaces require a special access sequence
  * when using 32-bit I/O instructions to transfer data.  We call this
@@ -182,115 +227,112 @@ void SELECT_MASK (ide_drive_t *drive, int mask)
  * of the sector count register location, with interrupts disabled
  * to ensure that the reads all happen together.
  */
-static void ata_vlb_sync(ide_drive_t *drive, unsigned long port)
+static void ata_vlb_sync(unsigned long port)
 {
-	(void) HWIF(drive)->INB(port);
-	(void) HWIF(drive)->INB(port);
-	(void) HWIF(drive)->INB(port);
+	(void)inb(port);
+	(void)inb(port);
+	(void)inb(port);
 }
 
 /*
  * This is used for most PIO data transfers *from* the IDE interface
+ *
+ * These routines will round up any request for an odd number of bytes,
+ * so if an odd len is specified, be sure that there's at least one
+ * extra byte allocated for the buffer.
  */
-static void ata_input_data(ide_drive_t *drive, void *buffer, u32 wcount)
+static void ata_input_data(ide_drive_t *drive, struct request *rq,
+			   void *buf, unsigned int len)
 {
-	ide_hwif_t *hwif	= HWIF(drive);
-	u8 io_32bit		= drive->io_32bit;
+	ide_hwif_t *hwif = drive->hwif;
+	struct ide_io_ports *io_ports = &hwif->io_ports;
+	unsigned long data_addr = io_ports->data_addr;
+	u8 io_32bit = drive->io_32bit;
+	u8 mmio = (hwif->host_flags & IDE_HFLAG_MMIO) ? 1 : 0;
+
+	len++;
 
 	if (io_32bit) {
-		if (io_32bit & 2) {
-			unsigned long flags;
+		unsigned long uninitialized_var(flags);
 
+		if ((io_32bit & 2) && !mmio) {
 			local_irq_save(flags);
-			ata_vlb_sync(drive, hwif->io_ports[IDE_NSECTOR_OFFSET]);
-			hwif->INSL(hwif->io_ports[IDE_DATA_OFFSET], buffer,
-				   wcount);
+			ata_vlb_sync(io_ports->nsect_addr);
+		}
+
+		if (mmio)
+			__ide_mm_insl((void __iomem *)data_addr, buf, len / 4);
+		else
+			insl(data_addr, buf, len / 4);
+
+		if ((io_32bit & 2) && !mmio)
 			local_irq_restore(flags);
-		} else
-			hwif->INSL(hwif->io_ports[IDE_DATA_OFFSET], buffer,
-				   wcount);
-	} else
-		hwif->INSW(hwif->io_ports[IDE_DATA_OFFSET], buffer,
-			   wcount << 1);
+
+		if ((len & 3) >= 2) {
+			if (mmio)
+				__ide_mm_insw((void __iomem *)data_addr,
+						(u8 *)buf + (len & ~3), 1);
+			else
+				insw(data_addr, (u8 *)buf + (len & ~3), 1);
+		}
+	} else {
+		if (mmio)
+			__ide_mm_insw((void __iomem *)data_addr, buf, len / 2);
+		else
+			insw(data_addr, buf, len / 2);
+	}
 }
 
 /*
  * This is used for most PIO data transfers *to* the IDE interface
  */
-static void ata_output_data(ide_drive_t *drive, void *buffer, u32 wcount)
+static void ata_output_data(ide_drive_t *drive, struct request *rq,
+			    void *buf, unsigned int len)
 {
-	ide_hwif_t *hwif	= HWIF(drive);
-	u8 io_32bit		= drive->io_32bit;
+	ide_hwif_t *hwif = drive->hwif;
+	struct ide_io_ports *io_ports = &hwif->io_ports;
+	unsigned long data_addr = io_ports->data_addr;
+	u8 io_32bit = drive->io_32bit;
+	u8 mmio = (hwif->host_flags & IDE_HFLAG_MMIO) ? 1 : 0;
 
 	if (io_32bit) {
-		if (io_32bit & 2) {
-			unsigned long flags;
+		unsigned long uninitialized_var(flags);
 
+		if ((io_32bit & 2) && !mmio) {
 			local_irq_save(flags);
-			ata_vlb_sync(drive, hwif->io_ports[IDE_NSECTOR_OFFSET]);
-			hwif->OUTSL(hwif->io_ports[IDE_DATA_OFFSET], buffer,
-				    wcount);
-			local_irq_restore(flags);
-		} else
-			hwif->OUTSL(hwif->io_ports[IDE_DATA_OFFSET], buffer,
-				    wcount);
-	} else
-		hwif->OUTSW(hwif->io_ports[IDE_DATA_OFFSET], buffer,
-			    wcount << 1);
-}
-
-/*
- * The following routines are mainly used by the ATAPI drivers.
- *
- * These routines will round up any request for an odd number of bytes,
- * so if an odd bytecount is specified, be sure that there's at least one
- * extra byte allocated for the buffer.
- */
-
-static void atapi_input_bytes(ide_drive_t *drive, void *buffer, u32 bytecount)
-{
-	ide_hwif_t *hwif = HWIF(drive);
+			ata_vlb_sync(io_ports->nsect_addr);
+		}
 
-	++bytecount;
-#if defined(CONFIG_ATARI) || defined(CONFIG_Q40)
-	if (MACH_IS_ATARI || MACH_IS_Q40) {
-		/* Atari has a byte-swapped IDE interface */
-		insw_swapw(hwif->io_ports[IDE_DATA_OFFSET], buffer,
-			   bytecount / 2);
-		return;
-	}
-#endif /* CONFIG_ATARI || CONFIG_Q40 */
-	hwif->ata_input_data(drive, buffer, bytecount / 4);
-	if ((bytecount & 0x03) >= 2)
-		hwif->INSW(hwif->io_ports[IDE_DATA_OFFSET],
-			   (u8 *)buffer + (bytecount & ~0x03), 1);
-}
+		if (mmio)
+			__ide_mm_outsl((void __iomem *)data_addr, buf, len / 4);
+		else
+			outsl(data_addr, buf, len / 4);
 
-static void atapi_output_bytes(ide_drive_t *drive, void *buffer, u32 bytecount)
-{
-	ide_hwif_t *hwif = HWIF(drive);
+		if ((io_32bit & 2) && !mmio)
+			local_irq_restore(flags);
 
-	++bytecount;
-#if defined(CONFIG_ATARI) || defined(CONFIG_Q40)
-	if (MACH_IS_ATARI || MACH_IS_Q40) {
-		/* Atari has a byte-swapped IDE interface */
-		outsw_swapw(hwif->io_ports[IDE_DATA_OFFSET], buffer,
-			    bytecount / 2);
-		return;
+		if ((len & 3) >= 2) {
+			if (mmio)
+				__ide_mm_outsw((void __iomem *)data_addr,
+						 (u8 *)buf + (len & ~3), 1);
+			else
+				outsw(data_addr, (u8 *)buf + (len & ~3), 1);
+		}
+	} else {
+		if (mmio)
+			__ide_mm_outsw((void __iomem *)data_addr, buf, len / 2);
+		else
+			outsw(data_addr, buf, len / 2);
 	}
-#endif /* CONFIG_ATARI || CONFIG_Q40 */
-	hwif->ata_output_data(drive, buffer, bytecount / 4);
-	if ((bytecount & 0x03) >= 2)
-		hwif->OUTSW(hwif->io_ports[IDE_DATA_OFFSET],
-			    (u8 *)buffer + (bytecount & ~0x03), 1);
 }
 
 void default_hwif_transport(ide_hwif_t *hwif)
 {
-	hwif->ata_input_data		= ata_input_data;
-	hwif->ata_output_data		= ata_output_data;
-	hwif->atapi_input_bytes		= atapi_input_bytes;
-	hwif->atapi_output_bytes	= atapi_output_bytes;
+	hwif->tf_load	  = ide_tf_load;
+	hwif->tf_read	  = ide_tf_read;
+
+	hwif->input_data  = ata_input_data;
+	hwif->output_data = ata_output_data;
 }
 
 void ide_fix_driveid (struct hd_driveid *id)
@@ -445,7 +487,7 @@ int drive_is_ready (ide_drive_t *drive)
 	 * an interrupt with another pci card/device.  We make no assumptions
 	 * about possible isa-pnp and pci-pnp issues yet.
 	 */
-	if (hwif->io_ports[IDE_CONTROL_OFFSET])
+	if (hwif->io_ports.ctl_addr)
 		stat = ide_read_altstatus(drive);
 	else
 		/* Note: this may clear a pending IRQ!! */
@@ -583,6 +625,8 @@ static const struct drive_list_entry ivb_list[] = {
 	{ "TSSTcorp CDDVDW SH-S202J"	, "SB01"	},
 	{ "TSSTcorp CDDVDW SH-S202N"	, "SB00"	},
 	{ "TSSTcorp CDDVDW SH-S202N"	, "SB01"	},
+	{ "TSSTcorp CDDVDW SH-S202H"	, "SB00"	},
+	{ "TSSTcorp CDDVDW SH-S202H"	, "SB01"	},
 	{ NULL				, NULL		}
 };
 
@@ -647,7 +691,7 @@ int ide_driveid_update(ide_drive_t *drive)
 	SELECT_MASK(drive, 1);
 	ide_set_irq(drive, 1);
 	msleep(50);
-	hwif->OUTB(WIN_IDENTIFY, hwif->io_ports[IDE_COMMAND_OFFSET]);
+	hwif->OUTBSYNC(drive, WIN_IDENTIFY, hwif->io_ports.command_addr);
 	timeout = jiffies + WAIT_WORSTCASE;
 	do {
 		if (time_after(jiffies, timeout)) {
@@ -674,7 +718,7 @@ int ide_driveid_update(ide_drive_t *drive)
 		local_irq_restore(flags);
 		return 0;
 	}
-	hwif->ata_input_data(drive, id, SECTOR_WORDS);
+	hwif->input_data(drive, NULL, id, SECTOR_SIZE);
 	(void)ide_read_status(drive);	/* clear drive IRQ */
 	local_irq_enable();
 	local_irq_restore(flags);
@@ -696,6 +740,7 @@ int ide_driveid_update(ide_drive_t *drive)
 int ide_config_drive_speed(ide_drive_t *drive, u8 speed)
 {
 	ide_hwif_t *hwif = drive->hwif;
+	struct ide_io_ports *io_ports = &hwif->io_ports;
 	int error = 0;
 	u8 stat;
 
@@ -734,10 +779,9 @@ int ide_config_drive_speed(ide_drive_t *drive, u8 speed)
 	SELECT_MASK(drive, 0);
 	udelay(1);
 	ide_set_irq(drive, 0);
-	hwif->OUTB(speed, hwif->io_ports[IDE_NSECTOR_OFFSET]);
-	hwif->OUTB(SETFEATURES_XFER, hwif->io_ports[IDE_FEATURE_OFFSET]);
-	hwif->OUTBSYNC(drive, WIN_SETFEATURES,
-		       hwif->io_ports[IDE_COMMAND_OFFSET]);
+	hwif->OUTB(speed, io_ports->nsect_addr);
+	hwif->OUTB(SETFEATURES_XFER, io_ports->feature_addr);
+	hwif->OUTBSYNC(drive, WIN_SETFEATURES, io_ports->command_addr);
 	if (drive->quirk_list == 2)
 		ide_set_irq(drive, 1);
 
@@ -845,7 +889,7 @@ void ide_execute_command(ide_drive_t *drive, u8 cmd, ide_handler_t *handler,
 
 	spin_lock_irqsave(&ide_lock, flags);
 	__ide_set_handler(drive, handler, timeout, expiry);
-	hwif->OUTBSYNC(drive, cmd, hwif->io_ports[IDE_COMMAND_OFFSET]);
+	hwif->OUTBSYNC(drive, cmd, hwif->io_ports.command_addr);
 	/*
 	 * Drive takes 400nS to respond, we must avoid the IRQ being
 	 * serviced before that.
@@ -855,9 +899,19 @@ void ide_execute_command(ide_drive_t *drive, u8 cmd, ide_handler_t *handler,
 	ndelay(400);
 	spin_unlock_irqrestore(&ide_lock, flags);
 }
-
 EXPORT_SYMBOL(ide_execute_command);
 
+void ide_execute_pkt_cmd(ide_drive_t *drive)
+{
+	ide_hwif_t *hwif = drive->hwif;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ide_lock, flags);
+	hwif->OUTBSYNC(drive, WIN_PACKETCMD, hwif->io_ports.command_addr);
+	ndelay(400);
+	spin_unlock_irqrestore(&ide_lock, flags);
+}
+EXPORT_SYMBOL_GPL(ide_execute_pkt_cmd);
 
 /* needed below */
 static ide_startstop_t do_reset1 (ide_drive_t *, int);
@@ -1029,6 +1083,7 @@ static ide_startstop_t do_reset1 (ide_drive_t *drive, int do_not_try_atapi)
 	unsigned long flags;
 	ide_hwif_t *hwif;
 	ide_hwgroup_t *hwgroup;
+	struct ide_io_ports *io_ports;
 	const struct ide_port_ops *port_ops;
 	u8 ctl;
 
@@ -1036,6 +1091,8 @@ static ide_startstop_t do_reset1 (ide_drive_t *drive, int do_not_try_atapi)
 	hwif = HWIF(drive);
 	hwgroup = HWGROUP(drive);
 
+	io_ports = &hwif->io_ports;
+
 	/* We must not reset with running handlers */
 	BUG_ON(hwgroup->handler != NULL);
 
@@ -1045,8 +1102,7 @@ static ide_startstop_t do_reset1 (ide_drive_t *drive, int do_not_try_atapi)
 		pre_reset(drive);
 		SELECT_DRIVE(drive);
 		udelay (20);
-		hwif->OUTBSYNC(drive, WIN_SRST,
-			       hwif->io_ports[IDE_COMMAND_OFFSET]);
+		hwif->OUTBSYNC(drive, WIN_SRST, io_ports->command_addr);
 		ndelay(400);
 		hwgroup->poll_timeout = jiffies + WAIT_WORSTCASE;
 		hwgroup->polling = 1;
@@ -1062,7 +1118,7 @@ static ide_startstop_t do_reset1 (ide_drive_t *drive, int do_not_try_atapi)
 	for (unit = 0; unit < MAX_DRIVES; ++unit)
 		pre_reset(&hwif->drives[unit]);
 
-	if (hwif->io_ports[IDE_CONTROL_OFFSET] == 0) {
+	if (io_ports->ctl_addr == 0) {
 		spin_unlock_irqrestore(&ide_lock, flags);
 		return ide_stopped;
 	}
@@ -1077,14 +1133,14 @@ static ide_startstop_t do_reset1 (ide_drive_t *drive, int do_not_try_atapi)
 	 * recover from reset very quickly, saving us the first 50ms wait time.
 	 */
 	/* set SRST and nIEN */
-	hwif->OUTBSYNC(drive, drive->ctl|6, hwif->io_ports[IDE_CONTROL_OFFSET]);
+	hwif->OUTBSYNC(drive, drive->ctl|6, io_ports->ctl_addr);
 	/* more than enough time */
 	udelay(10);
 	if (drive->quirk_list == 2)
 		ctl = drive->ctl;	/* clear SRST and nIEN */
 	else
 		ctl = drive->ctl | 2;	/* clear SRST, leave nIEN */
-	hwif->OUTBSYNC(drive, ctl, hwif->io_ports[IDE_CONTROL_OFFSET]);
+	hwif->OUTBSYNC(drive, ctl, io_ports->ctl_addr);
 	/* more than enough time */
 	udelay(10);
 	hwgroup->poll_timeout = jiffies + WAIT_WORSTCASE;
@@ -1129,7 +1185,7 @@ int ide_wait_not_busy(ide_hwif_t *hwif, unsigned long timeout)
 		 * about locking issues (2.5 work ?).
 		 */
 		mdelay(1);
-		stat = hwif->INB(hwif->io_ports[IDE_STATUS_OFFSET]);
+		stat = hwif->INB(hwif->io_ports.status_addr);
 		if ((stat & BUSY_STAT) == 0)
 			return 0;
 		/*
diff --git a/trunk/drivers/ide/ide-lib.c b/trunk/drivers/ide/ide-lib.c
index 6f04ea3e93a8..47af80df6872 100644
--- a/trunk/drivers/ide/ide-lib.c
+++ b/trunk/drivers/ide/ide-lib.c
@@ -487,7 +487,7 @@ static void ide_dump_sector(ide_drive_t *drive)
 	else
 		task.tf_flags = IDE_TFLAG_IN_LBA | IDE_TFLAG_IN_DEVICE;
 
-	ide_tf_read(drive, &task);
+	drive->hwif->tf_read(drive, &task);
 
 	if (lba48 || (tf->device & ATA_LBA))
 		printk(", LBAsect=%llu",
diff --git a/trunk/drivers/ide/ide-pnp.c b/trunk/drivers/ide/ide-pnp.c
index 10c20e9a5785..6a8953f68e9f 100644
--- a/trunk/drivers/ide/ide-pnp.c
+++ b/trunk/drivers/ide/ide-pnp.c
@@ -82,10 +82,7 @@ static void idepnp_remove(struct pnp_dev *dev)
 {
 	ide_hwif_t *hwif = pnp_get_drvdata(dev);
 
-	if (hwif)
-		ide_unregister(hwif->index);
-	else
-		printk(KERN_ERR "idepnp: Unable to remove device, please report.\n");
+	ide_unregister(hwif);
 
 	release_region(pnp_port_start(dev, 1), 1);
 	release_region(pnp_port_start(dev, 0), 8);
diff --git a/trunk/drivers/ide/ide-probe.c b/trunk/drivers/ide/ide-probe.c
index a4b65b321f51..099a0fe1745b 100644
--- a/trunk/drivers/ide/ide-probe.c
+++ b/trunk/drivers/ide/ide-probe.c
@@ -124,7 +124,7 @@ static inline void do_identify (ide_drive_t *drive, u8 cmd)
 
 	id = drive->id;
 	/* read 512 bytes of id info */
-	hwif->ata_input_data(drive, id, SECTOR_WORDS);
+	hwif->input_data(drive, NULL, id, SECTOR_SIZE);
 
 	drive->id_read = 1;
 	local_irq_enable();
@@ -264,6 +264,7 @@ static inline void do_identify (ide_drive_t *drive, u8 cmd)
 static int actual_try_to_identify (ide_drive_t *drive, u8 cmd)
 {
 	ide_hwif_t *hwif = HWIF(drive);
+	struct ide_io_ports *io_ports = &hwif->io_ports;
 	int use_altstatus = 0, rc;
 	unsigned long timeout;
 	u8 s = 0, a = 0;
@@ -271,7 +272,7 @@ static int actual_try_to_identify (ide_drive_t *drive, u8 cmd)
 	/* take a deep breath */
 	msleep(50);
 
-	if (hwif->io_ports[IDE_CONTROL_OFFSET]) {
+	if (io_ports->ctl_addr) {
 		a = ide_read_altstatus(drive);
 		s = ide_read_status(drive);
 		if ((a ^ s) & ~INDEX_STAT)
@@ -289,10 +290,10 @@ static int actual_try_to_identify (ide_drive_t *drive, u8 cmd)
 	 */
 	if ((cmd == WIN_PIDENTIFY))
 		/* disable dma & overlap */
-		hwif->OUTB(0, hwif->io_ports[IDE_FEATURE_OFFSET]);
+		hwif->OUTB(0, io_ports->feature_addr);
 
 	/* ask drive for ID */
-	hwif->OUTB(cmd, hwif->io_ports[IDE_COMMAND_OFFSET]);
+	hwif->OUTBSYNC(drive, cmd, io_ports->command_addr);
 
 	timeout = ((cmd == WIN_IDENTIFY) ? WAIT_WORSTCASE : WAIT_PIDENTIFY) / 2;
 	timeout += jiffies;
@@ -353,7 +354,7 @@ static int try_to_identify (ide_drive_t *drive, u8 cmd)
 	 * interrupts during the identify-phase that
 	 * the irq handler isn't expecting.
 	 */
-	if (hwif->io_ports[IDE_CONTROL_OFFSET]) {
+	if (hwif->io_ports.ctl_addr) {
 		if (!hwif->irq) {
 			autoprobe = 1;
 			cookie = probe_irq_on();
@@ -393,7 +394,7 @@ static int ide_busy_sleep(ide_hwif_t *hwif)
 
 	do {
 		msleep(50);
-		stat = hwif->INB(hwif->io_ports[IDE_STATUS_OFFSET]);
+		stat = hwif->INB(hwif->io_ports.status_addr);
 		if ((stat & BUSY_STAT) == 0)
 			return 0;
 	} while (time_before(jiffies, timeout));
@@ -425,6 +426,7 @@ static int ide_busy_sleep(ide_hwif_t *hwif)
 static int do_probe (ide_drive_t *drive, u8 cmd)
 {
 	ide_hwif_t *hwif = HWIF(drive);
+	struct ide_io_ports *io_ports = &hwif->io_ports;
 	int rc;
 	u8 stat;
 
@@ -445,7 +447,7 @@ static int do_probe (ide_drive_t *drive, u8 cmd)
 	msleep(50);
 	SELECT_DRIVE(drive);
 	msleep(50);
-	if (hwif->INB(hwif->io_ports[IDE_SELECT_OFFSET]) != drive->select.all &&
+	if (hwif->INB(io_ports->device_addr) != drive->select.all &&
 	    !drive->present) {
 		if (drive->select.b.unit != 0) {
 			/* exit with drive0 selected */
@@ -472,17 +474,13 @@ static int do_probe (ide_drive_t *drive, u8 cmd)
 		if (stat == (BUSY_STAT | READY_STAT))
 			return 4;
 
-		if ((rc == 1 && cmd == WIN_PIDENTIFY) &&
-			((drive->autotune == IDE_TUNE_DEFAULT) ||
-			(drive->autotune == IDE_TUNE_AUTO))) {
+		if (rc == 1 && cmd == WIN_PIDENTIFY) {
 			printk(KERN_ERR "%s: no response (status = 0x%02x), "
 					"resetting drive\n", drive->name, stat);
 			msleep(50);
-			hwif->OUTB(drive->select.all,
-				   hwif->io_ports[IDE_SELECT_OFFSET]);
+			hwif->OUTB(drive->select.all, io_ports->device_addr);
 			msleep(50);
-			hwif->OUTB(WIN_SRST,
-				   hwif->io_ports[IDE_COMMAND_OFFSET]);
+			hwif->OUTBSYNC(drive, WIN_SRST, io_ports->command_addr);
 			(void)ide_busy_sleep(hwif);
 			rc = try_to_identify(drive, cmd);
 		}
@@ -518,7 +516,7 @@ static void enable_nest (ide_drive_t *drive)
 	printk("%s: enabling %s -- ", hwif->name, drive->id->model);
 	SELECT_DRIVE(drive);
 	msleep(50);
-	hwif->OUTB(EXABYTE_ENABLE_NEST, hwif->io_ports[IDE_COMMAND_OFFSET]);
+	hwif->OUTBSYNC(drive, EXABYTE_ENABLE_NEST, hwif->io_ports.command_addr);
 
 	if (ide_busy_sleep(hwif)) {
 		printk(KERN_CONT "failed (timeout)\n");
@@ -800,14 +798,9 @@ static int ide_probe_port(ide_hwif_t *hwif)
 		if (drive->present)
 			rc = 0;
 	}
-	if (hwif->io_ports[IDE_CONTROL_OFFSET] && hwif->reset) {
-		printk(KERN_WARNING "%s: reset\n", hwif->name);
-		hwif->OUTB(12, hwif->io_ports[IDE_CONTROL_OFFSET]);
-		udelay(10);
-		hwif->OUTB(8, hwif->io_ports[IDE_CONTROL_OFFSET]);
-		(void)ide_busy_sleep(hwif);
-	}
+
 	local_irq_restore(flags);
+
 	/*
 	 * Use cached IRQ number. It might be (and is...) changed by probe
 	 * code above
@@ -834,12 +827,7 @@ static void ide_port_tune_devices(ide_hwif_t *hwif)
 		ide_drive_t *drive = &hwif->drives[unit];
 
 		if (drive->present) {
-			if (drive->autotune == IDE_TUNE_AUTO)
-				ide_set_max_pio(drive);
-
-			if (drive->autotune != IDE_TUNE_DEFAULT &&
-			    drive->autotune != IDE_TUNE_AUTO)
-				continue;
+			ide_set_max_pio(drive);
 
 			drive->nice1 = 1;
 
@@ -994,6 +982,7 @@ static void ide_port_setup_devices(ide_hwif_t *hwif)
  */
 static int init_irq (ide_hwif_t *hwif)
 {
+	struct ide_io_ports *io_ports = &hwif->io_ports;
 	unsigned int index;
 	ide_hwgroup_t *hwgroup;
 	ide_hwif_t *match = NULL;
@@ -1077,9 +1066,9 @@ static int init_irq (ide_hwif_t *hwif)
 		if (IDE_CHIPSET_IS_PCI(hwif->chipset))
 			sa = IRQF_SHARED;
 
-		if (hwif->io_ports[IDE_CONTROL_OFFSET])
+		if (io_ports->ctl_addr)
 			/* clear nIEN */
-			hwif->OUTB(0x08, hwif->io_ports[IDE_CONTROL_OFFSET]);
+			hwif->OUTB(0x08, io_ports->ctl_addr);
 
 		if (request_irq(hwif->irq,&ide_intr,sa,hwif->name,hwgroup))
 	       		goto out_unlink;
@@ -1095,12 +1084,11 @@ static int init_irq (ide_hwif_t *hwif)
 
 #if !defined(__mc68000__)
 	printk("%s at 0x%03lx-0x%03lx,0x%03lx on irq %d", hwif->name,
-		hwif->io_ports[IDE_DATA_OFFSET],
-		hwif->io_ports[IDE_DATA_OFFSET]+7,
-		hwif->io_ports[IDE_CONTROL_OFFSET], hwif->irq);
+		io_ports->data_addr, io_ports->status_addr,
+		io_ports->ctl_addr, hwif->irq);
 #else
 	printk("%s at 0x%08lx on irq %d", hwif->name,
-		hwif->io_ports[IDE_DATA_OFFSET], hwif->irq);
+		io_ports->data_addr, hwif->irq);
 #endif /* __mc68000__ */
 	if (match)
 		printk(" (%sed with %s)",
@@ -1242,8 +1230,8 @@ static int hwif_init(ide_hwif_t *hwif)
 	int old_irq;
 
 	if (!hwif->irq) {
-		if (!(hwif->irq = ide_default_irq(hwif->io_ports[IDE_DATA_OFFSET])))
-		{
+		hwif->irq = ide_default_irq(hwif->io_ports.data_addr);
+		if (!hwif->irq) {
 			printk("%s: DISABLED, NO IRQ\n", hwif->name);
 			return 0;
 		}
@@ -1272,7 +1260,8 @@ static int hwif_init(ide_hwif_t *hwif)
 	 *	It failed to initialise. Find the default IRQ for 
 	 *	this port and try that.
 	 */
-	if (!(hwif->irq = ide_default_irq(hwif->io_ports[IDE_DATA_OFFSET]))) {
+	hwif->irq = ide_default_irq(hwif->io_ports.data_addr);
+	if (!hwif->irq) {
 		printk("%s: Disabled unable to get IRQ %d.\n",
 			hwif->name, old_irq);
 		goto out;
@@ -1336,8 +1325,6 @@ static void ide_port_init_devices(ide_hwif_t *hwif)
 			drive->unmask = 1;
 		if (hwif->host_flags & IDE_HFLAG_NO_UNMASK_IRQS)
 			drive->no_unmask = 1;
-		if ((hwif->host_flags & IDE_HFLAG_NO_AUTOTUNE) == 0)
-			drive->autotune = 1;
 	}
 
 	if (port_ops && port_ops->port_init_devs)
@@ -1518,13 +1505,20 @@ int ide_device_add_all(u8 *idx, const struct ide_port_info *d)
 	int i, rc = 0;
 
 	for (i = 0; i < MAX_HWIFS; i++) {
-		if (d == NULL || idx[i] == 0xff) {
+		if (idx[i] == 0xff) {
 			mate = NULL;
 			continue;
 		}
 
 		hwif = &ide_hwifs[idx[i]];
 
+		ide_port_apply_params(hwif);
+
+		if (d == NULL) {
+			mate = NULL;
+			continue;
+		}
+
 		if (d->chipset != ide_etrax100 && (i & 1) && mate) {
 			hwif->mate = mate;
 			mate->mate = hwif;
@@ -1621,6 +1615,7 @@ EXPORT_SYMBOL_GPL(ide_device_add);
 
 void ide_port_scan(ide_hwif_t *hwif)
 {
+	ide_port_apply_params(hwif);
 	ide_port_cable_detect(hwif);
 	ide_port_init_devices(hwif);
 
diff --git a/trunk/drivers/ide/ide-proc.c b/trunk/drivers/ide/ide-proc.c
index d9d98ac85b29..8d6ad812a014 100644
--- a/trunk/drivers/ide/ide-proc.c
+++ b/trunk/drivers/ide/ide-proc.c
@@ -786,14 +786,6 @@ void ide_proc_register_port(ide_hwif_t *hwif)
 	}
 }
 
-#ifdef CONFIG_BLK_DEV_IDEPCI
-void ide_pci_create_host_proc(const char *name, get_info_t *get_info)
-{
-	create_proc_info_entry(name, 0, proc_ide_root, get_info);
-}
-EXPORT_SYMBOL_GPL(ide_pci_create_host_proc);
-#endif
-
 void ide_proc_unregister_port(ide_hwif_t *hwif)
 {
 	if (hwif->proc) {
@@ -830,6 +822,7 @@ static int ide_drivers_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations ide_drivers_operations = {
+	.owner		= THIS_MODULE,
 	.open		= ide_drivers_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -838,16 +831,12 @@ static const struct file_operations ide_drivers_operations = {
 
 void proc_ide_create(void)
 {
-	struct proc_dir_entry *entry;
-
 	proc_ide_root = proc_mkdir("ide", NULL);
 
 	if (!proc_ide_root)
 		return;
 
-	entry = create_proc_entry("drivers", 0, proc_ide_root);
-	if (entry)
-		entry->proc_fops = &ide_drivers_operations;
+	proc_create("drivers", 0, proc_ide_root, &ide_drivers_operations);
 }
 
 void proc_ide_destroy(void)
diff --git a/trunk/drivers/ide/ide-tape.c b/trunk/drivers/ide/ide-tape.c
index d3d8b8d5157c..1e1f26331a24 100644
--- a/trunk/drivers/ide/ide-tape.c
+++ b/trunk/drivers/ide/ide-tape.c
@@ -72,26 +72,6 @@ enum {
 #endif
 
 /**************************** Tunable parameters *****************************/
-
-
-/*
- * Pipelined mode parameters.
- *
- * We try to use the minimum number of stages which is enough to keep the tape
- * constantly streaming. To accomplish that, we implement a feedback loop around
- * the maximum number of stages:
- *
- * We start from MIN maximum stages (we will not even use MIN stages if we don't
- * need them), increment it by RATE*(MAX-MIN) whenever we sense that the
- * pipeline is empty, until we reach the optimum value or until we reach MAX.
- *
- * Setting the following parameter to 0 is illegal: the pipelined mode cannot be
- * disabled (idetape_calculate_speeds() divides by tape->max_stages.)
- */
-#define IDETAPE_MIN_PIPELINE_STAGES	  1
-#define IDETAPE_MAX_PIPELINE_STAGES	400
-#define IDETAPE_INCREASE_STAGES_RATE	 20
-
 /*
  * After each failed packet command we issue a request sense command and retry
  * the packet command IDETAPE_MAX_PC_RETRIES times.
@@ -224,28 +204,17 @@ enum {
 	/* 0 When the tape position is unknown */
 	IDETAPE_FLAG_ADDRESS_VALID	= (1 <<	1),
 	/* Device already opened */
-	IDETAPE_FLAG_BUSY			= (1 << 2),
-	/* Error detected in a pipeline stage */
-	IDETAPE_FLAG_PIPELINE_ERR	= (1 <<	3),
+	IDETAPE_FLAG_BUSY		= (1 << 2),
 	/* Attempt to auto-detect the current user block size */
-	IDETAPE_FLAG_DETECT_BS		= (1 << 4),
+	IDETAPE_FLAG_DETECT_BS		= (1 << 3),
 	/* Currently on a filemark */
-	IDETAPE_FLAG_FILEMARK		= (1 << 5),
+	IDETAPE_FLAG_FILEMARK		= (1 << 4),
 	/* DRQ interrupt device */
-	IDETAPE_FLAG_DRQ_INTERRUPT	= (1 << 6),
-	/* pipeline active */
-	IDETAPE_FLAG_PIPELINE_ACTIVE	= (1 << 7),
+	IDETAPE_FLAG_DRQ_INTERRUPT	= (1 << 5),
 	/* 0 = no tape is loaded, so we don't rewind after ejecting */
-	IDETAPE_FLAG_MEDIUM_PRESENT	= (1 << 8),
+	IDETAPE_FLAG_MEDIUM_PRESENT	= (1 << 6),
 };
 
-/* A pipeline stage. */
-typedef struct idetape_stage_s {
-	struct request rq;			/* The corresponding request */
-	struct idetape_bh *bh;			/* The data buffers */
-	struct idetape_stage_s *next;		/* Pointer to the next stage */
-} idetape_stage_t;
-
 /*
  * Most of our global data which we need to save even as we leave the driver due
  * to an interrupt or a timer event is stored in the struct defined below.
@@ -289,9 +258,7 @@ typedef struct ide_tape_obj {
 	 * While polling for DSC we use postponed_rq to postpone the current
 	 * request so that ide.c will be able to service pending requests on the
 	 * other device. Note that at most we will have only one DSC (usually
-	 * data transfer) request in the device request queue. Additional
-	 * requests can be queued in our internal pipeline, but they will be
-	 * visible to ide.c only one at a time.
+	 * data transfer) request in the device request queue.
 	 */
 	struct request *postponed_rq;
 	/* The time in which we started polling for DSC */
@@ -331,43 +298,20 @@ typedef struct ide_tape_obj {
 	 * At most, there is only one ide-tape originated data transfer request
 	 * in the device request queue. This allows ide.c to easily service
 	 * requests from the other device when we postpone our active request.
-	 * In the pipelined operation mode, we use our internal pipeline
-	 * structure to hold more data requests. The data buffer size is chosen
-	 * based on the tape's recommendation.
 	 */
-	/* ptr to the request which is waiting in the device request queue */
-	struct request *active_data_rq;
+
 	/* Data buffer size chosen based on the tape's recommendation */
-	int stage_size;
-	idetape_stage_t *merge_stage;
-	int merge_stage_size;
+	int buffer_size;
+	/* merge buffer */
+	struct idetape_bh *merge_bh;
+	/* size of the merge buffer */
+	int merge_bh_size;
+	/* pointer to current buffer head within the merge buffer */
 	struct idetape_bh *bh;
 	char *b_data;
 	int b_count;
 
-	/*
-	 * Pipeline parameters.
-	 *
-	 * To accomplish non-pipelined mode, we simply set the following
-	 * variables to zero (or NULL, where appropriate).
-	 */
-	/* Number of currently used stages */
-	int nr_stages;
-	/* Number of pending stages */
-	int nr_pending_stages;
-	/* We will not allocate more than this number of stages */
-	int max_stages, min_pipeline, max_pipeline;
-	/* The first stage which will be removed from the pipeline */
-	idetape_stage_t *first_stage;
-	/* The currently active stage */
-	idetape_stage_t *active_stage;
-	/* Will be serviced after the currently active request */
-	idetape_stage_t *next_stage;
-	/* New requests will be added to the pipeline here */
-	idetape_stage_t *last_stage;
-	/* Optional free stage which we can use */
-	idetape_stage_t *cache_stage;
-	int pages_per_stage;
+	int pages_per_buffer;
 	/* Wasted space in each stage */
 	int excess_bh_size;
 
@@ -388,45 +332,6 @@ typedef struct ide_tape_obj {
 	/* the tape is write protected (hardware or opened as read-only) */
 	char write_prot;
 
-	/*
-	 * Limit the number of times a request can be postponed, to avoid an
-	 * infinite postpone deadlock.
-	 */
-	int postpone_cnt;
-
-	/*
-	 * Measures number of frames:
-	 *
-	 * 1. written/read to/from the driver pipeline (pipeline_head).
-	 * 2. written/read to/from the tape buffers (idetape_bh).
-	 * 3. written/read by the tape to/from the media (tape_head).
-	 */
-	int pipeline_head;
-	int buffer_head;
-	int tape_head;
-	int last_tape_head;
-
-	/* Speed control at the tape buffers input/output */
-	unsigned long insert_time;
-	int insert_size;
-	int insert_speed;
-	int max_insert_speed;
-	int measure_insert_time;
-
-	/* Speed regulation negative feedback loop */
-	int speed_control;
-	int pipeline_head_speed;
-	int controlled_pipeline_head_speed;
-	int uncontrolled_pipeline_head_speed;
-	int controlled_last_pipeline_head;
-	unsigned long uncontrolled_pipeline_head_time;
-	unsigned long controlled_pipeline_head_time;
-	int controlled_previous_pipeline_head;
-	int uncontrolled_previous_pipeline_head;
-	unsigned long controlled_previous_head_time;
-	unsigned long uncontrolled_previous_head_time;
-	int restart_speed_control_req;
-
 	u32 debug_mask;
 } idetape_tape_t;
 
@@ -490,13 +395,13 @@ static void idetape_input_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
 		if (bh == NULL) {
 			printk(KERN_ERR "ide-tape: bh == NULL in "
 				"idetape_input_buffers\n");
-			ide_atapi_discard_data(drive, bcount);
+			ide_pad_transfer(drive, 0, bcount);
 			return;
 		}
 		count = min(
 			(unsigned int)(bh->b_size - atomic_read(&bh->b_count)),
 			bcount);
-		HWIF(drive)->atapi_input_bytes(drive, bh->b_data +
+		drive->hwif->input_data(drive, NULL, bh->b_data +
 					atomic_read(&bh->b_count), count);
 		bcount -= count;
 		atomic_add(count, &bh->b_count);
@@ -522,7 +427,7 @@ static void idetape_output_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
 			return;
 		}
 		count = min((unsigned int)pc->b_count, (unsigned int)bcount);
-		HWIF(drive)->atapi_output_bytes(drive, pc->b_data, count);
+		drive->hwif->output_data(drive, NULL, pc->b_data, count);
 		bcount -= count;
 		pc->b_data += count;
 		pc->b_count -= count;
@@ -674,128 +579,36 @@ static void idetape_analyze_error(ide_drive_t *drive, u8 *sense)
 	}
 }
 
-static void idetape_activate_next_stage(ide_drive_t *drive)
+/* Free data buffers completely. */
+static void ide_tape_kfree_buffer(idetape_tape_t *tape)
 {
-	idetape_tape_t *tape = drive->driver_data;
-	idetape_stage_t *stage = tape->next_stage;
-	struct request *rq = &stage->rq;
+	struct idetape_bh *prev_bh, *bh = tape->merge_bh;
 
-	debug_log(DBG_PROCS, "Enter %s\n", __func__);
+	while (bh) {
+		u32 size = bh->b_size;
 
-	if (stage == NULL) {
-		printk(KERN_ERR "ide-tape: bug: Trying to activate a non"
-				" existing stage\n");
-		return;
-	}
+		while (size) {
+			unsigned int order = fls(size >> PAGE_SHIFT)-1;
 
-	rq->rq_disk = tape->disk;
-	rq->buffer = NULL;
-	rq->special = (void *)stage->bh;
-	tape->active_data_rq = rq;
-	tape->active_stage = stage;
-	tape->next_stage = stage->next;
-}
-
-/* Free a stage along with its related buffers completely. */
-static void __idetape_kfree_stage(idetape_stage_t *stage)
-{
-	struct idetape_bh *prev_bh, *bh = stage->bh;
-	int size;
-
-	while (bh != NULL) {
-		if (bh->b_data != NULL) {
-			size = (int) bh->b_size;
-			while (size > 0) {
-				free_page((unsigned long) bh->b_data);
-				size -= PAGE_SIZE;
-				bh->b_data += PAGE_SIZE;
-			}
+			if (bh->b_data)
+				free_pages((unsigned long)bh->b_data, order);
+
+			size &= (order-1);
+			bh->b_data += (1 << order) * PAGE_SIZE;
 		}
 		prev_bh = bh;
 		bh = bh->b_reqnext;
 		kfree(prev_bh);
 	}
-	kfree(stage);
-}
-
-static void idetape_kfree_stage(idetape_tape_t *tape, idetape_stage_t *stage)
-{
-	__idetape_kfree_stage(stage);
-}
-
-/*
- * Remove tape->first_stage from the pipeline. The caller should avoid race
- * conditions.
- */
-static void idetape_remove_stage_head(ide_drive_t *drive)
-{
-	idetape_tape_t *tape = drive->driver_data;
-	idetape_stage_t *stage;
-
-	debug_log(DBG_PROCS, "Enter %s\n", __func__);
-
-	if (tape->first_stage == NULL) {
-		printk(KERN_ERR "ide-tape: bug: tape->first_stage is NULL\n");
-		return;
-	}
-	if (tape->active_stage == tape->first_stage) {
-		printk(KERN_ERR "ide-tape: bug: Trying to free our active "
-				"pipeline stage\n");
-		return;
-	}
-	stage = tape->first_stage;
-	tape->first_stage = stage->next;
-	idetape_kfree_stage(tape, stage);
-	tape->nr_stages--;
-	if (tape->first_stage == NULL) {
-		tape->last_stage = NULL;
-		if (tape->next_stage != NULL)
-			printk(KERN_ERR "ide-tape: bug: tape->next_stage !="
-					" NULL\n");
-		if (tape->nr_stages)
-			printk(KERN_ERR "ide-tape: bug: nr_stages should be 0 "
-					"now\n");
-	}
+	kfree(tape->merge_bh);
 }
 
-/*
- * This will free all the pipeline stages starting from new_last_stage->next
- * to the end of the list, and point tape->last_stage to new_last_stage.
- */
-static void idetape_abort_pipeline(ide_drive_t *drive,
-				   idetape_stage_t *new_last_stage)
-{
-	idetape_tape_t *tape = drive->driver_data;
-	idetape_stage_t *stage = new_last_stage->next;
-	idetape_stage_t *nstage;
-
-	debug_log(DBG_PROCS, "%s: Enter %s\n", tape->name, __func__);
-
-	while (stage) {
-		nstage = stage->next;
-		idetape_kfree_stage(tape, stage);
-		--tape->nr_stages;
-		--tape->nr_pending_stages;
-		stage = nstage;
-	}
-	if (new_last_stage)
-		new_last_stage->next = NULL;
-	tape->last_stage = new_last_stage;
-	tape->next_stage = NULL;
-}
-
-/*
- * Finish servicing a request and insert a pending pipeline request into the
- * main device queue.
- */
 static int idetape_end_request(ide_drive_t *drive, int uptodate, int nr_sects)
 {
 	struct request *rq = HWGROUP(drive)->rq;
 	idetape_tape_t *tape = drive->driver_data;
 	unsigned long flags;
 	int error;
-	int remove_stage = 0;
-	idetape_stage_t *active_stage;
 
 	debug_log(DBG_PROCS, "Enter %s\n", __func__);
 
@@ -815,58 +628,8 @@ static int idetape_end_request(ide_drive_t *drive, int uptodate, int nr_sects)
 
 	spin_lock_irqsave(&tape->lock, flags);
 
-	/* The request was a pipelined data transfer request */
-	if (tape->active_data_rq == rq) {
-		active_stage = tape->active_stage;
-		tape->active_stage = NULL;
-		tape->active_data_rq = NULL;
-		tape->nr_pending_stages--;
-		if (rq->cmd[0] & REQ_IDETAPE_WRITE) {
-			remove_stage = 1;
-			if (error) {
-				set_bit(IDETAPE_FLAG_PIPELINE_ERR,
-					&tape->flags);
-				if (error == IDETAPE_ERROR_EOD)
-					idetape_abort_pipeline(drive,
-								active_stage);
-			}
-		} else if (rq->cmd[0] & REQ_IDETAPE_READ) {
-			if (error == IDETAPE_ERROR_EOD) {
-				set_bit(IDETAPE_FLAG_PIPELINE_ERR,
-					&tape->flags);
-				idetape_abort_pipeline(drive, active_stage);
-			}
-		}
-		if (tape->next_stage != NULL) {
-			idetape_activate_next_stage(drive);
-
-			/* Insert the next request into the request queue. */
-			(void)ide_do_drive_cmd(drive, tape->active_data_rq,
-						ide_end);
-		} else if (!error) {
-			/*
-			 * This is a part of the feedback loop which tries to
-			 * find the optimum number of stages. We are starting
-			 * from a minimum maximum number of stages, and if we
-			 * sense that the pipeline is empty, we try to increase
-			 * it, until we reach the user compile time memory
-			 * limit.
-			 */
-			int i = (tape->max_pipeline - tape->min_pipeline) / 10;
-
-			tape->max_stages += max(i, 1);
-			tape->max_stages = max(tape->max_stages,
-						tape->min_pipeline);
-			tape->max_stages = min(tape->max_stages,
-						tape->max_pipeline);
-		}
-	}
 	ide_end_drive_cmd(drive, 0, 0);
 
-	if (remove_stage)
-		idetape_remove_stage_head(drive);
-	if (tape->active_data_rq == NULL)
-		clear_bit(IDETAPE_FLAG_PIPELINE_ACTIVE, &tape->flags);
 	spin_unlock_irqrestore(&tape->lock, flags);
 	return 0;
 }
@@ -899,7 +662,7 @@ static void idetape_create_request_sense_cmd(struct ide_atapi_pc *pc)
 
 static void idetape_init_rq(struct request *rq, u8 cmd)
 {
-	memset(rq, 0, sizeof(*rq));
+	blk_rq_init(NULL, rq);
 	rq->cmd_type = REQ_TYPE_SPECIAL;
 	rq->cmd[0] = cmd;
 }
@@ -1083,10 +846,10 @@ static ide_startstop_t idetape_pc_intr(ide_drive_t *drive)
 		return ide_do_reset(drive);
 	}
 	/* Get the number of bytes to transfer on this interrupt. */
-	bcount = (hwif->INB(hwif->io_ports[IDE_BCOUNTH_OFFSET]) << 8) |
-		  hwif->INB(hwif->io_ports[IDE_BCOUNTL_OFFSET]);
+	bcount = (hwif->INB(hwif->io_ports.lbah_addr) << 8) |
+		  hwif->INB(hwif->io_ports.lbam_addr);
 
-	ireason = hwif->INB(hwif->io_ports[IDE_IREASON_OFFSET]);
+	ireason = hwif->INB(hwif->io_ports.nsect_addr);
 
 	if (ireason & CD) {
 		printk(KERN_ERR "ide-tape: CoD != 0 in %s\n", __func__);
@@ -1108,7 +871,7 @@ static ide_startstop_t idetape_pc_intr(ide_drive_t *drive)
 				printk(KERN_ERR "ide-tape: The tape wants to "
 					"send us more data than expected "
 					"- discarding data\n");
-				ide_atapi_discard_data(drive, bcount);
+				ide_pad_transfer(drive, 0, bcount);
 				ide_set_handler(drive, &idetape_pc_intr,
 						IDETAPE_WAIT_CMD, NULL);
 				return ide_started;
@@ -1117,16 +880,16 @@ static ide_startstop_t idetape_pc_intr(ide_drive_t *drive)
 				"data than expected - allowing transfer\n");
 		}
 		iobuf = &idetape_input_buffers;
-		xferfunc = hwif->atapi_input_bytes;
+		xferfunc = hwif->input_data;
 	} else {
 		iobuf = &idetape_output_buffers;
-		xferfunc = hwif->atapi_output_bytes;
+		xferfunc = hwif->output_data;
 	}
 
 	if (pc->bh)
 		iobuf(drive, pc, bcount);
 	else
-		xferfunc(drive, pc->cur_pos, bcount);
+		xferfunc(drive, NULL, pc->cur_pos, bcount);
 
 	/* Update the current position */
 	pc->xferred += bcount;
@@ -1190,12 +953,12 @@ static ide_startstop_t idetape_transfer_pc(ide_drive_t *drive)
 				"yet DRQ isn't asserted\n");
 		return startstop;
 	}
-	ireason = hwif->INB(hwif->io_ports[IDE_IREASON_OFFSET]);
+	ireason = hwif->INB(hwif->io_ports.nsect_addr);
 	while (retries-- && ((ireason & CD) == 0 || (ireason & IO))) {
 		printk(KERN_ERR "ide-tape: (IO,CoD != (0,1) while issuing "
 				"a packet command, retrying\n");
 		udelay(100);
-		ireason = hwif->INB(hwif->io_ports[IDE_IREASON_OFFSET]);
+		ireason = hwif->INB(hwif->io_ports.nsect_addr);
 		if (retries == 0) {
 			printk(KERN_ERR "ide-tape: (IO,CoD != (0,1) while "
 					"issuing a packet command, ignoring\n");
@@ -1216,7 +979,8 @@ static ide_startstop_t idetape_transfer_pc(ide_drive_t *drive)
 		hwif->dma_ops->dma_start(drive);
 #endif
 	/* Send the actual packet */
-	HWIF(drive)->atapi_output_bytes(drive, pc->c, 12);
+	hwif->output_data(drive, NULL, pc->c, 12);
+
 	return ide_started;
 }
 
@@ -1292,7 +1056,7 @@ static ide_startstop_t idetape_issue_pc(ide_drive_t *drive,
 				    IDETAPE_WAIT_CMD, NULL);
 		return ide_started;
 	} else {
-		hwif->OUTB(WIN_PACKETCMD, hwif->io_ports[IDE_COMMAND_OFFSET]);
+		ide_execute_pkt_cmd(drive);
 		return idetape_transfer_pc(drive);
 	}
 }
@@ -1335,69 +1099,6 @@ static void idetape_create_mode_sense_cmd(struct ide_atapi_pc *pc, u8 page_code)
 	pc->idetape_callback = &idetape_pc_callback;
 }
 
-static void idetape_calculate_speeds(ide_drive_t *drive)
-{
-	idetape_tape_t *tape = drive->driver_data;
-
-	if (time_after(jiffies,
-			tape->controlled_pipeline_head_time + 120 * HZ)) {
-		tape->controlled_previous_pipeline_head =
-			tape->controlled_last_pipeline_head;
-		tape->controlled_previous_head_time =
-			tape->controlled_pipeline_head_time;
-		tape->controlled_last_pipeline_head = tape->pipeline_head;
-		tape->controlled_pipeline_head_time = jiffies;
-	}
-	if (time_after(jiffies, tape->controlled_pipeline_head_time + 60 * HZ))
-		tape->controlled_pipeline_head_speed = (tape->pipeline_head -
-				tape->controlled_last_pipeline_head) * 32 * HZ /
-				(jiffies - tape->controlled_pipeline_head_time);
-	else if (time_after(jiffies, tape->controlled_previous_head_time))
-		tape->controlled_pipeline_head_speed = (tape->pipeline_head -
-				tape->controlled_previous_pipeline_head) * 32 *
-			HZ / (jiffies - tape->controlled_previous_head_time);
-
-	if (tape->nr_pending_stages < tape->max_stages/*- 1 */) {
-		/* -1 for read mode error recovery */
-		if (time_after(jiffies, tape->uncontrolled_previous_head_time +
-					10 * HZ)) {
-			tape->uncontrolled_pipeline_head_time = jiffies;
-			tape->uncontrolled_pipeline_head_speed =
-				(tape->pipeline_head -
-				 tape->uncontrolled_previous_pipeline_head) *
-				32 * HZ / (jiffies -
-					tape->uncontrolled_previous_head_time);
-		}
-	} else {
-		tape->uncontrolled_previous_head_time = jiffies;
-		tape->uncontrolled_previous_pipeline_head = tape->pipeline_head;
-		if (time_after(jiffies, tape->uncontrolled_pipeline_head_time +
-					30 * HZ))
-			tape->uncontrolled_pipeline_head_time = jiffies;
-
-	}
-	tape->pipeline_head_speed = max(tape->uncontrolled_pipeline_head_speed,
-					tape->controlled_pipeline_head_speed);
-
-	if (tape->speed_control == 1) {
-		if (tape->nr_pending_stages >= tape->max_stages / 2)
-			tape->max_insert_speed = tape->pipeline_head_speed +
-				(1100 - tape->pipeline_head_speed) * 2 *
-				(tape->nr_pending_stages - tape->max_stages / 2)
-				/ tape->max_stages;
-		else
-			tape->max_insert_speed = 500 +
-				(tape->pipeline_head_speed - 500) * 2 *
-				tape->nr_pending_stages / tape->max_stages;
-
-		if (tape->nr_pending_stages >= tape->max_stages * 99 / 100)
-			tape->max_insert_speed = 5000;
-	} else
-		tape->max_insert_speed = tape->speed_control;
-
-	tape->max_insert_speed = max(tape->max_insert_speed, 500);
-}
-
 static ide_startstop_t idetape_media_access_finished(ide_drive_t *drive)
 {
 	idetape_tape_t *tape = drive->driver_data;
@@ -1432,17 +1133,7 @@ static ide_startstop_t idetape_rw_callback(ide_drive_t *drive)
 	int blocks = tape->pc->xferred / tape->blk_size;
 
 	tape->avg_size += blocks * tape->blk_size;
-	tape->insert_size += blocks * tape->blk_size;
-	if (tape->insert_size > 1024 * 1024)
-		tape->measure_insert_time = 1;
-	if (tape->measure_insert_time) {
-		tape->measure_insert_time = 0;
-		tape->insert_time = jiffies;
-		tape->insert_size = 0;
-	}
-	if (time_after(jiffies, tape->insert_time))
-		tape->insert_speed = tape->insert_size / 1024 * HZ /
-					(jiffies - tape->insert_time);
+
 	if (time_after_eq(jiffies, tape->avg_time + HZ)) {
 		tape->avg_speed = tape->avg_size * HZ /
 				(jiffies - tape->avg_time) / 1024;
@@ -1475,7 +1166,7 @@ static void idetape_create_read_cmd(idetape_tape_t *tape,
 	pc->buf = NULL;
 	pc->buf_size = length * tape->blk_size;
 	pc->req_xfer = pc->buf_size;
-	if (pc->req_xfer == tape->stage_size)
+	if (pc->req_xfer == tape->buffer_size)
 		pc->flags |= PC_FLAG_DMA_RECOMMENDED;
 }
 
@@ -1495,7 +1186,7 @@ static void idetape_create_write_cmd(idetape_tape_t *tape,
 	pc->buf = NULL;
 	pc->buf_size = length * tape->blk_size;
 	pc->req_xfer = pc->buf_size;
-	if (pc->req_xfer == tape->stage_size)
+	if (pc->req_xfer == tape->buffer_size)
 		pc->flags |= PC_FLAG_DMA_RECOMMENDED;
 }
 
@@ -1547,10 +1238,6 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 		drive->post_reset = 0;
 	}
 
-	if (time_after(jiffies, tape->insert_time))
-		tape->insert_speed = tape->insert_size / 1024 * HZ /
-					(jiffies - tape->insert_time);
-	idetape_calculate_speeds(drive);
 	if (!test_and_clear_bit(IDETAPE_FLAG_IGNORE_DSC, &tape->flags) &&
 	    (stat & SEEK_STAT) == 0) {
 		if (postponed_rq == NULL) {
@@ -1574,16 +1261,12 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 		return ide_stopped;
 	}
 	if (rq->cmd[0] & REQ_IDETAPE_READ) {
-		tape->buffer_head++;
-		tape->postpone_cnt = 0;
 		pc = idetape_next_pc_storage(drive);
 		idetape_create_read_cmd(tape, pc, rq->current_nr_sectors,
 					(struct idetape_bh *)rq->special);
 		goto out;
 	}
 	if (rq->cmd[0] & REQ_IDETAPE_WRITE) {
-		tape->buffer_head++;
-		tape->postpone_cnt = 0;
 		pc = idetape_next_pc_storage(drive);
 		idetape_create_write_cmd(tape, pc, rq->current_nr_sectors,
 					 (struct idetape_bh *)rq->special);
@@ -1604,103 +1287,91 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 	return idetape_issue_pc(drive, pc);
 }
 
-/* Pipeline related functions */
-
 /*
- * The function below uses __get_free_page to allocate a pipeline stage, along
- * with all the necessary small buffers which together make a buffer of size
- * tape->stage_size (or a bit more). We attempt to combine sequential pages as
+ * The function below uses __get_free_pages to allocate a data buffer of size
+ * tape->buffer_size (or a bit more). We attempt to combine sequential pages as
  * much as possible.
  *
- * It returns a pointer to the new allocated stage, or NULL if we can't (or
- * don't want to) allocate a stage.
- *
- * Pipeline stages are optional and are used to increase performance. If we
- * can't allocate them, we'll manage without them.
+ * It returns a pointer to the newly allocated buffer, or NULL in case of
+ * failure.
  */
-static idetape_stage_t *__idetape_kmalloc_stage(idetape_tape_t *tape, int full,
-						int clear)
+static struct idetape_bh *ide_tape_kmalloc_buffer(idetape_tape_t *tape,
+						  int full, int clear)
 {
-	idetape_stage_t *stage;
-	struct idetape_bh *prev_bh, *bh;
-	int pages = tape->pages_per_stage;
+	struct idetape_bh *prev_bh, *bh, *merge_bh;
+	int pages = tape->pages_per_buffer;
+	unsigned int order, b_allocd;
 	char *b_data = NULL;
 
-	stage = kmalloc(sizeof(idetape_stage_t), GFP_KERNEL);
-	if (!stage)
-		return NULL;
-	stage->next = NULL;
-
-	stage->bh = kmalloc(sizeof(struct idetape_bh), GFP_KERNEL);
-	bh = stage->bh;
+	merge_bh = kmalloc(sizeof(struct idetape_bh), GFP_KERNEL);
+	bh = merge_bh;
 	if (bh == NULL)
 		goto abort;
-	bh->b_reqnext = NULL;
-	bh->b_data = (char *) __get_free_page(GFP_KERNEL);
+
+	order = fls(pages) - 1;
+	bh->b_data = (char *) __get_free_pages(GFP_KERNEL, order);
 	if (!bh->b_data)
 		goto abort;
+	b_allocd = (1 << order) * PAGE_SIZE;
+	pages &= (order-1);
+
 	if (clear)
-		memset(bh->b_data, 0, PAGE_SIZE);
-	bh->b_size = PAGE_SIZE;
+		memset(bh->b_data, 0, b_allocd);
+	bh->b_reqnext = NULL;
+	bh->b_size = b_allocd;
 	atomic_set(&bh->b_count, full ? bh->b_size : 0);
 
-	while (--pages) {
-		b_data = (char *) __get_free_page(GFP_KERNEL);
+	while (pages) {
+		order = fls(pages) - 1;
+		b_data = (char *) __get_free_pages(GFP_KERNEL, order);
 		if (!b_data)
 			goto abort;
+		b_allocd = (1 << order) * PAGE_SIZE;
+
 		if (clear)
-			memset(b_data, 0, PAGE_SIZE);
-		if (bh->b_data == b_data + PAGE_SIZE) {
-			bh->b_size += PAGE_SIZE;
-			bh->b_data -= PAGE_SIZE;
+			memset(b_data, 0, b_allocd);
+
+		/* newly allocated page frames below buffer header or ...*/
+		if (bh->b_data == b_data + b_allocd) {
+			bh->b_size += b_allocd;
+			bh->b_data -= b_allocd;
 			if (full)
-				atomic_add(PAGE_SIZE, &bh->b_count);
+				atomic_add(b_allocd, &bh->b_count);
 			continue;
 		}
+		/* they are above the header */
 		if (b_data == bh->b_data + bh->b_size) {
-			bh->b_size += PAGE_SIZE;
+			bh->b_size += b_allocd;
 			if (full)
-				atomic_add(PAGE_SIZE, &bh->b_count);
+				atomic_add(b_allocd, &bh->b_count);
 			continue;
 		}
 		prev_bh = bh;
 		bh = kmalloc(sizeof(struct idetape_bh), GFP_KERNEL);
 		if (!bh) {
-			free_page((unsigned long) b_data);
+			free_pages((unsigned long) b_data, order);
 			goto abort;
 		}
 		bh->b_reqnext = NULL;
 		bh->b_data = b_data;
-		bh->b_size = PAGE_SIZE;
+		bh->b_size = b_allocd;
 		atomic_set(&bh->b_count, full ? bh->b_size : 0);
 		prev_bh->b_reqnext = bh;
+
+		pages &= (order-1);
 	}
+
 	bh->b_size -= tape->excess_bh_size;
 	if (full)
 		atomic_sub(tape->excess_bh_size, &bh->b_count);
-	return stage;
+	return merge_bh;
 abort:
-	__idetape_kfree_stage(stage);
+	ide_tape_kfree_buffer(tape);
 	return NULL;
 }
 
-static idetape_stage_t *idetape_kmalloc_stage(idetape_tape_t *tape)
-{
-	idetape_stage_t *cache_stage = tape->cache_stage;
-
-	debug_log(DBG_PROCS, "Enter %s\n", __func__);
-
-	if (tape->nr_stages >= tape->max_stages)
-		return NULL;
-	if (cache_stage != NULL) {
-		tape->cache_stage = NULL;
-		return cache_stage;
-	}
-	return __idetape_kmalloc_stage(tape, 0, 0);
-}
-
 static int idetape_copy_stage_from_user(idetape_tape_t *tape,
-		idetape_stage_t *stage, const char __user *buf, int n)
+					const char __user *buf, int n)
 {
 	struct idetape_bh *bh = tape->bh;
 	int count;
@@ -1732,7 +1403,7 @@ static int idetape_copy_stage_from_user(idetape_tape_t *tape,
 }
 
 static int idetape_copy_stage_to_user(idetape_tape_t *tape, char __user *buf,
-		idetape_stage_t *stage, int n)
+				      int n)
 {
 	struct idetape_bh *bh = tape->bh;
 	int count;
@@ -1763,11 +1434,11 @@ static int idetape_copy_stage_to_user(idetape_tape_t *tape, char __user *buf,
 	return ret;
 }
 
-static void idetape_init_merge_stage(idetape_tape_t *tape)
+static void idetape_init_merge_buffer(idetape_tape_t *tape)
 {
-	struct idetape_bh *bh = tape->merge_stage->bh;
+	struct idetape_bh *bh = tape->merge_bh;
+	tape->bh = tape->merge_bh;
 
-	tape->bh = bh;
 	if (tape->chrdev_dir == IDETAPE_DIR_WRITE)
 		atomic_set(&bh->b_count, 0);
 	else {
@@ -1776,61 +1447,6 @@ static void idetape_init_merge_stage(idetape_tape_t *tape)
 	}
 }
 
-static void idetape_switch_buffers(idetape_tape_t *tape, idetape_stage_t *stage)
-{
-	struct idetape_bh *tmp;
-
-	tmp = stage->bh;
-	stage->bh = tape->merge_stage->bh;
-	tape->merge_stage->bh = tmp;
-	idetape_init_merge_stage(tape);
-}
-
-/* Add a new stage at the end of the pipeline. */
-static void idetape_add_stage_tail(ide_drive_t *drive, idetape_stage_t *stage)
-{
-	idetape_tape_t *tape = drive->driver_data;
-	unsigned long flags;
-
-	debug_log(DBG_PROCS, "Enter %s\n", __func__);
-
-	spin_lock_irqsave(&tape->lock, flags);
-	stage->next = NULL;
-	if (tape->last_stage != NULL)
-		tape->last_stage->next = stage;
-	else
-		tape->first_stage = stage;
-		tape->next_stage  = stage;
-	tape->last_stage = stage;
-	if (tape->next_stage == NULL)
-		tape->next_stage = tape->last_stage;
-	tape->nr_stages++;
-	tape->nr_pending_stages++;
-	spin_unlock_irqrestore(&tape->lock, flags);
-}
-
-/* Install a completion in a pending request and sleep until it is serviced. The
- * caller should ensure that the request will not be serviced before we install
- * the completion (usually by disabling interrupts).
- */
-static void idetape_wait_for_request(ide_drive_t *drive, struct request *rq)
-{
-	DECLARE_COMPLETION_ONSTACK(wait);
-	idetape_tape_t *tape = drive->driver_data;
-
-	if (rq == NULL || !blk_special_request(rq)) {
-		printk(KERN_ERR "ide-tape: bug: Trying to sleep on non-valid"
-				 " request\n");
-		return;
-	}
-	rq->end_io_data = &wait;
-	rq->end_io = blk_end_sync_rq;
-	spin_unlock_irq(&tape->lock);
-	wait_for_completion(&wait);
-	/* The stage and its struct request have been deallocated */
-	spin_lock_irq(&tape->lock);
-}
-
 static ide_startstop_t idetape_read_position_callback(ide_drive_t *drive)
 {
 	idetape_tape_t *tape = drive->driver_data;
@@ -1899,7 +1515,7 @@ static void idetape_create_test_unit_ready_cmd(struct ide_atapi_pc *pc)
  * to the request list without waiting for it to be serviced! In that case, we
  * usually use idetape_queue_pc_head().
  */
-static int __idetape_queue_pc_tail(ide_drive_t *drive, struct ide_atapi_pc *pc)
+static int idetape_queue_pc_tail(ide_drive_t *drive, struct ide_atapi_pc *pc)
 {
 	struct ide_tape_obj *tape = drive->driver_data;
 	struct request rq;
@@ -1931,7 +1547,7 @@ static int idetape_wait_ready(ide_drive_t *drive, unsigned long timeout)
 	timeout += jiffies;
 	while (time_before(jiffies, timeout)) {
 		idetape_create_test_unit_ready_cmd(&pc);
-		if (!__idetape_queue_pc_tail(drive, &pc))
+		if (!idetape_queue_pc_tail(drive, &pc))
 			return 0;
 		if ((tape->sense_key == 2 && tape->asc == 4 && tape->ascq == 2)
 		    || (tape->asc == 0x3A)) {
@@ -1940,7 +1556,7 @@ static int idetape_wait_ready(ide_drive_t *drive, unsigned long timeout)
 				return -ENOMEDIUM;
 			idetape_create_load_unload_cmd(drive, &pc,
 							IDETAPE_LU_LOAD_MASK);
-			__idetape_queue_pc_tail(drive, &pc);
+			idetape_queue_pc_tail(drive, &pc);
 			load_attempted = 1;
 		/* not about to be ready */
 		} else if (!(tape->sense_key == 2 && tape->asc == 4 &&
@@ -1951,11 +1567,6 @@ static int idetape_wait_ready(ide_drive_t *drive, unsigned long timeout)
 	return -EIO;
 }
 
-static int idetape_queue_pc_tail(ide_drive_t *drive, struct ide_atapi_pc *pc)
-{
-	return __idetape_queue_pc_tail(drive, pc);
-}
-
 static int idetape_flush_tape_buffers(ide_drive_t *drive)
 {
 	struct ide_atapi_pc pc;
@@ -2021,50 +1632,21 @@ static int idetape_create_prevent_cmd(ide_drive_t *drive,
 	return 1;
 }
 
-static int __idetape_discard_read_pipeline(ide_drive_t *drive)
+static void __ide_tape_discard_merge_buffer(ide_drive_t *drive)
 {
 	idetape_tape_t *tape = drive->driver_data;
-	unsigned long flags;
-	int cnt;
 
 	if (tape->chrdev_dir != IDETAPE_DIR_READ)
-		return 0;
+		return;
 
-	/* Remove merge stage. */
-	cnt = tape->merge_stage_size / tape->blk_size;
-	if (test_and_clear_bit(IDETAPE_FLAG_FILEMARK, &tape->flags))
-		++cnt;		/* Filemarks count as 1 sector */
-	tape->merge_stage_size = 0;
-	if (tape->merge_stage != NULL) {
-		__idetape_kfree_stage(tape->merge_stage);
-		tape->merge_stage = NULL;
+	clear_bit(IDETAPE_FLAG_FILEMARK, &tape->flags);
+	tape->merge_bh_size = 0;
+	if (tape->merge_bh != NULL) {
+		ide_tape_kfree_buffer(tape);
+		tape->merge_bh = NULL;
 	}
 
-	/* Clear pipeline flags. */
-	clear_bit(IDETAPE_FLAG_PIPELINE_ERR, &tape->flags);
 	tape->chrdev_dir = IDETAPE_DIR_NONE;
-
-	/* Remove pipeline stages. */
-	if (tape->first_stage == NULL)
-		return 0;
-
-	spin_lock_irqsave(&tape->lock, flags);
-	tape->next_stage = NULL;
-	if (test_bit(IDETAPE_FLAG_PIPELINE_ACTIVE, &tape->flags))
-		idetape_wait_for_request(drive, tape->active_data_rq);
-	spin_unlock_irqrestore(&tape->lock, flags);
-
-	while (tape->first_stage != NULL) {
-		struct request *rq_ptr = &tape->first_stage->rq;
-
-		cnt += rq_ptr->nr_sectors - rq_ptr->current_nr_sectors;
-		if (rq_ptr->errors == IDETAPE_ERROR_FILEMARK)
-			++cnt;
-		idetape_remove_stage_head(drive);
-	}
-	tape->nr_pending_stages = 0;
-	tape->max_stages = tape->min_pipeline;
-	return cnt;
 }
 
 /*
@@ -2081,7 +1663,7 @@ static int idetape_position_tape(ide_drive_t *drive, unsigned int block,
 	struct ide_atapi_pc pc;
 
 	if (tape->chrdev_dir == IDETAPE_DIR_READ)
-		__idetape_discard_read_pipeline(drive);
+		__ide_tape_discard_merge_buffer(drive);
 	idetape_wait_ready(drive, 60 * 5 * HZ);
 	idetape_create_locate_cmd(drive, &pc, block, partition, skip);
 	retval = idetape_queue_pc_tail(drive, &pc);
@@ -2092,20 +1674,19 @@ static int idetape_position_tape(ide_drive_t *drive, unsigned int block,
 	return (idetape_queue_pc_tail(drive, &pc));
 }
 
-static void idetape_discard_read_pipeline(ide_drive_t *drive,
+static void ide_tape_discard_merge_buffer(ide_drive_t *drive,
 					  int restore_position)
 {
 	idetape_tape_t *tape = drive->driver_data;
-	int cnt;
 	int seek, position;
 
-	cnt = __idetape_discard_read_pipeline(drive);
+	__ide_tape_discard_merge_buffer(drive);
 	if (restore_position) {
 		position = idetape_read_position(drive);
-		seek = position > cnt ? position - cnt : 0;
+		seek = position > 0 ? position : 0;
 		if (idetape_position_tape(drive, seek, 0, 0)) {
 			printk(KERN_INFO "ide-tape: %s: position_tape failed in"
-					 " discard_pipeline()\n", tape->name);
+					 " %s\n", tape->name, __func__);
 			return;
 		}
 	}
@@ -2123,12 +1704,6 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int blocks,
 
 	debug_log(DBG_SENSE, "%s: cmd=%d\n", __func__, cmd);
 
-	if (test_bit(IDETAPE_FLAG_PIPELINE_ACTIVE, &tape->flags)) {
-		printk(KERN_ERR "ide-tape: bug: the pipeline is active in %s\n",
-				__func__);
-		return (0);
-	}
-
 	idetape_init_rq(&rq, cmd);
 	rq.rq_disk = tape->disk;
 	rq.special = (void *)bh;
@@ -2140,26 +1715,13 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int blocks,
 	if ((cmd & (REQ_IDETAPE_READ | REQ_IDETAPE_WRITE)) == 0)
 		return 0;
 
-	if (tape->merge_stage)
-		idetape_init_merge_stage(tape);
+	if (tape->merge_bh)
+		idetape_init_merge_buffer(tape);
 	if (rq.errors == IDETAPE_ERROR_GENERAL)
 		return -EIO;
 	return (tape->blk_size * (blocks-rq.current_nr_sectors));
 }
 
-/* start servicing the pipeline stages, starting from tape->next_stage. */
-static void idetape_plug_pipeline(ide_drive_t *drive)
-{
-	idetape_tape_t *tape = drive->driver_data;
-
-	if (tape->next_stage == NULL)
-		return;
-	if (!test_and_set_bit(IDETAPE_FLAG_PIPELINE_ACTIVE, &tape->flags)) {
-		idetape_activate_next_stage(drive);
-		(void) ide_do_drive_cmd(drive, tape->active_data_rq, ide_end);
-	}
-}
-
 static void idetape_create_inquiry_cmd(struct ide_atapi_pc *pc)
 {
 	idetape_init_pc(pc);
@@ -2197,137 +1759,39 @@ static void idetape_create_space_cmd(struct ide_atapi_pc *pc, int count, u8 cmd)
 	pc->idetape_callback = &idetape_pc_callback;
 }
 
-static void idetape_wait_first_stage(ide_drive_t *drive)
-{
-	idetape_tape_t *tape = drive->driver_data;
-	unsigned long flags;
-
-	if (tape->first_stage == NULL)
-		return;
-	spin_lock_irqsave(&tape->lock, flags);
-	if (tape->active_stage == tape->first_stage)
-		idetape_wait_for_request(drive, tape->active_data_rq);
-	spin_unlock_irqrestore(&tape->lock, flags);
-}
-
-/*
- * Try to add a character device originated write request to our pipeline. In
- * case we don't succeed, we revert to non-pipelined operation mode for this
- * request. In order to accomplish that, we
- *
- * 1. Try to allocate a new pipeline stage.
- * 2. If we can't, wait for more and more requests to be serviced and try again
- * each time.
- * 3. If we still can't allocate a stage, fallback to non-pipelined operation
- * mode for this request.
- */
+/* Queue up a character device originated write request. */
 static int idetape_add_chrdev_write_request(ide_drive_t *drive, int blocks)
 {
 	idetape_tape_t *tape = drive->driver_data;
-	idetape_stage_t *new_stage;
-	unsigned long flags;
-	struct request *rq;
 
 	debug_log(DBG_CHRDEV, "Enter %s\n", __func__);
 
-	/* Attempt to allocate a new stage. Beware possible race conditions. */
-	while ((new_stage = idetape_kmalloc_stage(tape)) == NULL) {
-		spin_lock_irqsave(&tape->lock, flags);
-		if (test_bit(IDETAPE_FLAG_PIPELINE_ACTIVE, &tape->flags)) {
-			idetape_wait_for_request(drive, tape->active_data_rq);
-			spin_unlock_irqrestore(&tape->lock, flags);
-		} else {
-			spin_unlock_irqrestore(&tape->lock, flags);
-			idetape_plug_pipeline(drive);
-			if (test_bit(IDETAPE_FLAG_PIPELINE_ACTIVE,
-					&tape->flags))
-				continue;
-			/*
-			 * The machine is short on memory. Fallback to non-
-			 * pipelined operation mode for this request.
-			 */
-			return idetape_queue_rw_tail(drive, REQ_IDETAPE_WRITE,
-						blocks, tape->merge_stage->bh);
-		}
-	}
-	rq = &new_stage->rq;
-	idetape_init_rq(rq, REQ_IDETAPE_WRITE);
-	/* Doesn't actually matter - We always assume sequential access */
-	rq->sector = tape->first_frame;
-	rq->current_nr_sectors = blocks;
-	rq->nr_sectors = blocks;
-
-	idetape_switch_buffers(tape, new_stage);
-	idetape_add_stage_tail(drive, new_stage);
-	tape->pipeline_head++;
-	idetape_calculate_speeds(drive);
-
-	/*
-	 * Estimate whether the tape has stopped writing by checking if our
-	 * write pipeline is currently empty. If we are not writing anymore,
-	 * wait for the pipeline to be almost completely full (90%) before
-	 * starting to service requests, so that we will be able to keep up with
-	 * the higher speeds of the tape.
-	 */
-	if (!test_bit(IDETAPE_FLAG_PIPELINE_ACTIVE, &tape->flags)) {
-		if (tape->nr_stages >= tape->max_stages * 9 / 10 ||
-			tape->nr_stages >= tape->max_stages -
-			tape->uncontrolled_pipeline_head_speed * 3 * 1024 /
-			tape->blk_size) {
-			tape->measure_insert_time = 1;
-			tape->insert_time = jiffies;
-			tape->insert_size = 0;
-			tape->insert_speed = 0;
-			idetape_plug_pipeline(drive);
-		}
-	}
-	if (test_and_clear_bit(IDETAPE_FLAG_PIPELINE_ERR, &tape->flags))
-		/* Return a deferred error */
-		return -EIO;
-	return blocks;
+	return idetape_queue_rw_tail(drive, REQ_IDETAPE_WRITE,
+				     blocks, tape->merge_bh);
 }
 
-/*
- * Wait until all pending pipeline requests are serviced. Typically called on
- * device close.
- */
-static void idetape_wait_for_pipeline(ide_drive_t *drive)
-{
-	idetape_tape_t *tape = drive->driver_data;
-	unsigned long flags;
-
-	while (tape->next_stage || test_bit(IDETAPE_FLAG_PIPELINE_ACTIVE,
-						&tape->flags)) {
-		idetape_plug_pipeline(drive);
-		spin_lock_irqsave(&tape->lock, flags);
-		if (test_bit(IDETAPE_FLAG_PIPELINE_ACTIVE, &tape->flags))
-			idetape_wait_for_request(drive, tape->active_data_rq);
-		spin_unlock_irqrestore(&tape->lock, flags);
-	}
-}
-
-static void idetape_empty_write_pipeline(ide_drive_t *drive)
+static void ide_tape_flush_merge_buffer(ide_drive_t *drive)
 {
 	idetape_tape_t *tape = drive->driver_data;
 	int blocks, min;
 	struct idetape_bh *bh;
 
 	if (tape->chrdev_dir != IDETAPE_DIR_WRITE) {
-		printk(KERN_ERR "ide-tape: bug: Trying to empty write pipeline,"
+		printk(KERN_ERR "ide-tape: bug: Trying to empty merge buffer"
 				" but we are not writing.\n");
 		return;
 	}
-	if (tape->merge_stage_size > tape->stage_size) {
+	if (tape->merge_bh_size > tape->buffer_size) {
 		printk(KERN_ERR "ide-tape: bug: merge_buffer too big\n");
-		tape->merge_stage_size = tape->stage_size;
+		tape->merge_bh_size = tape->buffer_size;
 	}
-	if (tape->merge_stage_size) {
-		blocks = tape->merge_stage_size / tape->blk_size;
-		if (tape->merge_stage_size % tape->blk_size) {
+	if (tape->merge_bh_size) {
+		blocks = tape->merge_bh_size / tape->blk_size;
+		if (tape->merge_bh_size % tape->blk_size) {
 			unsigned int i;
 
 			blocks++;
-			i = tape->blk_size - tape->merge_stage_size %
+			i = tape->blk_size - tape->merge_bh_size %
 				tape->blk_size;
 			bh = tape->bh->b_reqnext;
 			while (bh) {
@@ -2351,74 +1815,33 @@ static void idetape_empty_write_pipeline(ide_drive_t *drive)
 			}
 		}
 		(void) idetape_add_chrdev_write_request(drive, blocks);
-		tape->merge_stage_size = 0;
+		tape->merge_bh_size = 0;
 	}
-	idetape_wait_for_pipeline(drive);
-	if (tape->merge_stage != NULL) {
-		__idetape_kfree_stage(tape->merge_stage);
-		tape->merge_stage = NULL;
+	if (tape->merge_bh != NULL) {
+		ide_tape_kfree_buffer(tape);
+		tape->merge_bh = NULL;
 	}
-	clear_bit(IDETAPE_FLAG_PIPELINE_ERR, &tape->flags);
 	tape->chrdev_dir = IDETAPE_DIR_NONE;
-
-	/*
-	 * On the next backup, perform the feedback loop again. (I don't want to
-	 * keep sense information between backups, as some systems are
-	 * constantly on, and the system load can be totally different on the
-	 * next backup).
-	 */
-	tape->max_stages = tape->min_pipeline;
-	if (tape->first_stage != NULL ||
-	    tape->next_stage != NULL ||
-	    tape->last_stage != NULL ||
-	    tape->nr_stages != 0) {
-		printk(KERN_ERR "ide-tape: ide-tape pipeline bug, "
-			"first_stage %p, next_stage %p, "
-			"last_stage %p, nr_stages %d\n",
-			tape->first_stage, tape->next_stage,
-			tape->last_stage, tape->nr_stages);
-	}
 }
 
-static void idetape_restart_speed_control(ide_drive_t *drive)
+static int idetape_init_read(ide_drive_t *drive)
 {
 	idetape_tape_t *tape = drive->driver_data;
-
-	tape->restart_speed_control_req = 0;
-	tape->pipeline_head = 0;
-	tape->controlled_last_pipeline_head = 0;
-	tape->controlled_previous_pipeline_head = 0;
-	tape->uncontrolled_previous_pipeline_head = 0;
-	tape->controlled_pipeline_head_speed = 5000;
-	tape->pipeline_head_speed = 5000;
-	tape->uncontrolled_pipeline_head_speed = 0;
-	tape->controlled_pipeline_head_time =
-		tape->uncontrolled_pipeline_head_time = jiffies;
-	tape->controlled_previous_head_time =
-		tape->uncontrolled_previous_head_time = jiffies;
-}
-
-static int idetape_init_read(ide_drive_t *drive, int max_stages)
-{
-	idetape_tape_t *tape = drive->driver_data;
-	idetape_stage_t *new_stage;
-	struct request rq;
 	int bytes_read;
-	u16 blocks = *(u16 *)&tape->caps[12];
 
 	/* Initialize read operation */
 	if (tape->chrdev_dir != IDETAPE_DIR_READ) {
 		if (tape->chrdev_dir == IDETAPE_DIR_WRITE) {
-			idetape_empty_write_pipeline(drive);
+			ide_tape_flush_merge_buffer(drive);
 			idetape_flush_tape_buffers(drive);
 		}
-		if (tape->merge_stage || tape->merge_stage_size) {
-			printk(KERN_ERR "ide-tape: merge_stage_size should be"
+		if (tape->merge_bh || tape->merge_bh_size) {
+			printk(KERN_ERR "ide-tape: merge_bh_size should be"
 					 " 0 now\n");
-			tape->merge_stage_size = 0;
+			tape->merge_bh_size = 0;
 		}
-		tape->merge_stage = __idetape_kmalloc_stage(tape, 0, 0);
-		if (!tape->merge_stage)
+		tape->merge_bh = ide_tape_kmalloc_buffer(tape, 0, 0);
+		if (!tape->merge_bh)
 			return -ENOMEM;
 		tape->chrdev_dir = IDETAPE_DIR_READ;
 
@@ -2431,54 +1854,23 @@ static int idetape_init_read(ide_drive_t *drive, int max_stages)
 		if (drive->dsc_overlap) {
 			bytes_read = idetape_queue_rw_tail(drive,
 							REQ_IDETAPE_READ, 0,
-							tape->merge_stage->bh);
+							tape->merge_bh);
 			if (bytes_read < 0) {
-				__idetape_kfree_stage(tape->merge_stage);
-				tape->merge_stage = NULL;
+				ide_tape_kfree_buffer(tape);
+				tape->merge_bh = NULL;
 				tape->chrdev_dir = IDETAPE_DIR_NONE;
 				return bytes_read;
 			}
 		}
 	}
-	if (tape->restart_speed_control_req)
-		idetape_restart_speed_control(drive);
-	idetape_init_rq(&rq, REQ_IDETAPE_READ);
-	rq.sector = tape->first_frame;
-	rq.nr_sectors = blocks;
-	rq.current_nr_sectors = blocks;
-	if (!test_bit(IDETAPE_FLAG_PIPELINE_ERR, &tape->flags) &&
-	    tape->nr_stages < max_stages) {
-		new_stage = idetape_kmalloc_stage(tape);
-		while (new_stage != NULL) {
-			new_stage->rq = rq;
-			idetape_add_stage_tail(drive, new_stage);
-			if (tape->nr_stages >= max_stages)
-				break;
-			new_stage = idetape_kmalloc_stage(tape);
-		}
-	}
-	if (!test_bit(IDETAPE_FLAG_PIPELINE_ACTIVE, &tape->flags)) {
-		if (tape->nr_pending_stages >= 3 * max_stages / 4) {
-			tape->measure_insert_time = 1;
-			tape->insert_time = jiffies;
-			tape->insert_size = 0;
-			tape->insert_speed = 0;
-			idetape_plug_pipeline(drive);
-		}
-	}
+
 	return 0;
 }
 
-/*
- * Called from idetape_chrdev_read() to service a character device read request
- * and add read-ahead requests to our pipeline.
- */
+/* called from idetape_chrdev_read() to service a chrdev read request. */
 static int idetape_add_chrdev_read_request(ide_drive_t *drive, int blocks)
 {
 	idetape_tape_t *tape = drive->driver_data;
-	unsigned long flags;
-	struct request *rq_ptr;
-	int bytes_read;
 
 	debug_log(DBG_PROCS, "Enter %s, %d blocks\n", __func__, blocks);
 
@@ -2486,39 +1878,10 @@ static int idetape_add_chrdev_read_request(ide_drive_t *drive, int blocks)
 	if (test_bit(IDETAPE_FLAG_FILEMARK, &tape->flags))
 		return 0;
 
-	/* Wait for the next block to reach the head of the pipeline. */
-	idetape_init_read(drive, tape->max_stages);
-	if (tape->first_stage == NULL) {
-		if (test_bit(IDETAPE_FLAG_PIPELINE_ERR, &tape->flags))
-			return 0;
-		return idetape_queue_rw_tail(drive, REQ_IDETAPE_READ, blocks,
-					tape->merge_stage->bh);
-	}
-	idetape_wait_first_stage(drive);
-	rq_ptr = &tape->first_stage->rq;
-	bytes_read = tape->blk_size * (rq_ptr->nr_sectors -
-					rq_ptr->current_nr_sectors);
-	rq_ptr->nr_sectors = 0;
-	rq_ptr->current_nr_sectors = 0;
+	idetape_init_read(drive);
 
-	if (rq_ptr->errors == IDETAPE_ERROR_EOD)
-		return 0;
-	else {
-		idetape_switch_buffers(tape, tape->first_stage);
-		if (rq_ptr->errors == IDETAPE_ERROR_FILEMARK)
-			set_bit(IDETAPE_FLAG_FILEMARK, &tape->flags);
-		spin_lock_irqsave(&tape->lock, flags);
-		idetape_remove_stage_head(drive);
-		spin_unlock_irqrestore(&tape->lock, flags);
-		tape->pipeline_head++;
-		idetape_calculate_speeds(drive);
-	}
-	if (bytes_read > blocks * tape->blk_size) {
-		printk(KERN_ERR "ide-tape: bug: trying to return more bytes"
-				" than requested\n");
-		bytes_read = blocks * tape->blk_size;
-	}
-	return (bytes_read);
+	return idetape_queue_rw_tail(drive, REQ_IDETAPE_READ, blocks,
+				     tape->merge_bh);
 }
 
 static void idetape_pad_zeros(ide_drive_t *drive, int bcount)
@@ -2530,8 +1893,8 @@ static void idetape_pad_zeros(ide_drive_t *drive, int bcount)
 	while (bcount) {
 		unsigned int count;
 
-		bh = tape->merge_stage->bh;
-		count = min(tape->stage_size, bcount);
+		bh = tape->merge_bh;
+		count = min(tape->buffer_size, bcount);
 		bcount -= count;
 		blocks = count / tape->blk_size;
 		while (count) {
@@ -2542,29 +1905,8 @@ static void idetape_pad_zeros(ide_drive_t *drive, int bcount)
 			bh = bh->b_reqnext;
 		}
 		idetape_queue_rw_tail(drive, REQ_IDETAPE_WRITE, blocks,
-				      tape->merge_stage->bh);
-	}
-}
-
-static int idetape_pipeline_size(ide_drive_t *drive)
-{
-	idetape_tape_t *tape = drive->driver_data;
-	idetape_stage_t *stage;
-	struct request *rq;
-	int size = 0;
-
-	idetape_wait_for_pipeline(drive);
-	stage = tape->first_stage;
-	while (stage != NULL) {
-		rq = &stage->rq;
-		size += tape->blk_size * (rq->nr_sectors -
-				rq->current_nr_sectors);
-		if (rq->errors == IDETAPE_ERROR_FILEMARK)
-			size += tape->blk_size;
-		stage = stage->next;
+				      tape->merge_bh);
 	}
-	size += tape->merge_stage_size;
-	return size;
 }
 
 /*
@@ -2612,11 +1954,10 @@ static int idetape_blkdev_ioctl(ide_drive_t *drive, unsigned int cmd,
 		if (copy_from_user(&config, argp, sizeof(config)))
 			return -EFAULT;
 		tape->best_dsc_rw_freq = config.dsc_rw_frequency;
-		tape->max_stages = config.nr_stages;
 		break;
 	case 0x0350:
 		config.dsc_rw_frequency = (int) tape->best_dsc_rw_freq;
-		config.nr_stages = tape->max_stages;
+		config.nr_stages = 1;
 		if (copy_to_user(argp, &config, sizeof(config)))
 			return -EFAULT;
 		break;
@@ -2626,19 +1967,11 @@ static int idetape_blkdev_ioctl(ide_drive_t *drive, unsigned int cmd,
 	return 0;
 }
 
-/*
- * The function below is now a bit more complicated than just passing the
- * command to the tape since we may have crossed some filemarks during our
- * pipelined read-ahead mode. As a minor side effect, the pipeline enables us to
- * support MTFSFM when the filemark is in our internal pipeline even if the tape
- * doesn't support spacing over filemarks in the reverse direction.
- */
 static int idetape_space_over_filemarks(ide_drive_t *drive, short mt_op,
 					int mt_count)
 {
 	idetape_tape_t *tape = drive->driver_data;
 	struct ide_atapi_pc pc;
-	unsigned long flags;
 	int retval, count = 0;
 	int sprev = !!(tape->caps[4] & 0x20);
 
@@ -2651,48 +1984,12 @@ static int idetape_space_over_filemarks(ide_drive_t *drive, short mt_op,
 	}
 
 	if (tape->chrdev_dir == IDETAPE_DIR_READ) {
-		/* its a read-ahead buffer, scan it for crossed filemarks. */
-		tape->merge_stage_size = 0;
+		tape->merge_bh_size = 0;
 		if (test_and_clear_bit(IDETAPE_FLAG_FILEMARK, &tape->flags))
 			++count;
-		while (tape->first_stage != NULL) {
-			if (count == mt_count) {
-				if (mt_op == MTFSFM)
-					set_bit(IDETAPE_FLAG_FILEMARK,
-						&tape->flags);
-				return 0;
-			}
-			spin_lock_irqsave(&tape->lock, flags);
-			if (tape->first_stage == tape->active_stage) {
-				/*
-				 * We have reached the active stage in the read
-				 * pipeline. There is no point in allowing the
-				 * drive to continue reading any farther, so we
-				 * stop the pipeline.
-				 *
-				 * This section should be moved to a separate
-				 * subroutine because similar operations are
-				 * done in __idetape_discard_read_pipeline(),
-				 * for example.
-				 */
-				tape->next_stage = NULL;
-				spin_unlock_irqrestore(&tape->lock, flags);
-				idetape_wait_first_stage(drive);
-				tape->next_stage = tape->first_stage->next;
-			} else
-				spin_unlock_irqrestore(&tape->lock, flags);
-			if (tape->first_stage->rq.errors ==
-					IDETAPE_ERROR_FILEMARK)
-				++count;
-			idetape_remove_stage_head(drive);
-		}
-		idetape_discard_read_pipeline(drive, 0);
+		ide_tape_discard_merge_buffer(drive, 0);
 	}
 
-	/*
-	 * The filemark was not found in our internal pipeline;	now we can issue
-	 * the space command.
-	 */
 	switch (mt_op) {
 	case MTFSF:
 	case MTBSF:
@@ -2748,27 +2045,25 @@ static ssize_t idetape_chrdev_read(struct file *file, char __user *buf,
 			    (count % tape->blk_size) == 0)
 				tape->user_bs_factor = count / tape->blk_size;
 	}
-	rc = idetape_init_read(drive, tape->max_stages);
+	rc = idetape_init_read(drive);
 	if (rc < 0)
 		return rc;
 	if (count == 0)
 		return (0);
-	if (tape->merge_stage_size) {
-		actually_read = min((unsigned int)(tape->merge_stage_size),
+	if (tape->merge_bh_size) {
+		actually_read = min((unsigned int)(tape->merge_bh_size),
 				    (unsigned int)count);
-		if (idetape_copy_stage_to_user(tape, buf, tape->merge_stage,
-					       actually_read))
+		if (idetape_copy_stage_to_user(tape, buf, actually_read))
 			ret = -EFAULT;
 		buf += actually_read;
-		tape->merge_stage_size -= actually_read;
+		tape->merge_bh_size -= actually_read;
 		count -= actually_read;
 	}
-	while (count >= tape->stage_size) {
+	while (count >= tape->buffer_size) {
 		bytes_read = idetape_add_chrdev_read_request(drive, ctl);
 		if (bytes_read <= 0)
 			goto finish;
-		if (idetape_copy_stage_to_user(tape, buf, tape->merge_stage,
-					       bytes_read))
+		if (idetape_copy_stage_to_user(tape, buf, bytes_read))
 			ret = -EFAULT;
 		buf += bytes_read;
 		count -= bytes_read;
@@ -2779,11 +2074,10 @@ static ssize_t idetape_chrdev_read(struct file *file, char __user *buf,
 		if (bytes_read <= 0)
 			goto finish;
 		temp = min((unsigned long)count, (unsigned long)bytes_read);
-		if (idetape_copy_stage_to_user(tape, buf, tape->merge_stage,
-					       temp))
+		if (idetape_copy_stage_to_user(tape, buf, temp))
 			ret = -EFAULT;
 		actually_read += temp;
-		tape->merge_stage_size = bytes_read-temp;
+		tape->merge_bh_size = bytes_read-temp;
 	}
 finish:
 	if (!actually_read && test_bit(IDETAPE_FLAG_FILEMARK, &tape->flags)) {
@@ -2814,17 +2108,17 @@ static ssize_t idetape_chrdev_write(struct file *file, const char __user *buf,
 	/* Initialize write operation */
 	if (tape->chrdev_dir != IDETAPE_DIR_WRITE) {
 		if (tape->chrdev_dir == IDETAPE_DIR_READ)
-			idetape_discard_read_pipeline(drive, 1);
-		if (tape->merge_stage || tape->merge_stage_size) {
-			printk(KERN_ERR "ide-tape: merge_stage_size "
+			ide_tape_discard_merge_buffer(drive, 1);
+		if (tape->merge_bh || tape->merge_bh_size) {
+			printk(KERN_ERR "ide-tape: merge_bh_size "
 				"should be 0 now\n");
-			tape->merge_stage_size = 0;
+			tape->merge_bh_size = 0;
 		}
-		tape->merge_stage = __idetape_kmalloc_stage(tape, 0, 0);
-		if (!tape->merge_stage)
+		tape->merge_bh = ide_tape_kmalloc_buffer(tape, 0, 0);
+		if (!tape->merge_bh)
 			return -ENOMEM;
 		tape->chrdev_dir = IDETAPE_DIR_WRITE;
-		idetape_init_merge_stage(tape);
+		idetape_init_merge_buffer(tape);
 
 		/*
 		 * Issue a write 0 command to ensure that DSC handshake is
@@ -2835,10 +2129,10 @@ static ssize_t idetape_chrdev_write(struct file *file, const char __user *buf,
 		if (drive->dsc_overlap) {
 			ssize_t retval = idetape_queue_rw_tail(drive,
 							REQ_IDETAPE_WRITE, 0,
-							tape->merge_stage->bh);
+							tape->merge_bh);
 			if (retval < 0) {
-				__idetape_kfree_stage(tape->merge_stage);
-				tape->merge_stage = NULL;
+				ide_tape_kfree_buffer(tape);
+				tape->merge_bh = NULL;
 				tape->chrdev_dir = IDETAPE_DIR_NONE;
 				return retval;
 			}
@@ -2846,49 +2140,44 @@ static ssize_t idetape_chrdev_write(struct file *file, const char __user *buf,
 	}
 	if (count == 0)
 		return (0);
-	if (tape->restart_speed_control_req)
-		idetape_restart_speed_control(drive);
-	if (tape->merge_stage_size) {
-		if (tape->merge_stage_size >= tape->stage_size) {
+	if (tape->merge_bh_size) {
+		if (tape->merge_bh_size >= tape->buffer_size) {
 			printk(KERN_ERR "ide-tape: bug: merge buf too big\n");
-			tape->merge_stage_size = 0;
+			tape->merge_bh_size = 0;
 		}
 		actually_written = min((unsigned int)
-				(tape->stage_size - tape->merge_stage_size),
+				(tape->buffer_size - tape->merge_bh_size),
 				(unsigned int)count);
-		if (idetape_copy_stage_from_user(tape, tape->merge_stage, buf,
-						 actually_written))
+		if (idetape_copy_stage_from_user(tape, buf, actually_written))
 				ret = -EFAULT;
 		buf += actually_written;
-		tape->merge_stage_size += actually_written;
+		tape->merge_bh_size += actually_written;
 		count -= actually_written;
 
-		if (tape->merge_stage_size == tape->stage_size) {
+		if (tape->merge_bh_size == tape->buffer_size) {
 			ssize_t retval;
-			tape->merge_stage_size = 0;
+			tape->merge_bh_size = 0;
 			retval = idetape_add_chrdev_write_request(drive, ctl);
 			if (retval <= 0)
 				return (retval);
 		}
 	}
-	while (count >= tape->stage_size) {
+	while (count >= tape->buffer_size) {
 		ssize_t retval;
-		if (idetape_copy_stage_from_user(tape, tape->merge_stage, buf,
-						 tape->stage_size))
+		if (idetape_copy_stage_from_user(tape, buf, tape->buffer_size))
 			ret = -EFAULT;
-		buf += tape->stage_size;
-		count -= tape->stage_size;
+		buf += tape->buffer_size;
+		count -= tape->buffer_size;
 		retval = idetape_add_chrdev_write_request(drive, ctl);
-		actually_written += tape->stage_size;
+		actually_written += tape->buffer_size;
 		if (retval <= 0)
 			return (retval);
 	}
 	if (count) {
 		actually_written += count;
-		if (idetape_copy_stage_from_user(tape, tape->merge_stage, buf,
-						 count))
+		if (idetape_copy_stage_from_user(tape, buf, count))
 			ret = -EFAULT;
-		tape->merge_stage_size += count;
+		tape->merge_bh_size += count;
 	}
 	return ret ? ret : actually_written;
 }
@@ -2912,8 +2201,7 @@ static int idetape_write_filemark(ide_drive_t *drive)
  *
  * Note: MTBSF and MTBSFM are not supported when the tape doesn't support
  * spacing over filemarks in the reverse direction. In this case, MTFSFM is also
- * usually not supported (it is supported in the rare case in which we crossed
- * the filemark during our read-ahead pipelined operation mode).
+ * usually not supported.
  *
  * The following commands are currently not supported:
  *
@@ -2929,7 +2217,6 @@ static int idetape_mtioctop(ide_drive_t *drive, short mt_op, int mt_count)
 	debug_log(DBG_ERR, "Handling MTIOCTOP ioctl: mt_op=%d, mt_count=%d\n",
 			mt_op, mt_count);
 
-	/* Commands which need our pipelined read-ahead stages. */
 	switch (mt_op) {
 	case MTFSF:
 	case MTFSFM:
@@ -2946,7 +2233,7 @@ static int idetape_mtioctop(ide_drive_t *drive, short mt_op, int mt_count)
 	case MTWEOF:
 		if (tape->write_prot)
 			return -EACCES;
-		idetape_discard_read_pipeline(drive, 1);
+		ide_tape_discard_merge_buffer(drive, 1);
 		for (i = 0; i < mt_count; i++) {
 			retval = idetape_write_filemark(drive);
 			if (retval)
@@ -2954,12 +2241,12 @@ static int idetape_mtioctop(ide_drive_t *drive, short mt_op, int mt_count)
 		}
 		return 0;
 	case MTREW:
-		idetape_discard_read_pipeline(drive, 0);
+		ide_tape_discard_merge_buffer(drive, 0);
 		if (idetape_rewind_tape(drive))
 			return -EIO;
 		return 0;
 	case MTLOAD:
-		idetape_discard_read_pipeline(drive, 0);
+		ide_tape_discard_merge_buffer(drive, 0);
 		idetape_create_load_unload_cmd(drive, &pc,
 					       IDETAPE_LU_LOAD_MASK);
 		return idetape_queue_pc_tail(drive, &pc);
@@ -2974,7 +2261,7 @@ static int idetape_mtioctop(ide_drive_t *drive, short mt_op, int mt_count)
 				if (!idetape_queue_pc_tail(drive, &pc))
 					tape->door_locked = DOOR_UNLOCKED;
 		}
-		idetape_discard_read_pipeline(drive, 0);
+		ide_tape_discard_merge_buffer(drive, 0);
 		idetape_create_load_unload_cmd(drive, &pc,
 					      !IDETAPE_LU_LOAD_MASK);
 		retval = idetape_queue_pc_tail(drive, &pc);
@@ -2982,10 +2269,10 @@ static int idetape_mtioctop(ide_drive_t *drive, short mt_op, int mt_count)
 			clear_bit(IDETAPE_FLAG_MEDIUM_PRESENT, &tape->flags);
 		return retval;
 	case MTNOP:
-		idetape_discard_read_pipeline(drive, 0);
+		ide_tape_discard_merge_buffer(drive, 0);
 		return idetape_flush_tape_buffers(drive);
 	case MTRETEN:
-		idetape_discard_read_pipeline(drive, 0);
+		ide_tape_discard_merge_buffer(drive, 0);
 		idetape_create_load_unload_cmd(drive, &pc,
 			IDETAPE_LU_RETENSION_MASK | IDETAPE_LU_LOAD_MASK);
 		return idetape_queue_pc_tail(drive, &pc);
@@ -3007,11 +2294,11 @@ static int idetape_mtioctop(ide_drive_t *drive, short mt_op, int mt_count)
 			set_bit(IDETAPE_FLAG_DETECT_BS, &tape->flags);
 		return 0;
 	case MTSEEK:
-		idetape_discard_read_pipeline(drive, 0);
+		ide_tape_discard_merge_buffer(drive, 0);
 		return idetape_position_tape(drive,
 			mt_count * tape->user_bs_factor, tape->partition, 0);
 	case MTSETPART:
-		idetape_discard_read_pipeline(drive, 0);
+		ide_tape_discard_merge_buffer(drive, 0);
 		return idetape_position_tape(drive, 0, mt_count, 0);
 	case MTFSR:
 	case MTBSR:
@@ -3056,13 +2343,12 @@ static int idetape_chrdev_ioctl(struct inode *inode, struct file *file,
 
 	debug_log(DBG_CHRDEV, "Enter %s, cmd=%u\n", __func__, cmd);
 
-	tape->restart_speed_control_req = 1;
 	if (tape->chrdev_dir == IDETAPE_DIR_WRITE) {
-		idetape_empty_write_pipeline(drive);
+		ide_tape_flush_merge_buffer(drive);
 		idetape_flush_tape_buffers(drive);
 	}
 	if (cmd == MTIOCGET || cmd == MTIOCPOS) {
-		block_offset = idetape_pipeline_size(drive) /
+		block_offset = tape->merge_bh_size /
 			(tape->blk_size * tape->user_bs_factor);
 		position = idetape_read_position(drive);
 		if (position < 0)
@@ -3094,7 +2380,7 @@ static int idetape_chrdev_ioctl(struct inode *inode, struct file *file,
 		return 0;
 	default:
 		if (tape->chrdev_dir == IDETAPE_DIR_READ)
-			idetape_discard_read_pipeline(drive, 1);
+			ide_tape_discard_merge_buffer(drive, 1);
 		return idetape_blkdev_ioctl(drive, cmd, arg);
 	}
 }
@@ -3168,9 +2454,6 @@ static int idetape_chrdev_open(struct inode *inode, struct file *filp)
 	if (!test_bit(IDETAPE_FLAG_ADDRESS_VALID, &tape->flags))
 		(void)idetape_rewind_tape(drive);
 
-	if (tape->chrdev_dir != IDETAPE_DIR_READ)
-		clear_bit(IDETAPE_FLAG_PIPELINE_ERR, &tape->flags);
-
 	/* Read block size and write protect status from drive. */
 	ide_tape_get_bsize_from_bdesc(drive);
 
@@ -3199,8 +2482,6 @@ static int idetape_chrdev_open(struct inode *inode, struct file *filp)
 			}
 		}
 	}
-	idetape_restart_speed_control(drive);
-	tape->restart_speed_control_req = 0;
 	return 0;
 
 out_put_tape:
@@ -3212,13 +2493,13 @@ static void idetape_write_release(ide_drive_t *drive, unsigned int minor)
 {
 	idetape_tape_t *tape = drive->driver_data;
 
-	idetape_empty_write_pipeline(drive);
-	tape->merge_stage = __idetape_kmalloc_stage(tape, 1, 0);
-	if (tape->merge_stage != NULL) {
+	ide_tape_flush_merge_buffer(drive);
+	tape->merge_bh = ide_tape_kmalloc_buffer(tape, 1, 0);
+	if (tape->merge_bh != NULL) {
 		idetape_pad_zeros(drive, tape->blk_size *
 				(tape->user_bs_factor - 1));
-		__idetape_kfree_stage(tape->merge_stage);
-		tape->merge_stage = NULL;
+		ide_tape_kfree_buffer(tape);
+		tape->merge_bh = NULL;
 	}
 	idetape_write_filemark(drive);
 	idetape_flush_tape_buffers(drive);
@@ -3241,14 +2522,9 @@ static int idetape_chrdev_release(struct inode *inode, struct file *filp)
 		idetape_write_release(drive, minor);
 	if (tape->chrdev_dir == IDETAPE_DIR_READ) {
 		if (minor < 128)
-			idetape_discard_read_pipeline(drive, 1);
-		else
-			idetape_wait_for_pipeline(drive);
-	}
-	if (tape->cache_stage != NULL) {
-		__idetape_kfree_stage(tape->cache_stage);
-		tape->cache_stage = NULL;
+			ide_tape_discard_merge_buffer(drive, 1);
 	}
+
 	if (minor < 128 && test_bit(IDETAPE_FLAG_MEDIUM_PRESENT, &tape->flags))
 		(void) idetape_rewind_tape(drive);
 	if (tape->chrdev_dir == IDETAPE_DIR_NONE) {
@@ -3385,33 +2661,15 @@ static void idetape_add_settings(ide_drive_t *drive)
 
 	ide_add_setting(drive, "buffer", SETTING_READ, TYPE_SHORT, 0, 0xffff,
 			1, 2, (u16 *)&tape->caps[16], NULL);
-	ide_add_setting(drive, "pipeline_min", SETTING_RW, TYPE_INT, 1, 0xffff,
-			tape->stage_size / 1024, 1, &tape->min_pipeline, NULL);
-	ide_add_setting(drive, "pipeline", SETTING_RW, TYPE_INT, 1, 0xffff,
-			tape->stage_size / 1024, 1, &tape->max_stages, NULL);
-	ide_add_setting(drive, "pipeline_max", SETTING_RW, TYPE_INT, 1,	0xffff,
-			tape->stage_size / 1024, 1, &tape->max_pipeline, NULL);
-	ide_add_setting(drive, "pipeline_used",	SETTING_READ, TYPE_INT, 0,
-			0xffff,	tape->stage_size / 1024, 1, &tape->nr_stages,
-			NULL);
-	ide_add_setting(drive, "pipeline_pending", SETTING_READ, TYPE_INT, 0,
-			0xffff, tape->stage_size / 1024, 1,
-			&tape->nr_pending_stages, NULL);
 	ide_add_setting(drive, "speed", SETTING_READ, TYPE_SHORT, 0, 0xffff,
 			1, 1, (u16 *)&tape->caps[14], NULL);
-	ide_add_setting(drive, "stage", SETTING_READ, TYPE_INT,	0, 0xffff, 1,
-			1024, &tape->stage_size, NULL);
+	ide_add_setting(drive, "buffer_size", SETTING_READ, TYPE_INT, 0, 0xffff,
+			1, 1024, &tape->buffer_size, NULL);
 	ide_add_setting(drive, "tdsc", SETTING_RW, TYPE_INT, IDETAPE_DSC_RW_MIN,
 			IDETAPE_DSC_RW_MAX, 1000, HZ, &tape->best_dsc_rw_freq,
 			NULL);
 	ide_add_setting(drive, "dsc_overlap", SETTING_RW, TYPE_BYTE, 0, 1, 1,
 			1, &drive->dsc_overlap, NULL);
-	ide_add_setting(drive, "pipeline_head_speed_c", SETTING_READ, TYPE_INT,
-			0, 0xffff, 1, 1, &tape->controlled_pipeline_head_speed,
-			NULL);
-	ide_add_setting(drive, "pipeline_head_speed_u", SETTING_READ, TYPE_INT,
-			0, 0xffff, 1, 1,
-			&tape->uncontrolled_pipeline_head_speed, NULL);
 	ide_add_setting(drive, "avg_speed", SETTING_READ, TYPE_INT, 0, 0xffff,
 			1, 1, &tape->avg_speed, NULL);
 	ide_add_setting(drive, "debug_mask", SETTING_RW, TYPE_INT, 0, 0xffff, 1,
@@ -3434,11 +2692,10 @@ static inline void idetape_add_settings(ide_drive_t *drive) { ; }
  */
 static void idetape_setup(ide_drive_t *drive, idetape_tape_t *tape, int minor)
 {
-	unsigned long t1, tmid, tn, t;
+	unsigned long t;
 	int speed;
-	int stage_size;
+	int buffer_size;
 	u8 gcw[2];
-	struct sysinfo si;
 	u16 *ctl = (u16 *)&tape->caps[12];
 
 	spin_lock_init(&tape->lock);
@@ -3457,65 +2714,33 @@ static void idetape_setup(ide_drive_t *drive, idetape_tape_t *tape, int minor)
 	tape->name[2] = '0' + minor;
 	tape->chrdev_dir = IDETAPE_DIR_NONE;
 	tape->pc = tape->pc_stack;
-	tape->max_insert_speed = 10000;
-	tape->speed_control = 1;
 	*((unsigned short *) &gcw) = drive->id->config;
 
 	/* Command packet DRQ type */
 	if (((gcw[0] & 0x60) >> 5) == 1)
 		set_bit(IDETAPE_FLAG_DRQ_INTERRUPT, &tape->flags);
 
-	tape->min_pipeline = 10;
-	tape->max_pipeline = 10;
-	tape->max_stages   = 10;
-
 	idetape_get_inquiry_results(drive);
 	idetape_get_mode_sense_results(drive);
 	ide_tape_get_bsize_from_bdesc(drive);
 	tape->user_bs_factor = 1;
-	tape->stage_size = *ctl * tape->blk_size;
-	while (tape->stage_size > 0xffff) {
+	tape->buffer_size = *ctl * tape->blk_size;
+	while (tape->buffer_size > 0xffff) {
 		printk(KERN_NOTICE "ide-tape: decreasing stage size\n");
 		*ctl /= 2;
-		tape->stage_size = *ctl * tape->blk_size;
+		tape->buffer_size = *ctl * tape->blk_size;
 	}
-	stage_size = tape->stage_size;
-	tape->pages_per_stage = stage_size / PAGE_SIZE;
-	if (stage_size % PAGE_SIZE) {
-		tape->pages_per_stage++;
-		tape->excess_bh_size = PAGE_SIZE - stage_size % PAGE_SIZE;
+	buffer_size = tape->buffer_size;
+	tape->pages_per_buffer = buffer_size / PAGE_SIZE;
+	if (buffer_size % PAGE_SIZE) {
+		tape->pages_per_buffer++;
+		tape->excess_bh_size = PAGE_SIZE - buffer_size % PAGE_SIZE;
 	}
 
-	/* Select the "best" DSC read/write polling freq and pipeline size. */
+	/* select the "best" DSC read/write polling freq */
 	speed = max(*(u16 *)&tape->caps[14], *(u16 *)&tape->caps[8]);
 
-	tape->max_stages = speed * 1000 * 10 / tape->stage_size;
-
-	/* Limit memory use for pipeline to 10% of physical memory */
-	si_meminfo(&si);
-	if (tape->max_stages * tape->stage_size >
-			si.totalram * si.mem_unit / 10)
-		tape->max_stages =
-			si.totalram * si.mem_unit / (10 * tape->stage_size);
-
-	tape->max_stages   = min(tape->max_stages, IDETAPE_MAX_PIPELINE_STAGES);
-	tape->min_pipeline = min(tape->max_stages, IDETAPE_MIN_PIPELINE_STAGES);
-	tape->max_pipeline =
-		min(tape->max_stages * 2, IDETAPE_MAX_PIPELINE_STAGES);
-	if (tape->max_stages == 0) {
-		tape->max_stages   = 1;
-		tape->min_pipeline = 1;
-		tape->max_pipeline = 1;
-	}
-
-	t1 = (tape->stage_size * HZ) / (speed * 1000);
-	tmid = (*(u16 *)&tape->caps[16] * 32 * HZ) / (speed * 125);
-	tn = (IDETAPE_FIFO_THRESHOLD * tape->stage_size * HZ) / (speed * 1000);
-
-	if (tape->max_stages)
-		t = tn;
-	else
-		t = t1;
+	t = (IDETAPE_FIFO_THRESHOLD * tape->buffer_size * HZ) / (speed * 1000);
 
 	/*
 	 * Ensure that the number we got makes sense; limit it within
@@ -3525,11 +2750,10 @@ static void idetape_setup(ide_drive_t *drive, idetape_tape_t *tape, int minor)
 				min_t(unsigned long, t, IDETAPE_DSC_RW_MAX),
 				IDETAPE_DSC_RW_MIN);
 	printk(KERN_INFO "ide-tape: %s <-> %s: %dKBps, %d*%dkB buffer, "
-		"%dkB pipeline, %lums tDSC%s\n",
+		"%lums tDSC%s\n",
 		drive->name, tape->name, *(u16 *)&tape->caps[14],
-		(*(u16 *)&tape->caps[16] * 512) / tape->stage_size,
-		tape->stage_size / 1024,
-		tape->max_stages * tape->stage_size / 1024,
+		(*(u16 *)&tape->caps[16] * 512) / tape->buffer_size,
+		tape->buffer_size / 1024,
 		tape->best_dsc_rw_freq * 1000 / HZ,
 		drive->using_dma ? ", DMA":"");
 
@@ -3553,7 +2777,7 @@ static void ide_tape_release(struct kref *kref)
 	ide_drive_t *drive = tape->drive;
 	struct gendisk *g = tape->disk;
 
-	BUG_ON(tape->first_stage != NULL || tape->merge_stage_size);
+	BUG_ON(tape->merge_bh_size);
 
 	drive->dsc_overlap = 0;
 	drive->driver_data = NULL;
diff --git a/trunk/drivers/ide/ide-taskfile.c b/trunk/drivers/ide/ide-taskfile.c
index a317ca9c46e5..0c908ca3ff79 100644
--- a/trunk/drivers/ide/ide-taskfile.c
+++ b/trunk/drivers/ide/ide-taskfile.c
@@ -33,60 +33,18 @@
 #include <asm/uaccess.h>
 #include <asm/io.h>
 
-void ide_tf_load(ide_drive_t *drive, ide_task_t *task)
+void ide_tf_dump(const char *s, struct ide_taskfile *tf)
 {
-	ide_hwif_t *hwif = drive->hwif;
-	struct ide_taskfile *tf = &task->tf;
-	u8 HIHI = (task->tf_flags & IDE_TFLAG_LBA48) ? 0xE0 : 0xEF;
-
-	if (task->tf_flags & IDE_TFLAG_FLAGGED)
-		HIHI = 0xFF;
-
 #ifdef DEBUG
 	printk("%s: tf: feat 0x%02x nsect 0x%02x lbal 0x%02x "
 		"lbam 0x%02x lbah 0x%02x dev 0x%02x cmd 0x%02x\n",
-		drive->name, tf->feature, tf->nsect, tf->lbal,
+		s, tf->feature, tf->nsect, tf->lbal,
 		tf->lbam, tf->lbah, tf->device, tf->command);
 	printk("%s: hob: nsect 0x%02x lbal 0x%02x "
 		"lbam 0x%02x lbah 0x%02x\n",
-		drive->name, tf->hob_nsect, tf->hob_lbal,
+		s, tf->hob_nsect, tf->hob_lbal,
 		tf->hob_lbam, tf->hob_lbah);
 #endif
-
-	ide_set_irq(drive, 1);
-
-	if ((task->tf_flags & IDE_TFLAG_NO_SELECT_MASK) == 0)
-		SELECT_MASK(drive, 0);
-
-	if (task->tf_flags & IDE_TFLAG_OUT_DATA)
-		hwif->OUTW((tf->hob_data << 8) | tf->data,
-			   hwif->io_ports[IDE_DATA_OFFSET]);
-
-	if (task->tf_flags & IDE_TFLAG_OUT_HOB_FEATURE)
-		hwif->OUTB(tf->hob_feature, hwif->io_ports[IDE_FEATURE_OFFSET]);
-	if (task->tf_flags & IDE_TFLAG_OUT_HOB_NSECT)
-		hwif->OUTB(tf->hob_nsect, hwif->io_ports[IDE_NSECTOR_OFFSET]);
-	if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAL)
-		hwif->OUTB(tf->hob_lbal, hwif->io_ports[IDE_SECTOR_OFFSET]);
-	if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAM)
-		hwif->OUTB(tf->hob_lbam, hwif->io_ports[IDE_LCYL_OFFSET]);
-	if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAH)
-		hwif->OUTB(tf->hob_lbah, hwif->io_ports[IDE_HCYL_OFFSET]);
-
-	if (task->tf_flags & IDE_TFLAG_OUT_FEATURE)
-		hwif->OUTB(tf->feature, hwif->io_ports[IDE_FEATURE_OFFSET]);
-	if (task->tf_flags & IDE_TFLAG_OUT_NSECT)
-		hwif->OUTB(tf->nsect, hwif->io_ports[IDE_NSECTOR_OFFSET]);
-	if (task->tf_flags & IDE_TFLAG_OUT_LBAL)
-		hwif->OUTB(tf->lbal, hwif->io_ports[IDE_SECTOR_OFFSET]);
-	if (task->tf_flags & IDE_TFLAG_OUT_LBAM)
-		hwif->OUTB(tf->lbam, hwif->io_ports[IDE_LCYL_OFFSET]);
-	if (task->tf_flags & IDE_TFLAG_OUT_LBAH)
-		hwif->OUTB(tf->lbah, hwif->io_ports[IDE_HCYL_OFFSET]);
-
-	if (task->tf_flags & IDE_TFLAG_OUT_DEVICE)
-		hwif->OUTB((tf->device & HIHI) | drive->select.all,
-			   hwif->io_ports[IDE_SELECT_OFFSET]);
 }
 
 int taskfile_lib_get_identify (ide_drive_t *drive, u8 *buf)
@@ -149,14 +107,15 @@ ide_startstop_t do_rw_taskfile (ide_drive_t *drive, ide_task_t *task)
 	if (task->tf_flags & IDE_TFLAG_FLAGGED)
 		task->tf_flags |= IDE_TFLAG_FLAGGED_SET_IN_FLAGS;
 
-	if ((task->tf_flags & IDE_TFLAG_DMA_PIO_FALLBACK) == 0)
-		ide_tf_load(drive, task);
+	if ((task->tf_flags & IDE_TFLAG_DMA_PIO_FALLBACK) == 0) {
+		ide_tf_dump(drive->name, tf);
+		hwif->tf_load(drive, task);
+	}
 
 	switch (task->data_phase) {
 	case TASKFILE_MULTI_OUT:
 	case TASKFILE_OUT:
-		hwif->OUTBSYNC(drive, tf->command,
-			       hwif->io_ports[IDE_COMMAND_OFFSET]);
+		hwif->OUTBSYNC(drive, tf->command, hwif->io_ports.command_addr);
 		ndelay(400);	/* FIXME */
 		return pre_task_out_intr(drive, task->rq);
 	case TASKFILE_MULTI_IN:
@@ -284,7 +243,8 @@ static u8 wait_drive_not_busy(ide_drive_t *drive)
 	return stat;
 }
 
-static void ide_pio_sector(ide_drive_t *drive, unsigned int write)
+static void ide_pio_sector(ide_drive_t *drive, struct request *rq,
+			   unsigned int write)
 {
 	ide_hwif_t *hwif = drive->hwif;
 	struct scatterlist *sg = hwif->sg_table;
@@ -324,9 +284,9 @@ static void ide_pio_sector(ide_drive_t *drive, unsigned int write)
 
 	/* do the actual data transfer */
 	if (write)
-		hwif->ata_output_data(drive, buf, SECTOR_WORDS);
+		hwif->output_data(drive, rq, buf, SECTOR_SIZE);
 	else
-		hwif->ata_input_data(drive, buf, SECTOR_WORDS);
+		hwif->input_data(drive, rq, buf, SECTOR_SIZE);
 
 	kunmap_atomic(buf, KM_BIO_SRC_IRQ);
 #ifdef CONFIG_HIGHMEM
@@ -334,13 +294,14 @@ static void ide_pio_sector(ide_drive_t *drive, unsigned int write)
 #endif
 }
 
-static void ide_pio_multi(ide_drive_t *drive, unsigned int write)
+static void ide_pio_multi(ide_drive_t *drive, struct request *rq,
+			  unsigned int write)
 {
 	unsigned int nsect;
 
 	nsect = min_t(unsigned int, drive->hwif->nleft, drive->mult_count);
 	while (nsect--)
-		ide_pio_sector(drive, write);
+		ide_pio_sector(drive, rq, write);
 }
 
 static void ide_pio_datablock(ide_drive_t *drive, struct request *rq,
@@ -363,10 +324,10 @@ static void ide_pio_datablock(ide_drive_t *drive, struct request *rq,
 	switch (drive->hwif->data_phase) {
 	case TASKFILE_MULTI_IN:
 	case TASKFILE_MULTI_OUT:
-		ide_pio_multi(drive, write);
+		ide_pio_multi(drive, rq, write);
 		break;
 	default:
-		ide_pio_sector(drive, write);
+		ide_pio_sector(drive, rq, write);
 		break;
 	}
 
@@ -533,8 +494,7 @@ int ide_raw_taskfile(ide_drive_t *drive, ide_task_t *task, u8 *buf, u16 nsect)
 {
 	struct request rq;
 
-	memset(&rq, 0, sizeof(rq));
-	rq.ref_count = 1;
+	blk_rq_init(NULL, &rq);
 	rq.cmd_type = REQ_TYPE_ATA_TASKFILE;
 	rq.buffer = buf;
 
diff --git a/trunk/drivers/ide/ide.c b/trunk/drivers/ide/ide.c
index bced02f9f2c3..c758dcb13b14 100644
--- a/trunk/drivers/ide/ide.c
+++ b/trunk/drivers/ide/ide.c
@@ -94,12 +94,6 @@ DEFINE_MUTEX(ide_cfg_mtx);
 
 int noautodma = 0;
 
-#ifdef CONFIG_BLK_DEV_IDEACPI
-int ide_noacpi = 0;
-int ide_noacpitfs = 1;
-int ide_noacpionboot = 1;
-#endif
-
 ide_hwif_t ide_hwifs[MAX_HWIFS];	/* master data repository */
 
 static void ide_port_init_devices_data(ide_hwif_t *);
@@ -293,7 +287,7 @@ EXPORT_SYMBOL_GPL(ide_port_unregister_devices);
 
 /**
  *	ide_unregister		-	free an IDE interface
- *	@index: index of interface (will change soon to a pointer)
+ *	@hwif: IDE interface
  *
  *	Perform the final unregister of an IDE interface. At the moment
  *	we don't refcount interfaces so this will also get split up.
@@ -313,19 +307,16 @@ EXPORT_SYMBOL_GPL(ide_port_unregister_devices);
  *	This is raving bonkers.
  */
 
-void ide_unregister(unsigned int index)
+void ide_unregister(ide_hwif_t *hwif)
 {
-	ide_hwif_t *hwif, *g;
+	ide_hwif_t *g;
 	ide_hwgroup_t *hwgroup;
 	int irq_count = 0;
 
-	BUG_ON(index >= MAX_HWIFS);
-
 	BUG_ON(in_interrupt());
 	BUG_ON(irqs_disabled());
 	mutex_lock(&ide_cfg_mtx);
 	spin_lock_irq(&ide_lock);
-	hwif = &ide_hwifs[index];
 	if (!hwif->present)
 		goto abort;
 	__ide_port_unregister_devices(hwif);
@@ -366,7 +357,7 @@ void ide_unregister(unsigned int index)
 		ide_release_dma_engine(hwif);
 
 	/* restore hwif data to pristine status */
-	ide_init_port_data(hwif, index);
+	ide_init_port_data(hwif, hwif->index);
 
 abort:
 	spin_unlock_irq(&ide_lock);
@@ -377,7 +368,7 @@ EXPORT_SYMBOL(ide_unregister);
 
 void ide_init_port_hw(ide_hwif_t *hwif, hw_regs_t *hw)
 {
-	memcpy(hwif->io_ports, hw->io_ports, sizeof(hwif->io_ports));
+	memcpy(&hwif->io_ports, &hw->io_ports, sizeof(hwif->io_ports));
 	hwif->irq = hw->irq;
 	hwif->chipset = hw->chipset;
 	hwif->gendev.parent = hw->dev;
@@ -573,7 +564,7 @@ static int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	if (!(drive->dn % 2))
 		ide_acpi_get_timing(hwif);
 
-	memset(&rq, 0, sizeof(rq));
+	blk_rq_init(NULL, &rq);
 	memset(&rqpm, 0, sizeof(rqpm));
 	memset(&args, 0, sizeof(args));
 	rq.cmd_type = REQ_TYPE_PM_SUSPEND;
@@ -611,7 +602,7 @@ static int generic_ide_resume(struct device *dev)
 
 	ide_acpi_exec_tfs(drive);
 
-	memset(&rq, 0, sizeof(rq));
+	blk_rq_init(NULL, &rq);
 	memset(&rqpm, 0, sizeof(rqpm));
 	memset(&args, 0, sizeof(args));
 	rq.cmd_type = REQ_TYPE_PM_RESUME;
@@ -837,16 +828,6 @@ static int __init match_parm (char *s, const char *keywords[], int vals[], int m
 	return 0;	/* zero = nothing matched */
 }
 
-extern int probe_ali14xx;
-extern int probe_umc8672;
-extern int probe_dtc2278;
-extern int probe_ht6560b;
-extern int probe_qd65xx;
-extern int cmd640_vlb;
-extern int probe_4drives;
-
-static int __initdata is_chipset_set;
-
 /*
  * ide_setup() gets called VERY EARLY during initialization,
  * to handle kernel "command line" strings beginning with "hdx=" or "ide".
@@ -855,14 +836,12 @@ static int __initdata is_chipset_set;
  */
 static int __init ide_setup(char *s)
 {
-	int i, vals[3];
 	ide_hwif_t *hwif;
 	ide_drive_t *drive;
 	unsigned int hw, unit;
+	int vals[3];
 	const char max_drive = 'a' + ((MAX_HWIFS * MAX_DRIVES) - 1);
-	const char max_hwif  = '0' + (MAX_HWIFS - 1);
 
-	
 	if (strncmp(s,"hd",2) == 0 && s[2] == '=')	/* hd= is for hd.c   */
 		return 0;				/* driver and not us */
 
@@ -878,7 +857,7 @@ static int __init ide_setup(char *s)
 
 		printk(" : Enabled support for IDE doublers\n");
 		ide_doubler = 1;
-		return 1;
+		goto obsolete_option;
 	}
 #endif /* CONFIG_BLK_DEV_IDEDOUBLER */
 
@@ -892,17 +871,17 @@ static int __init ide_setup(char *s)
 	if (!strcmp(s, "ide=noacpi")) {
 		//printk(" : Disable IDE ACPI support.\n");
 		ide_noacpi = 1;
-		return 1;
+		goto obsolete_option;
 	}
 	if (!strcmp(s, "ide=acpigtf")) {
 		//printk(" : Enable IDE ACPI _GTF support.\n");
-		ide_noacpitfs = 0;
-		return 1;
+		ide_acpigtf = 1;
+		goto obsolete_option;
 	}
 	if (!strcmp(s, "ide=acpionboot")) {
 		//printk(" : Call IDE ACPI methods on boot.\n");
-		ide_noacpionboot = 0;
-		return 1;
+		ide_acpionboot = 1;
+		goto obsolete_option;
 	}
 #endif /* CONFIG_BLK_DEV_IDEACPI */
 
@@ -912,7 +891,7 @@ static int __init ide_setup(char *s)
 	if (s[0] == 'h' && s[1] == 'd' && s[2] >= 'a' && s[2] <= max_drive) {
 		const char *hd_words[] = {
 			"none", "noprobe", "nowerr", "cdrom", "nodma",
-			"autotune", "noautotune", "-8", "-9", "-10",
+			"-6", "-7", "-8", "-9", "-10",
 			"noflush", "remap", "remap63", "scsi", NULL };
 		unit = s[2] - 'a';
 		hw   = unit / MAX_DRIVES;
@@ -927,28 +906,22 @@ static int __init ide_setup(char *s)
 			case -1: /* "none" */
 			case -2: /* "noprobe" */
 				drive->noprobe = 1;
-				goto done;
+				goto obsolete_option;
 			case -3: /* "nowerr" */
 				drive->bad_wstat = BAD_R_STAT;
-				goto done;
+				goto obsolete_option;
 			case -4: /* "cdrom" */
 				drive->present = 1;
 				drive->media = ide_cdrom;
 				/* an ATAPI device ignores DRDY */
 				drive->ready_stat = 0;
-				goto done;
+				goto obsolete_option;
 			case -5: /* nodma */
 				drive->nodma = 1;
-				goto done;
-			case -6: /* "autotune" */
-				drive->autotune = IDE_TUNE_AUTO;
-				goto obsolete_option;
-			case -7: /* "noautotune" */
-				drive->autotune = IDE_TUNE_NOAUTO;
 				goto obsolete_option;
 			case -11: /* noflush */
 				drive->noflush = 1;
-				goto done;
+				goto obsolete_option;
 			case -12: /* "remap" */
 				drive->remap_0_to_1 = 1;
 				goto obsolete_option;
@@ -966,7 +939,7 @@ static int __init ide_setup(char *s)
 				drive->sect	= drive->bios_sect = vals[2];
 				drive->present	= 1;
 				drive->forced_geom = 1;
-				goto done;
+				goto obsolete_option;
 			default:
 				goto bad_option;
 		}
@@ -984,126 +957,15 @@ static int __init ide_setup(char *s)
 			idebus_parameter = vals[0];
 		} else
 			printk(" -- BAD BUS SPEED! Expected value from 20 to 66");
-		goto done;
+		goto obsolete_option;
 	}
-	/*
-	 * Look for interface options:  "idex="
-	 */
-	if (s[3] >= '0' && s[3] <= max_hwif) {
-		/*
-		 * Be VERY CAREFUL changing this: note hardcoded indexes below
-		 * (-8, -9, -10) are reserved to ease the hardcoding.
-		 */
-		static const char *ide_words[] = {
-			"minus1", "serialize", "minus3", "minus4",
-			"reset", "minus6", "ata66", "minus8", "minus9",
-			"minus10", "four", "qd65xx", "ht6560b", "cmd640_vlb",
-			"dtc2278", "umc8672", "ali14xx", NULL };
-
-		hw = s[3] - '0';
-		hwif = &ide_hwifs[hw];
-		i = match_parm(&s[4], ide_words, vals, 3);
-
-		/*
-		 * Cryptic check to ensure chipset not already set for hwif.
-		 * Note: we can't depend on hwif->chipset here.
-		 */
-		if (i >= -18 && i <= -11) {
-			/* chipset already specified */
-			if (is_chipset_set)
-				goto bad_option;
-			/* these drivers are for "ide0=" only */
-			if (hw != 0)
-				goto bad_hwif;
-			is_chipset_set = 1;
-			printk("\n");
-		}
-
-		switch (i) {
-#ifdef CONFIG_BLK_DEV_ALI14XX
-			case -17: /* "ali14xx" */
-				probe_ali14xx = 1;
-				goto obsolete_option;
-#endif
-#ifdef CONFIG_BLK_DEV_UMC8672
-			case -16: /* "umc8672" */
-				probe_umc8672 = 1;
-				goto obsolete_option;
-#endif
-#ifdef CONFIG_BLK_DEV_DTC2278
-			case -15: /* "dtc2278" */
-				probe_dtc2278 = 1;
-				goto obsolete_option;
-#endif
-#ifdef CONFIG_BLK_DEV_CMD640
-			case -14: /* "cmd640_vlb" */
-				cmd640_vlb = 1;
-				goto obsolete_option;
-#endif
-#ifdef CONFIG_BLK_DEV_HT6560B
-			case -13: /* "ht6560b" */
-				probe_ht6560b = 1;
-				goto obsolete_option;
-#endif
-#ifdef CONFIG_BLK_DEV_QD65XX
-			case -12: /* "qd65xx" */
-				probe_qd65xx = 1;
-				goto obsolete_option;
-#endif
-#ifdef CONFIG_BLK_DEV_4DRIVES
-			case -11: /* "four" drives on one set of ports */
-				probe_4drives = 1;
-				goto obsolete_option;
-#endif
-			case -10: /* minus10 */
-			case -9: /* minus9 */
-			case -8: /* minus8 */
-			case -6:
-			case -4:
-			case -3:
-				goto bad_option;
-			case -7: /* ata66 */
-#ifdef CONFIG_BLK_DEV_IDEPCI
-				/*
-				 * Use ATA_CBL_PATA40_SHORT so drive side
-				 * cable detection is also overriden.
-				 */
-				hwif->cbl = ATA_CBL_PATA40_SHORT;
-				goto obsolete_option;
-#else
-				goto bad_hwif;
-#endif
-			case -5: /* "reset" */
-				hwif->reset = 1;
-				goto obsolete_option;
-			case -2: /* "serialize" */
-				hwif->mate = &ide_hwifs[hw^1];
-				hwif->mate->mate = hwif;
-				hwif->serialized = hwif->mate->serialized = 1;
-				goto obsolete_option;
 
-			case -1:
-			case 0:
-			case 1:
-			case 2:
-			case 3:
-				goto bad_option;
-			default:
-				printk(" -- SUPPORT NOT CONFIGURED IN THIS KERNEL\n");
-				return 1;
-		}
-	}
 bad_option:
 	printk(" -- BAD OPTION\n");
 	return 1;
 obsolete_option:
 	printk(" -- OBSOLETE OPTION, WILL BE REMOVED SOON!\n");
 	return 1;
-bad_hwif:
-	printk("-- NOT SUPPORTED ON ide%d", hw);
-done:
-	printk("\n");
-	return 1;
 }
 
 EXPORT_SYMBOL(ide_lock);
@@ -1239,6 +1101,185 @@ static void ide_port_class_release(struct device *portdev)
 	put_device(&hwif->gendev);
 }
 
+int ide_vlb_clk;
+EXPORT_SYMBOL_GPL(ide_vlb_clk);
+
+module_param_named(vlb_clock, ide_vlb_clk, int, 0);
+MODULE_PARM_DESC(vlb_clock, "VLB clock frequency (in MHz)");
+
+int ide_pci_clk;
+EXPORT_SYMBOL_GPL(ide_pci_clk);
+
+module_param_named(pci_clock, ide_pci_clk, int, 0);
+MODULE_PARM_DESC(pci_clock, "PCI bus clock frequency (in MHz)");
+
+static int ide_set_dev_param_mask(const char *s, struct kernel_param *kp)
+{
+	int a, b, i, j = 1;
+	unsigned int *dev_param_mask = (unsigned int *)kp->arg;
+
+	if (sscanf(s, "%d.%d:%d", &a, &b, &j) != 3 &&
+	    sscanf(s, "%d.%d", &a, &b) != 2)
+		return -EINVAL;
+
+	i = a * MAX_DRIVES + b;
+
+	if (i >= MAX_HWIFS * MAX_DRIVES || j < 0 || j > 1)
+		return -EINVAL;
+
+	if (j)
+		*dev_param_mask |= (1 << i);
+	else
+		*dev_param_mask &= (1 << i);
+
+	return 0;
+}
+
+static unsigned int ide_nodma;
+
+module_param_call(nodma, ide_set_dev_param_mask, NULL, &ide_nodma, 0);
+MODULE_PARM_DESC(nodma, "disallow DMA for a device");
+
+static unsigned int ide_noflush;
+
+module_param_call(noflush, ide_set_dev_param_mask, NULL, &ide_noflush, 0);
+MODULE_PARM_DESC(noflush, "disable flush requests for a device");
+
+static unsigned int ide_noprobe;
+
+module_param_call(noprobe, ide_set_dev_param_mask, NULL, &ide_noprobe, 0);
+MODULE_PARM_DESC(noprobe, "skip probing for a device");
+
+static unsigned int ide_nowerr;
+
+module_param_call(nowerr, ide_set_dev_param_mask, NULL, &ide_nowerr, 0);
+MODULE_PARM_DESC(nowerr, "ignore the WRERR_STAT bit for a device");
+
+static unsigned int ide_cdroms;
+
+module_param_call(cdrom, ide_set_dev_param_mask, NULL, &ide_cdroms, 0);
+MODULE_PARM_DESC(cdrom, "force device as a CD-ROM");
+
+struct chs_geom {
+	unsigned int	cyl;
+	u8		head;
+	u8		sect;
+};
+
+static unsigned int ide_disks;
+static struct chs_geom ide_disks_chs[MAX_HWIFS * MAX_DRIVES];
+
+static int ide_set_disk_chs(const char *str, struct kernel_param *kp)
+{
+	int a, b, c = 0, h = 0, s = 0, i, j = 1;
+
+	if (sscanf(str, "%d.%d:%d,%d,%d", &a, &b, &c, &h, &s) != 5 &&
+	    sscanf(str, "%d.%d:%d", &a, &b, &j) != 3)
+		return -EINVAL;
+
+	i = a * MAX_DRIVES + b;
+
+	if (i >= MAX_HWIFS * MAX_DRIVES || j < 0 || j > 1)
+		return -EINVAL;
+
+	if (c > INT_MAX || h > 255 || s > 255)
+		return -EINVAL;
+
+	if (j)
+		ide_disks |= (1 << i);
+	else
+		ide_disks &= (1 << i);
+
+	ide_disks_chs[i].cyl  = c;
+	ide_disks_chs[i].head = h;
+	ide_disks_chs[i].sect = s;
+
+	return 0;
+}
+
+module_param_call(chs, ide_set_disk_chs, NULL, NULL, 0);
+MODULE_PARM_DESC(chs, "force device as a disk (using CHS)");
+
+static void ide_dev_apply_params(ide_drive_t *drive)
+{
+	int i = drive->hwif->index * MAX_DRIVES + drive->select.b.unit;
+
+	if (ide_nodma & (1 << i)) {
+		printk(KERN_INFO "ide: disallowing DMA for %s\n", drive->name);
+		drive->nodma = 1;
+	}
+	if (ide_noflush & (1 << i)) {
+		printk(KERN_INFO "ide: disabling flush requests for %s\n",
+				 drive->name);
+		drive->noflush = 1;
+	}
+	if (ide_noprobe & (1 << i)) {
+		printk(KERN_INFO "ide: skipping probe for %s\n", drive->name);
+		drive->noprobe = 1;
+	}
+	if (ide_nowerr & (1 << i)) {
+		printk(KERN_INFO "ide: ignoring the WRERR_STAT bit for %s\n",
+				 drive->name);
+		drive->bad_wstat = BAD_R_STAT;
+	}
+	if (ide_cdroms & (1 << i)) {
+		printk(KERN_INFO "ide: forcing %s as a CD-ROM\n", drive->name);
+		drive->present = 1;
+		drive->media = ide_cdrom;
+		/* an ATAPI device ignores DRDY */
+		drive->ready_stat = 0;
+	}
+	if (ide_disks & (1 << i)) {
+		drive->cyl  = drive->bios_cyl  = ide_disks_chs[i].cyl;
+		drive->head = drive->bios_head = ide_disks_chs[i].head;
+		drive->sect = drive->bios_sect = ide_disks_chs[i].sect;
+		drive->forced_geom = 1;
+		printk(KERN_INFO "ide: forcing %s as a disk (%d/%d/%d)\n",
+				 drive->name,
+				 drive->cyl, drive->head, drive->sect);
+		drive->present = 1;
+		drive->media = ide_disk;
+		drive->ready_stat = READY_STAT;
+	}
+}
+
+static unsigned int ide_ignore_cable;
+
+static int ide_set_ignore_cable(const char *s, struct kernel_param *kp)
+{
+	int i, j = 1;
+
+	if (sscanf(s, "%d:%d", &i, &j) != 2 && sscanf(s, "%d", &i) != 1)
+		return -EINVAL;
+
+	if (i >= MAX_HWIFS || j < 0 || j > 1)
+		return -EINVAL;
+
+	if (j)
+		ide_ignore_cable |= (1 << i);
+	else
+		ide_ignore_cable &= (1 << i);
+
+	return 0;
+}
+
+module_param_call(ignore_cable, ide_set_ignore_cable, NULL, NULL, 0);
+MODULE_PARM_DESC(ignore_cable, "ignore cable detection");
+
+void ide_port_apply_params(ide_hwif_t *hwif)
+{
+	int i;
+
+	if (ide_ignore_cable & (1 << hwif->index)) {
+		printk(KERN_INFO "ide: ignoring cable detection for %s\n",
+				 hwif->name);
+		hwif->cbl = ATA_CBL_PATA40_SHORT;
+	}
+
+	for (i = 0; i < MAX_DRIVES; i++)
+		ide_dev_apply_params(&hwif->drives[i]);
+}
+
 /*
  * This is gets invoked once during initialization, to set *everything* up
  */
@@ -1305,11 +1346,6 @@ int __init init_module (void)
 
 void __exit cleanup_module (void)
 {
-	int index;
-
-	for (index = 0; index < MAX_HWIFS; ++index)
-		ide_unregister(index);
-
 	proc_ide_destroy();
 
 	class_destroy(ide_port_class);
diff --git a/trunk/drivers/ide/legacy/ali14xx.c b/trunk/drivers/ide/legacy/ali14xx.c
index 6efbf947c6db..90c65cf97448 100644
--- a/trunk/drivers/ide/legacy/ali14xx.c
+++ b/trunk/drivers/ide/legacy/ali14xx.c
@@ -116,7 +116,7 @@ static void ali14xx_set_pio_mode(ide_drive_t *drive, const u8 pio)
 	int time1, time2;
 	u8 param1, param2, param3, param4;
 	unsigned long flags;
-	int bus_speed = system_bus_clock();
+	int bus_speed = ide_vlb_clk ? ide_vlb_clk : system_bus_clock();
 
 	/* calculate timing, according to PIO mode */
 	time1 = ide_pio_cycle_time(drive, pio);
@@ -202,7 +202,7 @@ static const struct ide_port_info ali14xx_port_info = {
 	.name			= DRV_NAME,
 	.chipset		= ide_ali14xx,
 	.port_ops		= &ali14xx_port_ops,
-	.host_flags		= IDE_HFLAG_NO_DMA | IDE_HFLAG_NO_AUTOTUNE,
+	.host_flags		= IDE_HFLAG_NO_DMA,
 	.pio_mask		= ATA_PIO4,
 };
 
@@ -220,7 +220,7 @@ static int __init ali14xx_probe(void)
 	return ide_legacy_device_add(&ali14xx_port_info, 0);
 }
 
-int probe_ali14xx;
+static int probe_ali14xx;
 
 module_param_named(probe, probe_ali14xx, bool, 0);
 MODULE_PARM_DESC(probe, "probe for ALI M14xx chipsets");
diff --git a/trunk/drivers/ide/legacy/buddha.c b/trunk/drivers/ide/legacy/buddha.c
index f51433bce8e4..5c730e4dd735 100644
--- a/trunk/drivers/ide/legacy/buddha.c
+++ b/trunk/drivers/ide/legacy/buddha.c
@@ -102,7 +102,7 @@ static int buddha_ack_intr(ide_hwif_t *hwif)
 {
     unsigned char ch;
 
-    ch = z_readb(hwif->io_ports[IDE_IRQ_OFFSET]);
+    ch = z_readb(hwif->io_ports.irq_addr);
     if (!(ch & 0x80))
 	    return 0;
     return 1;
@@ -112,9 +112,9 @@ static int xsurf_ack_intr(ide_hwif_t *hwif)
 {
     unsigned char ch;
 
-    ch = z_readb(hwif->io_ports[IDE_IRQ_OFFSET]);
+    ch = z_readb(hwif->io_ports.irq_addr);
     /* X-Surf needs a 0 written to IRQ register to ensure ISA bit A11 stays at 0 */
-    z_writeb(0, hwif->io_ports[IDE_IRQ_OFFSET]); 
+    z_writeb(0, hwif->io_ports.irq_addr);
     if (!(ch & 0x80))
 	    return 0;
     return 1;
@@ -128,13 +128,13 @@ static void __init buddha_setup_ports(hw_regs_t *hw, unsigned long base,
 
 	memset(hw, 0, sizeof(*hw));
 
-	hw->io_ports[IDE_DATA_OFFSET] = base;
+	hw->io_ports.data_addr = base;
 
 	for (i = 1; i < 8; i++)
-		hw->io_ports[i] = base + 2 + i * 4;
+		hw->io_ports_array[i] = base + 2 + i * 4;
 
-	hw->io_ports[IDE_CONTROL_OFFSET] = ctl;
-	hw->io_ports[IDE_IRQ_OFFSET] = irq_port;
+	hw->io_ports.ctl_addr = ctl;
+	hw->io_ports.irq_addr = irq_port;
 
 	hw->irq = IRQ_AMIGA_PORTS;
 	hw->ack_intr = ack_intr;
diff --git a/trunk/drivers/ide/legacy/dtc2278.c b/trunk/drivers/ide/legacy/dtc2278.c
index f7c4ad1c57c0..af791a02a120 100644
--- a/trunk/drivers/ide/legacy/dtc2278.c
+++ b/trunk/drivers/ide/legacy/dtc2278.c
@@ -101,8 +101,7 @@ static const struct ide_port_info dtc2278_port_info __initdata = {
 				  IDE_HFLAG_IO_32BIT |
 				  /* disallow ->io_32bit changes */
 				  IDE_HFLAG_NO_IO_32BIT |
-				  IDE_HFLAG_NO_DMA |
-				  IDE_HFLAG_NO_AUTOTUNE,
+				  IDE_HFLAG_NO_DMA,
 	.pio_mask		= ATA_PIO4,
 };
 
@@ -131,7 +130,7 @@ static int __init dtc2278_probe(void)
 	return ide_legacy_device_add(&dtc2278_port_info, 0);
 }
 
-int probe_dtc2278 = 0;
+static int probe_dtc2278;
 
 module_param_named(probe, probe_dtc2278, bool, 0);
 MODULE_PARM_DESC(probe, "probe for DTC2278xx chipsets");
diff --git a/trunk/drivers/ide/legacy/falconide.c b/trunk/drivers/ide/legacy/falconide.c
index 5c19c422c5cc..83555ca513b5 100644
--- a/trunk/drivers/ide/legacy/falconide.c
+++ b/trunk/drivers/ide/legacy/falconide.c
@@ -44,18 +44,40 @@
 int falconide_intr_lock;
 EXPORT_SYMBOL(falconide_intr_lock);
 
+static void falconide_input_data(ide_drive_t *drive, struct request *rq,
+				 void *buf, unsigned int len)
+{
+	unsigned long data_addr = drive->hwif->io_ports.data_addr;
+
+	if (drive->media == ide_disk && rq && rq->cmd_type == REQ_TYPE_FS)
+		return insw(data_addr, buf, (len + 1) / 2);
+
+	insw_swapw(data_addr, buf, (len + 1) / 2);
+}
+
+static void falconide_output_data(ide_drive_t *drive, struct request *rq,
+				  void *buf, unsigned int len)
+{
+	unsigned long data_addr = drive->hwif->io_ports.data_addr;
+
+	if (drive->media == ide_disk && rq && rq->cmd_type == REQ_TYPE_FS)
+		return outsw(data_adr, buf, (len + 1) / 2);
+
+	outsw_swapw(data_addr, buf, (len + 1) / 2);
+}
+
 static void __init falconide_setup_ports(hw_regs_t *hw)
 {
 	int i;
 
 	memset(hw, 0, sizeof(*hw));
 
-	hw->io_ports[IDE_DATA_OFFSET] = ATA_HD_BASE;
+	hw->io_ports.data_addr = ATA_HD_BASE;
 
 	for (i = 1; i < 8; i++)
-		hw->io_ports[i] = ATA_HD_BASE + 1 + i * 4;
+		hw->io_ports_array[i] = ATA_HD_BASE + 1 + i * 4;
 
-	hw->io_ports[IDE_CONTROL_OFFSET] = ATA_HD_BASE + ATA_HD_CONTROL;
+	hw->io_ports.ctl_addr = ATA_HD_BASE + ATA_HD_CONTROL;
 
 	hw->irq = IRQ_MFP_IDE;
 	hw->ack_intr = NULL;
@@ -90,6 +112,10 @@ static int __init falconide_init(void)
 		ide_init_port_data(hwif, index);
 		ide_init_port_hw(hwif, &hw);
 
+		/* Atari has a byte-swapped IDE interface */
+		hwif->input_data  = falconide_input_data;
+		hwif->output_data = falconide_output_data;
+
 		ide_get_lock(NULL, NULL);
 		ide_device_add(idx, NULL);
 		ide_release_lock();
diff --git a/trunk/drivers/ide/legacy/gayle.c b/trunk/drivers/ide/legacy/gayle.c
index a0c9601bdaf0..a9c2593a898c 100644
--- a/trunk/drivers/ide/legacy/gayle.c
+++ b/trunk/drivers/ide/legacy/gayle.c
@@ -63,6 +63,8 @@
 #define GAYLE_HAS_CONTROL_REG	(!ide_doubler)
 #define GAYLE_IDEREG_SIZE	(ide_doubler ? 0x1000 : 0x2000)
 int ide_doubler = 0;	/* support IDE doublers? */
+module_param_named(doubler, ide_doubler, bool, 0);
+MODULE_PARM_DESC(doubler, "enable support for IDE doublers");
 #endif /* CONFIG_BLK_DEV_IDEDOUBLER */
 
 
@@ -74,7 +76,7 @@ static int gayle_ack_intr_a4000(ide_hwif_t *hwif)
 {
     unsigned char ch;
 
-    ch = z_readb(hwif->io_ports[IDE_IRQ_OFFSET]);
+    ch = z_readb(hwif->io_ports.irq_addr);
     if (!(ch & GAYLE_IRQ_IDE))
 	return 0;
     return 1;
@@ -84,11 +86,11 @@ static int gayle_ack_intr_a1200(ide_hwif_t *hwif)
 {
     unsigned char ch;
 
-    ch = z_readb(hwif->io_ports[IDE_IRQ_OFFSET]);
+    ch = z_readb(hwif->io_ports.irq_addr);
     if (!(ch & GAYLE_IRQ_IDE))
 	return 0;
-    (void)z_readb(hwif->io_ports[IDE_STATUS_OFFSET]);
-    z_writeb(0x7c, hwif->io_ports[IDE_IRQ_OFFSET]);
+    (void)z_readb(hwif->io_ports.status_addr);
+    z_writeb(0x7c, hwif->io_ports.irq_addr);
     return 1;
 }
 
@@ -100,13 +102,13 @@ static void __init gayle_setup_ports(hw_regs_t *hw, unsigned long base,
 
 	memset(hw, 0, sizeof(*hw));
 
-	hw->io_ports[IDE_DATA_OFFSET] = base;
+	hw->io_ports.data_addr = base;
 
 	for (i = 1; i < 8; i++)
-		hw->io_ports[i] = base + 2 + i * 4;
+		hw->io_ports_array[i] = base + 2 + i * 4;
 
-	hw->io_ports[IDE_CONTROL_OFFSET] = ctl;
-	hw->io_ports[IDE_IRQ_OFFSET] = irq_port;
+	hw->io_ports.ctl_addr = ctl;
+	hw->io_ports.irq_addr = irq_port;
 
 	hw->irq = IRQ_AMIGA_PORTS;
 	hw->ack_intr = ack_intr;
diff --git a/trunk/drivers/ide/legacy/ht6560b.c b/trunk/drivers/ide/legacy/ht6560b.c
index 702d8deb5780..4fe516df9f74 100644
--- a/trunk/drivers/ide/legacy/ht6560b.c
+++ b/trunk/drivers/ide/legacy/ht6560b.c
@@ -157,8 +157,8 @@ static void ht6560b_selectproc (ide_drive_t *drive)
 		/*
 		 * Set timing for this drive:
 		 */
-		outb(timing, hwif->io_ports[IDE_SELECT_OFFSET]);
-		(void)inb(hwif->io_ports[IDE_STATUS_OFFSET]);
+		outb(timing, hwif->io_ports.device_addr);
+		(void)inb(hwif->io_ports.status_addr);
 #ifdef DEBUG
 		printk("ht6560b: %s: select=%#x timing=%#x\n",
 			drive->name, select, timing);
@@ -212,8 +212,8 @@ static u8 ht_pio2timings(ide_drive_t *drive, const u8 pio)
 {
 	int active_time, recovery_time;
 	int active_cycles, recovery_cycles;
-	int bus_speed = system_bus_clock();
-	
+	int bus_speed = ide_vlb_clk ? ide_vlb_clk : system_bus_clock();
+
         if (pio) {
 		unsigned int cycle_time;
 
@@ -323,7 +323,7 @@ static void __init ht6560b_port_init_devs(ide_hwif_t *hwif)
 	hwif->drives[1].drive_data = t;
 }
 
-int probe_ht6560b = 0;
+static int probe_ht6560b;
 
 module_param_named(probe, probe_ht6560b, bool, 0);
 MODULE_PARM_DESC(probe, "probe for HT6560B chipset");
@@ -340,7 +340,6 @@ static const struct ide_port_info ht6560b_port_info __initdata = {
 	.port_ops		= &ht6560b_port_ops,
 	.host_flags		= IDE_HFLAG_SERIALIZE | /* is this needed? */
 				  IDE_HFLAG_NO_DMA |
-				  IDE_HFLAG_NO_AUTOTUNE |
 				  IDE_HFLAG_ABUSE_PREFETCH,
 	.pio_mask		= ATA_PIO4,
 };
diff --git a/trunk/drivers/ide/legacy/ide-4drives.c b/trunk/drivers/ide/legacy/ide-4drives.c
index 17f94d0cb539..ecae916a3385 100644
--- a/trunk/drivers/ide/legacy/ide-4drives.c
+++ b/trunk/drivers/ide/legacy/ide-4drives.c
@@ -6,7 +6,7 @@
 
 #define DRV_NAME "ide-4drives"
 
-int probe_4drives;
+static int probe_4drives;
 
 module_param_named(probe, probe_4drives, bool, 0);
 MODULE_PARM_DESC(probe, "probe for generic IDE chipset with 4 drives/port");
diff --git a/trunk/drivers/ide/legacy/ide-cs.c b/trunk/drivers/ide/legacy/ide-cs.c
index 855e157b18d3..aa2ea3deac85 100644
--- a/trunk/drivers/ide/legacy/ide-cs.c
+++ b/trunk/drivers/ide/legacy/ide-cs.c
@@ -140,8 +140,8 @@ static void ide_detach(struct pcmcia_device *link)
 
     ide_release(link);
 
-    release_region(hwif->io_ports[IDE_CONTROL_OFFSET], 1);
-    release_region(hwif->io_ports[IDE_DATA_OFFSET], 8);
+    release_region(hwif->io_ports.ctl_addr, 1);
+    release_region(hwif->io_ports.data_addr, 8);
 
     kfree(info);
 } /* ide_detach */
@@ -183,11 +183,7 @@ static ide_hwif_t *idecs_register(unsigned long io, unsigned long ctl,
 
     i = hwif->index;
 
-    if (hwif->present)
-	ide_unregister(i);
-    else
-	ide_init_port_data(hwif, i);
-
+    ide_init_port_data(hwif, i);
     ide_init_port_hw(hwif, &hw);
     hwif->port_ops = &idecs_port_ops;
 
@@ -390,7 +386,7 @@ void ide_release(struct pcmcia_device *link)
     if (info->ndev) {
 	/* FIXME: if this fails we need to queue the cleanup somehow
 	   -- need to investigate the required PCMCIA magic */
-	ide_unregister(hwif->index);
+	ide_unregister(hwif);
     }
     info->ndev = 0;
 
diff --git a/trunk/drivers/ide/legacy/ide_platform.c b/trunk/drivers/ide/legacy/ide_platform.c
index 822f48b05c70..d3bc3f24e05d 100644
--- a/trunk/drivers/ide/legacy/ide_platform.c
+++ b/trunk/drivers/ide/legacy/ide_platform.c
@@ -30,14 +30,14 @@ static void __devinit plat_ide_setup_ports(hw_regs_t *hw,
 	unsigned long port = (unsigned long)base;
 	int i;
 
-	hw->io_ports[IDE_DATA_OFFSET] = port;
+	hw->io_ports.data_addr = port;
 
 	port += (1 << pdata->ioport_shift);
-	for (i = IDE_ERROR_OFFSET; i <= IDE_STATUS_OFFSET;
+	for (i = 1; i <= 7;
 	     i++, port += (1 << pdata->ioport_shift))
-		hw->io_ports[i] = port;
+		hw->io_ports_array[i] = port;
 
-	hw->io_ports[IDE_CONTROL_OFFSET] = (unsigned long)ctrl;
+	hw->io_ports.ctl_addr = (unsigned long)ctrl;
 
 	hw->irq = irq;
 
@@ -101,8 +101,10 @@ static int __devinit plat_ide_probe(struct platform_device *pdev)
 
 	ide_init_port_hw(hwif, &hw);
 
-	if (mmio)
+	if (mmio) {
+		hwif->host_flags = IDE_HFLAG_MMIO;
 		default_hwif_mmiops(hwif);
+	}
 
 	idx[0] = hwif->index;
 
@@ -120,7 +122,7 @@ static int __devexit plat_ide_remove(struct platform_device *pdev)
 {
 	ide_hwif_t *hwif = pdev->dev.driver_data;
 
-	ide_unregister(hwif->index);
+	ide_unregister(hwif);
 
 	return 0;
 }
diff --git a/trunk/drivers/ide/legacy/macide.c b/trunk/drivers/ide/legacy/macide.c
index 26546d0afc7f..1f527bbf8d96 100644
--- a/trunk/drivers/ide/legacy/macide.c
+++ b/trunk/drivers/ide/legacy/macide.c
@@ -72,9 +72,9 @@ static void __init macide_setup_ports(hw_regs_t *hw, unsigned long base,
 	memset(hw, 0, sizeof(*hw));
 
 	for (i = 0; i < 8; i++)
-		hw->io_ports[i] = base + i * 4;
+		hw->io_ports_array[i] = base + i * 4;
 
-	hw->io_ports[IDE_CONTROL_OFFSET] = base + IDE_CONTROL;
+	hw->io_ports.ctl_addr = base + IDE_CONTROL;
 
 	hw->irq = irq;
 	hw->ack_intr = ack_intr;
diff --git a/trunk/drivers/ide/legacy/q40ide.c b/trunk/drivers/ide/legacy/q40ide.c
index f23999dd3d46..6f535d00e638 100644
--- a/trunk/drivers/ide/legacy/q40ide.c
+++ b/trunk/drivers/ide/legacy/q40ide.c
@@ -36,23 +36,6 @@ static const unsigned long pcide_bases[Q40IDE_NUM_HWIFS] = {
     PCIDE_BASE6 */
 };
 
-
-    /*
-     *  Offsets from one of the above bases
-     */
-
-/* used to do addr translation here but it is easier to do in setup ports */
-/*#define IDE_OFF_B(x)	((unsigned long)Q40_ISA_IO_B((IDE_##x##_OFFSET)))*/
-
-#define IDE_OFF_B(x)	((unsigned long)((IDE_##x##_OFFSET)))
-#define IDE_OFF_W(x)	((unsigned long)((IDE_##x##_OFFSET)))
-
-static const int pcide_offsets[IDE_NR_PORTS] = {
-    IDE_OFF_W(DATA), IDE_OFF_B(ERROR), IDE_OFF_B(NSECTOR), IDE_OFF_B(SECTOR),
-    IDE_OFF_B(LCYL), IDE_OFF_B(HCYL), 6 /*IDE_OFF_B(CURRENT)*/, IDE_OFF_B(STATUS),
-    518/*IDE_OFF(CMD)*/
-};
-
 static int q40ide_default_irq(unsigned long base)
 {
            switch (base) {
@@ -68,29 +51,48 @@ static int q40ide_default_irq(unsigned long base)
 /*
  * Addresses are pretranslated for Q40 ISA access.
  */
-void q40_ide_setup_ports ( hw_regs_t *hw,
-			unsigned long base, int *offsets,
-			unsigned long ctrl, unsigned long intr,
+static void q40_ide_setup_ports(hw_regs_t *hw, unsigned long base,
 			ide_ack_intr_t *ack_intr,
 			int irq)
 {
-	int i;
-
 	memset(hw, 0, sizeof(hw_regs_t));
-	for (i = 0; i < IDE_NR_PORTS; i++) {
-		/* BIG FAT WARNING: 
-		   assumption: only DATA port is ever used in 16 bit mode */
-		if ( i==0 )
-			hw->io_ports[i] = Q40_ISA_IO_W(base + offsets[i]);
-		else
-			hw->io_ports[i] = Q40_ISA_IO_B(base + offsets[i]);
-	}
+	/* BIG FAT WARNING: 
+	   assumption: only DATA port is ever used in 16 bit mode */
+	hw->io_ports.data_addr = Q40_ISA_IO_W(base);
+	hw->io_ports.error_addr = Q40_ISA_IO_B(base + 1);
+	hw->io_ports.nsect_addr = Q40_ISA_IO_B(base + 2);
+	hw->io_ports.lbal_addr = Q40_ISA_IO_B(base + 3);
+	hw->io_ports.lbam_addr = Q40_ISA_IO_B(base + 4);
+	hw->io_ports.lbah_addr = Q40_ISA_IO_B(base + 5);
+	hw->io_ports.device_addr = Q40_ISA_IO_B(base + 6);
+	hw->io_ports.status_addr = Q40_ISA_IO_B(base + 7);
+	hw->io_ports.ctl_addr = Q40_ISA_IO_B(base + 0x206);
 
 	hw->irq = irq;
 	hw->ack_intr = ack_intr;
 }
 
+static void q40ide_input_data(ide_drive_t *drive, struct request *rq,
+			      void *buf, unsigned int len)
+{
+	unsigned long data_addr = drive->hwif->io_ports.data_addr;
+
+	if (drive->media == ide_disk && rq && rq->cmd_type == REQ_TYPE_FS)
+		return insw(data_addr, buf, (len + 1) / 2);
 
+	insw_swapw(data_addr, buf, (len + 1) / 2);
+}
+
+static void q40ide_output_data(ide_drive_t *drive, struct request *rq,
+			       void *buf, unsigned int len)
+{
+	unsigned long data_addr = drive->hwif->io_ports.data_addr;
+
+	if (drive->media == ide_disk && rq && rq->cmd_type == REQ_TYPE_FS)
+		return outsw(data_addr, buf, (len + 1) / 2);
+
+	outsw_swapw(data_addr, buf, (len + 1) / 2);
+}
 
 /* 
  * the static array is needed to have the name reported in /proc/ioports,
@@ -131,9 +133,8 @@ static int __init q40ide_init(void)
 		release_region(pcide_bases[i], 8);
 		continue;
 	}
-	q40_ide_setup_ports(&hw,(unsigned long) pcide_bases[i], (int *)pcide_offsets, 
-			pcide_bases[i]+0x206, 
-			0, NULL,
+	q40_ide_setup_ports(&hw, pcide_bases[i],
+			NULL,
 //			m68kide_iops,
 			q40ide_default_irq(pcide_bases[i]));
 
@@ -142,6 +143,10 @@ static int __init q40ide_init(void)
 		ide_init_port_data(hwif, hwif->index);
 		ide_init_port_hw(hwif, &hw);
 
+		/* Q40 has a byte-swapped IDE interface */
+		hwif->input_data  = q40ide_input_data;
+		hwif->output_data = q40ide_output_data;
+
 		idx[i] = hwif->index;
 	}
     }
diff --git a/trunk/drivers/ide/legacy/qd65xx.c b/trunk/drivers/ide/legacy/qd65xx.c
index 15a99aae0cf9..6424af154325 100644
--- a/trunk/drivers/ide/legacy/qd65xx.c
+++ b/trunk/drivers/ide/legacy/qd65xx.c
@@ -11,11 +11,7 @@
  *
  * QDI QD6500/QD6580 EIDE controller fast support
  *
- * Please set local bus speed using kernel parameter idebus
- * 	for example, "idebus=33" stands for 33Mhz VLbus
  * To activate controller support, use "ide0=qd65xx"
- * To enable tuning, use "hda=autotune hdb=autotune"
- * To enable 2nd channel tuning (qd6580 only), use "hdc=autotune hdd=autotune"
  */
 
 /*
@@ -114,17 +110,18 @@ static void qd65xx_select(ide_drive_t *drive)
 
 static u8 qd6500_compute_timing (ide_hwif_t *hwif, int active_time, int recovery_time)
 {
-	u8 active_cycle,recovery_cycle;
+	int clk = ide_vlb_clk ? ide_vlb_clk : system_bus_clock();
+	u8 act_cyc, rec_cyc;
 
-	if (system_bus_clock()<=33) {
-		active_cycle =   9  - IDE_IN(active_time   * system_bus_clock() / 1000 + 1, 2, 9);
-		recovery_cycle = 15 - IDE_IN(recovery_time * system_bus_clock() / 1000 + 1, 0, 15);
+	if (clk <= 33) {
+		act_cyc =  9 - IDE_IN(active_time   * clk / 1000 + 1, 2,  9);
+		rec_cyc = 15 - IDE_IN(recovery_time * clk / 1000 + 1, 0, 15);
 	} else {
-		active_cycle =   8  - IDE_IN(active_time   * system_bus_clock() / 1000 + 1, 1, 8);
-		recovery_cycle = 18 - IDE_IN(recovery_time * system_bus_clock() / 1000 + 1, 3, 18);
+		act_cyc =  8 - IDE_IN(active_time   * clk / 1000 + 1, 1,  8);
+		rec_cyc = 18 - IDE_IN(recovery_time * clk / 1000 + 1, 3, 18);
 	}
 
-	return((recovery_cycle<<4) | 0x08 | active_cycle);
+	return (rec_cyc << 4) | 0x08 | act_cyc;
 }
 
 /*
@@ -135,10 +132,13 @@ static u8 qd6500_compute_timing (ide_hwif_t *hwif, int active_time, int recovery
 
 static u8 qd6580_compute_timing (int active_time, int recovery_time)
 {
-	u8 active_cycle   = 17 - IDE_IN(active_time   * system_bus_clock() / 1000 + 1, 2, 17);
-	u8 recovery_cycle = 15 - IDE_IN(recovery_time * system_bus_clock() / 1000 + 1, 2, 15);
+	int clk = ide_vlb_clk ? ide_vlb_clk : system_bus_clock();
+	u8 act_cyc, rec_cyc;
 
-	return((recovery_cycle<<4) | active_cycle);
+	act_cyc = 17 - IDE_IN(active_time   * clk / 1000 + 1, 2, 17);
+	rec_cyc = 15 - IDE_IN(recovery_time * clk / 1000 + 1, 2, 15);
+
+	return (rec_cyc << 4) | act_cyc;
 }
 
 /*
@@ -322,8 +322,7 @@ static const struct ide_port_info qd65xx_port_info __initdata = {
 	.name			= DRV_NAME,
 	.chipset		= ide_qd65xx,
 	.host_flags		= IDE_HFLAG_IO_32BIT |
-				  IDE_HFLAG_NO_DMA |
-				  IDE_HFLAG_NO_AUTOTUNE,
+				  IDE_HFLAG_NO_DMA,
 	.pio_mask		= ATA_PIO4,
 };
 
@@ -399,7 +398,7 @@ static int __init qd_probe(int base)
 	return rc;
 }
 
-int probe_qd65xx = 0;
+static int probe_qd65xx;
 
 module_param_named(probe, probe_qd65xx, bool, 0);
 MODULE_PARM_DESC(probe, "probe for QD65xx chipsets");
diff --git a/trunk/drivers/ide/legacy/umc8672.c b/trunk/drivers/ide/legacy/umc8672.c
index 17d515329fe0..b54a14a57755 100644
--- a/trunk/drivers/ide/legacy/umc8672.c
+++ b/trunk/drivers/ide/legacy/umc8672.c
@@ -130,7 +130,7 @@ static const struct ide_port_info umc8672_port_info __initdata = {
 	.name			= DRV_NAME,
 	.chipset		= ide_umc8672,
 	.port_ops		= &umc8672_port_ops,
-	.host_flags		= IDE_HFLAG_NO_DMA | IDE_HFLAG_NO_AUTOTUNE,
+	.host_flags		= IDE_HFLAG_NO_DMA,
 	.pio_mask		= ATA_PIO4,
 };
 
@@ -158,7 +158,7 @@ static int __init umc8672_probe(void)
 	return ide_legacy_device_add(&umc8672_port_info, 0);
 }
 
-int probe_umc8672;
+static int probe_umc8672;
 
 module_param_named(probe, probe_umc8672, bool, 0);
 MODULE_PARM_DESC(probe, "probe for UMC8672 chipset");
diff --git a/trunk/drivers/ide/mips/au1xxx-ide.c b/trunk/drivers/ide/mips/au1xxx-ide.c
index 3485a310c95b..1a6c27b32498 100644
--- a/trunk/drivers/ide/mips/au1xxx-ide.c
+++ b/trunk/drivers/ide/mips/au1xxx-ide.c
@@ -48,8 +48,6 @@
 
 static _auide_hwif auide_hwif;
 
-static int auide_ddma_init(_auide_hwif *auide);
-
 #if defined(CONFIG_BLK_DEV_IDE_AU1XXX_PIO_DBDMA)
 
 void auide_insw(unsigned long port, void *addr, u32 count)
@@ -88,6 +86,17 @@ void auide_outsw(unsigned long port, void *addr, u32 count)
 	ctp->cur_ptr = au1xxx_ddma_get_nextptr_virt(dp);
 }
 
+static void au1xxx_input_data(ide_drive_t *drive, struct request *rq,
+			      void *buf, unsigned int len)
+{
+	auide_insw(drive->hwif->io_ports.data_addr, buf, (len + 1) / 2);
+}
+
+static void au1xxx_output_data(ide_drive_t *drive, struct request *rq,
+			       void *buf, unsigned int len)
+{
+	auide_outsw(drive->hwif->io_ports.data_addr, buf, (len + 1) / 2);
+}
 #endif
 
 static void au1xxx_set_pio_mode(ide_drive_t *drive, const u8 pio)
@@ -359,7 +368,7 @@ static void auide_ddma_rx_callback(int irq, void *param)
 static void auide_init_dbdma_dev(dbdev_tab_t *dev, u32 dev_id, u32 tsize, u32 devwidth, u32 flags)
 {
 	dev->dev_id          = dev_id;
-	dev->dev_physaddr    = (u32)AU1XXX_ATA_PHYS_ADDR;
+	dev->dev_physaddr    = (u32)IDE_PHYS_ADDR;
 	dev->dev_intlevel    = 0;
 	dev->dev_intpolarity = 0;
 	dev->dev_tsize       = tsize;
@@ -397,7 +406,7 @@ static int auide_ddma_init(ide_hwif_t *hwif, const struct ide_port_info *d)
 	dbdev_tab_t source_dev_tab, target_dev_tab;
 	u32 dev_id, tsize, devwidth, flags;
 
-	dev_id   = AU1XXX_ATA_DDMA_REQ;
+	dev_id	 = IDE_DDMA_REQ;
 
 	tsize    =  8; /*  1 */
 	devwidth = 32; /* 16 */
@@ -502,15 +511,14 @@ static int auide_ddma_init(ide_hwif_t *hwif, const struct ide_port_info *d)
 static void auide_setup_ports(hw_regs_t *hw, _auide_hwif *ahwif)
 {
 	int i;
-	unsigned long *ata_regs = hw->io_ports;
+	unsigned long *ata_regs = hw->io_ports_array;
 
 	/* FIXME? */
-	for (i = 0; i < IDE_CONTROL_OFFSET; i++) {
-		*ata_regs++ = ahwif->regbase + (i << AU1XXX_ATA_REG_OFFSET);
-	}
+	for (i = 0; i < 8; i++)
+		*ata_regs++ = ahwif->regbase + (i << IDE_REG_SHIFT);
 
 	/* set the Alternative Status register */
-	*ata_regs = ahwif->regbase + (14 << AU1XXX_ATA_REG_OFFSET);
+	*ata_regs = ahwif->regbase + (14 << IDE_REG_SHIFT);
 }
 
 static const struct ide_port_ops au1xxx_port_ops = {
@@ -599,8 +607,8 @@ static int au_ide_probe(struct device *dev)
 	*/
 
 #ifdef CONFIG_BLK_DEV_IDE_AU1XXX_PIO_DBDMA	
-	hwif->INSW                      = auide_insw;
-	hwif->OUTSW                     = auide_outsw;
+	hwif->input_data  = au1xxx_input_data;
+	hwif->output_data = au1xxx_output_data;
 #endif
 	hwif->select_data               = 0;    /* no chipset-specific code */
 	hwif->config_data               = 0;    /* no chipset-specific code */
@@ -627,7 +635,7 @@ static int au_ide_remove(struct device *dev)
 	ide_hwif_t *hwif = dev_get_drvdata(dev);
 	_auide_hwif *ahwif = &auide_hwif;
 
-	ide_unregister(hwif->index);
+	ide_unregister(hwif);
 
 	iounmap((void *)ahwif->regbase);
 
diff --git a/trunk/drivers/ide/mips/swarm.c b/trunk/drivers/ide/mips/swarm.c
index 112fe566bb93..712d17bdd470 100644
--- a/trunk/drivers/ide/mips/swarm.c
+++ b/trunk/drivers/ide/mips/swarm.c
@@ -109,14 +109,15 @@ static int __devinit swarm_ide_probe(struct device *dev)
 	base = ioremap(offset, size);
 
 	/* Setup MMIO ops.  */
+	hwif->host_flags = IDE_HFLAG_MMIO;
 	default_hwif_mmiops(hwif);
 
 	hwif->chipset = ide_generic;
 
-	for (i = IDE_DATA_OFFSET; i <= IDE_STATUS_OFFSET; i++)
-		hwif->io_ports[i] =
+	for (i = 0; i <= 7; i++)
+		hwif->io_ports_array[i] =
 				(unsigned long)(base + ((0x1f0 + i) << 5));
-	hwif->io_ports[IDE_CONTROL_OFFSET] =
+	hwif->io_ports.ctl_addr =
 				(unsigned long)(base + (0x3f6 << 5));
 	hwif->irq = K_INT_GB_IDE;
 
diff --git a/trunk/drivers/ide/pci/aec62xx.c b/trunk/drivers/ide/pci/aec62xx.c
index ca16f37f9486..7f46c224b7c4 100644
--- a/trunk/drivers/ide/pci/aec62xx.c
+++ b/trunk/drivers/ide/pci/aec62xx.c
@@ -140,7 +140,7 @@ static void aec_set_pio_mode(ide_drive_t *drive, const u8 pio)
 
 static unsigned int __devinit init_chipset_aec62xx(struct pci_dev *dev, const char *name)
 {
-	int bus_speed = system_bus_clock();
+	int bus_speed = ide_pci_clk ? ide_pci_clk : system_bus_clock();
 
 	if (bus_speed <= 33)
 		pci_set_drvdata(dev, (void *) aec6xxx_33_base);
diff --git a/trunk/drivers/ide/pci/alim15x3.c b/trunk/drivers/ide/pci/alim15x3.c
index b5a3bc33e167..b36a22b8c213 100644
--- a/trunk/drivers/ide/pci/alim15x3.c
+++ b/trunk/drivers/ide/pci/alim15x3.c
@@ -38,8 +38,6 @@
 
 #include <asm/io.h>
 
-#define DISPLAY_ALI_TIMINGS
-
 /*
  *	ALi devices are not plug in. Otherwise these static values would
  *	need to go. They ought to go away anyway
@@ -49,236 +47,6 @@ static u8 m5229_revision;
 static u8 chip_is_1543c_e;
 static struct pci_dev *isa_dev;
 
-#if defined(DISPLAY_ALI_TIMINGS) && defined(CONFIG_IDE_PROC_FS)
-#include <linux/stat.h>
-#include <linux/proc_fs.h>
-
-static u8 ali_proc = 0;
-
-static struct pci_dev *bmide_dev;
-
-static char *fifo[4] = {
-	"FIFO Off",
-	"FIFO On ",
-	"DMA mode",
-	"PIO mode" };
-
-static char *udmaT[8] = {
-	"1.5T",
-	"  2T",
-	"2.5T",
-	"  3T",
-	"3.5T",
-	"  4T",
-	"  6T",
-	"  8T"
-};
-
-static char *channel_status[8] = {
-	"OK            ",
-	"busy          ",
-	"DRQ           ",
-	"DRQ busy      ",
-	"error         ",
-	"error busy    ",
-	"error DRQ     ",
-	"error DRQ busy"
-};
-
-/**
- *	ali_get_info		-	generate proc file for ALi IDE
- *	@buffer: buffer to fill
- *	@addr: address of user start in buffer
- *	@offset: offset into 'file'
- *	@count: buffer count
- *
- *	Walks the Ali devices and outputs summary data on the tuning and
- *	anything else that will help with debugging
- */
- 
-static int ali_get_info (char *buffer, char **addr, off_t offset, int count)
-{
-	unsigned long bibma;
-	u8 reg53h, reg5xh, reg5yh, reg5xh1, reg5yh1, c0, c1, rev, tmp;
-	char *q, *p = buffer;
-
-	/* fetch rev. */
-	pci_read_config_byte(bmide_dev, 0x08, &rev);
-	if (rev >= 0xc1)	/* M1543C or newer */
-		udmaT[7] = " ???";
-	else
-		fifo[3]  = "   ???  ";
-
-	/* first fetch bibma: */
-	
-	bibma = pci_resource_start(bmide_dev, 4);
-
-	/*
-	 * at that point bibma+0x2 et bibma+0xa are byte
-	 * registers to investigate:
-	 */
-	c0 = inb(bibma + 0x02);
-	c1 = inb(bibma + 0x0a);
-
-	p += sprintf(p,
-		"\n                                Ali M15x3 Chipset.\n");
-	p += sprintf(p,
-		"                                ------------------\n");
-	pci_read_config_byte(bmide_dev, 0x78, &reg53h);
-	p += sprintf(p, "PCI Clock: %d.\n", reg53h);
-
-	pci_read_config_byte(bmide_dev, 0x53, &reg53h);
-	p += sprintf(p,
-		"CD_ROM FIFO:%s, CD_ROM DMA:%s\n",
-		(reg53h & 0x02) ? "Yes" : "No ",
-		(reg53h & 0x01) ? "Yes" : "No " );
-	pci_read_config_byte(bmide_dev, 0x74, &reg53h);
-	p += sprintf(p,
-		"FIFO Status: contains %d Words, runs%s%s\n\n",
-		(reg53h & 0x3f),
-		(reg53h & 0x40) ? " OVERWR" : "",
-		(reg53h & 0x80) ? " OVERRD." : "." );
-
-	p += sprintf(p,
-		"-------------------primary channel"
-		"-------------------secondary channel"
-		"---------\n\n");
-
-	pci_read_config_byte(bmide_dev, 0x09, &reg53h);
-	p += sprintf(p,
-		"channel status:       %s"
-		"                               %s\n",
-		(reg53h & 0x20) ? "On " : "Off",
-		(reg53h & 0x10) ? "On " : "Off" );
-
-	p += sprintf(p,
-		"both channels togth:  %s"
-		"                               %s\n",
-		(c0&0x80) ? "No " : "Yes",
-		(c1&0x80) ? "No " : "Yes" );
-
-	pci_read_config_byte(bmide_dev, 0x76, &reg53h);
-	p += sprintf(p,
-		"Channel state:        %s                    %s\n",
-		channel_status[reg53h & 0x07],
-		channel_status[(reg53h & 0x70) >> 4] );
-
-	pci_read_config_byte(bmide_dev, 0x58, &reg5xh);
-	pci_read_config_byte(bmide_dev, 0x5c, &reg5yh);
-	p += sprintf(p,
-		"Add. Setup Timing:    %dT"
-		"                                %dT\n",
-		(reg5xh & 0x07) ? (reg5xh & 0x07) : 8,
-		(reg5yh & 0x07) ? (reg5yh & 0x07) : 8 );
-
-	pci_read_config_byte(bmide_dev, 0x59, &reg5xh);
-	pci_read_config_byte(bmide_dev, 0x5d, &reg5yh);
-	p += sprintf(p,
-		"Command Act. Count:   %dT"
-		"                                %dT\n"
-		"Command Rec. Count:   %dT"
-		"                               %dT\n\n",
-		(reg5xh & 0x70) ? ((reg5xh & 0x70) >> 4) : 8,
-		(reg5yh & 0x70) ? ((reg5yh & 0x70) >> 4) : 8, 
-		(reg5xh & 0x0f) ? (reg5xh & 0x0f) : 16,
-		(reg5yh & 0x0f) ? (reg5yh & 0x0f) : 16 );
-
-	p += sprintf(p,
-		"----------------drive0-----------drive1"
-		"------------drive0-----------drive1------\n\n");
-	p += sprintf(p,
-		"DMA enabled:      %s              %s"
-		"               %s              %s\n",
-		(c0&0x20) ? "Yes" : "No ",
-		(c0&0x40) ? "Yes" : "No ",
-		(c1&0x20) ? "Yes" : "No ",
-		(c1&0x40) ? "Yes" : "No " );
-
-	pci_read_config_byte(bmide_dev, 0x54, &reg5xh);
-	pci_read_config_byte(bmide_dev, 0x55, &reg5yh);
-	q = "FIFO threshold:   %2d Words         %2d Words"
-		"          %2d Words         %2d Words\n";
-	if (rev < 0xc1) {
-		if ((rev == 0x20) &&
-		    (pci_read_config_byte(bmide_dev, 0x4f, &tmp), (tmp &= 0x20))) {
-			p += sprintf(p, q, 8, 8, 8, 8);
-		} else {
-			p += sprintf(p, q,
-				(reg5xh & 0x03) + 12,
-				((reg5xh & 0x30)>>4) + 12,
-				(reg5yh & 0x03) + 12,
-				((reg5yh & 0x30)>>4) + 12 );
-		}
-	} else {
-		int t1 = (tmp = (reg5xh & 0x03)) ? (tmp << 3) : 4;
-		int t2 = (tmp = ((reg5xh & 0x30)>>4)) ? (tmp << 3) : 4;
-		int t3 = (tmp = (reg5yh & 0x03)) ? (tmp << 3) : 4;
-		int t4 = (tmp = ((reg5yh & 0x30)>>4)) ? (tmp << 3) : 4;
-		p += sprintf(p, q, t1, t2, t3, t4);
-	}
-
-#if 0
-	p += sprintf(p, 
-		"FIFO threshold:   %2d Words         %2d Words"
-		"          %2d Words         %2d Words\n",
-		(reg5xh & 0x03) + 12,
-		((reg5xh & 0x30)>>4) + 12,
-		(reg5yh & 0x03) + 12,
-		((reg5yh & 0x30)>>4) + 12 );
-#endif
-
-	p += sprintf(p,
-		"FIFO mode:        %s         %s          %s         %s\n",
-		fifo[((reg5xh & 0x0c) >> 2)],
-		fifo[((reg5xh & 0xc0) >> 6)],
-		fifo[((reg5yh & 0x0c) >> 2)],
-		fifo[((reg5yh & 0xc0) >> 6)] );
-
-	pci_read_config_byte(bmide_dev, 0x5a, &reg5xh);
-	pci_read_config_byte(bmide_dev, 0x5b, &reg5xh1);
-	pci_read_config_byte(bmide_dev, 0x5e, &reg5yh);
-	pci_read_config_byte(bmide_dev, 0x5f, &reg5yh1);
-
-	p += sprintf(p,/*
-		"------------------drive0-----------drive1"
-		"------------drive0-----------drive1------\n")*/
-		"Dt RW act. Cnt    %2dT              %2dT"
-		"               %2dT              %2dT\n"
-		"Dt RW rec. Cnt    %2dT              %2dT"
-		"               %2dT              %2dT\n\n",
-		(reg5xh & 0x70) ? ((reg5xh & 0x70) >> 4) : 8,
-		(reg5xh1 & 0x70) ? ((reg5xh1 & 0x70) >> 4) : 8,
-		(reg5yh & 0x70) ? ((reg5yh & 0x70) >> 4) : 8,
-		(reg5yh1 & 0x70) ? ((reg5yh1 & 0x70) >> 4) : 8,
-		(reg5xh & 0x0f) ? (reg5xh & 0x0f) : 16,
-		(reg5xh1 & 0x0f) ? (reg5xh1 & 0x0f) : 16,
-		(reg5yh & 0x0f) ? (reg5yh & 0x0f) : 16,
-		(reg5yh1 & 0x0f) ? (reg5yh1 & 0x0f) : 16 );
-
-	p += sprintf(p,
-		"-----------------------------------UDMA Timings"
-		"--------------------------------\n\n");
-
-	pci_read_config_byte(bmide_dev, 0x56, &reg5xh);
-	pci_read_config_byte(bmide_dev, 0x57, &reg5yh);
-	p += sprintf(p,
-		"UDMA:             %s               %s"
-		"                %s               %s\n"
-		"UDMA timings:     %s             %s"
-		"              %s             %s\n\n",
-		(reg5xh & 0x08) ? "OK" : "No",
-		(reg5xh & 0x80) ? "OK" : "No",
-		(reg5yh & 0x08) ? "OK" : "No",
-		(reg5yh & 0x80) ? "OK" : "No",
-		udmaT[(reg5xh & 0x07)],
-		udmaT[(reg5xh & 0x70) >> 4],
-		udmaT[reg5yh & 0x07],
-		udmaT[(reg5yh & 0x70) >> 4] );
-
-	return p-buffer; /* => must be less than 4k! */
-}
-#endif  /* defined(DISPLAY_ALI_TIMINGS) && defined(CONFIG_IDE_PROC_FS) */
-
 /**
  *	ali_set_pio_mode	-	set host controller for PIO mode
  *	@drive: drive
@@ -294,7 +62,7 @@ static void ali_set_pio_mode(ide_drive_t *drive, const u8 pio)
 	int s_time, a_time, c_time;
 	u8 s_clc, a_clc, r_clc;
 	unsigned long flags;
-	int bus_speed = system_bus_clock();
+	int bus_speed = ide_pci_clk ? ide_pci_clk : system_bus_clock();
 	int port = hwif->channel ? 0x5c : 0x58;
 	int portFIFO = hwif->channel ? 0x55 : 0x54;
 	u8 cd_dma_fifo = 0;
@@ -465,14 +233,6 @@ static unsigned int __devinit init_chipset_ali15x3 (struct pci_dev *dev, const c
 
 	isa_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, NULL);
 
-#if defined(DISPLAY_ALI_TIMINGS) && defined(CONFIG_IDE_PROC_FS)
-	if (!ali_proc) {
-		ali_proc = 1;
-		bmide_dev = dev;
-		ide_pci_create_host_proc("ali", ali_get_info);
-	}
-#endif  /* defined(DISPLAY_ALI_TIMINGS) && defined(CONFIG_IDE_PROC_FS) */
-
 	local_irq_save(flags);
 
 	if (m5229_revision < 0xC2) {
diff --git a/trunk/drivers/ide/pci/amd74xx.c b/trunk/drivers/ide/pci/amd74xx.c
index f7c883808b02..efcf54338be7 100644
--- a/trunk/drivers/ide/pci/amd74xx.c
+++ b/trunk/drivers/ide/pci/amd74xx.c
@@ -179,7 +179,7 @@ static unsigned int __devinit init_chipset_amd74xx(struct pci_dev *dev,
  * Determine the system bus clock.
  */
 
-	amd_clock = system_bus_clock() * 1000;
+	amd_clock = (ide_pci_clk ? ide_pci_clk : system_bus_clock()) * 1000;
 
 	switch (amd_clock) {
 		case 33000: amd_clock = 33333; break;
diff --git a/trunk/drivers/ide/pci/cmd640.c b/trunk/drivers/ide/pci/cmd640.c
index 25c2f1bd175f..aaf38109eaec 100644
--- a/trunk/drivers/ide/pci/cmd640.c
+++ b/trunk/drivers/ide/pci/cmd640.c
@@ -111,10 +111,7 @@
 
 #define DRV_NAME "cmd640"
 
-/*
- * This flag is set in ide.c by the parameter:  ide0=cmd640_vlb
- */
-int cmd640_vlb;
+static int cmd640_vlb;
 
 /*
  * CMD640 specific registers definition.
@@ -350,12 +347,12 @@ static int __init secondary_port_responding(void)
 
 	spin_lock_irqsave(&cmd640_lock, flags);
 
-	outb_p(0x0a, 0x170 + IDE_SELECT_OFFSET);	/* select drive0 */
+	outb_p(0x0a, 0x176);	/* select drive0 */
 	udelay(100);
-	if ((inb_p(0x170 + IDE_SELECT_OFFSET) & 0x1f) != 0x0a) {
-		outb_p(0x1a, 0x170 + IDE_SELECT_OFFSET); /* select drive1 */
+	if ((inb_p(0x176) & 0x1f) != 0x0a) {
+		outb_p(0x1a, 0x176); /* select drive1 */
 		udelay(100);
-		if ((inb_p(0x170 + IDE_SELECT_OFFSET) & 0x1f) != 0x1a) {
+		if ((inb_p(0x176) & 0x1f) != 0x1a) {
 			spin_unlock_irqrestore(&cmd640_lock, flags);
 			return 0; /* nothing responded */
 		}
@@ -383,6 +380,7 @@ static void cmd640_dump_regs(void)
 }
 #endif
 
+#ifndef CONFIG_BLK_DEV_CMD640_ENHANCED
 /*
  * Check whether prefetch is on for a drive,
  * and initialize the unmask flags for safe operation.
@@ -403,9 +401,7 @@ static void __init check_prefetch(ide_drive_t *drive, unsigned int index)
 		drive->no_io_32bit = 0;
 	}
 }
-
-#ifdef CONFIG_BLK_DEV_CMD640_ENHANCED
-
+#else
 /*
  * Sets prefetch mode for a drive.
  */
@@ -461,34 +457,6 @@ static inline u8 pack_nibbles(u8 upper, u8 lower)
 	return ((upper & 0x0f) << 4) | (lower & 0x0f);
 }
 
-/*
- * This routine retrieves the initial drive timings from the chipset.
- */
-static void __init retrieve_drive_counts(unsigned int index)
-{
-	u8 b;
-
-	/*
-	 * Get the internal setup timing, and convert to clock count
-	 */
-	b = get_cmd640_reg(arttim_regs[index]) & ~0x3f;
-	switch (b) {
-	case 0x00: b = 4; break;
-	case 0x80: b = 3; break;
-	case 0x40: b = 2; break;
-	default:   b = 5; break;
-	}
-	setup_counts[index] = b;
-
-	/*
-	 * Get the active/recovery counts
-	 */
-	b = get_cmd640_reg(drwtim_regs[index]);
-	active_counts[index]   = (b >> 4)   ? (b >> 4)   : 0x10;
-	recovery_counts[index] = (b & 0x0f) ? (b & 0x0f) : 0x10;
-}
-
-
 /*
  * This routine writes the prepared setup/active/recovery counts
  * for a drive into the cmd640 chipset registers to active them.
@@ -555,7 +523,14 @@ static void cmd640_set_mode(ide_drive_t *drive, unsigned int index,
 {
 	int setup_time, active_time, recovery_time, clock_time;
 	u8 setup_count, active_count, recovery_count, recovery_count2, cycle_count;
-	int bus_speed = system_bus_clock();
+	int bus_speed;
+
+	if (cmd640_vlb && ide_vlb_clk)
+		bus_speed = ide_vlb_clk;
+	else if (!cmd640_vlb && ide_pci_clk)
+		bus_speed = ide_pci_clk;
+	else
+		bus_speed = system_bus_clock();
 
 	if (pio_mode > 5)
 		pio_mode = 5;
@@ -679,7 +654,6 @@ static const struct ide_port_info cmd640_port_info __initdata = {
 	.chipset		= ide_cmd640,
 	.host_flags		= IDE_HFLAG_SERIALIZE |
 				  IDE_HFLAG_NO_DMA |
-				  IDE_HFLAG_NO_AUTOTUNE |
 				  IDE_HFLAG_ABUSE_PREFETCH |
 				  IDE_HFLAG_ABUSE_FAST_DEVSEL,
 #ifdef CONFIG_BLK_DEV_CMD640_ENHANCED
@@ -862,29 +836,16 @@ static int __init cmd640x_init(void)
 		}
 
 #ifdef CONFIG_BLK_DEV_CMD640_ENHANCED
-		if (drive->autotune || ((index > 1) && second_port_toggled)) {
-			/*
-			 * Reset timing to the slowest speed and turn off
-			 * prefetch.  This way, the drive identify code has
-			 * a better chance.
-			 */
-			setup_counts    [index] = 4;	/* max possible */
-			active_counts   [index] = 16;	/* max possible */
-			recovery_counts [index] = 16;	/* max possible */
-			program_drive_counts(drive, index);
-			set_prefetch_mode(drive, index, 0);
-			printk("cmd640: drive%d timings/prefetch cleared\n", index);
-		} else {
-			/*
-			 * Record timings/prefetch without changing them.
-			 * This preserves any prior BIOS setup.
-			 */
-			retrieve_drive_counts (index);
-			check_prefetch(drive, index);
-			printk("cmd640: drive%d timings/prefetch(%s) preserved",
-				index, drive->no_io_32bit ? "off" : "on");
-			display_clocks(index);
-		}
+		/*
+		 * Reset timing to the slowest speed and turn off prefetch.
+		 * This way, the drive identify code has a better chance.
+		 */
+		setup_counts    [index] = 4;	/* max possible */
+		active_counts   [index] = 16;	/* max possible */
+		recovery_counts [index] = 16;	/* max possible */
+		program_drive_counts(drive, index);
+		set_prefetch_mode(drive, index, 0);
+		printk("cmd640: drive%d timings/prefetch cleared\n", index);
 #else
 		/*
 		 * Set the drive unmask flags to match the prefetch setting
diff --git a/trunk/drivers/ide/pci/cmd64x.c b/trunk/drivers/ide/pci/cmd64x.c
index 006fb62656bc..08674711d089 100644
--- a/trunk/drivers/ide/pci/cmd64x.c
+++ b/trunk/drivers/ide/pci/cmd64x.c
@@ -68,8 +68,8 @@ static u8 quantize_timing(int timing, int quant)
  */
 static void program_cycle_times (ide_drive_t *drive, int cycle_time, int active_time)
 {
-	struct pci_dev *dev	= to_pci_dev(drive->hwif->dev);
-	int clock_time		= 1000 / system_bus_clock();
+	struct pci_dev *dev = to_pci_dev(drive->hwif->dev);
+	int clock_time = 1000 / (ide_pci_clk ? ide_pci_clk : system_bus_clock());
 	u8  cycle_count, active_count, recovery_count, drwtim;
 	static const u8 recovery_values[] =
 		{15, 15, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 0};
@@ -128,7 +128,7 @@ static void cmd64x_tune_pio(ide_drive_t *drive, const u8 pio)
 			    ide_pio_timings[pio].active_time);
 
 	setup_count = quantize_timing(ide_pio_timings[pio].setup_time,
-				      1000 / system_bus_clock());
+			1000 / (ide_pci_clk ? ide_pci_clk : system_bus_clock()));
 
 	/*
 	 * The primary channel has individual address setup timing registers
diff --git a/trunk/drivers/ide/pci/cy82c693.c b/trunk/drivers/ide/pci/cy82c693.c
index e30eae5a01b6..77cc22c2ad45 100644
--- a/trunk/drivers/ide/pci/cy82c693.c
+++ b/trunk/drivers/ide/pci/cy82c693.c
@@ -18,8 +18,6 @@
  *   hdparm -t reports 8.17 MB/sec at about 6% CPU usage for the DTTA
  * - this is my first linux driver, so there's probably a lot  of room
  *   for optimizations and bug fixing, so feel free to do it.
- * - use idebus=xx parameter to set PCI bus speed - needed to calc
- *   timings for PIO modes (default will be 40)
  * - if using PIO mode it's a good idea to set the PIO mode and
  *   32-bit I/O support (if possible), e.g. hdparm -p2 -c1 /dev/hda
  * - I had some problems with my IBM DHEA with PIO modes < 2
@@ -136,7 +134,7 @@ static int calc_clk(int time, int bus_speed)
 static void compute_clocks(u8 pio, pio_clocks_t *p_pclk)
 {
 	int clk1, clk2;
-	int bus_speed = system_bus_clock();	/* get speed of PCI bus */
+	int bus_speed = ide_pci_clk ? ide_pci_clk : system_bus_clock();
 
 	/* we don't check against CY82C693's min and max speed,
 	 * so you can play with the idebus=xx parameter
diff --git a/trunk/drivers/ide/pci/delkin_cb.c b/trunk/drivers/ide/pci/delkin_cb.c
index c7b7e0483287..b9e457996d0e 100644
--- a/trunk/drivers/ide/pci/delkin_cb.c
+++ b/trunk/drivers/ide/pci/delkin_cb.c
@@ -87,11 +87,7 @@ delkin_cb_probe (struct pci_dev *dev, const struct pci_device_id *id)
 
 	i = hwif->index;
 
-	if (hwif->present)
-		ide_unregister(i);
-	else
-		ide_init_port_data(hwif, i);
-
+	ide_init_port_data(hwif, i);
 	ide_init_port_hw(hwif, &hw);
 	hwif->port_ops = &delkin_cb_port_ops;
 
@@ -123,8 +119,7 @@ delkin_cb_remove (struct pci_dev *dev)
 {
 	ide_hwif_t *hwif = pci_get_drvdata(dev);
 
-	if (hwif)
-		ide_unregister(hwif->index);
+	ide_unregister(hwif);
 
 	pci_release_regions(dev);
 	pci_disable_device(dev);
diff --git a/trunk/drivers/ide/pci/hpt366.c b/trunk/drivers/ide/pci/hpt366.c
index 8c02961d0188..c929dadaaaff 100644
--- a/trunk/drivers/ide/pci/hpt366.c
+++ b/trunk/drivers/ide/pci/hpt366.c
@@ -760,7 +760,7 @@ static void hpt3xx_maskproc(ide_drive_t *drive, int mask)
 		}
 	} else
 		outb(mask ? (drive->ctl | 2) : (drive->ctl & ~2),
-		     hwif->io_ports[IDE_CONTROL_OFFSET]);
+		     hwif->io_ports.ctl_addr);
 }
 
 /*
diff --git a/trunk/drivers/ide/pci/ns87415.c b/trunk/drivers/ide/pci/ns87415.c
index e1b0c9a9ab9c..fec4955f449b 100644
--- a/trunk/drivers/ide/pci/ns87415.c
+++ b/trunk/drivers/ide/pci/ns87415.c
@@ -63,6 +63,48 @@ static u8 superio_ide_inb (unsigned long port)
 	return inb(port);
 }
 
+static void superio_tf_read(ide_drive_t *drive, ide_task_t *task)
+{
+	struct ide_io_ports *io_ports = &drive->hwif->io_ports;
+	struct ide_taskfile *tf = &task->tf;
+
+	if (task->tf_flags & IDE_TFLAG_IN_DATA) {
+		u16 data = inw(io_ports->data_addr);
+
+		tf->data = data & 0xff;
+		tf->hob_data = (data >> 8) & 0xff;
+	}
+
+	/* be sure we're looking at the low order bits */
+	outb(drive->ctl & ~0x80, io_ports->ctl_addr);
+
+	if (task->tf_flags & IDE_TFLAG_IN_NSECT)
+		tf->nsect  = inb(io_ports->nsect_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_LBAL)
+		tf->lbal   = inb(io_ports->lbal_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_LBAM)
+		tf->lbam   = inb(io_ports->lbam_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_LBAH)
+		tf->lbah   = inb(io_ports->lbah_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_DEVICE)
+		tf->device = superio_ide_inb(io_ports->device_addr);
+
+	if (task->tf_flags & IDE_TFLAG_LBA48) {
+		outb(drive->ctl | 0x80, io_ports->ctl_addr);
+
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_FEATURE)
+			tf->hob_feature = inb(io_ports->feature_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_NSECT)
+			tf->hob_nsect   = inb(io_ports->nsect_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAL)
+			tf->hob_lbal    = inb(io_ports->lbal_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAM)
+			tf->hob_lbam    = inb(io_ports->lbam_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAH)
+			tf->hob_lbah    = inb(io_ports->lbah_addr);
+	}
+}
+
 static void __devinit superio_ide_init_iops (struct hwif_s *hwif)
 {
 	struct pci_dev *pdev = to_pci_dev(hwif->dev);
@@ -72,14 +114,16 @@ static void __devinit superio_ide_init_iops (struct hwif_s *hwif)
 	base = pci_resource_start(pdev, port * 2) & ~3;
 	dmabase = pci_resource_start(pdev, 4) & ~3;
 
-	superio_ide_status[port] = base + IDE_STATUS_OFFSET;
-	superio_ide_select[port] = base + IDE_SELECT_OFFSET;
+	superio_ide_status[port] = base + 7;
+	superio_ide_select[port] = base + 6;
 	superio_ide_dma_status[port] = dmabase + (!port ? 2 : 0xa);
 
 	/* Clear error/interrupt, enable dma */
 	tmp = superio_ide_inb(superio_ide_dma_status[port]);
 	outb(tmp | 0x66, superio_ide_dma_status[port]);
 
+	hwif->tf_read = superio_tf_read;
+
 	/* We need to override inb to workaround a SuperIO errata */
 	hwif->INB = superio_ide_inb;
 }
@@ -231,12 +275,12 @@ static void __devinit init_hwif_ns87415 (ide_hwif_t *hwif)
 		 *      SELECT_DRIVE() properly during first ide_probe_port().
 		 */
 		timeout = 10000;
-		outb(12, hwif->io_ports[IDE_CONTROL_OFFSET]);
+		outb(12, hwif->io_ports.ctl_addr);
 		udelay(10);
-		outb(8, hwif->io_ports[IDE_CONTROL_OFFSET]);
+		outb(8, hwif->io_ports.ctl_addr);
 		do {
 			udelay(50);
-			stat = hwif->INB(hwif->io_ports[IDE_STATUS_OFFSET]);
+			stat = hwif->INB(hwif->io_ports.status_addr);
                 	if (stat == 0xff)
                         	break;
         	} while ((stat & BUSY_STAT) && --timeout);
@@ -244,7 +288,7 @@ static void __devinit init_hwif_ns87415 (ide_hwif_t *hwif)
 	}
 
 	if (!using_inta)
-		hwif->irq = ide_default_irq(hwif->io_ports[IDE_DATA_OFFSET]);
+		hwif->irq = ide_default_irq(hwif->io_ports.data_addr);
 	else if (!hwif->irq && hwif->mate && hwif->mate->irq)
 		hwif->irq = hwif->mate->irq;	/* share IRQ with mate */
 
diff --git a/trunk/drivers/ide/pci/opti621.c b/trunk/drivers/ide/pci/opti621.c
index 9edacba20ffb..6e99080497bf 100644
--- a/trunk/drivers/ide/pci/opti621.c
+++ b/trunk/drivers/ide/pci/opti621.c
@@ -53,8 +53,7 @@
  * If you then set the second drive to another PIO, the old value
  * (automatically selected) will be overrided by yours.
  * There is a 25/33MHz switch in configuration
- * register, but driver is written for use at any frequency which get
- * (use idebus=xx to select PCI bus speed).
+ * register, but driver is written for use at any frequency.
  *
  * Version 0.1, Nov 8, 1996
  * by Jaromir Koutek, for 2.1.8.
@@ -210,7 +209,7 @@ static void compute_clocks(int pio, pio_clocks_t *clks)
 {
 	if (pio != PIO_NOT_EXIST) {
 		int adr_setup, data_pls;
-		int bus_speed = system_bus_clock();
+		int bus_speed = ide_pci_clk ? ide_pci_clk : system_bus_clock();
 
 		adr_setup = ide_pio_timings[pio].setup_time;
 		data_pls = ide_pio_timings[pio].active_time;
@@ -280,7 +279,7 @@ static void opti621_set_pio_mode(ide_drive_t *drive, const u8 pio)
 
 	spin_lock_irqsave(&opti621_lock, flags);
 
-	reg_base = hwif->io_ports[IDE_DATA_OFFSET];
+	reg_base = hwif->io_ports.data_addr;
 
 	/* allow Register-B */
 	outb(0xc0, reg_base + CNTRL_REG);
diff --git a/trunk/drivers/ide/pci/pdc202xx_new.c b/trunk/drivers/ide/pci/pdc202xx_new.c
index ec9bd7b352fc..070df8ab3b21 100644
--- a/trunk/drivers/ide/pci/pdc202xx_new.c
+++ b/trunk/drivers/ide/pci/pdc202xx_new.c
@@ -83,8 +83,8 @@ static u8 get_indexed_reg(ide_hwif_t *hwif, u8 index)
 {
 	u8 value;
 
-	outb(index, hwif->dma_vendor1);
-	value = inb(hwif->dma_vendor3);
+	outb(index, hwif->dma_base + 1);
+	value = inb(hwif->dma_base + 3);
 
 	DBG("index[%02X] value[%02X]\n", index, value);
 	return value;
@@ -97,8 +97,8 @@ static u8 get_indexed_reg(ide_hwif_t *hwif, u8 index)
  */
 static void set_indexed_reg(ide_hwif_t *hwif, u8 index, u8 value)
 {
-	outb(index, hwif->dma_vendor1);
-	outb(value, hwif->dma_vendor3);
+	outb(index, hwif->dma_base + 1);
+	outb(value, hwif->dma_base + 3);
 	DBG("index[%02X] value[%02X]\n", index, value);
 }
 
diff --git a/trunk/drivers/ide/pci/piix.c b/trunk/drivers/ide/pci/piix.c
index 21c5dd23f928..f04738d14a6f 100644
--- a/trunk/drivers/ide/pci/piix.c
+++ b/trunk/drivers/ide/pci/piix.c
@@ -250,6 +250,7 @@ static const struct ich_laptop ich_laptop[] = {
 	{ 0x27DF, 0x1043, 0x1267 },	/* ICH7 on Asus W5F */
 	{ 0x27DF, 0x103C, 0x30A1 },	/* ICH7 on HP Compaq nc2400 */
 	{ 0x24CA, 0x1025, 0x0061 },	/* ICH4 on Acer Aspire 2023WLMi */
+	{ 0x2653, 0x1043, 0x82D8 },	/* ICH6M on Asus Eee 701 */
 	/* end marker */
 	{ 0, }
 };
diff --git a/trunk/drivers/ide/pci/scc_pata.c b/trunk/drivers/ide/pci/scc_pata.c
index 17cf86490d59..910fb00deb71 100644
--- a/trunk/drivers/ide/pci/scc_pata.c
+++ b/trunk/drivers/ide/pci/scc_pata.c
@@ -126,12 +126,6 @@ static u8 scc_ide_inb(unsigned long port)
 	return (u8)data;
 }
 
-static u16 scc_ide_inw(unsigned long port)
-{
-	u32 data = in_be32((void*)port);
-	return (u16)data;
-}
-
 static void scc_ide_insw(unsigned long port, void *addr, u32 count)
 {
 	u16 *ptr = (u16 *)addr;
@@ -154,11 +148,6 @@ static void scc_ide_outb(u8 addr, unsigned long port)
 	out_be32((void*)port, addr);
 }
 
-static void scc_ide_outw(u16 addr, unsigned long port)
-{
-	out_be32((void*)port, addr);
-}
-
 static void
 scc_ide_outbsync(ide_drive_t * drive, u8 addr, unsigned long port)
 {
@@ -271,6 +260,20 @@ static void scc_set_dma_mode(ide_drive_t *drive, const u8 speed)
 	out_be32((void __iomem *)udenvt_port, reg);
 }
 
+static void scc_dma_host_set(ide_drive_t *drive, int on)
+{
+	ide_hwif_t *hwif = drive->hwif;
+	u8 unit = (drive->select.b.unit & 0x01);
+	u8 dma_stat = scc_ide_inb(hwif->dma_status);
+
+	if (on)
+		dma_stat |= (1 << (5 + unit));
+	else
+		dma_stat &= ~(1 << (5 + unit));
+
+	scc_ide_outb(dma_stat, hwif->dma_status);
+}
+
 /**
  *	scc_ide_dma_setup	-	begin a DMA phase
  *	@drive: target device
@@ -301,7 +304,7 @@ static int scc_dma_setup(ide_drive_t *drive)
 	}
 
 	/* PRD table */
-	out_be32((void __iomem *)hwif->dma_prdtable, hwif->dmatable_dma);
+	out_be32((void __iomem *)(hwif->dma_base + 8), hwif->dmatable_dma);
 
 	/* specify r/w */
 	out_be32((void __iomem *)hwif->dma_command, reading);
@@ -315,13 +318,45 @@ static int scc_dma_setup(ide_drive_t *drive)
 	return 0;
 }
 
+static void scc_dma_start(ide_drive_t *drive)
+{
+	ide_hwif_t *hwif = drive->hwif;
+	u8 dma_cmd = scc_ide_inb(hwif->dma_command);
+
+	/* start DMA */
+	scc_ide_outb(dma_cmd | 1, hwif->dma_command);
+	hwif->dma = 1;
+	wmb();
+}
+
+static int __scc_dma_end(ide_drive_t *drive)
+{
+	ide_hwif_t *hwif = drive->hwif;
+	u8 dma_stat, dma_cmd;
+
+	drive->waiting_for_dma = 0;
+	/* get DMA command mode */
+	dma_cmd = scc_ide_inb(hwif->dma_command);
+	/* stop DMA */
+	scc_ide_outb(dma_cmd & ~1, hwif->dma_command);
+	/* get DMA status */
+	dma_stat = scc_ide_inb(hwif->dma_status);
+	/* clear the INTR & ERROR bits */
+	scc_ide_outb(dma_stat | 6, hwif->dma_status);
+	/* purge DMA mappings */
+	ide_destroy_dmatable(drive);
+	/* verify good DMA status */
+	hwif->dma = 0;
+	wmb();
+	return (dma_stat & 7) != 4 ? (0x10 | dma_stat) : 0;
+}
 
 /**
  *	scc_dma_end	-	Stop DMA
  *	@drive: IDE drive
  *
  *	Check and clear INT Status register.
- *      Then call __ide_dma_end().
+ *	Then call __scc_dma_end().
  */
 
 static int scc_dma_end(ide_drive_t *drive)
@@ -334,7 +369,7 @@ static int scc_dma_end(ide_drive_t *drive)
 
 	/* errata A308 workaround: Step5 (check data loss) */
 	/* We don't check non ide_disk because it is limited to UDMA4 */
-	if (!(in_be32((void __iomem *)hwif->io_ports[IDE_ALTSTATUS_OFFSET])
+	if (!(in_be32((void __iomem *)hwif->io_ports.ctl_addr)
 	      & ERR_STAT) &&
 	    drive->media == ide_disk && drive->current_speed > XFER_UDMA_4) {
 		reg = in_be32((void __iomem *)intsts_port);
@@ -425,7 +460,7 @@ static int scc_dma_end(ide_drive_t *drive)
 		break;
 	}
 
-	dma_stat = __ide_dma_end(drive);
+	dma_stat = __scc_dma_end(drive);
 	if (data_loss)
 		dma_stat |= 2; /* emulate DMA error (to retry command) */
 	return dma_stat;
@@ -438,7 +473,7 @@ static int scc_dma_test_irq(ide_drive_t *drive)
 	u32 int_stat = in_be32((void __iomem *)hwif->dma_base + 0x014);
 
 	/* SCC errata A252,A308 workaround: Step4 */
-	if ((in_be32((void __iomem *)hwif->io_ports[IDE_ALTSTATUS_OFFSET])
+	if ((in_be32((void __iomem *)hwif->io_ports.ctl_addr)
 	     & ERR_STAT) &&
 	    (int_stat & INTSTS_INTRQ))
 		return 1;
@@ -534,8 +569,8 @@ static int scc_ide_setup_pci_device(struct pci_dev *dev,
 	}
 
 	memset(&hw, 0, sizeof(hw));
-	for (i = IDE_DATA_OFFSET; i <= IDE_CONTROL_OFFSET; i++)
-		hw.io_ports[i] = ports->dma + 0x20 + i * 4;
+	for (i = 0; i <= 8; i++)
+		hw.io_ports_array[i] = ports->dma + 0x20 + i * 4;
 	hw.irq = dev->irq;
 	hw.dev = &dev->dev;
 	hw.chipset = ide_pci;
@@ -618,6 +653,122 @@ static int __devinit init_setup_scc(struct pci_dev *dev,
 	return rc;
 }
 
+static void scc_tf_load(ide_drive_t *drive, ide_task_t *task)
+{
+	struct ide_io_ports *io_ports = &drive->hwif->io_ports;
+	struct ide_taskfile *tf = &task->tf;
+	u8 HIHI = (task->tf_flags & IDE_TFLAG_LBA48) ? 0xE0 : 0xEF;
+
+	if (task->tf_flags & IDE_TFLAG_FLAGGED)
+		HIHI = 0xFF;
+
+	ide_set_irq(drive, 1);
+
+	if (task->tf_flags & IDE_TFLAG_OUT_DATA)
+		out_be32((void *)io_ports->data_addr,
+			 (tf->hob_data << 8) | tf->data);
+
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_FEATURE)
+		scc_ide_outb(tf->hob_feature, io_ports->feature_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_NSECT)
+		scc_ide_outb(tf->hob_nsect, io_ports->nsect_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAL)
+		scc_ide_outb(tf->hob_lbal, io_ports->lbal_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAM)
+		scc_ide_outb(tf->hob_lbam, io_ports->lbam_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_HOB_LBAH)
+		scc_ide_outb(tf->hob_lbah, io_ports->lbah_addr);
+
+	if (task->tf_flags & IDE_TFLAG_OUT_FEATURE)
+		scc_ide_outb(tf->feature, io_ports->feature_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_NSECT)
+		scc_ide_outb(tf->nsect, io_ports->nsect_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_LBAL)
+		scc_ide_outb(tf->lbal, io_ports->lbal_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_LBAM)
+		scc_ide_outb(tf->lbam, io_ports->lbam_addr);
+	if (task->tf_flags & IDE_TFLAG_OUT_LBAH)
+		scc_ide_outb(tf->lbah, io_ports->lbah_addr);
+
+	if (task->tf_flags & IDE_TFLAG_OUT_DEVICE)
+		scc_ide_outb((tf->device & HIHI) | drive->select.all,
+			     io_ports->device_addr);
+}
+
+static void scc_tf_read(ide_drive_t *drive, ide_task_t *task)
+{
+	struct ide_io_ports *io_ports = &drive->hwif->io_ports;
+	struct ide_taskfile *tf = &task->tf;
+
+	if (task->tf_flags & IDE_TFLAG_IN_DATA) {
+		u16 data = (u16)in_be32((void *)io_ports->data_addr);
+
+		tf->data = data & 0xff;
+		tf->hob_data = (data >> 8) & 0xff;
+	}
+
+	/* be sure we're looking at the low order bits */
+	scc_ide_outb(drive->ctl & ~0x80, io_ports->ctl_addr);
+
+	if (task->tf_flags & IDE_TFLAG_IN_NSECT)
+		tf->nsect  = scc_ide_inb(io_ports->nsect_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_LBAL)
+		tf->lbal   = scc_ide_inb(io_ports->lbal_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_LBAM)
+		tf->lbam   = scc_ide_inb(io_ports->lbam_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_LBAH)
+		tf->lbah   = scc_ide_inb(io_ports->lbah_addr);
+	if (task->tf_flags & IDE_TFLAG_IN_DEVICE)
+		tf->device = scc_ide_inb(io_ports->device_addr);
+
+	if (task->tf_flags & IDE_TFLAG_LBA48) {
+		scc_ide_outb(drive->ctl | 0x80, io_ports->ctl_addr);
+
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_FEATURE)
+			tf->hob_feature = scc_ide_inb(io_ports->feature_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_NSECT)
+			tf->hob_nsect   = scc_ide_inb(io_ports->nsect_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAL)
+			tf->hob_lbal    = scc_ide_inb(io_ports->lbal_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAM)
+			tf->hob_lbam    = scc_ide_inb(io_ports->lbam_addr);
+		if (task->tf_flags & IDE_TFLAG_IN_HOB_LBAH)
+			tf->hob_lbah    = scc_ide_inb(io_ports->lbah_addr);
+	}
+}
+
+static void scc_input_data(ide_drive_t *drive, struct request *rq,
+			   void *buf, unsigned int len)
+{
+	unsigned long data_addr = drive->hwif->io_ports.data_addr;
+
+	len++;
+
+	if (drive->io_32bit) {
+		scc_ide_insl(data_addr, buf, len / 4);
+
+		if ((len & 3) >= 2)
+			scc_ide_insw(data_addr, (u8 *)buf + (len & ~3), 1);
+	} else
+		scc_ide_insw(data_addr, buf, len / 2);
+}
+
+static void scc_output_data(ide_drive_t *drive,  struct request *rq,
+			    void *buf, unsigned int len)
+{
+	unsigned long data_addr = drive->hwif->io_ports.data_addr;
+
+	len++;
+
+	if (drive->io_32bit) {
+		scc_ide_outsl(data_addr, buf, len / 4);
+
+		if ((len & 3) >= 2)
+			scc_ide_outsw(data_addr, (u8 *)buf + (len & ~3), 1);
+	} else
+		scc_ide_outsw(data_addr, buf, len / 2);
+}
+
 /**
  *	init_mmio_iops_scc	-	set up the iops for MMIO
  *	@hwif: interface to set up
@@ -632,15 +783,15 @@ static void __devinit init_mmio_iops_scc(ide_hwif_t *hwif)
 
 	ide_set_hwifdata(hwif, ports);
 
+	hwif->tf_load = scc_tf_load;
+	hwif->tf_read = scc_tf_read;
+
+	hwif->input_data  = scc_input_data;
+	hwif->output_data = scc_output_data;
+
 	hwif->INB = scc_ide_inb;
-	hwif->INW = scc_ide_inw;
-	hwif->INSW = scc_ide_insw;
-	hwif->INSL = scc_ide_insl;
 	hwif->OUTB = scc_ide_outb;
 	hwif->OUTBSYNC = scc_ide_outbsync;
-	hwif->OUTW = scc_ide_outw;
-	hwif->OUTSW = scc_ide_outsw;
-	hwif->OUTSL = scc_ide_outsl;
 
 	hwif->dma_base = dma_base;
 	hwif->config_data = ports->ctl;
@@ -687,7 +838,6 @@ static void __devinit init_hwif_scc(ide_hwif_t *hwif)
 
 	hwif->dma_command = hwif->dma_base;
 	hwif->dma_status = hwif->dma_base + 0x04;
-	hwif->dma_prdtable = hwif->dma_base + 0x08;
 
 	/* PTERADD */
 	out_be32((void __iomem *)(hwif->dma_base + 0x018), hwif->dmatable_dma);
@@ -706,10 +856,10 @@ static const struct ide_port_ops scc_port_ops = {
 };
 
 static const struct ide_dma_ops scc_dma_ops = {
-	.dma_host_set		= ide_dma_host_set,
+	.dma_host_set		= scc_dma_host_set,
 	.dma_setup		= scc_dma_setup,
 	.dma_exec_cmd		= ide_dma_exec_cmd,
-	.dma_start		= ide_dma_start,
+	.dma_start		= scc_dma_start,
 	.dma_end		= scc_dma_end,
 	.dma_test_irq		= scc_dma_test_irq,
 	.dma_lost_irq		= ide_dma_lost_irq,
@@ -763,9 +913,8 @@ static void __devexit scc_remove(struct pci_dev *dev)
 		hwif->dmatable_cpu = NULL;
 	}
 
-	ide_unregister(hwif->index);
+	ide_unregister(hwif);
 
-	hwif->chipset = ide_unknown;
 	iounmap((void*)ports->dma);
 	iounmap((void*)ports->ctl);
 	pci_release_selected_regions(dev, (1 << 2) - 1);
diff --git a/trunk/drivers/ide/pci/sgiioc4.c b/trunk/drivers/ide/pci/sgiioc4.c
index 321a4e28ac19..16a0bce17d69 100644
--- a/trunk/drivers/ide/pci/sgiioc4.c
+++ b/trunk/drivers/ide/pci/sgiioc4.c
@@ -98,28 +98,28 @@ sgiioc4_init_hwif_ports(hw_regs_t * hw, unsigned long data_port,
 	int i;
 
 	/* Registers are word (32 bit) aligned */
-	for (i = IDE_DATA_OFFSET; i <= IDE_STATUS_OFFSET; i++)
-		hw->io_ports[i] = reg + i * 4;
+	for (i = 0; i <= 7; i++)
+		hw->io_ports_array[i] = reg + i * 4;
 
 	if (ctrl_port)
-		hw->io_ports[IDE_CONTROL_OFFSET] = ctrl_port;
+		hw->io_ports.ctl_addr = ctrl_port;
 
 	if (irq_port)
-		hw->io_ports[IDE_IRQ_OFFSET] = irq_port;
+		hw->io_ports.irq_addr = irq_port;
 }
 
 static void
 sgiioc4_maskproc(ide_drive_t * drive, int mask)
 {
 	writeb(mask ? (drive->ctl | 2) : (drive->ctl & ~2),
-	       (void __iomem *)drive->hwif->io_ports[IDE_CONTROL_OFFSET]);
+	       (void __iomem *)drive->hwif->io_ports.ctl_addr);
 }
 
 static int
 sgiioc4_checkirq(ide_hwif_t * hwif)
 {
 	unsigned long intr_addr =
-		hwif->io_ports[IDE_IRQ_OFFSET] + IOC4_INTR_REG * 4;
+		hwif->io_ports.irq_addr + IOC4_INTR_REG * 4;
 
 	if ((u8)readl((void __iomem *)intr_addr) & 0x03)
 		return 1;
@@ -134,8 +134,8 @@ sgiioc4_clearirq(ide_drive_t * drive)
 {
 	u32 intr_reg;
 	ide_hwif_t *hwif = HWIF(drive);
-	unsigned long other_ir =
-	    hwif->io_ports[IDE_IRQ_OFFSET] + (IOC4_INTR_REG << 2);
+	struct ide_io_ports *io_ports = &hwif->io_ports;
+	unsigned long other_ir = io_ports->irq_addr + (IOC4_INTR_REG << 2);
 
 	/* Code to check for PCI error conditions */
 	intr_reg = readl((void __iomem *)other_ir);
@@ -147,12 +147,12 @@ sgiioc4_clearirq(ide_drive_t * drive)
 		 * a "clear" status if it got cleared.  If not, then spin
 		 * for a bit trying to clear it.
 		 */
-		u8 stat = sgiioc4_INB(hwif->io_ports[IDE_STATUS_OFFSET]);
+		u8 stat = sgiioc4_INB(io_ports->status_addr);
 		int count = 0;
-		stat = sgiioc4_INB(hwif->io_ports[IDE_STATUS_OFFSET]);
+		stat = sgiioc4_INB(io_ports->status_addr);
 		while ((stat & 0x80) && (count++ < 100)) {
 			udelay(1);
-			stat = sgiioc4_INB(hwif->io_ports[IDE_STATUS_OFFSET]);
+			stat = sgiioc4_INB(io_ports->status_addr);
 		}
 
 		if (intr_reg & 0x02) {
@@ -162,9 +162,9 @@ sgiioc4_clearirq(ide_drive_t * drive)
 			    pci_stat_cmd_reg;
 
 			pci_err_addr_low =
-				readl((void __iomem *)hwif->io_ports[IDE_IRQ_OFFSET]);
+				readl((void __iomem *)io_ports->irq_addr);
 			pci_err_addr_high =
-				readl((void __iomem *)(hwif->io_ports[IDE_IRQ_OFFSET] + 4));
+				readl((void __iomem *)(io_ports->irq_addr + 4));
 			pci_read_config_dword(dev, PCI_COMMAND,
 					      &pci_stat_cmd_reg);
 			printk(KERN_ERR
@@ -573,7 +573,7 @@ static const struct ide_port_info sgiioc4_port_info __devinitdata = {
 	.init_dma		= ide_dma_sgiioc4,
 	.port_ops		= &sgiioc4_port_ops,
 	.dma_ops		= &sgiioc4_dma_ops,
-	.host_flags		= IDE_HFLAG_NO_AUTOTUNE,
+	.host_flags		= IDE_HFLAG_MMIO,
 	.mwdma_mask		= ATA_MWDMA2_ONLY,
 };
 
diff --git a/trunk/drivers/ide/pci/siimage.c b/trunk/drivers/ide/pci/siimage.c
index 1fffea3211bd..4cf8fc54aa2a 100644
--- a/trunk/drivers/ide/pci/siimage.c
+++ b/trunk/drivers/ide/pci/siimage.c
@@ -1,8 +1,8 @@
 /*
  * Copyright (C) 2001-2002	Andre Hedrick <andre@linux-ide.org>
  * Copyright (C) 2003		Red Hat <alan@redhat.com>
- * Copyright (C) 2007		MontaVista Software, Inc.
- * Copyright (C) 2007		Bartlomiej Zolnierkiewicz
+ * Copyright (C) 2007-2008	MontaVista Software, Inc.
+ * Copyright (C) 2007-2008	Bartlomiej Zolnierkiewicz
  *
  *  May be copied or modified under the terms of the GNU General Public License
  *
@@ -17,10 +17,10 @@
  *
  *  FAQ Items:
  *	If you are using Marvell SATA-IDE adapters with Maxtor drives
- *	ensure the system is set up for ATA100/UDMA5 not UDMA6.
+ *	ensure the system is set up for ATA100/UDMA5, not UDMA6.
  *
  *	If you are using WD drives with SATA bridges you must set the
- *	drive to "Single". "Master" will hang
+ *	drive to "Single". "Master" will hang.
  *
  *	If you have strange problems with nVidia chipset systems please
  *	see the SI support documentation and update your system BIOS
@@ -42,25 +42,24 @@
 #include <linux/hdreg.h>
 #include <linux/ide.h>
 #include <linux/init.h>
-
-#include <asm/io.h>
+#include <linux/io.h>
 
 /**
  *	pdev_is_sata		-	check if device is SATA
  *	@pdev:	PCI device to check
- *	
+ *
  *	Returns true if this is a SATA controller
  */
- 
+
 static int pdev_is_sata(struct pci_dev *pdev)
 {
 #ifdef CONFIG_BLK_DEV_IDE_SATA
-	switch(pdev->device) {
-		case PCI_DEVICE_ID_SII_3112:
-		case PCI_DEVICE_ID_SII_1210SA:
-			return 1;
-		case PCI_DEVICE_ID_SII_680:
-			return 0;
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_SII_3112:
+	case PCI_DEVICE_ID_SII_1210SA:
+		return 1;
+	case PCI_DEVICE_ID_SII_680:
+		return 0;
 	}
 	BUG();
 #endif
@@ -70,10 +69,10 @@ static int pdev_is_sata(struct pci_dev *pdev)
 /**
  *	is_sata			-	check if hwif is SATA
  *	@hwif:	interface to check
- *	
+ *
  *	Returns true if this is a SATA controller
  */
- 
+
 static inline int is_sata(ide_hwif_t *hwif)
 {
 	return pdev_is_sata(to_pci_dev(hwif->dev));
@@ -86,21 +85,22 @@ static inline int is_sata(ide_hwif_t *hwif)
  *
  *	Turn a config register offset into the right address in either
  *	PCI space or MMIO space to access the control register in question
- *	Thankfully this is a configuration operation so isnt performance
- *	criticial. 
+ *	Thankfully this is a configuration operation, so isn't performance
+ *	critical.
  */
- 
+
 static unsigned long siimage_selreg(ide_hwif_t *hwif, int r)
 {
 	unsigned long base = (unsigned long)hwif->hwif_data;
+
 	base += 0xA0 + r;
-	if(hwif->mmio)
-		base += (hwif->channel << 6);
+	if (hwif->mmio)
+		base += hwif->channel << 6;
 	else
-		base += (hwif->channel << 4);
+		base += hwif->channel << 4;
 	return base;
 }
-	
+
 /**
  *	siimage_seldev		-	return register base
  *	@hwif: interface
@@ -110,20 +110,69 @@ static unsigned long siimage_selreg(ide_hwif_t *hwif, int r)
  *	PCI space or MMIO space to access the control register in question
  *	including accounting for the unit shift.
  */
- 
+
 static inline unsigned long siimage_seldev(ide_drive_t *drive, int r)
 {
 	ide_hwif_t *hwif	= HWIF(drive);
-	unsigned long base = (unsigned long)hwif->hwif_data;
+	unsigned long base	= (unsigned long)hwif->hwif_data;
+
 	base += 0xA0 + r;
-	if(hwif->mmio)
-		base += (hwif->channel << 6);
+	if (hwif->mmio)
+		base += hwif->channel << 6;
 	else
-		base += (hwif->channel << 4);
+		base += hwif->channel << 4;
 	base |= drive->select.b.unit << drive->select.b.unit;
 	return base;
 }
 
+static u8 sil_ioread8(struct pci_dev *dev, unsigned long addr)
+{
+	u8 tmp = 0;
+
+	if (pci_get_drvdata(dev))
+		tmp = readb((void __iomem *)addr);
+	else
+		pci_read_config_byte(dev, addr, &tmp);
+
+	return tmp;
+}
+
+static u16 sil_ioread16(struct pci_dev *dev, unsigned long addr)
+{
+	u16 tmp = 0;
+
+	if (pci_get_drvdata(dev))
+		tmp = readw((void __iomem *)addr);
+	else
+		pci_read_config_word(dev, addr, &tmp);
+
+	return tmp;
+}
+
+static void sil_iowrite8(struct pci_dev *dev, u8 val, unsigned long addr)
+{
+	if (pci_get_drvdata(dev))
+		writeb(val, (void __iomem *)addr);
+	else
+		pci_write_config_byte(dev, addr, val);
+}
+
+static void sil_iowrite16(struct pci_dev *dev, u16 val, unsigned long addr)
+{
+	if (pci_get_drvdata(dev))
+		writew(val, (void __iomem *)addr);
+	else
+		pci_write_config_word(dev, addr, val);
+}
+
+static void sil_iowrite32(struct pci_dev *dev, u32 val, unsigned long addr)
+{
+	if (pci_get_drvdata(dev))
+		writel(val, (void __iomem *)addr);
+	else
+		pci_write_config_dword(dev, addr, val);
+}
+
 /**
  *	sil_udma_filter		-	compute UDMA mask
  *	@drive: IDE device
@@ -136,24 +185,26 @@ static inline unsigned long siimage_seldev(ide_drive_t *drive, int r)
 
 static u8 sil_pata_udma_filter(ide_drive_t *drive)
 {
-	ide_hwif_t *hwif = drive->hwif;
-	struct pci_dev *dev = to_pci_dev(hwif->dev);
-	unsigned long base = (unsigned long) hwif->hwif_data;
-	u8 mask = 0, scsc = 0;
+	ide_hwif_t *hwif	= drive->hwif;
+	struct pci_dev *dev	= to_pci_dev(hwif->dev);
+	unsigned long base	= (unsigned long)hwif->hwif_data;
+	u8 scsc, mask		= 0;
 
-	if (hwif->mmio)
-		scsc = hwif->INB(base + 0x4A);
-	else
-		pci_read_config_byte(dev, 0x8A, &scsc);
+	scsc = sil_ioread8(dev, base + (hwif->mmio ? 0x4A : 0x8A));
 
-	if ((scsc & 0x30) == 0x10)	/* 133 */
+	switch (scsc & 0x30) {
+	case 0x10:	/* 133 */
 		mask = ATA_UDMA6;
-	else if ((scsc & 0x30) == 0x20)	/* 2xPCI */
+		break;
+	case 0x20:	/* 2xPCI */
 		mask = ATA_UDMA6;
-	else if ((scsc & 0x30) == 0x00)	/* 100 */
+		break;
+	case 0x00:	/* 100 */
 		mask = ATA_UDMA5;
-	else 	/* Disabled ? */
+		break;
+	default: 	/* Disabled ? */
 		BUG();
+	}
 
 	return mask;
 }
@@ -175,15 +226,16 @@ static u8 sil_sata_udma_filter(ide_drive_t *drive)
 
 static void sil_set_pio_mode(ide_drive_t *drive, u8 pio)
 {
-	const u16 tf_speed[]	= { 0x328a, 0x2283, 0x1281, 0x10c3, 0x10c1 };
-	const u16 data_speed[]	= { 0x328a, 0x2283, 0x1104, 0x10c3, 0x10c1 };
+	static const u16 tf_speed[]   = { 0x328a, 0x2283, 0x1281, 0x10c3, 0x10c1 };
+	static const u16 data_speed[] = { 0x328a, 0x2283, 0x1104, 0x10c3, 0x10c1 };
 
 	ide_hwif_t *hwif	= HWIF(drive);
+	struct pci_dev *dev	= to_pci_dev(hwif->dev);
 	ide_drive_t *pair	= ide_get_paired_drive(drive);
 	u32 speedt		= 0;
 	u16 speedp		= 0;
 	unsigned long addr	= siimage_seldev(drive, 0x04);
-	unsigned long tfaddr	= siimage_selreg(hwif, 0x02);
+	unsigned long tfaddr	= siimage_selreg(hwif,	0x02);
 	unsigned long base	= (unsigned long)hwif->hwif_data;
 	u8 tf_pio		= pio;
 	u8 addr_mask		= hwif->channel ? (hwif->mmio ? 0xF4 : 0x84)
@@ -203,36 +255,20 @@ static void sil_set_pio_mode(ide_drive_t *drive, u8 pio)
 	speedp = data_speed[pio];
 	speedt = tf_speed[tf_pio];
 
-	if (hwif->mmio) {
-		hwif->OUTW(speedp, addr);
-		hwif->OUTW(speedt, tfaddr);
-		/* Now set up IORDY */
-		if (pio > 2)
-			hwif->OUTW(hwif->INW(tfaddr-2)|0x200, tfaddr-2);
-		else
-			hwif->OUTW(hwif->INW(tfaddr-2)&~0x200, tfaddr-2);
-
-		mode = hwif->INB(base + addr_mask);
-		mode &= ~(unit ? 0x30 : 0x03);
-		mode |= (unit ? 0x10 : 0x01);
-		hwif->OUTB(mode, base + addr_mask);
-	} else {
-		struct pci_dev *dev = to_pci_dev(hwif->dev);
-
-		pci_write_config_word(dev, addr, speedp);
-		pci_write_config_word(dev, tfaddr, speedt);
-		pci_read_config_word(dev, tfaddr - 2, &speedp);
-		speedp &= ~0x200;
-		/* Set IORDY for mode 3 or 4 */
-		if (pio > 2)
-			speedp |= 0x200;
-		pci_write_config_word(dev, tfaddr - 2, speedp);
-
-		pci_read_config_byte(dev, addr_mask, &mode);
-		mode &= ~(unit ? 0x30 : 0x03);
-		mode |= (unit ? 0x10 : 0x01);
-		pci_write_config_byte(dev, addr_mask, mode);
-	}
+	sil_iowrite16(dev, speedp, addr);
+	sil_iowrite16(dev, speedt, tfaddr);
+
+	/* now set up IORDY */
+	speedp = sil_ioread16(dev, tfaddr - 2);
+	speedp &= ~0x200;
+	if (pio > 2)
+		speedp |= 0x200;
+	sil_iowrite16(dev, speedp, tfaddr - 2);
+
+	mode = sil_ioread8(dev, base + addr_mask);
+	mode &= ~(unit ? 0x30 : 0x03);
+	mode |= unit ? 0x10 : 0x01;
+	sil_iowrite8(dev, mode, base + addr_mask);
 }
 
 /**
@@ -245,59 +281,45 @@ static void sil_set_pio_mode(ide_drive_t *drive, u8 pio)
 
 static void sil_set_dma_mode(ide_drive_t *drive, const u8 speed)
 {
-	u8 ultra6[]		= { 0x0F, 0x0B, 0x07, 0x05, 0x03, 0x02, 0x01 };
-	u8 ultra5[]		= { 0x0C, 0x07, 0x05, 0x04, 0x02, 0x01 };
-	u16 dma[]		= { 0x2208, 0x10C2, 0x10C1 };
+	static const u8 ultra6[] = { 0x0F, 0x0B, 0x07, 0x05, 0x03, 0x02, 0x01 };
+	static const u8 ultra5[] = { 0x0C, 0x07, 0x05, 0x04, 0x02, 0x01 };
+	static const u16 dma[]	 = { 0x2208, 0x10C2, 0x10C1 };
 
 	ide_hwif_t *hwif	= HWIF(drive);
 	struct pci_dev *dev	= to_pci_dev(hwif->dev);
 	u16 ultra = 0, multi	= 0;
 	u8 mode = 0, unit	= drive->select.b.unit;
 	unsigned long base	= (unsigned long)hwif->hwif_data;
-	u8 scsc = 0, addr_mask	= ((hwif->channel) ?
-				    ((hwif->mmio) ? 0xF4 : 0x84) :
-				    ((hwif->mmio) ? 0xB4 : 0x80));
-				    
+	u8 scsc = 0, addr_mask	= hwif->channel ?
+					(hwif->mmio ? 0xF4 : 0x84) :
+					(hwif->mmio ? 0xB4 : 0x80);
 	unsigned long ma	= siimage_seldev(drive, 0x08);
 	unsigned long ua	= siimage_seldev(drive, 0x0C);
 
-	if (hwif->mmio) {
-		scsc = hwif->INB(base + 0x4A);
-		mode = hwif->INB(base + addr_mask);
-		multi = hwif->INW(ma);
-		ultra = hwif->INW(ua);
-	} else {
-		pci_read_config_byte(dev, 0x8A, &scsc);
-		pci_read_config_byte(dev, addr_mask, &mode);
-		pci_read_config_word(dev, ma, &multi);
-		pci_read_config_word(dev, ua, &ultra);
-	}
+	scsc  = sil_ioread8 (dev, base + (hwif->mmio ? 0x4A : 0x8A));
+	mode  = sil_ioread8 (dev, base + addr_mask);
+	multi = sil_ioread16(dev, ma);
+	ultra = sil_ioread16(dev, ua);
 
-	mode &= ~((unit) ? 0x30 : 0x03);
+	mode  &= ~(unit ? 0x30 : 0x03);
 	ultra &= ~0x3F;
 	scsc = ((scsc & 0x30) == 0x00) ? 0 : 1;
 
 	scsc = is_sata(hwif) ? 1 : scsc;
 
 	if (speed >= XFER_UDMA_0) {
-		multi = dma[2];
-		ultra |= (scsc ? ultra6[speed - XFER_UDMA_0] :
-				 ultra5[speed - XFER_UDMA_0]);
-		mode |= (unit ? 0x30 : 0x03);
+		multi  = dma[2];
+		ultra |= scsc ? ultra6[speed - XFER_UDMA_0] :
+				ultra5[speed - XFER_UDMA_0];
+		mode  |= unit ? 0x30 : 0x03;
 	} else {
 		multi = dma[speed - XFER_MW_DMA_0];
-		mode |= (unit ? 0x20 : 0x02);
+		mode |= unit ? 0x20 : 0x02;
 	}
 
-	if (hwif->mmio) {
-		hwif->OUTB(mode, base + addr_mask);
-		hwif->OUTW(multi, ma);
-		hwif->OUTW(ultra, ua);
-	} else {
-		pci_write_config_byte(dev, addr_mask, mode);
-		pci_write_config_word(dev, ma, multi);
-		pci_write_config_word(dev, ua, ultra);
-	}
+	sil_iowrite8 (dev, mode, base + addr_mask);
+	sil_iowrite16(dev, multi, ma);
+	sil_iowrite16(dev, ultra, ua);
 }
 
 /* returns 1 if dma irq issued, 0 otherwise */
@@ -309,13 +331,14 @@ static int siimage_io_dma_test_irq(ide_drive_t *drive)
 	unsigned long addr	= siimage_selreg(hwif, 1);
 
 	/* return 1 if INTR asserted */
-	if ((hwif->INB(hwif->dma_status) & 4) == 4)
+	if (hwif->INB(hwif->dma_status) & 4)
 		return 1;
 
 	/* return 1 if Device INTR asserted */
 	pci_read_config_byte(dev, addr, &dma_altstat);
 	if (dma_altstat & 8)
-		return 0;	//return 1;
+		return 0;	/* return 1; */
+
 	return 0;
 }
 
@@ -335,9 +358,9 @@ static int siimage_mmio_dma_test_irq(ide_drive_t *drive)
 		= (void __iomem *)hwif->sata_scr[SATA_ERROR_OFFSET];
 
 	if (sata_error_addr) {
-		unsigned long base = (unsigned long)hwif->hwif_data;
-		u32 ext_stat = readl((void __iomem *)(base + 0x10));
-		u8 watchdog = 0;
+		unsigned long base	= (unsigned long)hwif->hwif_data;
+		u32 ext_stat		= readl((void __iomem *)(base + 0x10));
+		u8 watchdog		= 0;
 
 		if (ext_stat & ((hwif->channel) ? 0x40 : 0x10)) {
 			u32 sata_error = readl(sata_error_addr);
@@ -346,25 +369,22 @@ static int siimage_mmio_dma_test_irq(ide_drive_t *drive)
 			watchdog = (sata_error & 0x00680000) ? 1 : 0;
 			printk(KERN_WARNING "%s: sata_error = 0x%08x, "
 				"watchdog = %d, %s\n",
-				drive->name, sata_error, watchdog,
-				__func__);
-
-		} else {
+				drive->name, sata_error, watchdog, __func__);
+		} else
 			watchdog = (ext_stat & 0x8000) ? 1 : 0;
-		}
-		ext_stat >>= 16;
 
+		ext_stat >>= 16;
 		if (!(ext_stat & 0x0404) && !watchdog)
 			return 0;
 	}
 
 	/* return 1 if INTR asserted */
-	if ((readb((void __iomem *)hwif->dma_status) & 0x04) == 0x04)
+	if (readb((void __iomem *)hwif->dma_status) & 0x04)
 		return 1;
 
 	/* return 1 if Device INTR asserted */
-	if ((readb((void __iomem *)addr) & 8) == 8)
-		return 0;	//return 1;
+	if (readb((void __iomem *)addr) & 8)
+		return 0;	/* return 1; */
 
 	return 0;
 }
@@ -423,63 +443,33 @@ static void sil_sata_pre_reset(ide_drive_t *drive)
 }
 
 /**
- *	proc_reports_siimage		-	add siimage controller to proc
- *	@dev: PCI device
- *	@clocking: SCSC value
- *	@name: controller name
- *
- *	Report the clocking mode of the controller and add it to
- *	the /proc interface layer
- */
- 
-static void proc_reports_siimage (struct pci_dev *dev, u8 clocking, const char *name)
-{
-	if (!pdev_is_sata(dev)) {
-		printk(KERN_INFO "%s: BASE CLOCK ", name);
-		clocking &= 0x03;
-		switch (clocking) {
-			case 0x03: printk("DISABLED!\n"); break;
-			case 0x02: printk("== 2X PCI\n"); break;
-			case 0x01: printk("== 133\n"); break;
-			case 0x00: printk("== 100\n"); break;
-		}
-	}
-}
-
-/**
- *	setup_mmio_siimage	-	switch an SI controller into MMIO
+ *	setup_mmio_siimage	-	switch controller into MMIO mode
  *	@dev: PCI device we are configuring
  *	@name: device name
  *
- *	Attempt to put the device into mmio mode. There are some slight
- *	complications here with certain systems where the mmio bar isnt
- *	mapped so we have to be sure we can fall back to I/O.
+ *	Attempt to put the device into MMIO mode. There are some slight
+ *	complications here with certain systems where the MMIO BAR isn't
+ *	mapped, so we have to be sure that we can fall back to I/O.
  */
- 
-static unsigned int setup_mmio_siimage (struct pci_dev *dev, const char *name)
+
+static unsigned int setup_mmio_siimage(struct pci_dev *dev, const char *name)
 {
 	resource_size_t bar5	= pci_resource_start(dev, 5);
 	unsigned long barsize	= pci_resource_len(dev, 5);
-	u8 tmpbyte	= 0;
 	void __iomem *ioaddr;
-	u32 tmp, irq_mask;
 
 	/*
-	 *	Drop back to PIO if we can't map the mmio. Some
-	 *	systems seem to get terminally confused in the PCI
-	 *	spaces.
+	 *	Drop back to PIO if we can't map the MMIO. Some	systems
+	 *	seem to get terminally confused in the PCI spaces.
 	 */
-	 
-	if(!request_mem_region(bar5, barsize, name))
-	{
-		printk(KERN_WARNING "siimage: IDE controller MMIO ports not available.\n");
+	if (!request_mem_region(bar5, barsize, name)) {
+		printk(KERN_WARNING "siimage: IDE controller MMIO ports not "
+				    "available.\n");
 		return 0;
 	}
-		
-	ioaddr = ioremap(bar5, barsize);
 
-	if (ioaddr == NULL)
-	{
+	ioaddr = ioremap(bar5, barsize);
+	if (ioaddr == NULL) {
 		release_mem_region(bar5, barsize);
 		return 0;
 	}
@@ -487,62 +477,6 @@ static unsigned int setup_mmio_siimage (struct pci_dev *dev, const char *name)
 	pci_set_master(dev);
 	pci_set_drvdata(dev, (void *) ioaddr);
 
-	if (pdev_is_sata(dev)) {
-		/* make sure IDE0/1 interrupts are not masked */
-		irq_mask = (1 << 22) | (1 << 23);
-		tmp = readl(ioaddr + 0x48);
-		if (tmp & irq_mask) {
-			tmp &= ~irq_mask;
-			writel(tmp, ioaddr + 0x48);
-			readl(ioaddr + 0x48); /* flush */
-		}
-		writel(0, ioaddr + 0x148);
-		writel(0, ioaddr + 0x1C8);
-	}
-
-	writeb(0, ioaddr + 0xB4);
-	writeb(0, ioaddr + 0xF4);
-	tmpbyte = readb(ioaddr + 0x4A);
-
-	switch(tmpbyte & 0x30) {
-		case 0x00:
-			/* In 100 MHz clocking, try and switch to 133 */
-			writeb(tmpbyte|0x10, ioaddr + 0x4A);
-			break;
-		case 0x10:
-			/* On 133Mhz clocking */
-			break;
-		case 0x20:
-			/* On PCIx2 clocking */
-			break;
-		case 0x30:
-			/* Clocking is disabled */
-			/* 133 clock attempt to force it on */
-			writeb(tmpbyte & ~0x20, ioaddr + 0x4A);
-			break;
-	}
-	
-	writeb(      0x72, ioaddr + 0xA1);
-	writew(    0x328A, ioaddr + 0xA2);
-	writel(0x62DD62DD, ioaddr + 0xA4);
-	writel(0x43924392, ioaddr + 0xA8);
-	writel(0x40094009, ioaddr + 0xAC);
-	writeb(      0x72, ioaddr + 0xE1);
-	writew(    0x328A, ioaddr + 0xE2);
-	writel(0x62DD62DD, ioaddr + 0xE4);
-	writel(0x43924392, ioaddr + 0xE8);
-	writel(0x40094009, ioaddr + 0xEC);
-
-	if (pdev_is_sata(dev)) {
-		writel(0xFFFF0000, ioaddr + 0x108);
-		writel(0xFFFF0000, ioaddr + 0x188);
-		writel(0x00680000, ioaddr + 0x148);
-		writel(0x00680000, ioaddr + 0x1C8);
-	}
-
-	tmpbyte = readb(ioaddr + 0x4A);
-
-	proc_reports_siimage(dev, (tmpbyte>>4), name);
 	return 1;
 }
 
@@ -552,55 +486,92 @@ static unsigned int setup_mmio_siimage (struct pci_dev *dev, const char *name)
  *	@name: device name
  *
  *	Perform the initial PCI set up for this device. Attempt to switch
- *	to 133MHz clocking if the system isn't already set up to do it.
+ *	to 133 MHz clocking if the system isn't already set up to do it.
  */
 
-static unsigned int __devinit init_chipset_siimage(struct pci_dev *dev, const char *name)
+static unsigned int __devinit init_chipset_siimage(struct pci_dev *dev,
+						   const char *name)
 {
-	u8 rev = dev->revision, tmpbyte = 0, BA5_EN = 0;
+	unsigned long base, scsc_addr;
+	void __iomem *ioaddr = NULL;
+	u8 rev = dev->revision, tmp, BA5_EN;
 
 	pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE, rev ? 1 : 255);
 
 	pci_read_config_byte(dev, 0x8A, &BA5_EN);
-	if ((BA5_EN & 0x01) || (pci_resource_start(dev, 5))) {
-		if (setup_mmio_siimage(dev, name)) {
-			return 0;
+
+	if ((BA5_EN & 0x01) || pci_resource_start(dev, 5))
+		if (setup_mmio_siimage(dev, name))
+			ioaddr = pci_get_drvdata(dev);
+
+	base = (unsigned long)ioaddr;
+
+	if (ioaddr && pdev_is_sata(dev)) {
+		u32 tmp32, irq_mask;
+
+		/* make sure IDE0/1 interrupts are not masked */
+		irq_mask = (1 << 22) | (1 << 23);
+		tmp32 = readl(ioaddr + 0x48);
+		if (tmp32 & irq_mask) {
+			tmp32 &= ~irq_mask;
+			writel(tmp32, ioaddr + 0x48);
+			readl(ioaddr + 0x48); /* flush */
 		}
+		writel(0, ioaddr + 0x148);
+		writel(0, ioaddr + 0x1C8);
+	}
+
+	sil_iowrite8(dev, 0, base ? (base + 0xB4) : 0x80);
+	sil_iowrite8(dev, 0, base ? (base + 0xF4) : 0x84);
+
+	scsc_addr = base ? (base + 0x4A) : 0x8A;
+	tmp = sil_ioread8(dev, scsc_addr);
+
+	switch (tmp & 0x30) {
+	case 0x00:
+		/* On 100 MHz clocking, try and switch to 133 MHz */
+		sil_iowrite8(dev, tmp | 0x10, scsc_addr);
+		break;
+	case 0x30:
+		/* Clocking is disabled, attempt to force 133MHz clocking. */
+		sil_iowrite8(dev, tmp & ~0x20, scsc_addr);
+	case 0x10:
+		/* On 133Mhz clocking. */
+		break;
+	case 0x20:
+		/* On PCIx2 clocking. */
+		break;
 	}
 
-	pci_write_config_byte(dev, 0x80, 0x00);
-	pci_write_config_byte(dev, 0x84, 0x00);
-	pci_read_config_byte(dev, 0x8A, &tmpbyte);
-	switch(tmpbyte & 0x30) {
-		case 0x00:
-			/* 133 clock attempt to force it on */
-			pci_write_config_byte(dev, 0x8A, tmpbyte|0x10);
-		case 0x30:
-			/* if clocking is disabled */
-			/* 133 clock attempt to force it on */
-			pci_write_config_byte(dev, 0x8A, tmpbyte & ~0x20);
-		case 0x10:
-			/* 133 already */
-			break;
-		case 0x20:
-			/* BIOS set PCI x2 clocking */
-			break;
+	tmp = sil_ioread8(dev, scsc_addr);
+
+	sil_iowrite8 (dev,       0x72, base + 0xA1);
+	sil_iowrite16(dev,     0x328A, base + 0xA2);
+	sil_iowrite32(dev, 0x62DD62DD, base + 0xA4);
+	sil_iowrite32(dev, 0x43924392, base + 0xA8);
+	sil_iowrite32(dev, 0x40094009, base + 0xAC);
+	sil_iowrite8 (dev,       0x72, base ? (base + 0xE1) : 0xB1);
+	sil_iowrite16(dev,     0x328A, base ? (base + 0xE2) : 0xB2);
+	sil_iowrite32(dev, 0x62DD62DD, base ? (base + 0xE4) : 0xB4);
+	sil_iowrite32(dev, 0x43924392, base ? (base + 0xE8) : 0xB8);
+	sil_iowrite32(dev, 0x40094009, base ? (base + 0xEC) : 0xBC);
+
+	if (base && pdev_is_sata(dev)) {
+		writel(0xFFFF0000, ioaddr + 0x108);
+		writel(0xFFFF0000, ioaddr + 0x188);
+		writel(0x00680000, ioaddr + 0x148);
+		writel(0x00680000, ioaddr + 0x1C8);
 	}
 
-	pci_read_config_byte(dev,   0x8A, &tmpbyte);
+	/* report the clocking mode of the controller */
+	if (!pdev_is_sata(dev)) {
+		static const char *clk_str[] =
+			{ "== 100", "== 133", "== 2X PCI", "DISABLED!" };
 
-	pci_write_config_byte(dev,  0xA1, 0x72);
-	pci_write_config_word(dev,  0xA2, 0x328A);
-	pci_write_config_dword(dev, 0xA4, 0x62DD62DD);
-	pci_write_config_dword(dev, 0xA8, 0x43924392);
-	pci_write_config_dword(dev, 0xAC, 0x40094009);
-	pci_write_config_byte(dev,  0xB1, 0x72);
-	pci_write_config_word(dev,  0xB2, 0x328A);
-	pci_write_config_dword(dev, 0xB4, 0x62DD62DD);
-	pci_write_config_dword(dev, 0xB8, 0x43924392);
-	pci_write_config_dword(dev, 0xBC, 0x40094009);
+		tmp >>= 4;
+		printk(KERN_INFO "%s: BASE CLOCK %s\n", name, clk_str[tmp & 3]);
+	}
 
-	proc_reports_siimage(dev, (tmpbyte>>4), name);
 	return 0;
 }
 
@@ -610,8 +581,7 @@ static unsigned int __devinit init_chipset_siimage(struct pci_dev *dev, const ch
  *
  *	The basic setup here is fairly simple, we can use standard MMIO
  *	operations. However we do have to set the taskfile register offsets
- *	by hand as there isnt a standard defined layout for them this
- *	time.
+ *	by hand as there isn't a standard defined layout for them this time.
  *
  *	The hardware supports buffered taskfiles and also some rather nice
  *	extended PRD tables. For better SI3112 support use the libata driver
@@ -622,23 +592,21 @@ static void __devinit init_mmio_iops_siimage(ide_hwif_t *hwif)
 	struct pci_dev *dev	= to_pci_dev(hwif->dev);
 	void *addr		= pci_get_drvdata(dev);
 	u8 ch			= hwif->channel;
-	hw_regs_t		hw;
-	unsigned long		base;
+	struct ide_io_ports *io_ports = &hwif->io_ports;
+	unsigned long base;
 
 	/*
-	 *	Fill in the basic HWIF bits
+	 *	Fill in the basic hwif bits
 	 */
-
+	hwif->host_flags |= IDE_HFLAG_MMIO;
 	default_hwif_mmiops(hwif);
-	hwif->hwif_data			= addr;
+	hwif->hwif_data	= addr;
 
 	/*
-	 *	Now set up the hw. We have to do this ourselves as
-	 *	the MMIO layout isnt the same as the standard port
-	 *	based I/O
+	 *	Now set up the hw. We have to do this ourselves as the
+	 *	MMIO layout isn't the same as the standard port based I/O.
 	 */
-
-	memset(&hw, 0, sizeof(hw_regs_t));
+	memset(io_ports, 0, sizeof(*io_ports));
 
 	base = (unsigned long)addr;
 	if (ch)
@@ -647,21 +615,18 @@ static void __devinit init_mmio_iops_siimage(ide_hwif_t *hwif)
 		base += 0x80;
 
 	/*
-	 *	The buffered task file doesn't have status/control
-	 *	so we can't currently use it sanely since we want to
-	 *	use LBA48 mode.
-	 */	
-	hw.io_ports[IDE_DATA_OFFSET]	= base;
-	hw.io_ports[IDE_ERROR_OFFSET]	= base + 1;
-	hw.io_ports[IDE_NSECTOR_OFFSET]	= base + 2;
-	hw.io_ports[IDE_SECTOR_OFFSET]	= base + 3;
-	hw.io_ports[IDE_LCYL_OFFSET]	= base + 4;
-	hw.io_ports[IDE_HCYL_OFFSET]	= base + 5;
-	hw.io_ports[IDE_SELECT_OFFSET]	= base + 6;
-	hw.io_ports[IDE_STATUS_OFFSET]	= base + 7;
-	hw.io_ports[IDE_CONTROL_OFFSET]	= base + 10;
-
-	hw.io_ports[IDE_IRQ_OFFSET]	= 0;
+	 *	The buffered task file doesn't have status/control, so we
+	 *	can't currently use it sanely since we want to use LBA48 mode.
+	 */
+	io_ports->data_addr	= base;
+	io_ports->error_addr	= base + 1;
+	io_ports->nsect_addr	= base + 2;
+	io_ports->lbal_addr	= base + 3;
+	io_ports->lbam_addr	= base + 4;
+	io_ports->lbah_addr	= base + 5;
+	io_ports->device_addr	= base + 6;
+	io_ports->status_addr	= base + 7;
+	io_ports->ctl_addr	= base + 10;
 
 	if (pdev_is_sata(dev)) {
 		base = (unsigned long)addr;
@@ -672,8 +637,6 @@ static void __devinit init_mmio_iops_siimage(ide_hwif_t *hwif)
 		hwif->sata_scr[SATA_CONTROL_OFFSET]	= base + 0x100;
 	}
 
-	memcpy(hwif->io_ports, hw.io_ports, sizeof(hwif->io_ports));
-
 	hwif->irq = dev->irq;
 
 	hwif->dma_base = (unsigned long)addr + (ch ? 0x08 : 0x00);
@@ -683,19 +646,17 @@ static void __devinit init_mmio_iops_siimage(ide_hwif_t *hwif)
 
 static int is_dev_seagate_sata(ide_drive_t *drive)
 {
-	const char *s = &drive->id->model[0];
-	unsigned len;
-
-	len = strnlen(s, sizeof(drive->id->model));
+	const char *s	= &drive->id->model[0];
+	unsigned len	= strnlen(s, sizeof(drive->id->model));
 
-	if ((len > 4) && (!memcmp(s, "ST", 2))) {
+	if ((len > 4) && (!memcmp(s, "ST", 2)))
 		if ((!memcmp(s + len - 2, "AS", 2)) ||
 		    (!memcmp(s + len - 3, "ASL", 3))) {
 			printk(KERN_INFO "%s: applying pessimistic Seagate "
 					 "errata fix\n", drive->name);
 			return 1;
 		}
-	}
+
 	return 0;
 }
 
@@ -712,7 +673,7 @@ static void __devinit sil_quirkproc(ide_drive_t *drive)
 {
 	ide_hwif_t *hwif = drive->hwif;
 
-	/* Try and raise the rqsize */
+	/* Try and rise the rqsize */
 	if (!is_sata(hwif) || !is_dev_seagate_sata(drive))
 		hwif->rqsize = 128;
 }
@@ -746,20 +707,14 @@ static void __devinit init_iops_siimage(ide_hwif_t *hwif)
  *	sil_cable_detect	-	cable detection
  *	@hwif: interface to check
  *
- *	Check for the presence of an ATA66 capable cable on the
- *	interface.
+ *	Check for the presence of an ATA66 capable cable on the interface.
  */
 
 static u8 __devinit sil_cable_detect(ide_hwif_t *hwif)
 {
-	struct pci_dev *dev = to_pci_dev(hwif->dev);
-	unsigned long addr = siimage_selreg(hwif, 0);
-	u8 ata66 = 0;
-
-	if (pci_get_drvdata(dev) == NULL)
-		pci_read_config_byte(dev, addr, &ata66);
-	else
-		ata66 = hwif->INB(addr);
+	struct pci_dev *dev	= to_pci_dev(hwif->dev);
+	unsigned long addr	= siimage_selreg(hwif, 0);
+	u8 ata66		= sil_ioread8(dev, addr);
 
 	return (ata66 & 0x01) ? ATA_CBL_PATA80 : ATA_CBL_PATA40;
 }
@@ -805,15 +760,16 @@ static const struct ide_port_info siimage_chipsets[] __devinitdata = {
 };
 
 /**
- *	siimage_init_one	-	pci layer discovery entry
+ *	siimage_init_one	-	PCI layer discovery entry
  *	@dev: PCI device
  *	@id: ident table entry
  *
- *	Called by the PCI code when it finds an SI680 or SI3112 controller.
+ *	Called by the PCI code when it finds an SiI680 or SiI3112 controller.
  *	We then use the IDE PCI generic helper to do most of the work.
  */
- 
-static int __devinit siimage_init_one(struct pci_dev *dev, const struct pci_device_id *id)
+
+static int __devinit siimage_init_one(struct pci_dev *dev,
+				      const struct pci_device_id *id)
 {
 	struct ide_port_info d;
 	u8 idx = id->driver_data;
diff --git a/trunk/drivers/ide/pci/trm290.c b/trunk/drivers/ide/pci/trm290.c
index 15ee38f7ad3f..a8a3138682ef 100644
--- a/trunk/drivers/ide/pci/trm290.c
+++ b/trunk/drivers/ide/pci/trm290.c
@@ -298,7 +298,7 @@ static void __devinit init_hwif_trm290(ide_hwif_t *hwif)
 		if (old != compat && old_mask == 0xff) {
 			/* leave lower 10 bits untouched */
 			compat += (next_offset += 0x400);
-			hwif->io_ports[IDE_CONTROL_OFFSET] = compat + 2;
+			hwif->io_ports.ctl_addr = compat + 2;
 			outw(compat | 1, hwif->config_data);
 			new = inw(hwif->config_data);
 			printk(KERN_INFO "%s: control basereg workaround: "
diff --git a/trunk/drivers/ide/pci/via82cxxx.c b/trunk/drivers/ide/pci/via82cxxx.c
index bbd17bec6ffe..566e0ecb8db1 100644
--- a/trunk/drivers/ide/pci/via82cxxx.c
+++ b/trunk/drivers/ide/pci/via82cxxx.c
@@ -340,7 +340,7 @@ static unsigned int __devinit init_chipset_via82cxxx(struct pci_dev *dev, const
 	 * Determine system bus clock.
 	 */
 
-	via_clock = system_bus_clock() * 1000;
+	via_clock = (ide_pci_clk ? ide_pci_clk : system_bus_clock()) * 1000;
 
 	switch (via_clock) {
 		case 33000: via_clock = 33333; break;
diff --git a/trunk/drivers/ide/ppc/mpc8xx.c b/trunk/drivers/ide/ppc/mpc8xx.c
index a82f6efb660b..f0e638dcc3ab 100644
--- a/trunk/drivers/ide/ppc/mpc8xx.c
+++ b/trunk/drivers/ide/ppc/mpc8xx.c
@@ -131,7 +131,7 @@ static int pcmcia_schlvl = PCMCIA_SCHLVL;
 #if defined(CONFIG_IDE_8xx_PCCARD) || defined(CONFIG_IDE_8xx_DIRECT)
 static int __init m8xx_ide_init_ports(hw_regs_t *hw, unsigned long data_port)
 {
-	unsigned long *p = hw->io_ports;
+	unsigned long *p = hw->io_ports_array;
 	int i;
 
 	typedef struct {
@@ -314,7 +314,7 @@ static int __init m8xx_ide_init_ports(hw_regs_t *hw, unsigned long data_port)
 #if defined(CONFIG_IDE_EXT_DIRECT)
 static int __init m8xx_ide_init_ports(hw_regs_t *hw, unsigned long data_port)
 {
-	unsigned long *p = hw->io_ports;
+	unsigned long *p = hw->io_ports_array;
 	int i;
 
 	u32 ide_phy_base;
@@ -811,24 +811,28 @@ static int __init mpc8xx_ide_probe(void)
 #ifdef IDE0_BASE_OFFSET
 	memset(&hw, 0, sizeof(hw));
 	if (!m8xx_ide_init_ports(&hw, 0)) {
-		ide_hwif_t *hwif = &ide_hwifs[0];
+		ide_hwif_t *hwif = ide_find_port();
 
-		ide_init_port_hw(hwif, &hw);
-		hwif->pio_mask = ATA_PIO4;
-		hwif->port_ops = &m8xx_port_ops;
+		if (hwif) {
+			ide_init_port_hw(hwif, &hw);
+			hwif->pio_mask = ATA_PIO4;
+			hwif->port_ops = &m8xx_port_ops;
 
-		idx[0] = 0;
+			idx[0] = hwif->index;
+		}
 	}
 #ifdef IDE1_BASE_OFFSET
 	memset(&hw, 0, sizeof(hw));
 	if (!m8xx_ide_init_ports(&hw, 1)) {
-		ide_hwif_t *mate = &ide_hwifs[1];
+		ide_hwif_t *mate = ide_find_port();
 
-		ide_init_port_hw(mate, &hw);
-		mate->pio_mask = ATA_PIO4;
-		mate->port_ops = &m8xx_port_ops;
+		if (mate) {
+			ide_init_port_hw(mate, &hw);
+			mate->pio_mask = ATA_PIO4;
+			mate->port_ops = &m8xx_port_ops;
 
-		idx[1] = 1;
+			idx[1] = mate->index;
+		}
 	}
 #endif
 #endif
diff --git a/trunk/drivers/ide/ppc/pmac.c b/trunk/drivers/ide/ppc/pmac.c
index 185faa0dce94..48aa019127bc 100644
--- a/trunk/drivers/ide/ppc/pmac.c
+++ b/trunk/drivers/ide/ppc/pmac.c
@@ -417,7 +417,7 @@ static void pmac_ide_kauai_selectproc(ide_drive_t *drive);
 #endif /* CONFIG_BLK_DEV_IDEDMA_PMAC */
 
 #define PMAC_IDE_REG(x) \
-	((void __iomem *)((drive)->hwif->io_ports[IDE_DATA_OFFSET] + (x)))
+	((void __iomem *)((drive)->hwif->io_ports.data_addr + (x)))
 
 /*
  * Apply the timings of the proper unit (master/slave) to the shared
@@ -941,6 +941,7 @@ static const struct ide_port_info pmac_port_info = {
 	.port_ops		= &pmac_ide_port_ops,
 	.host_flags		= IDE_HFLAG_SET_PIO_MODE_KEEP_DMA |
 				  IDE_HFLAG_POST_SET_MODE |
+				  IDE_HFLAG_MMIO |
 				  IDE_HFLAG_UNMASK_IRQS,
 	.pio_mask		= ATA_PIO4,
 	.mwdma_mask		= ATA_MWDMA2,
@@ -1086,8 +1087,9 @@ static void __devinit pmac_ide_init_ports(hw_regs_t *hw, unsigned long base)
 	int i;
 
 	for (i = 0; i < 8; ++i)
-		hw->io_ports[i] = base + i * 0x10;
-	hw->io_ports[8] = base + 0x160;
+		hw->io_ports_array[i] = base + i * 0x10;
+
+	hw->io_ports.ctl_addr = base + 0x160;
 }
 
 /*
diff --git a/trunk/drivers/infiniband/core/umem.c b/trunk/drivers/infiniband/core/umem.c
index 4e3128ff73c1..fe78f7d25099 100644
--- a/trunk/drivers/infiniband/core/umem.c
+++ b/trunk/drivers/infiniband/core/umem.c
@@ -38,6 +38,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/sched.h>
 #include <linux/hugetlb.h>
+#include <linux/dma-attrs.h>
 
 #include "uverbs.h"
 
@@ -72,9 +73,10 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
  * @addr: userspace virtual address to start at
  * @size: length of region to pin
  * @access: IB_ACCESS_xxx flags for memory being pinned
+ * @dmasync: flush in-flight DMA when the memory region is written
  */
 struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
-			    size_t size, int access)
+			    size_t size, int access, int dmasync)
 {
 	struct ib_umem *umem;
 	struct page **page_list;
@@ -87,6 +89,10 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	int ret;
 	int off;
 	int i;
+	DEFINE_DMA_ATTRS(attrs);
+
+	if (dmasync)
+		dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs);
 
 	if (!can_do_mlock())
 		return ERR_PTR(-EPERM);
@@ -174,10 +180,11 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 				sg_set_page(&chunk->page_list[i], page_list[i + off], PAGE_SIZE, 0);
 			}
 
-			chunk->nmap = ib_dma_map_sg(context->device,
-						    &chunk->page_list[0],
-						    chunk->nents,
-						    DMA_BIDIRECTIONAL);
+			chunk->nmap = ib_dma_map_sg_attrs(context->device,
+							  &chunk->page_list[0],
+							  chunk->nents,
+							  DMA_BIDIRECTIONAL,
+							  &attrs);
 			if (chunk->nmap <= 0) {
 				for (i = 0; i < chunk->nents; ++i)
 					put_page(sg_page(&chunk->page_list[i]));
diff --git a/trunk/drivers/infiniband/hw/amso1100/c2_provider.c b/trunk/drivers/infiniband/hw/amso1100/c2_provider.c
index 6af2c0f79a67..2acf9b62cf99 100644
--- a/trunk/drivers/infiniband/hw/amso1100/c2_provider.c
+++ b/trunk/drivers/infiniband/hw/amso1100/c2_provider.c
@@ -452,7 +452,7 @@ static struct ib_mr *c2_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 		return ERR_PTR(-ENOMEM);
 	c2mr->pd = c2pd;
 
-	c2mr->umem = ib_umem_get(pd->uobject->context, start, length, acc);
+	c2mr->umem = ib_umem_get(pd->uobject->context, start, length, acc, 0);
 	if (IS_ERR(c2mr->umem)) {
 		err = PTR_ERR(c2mr->umem);
 		kfree(c2mr);
diff --git a/trunk/drivers/infiniband/hw/cxgb3/iwch_provider.c b/trunk/drivers/infiniband/hw/cxgb3/iwch_provider.c
index ab4695c1dd56..e343e9e64844 100644
--- a/trunk/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/trunk/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -602,7 +602,7 @@ static struct ib_mr *iwch_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	if (!mhp)
 		return ERR_PTR(-ENOMEM);
 
-	mhp->umem = ib_umem_get(pd->uobject->context, start, length, acc);
+	mhp->umem = ib_umem_get(pd->uobject->context, start, length, acc, 0);
 	if (IS_ERR(mhp->umem)) {
 		err = PTR_ERR(mhp->umem);
 		kfree(mhp);
diff --git a/trunk/drivers/infiniband/hw/ehca/ehca_classes.h b/trunk/drivers/infiniband/hw/ehca/ehca_classes.h
index 0d13fe0a260b..3d6d9461c31d 100644
--- a/trunk/drivers/infiniband/hw/ehca/ehca_classes.h
+++ b/trunk/drivers/infiniband/hw/ehca/ehca_classes.h
@@ -160,6 +160,7 @@ struct ehca_qp {
 	};
 	u32 qp_type;
 	enum ehca_ext_qp_type ext_type;
+	enum ib_qp_state state;
 	struct ipz_queue ipz_squeue;
 	struct ipz_queue ipz_rqueue;
 	struct h_galpas galpas;
diff --git a/trunk/drivers/infiniband/hw/ehca/ehca_irq.c b/trunk/drivers/infiniband/hw/ehca/ehca_irq.c
index b5ca94c6b8d9..ca5eb0cb628c 100644
--- a/trunk/drivers/infiniband/hw/ehca/ehca_irq.c
+++ b/trunk/drivers/infiniband/hw/ehca/ehca_irq.c
@@ -633,7 +633,7 @@ static inline int find_next_online_cpu(struct ehca_comp_pool *pool)
 	unsigned long flags;
 
 	WARN_ON_ONCE(!in_interrupt());
-	if (ehca_debug_level)
+	if (ehca_debug_level >= 3)
 		ehca_dmp(&cpu_online_map, sizeof(cpumask_t), "");
 
 	spin_lock_irqsave(&pool->last_cpu_lock, flags);
diff --git a/trunk/drivers/infiniband/hw/ehca/ehca_main.c b/trunk/drivers/infiniband/hw/ehca/ehca_main.c
index 65b3362cdb9b..65048976198c 100644
--- a/trunk/drivers/infiniband/hw/ehca/ehca_main.c
+++ b/trunk/drivers/infiniband/hw/ehca/ehca_main.c
@@ -50,7 +50,7 @@
 #include "ehca_tools.h"
 #include "hcp_if.h"
 
-#define HCAD_VERSION "0025"
+#define HCAD_VERSION "0026"
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Christoph Raisch <raisch@de.ibm.com>");
@@ -60,7 +60,6 @@ MODULE_VERSION(HCAD_VERSION);
 static int ehca_open_aqp1     = 0;
 static int ehca_hw_level      = 0;
 static int ehca_poll_all_eqs  = 1;
-static int ehca_mr_largepage  = 1;
 
 int ehca_debug_level   = 0;
 int ehca_nr_ports      = 2;
@@ -70,45 +69,40 @@ int ehca_static_rate   = -1;
 int ehca_scaling_code  = 0;
 int ehca_lock_hcalls   = -1;
 
-module_param_named(open_aqp1,     ehca_open_aqp1,     int, S_IRUGO);
-module_param_named(debug_level,   ehca_debug_level,   int, S_IRUGO);
-module_param_named(hw_level,      ehca_hw_level,      int, S_IRUGO);
-module_param_named(nr_ports,      ehca_nr_ports,      int, S_IRUGO);
-module_param_named(use_hp_mr,     ehca_use_hp_mr,     int, S_IRUGO);
-module_param_named(port_act_time, ehca_port_act_time, int, S_IRUGO);
-module_param_named(poll_all_eqs,  ehca_poll_all_eqs,  int, S_IRUGO);
-module_param_named(static_rate,   ehca_static_rate,   int, S_IRUGO);
-module_param_named(scaling_code,  ehca_scaling_code,  int, S_IRUGO);
-module_param_named(mr_largepage,  ehca_mr_largepage,  int, S_IRUGO);
+module_param_named(open_aqp1,     ehca_open_aqp1,     bool, S_IRUGO);
+module_param_named(debug_level,   ehca_debug_level,   int,  S_IRUGO);
+module_param_named(hw_level,      ehca_hw_level,      int,  S_IRUGO);
+module_param_named(nr_ports,      ehca_nr_ports,      int,  S_IRUGO);
+module_param_named(use_hp_mr,     ehca_use_hp_mr,     bool, S_IRUGO);
+module_param_named(port_act_time, ehca_port_act_time, int,  S_IRUGO);
+module_param_named(poll_all_eqs,  ehca_poll_all_eqs,  bool, S_IRUGO);
+module_param_named(static_rate,   ehca_static_rate,   int,  S_IRUGO);
+module_param_named(scaling_code,  ehca_scaling_code,  bool, S_IRUGO);
 module_param_named(lock_hcalls,   ehca_lock_hcalls,   bool, S_IRUGO);
 
 MODULE_PARM_DESC(open_aqp1,
-		 "AQP1 on startup (0: no (default), 1: yes)");
+		 "Open AQP1 on startup (default: no)");
 MODULE_PARM_DESC(debug_level,
-		 "debug level"
-		 " (0: no debug traces (default), 1: with debug traces)");
+		 "Amount of debug output (0: none (default), 1: traces, "
+		 "2: some dumps, 3: lots)");
 MODULE_PARM_DESC(hw_level,
-		 "hardware level"
-		 " (0: autosensing (default), 1: v. 0.20, 2: v. 0.21)");
+		 "Hardware level (0: autosensing (default), "
+		 "0x10..0x14: eHCA, 0x20..0x23: eHCA2)");
 MODULE_PARM_DESC(nr_ports,
 		 "number of connected ports (-1: autodetect, 1: port one only, "
 		 "2: two ports (default)");
 MODULE_PARM_DESC(use_hp_mr,
-		 "high performance MRs (0: no (default), 1: yes)");
+		 "Use high performance MRs (default: no)");
 MODULE_PARM_DESC(port_act_time,
-		 "time to wait for port activation (default: 30 sec)");
+		 "Time to wait for port activation (default: 30 sec)");
 MODULE_PARM_DESC(poll_all_eqs,
-		 "polls all event queues periodically"
-		 " (0: no, 1: yes (default))");
+		 "Poll all event queues periodically (default: yes)");
 MODULE_PARM_DESC(static_rate,
-		 "set permanent static rate (default: disabled)");
+		 "Set permanent static rate (default: no static rate)");
 MODULE_PARM_DESC(scaling_code,
-		 "set scaling code (0: disabled/default, 1: enabled)");
-MODULE_PARM_DESC(mr_largepage,
-		 "use large page for MR (0: use PAGE_SIZE (default), "
-		 "1: use large page depending on MR size");
+		 "Enable scaling code (default: no)");
 MODULE_PARM_DESC(lock_hcalls,
-		 "serialize all hCalls made by the driver "
+		 "Serialize all hCalls made by the driver "
 		 "(default: autodetect)");
 
 DEFINE_RWLOCK(ehca_qp_idr_lock);
@@ -275,6 +269,7 @@ static int ehca_sense_attributes(struct ehca_shca *shca)
 	u64 h_ret;
 	struct hipz_query_hca *rblock;
 	struct hipz_query_port *port;
+	const char *loc_code;
 
 	static const u32 pgsize_map[] = {
 		HCA_CAP_MR_PGSIZE_4K,  0x1000,
@@ -283,6 +278,12 @@ static int ehca_sense_attributes(struct ehca_shca *shca)
 		HCA_CAP_MR_PGSIZE_16M, 0x1000000,
 	};
 
+	ehca_gen_dbg("Probing adapter %s...",
+		     shca->ofdev->node->full_name);
+	loc_code = of_get_property(shca->ofdev->node, "ibm,loc-code", NULL);
+	if (loc_code)
+		ehca_gen_dbg(" ... location lode=%s", loc_code);
+
 	rblock = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!rblock) {
 		ehca_gen_err("Cannot allocate rblock memory.");
@@ -350,11 +351,9 @@ static int ehca_sense_attributes(struct ehca_shca *shca)
 
 	/* translate supported MR page sizes; always support 4K */
 	shca->hca_cap_mr_pgsize = EHCA_PAGESIZE;
-	if (ehca_mr_largepage) { /* support extra sizes only if enabled */
-		for (i = 0; i < ARRAY_SIZE(pgsize_map); i += 2)
-			if (rblock->memory_page_size_supported & pgsize_map[i])
-				shca->hca_cap_mr_pgsize |= pgsize_map[i + 1];
-	}
+	for (i = 0; i < ARRAY_SIZE(pgsize_map); i += 2)
+		if (rblock->memory_page_size_supported & pgsize_map[i])
+			shca->hca_cap_mr_pgsize |= pgsize_map[i + 1];
 
 	/* query max MTU from first port -- it's the same for all ports */
 	port = (struct hipz_query_port *)rblock;
@@ -567,8 +566,7 @@ static int ehca_destroy_aqp1(struct ehca_sport *sport)
 
 static ssize_t ehca_show_debug_level(struct device_driver *ddp, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%d\n",
-			ehca_debug_level);
+	return snprintf(buf, PAGE_SIZE, "%d\n", ehca_debug_level);
 }
 
 static ssize_t ehca_store_debug_level(struct device_driver *ddp,
@@ -657,14 +655,6 @@ static ssize_t ehca_show_adapter_handle(struct device *dev,
 }
 static DEVICE_ATTR(adapter_handle, S_IRUGO, ehca_show_adapter_handle, NULL);
 
-static ssize_t ehca_show_mr_largepage(struct device *dev,
-				      struct device_attribute *attr,
-				      char *buf)
-{
-	return sprintf(buf, "%d\n", ehca_mr_largepage);
-}
-static DEVICE_ATTR(mr_largepage, S_IRUGO, ehca_show_mr_largepage, NULL);
-
 static struct attribute *ehca_dev_attrs[] = {
 	&dev_attr_adapter_handle.attr,
 	&dev_attr_num_ports.attr,
@@ -681,7 +671,6 @@ static struct attribute *ehca_dev_attrs[] = {
 	&dev_attr_cur_mw.attr,
 	&dev_attr_max_pd.attr,
 	&dev_attr_max_ah.attr,
-	&dev_attr_mr_largepage.attr,
 	NULL
 };
 
diff --git a/trunk/drivers/infiniband/hw/ehca/ehca_mrmw.c b/trunk/drivers/infiniband/hw/ehca/ehca_mrmw.c
index f26997fc00f8..f974367cad40 100644
--- a/trunk/drivers/infiniband/hw/ehca/ehca_mrmw.c
+++ b/trunk/drivers/infiniband/hw/ehca/ehca_mrmw.c
@@ -323,7 +323,7 @@ struct ib_mr *ehca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	}
 
 	e_mr->umem = ib_umem_get(pd->uobject->context, start, length,
-				 mr_access_flags);
+				 mr_access_flags, 0);
 	if (IS_ERR(e_mr->umem)) {
 		ib_mr = (void *)e_mr->umem;
 		goto reg_user_mr_exit1;
@@ -1794,8 +1794,9 @@ static int ehca_check_kpages_per_ate(struct scatterlist *page_list,
 	int t;
 	for (t = start_idx; t <= end_idx; t++) {
 		u64 pgaddr = page_to_pfn(sg_page(&page_list[t])) << PAGE_SHIFT;
-		ehca_gen_dbg("chunk_page=%lx value=%016lx", pgaddr,
-			     *(u64 *)abs_to_virt(phys_to_abs(pgaddr)));
+		if (ehca_debug_level >= 3)
+			ehca_gen_dbg("chunk_page=%lx value=%016lx", pgaddr,
+				     *(u64 *)abs_to_virt(phys_to_abs(pgaddr)));
 		if (pgaddr - PAGE_SIZE != *prev_pgaddr) {
 			ehca_gen_err("uncontiguous page found pgaddr=%lx "
 				     "prev_pgaddr=%lx page_list_i=%x",
@@ -1862,10 +1863,13 @@ static int ehca_set_pagebuf_user2(struct ehca_mr_pginfo *pginfo,
 						pgaddr &
 						~(pginfo->hwpage_size - 1));
 				}
-				ehca_gen_dbg("kpage=%lx chunk_page=%lx "
-					     "value=%016lx", *kpage, pgaddr,
-					     *(u64 *)abs_to_virt(
-						     phys_to_abs(pgaddr)));
+				if (ehca_debug_level >= 3) {
+					u64 val = *(u64 *)abs_to_virt(
+						phys_to_abs(pgaddr));
+					ehca_gen_dbg("kpage=%lx chunk_page=%lx "
+						     "value=%016lx",
+						     *kpage, pgaddr, val);
+				}
 				prev_pgaddr = pgaddr;
 				i++;
 				pginfo->kpage_cnt++;
diff --git a/trunk/drivers/infiniband/hw/ehca/ehca_qp.c b/trunk/drivers/infiniband/hw/ehca/ehca_qp.c
index 3eb14a52cbf2..57bef1152cc2 100644
--- a/trunk/drivers/infiniband/hw/ehca/ehca_qp.c
+++ b/trunk/drivers/infiniband/hw/ehca/ehca_qp.c
@@ -550,6 +550,7 @@ static struct ehca_qp *internal_create_qp(
 	spin_lock_init(&my_qp->spinlock_r);
 	my_qp->qp_type = qp_type;
 	my_qp->ext_type = parms.ext_type;
+	my_qp->state = IB_QPS_RESET;
 
 	if (init_attr->recv_cq)
 		my_qp->recv_cq =
@@ -965,7 +966,7 @@ static int prepare_sqe_rts(struct ehca_qp *my_qp, struct ehca_shca *shca,
 		 qp_num, bad_send_wqe_p);
 	/* convert wqe pointer to vadr */
 	bad_send_wqe_v = abs_to_virt((u64)bad_send_wqe_p);
-	if (ehca_debug_level)
+	if (ehca_debug_level >= 2)
 		ehca_dmp(bad_send_wqe_v, 32, "qp_num=%x bad_wqe", qp_num);
 	squeue = &my_qp->ipz_squeue;
 	if (ipz_queue_abs_to_offset(squeue, (u64)bad_send_wqe_p, &q_ofs)) {
@@ -978,7 +979,7 @@ static int prepare_sqe_rts(struct ehca_qp *my_qp, struct ehca_shca *shca,
 	wqe = (struct ehca_wqe *)ipz_qeit_calc(squeue, q_ofs);
 	*bad_wqe_cnt = 0;
 	while (wqe->optype != 0xff && wqe->wqef != 0xff) {
-		if (ehca_debug_level)
+		if (ehca_debug_level >= 2)
 			ehca_dmp(wqe, 32, "qp_num=%x wqe", qp_num);
 		wqe->nr_of_data_seg = 0; /* suppress data access */
 		wqe->wqef = WQEF_PURGE; /* WQE to be purged */
@@ -1450,7 +1451,7 @@ static int internal_modify_qp(struct ib_qp *ibqp,
 		/* no support for max_send/recv_sge yet */
 	}
 
-	if (ehca_debug_level)
+	if (ehca_debug_level >= 2)
 		ehca_dmp(mqpcb, 4*70, "qp_num=%x", ibqp->qp_num);
 
 	h_ret = hipz_h_modify_qp(shca->ipz_hca_handle,
@@ -1508,6 +1509,8 @@ static int internal_modify_qp(struct ib_qp *ibqp,
 	if (attr_mask & IB_QP_QKEY)
 		my_qp->qkey = attr->qkey;
 
+	my_qp->state = qp_new_state;
+
 modify_qp_exit2:
 	if (squeue_locked) { /* this means: sqe -> rts */
 		spin_unlock_irqrestore(&my_qp->spinlock_s, flags);
@@ -1763,7 +1766,7 @@ int ehca_query_qp(struct ib_qp *qp,
 	if (qp_init_attr)
 		*qp_init_attr = my_qp->init_attr;
 
-	if (ehca_debug_level)
+	if (ehca_debug_level >= 2)
 		ehca_dmp(qpcb, 4*70, "qp_num=%x", qp->qp_num);
 
 query_qp_exit1:
@@ -1811,7 +1814,7 @@ int ehca_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
 		goto modify_srq_exit0;
 	}
 
-	if (ehca_debug_level)
+	if (ehca_debug_level >= 2)
 		ehca_dmp(mqpcb, 4*70, "qp_num=%x", my_qp->real_qp_num);
 
 	h_ret = hipz_h_modify_qp(shca->ipz_hca_handle, my_qp->ipz_qp_handle,
@@ -1864,7 +1867,7 @@ int ehca_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr)
 	srq_attr->srq_limit = EHCA_BMASK_GET(
 		MQPCB_CURR_SRQ_LIMIT, qpcb->curr_srq_limit);
 
-	if (ehca_debug_level)
+	if (ehca_debug_level >= 2)
 		ehca_dmp(qpcb, 4*70, "qp_num=%x", my_qp->real_qp_num);
 
 query_srq_exit1:
diff --git a/trunk/drivers/infiniband/hw/ehca/ehca_reqs.c b/trunk/drivers/infiniband/hw/ehca/ehca_reqs.c
index a20bbf466188..bbe0436f4f75 100644
--- a/trunk/drivers/infiniband/hw/ehca/ehca_reqs.c
+++ b/trunk/drivers/infiniband/hw/ehca/ehca_reqs.c
@@ -81,7 +81,7 @@ static inline int ehca_write_rwqe(struct ipz_queue *ipz_rqueue,
 			recv_wr->sg_list[cnt_ds].length;
 	}
 
-	if (ehca_debug_level) {
+	if (ehca_debug_level >= 3) {
 		ehca_gen_dbg("RECEIVE WQE written into ipz_rqueue=%p",
 			     ipz_rqueue);
 		ehca_dmp(wqe_p, 16*(6 + wqe_p->nr_of_data_seg), "recv wqe");
@@ -281,7 +281,7 @@ static inline int ehca_write_swqe(struct ehca_qp *qp,
 		return -EINVAL;
 	}
 
-	if (ehca_debug_level) {
+	if (ehca_debug_level >= 3) {
 		ehca_gen_dbg("SEND WQE written into queue qp=%p ", qp);
 		ehca_dmp( wqe_p, 16*(6 + wqe_p->nr_of_data_seg), "send wqe");
 	}
@@ -421,6 +421,11 @@ int ehca_post_send(struct ib_qp *qp,
 	int ret = 0;
 	unsigned long flags;
 
+	if (unlikely(my_qp->state != IB_QPS_RTS)) {
+		ehca_err(qp->device, "QP not in RTS state  qpn=%x", qp->qp_num);
+		return -EINVAL;
+	}
+
 	/* LOCK the QUEUE */
 	spin_lock_irqsave(&my_qp->spinlock_s, flags);
 
@@ -454,13 +459,14 @@ int ehca_post_send(struct ib_qp *qp,
 			goto post_send_exit0;
 		}
 		wqe_cnt++;
-		ehca_dbg(qp->device, "ehca_qp=%p qp_num=%x wqe_cnt=%d",
-			 my_qp, qp->qp_num, wqe_cnt);
 	} /* eof for cur_send_wr */
 
 post_send_exit0:
 	iosync(); /* serialize GAL register access */
 	hipz_update_sqa(my_qp, wqe_cnt);
+	if (unlikely(ret || ehca_debug_level >= 2))
+		ehca_dbg(qp->device, "ehca_qp=%p qp_num=%x wqe_cnt=%d ret=%i",
+			 my_qp, qp->qp_num, wqe_cnt, ret);
 	my_qp->message_count += wqe_cnt;
 	spin_unlock_irqrestore(&my_qp->spinlock_s, flags);
 	return ret;
@@ -520,13 +526,14 @@ static int internal_post_recv(struct ehca_qp *my_qp,
 			goto post_recv_exit0;
 		}
 		wqe_cnt++;
-		ehca_dbg(dev, "ehca_qp=%p qp_num=%x wqe_cnt=%d",
-			 my_qp, my_qp->real_qp_num, wqe_cnt);
 	} /* eof for cur_recv_wr */
 
 post_recv_exit0:
 	iosync(); /* serialize GAL register access */
 	hipz_update_rqa(my_qp, wqe_cnt);
+	if (unlikely(ret || ehca_debug_level >= 2))
+	    ehca_dbg(dev, "ehca_qp=%p qp_num=%x wqe_cnt=%d ret=%i",
+		     my_qp, my_qp->real_qp_num, wqe_cnt, ret);
 	spin_unlock_irqrestore(&my_qp->spinlock_r, flags);
 	return ret;
 }
@@ -570,16 +577,17 @@ static inline int ehca_poll_cq_one(struct ib_cq *cq, struct ib_wc *wc)
 	struct ehca_cq *my_cq = container_of(cq, struct ehca_cq, ib_cq);
 	struct ehca_cqe *cqe;
 	struct ehca_qp *my_qp;
-	int cqe_count = 0;
+	int cqe_count = 0, is_error;
 
 poll_cq_one_read_cqe:
 	cqe = (struct ehca_cqe *)
 		ipz_qeit_get_inc_valid(&my_cq->ipz_queue);
 	if (!cqe) {
 		ret = -EAGAIN;
-		ehca_dbg(cq->device, "Completion queue is empty ehca_cq=%p "
-			 "cq_num=%x ret=%i", my_cq, my_cq->cq_number, ret);
-		goto  poll_cq_one_exit0;
+		if (ehca_debug_level >= 3)
+			ehca_dbg(cq->device, "Completion queue is empty  "
+				 "my_cq=%p cq_num=%x", my_cq, my_cq->cq_number);
+		goto poll_cq_one_exit0;
 	}
 
 	/* prevents loads being reordered across this point */
@@ -609,7 +617,7 @@ static inline int ehca_poll_cq_one(struct ib_cq *cq, struct ib_wc *wc)
 			ehca_dbg(cq->device,
 				 "Got CQE with purged bit qp_num=%x src_qp=%x",
 				 cqe->local_qp_number, cqe->remote_qp_number);
-			if (ehca_debug_level)
+			if (ehca_debug_level >= 2)
 				ehca_dmp(cqe, 64, "qp_num=%x src_qp=%x",
 					 cqe->local_qp_number,
 					 cqe->remote_qp_number);
@@ -622,11 +630,13 @@ static inline int ehca_poll_cq_one(struct ib_cq *cq, struct ib_wc *wc)
 		}
 	}
 
-	/* tracing cqe */
-	if (unlikely(ehca_debug_level)) {
+	is_error = cqe->status & WC_STATUS_ERROR_BIT;
+
+	/* trace error CQEs if debug_level >= 1, trace all CQEs if >= 3 */
+	if (unlikely(ehca_debug_level >= 3 || (ehca_debug_level && is_error))) {
 		ehca_dbg(cq->device,
-			 "Received COMPLETION ehca_cq=%p cq_num=%x -----",
-			 my_cq, my_cq->cq_number);
+			 "Received %sCOMPLETION ehca_cq=%p cq_num=%x -----",
+			 is_error ? "ERROR " : "", my_cq, my_cq->cq_number);
 		ehca_dmp(cqe, 64, "ehca_cq=%p cq_num=%x",
 			 my_cq, my_cq->cq_number);
 		ehca_dbg(cq->device,
@@ -649,8 +659,9 @@ static inline int ehca_poll_cq_one(struct ib_cq *cq, struct ib_wc *wc)
 		/* update also queue adder to throw away this entry!!! */
 		goto poll_cq_one_exit0;
 	}
+
 	/* eval ib_wc_status */
-	if (unlikely(cqe->status & WC_STATUS_ERROR_BIT)) {
+	if (unlikely(is_error)) {
 		/* complete with errors */
 		map_ib_wc_status(cqe->status, &wc->status);
 		wc->vendor_err = wc->status;
@@ -671,14 +682,6 @@ static inline int ehca_poll_cq_one(struct ib_cq *cq, struct ib_wc *wc)
 	wc->imm_data = cpu_to_be32(cqe->immediate_data);
 	wc->sl = cqe->service_level;
 
-	if (unlikely(wc->status != IB_WC_SUCCESS))
-		ehca_dbg(cq->device,
-			 "ehca_cq=%p cq_num=%x WARNING unsuccessful cqe "
-			 "OPType=%x status=%x qp_num=%x src_qp=%x wr_id=%lx "
-			 "cqe=%p", my_cq, my_cq->cq_number, cqe->optype,
-			 cqe->status, cqe->local_qp_number,
-			 cqe->remote_qp_number, cqe->work_request_id, cqe);
-
 poll_cq_one_exit0:
 	if (cqe_count > 0)
 		hipz_update_feca(my_cq, cqe_count);
diff --git a/trunk/drivers/infiniband/hw/ehca/ehca_uverbs.c b/trunk/drivers/infiniband/hw/ehca/ehca_uverbs.c
index 1b07f2beafaf..e43ed8f8a0c8 100644
--- a/trunk/drivers/infiniband/hw/ehca/ehca_uverbs.c
+++ b/trunk/drivers/infiniband/hw/ehca/ehca_uverbs.c
@@ -211,8 +211,7 @@ static int ehca_mmap_qp(struct vm_area_struct *vma, struct ehca_qp *qp,
 		break;
 
 	case 1: /* qp rqueue_addr */
-		ehca_dbg(qp->ib_qp.device, "qp_num=%x rqueue",
-			 qp->ib_qp.qp_num);
+		ehca_dbg(qp->ib_qp.device, "qp_num=%x rq", qp->ib_qp.qp_num);
 		ret = ehca_mmap_queue(vma, &qp->ipz_rqueue,
 				      &qp->mm_count_rqueue);
 		if (unlikely(ret)) {
@@ -224,8 +223,7 @@ static int ehca_mmap_qp(struct vm_area_struct *vma, struct ehca_qp *qp,
 		break;
 
 	case 2: /* qp squeue_addr */
-		ehca_dbg(qp->ib_qp.device, "qp_num=%x squeue",
-			 qp->ib_qp.qp_num);
+		ehca_dbg(qp->ib_qp.device, "qp_num=%x sq", qp->ib_qp.qp_num);
 		ret = ehca_mmap_queue(vma, &qp->ipz_squeue,
 				      &qp->mm_count_squeue);
 		if (unlikely(ret)) {
diff --git a/trunk/drivers/infiniband/hw/ehca/hcp_if.c b/trunk/drivers/infiniband/hw/ehca/hcp_if.c
index 7029aa653751..5245e13c3a30 100644
--- a/trunk/drivers/infiniband/hw/ehca/hcp_if.c
+++ b/trunk/drivers/infiniband/hw/ehca/hcp_if.c
@@ -123,8 +123,9 @@ static long ehca_plpar_hcall_norets(unsigned long opcode,
 	int i, sleep_msecs;
 	unsigned long flags = 0;
 
-	ehca_gen_dbg("opcode=%lx " HCALL7_REGS_FORMAT,
-		     opcode, arg1, arg2, arg3, arg4, arg5, arg6, arg7);
+	if (unlikely(ehca_debug_level >= 2))
+		ehca_gen_dbg("opcode=%lx " HCALL7_REGS_FORMAT,
+			     opcode, arg1, arg2, arg3, arg4, arg5, arg6, arg7);
 
 	for (i = 0; i < 5; i++) {
 		/* serialize hCalls to work around firmware issue */
@@ -148,7 +149,8 @@ static long ehca_plpar_hcall_norets(unsigned long opcode,
 				     opcode, ret, arg1, arg2, arg3,
 				     arg4, arg5, arg6, arg7);
 		else
-			ehca_gen_dbg("opcode=%lx ret=%li", opcode, ret);
+			if (unlikely(ehca_debug_level >= 2))
+				ehca_gen_dbg("opcode=%lx ret=%li", opcode, ret);
 
 		return ret;
 	}
@@ -172,8 +174,10 @@ static long ehca_plpar_hcall9(unsigned long opcode,
 	int i, sleep_msecs;
 	unsigned long flags = 0;
 
-	ehca_gen_dbg("INPUT -- opcode=%lx " HCALL9_REGS_FORMAT, opcode,
-		     arg1, arg2, arg3, arg4, arg5, arg6, arg7, arg8, arg9);
+	if (unlikely(ehca_debug_level >= 2))
+		ehca_gen_dbg("INPUT -- opcode=%lx " HCALL9_REGS_FORMAT, opcode,
+			     arg1, arg2, arg3, arg4, arg5,
+			     arg6, arg7, arg8, arg9);
 
 	for (i = 0; i < 5; i++) {
 		/* serialize hCalls to work around firmware issue */
@@ -201,7 +205,7 @@ static long ehca_plpar_hcall9(unsigned long opcode,
 				     ret, outs[0], outs[1], outs[2], outs[3],
 				     outs[4], outs[5], outs[6], outs[7],
 				     outs[8]);
-		} else
+		} else if (unlikely(ehca_debug_level >= 2))
 			ehca_gen_dbg("OUTPUT -- ret=%li " HCALL9_REGS_FORMAT,
 				     ret, outs[0], outs[1], outs[2], outs[3],
 				     outs[4], outs[5], outs[6], outs[7],
@@ -381,7 +385,7 @@ u64 hipz_h_query_port(const struct ipz_adapter_handle adapter_handle,
 				      r_cb,	             /* r6 */
 				      0, 0, 0, 0);
 
-	if (ehca_debug_level)
+	if (ehca_debug_level >= 2)
 		ehca_dmp(query_port_response_block, 64, "response_block");
 
 	return ret;
@@ -731,9 +735,6 @@ u64 hipz_h_alloc_resource_mr(const struct ipz_adapter_handle adapter_handle,
 	u64 ret;
 	u64 outs[PLPAR_HCALL9_BUFSIZE];
 
-	ehca_gen_dbg("kernel PAGE_SIZE=%x access_ctrl=%016x "
-		     "vaddr=%lx length=%lx",
-		     (u32)PAGE_SIZE, access_ctrl, vaddr, length);
 	ret = ehca_plpar_hcall9(H_ALLOC_RESOURCE, outs,
 				adapter_handle.handle,            /* r4 */
 				5,                                /* r5 */
@@ -758,7 +759,7 @@ u64 hipz_h_register_rpage_mr(const struct ipz_adapter_handle adapter_handle,
 {
 	u64 ret;
 
-	if (unlikely(ehca_debug_level >= 2)) {
+	if (unlikely(ehca_debug_level >= 3)) {
 		if (count > 1) {
 			u64 *kpage;
 			int i;
diff --git a/trunk/drivers/infiniband/hw/ipath/ipath_mr.c b/trunk/drivers/infiniband/hw/ipath/ipath_mr.c
index db4ba92f79fc..9d343b7c2f3b 100644
--- a/trunk/drivers/infiniband/hw/ipath/ipath_mr.c
+++ b/trunk/drivers/infiniband/hw/ipath/ipath_mr.c
@@ -195,7 +195,8 @@ struct ib_mr *ipath_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 		goto bail;
 	}
 
-	umem = ib_umem_get(pd->uobject->context, start, length, mr_access_flags);
+	umem = ib_umem_get(pd->uobject->context, start, length,
+			   mr_access_flags, 0);
 	if (IS_ERR(umem))
 		return (void *) umem;
 
diff --git a/trunk/drivers/infiniband/hw/mlx4/cq.c b/trunk/drivers/infiniband/hw/mlx4/cq.c
index 3557e7edc9b6..e3dddfc687f9 100644
--- a/trunk/drivers/infiniband/hw/mlx4/cq.c
+++ b/trunk/drivers/infiniband/hw/mlx4/cq.c
@@ -137,7 +137,7 @@ static int mlx4_ib_get_cq_umem(struct mlx4_ib_dev *dev, struct ib_ucontext *cont
 	int err;
 
 	*umem = ib_umem_get(context, buf_addr, cqe * sizeof (struct mlx4_cqe),
-			    IB_ACCESS_LOCAL_WRITE);
+			    IB_ACCESS_LOCAL_WRITE, 1);
 	if (IS_ERR(*umem))
 		return PTR_ERR(*umem);
 
@@ -204,7 +204,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 
 		uar = &to_mucontext(context)->uar;
 	} else {
-		err = mlx4_ib_db_alloc(dev, &cq->db, 1);
+		err = mlx4_db_alloc(dev->dev, &cq->db, 1);
 		if (err)
 			goto err_cq;
 
@@ -250,7 +250,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 
 err_db:
 	if (!context)
-		mlx4_ib_db_free(dev, &cq->db);
+		mlx4_db_free(dev->dev, &cq->db);
 
 err_cq:
 	kfree(cq);
@@ -435,7 +435,7 @@ int mlx4_ib_destroy_cq(struct ib_cq *cq)
 		ib_umem_release(mcq->umem);
 	} else {
 		mlx4_ib_free_cq_buf(dev, &mcq->buf, cq->cqe + 1);
-		mlx4_ib_db_free(dev, &mcq->db);
+		mlx4_db_free(dev->dev, &mcq->db);
 	}
 
 	kfree(mcq);
diff --git a/trunk/drivers/infiniband/hw/mlx4/doorbell.c b/trunk/drivers/infiniband/hw/mlx4/doorbell.c
index 1c36087aef14..8aee4233b388 100644
--- a/trunk/drivers/infiniband/hw/mlx4/doorbell.c
+++ b/trunk/drivers/infiniband/hw/mlx4/doorbell.c
@@ -34,124 +34,6 @@
 
 #include "mlx4_ib.h"
 
-struct mlx4_ib_db_pgdir {
-	struct list_head	list;
-	DECLARE_BITMAP(order0, MLX4_IB_DB_PER_PAGE);
-	DECLARE_BITMAP(order1, MLX4_IB_DB_PER_PAGE / 2);
-	unsigned long	       *bits[2];
-	__be32		       *db_page;
-	dma_addr_t		db_dma;
-};
-
-static struct mlx4_ib_db_pgdir *mlx4_ib_alloc_db_pgdir(struct mlx4_ib_dev *dev)
-{
-	struct mlx4_ib_db_pgdir *pgdir;
-
-	pgdir = kzalloc(sizeof *pgdir, GFP_KERNEL);
-	if (!pgdir)
-		return NULL;
-
-	bitmap_fill(pgdir->order1, MLX4_IB_DB_PER_PAGE / 2);
-	pgdir->bits[0] = pgdir->order0;
-	pgdir->bits[1] = pgdir->order1;
-	pgdir->db_page = dma_alloc_coherent(dev->ib_dev.dma_device,
-					    PAGE_SIZE, &pgdir->db_dma,
-					    GFP_KERNEL);
-	if (!pgdir->db_page) {
-		kfree(pgdir);
-		return NULL;
-	}
-
-	return pgdir;
-}
-
-static int mlx4_ib_alloc_db_from_pgdir(struct mlx4_ib_db_pgdir *pgdir,
-				       struct mlx4_ib_db *db, int order)
-{
-	int o;
-	int i;
-
-	for (o = order; o <= 1; ++o) {
-		i = find_first_bit(pgdir->bits[o], MLX4_IB_DB_PER_PAGE >> o);
-		if (i < MLX4_IB_DB_PER_PAGE >> o)
-			goto found;
-	}
-
-	return -ENOMEM;
-
-found:
-	clear_bit(i, pgdir->bits[o]);
-
-	i <<= o;
-
-	if (o > order)
-		set_bit(i ^ 1, pgdir->bits[order]);
-
-	db->u.pgdir = pgdir;
-	db->index   = i;
-	db->db      = pgdir->db_page + db->index;
-	db->dma     = pgdir->db_dma  + db->index * 4;
-	db->order   = order;
-
-	return 0;
-}
-
-int mlx4_ib_db_alloc(struct mlx4_ib_dev *dev, struct mlx4_ib_db *db, int order)
-{
-	struct mlx4_ib_db_pgdir *pgdir;
-	int ret = 0;
-
-	mutex_lock(&dev->pgdir_mutex);
-
-	list_for_each_entry(pgdir, &dev->pgdir_list, list)
-		if (!mlx4_ib_alloc_db_from_pgdir(pgdir, db, order))
-			goto out;
-
-	pgdir = mlx4_ib_alloc_db_pgdir(dev);
-	if (!pgdir) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	list_add(&pgdir->list, &dev->pgdir_list);
-
-	/* This should never fail -- we just allocated an empty page: */
-	WARN_ON(mlx4_ib_alloc_db_from_pgdir(pgdir, db, order));
-
-out:
-	mutex_unlock(&dev->pgdir_mutex);
-
-	return ret;
-}
-
-void mlx4_ib_db_free(struct mlx4_ib_dev *dev, struct mlx4_ib_db *db)
-{
-	int o;
-	int i;
-
-	mutex_lock(&dev->pgdir_mutex);
-
-	o = db->order;
-	i = db->index;
-
-	if (db->order == 0 && test_bit(i ^ 1, db->u.pgdir->order0)) {
-		clear_bit(i ^ 1, db->u.pgdir->order0);
-		++o;
-	}
-
-	i >>= o;
-	set_bit(i, db->u.pgdir->bits[o]);
-
-	if (bitmap_full(db->u.pgdir->order1, MLX4_IB_DB_PER_PAGE / 2)) {
-		dma_free_coherent(dev->ib_dev.dma_device, PAGE_SIZE,
-				  db->u.pgdir->db_page, db->u.pgdir->db_dma);
-		list_del(&db->u.pgdir->list);
-		kfree(db->u.pgdir);
-	}
-
-	mutex_unlock(&dev->pgdir_mutex);
-}
-
 struct mlx4_ib_user_db_page {
 	struct list_head	list;
 	struct ib_umem	       *umem;
@@ -160,7 +42,7 @@ struct mlx4_ib_user_db_page {
 };
 
 int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, unsigned long virt,
-			struct mlx4_ib_db *db)
+			struct mlx4_db *db)
 {
 	struct mlx4_ib_user_db_page *page;
 	struct ib_umem_chunk *chunk;
@@ -181,7 +63,7 @@ int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, unsigned long virt,
 	page->user_virt = (virt & PAGE_MASK);
 	page->refcnt    = 0;
 	page->umem      = ib_umem_get(&context->ibucontext, virt & PAGE_MASK,
-				      PAGE_SIZE, 0);
+				      PAGE_SIZE, 0, 0);
 	if (IS_ERR(page->umem)) {
 		err = PTR_ERR(page->umem);
 		kfree(page);
@@ -202,7 +84,7 @@ int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, unsigned long virt,
 	return err;
 }
 
-void mlx4_ib_db_unmap_user(struct mlx4_ib_ucontext *context, struct mlx4_ib_db *db)
+void mlx4_ib_db_unmap_user(struct mlx4_ib_ucontext *context, struct mlx4_db *db)
 {
 	mutex_lock(&context->db_page_mutex);
 
diff --git a/trunk/drivers/infiniband/hw/mlx4/main.c b/trunk/drivers/infiniband/hw/mlx4/main.c
index 4d9b5ac42202..4d61e32866c6 100644
--- a/trunk/drivers/infiniband/hw/mlx4/main.c
+++ b/trunk/drivers/infiniband/hw/mlx4/main.c
@@ -557,9 +557,6 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		goto err_uar;
 	MLX4_INIT_DOORBELL_LOCK(&ibdev->uar_lock);
 
-	INIT_LIST_HEAD(&ibdev->pgdir_list);
-	mutex_init(&ibdev->pgdir_mutex);
-
 	ibdev->dev = dev;
 
 	strlcpy(ibdev->ib_dev.name, "mlx4_%d", IB_DEVICE_NAME_MAX);
diff --git a/trunk/drivers/infiniband/hw/mlx4/mlx4_ib.h b/trunk/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 9e637323c155..5cf994794d25 100644
--- a/trunk/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/trunk/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -43,24 +43,6 @@
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
 
-enum {
-	MLX4_IB_DB_PER_PAGE	= PAGE_SIZE / 4
-};
-
-struct mlx4_ib_db_pgdir;
-struct mlx4_ib_user_db_page;
-
-struct mlx4_ib_db {
-	__be32		       *db;
-	union {
-		struct mlx4_ib_db_pgdir	       *pgdir;
-		struct mlx4_ib_user_db_page    *user_page;
-	}			u;
-	dma_addr_t		dma;
-	int			index;
-	int			order;
-};
-
 struct mlx4_ib_ucontext {
 	struct ib_ucontext	ibucontext;
 	struct mlx4_uar		uar;
@@ -88,7 +70,7 @@ struct mlx4_ib_cq {
 	struct mlx4_cq		mcq;
 	struct mlx4_ib_cq_buf	buf;
 	struct mlx4_ib_cq_resize *resize_buf;
-	struct mlx4_ib_db	db;
+	struct mlx4_db		db;
 	spinlock_t		lock;
 	struct mutex		resize_mutex;
 	struct ib_umem	       *umem;
@@ -127,7 +109,7 @@ struct mlx4_ib_qp {
 	struct mlx4_qp		mqp;
 	struct mlx4_buf		buf;
 
-	struct mlx4_ib_db	db;
+	struct mlx4_db		db;
 	struct mlx4_ib_wq	rq;
 
 	u32			doorbell_qpn;
@@ -154,7 +136,7 @@ struct mlx4_ib_srq {
 	struct ib_srq		ibsrq;
 	struct mlx4_srq		msrq;
 	struct mlx4_buf		buf;
-	struct mlx4_ib_db	db;
+	struct mlx4_db		db;
 	u64		       *wrid;
 	spinlock_t		lock;
 	int			head;
@@ -175,9 +157,6 @@ struct mlx4_ib_dev {
 	struct mlx4_dev	       *dev;
 	void __iomem	       *uar_map;
 
-	struct list_head	pgdir_list;
-	struct mutex		pgdir_mutex;
-
 	struct mlx4_uar		priv_uar;
 	u32			priv_pdn;
 	MLX4_DECLARE_DOORBELL_LOCK(uar_lock);
@@ -248,11 +227,9 @@ static inline struct mlx4_ib_ah *to_mah(struct ib_ah *ibah)
 	return container_of(ibah, struct mlx4_ib_ah, ibah);
 }
 
-int mlx4_ib_db_alloc(struct mlx4_ib_dev *dev, struct mlx4_ib_db *db, int order);
-void mlx4_ib_db_free(struct mlx4_ib_dev *dev, struct mlx4_ib_db *db);
 int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, unsigned long virt,
-			struct mlx4_ib_db *db);
-void mlx4_ib_db_unmap_user(struct mlx4_ib_ucontext *context, struct mlx4_ib_db *db);
+			struct mlx4_db *db);
+void mlx4_ib_db_unmap_user(struct mlx4_ib_ucontext *context, struct mlx4_db *db);
 
 struct ib_mr *mlx4_ib_get_dma_mr(struct ib_pd *pd, int acc);
 int mlx4_ib_umem_write_mtt(struct mlx4_ib_dev *dev, struct mlx4_mtt *mtt,
diff --git a/trunk/drivers/infiniband/hw/mlx4/mr.c b/trunk/drivers/infiniband/hw/mlx4/mr.c
index fe2c2e94a5f8..68e92485fc76 100644
--- a/trunk/drivers/infiniband/hw/mlx4/mr.c
+++ b/trunk/drivers/infiniband/hw/mlx4/mr.c
@@ -132,7 +132,8 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	if (!mr)
 		return ERR_PTR(-ENOMEM);
 
-	mr->umem = ib_umem_get(pd->uobject->context, start, length, access_flags);
+	mr->umem = ib_umem_get(pd->uobject->context, start, length,
+			       access_flags, 0);
 	if (IS_ERR(mr->umem)) {
 		err = PTR_ERR(mr->umem);
 		goto err_free;
diff --git a/trunk/drivers/infiniband/hw/mlx4/qp.c b/trunk/drivers/infiniband/hw/mlx4/qp.c
index b75efae7e449..8e02ecfec188 100644
--- a/trunk/drivers/infiniband/hw/mlx4/qp.c
+++ b/trunk/drivers/infiniband/hw/mlx4/qp.c
@@ -482,7 +482,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 			goto err;
 
 		qp->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr,
-				       qp->buf_size, 0);
+				       qp->buf_size, 0, 0);
 		if (IS_ERR(qp->umem)) {
 			err = PTR_ERR(qp->umem);
 			goto err;
@@ -514,7 +514,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 			goto err;
 
 		if (!init_attr->srq) {
-			err = mlx4_ib_db_alloc(dev, &qp->db, 0);
+			err = mlx4_db_alloc(dev->dev, &qp->db, 0);
 			if (err)
 				goto err;
 
@@ -580,7 +580,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 
 err_db:
 	if (!pd->uobject && !init_attr->srq)
-		mlx4_ib_db_free(dev, &qp->db);
+		mlx4_db_free(dev->dev, &qp->db);
 
 err:
 	return err;
@@ -666,7 +666,7 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 		kfree(qp->rq.wrid);
 		mlx4_buf_free(dev->dev, qp->buf_size, &qp->buf);
 		if (!qp->ibqp.srq)
-			mlx4_ib_db_free(dev, &qp->db);
+			mlx4_db_free(dev->dev, &qp->db);
 	}
 }
 
diff --git a/trunk/drivers/infiniband/hw/mlx4/srq.c b/trunk/drivers/infiniband/hw/mlx4/srq.c
index beaa3b06cf58..12d6bc6f8007 100644
--- a/trunk/drivers/infiniband/hw/mlx4/srq.c
+++ b/trunk/drivers/infiniband/hw/mlx4/srq.c
@@ -109,7 +109,7 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
 		}
 
 		srq->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr,
-					buf_size, 0);
+					buf_size, 0, 0);
 		if (IS_ERR(srq->umem)) {
 			err = PTR_ERR(srq->umem);
 			goto err_srq;
@@ -129,7 +129,7 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
 		if (err)
 			goto err_mtt;
 	} else {
-		err = mlx4_ib_db_alloc(dev, &srq->db, 0);
+		err = mlx4_db_alloc(dev->dev, &srq->db, 0);
 		if (err)
 			goto err_srq;
 
@@ -200,7 +200,7 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
 
 err_db:
 	if (!pd->uobject)
-		mlx4_ib_db_free(dev, &srq->db);
+		mlx4_db_free(dev->dev, &srq->db);
 
 err_srq:
 	kfree(srq);
@@ -267,7 +267,7 @@ int mlx4_ib_destroy_srq(struct ib_srq *srq)
 		kfree(msrq->wrid);
 		mlx4_buf_free(dev->dev, msrq->msrq.max << msrq->msrq.wqe_shift,
 			      &msrq->buf);
-		mlx4_ib_db_free(dev, &msrq->db);
+		mlx4_db_free(dev->dev, &msrq->db);
 	}
 
 	kfree(msrq);
diff --git a/trunk/drivers/infiniband/hw/mthca/mthca_provider.c b/trunk/drivers/infiniband/hw/mthca/mthca_provider.c
index 696e1f302332..2a9f460cf061 100644
--- a/trunk/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/trunk/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -1006,17 +1006,23 @@ static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	struct mthca_dev *dev = to_mdev(pd->device);
 	struct ib_umem_chunk *chunk;
 	struct mthca_mr *mr;
+	struct mthca_reg_mr ucmd;
 	u64 *pages;
 	int shift, n, len;
 	int i, j, k;
 	int err = 0;
 	int write_mtt_size;
 
+	if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd))
+		return ERR_PTR(-EFAULT);
+
 	mr = kmalloc(sizeof *mr, GFP_KERNEL);
 	if (!mr)
 		return ERR_PTR(-ENOMEM);
 
-	mr->umem = ib_umem_get(pd->uobject->context, start, length, acc);
+	mr->umem = ib_umem_get(pd->uobject->context, start, length, acc,
+			       ucmd.mr_attrs & MTHCA_MR_DMASYNC);
+
 	if (IS_ERR(mr->umem)) {
 		err = PTR_ERR(mr->umem);
 		goto err;
diff --git a/trunk/drivers/infiniband/hw/mthca/mthca_user.h b/trunk/drivers/infiniband/hw/mthca/mthca_user.h
index 02cc0a766f3a..f8cb3b664d37 100644
--- a/trunk/drivers/infiniband/hw/mthca/mthca_user.h
+++ b/trunk/drivers/infiniband/hw/mthca/mthca_user.h
@@ -41,7 +41,7 @@
  * Increment this value if any changes that break userspace ABI
  * compatibility are made.
  */
-#define MTHCA_UVERBS_ABI_VERSION	1
+#define MTHCA_UVERBS_ABI_VERSION	2
 
 /*
  * Make sure that all structs defined in this file remain laid out so
@@ -61,6 +61,14 @@ struct mthca_alloc_pd_resp {
 	__u32 reserved;
 };
 
+struct mthca_reg_mr {
+	__u32 mr_attrs;
+#define MTHCA_MR_DMASYNC 0x1
+/* mark the memory region with a DMA attribute that causes
+ * in-flight DMA to be flushed when the region is written to */
+	__u32 reserved;
+};
+
 struct mthca_create_cq {
 	__u32 lkey;
 	__u32 pdn;
diff --git a/trunk/drivers/infiniband/hw/nes/nes.c b/trunk/drivers/infiniband/hw/nes/nes.c
index b046262ed638..a4e9269a29bd 100644
--- a/trunk/drivers/infiniband/hw/nes/nes.c
+++ b/trunk/drivers/infiniband/hw/nes/nes.c
@@ -139,8 +139,9 @@ static int nes_inetaddr_event(struct notifier_block *notifier,
 
 	addr = ntohl(ifa->ifa_address);
 	mask = ntohl(ifa->ifa_mask);
-	nes_debug(NES_DBG_NETDEV, "nes_inetaddr_event: ip address %08X, netmask %08X.\n",
-			addr, mask);
+	nes_debug(NES_DBG_NETDEV, "nes_inetaddr_event: ip address " NIPQUAD_FMT
+		  ", netmask " NIPQUAD_FMT ".\n",
+		  HIPQUAD(addr), HIPQUAD(mask));
 	list_for_each_entry(nesdev, &nes_dev_list, list) {
 		nes_debug(NES_DBG_NETDEV, "Nesdev list entry = 0x%p. (%s)\n",
 				nesdev, nesdev->netdev[0]->name);
@@ -353,13 +354,11 @@ struct ib_qp *nes_get_qp(struct ib_device *device, int qpn)
  */
 static void nes_print_macaddr(struct net_device *netdev)
 {
-	nes_debug(NES_DBG_INIT, "%s: MAC %02X:%02X:%02X:%02X:%02X:%02X, IRQ %u\n",
-			netdev->name,
-			netdev->dev_addr[0], netdev->dev_addr[1], netdev->dev_addr[2],
-			netdev->dev_addr[3], netdev->dev_addr[4], netdev->dev_addr[5],
-			netdev->irq);
-}
+	DECLARE_MAC_BUF(mac);
 
+	nes_debug(NES_DBG_INIT, "%s: %s, IRQ %u\n",
+		  netdev->name, print_mac(mac, netdev->dev_addr), netdev->irq);
+}
 
 /**
  * nes_interrupt - handle interrupts
diff --git a/trunk/drivers/infiniband/hw/nes/nes_cm.c b/trunk/drivers/infiniband/hw/nes/nes_cm.c
index d0738623bcf3..d940fc27129a 100644
--- a/trunk/drivers/infiniband/hw/nes/nes_cm.c
+++ b/trunk/drivers/infiniband/hw/nes/nes_cm.c
@@ -852,8 +852,8 @@ static struct nes_cm_node *find_node(struct nes_cm_core *cm_core,
 	/* get a handle on the hte */
 	hte = &cm_core->connected_nodes;
 
-	nes_debug(NES_DBG_CM, "Searching for an owner node:%x:%x from core %p->%p\n",
-			loc_addr, loc_port, cm_core, hte);
+	nes_debug(NES_DBG_CM, "Searching for an owner node: " NIPQUAD_FMT ":%x from core %p->%p\n",
+		  HIPQUAD(loc_addr), loc_port, cm_core, hte);
 
 	/* walk list and find cm_node associated with this session ID */
 	spin_lock_irqsave(&cm_core->ht_lock, flags);
@@ -902,8 +902,8 @@ static struct nes_cm_listener *find_listener(struct nes_cm_core *cm_core,
 	}
 	spin_unlock_irqrestore(&cm_core->listen_list_lock, flags);
 
-	nes_debug(NES_DBG_CM, "Unable to find listener- %x:%x\n",
-			dst_addr, dst_port);
+	nes_debug(NES_DBG_CM, "Unable to find listener for " NIPQUAD_FMT ":%x\n",
+		  HIPQUAD(dst_addr), dst_port);
 
 	/* no listener */
 	return NULL;
@@ -1054,6 +1054,7 @@ static struct nes_cm_node *make_cm_node(struct nes_cm_core *cm_core,
 	int arpindex = 0;
 	struct nes_device *nesdev;
 	struct nes_adapter *nesadapter;
+	DECLARE_MAC_BUF(mac);
 
 	/* create an hte and cm_node for this instance */
 	cm_node = kzalloc(sizeof(*cm_node), GFP_ATOMIC);
@@ -1066,8 +1067,9 @@ static struct nes_cm_node *make_cm_node(struct nes_cm_core *cm_core,
 	cm_node->loc_port = cm_info->loc_port;
 	cm_node->rem_port = cm_info->rem_port;
 	cm_node->send_write0 = send_first;
-	nes_debug(NES_DBG_CM, "Make node addresses : loc = %x:%x, rem = %x:%x\n",
-			cm_node->loc_addr, cm_node->loc_port, cm_node->rem_addr, cm_node->rem_port);
+	nes_debug(NES_DBG_CM, "Make node addresses : loc = " NIPQUAD_FMT ":%x, rem = " NIPQUAD_FMT ":%x\n",
+		  HIPQUAD(cm_node->loc_addr), cm_node->loc_port,
+		  HIPQUAD(cm_node->rem_addr), cm_node->rem_port);
 	cm_node->listener = listener;
 	cm_node->netdev = nesvnic->netdev;
 	cm_node->cm_id = cm_info->cm_id;
@@ -1116,11 +1118,8 @@ static struct nes_cm_node *make_cm_node(struct nes_cm_core *cm_core,
 
 	/* copy the mac addr to node context */
 	memcpy(cm_node->rem_mac, nesadapter->arp_table[arpindex].mac_addr, ETH_ALEN);
-	nes_debug(NES_DBG_CM, "Remote mac addr from arp table:%02x,"
-			" %02x, %02x, %02x, %02x, %02x\n",
-			cm_node->rem_mac[0], cm_node->rem_mac[1],
-			cm_node->rem_mac[2], cm_node->rem_mac[3],
-			cm_node->rem_mac[4], cm_node->rem_mac[5]);
+	nes_debug(NES_DBG_CM, "Remote mac addr from arp table: %s\n",
+		  print_mac(mac, cm_node->rem_mac));
 
 	add_hte_node(cm_core, cm_node);
 	atomic_inc(&cm_nodes_created);
@@ -1850,8 +1849,10 @@ static int mini_cm_recv_pkt(struct nes_cm_core *cm_core, struct nes_vnic *nesvni
 	nfo.rem_addr = ntohl(iph->saddr);
 	nfo.rem_port = ntohs(tcph->source);
 
-	nes_debug(NES_DBG_CM, "Received packet: dest=0x%08X:0x%04X src=0x%08X:0x%04X\n",
-			iph->daddr, tcph->dest, iph->saddr, tcph->source);
+	nes_debug(NES_DBG_CM, "Received packet: dest=" NIPQUAD_FMT
+		  ":0x%04X src=" NIPQUAD_FMT ":0x%04X\n",
+		  NIPQUAD(iph->daddr), tcph->dest,
+		  NIPQUAD(iph->saddr), tcph->source);
 
 	/* note: this call is going to increment cm_node ref count */
 	cm_node = find_node(cm_core,
diff --git a/trunk/drivers/infiniband/hw/nes/nes_hw.c b/trunk/drivers/infiniband/hw/nes/nes_hw.c
index aa53aab91bf8..08964cc7e98a 100644
--- a/trunk/drivers/infiniband/hw/nes/nes_hw.c
+++ b/trunk/drivers/infiniband/hw/nes/nes_hw.c
@@ -636,6 +636,15 @@ static unsigned int nes_reset_adapter_ne020(struct nes_device *nesdev, u8 *OneG_
 			nes_debug(NES_DBG_INIT, "Did not see full soft reset done.\n");
 			return 0;
 		}
+
+		i = 0;
+		while ((nes_read_indexed(nesdev, NES_IDX_INT_CPU_STATUS) != 0x80) && i++ < 10000)
+			mdelay(1);
+		if (i >= 10000) {
+			printk(KERN_ERR PFX "Internal CPU not ready, status = %02X\n",
+			       nes_read_indexed(nesdev, NES_IDX_INT_CPU_STATUS));
+			return 0;
+		}
 	}
 
 	/* port reset */
@@ -684,17 +693,6 @@ static unsigned int nes_reset_adapter_ne020(struct nes_device *nesdev, u8 *OneG_
 		}
 	}
 
-
-
-	i = 0;
-	while ((nes_read_indexed(nesdev, NES_IDX_INT_CPU_STATUS) != 0x80) && i++ < 10000)
-		mdelay(1);
-	if (i >= 10000) {
-		printk(KERN_ERR PFX "Internal CPU not ready, status = %02X\n",
-				nes_read_indexed(nesdev, NES_IDX_INT_CPU_STATUS));
-		return 0;
-	}
-
 	return port_count;
 }
 
diff --git a/trunk/drivers/infiniband/hw/nes/nes_hw.h b/trunk/drivers/infiniband/hw/nes/nes_hw.h
index b7e2844f096b..8f36e231bdf5 100644
--- a/trunk/drivers/infiniband/hw/nes/nes_hw.h
+++ b/trunk/drivers/infiniband/hw/nes/nes_hw.h
@@ -905,7 +905,7 @@ struct nes_hw_qp {
 };
 
 struct nes_hw_cq {
-	struct nes_hw_cqe volatile *cq_vbase;	/* PCI memory for host rings */
+	struct nes_hw_cqe *cq_vbase;	/* PCI memory for host rings */
 	void (*ce_handler)(struct nes_device *nesdev, struct nes_hw_cq *cq);
 	dma_addr_t cq_pbase;	/* PCI memory for host rings */
 	u16 cq_head;
diff --git a/trunk/drivers/infiniband/hw/nes/nes_nic.c b/trunk/drivers/infiniband/hw/nes/nes_nic.c
index 01cd0effc492..e5366b013c1a 100644
--- a/trunk/drivers/infiniband/hw/nes/nes_nic.c
+++ b/trunk/drivers/infiniband/hw/nes/nes_nic.c
@@ -787,16 +787,14 @@ static int nes_netdev_set_mac_address(struct net_device *netdev, void *p)
 	int i;
 	u32 macaddr_low;
 	u16 macaddr_high;
+	DECLARE_MAC_BUF(mac);
 
 	if (!is_valid_ether_addr(mac_addr->sa_data))
 		return -EADDRNOTAVAIL;
 
 	memcpy(netdev->dev_addr, mac_addr->sa_data, netdev->addr_len);
-	printk(PFX "%s: Address length = %d, Address = %02X%02X%02X%02X%02X%02X..\n",
-		   __func__, netdev->addr_len,
-		   mac_addr->sa_data[0], mac_addr->sa_data[1],
-		   mac_addr->sa_data[2], mac_addr->sa_data[3],
-		   mac_addr->sa_data[4], mac_addr->sa_data[5]);
+	printk(PFX "%s: Address length = %d, Address = %s\n",
+	       __func__, netdev->addr_len, print_mac(mac, mac_addr->sa_data));
 	macaddr_high = ((u16)netdev->dev_addr[0]) << 8;
 	macaddr_high += (u16)netdev->dev_addr[1];
 	macaddr_low = ((u32)netdev->dev_addr[2]) << 24;
@@ -878,11 +876,11 @@ static void nes_netdev_set_multicast_list(struct net_device *netdev)
 			if (mc_nic_index < 0)
 				mc_nic_index = nesvnic->nic_index;
 			if (multicast_addr) {
-				nes_debug(NES_DBG_NIC_RX, "Assigning MC Address = %02X%02X%02X%02X%02X%02X to register 0x%04X nic_idx=%d\n",
-						  multicast_addr->dmi_addr[0], multicast_addr->dmi_addr[1],
-						  multicast_addr->dmi_addr[2], multicast_addr->dmi_addr[3],
-						  multicast_addr->dmi_addr[4], multicast_addr->dmi_addr[5],
-						  perfect_filter_register_address+(mc_index * 8), mc_nic_index);
+				DECLARE_MAC_BUF(mac);
+				nes_debug(NES_DBG_NIC_RX, "Assigning MC Address %s to register 0x%04X nic_idx=%d\n",
+					  print_mac(mac, multicast_addr->dmi_addr),
+					  perfect_filter_register_address+(mc_index * 8),
+					  mc_nic_index);
 				macaddr_high = ((u16)multicast_addr->dmi_addr[0]) << 8;
 				macaddr_high += (u16)multicast_addr->dmi_addr[1];
 				macaddr_low = ((u32)multicast_addr->dmi_addr[2]) << 24;
diff --git a/trunk/drivers/infiniband/hw/nes/nes_utils.c b/trunk/drivers/infiniband/hw/nes/nes_utils.c
index f9db07c2717d..c6d5631a6995 100644
--- a/trunk/drivers/infiniband/hw/nes/nes_utils.c
+++ b/trunk/drivers/infiniband/hw/nes/nes_utils.c
@@ -660,7 +660,9 @@ int nes_arp_table(struct nes_device *nesdev, u32 ip_addr, u8 *mac_addr, u32 acti
 
 	/* DELETE or RESOLVE */
 	if (arp_index == nesadapter->arp_table_size) {
-		nes_debug(NES_DBG_NETDEV, "mac address not in ARP table - cannot delete or resolve\n");
+		nes_debug(NES_DBG_NETDEV, "MAC for " NIPQUAD_FMT " not in ARP table - cannot %s\n",
+			  HIPQUAD(ip_addr),
+			  action == NES_ARP_RESOLVE ? "resolve" : "delete");
 		return -1;
 	}
 
diff --git a/trunk/drivers/infiniband/hw/nes/nes_verbs.c b/trunk/drivers/infiniband/hw/nes/nes_verbs.c
index f9a5d4390892..9ae397a0ff7e 100644
--- a/trunk/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/trunk/drivers/infiniband/hw/nes/nes_verbs.c
@@ -1976,7 +1976,7 @@ static int nes_destroy_cq(struct ib_cq *ib_cq)
 
 	if (nescq->cq_mem_size)
 		pci_free_consistent(nesdev->pcidev, nescq->cq_mem_size,
-				(void *)nescq->hw_cq.cq_vbase, nescq->hw_cq.cq_pbase);
+				    nescq->hw_cq.cq_vbase, nescq->hw_cq.cq_pbase);
 	kfree(nescq);
 
 	return ret;
@@ -2377,7 +2377,7 @@ static struct ib_mr *nes_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	u8 single_page = 1;
 	u8 stag_key;
 
-	region = ib_umem_get(pd->uobject->context, start, length, acc);
+	region = ib_umem_get(pd->uobject->context, start, length, acc, 0);
 	if (IS_ERR(region)) {
 		return (struct ib_mr *)region;
 	}
@@ -3610,6 +3610,12 @@ static int nes_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry)
 	while (cqe_count < num_entries) {
 		if (le32_to_cpu(nescq->hw_cq.cq_vbase[head].cqe_words[NES_CQE_OPCODE_IDX]) &
 				NES_CQE_VALID) {
+			/*
+			 * Make sure we read CQ entry contents *after*
+			 * we've checked the valid bit.
+			 */
+			rmb();
+
 			cqe = nescq->hw_cq.cq_vbase[head];
 			nescq->hw_cq.cq_vbase[head].cqe_words[NES_CQE_OPCODE_IDX] = 0;
 			u32temp = le32_to_cpu(cqe.cqe_words[NES_CQE_COMP_COMP_CTX_LOW_IDX]);
diff --git a/trunk/drivers/infiniband/ulp/ipoib/ipoib.h b/trunk/drivers/infiniband/ulp/ipoib/ipoib.h
index 73b2b176ad0e..f1f142dc64b1 100644
--- a/trunk/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/trunk/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -56,11 +56,11 @@
 /* constants */
 
 enum {
-	IPOIB_PACKET_SIZE	  = 2048,
-	IPOIB_BUF_SIZE		  = IPOIB_PACKET_SIZE + IB_GRH_BYTES,
-
 	IPOIB_ENCAP_LEN		  = 4,
 
+	IPOIB_UD_HEAD_SIZE	  = IB_GRH_BYTES + IPOIB_ENCAP_LEN,
+	IPOIB_UD_RX_SG		  = 2, /* max buffer needed for 4K mtu */
+
 	IPOIB_CM_MTU		  = 0x10000 - 0x10, /* padding to align header to 16 */
 	IPOIB_CM_BUF_SIZE	  = IPOIB_CM_MTU  + IPOIB_ENCAP_LEN,
 	IPOIB_CM_HEAD_SIZE	  = IPOIB_CM_BUF_SIZE % PAGE_SIZE,
@@ -139,7 +139,7 @@ struct ipoib_mcast {
 
 struct ipoib_rx_buf {
 	struct sk_buff *skb;
-	u64		mapping;
+	u64		mapping[IPOIB_UD_RX_SG];
 };
 
 struct ipoib_tx_buf {
@@ -294,6 +294,7 @@ struct ipoib_dev_priv {
 
 	unsigned int admin_mtu;
 	unsigned int mcast_mtu;
+	unsigned int max_ib_mtu;
 
 	struct ipoib_rx_buf *rx_ring;
 
@@ -305,6 +306,9 @@ struct ipoib_dev_priv {
 	struct ib_send_wr    tx_wr;
 	unsigned	     tx_outstanding;
 
+	struct ib_recv_wr    rx_wr;
+	struct ib_sge	     rx_sge[IPOIB_UD_RX_SG];
+
 	struct ib_wc ibwc[IPOIB_NUM_WC];
 
 	struct list_head dead_ahs;
@@ -366,6 +370,14 @@ struct ipoib_neigh {
 	struct list_head    list;
 };
 
+#define IPOIB_UD_MTU(ib_mtu)		(ib_mtu - IPOIB_ENCAP_LEN)
+#define IPOIB_UD_BUF_SIZE(ib_mtu)	(ib_mtu + IB_GRH_BYTES)
+
+static inline int ipoib_ud_need_sg(unsigned int ib_mtu)
+{
+	return IPOIB_UD_BUF_SIZE(ib_mtu) > PAGE_SIZE;
+}
+
 /*
  * We stash a pointer to our private neighbour information after our
  * hardware address in neigh->ha.  The ALIGN() expression here makes
diff --git a/trunk/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/trunk/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 0205eb7c1bd3..7cf1fa7074ab 100644
--- a/trunk/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/trunk/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -89,28 +89,59 @@ void ipoib_free_ah(struct kref *kref)
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
+static void ipoib_ud_dma_unmap_rx(struct ipoib_dev_priv *priv,
+				  u64 mapping[IPOIB_UD_RX_SG])
+{
+	if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
+		ib_dma_unmap_single(priv->ca, mapping[0], IPOIB_UD_HEAD_SIZE,
+				    DMA_FROM_DEVICE);
+		ib_dma_unmap_page(priv->ca, mapping[1], PAGE_SIZE,
+				  DMA_FROM_DEVICE);
+	} else
+		ib_dma_unmap_single(priv->ca, mapping[0],
+				    IPOIB_UD_BUF_SIZE(priv->max_ib_mtu),
+				    DMA_FROM_DEVICE);
+}
+
+static void ipoib_ud_skb_put_frags(struct ipoib_dev_priv *priv,
+				   struct sk_buff *skb,
+				   unsigned int length)
+{
+	if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
+		unsigned int size;
+		/*
+		 * There is only two buffers needed for max_payload = 4K,
+		 * first buf size is IPOIB_UD_HEAD_SIZE
+		 */
+		skb->tail += IPOIB_UD_HEAD_SIZE;
+		skb->len  += length;
+
+		size = length - IPOIB_UD_HEAD_SIZE;
+
+		frag->size     = size;
+		skb->data_len += size;
+		skb->truesize += size;
+	} else
+		skb_put(skb, length);
+
+}
+
 static int ipoib_ib_post_receive(struct net_device *dev, int id)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
-	struct ib_sge list;
-	struct ib_recv_wr param;
 	struct ib_recv_wr *bad_wr;
 	int ret;
 
-	list.addr     = priv->rx_ring[id].mapping;
-	list.length   = IPOIB_BUF_SIZE;
-	list.lkey     = priv->mr->lkey;
+	priv->rx_wr.wr_id   = id | IPOIB_OP_RECV;
+	priv->rx_sge[0].addr = priv->rx_ring[id].mapping[0];
+	priv->rx_sge[1].addr = priv->rx_ring[id].mapping[1];
 
-	param.next    = NULL;
-	param.wr_id   = id | IPOIB_OP_RECV;
-	param.sg_list = &list;
-	param.num_sge = 1;
 
-	ret = ib_post_recv(priv->qp, &param, &bad_wr);
+	ret = ib_post_recv(priv->qp, &priv->rx_wr, &bad_wr);
 	if (unlikely(ret)) {
 		ipoib_warn(priv, "receive failed for buf %d (%d)\n", id, ret);
-		ib_dma_unmap_single(priv->ca, priv->rx_ring[id].mapping,
-				    IPOIB_BUF_SIZE, DMA_FROM_DEVICE);
+		ipoib_ud_dma_unmap_rx(priv, priv->rx_ring[id].mapping);
 		dev_kfree_skb_any(priv->rx_ring[id].skb);
 		priv->rx_ring[id].skb = NULL;
 	}
@@ -118,15 +149,21 @@ static int ipoib_ib_post_receive(struct net_device *dev, int id)
 	return ret;
 }
 
-static int ipoib_alloc_rx_skb(struct net_device *dev, int id)
+static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct sk_buff *skb;
-	u64 addr;
+	int buf_size;
+	u64 *mapping;
 
-	skb = dev_alloc_skb(IPOIB_BUF_SIZE + 4);
-	if (!skb)
-		return -ENOMEM;
+	if (ipoib_ud_need_sg(priv->max_ib_mtu))
+		buf_size = IPOIB_UD_HEAD_SIZE;
+	else
+		buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
+
+	skb = dev_alloc_skb(buf_size + 4);
+	if (unlikely(!skb))
+		return NULL;
 
 	/*
 	 * IB will leave a 40 byte gap for a GRH and IPoIB adds a 4 byte
@@ -135,17 +172,32 @@ static int ipoib_alloc_rx_skb(struct net_device *dev, int id)
 	 */
 	skb_reserve(skb, 4);
 
-	addr = ib_dma_map_single(priv->ca, skb->data, IPOIB_BUF_SIZE,
-				 DMA_FROM_DEVICE);
-	if (unlikely(ib_dma_mapping_error(priv->ca, addr))) {
-		dev_kfree_skb_any(skb);
-		return -EIO;
+	mapping = priv->rx_ring[id].mapping;
+	mapping[0] = ib_dma_map_single(priv->ca, skb->data, buf_size,
+				       DMA_FROM_DEVICE);
+	if (unlikely(ib_dma_mapping_error(priv->ca, mapping[0])))
+		goto error;
+
+	if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
+		struct page *page = alloc_page(GFP_ATOMIC);
+		if (!page)
+			goto partial_error;
+		skb_fill_page_desc(skb, 0, page, 0, PAGE_SIZE);
+		mapping[1] =
+			ib_dma_map_page(priv->ca, skb_shinfo(skb)->frags[0].page,
+					0, PAGE_SIZE, DMA_FROM_DEVICE);
+		if (unlikely(ib_dma_mapping_error(priv->ca, mapping[1])))
+			goto partial_error;
 	}
 
-	priv->rx_ring[id].skb     = skb;
-	priv->rx_ring[id].mapping = addr;
+	priv->rx_ring[id].skb = skb;
+	return skb;
 
-	return 0;
+partial_error:
+	ib_dma_unmap_single(priv->ca, mapping[0], buf_size, DMA_FROM_DEVICE);
+error:
+	dev_kfree_skb_any(skb);
+	return NULL;
 }
 
 static int ipoib_ib_post_receives(struct net_device *dev)
@@ -154,7 +206,7 @@ static int ipoib_ib_post_receives(struct net_device *dev)
 	int i;
 
 	for (i = 0; i < ipoib_recvq_size; ++i) {
-		if (ipoib_alloc_rx_skb(dev, i)) {
+		if (!ipoib_alloc_rx_skb(dev, i)) {
 			ipoib_warn(priv, "failed to allocate receive buffer %d\n", i);
 			return -ENOMEM;
 		}
@@ -172,7 +224,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	unsigned int wr_id = wc->wr_id & ~IPOIB_OP_RECV;
 	struct sk_buff *skb;
-	u64 addr;
+	u64 mapping[IPOIB_UD_RX_SG];
 
 	ipoib_dbg_data(priv, "recv completion: id %d, status: %d\n",
 		       wr_id, wc->status);
@@ -184,15 +236,13 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	}
 
 	skb  = priv->rx_ring[wr_id].skb;
-	addr = priv->rx_ring[wr_id].mapping;
 
 	if (unlikely(wc->status != IB_WC_SUCCESS)) {
 		if (wc->status != IB_WC_WR_FLUSH_ERR)
 			ipoib_warn(priv, "failed recv event "
 				   "(status=%d, wrid=%d vend_err %x)\n",
 				   wc->status, wr_id, wc->vendor_err);
-		ib_dma_unmap_single(priv->ca, addr,
-				    IPOIB_BUF_SIZE, DMA_FROM_DEVICE);
+		ipoib_ud_dma_unmap_rx(priv, priv->rx_ring[wr_id].mapping);
 		dev_kfree_skb_any(skb);
 		priv->rx_ring[wr_id].skb = NULL;
 		return;
@@ -205,11 +255,14 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	if (wc->slid == priv->local_lid && wc->src_qp == priv->qp->qp_num)
 		goto repost;
 
+	memcpy(mapping, priv->rx_ring[wr_id].mapping,
+	       IPOIB_UD_RX_SG * sizeof *mapping);
+
 	/*
 	 * If we can't allocate a new RX buffer, dump
 	 * this packet and reuse the old buffer.
 	 */
-	if (unlikely(ipoib_alloc_rx_skb(dev, wr_id))) {
+	if (unlikely(!ipoib_alloc_rx_skb(dev, wr_id))) {
 		++dev->stats.rx_dropped;
 		goto repost;
 	}
@@ -217,9 +270,9 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	ipoib_dbg_data(priv, "received %d bytes, SLID 0x%04x\n",
 		       wc->byte_len, wc->slid);
 
-	ib_dma_unmap_single(priv->ca, addr, IPOIB_BUF_SIZE, DMA_FROM_DEVICE);
+	ipoib_ud_dma_unmap_rx(priv, mapping);
+	ipoib_ud_skb_put_frags(priv, skb, wc->byte_len);
 
-	skb_put(skb, wc->byte_len);
 	skb_pull(skb, IB_GRH_BYTES);
 
 	skb->protocol = ((struct ipoib_header *) skb->data)->proto;
@@ -733,10 +786,8 @@ int ipoib_ib_dev_stop(struct net_device *dev, int flush)
 				rx_req = &priv->rx_ring[i];
 				if (!rx_req->skb)
 					continue;
-				ib_dma_unmap_single(priv->ca,
-						    rx_req->mapping,
-						    IPOIB_BUF_SIZE,
-						    DMA_FROM_DEVICE);
+				ipoib_ud_dma_unmap_rx(priv,
+						      priv->rx_ring[i].mapping);
 				dev_kfree_skb_any(rx_req->skb);
 				rx_req->skb = NULL;
 			}
diff --git a/trunk/drivers/infiniband/ulp/ipoib/ipoib_main.c b/trunk/drivers/infiniband/ulp/ipoib/ipoib_main.c
index bd07f02cf02b..7a4ed9d3d844 100644
--- a/trunk/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/trunk/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -195,7 +195,7 @@ static int ipoib_change_mtu(struct net_device *dev, int new_mtu)
 		return 0;
 	}
 
-	if (new_mtu > IPOIB_PACKET_SIZE - IPOIB_ENCAP_LEN)
+	if (new_mtu > IPOIB_UD_MTU(priv->max_ib_mtu))
 		return -EINVAL;
 
 	priv->admin_mtu = new_mtu;
@@ -971,10 +971,6 @@ static void ipoib_setup(struct net_device *dev)
 				    NETIF_F_LLTX		|
 				    NETIF_F_HIGHDMA);
 
-	/* MTU will be reset when mcast join happens */
-	dev->mtu		 = IPOIB_PACKET_SIZE - IPOIB_ENCAP_LEN;
-	priv->mcast_mtu		 = priv->admin_mtu = dev->mtu;
-
 	memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN);
 
 	netif_carrier_off(dev);
@@ -1107,6 +1103,7 @@ static struct net_device *ipoib_add_port(const char *format,
 {
 	struct ipoib_dev_priv *priv;
 	struct ib_device_attr *device_attr;
+	struct ib_port_attr attr;
 	int result = -ENOMEM;
 
 	priv = ipoib_intf_alloc(format);
@@ -1115,6 +1112,18 @@ static struct net_device *ipoib_add_port(const char *format,
 
 	SET_NETDEV_DEV(priv->dev, hca->dma_device);
 
+	if (!ib_query_port(hca, port, &attr))
+		priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
+	else {
+		printk(KERN_WARNING "%s: ib_query_port %d failed\n",
+		       hca->name, port);
+		goto device_init_failed;
+	}
+
+	/* MTU will be reset when mcast join happens */
+	priv->dev->mtu  = IPOIB_UD_MTU(priv->max_ib_mtu);
+	priv->mcast_mtu  = priv->admin_mtu = priv->dev->mtu;
+
 	result = ib_query_pkey(hca, port, 0, &priv->pkey);
 	if (result) {
 		printk(KERN_WARNING "%s: ib_query_pkey port %d failed (ret = %d)\n",
diff --git a/trunk/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/trunk/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 31a53c5bcb13..d00a2c174aee 100644
--- a/trunk/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/trunk/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -567,8 +567,7 @@ void ipoib_mcast_join_task(struct work_struct *work)
 		return;
 	}
 
-	priv->mcast_mtu = ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu) -
-		IPOIB_ENCAP_LEN;
+	priv->mcast_mtu = IPOIB_UD_MTU(ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu));
 
 	if (!ipoib_cm_admin_enabled(dev))
 		dev->mtu = min(priv->mcast_mtu, priv->admin_mtu);
diff --git a/trunk/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/trunk/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index 8a20e3742c43..07c03f178a49 100644
--- a/trunk/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/trunk/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -150,7 +150,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 			.max_send_wr  = ipoib_sendq_size,
 			.max_recv_wr  = ipoib_recvq_size,
 			.max_send_sge = 1,
-			.max_recv_sge = 1
+			.max_recv_sge = IPOIB_UD_RX_SG
 		},
 		.sq_sig_type = IB_SIGNAL_ALL_WR,
 		.qp_type     = IB_QPT_UD
@@ -215,6 +215,19 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 	priv->tx_wr.sg_list	= priv->tx_sge;
 	priv->tx_wr.send_flags	= IB_SEND_SIGNALED;
 
+	priv->rx_sge[0].lkey = priv->mr->lkey;
+	if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
+		priv->rx_sge[0].length = IPOIB_UD_HEAD_SIZE;
+		priv->rx_sge[1].length = PAGE_SIZE;
+		priv->rx_sge[1].lkey = priv->mr->lkey;
+		priv->rx_wr.num_sge = IPOIB_UD_RX_SG;
+	} else {
+		priv->rx_sge[0].length = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
+		priv->rx_wr.num_sge = 1;
+	}
+	priv->rx_wr.next = NULL;
+	priv->rx_wr.sg_list = priv->rx_sge;
+
 	return 0;
 
 out_free_cq:
diff --git a/trunk/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/trunk/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index 293f5b892e3f..431fdeaa2dc4 100644
--- a/trunk/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/trunk/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -89,6 +89,7 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 		goto err;
 	}
 
+	priv->max_ib_mtu = ppriv->max_ib_mtu;
 	set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags);
 
 	priv->pkey = pkey;
diff --git a/trunk/drivers/input/input.c b/trunk/drivers/input/input.c
index f02c242c3114..27006fc18305 100644
--- a/trunk/drivers/input/input.c
+++ b/trunk/drivers/input/input.c
@@ -898,30 +898,26 @@ static int __init input_proc_init(void)
 {
 	struct proc_dir_entry *entry;
 
-	proc_bus_input_dir = proc_mkdir("input", proc_bus);
+	proc_bus_input_dir = proc_mkdir("bus/input", NULL);
 	if (!proc_bus_input_dir)
 		return -ENOMEM;
 
 	proc_bus_input_dir->owner = THIS_MODULE;
 
-	entry = create_proc_entry("devices", 0, proc_bus_input_dir);
+	entry = proc_create("devices", 0, proc_bus_input_dir,
+			    &input_devices_fileops);
 	if (!entry)
 		goto fail1;
 
-	entry->owner = THIS_MODULE;
-	entry->proc_fops = &input_devices_fileops;
-
-	entry = create_proc_entry("handlers", 0, proc_bus_input_dir);
+	entry = proc_create("handlers", 0, proc_bus_input_dir,
+			    &input_handlers_fileops);
 	if (!entry)
 		goto fail2;
 
-	entry->owner = THIS_MODULE;
-	entry->proc_fops = &input_handlers_fileops;
-
 	return 0;
 
  fail2:	remove_proc_entry("devices", proc_bus_input_dir);
- fail1: remove_proc_entry("input", proc_bus);
+ fail1: remove_proc_entry("bus/input", NULL);
 	return -ENOMEM;
 }
 
@@ -929,7 +925,7 @@ static void input_proc_exit(void)
 {
 	remove_proc_entry("devices", proc_bus_input_dir);
 	remove_proc_entry("handlers", proc_bus_input_dir);
-	remove_proc_entry("input", proc_bus);
+	remove_proc_entry("bus/input", NULL);
 }
 
 #else /* !CONFIG_PROC_FS */
diff --git a/trunk/drivers/input/joystick/iforce/iforce-usb.c b/trunk/drivers/input/joystick/iforce/iforce-usb.c
index 1457b73850e7..7fb3cf81cfbf 100644
--- a/trunk/drivers/input/joystick/iforce/iforce-usb.c
+++ b/trunk/drivers/input/joystick/iforce/iforce-usb.c
@@ -159,7 +159,7 @@ static int iforce_usb_probe(struct usb_interface *intf,
 
 	iforce->cr.bRequestType = USB_TYPE_VENDOR | USB_DIR_IN | USB_RECIP_INTERFACE;
 	iforce->cr.wIndex = 0;
-	iforce->cr.wLength = 16;
+	iforce->cr.wLength = cpu_to_le16(16);
 
 	usb_fill_int_urb(iforce->irq, dev, usb_rcvintpipe(dev, epirq->bEndpointAddress),
 			iforce->data, 16, iforce_usb_irq, iforce, epirq->bInterval);
diff --git a/trunk/drivers/input/joystick/xpad.c b/trunk/drivers/input/joystick/xpad.c
index 4b07bdadb81e..b29e3affb805 100644
--- a/trunk/drivers/input/joystick/xpad.c
+++ b/trunk/drivers/input/joystick/xpad.c
@@ -444,6 +444,23 @@ static void xpad_irq_in(struct urb *urb)
 		     __FUNCTION__, retval);
 }
 
+static void xpad_bulk_out(struct urb *urb)
+{
+	switch (urb->status) {
+	case 0:
+		/* success */
+		break;
+	case -ECONNRESET:
+	case -ENOENT:
+	case -ESHUTDOWN:
+		/* this urb is terminated, clean up */
+		dbg("%s - urb shutting down with status: %d", __FUNCTION__, urb->status);
+		break;
+	default:
+		dbg("%s - nonzero urb status received: %d", __FUNCTION__, urb->status);
+	}
+}
+
 #if defined(CONFIG_JOYSTICK_XPAD_FF) || defined(CONFIG_JOYSTICK_XPAD_LEDS)
 static void xpad_irq_out(struct urb *urb)
 {
@@ -475,23 +492,6 @@ static void xpad_irq_out(struct urb *urb)
 		    __FUNCTION__, retval);
 }
 
-static void xpad_bulk_out(struct urb *urb)
-{
-	switch (urb->status) {
-	case 0:
-		/* success */
-		break;
-	case -ECONNRESET:
-	case -ENOENT:
-	case -ESHUTDOWN:
-		/* this urb is terminated, clean up */
-		dbg("%s - urb shutting down with status: %d", __FUNCTION__, urb->status);
-		break;
-	default:
-		dbg("%s - nonzero urb status received: %d", __FUNCTION__, urb->status);
-	}
-}
-
 static int xpad_init_output(struct usb_interface *intf, struct usb_xpad *xpad)
 {
 	struct usb_endpoint_descriptor *ep_irq_out;
diff --git a/trunk/drivers/input/misc/sparcspkr.c b/trunk/drivers/input/misc/sparcspkr.c
index fed3c375ccf3..d8765cc93d27 100644
--- a/trunk/drivers/input/misc/sparcspkr.c
+++ b/trunk/drivers/input/misc/sparcspkr.c
@@ -2,33 +2,69 @@
  *  Driver for PC-speaker like devices found on various Sparc systems.
  *
  *  Copyright (c) 2002 Vojtech Pavlik
- *  Copyright (c) 2002, 2006 David S. Miller (davem@davemloft.net)
+ *  Copyright (c) 2002, 2006, 2008 David S. Miller (davem@davemloft.net)
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/input.h>
-#include <linux/platform_device.h>
+#include <linux/of_device.h>
 
 #include <asm/io.h>
-#include <asm/ebus.h>
-#include <asm/isa.h>
 
 MODULE_AUTHOR("David S. Miller <davem@davemloft.net>");
 MODULE_DESCRIPTION("Sparc Speaker beeper driver");
 MODULE_LICENSE("GPL");
 
+struct grover_beep_info {
+	void __iomem	*freq_regs;
+	void __iomem	*enable_reg;
+};
+
+struct bbc_beep_info {
+	u32		clock_freq;
+	void __iomem	*regs;
+};
+
 struct sparcspkr_state {
 	const char		*name;
-	unsigned long		iobase;
 	int (*event)(struct input_dev *dev, unsigned int type, unsigned int code, int value);
 	spinlock_t		lock;
 	struct input_dev	*input_dev;
+	union {
+		struct grover_beep_info grover;
+		struct bbc_beep_info bbc;
+	} u;
 };
 
-static int ebus_spkr_event(struct input_dev *dev, unsigned int type, unsigned int code, int value)
+static u32 bbc_count_to_reg(struct bbc_beep_info *info, unsigned int count)
+{
+	u32 val, clock_freq = info->clock_freq;
+	int i;
+
+	if (!count)
+		return 0;
+
+	if (count <= clock_freq >> 20)
+		return 1 << 18;
+
+	if (count >= clock_freq >> 12)
+		return 1 << 10;
+
+	val = 1 << 18;
+	for (i = 19; i >= 11; i--) {
+		val >>= 1;
+		if (count <= clock_freq >> i)
+			break;
+	}
+
+	return val;
+}
+
+static int bbc_spkr_event(struct input_dev *dev, unsigned int type, unsigned int code, int value)
 {
 	struct sparcspkr_state *state = dev_get_drvdata(dev->dev.parent);
+	struct bbc_beep_info *info = &state->u.bbc;
 	unsigned int count = 0;
 	unsigned long flags;
 
@@ -44,24 +80,29 @@ static int ebus_spkr_event(struct input_dev *dev, unsigned int type, unsigned in
 	if (value > 20 && value < 32767)
 		count = 1193182 / value;
 
+	count = bbc_count_to_reg(info, count);
+
 	spin_lock_irqsave(&state->lock, flags);
 
-	/* EBUS speaker only has on/off state, the frequency does not
-	 * appear to be programmable.
-	 */
-	if (state->iobase & 0x2UL)
-		outb(!!count, state->iobase);
-	else
-		outl(!!count, state->iobase);
+	if (count) {
+		outb(0x01,                 info->regs + 0);
+		outb(0x00,                 info->regs + 2);
+		outb((count >> 16) & 0xff, info->regs + 3);
+		outb((count >>  8) & 0xff, info->regs + 4);
+		outb(0x00,                 info->regs + 5);
+	} else {
+		outb(0x00,                 info->regs + 0);
+	}
 
 	spin_unlock_irqrestore(&state->lock, flags);
 
 	return 0;
 }
 
-static int isa_spkr_event(struct input_dev *dev, unsigned int type, unsigned int code, int value)
+static int grover_spkr_event(struct input_dev *dev, unsigned int type, unsigned int code, int value)
 {
 	struct sparcspkr_state *state = dev_get_drvdata(dev->dev.parent);
+	struct grover_beep_info *info = &state->u.grover;
 	unsigned int count = 0;
 	unsigned long flags;
 
@@ -81,15 +122,15 @@ static int isa_spkr_event(struct input_dev *dev, unsigned int type, unsigned int
 
 	if (count) {
 		/* enable counter 2 */
-		outb(inb(state->iobase + 0x61) | 3, state->iobase + 0x61);
+		outb(inb(info->enable_reg) | 3, info->enable_reg);
 		/* set command for counter 2, 2 byte write */
-		outb(0xB6, state->iobase + 0x43);
+		outb(0xB6, info->freq_regs + 1);
 		/* select desired HZ */
-		outb(count & 0xff, state->iobase + 0x42);
-		outb((count >> 8) & 0xff, state->iobase + 0x42);
+		outb(count & 0xff, info->freq_regs + 0);
+		outb((count >> 8) & 0xff, info->freq_regs + 0);
 	} else {
 		/* disable counter 2 */
-		outb(inb_p(state->iobase + 0x61) & 0xFC, state->iobase + 0x61);
+		outb(inb_p(info->enable_reg) & 0xFC, info->enable_reg);
 	}
 
 	spin_unlock_irqrestore(&state->lock, flags);
@@ -131,7 +172,7 @@ static int __devinit sparcspkr_probe(struct device *dev)
 	return 0;
 }
 
-static int __devexit sparcspkr_remove(struct of_device *dev)
+static int sparcspkr_shutdown(struct of_device *dev)
 {
 	struct sparcspkr_state *state = dev_get_drvdata(&dev->dev);
 	struct input_dev *input_dev = state->input_dev;
@@ -139,115 +180,180 @@ static int __devexit sparcspkr_remove(struct of_device *dev)
 	/* turn off the speaker */
 	state->event(input_dev, EV_SND, SND_BELL, 0);
 
-	input_unregister_device(input_dev);
-
-	dev_set_drvdata(&dev->dev, NULL);
-	kfree(state);
-
 	return 0;
 }
 
-static int sparcspkr_shutdown(struct of_device *dev)
+static int __devinit bbc_beep_probe(struct of_device *op, const struct of_device_id *match)
 {
-	struct sparcspkr_state *state = dev_get_drvdata(&dev->dev);
-	struct input_dev *input_dev = state->input_dev;
+	struct sparcspkr_state *state;
+	struct bbc_beep_info *info;
+	struct device_node *dp;
+	int err = -ENOMEM;
 
-	/* turn off the speaker */
-	state->event(input_dev, EV_SND, SND_BELL, 0);
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (!state)
+		goto out_err;
+
+	state->name = "Sparc BBC Speaker";
+	state->event = bbc_spkr_event;
+	spin_lock_init(&state->lock);
+
+	dp = of_find_node_by_path("/");
+	err = -ENODEV;
+	if (!dp)
+		goto out_free;
+
+	info = &state->u.bbc;
+	info->clock_freq = of_getintprop_default(dp, "clock-frequency", 0);
+	if (!info->clock_freq)
+		goto out_free;
+
+	info->regs = of_ioremap(&op->resource[0], 0, 6, "bbc beep");
+	if (!info->regs)
+		goto out_free;
+
+	dev_set_drvdata(&op->dev, state);
+
+	err = sparcspkr_probe(&op->dev);
+	if (err)
+		goto out_clear_drvdata;
 
 	return 0;
+
+out_clear_drvdata:
+	dev_set_drvdata(&op->dev, NULL);
+	of_iounmap(&op->resource[0], info->regs, 6);
+
+out_free:
+	kfree(state);
+out_err:
+	return err;
 }
 
-static int __devinit ebus_beep_probe(struct of_device *dev, const struct of_device_id *match)
+static int bbc_remove(struct of_device *op)
 {
-	struct linux_ebus_device *edev = to_ebus_device(&dev->dev);
-	struct sparcspkr_state *state;
-	int err;
+	struct sparcspkr_state *state = dev_get_drvdata(&op->dev);
+	struct input_dev *input_dev = state->input_dev;
+	struct bbc_beep_info *info = &state->u.bbc;
 
-	state = kzalloc(sizeof(*state), GFP_KERNEL);
-	if (!state)
-		return -ENOMEM;
+	/* turn off the speaker */
+	state->event(input_dev, EV_SND, SND_BELL, 0);
 
-	state->name = "Sparc EBUS Speaker";
-	state->iobase = edev->resource[0].start;
-	state->event = ebus_spkr_event;
-	spin_lock_init(&state->lock);
+	input_unregister_device(input_dev);
 
-	dev_set_drvdata(&dev->dev, state);
+	of_iounmap(&op->resource[0], info->regs, 6);
 
-	err = sparcspkr_probe(&dev->dev);
-	if (err) {
-		dev_set_drvdata(&dev->dev, NULL);
-		kfree(state);
-	}
+	dev_set_drvdata(&op->dev, NULL);
+	kfree(state);
 
 	return 0;
 }
 
-static struct of_device_id ebus_beep_match[] = {
+static struct of_device_id bbc_beep_match[] = {
 	{
 		.name = "beep",
+		.compatible = "SUNW,bbc-beep",
 	},
 	{},
 };
 
-static struct of_platform_driver ebus_beep_driver = {
-	.name		= "beep",
-	.match_table	= ebus_beep_match,
-	.probe		= ebus_beep_probe,
-	.remove		= __devexit_p(sparcspkr_remove),
+static struct of_platform_driver bbc_beep_driver = {
+	.name		= "bbcbeep",
+	.match_table	= bbc_beep_match,
+	.probe		= bbc_beep_probe,
+	.remove		= __devexit_p(bbc_remove),
 	.shutdown	= sparcspkr_shutdown,
 };
 
-static int __devinit isa_beep_probe(struct of_device *dev, const struct of_device_id *match)
+static int __devinit grover_beep_probe(struct of_device *op, const struct of_device_id *match)
 {
-	struct sparc_isa_device *idev = to_isa_device(&dev->dev);
 	struct sparcspkr_state *state;
-	int err;
+	struct grover_beep_info *info;
+	int err = -ENOMEM;
 
 	state = kzalloc(sizeof(*state), GFP_KERNEL);
 	if (!state)
-		return -ENOMEM;
+		goto out_err;
 
-	state->name = "Sparc ISA Speaker";
-	state->iobase = idev->resource.start;
-	state->event = isa_spkr_event;
+	state->name = "Sparc Grover Speaker";
+	state->event = grover_spkr_event;
 	spin_lock_init(&state->lock);
 
-	dev_set_drvdata(&dev->dev, state);
+	info = &state->u.grover;
+	info->freq_regs = of_ioremap(&op->resource[2], 0, 2, "grover beep freq");
+	if (!info->freq_regs)
+		goto out_free;
 
-	err = sparcspkr_probe(&dev->dev);
-	if (err) {
-		dev_set_drvdata(&dev->dev, NULL);
-		kfree(state);
-	}
+	info->enable_reg = of_ioremap(&op->resource[3], 0, 1, "grover beep enable");
+	if (!info->enable_reg)
+		goto out_unmap_freq_regs;
+
+	dev_set_drvdata(&op->dev, state);
+
+	err = sparcspkr_probe(&op->dev);
+	if (err)
+		goto out_clear_drvdata;
+
+	return 0;
+
+out_clear_drvdata:
+	dev_set_drvdata(&op->dev, NULL);
+	of_iounmap(&op->resource[3], info->enable_reg, 1);
+
+out_unmap_freq_regs:
+	of_iounmap(&op->resource[2], info->freq_regs, 2);
+out_free:
+	kfree(state);
+out_err:
+	return err;
+}
+
+static int grover_remove(struct of_device *op)
+{
+	struct sparcspkr_state *state = dev_get_drvdata(&op->dev);
+	struct grover_beep_info *info = &state->u.grover;
+	struct input_dev *input_dev = state->input_dev;
+
+	/* turn off the speaker */
+	state->event(input_dev, EV_SND, SND_BELL, 0);
+
+	input_unregister_device(input_dev);
+
+	of_iounmap(&op->resource[3], info->enable_reg, 1);
+	of_iounmap(&op->resource[2], info->freq_regs, 2);
+
+	dev_set_drvdata(&op->dev, NULL);
+	kfree(state);
 
 	return 0;
 }
 
-static struct of_device_id isa_beep_match[] = {
+static struct of_device_id grover_beep_match[] = {
 	{
-		.name = "dma",
+		.name = "beep",
+		.compatible = "SUNW,smbus-beep",
 	},
 	{},
 };
 
-static struct of_platform_driver isa_beep_driver = {
-	.name		= "beep",
-	.match_table	= isa_beep_match,
-	.probe		= isa_beep_probe,
-	.remove		= __devexit_p(sparcspkr_remove),
+static struct of_platform_driver grover_beep_driver = {
+	.name		= "groverbeep",
+	.match_table	= grover_beep_match,
+	.probe		= grover_beep_probe,
+	.remove		= __devexit_p(grover_remove),
 	.shutdown	= sparcspkr_shutdown,
 };
 
 static int __init sparcspkr_init(void)
 {
-	int err = of_register_driver(&ebus_beep_driver, &ebus_bus_type);
+	int err = of_register_driver(&bbc_beep_driver,
+				     &of_platform_bus_type);
 
 	if (!err) {
-		err = of_register_driver(&isa_beep_driver, &isa_bus_type);
+		err = of_register_driver(&grover_beep_driver,
+					 &of_platform_bus_type);
 		if (err)
-			of_unregister_driver(&ebus_beep_driver);
+			of_unregister_driver(&bbc_beep_driver);
 	}
 
 	return err;
@@ -255,8 +361,8 @@ static int __init sparcspkr_init(void)
 
 static void __exit sparcspkr_exit(void)
 {
-	of_unregister_driver(&ebus_beep_driver);
-	of_unregister_driver(&isa_beep_driver);
+	of_unregister_driver(&bbc_beep_driver);
+	of_unregister_driver(&grover_beep_driver);
 }
 
 module_init(sparcspkr_init);
diff --git a/trunk/drivers/input/tablet/aiptek.c b/trunk/drivers/input/tablet/aiptek.c
index 1d759f6f8076..55c1134d6137 100644
--- a/trunk/drivers/input/tablet/aiptek.c
+++ b/trunk/drivers/input/tablet/aiptek.c
@@ -528,9 +528,9 @@ static void aiptek_irq(struct urb *urb)
 			    (aiptek->curSetting.pointerMode)) {
 				aiptek->diagnostic = AIPTEK_DIAGNOSTIC_TOOL_DISALLOWED;
 		} else {
-			x = le16_to_cpu(get_unaligned((__le16 *) (data + 1)));
-			y = le16_to_cpu(get_unaligned((__le16 *) (data + 3)));
-			z = le16_to_cpu(get_unaligned((__le16 *) (data + 6)));
+			x = get_unaligned_le16(data + 1);
+			y = get_unaligned_le16(data + 3);
+			z = get_unaligned_le16(data + 6);
 
 			dv = (data[5] & 0x01) != 0 ? 1 : 0;
 			p = (data[5] & 0x02) != 0 ? 1 : 0;
@@ -613,8 +613,8 @@ static void aiptek_irq(struct urb *urb)
 			(aiptek->curSetting.pointerMode)) {
 			aiptek->diagnostic = AIPTEK_DIAGNOSTIC_TOOL_DISALLOWED;
 		} else {
-			x = le16_to_cpu(get_unaligned((__le16 *) (data + 1)));
-			y = le16_to_cpu(get_unaligned((__le16 *) (data + 3)));
+			x = get_unaligned_le16(data + 1);
+			y = get_unaligned_le16(data + 3);
 
 			jitterable = data[5] & 0x1c;
 
@@ -679,7 +679,7 @@ static void aiptek_irq(struct urb *urb)
 		pck = (data[1] & aiptek->curSetting.stylusButtonUpper) != 0 ? 1 : 0;
 
 		macro = dv && p && tip && !(data[3] & 1) ? (data[3] >> 1) : -1;
-		z = le16_to_cpu(get_unaligned((__le16 *) (data + 4)));
+		z = get_unaligned_le16(data + 4);
 
 		if (dv) {
 		        /* If the selected tool changed, reset the old
@@ -757,7 +757,7 @@ static void aiptek_irq(struct urb *urb)
 	 * hat switches (which just so happen to be the macroKeys.)
 	 */
 	else if (data[0] == 6) {
-		macro = le16_to_cpu(get_unaligned((__le16 *) (data + 1)));
+		macro = get_unaligned_le16(data + 1);
 		if (macro > 0) {
 			input_report_key(inputdev, macroKeyEvents[macro - 1],
 					 0);
@@ -952,7 +952,7 @@ aiptek_query(struct aiptek *aiptek, unsigned char command, unsigned char data)
 		    buf[0], buf[1], buf[2]);
 		ret = -EIO;
 	} else {
-		ret = le16_to_cpu(get_unaligned((__le16 *) (buf + 1)));
+		ret = get_unaligned_le16(buf + 1);
 	}
 	kfree(buf);
 	return ret;
diff --git a/trunk/drivers/input/tablet/gtco.c b/trunk/drivers/input/tablet/gtco.c
index d2c6da264722..c5a8661a1baa 100644
--- a/trunk/drivers/input/tablet/gtco.c
+++ b/trunk/drivers/input/tablet/gtco.c
@@ -245,11 +245,11 @@ static void parse_hid_report_descriptor(struct gtco *device, char * report,
 			data = report[i];
 			break;
 		case 2:
-			data16 = le16_to_cpu(get_unaligned((__le16 *)&report[i]));
+			data16 = get_unaligned_le16(&report[i]);
 			break;
 		case 3:
 			size = 4;
-			data32 = le32_to_cpu(get_unaligned((__le32 *)&report[i]));
+			data32 = get_unaligned_le32(&report[i]);
 			break;
 		}
 
@@ -695,10 +695,10 @@ static void gtco_urb_callback(struct urb *urbinfo)
 			/*  Fall thru */
 		case 1:
 			/* All reports have X and Y coords in the same place */
-			val = le16_to_cpu(get_unaligned((__le16 *)&device->buffer[1]));
+			val = get_unaligned_le16(&device->buffer[1]);
 			input_report_abs(inputdev, ABS_X, val);
 
-			val = le16_to_cpu(get_unaligned((__le16 *)&device->buffer[3]));
+			val = get_unaligned_le16(&device->buffer[3]);
 			input_report_abs(inputdev, ABS_Y, val);
 
 			/* Ditto for proximity bit */
@@ -762,7 +762,7 @@ static void gtco_urb_callback(struct urb *urbinfo)
 				le_buffer[1]  = (u8)(device->buffer[4] >> 1);
 				le_buffer[1] |= (u8)((device->buffer[5] & 0x1) << 7);
 
-				val = le16_to_cpu(get_unaligned((__le16 *)le_buffer));
+				val = get_unaligned_le16(le_buffer);
 				input_report_abs(inputdev, ABS_Y, val);
 
 				/*
@@ -772,10 +772,10 @@ static void gtco_urb_callback(struct urb *urbinfo)
 				buttonbyte = device->buffer[5] >> 1;
 			} else {
 
-				val = le16_to_cpu(get_unaligned((__le16 *)&device->buffer[1]));
+				val = get_unaligned_le16(&device->buffer[1]);
 				input_report_abs(inputdev, ABS_X, val);
 
-				val = le16_to_cpu(get_unaligned((__le16 *)&device->buffer[3]));
+				val = get_unaligned_le16(&device->buffer[3]);
 				input_report_abs(inputdev, ABS_Y, val);
 
 				buttonbyte = device->buffer[5];
@@ -897,7 +897,7 @@ static int gtco_probe(struct usb_interface *usbinterface,
 	dbg("Extra descriptor success: type:%d  len:%d",
 	    hid_desc->bDescriptorType,  hid_desc->wDescriptorLength);
 
-	report = kzalloc(hid_desc->wDescriptorLength, GFP_KERNEL);
+	report = kzalloc(le16_to_cpu(hid_desc->wDescriptorLength), GFP_KERNEL);
 	if (!report) {
 		err("No more memory for report");
 		error = -ENOMEM;
@@ -913,16 +913,16 @@ static int gtco_probe(struct usb_interface *usbinterface,
 					 REPORT_DEVICE_TYPE << 8,
 					 0, /* interface */
 					 report,
-					 hid_desc->wDescriptorLength,
+					 le16_to_cpu(hid_desc->wDescriptorLength),
 					 5000); /* 5 secs */
 
-		if (result == hid_desc->wDescriptorLength)
+		if (result == le16_to_cpu(hid_desc->wDescriptorLength))
 			break;
 	}
 
 	/* If we didn't get the report, fail */
 	dbg("usb_control_msg result: :%d", result);
-	if (result != hid_desc->wDescriptorLength) {
+	if (result != le16_to_cpu(hid_desc->wDescriptorLength)) {
 		err("Failed to get HID Report Descriptor of size: %d",
 		    hid_desc->wDescriptorLength);
 		error = -EIO;
diff --git a/trunk/drivers/input/tablet/kbtab.c b/trunk/drivers/input/tablet/kbtab.c
index 1182fc133167..f23f5a97fb38 100644
--- a/trunk/drivers/input/tablet/kbtab.c
+++ b/trunk/drivers/input/tablet/kbtab.c
@@ -63,8 +63,8 @@ static void kbtab_irq(struct urb *urb)
 		goto exit;
 	}
 
-	kbtab->x = le16_to_cpu(get_unaligned((__le16 *) &data[1]));
-	kbtab->y = le16_to_cpu(get_unaligned((__le16 *) &data[3]));
+	kbtab->x = get_unaligned_le16(&data[1]);
+	kbtab->y = get_unaligned_le16(&data[3]);
 
 	kbtab->pressure = (data[5]);
 
diff --git a/trunk/drivers/isdn/capi/capi.c b/trunk/drivers/isdn/capi/capi.c
index 23ae66c76d47..24c6b7ca62be 100644
--- a/trunk/drivers/isdn/capi/capi.c
+++ b/trunk/drivers/isdn/capi/capi.c
@@ -350,7 +350,7 @@ static void capincci_free(struct capidev *cdev, u32 ncci)
 		if (ncci == 0xffffffff || np->ncci == ncci) {
 			*pp = (*pp)->next;
 #ifdef CONFIG_ISDN_CAPI_MIDDLEWARE
-			if ((mp = np->minorp) != 0) {
+			if ((mp = np->minorp) != NULL) {
 #if defined(CONFIG_ISDN_CAPI_CAPIFS) || defined(CONFIG_ISDN_CAPI_CAPIFS_MODULE)
 				capifs_free_ncci(mp->minor);
 #endif
@@ -366,7 +366,7 @@ static void capincci_free(struct capidev *cdev, u32 ncci)
 			}
 #endif /* CONFIG_ISDN_CAPI_MIDDLEWARE */
 			kfree(np);
-			if (*pp == 0) return;
+			if (*pp == NULL) return;
 		} else {
 			pp = &(*pp)->next;
 		}
@@ -483,7 +483,7 @@ static int handle_recv_skb(struct capiminor *mp, struct sk_buff *skb)
 #endif
 		goto bad;
 	}
-	if ((nskb = gen_data_b3_resp_for(mp, skb)) == 0) {
+	if ((nskb = gen_data_b3_resp_for(mp, skb)) == NULL) {
 		printk(KERN_ERR "capi: gen_data_b3_resp failed\n");
 		goto bad;
 	}
@@ -512,7 +512,7 @@ static int handle_recv_skb(struct capiminor *mp, struct sk_buff *skb)
 static void handle_minor_recv(struct capiminor *mp)
 {
 	struct sk_buff *skb;
-	while ((skb = skb_dequeue(&mp->inqueue)) != 0) {
+	while ((skb = skb_dequeue(&mp->inqueue)) != NULL) {
 		unsigned int len = skb->len;
 		mp->inbytes -= len;
 		if (handle_recv_skb(mp, skb) < 0) {
@@ -538,7 +538,7 @@ static int handle_minor_send(struct capiminor *mp)
 		return 0;
 	}
 
-	while ((skb = skb_dequeue(&mp->outqueue)) != 0) {
+	while ((skb = skb_dequeue(&mp->outqueue)) != NULL) {
 		datahandle = mp->datahandle;
 		len = (u16)skb->len;
 		skb_push(skb, CAPI_DATA_B3_REQ_LEN);
@@ -689,19 +689,19 @@ capi_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 	if (!cdev->ap.applid)
 		return -ENODEV;
 
-	if ((skb = skb_dequeue(&cdev->recvqueue)) == 0) {
+	if ((skb = skb_dequeue(&cdev->recvqueue)) == NULL) {
 
 		if (file->f_flags & O_NONBLOCK)
 			return -EAGAIN;
 
 		for (;;) {
 			interruptible_sleep_on(&cdev->recvwait);
-			if ((skb = skb_dequeue(&cdev->recvqueue)) != 0)
+			if ((skb = skb_dequeue(&cdev->recvqueue)) != NULL)
 				break;
 			if (signal_pending(current))
 				break;
 		}
-		if (skb == 0)
+		if (skb == NULL)
 			return -ERESTARTNOHAND;
 	}
 	if (skb->len > count) {
@@ -940,12 +940,12 @@ capi_ioctl(struct inode *inode, struct file *file,
 				return -EFAULT;
 
 			mutex_lock(&cdev->ncci_list_mtx);
-			if ((nccip = capincci_find(cdev, (u32) ncci)) == 0) {
+			if ((nccip = capincci_find(cdev, (u32) ncci)) == NULL) {
 				mutex_unlock(&cdev->ncci_list_mtx);
 				return 0;
 			}
 #ifdef CONFIG_ISDN_CAPI_MIDDLEWARE
-			if ((mp = nccip->minorp) != 0) {
+			if ((mp = nccip->minorp) != NULL) {
 				count += atomic_read(&mp->ttyopencount);
 			}
 #endif /* CONFIG_ISDN_CAPI_MIDDLEWARE */
@@ -966,7 +966,7 @@ capi_ioctl(struct inode *inode, struct file *file,
 				return -EFAULT;
 			mutex_lock(&cdev->ncci_list_mtx);
 			nccip = capincci_find(cdev, (u32) ncci);
-			if (!nccip || (mp = nccip->minorp) == 0) {
+			if (!nccip || (mp = nccip->minorp) == NULL) {
 				mutex_unlock(&cdev->ncci_list_mtx);
 				return -ESRCH;
 			}
@@ -986,7 +986,7 @@ capi_open(struct inode *inode, struct file *file)
 	if (file->private_data)
 		return -EEXIST;
 
-	if ((file->private_data = capidev_alloc()) == 0)
+	if ((file->private_data = capidev_alloc()) == NULL)
 		return -ENOMEM;
 
 	return nonseekable_open(inode, file);
@@ -1023,9 +1023,9 @@ static int capinc_tty_open(struct tty_struct * tty, struct file * file)
 	struct capiminor *mp;
 	unsigned long flags;
 
-	if ((mp = capiminor_find(iminor(file->f_path.dentry->d_inode))) == 0)
+	if ((mp = capiminor_find(iminor(file->f_path.dentry->d_inode))) == NULL)
 		return -ENXIO;
-	if (mp->nccip == 0)
+	if (mp->nccip == NULL)
 		return -ENXIO;
 
 	tty->driver_data = (void *)mp;
@@ -1058,7 +1058,7 @@ static void capinc_tty_close(struct tty_struct * tty, struct file * file)
 #ifdef _DEBUG_REFCOUNT
 		printk(KERN_DEBUG "capinc_tty_close ocount=%d\n", atomic_read(&mp->ttyopencount));
 #endif
-		if (mp->nccip == 0)
+		if (mp->nccip == NULL)
 			capiminor_free(mp);
 	}
 
@@ -1526,9 +1526,9 @@ static int __init capi_init(void)
 	char *compileinfo;
 	int major_ret;
 
-	if ((p = strchr(revision, ':')) != 0 && p[1]) {
+	if ((p = strchr(revision, ':')) != NULL && p[1]) {
 		strlcpy(rev, p + 2, sizeof(rev));
-		if ((p = strchr(rev, '$')) != 0 && p > rev)
+		if ((p = strchr(rev, '$')) != NULL && p > rev)
 		   *(p-1) = 0;
 	} else
 		strcpy(rev, "1.0");
diff --git a/trunk/drivers/isdn/capi/capidrv.c b/trunk/drivers/isdn/capi/capidrv.c
index cb42b690b45e..d5b4cc357a3c 100644
--- a/trunk/drivers/isdn/capi/capidrv.c
+++ b/trunk/drivers/isdn/capi/capidrv.c
@@ -335,7 +335,7 @@ static capidrv_plci *new_plci(capidrv_contr * card, int chan)
 
 	plcip = kzalloc(sizeof(capidrv_plci), GFP_ATOMIC);
 
-	if (plcip == 0)
+	if (plcip == NULL)
 		return NULL;
 
 	plcip->state = ST_PLCI_NONE;
@@ -404,7 +404,7 @@ static inline capidrv_ncci *new_ncci(capidrv_contr * card,
 
 	nccip = kzalloc(sizeof(capidrv_ncci), GFP_ATOMIC);
 
-	if (nccip == 0)
+	if (nccip == NULL)
 		return NULL;
 
 	nccip->ncci = ncci;
@@ -426,7 +426,7 @@ static inline capidrv_ncci *find_ncci(capidrv_contr * card, u32 ncci)
 	capidrv_plci *plcip;
 	capidrv_ncci *p;
 
-	if ((plcip = find_plci_by_ncci(card, ncci)) == 0)
+	if ((plcip = find_plci_by_ncci(card, ncci)) == NULL)
 		return NULL;
 
 	for (p = plcip->ncci_list; p; p = p->next)
@@ -441,7 +441,7 @@ static inline capidrv_ncci *find_ncci_by_msgid(capidrv_contr * card,
 	capidrv_plci *plcip;
 	capidrv_ncci *p;
 
-	if ((plcip = find_plci_by_ncci(card, ncci)) == 0)
+	if ((plcip = find_plci_by_ncci(card, ncci)) == NULL)
 		return NULL;
 
 	for (p = plcip->ncci_list; p; p = p->next)
@@ -755,7 +755,7 @@ static inline int new_bchan(capidrv_contr * card)
 {
 	int i;
 	for (i = 0; i < card->nbchan; i++) {
-		if (card->bchans[i].plcip == 0) {
+		if (card->bchans[i].plcip == NULL) {
 			card->bchans[i].disconnecting = 0;
 			return i;
 		}
@@ -877,7 +877,7 @@ static void handle_incoming_call(capidrv_contr * card, _cmsg * cmsg)
 		return;
 	}
 	bchan = &card->bchans[chan];
-	if ((plcip = new_plci(card, chan)) == 0) {
+	if ((plcip = new_plci(card, chan)) == NULL) {
 		printk(KERN_ERR "capidrv-%d: incoming call: no memory, sorry.\n", card->contrnr);
 		return;
 	}
@@ -1388,12 +1388,12 @@ static void capidrv_recv_message(struct capi20_appl *ap, struct sk_buff *skb)
 		_cdebbuf *cdb = capi_cmsg2str(&s_cmsg);
 
 		if (cdb) {
-			printk(KERN_DEBUG "%s: applid=%d %s\n", __FUNCTION__,
+			printk(KERN_DEBUG "%s: applid=%d %s\n", __func__,
 				ap->applid, cdb->buf);
 			cdebbuf_free(cdb);
 		} else
 			printk(KERN_DEBUG "%s: applid=%d %s not traced\n",
-				__FUNCTION__, ap->applid,
+				__func__, ap->applid,
 				capi_cmd2str(s_cmsg.Command, s_cmsg.Subcommand));
 	}
 	if (s_cmsg.Command == CAPI_DATA_B3
@@ -1661,7 +1661,7 @@ static int capidrv_command(isdn_ctrl * c, capidrv_contr * card)
 					      NULL,	/* Useruserdata */
 					      NULL	/* Facilitydataarray */
 			    );
-			if ((plcip = new_plci(card, (c->arg % card->nbchan))) == 0) {
+			if ((plcip = new_plci(card, (c->arg % card->nbchan))) == NULL) {
 				cmd.command = ISDN_STAT_DHUP;
 				cmd.driver = card->myid;
 				cmd.arg = (c->arg % card->nbchan);
@@ -1966,7 +1966,7 @@ static void enable_dchannel_trace(capidrv_contr *card)
 			card->name, errcode);
 	   return;
 	}
-	if (strstr(manufacturer, "AVM") == 0) {
+	if (strstr(manufacturer, "AVM") == NULL) {
 	   printk(KERN_ERR "%s: not from AVM, no d-channel trace possible (%s)\n",
 			card->name, manufacturer);
 	   return;
@@ -2291,10 +2291,10 @@ static int __init capidrv_init(void)
 	u32 ncontr, contr;
 	u16 errcode;
 
-	if ((p = strchr(revision, ':')) != 0 && p[1]) {
+	if ((p = strchr(revision, ':')) != NULL && p[1]) {
 		strncpy(rev, p + 2, sizeof(rev));
 		rev[sizeof(rev)-1] = 0;
-		if ((p = strchr(rev, '$')) != 0 && p > rev)
+		if ((p = strchr(rev, '$')) != NULL && p > rev)
 		   *(p-1) = 0;
 	} else
 		strcpy(rev, "1.0");
@@ -2335,10 +2335,10 @@ static void __exit capidrv_exit(void)
 	char rev[32];
 	char *p;
 
-	if ((p = strchr(revision, ':')) != 0) {
+	if ((p = strchr(revision, ':')) != NULL) {
 		strncpy(rev, p + 1, sizeof(rev));
 		rev[sizeof(rev)-1] = 0;
-		if ((p = strchr(rev, '$')) != 0)
+		if ((p = strchr(rev, '$')) != NULL)
 			*p = 0;
 	} else {
 		strcpy(rev, " ??? ");
diff --git a/trunk/drivers/isdn/capi/capifs.c b/trunk/drivers/isdn/capi/capifs.c
index 6d7c47ec0367..550e80f390a6 100644
--- a/trunk/drivers/isdn/capi/capifs.c
+++ b/trunk/drivers/isdn/capi/capifs.c
@@ -69,6 +69,7 @@ static int capifs_remount(struct super_block *s, int *flags, char *data)
 		} else if (sscanf(this_char, "mode=%o%c", &n, &dummy) == 1)
 			mode = n & ~S_IFMT;
 		else {
+			kfree(new_opt);
 			printk("capifs: called with bogus options\n");
 			return -EINVAL;
 		}
@@ -189,9 +190,9 @@ static int __init capifs_init(void)
 	char *p;
 	int err;
 
-	if ((p = strchr(revision, ':')) != 0 && p[1]) {
+	if ((p = strchr(revision, ':')) != NULL && p[1]) {
 		strlcpy(rev, p + 2, sizeof(rev));
-		if ((p = strchr(rev, '$')) != 0 && p > rev)
+		if ((p = strchr(rev, '$')) != NULL && p > rev)
 		   *(p-1) = 0;
 	} else
 		strcpy(rev, "1.0");
diff --git a/trunk/drivers/isdn/capi/capilib.c b/trunk/drivers/isdn/capi/capilib.c
index 68409d971e73..fcaa1241ee77 100644
--- a/trunk/drivers/isdn/capi/capilib.c
+++ b/trunk/drivers/isdn/capi/capilib.c
@@ -4,7 +4,7 @@
 #include <linux/isdn/capilli.h>
 
 #define DBG(format, arg...) do { \
-printk(KERN_DEBUG "%s: " format "\n" , __FUNCTION__ , ## arg); \
+printk(KERN_DEBUG "%s: " format "\n" , __func__ , ## arg); \
 } while (0)
 
 struct capilib_msgidqueue {
@@ -44,7 +44,7 @@ static inline void mq_init(struct capilib_ncci * np)
 static inline int mq_enqueue(struct capilib_ncci * np, u16 msgid)
 {
 	struct capilib_msgidqueue *mq;
-	if ((mq = np->msgidfree) == 0)
+	if ((mq = np->msgidfree) == NULL)
 		return 0;
 	np->msgidfree = mq->next;
 	mq->msgid = msgid;
diff --git a/trunk/drivers/isdn/capi/capiutil.c b/trunk/drivers/isdn/capi/capiutil.c
index 22379b94e88f..ebef4ce1b00c 100644
--- a/trunk/drivers/isdn/capi/capiutil.c
+++ b/trunk/drivers/isdn/capi/capiutil.c
@@ -450,7 +450,7 @@ static void pars_2_message(_cmsg * cmsg)
 			cmsg->l += 4;
 			break;
 		case _CSTRUCT:
-			if (*(u8 **) OFF == 0) {
+			if (*(u8 **) OFF == NULL) {
 				*(cmsg->m + cmsg->l) = '\0';
 				cmsg->l++;
 			} else if (**(_cstruct *) OFF != 0xff) {
diff --git a/trunk/drivers/isdn/capi/kcapi.c b/trunk/drivers/isdn/capi/kcapi.c
index f55531869313..75726ea0fbbd 100644
--- a/trunk/drivers/isdn/capi/kcapi.c
+++ b/trunk/drivers/isdn/capi/kcapi.c
@@ -10,7 +10,7 @@
  *
  */
 
-#define CONFIG_AVMB1_COMPAT
+#define AVMB1_COMPAT
 
 #include "kcapi.h"
 #include <linux/module.h>
@@ -29,7 +29,7 @@
 #include <asm/uaccess.h>
 #include <linux/isdn/capicmd.h>
 #include <linux/isdn/capiutil.h>
-#ifdef CONFIG_AVMB1_COMPAT
+#ifdef AVMB1_COMPAT
 #include <linux/b1lli.h>
 #endif
 #include <linux/mutex.h>
@@ -154,7 +154,7 @@ static void register_appl(struct capi_ctr *card, u16 applid, capi_register_param
 	if (card)
 		card->register_appl(card, applid, rparam);
 	else
-		printk(KERN_WARNING "%s: cannot get card resources\n", __FUNCTION__);
+		printk(KERN_WARNING "%s: cannot get card resources\n", __func__);
 }
 
 
@@ -178,7 +178,7 @@ static void notify_up(u32 contr)
 	        printk(KERN_DEBUG "kcapi: notify up contr %d\n", contr);
 	}
 	if (!card) {
-		printk(KERN_WARNING "%s: invalid contr %d\n", __FUNCTION__, contr);
+		printk(KERN_WARNING "%s: invalid contr %d\n", __func__, contr);
 		return;
 	}
 	for (applid = 1; applid <= CAPI_MAXAPPL; applid++) {
@@ -740,7 +740,7 @@ u16 capi20_get_profile(u32 contr, struct capi_profile *profp)
 
 EXPORT_SYMBOL(capi20_get_profile);
 
-#ifdef CONFIG_AVMB1_COMPAT
+#ifdef AVMB1_COMPAT
 static int old_capi_manufacturer(unsigned int cmd, void __user *data)
 {
 	avmb1_loadandconfigdef ldef;
@@ -826,7 +826,7 @@ static int old_capi_manufacturer(unsigned int cmd, void __user *data)
 		card = capi_ctr_get(card);
 		if (!card)
 			return -ESRCH;
-		if (card->load_firmware == 0) {
+		if (card->load_firmware == NULL) {
 			printk(KERN_DEBUG "kcapi: load: no load function\n");
 			return -ESRCH;
 		}
@@ -835,7 +835,7 @@ static int old_capi_manufacturer(unsigned int cmd, void __user *data)
 			printk(KERN_DEBUG "kcapi: load: invalid parameter: length of t4file is %d ?\n", ldef.t4file.len);
 			return -EINVAL;
 		}
-		if (ldef.t4file.data == 0) {
+		if (ldef.t4file.data == NULL) {
 			printk(KERN_DEBUG "kcapi: load: invalid parameter: dataptr is 0\n");
 			return -EINVAL;
 		}
@@ -904,7 +904,7 @@ int capi20_manufacturer(unsigned int cmd, void __user *data)
         struct capi_ctr *card;
 
 	switch (cmd) {
-#ifdef CONFIG_AVMB1_COMPAT
+#ifdef AVMB1_COMPAT
 	case AVMB1_LOAD:
 	case AVMB1_LOAD_AND_CONFIG:
 	case AVMB1_RESETCARD:
@@ -951,7 +951,7 @@ int capi20_manufacturer(unsigned int cmd, void __user *data)
 			if (strcmp(driver->name, cdef.driver) == 0)
 				break;
 		}
-		if (driver == 0) {
+		if (driver == NULL) {
 			printk(KERN_ERR "kcapi: driver \"%s\" not loaded.\n",
 					cdef.driver);
 			return -ESRCH;
@@ -1004,9 +1004,9 @@ static int __init kcapi_init(void)
 		return ret;
         kcapi_proc_init();
 
-	if ((p = strchr(revision, ':')) != 0 && p[1]) {
+	if ((p = strchr(revision, ':')) != NULL && p[1]) {
 		strlcpy(rev, p + 2, sizeof(rev));
-		if ((p = strchr(rev, '$')) != 0 && p > rev)
+		if ((p = strchr(rev, '$')) != NULL && p > rev)
 		   *(p-1) = 0;
 	} else
 		strcpy(rev, "1.0");
diff --git a/trunk/drivers/isdn/capi/kcapi.h b/trunk/drivers/isdn/capi/kcapi.h
index 1cb2c40f9921..244711f7f838 100644
--- a/trunk/drivers/isdn/capi/kcapi.h
+++ b/trunk/drivers/isdn/capi/kcapi.h
@@ -17,7 +17,7 @@
 
 #ifdef KCAPI_DEBUG
 #define DBG(format, arg...) do { \
-printk(KERN_DEBUG "%s: " format "\n" , __FUNCTION__ , ## arg); \
+printk(KERN_DEBUG "%s: " format "\n" , __func__ , ## arg); \
 } while (0)
 #else
 #define DBG(format, arg...) /* */
diff --git a/trunk/drivers/isdn/capi/kcapi_proc.c b/trunk/drivers/isdn/capi/kcapi_proc.c
index 845a797b0030..c29208bd7521 100644
--- a/trunk/drivers/isdn/capi/kcapi_proc.c
+++ b/trunk/drivers/isdn/capi/kcapi_proc.c
@@ -114,6 +114,7 @@ static int seq_contrstats_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations proc_controller_ops = {
+	.owner		= THIS_MODULE,
 	.open		= seq_controller_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -121,6 +122,7 @@ static const struct file_operations proc_controller_ops = {
 };
 
 static const struct file_operations proc_contrstats_ops = {
+	.owner		= THIS_MODULE,
 	.open		= seq_contrstats_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -219,6 +221,7 @@ seq_applstats_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations proc_applications_ops = {
+	.owner		= THIS_MODULE,
 	.open		= seq_applications_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -226,21 +229,13 @@ static const struct file_operations proc_applications_ops = {
 };
 
 static const struct file_operations proc_applstats_ops = {
+	.owner		= THIS_MODULE,
 	.open		= seq_applstats_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release,
 };
 
-static void
-create_seq_entry(char *name, mode_t mode, const struct file_operations *f)
-{
-	struct proc_dir_entry *entry;
-	entry = create_proc_entry(name, mode, NULL);
-	if (entry)
-		entry->proc_fops = f;
-}
-
 // ---------------------------------------------------------------------------
 
 static void *capi_driver_start(struct seq_file *seq, loff_t *pos)
@@ -283,6 +278,7 @@ seq_capi_driver_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations proc_driver_ops = {
+	.owner		= THIS_MODULE,
 	.open		= seq_capi_driver_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -296,11 +292,11 @@ kcapi_proc_init(void)
 {
 	proc_mkdir("capi",             NULL);
 	proc_mkdir("capi/controllers", NULL);
-	create_seq_entry("capi/controller",   0, &proc_controller_ops);
-	create_seq_entry("capi/contrstats",   0, &proc_contrstats_ops);
-	create_seq_entry("capi/applications", 0, &proc_applications_ops);
-	create_seq_entry("capi/applstats",    0, &proc_applstats_ops);
-	create_seq_entry("capi/driver",       0, &proc_driver_ops);
+	proc_create("capi/controller",   0, NULL, &proc_controller_ops);
+	proc_create("capi/contrstats",   0, NULL, &proc_contrstats_ops);
+	proc_create("capi/applications", 0, NULL, &proc_applications_ops);
+	proc_create("capi/applstats",    0, NULL, &proc_applstats_ops);
+	proc_create("capi/driver",       0, NULL, &proc_driver_ops);
 }
 
 void __exit
diff --git a/trunk/drivers/isdn/divert/divert_procfs.c b/trunk/drivers/isdn/divert/divert_procfs.c
index 4fd4c46892e3..8b256a617c8a 100644
--- a/trunk/drivers/isdn/divert/divert_procfs.c
+++ b/trunk/drivers/isdn/divert/divert_procfs.c
@@ -288,13 +288,12 @@ divert_dev_init(void)
 	isdn_proc_entry = proc_mkdir("isdn", init_net.proc_net);
 	if (!isdn_proc_entry)
 		return (-1);
-	isdn_divert_entry = create_proc_entry("divert", S_IFREG | S_IRUGO, isdn_proc_entry);
+	isdn_divert_entry = proc_create("divert", S_IFREG | S_IRUGO,
+					isdn_proc_entry, &isdn_fops);
 	if (!isdn_divert_entry) {
 		remove_proc_entry("isdn", init_net.proc_net);
 		return (-1);
 	}
-	isdn_divert_entry->proc_fops = &isdn_fops; 
-	isdn_divert_entry->owner = THIS_MODULE; 
 #endif	/* CONFIG_PROC_FS */
 
 	return (0);
diff --git a/trunk/drivers/isdn/hardware/avm/b1.c b/trunk/drivers/isdn/hardware/avm/b1.c
index 4484a6417235..abf05ec31760 100644
--- a/trunk/drivers/isdn/hardware/avm/b1.c
+++ b/trunk/drivers/isdn/hardware/avm/b1.c
@@ -661,11 +661,11 @@ int b1ctl_read_proc(char *page, char **start, off_t off,
 	len += sprintf(page+len, "%-16s %s\n", "type", s);
 	if (card->cardtype == avm_t1isa)
 	   len += sprintf(page+len, "%-16s %d\n", "cardnr", card->cardnr);
-	if ((s = cinfo->version[VER_DRIVER]) != 0)
+	if ((s = cinfo->version[VER_DRIVER]) != NULL)
 	   len += sprintf(page+len, "%-16s %s\n", "ver_driver", s);
-	if ((s = cinfo->version[VER_CARDTYPE]) != 0)
+	if ((s = cinfo->version[VER_CARDTYPE]) != NULL)
 	   len += sprintf(page+len, "%-16s %s\n", "ver_cardtype", s);
-	if ((s = cinfo->version[VER_SERIAL]) != 0)
+	if ((s = cinfo->version[VER_SERIAL]) != NULL)
 	   len += sprintf(page+len, "%-16s %s\n", "ver_serial", s);
 
 	if (card->cardtype != avm_m1) {
@@ -788,9 +788,9 @@ static int __init b1_init(void)
 	char *p;
 	char rev[32];
 
-	if ((p = strchr(revision, ':')) != 0 && p[1]) {
+	if ((p = strchr(revision, ':')) != NULL && p[1]) {
 		strlcpy(rev, p + 2, 32);
-		if ((p = strchr(rev, '$')) != 0 && p > rev)
+		if ((p = strchr(rev, '$')) != NULL && p > rev)
 		   *(p-1) = 0;
 	} else
 		strcpy(rev, "1.0");
diff --git a/trunk/drivers/isdn/hardware/avm/b1dma.c b/trunk/drivers/isdn/hardware/avm/b1dma.c
index 669f6f67449c..da34b98e3de7 100644
--- a/trunk/drivers/isdn/hardware/avm/b1dma.c
+++ b/trunk/drivers/isdn/hardware/avm/b1dma.c
@@ -883,11 +883,11 @@ int b1dmactl_read_proc(char *page, char **start, off_t off,
 	default: s = "???"; break;
 	}
 	len += sprintf(page+len, "%-16s %s\n", "type", s);
-	if ((s = cinfo->version[VER_DRIVER]) != 0)
+	if ((s = cinfo->version[VER_DRIVER]) != NULL)
 	   len += sprintf(page+len, "%-16s %s\n", "ver_driver", s);
-	if ((s = cinfo->version[VER_CARDTYPE]) != 0)
+	if ((s = cinfo->version[VER_CARDTYPE]) != NULL)
 	   len += sprintf(page+len, "%-16s %s\n", "ver_cardtype", s);
-	if ((s = cinfo->version[VER_SERIAL]) != 0)
+	if ((s = cinfo->version[VER_SERIAL]) != NULL)
 	   len += sprintf(page+len, "%-16s %s\n", "ver_serial", s);
 
 	if (card->cardtype != avm_m1) {
@@ -970,9 +970,9 @@ static int __init b1dma_init(void)
 	char *p;
 	char rev[32];
 
-	if ((p = strchr(revision, ':')) != 0 && p[1]) {
+	if ((p = strchr(revision, ':')) != NULL && p[1]) {
 		strlcpy(rev, p + 2, sizeof(rev));
-		if ((p = strchr(rev, '$')) != 0 && p > rev)
+		if ((p = strchr(rev, '$')) != NULL && p > rev)
 		   *(p-1) = 0;
 	} else
 		strcpy(rev, "1.0");
diff --git a/trunk/drivers/isdn/hardware/avm/b1isa.c b/trunk/drivers/isdn/hardware/avm/b1isa.c
index 80fb488848b8..1e288eeb5e2a 100644
--- a/trunk/drivers/isdn/hardware/avm/b1isa.c
+++ b/trunk/drivers/isdn/hardware/avm/b1isa.c
@@ -203,9 +203,9 @@ static int __init b1isa_init(void)
 	char rev[32];
 	int i;
 
-	if ((p = strchr(revision, ':')) != 0 && p[1]) {
+	if ((p = strchr(revision, ':')) != NULL && p[1]) {
 		strlcpy(rev, p + 2, 32);
-		if ((p = strchr(rev, '$')) != 0 && p > rev)
+		if ((p = strchr(rev, '$')) != NULL && p > rev)
 		   *(p-1) = 0;
 	} else
 		strcpy(rev, "1.0");
diff --git a/trunk/drivers/isdn/hardware/avm/b1pci.c b/trunk/drivers/isdn/hardware/avm/b1pci.c
index 90e2e6643d19..5b314a2c4049 100644
--- a/trunk/drivers/isdn/hardware/avm/b1pci.c
+++ b/trunk/drivers/isdn/hardware/avm/b1pci.c
@@ -382,9 +382,9 @@ static int __init b1pci_init(void)
 	char rev[32];
 	int err;
 
-	if ((p = strchr(revision, ':')) != 0 && p[1]) {
+	if ((p = strchr(revision, ':')) != NULL && p[1]) {
 		strlcpy(rev, p + 2, 32);
-		if ((p = strchr(rev, '$')) != 0 && p > rev)
+		if ((p = strchr(rev, '$')) != NULL && p > rev)
 		   *(p-1) = 0;
 	} else
 		strcpy(rev, "1.0");
diff --git a/trunk/drivers/isdn/hardware/avm/b1pcmcia.c b/trunk/drivers/isdn/hardware/avm/b1pcmcia.c
index e479c0aef38d..7740403b40e1 100644
--- a/trunk/drivers/isdn/hardware/avm/b1pcmcia.c
+++ b/trunk/drivers/isdn/hardware/avm/b1pcmcia.c
@@ -201,9 +201,9 @@ static int __init b1pcmcia_init(void)
 	char *p;
 	char rev[32];
 
-	if ((p = strchr(revision, ':')) != 0 && p[1]) {
+	if ((p = strchr(revision, ':')) != NULL && p[1]) {
 		strlcpy(rev, p + 2, 32);
-		if ((p = strchr(rev, '$')) != 0 && p > rev)
+		if ((p = strchr(rev, '$')) != NULL && p > rev)
 		   *(p-1) = 0;
 	} else
 		strcpy(rev, "1.0");
diff --git a/trunk/drivers/isdn/hardware/avm/c4.c b/trunk/drivers/isdn/hardware/avm/c4.c
index 4bbbbe688077..9df1d3f66c87 100644
--- a/trunk/drivers/isdn/hardware/avm/c4.c
+++ b/trunk/drivers/isdn/hardware/avm/c4.c
@@ -1088,11 +1088,11 @@ static int c4_read_proc(char *page, char **start, off_t off,
 	default: s = "???"; break;
 	}
 	len += sprintf(page+len, "%-16s %s\n", "type", s);
-	if ((s = cinfo->version[VER_DRIVER]) != 0)
+	if ((s = cinfo->version[VER_DRIVER]) != NULL)
 	   len += sprintf(page+len, "%-16s %s\n", "ver_driver", s);
-	if ((s = cinfo->version[VER_CARDTYPE]) != 0)
+	if ((s = cinfo->version[VER_CARDTYPE]) != NULL)
 	   len += sprintf(page+len, "%-16s %s\n", "ver_cardtype", s);
-	if ((s = cinfo->version[VER_SERIAL]) != 0)
+	if ((s = cinfo->version[VER_SERIAL]) != NULL)
 	   len += sprintf(page+len, "%-16s %s\n", "ver_serial", s);
 
 	if (card->cardtype != avm_m1) {
@@ -1167,7 +1167,7 @@ static int c4_add_card(struct capicardparams *p, struct pci_dev *dev,
 	}
 
 	card->mbase = ioremap(card->membase, 128);
-	if (card->mbase == 0) {
+	if (card->mbase == NULL) {
 		printk(KERN_NOTICE "c4: can't remap memory at 0x%lx\n",
 		       card->membase);
 		retval = -EIO;
@@ -1291,9 +1291,9 @@ static int __init c4_init(void)
 	char rev[32];
 	int err;
 
-	if ((p = strchr(revision, ':')) != 0 && p[1]) {
+	if ((p = strchr(revision, ':')) != NULL && p[1]) {
 		strlcpy(rev, p + 2, 32);
-		if ((p = strchr(rev, '$')) != 0 && p > rev)
+		if ((p = strchr(rev, '$')) != NULL && p > rev)
 		   *(p-1) = 0;
 	} else
 		strcpy(rev, "1.0");
diff --git a/trunk/drivers/isdn/hardware/avm/t1isa.c b/trunk/drivers/isdn/hardware/avm/t1isa.c
index 6130724e46e7..e7724493738c 100644
--- a/trunk/drivers/isdn/hardware/avm/t1isa.c
+++ b/trunk/drivers/isdn/hardware/avm/t1isa.c
@@ -551,9 +551,9 @@ static int __init t1isa_init(void)
 	char *p;
 	int i;
 
-	if ((p = strchr(revision, ':')) != 0 && p[1]) {
+	if ((p = strchr(revision, ':')) != NULL && p[1]) {
 		strlcpy(rev, p + 2, 32);
-		if ((p = strchr(rev, '$')) != 0 && p > rev)
+		if ((p = strchr(rev, '$')) != NULL && p > rev)
 		   *(p-1) = 0;
 	} else
 		strcpy(rev, "1.0");
diff --git a/trunk/drivers/isdn/hardware/avm/t1pci.c b/trunk/drivers/isdn/hardware/avm/t1pci.c
index d1e253c94db4..e6d298d75146 100644
--- a/trunk/drivers/isdn/hardware/avm/t1pci.c
+++ b/trunk/drivers/isdn/hardware/avm/t1pci.c
@@ -233,9 +233,9 @@ static int __init t1pci_init(void)
 	char rev[32];
 	int err;
 
-	if ((p = strchr(revision, ':')) != 0 && p[1]) {
+	if ((p = strchr(revision, ':')) != NULL && p[1]) {
 		strlcpy(rev, p + 2, 32);
-		if ((p = strchr(rev, '$')) != 0 && p > rev)
+		if ((p = strchr(rev, '$')) != NULL && p > rev)
 		   *(p-1) = 0;
 	} else
 		strcpy(rev, "1.0");
diff --git a/trunk/drivers/isdn/hardware/eicon/divasmain.c b/trunk/drivers/isdn/hardware/eicon/divasmain.c
index 6d39f9360766..5fcbdccd7a53 100644
--- a/trunk/drivers/isdn/hardware/eicon/divasmain.c
+++ b/trunk/drivers/isdn/hardware/eicon/divasmain.c
@@ -393,7 +393,7 @@ void diva_free_dma_map(void *hdev, struct _diva_dma_map_entry *pmap)
 	dma_addr_t dma_handle;
 	void *addr_handle;
 
-	for (i = 0; (pmap != 0); i++) {
+	for (i = 0; (pmap != NULL); i++) {
 		diva_get_dma_map_entry(pmap, i, &cpu_addr, &phys_addr);
 		if (!cpu_addr) {
 			break;
diff --git a/trunk/drivers/isdn/hardware/eicon/divasproc.c b/trunk/drivers/isdn/hardware/eicon/divasproc.c
index 0632a2606998..fae895828a17 100644
--- a/trunk/drivers/isdn/hardware/eicon/divasproc.c
+++ b/trunk/drivers/isdn/hardware/eicon/divasproc.c
@@ -125,15 +125,11 @@ static const struct file_operations divas_fops = {
 
 int create_divas_proc(void)
 {
-	divas_proc_entry = create_proc_entry(divas_proc_name,
-					     S_IFREG | S_IRUGO,
-					     proc_net_eicon);
+	proc_create(divas_proc_name, S_IFREG | S_IRUGO, proc_net_eicon,
+		    &divas_fops);
 	if (!divas_proc_entry)
 		return (0);
 
-	divas_proc_entry->proc_fops = &divas_fops;
-	divas_proc_entry->owner = THIS_MODULE;
-
 	return (1);
 }
 
diff --git a/trunk/drivers/isdn/hardware/eicon/message.c b/trunk/drivers/isdn/hardware/eicon/message.c
index 1ff98e7eb794..599fed88222d 100644
--- a/trunk/drivers/isdn/hardware/eicon/message.c
+++ b/trunk/drivers/isdn/hardware/eicon/message.c
@@ -742,7 +742,7 @@ static void start_internal_command (dword Id, PLCI   *plci, t_std_internal_comma
   else
   {
     i = 1;
-    while (plci->internal_command_queue[i] != 0)
+    while (plci->internal_command_queue[i] != NULL)
       i++;
     plci->internal_command_queue[i] = command_function;
   }
@@ -758,7 +758,7 @@ static void next_internal_command (dword Id, PLCI   *plci)
 
   plci->internal_command = 0;
   plci->internal_command_queue[0] = NULL;
-  while (plci->internal_command_queue[1] != 0)
+  while (plci->internal_command_queue[1] != NULL)
   {
     for (i = 0; i < MAX_INTERNAL_COMMAND_LEVELS - 1; i++)
       plci->internal_command_queue[i] = plci->internal_command_queue[i+1];
@@ -9119,7 +9119,7 @@ word AdvCodecSupport(DIVA_CAPI_ADAPTER   *a, PLCI   *plci, APPL   *appl, byte ho
         dbug(1,dprintf("AdvSigPlci=0x%x",a->AdvSignalPLCI));
         return 0x2001; /* codec in use by another application */
       }
-      if(plci!=0)
+      if(plci!=NULL)
       {
         a->AdvSignalPLCI = plci;
         plci->tel=ADV_VOICE;
@@ -9144,7 +9144,7 @@ word AdvCodecSupport(DIVA_CAPI_ADAPTER   *a, PLCI   *plci, APPL   *appl, byte ho
         }
                                                /* indicate D-ch connect if  */
       }                                        /* codec is connected OK     */
-      if(plci!=0)
+      if(plci!=NULL)
       {
         a->AdvSignalPLCI = plci;
         plci->tel=ADV_VOICE;
@@ -9170,7 +9170,7 @@ word AdvCodecSupport(DIVA_CAPI_ADAPTER   *a, PLCI   *plci, APPL   *appl, byte ho
   {
     if(hook_listen) return 0x300B;               /* Facility not supported */
                                                  /* no hook with SCOM      */
-    if(plci!=0) plci->tel = CODEC;
+    if(plci!=NULL) plci->tel = CODEC;
     dbug(1,dprintf("S/SCOM codec"));
     /* first time we use the scom-s codec we must shut down the internal   */
     /* handset application of the card. This can be done by an assign with */
@@ -14604,7 +14604,7 @@ static void channel_xmit_extended_xon (PLCI   * plci) {
   int max_ch = ARRAY_SIZE(a->ch_flow_control);
   int i, one_requested = 0;
 
-  if ((!plci) || (!plci->Id) || ((a = plci->adapter) == 0)) {
+  if ((!plci) || (!plci->Id) || ((a = plci->adapter) == NULL)) {
     return;
   }
 
diff --git a/trunk/drivers/isdn/hisax/asuscom.c b/trunk/drivers/isdn/hisax/asuscom.c
index b96f3184c2e5..1f879b500d83 100644
--- a/trunk/drivers/isdn/hisax/asuscom.c
+++ b/trunk/drivers/isdn/hisax/asuscom.c
@@ -344,7 +344,7 @@ setup_asuscom(struct IsdnCard *card)
 					err = pnp_activate_dev(pnp_d);
 					if (err<0) {
 						printk(KERN_WARNING "%s: pnp_activate_dev ret(%d)\n",
-							__FUNCTION__, err);
+							__func__, err);
 						return(0);
 					}
 					card->para[1] = pnp_port_start(pnp_d, 0);
diff --git a/trunk/drivers/isdn/hisax/avm_pci.c b/trunk/drivers/isdn/hisax/avm_pci.c
index 0f1db1f669b2..7cabc5a19492 100644
--- a/trunk/drivers/isdn/hisax/avm_pci.c
+++ b/trunk/drivers/isdn/hisax/avm_pci.c
@@ -797,7 +797,7 @@ static int __devinit avm_pnp_setup(struct IsdnCardState *cs)
 			err = pnp_activate_dev(pnp_avm_d);
 			if (err<0) {
 				printk(KERN_WARNING "%s: pnp_activate_dev ret(%d)\n",
-					__FUNCTION__, err);
+					__func__, err);
 				return(0);
 			}
 			cs->hw.avm.cfg_reg =
diff --git a/trunk/drivers/isdn/hisax/diva.c b/trunk/drivers/isdn/hisax/diva.c
index 2d670856d141..018bd293e580 100644
--- a/trunk/drivers/isdn/hisax/diva.c
+++ b/trunk/drivers/isdn/hisax/diva.c
@@ -1088,7 +1088,7 @@ static int __devinit setup_diva_isapnp(struct IsdnCard *card)
 				err = pnp_activate_dev(pnp_d);
 				if (err<0) {
 					printk(KERN_WARNING "%s: pnp_activate_dev ret(%d)\n",
-						__FUNCTION__, err);
+						__func__, err);
 					return(0);
 				}
 				card->para[1] = pnp_port_start(pnp_d, 0);
diff --git a/trunk/drivers/isdn/hisax/elsa.c b/trunk/drivers/isdn/hisax/elsa.c
index 2c3691fda300..aa29d1cf16af 100644
--- a/trunk/drivers/isdn/hisax/elsa.c
+++ b/trunk/drivers/isdn/hisax/elsa.c
@@ -937,7 +937,7 @@ setup_elsa_isapnp(struct IsdnCard *card)
 					err = pnp_activate_dev(pnp_d);
 					if (err<0) {
 						printk(KERN_WARNING "%s: pnp_activate_dev ret(%d)\n",
-							__FUNCTION__, err);
+							__func__, err);
 						return(0);
 					}
 					card->para[1] = pnp_port_start(pnp_d, 0);
diff --git a/trunk/drivers/isdn/hisax/hfc_sx.c b/trunk/drivers/isdn/hisax/hfc_sx.c
index f4a213877e35..d92e8d6c2ae2 100644
--- a/trunk/drivers/isdn/hisax/hfc_sx.c
+++ b/trunk/drivers/isdn/hisax/hfc_sx.c
@@ -1417,7 +1417,7 @@ setup_hfcsx(struct IsdnCard *card)
 					err = pnp_activate_dev(pnp_d);
 					if (err<0) {
 						printk(KERN_WARNING "%s: pnp_activate_dev ret(%d)\n",
-							__FUNCTION__, err);
+							__func__, err);
 						return(0);
 					}
 					card->para[1] = pnp_port_start(pnp_d, 0);
diff --git a/trunk/drivers/isdn/hisax/hfc_usb.c b/trunk/drivers/isdn/hisax/hfc_usb.c
index 98b0149bca68..8df889b0c1a9 100644
--- a/trunk/drivers/isdn/hisax/hfc_usb.c
+++ b/trunk/drivers/isdn/hisax/hfc_usb.c
@@ -905,7 +905,7 @@ rx_int_complete(struct urb *urb)
 	if (status) {
 		printk(KERN_INFO
 		       "HFC-S USB: %s error resubmitting URB fifo(%d)\n",
-		       __FUNCTION__, fifon);
+		       __func__, fifon);
 	}
 }
 
@@ -1543,14 +1543,14 @@ hfc_usb_disconnect(struct usb_interface *intf)
 				stop_isoc_chain(&context->fifos[i]);
 				DBG(HFCUSB_DBG_INIT,
 				    "HFC-S USB: %s stopping ISOC chain Fifo(%i)",
-				    __FUNCTION__, i);
+				    __func__, i);
 			}
 		} else {
 			if (context->fifos[i].active > 0) {
 				context->fifos[i].active = 0;
 				DBG(HFCUSB_DBG_INIT,
 				    "HFC-S USB: %s unlinking URB for Fifo(%i)",
-				    __FUNCTION__, i);
+				    __func__, i);
 			}
 			usb_kill_urb(context->fifos[i].urb);
 			usb_free_urb(context->fifos[i].urb);
diff --git a/trunk/drivers/isdn/hisax/hfcscard.c b/trunk/drivers/isdn/hisax/hfcscard.c
index 909d6709ec16..cf082665cc8b 100644
--- a/trunk/drivers/isdn/hisax/hfcscard.c
+++ b/trunk/drivers/isdn/hisax/hfcscard.c
@@ -193,7 +193,7 @@ setup_hfcs(struct IsdnCard *card)
 					err = pnp_activate_dev(pnp_d);
 					if (err<0) {
 						printk(KERN_WARNING "%s: pnp_activate_dev ret(%d)\n",
-							__FUNCTION__, err);
+							__func__, err);
 						return(0);
 					}
 					card->para[1] = pnp_port_start(pnp_d, 0);
diff --git a/trunk/drivers/isdn/hisax/hisax_debug.h b/trunk/drivers/isdn/hisax/hisax_debug.h
index ceafecdb1037..5ed3b1c44184 100644
--- a/trunk/drivers/isdn/hisax/hisax_debug.h
+++ b/trunk/drivers/isdn/hisax/hisax_debug.h
@@ -27,14 +27,14 @@
 
 #define DBG(level, format, arg...) do { \
 if (level & __debug_variable) \
-printk(KERN_DEBUG "%s: " format "\n" , __FUNCTION__ , ## arg); \
+printk(KERN_DEBUG "%s: " format "\n" , __func__ , ## arg); \
 } while (0)
 
 #define DBG_PACKET(level,data,count) \
-  if (level & __debug_variable) dump_packet(__FUNCTION__,data,count)
+  if (level & __debug_variable) dump_packet(__func__,data,count)
 
 #define DBG_SKB(level,skb) \
-  if ((level & __debug_variable) && skb) dump_packet(__FUNCTION__,skb->data,skb->len)
+  if ((level & __debug_variable) && skb) dump_packet(__func__,skb->data,skb->len)
 
 
 static void __attribute__((unused))
diff --git a/trunk/drivers/isdn/hisax/hisax_fcpcipnp.c b/trunk/drivers/isdn/hisax/hisax_fcpcipnp.c
index 76043dedba5b..c0b4db2f8364 100644
--- a/trunk/drivers/isdn/hisax/hisax_fcpcipnp.c
+++ b/trunk/drivers/isdn/hisax/hisax_fcpcipnp.c
@@ -68,7 +68,7 @@ static struct pci_device_id fcpci_ids[] = {
 
 MODULE_DEVICE_TABLE(pci, fcpci_ids);
 
-#ifdef __ISAPNP__
+#ifdef CONFIG_PNP
 static struct pnp_device_id fcpnp_ids[] __devinitdata = {
 	{ 
 		.id		= "AVM0900",
@@ -914,7 +914,7 @@ static int __devinit fcpci_probe(struct pci_dev *pdev,
 	return retval;
 }
 
-#ifdef __ISAPNP__
+#ifdef CONFIG_PNP
 static int __devinit fcpnp_probe(struct pnp_dev *pdev, const struct pnp_device_id *dev_id)
 {
 	struct fritz_adapter *adapter;
@@ -935,7 +935,7 @@ static int __devinit fcpnp_probe(struct pnp_dev *pdev, const struct pnp_device_i
 	pnp_disable_dev(pdev);
 	retval = pnp_activate_dev(pdev);
 	if (retval < 0) {
-		printk(KERN_WARNING "%s: pnp_activate_dev(%s) ret(%d)\n", __FUNCTION__,
+		printk(KERN_WARNING "%s: pnp_activate_dev(%s) ret(%d)\n", __func__,
 			(char *)dev_id->driver_data, retval);
 		goto err_free;
 	}
@@ -974,6 +974,8 @@ static struct pnp_driver fcpnp_driver = {
 	.remove		= __devexit_p(fcpnp_remove),
 	.id_table	= fcpnp_ids,
 };
+#else
+static struct pnp_driver fcpnp_driver;
 #endif
 
 static void __devexit fcpci_remove(struct pci_dev *pdev)
@@ -1001,7 +1003,7 @@ static int __init hisax_fcpcipnp_init(void)
 	retval = pci_register_driver(&fcpci_driver);
 	if (retval)
 		return retval;
-#ifdef __ISAPNP__
+#ifdef CONFIG_PNP
 	retval = pnp_register_driver(&fcpnp_driver);
 	if (retval < 0) {
 		pci_unregister_driver(&fcpci_driver);
@@ -1013,7 +1015,7 @@ static int __init hisax_fcpcipnp_init(void)
 
 static void __exit hisax_fcpcipnp_exit(void)
 {
-#ifdef __ISAPNP__
+#ifdef CONFIG_PNP
 	pnp_unregister_driver(&fcpnp_driver);
 #endif
 	pci_unregister_driver(&fcpci_driver);
diff --git a/trunk/drivers/isdn/hisax/ix1_micro.c b/trunk/drivers/isdn/hisax/ix1_micro.c
index 2d18d4f1e57e..a92bf0d2cab2 100644
--- a/trunk/drivers/isdn/hisax/ix1_micro.c
+++ b/trunk/drivers/isdn/hisax/ix1_micro.c
@@ -252,7 +252,7 @@ setup_ix1micro(struct IsdnCard *card)
 					err = pnp_activate_dev(pnp_d);
 					if (err<0) {
 						printk(KERN_WARNING "%s: pnp_activate_dev ret(%d)\n",
-							__FUNCTION__, err);
+							__func__, err);
 						return(0);
 					}
 					card->para[1] = pnp_port_start(pnp_d, 0);
diff --git a/trunk/drivers/isdn/hisax/niccy.c b/trunk/drivers/isdn/hisax/niccy.c
index 421b8e6763d7..ef00633e1d2a 100644
--- a/trunk/drivers/isdn/hisax/niccy.c
+++ b/trunk/drivers/isdn/hisax/niccy.c
@@ -255,7 +255,7 @@ int __devinit setup_niccy(struct IsdnCard *card)
 			err = pnp_activate_dev(pnp_d);
 			if (err < 0) {
 				printk(KERN_WARNING "%s: pnp_activate_dev "
-					"ret(%d)\n", __FUNCTION__, err);
+					"ret(%d)\n", __func__, err);
 				return 0;
 			}
 			card->para[1] = pnp_port_start(pnp_d, 0);
diff --git a/trunk/drivers/isdn/hisax/sedlbauer.c b/trunk/drivers/isdn/hisax/sedlbauer.c
index 95425f3d2220..a10dfa82c734 100644
--- a/trunk/drivers/isdn/hisax/sedlbauer.c
+++ b/trunk/drivers/isdn/hisax/sedlbauer.c
@@ -555,7 +555,7 @@ setup_sedlbauer_isapnp(struct IsdnCard *card, int *bytecnt)
 				err = pnp_activate_dev(pnp_d);
 				if (err<0) {
 					printk(KERN_WARNING "%s: pnp_activate_dev ret(%d)\n",
-						__FUNCTION__, err);
+						__func__, err);
 					return(0);
 				}
 				card->para[1] = pnp_port_start(pnp_d, 0);
diff --git a/trunk/drivers/isdn/hisax/st5481.h b/trunk/drivers/isdn/hisax/st5481.h
index 04416bad611d..2044e7173ab4 100644
--- a/trunk/drivers/isdn/hisax/st5481.h
+++ b/trunk/drivers/isdn/hisax/st5481.h
@@ -218,13 +218,13 @@ enum {
 #define L1_EVENT_COUNT (EV_TIMER3 + 1)
 
 #define ERR(format, arg...) \
-printk(KERN_ERR "%s:%s: " format "\n" , __FILE__,  __FUNCTION__ , ## arg)
+printk(KERN_ERR "%s:%s: " format "\n" , __FILE__,  __func__ , ## arg)
 
 #define WARN(format, arg...) \
-printk(KERN_WARNING "%s:%s: " format "\n" , __FILE__,  __FUNCTION__ , ## arg)
+printk(KERN_WARNING "%s:%s: " format "\n" , __FILE__,  __func__ , ## arg)
 
 #define INFO(format, arg...) \
-printk(KERN_INFO "%s:%s: " format "\n" , __FILE__,  __FUNCTION__ , ## arg)
+printk(KERN_INFO "%s:%s: " format "\n" , __FILE__,  __func__ , ## arg)
 
 #include "isdnhdlc.h"
 #include "fsm.h"
@@ -406,7 +406,7 @@ struct st5481_adapter {
 
 /*
  * Submit an URB with error reporting. This is a macro so
- * the __FUNCTION__ returns the caller function name.
+ * the __func__ returns the caller function name.
  */
 #define SUBMIT_URB(urb, mem_flags) \
 ({ \
@@ -470,7 +470,7 @@ extern int st5481_debug;
 #ifdef CONFIG_HISAX_DEBUG
 
 #define DBG_ISO_PACKET(level,urb) \
-  if (level & __debug_variable) dump_iso_packet(__FUNCTION__,urb)
+  if (level & __debug_variable) dump_iso_packet(__func__,urb)
 
 static void __attribute__((unused))
 dump_iso_packet(const char *name, struct urb *urb)
diff --git a/trunk/drivers/isdn/hisax/st5481_usb.c b/trunk/drivers/isdn/hisax/st5481_usb.c
index 4ada66b8b679..427a8b0520f5 100644
--- a/trunk/drivers/isdn/hisax/st5481_usb.c
+++ b/trunk/drivers/isdn/hisax/st5481_usb.c
@@ -342,7 +342,7 @@ void st5481_release_usb(struct st5481_adapter *adapter)
 	usb_kill_urb(intr->urb);
 	kfree(intr->urb->transfer_buffer);
 	usb_free_urb(intr->urb);
-	ctrl->urb = NULL;
+	intr->urb = NULL;
 }
 
 /*
diff --git a/trunk/drivers/isdn/hisax/teles3.c b/trunk/drivers/isdn/hisax/teles3.c
index 6a5e379e0774..5dc9f1a43629 100644
--- a/trunk/drivers/isdn/hisax/teles3.c
+++ b/trunk/drivers/isdn/hisax/teles3.c
@@ -301,7 +301,7 @@ setup_teles3(struct IsdnCard *card)
 					err = pnp_activate_dev(pnp_d);
 					if (err<0) {
 						printk(KERN_WARNING "%s: pnp_activate_dev ret(%d)\n",
-							__FUNCTION__, err);
+							__func__, err);
 						return(0);
 					}
 					card->para[3] = pnp_port_start(pnp_d, 2);
diff --git a/trunk/drivers/isdn/hysdn/hysdn_procconf.c b/trunk/drivers/isdn/hysdn/hysdn_procconf.c
index 27d890b48f88..877be9922c3d 100644
--- a/trunk/drivers/isdn/hysdn/hysdn_procconf.c
+++ b/trunk/drivers/isdn/hysdn/hysdn_procconf.c
@@ -370,6 +370,7 @@ hysdn_conf_close(struct inode *ino, struct file *filep)
 /******************************************************/
 static const struct file_operations conf_fops =
 {
+	.owner		= THIS_MODULE,
 	.llseek         = no_llseek,
 	.read           = hysdn_conf_read,
 	.write          = hysdn_conf_write,
@@ -402,11 +403,9 @@ hysdn_procconf_init(void)
 	while (card) {
 
 		sprintf(conf_name, "%s%d", PROC_CONF_BASENAME, card->myid);
-		if ((card->procconf = (void *) create_proc_entry(conf_name,
-					     S_IFREG | S_IRUGO | S_IWUSR,
-					    hysdn_proc_entry)) != NULL) {
-			((struct proc_dir_entry *) card->procconf)->proc_fops = &conf_fops;
-			((struct proc_dir_entry *) card->procconf)->owner = THIS_MODULE;
+		if ((card->procconf = (void *) proc_create(conf_name,
+						S_IFREG | S_IRUGO | S_IWUSR,
+						hysdn_proc_entry)) != NULL) {
 			hysdn_proclog_init(card);	/* init the log file entry */
 		}
 		card = card->next;	/* next entry */
diff --git a/trunk/drivers/isdn/hysdn/hysdn_proclog.c b/trunk/drivers/isdn/hysdn/hysdn_proclog.c
index 27b3991fb0ec..8991d2c8ee4a 100644
--- a/trunk/drivers/isdn/hysdn/hysdn_proclog.c
+++ b/trunk/drivers/isdn/hysdn/hysdn_proclog.c
@@ -380,6 +380,7 @@ hysdn_log_poll(struct file *file, poll_table * wait)
 /**************************************************/
 static const struct file_operations log_fops =
 {
+	.owner		= THIS_MODULE,
 	.llseek         = no_llseek,
 	.read           = hysdn_log_read,
 	.write          = hysdn_log_write,
@@ -402,10 +403,9 @@ hysdn_proclog_init(hysdn_card * card)
 
 	if ((pd = kzalloc(sizeof(struct procdata), GFP_KERNEL)) != NULL) {
 		sprintf(pd->log_name, "%s%d", PROC_LOG_BASENAME, card->myid);
-		if ((pd->log = create_proc_entry(pd->log_name, S_IFREG | S_IRUGO | S_IWUSR, hysdn_proc_entry)) != NULL) {
-		        pd->log->proc_fops = &log_fops; 
-		        pd->log->owner = THIS_MODULE;
-		}
+		pd->log = proc_create(pd->log_name,
+				S_IFREG | S_IRUGO | S_IWUSR, hysdn_proc_entry,
+				&log_fops);
 
 		init_waitqueue_head(&(pd->rd_queue));
 
diff --git a/trunk/drivers/isdn/i4l/isdn_common.c b/trunk/drivers/isdn/i4l/isdn_common.c
index d4ad6992f776..0f3c66de69bc 100644
--- a/trunk/drivers/isdn/i4l/isdn_common.c
+++ b/trunk/drivers/isdn/i4l/isdn_common.c
@@ -1924,7 +1924,7 @@ isdn_free_channel(int di, int ch, int usage)
 
 	if ((di < 0) || (ch < 0)) {
 		printk(KERN_WARNING "%s: called with invalid drv(%d) or channel(%d)\n",
-			__FUNCTION__, di, ch);
+			__func__, di, ch);
 		return;
 	}
 	for (i = 0; i < ISDN_MAX_CHANNELS; i++)
diff --git a/trunk/drivers/isdn/i4l/isdn_net.h b/trunk/drivers/isdn/i4l/isdn_net.h
index bc2f0dd962ea..be4949715d55 100644
--- a/trunk/drivers/isdn/i4l/isdn_net.h
+++ b/trunk/drivers/isdn/i4l/isdn_net.h
@@ -108,7 +108,7 @@ static __inline__ void isdn_net_add_to_bundle(isdn_net_dev *nd, isdn_net_local *
 
 	lp = nd->queue;
 //	printk(KERN_DEBUG "%s: lp:%s(%p) nlp:%s(%p) last(%p)\n",
-//		__FUNCTION__, lp->name, lp, nlp->name, nlp, lp->last);
+//		__func__, lp->name, lp, nlp->name, nlp, lp->last);
 	nlp->last = lp->last;
 	lp->last->next = nlp;
 	lp->last = nlp;
@@ -129,7 +129,7 @@ static __inline__ void isdn_net_rm_from_bundle(isdn_net_local *lp)
 		master_lp = (isdn_net_local *) lp->master->priv;
 
 //	printk(KERN_DEBUG "%s: lp:%s(%p) mlp:%s(%p) last(%p) next(%p) mndq(%p)\n",
-//		__FUNCTION__, lp->name, lp, master_lp->name, master_lp, lp->last, lp->next, master_lp->netdev->queue);
+//		__func__, lp->name, lp, master_lp->name, master_lp, lp->last, lp->next, master_lp->netdev->queue);
 	spin_lock_irqsave(&master_lp->netdev->queue_lock, flags);
 	lp->last->next = lp->next;
 	lp->next->last = lp->last;
@@ -141,7 +141,7 @@ static __inline__ void isdn_net_rm_from_bundle(isdn_net_local *lp)
 	}
 	lp->next = lp->last = lp;	/* (re)set own pointers */
 //	printk(KERN_DEBUG "%s: mndq(%p)\n",
-//		__FUNCTION__, master_lp->netdev->queue);
+//		__func__, master_lp->netdev->queue);
 	spin_unlock_irqrestore(&master_lp->netdev->queue_lock, flags);
 }
 
diff --git a/trunk/drivers/isdn/i4l/isdn_ppp.c b/trunk/drivers/isdn/i4l/isdn_ppp.c
index 9f5fe372f83d..127cfdad68e7 100644
--- a/trunk/drivers/isdn/i4l/isdn_ppp.c
+++ b/trunk/drivers/isdn/i4l/isdn_ppp.c
@@ -110,7 +110,7 @@ isdn_ppp_free(isdn_net_local * lp)
 
 	if (lp->ppp_slot < 0 || lp->ppp_slot >= ISDN_MAX_CHANNELS) {
 		printk(KERN_ERR "%s: ppp_slot(%d) out of range\n",
-			__FUNCTION__, lp->ppp_slot);
+			__func__, lp->ppp_slot);
 		return 0;
 	}
 
@@ -127,7 +127,7 @@ isdn_ppp_free(isdn_net_local * lp)
 #endif /* CONFIG_ISDN_MPP */
 	if (lp->ppp_slot < 0 || lp->ppp_slot >= ISDN_MAX_CHANNELS) {
 		printk(KERN_ERR "%s: ppp_slot(%d) now invalid\n",
-			__FUNCTION__, lp->ppp_slot);
+			__func__, lp->ppp_slot);
 		return 0;
 	}
 	is = ippp_table[lp->ppp_slot];
@@ -226,7 +226,7 @@ isdn_ppp_wakeup_daemon(isdn_net_local * lp)
 {
 	if (lp->ppp_slot < 0 || lp->ppp_slot >= ISDN_MAX_CHANNELS) {
 		printk(KERN_ERR "%s: ppp_slot(%d) out of range\n",
-			__FUNCTION__, lp->ppp_slot);
+			__func__, lp->ppp_slot);
 		return;
 	}
 	ippp_table[lp->ppp_slot]->state = IPPP_OPEN | IPPP_CONNECT | IPPP_NOBLOCK;
@@ -245,7 +245,7 @@ isdn_ppp_closewait(int slot)
 
 	if (slot < 0 || slot >= ISDN_MAX_CHANNELS) {
 		printk(KERN_ERR "%s: slot(%d) out of range\n",
-			__FUNCTION__, slot);
+			__func__, slot);
 		return 0;
 	}
 	is = ippp_table[slot];
@@ -343,7 +343,7 @@ isdn_ppp_release(int min, struct file *file)
 	is = file->private_data;
 
 	if (!is) {
-		printk(KERN_ERR "%s: no file->private_data\n", __FUNCTION__);
+		printk(KERN_ERR "%s: no file->private_data\n", __func__);
 		return;
 	}
 	if (is->debug & 0x1)
@@ -353,7 +353,7 @@ isdn_ppp_release(int min, struct file *file)
 		isdn_net_dev *p = is->lp->netdev;
 
 		if (!p) {
-			printk(KERN_ERR "%s: no lp->netdev\n", __FUNCTION__);
+			printk(KERN_ERR "%s: no lp->netdev\n", __func__);
 			return;
 		}
 		is->state &= ~IPPP_CONNECT;	/* -> effect: no call of wakeup */
@@ -1080,7 +1080,7 @@ isdn_ppp_push_higher(isdn_net_dev * net_dev, isdn_net_local * lp, struct sk_buff
 				printk(KERN_DEBUG "isdn_ppp: VJC_UNCOMP\n");
 			if (net_dev->local->ppp_slot < 0) {
 				printk(KERN_ERR "%s: net_dev->local->ppp_slot(%d) out of range\n",
-					__FUNCTION__, net_dev->local->ppp_slot);
+					__func__, net_dev->local->ppp_slot);
 				goto drop_packet;
 			}
 			if (slhc_remember(ippp_table[net_dev->local->ppp_slot]->slcomp, skb->data, skb->len) <= 0) {
@@ -1107,7 +1107,7 @@ isdn_ppp_push_higher(isdn_net_dev * net_dev, isdn_net_local * lp, struct sk_buff
 							  skb_old->len);
 				if (net_dev->local->ppp_slot < 0) {
 					printk(KERN_ERR "%s: net_dev->local->ppp_slot(%d) out of range\n",
-						__FUNCTION__, net_dev->local->ppp_slot);
+						__func__, net_dev->local->ppp_slot);
 					goto drop_packet;
 				}
 				pkt_len = slhc_uncompress(ippp_table[net_dev->local->ppp_slot]->slcomp,
@@ -1553,7 +1553,7 @@ static int isdn_ppp_mp_init( isdn_net_local * lp, ippp_bundle * add_to )
 
 	if (lp->ppp_slot < 0) {
 		printk(KERN_ERR "%s: lp->ppp_slot(%d) out of range\n",
-			__FUNCTION__, lp->ppp_slot);
+			__func__, lp->ppp_slot);
 		return(-EINVAL);
 	}
 
@@ -1604,7 +1604,7 @@ static void isdn_ppp_mp_receive(isdn_net_dev * net_dev, isdn_net_local * lp,
 	slot = lp->ppp_slot;
 	if (slot < 0 || slot >= ISDN_MAX_CHANNELS) {
 		printk(KERN_ERR "%s: lp->ppp_slot(%d)\n",
-			__FUNCTION__, lp->ppp_slot);
+			__func__, lp->ppp_slot);
 		stats->frame_drops++;
 		dev_kfree_skb(skb);
 		spin_unlock_irqrestore(&mp->lock, flags);
@@ -1641,7 +1641,7 @@ static void isdn_ppp_mp_receive(isdn_net_dev * net_dev, isdn_net_local * lp,
 		slot = lpq->ppp_slot;
 		if (slot < 0 || slot >= ISDN_MAX_CHANNELS) {
 			printk(KERN_ERR "%s: lpq->ppp_slot(%d)\n",
-				__FUNCTION__, lpq->ppp_slot);
+				__func__, lpq->ppp_slot);
 		} else {
 			u32 lls = ippp_table[slot]->last_link_seqno;
 			if (MP_LT(lls, minseq))
@@ -1875,7 +1875,7 @@ void isdn_ppp_mp_reassembly( isdn_net_dev * net_dev, isdn_net_local * lp,
 
 	if (lp->ppp_slot < 0 || lp->ppp_slot >= ISDN_MAX_CHANNELS) {
 		printk(KERN_ERR "%s: lp->ppp_slot(%d) out of range\n",
-			__FUNCTION__, lp->ppp_slot);
+			__func__, lp->ppp_slot);
 		return;
 	}
 	if( MP_FLAGS(from) == (MP_BEGIN_FRAG | MP_END_FRAG) ) {
@@ -2655,7 +2655,7 @@ static void isdn_ppp_receive_ccp(isdn_net_dev *net_dev, isdn_net_local *lp,
 		lp->ppp_slot);
 	if (lp->ppp_slot < 0 || lp->ppp_slot >= ISDN_MAX_CHANNELS) {
 		printk(KERN_ERR "%s: lp->ppp_slot(%d) out of range\n",
-			__FUNCTION__, lp->ppp_slot);
+			__func__, lp->ppp_slot);
 		return;
 	}
 	is = ippp_table[lp->ppp_slot];
@@ -2665,7 +2665,7 @@ static void isdn_ppp_receive_ccp(isdn_net_dev *net_dev, isdn_net_local *lp,
 		int slot = ((isdn_net_local *) (lp->master->priv))->ppp_slot;
 		if (slot < 0 || slot >= ISDN_MAX_CHANNELS) {
 			printk(KERN_ERR "%s: slot(%d) out of range\n",
-				__FUNCTION__, slot);
+				__func__, slot);
 			return;
 		}	
 		mis = ippp_table[slot];
@@ -2829,7 +2829,7 @@ static void isdn_ppp_send_ccp(isdn_net_dev *net_dev, isdn_net_local *lp, struct
 		return;
 	if (slot < 0 || slot >= ISDN_MAX_CHANNELS) {
 		printk(KERN_ERR "%s: lp->ppp_slot(%d) out of range\n",
-			__FUNCTION__, slot);
+			__func__, slot);
 		return;
 	}	
 	is = ippp_table[slot];
@@ -2852,7 +2852,7 @@ static void isdn_ppp_send_ccp(isdn_net_dev *net_dev, isdn_net_local *lp, struct
 		slot = ((isdn_net_local *) (lp->master->priv))->ppp_slot;
 		if (slot < 0 || slot >= ISDN_MAX_CHANNELS) {
 			printk(KERN_ERR "%s: slot(%d) out of range\n",
-				__FUNCTION__, slot);
+				__func__, slot);
 			return;
 		}	
 		mis = ippp_table[slot];
diff --git a/trunk/drivers/isdn/i4l/isdn_tty.c b/trunk/drivers/isdn/i4l/isdn_tty.c
index 133eb18e65cc..8af0df1d5b8c 100644
--- a/trunk/drivers/isdn/i4l/isdn_tty.c
+++ b/trunk/drivers/isdn/i4l/isdn_tty.c
@@ -1347,7 +1347,7 @@ isdn_tty_tiocmget(struct tty_struct *tty, struct file *file)
 	modem_info *info = (modem_info *) tty->driver_data;
 	u_char control, status;
 
-	if (isdn_tty_paranoia_check(info, tty->name, __FUNCTION__))
+	if (isdn_tty_paranoia_check(info, tty->name, __func__))
 		return -ENODEV;
 	if (tty->flags & (1 << TTY_IO_ERROR))
 		return -EIO;
@@ -1372,7 +1372,7 @@ isdn_tty_tiocmset(struct tty_struct *tty, struct file *file,
 {
 	modem_info *info = (modem_info *) tty->driver_data;
 
-	if (isdn_tty_paranoia_check(info, tty->name, __FUNCTION__))
+	if (isdn_tty_paranoia_check(info, tty->name, __func__))
 		return -ENODEV;
 	if (tty->flags & (1 << TTY_IO_ERROR))
 		return -EIO;
@@ -1608,7 +1608,7 @@ isdn_tty_open(struct tty_struct *tty, struct file *filp)
 	if (isdn_tty_paranoia_check(info, tty->name, "isdn_tty_open"))
 		return -ENODEV;
 	if (!try_module_get(info->owner)) {
-		printk(KERN_WARNING "%s: cannot reserve module\n", __FUNCTION__);
+		printk(KERN_WARNING "%s: cannot reserve module\n", __func__);
 		return -ENODEV;
 	}
 #ifdef ISDN_DEBUG_MODEM_OPEN
diff --git a/trunk/drivers/leds/led-class.c b/trunk/drivers/leds/led-class.c
index ac05a928f764..b3c54be74556 100644
--- a/trunk/drivers/leds/led-class.c
+++ b/trunk/drivers/leds/led-class.c
@@ -105,7 +105,7 @@ int led_classdev_register(struct device *parent, struct led_classdev *led_cdev)
 
 	led_cdev->dev = device_create(leds_class, parent, 0, "%s",
 					    led_cdev->name);
-	if (unlikely(IS_ERR(led_cdev->dev)))
+	if (IS_ERR(led_cdev->dev))
 		return PTR_ERR(led_cdev->dev);
 
 	dev_set_drvdata(led_cdev->dev, led_cdev);
diff --git a/trunk/drivers/macintosh/Kconfig b/trunk/drivers/macintosh/Kconfig
index 77f50b63a970..b52659620d50 100644
--- a/trunk/drivers/macintosh/Kconfig
+++ b/trunk/drivers/macintosh/Kconfig
@@ -234,6 +234,14 @@ config WINDFARM_PM112
 	  which are the recent dual and quad G5 machines using the
 	  970MP dual-core processor.
 
+config WINDFARM_PM121
+	tristate "Support for thermal management on PowerMac12,1"
+	depends on WINDFARM && I2C && PMAC_SMU
+	select I2C_POWERMAC
+	help
+	  This driver provides thermal control for the PowerMac12,1
+	  which is the iMac G5 (iSight).
+
 config ANSLCD
 	tristate "Support for ANS LCD display"
 	depends on ADB_CUDA && PPC_PMAC
diff --git a/trunk/drivers/macintosh/Makefile b/trunk/drivers/macintosh/Makefile
index 2dfc3f4eaf42..e3132efa17c0 100644
--- a/trunk/drivers/macintosh/Makefile
+++ b/trunk/drivers/macintosh/Makefile
@@ -42,4 +42,9 @@ obj-$(CONFIG_WINDFARM_PM112)	+= windfarm_pm112.o windfarm_smu_sat.o \
 				   windfarm_smu_sensors.o \
 				   windfarm_max6690_sensor.o \
 				   windfarm_lm75_sensor.o windfarm_pid.o
+obj-$(CONFIG_WINDFARM_PM121)	+= windfarm_pm121.o windfarm_smu_sat.o \
+				   windfarm_smu_controls.o \
+				   windfarm_smu_sensors.o \
+				   windfarm_max6690_sensor.o \
+				   windfarm_lm75_sensor.o windfarm_pid.o
 obj-$(CONFIG_PMAC_RACKMETER)	+= rack-meter.o
diff --git a/trunk/drivers/macintosh/windfarm_lm75_sensor.c b/trunk/drivers/macintosh/windfarm_lm75_sensor.c
index 7e10c3ab4d50..b92b959fe16e 100644
--- a/trunk/drivers/macintosh/windfarm_lm75_sensor.c
+++ b/trunk/drivers/macintosh/windfarm_lm75_sensor.c
@@ -127,6 +127,12 @@ static struct wf_lm75_sensor *wf_lm75_create(struct i2c_adapter *adapter,
 	 */
 	if (!strcmp(loc, "Hard drive") || !strcmp(loc, "DRIVE BAY"))
 		lm->sens.name = "hd-temp";
+	else if (!strcmp(loc, "Incoming Air Temp"))
+		lm->sens.name = "incoming-air-temp";
+	else if (!strcmp(loc, "ODD Temp"))
+		lm->sens.name = "optical-drive-temp";
+	else if (!strcmp(loc, "HD Temp"))
+		lm->sens.name = "hard-drive-temp";
 	else
 		goto fail;
 
diff --git a/trunk/drivers/macintosh/windfarm_max6690_sensor.c b/trunk/drivers/macintosh/windfarm_max6690_sensor.c
index 5f03aab9fb5d..e207a90d6b27 100644
--- a/trunk/drivers/macintosh/windfarm_max6690_sensor.c
+++ b/trunk/drivers/macintosh/windfarm_max6690_sensor.c
@@ -77,18 +77,28 @@ static struct wf_sensor_ops wf_max6690_ops = {
 	.owner		= THIS_MODULE,
 };
 
-static void wf_max6690_create(struct i2c_adapter *adapter, u8 addr)
+static void wf_max6690_create(struct i2c_adapter *adapter, u8 addr,
+			      const char *loc)
 {
 	struct wf_6690_sensor *max;
-	char *name = "backside-temp";
+	char *name;
 
 	max = kzalloc(sizeof(struct wf_6690_sensor), GFP_KERNEL);
 	if (max == NULL) {
 		printk(KERN_ERR "windfarm: Couldn't create MAX6690 sensor %s: "
-		       "no memory\n", name);
+		       "no memory\n", loc);
 		return;
 	}
 
+	if (!strcmp(loc, "BACKSIDE"))
+		name = "backside-temp";
+	else if (!strcmp(loc, "NB Ambient"))
+		name = "north-bridge-temp";
+	else if (!strcmp(loc, "GPU Ambient"))
+		name = "gpu-temp";
+	else
+		goto fail;
+
 	max->sens.ops = &wf_max6690_ops;
 	max->sens.name = name;
 	max->i2c.addr = addr >> 1;
@@ -138,9 +148,7 @@ static int wf_max6690_attach(struct i2c_adapter *adapter)
 		if (loc == NULL || addr == 0)
 			continue;
 		printk("found max6690, loc=%s addr=0x%02x\n", loc, addr);
-		if (strcmp(loc, "BACKSIDE"))
-			continue;
-		wf_max6690_create(adapter, addr);
+		wf_max6690_create(adapter, addr, loc);
 	}
 
 	return 0;
diff --git a/trunk/drivers/macintosh/windfarm_pm121.c b/trunk/drivers/macintosh/windfarm_pm121.c
new file mode 100644
index 000000000000..66ec4fb115bb
--- /dev/null
+++ b/trunk/drivers/macintosh/windfarm_pm121.c
@@ -0,0 +1,1040 @@
+/*
+ * Windfarm PowerMac thermal control. iMac G5 iSight
+ *
+ * (c) Copyright 2007 Étienne Bersac <bersace@gmail.com>
+ *
+ * Bits & pieces from windfarm_pm81.c by (c) Copyright 2005 Benjamin
+ * Herrenschmidt, IBM Corp. <benh@kernel.crashing.org>
+ *
+ * Released under the term of the GNU GPL v2.
+ *
+ *
+ *
+ * PowerMac12,1
+ * ============
+ *
+ *
+ * The algorithm used is the PID control algorithm, used the same way
+ * the published Darwin code does, using the same values that are
+ * present in the Darwin 8.10 snapshot property lists (note however
+ * that none of the code has been re-used, it's a complete
+ * re-implementation
+ *
+ * There is two models using PowerMac12,1. Model 2 is iMac G5 iSight
+ * 17" while Model 3 is iMac G5 20". They do have both the same
+ * controls with a tiny difference. The control-ids of hard-drive-fan
+ * and cpu-fan is swapped.
+ *
+ *
+ * Target Correction :
+ *
+ * controls have a target correction calculated as :
+ *
+ * new_min = ((((average_power * slope) >> 16) + offset) >> 16) + min_value
+ * new_value = max(new_value, max(new_min, 0))
+ *
+ * OD Fan control correction.
+ *
+ * # model_id: 2
+ *   offset		: -19563152
+ *   slope		:  1956315
+ *
+ * # model_id: 3
+ *   offset		: -15650652
+ *   slope		:  1565065
+ *
+ * HD Fan control correction.
+ *
+ * # model_id: 2
+ *   offset		: -15650652
+ *   slope		:  1565065
+ *
+ * # model_id: 3
+ *   offset		: -19563152
+ *   slope		:  1956315
+ *
+ * CPU Fan control correction.
+ *
+ * # model_id: 2
+ *   offset		: -25431900
+ *   slope		:  2543190
+ *
+ * # model_id: 3
+ *   offset		: -15650652
+ *   slope		:  1565065
+ *
+ *
+ * Target rubber-banding :
+ *
+ * Some controls have a target correction which depends on another
+ * control value. The correction is computed in the following way :
+ *
+ * new_min = ref_value * slope + offset
+ *
+ * ref_value is the value of the reference control. If new_min is
+ * greater than 0, then we correct the target value using :
+ *
+ * new_target = max (new_target, new_min >> 16)
+ *
+ *
+ * # model_id : 2
+ *   control	: cpu-fan
+ *   ref	: optical-drive-fan
+ *   offset	: -15650652
+ *   slope	: 1565065
+ *
+ * # model_id : 3
+ *   control	: optical-drive-fan
+ *   ref	: hard-drive-fan
+ *   offset	: -32768000
+ *   slope	: 65536
+ *
+ *
+ * In order to have the moste efficient correction with those
+ * dependencies, we must trigger HD loop before OD loop before CPU
+ * loop.
+ *
+ *
+ * The various control loops found in Darwin config file are:
+ *
+ * HD Fan control loop.
+ *
+ * # model_id: 2
+ *   control        : hard-drive-fan
+ *   sensor         : hard-drive-temp
+ *   PID params     : G_d = 0x00000000
+ *                    G_p = 0x002D70A3
+ *                    G_r = 0x00019999
+ *                    History = 2 entries
+ *                    Input target = 0x370000
+ *                    Interval = 5s
+ *
+ * # model_id: 3
+ *   control        : hard-drive-fan
+ *   sensor         : hard-drive-temp
+ *   PID params     : G_d = 0x00000000
+ *                    G_p = 0x002170A3
+ *                    G_r = 0x00019999
+ *                    History = 2 entries
+ *                    Input target = 0x370000
+ *                    Interval = 5s
+ *
+ * OD Fan control loop.
+ *
+ * # model_id: 2
+ *   control        : optical-drive-fan
+ *   sensor         : optical-drive-temp
+ *   PID params     : G_d = 0x00000000
+ *                    G_p = 0x001FAE14
+ *                    G_r = 0x00019999
+ *                    History = 2 entries
+ *                    Input target = 0x320000
+ *                    Interval = 5s
+ *
+ * # model_id: 3
+ *   control        : optical-drive-fan
+ *   sensor         : optical-drive-temp
+ *   PID params     : G_d = 0x00000000
+ *                    G_p = 0x001FAE14
+ *                    G_r = 0x00019999
+ *                    History = 2 entries
+ *                    Input target = 0x320000
+ *                    Interval = 5s
+ *
+ * GPU Fan control loop.
+ *
+ * # model_id: 2
+ *   control        : hard-drive-fan
+ *   sensor         : gpu-temp
+ *   PID params     : G_d = 0x00000000
+ *                    G_p = 0x002A6666
+ *                    G_r = 0x00019999
+ *                    History = 2 entries
+ *                    Input target = 0x5A0000
+ *                    Interval = 5s
+ *
+ * # model_id: 3
+ *   control        : cpu-fan
+ *   sensor         : gpu-temp
+ *   PID params     : G_d = 0x00000000
+ *                    G_p = 0x0010CCCC
+ *                    G_r = 0x00019999
+ *                    History = 2 entries
+ *                    Input target = 0x500000
+ *                    Interval = 5s
+ *
+ * KODIAK (aka northbridge) Fan control loop.
+ *
+ * # model_id: 2
+ *   control        : optical-drive-fan
+ *   sensor         : north-bridge-temp
+ *   PID params     : G_d = 0x00000000
+ *                    G_p = 0x003BD70A
+ *                    G_r = 0x00019999
+ *                    History = 2 entries
+ *                    Input target = 0x550000
+ *                    Interval = 5s
+ *
+ * # model_id: 3
+ *   control        : hard-drive-fan
+ *   sensor         : north-bridge-temp
+ *   PID params     : G_d = 0x00000000
+ *                    G_p = 0x0030F5C2
+ *                    G_r = 0x00019999
+ *                    History = 2 entries
+ *                    Input target = 0x550000
+ *                    Interval = 5s
+ *
+ * CPU Fan control loop.
+ *
+ *   control        : cpu-fan
+ *   sensors        : cpu-temp, cpu-power
+ *   PID params     : from SDB partition
+ *
+ *
+ * CPU Slew control loop.
+ *
+ *   control        : cpufreq-clamp
+ *   sensor         : cpu-temp
+ *
+ */
+
+#undef	DEBUG
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+#include <linux/kmod.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <asm/prom.h>
+#include <asm/machdep.h>
+#include <asm/io.h>
+#include <asm/system.h>
+#include <asm/sections.h>
+#include <asm/smu.h>
+
+#include "windfarm.h"
+#include "windfarm_pid.h"
+
+#define VERSION "0.3"
+
+static int pm121_mach_model;	/* machine model id */
+
+/* Controls & sensors */
+static struct wf_sensor	*sensor_cpu_power;
+static struct wf_sensor	*sensor_cpu_temp;
+static struct wf_sensor	*sensor_cpu_voltage;
+static struct wf_sensor	*sensor_cpu_current;
+static struct wf_sensor	*sensor_gpu_temp;
+static struct wf_sensor	*sensor_north_bridge_temp;
+static struct wf_sensor	*sensor_hard_drive_temp;
+static struct wf_sensor	*sensor_optical_drive_temp;
+static struct wf_sensor	*sensor_incoming_air_temp; /* unused ! */
+
+enum {
+	FAN_CPU,
+	FAN_HD,
+	FAN_OD,
+	CPUFREQ,
+	N_CONTROLS
+};
+static struct wf_control *controls[N_CONTROLS] = {};
+
+/* Set to kick the control loop into life */
+static int pm121_all_controls_ok, pm121_all_sensors_ok, pm121_started;
+
+enum {
+	FAILURE_FAN		= 1 << 0,
+	FAILURE_SENSOR		= 1 << 1,
+	FAILURE_OVERTEMP	= 1 << 2
+};
+
+/* All sys loops. Note the HD before the OD loop in order to have it
+   run before. */
+enum {
+	LOOP_GPU,		/* control = hd or cpu, but luckily,
+				   it doesn't matter */
+	LOOP_HD,		/* control = hd */
+	LOOP_KODIAK,		/* control = hd or od */
+	LOOP_OD,		/* control = od */
+	N_LOOPS
+};
+
+static const char *loop_names[N_LOOPS] = {
+	"GPU",
+	"HD",
+	"KODIAK",
+	"OD",
+};
+
+#define	PM121_NUM_CONFIGS	2
+
+static unsigned int pm121_failure_state;
+static int pm121_readjust, pm121_skipping;
+static s32 average_power;
+
+struct pm121_correction {
+	int	offset;
+	int	slope;
+};
+
+static struct pm121_correction corrections[N_CONTROLS][PM121_NUM_CONFIGS] = {
+	/* FAN_OD */
+	{
+		/* MODEL 2 */
+		{ .offset	= -19563152,
+		  .slope	=  1956315
+		},
+		/* MODEL 3 */
+		{ .offset	= -15650652,
+		  .slope	=  1565065
+		},
+	},
+	/* FAN_HD */
+	{
+		/* MODEL 2 */
+		{ .offset	= -15650652,
+		  .slope	=  1565065
+		},
+		/* MODEL 3 */
+		{ .offset	= -19563152,
+		  .slope	=  1956315
+		},
+	},
+	/* FAN_CPU */
+	{
+		/* MODEL 2 */
+		{ .offset	= -25431900,
+		  .slope	=  2543190
+		},
+		/* MODEL 3 */
+		{ .offset	= -15650652,
+		  .slope	=  1565065
+		},
+	},
+	/* CPUFREQ has no correction (and is not implemented at all) */
+};
+
+struct pm121_connection {
+	unsigned int	control_id;
+	unsigned int	ref_id;
+	struct pm121_correction	correction;
+};
+
+static struct pm121_connection pm121_connections[] = {
+	/* MODEL 2 */
+	{ .control_id	= FAN_CPU,
+	  .ref_id	= FAN_OD,
+	  { .offset	= -32768000,
+	    .slope	=  65536
+	  }
+	},
+	/* MODEL 3 */
+	{ .control_id	= FAN_OD,
+	  .ref_id	= FAN_HD,
+	  { .offset	= -32768000,
+	    .slope	=  65536
+	  }
+	},
+};
+
+/* pointer to the current model connection */
+static struct pm121_connection *pm121_connection;
+
+/*
+ * ****** System Fans Control Loop ******
+ *
+ */
+
+/* Since each loop handles only one control and we want to avoid
+ * writing virtual control, we store the control correction with the
+ * loop params. Some data are not set, there are common to all loop
+ * and thus, hardcoded.
+ */
+struct pm121_sys_param {
+	/* purely informative since we use mach_model-2 as index */
+	int			model_id;
+	struct wf_sensor	**sensor; /* use sensor_id instead ? */
+	s32			gp, itarget;
+	unsigned int		control_id;
+};
+
+static struct pm121_sys_param
+pm121_sys_all_params[N_LOOPS][PM121_NUM_CONFIGS] = {
+	/* GPU Fan control loop */
+	{
+		{ .model_id	= 2,
+		  .sensor	= &sensor_gpu_temp,
+		  .gp		= 0x002A6666,
+		  .itarget	= 0x5A0000,
+		  .control_id	= FAN_HD,
+		},
+		{ .model_id	= 3,
+		  .sensor	= &sensor_gpu_temp,
+		  .gp		= 0x0010CCCC,
+		  .itarget	= 0x500000,
+		  .control_id	= FAN_CPU,
+		},
+	},
+	/* HD Fan control loop */
+	{
+		{ .model_id	= 2,
+		  .sensor	= &sensor_hard_drive_temp,
+		  .gp		= 0x002D70A3,
+		  .itarget	= 0x370000,
+		  .control_id	= FAN_HD,
+		},
+		{ .model_id	= 3,
+		  .sensor	= &sensor_hard_drive_temp,
+		  .gp		= 0x002170A3,
+		  .itarget	= 0x370000,
+		  .control_id	= FAN_HD,
+		},
+	},
+	/* KODIAK Fan control loop */
+	{
+		{ .model_id	= 2,
+		  .sensor	= &sensor_north_bridge_temp,
+		  .gp		= 0x003BD70A,
+		  .itarget	= 0x550000,
+		  .control_id	= FAN_OD,
+		},
+		{ .model_id	= 3,
+		  .sensor	= &sensor_north_bridge_temp,
+		  .gp		= 0x0030F5C2,
+		  .itarget	= 0x550000,
+		  .control_id	= FAN_HD,
+		},
+	},
+	/* OD Fan control loop */
+	{
+		{ .model_id	= 2,
+		  .sensor	= &sensor_optical_drive_temp,
+		  .gp		= 0x001FAE14,
+		  .itarget	= 0x320000,
+		  .control_id	= FAN_OD,
+		},
+		{ .model_id	= 3,
+		  .sensor	= &sensor_optical_drive_temp,
+		  .gp		= 0x001FAE14,
+		  .itarget	= 0x320000,
+		  .control_id	= FAN_OD,
+		},
+	},
+};
+
+/* the hardcoded values */
+#define	PM121_SYS_GD		0x00000000
+#define	PM121_SYS_GR		0x00019999
+#define	PM121_SYS_HISTORY_SIZE	2
+#define	PM121_SYS_INTERVAL	5
+
+/* State data used by the system fans control loop
+ */
+struct pm121_sys_state {
+	int			ticks;
+	s32			setpoint;
+	struct wf_pid_state	pid;
+};
+
+struct pm121_sys_state *pm121_sys_state[N_LOOPS] = {};
+
+/*
+ * ****** CPU Fans Control Loop ******
+ *
+ */
+
+#define PM121_CPU_INTERVAL	1
+
+/* State data used by the cpu fans control loop
+ */
+struct pm121_cpu_state {
+	int			ticks;
+	s32			setpoint;
+	struct wf_cpu_pid_state	pid;
+};
+
+static struct pm121_cpu_state *pm121_cpu_state;
+
+
+
+/*
+ * ***** Implementation *****
+ *
+ */
+
+/* correction the value using the output-low-bound correction algo */
+static s32 pm121_correct(s32 new_setpoint,
+			 unsigned int control_id,
+			 s32 min)
+{
+	s32 new_min;
+	struct pm121_correction *correction;
+	correction = &corrections[control_id][pm121_mach_model - 2];
+
+	new_min = (average_power * correction->slope) >> 16;
+	new_min += correction->offset;
+	new_min = (new_min >> 16) + min;
+
+	return max(new_setpoint, max(new_min, 0));
+}
+
+static s32 pm121_connect(unsigned int control_id, s32 setpoint)
+{
+	s32 new_min, value, new_setpoint;
+
+	if (pm121_connection->control_id == control_id) {
+		controls[control_id]->ops->get_value(controls[control_id],
+						     &value);
+		new_min = value * pm121_connection->correction.slope;
+		new_min += pm121_connection->correction.offset;
+		if (new_min > 0) {
+			new_setpoint = max(setpoint, (new_min >> 16));
+			if (new_setpoint != setpoint) {
+				pr_debug("pm121: %s depending on %s, "
+					 "corrected from %d to %d RPM\n",
+					 controls[control_id]->name,
+					 controls[pm121_connection->ref_id]->name,
+					 (int) setpoint, (int) new_setpoint);
+			}
+		} else
+			new_setpoint = setpoint;
+	}
+	/* no connection */
+	else
+		new_setpoint = setpoint;
+
+	return new_setpoint;
+}
+
+/* FAN LOOPS */
+static void pm121_create_sys_fans(int loop_id)
+{
+	struct pm121_sys_param *param = NULL;
+	struct wf_pid_param pid_param;
+	struct wf_control *control = NULL;
+	int i;
+
+	/* First, locate the params for this model */
+	for (i = 0; i < PM121_NUM_CONFIGS; i++) {
+		if (pm121_sys_all_params[loop_id][i].model_id == pm121_mach_model) {
+			param = &(pm121_sys_all_params[loop_id][i]);
+			break;
+		}
+	}
+
+	/* No params found, put fans to max */
+	if (param == NULL) {
+		printk(KERN_WARNING "pm121: %s fan config not found "
+		       " for this machine model\n",
+		       loop_names[loop_id]);
+		goto fail;
+	}
+
+	control = controls[param->control_id];
+
+	/* Alloc & initialize state */
+	pm121_sys_state[loop_id] = kmalloc(sizeof(struct pm121_sys_state),
+					   GFP_KERNEL);
+	if (pm121_sys_state[loop_id] == NULL) {
+		printk(KERN_WARNING "pm121: Memory allocation error\n");
+		goto fail;
+	}
+	pm121_sys_state[loop_id]->ticks = 1;
+
+	/* Fill PID params */
+	pid_param.gd		= PM121_SYS_GD;
+	pid_param.gp		= param->gp;
+	pid_param.gr		= PM121_SYS_GR;
+	pid_param.interval	= PM121_SYS_INTERVAL;
+	pid_param.history_len	= PM121_SYS_HISTORY_SIZE;
+	pid_param.itarget	= param->itarget;
+	pid_param.min		= control->ops->get_min(control);
+	pid_param.max		= control->ops->get_max(control);
+
+	wf_pid_init(&pm121_sys_state[loop_id]->pid, &pid_param);
+
+	pr_debug("pm121: %s Fan control loop initialized.\n"
+		 "       itarged=%d.%03d, min=%d RPM, max=%d RPM\n",
+		 loop_names[loop_id], FIX32TOPRINT(pid_param.itarget),
+		 pid_param.min, pid_param.max);
+	return;
+
+ fail:
+	/* note that this is not optimal since another loop may still
+	   control the same control */
+	printk(KERN_WARNING "pm121: failed to set up %s loop "
+	       "setting \"%s\" to max speed.\n",
+	       loop_names[loop_id], control->name);
+
+	if (control)
+		wf_control_set_max(control);
+}
+
+static void pm121_sys_fans_tick(int loop_id)
+{
+	struct pm121_sys_param *param;
+	struct pm121_sys_state *st;
+	struct wf_sensor *sensor;
+	struct wf_control *control;
+	s32 temp, new_setpoint;
+	int rc;
+
+	param = &(pm121_sys_all_params[loop_id][pm121_mach_model-2]);
+	st = pm121_sys_state[loop_id];
+	sensor = *(param->sensor);
+	control = controls[param->control_id];
+
+	if (--st->ticks != 0) {
+		if (pm121_readjust)
+			goto readjust;
+		return;
+	}
+	st->ticks = PM121_SYS_INTERVAL;
+
+	rc = sensor->ops->get_value(sensor, &temp);
+	if (rc) {
+		printk(KERN_WARNING "windfarm: %s sensor error %d\n",
+		       sensor->name, rc);
+		pm121_failure_state |= FAILURE_SENSOR;
+		return;
+	}
+
+	pr_debug("pm121: %s Fan tick ! %s: %d.%03d\n",
+		 loop_names[loop_id], sensor->name,
+		 FIX32TOPRINT(temp));
+
+	new_setpoint = wf_pid_run(&st->pid, temp);
+
+	/* correction */
+	new_setpoint = pm121_correct(new_setpoint,
+				     param->control_id,
+				     st->pid.param.min);
+	/* linked corretion */
+	new_setpoint = pm121_connect(param->control_id, new_setpoint);
+
+	if (new_setpoint == st->setpoint)
+		return;
+	st->setpoint = new_setpoint;
+	pr_debug("pm121: %s corrected setpoint: %d RPM\n",
+		 control->name, (int)new_setpoint);
+ readjust:
+	if (control && pm121_failure_state == 0) {
+		rc = control->ops->set_value(control, st->setpoint);
+		if (rc) {
+			printk(KERN_WARNING "windfarm: %s fan error %d\n",
+			       control->name, rc);
+			pm121_failure_state |= FAILURE_FAN;
+		}
+	}
+}
+
+
+/* CPU LOOP */
+static void pm121_create_cpu_fans(void)
+{
+	struct wf_cpu_pid_param pid_param;
+	const struct smu_sdbp_header *hdr;
+	struct smu_sdbp_cpupiddata *piddata;
+	struct smu_sdbp_fvt *fvt;
+	struct wf_control *fan_cpu;
+	s32 tmax, tdelta, maxpow, powadj;
+
+	fan_cpu = controls[FAN_CPU];
+
+	/* First, locate the PID params in SMU SBD */
+	hdr = smu_get_sdb_partition(SMU_SDB_CPUPIDDATA_ID, NULL);
+	if (hdr == 0) {
+		printk(KERN_WARNING "pm121: CPU PID fan config not found.\n");
+		goto fail;
+	}
+	piddata = (struct smu_sdbp_cpupiddata *)&hdr[1];
+
+	/* Get the FVT params for operating point 0 (the only supported one
+	 * for now) in order to get tmax
+	 */
+	hdr = smu_get_sdb_partition(SMU_SDB_FVT_ID, NULL);
+	if (hdr) {
+		fvt = (struct smu_sdbp_fvt *)&hdr[1];
+		tmax = ((s32)fvt->maxtemp) << 16;
+	} else
+		tmax = 0x5e0000; /* 94 degree default */
+
+	/* Alloc & initialize state */
+	pm121_cpu_state = kmalloc(sizeof(struct pm121_cpu_state),
+				  GFP_KERNEL);
+	if (pm121_cpu_state == NULL)
+		goto fail;
+	pm121_cpu_state->ticks = 1;
+
+	/* Fill PID params */
+	pid_param.interval = PM121_CPU_INTERVAL;
+	pid_param.history_len = piddata->history_len;
+	if (pid_param.history_len > WF_CPU_PID_MAX_HISTORY) {
+		printk(KERN_WARNING "pm121: History size overflow on "
+		       "CPU control loop (%d)\n", piddata->history_len);
+		pid_param.history_len = WF_CPU_PID_MAX_HISTORY;
+	}
+	pid_param.gd = piddata->gd;
+	pid_param.gp = piddata->gp;
+	pid_param.gr = piddata->gr / pid_param.history_len;
+
+	tdelta = ((s32)piddata->target_temp_delta) << 16;
+	maxpow = ((s32)piddata->max_power) << 16;
+	powadj = ((s32)piddata->power_adj) << 16;
+
+	pid_param.tmax = tmax;
+	pid_param.ttarget = tmax - tdelta;
+	pid_param.pmaxadj = maxpow - powadj;
+
+	pid_param.min = fan_cpu->ops->get_min(fan_cpu);
+	pid_param.max = fan_cpu->ops->get_max(fan_cpu);
+
+	wf_cpu_pid_init(&pm121_cpu_state->pid, &pid_param);
+
+	pr_debug("pm121: CPU Fan control initialized.\n");
+	pr_debug("       ttarged=%d.%03d, tmax=%d.%03d, min=%d RPM, max=%d RPM,\n",
+		 FIX32TOPRINT(pid_param.ttarget), FIX32TOPRINT(pid_param.tmax),
+		 pid_param.min, pid_param.max);
+
+	return;
+
+ fail:
+	printk(KERN_WARNING "pm121: CPU fan config not found, max fan speed\n");
+
+	if (controls[CPUFREQ])
+		wf_control_set_max(controls[CPUFREQ]);
+	if (fan_cpu)
+		wf_control_set_max(fan_cpu);
+}
+
+
+static void pm121_cpu_fans_tick(struct pm121_cpu_state *st)
+{
+	s32 new_setpoint, temp, power;
+	struct wf_control *fan_cpu = NULL;
+	int rc;
+
+	if (--st->ticks != 0) {
+		if (pm121_readjust)
+			goto readjust;
+		return;
+	}
+	st->ticks = PM121_CPU_INTERVAL;
+
+	fan_cpu = controls[FAN_CPU];
+
+	rc = sensor_cpu_temp->ops->get_value(sensor_cpu_temp, &temp);
+	if (rc) {
+		printk(KERN_WARNING "pm121: CPU temp sensor error %d\n",
+		       rc);
+		pm121_failure_state |= FAILURE_SENSOR;
+		return;
+	}
+
+	rc = sensor_cpu_power->ops->get_value(sensor_cpu_power, &power);
+	if (rc) {
+		printk(KERN_WARNING "pm121: CPU power sensor error %d\n",
+		       rc);
+		pm121_failure_state |= FAILURE_SENSOR;
+		return;
+	}
+
+	pr_debug("pm121: CPU Fans tick ! CPU temp: %d.%03d°C, power: %d.%03d\n",
+		 FIX32TOPRINT(temp), FIX32TOPRINT(power));
+
+	if (temp > st->pid.param.tmax)
+		pm121_failure_state |= FAILURE_OVERTEMP;
+
+	new_setpoint = wf_cpu_pid_run(&st->pid, power, temp);
+
+	/* correction */
+	new_setpoint = pm121_correct(new_setpoint,
+				     FAN_CPU,
+				     st->pid.param.min);
+
+	/* connected correction */
+	new_setpoint = pm121_connect(FAN_CPU, new_setpoint);
+
+	if (st->setpoint == new_setpoint)
+		return;
+	st->setpoint = new_setpoint;
+	pr_debug("pm121: CPU corrected setpoint: %d RPM\n", (int)new_setpoint);
+
+ readjust:
+	if (fan_cpu && pm121_failure_state == 0) {
+		rc = fan_cpu->ops->set_value(fan_cpu, st->setpoint);
+		if (rc) {
+			printk(KERN_WARNING "pm121: %s fan error %d\n",
+			       fan_cpu->name, rc);
+			pm121_failure_state |= FAILURE_FAN;
+		}
+	}
+}
+
+/*
+ * ****** Common ******
+ *
+ */
+
+static void pm121_tick(void)
+{
+	unsigned int last_failure = pm121_failure_state;
+	unsigned int new_failure;
+	s32 total_power;
+	int i;
+
+	if (!pm121_started) {
+		pr_debug("pm121: creating control loops !\n");
+		for (i = 0; i < N_LOOPS; i++)
+			pm121_create_sys_fans(i);
+
+		pm121_create_cpu_fans();
+		pm121_started = 1;
+	}
+
+	/* skipping ticks */
+	if (pm121_skipping && --pm121_skipping)
+		return;
+
+	/* compute average power */
+	total_power = 0;
+	for (i = 0; i < pm121_cpu_state->pid.param.history_len; i++)
+		total_power += pm121_cpu_state->pid.powers[i];
+
+	average_power = total_power / pm121_cpu_state->pid.param.history_len;
+
+
+	pm121_failure_state = 0;
+	for (i = 0 ; i < N_LOOPS; i++) {
+		if (pm121_sys_state[i])
+			pm121_sys_fans_tick(i);
+	}
+
+	if (pm121_cpu_state)
+		pm121_cpu_fans_tick(pm121_cpu_state);
+
+	pm121_readjust = 0;
+	new_failure = pm121_failure_state & ~last_failure;
+
+	/* If entering failure mode, clamp cpufreq and ramp all
+	 * fans to full speed.
+	 */
+	if (pm121_failure_state && !last_failure) {
+		for (i = 0; i < N_CONTROLS; i++) {
+			if (controls[i])
+				wf_control_set_max(controls[i]);
+		}
+	}
+
+	/* If leaving failure mode, unclamp cpufreq and readjust
+	 * all fans on next iteration
+	 */
+	if (!pm121_failure_state && last_failure) {
+		if (controls[CPUFREQ])
+			wf_control_set_min(controls[CPUFREQ]);
+		pm121_readjust = 1;
+	}
+
+	/* Overtemp condition detected, notify and start skipping a couple
+	 * ticks to let the temperature go down
+	 */
+	if (new_failure & FAILURE_OVERTEMP) {
+		wf_set_overtemp();
+		pm121_skipping = 2;
+	}
+
+	/* We only clear the overtemp condition if overtemp is cleared
+	 * _and_ no other failure is present. Since a sensor error will
+	 * clear the overtemp condition (can't measure temperature) at
+	 * the control loop levels, but we don't want to keep it clear
+	 * here in this case
+	 */
+	if (new_failure == 0 && last_failure & FAILURE_OVERTEMP)
+		wf_clear_overtemp();
+}
+
+
+static struct wf_control* pm121_register_control(struct wf_control *ct,
+						 const char *match,
+						 unsigned int id)
+{
+	if (controls[id] == NULL && !strcmp(ct->name, match)) {
+		if (wf_get_control(ct) == 0)
+			controls[id] = ct;
+	}
+	return controls[id];
+}
+
+static void pm121_new_control(struct wf_control *ct)
+{
+	int all = 1;
+
+	if (pm121_all_controls_ok)
+		return;
+
+	all = pm121_register_control(ct, "optical-drive-fan", FAN_OD) && all;
+	all = pm121_register_control(ct, "hard-drive-fan", FAN_HD) && all;
+	all = pm121_register_control(ct, "cpu-fan", FAN_CPU) && all;
+	all = pm121_register_control(ct, "cpufreq-clamp", CPUFREQ) && all;
+
+	if (all)
+		pm121_all_controls_ok = 1;
+}
+
+
+
+
+static struct wf_sensor* pm121_register_sensor(struct wf_sensor *sensor,
+					       const char *match,
+					       struct wf_sensor **var)
+{
+	if (*var == NULL && !strcmp(sensor->name, match)) {
+		if (wf_get_sensor(sensor) == 0)
+			*var = sensor;
+	}
+	return *var;
+}
+
+static void pm121_new_sensor(struct wf_sensor *sr)
+{
+	int all = 1;
+
+	if (pm121_all_sensors_ok)
+		return;
+
+	all = pm121_register_sensor(sr, "cpu-temp",
+				    &sensor_cpu_temp) && all;
+	all = pm121_register_sensor(sr, "cpu-current",
+				    &sensor_cpu_current) && all;
+	all = pm121_register_sensor(sr, "cpu-voltage",
+				    &sensor_cpu_voltage) && all;
+	all = pm121_register_sensor(sr, "cpu-power",
+				    &sensor_cpu_power) && all;
+	all = pm121_register_sensor(sr, "hard-drive-temp",
+				    &sensor_hard_drive_temp) && all;
+	all = pm121_register_sensor(sr, "optical-drive-temp",
+				    &sensor_optical_drive_temp) && all;
+	all = pm121_register_sensor(sr, "incoming-air-temp",
+				    &sensor_incoming_air_temp) && all;
+	all = pm121_register_sensor(sr, "north-bridge-temp",
+				    &sensor_north_bridge_temp) && all;
+	all = pm121_register_sensor(sr, "gpu-temp",
+				    &sensor_gpu_temp) && all;
+
+	if (all)
+		pm121_all_sensors_ok = 1;
+}
+
+
+
+static int pm121_notify(struct notifier_block *self,
+			unsigned long event, void *data)
+{
+	switch (event) {
+	case WF_EVENT_NEW_CONTROL:
+		pr_debug("pm121: new control %s detected\n",
+			 ((struct wf_control *)data)->name);
+		pm121_new_control(data);
+		break;
+	case WF_EVENT_NEW_SENSOR:
+		pr_debug("pm121: new sensor %s detected\n",
+			 ((struct wf_sensor *)data)->name);
+		pm121_new_sensor(data);
+		break;
+	case WF_EVENT_TICK:
+		if (pm121_all_controls_ok && pm121_all_sensors_ok)
+			pm121_tick();
+		break;
+	}
+
+	return 0;
+}
+
+static struct notifier_block pm121_events = {
+	.notifier_call	= pm121_notify,
+};
+
+static int pm121_init_pm(void)
+{
+	const struct smu_sdbp_header *hdr;
+
+	hdr = smu_get_sdb_partition(SMU_SDB_SENSORTREE_ID, NULL);
+	if (hdr != 0) {
+		struct smu_sdbp_sensortree *st =
+			(struct smu_sdbp_sensortree *)&hdr[1];
+		pm121_mach_model = st->model_id;
+	}
+
+	pm121_connection = &pm121_connections[pm121_mach_model - 2];
+
+	printk(KERN_INFO "pm121: Initializing for iMac G5 iSight model ID %d\n",
+	       pm121_mach_model);
+
+	return 0;
+}
+
+
+static int pm121_probe(struct platform_device *ddev)
+{
+	wf_register_client(&pm121_events);
+
+	return 0;
+}
+
+static int __devexit pm121_remove(struct platform_device *ddev)
+{
+	wf_unregister_client(&pm121_events);
+	return 0;
+}
+
+static struct platform_driver pm121_driver = {
+	.probe = pm121_probe,
+	.remove = __devexit_p(pm121_remove),
+	.driver = {
+		.name = "windfarm",
+		.bus = &platform_bus_type,
+	},
+};
+
+
+static int __init pm121_init(void)
+{
+	int rc = -ENODEV;
+
+	if (machine_is_compatible("PowerMac12,1"))
+		rc = pm121_init_pm();
+
+	if (rc == 0) {
+		request_module("windfarm_smu_controls");
+		request_module("windfarm_smu_sensors");
+		request_module("windfarm_smu_sat");
+		request_module("windfarm_lm75_sensor");
+		request_module("windfarm_max6690_sensor");
+		request_module("windfarm_cpufreq_clamp");
+		platform_driver_register(&pm121_driver);
+	}
+
+	return rc;
+}
+
+static void __exit pm121_exit(void)
+{
+
+	platform_driver_unregister(&pm121_driver);
+}
+
+
+module_init(pm121_init);
+module_exit(pm121_exit);
+
+MODULE_AUTHOR("Étienne Bersac <bersace@gmail.com>");
+MODULE_DESCRIPTION("Thermal control logic for iMac G5 (iSight)");
+MODULE_LICENSE("GPL");
+
diff --git a/trunk/drivers/macintosh/windfarm_smu_controls.c b/trunk/drivers/macintosh/windfarm_smu_controls.c
index 58c2590f05ec..961fa0e7c2cf 100644
--- a/trunk/drivers/macintosh/windfarm_smu_controls.c
+++ b/trunk/drivers/macintosh/windfarm_smu_controls.c
@@ -218,6 +218,10 @@ static struct smu_fan_control *smu_fan_create(struct device_node *node,
 		fct->ctrl.name = "cpu-fan";
 	else if (!strcmp(l, "Hard Drive") || !strcmp(l, "Hard drive"))
 		fct->ctrl.name = "drive-bay-fan";
+	else if (!strcmp(l, "HDD Fan")) /* seen on iMac G5 iSight */
+		fct->ctrl.name = "hard-drive-fan";
+	else if (!strcmp(l, "ODD Fan")) /* same */
+		fct->ctrl.name = "optical-drive-fan";
 
 	/* Unrecognized fan, bail out */
 	if (fct->ctrl.name == NULL)
diff --git a/trunk/drivers/mca/mca-legacy.c b/trunk/drivers/mca/mca-legacy.c
index 0c7bfa74c8ef..494f0c2001f5 100644
--- a/trunk/drivers/mca/mca-legacy.c
+++ b/trunk/drivers/mca/mca-legacy.c
@@ -281,24 +281,6 @@ void mca_set_adapter_name(int slot, char* name)
 }
 EXPORT_SYMBOL(mca_set_adapter_name);
 
-/**
- *	mca_is_adapter_used - check if claimed by driver
- *	@slot:	slot to check
- *
- *	Returns 1 if the slot has been claimed by a driver
- */
-
-int mca_is_adapter_used(int slot)
-{
-	struct mca_device *mca_dev = mca_find_device_by_slot(slot);
-
-	if(!mca_dev)
-		return 0;
-
-	return mca_device_claimed(mca_dev);
-}
-EXPORT_SYMBOL(mca_is_adapter_used);
-
 /**
  *	mca_mark_as_used - claim an MCA device
  *	@slot:	slot to claim
diff --git a/trunk/drivers/mca/mca-proc.c b/trunk/drivers/mca/mca-proc.c
index 33d5e0820cc5..81ea0d377bf4 100644
--- a/trunk/drivers/mca/mca-proc.c
+++ b/trunk/drivers/mca/mca-proc.c
@@ -183,7 +183,7 @@ void __init mca_do_proc_init(void)
 	struct proc_dir_entry* node = NULL;
 	struct mca_device *mca_dev;
 
-	proc_mca = proc_mkdir("mca", &proc_root);
+	proc_mca = proc_mkdir("mca", NULL);
 	create_proc_read_entry("pos",0,proc_mca,get_mca_info,NULL);
 	create_proc_read_entry("machine",0,proc_mca,get_mca_machine_info,NULL);
 
diff --git a/trunk/drivers/md/dm-emc.c b/trunk/drivers/md/dm-emc.c
index 6b91b9ab1d41..3ea5ad4b7805 100644
--- a/trunk/drivers/md/dm-emc.c
+++ b/trunk/drivers/md/dm-emc.c
@@ -110,8 +110,6 @@ static struct request *get_failover_req(struct emc_handler *h,
 	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
 	rq->sense_len = 0;
 
-	memset(&rq->cmd, 0, BLK_MAX_CDB);
-
 	rq->timeout = EMC_FAILOVER_TIMEOUT;
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 	rq->cmd_flags |= REQ_FAILFAST | REQ_NOMERGE;
diff --git a/trunk/drivers/md/dm-mpath-hp-sw.c b/trunk/drivers/md/dm-mpath-hp-sw.c
index 204bf42c9449..b63a0ab37c53 100644
--- a/trunk/drivers/md/dm-mpath-hp-sw.c
+++ b/trunk/drivers/md/dm-mpath-hp-sw.c
@@ -137,7 +137,6 @@ static struct request *hp_sw_get_request(struct dm_path *path)
 	req->sense = h->sense;
 	memset(req->sense, 0, SCSI_SENSE_BUFFERSIZE);
 
-	memset(&req->cmd, 0, BLK_MAX_CDB);
 	req->cmd[0] = START_STOP;
 	req->cmd[4] = 1;
 	req->cmd_len = COMMAND_SIZE(req->cmd[0]);
diff --git a/trunk/drivers/md/dm-mpath-rdac.c b/trunk/drivers/md/dm-mpath-rdac.c
index e04eb5c697fb..95e77734880a 100644
--- a/trunk/drivers/md/dm-mpath-rdac.c
+++ b/trunk/drivers/md/dm-mpath-rdac.c
@@ -284,7 +284,6 @@ static struct request *get_rdac_req(struct rdac_handler *h,
 		return NULL;
 	}
 
- 	memset(&rq->cmd, 0, BLK_MAX_CDB);
 	rq->sense = h->sense;
 	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
 	rq->sense_len = 0;
diff --git a/trunk/drivers/md/dm-table.c b/trunk/drivers/md/dm-table.c
index 51be53344214..73326e7c54bf 100644
--- a/trunk/drivers/md/dm-table.c
+++ b/trunk/drivers/md/dm-table.c
@@ -873,10 +873,13 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q)
 	q->max_hw_sectors = t->limits.max_hw_sectors;
 	q->seg_boundary_mask = t->limits.seg_boundary_mask;
 	q->bounce_pfn = t->limits.bounce_pfn;
+	/* XXX: the below will probably go bug. must ensure there can be no
+	 * concurrency on queue_flags, and use the unlocked versions...
+	 */
 	if (t->limits.no_cluster)
-		q->queue_flags &= ~(1 << QUEUE_FLAG_CLUSTER);
+		queue_flag_clear(QUEUE_FLAG_CLUSTER, q);
 	else
-		q->queue_flags |= (1 << QUEUE_FLAG_CLUSTER);
+		queue_flag_set(QUEUE_FLAG_CLUSTER, q);
 
 }
 
diff --git a/trunk/drivers/md/dm-uevent.c b/trunk/drivers/md/dm-uevent.c
index 50377e5dc2a3..6f65883aef12 100644
--- a/trunk/drivers/md/dm-uevent.c
+++ b/trunk/drivers/md/dm-uevent.c
@@ -78,7 +78,7 @@ static struct dm_uevent *dm_build_path_uevent(struct mapped_device *md,
 
 	event = dm_uevent_alloc(md);
 	if (!event) {
-		DMERR("%s: dm_uevent_alloc() failed", __FUNCTION__);
+		DMERR("%s: dm_uevent_alloc() failed", __func__);
 		goto err_nomem;
 	}
 
@@ -86,32 +86,32 @@ static struct dm_uevent *dm_build_path_uevent(struct mapped_device *md,
 
 	if (add_uevent_var(&event->ku_env, "DM_TARGET=%s", ti->type->name)) {
 		DMERR("%s: add_uevent_var() for DM_TARGET failed",
-		      __FUNCTION__);
+		      __func__);
 		goto err_add;
 	}
 
 	if (add_uevent_var(&event->ku_env, "DM_ACTION=%s", dm_action)) {
 		DMERR("%s: add_uevent_var() for DM_ACTION failed",
-		      __FUNCTION__);
+		      __func__);
 		goto err_add;
 	}
 
 	if (add_uevent_var(&event->ku_env, "DM_SEQNUM=%u",
 			   dm_next_uevent_seq(md))) {
 		DMERR("%s: add_uevent_var() for DM_SEQNUM failed",
-		      __FUNCTION__);
+		      __func__);
 		goto err_add;
 	}
 
 	if (add_uevent_var(&event->ku_env, "DM_PATH=%s", path)) {
-		DMERR("%s: add_uevent_var() for DM_PATH failed", __FUNCTION__);
+		DMERR("%s: add_uevent_var() for DM_PATH failed", __func__);
 		goto err_add;
 	}
 
 	if (add_uevent_var(&event->ku_env, "DM_NR_VALID_PATHS=%d",
 			   nr_valid_paths)) {
 		DMERR("%s: add_uevent_var() for DM_NR_VALID_PATHS failed",
-		      __FUNCTION__);
+		      __func__);
 		goto err_add;
 	}
 
@@ -146,25 +146,25 @@ void dm_send_uevents(struct list_head *events, struct kobject *kobj)
 		if (dm_copy_name_and_uuid(event->md, event->name,
 					  event->uuid)) {
 			DMERR("%s: dm_copy_name_and_uuid() failed",
-			      __FUNCTION__);
+			      __func__);
 			goto uevent_free;
 		}
 
 		if (add_uevent_var(&event->ku_env, "DM_NAME=%s", event->name)) {
 			DMERR("%s: add_uevent_var() for DM_NAME failed",
-			      __FUNCTION__);
+			      __func__);
 			goto uevent_free;
 		}
 
 		if (add_uevent_var(&event->ku_env, "DM_UUID=%s", event->uuid)) {
 			DMERR("%s: add_uevent_var() for DM_UUID failed",
-			      __FUNCTION__);
+			      __func__);
 			goto uevent_free;
 		}
 
 		r = kobject_uevent_env(kobj, event->action, event->ku_env.envp);
 		if (r)
-			DMERR("%s: kobject_uevent_env failed", __FUNCTION__);
+			DMERR("%s: kobject_uevent_env failed", __func__);
 uevent_free:
 		dm_uevent_free(event);
 	}
@@ -187,7 +187,7 @@ void dm_path_uevent(enum dm_uevent_type event_type, struct dm_target *ti,
 	struct dm_uevent *event;
 
 	if (event_type >= ARRAY_SIZE(_dm_uevent_type_names)) {
-		DMERR("%s: Invalid event_type %d", __FUNCTION__, event_type);
+		DMERR("%s: Invalid event_type %d", __func__, event_type);
 		goto out;
 	}
 
diff --git a/trunk/drivers/md/md.c b/trunk/drivers/md/md.c
index 5ebfb4d79901..bb3e4b1cb773 100644
--- a/trunk/drivers/md/md.c
+++ b/trunk/drivers/md/md.c
@@ -282,7 +282,8 @@ static mddev_t * mddev_find(dev_t unit)
 		kfree(new);
 		return NULL;
 	}
-	set_bit(QUEUE_FLAG_CLUSTER, &new->queue->queue_flags);
+	/* Can be unlocked because the queue is new: no concurrency */
+	queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, new->queue);
 
 	blk_queue_make_request(new->queue, md_fail_request);
 
@@ -731,9 +732,9 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
 	else
 		rdev->desc_nr = sb->this_disk.number;
 
-	if (refdev == 0)
+	if (!refdev) {
 		ret = 1;
-	else {
+	} else {
 		__u64 ev1, ev2;
 		mdp_super_t *refsb = (mdp_super_t*)page_address(refdev->sb_page);
 		if (!uuid_equal(refsb, sb)) {
@@ -1116,9 +1117,9 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
 	else
 		rdev->desc_nr = le32_to_cpu(sb->dev_number);
 
-	if (refdev == 0)
+	if (!refdev) {
 		ret = 1;
-	else {
+	} else {
 		__u64 ev1, ev2;
 		struct mdp_superblock_1 *refsb = 
 			(struct mdp_superblock_1*)page_address(refdev->sb_page);
@@ -5947,13 +5948,9 @@ static struct notifier_block md_notifier = {
 
 static void md_geninit(void)
 {
-	struct proc_dir_entry *p;
-
 	dprintk("md: sizeof(mdp_super_t) = %d\n", (int)sizeof(mdp_super_t));
 
-	p = create_proc_entry("mdstat", S_IRUGO, NULL);
-	if (p)
-		p->proc_fops = &md_seq_fops;
+	proc_create("mdstat", S_IRUGO, NULL, &md_seq_fops);
 }
 
 static int __init md_init(void)
diff --git a/trunk/drivers/md/multipath.c b/trunk/drivers/md/multipath.c
index 3f299d835a2b..42ee1a2dc144 100644
--- a/trunk/drivers/md/multipath.c
+++ b/trunk/drivers/md/multipath.c
@@ -244,7 +244,8 @@ static void multipath_error (mddev_t *mddev, mdk_rdev_t *rdev)
 			conf->working_disks--;
 			mddev->degraded++;
 			printk(KERN_ALERT "multipath: IO failure on %s,"
-				" disabling IO path. \n	Operation continuing"
+				" disabling IO path.\n"
+				"multipath: Operation continuing"
 				" on %d IO paths.\n",
 				bdevname (rdev->bdev,b),
 				conf->working_disks);
diff --git a/trunk/drivers/md/raid1.c b/trunk/drivers/md/raid1.c
index ff61b309129a..9fd473a6dbf5 100644
--- a/trunk/drivers/md/raid1.c
+++ b/trunk/drivers/md/raid1.c
@@ -1008,8 +1008,8 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 	} else
 		set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
-	printk(KERN_ALERT "raid1: Disk failure on %s, disabling device. \n"
-		"	Operation continuing on %d devices\n",
+	printk(KERN_ALERT "raid1: Disk failure on %s, disabling device.\n"
+		"raid1: Operation continuing on %d devices.\n",
 		bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
 }
 
diff --git a/trunk/drivers/md/raid10.c b/trunk/drivers/md/raid10.c
index 32389d2f18fc..1e96aa3ff513 100644
--- a/trunk/drivers/md/raid10.c
+++ b/trunk/drivers/md/raid10.c
@@ -1001,8 +1001,8 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 	}
 	set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
-	printk(KERN_ALERT "raid10: Disk failure on %s, disabling device. \n"
-		"	Operation continuing on %d devices\n",
+	printk(KERN_ALERT "raid10: Disk failure on %s, disabling device.\n"
+		"raid10: Operation continuing on %d devices.\n",
 		bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
 }
 
diff --git a/trunk/drivers/md/raid5.c b/trunk/drivers/md/raid5.c
index b162b839a662..968dacaced6d 100644
--- a/trunk/drivers/md/raid5.c
+++ b/trunk/drivers/md/raid5.c
@@ -63,6 +63,7 @@
 #define STRIPE_SHIFT		(PAGE_SHIFT - 9)
 #define STRIPE_SECTORS		(STRIPE_SIZE>>9)
 #define	IO_THRESHOLD		1
+#define BYPASS_THRESHOLD	1
 #define NR_HASH			(PAGE_SIZE / sizeof(struct hlist_head))
 #define HASH_MASK		(NR_HASH - 1)
 
@@ -398,6 +399,7 @@ static void ops_run_io(struct stripe_head *sh)
 
 	might_sleep();
 
+	set_bit(STRIPE_IO_STARTED, &sh->state);
 	for (i = disks; i--; ) {
 		int rw;
 		struct bio *bi;
@@ -433,7 +435,7 @@ static void ops_run_io(struct stripe_head *sh)
 
 			bi->bi_bdev = rdev->bdev;
 			pr_debug("%s: for %llu schedule op %ld on disc %d\n",
-				__FUNCTION__, (unsigned long long)sh->sector,
+				__func__, (unsigned long long)sh->sector,
 				bi->bi_rw, i);
 			atomic_inc(&sh->count);
 			bi->bi_sector = sh->sector + rdev->data_offset;
@@ -520,7 +522,7 @@ static void ops_complete_biofill(void *stripe_head_ref)
 	raid5_conf_t *conf = sh->raid_conf;
 	int i;
 
-	pr_debug("%s: stripe %llu\n", __FUNCTION__,
+	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
 	/* clear completed biofills */
@@ -569,7 +571,7 @@ static void ops_run_biofill(struct stripe_head *sh)
 	raid5_conf_t *conf = sh->raid_conf;
 	int i;
 
-	pr_debug("%s: stripe %llu\n", __FUNCTION__,
+	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
 	for (i = sh->disks; i--; ) {
@@ -600,7 +602,7 @@ static void ops_complete_compute5(void *stripe_head_ref)
 	int target = sh->ops.target;
 	struct r5dev *tgt = &sh->dev[target];
 
-	pr_debug("%s: stripe %llu\n", __FUNCTION__,
+	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
 	set_bit(R5_UPTODATE, &tgt->flags);
@@ -625,7 +627,7 @@ ops_run_compute5(struct stripe_head *sh, unsigned long pending)
 	int i;
 
 	pr_debug("%s: stripe %llu block: %d\n",
-		__FUNCTION__, (unsigned long long)sh->sector, target);
+		__func__, (unsigned long long)sh->sector, target);
 	BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
 
 	for (i = disks; i--; )
@@ -653,7 +655,7 @@ static void ops_complete_prexor(void *stripe_head_ref)
 {
 	struct stripe_head *sh = stripe_head_ref;
 
-	pr_debug("%s: stripe %llu\n", __FUNCTION__,
+	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
 	set_bit(STRIPE_OP_PREXOR, &sh->ops.complete);
@@ -670,7 +672,7 @@ ops_run_prexor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 	/* existing parity data subtracted */
 	struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
 
-	pr_debug("%s: stripe %llu\n", __FUNCTION__,
+	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
 	for (i = disks; i--; ) {
@@ -699,7 +701,7 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
 	 */
 	int prexor = test_bit(STRIPE_OP_PREXOR, &pending);
 
-	pr_debug("%s: stripe %llu\n", __FUNCTION__,
+	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
 	for (i = disks; i--; ) {
@@ -744,7 +746,7 @@ static void ops_complete_postxor(void *stripe_head_ref)
 {
 	struct stripe_head *sh = stripe_head_ref;
 
-	pr_debug("%s: stripe %llu\n", __FUNCTION__,
+	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
 	set_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
@@ -757,7 +759,7 @@ static void ops_complete_write(void *stripe_head_ref)
 	struct stripe_head *sh = stripe_head_ref;
 	int disks = sh->disks, i, pd_idx = sh->pd_idx;
 
-	pr_debug("%s: stripe %llu\n", __FUNCTION__,
+	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
 	for (i = disks; i--; ) {
@@ -787,7 +789,7 @@ ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
 	unsigned long flags;
 	dma_async_tx_callback callback;
 
-	pr_debug("%s: stripe %llu\n", __FUNCTION__,
+	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
 	/* check if prexor is active which means only process blocks
@@ -837,7 +839,7 @@ static void ops_complete_check(void *stripe_head_ref)
 	struct stripe_head *sh = stripe_head_ref;
 	int pd_idx = sh->pd_idx;
 
-	pr_debug("%s: stripe %llu\n", __FUNCTION__,
+	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
 	if (test_and_clear_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending) &&
@@ -859,7 +861,7 @@ static void ops_run_check(struct stripe_head *sh)
 	int count = 0, pd_idx = sh->pd_idx, i;
 	struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
 
-	pr_debug("%s: stripe %llu\n", __FUNCTION__,
+	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
 	for (i = disks; i--; ) {
@@ -1260,8 +1262,8 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 		}
 		set_bit(Faulty, &rdev->flags);
 		printk (KERN_ALERT
-			"raid5: Disk failure on %s, disabling device."
-			" Operation continuing on %d devices\n",
+			"raid5: Disk failure on %s, disabling device.\n"
+			"raid5: Operation continuing on %d devices.\n",
 			bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
 	}
 }
@@ -1720,6 +1722,9 @@ handle_write_operations5(struct stripe_head *sh, int rcw, int expand)
 				locked++;
 			}
 		}
+		if (locked + 1 == disks)
+			if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
+				atomic_inc(&sh->raid_conf->pending_full_writes);
 	} else {
 		BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
 			test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
@@ -1759,7 +1764,7 @@ handle_write_operations5(struct stripe_head *sh, int rcw, int expand)
 	locked++;
 
 	pr_debug("%s: stripe %llu locked: %d pending: %lx\n",
-		__FUNCTION__, (unsigned long long)sh->sector,
+		__func__, (unsigned long long)sh->sector,
 		locked, sh->ops.pending);
 
 	return locked;
@@ -1947,6 +1952,9 @@ handle_requests_to_failed_array(raid5_conf_t *conf, struct stripe_head *sh,
 					STRIPE_SECTORS, 0, 0);
 	}
 
+	if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
+		if (atomic_dec_and_test(&conf->pending_full_writes))
+			md_wakeup_thread(conf->mddev->thread);
 }
 
 /* __handle_issuing_new_read_requests5 - returns 0 if there are no more disks
@@ -2149,6 +2157,10 @@ static void handle_completed_write_requests(raid5_conf_t *conf,
 							0);
 			}
 		}
+
+	if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
+		if (atomic_dec_and_test(&conf->pending_full_writes))
+			md_wakeup_thread(conf->mddev->thread);
 }
 
 static void handle_issuing_new_write_requests5(raid5_conf_t *conf,
@@ -2333,6 +2345,9 @@ static void handle_issuing_new_write_requests6(raid5_conf_t *conf,
 				s->locked++;
 				set_bit(R5_Wantwrite, &sh->dev[i].flags);
 			}
+		if (s->locked == disks)
+			if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
+				atomic_inc(&conf->pending_full_writes);
 		/* after a RECONSTRUCT_WRITE, the stripe MUST be in-sync */
 		set_bit(STRIPE_INSYNC, &sh->state);
 
@@ -3094,6 +3109,8 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 		else
 			continue;
 
+		set_bit(STRIPE_IO_STARTED, &sh->state);
+
 		bi = &sh->dev[i].req;
 
 		bi->bi_rw = rw;
@@ -3164,7 +3181,7 @@ static void raid5_activate_delayed(raid5_conf_t *conf)
 			clear_bit(STRIPE_DELAYED, &sh->state);
 			if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
 				atomic_inc(&conf->preread_active_stripes);
-			list_add_tail(&sh->lru, &conf->handle_list);
+			list_add_tail(&sh->lru, &conf->hold_list);
 		}
 	} else
 		blk_plug_device(conf->mddev->queue);
@@ -3442,6 +3459,58 @@ static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio)
 	}
 }
 
+/* __get_priority_stripe - get the next stripe to process
+ *
+ * Full stripe writes are allowed to pass preread active stripes up until
+ * the bypass_threshold is exceeded.  In general the bypass_count
+ * increments when the handle_list is handled before the hold_list; however, it
+ * will not be incremented when STRIPE_IO_STARTED is sampled set signifying a
+ * stripe with in flight i/o.  The bypass_count will be reset when the
+ * head of the hold_list has changed, i.e. the head was promoted to the
+ * handle_list.
+ */
+static struct stripe_head *__get_priority_stripe(raid5_conf_t *conf)
+{
+	struct stripe_head *sh;
+
+	pr_debug("%s: handle: %s hold: %s full_writes: %d bypass_count: %d\n",
+		  __func__,
+		  list_empty(&conf->handle_list) ? "empty" : "busy",
+		  list_empty(&conf->hold_list) ? "empty" : "busy",
+		  atomic_read(&conf->pending_full_writes), conf->bypass_count);
+
+	if (!list_empty(&conf->handle_list)) {
+		sh = list_entry(conf->handle_list.next, typeof(*sh), lru);
+
+		if (list_empty(&conf->hold_list))
+			conf->bypass_count = 0;
+		else if (!test_bit(STRIPE_IO_STARTED, &sh->state)) {
+			if (conf->hold_list.next == conf->last_hold)
+				conf->bypass_count++;
+			else {
+				conf->last_hold = conf->hold_list.next;
+				conf->bypass_count -= conf->bypass_threshold;
+				if (conf->bypass_count < 0)
+					conf->bypass_count = 0;
+			}
+		}
+	} else if (!list_empty(&conf->hold_list) &&
+		   ((conf->bypass_threshold &&
+		     conf->bypass_count > conf->bypass_threshold) ||
+		    atomic_read(&conf->pending_full_writes) == 0)) {
+		sh = list_entry(conf->hold_list.next,
+				typeof(*sh), lru);
+		conf->bypass_count -= conf->bypass_threshold;
+		if (conf->bypass_count < 0)
+			conf->bypass_count = 0;
+	} else
+		return NULL;
+
+	list_del_init(&sh->lru);
+	atomic_inc(&sh->count);
+	BUG_ON(atomic_read(&sh->count) != 1);
+	return sh;
+}
 
 static int make_request(struct request_queue *q, struct bio * bi)
 {
@@ -3914,7 +3983,6 @@ static void raid5d(mddev_t *mddev)
 	handled = 0;
 	spin_lock_irq(&conf->device_lock);
 	while (1) {
-		struct list_head *first;
 		struct bio *bio;
 
 		if (conf->seq_flush != conf->seq_write) {
@@ -3936,17 +4004,12 @@ static void raid5d(mddev_t *mddev)
 			handled++;
 		}
 
-		if (list_empty(&conf->handle_list)) {
+		sh = __get_priority_stripe(conf);
+
+		if (!sh) {
 			async_tx_issue_pending_all();
 			break;
 		}
-
-		first = conf->handle_list.next;
-		sh = list_entry(first, struct stripe_head, lru);
-
-		list_del_init(first);
-		atomic_inc(&sh->count);
-		BUG_ON(atomic_read(&sh->count)!= 1);
 		spin_unlock_irq(&conf->device_lock);
 		
 		handled++;
@@ -3978,15 +4041,13 @@ static ssize_t
 raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
 {
 	raid5_conf_t *conf = mddev_to_conf(mddev);
-	char *end;
-	int new;
+	unsigned long new;
 	if (len >= PAGE_SIZE)
 		return -EINVAL;
 	if (!conf)
 		return -ENODEV;
 
-	new = simple_strtoul(page, &end, 10);
-	if (!*page || (*end && *end != '\n') )
+	if (strict_strtoul(page, 10, &new))
 		return -EINVAL;
 	if (new <= 16 || new > 32768)
 		return -EINVAL;
@@ -4010,6 +4071,40 @@ raid5_stripecache_size = __ATTR(stripe_cache_size, S_IRUGO | S_IWUSR,
 				raid5_show_stripe_cache_size,
 				raid5_store_stripe_cache_size);
 
+static ssize_t
+raid5_show_preread_threshold(mddev_t *mddev, char *page)
+{
+	raid5_conf_t *conf = mddev_to_conf(mddev);
+	if (conf)
+		return sprintf(page, "%d\n", conf->bypass_threshold);
+	else
+		return 0;
+}
+
+static ssize_t
+raid5_store_preread_threshold(mddev_t *mddev, const char *page, size_t len)
+{
+	raid5_conf_t *conf = mddev_to_conf(mddev);
+	unsigned long new;
+	if (len >= PAGE_SIZE)
+		return -EINVAL;
+	if (!conf)
+		return -ENODEV;
+
+	if (strict_strtoul(page, 10, &new))
+		return -EINVAL;
+	if (new > conf->max_nr_stripes)
+		return -EINVAL;
+	conf->bypass_threshold = new;
+	return len;
+}
+
+static struct md_sysfs_entry
+raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold,
+					S_IRUGO | S_IWUSR,
+					raid5_show_preread_threshold,
+					raid5_store_preread_threshold);
+
 static ssize_t
 stripe_cache_active_show(mddev_t *mddev, char *page)
 {
@@ -4026,6 +4121,7 @@ raid5_stripecache_active = __ATTR_RO(stripe_cache_active);
 static struct attribute *raid5_attrs[] =  {
 	&raid5_stripecache_size.attr,
 	&raid5_stripecache_active.attr,
+	&raid5_preread_bypass_threshold.attr,
 	NULL,
 };
 static struct attribute_group raid5_attrs_group = {
@@ -4130,12 +4226,14 @@ static int run(mddev_t *mddev)
 	init_waitqueue_head(&conf->wait_for_stripe);
 	init_waitqueue_head(&conf->wait_for_overlap);
 	INIT_LIST_HEAD(&conf->handle_list);
+	INIT_LIST_HEAD(&conf->hold_list);
 	INIT_LIST_HEAD(&conf->delayed_list);
 	INIT_LIST_HEAD(&conf->bitmap_list);
 	INIT_LIST_HEAD(&conf->inactive_list);
 	atomic_set(&conf->active_stripes, 0);
 	atomic_set(&conf->preread_active_stripes, 0);
 	atomic_set(&conf->active_aligned_reads, 0);
+	conf->bypass_threshold = BYPASS_THRESHOLD;
 
 	pr_debug("raid5: run(%s) called.\n", mdname(mddev));
 
diff --git a/trunk/drivers/md/raid6algos.c b/trunk/drivers/md/raid6algos.c
index 77a6e4bf503d..21987e3dbe6c 100644
--- a/trunk/drivers/md/raid6algos.c
+++ b/trunk/drivers/md/raid6algos.c
@@ -121,7 +121,8 @@ int __init raid6_select_algo(void)
 			j0 = jiffies;
 			while ( (j1 = jiffies) == j0 )
 				cpu_relax();
-			while ( (jiffies-j1) < (1 << RAID6_TIME_JIFFIES_LG2) ) {
+			while (time_before(jiffies,
+					    j1 + (1<<RAID6_TIME_JIFFIES_LG2))) {
 				(*algo)->gen_syndrome(disks, PAGE_SIZE, dptrs);
 				perf++;
 			}
diff --git a/trunk/drivers/media/video/au0828/au0828-dvb.c b/trunk/drivers/media/video/au0828/au0828-dvb.c
index 5040d7fc4af5..1371b4e4b5f1 100644
--- a/trunk/drivers/media/video/au0828/au0828-dvb.c
+++ b/trunk/drivers/media/video/au0828/au0828-dvb.c
@@ -119,7 +119,7 @@ static int start_urb_transfer(struct au0828_dev *dev)
 		purb->transfer_buffer = kzalloc(URB_BUFSIZE, GFP_KERNEL);
 		if (!purb->transfer_buffer) {
 			usb_free_urb(purb);
-			dev->urbs[i] = 0;
+			dev->urbs[i] = NULL;
 			goto err;
 		}
 
diff --git a/trunk/drivers/media/video/ivtv/ivtv-yuv.c b/trunk/drivers/media/video/ivtv/ivtv-yuv.c
index 393d917cd672..62f70bd5e3cb 100644
--- a/trunk/drivers/media/video/ivtv/ivtv-yuv.c
+++ b/trunk/drivers/media/video/ivtv/ivtv-yuv.c
@@ -1098,8 +1098,8 @@ void ivtv_yuv_setup_stream_frame(struct ivtv *itv)
 	ivtv_yuv_next_free(itv);
 
 	/* Copy V4L2 parameters to an ivtv_dma_frame struct... */
-	dma_args.y_source = 0L;
-	dma_args.uv_source = 0L;
+	dma_args.y_source = NULL;
+	dma_args.uv_source = NULL;
 	dma_args.src.left = 0;
 	dma_args.src.top = 0;
 	dma_args.src.width = yi->v4l2_src_w;
diff --git a/trunk/drivers/media/video/pvrusb2/pvrusb2-audio.c b/trunk/drivers/media/video/pvrusb2/pvrusb2-audio.c
index 9a7c8e9c3e8b..8d859ccd48ec 100644
--- a/trunk/drivers/media/video/pvrusb2/pvrusb2-audio.c
+++ b/trunk/drivers/media/video/pvrusb2/pvrusb2-audio.c
@@ -75,7 +75,7 @@ static void set_stereo(struct pvr2_msp3400_handler *ctxt)
 	pvr2_trace(PVR2_TRACE_CHIPS,"i2c msp3400 v4l2 set_stereo");
 
 	if ((sid < ARRAY_SIZE(routing_schemes)) &&
-	    ((sp = routing_schemes + sid) != 0) &&
+	    ((sp = routing_schemes + sid) != NULL) &&
 	    (hdw->input_val >= 0) &&
 	    (hdw->input_val < sp->cnt)) {
 		route.input = sp->def[hdw->input_val];
diff --git a/trunk/drivers/media/video/pvrusb2/pvrusb2-context.c b/trunk/drivers/media/video/pvrusb2/pvrusb2-context.c
index b5db6a5bab31..73dcb1c57ae6 100644
--- a/trunk/drivers/media/video/pvrusb2/pvrusb2-context.c
+++ b/trunk/drivers/media/video/pvrusb2/pvrusb2-context.c
@@ -195,7 +195,7 @@ static int pvr2_context_thread_func(void *foo)
 int pvr2_context_global_init(void)
 {
 	pvr2_context_thread_ptr = kthread_run(pvr2_context_thread_func,
-					      0,
+					      NULL,
 					      "pvrusb2-context");
 	return (pvr2_context_thread_ptr ? 0 : -ENOMEM);
 }
diff --git a/trunk/drivers/media/video/pvrusb2/pvrusb2-cx2584x-v4l.c b/trunk/drivers/media/video/pvrusb2/pvrusb2-cx2584x-v4l.c
index 97350b048b8d..29d50597c88a 100644
--- a/trunk/drivers/media/video/pvrusb2/pvrusb2-cx2584x-v4l.c
+++ b/trunk/drivers/media/video/pvrusb2/pvrusb2-cx2584x-v4l.c
@@ -123,7 +123,7 @@ static void set_input(struct pvr2_v4l_cx2584x *ctxt)
 	memset(&route,0,sizeof(route));
 
 	if ((sid < ARRAY_SIZE(routing_schemes)) &&
-	    ((sp = routing_schemes + sid) != 0) &&
+	    ((sp = routing_schemes + sid) != NULL) &&
 	    (hdw->input_val >= 0) &&
 	    (hdw->input_val < sp->cnt)) {
 		vid_input = sp->def[hdw->input_val].vid;
diff --git a/trunk/drivers/media/video/pvrusb2/pvrusb2-dvb.c b/trunk/drivers/media/video/pvrusb2/pvrusb2-dvb.c
index 2e64f98d1241..6504c97e0bbc 100644
--- a/trunk/drivers/media/video/pvrusb2/pvrusb2-dvb.c
+++ b/trunk/drivers/media/video/pvrusb2/pvrusb2-dvb.c
@@ -130,7 +130,7 @@ static void pvr2_dvb_stream_end(struct pvr2_dvb_adapter *adap)
 		for (idx = 0; idx < PVR2_DVB_BUFFER_COUNT; idx++) {
 			if (!(adap->buffer_storage[idx])) continue;
 			kfree(adap->buffer_storage[idx]);
-			adap->buffer_storage[idx] = 0;
+			adap->buffer_storage[idx] = NULL;
 		}
 		adap->stream_run = 0;
 	}
@@ -142,7 +142,7 @@ static int pvr2_dvb_stream_do_start(struct pvr2_dvb_adapter *adap)
 	unsigned int idx;
 	int ret;
 	struct pvr2_buffer *bp;
-	struct pvr2_stream *stream = 0;
+	struct pvr2_stream *stream = NULL;
 
 	if (adap->stream_run) return -EIO;
 
@@ -174,7 +174,7 @@ static int pvr2_dvb_stream_do_start(struct pvr2_dvb_adapter *adap)
 	ret = pvr2_hdw_set_streaming(adap->channel.hdw, 1);
 	if (ret < 0) return ret;
 
-	while ((bp = pvr2_stream_get_idle_buffer(stream)) != 0) {
+	while ((bp = pvr2_stream_get_idle_buffer(stream)) != NULL) {
 		ret = pvr2_buffer_queue(bp);
 		if (ret < 0) return ret;
 	}
diff --git a/trunk/drivers/media/video/pvrusb2/pvrusb2-v4l2.c b/trunk/drivers/media/video/pvrusb2/pvrusb2-v4l2.c
index 087a18245560..e9b5d4e91327 100644
--- a/trunk/drivers/media/video/pvrusb2/pvrusb2-v4l2.c
+++ b/trunk/drivers/media/video/pvrusb2/pvrusb2-v4l2.c
@@ -1261,7 +1261,7 @@ struct pvr2_v4l2 *pvr2_v4l2_create(struct pvr2_context *mnp)
  fail:
 	pvr2_trace(PVR2_TRACE_STRUCT,"Failure creating pvr2_v4l2 id=%p",vp);
 	pvr2_v4l2_destroy_no_lock(vp);
-	return 0;
+	return NULL;
 }
 
 /*
diff --git a/trunk/drivers/media/video/pvrusb2/pvrusb2-video-v4l.c b/trunk/drivers/media/video/pvrusb2/pvrusb2-video-v4l.c
index 7c47345501b6..2433a3160041 100644
--- a/trunk/drivers/media/video/pvrusb2/pvrusb2-video-v4l.c
+++ b/trunk/drivers/media/video/pvrusb2/pvrusb2-video-v4l.c
@@ -81,7 +81,7 @@ static void set_input(struct pvr2_v4l_decoder *ctxt)
 	pvr2_trace(PVR2_TRACE_CHIPS,"i2c v4l2 set_input(%d)",hdw->input_val);
 
 	if ((sid < ARRAY_SIZE(routing_schemes)) &&
-	    ((sp = routing_schemes + sid) != 0) &&
+	    ((sp = routing_schemes + sid) != NULL) &&
 	    (hdw->input_val >= 0) &&
 	    (hdw->input_val < sp->cnt)) {
 		route.input = sp->def[hdw->input_val];
diff --git a/trunk/drivers/media/video/v4l2-common.c b/trunk/drivers/media/video/v4l2-common.c
index 34deb68ae568..7cc42c1da457 100644
--- a/trunk/drivers/media/video/v4l2-common.c
+++ b/trunk/drivers/media/video/v4l2-common.c
@@ -716,7 +716,7 @@ int v4l2_i2c_attach(struct i2c_adapter *adapter, int address, struct i2c_driver
 	int err;
 
 	client = kzalloc(sizeof(struct i2c_client), GFP_KERNEL);
-	if (client == 0)
+	if (!client)
 		return -ENOMEM;
 
 	client->addr = address;
diff --git a/trunk/drivers/media/video/videobuf-core.c b/trunk/drivers/media/video/videobuf-core.c
index fc51e4918bbf..982f4463896c 100644
--- a/trunk/drivers/media/video/videobuf-core.c
+++ b/trunk/drivers/media/video/videobuf-core.c
@@ -97,7 +97,10 @@ int videobuf_iolock(struct videobuf_queue *q, struct videobuf_buffer *vb,
 void *videobuf_queue_to_vmalloc (struct videobuf_queue *q,
 			   struct videobuf_buffer *buf)
 {
-	return CALL(q, vmalloc, buf);
+	if (q->int_ops->vmalloc)
+		return q->int_ops->vmalloc(buf);
+	else
+		return NULL;
 }
 EXPORT_SYMBOL_GPL(videobuf_queue_to_vmalloc);
 
diff --git a/trunk/drivers/media/video/vino.c b/trunk/drivers/media/video/vino.c
index d545c98dd5e7..01ea99c9bc1a 100644
--- a/trunk/drivers/media/video/vino.c
+++ b/trunk/drivers/media/video/vino.c
@@ -13,7 +13,7 @@
 /*
  * TODO:
  * - remove "mark pages reserved-hacks" from memory allocation code
- *   and implement nopage()
+ *   and implement fault()
  * - check decimation, calculating and reporting image size when
  *   using decimation
  * - implement read(), user mode buffers and overlay (?)
diff --git a/trunk/drivers/media/video/zoran_procfs.c b/trunk/drivers/media/video/zoran_procfs.c
index 328ed6e7ac6a..870bc5a70e3f 100644
--- a/trunk/drivers/media/video/zoran_procfs.c
+++ b/trunk/drivers/media/video/zoran_procfs.c
@@ -180,6 +180,7 @@ static ssize_t zoran_write(struct file *file, const char __user *buffer,
 }
 
 static const struct file_operations zoran_operations = {
+	.owner		= THIS_MODULE,
 	.open		= zoran_open,
 	.read		= seq_read,
 	.write		= zoran_write,
@@ -195,10 +196,8 @@ zoran_proc_init (struct zoran *zr)
 	char name[8];
 
 	snprintf(name, 7, "zoran%d", zr->id);
-	if ((zr->zoran_proc = create_proc_entry(name, 0, NULL))) {
-		zr->zoran_proc->data = zr;
-		zr->zoran_proc->owner = THIS_MODULE;
-		zr->zoran_proc->proc_fops = &zoran_operations;
+	zr->zoran_proc = proc_create_data(name, 0, NULL, &zoran_operations, zr);
+	if (zr->zoran_proc != NULL) {
 		dprintk(2,
 			KERN_INFO
 			"%s: procfs entry /proc/%s allocated. data=%p\n",
diff --git a/trunk/drivers/message/i2o/i2o_block.c b/trunk/drivers/message/i2o/i2o_block.c
index a95314897402..81483de8c0fd 100644
--- a/trunk/drivers/message/i2o/i2o_block.c
+++ b/trunk/drivers/message/i2o/i2o_block.c
@@ -371,7 +371,7 @@ static int i2o_block_prep_req_fn(struct request_queue *q, struct request *req)
 	/* connect the i2o_block_request to the request */
 	if (!req->special) {
 		ireq = i2o_block_request_alloc();
-		if (unlikely(IS_ERR(ireq))) {
+		if (IS_ERR(ireq)) {
 			osm_debug("unable to allocate i2o_block_request!\n");
 			return BLKPREP_DEFER;
 		}
diff --git a/trunk/drivers/message/i2o/i2o_proc.c b/trunk/drivers/message/i2o/i2o_proc.c
index 6fdd072201f9..54a3016ff45d 100644
--- a/trunk/drivers/message/i2o/i2o_proc.c
+++ b/trunk/drivers/message/i2o/i2o_proc.c
@@ -1893,13 +1893,11 @@ static int i2o_proc_create_entries(struct proc_dir_entry *dir,
 	struct proc_dir_entry *tmp;
 
 	while (i2o_pe->name) {
-		tmp = create_proc_entry(i2o_pe->name, i2o_pe->mode, dir);
+		tmp = proc_create_data(i2o_pe->name, i2o_pe->mode, dir,
+				       i2o_pe->fops, data);
 		if (!tmp)
 			return -1;
 
-		tmp->data = data;
-		tmp->proc_fops = i2o_pe->fops;
-
 		i2o_pe++;
 	}
 
diff --git a/trunk/drivers/mfd/sm501.c b/trunk/drivers/mfd/sm501.c
index 13bac53db69a..6e655b4c6682 100644
--- a/trunk/drivers/mfd/sm501.c
+++ b/trunk/drivers/mfd/sm501.c
@@ -22,6 +22,7 @@
 
 #include <linux/sm501.h>
 #include <linux/sm501-regs.h>
+#include <linux/serial_8250.h>
 
 #include <asm/io.h>
 
@@ -723,13 +724,14 @@ static void sm501_device_release(struct device *dev)
 */
 
 static struct platform_device *
-sm501_create_subdev(struct sm501_devdata *sm,
-		    char *name, unsigned int res_count)
+sm501_create_subdev(struct sm501_devdata *sm, char *name,
+		    unsigned int res_count, unsigned int platform_data_size)
 {
 	struct sm501_device *smdev;
 
 	smdev = kzalloc(sizeof(struct sm501_device) +
-			sizeof(struct resource) * res_count, GFP_KERNEL);
+			(sizeof(struct resource) * res_count) +
+			platform_data_size, GFP_KERNEL);
 	if (!smdev)
 		return NULL;
 
@@ -737,11 +739,15 @@ sm501_create_subdev(struct sm501_devdata *sm,
 
 	smdev->pdev.name = name;
 	smdev->pdev.id = sm->pdev_id;
-	smdev->pdev.resource = (struct resource *)(smdev+1);
-	smdev->pdev.num_resources = res_count;
-
 	smdev->pdev.dev.parent = sm->dev;
 
+	if (res_count) {
+		smdev->pdev.resource = (struct resource *)(smdev+1);
+		smdev->pdev.num_resources = res_count;
+	}
+	if (platform_data_size)
+		smdev->pdev.dev.platform_data = (void *)(smdev+1);
+
 	return &smdev->pdev;
 }
 
@@ -829,7 +835,7 @@ static int sm501_register_usbhost(struct sm501_devdata *sm,
 {
 	struct platform_device *pdev;
 
-	pdev = sm501_create_subdev(sm, "sm501-usb", 3);
+	pdev = sm501_create_subdev(sm, "sm501-usb", 3, 0);
 	if (!pdev)
 		return -ENOMEM;
 
@@ -840,12 +846,55 @@ static int sm501_register_usbhost(struct sm501_devdata *sm,
 	return sm501_register_device(sm, pdev);
 }
 
+static void sm501_setup_uart_data(struct sm501_devdata *sm,
+				  struct plat_serial8250_port *uart_data,
+				  unsigned int offset)
+{
+	uart_data->membase = sm->regs + offset;
+	uart_data->mapbase = sm->io_res->start + offset;
+	uart_data->iotype = UPIO_MEM;
+	uart_data->irq = sm->irq;
+	uart_data->flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ;
+	uart_data->regshift = 2;
+	uart_data->uartclk = (9600 * 16);
+}
+
+static int sm501_register_uart(struct sm501_devdata *sm, int devices)
+{
+	struct platform_device *pdev;
+	struct plat_serial8250_port *uart_data;
+
+	pdev = sm501_create_subdev(sm, "serial8250", 0,
+				   sizeof(struct plat_serial8250_port) * 3);
+	if (!pdev)
+		return -ENOMEM;
+
+	uart_data = pdev->dev.platform_data;
+
+	if (devices & SM501_USE_UART0) {
+		sm501_setup_uart_data(sm, uart_data++, 0x30000);
+		sm501_unit_power(sm->dev, SM501_GATE_UART0, 1);
+		sm501_modify_reg(sm->dev, SM501_IRQ_MASK, 1 << 12, 0);
+		sm501_modify_reg(sm->dev, SM501_GPIO63_32_CONTROL, 0x01e0, 0);
+	}
+	if (devices & SM501_USE_UART1) {
+		sm501_setup_uart_data(sm, uart_data++, 0x30020);
+		sm501_unit_power(sm->dev, SM501_GATE_UART1, 1);
+		sm501_modify_reg(sm->dev, SM501_IRQ_MASK, 1 << 13, 0);
+		sm501_modify_reg(sm->dev, SM501_GPIO63_32_CONTROL, 0x1e00, 0);
+	}
+
+	pdev->id = PLAT8250_DEV_SM501;
+
+	return sm501_register_device(sm, pdev);
+}
+
 static int sm501_register_display(struct sm501_devdata *sm,
 				  resource_size_t *mem_avail)
 {
 	struct platform_device *pdev;
 
-	pdev = sm501_create_subdev(sm, "sm501-fb", 4);
+	pdev = sm501_create_subdev(sm, "sm501-fb", 4, 0);
 	if (!pdev)
 		return -ENOMEM;
 
@@ -963,6 +1012,7 @@ static unsigned int sm501_mem_local[] = {
 
 static int sm501_init_dev(struct sm501_devdata *sm)
 {
+	struct sm501_initdata *idata;
 	resource_size_t mem_avail;
 	unsigned long dramctrl;
 	unsigned long devid;
@@ -980,6 +1030,9 @@ static int sm501_init_dev(struct sm501_devdata *sm)
 		return -EINVAL;
 	}
 
+	/* disable irqs */
+	writel(0, sm->regs + SM501_IRQ_MASK);
+
 	dramctrl = readl(sm->regs + SM501_DRAM_CONTROL);
 	mem_avail = sm501_mem_local[(dramctrl >> 13) & 0x7];
 
@@ -998,15 +1051,14 @@ static int sm501_init_dev(struct sm501_devdata *sm)
 
 	/* check to see if we have some device initialisation */
 
-	if (sm->platdata) {
-		struct sm501_platdata *pdata = sm->platdata;
+	idata = sm->platdata ? sm->platdata->init : NULL;
+	if (idata) {
+		sm501_init_regs(sm, idata);
 
-		if (pdata->init) {
-			sm501_init_regs(sm, sm->platdata->init);
-
-			if (pdata->init->devices & SM501_USE_USB_HOST)
-				sm501_register_usbhost(sm, &mem_avail);
-		}
+		if (idata->devices & SM501_USE_USB_HOST)
+			sm501_register_usbhost(sm, &mem_avail);
+		if (idata->devices & (SM501_USE_UART0 | SM501_USE_UART1))
+			sm501_register_uart(sm, idata->devices);
 	}
 
 	ret = sm501_check_clocks(sm);
diff --git a/trunk/drivers/mfd/ucb1x00-ts.c b/trunk/drivers/mfd/ucb1x00-ts.c
index 5e859486eaf8..ad34e2d22524 100644
--- a/trunk/drivers/mfd/ucb1x00-ts.c
+++ b/trunk/drivers/mfd/ucb1x00-ts.c
@@ -204,8 +204,7 @@ static inline int ucb1x00_ts_pen_down(struct ucb1x00_ts *ts)
 static int ucb1x00_thread(void *_ts)
 {
 	struct ucb1x00_ts *ts = _ts;
-	struct task_struct *tsk = current;
-	DECLARE_WAITQUEUE(wait, tsk);
+	DECLARE_WAITQUEUE(wait, current);
 	int valid = 0;
 
 	set_freezable();
@@ -234,7 +233,7 @@ static int ucb1x00_thread(void *_ts)
 
 
 		if (ucb1x00_ts_pen_down(ts)) {
-			set_task_state(tsk, TASK_INTERRUPTIBLE);
+			set_current_state(TASK_INTERRUPTIBLE);
 
 			ucb1x00_enable_irq(ts->ucb, UCB_IRQ_TSPX, machine_is_collie() ? UCB_RISING : UCB_FALLING);
 			ucb1x00_disable(ts->ucb);
@@ -262,7 +261,7 @@ static int ucb1x00_thread(void *_ts)
 				valid = 1;
 			}
 
-			set_task_state(tsk, TASK_INTERRUPTIBLE);
+			set_current_state(TASK_INTERRUPTIBLE);
 			timeout = HZ / 100;
 		}
 
diff --git a/trunk/drivers/misc/enclosure.c b/trunk/drivers/misc/enclosure.c
index fafb57fed761..0736cff9d97a 100644
--- a/trunk/drivers/misc/enclosure.c
+++ b/trunk/drivers/misc/enclosure.c
@@ -31,7 +31,6 @@
 static LIST_HEAD(container_list);
 static DEFINE_MUTEX(container_list_lock);
 static struct class enclosure_class;
-static struct class enclosure_component_class;
 
 /**
  * enclosure_find - find an enclosure given a device
@@ -166,6 +165,40 @@ void enclosure_unregister(struct enclosure_device *edev)
 }
 EXPORT_SYMBOL_GPL(enclosure_unregister);
 
+#define ENCLOSURE_NAME_SIZE	64
+
+static void enclosure_link_name(struct enclosure_component *cdev, char *name)
+{
+	strcpy(name, "enclosure_device:");
+	strcat(name, cdev->cdev.bus_id);
+}
+
+static void enclosure_remove_links(struct enclosure_component *cdev)
+{
+	char name[ENCLOSURE_NAME_SIZE];
+
+	enclosure_link_name(cdev, name);
+	sysfs_remove_link(&cdev->dev->kobj, name);
+	sysfs_remove_link(&cdev->cdev.kobj, "device");
+}
+
+static int enclosure_add_links(struct enclosure_component *cdev)
+{
+	int error;
+	char name[ENCLOSURE_NAME_SIZE];
+
+	error = sysfs_create_link(&cdev->cdev.kobj, &cdev->dev->kobj, "device");
+	if (error)
+		return error;
+
+	enclosure_link_name(cdev, name);
+	error = sysfs_create_link(&cdev->dev->kobj, &cdev->cdev.kobj, name);
+	if (error)
+		sysfs_remove_link(&cdev->cdev.kobj, "device");
+
+	return error;
+}
+
 static void enclosure_release(struct device *cdev)
 {
 	struct enclosure_device *edev = to_enclosure_device(cdev);
@@ -178,10 +211,15 @@ static void enclosure_component_release(struct device *dev)
 {
 	struct enclosure_component *cdev = to_enclosure_component(dev);
 
-	put_device(cdev->dev);
+	if (cdev->dev) {
+		enclosure_remove_links(cdev);
+		put_device(cdev->dev);
+	}
 	put_device(dev->parent);
 }
 
+static struct attribute_group *enclosure_groups[];
+
 /**
  * enclosure_component_register - add a particular component to an enclosure
  * @edev:	the enclosure to add the component
@@ -217,12 +255,14 @@ enclosure_component_register(struct enclosure_device *edev,
 	ecomp->number = number;
 	cdev = &ecomp->cdev;
 	cdev->parent = get_device(&edev->edev);
-	cdev->class = &enclosure_component_class;
 	if (name)
 		snprintf(cdev->bus_id, BUS_ID_SIZE, "%s", name);
 	else
 		snprintf(cdev->bus_id, BUS_ID_SIZE, "%u", number);
 
+	cdev->release = enclosure_component_release;
+	cdev->groups = enclosure_groups;
+
 	err = device_register(cdev);
 	if (err)
 		ERR_PTR(err);
@@ -255,10 +295,12 @@ int enclosure_add_device(struct enclosure_device *edev, int component,
 
 	cdev = &edev->component[component];
 
-	device_del(&cdev->cdev);
+	if (cdev->dev)
+		enclosure_remove_links(cdev);
+
 	put_device(cdev->dev);
 	cdev->dev = get_device(dev);
-	return device_add(&cdev->cdev);
+	return enclosure_add_links(cdev);
 }
 EXPORT_SYMBOL_GPL(enclosure_add_device);
 
@@ -442,24 +484,32 @@ static ssize_t get_component_type(struct device *cdev,
 }
 
 
-static struct device_attribute enclosure_component_attrs[] = {
-	__ATTR(fault, S_IRUGO | S_IWUSR, get_component_fault,
-	       set_component_fault),
-	__ATTR(status, S_IRUGO | S_IWUSR, get_component_status,
-	       set_component_status),
-	__ATTR(active, S_IRUGO | S_IWUSR, get_component_active,
-	       set_component_active),
-	__ATTR(locate, S_IRUGO | S_IWUSR, get_component_locate,
-	       set_component_locate),
-	__ATTR(type, S_IRUGO, get_component_type, NULL),
-	__ATTR_NULL
+static DEVICE_ATTR(fault, S_IRUGO | S_IWUSR, get_component_fault,
+		    set_component_fault);
+static DEVICE_ATTR(status, S_IRUGO | S_IWUSR, get_component_status,
+		   set_component_status);
+static DEVICE_ATTR(active, S_IRUGO | S_IWUSR, get_component_active,
+		   set_component_active);
+static DEVICE_ATTR(locate, S_IRUGO | S_IWUSR, get_component_locate,
+		   set_component_locate);
+static DEVICE_ATTR(type, S_IRUGO, get_component_type, NULL);
+
+static struct attribute *enclosure_component_attrs[] = {
+	&dev_attr_fault.attr,
+	&dev_attr_status.attr,
+	&dev_attr_active.attr,
+	&dev_attr_locate.attr,
+	&dev_attr_type.attr,
+	NULL
 };
 
-static struct class enclosure_component_class =  {
-	.name			= "enclosure_component",
-	.owner			= THIS_MODULE,
-	.dev_attrs	= enclosure_component_attrs,
-	.dev_release		= enclosure_component_release,
+static struct attribute_group enclosure_group = {
+	.attrs = enclosure_component_attrs,
+};
+
+static struct attribute_group *enclosure_groups[] = {
+	&enclosure_group,
+	NULL
 };
 
 static int __init enclosure_init(void)
@@ -469,20 +519,12 @@ static int __init enclosure_init(void)
 	err = class_register(&enclosure_class);
 	if (err)
 		return err;
-	err = class_register(&enclosure_component_class);
-	if (err)
-		goto err_out;
 
 	return 0;
- err_out:
-	class_unregister(&enclosure_class);
-
-	return err;
 }
 
 static void __exit enclosure_exit(void)
 {
-	class_unregister(&enclosure_component_class);
 	class_unregister(&enclosure_class);
 }
 
diff --git a/trunk/drivers/misc/hdpuftrs/hdpu_cpustate.c b/trunk/drivers/misc/hdpuftrs/hdpu_cpustate.c
index 302e92418bbe..ff51ab67231c 100644
--- a/trunk/drivers/misc/hdpuftrs/hdpu_cpustate.c
+++ b/trunk/drivers/misc/hdpuftrs/hdpu_cpustate.c
@@ -210,13 +210,10 @@ static int hdpu_cpustate_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	proc_de = create_proc_entry("sky_cpustate", 0666, &proc_root);
+	proc_de = proc_create("sky_cpustate", 0666, NULL, &proc_cpustate);
 	if (!proc_de) {
 		printk(KERN_WARNING "sky_cpustate: "
 		       "Unable to create proc entry\n");
-	} else {
-		proc_de->proc_fops = &proc_cpustate;
-		proc_de->owner = THIS_MODULE;
 	}
 
 	printk(KERN_INFO "Sky CPU State Driver v" SKY_CPUSTATE_VERSION "\n");
diff --git a/trunk/drivers/misc/hdpuftrs/hdpu_nexus.c b/trunk/drivers/misc/hdpuftrs/hdpu_nexus.c
index 2fa36f7a6eb3..08e26beefe64 100644
--- a/trunk/drivers/misc/hdpuftrs/hdpu_nexus.c
+++ b/trunk/drivers/misc/hdpuftrs/hdpu_nexus.c
@@ -102,22 +102,17 @@ static int hdpu_nexus_probe(struct platform_device *pdev)
 		printk(KERN_ERR "sky_nexus: Could not map slot id\n");
 	}
 
-	hdpu_slot_id = create_proc_entry("sky_slot_id", 0666, &proc_root);
+	hdpu_slot_id = proc_create("sky_slot_id", 0666, NULL, &proc_slot_id);
 	if (!hdpu_slot_id) {
 		printk(KERN_WARNING "sky_nexus: "
 		       "Unable to create proc dir entry: sky_slot_id\n");
-	} else {
-		hdpu_slot_id->proc_fops = &proc_slot_id;
-		hdpu_slot_id->owner = THIS_MODULE;
 	}
 
-	hdpu_chassis_id = create_proc_entry("sky_chassis_id", 0666, &proc_root);
-	if (!hdpu_chassis_id) {
+	hdpu_chassis_id = proc_create("sky_chassis_id", 0666, NULL,
+				      &proc_chassis_id);
+	if (!hdpu_chassis_id)
 		printk(KERN_WARNING "sky_nexus: "
 		       "Unable to create proc dir entry: sky_chassis_id\n");
-	} else {
-		hdpu_chassis_id->proc_fops = &proc_chassis_id;
-		hdpu_chassis_id->owner = THIS_MODULE;
 	}
 
 	return 0;
@@ -128,8 +123,8 @@ static int hdpu_nexus_remove(struct platform_device *pdev)
 	slot_id = -1;
 	chassis_id = -1;
 
-	remove_proc_entry("sky_slot_id", &proc_root);
-	remove_proc_entry("sky_chassis_id", &proc_root);
+	remove_proc_entry("sky_slot_id", NULL);
+	remove_proc_entry("sky_chassis_id", NULL);
 
 	hdpu_slot_id = 0;
 	hdpu_chassis_id = 0;
diff --git a/trunk/drivers/misc/ibmasm/command.c b/trunk/drivers/misc/ibmasm/command.c
index 1a0e7978226a..276d3fb68094 100644
--- a/trunk/drivers/misc/ibmasm/command.c
+++ b/trunk/drivers/misc/ibmasm/command.c
@@ -96,7 +96,7 @@ static inline void do_exec_command(struct service_processor *sp)
 {
 	char tsbuf[32];
 
-	dbg("%s:%d at %s\n", __FUNCTION__, __LINE__, get_timestamp(tsbuf));
+	dbg("%s:%d at %s\n", __func__, __LINE__, get_timestamp(tsbuf));
 
 	if (ibmasm_send_i2o_message(sp)) {
 		sp->current_command->status = IBMASM_CMD_FAILED;
@@ -119,7 +119,7 @@ void ibmasm_exec_command(struct service_processor *sp, struct command *cmd)
 	unsigned long flags;
 	char tsbuf[32];
 
-	dbg("%s:%d at %s\n", __FUNCTION__, __LINE__, get_timestamp(tsbuf));
+	dbg("%s:%d at %s\n", __func__, __LINE__, get_timestamp(tsbuf));
 
 	spin_lock_irqsave(&sp->lock, flags);
 
@@ -139,7 +139,7 @@ static void exec_next_command(struct service_processor *sp)
 	unsigned long flags;
 	char tsbuf[32];
 
-	dbg("%s:%d at %s\n", __FUNCTION__, __LINE__, get_timestamp(tsbuf));
+	dbg("%s:%d at %s\n", __func__, __LINE__, get_timestamp(tsbuf));
 
 	spin_lock_irqsave(&sp->lock, flags);
 	sp->current_command = dequeue_command(sp);
diff --git a/trunk/drivers/misc/ibmasm/heartbeat.c b/trunk/drivers/misc/ibmasm/heartbeat.c
index 3036e785b3e4..1bc4306572a4 100644
--- a/trunk/drivers/misc/ibmasm/heartbeat.c
+++ b/trunk/drivers/misc/ibmasm/heartbeat.c
@@ -75,9 +75,9 @@ void ibmasm_heartbeat_exit(struct service_processor *sp)
 {
 	char tsbuf[32];
 
-	dbg("%s:%d at %s\n", __FUNCTION__, __LINE__, get_timestamp(tsbuf));
+	dbg("%s:%d at %s\n", __func__, __LINE__, get_timestamp(tsbuf));
 	ibmasm_wait_for_response(sp->heartbeat, IBMASM_CMD_TIMEOUT_NORMAL);
-	dbg("%s:%d at %s\n", __FUNCTION__, __LINE__, get_timestamp(tsbuf));
+	dbg("%s:%d at %s\n", __func__, __LINE__, get_timestamp(tsbuf));
 	suspend_heartbeats = 1;
 	command_put(sp->heartbeat);
 }
@@ -88,7 +88,7 @@ void ibmasm_receive_heartbeat(struct service_processor *sp,  void *message, size
 	struct dot_command_header *header = (struct dot_command_header *)cmd->buffer;
 	char tsbuf[32];
 
-	dbg("%s:%d at %s\n", __FUNCTION__, __LINE__, get_timestamp(tsbuf));
+	dbg("%s:%d at %s\n", __func__, __LINE__, get_timestamp(tsbuf));
 	if (suspend_heartbeats)
 		return;
 
diff --git a/trunk/drivers/misc/intel_menlow.c b/trunk/drivers/misc/intel_menlow.c
index 0c0bb3093e07..80a136352408 100644
--- a/trunk/drivers/misc/intel_menlow.c
+++ b/trunk/drivers/misc/intel_menlow.c
@@ -175,19 +175,17 @@ static int intel_menlow_memory_add(struct acpi_device *device)
 		goto end;
 	}
 
-	if (cdev) {
-		acpi_driver_data(device) = cdev;
-		result = sysfs_create_link(&device->dev.kobj,
-					&cdev->device.kobj, "thermal_cooling");
-		if (result)
-			goto unregister;
-
-		result = sysfs_create_link(&cdev->device.kobj,
-					&device->dev.kobj, "device");
-		if (result) {
-			sysfs_remove_link(&device->dev.kobj, "thermal_cooling");
-			goto unregister;
-		}
+	acpi_driver_data(device) = cdev;
+	result = sysfs_create_link(&device->dev.kobj,
+				&cdev->device.kobj, "thermal_cooling");
+	if (result)
+		goto unregister;
+
+	result = sysfs_create_link(&cdev->device.kobj,
+				&device->dev.kobj, "device");
+	if (result) {
+		sysfs_remove_link(&device->dev.kobj, "thermal_cooling");
+		goto unregister;
 	}
 
  end:
diff --git a/trunk/drivers/misc/ioc4.c b/trunk/drivers/misc/ioc4.c
index 05172d2613d6..6f76573e7c8a 100644
--- a/trunk/drivers/misc/ioc4.c
+++ b/trunk/drivers/misc/ioc4.c
@@ -75,7 +75,7 @@ ioc4_register_submodule(struct ioc4_submodule *is)
 			printk(KERN_WARNING
 			       "%s: IOC4 submodule %s probe failed "
 			       "for pci_dev %s",
-			       __FUNCTION__, module_name(is->is_owner),
+			       __func__, module_name(is->is_owner),
 			       pci_name(idd->idd_pdev));
 		}
 	}
@@ -102,7 +102,7 @@ ioc4_unregister_submodule(struct ioc4_submodule *is)
 			printk(KERN_WARNING
 			       "%s: IOC4 submodule %s remove failed "
 			       "for pci_dev %s.\n",
-			       __FUNCTION__, module_name(is->is_owner),
+			       __func__, module_name(is->is_owner),
 			       pci_name(idd->idd_pdev));
 		}
 	}
@@ -282,7 +282,7 @@ ioc4_probe(struct pci_dev *pdev, const struct pci_device_id *pci_id)
 	if ((ret = pci_enable_device(pdev))) {
 		printk(KERN_WARNING
 		       "%s: Failed to enable IOC4 device for pci_dev %s.\n",
-		       __FUNCTION__, pci_name(pdev));
+		       __func__, pci_name(pdev));
 		goto out;
 	}
 	pci_set_master(pdev);
@@ -292,7 +292,7 @@ ioc4_probe(struct pci_dev *pdev, const struct pci_device_id *pci_id)
 	if (!idd) {
 		printk(KERN_WARNING
 		       "%s: Failed to allocate IOC4 data for pci_dev %s.\n",
-		       __FUNCTION__, pci_name(pdev));
+		       __func__, pci_name(pdev));
 		ret = -ENODEV;
 		goto out_idd;
 	}
@@ -307,7 +307,7 @@ ioc4_probe(struct pci_dev *pdev, const struct pci_device_id *pci_id)
 		printk(KERN_WARNING
 		       "%s: Unable to find IOC4 misc resource "
 		       "for pci_dev %s.\n",
-		       __FUNCTION__, pci_name(idd->idd_pdev));
+		       __func__, pci_name(idd->idd_pdev));
 		ret = -ENODEV;
 		goto out_pci;
 	}
@@ -316,7 +316,7 @@ ioc4_probe(struct pci_dev *pdev, const struct pci_device_id *pci_id)
 		printk(KERN_WARNING
 		       "%s: Unable to request IOC4 misc region "
 		       "for pci_dev %s.\n",
-		       __FUNCTION__, pci_name(idd->idd_pdev));
+		       __func__, pci_name(idd->idd_pdev));
 		ret = -ENODEV;
 		goto out_pci;
 	}
@@ -326,7 +326,7 @@ ioc4_probe(struct pci_dev *pdev, const struct pci_device_id *pci_id)
 		printk(KERN_WARNING
 		       "%s: Unable to remap IOC4 misc region "
 		       "for pci_dev %s.\n",
-		       __FUNCTION__, pci_name(idd->idd_pdev));
+		       __func__, pci_name(idd->idd_pdev));
 		ret = -ENODEV;
 		goto out_misc_region;
 	}
@@ -372,7 +372,7 @@ ioc4_probe(struct pci_dev *pdev, const struct pci_device_id *pci_id)
 			printk(KERN_WARNING
 			       "%s: IOC4 submodule 0x%s probe failed "
 			       "for pci_dev %s.\n",
-			       __FUNCTION__, module_name(is->is_owner),
+			       __func__, module_name(is->is_owner),
 			       pci_name(idd->idd_pdev));
 		}
 	}
@@ -406,7 +406,7 @@ ioc4_remove(struct pci_dev *pdev)
 			printk(KERN_WARNING
 			       "%s: IOC4 submodule 0x%s remove failed "
 			       "for pci_dev %s.\n",
-			       __FUNCTION__, module_name(is->is_owner),
+			       __func__, module_name(is->is_owner),
 			       pci_name(idd->idd_pdev));
 		}
 	}
@@ -418,7 +418,7 @@ ioc4_remove(struct pci_dev *pdev)
 		printk(KERN_WARNING
 		       "%s: Unable to get IOC4 misc mapping for pci_dev %s. "
 		       "Device removal may be incomplete.\n",
-		       __FUNCTION__, pci_name(idd->idd_pdev));
+		       __func__, pci_name(idd->idd_pdev));
 	}
 	release_mem_region(idd->idd_bar0, sizeof(struct ioc4_misc_regs));
 
diff --git a/trunk/drivers/misc/phantom.c b/trunk/drivers/misc/phantom.c
index 7fa61e907e1c..71d1c84e2fa8 100644
--- a/trunk/drivers/misc/phantom.c
+++ b/trunk/drivers/misc/phantom.c
@@ -12,6 +12,7 @@
  *  or alternatively, you might use OpenHaptics provided by Sensable.
  */
 
+#include <linux/compat.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/device.h>
@@ -91,11 +92,8 @@ static long phantom_ioctl(struct file *file, unsigned int cmd,
 	unsigned long flags;
 	unsigned int i;
 
-	if (_IOC_TYPE(cmd) != PH_IOC_MAGIC ||
-			_IOC_NR(cmd) > PH_IOC_MAXNR)
-		return -ENOTTY;
-
 	switch (cmd) {
+	case PHN_SETREG:
 	case PHN_SET_REG:
 		if (copy_from_user(&r, argp, sizeof(r)))
 			return -EFAULT;
@@ -126,6 +124,7 @@ static long phantom_ioctl(struct file *file, unsigned int cmd,
 			phantom_status(dev, dev->status & ~PHB_RUNNING);
 		spin_unlock_irqrestore(&dev->regs_lock, flags);
 		break;
+	case PHN_SETREGS:
 	case PHN_SET_REGS:
 		if (copy_from_user(&rs, argp, sizeof(rs)))
 			return -EFAULT;
@@ -143,6 +142,7 @@ static long phantom_ioctl(struct file *file, unsigned int cmd,
 		}
 		spin_unlock_irqrestore(&dev->regs_lock, flags);
 		break;
+	case PHN_GETREG:
 	case PHN_GET_REG:
 		if (copy_from_user(&r, argp, sizeof(r)))
 			return -EFAULT;
@@ -155,6 +155,7 @@ static long phantom_ioctl(struct file *file, unsigned int cmd,
 		if (copy_to_user(argp, &r, sizeof(r)))
 			return -EFAULT;
 		break;
+	case PHN_GETREGS:
 	case PHN_GET_REGS: {
 		u32 m;
 
@@ -168,6 +169,7 @@ static long phantom_ioctl(struct file *file, unsigned int cmd,
 		for (i = 0; i < m; i++)
 			if (rs.mask & BIT(i))
 				rs.values[i] = ioread32(dev->iaddr + i);
+		atomic_set(&dev->counter, 0);
 		spin_unlock_irqrestore(&dev->regs_lock, flags);
 
 		if (copy_to_user(argp, &rs, sizeof(rs)))
@@ -191,6 +193,20 @@ static long phantom_ioctl(struct file *file, unsigned int cmd,
 	return 0;
 }
 
+#ifdef CONFIG_COMPAT
+static long phantom_compat_ioctl(struct file *filp, unsigned int cmd,
+		unsigned long arg)
+{
+	if (_IOC_NR(cmd) <= 3 && _IOC_SIZE(cmd) == sizeof(compat_uptr_t)) {
+		cmd &= ~(_IOC_SIZEMASK << _IOC_SIZESHIFT);
+		cmd |= sizeof(void *) << _IOC_SIZESHIFT;
+	}
+	return phantom_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
+}
+#else
+#define phantom_compat_ioctl NULL
+#endif
+
 static int phantom_open(struct inode *inode, struct file *file)
 {
 	struct phantom_device *dev = container_of(inode->i_cdev,
@@ -239,11 +255,12 @@ static unsigned int phantom_poll(struct file *file, poll_table *wait)
 
 	pr_debug("phantom_poll: %d\n", atomic_read(&dev->counter));
 	poll_wait(file, &dev->wait, wait);
-	if (atomic_read(&dev->counter)) {
+
+	if (!(dev->status & PHB_RUNNING))
+		mask = POLLERR;
+	else if (atomic_read(&dev->counter))
 		mask = POLLIN | POLLRDNORM;
-		atomic_dec(&dev->counter);
-	} else if ((dev->status & PHB_RUNNING) == 0)
-		mask = POLLIN | POLLRDNORM | POLLERR;
+
 	pr_debug("phantom_poll end: %x/%d\n", mask, atomic_read(&dev->counter));
 
 	return mask;
@@ -253,6 +270,7 @@ static struct file_operations phantom_file_ops = {
 	.open = phantom_open,
 	.release = phantom_release,
 	.unlocked_ioctl = phantom_ioctl,
+	.compat_ioctl = phantom_compat_ioctl,
 	.poll = phantom_poll,
 };
 
diff --git a/trunk/drivers/misc/sony-laptop.c b/trunk/drivers/misc/sony-laptop.c
index 02ff3d19b1cc..00e48e2a9c11 100644
--- a/trunk/drivers/misc/sony-laptop.c
+++ b/trunk/drivers/misc/sony-laptop.c
@@ -961,7 +961,7 @@ static int sony_nc_resume(struct acpi_device *device)
 		ret = acpi_callsetfunc(sony_nc_acpi_handle, *item->acpiset,
 				       item->value, NULL);
 		if (ret < 0) {
-			printk("%s: %d\n", __FUNCTION__, ret);
+			printk("%s: %d\n", __func__, ret);
 			break;
 		}
 	}
@@ -1453,7 +1453,7 @@ static struct sonypi_eventtypes type4_events[] = {
 		udelay(1);						\
 	if (!n)								\
 		dprintk("command failed at %s : %s (line %d)\n",	\
-				__FILE__, __FUNCTION__, __LINE__);	\
+				__FILE__, __func__, __LINE__);	\
 }
 
 static u8 sony_pic_call1(u8 dev)
diff --git a/trunk/drivers/mmc/host/mmc_spi.c b/trunk/drivers/mmc/host/mmc_spi.c
index 365024b83d3d..35508584ac2a 100644
--- a/trunk/drivers/mmc/host/mmc_spi.c
+++ b/trunk/drivers/mmc/host/mmc_spi.c
@@ -340,7 +340,7 @@ static int mmc_spi_response_get(struct mmc_spi_host *host,
 
 	/* SPI R3, R4, or R7 == R1 + 4 bytes */
 	case MMC_RSP_SPI_R3:
-		cmd->resp[1] = be32_to_cpu(get_unaligned((u32 *)cp));
+		cmd->resp[1] = get_unaligned_be32(cp);
 		break;
 
 	/* SPI R1 == just one status byte */
diff --git a/trunk/drivers/mtd/maps/plat-ram.c b/trunk/drivers/mtd/maps/plat-ram.c
index f0b10ca05029..3eb2643b2328 100644
--- a/trunk/drivers/mtd/maps/plat-ram.c
+++ b/trunk/drivers/mtd/maps/plat-ram.c
@@ -209,7 +209,7 @@ static int platram_probe(struct platform_device *pdev)
 	/* probe for the right mtd map driver
 	 * supplied by the platform_data struct */
 
-	if (pdata->map_probes != 0) {
+	if (pdata->map_probes) {
 		const char **map_probes = pdata->map_probes;
 
 		for ( ; !info->mtd && *map_probes; map_probes++)
diff --git a/trunk/drivers/net/Kconfig b/trunk/drivers/net/Kconfig
index 0697aa8ea774..f90a86ba7e2f 100644
--- a/trunk/drivers/net/Kconfig
+++ b/trunk/drivers/net/Kconfig
@@ -469,7 +469,7 @@ config SNI_82596
 
 config KORINA
 	tristate "Korina (IDT RC32434) Ethernet support"
-	depends on NET_ETHERNET && MIKROTIK_RB500
+	depends on NET_ETHERNET && MIKROTIK_RB532
 	help
 	  If you have a Mikrotik RouterBoard 500 or IDT RC32434
 	  based system say Y. Otherwise say N.
@@ -2011,7 +2011,7 @@ config E1000_DISABLE_PACKET_SPLIT
 
 config E1000E
 	tristate "Intel(R) PRO/1000 PCI-Express Gigabit Ethernet support"
-	depends on PCI
+	depends on PCI && (!SPARC32 || BROKEN)
 	---help---
 	  This driver supports the PCI-Express Intel(R) PRO/1000 gigabit
 	  ethernet family of adapters. For PCI or PCI-X e1000 adapters,
diff --git a/trunk/drivers/net/bonding/bond_main.c b/trunk/drivers/net/bonding/bond_main.c
index 6e91b4b7aabb..6425603bc379 100644
--- a/trunk/drivers/net/bonding/bond_main.c
+++ b/trunk/drivers/net/bonding/bond_main.c
@@ -3282,17 +3282,14 @@ static int bond_create_proc_entry(struct bonding *bond)
 	struct net_device *bond_dev = bond->dev;
 
 	if (bond_proc_dir) {
-		bond->proc_entry = create_proc_entry(bond_dev->name,
-						     S_IRUGO,
-						     bond_proc_dir);
+		bond->proc_entry = proc_create_data(bond_dev->name,
+						    S_IRUGO, bond_proc_dir,
+						    &bond_info_fops, bond);
 		if (bond->proc_entry == NULL) {
 			printk(KERN_WARNING DRV_NAME
 			       ": Warning: Cannot create /proc/net/%s/%s\n",
 			       DRV_NAME, bond_dev->name);
 		} else {
-			bond->proc_entry->data = bond;
-			bond->proc_entry->proc_fops = &bond_info_fops;
-			bond->proc_entry->owner = THIS_MODULE;
 			memcpy(bond->proc_file_name, bond_dev->name, IFNAMSIZ);
 		}
 	}
diff --git a/trunk/drivers/net/e100.c b/trunk/drivers/net/e100.c
index 2d139ec79777..f3cba5e24ec5 100644
--- a/trunk/drivers/net/e100.c
+++ b/trunk/drivers/net/e100.c
@@ -1802,7 +1802,7 @@ static int e100_rx_alloc_skb(struct nic *nic, struct rx *rx)
 	 * it is protected by the before last buffer's el bit being set */
 	if (rx->prev->skb) {
 		struct rfd *prev_rfd = (struct rfd *)rx->prev->skb->data;
-		put_unaligned(cpu_to_le32(rx->dma_addr), &prev_rfd->link);
+		put_unaligned_le32(rx->dma_addr, &prev_rfd->link);
 	}
 
 	return 0;
diff --git a/trunk/drivers/net/hamachi.c b/trunk/drivers/net/hamachi.c
index b53f6b6491b3..e5c2380f50ca 100644
--- a/trunk/drivers/net/hamachi.c
+++ b/trunk/drivers/net/hamachi.c
@@ -1508,7 +1508,7 @@ static int hamachi_rx(struct net_device *dev)
 					    hmp->rx_buf_sz,
 					    PCI_DMA_FROMDEVICE);
 		buf_addr = (u8 *) hmp->rx_skbuff[entry]->data;
-		frame_status = le32_to_cpu(get_unaligned((__le32*)&(buf_addr[data_size - 12])));
+		frame_status = get_unaligned_le32(&(buf_addr[data_size - 12]));
 		if (hamachi_debug > 4)
 			printk(KERN_DEBUG "  hamachi_rx() status was %8.8x.\n",
 				frame_status);
diff --git a/trunk/drivers/net/ibmveth.c b/trunk/drivers/net/ibmveth.c
index ce4fc2ec2fe4..00527805e4f1 100644
--- a/trunk/drivers/net/ibmveth.c
+++ b/trunk/drivers/net/ibmveth.c
@@ -1302,13 +1302,10 @@ static void ibmveth_proc_register_adapter(struct ibmveth_adapter *adapter)
 	if (ibmveth_proc_dir) {
 		char u_addr[10];
 		sprintf(u_addr, "%x", adapter->vdev->unit_address);
-		entry = create_proc_entry(u_addr, S_IFREG, ibmveth_proc_dir);
-		if (!entry) {
+		entry = proc_create_data(u_addr, S_IFREG, ibmveth_proc_dir,
+					 &ibmveth_proc_fops, adapter);
+		if (!entry)
 			ibmveth_error_printk("Cannot create adapter proc entry");
-		} else {
-			entry->data = (void *) adapter;
-			entry->proc_fops = &ibmveth_proc_fops;
-		}
 	}
 	return;
 }
diff --git a/trunk/drivers/net/irda/mcs7780.c b/trunk/drivers/net/irda/mcs7780.c
index 93916cf33f29..ad92d3ff1c40 100644
--- a/trunk/drivers/net/irda/mcs7780.c
+++ b/trunk/drivers/net/irda/mcs7780.c
@@ -464,7 +464,7 @@ static void mcs_unwrap_fir(struct mcs_cb *mcs, __u8 *buf, int len)
 	}
 
 	fcs = ~(crc32_le(~0, buf, new_len));
-	if(fcs != le32_to_cpu(get_unaligned((__le32 *)(buf+new_len)))) {
+	if(fcs != get_unaligned_le32(buf + new_len)) {
 		IRDA_ERROR("crc error calc 0x%x len %d\n", fcs, new_len);
 		mcs->stats.rx_errors++;
 		mcs->stats.rx_crc_errors++;
diff --git a/trunk/drivers/net/irda/stir4200.c b/trunk/drivers/net/irda/stir4200.c
index e59c485bc497..051963782749 100644
--- a/trunk/drivers/net/irda/stir4200.c
+++ b/trunk/drivers/net/irda/stir4200.c
@@ -329,7 +329,7 @@ static void fir_eof(struct stir_cb *stir)
 	}
 
 	fcs = ~(crc32_le(~0, rx_buff->data, len));
-	if (fcs != le32_to_cpu(get_unaligned((__le32 *)(rx_buff->data+len)))) {
+	if (fcs != get_unaligned_le32(rx_buff->data + len)) {
 		pr_debug("crc error calc 0x%x len %d\n", fcs, len);
 		stir->stats.rx_errors++;
 		stir->stats.rx_crc_errors++;
diff --git a/trunk/drivers/net/irda/vlsi_ir.c b/trunk/drivers/net/irda/vlsi_ir.c
index acd082a96a4f..d15e00b8591e 100644
--- a/trunk/drivers/net/irda/vlsi_ir.c
+++ b/trunk/drivers/net/irda/vlsi_ir.c
@@ -1674,13 +1674,12 @@ vlsi_irda_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (vlsi_proc_root != NULL) {
 		struct proc_dir_entry *ent;
 
-		ent = create_proc_entry(ndev->name, S_IFREG|S_IRUGO, vlsi_proc_root);
+		ent = proc_create_data(ndev->name, S_IFREG|S_IRUGO,
+				       vlsi_proc_root, VLSI_PROC_FOPS, ndev);
 		if (!ent) {
 			IRDA_WARNING("%s: failed to create proc entry\n",
 				     __FUNCTION__);
 		} else {
-			ent->data = ndev;
-			ent->proc_fops = VLSI_PROC_FOPS;
 			ent->size = 0;
 		}
 		idev->proc_entry = ent;
diff --git a/trunk/drivers/net/mlx4/alloc.c b/trunk/drivers/net/mlx4/alloc.c
index 75ef9d0d974d..f9d6b4dca180 100644
--- a/trunk/drivers/net/mlx4/alloc.c
+++ b/trunk/drivers/net/mlx4/alloc.c
@@ -196,3 +196,160 @@ void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf)
 	}
 }
 EXPORT_SYMBOL_GPL(mlx4_buf_free);
+
+static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device)
+{
+	struct mlx4_db_pgdir *pgdir;
+
+	pgdir = kzalloc(sizeof *pgdir, GFP_KERNEL);
+	if (!pgdir)
+		return NULL;
+
+	bitmap_fill(pgdir->order1, MLX4_DB_PER_PAGE / 2);
+	pgdir->bits[0] = pgdir->order0;
+	pgdir->bits[1] = pgdir->order1;
+	pgdir->db_page = dma_alloc_coherent(dma_device, PAGE_SIZE,
+					    &pgdir->db_dma, GFP_KERNEL);
+	if (!pgdir->db_page) {
+		kfree(pgdir);
+		return NULL;
+	}
+
+	return pgdir;
+}
+
+static int mlx4_alloc_db_from_pgdir(struct mlx4_db_pgdir *pgdir,
+				    struct mlx4_db *db, int order)
+{
+	int o;
+	int i;
+
+	for (o = order; o <= 1; ++o) {
+		i = find_first_bit(pgdir->bits[o], MLX4_DB_PER_PAGE >> o);
+		if (i < MLX4_DB_PER_PAGE >> o)
+			goto found;
+	}
+
+	return -ENOMEM;
+
+found:
+	clear_bit(i, pgdir->bits[o]);
+
+	i <<= o;
+
+	if (o > order)
+		set_bit(i ^ 1, pgdir->bits[order]);
+
+	db->u.pgdir = pgdir;
+	db->index   = i;
+	db->db      = pgdir->db_page + db->index;
+	db->dma     = pgdir->db_dma  + db->index * 4;
+	db->order   = order;
+
+	return 0;
+}
+
+int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_db_pgdir *pgdir;
+	int ret = 0;
+
+	mutex_lock(&priv->pgdir_mutex);
+
+	list_for_each_entry(pgdir, &priv->pgdir_list, list)
+		if (!mlx4_alloc_db_from_pgdir(pgdir, db, order))
+			goto out;
+
+	pgdir = mlx4_alloc_db_pgdir(&(dev->pdev->dev));
+	if (!pgdir) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	list_add(&pgdir->list, &priv->pgdir_list);
+
+	/* This should never fail -- we just allocated an empty page: */
+	WARN_ON(mlx4_alloc_db_from_pgdir(pgdir, db, order));
+
+out:
+	mutex_unlock(&priv->pgdir_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mlx4_db_alloc);
+
+void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int o;
+	int i;
+
+	mutex_lock(&priv->pgdir_mutex);
+
+	o = db->order;
+	i = db->index;
+
+	if (db->order == 0 && test_bit(i ^ 1, db->u.pgdir->order0)) {
+		clear_bit(i ^ 1, db->u.pgdir->order0);
+		++o;
+	}
+	i >>= o;
+	set_bit(i, db->u.pgdir->bits[o]);
+
+	if (bitmap_full(db->u.pgdir->order1, MLX4_DB_PER_PAGE / 2)) {
+		dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE,
+				  db->u.pgdir->db_page, db->u.pgdir->db_dma);
+		list_del(&db->u.pgdir->list);
+		kfree(db->u.pgdir);
+	}
+
+	mutex_unlock(&priv->pgdir_mutex);
+}
+EXPORT_SYMBOL_GPL(mlx4_db_free);
+
+int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
+		       int size, int max_direct)
+{
+	int err;
+
+	err = mlx4_db_alloc(dev, &wqres->db, 1);
+	if (err)
+		return err;
+
+	*wqres->db.db = 0;
+
+	err = mlx4_buf_alloc(dev, size, max_direct, &wqres->buf);
+	if (err)
+		goto err_db;
+
+	err = mlx4_mtt_init(dev, wqres->buf.npages, wqres->buf.page_shift,
+			    &wqres->mtt);
+	if (err)
+		goto err_buf;
+
+	err = mlx4_buf_write_mtt(dev, &wqres->mtt, &wqres->buf);
+	if (err)
+		goto err_mtt;
+
+	return 0;
+
+err_mtt:
+	mlx4_mtt_cleanup(dev, &wqres->mtt);
+err_buf:
+	mlx4_buf_free(dev, size, &wqres->buf);
+err_db:
+	mlx4_db_free(dev, &wqres->db);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_alloc_hwq_res);
+
+void mlx4_free_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
+		       int size)
+{
+	mlx4_mtt_cleanup(dev, &wqres->mtt);
+	mlx4_buf_free(dev, size, &wqres->buf);
+	mlx4_db_free(dev, &wqres->db);
+}
+EXPORT_SYMBOL_GPL(mlx4_free_hwq_res);
diff --git a/trunk/drivers/net/mlx4/cq.c b/trunk/drivers/net/mlx4/cq.c
index caa5bcf54e35..6fda0af9d0a6 100644
--- a/trunk/drivers/net/mlx4/cq.c
+++ b/trunk/drivers/net/mlx4/cq.c
@@ -180,7 +180,7 @@ int mlx4_cq_resize(struct mlx4_dev *dev, struct mlx4_cq *cq,
 	cq_context->mtt_base_addr_h = mtt_addr >> 32;
 	cq_context->mtt_base_addr_l = cpu_to_be32(mtt_addr & 0xffffffff);
 
-	err = mlx4_MODIFY_CQ(dev, mailbox, cq->cqn, 1);
+	err = mlx4_MODIFY_CQ(dev, mailbox, cq->cqn, 0);
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	return err;
diff --git a/trunk/drivers/net/mlx4/main.c b/trunk/drivers/net/mlx4/main.c
index 49a4acab5e82..a6aa49fc1d68 100644
--- a/trunk/drivers/net/mlx4/main.c
+++ b/trunk/drivers/net/mlx4/main.c
@@ -798,6 +798,9 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
 
+	INIT_LIST_HEAD(&priv->pgdir_list);
+	mutex_init(&priv->pgdir_mutex);
+
 	/*
 	 * Now reset the HCA before we touch the PCI capabilities or
 	 * attempt a firmware command, since a boot ROM may have left
diff --git a/trunk/drivers/net/mlx4/mlx4.h b/trunk/drivers/net/mlx4/mlx4.h
index 73336810e652..a4023c2dd050 100644
--- a/trunk/drivers/net/mlx4/mlx4.h
+++ b/trunk/drivers/net/mlx4/mlx4.h
@@ -257,6 +257,9 @@ struct mlx4_priv {
 	struct list_head	ctx_list;
 	spinlock_t		ctx_lock;
 
+	struct list_head        pgdir_list;
+	struct mutex            pgdir_mutex;
+
 	struct mlx4_fw		fw;
 	struct mlx4_cmd		cmd;
 
diff --git a/trunk/drivers/net/mlx4/qp.c b/trunk/drivers/net/mlx4/qp.c
index fa24e6597591..ee5484c44a18 100644
--- a/trunk/drivers/net/mlx4/qp.c
+++ b/trunk/drivers/net/mlx4/qp.c
@@ -299,3 +299,34 @@ int mlx4_qp_query(struct mlx4_dev *dev, struct mlx4_qp *qp,
 }
 EXPORT_SYMBOL_GPL(mlx4_qp_query);
 
+int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+		     struct mlx4_qp_context *context,
+		     struct mlx4_qp *qp, enum mlx4_qp_state *qp_state)
+{
+	int err;
+	int i;
+	enum mlx4_qp_state states[] = {
+		MLX4_QP_STATE_RST,
+		MLX4_QP_STATE_INIT,
+		MLX4_QP_STATE_RTR,
+		MLX4_QP_STATE_RTS
+	};
+
+	for (i = 0; i < ARRAY_SIZE(states) - 1; i++) {
+		context->flags &= cpu_to_be32(~(0xf << 28));
+		context->flags |= cpu_to_be32(states[i + 1] << 28);
+		err = mlx4_qp_modify(dev, mtt, states[i], states[i + 1],
+				     context, 0, 0, qp);
+		if (err) {
+			mlx4_err(dev, "Failed to bring QP to state: "
+				 "%d with error: %d\n",
+				 states[i + 1], err);
+			return err;
+		}
+
+		*qp_state = states[i + 1];
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_qp_to_ready);
diff --git a/trunk/drivers/net/myri10ge/myri10ge.c b/trunk/drivers/net/myri10ge/myri10ge.c
index cead81e80f0c..ef63c8d2bd7e 100644
--- a/trunk/drivers/net/myri10ge/myri10ge.c
+++ b/trunk/drivers/net/myri10ge/myri10ge.c
@@ -2437,7 +2437,7 @@ static int myri10ge_sw_tso(struct sk_buff *skb, struct net_device *dev)
 	int status;
 
 	segs = skb_gso_segment(skb, dev->features & ~NETIF_F_TSO6);
-	if (unlikely(IS_ERR(segs)))
+	if (IS_ERR(segs))
 		goto drop;
 
 	while (segs) {
diff --git a/trunk/drivers/net/pppoe.c b/trunk/drivers/net/pppoe.c
index 4fad4ddb3504..58a26a47af29 100644
--- a/trunk/drivers/net/pppoe.c
+++ b/trunk/drivers/net/pppoe.c
@@ -1052,11 +1052,9 @@ static int __init pppoe_proc_init(void)
 {
 	struct proc_dir_entry *p;
 
-	p = create_proc_entry("pppoe", S_IRUGO, init_net.proc_net);
+	p = proc_net_fops_create(&init_net, "pppoe", S_IRUGO, &pppoe_seq_fops);
 	if (!p)
 		return -ENOMEM;
-
-	p->proc_fops = &pppoe_seq_fops;
 	return 0;
 }
 #else /* CONFIG_PROC_FS */
diff --git a/trunk/drivers/net/pppol2tp.c b/trunk/drivers/net/pppol2tp.c
index 3d10ca050b79..244d7830c92a 100644
--- a/trunk/drivers/net/pppol2tp.c
+++ b/trunk/drivers/net/pppol2tp.c
@@ -2469,12 +2469,12 @@ static int __init pppol2tp_init(void)
 		goto out_unregister_pppol2tp_proto;
 
 #ifdef CONFIG_PROC_FS
-	pppol2tp_proc = create_proc_entry("pppol2tp", 0, init_net.proc_net);
+	pppol2tp_proc = proc_net_fops_create(&init_net, "pppol2tp", 0,
+					     &pppol2tp_proc_fops);
 	if (!pppol2tp_proc) {
 		err = -ENOMEM;
 		goto out_unregister_pppox_proto;
 	}
-	pppol2tp_proc->proc_fops = &pppol2tp_proc_fops;
 #endif /* CONFIG_PROC_FS */
 	printk(KERN_INFO "PPPoL2TP kernel driver, %s\n",
 	       PPPOL2TP_DRV_VERSION);
diff --git a/trunk/drivers/net/rionet.c b/trunk/drivers/net/rionet.c
index e7fd08adbbac..2b8fd68bc516 100644
--- a/trunk/drivers/net/rionet.c
+++ b/trunk/drivers/net/rionet.c
@@ -77,7 +77,7 @@ static int rionet_capable = 1;
  * could be made into a hash table to save memory depending
  * on system trade-offs.
  */
-static struct rio_dev *rionet_active[RIO_MAX_ROUTE_ENTRIES];
+static struct rio_dev **rionet_active;
 
 #define is_rionet_capable(pef, src_ops, dst_ops)		\
 			((pef & RIO_PEF_INB_MBOX) &&		\
@@ -195,7 +195,8 @@ static int rionet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	}
 
 	if (eth->h_dest[0] & 0x01) {
-		for (i = 0; i < RIO_MAX_ROUTE_ENTRIES; i++)
+		for (i = 0; i < RIO_MAX_ROUTE_ENTRIES(rnet->mport->sys_size);
+				i++)
 			if (rionet_active[i])
 				rionet_queue_tx_msg(skb, ndev,
 						    rionet_active[i]);
@@ -385,6 +386,8 @@ static void rionet_remove(struct rio_dev *rdev)
 	struct net_device *ndev = NULL;
 	struct rionet_peer *peer, *tmp;
 
+	free_pages((unsigned long)rionet_active, rdev->net->hport->sys_size ?
+					__ilog2(sizeof(void *)) + 4 : 0);
 	unregister_netdev(ndev);
 	kfree(ndev);
 
@@ -443,6 +446,15 @@ static int rionet_setup_netdev(struct rio_mport *mport)
 		goto out;
 	}
 
+	rionet_active = (struct rio_dev **)__get_free_pages(GFP_KERNEL,
+			mport->sys_size ? __ilog2(sizeof(void *)) + 4 : 0);
+	if (!rionet_active) {
+		rc = -ENOMEM;
+		goto out;
+	}
+	memset((void *)rionet_active, 0, sizeof(void *) *
+				RIO_MAX_ROUTE_ENTRIES(mport->sys_size));
+
 	/* Set up private area */
 	rnet = (struct rionet_private *)ndev->priv;
 	rnet->mport = mport;
diff --git a/trunk/drivers/net/tg3.c b/trunk/drivers/net/tg3.c
index e3f74c9f78bd..b66c75e3b8a1 100644
--- a/trunk/drivers/net/tg3.c
+++ b/trunk/drivers/net/tg3.c
@@ -4361,7 +4361,7 @@ static int tg3_tso_bug(struct tg3 *tp, struct sk_buff *skb)
 	}
 
 	segs = skb_gso_segment(skb, tp->dev->features & ~NETIF_F_TSO);
-	if (unlikely(IS_ERR(segs)))
+	if (IS_ERR(segs))
 		goto tg3_tso_bug_end;
 
 	do {
diff --git a/trunk/drivers/net/tulip/de4x5.c b/trunk/drivers/net/tulip/de4x5.c
index 6c6fc325c8f9..bc30c6e8fea2 100644
--- a/trunk/drivers/net/tulip/de4x5.c
+++ b/trunk/drivers/net/tulip/de4x5.c
@@ -482,7 +482,6 @@
 static char version[] __devinitdata = "de4x5.c:V0.546 2001/02/22 davies@maniac.ultranet.com\n";
 
 #define c_char const char
-#define TWIDDLE(a) (u_short)le16_to_cpu(get_unaligned((__le16 *)(a)))
 
 /*
 ** MII Information
@@ -4405,7 +4404,7 @@ srom_infoleaf_info(struct net_device *dev)
 	}
     }
 
-    lp->infoleaf_offset = TWIDDLE(p+1);
+	lp->infoleaf_offset = get_unaligned_le16(p + 1);
 
     return 0;
 }
@@ -4476,7 +4475,7 @@ srom_exec(struct net_device *dev, u_char *p)
 
     while (count--) {
 	gep_wr(((lp->chipset==DC21140) && (lp->ibn!=5) ?
-		                                   *p++ : TWIDDLE(w++)), dev);
+		                                   *p++ : get_unaligned_le16(w++)), dev);
 	mdelay(2);                          /* 2ms per action */
     }
 
@@ -4711,10 +4710,10 @@ type1_infoblock(struct net_device *dev, u_char count, u_char *p)
 	lp->active = *p++;
 	lp->phy[lp->active].gep = (*p ? p : NULL); p += (*p + 1);
 	lp->phy[lp->active].rst = (*p ? p : NULL); p += (*p + 1);
-	lp->phy[lp->active].mc  = TWIDDLE(p); p += 2;
-	lp->phy[lp->active].ana = TWIDDLE(p); p += 2;
-	lp->phy[lp->active].fdx = TWIDDLE(p); p += 2;
-	lp->phy[lp->active].ttm = TWIDDLE(p);
+	lp->phy[lp->active].mc  = get_unaligned_le16(p); p += 2;
+	lp->phy[lp->active].ana = get_unaligned_le16(p); p += 2;
+	lp->phy[lp->active].fdx = get_unaligned_le16(p); p += 2;
+	lp->phy[lp->active].ttm = get_unaligned_le16(p);
 	return 0;
     } else if ((lp->media == INIT) && (lp->timeout < 0)) {
         lp->ibn = 1;
@@ -4751,16 +4750,16 @@ type2_infoblock(struct net_device *dev, u_char count, u_char *p)
 	lp->infoblock_media = (*p) & MEDIA_CODE;
 
         if ((*p++) & EXT_FIELD) {
-	    lp->cache.csr13 = TWIDDLE(p); p += 2;
-	    lp->cache.csr14 = TWIDDLE(p); p += 2;
-	    lp->cache.csr15 = TWIDDLE(p); p += 2;
+	    lp->cache.csr13 = get_unaligned_le16(p); p += 2;
+	    lp->cache.csr14 = get_unaligned_le16(p); p += 2;
+	    lp->cache.csr15 = get_unaligned_le16(p); p += 2;
 	} else {
 	    lp->cache.csr13 = CSR13;
 	    lp->cache.csr14 = CSR14;
 	    lp->cache.csr15 = CSR15;
 	}
-        lp->cache.gepc = ((s32)(TWIDDLE(p)) << 16); p += 2;
-        lp->cache.gep  = ((s32)(TWIDDLE(p)) << 16);
+        lp->cache.gepc = ((s32)(get_unaligned_le16(p)) << 16); p += 2;
+        lp->cache.gep  = ((s32)(get_unaligned_le16(p)) << 16);
 	lp->infoblock_csr6 = OMR_SIA;
 	lp->useMII = false;
 
@@ -4792,10 +4791,10 @@ type3_infoblock(struct net_device *dev, u_char count, u_char *p)
 	if (MOTO_SROM_BUG) lp->active = 0;
 	lp->phy[lp->active].gep = (*p ? p : NULL); p += (2 * (*p) + 1);
 	lp->phy[lp->active].rst = (*p ? p : NULL); p += (2 * (*p) + 1);
-	lp->phy[lp->active].mc  = TWIDDLE(p); p += 2;
-	lp->phy[lp->active].ana = TWIDDLE(p); p += 2;
-	lp->phy[lp->active].fdx = TWIDDLE(p); p += 2;
-	lp->phy[lp->active].ttm = TWIDDLE(p); p += 2;
+	lp->phy[lp->active].mc  = get_unaligned_le16(p); p += 2;
+	lp->phy[lp->active].ana = get_unaligned_le16(p); p += 2;
+	lp->phy[lp->active].fdx = get_unaligned_le16(p); p += 2;
+	lp->phy[lp->active].ttm = get_unaligned_le16(p); p += 2;
 	lp->phy[lp->active].mci = *p;
 	return 0;
     } else if ((lp->media == INIT) && (lp->timeout < 0)) {
@@ -4835,8 +4834,8 @@ type4_infoblock(struct net_device *dev, u_char count, u_char *p)
         lp->cache.csr13 = CSR13;              /* Hard coded defaults */
 	lp->cache.csr14 = CSR14;
 	lp->cache.csr15 = CSR15;
-        lp->cache.gepc = ((s32)(TWIDDLE(p)) << 16); p += 2;
-        lp->cache.gep  = ((s32)(TWIDDLE(p)) << 16); p += 2;
+        lp->cache.gepc = ((s32)(get_unaligned_le16(p)) << 16); p += 2;
+        lp->cache.gep  = ((s32)(get_unaligned_le16(p)) << 16); p += 2;
 	csr6 = *p++;
 	flags = *p++;
 
diff --git a/trunk/drivers/net/tulip/de4x5.h b/trunk/drivers/net/tulip/de4x5.h
index 9fb8d7f07994..f5f33b3eb067 100644
--- a/trunk/drivers/net/tulip/de4x5.h
+++ b/trunk/drivers/net/tulip/de4x5.h
@@ -1017,4 +1017,4 @@ struct de4x5_ioctl {
 #define DE4X5_SET_OMR           0x0d /* Set the OMR Register contents */
 #define DE4X5_GET_REG           0x0e /* Get the DE4X5 Registers */
 
-#define MOTO_SROM_BUG    ((lp->active == 8) && (((le32_to_cpu(get_unaligned(((__le32 *)dev->dev_addr))))&0x00ffffff)==0x3e0008))
+#define MOTO_SROM_BUG    (lp->active == 8 && (get_unaligned_le32(dev->dev_addr) & 0x00ffffff) == 0x3e0008)
diff --git a/trunk/drivers/net/tulip/tulip.h b/trunk/drivers/net/tulip/tulip.h
index 908422f2f320..92c68a22f16b 100644
--- a/trunk/drivers/net/tulip/tulip.h
+++ b/trunk/drivers/net/tulip/tulip.h
@@ -25,6 +25,7 @@
 #include <linux/pci.h>
 #include <asm/io.h>
 #include <asm/irq.h>
+#include <asm/unaligned.h>
 
 
 
@@ -304,11 +305,7 @@ enum t21143_csr6_bits {
 
 #define RUN_AT(x) (jiffies + (x))
 
-#if defined(__i386__)			/* AKA get_unaligned() */
-#define get_u16(ptr) (*(u16 *)(ptr))
-#else
-#define get_u16(ptr) (((u8*)(ptr))[0] + (((u8*)(ptr))[1]<<8))
-#endif
+#define get_u16(ptr) get_unaligned_le16((ptr))
 
 struct medialeaf {
 	u8 type;
diff --git a/trunk/drivers/net/tulip/tulip_core.c b/trunk/drivers/net/tulip/tulip_core.c
index fa1c1c329a2d..f9d13fa05d64 100644
--- a/trunk/drivers/net/tulip/tulip_core.c
+++ b/trunk/drivers/net/tulip/tulip_core.c
@@ -327,8 +327,8 @@ static void tulip_up(struct net_device *dev)
 	tp->dirty_rx = tp->dirty_tx = 0;
 
 	if (tp->flags & MC_HASH_ONLY) {
-		u32 addr_low = le32_to_cpu(get_unaligned((__le32 *)dev->dev_addr));
-		u32 addr_high = le16_to_cpu(get_unaligned((__le16 *)(dev->dev_addr+4)));
+		u32 addr_low = get_unaligned_le32(dev->dev_addr);
+		u32 addr_high = get_unaligned_le16(dev->dev_addr + 4);
 		if (tp->chip_id == AX88140) {
 			iowrite32(0, ioaddr + CSR13);
 			iowrite32(addr_low,  ioaddr + CSR14);
@@ -1437,13 +1437,13 @@ static int __devinit tulip_init_one (struct pci_dev *pdev,
 			do
 				value = ioread32(ioaddr + CSR9);
 			while (value < 0  && --boguscnt > 0);
-			put_unaligned(cpu_to_le16(value), ((__le16*)dev->dev_addr) + i);
+			put_unaligned_le16(value, ((__le16 *)dev->dev_addr) + i);
 			sum += value & 0xffff;
 		}
 	} else if (chip_idx == COMET) {
 		/* No need to read the EEPROM. */
-		put_unaligned(cpu_to_le32(ioread32(ioaddr + 0xA4)), (__le32 *)dev->dev_addr);
-		put_unaligned(cpu_to_le16(ioread32(ioaddr + 0xA8)), (__le16 *)(dev->dev_addr + 4));
+		put_unaligned_le32(ioread32(ioaddr + 0xA4), dev->dev_addr);
+		put_unaligned_le16(ioread32(ioaddr + 0xA8), dev->dev_addr + 4);
 		for (i = 0; i < 6; i ++)
 			sum += dev->dev_addr[i];
 	} else {
diff --git a/trunk/drivers/net/wireless/Makefile b/trunk/drivers/net/wireless/Makefile
index c2642bc1d49b..2c343aae38d4 100644
--- a/trunk/drivers/net/wireless/Makefile
+++ b/trunk/drivers/net/wireless/Makefile
@@ -56,7 +56,7 @@ obj-$(CONFIG_RTL8187)	+= rtl8187.o
 
 obj-$(CONFIG_ADM8211)	+= adm8211.o
 
-obj-$(CONFIG_IWLCORE)	+= iwlwifi/
+obj-$(CONFIG_IWLWIFI)	+= iwlwifi/
 obj-$(CONFIG_RT2X00)	+= rt2x00/
 
 obj-$(CONFIG_P54_COMMON)	+= p54/
diff --git a/trunk/drivers/net/wireless/airo.c b/trunk/drivers/net/wireless/airo.c
index 932d6b1c9d0b..45f47c1c0a35 100644
--- a/trunk/drivers/net/wireless/airo.c
+++ b/trunk/drivers/net/wireless/airo.c
@@ -3657,7 +3657,7 @@ void mpi_receive_802_11 (struct airo_info *ai)
 	ptr += hdrlen;
 	if (hdrlen == 24)
 		ptr += 6;
-	gap = le16_to_cpu(get_unaligned((__le16 *)ptr));
+	gap = get_unaligned_le16(ptr);
 	ptr += sizeof(__le16);
 	if (gap) {
 		if (gap <= 8)
@@ -4347,24 +4347,28 @@ static int proc_config_open( struct inode *inode, struct file *file );
 static int proc_wepkey_open( struct inode *inode, struct file *file );
 
 static const struct file_operations proc_statsdelta_ops = {
+	.owner		= THIS_MODULE,
 	.read		= proc_read,
 	.open		= proc_statsdelta_open,
 	.release	= proc_close
 };
 
 static const struct file_operations proc_stats_ops = {
+	.owner		= THIS_MODULE,
 	.read		= proc_read,
 	.open		= proc_stats_open,
 	.release	= proc_close
 };
 
 static const struct file_operations proc_status_ops = {
+	.owner		= THIS_MODULE,
 	.read		= proc_read,
 	.open		= proc_status_open,
 	.release	= proc_close
 };
 
 static const struct file_operations proc_SSID_ops = {
+	.owner		= THIS_MODULE,
 	.read		= proc_read,
 	.write		= proc_write,
 	.open		= proc_SSID_open,
@@ -4372,6 +4376,7 @@ static const struct file_operations proc_SSID_ops = {
 };
 
 static const struct file_operations proc_BSSList_ops = {
+	.owner		= THIS_MODULE,
 	.read		= proc_read,
 	.write		= proc_write,
 	.open		= proc_BSSList_open,
@@ -4379,6 +4384,7 @@ static const struct file_operations proc_BSSList_ops = {
 };
 
 static const struct file_operations proc_APList_ops = {
+	.owner		= THIS_MODULE,
 	.read		= proc_read,
 	.write		= proc_write,
 	.open		= proc_APList_open,
@@ -4386,6 +4392,7 @@ static const struct file_operations proc_APList_ops = {
 };
 
 static const struct file_operations proc_config_ops = {
+	.owner		= THIS_MODULE,
 	.read		= proc_read,
 	.write		= proc_write,
 	.open		= proc_config_open,
@@ -4393,6 +4400,7 @@ static const struct file_operations proc_config_ops = {
 };
 
 static const struct file_operations proc_wepkey_ops = {
+	.owner		= THIS_MODULE,
 	.read		= proc_read,
 	.write		= proc_write,
 	.open		= proc_wepkey_open,
@@ -4411,10 +4419,6 @@ struct proc_data {
 	void (*on_close) (struct inode *, struct file *);
 };
 
-#ifndef SETPROC_OPS
-#define SETPROC_OPS(entry, ops) (entry)->proc_fops = &(ops)
-#endif
-
 static int setup_proc_entry( struct net_device *dev,
 			     struct airo_info *apriv ) {
 	struct proc_dir_entry *entry;
@@ -4430,100 +4434,76 @@ static int setup_proc_entry( struct net_device *dev,
 	apriv->proc_entry->owner = THIS_MODULE;
 
 	/* Setup the StatsDelta */
-	entry = create_proc_entry("StatsDelta",
-				  S_IFREG | (S_IRUGO&proc_perm),
-				  apriv->proc_entry);
+	entry = proc_create_data("StatsDelta",
+				 S_IFREG | (S_IRUGO&proc_perm),
+				 apriv->proc_entry, &proc_statsdelta_ops, dev);
 	if (!entry)
 		goto fail_stats_delta;
 	entry->uid = proc_uid;
 	entry->gid = proc_gid;
-	entry->data = dev;
-	entry->owner = THIS_MODULE;
-	SETPROC_OPS(entry, proc_statsdelta_ops);
 
 	/* Setup the Stats */
-	entry = create_proc_entry("Stats",
-				  S_IFREG | (S_IRUGO&proc_perm),
-				  apriv->proc_entry);
+	entry = proc_create_data("Stats",
+				 S_IFREG | (S_IRUGO&proc_perm),
+				 apriv->proc_entry, &proc_stats_ops, dev);
 	if (!entry)
 		goto fail_stats;
 	entry->uid = proc_uid;
 	entry->gid = proc_gid;
-	entry->data = dev;
-	entry->owner = THIS_MODULE;
-	SETPROC_OPS(entry, proc_stats_ops);
 
 	/* Setup the Status */
-	entry = create_proc_entry("Status",
-				  S_IFREG | (S_IRUGO&proc_perm),
-				  apriv->proc_entry);
+	entry = proc_create_data("Status",
+				 S_IFREG | (S_IRUGO&proc_perm),
+				 apriv->proc_entry, &proc_status_ops, dev);
 	if (!entry)
 		goto fail_status;
 	entry->uid = proc_uid;
 	entry->gid = proc_gid;
-	entry->data = dev;
-	entry->owner = THIS_MODULE;
-	SETPROC_OPS(entry, proc_status_ops);
 
 	/* Setup the Config */
-	entry = create_proc_entry("Config",
-				  S_IFREG | proc_perm,
-				  apriv->proc_entry);
+	entry = proc_create_data("Config",
+				 S_IFREG | proc_perm,
+				 apriv->proc_entry, &proc_config_ops, dev);
 	if (!entry)
 		goto fail_config;
 	entry->uid = proc_uid;
 	entry->gid = proc_gid;
-	entry->data = dev;
-	entry->owner = THIS_MODULE;
-	SETPROC_OPS(entry, proc_config_ops);
 
 	/* Setup the SSID */
-	entry = create_proc_entry("SSID",
-				  S_IFREG | proc_perm,
-				  apriv->proc_entry);
+	entry = proc_create_data("SSID",
+				 S_IFREG | proc_perm,
+				 apriv->proc_entry, &proc_SSID_ops, dev);
 	if (!entry)
 		goto fail_ssid;
 	entry->uid = proc_uid;
 	entry->gid = proc_gid;
-	entry->data = dev;
-	entry->owner = THIS_MODULE;
-	SETPROC_OPS(entry, proc_SSID_ops);
 
 	/* Setup the APList */
-	entry = create_proc_entry("APList",
-				  S_IFREG | proc_perm,
-				  apriv->proc_entry);
+	entry = proc_create_data("APList",
+				 S_IFREG | proc_perm,
+				 apriv->proc_entry, &proc_APList_ops, dev);
 	if (!entry)
 		goto fail_aplist;
 	entry->uid = proc_uid;
 	entry->gid = proc_gid;
-	entry->data = dev;
-	entry->owner = THIS_MODULE;
-	SETPROC_OPS(entry, proc_APList_ops);
 
 	/* Setup the BSSList */
-	entry = create_proc_entry("BSSList",
-				  S_IFREG | proc_perm,
-				  apriv->proc_entry);
+	entry = proc_create_data("BSSList",
+				 S_IFREG | proc_perm,
+				 apriv->proc_entry, &proc_BSSList_ops, dev);
 	if (!entry)
 		goto fail_bsslist;
 	entry->uid = proc_uid;
 	entry->gid = proc_gid;
-	entry->data = dev;
-	entry->owner = THIS_MODULE;
-	SETPROC_OPS(entry, proc_BSSList_ops);
 
 	/* Setup the WepKey */
-	entry = create_proc_entry("WepKey",
-				  S_IFREG | proc_perm,
-				  apriv->proc_entry);
+	entry = proc_create_data("WepKey",
+				 S_IFREG | proc_perm,
+				 apriv->proc_entry, &proc_wepkey_ops, dev);
 	if (!entry)
 		goto fail_wepkey;
 	entry->uid = proc_uid;
 	entry->gid = proc_gid;
-	entry->data = dev;
-	entry->owner = THIS_MODULE;
-	SETPROC_OPS(entry, proc_wepkey_ops);
 
 	return 0;
 
@@ -5625,9 +5605,9 @@ static int __init airo_init_module( void )
 	int have_isa_dev = 0;
 #endif
 
-	airo_entry = create_proc_entry("aironet",
+	airo_entry = create_proc_entry("driver/aironet",
 				       S_IFDIR | airo_perm,
-				       proc_root_driver);
+				       NULL);
 
 	if (airo_entry) {
 		airo_entry->uid = proc_uid;
@@ -5651,7 +5631,7 @@ static int __init airo_init_module( void )
 	airo_print_info("", "Finished probing for PCI adapters");
 
 	if (i) {
-		remove_proc_entry("aironet", proc_root_driver);
+		remove_proc_entry("driver/aironet", NULL);
 		return i;
 	}
 #endif
@@ -5673,7 +5653,7 @@ static void __exit airo_cleanup_module( void )
 #ifdef CONFIG_PCI
 	pci_unregister_driver(&airo_driver);
 #endif
-	remove_proc_entry("aironet", proc_root_driver);
+	remove_proc_entry("driver/aironet", NULL);
 }
 
 /*
diff --git a/trunk/drivers/net/wireless/ath5k/base.c b/trunk/drivers/net/wireless/ath5k/base.c
index e18305b781c9..4e5c8fc35200 100644
--- a/trunk/drivers/net/wireless/ath5k/base.c
+++ b/trunk/drivers/net/wireless/ath5k/base.c
@@ -58,10 +58,6 @@
 #include "reg.h"
 #include "debug.h"
 
-/* unaligned little endian access */
-#define LE_READ_2(_p) (le16_to_cpu(get_unaligned((__le16 *)(_p))))
-#define LE_READ_4(_p) (le32_to_cpu(get_unaligned((__le32 *)(_p))))
-
 enum {
 	ATH_LED_TX,
 	ATH_LED_RX,
@@ -2909,9 +2905,9 @@ static void ath5k_configure_filter(struct ieee80211_hw *hw,
 			if (!mclist)
 				break;
 			/* calculate XOR of eight 6-bit values */
-			val = LE_READ_4(mclist->dmi_addr + 0);
+			val = get_unaligned_le32(mclist->dmi_addr + 0);
 			pos = (val >> 18) ^ (val >> 12) ^ (val >> 6) ^ val;
-			val = LE_READ_4(mclist->dmi_addr + 3);
+			val = get_unaligned_le32(mclist->dmi_addr + 3);
 			pos ^= (val >> 18) ^ (val >> 12) ^ (val >> 6) ^ val;
 			pos &= 0x3f;
 			mfilt[pos / 32] |= (1 << (pos % 32));
diff --git a/trunk/drivers/net/wireless/b43/main.c b/trunk/drivers/net/wireless/b43/main.c
index 4bf8a99099fe..8c24cd72aaca 100644
--- a/trunk/drivers/net/wireless/b43/main.c
+++ b/trunk/drivers/net/wireless/b43/main.c
@@ -2171,7 +2171,7 @@ static int b43_write_initvals(struct b43_wldev *dev,
 				goto err_format;
 			array_size -= sizeof(iv->data.d32);
 
-			value = be32_to_cpu(get_unaligned(&iv->data.d32));
+			value = get_unaligned_be32(&iv->data.d32);
 			b43_write32(dev, offset, value);
 
 			iv = (const struct b43_iv *)((const uint8_t *)iv +
diff --git a/trunk/drivers/net/wireless/b43legacy/main.c b/trunk/drivers/net/wireless/b43legacy/main.c
index ef829ee8ffd4..14a5eea2573e 100644
--- a/trunk/drivers/net/wireless/b43legacy/main.c
+++ b/trunk/drivers/net/wireless/b43legacy/main.c
@@ -1720,7 +1720,7 @@ static int b43legacy_write_initvals(struct b43legacy_wldev *dev,
 				goto err_format;
 			array_size -= sizeof(iv->data.d32);
 
-			value = be32_to_cpu(get_unaligned(&iv->data.d32));
+			value = get_unaligned_be32(&iv->data.d32);
 			b43legacy_write32(dev, offset, value);
 
 			iv = (const struct b43legacy_iv *)((const uint8_t *)iv +
diff --git a/trunk/drivers/net/wireless/iwlwifi/Kconfig b/trunk/drivers/net/wireless/iwlwifi/Kconfig
index c4e631d14bfe..9a25f550fd16 100644
--- a/trunk/drivers/net/wireless/iwlwifi/Kconfig
+++ b/trunk/drivers/net/wireless/iwlwifi/Kconfig
@@ -1,6 +1,11 @@
+config IWLWIFI
+	bool
+	default n
+
 config IWLCORE
 	tristate "Intel Wireless Wifi Core"
 	depends on PCI && MAC80211 && WLAN_80211 && EXPERIMENTAL
+	select IWLWIFI
 
 config IWLWIFI_LEDS
 	bool
@@ -106,6 +111,7 @@ config IWL3945
 	tristate "Intel PRO/Wireless 3945ABG/BG Network Connection"
 	depends on PCI && MAC80211 && WLAN_80211 && EXPERIMENTAL
 	select FW_LOADER
+	select IWLWIFI
 	---help---
 	  Select to build the driver supporting the:
 
diff --git a/trunk/drivers/net/wireless/iwlwifi/iwl-3945.c b/trunk/drivers/net/wireless/iwlwifi/iwl-3945.c
index 598e4eef4f40..d3406830c8e3 100644
--- a/trunk/drivers/net/wireless/iwlwifi/iwl-3945.c
+++ b/trunk/drivers/net/wireless/iwlwifi/iwl-3945.c
@@ -554,40 +554,36 @@ static void iwl3945_add_radiotap(struct iwl3945_priv *priv,
 	iwl3945_rt->rt_hdr.it_pad = 0;
 
 	/* total header + data */
-	put_unaligned(cpu_to_le16(sizeof(*iwl3945_rt)),
-		      &iwl3945_rt->rt_hdr.it_len);
+	put_unaligned_le16(sizeof(*iwl3945_rt), &iwl3945_rt->rt_hdr.it_len);
 
 	/* Indicate all the fields we add to the radiotap header */
-	put_unaligned(cpu_to_le32((1 << IEEE80211_RADIOTAP_TSFT) |
-				  (1 << IEEE80211_RADIOTAP_FLAGS) |
-				  (1 << IEEE80211_RADIOTAP_RATE) |
-				  (1 << IEEE80211_RADIOTAP_CHANNEL) |
-				  (1 << IEEE80211_RADIOTAP_DBM_ANTSIGNAL) |
-				  (1 << IEEE80211_RADIOTAP_DBM_ANTNOISE) |
-				  (1 << IEEE80211_RADIOTAP_ANTENNA)),
-		      &iwl3945_rt->rt_hdr.it_present);
+	put_unaligned_le32((1 << IEEE80211_RADIOTAP_TSFT) |
+			   (1 << IEEE80211_RADIOTAP_FLAGS) |
+			   (1 << IEEE80211_RADIOTAP_RATE) |
+			   (1 << IEEE80211_RADIOTAP_CHANNEL) |
+			   (1 << IEEE80211_RADIOTAP_DBM_ANTSIGNAL) |
+			   (1 << IEEE80211_RADIOTAP_DBM_ANTNOISE) |
+			   (1 << IEEE80211_RADIOTAP_ANTENNA),
+			&iwl3945_rt->rt_hdr.it_present);
 
 	/* Zero the flags, we'll add to them as we go */
 	iwl3945_rt->rt_flags = 0;
 
-	put_unaligned(cpu_to_le64(tsf), &iwl3945_rt->rt_tsf);
+	put_unaligned_le64(tsf, &iwl3945_rt->rt_tsf);
 
 	iwl3945_rt->rt_dbmsignal = signal;
 	iwl3945_rt->rt_dbmnoise = noise;
 
 	/* Convert the channel frequency and set the flags */
-	put_unaligned(cpu_to_le16(stats->freq), &iwl3945_rt->rt_channelMHz);
+	put_unaligned_le16(stats->freq, &iwl3945_rt->rt_channelMHz);
 	if (!(phy_flags_hw & RX_RES_PHY_FLAGS_BAND_24_MSK))
-		put_unaligned(cpu_to_le16(IEEE80211_CHAN_OFDM |
-					  IEEE80211_CHAN_5GHZ),
+		put_unaligned_le16(IEEE80211_CHAN_OFDM | IEEE80211_CHAN_5GHZ,
 			      &iwl3945_rt->rt_chbitmask);
 	else if (phy_flags_hw & RX_RES_PHY_FLAGS_MOD_CCK_MSK)
-		put_unaligned(cpu_to_le16(IEEE80211_CHAN_CCK |
-					  IEEE80211_CHAN_2GHZ),
+		put_unaligned_le16(IEEE80211_CHAN_CCK | IEEE80211_CHAN_2GHZ,
 			      &iwl3945_rt->rt_chbitmask);
 	else	/* 802.11g */
-		put_unaligned(cpu_to_le16(IEEE80211_CHAN_OFDM |
-					  IEEE80211_CHAN_2GHZ),
+		put_unaligned_le16(IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ,
 			      &iwl3945_rt->rt_chbitmask);
 
 	if (rate == -1)
diff --git a/trunk/drivers/net/wireless/libertas/scan.c b/trunk/drivers/net/wireless/libertas/scan.c
index e72c97a0d6c1..1a409fcc80d3 100644
--- a/trunk/drivers/net/wireless/libertas/scan.c
+++ b/trunk/drivers/net/wireless/libertas/scan.c
@@ -522,7 +522,7 @@ static int lbs_process_bss(struct bss_descriptor *bss,
 
 	if (*bytesleft >= sizeof(beaconsize)) {
 		/* Extract & convert beacon size from the command buffer */
-		beaconsize = le16_to_cpu(get_unaligned((__le16 *)*pbeaconinfo));
+		beaconsize = get_unaligned_le16(*pbeaconinfo);
 		*bytesleft -= sizeof(beaconsize);
 		*pbeaconinfo += sizeof(beaconsize);
 	}
diff --git a/trunk/drivers/net/wireless/zd1211rw/zd_usb.c b/trunk/drivers/net/wireless/zd1211rw/zd_usb.c
index e34675c2f8fc..5316074f39f0 100644
--- a/trunk/drivers/net/wireless/zd1211rw/zd_usb.c
+++ b/trunk/drivers/net/wireless/zd1211rw/zd_usb.c
@@ -545,11 +545,11 @@ static void handle_rx_packet(struct zd_usb *usb, const u8 *buffer,
 	 * be padded. Unaligned access might also happen if the length_info
 	 * structure is not present.
 	 */
-	if (get_unaligned(&length_info->tag) == cpu_to_le16(RX_LENGTH_INFO_TAG))
+	if (get_unaligned_le16(&length_info->tag) == RX_LENGTH_INFO_TAG)
 	{
 		unsigned int l, k, n;
 		for (i = 0, l = 0;; i++) {
-			k = le16_to_cpu(get_unaligned(&length_info->length[i]));
+			k = get_unaligned_le16(&length_info->length[i]);
 			if (k == 0)
 				return;
 			n = l+k;
diff --git a/trunk/drivers/net/yellowfin.c b/trunk/drivers/net/yellowfin.c
index 24640726f8bb..57e1f495b9fc 100644
--- a/trunk/drivers/net/yellowfin.c
+++ b/trunk/drivers/net/yellowfin.c
@@ -1062,7 +1062,7 @@ static int yellowfin_rx(struct net_device *dev)
 		buf_addr = rx_skb->data;
 		data_size = (le32_to_cpu(desc->dbdma_cmd) -
 			le32_to_cpu(desc->result_status)) & 0xffff;
-		frame_status = le16_to_cpu(get_unaligned((__le16*)&(buf_addr[data_size - 2])));
+		frame_status = get_unaligned_le16(&(buf_addr[data_size - 2]));
 		if (yellowfin_debug > 4)
 			printk(KERN_DEBUG "  yellowfin_rx() status was %4.4x.\n",
 				   frame_status);
diff --git a/trunk/drivers/nubus/proc.c b/trunk/drivers/nubus/proc.c
index e07492be1f4a..208dd12825bc 100644
--- a/trunk/drivers/nubus/proc.c
+++ b/trunk/drivers/nubus/proc.c
@@ -21,6 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/nubus.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/module.h>
 
@@ -28,38 +29,36 @@
 #include <asm/byteorder.h>
 
 static int
-get_nubus_dev_info(char *buf, char **start, off_t pos, int count)
+nubus_devices_proc_show(struct seq_file *m, void *v)
 {
 	struct nubus_dev *dev = nubus_devices;
-	off_t at = 0;
-	int len, cnt;
 
-	cnt = 0;
-	while (dev && count > cnt) {
-		len = sprintf(buf, "%x\t%04x %04x %04x %04x",
+	while (dev) {
+		seq_printf(m, "%x\t%04x %04x %04x %04x",
 			      dev->board->slot,
 			      dev->category,
 			      dev->type,
 			      dev->dr_sw,
 			      dev->dr_hw);
-		len += sprintf(buf+len,
-			       "\t%08lx",
-			       dev->board->slot_addr);
-		buf[len++] = '\n';
-		at += len;
-		if (at >= pos) {
-			if (!*start) {
-				*start = buf + (pos - (at - len));
-				cnt = at - pos;
-			} else
-				cnt += len;
-			buf += len;
-		}
+		seq_printf(m, "\t%08lx\n", dev->board->slot_addr);
 		dev = dev->next;
 	}
-	return (count > cnt) ? cnt : count;
+	return 0;
+}
+
+static int nubus_devices_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, nubus_devices_proc_show, NULL);
 }
 
+static const struct file_operations nubus_devices_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= nubus_devices_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static struct proc_dir_entry *proc_bus_nubus_dir;
 
 static void nubus_proc_subdir(struct nubus_dev* dev,
@@ -171,8 +170,7 @@ void __init nubus_proc_init(void)
 {
 	if (!MACH_IS_MAC)
 		return;
-	proc_bus_nubus_dir = proc_mkdir("nubus", proc_bus);
-	create_proc_info_entry("devices", 0, proc_bus_nubus_dir,
-				get_nubus_dev_info);
+	proc_bus_nubus_dir = proc_mkdir("bus/nubus", NULL);
+	proc_create("devices", 0, proc_bus_nubus_dir, &nubus_devices_proc_fops);
 	proc_bus_nubus_add_devices();
 }
diff --git a/trunk/drivers/oprofile/buffer_sync.c b/trunk/drivers/oprofile/buffer_sync.c
index b07ba2a14119..9304c4555079 100644
--- a/trunk/drivers/oprofile/buffer_sync.c
+++ b/trunk/drivers/oprofile/buffer_sync.c
@@ -491,7 +491,7 @@ typedef enum {
  */
 void sync_buffer(int cpu)
 {
-	struct oprofile_cpu_buffer * cpu_buf = &cpu_buffer[cpu];
+	struct oprofile_cpu_buffer *cpu_buf = &per_cpu(cpu_buffer, cpu);
 	struct mm_struct *mm = NULL;
 	struct task_struct * new;
 	unsigned long cookie = 0;
diff --git a/trunk/drivers/oprofile/cpu_buffer.c b/trunk/drivers/oprofile/cpu_buffer.c
index c93d3d2640ab..efcbf4b4579f 100644
--- a/trunk/drivers/oprofile/cpu_buffer.c
+++ b/trunk/drivers/oprofile/cpu_buffer.c
@@ -27,7 +27,7 @@
 #include "buffer_sync.h"
 #include "oprof.h"
 
-struct oprofile_cpu_buffer cpu_buffer[NR_CPUS] __cacheline_aligned;
+DEFINE_PER_CPU_SHARED_ALIGNED(struct oprofile_cpu_buffer, cpu_buffer);
 
 static void wq_sync_buffer(struct work_struct *work);
 
@@ -39,7 +39,7 @@ void free_cpu_buffers(void)
 	int i;
  
 	for_each_online_cpu(i)
-		vfree(cpu_buffer[i].buffer);
+		vfree(per_cpu(cpu_buffer, i).buffer);
 }
 
 int alloc_cpu_buffers(void)
@@ -49,7 +49,7 @@ int alloc_cpu_buffers(void)
 	unsigned long buffer_size = fs_cpu_buffer_size;
  
 	for_each_online_cpu(i) {
-		struct oprofile_cpu_buffer * b = &cpu_buffer[i];
+		struct oprofile_cpu_buffer *b = &per_cpu(cpu_buffer, i);
  
 		b->buffer = vmalloc_node(sizeof(struct op_sample) * buffer_size,
 			cpu_to_node(i));
@@ -83,7 +83,7 @@ void start_cpu_work(void)
 	work_enabled = 1;
 
 	for_each_online_cpu(i) {
-		struct oprofile_cpu_buffer * b = &cpu_buffer[i];
+		struct oprofile_cpu_buffer *b = &per_cpu(cpu_buffer, i);
 
 		/*
 		 * Spread the work by 1 jiffy per cpu so they dont all
@@ -100,7 +100,7 @@ void end_cpu_work(void)
 	work_enabled = 0;
 
 	for_each_online_cpu(i) {
-		struct oprofile_cpu_buffer * b = &cpu_buffer[i];
+		struct oprofile_cpu_buffer *b = &per_cpu(cpu_buffer, i);
 
 		cancel_delayed_work(&b->work);
 	}
@@ -227,7 +227,7 @@ static void oprofile_end_trace(struct oprofile_cpu_buffer * cpu_buf)
 void oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
 				unsigned long event, int is_kernel)
 {
-	struct oprofile_cpu_buffer * cpu_buf = &cpu_buffer[smp_processor_id()];
+	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
 
 	if (!backtrace_depth) {
 		log_sample(cpu_buf, pc, is_kernel, event);
@@ -254,13 +254,13 @@ void oprofile_add_sample(struct pt_regs * const regs, unsigned long event)
 
 void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
 {
-	struct oprofile_cpu_buffer * cpu_buf = &cpu_buffer[smp_processor_id()];
+	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
 	log_sample(cpu_buf, pc, is_kernel, event);
 }
 
 void oprofile_add_trace(unsigned long pc)
 {
-	struct oprofile_cpu_buffer * cpu_buf = &cpu_buffer[smp_processor_id()];
+	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
 
 	if (!cpu_buf->tracing)
 		return;
diff --git a/trunk/drivers/oprofile/cpu_buffer.h b/trunk/drivers/oprofile/cpu_buffer.h
index c66c025abe75..13588174311d 100644
--- a/trunk/drivers/oprofile/cpu_buffer.h
+++ b/trunk/drivers/oprofile/cpu_buffer.h
@@ -14,6 +14,7 @@
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
 #include <linux/cache.h>
+#include <linux/sched.h>
  
 struct task_struct;
  
@@ -47,7 +48,7 @@ struct oprofile_cpu_buffer {
 	struct delayed_work work;
 } ____cacheline_aligned;
 
-extern struct oprofile_cpu_buffer cpu_buffer[];
+DECLARE_PER_CPU(struct oprofile_cpu_buffer, cpu_buffer);
 
 void cpu_buffer_reset(struct oprofile_cpu_buffer * cpu_buf);
 
diff --git a/trunk/drivers/oprofile/oprofile_stats.c b/trunk/drivers/oprofile/oprofile_stats.c
index d1f6d776e9e4..f99b28e7b79a 100644
--- a/trunk/drivers/oprofile/oprofile_stats.c
+++ b/trunk/drivers/oprofile/oprofile_stats.c
@@ -23,7 +23,7 @@ void oprofile_reset_stats(void)
 	int i;
  
 	for_each_possible_cpu(i) {
-		cpu_buf = &cpu_buffer[i]; 
+		cpu_buf = &per_cpu(cpu_buffer, i);
 		cpu_buf->sample_received = 0;
 		cpu_buf->sample_lost_overflow = 0;
 		cpu_buf->backtrace_aborted = 0;
@@ -49,7 +49,7 @@ void oprofile_create_stats_files(struct super_block * sb, struct dentry * root)
 		return;
 
 	for_each_possible_cpu(i) {
-		cpu_buf = &cpu_buffer[i]; 
+		cpu_buf = &per_cpu(cpu_buffer, i);
 		snprintf(buf, 10, "cpu%d", i);
 		cpudir = oprofilefs_mkdir(sb, dir, buf);
  
diff --git a/trunk/drivers/parisc/ccio-dma.c b/trunk/drivers/parisc/ccio-dma.c
index 62db3c3fe4dc..07d2a8d4498f 100644
--- a/trunk/drivers/parisc/ccio-dma.c
+++ b/trunk/drivers/parisc/ccio-dma.c
@@ -1551,8 +1551,7 @@ static int __init ccio_probe(struct parisc_device *dev)
 {
 	int i;
 	struct ioc *ioc, **ioc_p = &ioc_list;
-	struct proc_dir_entry *info_entry, *bitmap_entry;
-	
+
 	ioc = kzalloc(sizeof(struct ioc), GFP_KERNEL);
 	if (ioc == NULL) {
 		printk(KERN_ERR MODULE_NAME ": memory allocation failure\n");
@@ -1580,13 +1579,10 @@ static int __init ccio_probe(struct parisc_device *dev)
 	HBA_DATA(dev->dev.platform_data)->iommu = ioc;
 	
 	if (ioc_count == 0) {
-		info_entry = create_proc_entry(MODULE_NAME, 0, proc_runway_root);
-		if (info_entry)
-			info_entry->proc_fops = &ccio_proc_info_fops;
-
-		bitmap_entry = create_proc_entry(MODULE_NAME"-bitmap", 0, proc_runway_root);
-		if (bitmap_entry)
-			bitmap_entry->proc_fops = &ccio_proc_bitmap_fops;
+		proc_create(MODULE_NAME, 0, proc_runway_root,
+			    &ccio_proc_info_fops);
+		proc_create(MODULE_NAME"-bitmap", 0, proc_runway_root,
+			    &ccio_proc_bitmap_fops);
 	}
 
 	ioc_count++;
diff --git a/trunk/drivers/parisc/sba_iommu.c b/trunk/drivers/parisc/sba_iommu.c
index 8c4d2c13d5f2..afc849bd3f58 100644
--- a/trunk/drivers/parisc/sba_iommu.c
+++ b/trunk/drivers/parisc/sba_iommu.c
@@ -1895,7 +1895,9 @@ sba_driver_callback(struct parisc_device *dev)
 	int i;
 	char *version;
 	void __iomem *sba_addr = ioremap_nocache(dev->hpa.start, SBA_FUNC_SIZE);
-	struct proc_dir_entry *info_entry, *bitmap_entry, *root;
+#ifdef CONFIG_PROC_FS
+	struct proc_dir_entry *root;
+#endif
 
 	sba_dump_ranges(sba_addr);
 
@@ -1973,14 +1975,8 @@ sba_driver_callback(struct parisc_device *dev)
 		break;
 	}
 
-	info_entry = create_proc_entry("sba_iommu", 0, root);
-	bitmap_entry = create_proc_entry("sba_iommu-bitmap", 0, root);
-
-	if (info_entry)
-		info_entry->proc_fops = &sba_proc_fops;
-
-	if (bitmap_entry)
-		bitmap_entry->proc_fops = &sba_proc_bitmap_fops;
+	proc_create("sba_iommu", 0, root, &sba_proc_fops);
+	proc_create("sba_iommu-bitmap", 0, root, &sba_proc_bitmap_fops);
 #endif
 
 	parisc_vmerge_boundary = IOVP_SIZE;
diff --git a/trunk/drivers/parport/parport_pc.c b/trunk/drivers/parport/parport_pc.c
index a85808938205..e71092e80288 100644
--- a/trunk/drivers/parport/parport_pc.c
+++ b/trunk/drivers/parport/parport_pc.c
@@ -3082,6 +3082,7 @@ static struct pci_driver parport_pc_pci_driver;
 static int __init parport_pc_init_superio(int autoirq, int autodma) {return 0;}
 #endif /* CONFIG_PCI */
 
+#ifdef CONFIG_PNP
 
 static const struct pnp_device_id parport_pc_pnp_tbl[] = {
 	/* Standard LPT Printer Port */
@@ -3148,6 +3149,9 @@ static struct pnp_driver parport_pc_pnp_driver = {
 	.remove		= parport_pc_pnp_remove,
 };
 
+#else
+static struct pnp_driver parport_pc_pnp_driver;
+#endif /* CONFIG_PNP */
 
 static int __devinit parport_pc_platform_probe(struct platform_device *pdev)
 {
diff --git a/trunk/drivers/pci/pcie/aer/aerdrv_acpi.c b/trunk/drivers/pci/pcie/aer/aerdrv_acpi.c
index 96ac54072f6f..d39a78dbd026 100644
--- a/trunk/drivers/pci/pcie/aer/aerdrv_acpi.c
+++ b/trunk/drivers/pci/pcie/aer/aerdrv_acpi.c
@@ -31,7 +31,7 @@ int aer_osc_setup(struct pcie_device *pciedev)
 {
 	acpi_status status = AE_NOT_FOUND;
 	struct pci_dev *pdev = pciedev->port;
-	acpi_handle handle = 0;
+	acpi_handle handle = NULL;
 
 	if (acpi_pci_disabled)
 		return -1;
diff --git a/trunk/drivers/pci/proc.c b/trunk/drivers/pci/proc.c
index ef18fcd641e2..963a97642ae9 100644
--- a/trunk/drivers/pci/proc.c
+++ b/trunk/drivers/pci/proc.c
@@ -293,6 +293,7 @@ static int proc_bus_pci_release(struct inode *inode, struct file *file)
 #endif /* HAVE_PCI_MMAP */
 
 static const struct file_operations proc_bus_pci_operations = {
+	.owner		= THIS_MODULE,
 	.llseek		= proc_bus_pci_lseek,
 	.read		= proc_bus_pci_read,
 	.write		= proc_bus_pci_write,
@@ -406,11 +407,10 @@ int pci_proc_attach_device(struct pci_dev *dev)
 	}
 
 	sprintf(name, "%02x.%x", PCI_SLOT(dev->devfn), PCI_FUNC(dev->devfn));
-	e = create_proc_entry(name, S_IFREG | S_IRUGO | S_IWUSR, bus->procdir);
+	e = proc_create_data(name, S_IFREG | S_IRUGO | S_IWUSR, bus->procdir,
+			     &proc_bus_pci_operations, dev);
 	if (!e)
 		return -ENOMEM;
-	e->proc_fops = &proc_bus_pci_operations;
-	e->data = dev;
 	e->size = dev->cfg_size;
 	dev->procent = e;
 
@@ -462,6 +462,7 @@ static int proc_bus_pci_dev_open(struct inode *inode, struct file *file)
 	return seq_open(file, &proc_bus_pci_devices_op);
 }
 static const struct file_operations proc_bus_pci_dev_operations = {
+	.owner		= THIS_MODULE,
 	.open		= proc_bus_pci_dev_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -470,12 +471,10 @@ static const struct file_operations proc_bus_pci_dev_operations = {
 
 static int __init pci_proc_init(void)
 {
-	struct proc_dir_entry *entry;
 	struct pci_dev *dev = NULL;
-	proc_bus_pci_dir = proc_mkdir("pci", proc_bus);
-	entry = create_proc_entry("devices", 0, proc_bus_pci_dir);
-	if (entry)
-		entry->proc_fops = &proc_bus_pci_dev_operations;
+	proc_bus_pci_dir = proc_mkdir("bus/pci", NULL);
+	proc_create("devices", 0, proc_bus_pci_dir,
+		    &proc_bus_pci_dev_operations);
 	proc_initialized = 1;
 	while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
 		pci_proc_attach_device(dev);
diff --git a/trunk/drivers/pcmcia/Kconfig b/trunk/drivers/pcmcia/Kconfig
index 8d8852651fd2..1b0eb5aaf650 100644
--- a/trunk/drivers/pcmcia/Kconfig
+++ b/trunk/drivers/pcmcia/Kconfig
@@ -38,7 +38,6 @@ config PCMCIA_DEBUG
 config PCMCIA
 	tristate "16-bit PCMCIA support"
 	select CRC32
-	select HAVE_IDE
 	default y
 	---help---
 	   This option enables support for 16-bit PCMCIA cards. Most older
diff --git a/trunk/drivers/pcmcia/cistpl.c b/trunk/drivers/pcmcia/cistpl.c
index 06a85d7d5aa2..36379535f9da 100644
--- a/trunk/drivers/pcmcia/cistpl.c
+++ b/trunk/drivers/pcmcia/cistpl.c
@@ -402,15 +402,6 @@ EXPORT_SYMBOL(pcmcia_replace_cis);
     
 ======================================================================*/
 
-static inline u16 cis_get_u16(void *ptr)
-{
-	return le16_to_cpu(get_unaligned((__le16 *) ptr));
-}
-static inline u32 cis_get_u32(void *ptr)
-{
-	return le32_to_cpu(get_unaligned((__le32 *) ptr));
-}
-
 typedef struct tuple_flags {
     u_int		link_space:4;
     u_int		has_link:1;
@@ -471,7 +462,7 @@ static int follow_link(struct pcmcia_socket *s, tuple_t *tuple)
 	/* Get indirect link from the MFC tuple */
 	read_cis_cache(s, LINK_SPACE(tuple->Flags),
 		       tuple->LinkOffset, 5, link);
-	ofs = cis_get_u32(link + 1);
+	ofs = get_unaligned_le32(link + 1);
 	SPACE(tuple->Flags) = (link[0] == CISTPL_MFC_ATTR);
 	/* Move to the next indirect link */
 	tuple->LinkOffset += 5;
@@ -679,8 +670,8 @@ static int parse_checksum(tuple_t *tuple, cistpl_checksum_t *csum)
     if (tuple->TupleDataLen < 5)
 	return CS_BAD_TUPLE;
     p = (u_char *) tuple->TupleData;
-    csum->addr = tuple->CISOffset + cis_get_u16(p) - 2;
-    csum->len = cis_get_u16(p + 2);
+    csum->addr = tuple->CISOffset + get_unaligned_le16(p) - 2;
+    csum->len = get_unaligned_le16(p + 2);
     csum->sum = *(p + 4);
     return CS_SUCCESS;
 }
@@ -691,7 +682,7 @@ static int parse_longlink(tuple_t *tuple, cistpl_longlink_t *link)
 {
     if (tuple->TupleDataLen < 4)
 	return CS_BAD_TUPLE;
-    link->addr = cis_get_u32(tuple->TupleData);
+    link->addr = get_unaligned_le32(tuple->TupleData);
     return CS_SUCCESS;
 }
 
@@ -710,7 +701,7 @@ static int parse_longlink_mfc(tuple_t *tuple,
 	return CS_BAD_TUPLE;
     for (i = 0; i < link->nfn; i++) {
 	link->fn[i].space = *p; p++;
-	link->fn[i].addr = cis_get_u32(p);
+	link->fn[i].addr = get_unaligned_le32(p);
 	p += 4;
     }
     return CS_SUCCESS;
@@ -800,8 +791,8 @@ static int parse_manfid(tuple_t *tuple, cistpl_manfid_t *m)
 {
     if (tuple->TupleDataLen < 4)
 	return CS_BAD_TUPLE;
-    m->manf = cis_get_u16(tuple->TupleData);
-    m->card = cis_get_u16(tuple->TupleData + 2);
+    m->manf = get_unaligned_le16(tuple->TupleData);
+    m->card = get_unaligned_le16(tuple->TupleData + 2);
     return CS_SUCCESS;
 }
 
@@ -1100,7 +1091,7 @@ static int parse_cftable_entry(tuple_t *tuple,
 	break;
     case 0x20:
 	entry->mem.nwin = 1;
-	entry->mem.win[0].len = cis_get_u16(p) << 8;
+	entry->mem.win[0].len = get_unaligned_le16(p) << 8;
 	entry->mem.win[0].card_addr = 0;
 	entry->mem.win[0].host_addr = 0;
 	p += 2;
@@ -1108,8 +1099,8 @@ static int parse_cftable_entry(tuple_t *tuple,
 	break;
     case 0x40:
 	entry->mem.nwin = 1;
-	entry->mem.win[0].len = cis_get_u16(p) << 8;
-	entry->mem.win[0].card_addr = cis_get_u16(p + 2) << 8;
+	entry->mem.win[0].len = get_unaligned_le16(p) << 8;
+	entry->mem.win[0].card_addr = get_unaligned_le16(p + 2) << 8;
 	entry->mem.win[0].host_addr = 0;
 	p += 4;
 	if (p > q) return CS_BAD_TUPLE;
@@ -1146,7 +1137,7 @@ static int parse_bar(tuple_t *tuple, cistpl_bar_t *bar)
     p = (u_char *)tuple->TupleData;
     bar->attr = *p;
     p += 2;
-    bar->size = cis_get_u32(p);
+    bar->size = get_unaligned_le32(p);
     return CS_SUCCESS;
 }
 
@@ -1159,7 +1150,7 @@ static int parse_config_cb(tuple_t *tuple, cistpl_config_t *config)
 	return CS_BAD_TUPLE;
     config->last_idx = *(++p);
     p++;
-    config->base = cis_get_u32(p);
+    config->base = get_unaligned_le32(p);
     config->subtuples = tuple->TupleDataLen - 6;
     return CS_SUCCESS;
 }
@@ -1275,7 +1266,7 @@ static int parse_vers_2(tuple_t *tuple, cistpl_vers_2_t *v2)
 
     v2->vers = p[0];
     v2->comply = p[1];
-    v2->dindex = cis_get_u16(p +2 );
+    v2->dindex = get_unaligned_le16(p +2 );
     v2->vspec8 = p[6];
     v2->vspec9 = p[7];
     v2->nhdr = p[8];
@@ -1316,8 +1307,8 @@ static int parse_format(tuple_t *tuple, cistpl_format_t *fmt)
 
     fmt->type = p[0];
     fmt->edc = p[1];
-    fmt->offset = cis_get_u32(p + 2);
-    fmt->length = cis_get_u32(p + 6);
+    fmt->offset = get_unaligned_le32(p + 2);
+    fmt->length = get_unaligned_le32(p + 6);
 
     return CS_SUCCESS;
 }
diff --git a/trunk/drivers/pnp/driver.c b/trunk/drivers/pnp/driver.c
index 12a1645a2e43..e85cbf116db1 100644
--- a/trunk/drivers/pnp/driver.c
+++ b/trunk/drivers/pnp/driver.c
@@ -167,7 +167,7 @@ static int pnp_bus_suspend(struct device *dev, pm_message_t state)
 			return error;
 	}
 
-	if (pnp_dev->protocol && pnp_dev->protocol->suspend)
+	if (pnp_dev->protocol->suspend)
 		pnp_dev->protocol->suspend(pnp_dev, state);
 	return 0;
 }
@@ -181,7 +181,7 @@ static int pnp_bus_resume(struct device *dev)
 	if (!pnp_drv)
 		return 0;
 
-	if (pnp_dev->protocol && pnp_dev->protocol->resume)
+	if (pnp_dev->protocol->resume)
 		pnp_dev->protocol->resume(pnp_dev);
 
 	if (pnp_can_write(pnp_dev)) {
diff --git a/trunk/drivers/pnp/isapnp/proc.c b/trunk/drivers/pnp/isapnp/proc.c
index 2b8266c3d40f..3f94edab25fa 100644
--- a/trunk/drivers/pnp/isapnp/proc.c
+++ b/trunk/drivers/pnp/isapnp/proc.c
@@ -85,6 +85,7 @@ static ssize_t isapnp_proc_bus_read(struct file *file, char __user * buf,
 }
 
 static const struct file_operations isapnp_proc_bus_file_operations = {
+	.owner	= THIS_MODULE,
 	.llseek = isapnp_proc_bus_lseek,
 	.read = isapnp_proc_bus_read,
 };
@@ -102,12 +103,10 @@ static int isapnp_proc_attach_device(struct pnp_dev *dev)
 			return -ENOMEM;
 	}
 	sprintf(name, "%02x", dev->number);
-	e = dev->procent = create_proc_entry(name, S_IFREG | S_IRUGO, de);
+	e = dev->procent = proc_create_data(name, S_IFREG | S_IRUGO, de,
+			&isapnp_proc_bus_file_operations, dev);
 	if (!e)
 		return -ENOMEM;
-	e->proc_fops = &isapnp_proc_bus_file_operations;
-	e->owner = THIS_MODULE;
-	e->data = dev;
 	e->size = 256;
 	return 0;
 }
@@ -116,7 +115,7 @@ int __init isapnp_proc_init(void)
 {
 	struct pnp_dev *dev;
 
-	isapnp_proc_bus_dir = proc_mkdir("isapnp", proc_bus);
+	isapnp_proc_bus_dir = proc_mkdir("bus/isapnp", NULL);
 	protocol_for_each_dev(&isapnp_protocol, dev) {
 		isapnp_proc_attach_device(dev);
 	}
diff --git a/trunk/drivers/pnp/pnpbios/proc.c b/trunk/drivers/pnp/pnpbios/proc.c
index bb19bc957bad..46d506f66259 100644
--- a/trunk/drivers/pnp/pnpbios/proc.c
+++ b/trunk/drivers/pnp/pnpbios/proc.c
@@ -256,7 +256,7 @@ int pnpbios_interface_attach_device(struct pnp_bios_node *node)
  */
 int __init pnpbios_proc_init(void)
 {
-	proc_pnp = proc_mkdir("pnp", proc_bus);
+	proc_pnp = proc_mkdir("bus/pnp", NULL);
 	if (!proc_pnp)
 		return -EIO;
 	proc_pnp_boot = proc_mkdir("boot", proc_pnp);
@@ -294,5 +294,5 @@ void __exit pnpbios_proc_exit(void)
 	remove_proc_entry("configuration_info", proc_pnp);
 	remove_proc_entry("devices", proc_pnp);
 	remove_proc_entry("boot", proc_pnp);
-	remove_proc_entry("pnp", proc_bus);
+	remove_proc_entry("bus/pnp", NULL);
 }
diff --git a/trunk/drivers/pnp/quirks.c b/trunk/drivers/pnp/quirks.c
index 37993206ae5d..e4daf4635c48 100644
--- a/trunk/drivers/pnp/quirks.c
+++ b/trunk/drivers/pnp/quirks.c
@@ -49,8 +49,11 @@ static void quirk_awe32_resources(struct pnp_dev *dev)
 		port2->max += 0x400;
 		port3->min += 0x800;
 		port3->max += 0x800;
+		dev_info(&dev->dev,
+			"AWE32 quirk - added ioports 0x%lx and 0x%lx\n",
+			(unsigned long)port2->min,
+			(unsigned long)port3->min);
 	}
-	printk(KERN_INFO "pnp: AWE32 quirk - adding two ports\n");
 }
 
 static void quirk_cmi8330_resources(struct pnp_dev *dev)
@@ -73,7 +76,8 @@ static void quirk_cmi8330_resources(struct pnp_dev *dev)
 			    IORESOURCE_DMA_8BIT)
 				dma->map = 0x000A;
 	}
-	printk(KERN_INFO "pnp: CMI8330 quirk - fixing interrupts and dma\n");
+	dev_info(&dev->dev, "CMI8330 quirk - forced possible IRQs to 5, 7, 10 "
+		"and DMA channels to 1, 3\n");
 }
 
 static void quirk_sb16audio_resources(struct pnp_dev *dev)
@@ -104,8 +108,7 @@ static void quirk_sb16audio_resources(struct pnp_dev *dev)
 		changed = 1;
 	}
 	if (changed)
-		printk(KERN_INFO
-		       "pnp: SB audio device quirk - increasing port range\n");
+		dev_info(&dev->dev, "SB audio device quirk - increased port range\n");
 }
 
 
@@ -214,8 +217,8 @@ void pnp_fixup_device(struct pnp_dev *dev)
 			quirk = pnp_fixups[i].quirk_function;
 
 #ifdef DEBUG
-			dev_dbg(&dev->dev, "calling quirk 0x%p", quirk);
-			print_fn_descriptor_symbol(": %s()\n",
+			dev_dbg(&dev->dev, "calling ");
+			print_fn_descriptor_symbol("%s()\n",
 				(unsigned long) *quirk);
 #endif
 			(*quirk)(dev);
diff --git a/trunk/drivers/power/ds2760_battery.c b/trunk/drivers/power/ds2760_battery.c
index bdb9b7285b3d..71be36f18709 100644
--- a/trunk/drivers/power/ds2760_battery.c
+++ b/trunk/drivers/power/ds2760_battery.c
@@ -262,7 +262,7 @@ static void ds2760_battery_work(struct work_struct *work)
 		struct ds2760_device_info, monitor_work.work);
 	const int interval = HZ * 60;
 
-	dev_dbg(di->dev, "%s\n", __FUNCTION__);
+	dev_dbg(di->dev, "%s\n", __func__);
 
 	ds2760_battery_update_status(di);
 	queue_delayed_work(di->monitor_wqueue, &di->monitor_work, interval);
@@ -275,7 +275,7 @@ static void ds2760_battery_external_power_changed(struct power_supply *psy)
 {
 	struct ds2760_device_info *di = to_ds2760_device_info(psy);
 
-	dev_dbg(di->dev, "%s\n", __FUNCTION__);
+	dev_dbg(di->dev, "%s\n", __func__);
 
 	cancel_delayed_work(&di->monitor_work);
 	queue_delayed_work(di->monitor_wqueue, &di->monitor_work, HZ/10);
diff --git a/trunk/drivers/power/olpc_battery.c b/trunk/drivers/power/olpc_battery.c
index af7a231092a4..ab1e8289f07f 100644
--- a/trunk/drivers/power/olpc_battery.c
+++ b/trunk/drivers/power/olpc_battery.c
@@ -315,7 +315,6 @@ static int __init olpc_bat_init(void)
 	if (ret)
 		goto battery_failed;
 
-	olpc_register_battery_callback(&olpc_battery_trigger_uevent);
 	goto success;
 
 battery_failed:
@@ -328,7 +327,6 @@ static int __init olpc_bat_init(void)
 
 static void __exit olpc_bat_exit(void)
 {
-	olpc_deregister_battery_callback();
 	power_supply_unregister(&olpc_bat);
 	power_supply_unregister(&olpc_ac);
 	platform_device_unregister(bat_pdev);
diff --git a/trunk/drivers/power/power_supply_core.c b/trunk/drivers/power/power_supply_core.c
index 03d6a38464ef..138dd76ee347 100644
--- a/trunk/drivers/power/power_supply_core.c
+++ b/trunk/drivers/power/power_supply_core.c
@@ -39,7 +39,7 @@ static void power_supply_changed_work(struct work_struct *work)
 	struct power_supply *psy = container_of(work, struct power_supply,
 						changed_work);
 
-	dev_dbg(psy->dev, "%s\n", __FUNCTION__);
+	dev_dbg(psy->dev, "%s\n", __func__);
 
 	class_for_each_device(power_supply_class, psy,
 			      __power_supply_changed_work);
@@ -51,7 +51,7 @@ static void power_supply_changed_work(struct work_struct *work)
 
 void power_supply_changed(struct power_supply *psy)
 {
-	dev_dbg(psy->dev, "%s\n", __FUNCTION__);
+	dev_dbg(psy->dev, "%s\n", __func__);
 
 	schedule_work(&psy->changed_work);
 }
@@ -82,7 +82,7 @@ int power_supply_am_i_supplied(struct power_supply *psy)
 	error = class_for_each_device(power_supply_class, psy,
 				      __power_supply_am_i_supplied);
 
-	dev_dbg(psy->dev, "%s %d\n", __FUNCTION__, error);
+	dev_dbg(psy->dev, "%s %d\n", __func__, error);
 
 	return error;
 }
diff --git a/trunk/drivers/power/power_supply_leds.c b/trunk/drivers/power/power_supply_leds.c
index fa3034f85c38..2dece40c544f 100644
--- a/trunk/drivers/power/power_supply_leds.c
+++ b/trunk/drivers/power/power_supply_leds.c
@@ -24,7 +24,7 @@ static void power_supply_update_bat_leds(struct power_supply *psy)
 	if (psy->get_property(psy, POWER_SUPPLY_PROP_STATUS, &status))
 		return;
 
-	dev_dbg(psy->dev, "%s %d\n", __FUNCTION__, status.intval);
+	dev_dbg(psy->dev, "%s %d\n", __func__, status.intval);
 
 	switch (status.intval) {
 	case POWER_SUPPLY_STATUS_FULL:
@@ -101,7 +101,7 @@ static void power_supply_update_gen_leds(struct power_supply *psy)
 	if (psy->get_property(psy, POWER_SUPPLY_PROP_ONLINE, &online))
 		return;
 
-	dev_dbg(psy->dev, "%s %d\n", __FUNCTION__, online.intval);
+	dev_dbg(psy->dev, "%s %d\n", __func__, online.intval);
 
 	if (online.intval)
 		led_trigger_event(psy->online_trig, LED_FULL);
diff --git a/trunk/drivers/rapidio/Kconfig b/trunk/drivers/rapidio/Kconfig
index 4142115d298e..c32822ad84a4 100644
--- a/trunk/drivers/rapidio/Kconfig
+++ b/trunk/drivers/rapidio/Kconfig
@@ -1,14 +1,6 @@
 #
 # RapidIO configuration
 #
-config RAPIDIO_8_BIT_TRANSPORT
-	bool "8-bit transport addressing"
-	depends on RAPIDIO
-	---help---
-	  By default, the kernel assumes a 16-bit addressed RapidIO
-	  network. By selecting this option, the kernel will support
-	  an 8-bit addressed network.
-
 config RAPIDIO_DISC_TIMEOUT
 	int "Discovery timeout duration (seconds)"
 	depends on RAPIDIO
diff --git a/trunk/drivers/rapidio/rio-access.c b/trunk/drivers/rapidio/rio-access.c
index 8b56bbdd011e..a3824baca2e5 100644
--- a/trunk/drivers/rapidio/rio-access.c
+++ b/trunk/drivers/rapidio/rio-access.c
@@ -48,7 +48,7 @@ int __rio_local_read_config_##size \
 	u32 data = 0;							\
 	if (RIO_##size##_BAD) return RIO_BAD_SIZE;			\
 	spin_lock_irqsave(&rio_config_lock, flags);			\
-	res = mport->ops->lcread(mport->id, offset, len, &data);	\
+	res = mport->ops->lcread(mport, mport->id, offset, len, &data);	\
 	*value = (type)data;						\
 	spin_unlock_irqrestore(&rio_config_lock, flags);		\
 	return res;							\
@@ -71,7 +71,7 @@ int __rio_local_write_config_##size \
 	unsigned long flags;						\
 	if (RIO_##size##_BAD) return RIO_BAD_SIZE;			\
 	spin_lock_irqsave(&rio_config_lock, flags);			\
-	res = mport->ops->lcwrite(mport->id, offset, len, value);	\
+	res = mport->ops->lcwrite(mport, mport->id, offset, len, value);\
 	spin_unlock_irqrestore(&rio_config_lock, flags);		\
 	return res;							\
 }
@@ -108,7 +108,7 @@ int rio_mport_read_config_##size \
 	u32 data = 0;							\
 	if (RIO_##size##_BAD) return RIO_BAD_SIZE;			\
 	spin_lock_irqsave(&rio_config_lock, flags);			\
-	res = mport->ops->cread(mport->id, destid, hopcount, offset, len, &data); \
+	res = mport->ops->cread(mport, mport->id, destid, hopcount, offset, len, &data); \
 	*value = (type)data;						\
 	spin_unlock_irqrestore(&rio_config_lock, flags);		\
 	return res;							\
@@ -131,7 +131,7 @@ int rio_mport_write_config_##size \
 	unsigned long flags;						\
 	if (RIO_##size##_BAD) return RIO_BAD_SIZE;			\
 	spin_lock_irqsave(&rio_config_lock, flags);			\
-	res = mport->ops->cwrite(mport->id, destid, hopcount, offset, len, value); \
+	res = mport->ops->cwrite(mport, mport->id, destid, hopcount, offset, len, value); \
 	spin_unlock_irqrestore(&rio_config_lock, flags);		\
 	return res;							\
 }
@@ -166,7 +166,7 @@ int rio_mport_send_doorbell(struct rio_mport *mport, u16 destid, u16 data)
 	unsigned long flags;
 
 	spin_lock_irqsave(&rio_doorbell_lock, flags);
-	res = mport->ops->dsend(mport->id, destid, data);
+	res = mport->ops->dsend(mport, mport->id, destid, data);
 	spin_unlock_irqrestore(&rio_doorbell_lock, flags);
 
 	return res;
diff --git a/trunk/drivers/rapidio/rio-scan.c b/trunk/drivers/rapidio/rio-scan.c
index 44420723a359..a926c896475e 100644
--- a/trunk/drivers/rapidio/rio-scan.c
+++ b/trunk/drivers/rapidio/rio-scan.c
@@ -73,7 +73,7 @@ static u16 rio_get_device_id(struct rio_mport *port, u16 destid, u8 hopcount)
 
 	rio_mport_read_config_32(port, destid, hopcount, RIO_DID_CSR, &result);
 
-	return RIO_GET_DID(result);
+	return RIO_GET_DID(port->sys_size, result);
 }
 
 /**
@@ -88,7 +88,7 @@ static u16 rio_get_device_id(struct rio_mport *port, u16 destid, u8 hopcount)
 static void rio_set_device_id(struct rio_mport *port, u16 destid, u8 hopcount, u16 did)
 {
 	rio_mport_write_config_32(port, destid, hopcount, RIO_DID_CSR,
-				  RIO_SET_DID(did));
+				  RIO_SET_DID(port->sys_size, did));
 }
 
 /**
@@ -100,7 +100,8 @@ static void rio_set_device_id(struct rio_mport *port, u16 destid, u8 hopcount, u
  */
 static void rio_local_set_device_id(struct rio_mport *port, u16 did)
 {
-	rio_local_write_config_32(port, RIO_DID_CSR, RIO_SET_DID(did));
+	rio_local_write_config_32(port, RIO_DID_CSR, RIO_SET_DID(port->sys_size,
+				did));
 }
 
 /**
@@ -350,8 +351,18 @@ static struct rio_dev *rio_setup_device(struct rio_net *net,
 		rswitch->switchid = next_switchid;
 		rswitch->hopcount = hopcount;
 		rswitch->destid = destid;
+		rswitch->route_table = kzalloc(sizeof(u8)*
+					RIO_MAX_ROUTE_ENTRIES(port->sys_size),
+					GFP_KERNEL);
+		if (!rswitch->route_table) {
+			kfree(rdev);
+			rdev = NULL;
+			kfree(rswitch);
+			goto out;
+		}
 		/* Initialize switch route table */
-		for (rdid = 0; rdid < RIO_MAX_ROUTE_ENTRIES; rdid++)
+		for (rdid = 0; rdid < RIO_MAX_ROUTE_ENTRIES(port->sys_size);
+				rdid++)
 			rswitch->route_table[rdid] = RIO_INVALID_ROUTE;
 		rdev->rswitch = rswitch;
 		sprintf(rio_name(rdev), "%02x:s:%04x", rdev->net->id,
@@ -480,7 +491,7 @@ static u16 rio_get_host_deviceid_lock(struct rio_mport *port, u8 hopcount)
 {
 	u32 result;
 
-	rio_mport_read_config_32(port, RIO_ANY_DESTID, hopcount,
+	rio_mport_read_config_32(port, RIO_ANY_DESTID(port->sys_size), hopcount,
 				 RIO_HOST_DID_LOCK_CSR, &result);
 
 	return (u16) (result & 0xffff);
@@ -571,14 +582,16 @@ static int rio_enum_peer(struct rio_net *net, struct rio_mport *port,
 	}
 
 	/* Attempt to acquire device lock */
-	rio_mport_write_config_32(port, RIO_ANY_DESTID, hopcount,
+	rio_mport_write_config_32(port, RIO_ANY_DESTID(port->sys_size),
+				  hopcount,
 				  RIO_HOST_DID_LOCK_CSR, port->host_deviceid);
 	while ((tmp = rio_get_host_deviceid_lock(port, hopcount))
 	       < port->host_deviceid) {
 		/* Delay a bit */
 		mdelay(1);
 		/* Attempt to acquire device lock again */
-		rio_mport_write_config_32(port, RIO_ANY_DESTID, hopcount,
+		rio_mport_write_config_32(port, RIO_ANY_DESTID(port->sys_size),
+					  hopcount,
 					  RIO_HOST_DID_LOCK_CSR,
 					  port->host_deviceid);
 	}
@@ -590,7 +603,9 @@ static int rio_enum_peer(struct rio_net *net, struct rio_mport *port,
 	}
 
 	/* Setup new RIO device */
-	if ((rdev = rio_setup_device(net, port, RIO_ANY_DESTID, hopcount, 1))) {
+	rdev = rio_setup_device(net, port, RIO_ANY_DESTID(port->sys_size),
+					hopcount, 1);
+	if (rdev) {
 		/* Add device to the global and bus/net specific list. */
 		list_add_tail(&rdev->net_list, &net->devices);
 	} else
@@ -598,7 +613,8 @@ static int rio_enum_peer(struct rio_net *net, struct rio_mport *port,
 
 	if (rio_is_switch(rdev)) {
 		next_switchid++;
-		sw_inport = rio_get_swpinfo_inport(port, RIO_ANY_DESTID, hopcount);
+		sw_inport = rio_get_swpinfo_inport(port,
+				RIO_ANY_DESTID(port->sys_size), hopcount);
 		rio_route_add_entry(port, rdev->rswitch, RIO_GLOBAL_TABLE,
 				    port->host_deviceid, sw_inport);
 		rdev->rswitch->route_table[port->host_deviceid] = sw_inport;
@@ -612,7 +628,8 @@ static int rio_enum_peer(struct rio_net *net, struct rio_mport *port,
 		}
 
 		num_ports =
-		    rio_get_swpinfo_tports(port, RIO_ANY_DESTID, hopcount);
+		    rio_get_swpinfo_tports(port, RIO_ANY_DESTID(port->sys_size),
+						hopcount);
 		pr_debug(
 		    "RIO: found %s (vid %4.4x did %4.4x) with %d ports\n",
 		    rio_name(rdev), rdev->vid, rdev->did, num_ports);
@@ -624,13 +641,15 @@ static int rio_enum_peer(struct rio_net *net, struct rio_mport *port,
 			cur_destid = next_destid;
 
 			if (rio_sport_is_active
-			    (port, RIO_ANY_DESTID, hopcount, port_num)) {
+			    (port, RIO_ANY_DESTID(port->sys_size), hopcount,
+			     port_num)) {
 				pr_debug(
 				    "RIO: scanning device on port %d\n",
 				    port_num);
 				rio_route_add_entry(port, rdev->rswitch,
-						    RIO_GLOBAL_TABLE,
-						    RIO_ANY_DESTID, port_num);
+						RIO_GLOBAL_TABLE,
+						RIO_ANY_DESTID(port->sys_size),
+						port_num);
 
 				if (rio_enum_peer(net, port, hopcount + 1) < 0)
 					return -1;
@@ -735,7 +754,8 @@ rio_disc_peer(struct rio_net *net, struct rio_mport *port, u16 destid,
 				pr_debug(
 				    "RIO: scanning device on port %d\n",
 				    port_num);
-				for (ndestid = 0; ndestid < RIO_ANY_DESTID;
+				for (ndestid = 0;
+				     ndestid < RIO_ANY_DESTID(port->sys_size);
 				     ndestid++) {
 					rio_route_get_entry(port, rdev->rswitch,
 							    RIO_GLOBAL_TABLE,
@@ -917,7 +937,9 @@ static void rio_build_route_tables(void)
 
 	list_for_each_entry(rdev, &rio_devices, global_list)
 	    if (rio_is_switch(rdev))
-		for (i = 0; i < RIO_MAX_ROUTE_ENTRIES; i++) {
+		for (i = 0;
+		     i < RIO_MAX_ROUTE_ENTRIES(rdev->net->hport->sys_size);
+		     i++) {
 			if (rio_route_get_entry
 			    (rdev->net->hport, rdev->rswitch, RIO_GLOBAL_TABLE,
 			     i, &sport) < 0)
@@ -981,7 +1003,8 @@ int rio_disc_mport(struct rio_mport *mport)
 		del_timer_sync(&rio_enum_timer);
 
 		pr_debug("done\n");
-		if (rio_disc_peer(net, mport, RIO_ANY_DESTID, 0) < 0) {
+		if (rio_disc_peer(net, mport, RIO_ANY_DESTID(mport->sys_size),
+					0) < 0) {
 			printk(KERN_INFO
 			       "RIO: master port %d device has failed discovery\n",
 			       mport->id);
diff --git a/trunk/drivers/rapidio/rio-sysfs.c b/trunk/drivers/rapidio/rio-sysfs.c
index 659e31164cf0..97a147f050d6 100644
--- a/trunk/drivers/rapidio/rio-sysfs.c
+++ b/trunk/drivers/rapidio/rio-sysfs.c
@@ -43,7 +43,8 @@ static ssize_t routes_show(struct device *dev, struct device_attribute *attr, ch
 	if (!rdev->rswitch)
 		goto out;
 
-	for (i = 0; i < RIO_MAX_ROUTE_ENTRIES; i++) {
+	for (i = 0; i < RIO_MAX_ROUTE_ENTRIES(rdev->net->hport->sys_size);
+			i++) {
 		if (rdev->rswitch->route_table[i] == RIO_INVALID_ROUTE)
 			continue;
 		str +=
diff --git a/trunk/drivers/rapidio/rio.c b/trunk/drivers/rapidio/rio.c
index 80c5f1ba2e49..680661abbc4b 100644
--- a/trunk/drivers/rapidio/rio.c
+++ b/trunk/drivers/rapidio/rio.c
@@ -43,7 +43,7 @@ u16 rio_local_get_device_id(struct rio_mport *port)
 
 	rio_local_read_config_32(port, RIO_DID_CSR, &result);
 
-	return (RIO_GET_DID(result));
+	return (RIO_GET_DID(port->sys_size, result));
 }
 
 /**
diff --git a/trunk/drivers/rapidio/rio.h b/trunk/drivers/rapidio/rio.h
index 80e3f03b5041..7786d02581f2 100644
--- a/trunk/drivers/rapidio/rio.h
+++ b/trunk/drivers/rapidio/rio.h
@@ -51,10 +51,5 @@ extern struct rio_route_ops __end_rio_route_ops[];
 	DECLARE_RIO_ROUTE_SECTION(.rio_route_ops,			\
 			vid, did, add_hook, get_hook)
 
-#ifdef CONFIG_RAPIDIO_8_BIT_TRANSPORT
-#define RIO_GET_DID(x)	((x & 0x00ff0000) >> 16)
-#define RIO_SET_DID(x)	((x & 0x000000ff) << 16)
-#else
-#define RIO_GET_DID(x)	(x & 0xffff)
-#define RIO_SET_DID(x)	(x & 0xffff)
-#endif
+#define RIO_GET_DID(size, x)	(size ? (x & 0xffff) : ((x & 0x00ff0000) >> 16))
+#define RIO_SET_DID(size, x)	(size ? (x & 0xffff) : ((x & 0x000000ff) << 16))
diff --git a/trunk/drivers/rtc/Kconfig b/trunk/drivers/rtc/Kconfig
index 02a4c8cf2b2d..6cc2c0330230 100644
--- a/trunk/drivers/rtc/Kconfig
+++ b/trunk/drivers/rtc/Kconfig
@@ -20,10 +20,6 @@ menuconfig RTC_CLASS
 
 if RTC_CLASS
 
-if GEN_RTC || RTC
-comment "Conflicting RTC option has been selected, check GEN_RTC and RTC"
-endif
-
 config RTC_HCTOSYS
 	bool "Set system time from RTC on startup and resume"
 	depends on RTC_CLASS = y
@@ -304,6 +300,7 @@ comment "Platform RTC drivers"
 config RTC_DRV_CMOS
 	tristate "PC-style 'CMOS'"
 	depends on X86 || ALPHA || ARM || M32R || ATARI || PPC || MIPS
+	default y if X86
 	help
 	  Say "yes" here to get direct support for the real time clock
 	  found in every PC or ACPI-based system, and some other boards.
diff --git a/trunk/drivers/rtc/rtc-at91rm9200.c b/trunk/drivers/rtc/rtc-at91rm9200.c
index 52abffc86bcd..39e64ab1ecb7 100644
--- a/trunk/drivers/rtc/rtc-at91rm9200.c
+++ b/trunk/drivers/rtc/rtc-at91rm9200.c
@@ -83,7 +83,7 @@ static int at91_rtc_readtime(struct device *dev, struct rtc_time *tm)
 	tm->tm_yday = rtc_year_days(tm->tm_mday, tm->tm_mon, tm->tm_year);
 	tm->tm_year = tm->tm_year - 1900;
 
-	pr_debug("%s(): %4d-%02d-%02d %02d:%02d:%02d\n", __FUNCTION__,
+	pr_debug("%s(): %4d-%02d-%02d %02d:%02d:%02d\n", __func__,
 		1900 + tm->tm_year, tm->tm_mon, tm->tm_mday,
 		tm->tm_hour, tm->tm_min, tm->tm_sec);
 
@@ -97,7 +97,7 @@ static int at91_rtc_settime(struct device *dev, struct rtc_time *tm)
 {
 	unsigned long cr;
 
-	pr_debug("%s(): %4d-%02d-%02d %02d:%02d:%02d\n", __FUNCTION__,
+	pr_debug("%s(): %4d-%02d-%02d %02d:%02d:%02d\n", __func__,
 		1900 + tm->tm_year, tm->tm_mon, tm->tm_mday,
 		tm->tm_hour, tm->tm_min, tm->tm_sec);
 
@@ -142,7 +142,7 @@ static int at91_rtc_readalarm(struct device *dev, struct rtc_wkalrm *alrm)
 	alrm->enabled = (at91_sys_read(AT91_RTC_IMR) & AT91_RTC_ALARM)
 			? 1 : 0;
 
-	pr_debug("%s(): %4d-%02d-%02d %02d:%02d:%02d\n", __FUNCTION__,
+	pr_debug("%s(): %4d-%02d-%02d %02d:%02d:%02d\n", __func__,
 		1900 + tm->tm_year, tm->tm_mon, tm->tm_mday,
 		tm->tm_hour, tm->tm_min, tm->tm_sec);
 
@@ -178,7 +178,7 @@ static int at91_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 	if (alrm->enabled)
 		at91_sys_write(AT91_RTC_IER, AT91_RTC_ALARM);
 
-	pr_debug("%s(): %4d-%02d-%02d %02d:%02d:%02d\n", __FUNCTION__,
+	pr_debug("%s(): %4d-%02d-%02d %02d:%02d:%02d\n", __func__,
 		at91_alarm_year, tm.tm_mon, tm.tm_mday, tm.tm_hour,
 		tm.tm_min, tm.tm_sec);
 
@@ -193,7 +193,7 @@ static int at91_rtc_ioctl(struct device *dev, unsigned int cmd,
 {
 	int ret = 0;
 
-	pr_debug("%s(): cmd=%08x, arg=%08lx.\n", __FUNCTION__, cmd, arg);
+	pr_debug("%s(): cmd=%08x, arg=%08lx.\n", __func__, cmd, arg);
 
 	switch (cmd) {
 	case RTC_AIE_OFF:	/* alarm off */
@@ -265,7 +265,7 @@ static irqreturn_t at91_rtc_interrupt(int irq, void *dev_id)
 
 		rtc_update_irq(rtc, 1, events);
 
-		pr_debug("%s(): num=%ld, events=0x%02lx\n", __FUNCTION__,
+		pr_debug("%s(): num=%ld, events=0x%02lx\n", __func__,
 			events >> 8, events & 0x000000FF);
 
 		return IRQ_HANDLED;
diff --git a/trunk/drivers/rtc/rtc-at91sam9.c b/trunk/drivers/rtc/rtc-at91sam9.c
index 56728a2a3385..38d8742a4bdf 100644
--- a/trunk/drivers/rtc/rtc-at91sam9.c
+++ b/trunk/drivers/rtc/rtc-at91sam9.c
@@ -288,7 +288,7 @@ static irqreturn_t at91_rtc_interrupt(int irq, void *_rtc)
 
 	rtc_update_irq(rtc->rtcdev, 1, events);
 
-	pr_debug("%s: num=%ld, events=0x%02lx\n", __FUNCTION__,
+	pr_debug("%s: num=%ld, events=0x%02lx\n", __func__,
 		events >> 8, events & 0x000000FF);
 
 	return IRQ_HANDLED;
diff --git a/trunk/drivers/rtc/rtc-bfin.c b/trunk/drivers/rtc/rtc-bfin.c
index 4f28045d9ef2..8624f55d0560 100644
--- a/trunk/drivers/rtc/rtc-bfin.c
+++ b/trunk/drivers/rtc/rtc-bfin.c
@@ -419,7 +419,7 @@ static int __devinit bfin_rtc_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	rtc->rtc_dev = rtc_device_register(pdev->name, &pdev->dev, &bfin_rtc_ops, THIS_MODULE);
-	if (unlikely(IS_ERR(rtc))) {
+	if (IS_ERR(rtc)) {
 		ret = PTR_ERR(rtc->rtc_dev);
 		goto err;
 	}
diff --git a/trunk/drivers/rtc/rtc-ds1302.c b/trunk/drivers/rtc/rtc-ds1302.c
index 7b002ceeaa7d..b9397818f73a 100644
--- a/trunk/drivers/rtc/rtc-ds1302.c
+++ b/trunk/drivers/rtc/rtc-ds1302.c
@@ -122,7 +122,7 @@ static int ds1302_rtc_read_time(struct device *dev, struct rtc_time *tm)
 
 	dev_dbg(dev, "%s: tm is secs=%d, mins=%d, hours=%d, "
 		"mday=%d, mon=%d, year=%d, wday=%d\n",
-		__FUNCTION__,
+		__func__,
 		tm->tm_sec, tm->tm_min, tm->tm_hour,
 		tm->tm_mday, tm->tm_mon + 1, tm->tm_year, tm->tm_wday);
 
diff --git a/trunk/drivers/rtc/rtc-ds1511.c b/trunk/drivers/rtc/rtc-ds1511.c
index d08912f18ddd..a83a40b3ebaa 100644
--- a/trunk/drivers/rtc/rtc-ds1511.c
+++ b/trunk/drivers/rtc/rtc-ds1511.c
@@ -181,8 +181,7 @@ ds1511_wdog_disable(void)
  * stupidly, some callers call with year unmolested;
  * and some call with  year = year - 1900.  thanks.
  */
- int
-ds1511_rtc_set_time(struct device *dev, struct rtc_time *rtc_tm)
+static int ds1511_rtc_set_time(struct device *dev, struct rtc_time *rtc_tm)
 {
 	u8 mon, day, dow, hrs, min, sec, yrs, cen;
 	unsigned int flags;
@@ -245,8 +244,7 @@ ds1511_rtc_set_time(struct device *dev, struct rtc_time *rtc_tm)
 	return 0;
 }
 
- int
-ds1511_rtc_read_time(struct device *dev, struct rtc_time *rtc_tm)
+static int ds1511_rtc_read_time(struct device *dev, struct rtc_time *rtc_tm)
 {
 	unsigned int century;
 	unsigned int flags;
diff --git a/trunk/drivers/rtc/rtc-ds1672.c b/trunk/drivers/rtc/rtc-ds1672.c
index e0900ca678ec..6fa4556f5f5c 100644
--- a/trunk/drivers/rtc/rtc-ds1672.c
+++ b/trunk/drivers/rtc/rtc-ds1672.c
@@ -50,13 +50,13 @@ static int ds1672_get_datetime(struct i2c_client *client, struct rtc_time *tm)
 
 	/* read date registers */
 	if ((i2c_transfer(client->adapter, &msgs[0], 2)) != 2) {
-		dev_err(&client->dev, "%s: read error\n", __FUNCTION__);
+		dev_err(&client->dev, "%s: read error\n", __func__);
 		return -EIO;
 	}
 
 	dev_dbg(&client->dev,
 		"%s: raw read data - counters=%02x,%02x,%02x,%02x\n",
-		__FUNCTION__, buf[0], buf[1], buf[2], buf[3]);
+		__func__, buf[0], buf[1], buf[2], buf[3]);
 
 	time = (buf[3] << 24) | (buf[2] << 16) | (buf[1] << 8) | buf[0];
 
@@ -64,7 +64,7 @@ static int ds1672_get_datetime(struct i2c_client *client, struct rtc_time *tm)
 
 	dev_dbg(&client->dev, "%s: tm is secs=%d, mins=%d, hours=%d, "
 		"mday=%d, mon=%d, year=%d, wday=%d\n",
-		__FUNCTION__, tm->tm_sec, tm->tm_min, tm->tm_hour,
+		__func__, tm->tm_sec, tm->tm_min, tm->tm_hour,
 		tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday);
 
 	return 0;
@@ -84,7 +84,7 @@ static int ds1672_set_mmss(struct i2c_client *client, unsigned long secs)
 
 	xfer = i2c_master_send(client, buf, 6);
 	if (xfer != 6) {
-		dev_err(&client->dev, "%s: send: %d\n", __FUNCTION__, xfer);
+		dev_err(&client->dev, "%s: send: %d\n", __func__, xfer);
 		return -EIO;
 	}
 
@@ -98,7 +98,7 @@ static int ds1672_set_datetime(struct i2c_client *client, struct rtc_time *tm)
 	dev_dbg(&client->dev,
 		"%s: secs=%d, mins=%d, hours=%d, "
 		"mday=%d, mon=%d, year=%d, wday=%d\n",
-		__FUNCTION__,
+		__func__,
 		tm->tm_sec, tm->tm_min, tm->tm_hour,
 		tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday);
 
@@ -133,7 +133,7 @@ static int ds1672_get_control(struct i2c_client *client, u8 *status)
 
 	/* read control register */
 	if ((i2c_transfer(client->adapter, &msgs[0], 2)) != 2) {
-		dev_err(&client->dev, "%s: read error\n", __FUNCTION__);
+		dev_err(&client->dev, "%s: read error\n", __func__);
 		return -EIO;
 	}
 
@@ -199,7 +199,7 @@ static int ds1672_probe(struct i2c_adapter *adapter, int address, int kind)
 	struct i2c_client *client;
 	struct rtc_device *rtc;
 
-	dev_dbg(&adapter->dev, "%s\n", __FUNCTION__);
+	dev_dbg(&adapter->dev, "%s\n", __func__);
 
 	if (!i2c_check_functionality(adapter, I2C_FUNC_I2C)) {
 		err = -ENODEV;
diff --git a/trunk/drivers/rtc/rtc-isl1208.c b/trunk/drivers/rtc/rtc-isl1208.c
index 725b0c73c333..fb15e3fb4ce2 100644
--- a/trunk/drivers/rtc/rtc-isl1208.c
+++ b/trunk/drivers/rtc/rtc-isl1208.c
@@ -15,16 +15,15 @@
 #include <linux/bcd.h>
 #include <linux/rtc.h>
 
-#define DRV_NAME "isl1208"
-#define DRV_VERSION "0.2"
+#define DRV_VERSION "0.3"
 
 /* Register map */
 /* rtc section */
 #define ISL1208_REG_SC  0x00
 #define ISL1208_REG_MN  0x01
 #define ISL1208_REG_HR  0x02
-#define ISL1208_REG_HR_MIL     (1<<7) /* 24h/12h mode */
-#define ISL1208_REG_HR_PM      (1<<5) /* PM/AM bit in 12h mode */
+#define ISL1208_REG_HR_MIL     (1<<7)	/* 24h/12h mode */
+#define ISL1208_REG_HR_PM      (1<<5)	/* PM/AM bit in 12h mode */
 #define ISL1208_REG_DT  0x03
 #define ISL1208_REG_MO  0x04
 #define ISL1208_REG_YR  0x05
@@ -33,14 +32,14 @@
 
 /* control/status section */
 #define ISL1208_REG_SR  0x07
-#define ISL1208_REG_SR_ARST    (1<<7) /* auto reset */
-#define ISL1208_REG_SR_XTOSCB  (1<<6) /* crystal oscillator */
-#define ISL1208_REG_SR_WRTC    (1<<4) /* write rtc */
-#define ISL1208_REG_SR_ALM     (1<<2) /* alarm */
-#define ISL1208_REG_SR_BAT     (1<<1) /* battery */
-#define ISL1208_REG_SR_RTCF    (1<<0) /* rtc fail */
+#define ISL1208_REG_SR_ARST    (1<<7)	/* auto reset */
+#define ISL1208_REG_SR_XTOSCB  (1<<6)	/* crystal oscillator */
+#define ISL1208_REG_SR_WRTC    (1<<4)	/* write rtc */
+#define ISL1208_REG_SR_ALM     (1<<2)	/* alarm */
+#define ISL1208_REG_SR_BAT     (1<<1)	/* battery */
+#define ISL1208_REG_SR_RTCF    (1<<0)	/* rtc fail */
 #define ISL1208_REG_INT 0x08
-#define ISL1208_REG_09  0x09 /* reserved */
+#define ISL1208_REG_09  0x09	/* reserved */
 #define ISL1208_REG_ATR 0x0a
 #define ISL1208_REG_DTR 0x0b
 
@@ -58,39 +57,21 @@
 #define ISL1208_REG_USR2 0x13
 #define ISL1208_USR_SECTION_LEN 2
 
-/* i2c configuration */
-#define ISL1208_I2C_ADDR 0xde
-
-static const unsigned short normal_i2c[] = {
-	ISL1208_I2C_ADDR>>1, I2C_CLIENT_END
-};
-I2C_CLIENT_INSMOD; /* defines addr_data */
-
-static int isl1208_attach_adapter(struct i2c_adapter *adapter);
-static int isl1208_detach_client(struct i2c_client *client);
-
-static struct i2c_driver isl1208_driver = {
-	.driver		= {
-		.name	= DRV_NAME,
-	},
-	.id		= I2C_DRIVERID_ISL1208,
-	.attach_adapter = &isl1208_attach_adapter,
-	.detach_client	= &isl1208_detach_client,
-};
+static struct i2c_driver isl1208_driver;
 
 /* block read */
 static int
 isl1208_i2c_read_regs(struct i2c_client *client, u8 reg, u8 buf[],
-		       unsigned len)
+		      unsigned len)
 {
 	u8 reg_addr[1] = { reg };
 	struct i2c_msg msgs[2] = {
-		{ client->addr, client->flags, sizeof(reg_addr), reg_addr },
-		{ client->addr, client->flags | I2C_M_RD, len, buf }
+		{client->addr, 0, sizeof(reg_addr), reg_addr}
+		,
+		{client->addr, I2C_M_RD, len, buf}
 	};
 	int ret;
 
-	BUG_ON(len == 0);
 	BUG_ON(reg > ISL1208_REG_USR2);
 	BUG_ON(reg + len > ISL1208_REG_USR2 + 1);
 
@@ -103,15 +84,14 @@ isl1208_i2c_read_regs(struct i2c_client *client, u8 reg, u8 buf[],
 /* block write */
 static int
 isl1208_i2c_set_regs(struct i2c_client *client, u8 reg, u8 const buf[],
-		       unsigned len)
+		     unsigned len)
 {
 	u8 i2c_buf[ISL1208_REG_USR2 + 2];
 	struct i2c_msg msgs[1] = {
-		{ client->addr, client->flags, len + 1, i2c_buf }
+		{client->addr, 0, len + 1, i2c_buf}
 	};
 	int ret;
 
-	BUG_ON(len == 0);
 	BUG_ON(reg > ISL1208_REG_USR2);
 	BUG_ON(reg + len > ISL1208_REG_USR2 + 1);
 
@@ -125,7 +105,8 @@ isl1208_i2c_set_regs(struct i2c_client *client, u8 reg, u8 const buf[],
 }
 
 /* simple check to see wether we have a isl1208 */
-static int isl1208_i2c_validate_client(struct i2c_client *client)
+static int
+isl1208_i2c_validate_client(struct i2c_client *client)
 {
 	u8 regs[ISL1208_RTC_SECTION_LEN] = { 0, };
 	u8 zero_mask[ISL1208_RTC_SECTION_LEN] = {
@@ -139,24 +120,29 @@ static int isl1208_i2c_validate_client(struct i2c_client *client)
 		return ret;
 
 	for (i = 0; i < ISL1208_RTC_SECTION_LEN; ++i) {
-		if (regs[i] & zero_mask[i]) /* check if bits are cleared */
+		if (regs[i] & zero_mask[i])	/* check if bits are cleared */
 			return -ENODEV;
 	}
 
 	return 0;
 }
 
-static int isl1208_i2c_get_sr(struct i2c_client *client)
+static int
+isl1208_i2c_get_sr(struct i2c_client *client)
 {
-	return i2c_smbus_read_byte_data(client, ISL1208_REG_SR) == -1 ? -EIO:0;
+	int sr = i2c_smbus_read_byte_data(client, ISL1208_REG_SR);
+	if (sr < 0)
+		return -EIO;
+
+	return sr;
 }
 
-static int isl1208_i2c_get_atr(struct i2c_client *client)
+static int
+isl1208_i2c_get_atr(struct i2c_client *client)
 {
 	int atr = i2c_smbus_read_byte_data(client, ISL1208_REG_ATR);
-
 	if (atr < 0)
-		return -EIO;
+		return atr;
 
 	/* The 6bit value in the ATR register controls the load
 	 * capacitance C_load * in steps of 0.25pF
@@ -169,51 +155,54 @@ static int isl1208_i2c_get_atr(struct i2c_client *client)
 	 *
 	 */
 
-	atr &= 0x3f; /* mask out lsb */
-	atr ^= 1<<5; /* invert 6th bit */
-	atr += 2*9; /* add offset of 4.5pF; unit[atr] = 0.25pF */
+	atr &= 0x3f;		/* mask out lsb */
+	atr ^= 1 << 5;		/* invert 6th bit */
+	atr += 2 * 9;		/* add offset of 4.5pF; unit[atr] = 0.25pF */
 
 	return atr;
 }
 
-static int isl1208_i2c_get_dtr(struct i2c_client *client)
+static int
+isl1208_i2c_get_dtr(struct i2c_client *client)
 {
 	int dtr = i2c_smbus_read_byte_data(client, ISL1208_REG_DTR);
-
 	if (dtr < 0)
 		return -EIO;
 
 	/* dtr encodes adjustments of {-60,-40,-20,0,20,40,60} ppm */
-	dtr = ((dtr & 0x3) * 20) * (dtr & (1<<2) ? -1 : 1);
+	dtr = ((dtr & 0x3) * 20) * (dtr & (1 << 2) ? -1 : 1);
 
 	return dtr;
 }
 
-static int isl1208_i2c_get_usr(struct i2c_client *client)
+static int
+isl1208_i2c_get_usr(struct i2c_client *client)
 {
 	u8 buf[ISL1208_USR_SECTION_LEN] = { 0, };
 	int ret;
 
-	ret = isl1208_i2c_read_regs (client, ISL1208_REG_USR1, buf,
-				   ISL1208_USR_SECTION_LEN);
+	ret = isl1208_i2c_read_regs(client, ISL1208_REG_USR1, buf,
+				    ISL1208_USR_SECTION_LEN);
 	if (ret < 0)
 		return ret;
 
 	return (buf[1] << 8) | buf[0];
 }
 
-static int isl1208_i2c_set_usr(struct i2c_client *client, u16 usr)
+static int
+isl1208_i2c_set_usr(struct i2c_client *client, u16 usr)
 {
 	u8 buf[ISL1208_USR_SECTION_LEN];
 
 	buf[0] = usr & 0xff;
 	buf[1] = (usr >> 8) & 0xff;
 
-	return isl1208_i2c_set_regs (client, ISL1208_REG_USR1, buf,
-				     ISL1208_USR_SECTION_LEN);
+	return isl1208_i2c_set_regs(client, ISL1208_REG_USR1, buf,
+				    ISL1208_USR_SECTION_LEN);
 }
 
-static int isl1208_rtc_proc(struct device *dev, struct seq_file *seq)
+static int
+isl1208_rtc_proc(struct device *dev, struct seq_file *seq)
 {
 	struct i2c_client *const client = to_i2c_client(dev);
 	int sr, dtr, atr, usr;
@@ -230,20 +219,19 @@ static int isl1208_rtc_proc(struct device *dev, struct seq_file *seq)
 		   (sr & ISL1208_REG_SR_ALM) ? " ALM" : "",
 		   (sr & ISL1208_REG_SR_WRTC) ? " WRTC" : "",
 		   (sr & ISL1208_REG_SR_XTOSCB) ? " XTOSCB" : "",
-		   (sr & ISL1208_REG_SR_ARST) ? " ARST" : "",
-		   sr);
+		   (sr & ISL1208_REG_SR_ARST) ? " ARST" : "", sr);
 
 	seq_printf(seq, "batt_status\t: %s\n",
 		   (sr & ISL1208_REG_SR_RTCF) ? "bad" : "okay");
 
 	dtr = isl1208_i2c_get_dtr(client);
-	if (dtr >= 0 -1)
+	if (dtr >= 0 - 1)
 		seq_printf(seq, "digital_trim\t: %d ppm\n", dtr);
 
 	atr = isl1208_i2c_get_atr(client);
 	if (atr >= 0)
 		seq_printf(seq, "analog_trim\t: %d.%.2d pF\n",
-			   atr>>2, (atr&0x3)*25);
+			   atr >> 2, (atr & 0x3) * 25);
 
 	usr = isl1208_i2c_get_usr(client);
 	if (usr >= 0)
@@ -252,9 +240,8 @@ static int isl1208_rtc_proc(struct device *dev, struct seq_file *seq)
 	return 0;
 }
 
-
-static int isl1208_i2c_read_time(struct i2c_client *client,
-				 struct rtc_time *tm)
+static int
+isl1208_i2c_read_time(struct i2c_client *client, struct rtc_time *tm)
 {
 	int sr;
 	u8 regs[ISL1208_RTC_SECTION_LEN] = { 0, };
@@ -274,27 +261,30 @@ static int isl1208_i2c_read_time(struct i2c_client *client,
 
 	tm->tm_sec = BCD2BIN(regs[ISL1208_REG_SC]);
 	tm->tm_min = BCD2BIN(regs[ISL1208_REG_MN]);
-	{ /* HR field has a more complex interpretation */
+
+	/* HR field has a more complex interpretation */
+	{
 		const u8 _hr = regs[ISL1208_REG_HR];
-		if (_hr & ISL1208_REG_HR_MIL) /* 24h format */
+		if (_hr & ISL1208_REG_HR_MIL)	/* 24h format */
 			tm->tm_hour = BCD2BIN(_hr & 0x3f);
-		else { // 12h format
+		else {
+			/* 12h format */
 			tm->tm_hour = BCD2BIN(_hr & 0x1f);
-			if (_hr & ISL1208_REG_HR_PM) /* PM flag set */
+			if (_hr & ISL1208_REG_HR_PM)	/* PM flag set */
 				tm->tm_hour += 12;
 		}
 	}
 
 	tm->tm_mday = BCD2BIN(regs[ISL1208_REG_DT]);
-	tm->tm_mon = BCD2BIN(regs[ISL1208_REG_MO]) - 1; /* rtc starts at 1 */
+	tm->tm_mon = BCD2BIN(regs[ISL1208_REG_MO]) - 1;	/* rtc starts at 1 */
 	tm->tm_year = BCD2BIN(regs[ISL1208_REG_YR]) + 100;
 	tm->tm_wday = BCD2BIN(regs[ISL1208_REG_DW]);
 
 	return 0;
 }
 
-static int isl1208_i2c_read_alarm(struct i2c_client *client,
-				  struct rtc_wkalrm *alarm)
+static int
+isl1208_i2c_read_alarm(struct i2c_client *client, struct rtc_wkalrm *alarm)
 {
 	struct rtc_time *const tm = &alarm->time;
 	u8 regs[ISL1208_ALARM_SECTION_LEN] = { 0, };
@@ -307,7 +297,7 @@ static int isl1208_i2c_read_alarm(struct i2c_client *client,
 	}
 
 	sr = isl1208_i2c_read_regs(client, ISL1208_REG_SCA, regs,
-				  ISL1208_ALARM_SECTION_LEN);
+				   ISL1208_ALARM_SECTION_LEN);
 	if (sr < 0) {
 		dev_err(&client->dev, "%s: reading alarm section failed\n",
 			__func__);
@@ -315,23 +305,25 @@ static int isl1208_i2c_read_alarm(struct i2c_client *client,
 	}
 
 	/* MSB of each alarm register is an enable bit */
-	tm->tm_sec  = BCD2BIN(regs[ISL1208_REG_SCA-ISL1208_REG_SCA] & 0x7f);
-	tm->tm_min  = BCD2BIN(regs[ISL1208_REG_MNA-ISL1208_REG_SCA] & 0x7f);
-	tm->tm_hour = BCD2BIN(regs[ISL1208_REG_HRA-ISL1208_REG_SCA] & 0x3f);
-	tm->tm_mday = BCD2BIN(regs[ISL1208_REG_DTA-ISL1208_REG_SCA] & 0x3f);
-	tm->tm_mon  = BCD2BIN(regs[ISL1208_REG_MOA-ISL1208_REG_SCA] & 0x1f)-1;
-	tm->tm_wday = BCD2BIN(regs[ISL1208_REG_DWA-ISL1208_REG_SCA] & 0x03);
+	tm->tm_sec = BCD2BIN(regs[ISL1208_REG_SCA - ISL1208_REG_SCA] & 0x7f);
+	tm->tm_min = BCD2BIN(regs[ISL1208_REG_MNA - ISL1208_REG_SCA] & 0x7f);
+	tm->tm_hour = BCD2BIN(regs[ISL1208_REG_HRA - ISL1208_REG_SCA] & 0x3f);
+	tm->tm_mday = BCD2BIN(regs[ISL1208_REG_DTA - ISL1208_REG_SCA] & 0x3f);
+	tm->tm_mon =
+		BCD2BIN(regs[ISL1208_REG_MOA - ISL1208_REG_SCA] & 0x1f) - 1;
+	tm->tm_wday = BCD2BIN(regs[ISL1208_REG_DWA - ISL1208_REG_SCA] & 0x03);
 
 	return 0;
 }
 
-static int isl1208_rtc_read_time(struct device *dev, struct rtc_time *tm)
+static int
+isl1208_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
 	return isl1208_i2c_read_time(to_i2c_client(dev), tm);
 }
 
-static int isl1208_i2c_set_time(struct i2c_client *client,
-				struct rtc_time const *tm)
+static int
+isl1208_i2c_set_time(struct i2c_client *client, struct rtc_time const *tm)
 {
 	int sr;
 	u8 regs[ISL1208_RTC_SECTION_LEN] = { 0, };
@@ -353,7 +345,7 @@ static int isl1208_i2c_set_time(struct i2c_client *client,
 	}
 
 	/* set WRTC */
-	sr = i2c_smbus_write_byte_data (client, ISL1208_REG_SR,
+	sr = i2c_smbus_write_byte_data(client, ISL1208_REG_SR,
 				       sr | ISL1208_REG_SR_WRTC);
 	if (sr < 0) {
 		dev_err(&client->dev, "%s: writing SR failed\n", __func__);
@@ -369,7 +361,7 @@ static int isl1208_i2c_set_time(struct i2c_client *client,
 	}
 
 	/* clear WRTC again */
-	sr = i2c_smbus_write_byte_data (client, ISL1208_REG_SR,
+	sr = i2c_smbus_write_byte_data(client, ISL1208_REG_SR,
 				       sr & ~ISL1208_REG_SR_WRTC);
 	if (sr < 0) {
 		dev_err(&client->dev, "%s: writing SR failed\n", __func__);
@@ -380,70 +372,69 @@ static int isl1208_i2c_set_time(struct i2c_client *client,
 }
 
 
-static int isl1208_rtc_set_time(struct device *dev, struct rtc_time *tm)
+static int
+isl1208_rtc_set_time(struct device *dev, struct rtc_time *tm)
 {
 	return isl1208_i2c_set_time(to_i2c_client(dev), tm);
 }
 
-static int isl1208_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
+static int
+isl1208_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 {
 	return isl1208_i2c_read_alarm(to_i2c_client(dev), alarm);
 }
 
 static const struct rtc_class_ops isl1208_rtc_ops = {
-	.proc		= isl1208_rtc_proc,
-	.read_time	= isl1208_rtc_read_time,
-	.set_time	= isl1208_rtc_set_time,
-	.read_alarm	= isl1208_rtc_read_alarm,
-	//.set_alarm	= isl1208_rtc_set_alarm,
+	.proc = isl1208_rtc_proc,
+	.read_time = isl1208_rtc_read_time,
+	.set_time = isl1208_rtc_set_time,
+	.read_alarm = isl1208_rtc_read_alarm,
+	/*.set_alarm    = isl1208_rtc_set_alarm, */
 };
 
 /* sysfs interface */
 
-static ssize_t isl1208_sysfs_show_atrim(struct device *dev,
-					struct device_attribute *attr,
-					char *buf)
+static ssize_t
+isl1208_sysfs_show_atrim(struct device *dev,
+			 struct device_attribute *attr, char *buf)
 {
-	int atr;
-
-	atr = isl1208_i2c_get_atr(to_i2c_client(dev));
+	int atr = isl1208_i2c_get_atr(to_i2c_client(dev));
 	if (atr < 0)
 		return atr;
 
-	return sprintf(buf, "%d.%.2d pF\n", atr>>2, (atr&0x3)*25);
+	return sprintf(buf, "%d.%.2d pF\n", atr >> 2, (atr & 0x3) * 25);
 }
+
 static DEVICE_ATTR(atrim, S_IRUGO, isl1208_sysfs_show_atrim, NULL);
 
-static ssize_t isl1208_sysfs_show_dtrim(struct device *dev,
-					struct device_attribute *attr,
-					char *buf)
+static ssize_t
+isl1208_sysfs_show_dtrim(struct device *dev,
+			 struct device_attribute *attr, char *buf)
 {
-	int dtr;
-
-	dtr = isl1208_i2c_get_dtr(to_i2c_client(dev));
+	int dtr = isl1208_i2c_get_dtr(to_i2c_client(dev));
 	if (dtr < 0)
 		return dtr;
 
 	return sprintf(buf, "%d ppm\n", dtr);
 }
+
 static DEVICE_ATTR(dtrim, S_IRUGO, isl1208_sysfs_show_dtrim, NULL);
 
-static ssize_t isl1208_sysfs_show_usr(struct device *dev,
-				       struct device_attribute *attr,
-				       char *buf)
+static ssize_t
+isl1208_sysfs_show_usr(struct device *dev,
+		       struct device_attribute *attr, char *buf)
 {
-	int usr;
-
-	usr = isl1208_i2c_get_usr(to_i2c_client(dev));
+	int usr = isl1208_i2c_get_usr(to_i2c_client(dev));
 	if (usr < 0)
 		return usr;
 
 	return sprintf(buf, "0x%.4x\n", usr);
 }
 
-static ssize_t isl1208_sysfs_store_usr(struct device *dev,
-				       struct device_attribute *attr,
-				       const char *buf, size_t count)
+static ssize_t
+isl1208_sysfs_store_usr(struct device *dev,
+			struct device_attribute *attr,
+			const char *buf, size_t count)
 {
 	int usr = -1;
 
@@ -460,124 +451,116 @@ static ssize_t isl1208_sysfs_store_usr(struct device *dev,
 
 	return isl1208_i2c_set_usr(to_i2c_client(dev), usr) ? -EIO : count;
 }
+
 static DEVICE_ATTR(usr, S_IRUGO | S_IWUSR, isl1208_sysfs_show_usr,
 		   isl1208_sysfs_store_usr);
 
 static int
-isl1208_probe(struct i2c_adapter *adapter, int addr, int kind)
+isl1208_sysfs_register(struct device *dev)
 {
-	int rc = 0;
-	struct i2c_client *new_client = NULL;
-	struct rtc_device *rtc = NULL;
+	int err;
+
+	err = device_create_file(dev, &dev_attr_atrim);
+	if (err)
+		return err;
 
-	if (!i2c_check_functionality(adapter, I2C_FUNC_I2C)) {
-		rc = -ENODEV;
-		goto failout;
+	err = device_create_file(dev, &dev_attr_dtrim);
+	if (err) {
+		device_remove_file(dev, &dev_attr_atrim);
+		return err;
 	}
 
-	new_client = kzalloc(sizeof(struct i2c_client), GFP_KERNEL);
-	if (new_client == NULL) {
-		rc = -ENOMEM;
-		goto failout;
+	err = device_create_file(dev, &dev_attr_usr);
+	if (err) {
+		device_remove_file(dev, &dev_attr_atrim);
+		device_remove_file(dev, &dev_attr_dtrim);
 	}
 
-	new_client->addr = addr;
-	new_client->adapter = adapter;
-	new_client->driver = &isl1208_driver;
-	new_client->flags = 0;
-	strcpy(new_client->name, DRV_NAME);
+	return 0;
+}
 
-	if (kind < 0) {
-		rc = isl1208_i2c_validate_client(new_client);
-		if (rc < 0)
-			goto failout;
-	}
+static int
+isl1208_sysfs_unregister(struct device *dev)
+{
+	device_remove_file(dev, &dev_attr_atrim);
+	device_remove_file(dev, &dev_attr_atrim);
+	device_remove_file(dev, &dev_attr_usr);
+
+	return 0;
+}
+
+static int
+isl1208_probe(struct i2c_client *client)
+{
+	int rc = 0;
+	struct rtc_device *rtc;
 
-	rc = i2c_attach_client(new_client);
-	if (rc < 0)
-		goto failout;
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
+		return -ENODEV;
 
-	dev_info(&new_client->dev,
+	if (isl1208_i2c_validate_client(client) < 0)
+		return -ENODEV;
+
+	dev_info(&client->dev,
 		 "chip found, driver version " DRV_VERSION "\n");
 
 	rtc = rtc_device_register(isl1208_driver.driver.name,
-				  &new_client->dev,
-				  &isl1208_rtc_ops, THIS_MODULE);
-
-	if (IS_ERR(rtc)) {
-		rc = PTR_ERR(rtc);
-		goto failout_detach;
-	}
+				  &client->dev, &isl1208_rtc_ops,
+				  THIS_MODULE);
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
 
-	i2c_set_clientdata(new_client, rtc);
+	i2c_set_clientdata(client, rtc);
 
-	rc = isl1208_i2c_get_sr(new_client);
+	rc = isl1208_i2c_get_sr(client);
 	if (rc < 0) {
-		dev_err(&new_client->dev, "reading status failed\n");
-		goto failout_unregister;
+		dev_err(&client->dev, "reading status failed\n");
+		goto exit_unregister;
 	}
 
 	if (rc & ISL1208_REG_SR_RTCF)
-		dev_warn(&new_client->dev, "rtc power failure detected, "
+		dev_warn(&client->dev, "rtc power failure detected, "
 			 "please set clock.\n");
 
-	rc = device_create_file(&new_client->dev, &dev_attr_atrim);
-	if (rc < 0)
-		goto failout_unregister;
-	rc = device_create_file(&new_client->dev, &dev_attr_dtrim);
-	if (rc < 0)
-		goto failout_atrim;
-	rc = device_create_file(&new_client->dev, &dev_attr_usr);
-	if (rc < 0)
-		goto failout_dtrim;
+	rc = isl1208_sysfs_register(&client->dev);
+	if (rc)
+		goto exit_unregister;
 
 	return 0;
 
- failout_dtrim:
-	device_remove_file(&new_client->dev, &dev_attr_dtrim);
- failout_atrim:
-	device_remove_file(&new_client->dev, &dev_attr_atrim);
- failout_unregister:
+exit_unregister:
 	rtc_device_unregister(rtc);
- failout_detach:
-	i2c_detach_client(new_client);
- failout:
-	kfree(new_client);
-	return rc;
-}
 
-static int
-isl1208_attach_adapter (struct i2c_adapter *adapter)
-{
-	return i2c_probe(adapter, &addr_data, isl1208_probe);
+	return rc;
 }
 
 static int
-isl1208_detach_client(struct i2c_client *client)
+isl1208_remove(struct i2c_client *client)
 {
-	int rc;
-	struct rtc_device *const rtc = i2c_get_clientdata(client);
-
-	if (rtc)
-		rtc_device_unregister(rtc); /* do we need to kfree? */
-
-	rc = i2c_detach_client(client);
-	if (rc)
-		return rc;
+	struct rtc_device *rtc = i2c_get_clientdata(client);
 
-	kfree(client);
+	isl1208_sysfs_unregister(&client->dev);
+	rtc_device_unregister(rtc);
 
 	return 0;
 }
 
-/* module management */
+static struct i2c_driver isl1208_driver = {
+	.driver = {
+		   .name = "rtc-isl1208",
+		   },
+	.probe = isl1208_probe,
+	.remove = isl1208_remove,
+};
 
-static int __init isl1208_init(void)
+static int __init
+isl1208_init(void)
 {
 	return i2c_add_driver(&isl1208_driver);
 }
 
-static void __exit isl1208_exit(void)
+static void __exit
+isl1208_exit(void)
 {
 	i2c_del_driver(&isl1208_driver);
 }
diff --git a/trunk/drivers/rtc/rtc-max6900.c b/trunk/drivers/rtc/rtc-max6900.c
index 7683412970c4..ded3c0abad83 100644
--- a/trunk/drivers/rtc/rtc-max6900.c
+++ b/trunk/drivers/rtc/rtc-max6900.c
@@ -98,7 +98,7 @@ static int max6900_i2c_read_regs(struct i2c_client *client, u8 *buf)
 	rc = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
 	if (rc != ARRAY_SIZE(msgs)) {
 		dev_err(&client->dev, "%s: register read failed\n",
-			__FUNCTION__);
+			__func__);
 		return -EIO;
 	}
 	return 0;
@@ -150,7 +150,7 @@ static int max6900_i2c_write_regs(struct i2c_client *client, u8 const *buf)
 
 write_failed:
 	dev_err(&client->dev, "%s: register write failed\n",
-		__FUNCTION__);
+		__func__);
 	return -EIO;
 }
 
@@ -214,7 +214,7 @@ static int max6900_i2c_clear_write_protect(struct i2c_client *client)
 	rc = i2c_smbus_write_byte_data (client, MAX6900_REG_CONTROL_WRITE, 0);
 	if (rc < 0) {
 		dev_err(&client->dev, "%s: control register write failed\n",
-			__FUNCTION__);
+			__func__);
 		return -EIO;
 	}
 	return 0;
diff --git a/trunk/drivers/rtc/rtc-max6902.c b/trunk/drivers/rtc/rtc-max6902.c
index 1f956dc5d56e..12f0310ae89c 100644
--- a/trunk/drivers/rtc/rtc-max6902.c
+++ b/trunk/drivers/rtc/rtc-max6902.c
@@ -140,7 +140,7 @@ static int max6902_get_datetime(struct device *dev, struct rtc_time *dt)
 	dt->tm_year -= 1900;
 
 #ifdef MAX6902_DEBUG
-	printk("\n%s : Read RTC values\n",__FUNCTION__);
+	printk("\n%s : Read RTC values\n",__func__);
 	printk("tm_hour: %i\n",dt->tm_hour);
 	printk("tm_min : %i\n",dt->tm_min);
 	printk("tm_sec : %i\n",dt->tm_sec);
@@ -158,7 +158,7 @@ static int max6902_set_datetime(struct device *dev, struct rtc_time *dt)
 	dt->tm_year = dt->tm_year+1900;
 
 #ifdef MAX6902_DEBUG
-	printk("\n%s : Setting RTC values\n",__FUNCTION__);
+	printk("\n%s : Setting RTC values\n",__func__);
 	printk("tm_sec : %i\n",dt->tm_sec);
 	printk("tm_min : %i\n",dt->tm_min);
 	printk("tm_hour: %i\n",dt->tm_hour);
diff --git a/trunk/drivers/rtc/rtc-pcf8563.c b/trunk/drivers/rtc/rtc-pcf8563.c
index b3317fcc16c3..a41681d26eba 100644
--- a/trunk/drivers/rtc/rtc-pcf8563.c
+++ b/trunk/drivers/rtc/rtc-pcf8563.c
@@ -18,17 +18,7 @@
 #include <linux/bcd.h>
 #include <linux/rtc.h>
 
-#define DRV_VERSION "0.4.2"
-
-/* Addresses to scan: none
- * This chip cannot be reliably autodetected. An empty eeprom
- * located at 0x51 will pass the validation routine due to
- * the way the registers are implemented.
- */
-static const unsigned short normal_i2c[] = { I2C_CLIENT_END };
-
-/* Module parameters */
-I2C_CLIENT_INSMOD;
+#define DRV_VERSION "0.4.3"
 
 #define PCF8563_REG_ST1		0x00 /* status */
 #define PCF8563_REG_ST2		0x01
@@ -53,8 +43,10 @@ I2C_CLIENT_INSMOD;
 #define PCF8563_SC_LV		0x80 /* low voltage */
 #define PCF8563_MO_C		0x80 /* century */
 
+static struct i2c_driver pcf8563_driver;
+
 struct pcf8563 {
-	struct i2c_client client;
+	struct rtc_device *rtc;
 	/*
 	 * The meaning of MO_C bit varies by the chip type.
 	 * From PCF8563 datasheet: this bit is toggled when the years
@@ -72,16 +64,13 @@ struct pcf8563 {
 	int c_polarity;	/* 0: MO_C=1 means 19xx, otherwise MO_C=1 means 20xx */
 };
 
-static int pcf8563_probe(struct i2c_adapter *adapter, int address, int kind);
-static int pcf8563_detach(struct i2c_client *client);
-
 /*
  * In the routines that deal directly with the pcf8563 hardware, we use
  * rtc_time -- month 0-11, hour 0-23, yr = calendar year-epoch.
  */
 static int pcf8563_get_datetime(struct i2c_client *client, struct rtc_time *tm)
 {
-	struct pcf8563 *pcf8563 = container_of(client, struct pcf8563, client);
+	struct pcf8563 *pcf8563 = i2c_get_clientdata(client);
 	unsigned char buf[13] = { PCF8563_REG_ST1 };
 
 	struct i2c_msg msgs[] = {
@@ -91,7 +80,7 @@ static int pcf8563_get_datetime(struct i2c_client *client, struct rtc_time *tm)
 
 	/* read registers */
 	if ((i2c_transfer(client->adapter, msgs, 2)) != 2) {
-		dev_err(&client->dev, "%s: read error\n", __FUNCTION__);
+		dev_err(&client->dev, "%s: read error\n", __func__);
 		return -EIO;
 	}
 
@@ -102,7 +91,7 @@ static int pcf8563_get_datetime(struct i2c_client *client, struct rtc_time *tm)
 	dev_dbg(&client->dev,
 		"%s: raw data is st1=%02x, st2=%02x, sec=%02x, min=%02x, hr=%02x, "
 		"mday=%02x, wday=%02x, mon=%02x, year=%02x\n",
-		__FUNCTION__,
+		__func__,
 		buf[0], buf[1], buf[2], buf[3],
 		buf[4], buf[5], buf[6], buf[7],
 		buf[8]);
@@ -123,7 +112,7 @@ static int pcf8563_get_datetime(struct i2c_client *client, struct rtc_time *tm)
 
 	dev_dbg(&client->dev, "%s: tm is secs=%d, mins=%d, hours=%d, "
 		"mday=%d, mon=%d, year=%d, wday=%d\n",
-		__FUNCTION__,
+		__func__,
 		tm->tm_sec, tm->tm_min, tm->tm_hour,
 		tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday);
 
@@ -138,13 +127,13 @@ static int pcf8563_get_datetime(struct i2c_client *client, struct rtc_time *tm)
 
 static int pcf8563_set_datetime(struct i2c_client *client, struct rtc_time *tm)
 {
-	struct pcf8563 *pcf8563 = container_of(client, struct pcf8563, client);
+	struct pcf8563 *pcf8563 = i2c_get_clientdata(client);
 	int i, err;
 	unsigned char buf[9];
 
 	dev_dbg(&client->dev, "%s: secs=%d, mins=%d, hours=%d, "
 		"mday=%d, mon=%d, year=%d, wday=%d\n",
-		__FUNCTION__,
+		__func__,
 		tm->tm_sec, tm->tm_min, tm->tm_hour,
 		tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday);
 
@@ -174,7 +163,7 @@ static int pcf8563_set_datetime(struct i2c_client *client, struct rtc_time *tm)
 		if (err != sizeof(data)) {
 			dev_err(&client->dev,
 				"%s: err=%d addr=%02x, data=%02x\n",
-				__FUNCTION__, err, data[0], data[1]);
+				__func__, err, data[0], data[1]);
 			return -EIO;
 		}
 	};
@@ -219,7 +208,7 @@ static int pcf8563_validate_client(struct i2c_client *client)
 		if (xfer != ARRAY_SIZE(msgs)) {
 			dev_err(&client->dev,
 				"%s: could not read register 0x%02X\n",
-				__FUNCTION__, pattern[i].reg);
+				__func__, pattern[i].reg);
 
 			return -EIO;
 		}
@@ -231,7 +220,7 @@ static int pcf8563_validate_client(struct i2c_client *client)
 			dev_dbg(&client->dev,
 				"%s: pattern=%d, reg=%x, mask=0x%02x, min=%d, "
 				"max=%d, value=%d, raw=0x%02X\n",
-				__FUNCTION__, i, pattern[i].reg, pattern[i].mask,
+				__func__, i, pattern[i].reg, pattern[i].mask,
 				pattern[i].min, pattern[i].max,
 				value, buf);
 
@@ -257,100 +246,67 @@ static const struct rtc_class_ops pcf8563_rtc_ops = {
 	.set_time	= pcf8563_rtc_set_time,
 };
 
-static int pcf8563_attach(struct i2c_adapter *adapter)
-{
-	return i2c_probe(adapter, &addr_data, pcf8563_probe);
-}
-
-static struct i2c_driver pcf8563_driver = {
-	.driver		= {
-		.name	= "pcf8563",
-	},
-	.id		= I2C_DRIVERID_PCF8563,
-	.attach_adapter = &pcf8563_attach,
-	.detach_client	= &pcf8563_detach,
-};
-
-static int pcf8563_probe(struct i2c_adapter *adapter, int address, int kind)
+static int pcf8563_probe(struct i2c_client *client)
 {
 	struct pcf8563 *pcf8563;
-	struct i2c_client *client;
-	struct rtc_device *rtc;
 
 	int err = 0;
 
-	dev_dbg(&adapter->dev, "%s\n", __FUNCTION__);
+	dev_dbg(&client->dev, "%s\n", __func__);
 
-	if (!i2c_check_functionality(adapter, I2C_FUNC_I2C)) {
-		err = -ENODEV;
-		goto exit;
-	}
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
+		return -ENODEV;
 
-	if (!(pcf8563 = kzalloc(sizeof(struct pcf8563), GFP_KERNEL))) {
-		err = -ENOMEM;
-		goto exit;
-	}
-
-	client = &pcf8563->client;
-	client->addr = address;
-	client->driver = &pcf8563_driver;
-	client->adapter	= adapter;
-
-	strlcpy(client->name, pcf8563_driver.driver.name, I2C_NAME_SIZE);
+	pcf8563 = kzalloc(sizeof(struct pcf8563), GFP_KERNEL);
+	if (!pcf8563)
+		return -ENOMEM;
 
 	/* Verify the chip is really an PCF8563 */
-	if (kind < 0) {
-		if (pcf8563_validate_client(client) < 0) {
-			err = -ENODEV;
-			goto exit_kfree;
-		}
-	}
-
-	/* Inform the i2c layer */
-	if ((err = i2c_attach_client(client)))
+	if (pcf8563_validate_client(client) < 0) {
+		err = -ENODEV;
 		goto exit_kfree;
+	}
 
 	dev_info(&client->dev, "chip found, driver version " DRV_VERSION "\n");
 
-	rtc = rtc_device_register(pcf8563_driver.driver.name, &client->dev,
-				&pcf8563_rtc_ops, THIS_MODULE);
+	pcf8563->rtc = rtc_device_register(pcf8563_driver.driver.name,
+				&client->dev, &pcf8563_rtc_ops, THIS_MODULE);
 
-	if (IS_ERR(rtc)) {
-		err = PTR_ERR(rtc);
-		goto exit_detach;
+	if (IS_ERR(pcf8563->rtc)) {
+		err = PTR_ERR(pcf8563->rtc);
+		goto exit_kfree;
 	}
 
-	i2c_set_clientdata(client, rtc);
+	i2c_set_clientdata(client, pcf8563);
 
 	return 0;
 
-exit_detach:
-	i2c_detach_client(client);
-
 exit_kfree:
 	kfree(pcf8563);
 
-exit:
 	return err;
 }
 
-static int pcf8563_detach(struct i2c_client *client)
+static int pcf8563_remove(struct i2c_client *client)
 {
-	struct pcf8563 *pcf8563 = container_of(client, struct pcf8563, client);
-	int err;
-	struct rtc_device *rtc = i2c_get_clientdata(client);
+	struct pcf8563 *pcf8563 = i2c_get_clientdata(client);
 
-	if (rtc)
-		rtc_device_unregister(rtc);
-
-	if ((err = i2c_detach_client(client)))
-		return err;
+	if (pcf8563->rtc)
+		rtc_device_unregister(pcf8563->rtc);
 
 	kfree(pcf8563);
 
 	return 0;
 }
 
+static struct i2c_driver pcf8563_driver = {
+	.driver		= {
+		.name	= "rtc-pcf8563",
+	},
+	.probe		= pcf8563_probe,
+	.remove		= pcf8563_remove,
+};
+
 static int __init pcf8563_init(void)
 {
 	return i2c_add_driver(&pcf8563_driver);
diff --git a/trunk/drivers/rtc/rtc-pcf8583.c b/trunk/drivers/rtc/rtc-pcf8583.c
index 8b3997007506..3d09d8f0b1f0 100644
--- a/trunk/drivers/rtc/rtc-pcf8583.c
+++ b/trunk/drivers/rtc/rtc-pcf8583.c
@@ -15,7 +15,7 @@
 #include <linux/i2c.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/mc146818rtc.h>
+#include <linux/rtc.h>
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/bcd.h>
diff --git a/trunk/drivers/rtc/rtc-proc.c b/trunk/drivers/rtc/rtc-proc.c
index 8d300e6d0d9e..0c6257a034ff 100644
--- a/trunk/drivers/rtc/rtc-proc.c
+++ b/trunk/drivers/rtc/rtc-proc.c
@@ -108,12 +108,10 @@ void rtc_proc_add_device(struct rtc_device *rtc)
 	if (rtc->id == 0) {
 		struct proc_dir_entry *ent;
 
-		ent = create_proc_entry("driver/rtc", 0, NULL);
-		if (ent) {
-			ent->proc_fops = &rtc_proc_fops;
+		ent = proc_create_data("driver/rtc", 0, NULL,
+				       &rtc_proc_fops, rtc);
+		if (ent)
 			ent->owner = rtc->owner;
-			ent->data = rtc;
-		}
 	}
 }
 
diff --git a/trunk/drivers/rtc/rtc-rs5c313.c b/trunk/drivers/rtc/rtc-rs5c313.c
index 664e89a817ed..1c14d4497c4d 100644
--- a/trunk/drivers/rtc/rtc-rs5c313.c
+++ b/trunk/drivers/rtc/rtc-rs5c313.c
@@ -228,7 +228,7 @@ static int rs5c313_rtc_read_time(struct device *dev, struct rtc_time *tm)
 		ndelay(700);	/* CE:L */
 
 		if (cnt++ > 100) {
-			dev_err(dev, "%s: timeout error\n", __FUNCTION__);
+			dev_err(dev, "%s: timeout error\n", __func__);
 			return -EIO;
 		}
 	}
@@ -289,7 +289,7 @@ static int rs5c313_rtc_set_time(struct device *dev, struct rtc_time *tm)
 		ndelay(700);	/* CE:L */
 
 		if (cnt++ > 100) {
-			dev_err(dev, "%s: timeout error\n", __FUNCTION__);
+			dev_err(dev, "%s: timeout error\n", __func__);
 			return -EIO;
 		}
 	}
diff --git a/trunk/drivers/rtc/rtc-rs5c372.c b/trunk/drivers/rtc/rtc-rs5c372.c
index 6b67b5097927..7e63074708eb 100644
--- a/trunk/drivers/rtc/rtc-rs5c372.c
+++ b/trunk/drivers/rtc/rtc-rs5c372.c
@@ -99,7 +99,7 @@ static int rs5c_get_regs(struct rs5c372 *rs5c)
 	 * least 80219 chips; this works around that bug.
 	 */
 	if ((i2c_transfer(client->adapter, msgs, 1)) != 1) {
-		pr_debug("%s: can't read registers\n", rs5c->rtc->name);
+		dev_warn(&client->dev, "can't read registers\n");
 		return -EIO;
 	}
 
@@ -166,7 +166,7 @@ static int rs5c372_get_datetime(struct i2c_client *client, struct rtc_time *tm)
 
 	dev_dbg(&client->dev, "%s: tm is secs=%d, mins=%d, hours=%d, "
 		"mday=%d, mon=%d, year=%d, wday=%d\n",
-		__FUNCTION__,
+		__func__,
 		tm->tm_sec, tm->tm_min, tm->tm_hour,
 		tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday);
 
@@ -181,7 +181,7 @@ static int rs5c372_set_datetime(struct i2c_client *client, struct rtc_time *tm)
 
 	dev_dbg(&client->dev, "%s: tm is secs=%d, mins=%d, hours=%d "
 		"mday=%d, mon=%d, year=%d, wday=%d\n",
-		__FUNCTION__,
+		__func__,
 		tm->tm_sec, tm->tm_min, tm->tm_hour,
 		tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday);
 
@@ -195,7 +195,7 @@ static int rs5c372_set_datetime(struct i2c_client *client, struct rtc_time *tm)
 	buf[7] = BIN2BCD(tm->tm_year - 100);
 
 	if ((i2c_master_send(client, buf, 8)) != 8) {
-		dev_err(&client->dev, "%s: write error\n", __FUNCTION__);
+		dev_err(&client->dev, "%s: write error\n", __func__);
 		return -EIO;
 	}
 
@@ -220,7 +220,7 @@ static int rs5c372_get_trim(struct i2c_client *client, int *osc, int *trim)
 		*osc = (tmp & RS5C372_TRIM_XSL) ? 32000 : 32768;
 
 	if (trim) {
-		dev_dbg(&client->dev, "%s: raw trim=%x\n", __FUNCTION__, tmp);
+		dev_dbg(&client->dev, "%s: raw trim=%x\n", __func__, tmp);
 		tmp &= RS5C372_TRIM_MASK;
 		if (tmp & 0x3e) {
 			int t = tmp & 0x3f;
@@ -500,7 +500,7 @@ static int rs5c372_probe(struct i2c_client *client)
 	struct rs5c372 *rs5c372;
 	struct rtc_time tm;
 
-	dev_dbg(&client->dev, "%s\n", __FUNCTION__);
+	dev_dbg(&client->dev, "%s\n", __func__);
 
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
 		err = -ENODEV;
@@ -512,12 +512,12 @@ static int rs5c372_probe(struct i2c_client *client)
 		goto exit;
 	}
 
-	/* we read registers 0x0f then 0x00-0x0f; skip the first one */
-	rs5c372->regs=&rs5c372->buf[1];
-
 	rs5c372->client = client;
 	i2c_set_clientdata(client, rs5c372);
 
+	/* we read registers 0x0f then 0x00-0x0f; skip the first one */
+	rs5c372->regs = &rs5c372->buf[1];
+
 	err = rs5c_get_regs(rs5c372);
 	if (err < 0)
 		goto exit_kfree;
diff --git a/trunk/drivers/rtc/rtc-s3c.c b/trunk/drivers/rtc/rtc-s3c.c
index 9f4d5129a496..f26e0cad8f16 100644
--- a/trunk/drivers/rtc/rtc-s3c.c
+++ b/trunk/drivers/rtc/rtc-s3c.c
@@ -68,7 +68,7 @@ static void s3c_rtc_setaie(int to)
 {
 	unsigned int tmp;
 
-	pr_debug("%s: aie=%d\n", __FUNCTION__, to);
+	pr_debug("%s: aie=%d\n", __func__, to);
 
 	tmp = readb(s3c_rtc_base + S3C2410_RTCALM) & ~S3C2410_RTCALM_ALMEN;
 
@@ -82,7 +82,7 @@ static void s3c_rtc_setpie(int to)
 {
 	unsigned int tmp;
 
-	pr_debug("%s: pie=%d\n", __FUNCTION__, to);
+	pr_debug("%s: pie=%d\n", __func__, to);
 
 	spin_lock_irq(&s3c_rtc_pie_lock);
 	tmp = readb(s3c_rtc_base + S3C2410_TICNT) & ~S3C2410_TICNT_ENABLE;
@@ -457,7 +457,7 @@ static int s3c_rtc_probe(struct platform_device *pdev)
 	struct resource *res;
 	int ret;
 
-	pr_debug("%s: probe=%p\n", __FUNCTION__, pdev);
+	pr_debug("%s: probe=%p\n", __func__, pdev);
 
 	/* find the IRQs */
 
diff --git a/trunk/drivers/rtc/rtc-sh.c b/trunk/drivers/rtc/rtc-sh.c
index c594b34c6767..110699bb4787 100644
--- a/trunk/drivers/rtc/rtc-sh.c
+++ b/trunk/drivers/rtc/rtc-sh.c
@@ -361,7 +361,7 @@ static int sh_rtc_read_time(struct device *dev, struct rtc_time *tm)
 
 	dev_dbg(dev, "%s: tm is secs=%d, mins=%d, hours=%d, "
 		"mday=%d, mon=%d, year=%d, wday=%d\n",
-		__FUNCTION__,
+		__func__,
 		tm->tm_sec, tm->tm_min, tm->tm_hour,
 		tm->tm_mday, tm->tm_mon + 1, tm->tm_year, tm->tm_wday);
 
diff --git a/trunk/drivers/rtc/rtc-sysfs.c b/trunk/drivers/rtc/rtc-sysfs.c
index 4d27ccc4fc06..2531ce4c9db0 100644
--- a/trunk/drivers/rtc/rtc-sysfs.c
+++ b/trunk/drivers/rtc/rtc-sysfs.c
@@ -145,6 +145,8 @@ rtc_sysfs_set_wakealarm(struct device *dev, struct device_attribute *attr,
 	unsigned long now, alarm;
 	struct rtc_wkalrm alm;
 	struct rtc_device *rtc = to_rtc_device(dev);
+	char *buf_ptr;
+	int adjust = 0;
 
 	/* Only request alarms that trigger in the future.  Disable them
 	 * by writing another time, e.g. 0 meaning Jan 1 1970 UTC.
@@ -154,7 +156,15 @@ rtc_sysfs_set_wakealarm(struct device *dev, struct device_attribute *attr,
 		return retval;
 	rtc_tm_to_time(&alm.time, &now);
 
-	alarm = simple_strtoul(buf, NULL, 0);
+	buf_ptr = (char *)buf;
+	if (*buf_ptr == '+') {
+		buf_ptr++;
+		adjust = 1;
+	}
+	alarm = simple_strtoul(buf_ptr, NULL, 0);
+	if (adjust) {
+		alarm += now;
+	}
 	if (alarm > now) {
 		/* Avoid accidentally clobbering active alarms; we can't
 		 * entirely prevent that here, without even the minimal
diff --git a/trunk/drivers/rtc/rtc-test.c b/trunk/drivers/rtc/rtc-test.c
index 254c9fce27da..bc930022004a 100644
--- a/trunk/drivers/rtc/rtc-test.c
+++ b/trunk/drivers/rtc/rtc-test.c
@@ -147,7 +147,7 @@ static int __devexit test_remove(struct platform_device *plat_dev)
 	return 0;
 }
 
-static struct platform_driver test_drv = {
+static struct platform_driver test_driver = {
 	.probe	= test_probe,
 	.remove = __devexit_p(test_remove),
 	.driver = {
@@ -160,7 +160,7 @@ static int __init test_init(void)
 {
 	int err;
 
-	if ((err = platform_driver_register(&test_drv)))
+	if ((err = platform_driver_register(&test_driver)))
 		return err;
 
 	if ((test0 = platform_device_alloc("rtc-test", 0)) == NULL) {
@@ -191,7 +191,7 @@ static int __init test_init(void)
 	platform_device_put(test0);
 
 exit_driver_unregister:
-	platform_driver_unregister(&test_drv);
+	platform_driver_unregister(&test_driver);
 	return err;
 }
 
@@ -199,7 +199,7 @@ static void __exit test_exit(void)
 {
 	platform_device_unregister(test0);
 	platform_device_unregister(test1);
-	platform_driver_unregister(&test_drv);
+	platform_driver_unregister(&test_driver);
 }
 
 MODULE_AUTHOR("Alessandro Zummo <a.zummo@towertech.it>");
diff --git a/trunk/drivers/rtc/rtc-v3020.c b/trunk/drivers/rtc/rtc-v3020.c
index 24203a06051a..10025d840268 100644
--- a/trunk/drivers/rtc/rtc-v3020.c
+++ b/trunk/drivers/rtc/rtc-v3020.c
@@ -107,7 +107,7 @@ static int v3020_read_time(struct device *dev, struct rtc_time *dt)
 	dt->tm_year = BCD2BIN(tmp)+100;
 
 #ifdef DEBUG
-	printk("\n%s : Read RTC values\n",__FUNCTION__);
+	printk("\n%s : Read RTC values\n",__func__);
 	printk("tm_hour: %i\n",dt->tm_hour);
 	printk("tm_min : %i\n",dt->tm_min);
 	printk("tm_sec : %i\n",dt->tm_sec);
@@ -126,7 +126,7 @@ static int v3020_set_time(struct device *dev, struct rtc_time *dt)
 	struct v3020 *chip = dev_get_drvdata(dev);
 
 #ifdef DEBUG
-	printk("\n%s : Setting RTC values\n",__FUNCTION__);
+	printk("\n%s : Setting RTC values\n",__func__);
 	printk("tm_sec : %i\n",dt->tm_sec);
 	printk("tm_min : %i\n",dt->tm_min);
 	printk("tm_hour: %i\n",dt->tm_hour);
diff --git a/trunk/drivers/rtc/rtc-x1205.c b/trunk/drivers/rtc/rtc-x1205.c
index b90fb1866ce9..095282f63523 100644
--- a/trunk/drivers/rtc/rtc-x1205.c
+++ b/trunk/drivers/rtc/rtc-x1205.c
@@ -22,20 +22,7 @@
 #include <linux/rtc.h>
 #include <linux/delay.h>
 
-#define DRV_VERSION "1.0.7"
-
-/* Addresses to scan: none. This chip is located at
- * 0x6f and uses a two bytes register addressing.
- * Two bytes need to be written to read a single register,
- * while most other chips just require one and take the second
- * one as the data to be written. To prevent corrupting
- * unknown chips, the user must explicitly set the probe parameter.
- */
-
-static const unsigned short normal_i2c[] = { I2C_CLIENT_END };
-
-/* Insmod parameters */
-I2C_CLIENT_INSMOD;
+#define DRV_VERSION "1.0.8"
 
 /* offsets into CCR area */
 
@@ -91,19 +78,7 @@ I2C_CLIENT_INSMOD;
 
 #define X1205_HR_MIL		0x80	/* Set in ccr.hour for 24 hr mode */
 
-/* Prototypes */
-static int x1205_attach(struct i2c_adapter *adapter);
-static int x1205_detach(struct i2c_client *client);
-static int x1205_probe(struct i2c_adapter *adapter, int address, int kind);
-
-static struct i2c_driver x1205_driver = {
-	.driver		= {
-		.name	= "x1205",
-	},
-	.id		= I2C_DRIVERID_X1205,
-	.attach_adapter = &x1205_attach,
-	.detach_client	= &x1205_detach,
-};
+static struct i2c_driver x1205_driver;
 
 /*
  * In the routines that deal directly with the x1205 hardware, we use
@@ -124,14 +99,14 @@ static int x1205_get_datetime(struct i2c_client *client, struct rtc_time *tm,
 
 	/* read date registers */
 	if ((i2c_transfer(client->adapter, &msgs[0], 2)) != 2) {
-		dev_err(&client->dev, "%s: read error\n", __FUNCTION__);
+		dev_err(&client->dev, "%s: read error\n", __func__);
 		return -EIO;
 	}
 
 	dev_dbg(&client->dev,
 		"%s: raw read data - sec=%02x, min=%02x, hr=%02x, "
 		"mday=%02x, mon=%02x, year=%02x, wday=%02x, y2k=%02x\n",
-		__FUNCTION__,
+		__func__,
 		buf[0], buf[1], buf[2], buf[3],
 		buf[4], buf[5], buf[6], buf[7]);
 
@@ -146,7 +121,7 @@ static int x1205_get_datetime(struct i2c_client *client, struct rtc_time *tm,
 
 	dev_dbg(&client->dev, "%s: tm is secs=%d, mins=%d, hours=%d, "
 		"mday=%d, mon=%d, year=%d, wday=%d\n",
-		__FUNCTION__,
+		__func__,
 		tm->tm_sec, tm->tm_min, tm->tm_hour,
 		tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday);
 
@@ -164,7 +139,7 @@ static int x1205_get_status(struct i2c_client *client, unsigned char *sr)
 
 	/* read status register */
 	if ((i2c_transfer(client->adapter, &msgs[0], 2)) != 2) {
-		dev_err(&client->dev, "%s: read error\n", __FUNCTION__);
+		dev_err(&client->dev, "%s: read error\n", __func__);
 		return -EIO;
 	}
 
@@ -187,7 +162,7 @@ static int x1205_set_datetime(struct i2c_client *client, struct rtc_time *tm,
 
 	dev_dbg(&client->dev,
 		"%s: secs=%d, mins=%d, hours=%d\n",
-		__FUNCTION__,
+		__func__,
 		tm->tm_sec, tm->tm_min, tm->tm_hour);
 
 	buf[CCR_SEC] = BIN2BCD(tm->tm_sec);
@@ -200,7 +175,7 @@ static int x1205_set_datetime(struct i2c_client *client, struct rtc_time *tm,
 	if (datetoo) {
 		dev_dbg(&client->dev,
 			"%s: mday=%d, mon=%d, year=%d, wday=%d\n",
-			__FUNCTION__,
+			__func__,
 			tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday);
 
 		buf[CCR_MDAY] = BIN2BCD(tm->tm_mday);
@@ -216,12 +191,12 @@ static int x1205_set_datetime(struct i2c_client *client, struct rtc_time *tm,
 
 	/* this sequence is required to unlock the chip */
 	if ((xfer = i2c_master_send(client, wel, 3)) != 3) {
-		dev_err(&client->dev, "%s: wel - %d\n", __FUNCTION__, xfer);
+		dev_err(&client->dev, "%s: wel - %d\n", __func__, xfer);
 		return -EIO;
 	}
 
 	if ((xfer = i2c_master_send(client, rwel, 3)) != 3) {
-		dev_err(&client->dev, "%s: rwel - %d\n", __FUNCTION__, xfer);
+		dev_err(&client->dev, "%s: rwel - %d\n", __func__, xfer);
 		return -EIO;
 	}
 
@@ -233,7 +208,7 @@ static int x1205_set_datetime(struct i2c_client *client, struct rtc_time *tm,
 		if (xfer != 3) {
 			dev_err(&client->dev,
 				"%s: xfer=%d addr=%02x, data=%02x\n",
-				__FUNCTION__,
+				__func__,
 				 xfer, rdata[1], rdata[2]);
 			return -EIO;
 		}
@@ -241,7 +216,7 @@ static int x1205_set_datetime(struct i2c_client *client, struct rtc_time *tm,
 
 	/* disable further writes */
 	if ((xfer = i2c_master_send(client, diswe, 3)) != 3) {
-		dev_err(&client->dev, "%s: diswe - %d\n", __FUNCTION__, xfer);
+		dev_err(&client->dev, "%s: diswe - %d\n", __func__, xfer);
 		return -EIO;
 	}
 
@@ -274,11 +249,11 @@ static int x1205_get_dtrim(struct i2c_client *client, int *trim)
 
 	/* read dtr register */
 	if ((i2c_transfer(client->adapter, &msgs[0], 2)) != 2) {
-		dev_err(&client->dev, "%s: read error\n", __FUNCTION__);
+		dev_err(&client->dev, "%s: read error\n", __func__);
 		return -EIO;
 	}
 
-	dev_dbg(&client->dev, "%s: raw dtr=%x\n", __FUNCTION__, dtr);
+	dev_dbg(&client->dev, "%s: raw dtr=%x\n", __func__, dtr);
 
 	*trim = 0;
 
@@ -306,11 +281,11 @@ static int x1205_get_atrim(struct i2c_client *client, int *trim)
 
 	/* read atr register */
 	if ((i2c_transfer(client->adapter, &msgs[0], 2)) != 2) {
-		dev_err(&client->dev, "%s: read error\n", __FUNCTION__);
+		dev_err(&client->dev, "%s: read error\n", __func__);
 		return -EIO;
 	}
 
-	dev_dbg(&client->dev, "%s: raw atr=%x\n", __FUNCTION__, atr);
+	dev_dbg(&client->dev, "%s: raw atr=%x\n", __func__, atr);
 
 	/* atr is a two's complement value on 6 bits,
 	 * perform sign extension. The formula is
@@ -319,11 +294,11 @@ static int x1205_get_atrim(struct i2c_client *client, int *trim)
 	if (atr & 0x20)
 		atr |= 0xC0;
 
-	dev_dbg(&client->dev, "%s: raw atr=%x (%d)\n", __FUNCTION__, atr, atr);
+	dev_dbg(&client->dev, "%s: raw atr=%x (%d)\n", __func__, atr, atr);
 
 	*trim = (atr * 250) + 11000;
 
-	dev_dbg(&client->dev, "%s: real=%d\n", __FUNCTION__, *trim);
+	dev_dbg(&client->dev, "%s: real=%d\n", __func__, *trim);
 
 	return 0;
 }
@@ -377,7 +352,7 @@ static int x1205_validate_client(struct i2c_client *client)
 		if ((xfer = i2c_transfer(client->adapter, msgs, 2)) != 2) {
 			dev_err(&client->dev,
 				"%s: could not read register %x\n",
-				__FUNCTION__, probe_zero_pattern[i]);
+				__func__, probe_zero_pattern[i]);
 
 			return -EIO;
 		}
@@ -385,7 +360,7 @@ static int x1205_validate_client(struct i2c_client *client)
 		if ((buf & probe_zero_pattern[i+1]) != 0) {
 			dev_err(&client->dev,
 				"%s: register=%02x, zero pattern=%d, value=%x\n",
-				__FUNCTION__, probe_zero_pattern[i], i, buf);
+				__func__, probe_zero_pattern[i], i, buf);
 
 			return -ENODEV;
 		}
@@ -405,7 +380,7 @@ static int x1205_validate_client(struct i2c_client *client)
 		if ((xfer = i2c_transfer(client->adapter, msgs, 2)) != 2) {
 			dev_err(&client->dev,
 				"%s: could not read register %x\n",
-				__FUNCTION__, probe_limits_pattern[i].reg);
+				__func__, probe_limits_pattern[i].reg);
 
 			return -EIO;
 		}
@@ -416,7 +391,7 @@ static int x1205_validate_client(struct i2c_client *client)
 			value < probe_limits_pattern[i].min) {
 			dev_dbg(&client->dev,
 				"%s: register=%x, lim pattern=%d, value=%d\n",
-				__FUNCTION__, probe_limits_pattern[i].reg,
+				__func__, probe_limits_pattern[i].reg,
 				i, value);
 
 			return -ENODEV;
@@ -497,58 +472,49 @@ static ssize_t x1205_sysfs_show_dtrim(struct device *dev,
 }
 static DEVICE_ATTR(dtrim, S_IRUGO, x1205_sysfs_show_dtrim, NULL);
 
-static int x1205_attach(struct i2c_adapter *adapter)
+static int x1205_sysfs_register(struct device *dev)
+{
+	int err;
+
+	err = device_create_file(dev, &dev_attr_atrim);
+	if (err)
+		return err;
+
+	err = device_create_file(dev, &dev_attr_dtrim);
+	if (err)
+		device_remove_file(dev, &dev_attr_atrim);
+
+	return err;
+}
+
+static void x1205_sysfs_unregister(struct device *dev)
 {
-	return i2c_probe(adapter, &addr_data, x1205_probe);
+	device_remove_file(dev, &dev_attr_atrim);
+	device_remove_file(dev, &dev_attr_dtrim);
 }
 
-static int x1205_probe(struct i2c_adapter *adapter, int address, int kind)
+
+static int x1205_probe(struct i2c_client *client)
 {
 	int err = 0;
 	unsigned char sr;
-	struct i2c_client *client;
 	struct rtc_device *rtc;
 
-	dev_dbg(&adapter->dev, "%s\n", __FUNCTION__);
-
-	if (!i2c_check_functionality(adapter, I2C_FUNC_I2C)) {
-		err = -ENODEV;
-		goto exit;
-	}
-
-	if (!(client = kzalloc(sizeof(struct i2c_client), GFP_KERNEL))) {
-		err = -ENOMEM;
-		goto exit;
-	}
-
-	/* I2C client */
-	client->addr = address;
-	client->driver = &x1205_driver;
-	client->adapter	= adapter;
+	dev_dbg(&client->dev, "%s\n", __func__);
 
-	strlcpy(client->name, x1205_driver.driver.name, I2C_NAME_SIZE);
-
-	/* Verify the chip is really an X1205 */
-	if (kind < 0) {
-		if (x1205_validate_client(client) < 0) {
-			err = -ENODEV;
-			goto exit_kfree;
-		}
-	}
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
+		return -ENODEV;
 
-	/* Inform the i2c layer */
-	if ((err = i2c_attach_client(client)))
-		goto exit_kfree;
+	if (x1205_validate_client(client) < 0)
+		return -ENODEV;
 
 	dev_info(&client->dev, "chip found, driver version " DRV_VERSION "\n");
 
 	rtc = rtc_device_register(x1205_driver.driver.name, &client->dev,
 				&x1205_rtc_ops, THIS_MODULE);
 
-	if (IS_ERR(rtc)) {
-		err = PTR_ERR(rtc);
-		goto exit_detach;
-	}
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
 
 	i2c_set_clientdata(client, rtc);
 
@@ -565,45 +531,35 @@ static int x1205_probe(struct i2c_adapter *adapter, int address, int kind)
 	else
 		dev_err(&client->dev, "couldn't read status\n");
 
-	err = device_create_file(&client->dev, &dev_attr_atrim);
-	if (err) goto exit_devreg;
-	err = device_create_file(&client->dev, &dev_attr_dtrim);
-	if (err) goto exit_atrim;
+	err = x1205_sysfs_register(&client->dev);
+	if (err)
+		goto exit_devreg;
 
 	return 0;
 
-exit_atrim:
-	device_remove_file(&client->dev, &dev_attr_atrim);
-
 exit_devreg:
 	rtc_device_unregister(rtc);
 
-exit_detach:
-	i2c_detach_client(client);
-
-exit_kfree:
-	kfree(client);
-
-exit:
 	return err;
 }
 
-static int x1205_detach(struct i2c_client *client)
+static int x1205_remove(struct i2c_client *client)
 {
-	int err;
 	struct rtc_device *rtc = i2c_get_clientdata(client);
 
- 	if (rtc)
-		rtc_device_unregister(rtc);
-
-	if ((err = i2c_detach_client(client)))
-		return err;
-
-	kfree(client);
-
+	rtc_device_unregister(rtc);
+	x1205_sysfs_unregister(&client->dev);
 	return 0;
 }
 
+static struct i2c_driver x1205_driver = {
+	.driver		= {
+		.name	= "rtc-x1205",
+	},
+	.probe		= x1205_probe,
+	.remove		= x1205_remove,
+};
+
 static int __init x1205_init(void)
 {
 	return i2c_add_driver(&x1205_driver);
diff --git a/trunk/drivers/s390/Makefile b/trunk/drivers/s390/Makefile
index 5a888704a8d0..4f4e7cf105d4 100644
--- a/trunk/drivers/s390/Makefile
+++ b/trunk/drivers/s390/Makefile
@@ -5,7 +5,7 @@
 CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w
 
 obj-y += s390mach.o sysinfo.o s390_rdev.o
-obj-y += cio/ block/ char/ crypto/ net/ scsi/
+obj-y += cio/ block/ char/ crypto/ net/ scsi/ kvm/
 
 drivers-y += drivers/s390/built-in.o
 
diff --git a/trunk/drivers/s390/block/dasd_proc.c b/trunk/drivers/s390/block/dasd_proc.c
index 556063e8f7a9..03c0e40a92ff 100644
--- a/trunk/drivers/s390/block/dasd_proc.c
+++ b/trunk/drivers/s390/block/dasd_proc.c
@@ -157,6 +157,7 @@ static int dasd_devices_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations dasd_devices_file_ops = {
+	.owner		= THIS_MODULE,
 	.open		= dasd_devices_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -311,17 +312,16 @@ dasd_statistics_write(struct file *file, const char __user *user_buf,
 int
 dasd_proc_init(void)
 {
-	dasd_proc_root_entry = proc_mkdir("dasd", &proc_root);
+	dasd_proc_root_entry = proc_mkdir("dasd", NULL);
 	if (!dasd_proc_root_entry)
 		goto out_nodasd;
 	dasd_proc_root_entry->owner = THIS_MODULE;
-	dasd_devices_entry = create_proc_entry("devices",
-					       S_IFREG | S_IRUGO | S_IWUSR,
-					       dasd_proc_root_entry);
+	dasd_devices_entry = proc_create("devices",
+					 S_IFREG | S_IRUGO | S_IWUSR,
+					 dasd_proc_root_entry,
+					 &dasd_devices_file_ops);
 	if (!dasd_devices_entry)
 		goto out_nodevices;
-	dasd_devices_entry->proc_fops = &dasd_devices_file_ops;
-	dasd_devices_entry->owner = THIS_MODULE;
 	dasd_statistics_entry = create_proc_entry("statistics",
 						  S_IFREG | S_IRUGO | S_IWUSR,
 						  dasd_proc_root_entry);
@@ -335,7 +335,7 @@ dasd_proc_init(void)
  out_nostatistics:
 	remove_proc_entry("devices", dasd_proc_root_entry);
  out_nodevices:
-	remove_proc_entry("dasd", &proc_root);
+	remove_proc_entry("dasd", NULL);
  out_nodasd:
 	return -ENOENT;
 }
@@ -345,5 +345,5 @@ dasd_proc_exit(void)
 {
 	remove_proc_entry("devices", dasd_proc_root_entry);
 	remove_proc_entry("statistics", dasd_proc_root_entry);
-	remove_proc_entry("dasd", &proc_root);
+	remove_proc_entry("dasd", NULL);
 }
diff --git a/trunk/drivers/s390/block/dcssblk.c b/trunk/drivers/s390/block/dcssblk.c
index 04787eab1016..bb52d2fbac18 100644
--- a/trunk/drivers/s390/block/dcssblk.c
+++ b/trunk/drivers/s390/block/dcssblk.c
@@ -36,7 +36,7 @@ static int dcssblk_open(struct inode *inode, struct file *filp);
 static int dcssblk_release(struct inode *inode, struct file *filp);
 static int dcssblk_make_request(struct request_queue *q, struct bio *bio);
 static int dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
-				 unsigned long *data);
+				 void **kaddr, unsigned long *pfn);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 
@@ -636,7 +636,7 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio)
 
 static int
 dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
-			unsigned long *data)
+			void **kaddr, unsigned long *pfn)
 {
 	struct dcssblk_dev_info *dev_info;
 	unsigned long pgoff;
@@ -649,7 +649,9 @@ dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
 	pgoff = secnum / (PAGE_SIZE / 512);
 	if ((pgoff+1)*PAGE_SIZE-1 > dev_info->end - dev_info->start)
 		return -ERANGE;
-	*data = (unsigned long) (dev_info->start+pgoff*PAGE_SIZE);
+	*kaddr = (void *) (dev_info->start+pgoff*PAGE_SIZE);
+	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
+
 	return 0;
 }
 
diff --git a/trunk/drivers/s390/char/tape_proc.c b/trunk/drivers/s390/char/tape_proc.c
index c9b96d51b28f..e7c888c14e71 100644
--- a/trunk/drivers/s390/char/tape_proc.c
+++ b/trunk/drivers/s390/char/tape_proc.c
@@ -111,6 +111,7 @@ static int tape_proc_open(struct inode *inode, struct file *file)
 
 static const struct file_operations tape_proc_ops =
 {
+	.owner		= THIS_MODULE,
 	.open		= tape_proc_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -124,14 +125,12 @@ void
 tape_proc_init(void)
 {
 	tape_proc_devices =
-		create_proc_entry ("tapedevices", S_IFREG | S_IRUGO | S_IWUSR,
-				   &proc_root);
+		proc_create("tapedevices", S_IFREG | S_IRUGO | S_IWUSR, NULL,
+			    &tape_proc_ops);
 	if (tape_proc_devices == NULL) {
 		PRINT_WARN("tape: Cannot register procfs entry tapedevices\n");
 		return;
 	}
-	tape_proc_devices->proc_fops = &tape_proc_ops;
-	tape_proc_devices->owner = THIS_MODULE;
 }
 
 /*
@@ -141,5 +140,5 @@ void
 tape_proc_cleanup(void)
 {
 	if (tape_proc_devices != NULL)
-		remove_proc_entry ("tapedevices", &proc_root);
+		remove_proc_entry ("tapedevices", NULL);
 }
diff --git a/trunk/drivers/s390/cio/blacklist.c b/trunk/drivers/s390/cio/blacklist.c
index e8597ec92247..40ef948fcb3a 100644
--- a/trunk/drivers/s390/cio/blacklist.c
+++ b/trunk/drivers/s390/cio/blacklist.c
@@ -374,13 +374,10 @@ cio_ignore_proc_init (void)
 {
 	struct proc_dir_entry *entry;
 
-	entry = create_proc_entry ("cio_ignore", S_IFREG | S_IRUGO | S_IWUSR,
-				   &proc_root);
+	entry = proc_create("cio_ignore", S_IFREG | S_IRUGO | S_IWUSR, NULL,
+			    &cio_ignore_proc_fops);
 	if (!entry)
 		return -ENOENT;
-
-	entry->proc_fops = &cio_ignore_proc_fops;
-
 	return 0;
 }
 
diff --git a/trunk/drivers/s390/cio/qdio.c b/trunk/drivers/s390/cio/qdio.c
index 10aa1e780801..43876e287370 100644
--- a/trunk/drivers/s390/cio/qdio.c
+++ b/trunk/drivers/s390/cio/qdio.c
@@ -3632,7 +3632,7 @@ qdio_add_procfs_entry(void)
 {
         proc_perf_file_registration=0;
 	qdio_perf_proc_file=create_proc_entry(QDIO_PERF,
-					      S_IFREG|0444,&proc_root);
+					      S_IFREG|0444,NULL);
 	if (qdio_perf_proc_file) {
 		qdio_perf_proc_file->read_proc=&qdio_perf_procfile_read;
 	} else proc_perf_file_registration=-1;
@@ -3647,7 +3647,7 @@ static void
 qdio_remove_procfs_entry(void)
 {
         if (!proc_perf_file_registration) /* means if it went ok earlier */
-		remove_proc_entry(QDIO_PERF,&proc_root);
+		remove_proc_entry(QDIO_PERF,NULL);
 }
 
 /**
diff --git a/trunk/drivers/s390/kvm/Makefile b/trunk/drivers/s390/kvm/Makefile
new file mode 100644
index 000000000000..4a5ec39f9ca6
--- /dev/null
+++ b/trunk/drivers/s390/kvm/Makefile
@@ -0,0 +1,9 @@
+# Makefile for kvm guest drivers on s390
+#
+# Copyright IBM Corp. 2008
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License (version 2 only)
+# as published by the Free Software Foundation.
+
+obj-$(CONFIG_VIRTIO) += kvm_virtio.o
diff --git a/trunk/drivers/s390/kvm/kvm_virtio.c b/trunk/drivers/s390/kvm/kvm_virtio.c
new file mode 100644
index 000000000000..bbef3764fbf8
--- /dev/null
+++ b/trunk/drivers/s390/kvm/kvm_virtio.c
@@ -0,0 +1,338 @@
+/*
+ * kvm_virtio.c - virtio for kvm on s390
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/err.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/interrupt.h>
+#include <linux/virtio_ring.h>
+#include <asm/io.h>
+#include <asm/kvm_para.h>
+#include <asm/kvm_virtio.h>
+#include <asm/setup.h>
+#include <asm/s390_ext.h>
+
+#define VIRTIO_SUBCODE_64 0x0D00
+
+/*
+ * The pointer to our (page) of device descriptions.
+ */
+static void *kvm_devices;
+
+/*
+ * Unique numbering for kvm devices.
+ */
+static unsigned int dev_index;
+
+struct kvm_device {
+	struct virtio_device vdev;
+	struct kvm_device_desc *desc;
+};
+
+#define to_kvmdev(vd) container_of(vd, struct kvm_device, vdev)
+
+/*
+ * memory layout:
+ * - kvm_device_descriptor
+ *        struct kvm_device_desc
+ * - configuration
+ *        struct kvm_vqconfig
+ * - feature bits
+ * - config space
+ */
+static struct kvm_vqconfig *kvm_vq_config(const struct kvm_device_desc *desc)
+{
+	return (struct kvm_vqconfig *)(desc + 1);
+}
+
+static u8 *kvm_vq_features(const struct kvm_device_desc *desc)
+{
+	return (u8 *)(kvm_vq_config(desc) + desc->num_vq);
+}
+
+static u8 *kvm_vq_configspace(const struct kvm_device_desc *desc)
+{
+	return kvm_vq_features(desc) + desc->feature_len * 2;
+}
+
+/*
+ * The total size of the config page used by this device (incl. desc)
+ */
+static unsigned desc_size(const struct kvm_device_desc *desc)
+{
+	return sizeof(*desc)
+		+ desc->num_vq * sizeof(struct kvm_vqconfig)
+		+ desc->feature_len * 2
+		+ desc->config_len;
+}
+
+/*
+ * This tests (and acknowleges) a feature bit.
+ */
+static bool kvm_feature(struct virtio_device *vdev, unsigned fbit)
+{
+	struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
+	u8 *features;
+
+	if (fbit / 8 > desc->feature_len)
+		return false;
+
+	features = kvm_vq_features(desc);
+	if (!(features[fbit / 8] & (1 << (fbit % 8))))
+		return false;
+
+	/*
+	 * We set the matching bit in the other half of the bitmap to tell the
+	 * Host we want to use this feature.
+	 */
+	features[desc->feature_len + fbit / 8] |= (1 << (fbit % 8));
+	return true;
+}
+
+/*
+ * Reading and writing elements in config space
+ */
+static void kvm_get(struct virtio_device *vdev, unsigned int offset,
+		   void *buf, unsigned len)
+{
+	struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
+
+	BUG_ON(offset + len > desc->config_len);
+	memcpy(buf, kvm_vq_configspace(desc) + offset, len);
+}
+
+static void kvm_set(struct virtio_device *vdev, unsigned int offset,
+		   const void *buf, unsigned len)
+{
+	struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
+
+	BUG_ON(offset + len > desc->config_len);
+	memcpy(kvm_vq_configspace(desc) + offset, buf, len);
+}
+
+/*
+ * The operations to get and set the status word just access
+ * the status field of the device descriptor. set_status will also
+ * make a hypercall to the host, to tell about status changes
+ */
+static u8 kvm_get_status(struct virtio_device *vdev)
+{
+	return to_kvmdev(vdev)->desc->status;
+}
+
+static void kvm_set_status(struct virtio_device *vdev, u8 status)
+{
+	BUG_ON(!status);
+	to_kvmdev(vdev)->desc->status = status;
+	kvm_hypercall1(KVM_S390_VIRTIO_SET_STATUS,
+		       (unsigned long) to_kvmdev(vdev)->desc);
+}
+
+/*
+ * To reset the device, we use the KVM_VIRTIO_RESET hypercall, using the
+ * descriptor address. The Host will zero the status and all the
+ * features.
+ */
+static void kvm_reset(struct virtio_device *vdev)
+{
+	kvm_hypercall1(KVM_S390_VIRTIO_RESET,
+		       (unsigned long) to_kvmdev(vdev)->desc);
+}
+
+/*
+ * When the virtio_ring code wants to notify the Host, it calls us here and we
+ * make a hypercall.  We hand the address  of the virtqueue so the Host
+ * knows which virtqueue we're talking about.
+ */
+static void kvm_notify(struct virtqueue *vq)
+{
+	struct kvm_vqconfig *config = vq->priv;
+
+	kvm_hypercall1(KVM_S390_VIRTIO_NOTIFY, config->address);
+}
+
+/*
+ * This routine finds the first virtqueue described in the configuration of
+ * this device and sets it up.
+ */
+static struct virtqueue *kvm_find_vq(struct virtio_device *vdev,
+				    unsigned index,
+				    void (*callback)(struct virtqueue *vq))
+{
+	struct kvm_device *kdev = to_kvmdev(vdev);
+	struct kvm_vqconfig *config;
+	struct virtqueue *vq;
+	int err;
+
+	if (index >= kdev->desc->num_vq)
+		return ERR_PTR(-ENOENT);
+
+	config = kvm_vq_config(kdev->desc)+index;
+
+	if (add_shared_memory(config->address,
+				vring_size(config->num, PAGE_SIZE))) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	vq = vring_new_virtqueue(config->num, vdev, (void *) config->address,
+				 kvm_notify, callback);
+	if (!vq) {
+		err = -ENOMEM;
+		goto unmap;
+	}
+
+	/*
+	 * register a callback token
+	 * The host will sent this via the external interrupt parameter
+	 */
+	config->token = (u64) vq;
+
+	vq->priv = config;
+	return vq;
+unmap:
+	remove_shared_memory(config->address, vring_size(config->num,
+			     PAGE_SIZE));
+out:
+	return ERR_PTR(err);
+}
+
+static void kvm_del_vq(struct virtqueue *vq)
+{
+	struct kvm_vqconfig *config = vq->priv;
+
+	vring_del_virtqueue(vq);
+	remove_shared_memory(config->address,
+			     vring_size(config->num, PAGE_SIZE));
+}
+
+/*
+ * The config ops structure as defined by virtio config
+ */
+static struct virtio_config_ops kvm_vq_configspace_ops = {
+	.feature = kvm_feature,
+	.get = kvm_get,
+	.set = kvm_set,
+	.get_status = kvm_get_status,
+	.set_status = kvm_set_status,
+	.reset = kvm_reset,
+	.find_vq = kvm_find_vq,
+	.del_vq = kvm_del_vq,
+};
+
+/*
+ * The root device for the kvm virtio devices.
+ * This makes them appear as /sys/devices/kvm_s390/0,1,2 not /sys/devices/0,1,2.
+ */
+static struct device kvm_root = {
+	.parent = NULL,
+	.bus_id = "kvm_s390",
+};
+
+/*
+ * adds a new device and register it with virtio
+ * appropriate drivers are loaded by the device model
+ */
+static void add_kvm_device(struct kvm_device_desc *d)
+{
+	struct kvm_device *kdev;
+
+	kdev = kzalloc(sizeof(*kdev), GFP_KERNEL);
+	if (!kdev) {
+		printk(KERN_EMERG "Cannot allocate kvm dev %u\n",
+		       dev_index++);
+		return;
+	}
+
+	kdev->vdev.dev.parent = &kvm_root;
+	kdev->vdev.index = dev_index++;
+	kdev->vdev.id.device = d->type;
+	kdev->vdev.config = &kvm_vq_configspace_ops;
+	kdev->desc = d;
+
+	if (register_virtio_device(&kdev->vdev) != 0) {
+		printk(KERN_ERR "Failed to register kvm device %u\n",
+		       kdev->vdev.index);
+		kfree(kdev);
+	}
+}
+
+/*
+ * scan_devices() simply iterates through the device page.
+ * The type 0 is reserved to mean "end of devices".
+ */
+static void scan_devices(void)
+{
+	unsigned int i;
+	struct kvm_device_desc *d;
+
+	for (i = 0; i < PAGE_SIZE; i += desc_size(d)) {
+		d = kvm_devices + i;
+
+		if (d->type == 0)
+			break;
+
+		add_kvm_device(d);
+	}
+}
+
+/*
+ * we emulate the request_irq behaviour on top of s390 extints
+ */
+static void kvm_extint_handler(u16 code)
+{
+	void *data = (void *) *(long *) __LC_PFAULT_INTPARM;
+	u16 subcode = S390_lowcore.cpu_addr;
+
+	if ((subcode & 0xff00) != VIRTIO_SUBCODE_64)
+		return;
+
+	vring_interrupt(0, data);
+}
+
+/*
+ * Init function for virtio
+ * devices are in a single page above top of "normal" mem
+ */
+static int __init kvm_devices_init(void)
+{
+	int rc;
+
+	if (!MACHINE_IS_KVM)
+		return -ENODEV;
+
+	rc = device_register(&kvm_root);
+	if (rc) {
+		printk(KERN_ERR "Could not register kvm_s390 root device");
+		return rc;
+	}
+
+	if (add_shared_memory((max_pfn) << PAGE_SHIFT, PAGE_SIZE)) {
+		device_unregister(&kvm_root);
+		return -ENOMEM;
+	}
+
+	kvm_devices  = (void *) (max_pfn << PAGE_SHIFT);
+
+	ctl_set_bit(0, 9);
+	register_external_interrupt(0x2603, kvm_extint_handler);
+
+	scan_devices();
+	return 0;
+}
+
+/*
+ * We do this after core stuff, but before the drivers.
+ */
+postcore_initcall(kvm_devices_init);
diff --git a/trunk/drivers/s390/scsi/zfcp_fsf.c b/trunk/drivers/s390/scsi/zfcp_fsf.c
index 7c3f02816e95..9af2330f07a2 100644
--- a/trunk/drivers/s390/scsi/zfcp_fsf.c
+++ b/trunk/drivers/s390/scsi/zfcp_fsf.c
@@ -1927,7 +1927,8 @@ zfcp_fsf_exchange_config_data_sync(struct zfcp_adapter *adapter,
 
 	/* setup new FSF request */
 	retval = zfcp_fsf_req_create(adapter, FSF_QTCB_EXCHANGE_CONFIG_DATA,
-				     0, NULL, &lock_flags, &fsf_req);
+				     ZFCP_WAIT_FOR_SBAL, NULL, &lock_flags,
+				     &fsf_req);
 	if (retval) {
 		ZFCP_LOG_INFO("error: Could not create exchange configuration "
 			      "data request for adapter %s.\n",
@@ -2035,21 +2036,21 @@ zfcp_fsf_exchange_config_evaluate(struct zfcp_fsf_req *fsf_req, int xchg_ok)
 		       min(FC_SERIAL_NUMBER_SIZE, 17));
 	}
 
-	ZFCP_LOG_NORMAL("The adapter %s reported the following "
-			"characteristics:\n"
-			"WWNN 0x%016Lx, "
-			"WWPN 0x%016Lx, "
-			"S_ID 0x%06x,\n"
-			"adapter version 0x%x, "
-			"LIC version 0x%x, "
-			"FC link speed %d Gb/s\n",
-			zfcp_get_busid_by_adapter(adapter),
-			(wwn_t) fc_host_node_name(shost),
-			(wwn_t) fc_host_port_name(shost),
-			fc_host_port_id(shost),
-			adapter->hydra_version,
-			adapter->fsf_lic_version,
-			fc_host_speed(shost));
+	if (fsf_req->erp_action)
+		ZFCP_LOG_NORMAL("The adapter %s reported the following "
+				"characteristics:\n"
+				"WWNN 0x%016Lx, WWPN 0x%016Lx, "
+				"S_ID 0x%06x,\n"
+				"adapter version 0x%x, "
+				"LIC version 0x%x, "
+				"FC link speed %d Gb/s\n",
+				zfcp_get_busid_by_adapter(adapter),
+				(wwn_t) fc_host_node_name(shost),
+				(wwn_t) fc_host_port_name(shost),
+				fc_host_port_id(shost),
+				adapter->hydra_version,
+				adapter->fsf_lic_version,
+				fc_host_speed(shost));
 	if (ZFCP_QTCB_VERSION < bottom->low_qtcb_version) {
 		ZFCP_LOG_NORMAL("error: the adapter %s "
 				"only supports newer control block "
@@ -2114,8 +2115,10 @@ zfcp_fsf_exchange_config_data_handler(struct zfcp_fsf_req *fsf_req)
 			zfcp_erp_adapter_shutdown(adapter, 0, 127, fsf_req);
 			return -EIO;
 		case FC_PORTTYPE_NPORT:
-			ZFCP_LOG_NORMAL("Switched fabric fibrechannel "
-					"network detected at adapter %s.\n",
+			if (fsf_req->erp_action)
+				ZFCP_LOG_NORMAL("Switched fabric fibrechannel "
+						"network detected at adapter "
+						"%s.\n",
 					zfcp_get_busid_by_adapter(adapter));
 			break;
 		default:
diff --git a/trunk/drivers/s390/scsi/zfcp_fsf.h b/trunk/drivers/s390/scsi/zfcp_fsf.h
index 8cce5cc11d50..099970b27001 100644
--- a/trunk/drivers/s390/scsi/zfcp_fsf.h
+++ b/trunk/drivers/s390/scsi/zfcp_fsf.h
@@ -213,6 +213,7 @@
 #define FSF_FEATURE_HBAAPI_MANAGEMENT           0x00000010
 #define FSF_FEATURE_ELS_CT_CHAINED_SBALS        0x00000020
 #define FSF_FEATURE_UPDATE_ALERT		0x00000100
+#define FSF_FEATURE_MEASUREMENT_DATA		0x00000200
 
 /* host connection features */
 #define FSF_FEATURE_NPIV_MODE			0x00000001
@@ -340,6 +341,15 @@ struct fsf_qtcb_prefix {
 	u8  res1[20];
 } __attribute__ ((packed));
 
+struct fsf_statistics_info {
+	u64 input_req;
+	u64 output_req;
+	u64 control_req;
+	u64 input_mb;
+	u64 output_mb;
+	u64 seconds_act;
+} __attribute__ ((packed));
+
 union fsf_status_qual {
 	u8  byte[FSF_STATUS_QUALIFIER_SIZE];
 	u16 halfword[FSF_STATUS_QUALIFIER_SIZE / sizeof (u16)];
@@ -436,7 +446,8 @@ struct fsf_qtcb_bottom_config {
 	u32 hardware_version;
 	u8 serial_number[32];
 	struct fsf_nport_serv_param plogi_payload;
-	u8 res4[160];
+	struct fsf_statistics_info stat_info;
+	u8 res4[112];
 } __attribute__ ((packed));
 
 struct fsf_qtcb_bottom_port {
@@ -469,7 +480,10 @@ struct fsf_qtcb_bottom_port {
 	u64 control_requests;
 	u64 input_mb;		/* where 1 MByte == 1.000.000 Bytes */
 	u64 output_mb;		/* where 1 MByte == 1.000.000 Bytes */
-	u8 res2[256];
+	u8 cp_util;
+	u8 cb_util;
+	u8 a_util;
+	u8 res2[253];
 } __attribute__ ((packed));
 
 union fsf_qtcb_bottom {
diff --git a/trunk/drivers/s390/scsi/zfcp_scsi.c b/trunk/drivers/s390/scsi/zfcp_scsi.c
index f81850624eed..01687559dc06 100644
--- a/trunk/drivers/s390/scsi/zfcp_scsi.c
+++ b/trunk/drivers/s390/scsi/zfcp_scsi.c
@@ -40,6 +40,7 @@ static struct zfcp_unit *zfcp_unit_lookup(struct zfcp_adapter *, int,
 					  unsigned int, unsigned int);
 
 static struct device_attribute *zfcp_sysfs_sdev_attrs[];
+static struct device_attribute *zfcp_a_stats_attrs[];
 
 struct zfcp_data zfcp_data = {
 	.scsi_host_template = {
@@ -61,6 +62,7 @@ struct zfcp_data zfcp_data = {
 		.use_clustering		= 1,
 		.sdev_attrs		= zfcp_sysfs_sdev_attrs,
 		.max_sectors		= ZFCP_MAX_SECTORS,
+		.shost_attrs		= zfcp_a_stats_attrs,
 	},
 	.driver_version = ZFCP_VERSION,
 };
@@ -809,4 +811,116 @@ static struct device_attribute *zfcp_sysfs_sdev_attrs[] = {
 	NULL
 };
 
+static ssize_t zfcp_sysfs_adapter_util_show(struct device *dev,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	struct Scsi_Host *scsi_host = dev_to_shost(dev);
+	struct fsf_qtcb_bottom_port *qtcb_port;
+	int retval;
+	struct zfcp_adapter *adapter;
+
+	adapter = (struct zfcp_adapter *) scsi_host->hostdata[0];
+	if (!(adapter->adapter_features & FSF_FEATURE_MEASUREMENT_DATA))
+		return -EOPNOTSUPP;
+
+	qtcb_port = kzalloc(sizeof(struct fsf_qtcb_bottom_port), GFP_KERNEL);
+	if (!qtcb_port)
+		return -ENOMEM;
+
+	retval = zfcp_fsf_exchange_port_data_sync(adapter, qtcb_port);
+	if (!retval)
+		retval = sprintf(buf, "%u %u %u\n", qtcb_port->cp_util,
+				 qtcb_port->cb_util, qtcb_port->a_util);
+	kfree(qtcb_port);
+	return retval;
+}
+
+static int zfcp_sysfs_adapter_ex_config(struct device *dev,
+					struct fsf_statistics_info *stat_inf)
+{
+	int retval;
+	struct fsf_qtcb_bottom_config *qtcb_config;
+	struct Scsi_Host *scsi_host = dev_to_shost(dev);
+	struct zfcp_adapter *adapter;
+
+	adapter = (struct zfcp_adapter *) scsi_host->hostdata[0];
+	if (!(adapter->adapter_features & FSF_FEATURE_MEASUREMENT_DATA))
+		return -EOPNOTSUPP;
+
+	qtcb_config = kzalloc(sizeof(struct fsf_qtcb_bottom_config),
+			       GFP_KERNEL);
+	if (!qtcb_config)
+		return -ENOMEM;
+
+	retval = zfcp_fsf_exchange_config_data_sync(adapter, qtcb_config);
+	if (!retval)
+		*stat_inf = qtcb_config->stat_info;
+
+	kfree(qtcb_config);
+	return retval;
+}
+
+static ssize_t zfcp_sysfs_adapter_request_show(struct device *dev,
+					       struct device_attribute *attr,
+					       char *buf)
+{
+	struct fsf_statistics_info stat_info;
+	int retval;
+
+	retval = zfcp_sysfs_adapter_ex_config(dev, &stat_info);
+	if (retval)
+		return retval;
+
+	return sprintf(buf, "%llu %llu %llu\n",
+		       (unsigned long long) stat_info.input_req,
+		       (unsigned long long) stat_info.output_req,
+		       (unsigned long long) stat_info.control_req);
+}
+
+static ssize_t zfcp_sysfs_adapter_mb_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct fsf_statistics_info stat_info;
+	int retval;
+
+	retval = zfcp_sysfs_adapter_ex_config(dev, &stat_info);
+	if (retval)
+		return retval;
+
+	return sprintf(buf, "%llu %llu\n",
+		       (unsigned long long) stat_info.input_mb,
+		       (unsigned long long) stat_info.output_mb);
+}
+
+static ssize_t zfcp_sysfs_adapter_sec_active_show(struct device *dev,
+						  struct device_attribute *attr,
+						  char *buf)
+{
+	struct fsf_statistics_info stat_info;
+	int retval;
+
+	retval = zfcp_sysfs_adapter_ex_config(dev, &stat_info);
+	if (retval)
+		return retval;
+
+	return sprintf(buf, "%llu\n",
+		       (unsigned long long) stat_info.seconds_act);
+}
+
+static DEVICE_ATTR(utilization, S_IRUGO, zfcp_sysfs_adapter_util_show, NULL);
+static DEVICE_ATTR(requests, S_IRUGO, zfcp_sysfs_adapter_request_show, NULL);
+static DEVICE_ATTR(megabytes, S_IRUGO, zfcp_sysfs_adapter_mb_show, NULL);
+static DEVICE_ATTR(seconds_active, S_IRUGO,
+		   zfcp_sysfs_adapter_sec_active_show, NULL);
+
+static struct device_attribute *zfcp_a_stats_attrs[] = {
+	&dev_attr_utilization,
+	&dev_attr_requests,
+	&dev_attr_megabytes,
+	&dev_attr_seconds_active,
+	NULL
+};
+
 #undef ZFCP_LOG_AREA
diff --git a/trunk/drivers/scsi/FlashPoint.c b/trunk/drivers/scsi/FlashPoint.c
index b374e457e5e2..b898d382b7b0 100644
--- a/trunk/drivers/scsi/FlashPoint.c
+++ b/trunk/drivers/scsi/FlashPoint.c
@@ -1499,7 +1499,7 @@ static void FlashPoint_StartCCB(unsigned long pCurrCard, struct sccb *p_Sccb)
 	thisCard = ((struct sccb_card *)pCurrCard)->cardIndex;
 	ioport = ((struct sccb_card *)pCurrCard)->ioPort;
 
-	if ((p_Sccb->TargID > MAX_SCSI_TAR) || (p_Sccb->Lun > MAX_LUN)) {
+	if ((p_Sccb->TargID >= MAX_SCSI_TAR) || (p_Sccb->Lun >= MAX_LUN)) {
 
 		p_Sccb->HostStatus = SCCB_COMPLETE;
 		p_Sccb->SccbStatus = SCCB_ERROR;
diff --git a/trunk/drivers/scsi/Kconfig b/trunk/drivers/scsi/Kconfig
index 7f78e3ea517d..99c57b0c1d54 100644
--- a/trunk/drivers/scsi/Kconfig
+++ b/trunk/drivers/scsi/Kconfig
@@ -1677,6 +1677,16 @@ config MAC_SCSI
 	  SCSI-HOWTO, available from
 	  <http://www.tldp.org/docs.html#howto>.
 
+config SCSI_MAC_ESP
+	tristate "Macintosh NCR53c9[46] SCSI"
+	depends on MAC && SCSI
+	help
+	  This is the NCR 53c9x SCSI controller found on most of the 68040
+	  based Macintoshes.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called mac_esp.
+
 config MVME147_SCSI
 	bool "WD33C93 SCSI driver for MVME147"
 	depends on MVME147 && SCSI=y
diff --git a/trunk/drivers/scsi/Makefile b/trunk/drivers/scsi/Makefile
index 23e6ecbd4778..6c775e350c98 100644
--- a/trunk/drivers/scsi/Makefile
+++ b/trunk/drivers/scsi/Makefile
@@ -46,6 +46,7 @@ obj-$(CONFIG_MVME147_SCSI)	+= mvme147.o	wd33c93.o
 obj-$(CONFIG_SGIWD93_SCSI)	+= sgiwd93.o	wd33c93.o
 obj-$(CONFIG_ATARI_SCSI)	+= atari_scsi.o
 obj-$(CONFIG_MAC_SCSI)		+= mac_scsi.o
+obj-$(CONFIG_SCSI_MAC_ESP)	+= esp_scsi.o	mac_esp.o
 obj-$(CONFIG_SUN3_SCSI)		+= sun3_scsi.o  sun3_scsi_vme.o
 obj-$(CONFIG_MVME16x_SCSI)	+= 53c700.o	mvme16x_scsi.o
 obj-$(CONFIG_BVME6000_SCSI)	+= 53c700.o	bvme6000_scsi.o
diff --git a/trunk/drivers/scsi/aha152x.c b/trunk/drivers/scsi/aha152x.c
index 6ccdc96cc480..f5215fd4b73d 100644
--- a/trunk/drivers/scsi/aha152x.c
+++ b/trunk/drivers/scsi/aha152x.c
@@ -994,13 +994,13 @@ static int aha152x_internal_queue(Scsi_Cmnd *SCpnt, struct completion *complete,
 	SCpnt->SCp.sent_command	= 0;
 
 	if(SCpnt->SCp.phase & (resetting|check_condition)) {
-		if(SCpnt->host_scribble==0 || SCSEM(SCpnt) || SCNEXT(SCpnt)) {
+		if (!SCpnt->host_scribble || SCSEM(SCpnt) || SCNEXT(SCpnt)) {
 			printk(ERR_LEAD "cannot reuse command\n", CMDINFO(SCpnt));
 			return FAILED;
 		}
 	} else {
 		SCpnt->host_scribble = kmalloc(sizeof(struct aha152x_scdata), GFP_ATOMIC);
-		if(SCpnt->host_scribble==0) {
+		if(!SCpnt->host_scribble) {
 			printk(ERR_LEAD "allocation failed\n", CMDINFO(SCpnt));
 			return FAILED;
 		}
@@ -1162,7 +1162,7 @@ static int aha152x_device_reset(Scsi_Cmnd * SCpnt)
 	}
 
 	DO_LOCK(flags);
-	issued       = remove_SC(&ISSUE_SC, SCpnt)==0;
+	issued       = remove_SC(&ISSUE_SC, SCpnt) == NULL;
 	disconnected = issued && remove_SC(&DISCONNECTED_SC, SCpnt);
 	DO_UNLOCK(flags);
 
@@ -1432,15 +1432,10 @@ static void run(struct work_struct *work)
  */
 static irqreturn_t intr(int irqno, void *dev_id)
 {
-	struct Scsi_Host *shpnt = (struct Scsi_Host *)dev_id;
+	struct Scsi_Host *shpnt = dev_id;
 	unsigned long flags;
 	unsigned char rev, dmacntrl0;
 
-	if (!shpnt) {
-		printk(KERN_ERR "aha152x: catched interrupt %d for unknown controller.\n", irqno);
-		return IRQ_NONE;
-	}
-
 	/*
 	 * Read a couple of registers that are known to not be all 1's. If
 	 * we read all 1's (-1), that means that either:
diff --git a/trunk/drivers/scsi/aha1542.c b/trunk/drivers/scsi/aha1542.c
index 5a1471c370fa..80594947c6f6 100644
--- a/trunk/drivers/scsi/aha1542.c
+++ b/trunk/drivers/scsi/aha1542.c
@@ -153,8 +153,6 @@ struct aha1542_hostdata {
 
 #define HOSTDATA(host) ((struct aha1542_hostdata *) &host->hostdata)
 
-static struct Scsi_Host *aha_host[7];	/* One for each IRQ level (9-15) */
-
 static DEFINE_SPINLOCK(aha1542_lock);
 
 
@@ -163,8 +161,7 @@ static DEFINE_SPINLOCK(aha1542_lock);
 
 static void setup_mailboxes(int base_io, struct Scsi_Host *shpnt);
 static int aha1542_restart(struct Scsi_Host *shost);
-static void aha1542_intr_handle(struct Scsi_Host *shost, void *dev_id);
-static irqreturn_t do_aha1542_intr_handle(int irq, void *dev_id);
+static void aha1542_intr_handle(struct Scsi_Host *shost);
 
 #define aha1542_intr_reset(base)  outb(IRST, CONTROL(base))
 
@@ -404,23 +401,19 @@ static int __init aha1542_test_port(int bse, struct Scsi_Host *shpnt)
 }
 
 /* A quick wrapper for do_aha1542_intr_handle to grab the spin lock */
-static irqreturn_t do_aha1542_intr_handle(int irq, void *dev_id)
+static irqreturn_t do_aha1542_intr_handle(int dummy, void *dev_id)
 {
 	unsigned long flags;
-	struct Scsi_Host *shost;
-
-	shost = aha_host[irq - 9];
-	if (!shost)
-		panic("Splunge!");
+	struct Scsi_Host *shost = dev_id;
 
 	spin_lock_irqsave(shost->host_lock, flags);
-	aha1542_intr_handle(shost, dev_id);
+	aha1542_intr_handle(shost);
 	spin_unlock_irqrestore(shost->host_lock, flags);
 	return IRQ_HANDLED;
 }
 
 /* A "high" level interrupt handler */
-static void aha1542_intr_handle(struct Scsi_Host *shost, void *dev_id)
+static void aha1542_intr_handle(struct Scsi_Host *shost)
 {
 	void (*my_done) (Scsi_Cmnd *) = NULL;
 	int errstatus, mbi, mbo, mbistatus;
@@ -1197,7 +1190,8 @@ static int __init aha1542_detect(struct scsi_host_template * tpnt)
 
 			DEB(printk("aha1542_detect: enable interrupt channel %d\n", irq_level));
 			spin_lock_irqsave(&aha1542_lock, flags);
-			if (request_irq(irq_level, do_aha1542_intr_handle, 0, "aha1542", NULL)) {
+			if (request_irq(irq_level, do_aha1542_intr_handle, 0,
+					"aha1542", shpnt)) {
 				printk(KERN_ERR "Unable to allocate IRQ for adaptec controller.\n");
 				spin_unlock_irqrestore(&aha1542_lock, flags);
 				goto unregister;
@@ -1205,7 +1199,7 @@ static int __init aha1542_detect(struct scsi_host_template * tpnt)
 			if (dma_chan != 0xFF) {
 				if (request_dma(dma_chan, "aha1542")) {
 					printk(KERN_ERR "Unable to allocate DMA channel for Adaptec.\n");
-					free_irq(irq_level, NULL);
+					free_irq(irq_level, shpnt);
 					spin_unlock_irqrestore(&aha1542_lock, flags);
 					goto unregister;
 				}
@@ -1214,7 +1208,7 @@ static int __init aha1542_detect(struct scsi_host_template * tpnt)
 					enable_dma(dma_chan);
 				}
 			}
-			aha_host[irq_level - 9] = shpnt;
+
 			shpnt->this_id = scsi_id;
 			shpnt->unique_id = base_io;
 			shpnt->io_port = base_io;
@@ -1276,7 +1270,7 @@ static int __init aha1542_detect(struct scsi_host_template * tpnt)
 static int aha1542_release(struct Scsi_Host *shost)
 {
 	if (shost->irq)
-		free_irq(shost->irq, NULL);
+		free_irq(shost->irq, shost);
 	if (shost->dma_channel != 0xff)
 		free_dma(shost->dma_channel);
 	if (shost->io_port && shost->n_io_port)
diff --git a/trunk/drivers/scsi/aic7xxx/aic7770_osm.c b/trunk/drivers/scsi/aic7xxx/aic7770_osm.c
index 1ac119733bac..f220e5e436ab 100644
--- a/trunk/drivers/scsi/aic7xxx/aic7770_osm.c
+++ b/trunk/drivers/scsi/aic7xxx/aic7770_osm.c
@@ -50,7 +50,7 @@ aic7770_map_registers(struct ahc_softc *ahc, u_int port)
 	/*
 	 * Lock out other contenders for our i/o space.
 	 */
-	if (request_region(port, AHC_EISA_IOSIZE, "aic7xxx") == 0)
+	if (!request_region(port, AHC_EISA_IOSIZE, "aic7xxx"))
 		return (ENOMEM);
 	ahc->tag = BUS_SPACE_PIO;
 	ahc->bsh.ioport = port;
diff --git a/trunk/drivers/scsi/aic7xxx/aic79xx.h b/trunk/drivers/scsi/aic7xxx/aic79xx.h
index 2f00467b6b8c..be5558ab84ea 100644
--- a/trunk/drivers/scsi/aic7xxx/aic79xx.h
+++ b/trunk/drivers/scsi/aic7xxx/aic79xx.h
@@ -815,7 +815,7 @@ struct ahd_tmode_tstate {
 struct ahd_phase_table_entry {
         uint8_t phase;
         uint8_t mesg_out; /* Message response to parity errors */
-	char *phasemsg;
+	const char *phasemsg;
 };
 
 /************************** Serial EEPROM Format ******************************/
@@ -1314,7 +1314,7 @@ typedef int (ahd_device_setup_t)(struct ahd_softc *);
 struct ahd_pci_identity {
 	uint64_t		 full_id;
 	uint64_t		 id_mask;
-	char			*name;
+	const char		*name;
 	ahd_device_setup_t	*setup;
 };
 
@@ -1322,7 +1322,7 @@ struct ahd_pci_identity {
 struct aic7770_identity {
 	uint32_t		 full_id;
 	uint32_t		 id_mask;
-	char			*name;
+	const char		*name;
 	ahd_device_setup_t	*setup;
 };
 extern struct aic7770_identity aic7770_ident_table [];
@@ -1333,12 +1333,11 @@ extern const int ahd_num_aic7770_devs;
 
 /*************************** Function Declarations ****************************/
 /******************************************************************************/
-void			ahd_reset_cmds_pending(struct ahd_softc *ahd);
 
 /***************************** PCI Front End *********************************/
-struct	ahd_pci_identity *ahd_find_pci_device(ahd_dev_softc_t);
+const struct	ahd_pci_identity *ahd_find_pci_device(ahd_dev_softc_t);
 int			  ahd_pci_config(struct ahd_softc *,
-					 struct ahd_pci_identity *);
+					 const struct ahd_pci_identity *);
 int	ahd_pci_test_register_access(struct ahd_softc *);
 #ifdef CONFIG_PM
 void	ahd_pci_suspend(struct ahd_softc *);
@@ -1376,16 +1375,6 @@ int			 ahd_write_flexport(struct ahd_softc *ahd,
 int			 ahd_read_flexport(struct ahd_softc *ahd, u_int addr,
 					   uint8_t *value);
 
-/*************************** Interrupt Services *******************************/
-void			ahd_run_qoutfifo(struct ahd_softc *ahd);
-#ifdef AHD_TARGET_MODE
-void			ahd_run_tqinfifo(struct ahd_softc *ahd, int paused);
-#endif
-void			ahd_handle_hwerrint(struct ahd_softc *ahd);
-void			ahd_handle_seqint(struct ahd_softc *ahd, u_int intstat);
-void			ahd_handle_scsiint(struct ahd_softc *ahd,
-					   u_int intstat);
-
 /***************************** Error Recovery *********************************/
 typedef enum {
 	SEARCH_COMPLETE,
@@ -1479,7 +1468,7 @@ extern uint32_t ahd_debug;
 void			ahd_print_devinfo(struct ahd_softc *ahd,
 					  struct ahd_devinfo *devinfo);
 void			ahd_dump_card_state(struct ahd_softc *ahd);
-int			ahd_print_register(ahd_reg_parse_entry_t *table,
+int			ahd_print_register(const ahd_reg_parse_entry_t *table,
 					   u_int num_entries,
 					   const char *name,
 					   u_int address,
diff --git a/trunk/drivers/scsi/aic7xxx/aic79xx.reg b/trunk/drivers/scsi/aic7xxx/aic79xx.reg
index be14e2ecb8f7..cca16fc5b4ad 100644
--- a/trunk/drivers/scsi/aic7xxx/aic79xx.reg
+++ b/trunk/drivers/scsi/aic7xxx/aic79xx.reg
@@ -198,6 +198,7 @@ register SEQINTCODE {
 register CLRINT {
 	address			0x003
 	access_mode	WO
+	count		19
 	field	CLRHWERRINT	0x80 /* Rev B or greater */
 	field	CLRBRKADRINT	0x40
 	field	CLRSWTMINT	0x20
@@ -245,6 +246,7 @@ register CLRERR {
 register HCNTRL {
 	address			0x005
 	access_mode	RW
+	count		12
 	field	SEQ_RESET	0x80 /* Rev B or greater */
 	field	POWRDN		0x40
 	field	SWINT		0x10
@@ -262,6 +264,7 @@ register HNSCB_QOFF {
 	address			0x006
 	access_mode	RW
 	size		2
+	count		2
 }
 
 /*
@@ -270,6 +273,7 @@ register HNSCB_QOFF {
 register HESCB_QOFF {
 	address			0x008
 	access_mode	RW
+	count		2
 }
 
 /*
@@ -287,6 +291,7 @@ register HS_MAILBOX {
  */
 register SEQINTSTAT {
 	address			0x00C
+	count		1
 	access_mode	RO
 	field	SEQ_SWTMRTO	0x10
 	field	SEQ_SEQINT	0x08
@@ -332,6 +337,7 @@ register SNSCB_QOFF {
  */
 register SESCB_QOFF {
 	address			0x012
+	count		2
 	access_mode	RW
 	modes		M_CCHAN
 }
@@ -397,6 +403,7 @@ register DFCNTRL {
 	address			0x019
 	access_mode	RW
 	modes		M_DFF0, M_DFF1
+	count		11
 	field	PRELOADEN	0x80
 	field	SCSIENWRDIS	0x40	/* Rev B only. */
 	field	SCSIEN		0x20
@@ -415,6 +422,7 @@ register DFCNTRL {
  */
 register DSCOMMAND0 {
 	address			0x019
+	count		1
 	access_mode	RW
 	modes		M_CFG
 	field	CACHETHEN	0x80	/* Cache Threshold enable */
@@ -580,6 +588,7 @@ register DFF_THRSH {
 	address			0x088
 	access_mode	RW
 	modes		M_CFG
+	count		1
 	field	WR_DFTHRSH	0x70 {
 		WR_DFTHRSH_MIN,
 		WR_DFTHRSH_25,
@@ -800,6 +809,7 @@ register PCIXCTL {
 	address			0x093
 	access_mode	RW
 	modes		M_CFG
+	count		1
 	field	SERRPULSE	0x80
 	field	UNEXPSCIEN	0x20
 	field	SPLTSMADIS	0x10
@@ -844,6 +854,7 @@ register DCHSPLTSTAT0 {
 	address			0x096
 	access_mode	RW
 	modes		M_DFF0, M_DFF1
+	count		2
 	field	STAETERM	0x80
 	field	SCBCERR		0x40
 	field	SCADERR		0x20
@@ -895,6 +906,7 @@ register DCHSPLTSTAT1 {
 	address			0x097
 	access_mode	RW
 	modes		M_DFF0, M_DFF1
+	count		2
 	field	RXDATABUCKET	0x01
 }
 
@@ -1048,6 +1060,7 @@ register SGSPLTSTAT0 {
 	address			0x09E
 	access_mode	RW
 	modes		M_DFF0, M_DFF1
+	count		2
 	field	STAETERM	0x80
 	field	SCBCERR		0x40
 	field	SCADERR		0x20
@@ -1065,6 +1078,7 @@ register SGSPLTSTAT1 {
 	address			0x09F
 	access_mode	RW
 	modes		M_DFF0, M_DFF1
+	count		2
 	field	RXDATABUCKET	0x01
 }
 
@@ -1086,6 +1100,7 @@ register DF0PCISTAT {
 	address			0x0A0
 	access_mode	RW
 	modes		M_CFG
+	count		1
 	field	DPE		0x80
 	field	SSE		0x40
 	field	RMA		0x20
@@ -1184,6 +1199,7 @@ register TARGPCISTAT {
 	address			0x0A7
 	access_mode	RW
 	modes		M_CFG
+	count		5
 	field	DPE		0x80
 	field	SSE		0x40
 	field	STA		0x08
@@ -1198,6 +1214,7 @@ register LQIN {
 	address			0x020
 	access_mode	RW
 	size		20
+	count		2
 	modes		M_DFF0, M_DFF1, M_SCSI
 }
 
@@ -1229,6 +1246,7 @@ register LUNPTR {
 	address			0x022
 	access_mode	RW
 	modes		M_CFG
+	count		2
 }
 
 /*
@@ -1259,6 +1277,7 @@ register CMDLENPTR {
 	address			0x025
 	access_mode	RW
 	modes		M_CFG
+	count		1
 }
 
 /*
@@ -1270,6 +1289,7 @@ register ATTRPTR {
 	address			0x026
 	access_mode	RW
 	modes		M_CFG
+	count		1
 }
 
 /*
@@ -1281,6 +1301,7 @@ register FLAGPTR {
 	address			0x027
 	access_mode	RW
 	modes		M_CFG
+	count		1
 }
 
 /*
@@ -1291,6 +1312,7 @@ register CMDPTR {
 	address			0x028
 	access_mode	RW
 	modes		M_CFG
+	count		1
 }
 
 /*
@@ -1301,6 +1323,7 @@ register QNEXTPTR {
 	address			0x029
 	access_mode	RW
 	modes		M_CFG
+	count		1
 }
 
 /*
@@ -1323,6 +1346,7 @@ register ABRTBYTEPTR {
 	address			0x02B
 	access_mode	RW
 	modes		M_CFG
+	count		1
 }
 
 /*
@@ -1333,6 +1357,7 @@ register ABRTBITPTR {
 	address			0x02C
 	access_mode	RW
 	modes		M_CFG
+	count		1
 }
 
 /*
@@ -1370,6 +1395,7 @@ register LUNLEN {
 	address			0x030
 	access_mode	RW
 	modes		M_CFG
+	count		2
 	mask		ILUNLEN	0x0F
 	mask		TLUNLEN	0xF0
 }
@@ -1383,6 +1409,7 @@ register CDBLIMIT {
 	address			0x031
 	access_mode	RW
 	modes		M_CFG
+	count		1
 }
 
 /*
@@ -1394,6 +1421,7 @@ register MAXCMD {
 	address			0x032
 	access_mode	RW
 	modes		M_CFG
+	count		9
 }
 
 /*
@@ -1458,6 +1486,7 @@ register LQCTL1 {
 	address			0x038
 	access_mode	RW
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		2
 	field	PCI2PCI		0x04
 	field	SINGLECMD	0x02
 	field	ABORTPENDING	0x01
@@ -1470,6 +1499,7 @@ register LQCTL2 {
 	address			0x039
 	access_mode	RW
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		5
 	field	LQIRETRY	0x80
 	field	LQICONTINUE	0x40
 	field	LQITOIDLE	0x20
@@ -1528,6 +1558,7 @@ register SCSISEQ1 {
 	address			0x03B
 	access_mode	RW
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		8
 	field	MANUALCTL	0x40
 	field	ENSELI		0x20
 	field	ENRSELI		0x10
@@ -1667,6 +1698,9 @@ register SCSISIGO {
 	}
 }
 
+/*
+ * SCSI Control Signal In
+ */
 register SCSISIGI {
 	address			0x041
 	access_mode	RO
@@ -1703,6 +1737,7 @@ register MULTARGID {
 	access_mode	RW
 	modes		M_CFG
 	size		2
+	count		2
 }
 
 /*
@@ -1758,6 +1793,7 @@ register TARGIDIN {
 	address			0x048
 	access_mode	RO
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		2
 	field	CLKOUT		0x80
 	field	TARGID		0x0F
 }
@@ -1798,6 +1834,7 @@ register OPTIONMODE {
 	address			0x04A
 	access_mode	RW
 	modes		M_CFG
+	count		4
 	field	BIOSCANCTL		0x80
 	field	AUTOACKEN		0x40
 	field	BIASCANCTL		0x20
@@ -1850,6 +1887,7 @@ register SIMODE0 {
 	address			0x04B
 	access_mode	RW
 	modes		M_CFG
+	count		8
 	field	ENSELDO		0x40
 	field	ENSELDI		0x20
 	field	ENSELINGO	0x10
@@ -1945,6 +1983,7 @@ register PERRDIAG {
 	address			0x04E
 	access_mode	RO
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		3
 	field	HIZERO		0x80
 	field	HIPERR		0x40
 	field	PREVPHASE	0x20
@@ -1962,6 +2001,7 @@ register LQISTATE {
 	address			0x04E
 	access_mode	RO
 	modes		M_CFG
+	count		6
 }
 
 /*
@@ -1971,6 +2011,7 @@ register SOFFCNT {
 	address			0x04F
 	access_mode	RO
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		1
 }
 
 /*
@@ -1980,6 +2021,7 @@ register LQOSTATE {
 	address			0x04F
 	access_mode	RO
 	modes		M_CFG
+	count		2
 }
 
 /*
@@ -1989,6 +2031,7 @@ register LQISTAT0 {
 	address			0x050
 	access_mode	RO
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		2
 	field	LQIATNQAS	0x20
 	field	LQICRCT1	0x10
 	field	LQICRCT2	0x08
@@ -2004,6 +2047,7 @@ register CLRLQIINT0 {
 	address			0x050
 	access_mode	WO
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		1
 	field	CLRLQIATNQAS	0x20
 	field	CLRLQICRCT1	0x10
 	field	CLRLQICRCT2	0x08
@@ -2019,6 +2063,7 @@ register LQIMODE0 {
 	address			0x050
 	access_mode	RW
 	modes		M_CFG
+	count		3
 	field	ENLQIATNQASK	0x20
 	field	ENLQICRCT1	0x10
 	field	ENLQICRCT2	0x08
@@ -2034,6 +2079,7 @@ register LQISTAT1 {
 	address			0x051
 	access_mode	RO
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		3
 	field	LQIPHASE_LQ	0x80
 	field	LQIPHASE_NLQ	0x40
 	field	LQIABORT	0x20
@@ -2051,6 +2097,7 @@ register CLRLQIINT1 {
 	address			0x051
 	access_mode	WO
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		4
 	field	CLRLQIPHASE_LQ	0x80
 	field	CLRLQIPHASE_NLQ	0x40
 	field	CLRLIQABORT	0x20
@@ -2068,6 +2115,7 @@ register LQIMODE1 {
 	address			0x051
 	access_mode	RW
 	modes		M_CFG
+	count		4
 	field	ENLQIPHASE_LQ	0x80	/* LQIPHASE1 */
 	field	ENLQIPHASE_NLQ	0x40	/* LQIPHASE2 */
 	field	ENLIQABORT	0x20
@@ -2102,6 +2150,7 @@ register SSTAT3 {
 	address			0x053
 	access_mode	RO
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		3
 	field	NTRAMPERR	0x02
 	field	OSRAMPERR	0x01
 }
@@ -2113,6 +2162,7 @@ register CLRSINT3 {
 	address			0x053
 	access_mode	WO
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		3
 	field	CLRNTRAMPERR	0x02
 	field	CLROSRAMPERR	0x01
 }
@@ -2124,6 +2174,7 @@ register SIMODE3 {
 	address			0x053
 	access_mode	RW
 	modes		M_CFG
+	count		4
 	field	ENNTRAMPERR	0x02
 	field	ENOSRAMPERR	0x01
 }
@@ -2135,6 +2186,7 @@ register LQOSTAT0 {
 	address			0x054
 	access_mode	RO
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		2
 	field	LQOTARGSCBPERR	0x10
 	field	LQOSTOPT2	0x08
 	field	LQOATNLQ	0x04
@@ -2149,6 +2201,7 @@ register CLRLQOINT0 {
 	address			0x054
 	access_mode	WO
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		3
 	field	CLRLQOTARGSCBPERR	0x10
 	field	CLRLQOSTOPT2		0x08
 	field	CLRLQOATNLQ		0x04
@@ -2163,6 +2216,7 @@ register LQOMODE0 {
 	address			0x054
 	access_mode	RW
 	modes		M_CFG
+	count		4
 	field	ENLQOTARGSCBPERR	0x10
 	field	ENLQOSTOPT2		0x08
 	field	ENLQOATNLQ		0x04
@@ -2191,6 +2245,7 @@ register CLRLQOINT1 {
 	address			0x055
 	access_mode	WO
 	modes		M_DFF0, M_DFF1, M_SCSI
+	count		7
 	field	CLRLQOINITSCBPERR	0x10
 	field	CLRLQOSTOPI2		0x08
 	field	CLRLQOBADQAS		0x04
@@ -2205,6 +2260,7 @@ register LQOMODE1 {
 	address			0x055
 	access_mode	RW
 	modes		M_CFG
+	count		4
 	field	ENLQOINITSCBPERR	0x10
 	field	ENLQOSTOPI2		0x08
 	field	ENLQOBADQAS		0x04
@@ -2232,6 +2288,7 @@ register OS_SPACE_CNT {
 	address			0x056
 	access_mode	RO
 	modes		M_CFG
+	count		2
 }
 
 /*
@@ -2286,13 +2343,19 @@ register NEXTSCB {
 	modes		M_SCSI
 }
 
-/* Rev B only. */
+/*
+ * LQO SCSI Control
+ * (Rev B only.)
+ */
 register LQOSCSCTL {
 	address			0x05A
 	access_mode	RW
 	size		1
 	modes		M_CFG
+	count		1
 	field		LQOH2A_VERSION	0x80
+	field		LQOBUSETDLY	0x40
+	field		LQONOHOLDLACK	0x02
 	field		LQONOCHKOVER	0x01
 }
 
@@ -2459,6 +2522,7 @@ register NEGPERIOD {
 	address			0x061
 	access_mode	RW
 	modes		M_SCSI
+	count		1
 }
 
 /*
@@ -2478,6 +2542,7 @@ register NEGOFFSET {
 	address			0x062
 	access_mode	RW
 	modes		M_SCSI
+	count		1
 }
 
 /*
@@ -2487,6 +2552,7 @@ register NEGPPROPTS {
 	address			0x063
 	access_mode	RW
 	modes		M_SCSI
+	count		1
 	field	PPROPT_PACE	0x08
 	field	PPROPT_QAS	0x04
 	field	PPROPT_DT	0x02
@@ -2516,12 +2582,19 @@ register ANNEXCOL {
 	address			0x065
 	access_mode	RW
 	modes		M_SCSI
+	count		7
 }
 
+/*
+ * SCSI Check
+ * (Rev. B only)
+ */
 register SCSCHKN {
 	address			0x066
 	access_mode	RW
 	modes		M_CFG
+	count		1
+	field	BIDICHKDIS	0x80
 	field	STSELSKIDDIS	0x40
 	field	CURRFIFODEF	0x20
 	field	WIDERESEN	0x10
@@ -2561,6 +2634,7 @@ register ANNEXDAT {
 	address			0x066
 	access_mode	RW
 	modes		M_SCSI
+	count		3
 }
 
 /*
@@ -2596,6 +2670,7 @@ register TOWNID {
 	address			0x069
 	access_mode	RW
 	modes		M_SCSI
+	count		2
 }
 
 /*
@@ -2737,6 +2812,7 @@ register SCBAUTOPTR {
 	address			0x0AB
 	access_mode	RW
 	modes		M_CFG
+	count		1
 	field	AUSCBPTR_EN	0x80
 	field	SCBPTR_ADDR	0x38
 	field	SCBPTR_OFF	0x07
@@ -2881,6 +2957,7 @@ register BRDDAT {
 	address			0x0B8
 	access_mode	RW
 	modes		M_SCSI
+	count		2
 }
 
 /*
@@ -2890,6 +2967,7 @@ register BRDCTL {
 	address			0x0B9
 	access_mode	RW
 	modes		M_SCSI
+	count		7
 	field	FLXARBACK	0x80
 	field	FLXARBREQ	0x40
 	field	BRDADDR		0x38
@@ -2905,6 +2983,7 @@ register SEEADR {
 	address			0x0BA
 	access_mode	RW
 	modes		M_SCSI
+	count		4
 }
 
 /*
@@ -2915,6 +2994,7 @@ register SEEDAT {
 	access_mode	RW
 	size		2
 	modes		M_SCSI
+	count		4
 }
 
 /*
@@ -2924,6 +3004,7 @@ register SEESTAT {
 	address			0x0BE
 	access_mode	RO
 	modes		M_SCSI
+	count		1
 	field	INIT_DONE	0x80
 	field	SEEOPCODE	0x70
 	field	LDALTID_L	0x08
@@ -2939,6 +3020,7 @@ register SEECTL {
 	address			0x0BE
 	access_mode	RW
 	modes		M_SCSI
+	count		4
 	field	SEEOPCODE	0x70 {
 		SEEOP_ERASE	0x70,
 		SEEOP_READ	0x60,
@@ -3000,6 +3082,7 @@ register DSPDATACTL {
 	address			0x0C1
 	access_mode	RW
 	modes		M_CFG
+	count		3
 	field	BYPASSENAB	0x80
 	field	DESQDIS		0x10
 	field	RCVROFFSTDIS	0x04
@@ -3058,6 +3141,7 @@ register DSPSELECT {
 	address			0x0C4
 	access_mode	RW
 	modes		M_CFG
+	count		1
 	field	AUTOINCEN	0x80
 	field	DSPSEL		0x1F
 }
@@ -3071,6 +3155,7 @@ register WRTBIASCTL {
 	address			0x0C5
 	access_mode	WO
 	modes		M_CFG
+	count		3
 	field	AUTOXBCDIS	0x80
 	field	XMITMANVAL	0x3F
 }
@@ -3196,7 +3281,8 @@ register OVLYADDR {
  */
 register SEQCTL0 {
 	address			0x0D6
-	access_mode RW
+	access_mode	RW
+	count		11
 	field	PERRORDIS	0x80
 	field	PAUSEDIS	0x40
 	field	FAILDIS		0x20
@@ -3226,7 +3312,8 @@ register SEQCTL1 {
  */
 register FLAGS {
 	address			0x0D8
-	access_mode RO
+	access_mode 	RO
+	count		23
 	field	ZERO		0x02
 	field	CARRY		0x01
 }
@@ -3255,7 +3342,8 @@ register SEQINTCTL {
  */
 register SEQRAM {
 	address			0x0DA
-	access_mode RW
+	access_mode 	RW
+	count		2
 }
 
 /*
@@ -3266,6 +3354,7 @@ register PRGMCNT {
 	address			0x0DE
 	access_mode	RW
 	size		2
+	count		5
 }
 
 /*
@@ -3273,7 +3362,7 @@ register PRGMCNT {
  */
 register ACCUM {
 	address			0x0E0
-	access_mode RW
+	access_mode 	RW
 	accumulator
 }
 
@@ -3401,6 +3490,7 @@ register INTVEC1_ADDR {
 	access_mode	RW
 	size		2
 	modes		M_CFG
+	count		1
 }
 
 /*
@@ -3412,6 +3502,7 @@ register CURADDR {
 	access_mode	RW
 	size		2
 	modes		M_SCSI
+	count		2
 }
 
 /*
@@ -3423,6 +3514,7 @@ register INTVEC2_ADDR {
 	access_mode	RW
 	size		2
 	modes		M_CFG
+	count		1
 }
 
 /*
@@ -3579,6 +3671,7 @@ scratch_ram {
 	/* Parameters for DMA Logic */
 	DMAPARAMS {
 		size		1
+		count		8
 		field	PRELOADEN	0x80
 		field	WIDEODD		0x40
 		field	SCSIEN		0x20
@@ -3648,9 +3741,11 @@ scratch_ram {
 	 */
 	KERNEL_TQINPOS {
 		size		1
+		count		1
 	}
-	TQINPOS {                
+	TQINPOS {
 		size		1
+		count		8
 	}
 	/*
 	 * Base address of our shared data with the kernel driver in host
@@ -3681,6 +3776,7 @@ scratch_ram {
 	}
 	ARG_2 {
 		size		1
+		count		1
 		alias	RETURN_2
 	}
 
@@ -3698,6 +3794,7 @@ scratch_ram {
 	 */
 	SCSISEQ_TEMPLATE {
 		size		1
+		count		7
 		field	MANUALCTL	0x40
 		field	ENSELI		0x20
 		field	ENRSELI		0x10
@@ -3711,6 +3808,7 @@ scratch_ram {
 	 */
 	INITIATOR_TAG {
 		size		1
+		count		1
 	}
 
 	SEQ_FLAGS2 {
@@ -3777,6 +3875,7 @@ scratch_ram {
 	 */
 	CMDSIZE_TABLE {
 		size		8
+		count		8
 	}
 	/*
 	 * When an SCB with the MK_MESSAGE flag is
@@ -3803,8 +3902,8 @@ scratch_ram {
 /************************* Hardware SCB Definition ****************************/
 scb {
 	address			0x180
-	size	64
-	modes	0, 1, 2, 3
+	size		64
+	modes		0, 1, 2, 3
 	SCB_RESIDUAL_DATACNT {
 		size	4
 		alias	SCB_CDB_STORE
diff --git a/trunk/drivers/scsi/aic7xxx/aic79xx_core.c b/trunk/drivers/scsi/aic7xxx/aic79xx_core.c
index ade0fb8fbdb2..55508b0fcec4 100644
--- a/trunk/drivers/scsi/aic7xxx/aic79xx_core.c
+++ b/trunk/drivers/scsi/aic7xxx/aic79xx_core.c
@@ -52,7 +52,7 @@
 
 
 /***************************** Lookup Tables **********************************/
-static char *ahd_chip_names[] =
+static const char *const ahd_chip_names[] =
 {
 	"NONE",
 	"aic7901",
@@ -66,10 +66,10 @@ static const u_int num_chip_names = ARRAY_SIZE(ahd_chip_names);
  */
 struct ahd_hard_error_entry {
         uint8_t errno;
-	char *errmesg;
+	const char *errmesg;
 };
 
-static struct ahd_hard_error_entry ahd_hard_errors[] = {
+static const struct ahd_hard_error_entry ahd_hard_errors[] = {
 	{ DSCTMOUT,	"Discard Timer has timed out" },
 	{ ILLOPCODE,	"Illegal Opcode in sequencer program" },
 	{ SQPARERR,	"Sequencer Parity Error" },
@@ -79,7 +79,7 @@ static struct ahd_hard_error_entry ahd_hard_errors[] = {
 };
 static const u_int num_errors = ARRAY_SIZE(ahd_hard_errors);
 
-static struct ahd_phase_table_entry ahd_phase_table[] =
+static const struct ahd_phase_table_entry ahd_phase_table[] =
 {
 	{ P_DATAOUT,	MSG_NOOP,		"in Data-out phase"	},
 	{ P_DATAIN,	MSG_INITIATOR_DET_ERR,	"in Data-in phase"	},
@@ -213,7 +213,7 @@ static void		ahd_dumpseq(struct ahd_softc *ahd);
 #endif
 static void		ahd_loadseq(struct ahd_softc *ahd);
 static int		ahd_check_patch(struct ahd_softc *ahd,
-					struct patch **start_patch,
+					const struct patch **start_patch,
 					u_int start_instr, u_int *skip_addr);
 static u_int		ahd_resolve_seqaddr(struct ahd_softc *ahd,
 					    u_int address);
@@ -254,7 +254,7 @@ static void		ahd_freeze_devq(struct ahd_softc *ahd,
 					struct scb *scb);
 static void		ahd_handle_scb_status(struct ahd_softc *ahd,
 					      struct scb *scb);
-static struct ahd_phase_table_entry* ahd_lookup_phase_entry(int phase);
+static const struct ahd_phase_table_entry* ahd_lookup_phase_entry(int phase);
 static void		ahd_shutdown(void *arg);
 static void		ahd_update_coalescing_values(struct ahd_softc *ahd,
 						     u_int timer,
@@ -266,8 +266,774 @@ static int		ahd_match_scb(struct ahd_softc *ahd, struct scb *scb,
 				      int target, char channel, int lun,
 				      u_int tag, role_t role);
 
-/******************************** Private Inlines *****************************/
+static void		ahd_reset_cmds_pending(struct ahd_softc *ahd);
+
+/*************************** Interrupt Services *******************************/
+static void		ahd_run_qoutfifo(struct ahd_softc *ahd);
+#ifdef AHD_TARGET_MODE
+static void		ahd_run_tqinfifo(struct ahd_softc *ahd, int paused);
+#endif
+static void		ahd_handle_hwerrint(struct ahd_softc *ahd);
+static void		ahd_handle_seqint(struct ahd_softc *ahd, u_int intstat);
+static void		ahd_handle_scsiint(struct ahd_softc *ahd,
+				           u_int intstat);
+
+/************************ Sequencer Execution Control *************************/
+void
+ahd_set_modes(struct ahd_softc *ahd, ahd_mode src, ahd_mode dst)
+{
+	if (ahd->src_mode == src && ahd->dst_mode == dst)
+		return;
+#ifdef AHD_DEBUG
+	if (ahd->src_mode == AHD_MODE_UNKNOWN
+	 || ahd->dst_mode == AHD_MODE_UNKNOWN)
+		panic("Setting mode prior to saving it.\n");
+	if ((ahd_debug & AHD_SHOW_MODEPTR) != 0)
+		printf("%s: Setting mode 0x%x\n", ahd_name(ahd),
+		       ahd_build_mode_state(ahd, src, dst));
+#endif
+	ahd_outb(ahd, MODE_PTR, ahd_build_mode_state(ahd, src, dst));
+	ahd->src_mode = src;
+	ahd->dst_mode = dst;
+}
+
+static void
+ahd_update_modes(struct ahd_softc *ahd)
+{
+	ahd_mode_state mode_ptr;
+	ahd_mode src;
+	ahd_mode dst;
+
+	mode_ptr = ahd_inb(ahd, MODE_PTR);
+#ifdef AHD_DEBUG
+	if ((ahd_debug & AHD_SHOW_MODEPTR) != 0)
+		printf("Reading mode 0x%x\n", mode_ptr);
+#endif
+	ahd_extract_mode_state(ahd, mode_ptr, &src, &dst);
+	ahd_known_modes(ahd, src, dst);
+}
+
+static void
+ahd_assert_modes(struct ahd_softc *ahd, ahd_mode srcmode,
+		 ahd_mode dstmode, const char *file, int line)
+{
+#ifdef AHD_DEBUG
+	if ((srcmode & AHD_MK_MSK(ahd->src_mode)) == 0
+	 || (dstmode & AHD_MK_MSK(ahd->dst_mode)) == 0) {
+		panic("%s:%s:%d: Mode assertion failed.\n",
+		       ahd_name(ahd), file, line);
+	}
+#endif
+}
+
+#define AHD_ASSERT_MODES(ahd, source, dest) \
+	ahd_assert_modes(ahd, source, dest, __FILE__, __LINE__);
+
+ahd_mode_state
+ahd_save_modes(struct ahd_softc *ahd)
+{
+	if (ahd->src_mode == AHD_MODE_UNKNOWN
+	 || ahd->dst_mode == AHD_MODE_UNKNOWN)
+		ahd_update_modes(ahd);
+
+	return (ahd_build_mode_state(ahd, ahd->src_mode, ahd->dst_mode));
+}
+
+void
+ahd_restore_modes(struct ahd_softc *ahd, ahd_mode_state state)
+{
+	ahd_mode src;
+	ahd_mode dst;
+
+	ahd_extract_mode_state(ahd, state, &src, &dst);
+	ahd_set_modes(ahd, src, dst);
+}
+
+/*
+ * Determine whether the sequencer has halted code execution.
+ * Returns non-zero status if the sequencer is stopped.
+ */
+int
+ahd_is_paused(struct ahd_softc *ahd)
+{
+	return ((ahd_inb(ahd, HCNTRL) & PAUSE) != 0);
+}
+
+/*
+ * Request that the sequencer stop and wait, indefinitely, for it
+ * to stop.  The sequencer will only acknowledge that it is paused
+ * once it has reached an instruction boundary and PAUSEDIS is
+ * cleared in the SEQCTL register.  The sequencer may use PAUSEDIS
+ * for critical sections.
+ */
+void
+ahd_pause(struct ahd_softc *ahd)
+{
+	ahd_outb(ahd, HCNTRL, ahd->pause);
+
+	/*
+	 * Since the sequencer can disable pausing in a critical section, we
+	 * must loop until it actually stops.
+	 */
+	while (ahd_is_paused(ahd) == 0)
+		;
+}
+
+/*
+ * Allow the sequencer to continue program execution.
+ * We check here to ensure that no additional interrupt
+ * sources that would cause the sequencer to halt have been
+ * asserted.  If, for example, a SCSI bus reset is detected
+ * while we are fielding a different, pausing, interrupt type,
+ * we don't want to release the sequencer before going back
+ * into our interrupt handler and dealing with this new
+ * condition.
+ */
+void
+ahd_unpause(struct ahd_softc *ahd)
+{
+	/*
+	 * Automatically restore our modes to those saved
+	 * prior to the first change of the mode.
+	 */
+	if (ahd->saved_src_mode != AHD_MODE_UNKNOWN
+	 && ahd->saved_dst_mode != AHD_MODE_UNKNOWN) {
+		if ((ahd->flags & AHD_UPDATE_PEND_CMDS) != 0)
+			ahd_reset_cmds_pending(ahd);
+		ahd_set_modes(ahd, ahd->saved_src_mode, ahd->saved_dst_mode);
+	}
+
+	if ((ahd_inb(ahd, INTSTAT) & ~CMDCMPLT) == 0)
+		ahd_outb(ahd, HCNTRL, ahd->unpause);
+
+	ahd_known_modes(ahd, AHD_MODE_UNKNOWN, AHD_MODE_UNKNOWN);
+}
+
+/*********************** Scatter Gather List Handling *************************/
+void *
+ahd_sg_setup(struct ahd_softc *ahd, struct scb *scb,
+	     void *sgptr, dma_addr_t addr, bus_size_t len, int last)
+{
+	scb->sg_count++;
+	if (sizeof(dma_addr_t) > 4
+	 && (ahd->flags & AHD_64BIT_ADDRESSING) != 0) {
+		struct ahd_dma64_seg *sg;
+
+		sg = (struct ahd_dma64_seg *)sgptr;
+		sg->addr = ahd_htole64(addr);
+		sg->len = ahd_htole32(len | (last ? AHD_DMA_LAST_SEG : 0));
+		return (sg + 1);
+	} else {
+		struct ahd_dma_seg *sg;
 
+		sg = (struct ahd_dma_seg *)sgptr;
+		sg->addr = ahd_htole32(addr & 0xFFFFFFFF);
+		sg->len = ahd_htole32(len | ((addr >> 8) & 0x7F000000)
+				    | (last ? AHD_DMA_LAST_SEG : 0));
+		return (sg + 1);
+	}
+}
+
+static void
+ahd_setup_scb_common(struct ahd_softc *ahd, struct scb *scb)
+{
+	/* XXX Handle target mode SCBs. */
+	scb->crc_retry_count = 0;
+	if ((scb->flags & SCB_PACKETIZED) != 0) {
+		/* XXX what about ACA??  It is type 4, but TAG_TYPE == 0x3. */
+		scb->hscb->task_attribute = scb->hscb->control & SCB_TAG_TYPE;
+	} else {
+		if (ahd_get_transfer_length(scb) & 0x01)
+			scb->hscb->task_attribute = SCB_XFERLEN_ODD;
+		else
+			scb->hscb->task_attribute = 0;
+	}
+
+	if (scb->hscb->cdb_len <= MAX_CDB_LEN_WITH_SENSE_ADDR
+	 || (scb->hscb->cdb_len & SCB_CDB_LEN_PTR) != 0)
+		scb->hscb->shared_data.idata.cdb_plus_saddr.sense_addr =
+		    ahd_htole32(scb->sense_busaddr);
+}
+
+static void
+ahd_setup_data_scb(struct ahd_softc *ahd, struct scb *scb)
+{
+	/*
+	 * Copy the first SG into the "current" data ponter area.
+	 */
+	if ((ahd->flags & AHD_64BIT_ADDRESSING) != 0) {
+		struct ahd_dma64_seg *sg;
+
+		sg = (struct ahd_dma64_seg *)scb->sg_list;
+		scb->hscb->dataptr = sg->addr;
+		scb->hscb->datacnt = sg->len;
+	} else {
+		struct ahd_dma_seg *sg;
+		uint32_t *dataptr_words;
+
+		sg = (struct ahd_dma_seg *)scb->sg_list;
+		dataptr_words = (uint32_t*)&scb->hscb->dataptr;
+		dataptr_words[0] = sg->addr;
+		dataptr_words[1] = 0;
+		if ((ahd->flags & AHD_39BIT_ADDRESSING) != 0) {
+			uint64_t high_addr;
+
+			high_addr = ahd_le32toh(sg->len) & 0x7F000000;
+			scb->hscb->dataptr |= ahd_htole64(high_addr << 8);
+		}
+		scb->hscb->datacnt = sg->len;
+	}
+	/*
+	 * Note where to find the SG entries in bus space.
+	 * We also set the full residual flag which the
+	 * sequencer will clear as soon as a data transfer
+	 * occurs.
+	 */
+	scb->hscb->sgptr = ahd_htole32(scb->sg_list_busaddr|SG_FULL_RESID);
+}
+
+static void
+ahd_setup_noxfer_scb(struct ahd_softc *ahd, struct scb *scb)
+{
+	scb->hscb->sgptr = ahd_htole32(SG_LIST_NULL);
+	scb->hscb->dataptr = 0;
+	scb->hscb->datacnt = 0;
+}
+
+/************************** Memory mapping routines ***************************/
+static void *
+ahd_sg_bus_to_virt(struct ahd_softc *ahd, struct scb *scb, uint32_t sg_busaddr)
+{
+	dma_addr_t sg_offset;
+
+	/* sg_list_phys points to entry 1, not 0 */
+	sg_offset = sg_busaddr - (scb->sg_list_busaddr - ahd_sg_size(ahd));
+	return ((uint8_t *)scb->sg_list + sg_offset);
+}
+
+static uint32_t
+ahd_sg_virt_to_bus(struct ahd_softc *ahd, struct scb *scb, void *sg)
+{
+	dma_addr_t sg_offset;
+
+	/* sg_list_phys points to entry 1, not 0 */
+	sg_offset = ((uint8_t *)sg - (uint8_t *)scb->sg_list)
+		  - ahd_sg_size(ahd);
+
+	return (scb->sg_list_busaddr + sg_offset);
+}
+
+static void
+ahd_sync_scb(struct ahd_softc *ahd, struct scb *scb, int op)
+{
+	ahd_dmamap_sync(ahd, ahd->scb_data.hscb_dmat,
+			scb->hscb_map->dmamap,
+			/*offset*/(uint8_t*)scb->hscb - scb->hscb_map->vaddr,
+			/*len*/sizeof(*scb->hscb), op);
+}
+
+void
+ahd_sync_sglist(struct ahd_softc *ahd, struct scb *scb, int op)
+{
+	if (scb->sg_count == 0)
+		return;
+
+	ahd_dmamap_sync(ahd, ahd->scb_data.sg_dmat,
+			scb->sg_map->dmamap,
+			/*offset*/scb->sg_list_busaddr - ahd_sg_size(ahd),
+			/*len*/ahd_sg_size(ahd) * scb->sg_count, op);
+}
+
+static void
+ahd_sync_sense(struct ahd_softc *ahd, struct scb *scb, int op)
+{
+	ahd_dmamap_sync(ahd, ahd->scb_data.sense_dmat,
+			scb->sense_map->dmamap,
+			/*offset*/scb->sense_busaddr,
+			/*len*/AHD_SENSE_BUFSIZE, op);
+}
+
+#ifdef AHD_TARGET_MODE
+static uint32_t
+ahd_targetcmd_offset(struct ahd_softc *ahd, u_int index)
+{
+	return (((uint8_t *)&ahd->targetcmds[index])
+	       - (uint8_t *)ahd->qoutfifo);
+}
+#endif
+
+/*********************** Miscelaneous Support Functions ***********************/
+/*
+ * Return pointers to the transfer negotiation information
+ * for the specified our_id/remote_id pair.
+ */
+struct ahd_initiator_tinfo *
+ahd_fetch_transinfo(struct ahd_softc *ahd, char channel, u_int our_id,
+		    u_int remote_id, struct ahd_tmode_tstate **tstate)
+{
+	/*
+	 * Transfer data structures are stored from the perspective
+	 * of the target role.  Since the parameters for a connection
+	 * in the initiator role to a given target are the same as
+	 * when the roles are reversed, we pretend we are the target.
+	 */
+	if (channel == 'B')
+		our_id += 8;
+	*tstate = ahd->enabled_targets[our_id];
+	return (&(*tstate)->transinfo[remote_id]);
+}
+
+uint16_t
+ahd_inw(struct ahd_softc *ahd, u_int port)
+{
+	/*
+	 * Read high byte first as some registers increment
+	 * or have other side effects when the low byte is
+	 * read.
+	 */
+	uint16_t r = ahd_inb(ahd, port+1) << 8;
+	return r | ahd_inb(ahd, port);
+}
+
+void
+ahd_outw(struct ahd_softc *ahd, u_int port, u_int value)
+{
+	/*
+	 * Write low byte first to accomodate registers
+	 * such as PRGMCNT where the order maters.
+	 */
+	ahd_outb(ahd, port, value & 0xFF);
+	ahd_outb(ahd, port+1, (value >> 8) & 0xFF);
+}
+
+uint32_t
+ahd_inl(struct ahd_softc *ahd, u_int port)
+{
+	return ((ahd_inb(ahd, port))
+	      | (ahd_inb(ahd, port+1) << 8)
+	      | (ahd_inb(ahd, port+2) << 16)
+	      | (ahd_inb(ahd, port+3) << 24));
+}
+
+void
+ahd_outl(struct ahd_softc *ahd, u_int port, uint32_t value)
+{
+	ahd_outb(ahd, port, (value) & 0xFF);
+	ahd_outb(ahd, port+1, ((value) >> 8) & 0xFF);
+	ahd_outb(ahd, port+2, ((value) >> 16) & 0xFF);
+	ahd_outb(ahd, port+3, ((value) >> 24) & 0xFF);
+}
+
+uint64_t
+ahd_inq(struct ahd_softc *ahd, u_int port)
+{
+	return ((ahd_inb(ahd, port))
+	      | (ahd_inb(ahd, port+1) << 8)
+	      | (ahd_inb(ahd, port+2) << 16)
+	      | (ahd_inb(ahd, port+3) << 24)
+	      | (((uint64_t)ahd_inb(ahd, port+4)) << 32)
+	      | (((uint64_t)ahd_inb(ahd, port+5)) << 40)
+	      | (((uint64_t)ahd_inb(ahd, port+6)) << 48)
+	      | (((uint64_t)ahd_inb(ahd, port+7)) << 56));
+}
+
+void
+ahd_outq(struct ahd_softc *ahd, u_int port, uint64_t value)
+{
+	ahd_outb(ahd, port, value & 0xFF);
+	ahd_outb(ahd, port+1, (value >> 8) & 0xFF);
+	ahd_outb(ahd, port+2, (value >> 16) & 0xFF);
+	ahd_outb(ahd, port+3, (value >> 24) & 0xFF);
+	ahd_outb(ahd, port+4, (value >> 32) & 0xFF);
+	ahd_outb(ahd, port+5, (value >> 40) & 0xFF);
+	ahd_outb(ahd, port+6, (value >> 48) & 0xFF);
+	ahd_outb(ahd, port+7, (value >> 56) & 0xFF);
+}
+
+u_int
+ahd_get_scbptr(struct ahd_softc *ahd)
+{
+	AHD_ASSERT_MODES(ahd, ~(AHD_MODE_UNKNOWN_MSK|AHD_MODE_CFG_MSK),
+			 ~(AHD_MODE_UNKNOWN_MSK|AHD_MODE_CFG_MSK));
+	return (ahd_inb(ahd, SCBPTR) | (ahd_inb(ahd, SCBPTR + 1) << 8));
+}
+
+void
+ahd_set_scbptr(struct ahd_softc *ahd, u_int scbptr)
+{
+	AHD_ASSERT_MODES(ahd, ~(AHD_MODE_UNKNOWN_MSK|AHD_MODE_CFG_MSK),
+			 ~(AHD_MODE_UNKNOWN_MSK|AHD_MODE_CFG_MSK));
+	ahd_outb(ahd, SCBPTR, scbptr & 0xFF);
+	ahd_outb(ahd, SCBPTR+1, (scbptr >> 8) & 0xFF);
+}
+
+#if 0 /* unused */
+static u_int
+ahd_get_hnscb_qoff(struct ahd_softc *ahd)
+{
+	return (ahd_inw_atomic(ahd, HNSCB_QOFF));
+}
+#endif
+
+static void
+ahd_set_hnscb_qoff(struct ahd_softc *ahd, u_int value)
+{
+	ahd_outw_atomic(ahd, HNSCB_QOFF, value);
+}
+
+#if 0 /* unused */
+static u_int
+ahd_get_hescb_qoff(struct ahd_softc *ahd)
+{
+	return (ahd_inb(ahd, HESCB_QOFF));
+}
+#endif
+
+static void
+ahd_set_hescb_qoff(struct ahd_softc *ahd, u_int value)
+{
+	ahd_outb(ahd, HESCB_QOFF, value);
+}
+
+static u_int
+ahd_get_snscb_qoff(struct ahd_softc *ahd)
+{
+	u_int oldvalue;
+
+	AHD_ASSERT_MODES(ahd, AHD_MODE_CCHAN_MSK, AHD_MODE_CCHAN_MSK);
+	oldvalue = ahd_inw(ahd, SNSCB_QOFF);
+	ahd_outw(ahd, SNSCB_QOFF, oldvalue);
+	return (oldvalue);
+}
+
+static void
+ahd_set_snscb_qoff(struct ahd_softc *ahd, u_int value)
+{
+	AHD_ASSERT_MODES(ahd, AHD_MODE_CCHAN_MSK, AHD_MODE_CCHAN_MSK);
+	ahd_outw(ahd, SNSCB_QOFF, value);
+}
+
+#if 0 /* unused */
+static u_int
+ahd_get_sescb_qoff(struct ahd_softc *ahd)
+{
+	AHD_ASSERT_MODES(ahd, AHD_MODE_CCHAN_MSK, AHD_MODE_CCHAN_MSK);
+	return (ahd_inb(ahd, SESCB_QOFF));
+}
+#endif
+
+static void
+ahd_set_sescb_qoff(struct ahd_softc *ahd, u_int value)
+{
+	AHD_ASSERT_MODES(ahd, AHD_MODE_CCHAN_MSK, AHD_MODE_CCHAN_MSK);
+	ahd_outb(ahd, SESCB_QOFF, value);
+}
+
+#if 0 /* unused */
+static u_int
+ahd_get_sdscb_qoff(struct ahd_softc *ahd)
+{
+	AHD_ASSERT_MODES(ahd, AHD_MODE_CCHAN_MSK, AHD_MODE_CCHAN_MSK);
+	return (ahd_inb(ahd, SDSCB_QOFF) | (ahd_inb(ahd, SDSCB_QOFF + 1) << 8));
+}
+#endif
+
+static void
+ahd_set_sdscb_qoff(struct ahd_softc *ahd, u_int value)
+{
+	AHD_ASSERT_MODES(ahd, AHD_MODE_CCHAN_MSK, AHD_MODE_CCHAN_MSK);
+	ahd_outb(ahd, SDSCB_QOFF, value & 0xFF);
+	ahd_outb(ahd, SDSCB_QOFF+1, (value >> 8) & 0xFF);
+}
+
+u_int
+ahd_inb_scbram(struct ahd_softc *ahd, u_int offset)
+{
+	u_int value;
+
+	/*
+	 * Workaround PCI-X Rev A. hardware bug.
+	 * After a host read of SCB memory, the chip
+	 * may become confused into thinking prefetch
+	 * was required.  This starts the discard timer
+	 * running and can cause an unexpected discard
+	 * timer interrupt.  The work around is to read
+	 * a normal register prior to the exhaustion of
+	 * the discard timer.  The mode pointer register
+	 * has no side effects and so serves well for
+	 * this purpose.
+	 *
+	 * Razor #528
+	 */
+	value = ahd_inb(ahd, offset);
+	if ((ahd->bugs & AHD_PCIX_SCBRAM_RD_BUG) != 0)
+		ahd_inb(ahd, MODE_PTR);
+	return (value);
+}
+
+u_int
+ahd_inw_scbram(struct ahd_softc *ahd, u_int offset)
+{
+	return (ahd_inb_scbram(ahd, offset)
+	      | (ahd_inb_scbram(ahd, offset+1) << 8));
+}
+
+static uint32_t
+ahd_inl_scbram(struct ahd_softc *ahd, u_int offset)
+{
+	return (ahd_inw_scbram(ahd, offset)
+	      | (ahd_inw_scbram(ahd, offset+2) << 16));
+}
+
+static uint64_t
+ahd_inq_scbram(struct ahd_softc *ahd, u_int offset)
+{
+	return (ahd_inl_scbram(ahd, offset)
+	      | ((uint64_t)ahd_inl_scbram(ahd, offset+4)) << 32);
+}
+
+struct scb *
+ahd_lookup_scb(struct ahd_softc *ahd, u_int tag)
+{
+	struct scb* scb;
+
+	if (tag >= AHD_SCB_MAX)
+		return (NULL);
+	scb = ahd->scb_data.scbindex[tag];
+	if (scb != NULL)
+		ahd_sync_scb(ahd, scb,
+			     BUS_DMASYNC_POSTREAD|BUS_DMASYNC_POSTWRITE);
+	return (scb);
+}
+
+static void
+ahd_swap_with_next_hscb(struct ahd_softc *ahd, struct scb *scb)
+{
+	struct	 hardware_scb *q_hscb;
+	struct	 map_node *q_hscb_map;
+	uint32_t saved_hscb_busaddr;
+
+	/*
+	 * Our queuing method is a bit tricky.  The card
+	 * knows in advance which HSCB (by address) to download,
+	 * and we can't disappoint it.  To achieve this, the next
+	 * HSCB to download is saved off in ahd->next_queued_hscb.
+	 * When we are called to queue "an arbitrary scb",
+	 * we copy the contents of the incoming HSCB to the one
+	 * the sequencer knows about, swap HSCB pointers and
+	 * finally assign the SCB to the tag indexed location
+	 * in the scb_array.  This makes sure that we can still
+	 * locate the correct SCB by SCB_TAG.
+	 */
+	q_hscb = ahd->next_queued_hscb;
+	q_hscb_map = ahd->next_queued_hscb_map;
+	saved_hscb_busaddr = q_hscb->hscb_busaddr;
+	memcpy(q_hscb, scb->hscb, sizeof(*scb->hscb));
+	q_hscb->hscb_busaddr = saved_hscb_busaddr;
+	q_hscb->next_hscb_busaddr = scb->hscb->hscb_busaddr;
+
+	/* Now swap HSCB pointers. */
+	ahd->next_queued_hscb = scb->hscb;
+	ahd->next_queued_hscb_map = scb->hscb_map;
+	scb->hscb = q_hscb;
+	scb->hscb_map = q_hscb_map;
+
+	/* Now define the mapping from tag to SCB in the scbindex */
+	ahd->scb_data.scbindex[SCB_GET_TAG(scb)] = scb;
+}
+
+/*
+ * Tell the sequencer about a new transaction to execute.
+ */
+void
+ahd_queue_scb(struct ahd_softc *ahd, struct scb *scb)
+{
+	ahd_swap_with_next_hscb(ahd, scb);
+
+	if (SCBID_IS_NULL(SCB_GET_TAG(scb)))
+		panic("Attempt to queue invalid SCB tag %x\n",
+		      SCB_GET_TAG(scb));
+
+	/*
+	 * Keep a history of SCBs we've downloaded in the qinfifo.
+	 */
+	ahd->qinfifo[AHD_QIN_WRAP(ahd->qinfifonext)] = SCB_GET_TAG(scb);
+	ahd->qinfifonext++;
+
+	if (scb->sg_count != 0)
+		ahd_setup_data_scb(ahd, scb);
+	else
+		ahd_setup_noxfer_scb(ahd, scb);
+	ahd_setup_scb_common(ahd, scb);
+
+	/*
+	 * Make sure our data is consistent from the
+	 * perspective of the adapter.
+	 */
+	ahd_sync_scb(ahd, scb, BUS_DMASYNC_PREREAD|BUS_DMASYNC_PREWRITE);
+
+#ifdef AHD_DEBUG
+	if ((ahd_debug & AHD_SHOW_QUEUE) != 0) {
+		uint64_t host_dataptr;
+
+		host_dataptr = ahd_le64toh(scb->hscb->dataptr);
+		printf("%s: Queueing SCB %d:0x%x bus addr 0x%x - 0x%x%x/0x%x\n",
+		       ahd_name(ahd),
+		       SCB_GET_TAG(scb), scb->hscb->scsiid,
+		       ahd_le32toh(scb->hscb->hscb_busaddr),
+		       (u_int)((host_dataptr >> 32) & 0xFFFFFFFF),
+		       (u_int)(host_dataptr & 0xFFFFFFFF),
+		       ahd_le32toh(scb->hscb->datacnt));
+	}
+#endif
+	/* Tell the adapter about the newly queued SCB */
+	ahd_set_hnscb_qoff(ahd, ahd->qinfifonext);
+}
+
+/************************** Interrupt Processing ******************************/
+static void
+ahd_sync_qoutfifo(struct ahd_softc *ahd, int op)
+{
+	ahd_dmamap_sync(ahd, ahd->shared_data_dmat, ahd->shared_data_map.dmamap,
+			/*offset*/0,
+			/*len*/AHD_SCB_MAX * sizeof(struct ahd_completion), op);
+}
+
+static void
+ahd_sync_tqinfifo(struct ahd_softc *ahd, int op)
+{
+#ifdef AHD_TARGET_MODE
+	if ((ahd->flags & AHD_TARGETROLE) != 0) {
+		ahd_dmamap_sync(ahd, ahd->shared_data_dmat,
+				ahd->shared_data_map.dmamap,
+				ahd_targetcmd_offset(ahd, 0),
+				sizeof(struct target_cmd) * AHD_TMODE_CMDS,
+				op);
+	}
+#endif
+}
+
+/*
+ * See if the firmware has posted any completed commands
+ * into our in-core command complete fifos.
+ */
+#define AHD_RUN_QOUTFIFO 0x1
+#define AHD_RUN_TQINFIFO 0x2
+static u_int
+ahd_check_cmdcmpltqueues(struct ahd_softc *ahd)
+{
+	u_int retval;
+
+	retval = 0;
+	ahd_dmamap_sync(ahd, ahd->shared_data_dmat, ahd->shared_data_map.dmamap,
+			/*offset*/ahd->qoutfifonext * sizeof(*ahd->qoutfifo),
+			/*len*/sizeof(*ahd->qoutfifo), BUS_DMASYNC_POSTREAD);
+	if (ahd->qoutfifo[ahd->qoutfifonext].valid_tag
+	  == ahd->qoutfifonext_valid_tag)
+		retval |= AHD_RUN_QOUTFIFO;
+#ifdef AHD_TARGET_MODE
+	if ((ahd->flags & AHD_TARGETROLE) != 0
+	 && (ahd->flags & AHD_TQINFIFO_BLOCKED) == 0) {
+		ahd_dmamap_sync(ahd, ahd->shared_data_dmat,
+				ahd->shared_data_map.dmamap,
+				ahd_targetcmd_offset(ahd, ahd->tqinfifofnext),
+				/*len*/sizeof(struct target_cmd),
+				BUS_DMASYNC_POSTREAD);
+		if (ahd->targetcmds[ahd->tqinfifonext].cmd_valid != 0)
+			retval |= AHD_RUN_TQINFIFO;
+	}
+#endif
+	return (retval);
+}
+
+/*
+ * Catch an interrupt from the adapter
+ */
+int
+ahd_intr(struct ahd_softc *ahd)
+{
+	u_int	intstat;
+
+	if ((ahd->pause & INTEN) == 0) {
+		/*
+		 * Our interrupt is not enabled on the chip
+		 * and may be disabled for re-entrancy reasons,
+		 * so just return.  This is likely just a shared
+		 * interrupt.
+		 */
+		return (0);
+	}
+
+	/*
+	 * Instead of directly reading the interrupt status register,
+	 * infer the cause of the interrupt by checking our in-core
+	 * completion queues.  This avoids a costly PCI bus read in
+	 * most cases.
+	 */
+	if ((ahd->flags & AHD_ALL_INTERRUPTS) == 0
+	 && (ahd_check_cmdcmpltqueues(ahd) != 0))
+		intstat = CMDCMPLT;
+	else
+		intstat = ahd_inb(ahd, INTSTAT);
+
+	if ((intstat & INT_PEND) == 0)
+		return (0);
+
+	if (intstat & CMDCMPLT) {
+		ahd_outb(ahd, CLRINT, CLRCMDINT);
+
+		/*
+		 * Ensure that the chip sees that we've cleared
+		 * this interrupt before we walk the output fifo.
+		 * Otherwise, we may, due to posted bus writes,
+		 * clear the interrupt after we finish the scan,
+		 * and after the sequencer has added new entries
+		 * and asserted the interrupt again.
+		 */
+		if ((ahd->bugs & AHD_INTCOLLISION_BUG) != 0) {
+			if (ahd_is_paused(ahd)) {
+				/*
+				 * Potentially lost SEQINT.
+				 * If SEQINTCODE is non-zero,
+				 * simulate the SEQINT.
+				 */
+				if (ahd_inb(ahd, SEQINTCODE) != NO_SEQINT)
+					intstat |= SEQINT;
+			}
+		} else {
+			ahd_flush_device_writes(ahd);
+		}
+		ahd_run_qoutfifo(ahd);
+		ahd->cmdcmplt_counts[ahd->cmdcmplt_bucket]++;
+		ahd->cmdcmplt_total++;
+#ifdef AHD_TARGET_MODE
+		if ((ahd->flags & AHD_TARGETROLE) != 0)
+			ahd_run_tqinfifo(ahd, /*paused*/FALSE);
+#endif
+	}
+
+	/*
+	 * Handle statuses that may invalidate our cached
+	 * copy of INTSTAT separately.
+	 */
+	if (intstat == 0xFF && (ahd->features & AHD_REMOVABLE) != 0) {
+		/* Hot eject.  Do nothing */
+	} else if (intstat & HWERRINT) {
+		ahd_handle_hwerrint(ahd);
+	} else if ((intstat & (PCIINT|SPLTINT)) != 0) {
+		ahd->bus_intr(ahd);
+	} else {
+
+		if ((intstat & SEQINT) != 0)
+			ahd_handle_seqint(ahd, intstat);
+
+		if ((intstat & SCSIINT) != 0)
+			ahd_handle_scsiint(ahd, intstat);
+	}
+	return (1);
+}
+
+/******************************** Private Inlines *****************************/
 static __inline void
 ahd_assert_atn(struct ahd_softc *ahd)
 {
@@ -280,7 +1046,7 @@ ahd_assert_atn(struct ahd_softc *ahd)
  * are currently in a packetized transfer.  We could
  * just as easily be sending or receiving a message.
  */
-static __inline int
+static int
 ahd_currently_packetized(struct ahd_softc *ahd)
 {
 	ahd_mode_state	 saved_modes;
@@ -896,7 +1662,7 @@ ahd_run_data_fifo(struct ahd_softc *ahd, struct scb *scb)
  * a copy of the first byte (little endian) of the sgptr
  * hscb field.
  */
-void
+static void
 ahd_run_qoutfifo(struct ahd_softc *ahd)
 {
 	struct ahd_completion *completion;
@@ -935,7 +1701,7 @@ ahd_run_qoutfifo(struct ahd_softc *ahd)
 }
 
 /************************* Interrupt Handling *********************************/
-void
+static void
 ahd_handle_hwerrint(struct ahd_softc *ahd)
 {
 	/*
@@ -1009,7 +1775,7 @@ ahd_dump_sglist(struct scb *scb)
 }
 #endif  /*  AHD_DEBUG  */
 
-void
+static void
 ahd_handle_seqint(struct ahd_softc *ahd, u_int intstat)
 {
 	u_int seqintcode;
@@ -1621,7 +2387,7 @@ ahd_handle_seqint(struct ahd_softc *ahd, u_int intstat)
 	ahd_unpause(ahd);
 }
 
-void
+static void
 ahd_handle_scsiint(struct ahd_softc *ahd, u_int intstat)
 {
 	struct scb	*scb;
@@ -3571,11 +4337,11 @@ ahd_print_devinfo(struct ahd_softc *ahd, struct ahd_devinfo *devinfo)
 	       devinfo->target, devinfo->lun);
 }
 
-static struct ahd_phase_table_entry*
+static const struct ahd_phase_table_entry*
 ahd_lookup_phase_entry(int phase)
 {
-	struct ahd_phase_table_entry *entry;
-	struct ahd_phase_table_entry *last_entry;
+	const struct ahd_phase_table_entry *entry;
+	const struct ahd_phase_table_entry *last_entry;
 
 	/*
 	 * num_phases doesn't include the default entry which
@@ -3941,7 +4707,7 @@ ahd_clear_msg_state(struct ahd_softc *ahd)
  */
 static void
 ahd_handle_message_phase(struct ahd_softc *ahd)
-{ 
+{
 	struct	ahd_devinfo devinfo;
 	u_int	bus_phase;
 	int	end_session;
@@ -5983,8 +6749,7 @@ ahd_get_scb(struct ahd_softc *ahd, u_int col_idx)
  */
 void
 ahd_free_scb(struct ahd_softc *ahd, struct scb *scb)
-{       
-
+{
 	/* Clean up for the next user */
 	scb->flags = SCB_FLAG_NONE;
 	scb->hscb->control = 0;
@@ -6272,6 +7037,24 @@ static const char *termstat_strings[] = {
 	"Not Configured"
 };
 
+/***************************** Timer Facilities *******************************/
+#define ahd_timer_init init_timer
+#define ahd_timer_stop del_timer_sync
+typedef void ahd_linux_callback_t (u_long);
+
+static void
+ahd_timer_reset(ahd_timer_t *timer, int usec, ahd_callback_t *func, void *arg)
+{
+	struct ahd_softc *ahd;
+
+	ahd = (struct ahd_softc *)arg;
+	del_timer(timer);
+	timer->data = (u_long)arg;
+	timer->expires = jiffies + (usec * HZ)/1000000;
+	timer->function = (ahd_linux_callback_t*)func;
+	add_timer(timer);
+}
+
 /*
  * Start the board, ready for normal operation
  */
@@ -7370,7 +8153,7 @@ ahd_qinfifo_count(struct ahd_softc *ahd)
 		      + ARRAY_SIZE(ahd->qinfifo) - wrap_qinpos);
 }
 
-void
+static void
 ahd_reset_cmds_pending(struct ahd_softc *ahd)
 {
 	struct		scb *scb;
@@ -8571,7 +9354,7 @@ ahd_loadseq(struct ahd_softc *ahd)
 	struct	cs cs_table[num_critical_sections];
 	u_int	begin_set[num_critical_sections];
 	u_int	end_set[num_critical_sections];
-	struct	patch *cur_patch;
+	const struct patch *cur_patch;
 	u_int	cs_count;
 	u_int	cur_cs;
 	u_int	i;
@@ -8726,11 +9509,11 @@ ahd_loadseq(struct ahd_softc *ahd)
 }
 
 static int
-ahd_check_patch(struct ahd_softc *ahd, struct patch **start_patch,
+ahd_check_patch(struct ahd_softc *ahd, const struct patch **start_patch,
 		u_int start_instr, u_int *skip_addr)
 {
-	struct	patch *cur_patch;
-	struct	patch *last_patch;
+	const struct patch *cur_patch;
+	const struct patch *last_patch;
 	u_int	num_patches;
 
 	num_patches = ARRAY_SIZE(patches);
@@ -8764,7 +9547,7 @@ ahd_check_patch(struct ahd_softc *ahd, struct patch **start_patch,
 static u_int
 ahd_resolve_seqaddr(struct ahd_softc *ahd, u_int address)
 {
-	struct patch *cur_patch;
+	const struct patch *cur_patch;
 	int address_offset;
 	u_int skip_addr;
 	u_int i;
@@ -8895,7 +9678,7 @@ ahd_probe_stack_size(struct ahd_softc *ahd)
 }
 
 int
-ahd_print_register(ahd_reg_parse_entry_t *table, u_int num_entries,
+ahd_print_register(const ahd_reg_parse_entry_t *table, u_int num_entries,
 		   const char *name, u_int address, u_int value,
 		   u_int *cur_column, u_int wrap_point)
 {
@@ -9886,7 +10669,7 @@ ahd_update_scsiid(struct ahd_softc *ahd, u_int targid_mask)
 #endif
 }
 
-void
+static void
 ahd_run_tqinfifo(struct ahd_softc *ahd, int paused)
 {
 	struct target_cmd *cmd;
diff --git a/trunk/drivers/scsi/aic7xxx/aic79xx_inline.h b/trunk/drivers/scsi/aic7xxx/aic79xx_inline.h
index 45e55575a0fa..5f12cf9d99d0 100644
--- a/trunk/drivers/scsi/aic7xxx/aic79xx_inline.h
+++ b/trunk/drivers/scsi/aic7xxx/aic79xx_inline.h
@@ -63,18 +63,15 @@ static __inline ahd_mode_state ahd_build_mode_state(struct ahd_softc *ahd,
 static __inline void ahd_extract_mode_state(struct ahd_softc *ahd,
 					    ahd_mode_state state,
 					    ahd_mode *src, ahd_mode *dst);
-static __inline void ahd_set_modes(struct ahd_softc *ahd, ahd_mode src,
-				   ahd_mode dst);
-static __inline void ahd_update_modes(struct ahd_softc *ahd);
-static __inline void ahd_assert_modes(struct ahd_softc *ahd, ahd_mode srcmode,
-				      ahd_mode dstmode, const char *file,
-				      int line);
-static __inline ahd_mode_state ahd_save_modes(struct ahd_softc *ahd);
-static __inline void ahd_restore_modes(struct ahd_softc *ahd,
-				       ahd_mode_state state);
-static __inline int  ahd_is_paused(struct ahd_softc *ahd);
-static __inline void ahd_pause(struct ahd_softc *ahd);
-static __inline void ahd_unpause(struct ahd_softc *ahd);
+
+void ahd_set_modes(struct ahd_softc *ahd, ahd_mode src,
+		   ahd_mode dst);
+ahd_mode_state ahd_save_modes(struct ahd_softc *ahd);
+void ahd_restore_modes(struct ahd_softc *ahd,
+		       ahd_mode_state state);
+int  ahd_is_paused(struct ahd_softc *ahd);
+void ahd_pause(struct ahd_softc *ahd);
+void ahd_unpause(struct ahd_softc *ahd);
 
 static __inline void
 ahd_known_modes(struct ahd_softc *ahd, ahd_mode src, ahd_mode dst)
@@ -99,256 +96,16 @@ ahd_extract_mode_state(struct ahd_softc *ahd, ahd_mode_state state,
 	*dst = (state & DST_MODE) >> DST_MODE_SHIFT;
 }
 
-static __inline void
-ahd_set_modes(struct ahd_softc *ahd, ahd_mode src, ahd_mode dst)
-{
-	if (ahd->src_mode == src && ahd->dst_mode == dst)
-		return;
-#ifdef AHD_DEBUG
-	if (ahd->src_mode == AHD_MODE_UNKNOWN
-	 || ahd->dst_mode == AHD_MODE_UNKNOWN)
-		panic("Setting mode prior to saving it.\n");
-	if ((ahd_debug & AHD_SHOW_MODEPTR) != 0)
-		printf("%s: Setting mode 0x%x\n", ahd_name(ahd),
-		       ahd_build_mode_state(ahd, src, dst));
-#endif
-	ahd_outb(ahd, MODE_PTR, ahd_build_mode_state(ahd, src, dst));
-	ahd->src_mode = src;
-	ahd->dst_mode = dst;
-}
-
-static __inline void
-ahd_update_modes(struct ahd_softc *ahd)
-{
-	ahd_mode_state mode_ptr;
-	ahd_mode src;
-	ahd_mode dst;
-
-	mode_ptr = ahd_inb(ahd, MODE_PTR);
-#ifdef AHD_DEBUG
-	if ((ahd_debug & AHD_SHOW_MODEPTR) != 0)
-		printf("Reading mode 0x%x\n", mode_ptr);
-#endif
-	ahd_extract_mode_state(ahd, mode_ptr, &src, &dst);
-	ahd_known_modes(ahd, src, dst);
-}
-
-static __inline void
-ahd_assert_modes(struct ahd_softc *ahd, ahd_mode srcmode,
-		 ahd_mode dstmode, const char *file, int line)
-{
-#ifdef AHD_DEBUG
-	if ((srcmode & AHD_MK_MSK(ahd->src_mode)) == 0
-	 || (dstmode & AHD_MK_MSK(ahd->dst_mode)) == 0) {
-		panic("%s:%s:%d: Mode assertion failed.\n",
-		       ahd_name(ahd), file, line);
-	}
-#endif
-}
-
-static __inline ahd_mode_state
-ahd_save_modes(struct ahd_softc *ahd)
-{
-	if (ahd->src_mode == AHD_MODE_UNKNOWN
-	 || ahd->dst_mode == AHD_MODE_UNKNOWN)
-		ahd_update_modes(ahd);
-
-	return (ahd_build_mode_state(ahd, ahd->src_mode, ahd->dst_mode));
-}
-
-static __inline void
-ahd_restore_modes(struct ahd_softc *ahd, ahd_mode_state state)
-{
-	ahd_mode src;
-	ahd_mode dst;
-
-	ahd_extract_mode_state(ahd, state, &src, &dst);
-	ahd_set_modes(ahd, src, dst);
-}
-
-#define AHD_ASSERT_MODES(ahd, source, dest) \
-	ahd_assert_modes(ahd, source, dest, __FILE__, __LINE__);
-
-/*
- * Determine whether the sequencer has halted code execution.
- * Returns non-zero status if the sequencer is stopped.
- */
-static __inline int
-ahd_is_paused(struct ahd_softc *ahd)
-{
-	return ((ahd_inb(ahd, HCNTRL) & PAUSE) != 0);
-}
-
-/*
- * Request that the sequencer stop and wait, indefinitely, for it
- * to stop.  The sequencer will only acknowledge that it is paused
- * once it has reached an instruction boundary and PAUSEDIS is
- * cleared in the SEQCTL register.  The sequencer may use PAUSEDIS
- * for critical sections.
- */
-static __inline void
-ahd_pause(struct ahd_softc *ahd)
-{
-	ahd_outb(ahd, HCNTRL, ahd->pause);
-
-	/*
-	 * Since the sequencer can disable pausing in a critical section, we
-	 * must loop until it actually stops.
-	 */
-	while (ahd_is_paused(ahd) == 0)
-		;
-}
-
-/*
- * Allow the sequencer to continue program execution.
- * We check here to ensure that no additional interrupt
- * sources that would cause the sequencer to halt have been
- * asserted.  If, for example, a SCSI bus reset is detected
- * while we are fielding a different, pausing, interrupt type,
- * we don't want to release the sequencer before going back
- * into our interrupt handler and dealing with this new
- * condition.
- */
-static __inline void
-ahd_unpause(struct ahd_softc *ahd)
-{
-	/*
-	 * Automatically restore our modes to those saved
-	 * prior to the first change of the mode.
-	 */
-	if (ahd->saved_src_mode != AHD_MODE_UNKNOWN
-	 && ahd->saved_dst_mode != AHD_MODE_UNKNOWN) {
-		if ((ahd->flags & AHD_UPDATE_PEND_CMDS) != 0)
-			ahd_reset_cmds_pending(ahd);
-		ahd_set_modes(ahd, ahd->saved_src_mode, ahd->saved_dst_mode);
-	}
-
-	if ((ahd_inb(ahd, INTSTAT) & ~CMDCMPLT) == 0)
-		ahd_outb(ahd, HCNTRL, ahd->unpause);
-
-	ahd_known_modes(ahd, AHD_MODE_UNKNOWN, AHD_MODE_UNKNOWN);
-}
-
 /*********************** Scatter Gather List Handling *************************/
-static __inline void	*ahd_sg_setup(struct ahd_softc *ahd, struct scb *scb,
-				      void *sgptr, dma_addr_t addr,
-				      bus_size_t len, int last);
-static __inline void	 ahd_setup_scb_common(struct ahd_softc *ahd,
-					      struct scb *scb);
-static __inline void	 ahd_setup_data_scb(struct ahd_softc *ahd,
-					    struct scb *scb);
-static __inline void	 ahd_setup_noxfer_scb(struct ahd_softc *ahd,
-					      struct scb *scb);
-
-static __inline void *
-ahd_sg_setup(struct ahd_softc *ahd, struct scb *scb,
-	     void *sgptr, dma_addr_t addr, bus_size_t len, int last)
-{
-	scb->sg_count++;
-	if (sizeof(dma_addr_t) > 4
-	 && (ahd->flags & AHD_64BIT_ADDRESSING) != 0) {
-		struct ahd_dma64_seg *sg;
-
-		sg = (struct ahd_dma64_seg *)sgptr;
-		sg->addr = ahd_htole64(addr);
-		sg->len = ahd_htole32(len | (last ? AHD_DMA_LAST_SEG : 0));
-		return (sg + 1);
-	} else {
-		struct ahd_dma_seg *sg;
-
-		sg = (struct ahd_dma_seg *)sgptr;
-		sg->addr = ahd_htole32(addr & 0xFFFFFFFF);
-		sg->len = ahd_htole32(len | ((addr >> 8) & 0x7F000000)
-				    | (last ? AHD_DMA_LAST_SEG : 0));
-		return (sg + 1);
-	}
-}
-
-static __inline void
-ahd_setup_scb_common(struct ahd_softc *ahd, struct scb *scb)
-{
-	/* XXX Handle target mode SCBs. */
-	scb->crc_retry_count = 0;
-	if ((scb->flags & SCB_PACKETIZED) != 0) {
-		/* XXX what about ACA??  It is type 4, but TAG_TYPE == 0x3. */
-		scb->hscb->task_attribute = scb->hscb->control & SCB_TAG_TYPE;
-	} else {
-		if (ahd_get_transfer_length(scb) & 0x01)
-			scb->hscb->task_attribute = SCB_XFERLEN_ODD;
-		else
-			scb->hscb->task_attribute = 0;
-	}
-
-	if (scb->hscb->cdb_len <= MAX_CDB_LEN_WITH_SENSE_ADDR
-	 || (scb->hscb->cdb_len & SCB_CDB_LEN_PTR) != 0)
-		scb->hscb->shared_data.idata.cdb_plus_saddr.sense_addr =
-		    ahd_htole32(scb->sense_busaddr);
-}
-
-static __inline void
-ahd_setup_data_scb(struct ahd_softc *ahd, struct scb *scb)
-{
-	/*
-	 * Copy the first SG into the "current" data ponter area.
-	 */
-	if ((ahd->flags & AHD_64BIT_ADDRESSING) != 0) {
-		struct ahd_dma64_seg *sg;
-
-		sg = (struct ahd_dma64_seg *)scb->sg_list;
-		scb->hscb->dataptr = sg->addr;
-		scb->hscb->datacnt = sg->len;
-	} else {
-		struct ahd_dma_seg *sg;
-		uint32_t *dataptr_words;
-
-		sg = (struct ahd_dma_seg *)scb->sg_list;
-		dataptr_words = (uint32_t*)&scb->hscb->dataptr;
-		dataptr_words[0] = sg->addr;
-		dataptr_words[1] = 0;
-		if ((ahd->flags & AHD_39BIT_ADDRESSING) != 0) {
-			uint64_t high_addr;
-
-			high_addr = ahd_le32toh(sg->len) & 0x7F000000;
-			scb->hscb->dataptr |= ahd_htole64(high_addr << 8);
-		}
-		scb->hscb->datacnt = sg->len;
-	}
-	/*
-	 * Note where to find the SG entries in bus space.
-	 * We also set the full residual flag which the 
-	 * sequencer will clear as soon as a data transfer
-	 * occurs.
-	 */
-	scb->hscb->sgptr = ahd_htole32(scb->sg_list_busaddr|SG_FULL_RESID);
-}
-
-static __inline void
-ahd_setup_noxfer_scb(struct ahd_softc *ahd, struct scb *scb)
-{
-	scb->hscb->sgptr = ahd_htole32(SG_LIST_NULL);
-	scb->hscb->dataptr = 0;
-	scb->hscb->datacnt = 0;
-}
+void	*ahd_sg_setup(struct ahd_softc *ahd, struct scb *scb,
+		      void *sgptr, dma_addr_t addr,
+		      bus_size_t len, int last);
 
 /************************** Memory mapping routines ***************************/
 static __inline size_t	ahd_sg_size(struct ahd_softc *ahd);
-static __inline void *
-			ahd_sg_bus_to_virt(struct ahd_softc *ahd,
-					   struct scb *scb,
-					   uint32_t sg_busaddr);
-static __inline uint32_t
-			ahd_sg_virt_to_bus(struct ahd_softc *ahd,
-					   struct scb *scb,
-					   void *sg);
-static __inline void	ahd_sync_scb(struct ahd_softc *ahd,
-				     struct scb *scb, int op);
-static __inline void	ahd_sync_sglist(struct ahd_softc *ahd,
-					struct scb *scb, int op);
-static __inline void	ahd_sync_sense(struct ahd_softc *ahd,
-				       struct scb *scb, int op);
-static __inline uint32_t
-			ahd_targetcmd_offset(struct ahd_softc *ahd,
-					     u_int index);
+
+void	ahd_sync_sglist(struct ahd_softc *ahd,
+			struct scb *scb, int op);
 
 static __inline size_t
 ahd_sg_size(struct ahd_softc *ahd)
@@ -358,104 +115,32 @@ ahd_sg_size(struct ahd_softc *ahd)
 	return (sizeof(struct ahd_dma_seg));
 }
 
-static __inline void *
-ahd_sg_bus_to_virt(struct ahd_softc *ahd, struct scb *scb, uint32_t sg_busaddr)
-{
-	dma_addr_t sg_offset;
-
-	/* sg_list_phys points to entry 1, not 0 */
-	sg_offset = sg_busaddr - (scb->sg_list_busaddr - ahd_sg_size(ahd));
-	return ((uint8_t *)scb->sg_list + sg_offset);
-}
-
-static __inline uint32_t
-ahd_sg_virt_to_bus(struct ahd_softc *ahd, struct scb *scb, void *sg)
-{
-	dma_addr_t sg_offset;
-
-	/* sg_list_phys points to entry 1, not 0 */
-	sg_offset = ((uint8_t *)sg - (uint8_t *)scb->sg_list)
-		  - ahd_sg_size(ahd);
-
-	return (scb->sg_list_busaddr + sg_offset);
-}
-
-static __inline void
-ahd_sync_scb(struct ahd_softc *ahd, struct scb *scb, int op)
-{
-	ahd_dmamap_sync(ahd, ahd->scb_data.hscb_dmat,
-			scb->hscb_map->dmamap,
-			/*offset*/(uint8_t*)scb->hscb - scb->hscb_map->vaddr,
-			/*len*/sizeof(*scb->hscb), op);
-}
-
-static __inline void
-ahd_sync_sglist(struct ahd_softc *ahd, struct scb *scb, int op)
-{
-	if (scb->sg_count == 0)
-		return;
-
-	ahd_dmamap_sync(ahd, ahd->scb_data.sg_dmat,
-			scb->sg_map->dmamap,
-			/*offset*/scb->sg_list_busaddr - ahd_sg_size(ahd),
-			/*len*/ahd_sg_size(ahd) * scb->sg_count, op);
-}
-
-static __inline void
-ahd_sync_sense(struct ahd_softc *ahd, struct scb *scb, int op)
-{
-	ahd_dmamap_sync(ahd, ahd->scb_data.sense_dmat,
-			scb->sense_map->dmamap,
-			/*offset*/scb->sense_busaddr,
-			/*len*/AHD_SENSE_BUFSIZE, op);
-}
-
-static __inline uint32_t
-ahd_targetcmd_offset(struct ahd_softc *ahd, u_int index)
-{
-	return (((uint8_t *)&ahd->targetcmds[index])
-	       - (uint8_t *)ahd->qoutfifo);
-}
-
 /*********************** Miscellaneous Support Functions ***********************/
-static __inline struct ahd_initiator_tinfo *
-			ahd_fetch_transinfo(struct ahd_softc *ahd,
-					    char channel, u_int our_id,
-					    u_int remote_id,
-					    struct ahd_tmode_tstate **tstate);
-static __inline uint16_t
-			ahd_inw(struct ahd_softc *ahd, u_int port);
-static __inline void	ahd_outw(struct ahd_softc *ahd, u_int port,
-				 u_int value);
-static __inline uint32_t
-			ahd_inl(struct ahd_softc *ahd, u_int port);
-static __inline void	ahd_outl(struct ahd_softc *ahd, u_int port,
-				 uint32_t value);
-static __inline uint64_t
-			ahd_inq(struct ahd_softc *ahd, u_int port);
-static __inline void	ahd_outq(struct ahd_softc *ahd, u_int port,
-				 uint64_t value);
-static __inline u_int	ahd_get_scbptr(struct ahd_softc *ahd);
-static __inline void	ahd_set_scbptr(struct ahd_softc *ahd, u_int scbptr);
-static __inline u_int	ahd_get_hnscb_qoff(struct ahd_softc *ahd);
-static __inline void	ahd_set_hnscb_qoff(struct ahd_softc *ahd, u_int value);
-static __inline u_int	ahd_get_hescb_qoff(struct ahd_softc *ahd);
-static __inline void	ahd_set_hescb_qoff(struct ahd_softc *ahd, u_int value);
-static __inline u_int	ahd_get_snscb_qoff(struct ahd_softc *ahd);
-static __inline void	ahd_set_snscb_qoff(struct ahd_softc *ahd, u_int value);
-static __inline u_int	ahd_get_sescb_qoff(struct ahd_softc *ahd);
-static __inline void	ahd_set_sescb_qoff(struct ahd_softc *ahd, u_int value);
-static __inline u_int	ahd_get_sdscb_qoff(struct ahd_softc *ahd);
-static __inline void	ahd_set_sdscb_qoff(struct ahd_softc *ahd, u_int value);
-static __inline u_int	ahd_inb_scbram(struct ahd_softc *ahd, u_int offset);
-static __inline u_int	ahd_inw_scbram(struct ahd_softc *ahd, u_int offset);
-static __inline uint32_t
-			ahd_inl_scbram(struct ahd_softc *ahd, u_int offset);
-static __inline uint64_t
-			ahd_inq_scbram(struct ahd_softc *ahd, u_int offset);
-static __inline void	ahd_swap_with_next_hscb(struct ahd_softc *ahd,
-						struct scb *scb);
-static __inline void	ahd_queue_scb(struct ahd_softc *ahd, struct scb *scb);
+struct ahd_initiator_tinfo *
+	ahd_fetch_transinfo(struct ahd_softc *ahd,
+			    char channel, u_int our_id,
+			    u_int remote_id,
+			    struct ahd_tmode_tstate **tstate);
+uint16_t
+	ahd_inw(struct ahd_softc *ahd, u_int port);
+void	ahd_outw(struct ahd_softc *ahd, u_int port,
+		 u_int value);
+uint32_t
+	ahd_inl(struct ahd_softc *ahd, u_int port);
+void	ahd_outl(struct ahd_softc *ahd, u_int port,
+		 uint32_t value);
+uint64_t
+	ahd_inq(struct ahd_softc *ahd, u_int port);
+void	ahd_outq(struct ahd_softc *ahd, u_int port,
+		 uint64_t value);
+u_int	ahd_get_scbptr(struct ahd_softc *ahd);
+void	ahd_set_scbptr(struct ahd_softc *ahd, u_int scbptr);
+u_int	ahd_inb_scbram(struct ahd_softc *ahd, u_int offset);
+u_int	ahd_inw_scbram(struct ahd_softc *ahd, u_int offset);
+struct scb *
+	ahd_lookup_scb(struct ahd_softc *ahd, u_int tag);
+void	ahd_queue_scb(struct ahd_softc *ahd, struct scb *scb);
+
 static __inline uint8_t *
 			ahd_get_sense_buf(struct ahd_softc *ahd,
 					  struct scb *scb);
@@ -463,25 +148,7 @@ static __inline uint32_t
 			ahd_get_sense_bufaddr(struct ahd_softc *ahd,
 					      struct scb *scb);
 
-/*
- * Return pointers to the transfer negotiation information
- * for the specified our_id/remote_id pair.
- */
-static __inline struct ahd_initiator_tinfo *
-ahd_fetch_transinfo(struct ahd_softc *ahd, char channel, u_int our_id,
-		    u_int remote_id, struct ahd_tmode_tstate **tstate)
-{
-	/*
-	 * Transfer data structures are stored from the perspective
-	 * of the target role.  Since the parameters for a connection
-	 * in the initiator role to a given target are the same as
-	 * when the roles are reversed, we pretend we are the target.
-	 */
-	if (channel == 'B')
-		our_id += 8;
-	*tstate = ahd->enabled_targets[our_id];
-	return (&(*tstate)->transinfo[remote_id]);
-}
+#if 0 /* unused */
 
 #define AHD_COPY_COL_IDX(dst, src)				\
 do {								\
@@ -489,304 +156,7 @@ do {								\
 	dst->hscb->lun = src->hscb->lun;			\
 } while (0)
 
-static __inline uint16_t
-ahd_inw(struct ahd_softc *ahd, u_int port)
-{
-	/*
-	 * Read high byte first as some registers increment
-	 * or have other side effects when the low byte is
-	 * read.
-	 */
-	uint16_t r = ahd_inb(ahd, port+1) << 8;
-	return r | ahd_inb(ahd, port);
-}
-
-static __inline void
-ahd_outw(struct ahd_softc *ahd, u_int port, u_int value)
-{
-	/*
-	 * Write low byte first to accomodate registers
-	 * such as PRGMCNT where the order maters.
-	 */
-	ahd_outb(ahd, port, value & 0xFF);
-	ahd_outb(ahd, port+1, (value >> 8) & 0xFF);
-}
-
-static __inline uint32_t
-ahd_inl(struct ahd_softc *ahd, u_int port)
-{
-	return ((ahd_inb(ahd, port))
-	      | (ahd_inb(ahd, port+1) << 8)
-	      | (ahd_inb(ahd, port+2) << 16)
-	      | (ahd_inb(ahd, port+3) << 24));
-}
-
-static __inline void
-ahd_outl(struct ahd_softc *ahd, u_int port, uint32_t value)
-{
-	ahd_outb(ahd, port, (value) & 0xFF);
-	ahd_outb(ahd, port+1, ((value) >> 8) & 0xFF);
-	ahd_outb(ahd, port+2, ((value) >> 16) & 0xFF);
-	ahd_outb(ahd, port+3, ((value) >> 24) & 0xFF);
-}
-
-static __inline uint64_t
-ahd_inq(struct ahd_softc *ahd, u_int port)
-{
-	return ((ahd_inb(ahd, port))
-	      | (ahd_inb(ahd, port+1) << 8)
-	      | (ahd_inb(ahd, port+2) << 16)
-	      | (ahd_inb(ahd, port+3) << 24)
-	      | (((uint64_t)ahd_inb(ahd, port+4)) << 32)
-	      | (((uint64_t)ahd_inb(ahd, port+5)) << 40)
-	      | (((uint64_t)ahd_inb(ahd, port+6)) << 48)
-	      | (((uint64_t)ahd_inb(ahd, port+7)) << 56));
-}
-
-static __inline void
-ahd_outq(struct ahd_softc *ahd, u_int port, uint64_t value)
-{
-	ahd_outb(ahd, port, value & 0xFF);
-	ahd_outb(ahd, port+1, (value >> 8) & 0xFF);
-	ahd_outb(ahd, port+2, (value >> 16) & 0xFF);
-	ahd_outb(ahd, port+3, (value >> 24) & 0xFF);
-	ahd_outb(ahd, port+4, (value >> 32) & 0xFF);
-	ahd_outb(ahd, port+5, (value >> 40) & 0xFF);
-	ahd_outb(ahd, port+6, (value >> 48) & 0xFF);
-	ahd_outb(ahd, port+7, (value >> 56) & 0xFF);
-}
-
-static __inline u_int
-ahd_get_scbptr(struct ahd_softc *ahd)
-{
-	AHD_ASSERT_MODES(ahd, ~(AHD_MODE_UNKNOWN_MSK|AHD_MODE_CFG_MSK),
-			 ~(AHD_MODE_UNKNOWN_MSK|AHD_MODE_CFG_MSK));
-	return (ahd_inb(ahd, SCBPTR) | (ahd_inb(ahd, SCBPTR + 1) << 8));
-}
-
-static __inline void
-ahd_set_scbptr(struct ahd_softc *ahd, u_int scbptr)
-{
-	AHD_ASSERT_MODES(ahd, ~(AHD_MODE_UNKNOWN_MSK|AHD_MODE_CFG_MSK),
-			 ~(AHD_MODE_UNKNOWN_MSK|AHD_MODE_CFG_MSK));
-	ahd_outb(ahd, SCBPTR, scbptr & 0xFF);
-	ahd_outb(ahd, SCBPTR+1, (scbptr >> 8) & 0xFF);
-}
-
-static __inline u_int
-ahd_get_hnscb_qoff(struct ahd_softc *ahd)
-{
-	return (ahd_inw_atomic(ahd, HNSCB_QOFF));
-}
-
-static __inline void
-ahd_set_hnscb_qoff(struct ahd_softc *ahd, u_int value)
-{
-	ahd_outw_atomic(ahd, HNSCB_QOFF, value);
-}
-
-static __inline u_int
-ahd_get_hescb_qoff(struct ahd_softc *ahd)
-{
-	return (ahd_inb(ahd, HESCB_QOFF));
-}
-
-static __inline void
-ahd_set_hescb_qoff(struct ahd_softc *ahd, u_int value)
-{
-	ahd_outb(ahd, HESCB_QOFF, value);
-}
-
-static __inline u_int
-ahd_get_snscb_qoff(struct ahd_softc *ahd)
-{
-	u_int oldvalue;
-
-	AHD_ASSERT_MODES(ahd, AHD_MODE_CCHAN_MSK, AHD_MODE_CCHAN_MSK);
-	oldvalue = ahd_inw(ahd, SNSCB_QOFF);
-	ahd_outw(ahd, SNSCB_QOFF, oldvalue);
-	return (oldvalue);
-}
-
-static __inline void
-ahd_set_snscb_qoff(struct ahd_softc *ahd, u_int value)
-{
-	AHD_ASSERT_MODES(ahd, AHD_MODE_CCHAN_MSK, AHD_MODE_CCHAN_MSK);
-	ahd_outw(ahd, SNSCB_QOFF, value);
-}
-
-static __inline u_int
-ahd_get_sescb_qoff(struct ahd_softc *ahd)
-{
-	AHD_ASSERT_MODES(ahd, AHD_MODE_CCHAN_MSK, AHD_MODE_CCHAN_MSK);
-	return (ahd_inb(ahd, SESCB_QOFF));
-}
-
-static __inline void
-ahd_set_sescb_qoff(struct ahd_softc *ahd, u_int value)
-{
-	AHD_ASSERT_MODES(ahd, AHD_MODE_CCHAN_MSK, AHD_MODE_CCHAN_MSK);
-	ahd_outb(ahd, SESCB_QOFF, value);
-}
-
-static __inline u_int
-ahd_get_sdscb_qoff(struct ahd_softc *ahd)
-{
-	AHD_ASSERT_MODES(ahd, AHD_MODE_CCHAN_MSK, AHD_MODE_CCHAN_MSK);
-	return (ahd_inb(ahd, SDSCB_QOFF) | (ahd_inb(ahd, SDSCB_QOFF + 1) << 8));
-}
-
-static __inline void
-ahd_set_sdscb_qoff(struct ahd_softc *ahd, u_int value)
-{
-	AHD_ASSERT_MODES(ahd, AHD_MODE_CCHAN_MSK, AHD_MODE_CCHAN_MSK);
-	ahd_outb(ahd, SDSCB_QOFF, value & 0xFF);
-	ahd_outb(ahd, SDSCB_QOFF+1, (value >> 8) & 0xFF);
-}
-
-static __inline u_int
-ahd_inb_scbram(struct ahd_softc *ahd, u_int offset)
-{
-	u_int value;
-
-	/*
-	 * Workaround PCI-X Rev A. hardware bug.
-	 * After a host read of SCB memory, the chip
-	 * may become confused into thinking prefetch
-	 * was required.  This starts the discard timer
-	 * running and can cause an unexpected discard
-	 * timer interrupt.  The work around is to read
-	 * a normal register prior to the exhaustion of
-	 * the discard timer.  The mode pointer register
-	 * has no side effects and so serves well for
-	 * this purpose.
-	 *
-	 * Razor #528
-	 */
-	value = ahd_inb(ahd, offset);
-	if ((ahd->bugs & AHD_PCIX_SCBRAM_RD_BUG) != 0)
-		ahd_inb(ahd, MODE_PTR);
-	return (value);
-}
-
-static __inline u_int
-ahd_inw_scbram(struct ahd_softc *ahd, u_int offset)
-{
-	return (ahd_inb_scbram(ahd, offset)
-	      | (ahd_inb_scbram(ahd, offset+1) << 8));
-}
-
-static __inline uint32_t
-ahd_inl_scbram(struct ahd_softc *ahd, u_int offset)
-{
-	return (ahd_inw_scbram(ahd, offset)
-	      | (ahd_inw_scbram(ahd, offset+2) << 16));
-}
-
-static __inline uint64_t
-ahd_inq_scbram(struct ahd_softc *ahd, u_int offset)
-{
-	return (ahd_inl_scbram(ahd, offset)
-	      | ((uint64_t)ahd_inl_scbram(ahd, offset+4)) << 32);
-}
-
-static __inline struct scb *
-ahd_lookup_scb(struct ahd_softc *ahd, u_int tag)
-{
-	struct scb* scb;
-
-	if (tag >= AHD_SCB_MAX)
-		return (NULL);
-	scb = ahd->scb_data.scbindex[tag];
-	if (scb != NULL)
-		ahd_sync_scb(ahd, scb,
-			     BUS_DMASYNC_POSTREAD|BUS_DMASYNC_POSTWRITE);
-	return (scb);
-}
-
-static __inline void
-ahd_swap_with_next_hscb(struct ahd_softc *ahd, struct scb *scb)
-{
-	struct	 hardware_scb *q_hscb;
-	struct	 map_node *q_hscb_map;
-	uint32_t saved_hscb_busaddr;
-
-	/*
-	 * Our queuing method is a bit tricky.  The card
-	 * knows in advance which HSCB (by address) to download,
-	 * and we can't disappoint it.  To achieve this, the next
-	 * HSCB to download is saved off in ahd->next_queued_hscb.
-	 * When we are called to queue "an arbitrary scb",
-	 * we copy the contents of the incoming HSCB to the one
-	 * the sequencer knows about, swap HSCB pointers and
-	 * finally assign the SCB to the tag indexed location
-	 * in the scb_array.  This makes sure that we can still
-	 * locate the correct SCB by SCB_TAG.
-	 */
-	q_hscb = ahd->next_queued_hscb;
-	q_hscb_map = ahd->next_queued_hscb_map;
-	saved_hscb_busaddr = q_hscb->hscb_busaddr;
-	memcpy(q_hscb, scb->hscb, sizeof(*scb->hscb));
-	q_hscb->hscb_busaddr = saved_hscb_busaddr;
-	q_hscb->next_hscb_busaddr = scb->hscb->hscb_busaddr;
-
-	/* Now swap HSCB pointers. */
-	ahd->next_queued_hscb = scb->hscb;
-	ahd->next_queued_hscb_map = scb->hscb_map;
-	scb->hscb = q_hscb;
-	scb->hscb_map = q_hscb_map;
-
-	/* Now define the mapping from tag to SCB in the scbindex */
-	ahd->scb_data.scbindex[SCB_GET_TAG(scb)] = scb;
-}
-
-/*
- * Tell the sequencer about a new transaction to execute.
- */
-static __inline void
-ahd_queue_scb(struct ahd_softc *ahd, struct scb *scb)
-{
-	ahd_swap_with_next_hscb(ahd, scb);
-
-	if (SCBID_IS_NULL(SCB_GET_TAG(scb)))
-		panic("Attempt to queue invalid SCB tag %x\n",
-		      SCB_GET_TAG(scb));
-
-	/*
-	 * Keep a history of SCBs we've downloaded in the qinfifo.
-	 */
-	ahd->qinfifo[AHD_QIN_WRAP(ahd->qinfifonext)] = SCB_GET_TAG(scb);
-	ahd->qinfifonext++;
-
-	if (scb->sg_count != 0)
-		ahd_setup_data_scb(ahd, scb);
-	else
-		ahd_setup_noxfer_scb(ahd, scb);
-	ahd_setup_scb_common(ahd, scb);
-
-	/*
-	 * Make sure our data is consistent from the
-	 * perspective of the adapter.
-	 */
-	ahd_sync_scb(ahd, scb, BUS_DMASYNC_PREREAD|BUS_DMASYNC_PREWRITE);
-
-#ifdef AHD_DEBUG
-	if ((ahd_debug & AHD_SHOW_QUEUE) != 0) {
-		uint64_t host_dataptr;
-
-		host_dataptr = ahd_le64toh(scb->hscb->dataptr);
-		printf("%s: Queueing SCB %d:0x%x bus addr 0x%x - 0x%x%x/0x%x\n",
-		       ahd_name(ahd),
-		       SCB_GET_TAG(scb), scb->hscb->scsiid,
-		       ahd_le32toh(scb->hscb->hscb_busaddr),
-		       (u_int)((host_dataptr >> 32) & 0xFFFFFFFF),
-		       (u_int)(host_dataptr & 0xFFFFFFFF),
-		       ahd_le32toh(scb->hscb->datacnt));
-	}
 #endif
-	/* Tell the adapter about the newly queued SCB */
-	ahd_set_hnscb_qoff(ahd, ahd->qinfifonext);
-}
 
 static __inline uint8_t *
 ahd_get_sense_buf(struct ahd_softc *ahd, struct scb *scb)
@@ -801,151 +171,6 @@ ahd_get_sense_bufaddr(struct ahd_softc *ahd, struct scb *scb)
 }
 
 /************************** Interrupt Processing ******************************/
-static __inline void	ahd_sync_qoutfifo(struct ahd_softc *ahd, int op);
-static __inline void	ahd_sync_tqinfifo(struct ahd_softc *ahd, int op);
-static __inline u_int	ahd_check_cmdcmpltqueues(struct ahd_softc *ahd);
-static __inline int	ahd_intr(struct ahd_softc *ahd);
-
-static __inline void
-ahd_sync_qoutfifo(struct ahd_softc *ahd, int op)
-{
-	ahd_dmamap_sync(ahd, ahd->shared_data_dmat, ahd->shared_data_map.dmamap,
-			/*offset*/0,
-			/*len*/AHD_SCB_MAX * sizeof(struct ahd_completion), op);
-}
-
-static __inline void
-ahd_sync_tqinfifo(struct ahd_softc *ahd, int op)
-{
-#ifdef AHD_TARGET_MODE
-	if ((ahd->flags & AHD_TARGETROLE) != 0) {
-		ahd_dmamap_sync(ahd, ahd->shared_data_dmat,
-				ahd->shared_data_map.dmamap,
-				ahd_targetcmd_offset(ahd, 0),
-				sizeof(struct target_cmd) * AHD_TMODE_CMDS,
-				op);
-	}
-#endif
-}
-
-/*
- * See if the firmware has posted any completed commands
- * into our in-core command complete fifos.
- */
-#define AHD_RUN_QOUTFIFO 0x1
-#define AHD_RUN_TQINFIFO 0x2
-static __inline u_int
-ahd_check_cmdcmpltqueues(struct ahd_softc *ahd)
-{
-	u_int retval;
-
-	retval = 0;
-	ahd_dmamap_sync(ahd, ahd->shared_data_dmat, ahd->shared_data_map.dmamap,
-			/*offset*/ahd->qoutfifonext * sizeof(*ahd->qoutfifo),
-			/*len*/sizeof(*ahd->qoutfifo), BUS_DMASYNC_POSTREAD);
-	if (ahd->qoutfifo[ahd->qoutfifonext].valid_tag
-	  == ahd->qoutfifonext_valid_tag)
-		retval |= AHD_RUN_QOUTFIFO;
-#ifdef AHD_TARGET_MODE
-	if ((ahd->flags & AHD_TARGETROLE) != 0
-	 && (ahd->flags & AHD_TQINFIFO_BLOCKED) == 0) {
-		ahd_dmamap_sync(ahd, ahd->shared_data_dmat,
-				ahd->shared_data_map.dmamap,
-				ahd_targetcmd_offset(ahd, ahd->tqinfifofnext),
-				/*len*/sizeof(struct target_cmd),
-				BUS_DMASYNC_POSTREAD);
-		if (ahd->targetcmds[ahd->tqinfifonext].cmd_valid != 0)
-			retval |= AHD_RUN_TQINFIFO;
-	}
-#endif
-	return (retval);
-}
-
-/*
- * Catch an interrupt from the adapter
- */
-static __inline int
-ahd_intr(struct ahd_softc *ahd)
-{
-	u_int	intstat;
-
-	if ((ahd->pause & INTEN) == 0) {
-		/*
-		 * Our interrupt is not enabled on the chip
-		 * and may be disabled for re-entrancy reasons,
-		 * so just return.  This is likely just a shared
-		 * interrupt.
-		 */
-		return (0);
-	}
-
-	/*
-	 * Instead of directly reading the interrupt status register,
-	 * infer the cause of the interrupt by checking our in-core
-	 * completion queues.  This avoids a costly PCI bus read in
-	 * most cases.
-	 */
-	if ((ahd->flags & AHD_ALL_INTERRUPTS) == 0
-	 && (ahd_check_cmdcmpltqueues(ahd) != 0))
-		intstat = CMDCMPLT;
-	else
-		intstat = ahd_inb(ahd, INTSTAT);
-
-	if ((intstat & INT_PEND) == 0)
-		return (0);
-
-	if (intstat & CMDCMPLT) {
-		ahd_outb(ahd, CLRINT, CLRCMDINT);
-
-		/*
-		 * Ensure that the chip sees that we've cleared
-		 * this interrupt before we walk the output fifo.
-		 * Otherwise, we may, due to posted bus writes,
-		 * clear the interrupt after we finish the scan,
-		 * and after the sequencer has added new entries
-		 * and asserted the interrupt again.
-		 */
-		if ((ahd->bugs & AHD_INTCOLLISION_BUG) != 0) {
-			if (ahd_is_paused(ahd)) {
-				/*
-				 * Potentially lost SEQINT.
-				 * If SEQINTCODE is non-zero,
-				 * simulate the SEQINT.
-				 */
-				if (ahd_inb(ahd, SEQINTCODE) != NO_SEQINT)
-					intstat |= SEQINT;
-			}
-		} else {
-			ahd_flush_device_writes(ahd);
-		}
-		ahd_run_qoutfifo(ahd);
-		ahd->cmdcmplt_counts[ahd->cmdcmplt_bucket]++;
-		ahd->cmdcmplt_total++;
-#ifdef AHD_TARGET_MODE
-		if ((ahd->flags & AHD_TARGETROLE) != 0)
-			ahd_run_tqinfifo(ahd, /*paused*/FALSE);
-#endif
-	}
-
-	/*
-	 * Handle statuses that may invalidate our cached
-	 * copy of INTSTAT separately.
-	 */
-	if (intstat == 0xFF && (ahd->features & AHD_REMOVABLE) != 0) {
-		/* Hot eject.  Do nothing */
-	} else if (intstat & HWERRINT) {
-		ahd_handle_hwerrint(ahd);
-	} else if ((intstat & (PCIINT|SPLTINT)) != 0) {
-		ahd->bus_intr(ahd);
-	} else {
-
-		if ((intstat & SEQINT) != 0)
-			ahd_handle_seqint(ahd, intstat);
-
-		if ((intstat & SCSIINT) != 0)
-			ahd_handle_scsiint(ahd, intstat);
-	}
-	return (1);
-}
+int	ahd_intr(struct ahd_softc *ahd);
 
 #endif  /* _AIC79XX_INLINE_H_ */
diff --git a/trunk/drivers/scsi/aic7xxx/aic79xx_osm.c b/trunk/drivers/scsi/aic7xxx/aic79xx_osm.c
index 0081aa357c8b..0f829b3b8ab7 100644
--- a/trunk/drivers/scsi/aic7xxx/aic79xx_osm.c
+++ b/trunk/drivers/scsi/aic7xxx/aic79xx_osm.c
@@ -193,7 +193,7 @@ struct ahd_linux_iocell_opts
 #define AIC79XX_PRECOMP_INDEX	0
 #define AIC79XX_SLEWRATE_INDEX	1
 #define AIC79XX_AMPLITUDE_INDEX	2
-static struct ahd_linux_iocell_opts aic79xx_iocell_info[] =
+static const struct ahd_linux_iocell_opts aic79xx_iocell_info[] =
 {
 	AIC79XX_DEFAULT_IOOPTS,
 	AIC79XX_DEFAULT_IOOPTS,
@@ -369,10 +369,167 @@ static void ahd_release_simq(struct ahd_softc *ahd);
 static int ahd_linux_unit;
 
 
+/************************** OS Utility Wrappers *******************************/
+void ahd_delay(long);
+void
+ahd_delay(long usec)
+{
+	/*
+	 * udelay on Linux can have problems for
+	 * multi-millisecond waits.  Wait at most
+	 * 1024us per call.
+	 */
+	while (usec > 0) {
+		udelay(usec % 1024);
+		usec -= 1024;
+	}
+}
+
+
+/***************************** Low Level I/O **********************************/
+uint8_t ahd_inb(struct ahd_softc * ahd, long port);
+void ahd_outb(struct ahd_softc * ahd, long port, uint8_t val);
+void ahd_outw_atomic(struct ahd_softc * ahd,
+				     long port, uint16_t val);
+void ahd_outsb(struct ahd_softc * ahd, long port,
+			       uint8_t *, int count);
+void ahd_insb(struct ahd_softc * ahd, long port,
+			       uint8_t *, int count);
+
+uint8_t
+ahd_inb(struct ahd_softc * ahd, long port)
+{
+	uint8_t x;
+
+	if (ahd->tags[0] == BUS_SPACE_MEMIO) {
+		x = readb(ahd->bshs[0].maddr + port);
+	} else {
+		x = inb(ahd->bshs[(port) >> 8].ioport + ((port) & 0xFF));
+	}
+	mb();
+	return (x);
+}
+
+#if 0 /* unused */
+static uint16_t
+ahd_inw_atomic(struct ahd_softc * ahd, long port)
+{
+	uint8_t x;
+
+	if (ahd->tags[0] == BUS_SPACE_MEMIO) {
+		x = readw(ahd->bshs[0].maddr + port);
+	} else {
+		x = inw(ahd->bshs[(port) >> 8].ioport + ((port) & 0xFF));
+	}
+	mb();
+	return (x);
+}
+#endif
+
+void
+ahd_outb(struct ahd_softc * ahd, long port, uint8_t val)
+{
+	if (ahd->tags[0] == BUS_SPACE_MEMIO) {
+		writeb(val, ahd->bshs[0].maddr + port);
+	} else {
+		outb(val, ahd->bshs[(port) >> 8].ioport + (port & 0xFF));
+	}
+	mb();
+}
+
+void
+ahd_outw_atomic(struct ahd_softc * ahd, long port, uint16_t val)
+{
+	if (ahd->tags[0] == BUS_SPACE_MEMIO) {
+		writew(val, ahd->bshs[0].maddr + port);
+	} else {
+		outw(val, ahd->bshs[(port) >> 8].ioport + (port & 0xFF));
+	}
+	mb();
+}
+
+void
+ahd_outsb(struct ahd_softc * ahd, long port, uint8_t *array, int count)
+{
+	int i;
+
+	/*
+	 * There is probably a more efficient way to do this on Linux
+	 * but we don't use this for anything speed critical and this
+	 * should work.
+	 */
+	for (i = 0; i < count; i++)
+		ahd_outb(ahd, port, *array++);
+}
+
+void
+ahd_insb(struct ahd_softc * ahd, long port, uint8_t *array, int count)
+{
+	int i;
+
+	/*
+	 * There is probably a more efficient way to do this on Linux
+	 * but we don't use this for anything speed critical and this
+	 * should work.
+	 */
+	for (i = 0; i < count; i++)
+		*array++ = ahd_inb(ahd, port);
+}
+
+/******************************* PCI Routines *********************************/
+uint32_t
+ahd_pci_read_config(ahd_dev_softc_t pci, int reg, int width)
+{
+	switch (width) {
+	case 1:
+	{
+		uint8_t retval;
+
+		pci_read_config_byte(pci, reg, &retval);
+		return (retval);
+	}
+	case 2:
+	{
+		uint16_t retval;
+		pci_read_config_word(pci, reg, &retval);
+		return (retval);
+	}
+	case 4:
+	{
+		uint32_t retval;
+		pci_read_config_dword(pci, reg, &retval);
+		return (retval);
+	}
+	default:
+		panic("ahd_pci_read_config: Read size too big");
+		/* NOTREACHED */
+		return (0);
+	}
+}
+
+void
+ahd_pci_write_config(ahd_dev_softc_t pci, int reg, uint32_t value, int width)
+{
+	switch (width) {
+	case 1:
+		pci_write_config_byte(pci, reg, value);
+		break;
+	case 2:
+		pci_write_config_word(pci, reg, value);
+		break;
+	case 4:
+		pci_write_config_dword(pci, reg, value);
+		break;
+	default:
+		panic("ahd_pci_write_config: Write size too big");
+		/* NOTREACHED */
+	}
+}
+
 /****************************** Inlines ***************************************/
-static __inline void ahd_linux_unmap_scb(struct ahd_softc*, struct scb*);
+static void ahd_linux_unmap_scb(struct ahd_softc*, struct scb*);
 
-static __inline void
+static void
 ahd_linux_unmap_scb(struct ahd_softc *ahd, struct scb *scb)
 {
 	struct scsi_cmnd *cmd;
@@ -400,13 +557,11 @@ ahd_linux_info(struct Scsi_Host *host)
 	bp = &buffer[0];
 	ahd = *(struct ahd_softc **)host->hostdata;
 	memset(bp, 0, sizeof(buffer));
-	strcpy(bp, "Adaptec AIC79XX PCI-X SCSI HBA DRIVER, Rev ");
-	strcat(bp, AIC79XX_DRIVER_VERSION);
-	strcat(bp, "\n");
-	strcat(bp, "        <");
+	strcpy(bp, "Adaptec AIC79XX PCI-X SCSI HBA DRIVER, Rev " AIC79XX_DRIVER_VERSION "\n"
+			"        <");
 	strcat(bp, ahd->description);
-	strcat(bp, ">\n");
-	strcat(bp, "        ");
+	strcat(bp, ">\n"
+			"        ");
 	ahd_controller_info(ahd, ahd_info);
 	strcat(bp, ahd_info);
 
@@ -432,7 +587,7 @@ ahd_linux_queue(struct scsi_cmnd * cmd, void (*scsi_done) (struct scsi_cmnd *))
 	return rtn;
 }
 
-static inline struct scsi_target **
+static struct scsi_target **
 ahd_linux_target_in_softc(struct scsi_target *starget)
 {
 	struct	ahd_softc *ahd =
@@ -991,7 +1146,7 @@ aic79xx_setup(char *s)
 	char   *p;
 	char   *end;
 
-	static struct {
+	static const struct {
 		const char *name;
 		uint32_t *flag;
 	} options[] = {
@@ -1223,7 +1378,7 @@ ahd_platform_init(struct ahd_softc *ahd)
 	 * Lookup and commit any modified IO Cell options.
 	 */
 	if (ahd->unit < ARRAY_SIZE(aic79xx_iocell_info)) {
-		struct ahd_linux_iocell_opts *iocell_opts;
+		const struct ahd_linux_iocell_opts *iocell_opts;
 
 		iocell_opts = &aic79xx_iocell_info[ahd->unit];
 		if (iocell_opts->precomp != AIC79XX_DEFAULT_PRECOMP)
@@ -2613,7 +2768,7 @@ static void ahd_linux_set_pcomp_en(struct scsi_target *starget, int pcomp)
 		uint8_t precomp;
 
 		if (ahd->unit < ARRAY_SIZE(aic79xx_iocell_info)) {
-			struct ahd_linux_iocell_opts *iocell_opts;
+			const struct ahd_linux_iocell_opts *iocell_opts;
 
 			iocell_opts = &aic79xx_iocell_info[ahd->unit];
 			precomp = iocell_opts->precomp;
diff --git a/trunk/drivers/scsi/aic7xxx/aic79xx_osm.h b/trunk/drivers/scsi/aic7xxx/aic79xx_osm.h
index 853998be1474..8d6612c19922 100644
--- a/trunk/drivers/scsi/aic7xxx/aic79xx_osm.h
+++ b/trunk/drivers/scsi/aic7xxx/aic79xx_osm.h
@@ -222,22 +222,6 @@ typedef struct timer_list ahd_timer_t;
 /***************************** Timer Facilities *******************************/
 #define ahd_timer_init init_timer
 #define ahd_timer_stop del_timer_sync
-typedef void ahd_linux_callback_t (u_long);  
-static __inline void ahd_timer_reset(ahd_timer_t *timer, int usec,
-				     ahd_callback_t *func, void *arg);
-
-static __inline void
-ahd_timer_reset(ahd_timer_t *timer, int usec, ahd_callback_t *func, void *arg)
-{
-	struct ahd_softc *ahd;
-
-	ahd = (struct ahd_softc *)arg;
-	del_timer(timer);
-	timer->data = (u_long)arg;
-	timer->expires = jiffies + (usec * HZ)/1000000;
-	timer->function = (ahd_linux_callback_t*)func;
-	add_timer(timer);
-}
 
 /***************************** SMP support ************************************/
 #include <linux/spinlock.h>
@@ -376,7 +360,7 @@ struct ahd_platform_data {
 #define AHD_LINUX_NOIRQ	((uint32_t)~0)
 	uint32_t		 irq;		/* IRQ for this adapter */
 	uint32_t		 bios_address;
-	uint32_t		 mem_busaddr;	/* Mem Base Addr */
+	resource_size_t		 mem_busaddr;	/* Mem Base Addr */
 };
 
 /************************** OS Utility Wrappers *******************************/
@@ -386,111 +370,18 @@ struct ahd_platform_data {
 #define malloc(size, type, flags) kmalloc(size, flags)
 #define free(ptr, type) kfree(ptr)
 
-static __inline void ahd_delay(long);
-static __inline void
-ahd_delay(long usec)
-{
-	/*
-	 * udelay on Linux can have problems for
-	 * multi-millisecond waits.  Wait at most
-	 * 1024us per call.
-	 */
-	while (usec > 0) {
-		udelay(usec % 1024);
-		usec -= 1024;
-	}
-}
-
+void ahd_delay(long);
 
 /***************************** Low Level I/O **********************************/
-static __inline uint8_t ahd_inb(struct ahd_softc * ahd, long port);
-static __inline uint16_t ahd_inw_atomic(struct ahd_softc * ahd, long port);
-static __inline void ahd_outb(struct ahd_softc * ahd, long port, uint8_t val);
-static __inline void ahd_outw_atomic(struct ahd_softc * ahd,
+uint8_t ahd_inb(struct ahd_softc * ahd, long port);
+void ahd_outb(struct ahd_softc * ahd, long port, uint8_t val);
+void ahd_outw_atomic(struct ahd_softc * ahd,
 				     long port, uint16_t val);
-static __inline void ahd_outsb(struct ahd_softc * ahd, long port,
+void ahd_outsb(struct ahd_softc * ahd, long port,
 			       uint8_t *, int count);
-static __inline void ahd_insb(struct ahd_softc * ahd, long port,
+void ahd_insb(struct ahd_softc * ahd, long port,
 			       uint8_t *, int count);
 
-static __inline uint8_t
-ahd_inb(struct ahd_softc * ahd, long port)
-{
-	uint8_t x;
-
-	if (ahd->tags[0] == BUS_SPACE_MEMIO) {
-		x = readb(ahd->bshs[0].maddr + port);
-	} else {
-		x = inb(ahd->bshs[(port) >> 8].ioport + ((port) & 0xFF));
-	}
-	mb();
-	return (x);
-}
-
-static __inline uint16_t
-ahd_inw_atomic(struct ahd_softc * ahd, long port)
-{
-	uint8_t x;
-
-	if (ahd->tags[0] == BUS_SPACE_MEMIO) {
-		x = readw(ahd->bshs[0].maddr + port);
-	} else {
-		x = inw(ahd->bshs[(port) >> 8].ioport + ((port) & 0xFF));
-	}
-	mb();
-	return (x);
-}
-
-static __inline void
-ahd_outb(struct ahd_softc * ahd, long port, uint8_t val)
-{
-	if (ahd->tags[0] == BUS_SPACE_MEMIO) {
-		writeb(val, ahd->bshs[0].maddr + port);
-	} else {
-		outb(val, ahd->bshs[(port) >> 8].ioport + (port & 0xFF));
-	}
-	mb();
-}
-
-static __inline void
-ahd_outw_atomic(struct ahd_softc * ahd, long port, uint16_t val)
-{
-	if (ahd->tags[0] == BUS_SPACE_MEMIO) {
-		writew(val, ahd->bshs[0].maddr + port);
-	} else {
-		outw(val, ahd->bshs[(port) >> 8].ioport + (port & 0xFF));
-	}
-	mb();
-}
-
-static __inline void
-ahd_outsb(struct ahd_softc * ahd, long port, uint8_t *array, int count)
-{
-	int i;
-
-	/*
-	 * There is probably a more efficient way to do this on Linux
-	 * but we don't use this for anything speed critical and this
-	 * should work.
-	 */
-	for (i = 0; i < count; i++)
-		ahd_outb(ahd, port, *array++);
-}
-
-static __inline void
-ahd_insb(struct ahd_softc * ahd, long port, uint8_t *array, int count)
-{
-	int i;
-
-	/*
-	 * There is probably a more efficient way to do this on Linux
-	 * but we don't use this for anything speed critical and this
-	 * should work.
-	 */
-	for (i = 0; i < count; i++)
-		*array++ = ahd_inb(ahd, port);
-}
-
 /**************************** Initialization **********************************/
 int		ahd_linux_register_host(struct ahd_softc *,
 					struct scsi_host_template *);
@@ -593,62 +484,12 @@ void			 ahd_linux_pci_exit(void);
 int			 ahd_pci_map_registers(struct ahd_softc *ahd);
 int			 ahd_pci_map_int(struct ahd_softc *ahd);
 
-static __inline uint32_t ahd_pci_read_config(ahd_dev_softc_t pci,
+uint32_t		 ahd_pci_read_config(ahd_dev_softc_t pci,
 					     int reg, int width);
-
-static __inline uint32_t
-ahd_pci_read_config(ahd_dev_softc_t pci, int reg, int width)
-{
-	switch (width) {
-	case 1:
-	{
-		uint8_t retval;
-
-		pci_read_config_byte(pci, reg, &retval);
-		return (retval);
-	}
-	case 2:
-	{
-		uint16_t retval;
-		pci_read_config_word(pci, reg, &retval);
-		return (retval);
-	}
-	case 4:
-	{
-		uint32_t retval;
-		pci_read_config_dword(pci, reg, &retval);
-		return (retval);
-	}
-	default:
-		panic("ahd_pci_read_config: Read size too big");
-		/* NOTREACHED */
-		return (0);
-	}
-}
-
-static __inline void ahd_pci_write_config(ahd_dev_softc_t pci,
+void			 ahd_pci_write_config(ahd_dev_softc_t pci,
 					  int reg, uint32_t value,
 					  int width);
 
-static __inline void
-ahd_pci_write_config(ahd_dev_softc_t pci, int reg, uint32_t value, int width)
-{
-	switch (width) {
-	case 1:
-		pci_write_config_byte(pci, reg, value);
-		break;
-	case 2:
-		pci_write_config_word(pci, reg, value);
-		break;
-	case 4:
-		pci_write_config_dword(pci, reg, value);
-		break;
-	default:
-		panic("ahd_pci_write_config: Write size too big");
-		/* NOTREACHED */
-	}
-}
-
 static __inline int ahd_get_pci_function(ahd_dev_softc_t);
 static __inline int
 ahd_get_pci_function(ahd_dev_softc_t pci)
diff --git a/trunk/drivers/scsi/aic7xxx/aic79xx_osm_pci.c b/trunk/drivers/scsi/aic7xxx/aic79xx_osm_pci.c
index dfaaae5e73ae..6593056867f6 100644
--- a/trunk/drivers/scsi/aic7xxx/aic79xx_osm_pci.c
+++ b/trunk/drivers/scsi/aic7xxx/aic79xx_osm_pci.c
@@ -49,7 +49,7 @@
 	ID2C(x),         \
 	ID2C(IDIROC(x))
 
-static struct pci_device_id ahd_linux_pci_id_table[] = {
+static const struct pci_device_id ahd_linux_pci_id_table[] = {
 	/* aic7901 based controllers */
 	ID(ID_AHA_29320A),
 	ID(ID_AHA_29320ALP),
@@ -159,7 +159,7 @@ ahd_linux_pci_dev_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	char		 buf[80];
 	struct		 ahd_softc *ahd;
 	ahd_dev_softc_t	 pci;
-	struct		 ahd_pci_identity *entry;
+	const struct ahd_pci_identity *entry;
 	char		*name;
 	int		 error;
 	struct device	*dev = &pdev->dev;
@@ -249,8 +249,8 @@ ahd_linux_pci_exit(void)
 }
 
 static int
-ahd_linux_pci_reserve_io_regions(struct ahd_softc *ahd, u_long *base,
-				 u_long *base2)
+ahd_linux_pci_reserve_io_regions(struct ahd_softc *ahd, resource_size_t *base,
+				 resource_size_t *base2)
 {
 	*base = pci_resource_start(ahd->dev_softc, 0);
 	/*
@@ -272,11 +272,11 @@ ahd_linux_pci_reserve_io_regions(struct ahd_softc *ahd, u_long *base,
 
 static int
 ahd_linux_pci_reserve_mem_region(struct ahd_softc *ahd,
-				 u_long *bus_addr,
+				 resource_size_t *bus_addr,
 				 uint8_t __iomem **maddr)
 {
-	u_long	start;
-	u_long	base_page;
+	resource_size_t	start;
+	resource_size_t	base_page;
 	u_long	base_offset;
 	int	error = 0;
 
@@ -310,7 +310,7 @@ int
 ahd_pci_map_registers(struct ahd_softc *ahd)
 {
 	uint32_t command;
-	u_long	 base;
+	resource_size_t base;
 	uint8_t	__iomem *maddr;
 	int	 error;
 
@@ -346,31 +346,32 @@ ahd_pci_map_registers(struct ahd_softc *ahd)
 		} else
 			command |= PCIM_CMD_MEMEN;
 	} else if (bootverbose) {
-		printf("aic79xx: PCI%d:%d:%d MEM region 0x%lx "
+		printf("aic79xx: PCI%d:%d:%d MEM region 0x%llx "
 		       "unavailable. Cannot memory map device.\n",
 		       ahd_get_pci_bus(ahd->dev_softc),
 		       ahd_get_pci_slot(ahd->dev_softc),
 		       ahd_get_pci_function(ahd->dev_softc),
-		       base);
+		       (unsigned long long)base);
 	}
 
 	if (maddr == NULL) {
-		u_long	 base2;
+		resource_size_t base2;
 
 		error = ahd_linux_pci_reserve_io_regions(ahd, &base, &base2);
 		if (error == 0) {
 			ahd->tags[0] = BUS_SPACE_PIO;
 			ahd->tags[1] = BUS_SPACE_PIO;
-			ahd->bshs[0].ioport = base;
-			ahd->bshs[1].ioport = base2;
+			ahd->bshs[0].ioport = (u_long)base;
+			ahd->bshs[1].ioport = (u_long)base2;
 			command |= PCIM_CMD_PORTEN;
 		} else {
-			printf("aic79xx: PCI%d:%d:%d IO regions 0x%lx and 0x%lx"
-			       "unavailable. Cannot map device.\n",
+			printf("aic79xx: PCI%d:%d:%d IO regions 0x%llx and "
+			       "0x%llx unavailable. Cannot map device.\n",
 			       ahd_get_pci_bus(ahd->dev_softc),
 			       ahd_get_pci_slot(ahd->dev_softc),
 			       ahd_get_pci_function(ahd->dev_softc),
-			       base, base2);
+			       (unsigned long long)base,
+			       (unsigned long long)base2);
 		}
 	}
 	ahd_pci_write_config(ahd->dev_softc, PCIR_COMMAND, command, 4);
diff --git a/trunk/drivers/scsi/aic7xxx/aic79xx_pci.c b/trunk/drivers/scsi/aic7xxx/aic79xx_pci.c
index c9f79fdf9131..c25b6adffbf9 100644
--- a/trunk/drivers/scsi/aic7xxx/aic79xx_pci.c
+++ b/trunk/drivers/scsi/aic7xxx/aic79xx_pci.c
@@ -97,7 +97,7 @@ static ahd_device_setup_t ahd_aic7901A_setup;
 static ahd_device_setup_t ahd_aic7902_setup;
 static ahd_device_setup_t ahd_aic790X_setup;
 
-static struct ahd_pci_identity ahd_pci_ident_table [] =
+static const struct ahd_pci_identity ahd_pci_ident_table[] =
 {
 	/* aic7901 based controllers */
 	{
@@ -253,7 +253,7 @@ static void	ahd_configure_termination(struct ahd_softc *ahd,
 static void	ahd_pci_split_intr(struct ahd_softc *ahd, u_int intstat);
 static void	ahd_pci_intr(struct ahd_softc *ahd);
 
-struct ahd_pci_identity *
+const struct ahd_pci_identity *
 ahd_find_pci_device(ahd_dev_softc_t pci)
 {
 	uint64_t  full_id;
@@ -261,7 +261,7 @@ ahd_find_pci_device(ahd_dev_softc_t pci)
 	uint16_t  vendor;
 	uint16_t  subdevice;
 	uint16_t  subvendor;
-	struct	  ahd_pci_identity *entry;
+	const struct ahd_pci_identity *entry;
 	u_int	  i;
 
 	vendor = ahd_pci_read_config(pci, PCIR_DEVVENDOR, /*bytes*/2);
@@ -292,7 +292,7 @@ ahd_find_pci_device(ahd_dev_softc_t pci)
 }
 
 int
-ahd_pci_config(struct ahd_softc *ahd, struct ahd_pci_identity *entry)
+ahd_pci_config(struct ahd_softc *ahd, const struct ahd_pci_identity *entry)
 {
 	struct scb_data *shared_scb_data;
 	u_int		 command;
diff --git a/trunk/drivers/scsi/aic7xxx/aic79xx_proc.c b/trunk/drivers/scsi/aic7xxx/aic79xx_proc.c
index 6b28bebcbca0..014bed716e7c 100644
--- a/trunk/drivers/scsi/aic7xxx/aic79xx_proc.c
+++ b/trunk/drivers/scsi/aic7xxx/aic79xx_proc.c
@@ -57,7 +57,7 @@ static int	ahd_proc_write_seeprom(struct ahd_softc *ahd,
  * Table of syncrates that don't follow the "divisible by 4"
  * rule. This table will be expanded in future SCSI specs.
  */
-static struct {
+static const struct {
 	u_int period_factor;
 	u_int period;	/* in 100ths of ns */
 } scsi_syncrates[] = {
diff --git a/trunk/drivers/scsi/aic7xxx/aic79xx_reg.h_shipped b/trunk/drivers/scsi/aic7xxx/aic79xx_reg.h_shipped
index 2068e00d2c75..c21ceab8e913 100644
--- a/trunk/drivers/scsi/aic7xxx/aic79xx_reg.h_shipped
+++ b/trunk/drivers/scsi/aic7xxx/aic79xx_reg.h_shipped
@@ -47,13 +47,6 @@ ahd_reg_print_t ahd_error_print;
     ahd_print_register(NULL, 0, "ERROR", 0x04, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_clrerr_print;
-#else
-#define ahd_clrerr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CLRERR", 0x04, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_hcntrl_print;
 #else
@@ -166,13 +159,6 @@ ahd_reg_print_t ahd_sg_cache_shadow_print;
     ahd_print_register(NULL, 0, "SG_CACHE_SHADOW", 0x1b, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_arbctl_print;
-#else
-#define ahd_arbctl_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "ARBCTL", 0x1b, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_sg_cache_pre_print;
 #else
@@ -187,20 +173,6 @@ ahd_reg_print_t ahd_lqin_print;
     ahd_print_register(NULL, 0, "LQIN", 0x20, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_typeptr_print;
-#else
-#define ahd_typeptr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "TYPEPTR", 0x20, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_tagptr_print;
-#else
-#define ahd_tagptr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "TAGPTR", 0x21, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_lunptr_print;
 #else
@@ -208,20 +180,6 @@ ahd_reg_print_t ahd_lunptr_print;
     ahd_print_register(NULL, 0, "LUNPTR", 0x22, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_datalenptr_print;
-#else
-#define ahd_datalenptr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DATALENPTR", 0x23, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_statlenptr_print;
-#else
-#define ahd_statlenptr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "STATLENPTR", 0x24, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_cmdlenptr_print;
 #else
@@ -257,13 +215,6 @@ ahd_reg_print_t ahd_qnextptr_print;
     ahd_print_register(NULL, 0, "QNEXTPTR", 0x29, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_idptr_print;
-#else
-#define ahd_idptr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "IDPTR", 0x2a, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_abrtbyteptr_print;
 #else
@@ -278,27 +229,6 @@ ahd_reg_print_t ahd_abrtbitptr_print;
     ahd_print_register(NULL, 0, "ABRTBITPTR", 0x2c, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_maxcmdbytes_print;
-#else
-#define ahd_maxcmdbytes_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "MAXCMDBYTES", 0x2d, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_maxcmd2rcv_print;
-#else
-#define ahd_maxcmd2rcv_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "MAXCMD2RCV", 0x2e, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_shortthresh_print;
-#else
-#define ahd_shortthresh_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SHORTTHRESH", 0x2f, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_lunlen_print;
 #else
@@ -327,41 +257,6 @@ ahd_reg_print_t ahd_maxcmdcnt_print;
     ahd_print_register(NULL, 0, "MAXCMDCNT", 0x33, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_lqrsvd01_print;
-#else
-#define ahd_lqrsvd01_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "LQRSVD01", 0x34, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_lqrsvd16_print;
-#else
-#define ahd_lqrsvd16_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "LQRSVD16", 0x35, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_lqrsvd17_print;
-#else
-#define ahd_lqrsvd17_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "LQRSVD17", 0x36, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_cmdrsvd0_print;
-#else
-#define ahd_cmdrsvd0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CMDRSVD0", 0x37, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_lqctl0_print;
-#else
-#define ahd_lqctl0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "LQCTL0", 0x38, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_lqctl1_print;
 #else
@@ -369,13 +264,6 @@ ahd_reg_print_t ahd_lqctl1_print;
     ahd_print_register(NULL, 0, "LQCTL1", 0x38, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_scsbist0_print;
-#else
-#define ahd_scsbist0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SCSBIST0", 0x39, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_lqctl2_print;
 #else
@@ -383,13 +271,6 @@ ahd_reg_print_t ahd_lqctl2_print;
     ahd_print_register(NULL, 0, "LQCTL2", 0x39, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_scsbist1_print;
-#else
-#define ahd_scsbist1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SCSBIST1", 0x3a, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_scsiseq0_print;
 #else
@@ -411,20 +292,6 @@ ahd_reg_print_t ahd_sxfrctl0_print;
     ahd_print_register(NULL, 0, "SXFRCTL0", 0x3c, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dlcount_print;
-#else
-#define ahd_dlcount_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DLCOUNT", 0x3c, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_businitid_print;
-#else
-#define ahd_businitid_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "BUSINITID", 0x3c, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_sxfrctl1_print;
 #else
@@ -432,20 +299,6 @@ ahd_reg_print_t ahd_sxfrctl1_print;
     ahd_print_register(NULL, 0, "SXFRCTL1", 0x3d, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_bustargid_print;
-#else
-#define ahd_bustargid_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "BUSTARGID", 0x3e, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_sxfrctl2_print;
-#else
-#define ahd_sxfrctl2_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SXFRCTL2", 0x3e, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_dffstat_print;
 #else
@@ -454,17 +307,17 @@ ahd_reg_print_t ahd_dffstat_print;
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_scsisigo_print;
+ahd_reg_print_t ahd_multargid_print;
 #else
-#define ahd_scsisigo_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SCSISIGO", 0x40, regvalue, cur_col, wrap)
+#define ahd_multargid_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "MULTARGID", 0x40, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_multargid_print;
+ahd_reg_print_t ahd_scsisigo_print;
 #else
-#define ahd_multargid_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "MULTARGID", 0x40, regvalue, cur_col, wrap)
+#define ahd_scsisigo_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "SCSISIGO", 0x40, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
@@ -481,13 +334,6 @@ ahd_reg_print_t ahd_scsiphase_print;
     ahd_print_register(NULL, 0, "SCSIPHASE", 0x42, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_scsidat0_img_print;
-#else
-#define ahd_scsidat0_img_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SCSIDAT0_IMG", 0x43, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_scsidat_print;
 #else
@@ -530,13 +376,6 @@ ahd_reg_print_t ahd_sblkctl_print;
     ahd_print_register(NULL, 0, "SBLKCTL", 0x4a, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_clrsint0_print;
-#else
-#define ahd_clrsint0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CLRSINT0", 0x4b, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_sstat0_print;
 #else
@@ -552,10 +391,10 @@ ahd_reg_print_t ahd_simode0_print;
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_clrsint1_print;
+ahd_reg_print_t ahd_clrsint0_print;
 #else
-#define ahd_clrsint1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CLRSINT1", 0x4c, regvalue, cur_col, wrap)
+#define ahd_clrsint0_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "CLRSINT0", 0x4b, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
@@ -566,17 +405,17 @@ ahd_reg_print_t ahd_sstat1_print;
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_sstat2_print;
+ahd_reg_print_t ahd_clrsint1_print;
 #else
-#define ahd_sstat2_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SSTAT2", 0x4d, regvalue, cur_col, wrap)
+#define ahd_clrsint1_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "CLRSINT1", 0x4c, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_simode2_print;
+ahd_reg_print_t ahd_sstat2_print;
 #else
-#define ahd_simode2_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SIMODE2", 0x4d, regvalue, cur_col, wrap)
+#define ahd_sstat2_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "SSTAT2", 0x4d, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
@@ -622,17 +461,17 @@ ahd_reg_print_t ahd_lqistat0_print;
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_clrlqiint0_print;
+ahd_reg_print_t ahd_lqimode0_print;
 #else
-#define ahd_clrlqiint0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CLRLQIINT0", 0x50, regvalue, cur_col, wrap)
+#define ahd_lqimode0_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "LQIMODE0", 0x50, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_lqimode0_print;
+ahd_reg_print_t ahd_clrlqiint0_print;
 #else
-#define ahd_lqimode0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "LQIMODE0", 0x50, regvalue, cur_col, wrap)
+#define ahd_clrlqiint0_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "CLRLQIINT0", 0x50, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
@@ -789,13 +628,6 @@ ahd_reg_print_t ahd_seqintsrc_print;
     ahd_print_register(NULL, 0, "SEQINTSRC", 0x5b, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_currscb_print;
-#else
-#define ahd_currscb_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CURRSCB", 0x5c, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_seqimode_print;
 #else
@@ -804,24 +636,17 @@ ahd_reg_print_t ahd_seqimode_print;
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_mdffstat_print;
-#else
-#define ahd_mdffstat_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "MDFFSTAT", 0x5d, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_crccontrol_print;
+ahd_reg_print_t ahd_currscb_print;
 #else
-#define ahd_crccontrol_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CRCCONTROL", 0x5d, regvalue, cur_col, wrap)
+#define ahd_currscb_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "CURRSCB", 0x5c, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dfftag_print;
+ahd_reg_print_t ahd_mdffstat_print;
 #else
-#define ahd_dfftag_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DFFTAG", 0x5e, regvalue, cur_col, wrap)
+#define ahd_mdffstat_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "MDFFSTAT", 0x5d, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
@@ -831,20 +656,6 @@ ahd_reg_print_t ahd_lastscb_print;
     ahd_print_register(NULL, 0, "LASTSCB", 0x5e, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_scsitest_print;
-#else
-#define ahd_scsitest_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SCSITEST", 0x5e, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_iopdnctl_print;
-#else
-#define ahd_iopdnctl_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "IOPDNCTL", 0x5f, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_shaddr_print;
 #else
@@ -859,13 +670,6 @@ ahd_reg_print_t ahd_negoaddr_print;
     ahd_print_register(NULL, 0, "NEGOADDR", 0x60, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dgrpcrci_print;
-#else
-#define ahd_dgrpcrci_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DGRPCRCI", 0x60, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_negperiod_print;
 #else
@@ -873,13 +677,6 @@ ahd_reg_print_t ahd_negperiod_print;
     ahd_print_register(NULL, 0, "NEGPERIOD", 0x61, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_packcrci_print;
-#else
-#define ahd_packcrci_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "PACKCRCI", 0x62, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_negoffset_print;
 #else
@@ -929,13 +726,6 @@ ahd_reg_print_t ahd_iownid_print;
     ahd_print_register(NULL, 0, "IOWNID", 0x67, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_pll960ctl0_print;
-#else
-#define ahd_pll960ctl0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "PLL960CTL0", 0x68, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_shcnt_print;
 #else
@@ -950,27 +740,6 @@ ahd_reg_print_t ahd_townid_print;
     ahd_print_register(NULL, 0, "TOWNID", 0x69, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_pll960ctl1_print;
-#else
-#define ahd_pll960ctl1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "PLL960CTL1", 0x69, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_pll960cnt0_print;
-#else
-#define ahd_pll960cnt0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "PLL960CNT0", 0x6a, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_xsig_print;
-#else
-#define ahd_xsig_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "XSIG", 0x6a, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_seloid_print;
 #else
@@ -978,41 +747,6 @@ ahd_reg_print_t ahd_seloid_print;
     ahd_print_register(NULL, 0, "SELOID", 0x6b, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_pll400ctl0_print;
-#else
-#define ahd_pll400ctl0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "PLL400CTL0", 0x6c, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_fairness_print;
-#else
-#define ahd_fairness_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "FAIRNESS", 0x6c, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_pll400ctl1_print;
-#else
-#define ahd_pll400ctl1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "PLL400CTL1", 0x6d, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_unfairness_print;
-#else
-#define ahd_unfairness_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "UNFAIRNESS", 0x6e, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_pll400cnt0_print;
-#else
-#define ahd_pll400cnt0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "PLL400CNT0", 0x6e, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_haddr_print;
 #else
@@ -1020,27 +754,6 @@ ahd_reg_print_t ahd_haddr_print;
     ahd_print_register(NULL, 0, "HADDR", 0x70, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_plldelay_print;
-#else
-#define ahd_plldelay_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "PLLDELAY", 0x70, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_hodmaadr_print;
-#else
-#define ahd_hodmaadr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "HODMAADR", 0x70, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_hodmacnt_print;
-#else
-#define ahd_hodmacnt_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "HODMACNT", 0x78, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_hcnt_print;
 #else
@@ -1049,10 +762,10 @@ ahd_reg_print_t ahd_hcnt_print;
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_hodmaen_print;
+ahd_reg_print_t ahd_sghaddr_print;
 #else
-#define ahd_hodmaen_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "HODMAEN", 0x7a, regvalue, cur_col, wrap)
+#define ahd_sghaddr_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "SGHADDR", 0x7c, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
@@ -1063,10 +776,10 @@ ahd_reg_print_t ahd_scbhaddr_print;
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_sghaddr_print;
+ahd_reg_print_t ahd_sghcnt_print;
 #else
-#define ahd_sghaddr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SGHADDR", 0x7c, regvalue, cur_col, wrap)
+#define ahd_sghcnt_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "SGHCNT", 0x84, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
@@ -1076,13 +789,6 @@ ahd_reg_print_t ahd_scbhcnt_print;
     ahd_print_register(NULL, 0, "SCBHCNT", 0x84, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_sghcnt_print;
-#else
-#define ahd_sghcnt_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SGHCNT", 0x84, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_dff_thrsh_print;
 #else
@@ -1091,357 +797,56 @@ ahd_reg_print_t ahd_dff_thrsh_print;
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_romaddr_print;
+ahd_reg_print_t ahd_pcixctl_print;
 #else
-#define ahd_romaddr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "ROMADDR", 0x8a, regvalue, cur_col, wrap)
+#define ahd_pcixctl_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "PCIXCTL", 0x93, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_romcntrl_print;
+ahd_reg_print_t ahd_dchspltstat0_print;
 #else
-#define ahd_romcntrl_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "ROMCNTRL", 0x8d, regvalue, cur_col, wrap)
+#define ahd_dchspltstat0_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "DCHSPLTSTAT0", 0x96, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_romdata_print;
+ahd_reg_print_t ahd_dchspltstat1_print;
 #else
-#define ahd_romdata_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "ROMDATA", 0x8e, regvalue, cur_col, wrap)
+#define ahd_dchspltstat1_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "DCHSPLTSTAT1", 0x97, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_cmcrxmsg0_print;
+ahd_reg_print_t ahd_sgspltstat0_print;
 #else
-#define ahd_cmcrxmsg0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CMCRXMSG0", 0x90, regvalue, cur_col, wrap)
+#define ahd_sgspltstat0_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "SGSPLTSTAT0", 0x9e, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_roenable_print;
+ahd_reg_print_t ahd_sgspltstat1_print;
 #else
-#define ahd_roenable_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "ROENABLE", 0x90, regvalue, cur_col, wrap)
+#define ahd_sgspltstat1_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "SGSPLTSTAT1", 0x9f, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_ovlyrxmsg0_print;
+ahd_reg_print_t ahd_df0pcistat_print;
 #else
-#define ahd_ovlyrxmsg0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "OVLYRXMSG0", 0x90, regvalue, cur_col, wrap)
+#define ahd_df0pcistat_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "DF0PCISTAT", 0xa0, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dchrxmsg0_print;
+ahd_reg_print_t ahd_reg0_print;
 #else
-#define ahd_dchrxmsg0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DCHRXMSG0", 0x90, regvalue, cur_col, wrap)
+#define ahd_reg0_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "REG0", 0xa0, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_ovlyrxmsg1_print;
-#else
-#define ahd_ovlyrxmsg1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "OVLYRXMSG1", 0x91, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_nsenable_print;
-#else
-#define ahd_nsenable_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "NSENABLE", 0x91, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_cmcrxmsg1_print;
-#else
-#define ahd_cmcrxmsg1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CMCRXMSG1", 0x91, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dchrxmsg1_print;
-#else
-#define ahd_dchrxmsg1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DCHRXMSG1", 0x91, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dchrxmsg2_print;
-#else
-#define ahd_dchrxmsg2_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DCHRXMSG2", 0x92, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_cmcrxmsg2_print;
-#else
-#define ahd_cmcrxmsg2_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CMCRXMSG2", 0x92, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_ost_print;
-#else
-#define ahd_ost_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "OST", 0x92, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_ovlyrxmsg2_print;
-#else
-#define ahd_ovlyrxmsg2_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "OVLYRXMSG2", 0x92, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dchrxmsg3_print;
-#else
-#define ahd_dchrxmsg3_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DCHRXMSG3", 0x93, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_ovlyrxmsg3_print;
-#else
-#define ahd_ovlyrxmsg3_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "OVLYRXMSG3", 0x93, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_cmcrxmsg3_print;
-#else
-#define ahd_cmcrxmsg3_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CMCRXMSG3", 0x93, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_pcixctl_print;
-#else
-#define ahd_pcixctl_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "PCIXCTL", 0x93, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_ovlyseqbcnt_print;
-#else
-#define ahd_ovlyseqbcnt_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "OVLYSEQBCNT", 0x94, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dchseqbcnt_print;
-#else
-#define ahd_dchseqbcnt_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DCHSEQBCNT", 0x94, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_cmcseqbcnt_print;
-#else
-#define ahd_cmcseqbcnt_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CMCSEQBCNT", 0x94, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_cmcspltstat0_print;
-#else
-#define ahd_cmcspltstat0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CMCSPLTSTAT0", 0x96, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dchspltstat0_print;
-#else
-#define ahd_dchspltstat0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DCHSPLTSTAT0", 0x96, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_ovlyspltstat0_print;
-#else
-#define ahd_ovlyspltstat0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "OVLYSPLTSTAT0", 0x96, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_cmcspltstat1_print;
-#else
-#define ahd_cmcspltstat1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CMCSPLTSTAT1", 0x97, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_ovlyspltstat1_print;
-#else
-#define ahd_ovlyspltstat1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "OVLYSPLTSTAT1", 0x97, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dchspltstat1_print;
-#else
-#define ahd_dchspltstat1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DCHSPLTSTAT1", 0x97, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_sgrxmsg0_print;
-#else
-#define ahd_sgrxmsg0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SGRXMSG0", 0x98, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_slvspltoutadr0_print;
-#else
-#define ahd_slvspltoutadr0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SLVSPLTOUTADR0", 0x98, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_sgrxmsg1_print;
-#else
-#define ahd_sgrxmsg1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SGRXMSG1", 0x99, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_slvspltoutadr1_print;
-#else
-#define ahd_slvspltoutadr1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SLVSPLTOUTADR1", 0x99, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_sgrxmsg2_print;
-#else
-#define ahd_sgrxmsg2_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SGRXMSG2", 0x9a, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_slvspltoutadr2_print;
-#else
-#define ahd_slvspltoutadr2_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SLVSPLTOUTADR2", 0x9a, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_sgrxmsg3_print;
-#else
-#define ahd_sgrxmsg3_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SGRXMSG3", 0x9b, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_slvspltoutadr3_print;
-#else
-#define ahd_slvspltoutadr3_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SLVSPLTOUTADR3", 0x9b, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_sgseqbcnt_print;
-#else
-#define ahd_sgseqbcnt_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SGSEQBCNT", 0x9c, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_slvspltoutattr0_print;
-#else
-#define ahd_slvspltoutattr0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SLVSPLTOUTATTR0", 0x9c, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_slvspltoutattr1_print;
-#else
-#define ahd_slvspltoutattr1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SLVSPLTOUTATTR1", 0x9d, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_slvspltoutattr2_print;
-#else
-#define ahd_slvspltoutattr2_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SLVSPLTOUTATTR2", 0x9e, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_sgspltstat0_print;
-#else
-#define ahd_sgspltstat0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SGSPLTSTAT0", 0x9e, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_sgspltstat1_print;
-#else
-#define ahd_sgspltstat1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SGSPLTSTAT1", 0x9f, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_sfunct_print;
-#else
-#define ahd_sfunct_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SFUNCT", 0x9f, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_df0pcistat_print;
-#else
-#define ahd_df0pcistat_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DF0PCISTAT", 0xa0, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_reg0_print;
-#else
-#define ahd_reg0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "REG0", 0xa0, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_df1pcistat_print;
-#else
-#define ahd_df1pcistat_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DF1PCISTAT", 0xa1, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_sgpcistat_print;
-#else
-#define ahd_sgpcistat_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SGPCISTAT", 0xa2, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_reg1_print;
-#else
-#define ahd_reg1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "REG1", 0xa2, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_cmcpcistat_print;
-#else
-#define ahd_cmcpcistat_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CMCPCISTAT", 0xa3, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_ovlypcistat_print;
-#else
-#define ahd_ovlypcistat_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "OVLYPCISTAT", 0xa4, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_reg_isr_print;
+ahd_reg_print_t ahd_reg_isr_print;
 #else
 #define ahd_reg_isr_print(regvalue, cur_col, wrap) \
     ahd_print_register(NULL, 0, "REG_ISR", 0xa4, regvalue, cur_col, wrap)
@@ -1454,13 +859,6 @@ ahd_reg_print_t ahd_sg_state_print;
     ahd_print_register(NULL, 0, "SG_STATE", 0xa6, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_msipcistat_print;
-#else
-#define ahd_msipcistat_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "MSIPCISTAT", 0xa6, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_targpcistat_print;
 #else
@@ -1468,13 +866,6 @@ ahd_reg_print_t ahd_targpcistat_print;
     ahd_print_register(NULL, 0, "TARGPCISTAT", 0xa7, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_data_count_odd_print;
-#else
-#define ahd_data_count_odd_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DATA_COUNT_ODD", 0xa7, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_scbptr_print;
 #else
@@ -1482,13 +873,6 @@ ahd_reg_print_t ahd_scbptr_print;
     ahd_print_register(NULL, 0, "SCBPTR", 0xa8, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_ccscbacnt_print;
-#else
-#define ahd_ccscbacnt_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CCSCBACNT", 0xab, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_scbautoptr_print;
 #else
@@ -1503,13 +887,6 @@ ahd_reg_print_t ahd_ccsgaddr_print;
     ahd_print_register(NULL, 0, "CCSGADDR", 0xac, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_ccscbadr_bk_print;
-#else
-#define ahd_ccscbadr_bk_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CCSCBADR_BK", 0xac, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_ccscbaddr_print;
 #else
@@ -1517,13 +894,6 @@ ahd_reg_print_t ahd_ccscbaddr_print;
     ahd_print_register(NULL, 0, "CCSCBADDR", 0xac, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_cmc_rambist_print;
-#else
-#define ahd_cmc_rambist_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "CMC_RAMBIST", 0xad, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_ccscbctl_print;
 #else
@@ -1545,13 +915,6 @@ ahd_reg_print_t ahd_ccsgram_print;
     ahd_print_register(NULL, 0, "CCSGRAM", 0xb0, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_flexadr_print;
-#else
-#define ahd_flexadr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "FLEXADR", 0xb0, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_ccscbram_print;
 #else
@@ -1559,27 +922,6 @@ ahd_reg_print_t ahd_ccscbram_print;
     ahd_print_register(NULL, 0, "CCSCBRAM", 0xb0, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_flexcnt_print;
-#else
-#define ahd_flexcnt_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "FLEXCNT", 0xb3, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_flexdmastat_print;
-#else
-#define ahd_flexdmastat_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "FLEXDMASTAT", 0xb5, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_flexdata_print;
-#else
-#define ahd_flexdata_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "FLEXDATA", 0xb6, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_brddat_print;
 #else
@@ -1622,27 +964,6 @@ ahd_reg_print_t ahd_seestat_print;
     ahd_print_register(NULL, 0, "SEESTAT", 0xbe, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_scbcnt_print;
-#else
-#define ahd_scbcnt_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SCBCNT", 0xbf, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dfwaddr_print;
-#else
-#define ahd_dfwaddr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DFWADDR", 0xc0, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dspfltrctl_print;
-#else
-#define ahd_dspfltrctl_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DSPFLTRCTL", 0xc0, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_dspdatactl_print;
 #else
@@ -1650,27 +971,6 @@ ahd_reg_print_t ahd_dspdatactl_print;
     ahd_print_register(NULL, 0, "DSPDATACTL", 0xc1, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dfraddr_print;
-#else
-#define ahd_dfraddr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DFRADDR", 0xc2, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dspreqctl_print;
-#else
-#define ahd_dspreqctl_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DSPREQCTL", 0xc2, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dspackctl_print;
-#else
-#define ahd_dspackctl_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DSPACKCTL", 0xc3, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_dfdat_print;
 #else
@@ -1692,76 +992,6 @@ ahd_reg_print_t ahd_wrtbiasctl_print;
     ahd_print_register(NULL, 0, "WRTBIASCTL", 0xc5, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_rcvrbiosctl_print;
-#else
-#define ahd_rcvrbiosctl_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "RCVRBIOSCTL", 0xc6, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_wrtbiascalc_print;
-#else
-#define ahd_wrtbiascalc_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "WRTBIASCALC", 0xc7, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_rcvrbiascalc_print;
-#else
-#define ahd_rcvrbiascalc_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "RCVRBIASCALC", 0xc8, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dfptrs_print;
-#else
-#define ahd_dfptrs_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DFPTRS", 0xc8, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_skewcalc_print;
-#else
-#define ahd_skewcalc_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SKEWCALC", 0xc9, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dfbkptr_print;
-#else
-#define ahd_dfbkptr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DFBKPTR", 0xc9, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dfdbctl_print;
-#else
-#define ahd_dfdbctl_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DFDBCTL", 0xcb, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dfscnt_print;
-#else
-#define ahd_dfscnt_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DFSCNT", 0xcc, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_dfbcnt_print;
-#else
-#define ahd_dfbcnt_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "DFBCNT", 0xce, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_ovlyaddr_print;
-#else
-#define ahd_ovlyaddr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "OVLYADDR", 0xd4, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_seqctl0_print;
 #else
@@ -1769,13 +999,6 @@ ahd_reg_print_t ahd_seqctl0_print;
     ahd_print_register(NULL, 0, "SEQCTL0", 0xd6, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_seqctl1_print;
-#else
-#define ahd_seqctl1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SEQCTL1", 0xd7, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_flags_print;
 #else
@@ -1825,20 +1048,6 @@ ahd_reg_print_t ahd_dindex_print;
     ahd_print_register(NULL, 0, "DINDEX", 0xe4, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_brkaddr0_print;
-#else
-#define ahd_brkaddr0_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "BRKADDR0", 0xe6, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_brkaddr1_print;
-#else
-#define ahd_brkaddr1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "BRKADDR1", 0xe6, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_allones_print;
 #else
@@ -1874,13 +1083,6 @@ ahd_reg_print_t ahd_dindir_print;
     ahd_print_register(NULL, 0, "DINDIR", 0xed, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_function1_print;
-#else
-#define ahd_function1_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "FUNCTION1", 0xf0, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_stack_print;
 #else
@@ -1902,13 +1104,6 @@ ahd_reg_print_t ahd_curaddr_print;
     ahd_print_register(NULL, 0, "CURADDR", 0xf4, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_lastaddr_print;
-#else
-#define ahd_lastaddr_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "LASTADDR", 0xf6, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_intvec2_addr_print;
 #else
@@ -1931,24 +1126,17 @@ ahd_reg_print_t ahd_accum_save_print;
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_waiting_scb_tails_print;
-#else
-#define ahd_waiting_scb_tails_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "WAITING_SCB_TAILS", 0x100, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_ahd_pci_config_base_print;
+ahd_reg_print_t ahd_sram_base_print;
 #else
-#define ahd_ahd_pci_config_base_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "AHD_PCI_CONFIG_BASE", 0x100, regvalue, cur_col, wrap)
+#define ahd_sram_base_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "SRAM_BASE", 0x100, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_sram_base_print;
+ahd_reg_print_t ahd_waiting_scb_tails_print;
 #else
-#define ahd_sram_base_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SRAM_BASE", 0x100, regvalue, cur_col, wrap)
+#define ahd_waiting_scb_tails_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "WAITING_SCB_TAILS", 0x100, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
@@ -2218,17 +1406,17 @@ ahd_reg_print_t ahd_mk_message_scsiid_print;
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_scb_base_print;
+ahd_reg_print_t ahd_scb_residual_datacnt_print;
 #else
-#define ahd_scb_base_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SCB_BASE", 0x180, regvalue, cur_col, wrap)
+#define ahd_scb_residual_datacnt_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "SCB_RESIDUAL_DATACNT", 0x180, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_scb_residual_datacnt_print;
+ahd_reg_print_t ahd_scb_base_print;
 #else
-#define ahd_scb_residual_datacnt_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SCB_RESIDUAL_DATACNT", 0x180, regvalue, cur_col, wrap)
+#define ahd_scb_base_print(regvalue, cur_col, wrap) \
+    ahd_print_register(NULL, 0, "SCB_BASE", 0x180, regvalue, cur_col, wrap)
 #endif
 
 #if AIC_DEBUG_REGISTERS
@@ -2245,27 +1433,6 @@ ahd_reg_print_t ahd_scb_scsi_status_print;
     ahd_print_register(NULL, 0, "SCB_SCSI_STATUS", 0x188, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_scb_target_phases_print;
-#else
-#define ahd_scb_target_phases_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SCB_TARGET_PHASES", 0x189, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_scb_target_data_dir_print;
-#else
-#define ahd_scb_target_data_dir_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SCB_TARGET_DATA_DIR", 0x18a, regvalue, cur_col, wrap)
-#endif
-
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_scb_target_itag_print;
-#else
-#define ahd_scb_target_itag_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SCB_TARGET_ITAG", 0x18b, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_scb_sense_busaddr_print;
 #else
@@ -2364,13 +1531,6 @@ ahd_reg_print_t ahd_scb_next2_print;
     ahd_print_register(NULL, 0, "SCB_NEXT2", 0x1ae, regvalue, cur_col, wrap)
 #endif
 
-#if AIC_DEBUG_REGISTERS
-ahd_reg_print_t ahd_scb_spare_print;
-#else
-#define ahd_scb_spare_print(regvalue, cur_col, wrap) \
-    ahd_print_register(NULL, 0, "SCB_SPARE", 0x1b0, regvalue, cur_col, wrap)
-#endif
-
 #if AIC_DEBUG_REGISTERS
 ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #else
@@ -2557,10 +1717,10 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 
 #define	SG_CACHE_PRE    		0x1b
 
-#define	LQIN            		0x20
-
 #define	TYPEPTR         		0x20
 
+#define	LQIN            		0x20
+
 #define	TAGPTR          		0x21
 
 #define	LUNPTR          		0x22
@@ -2620,14 +1780,6 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		SINGLECMD       	0x02
 #define		ABORTPENDING    	0x01
 
-#define	SCSBIST0        		0x39
-#define		GSBISTERR       	0x40
-#define		GSBISTDONE      	0x20
-#define		GSBISTRUN       	0x10
-#define		OSBISTERR       	0x04
-#define		OSBISTDONE      	0x02
-#define		OSBISTRUN       	0x01
-
 #define	LQCTL2          		0x39
 #define		LQIRETRY        	0x80
 #define		LQICONTINUE     	0x40
@@ -2638,10 +1790,13 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		LQOTOIDLE       	0x02
 #define		LQOPAUSE        	0x01
 
-#define	SCSBIST1        		0x3a
-#define		NTBISTERR       	0x04
-#define		NTBISTDONE      	0x02
-#define		NTBISTRUN       	0x01
+#define	SCSBIST0        		0x39
+#define		GSBISTERR       	0x40
+#define		GSBISTDONE      	0x20
+#define		GSBISTRUN       	0x10
+#define		OSBISTERR       	0x04
+#define		OSBISTDONE      	0x02
+#define		OSBISTRUN       	0x01
 
 #define	SCSISEQ0        		0x3a
 #define		TEMODEO         	0x80
@@ -2650,8 +1805,15 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		FORCEBUSFREE    	0x10
 #define		SCSIRSTO        	0x01
 
+#define	SCSBIST1        		0x3a
+#define		NTBISTERR       	0x04
+#define		NTBISTDONE      	0x02
+#define		NTBISTRUN       	0x01
+
 #define	SCSISEQ1        		0x3b
 
+#define	BUSINITID       		0x3c
+
 #define	SXFRCTL0        		0x3c
 #define		DFON            	0x80
 #define		DFPEXP          	0x40
@@ -2660,8 +1822,6 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 
 #define	DLCOUNT         		0x3c
 
-#define	BUSINITID       		0x3c
-
 #define	SXFRCTL1        		0x3d
 #define		BITBUCKET       	0x80
 #define		ENSACHK         	0x40
@@ -2686,6 +1846,8 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		CURRFIFO_1      	0x01
 #define		CURRFIFO_0      	0x00
 
+#define	MULTARGID       		0x40
+
 #define	SCSISIGO        		0x40
 #define		CDO             	0x80
 #define		IOO             	0x40
@@ -2696,8 +1858,6 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		REQO            	0x02
 #define		ACKO            	0x01
 
-#define	MULTARGID       		0x40
-
 #define	SCSISIGI        		0x41
 #define		ATNI            	0x10
 #define		SELI            	0x08
@@ -2744,15 +1904,6 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		ENAB20          	0x04
 #define		SELWIDE         	0x02
 
-#define	CLRSINT0        		0x4b
-#define		CLRSELDO        	0x40
-#define		CLRSELDI        	0x20
-#define		CLRSELINGO      	0x10
-#define		CLRIOERR        	0x08
-#define		CLROVERRUN      	0x04
-#define		CLRSPIORDY      	0x02
-#define		CLRARBDO        	0x01
-
 #define	SSTAT0          		0x4b
 #define		TARGET          	0x80
 #define		SELDO           	0x40
@@ -2772,14 +1923,14 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		ENSPIORDY       	0x02
 #define		ENARBDO         	0x01
 
-#define	CLRSINT1        		0x4c
-#define		CLRSELTIMEO     	0x80
-#define		CLRATNO         	0x40
-#define		CLRSCSIRSTI     	0x20
-#define		CLRBUSFREE      	0x08
-#define		CLRSCSIPERR     	0x04
-#define		CLRSTRB2FAST    	0x02
-#define		CLRREQINIT      	0x01
+#define	CLRSINT0        		0x4b
+#define		CLRSELDO        	0x40
+#define		CLRSELDI        	0x20
+#define		CLRSELINGO      	0x10
+#define		CLRIOERR        	0x08
+#define		CLROVERRUN      	0x04
+#define		CLRSPIORDY      	0x02
+#define		CLRARBDO        	0x01
 
 #define	SSTAT1          		0x4c
 #define		SELTO           	0x80
@@ -2791,6 +1942,15 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		STRB2FAST       	0x02
 #define		REQINIT         	0x01
 
+#define	CLRSINT1        		0x4c
+#define		CLRSELTIMEO     	0x80
+#define		CLRATNO         	0x40
+#define		CLRSCSIRSTI     	0x20
+#define		CLRBUSFREE      	0x08
+#define		CLRSCSIPERR     	0x04
+#define		CLRSTRB2FAST    	0x02
+#define		CLRREQINIT      	0x01
+
 #define	SSTAT2          		0x4d
 #define		BUSFREETIME     	0xc0
 #define		NONPACKREQ      	0x20
@@ -2838,14 +1998,6 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		LQIATNLQ        	0x02
 #define		LQIATNCMD       	0x01
 
-#define	CLRLQIINT0      		0x50
-#define		CLRLQIATNQAS    	0x20
-#define		CLRLQICRCT1     	0x10
-#define		CLRLQICRCT2     	0x08
-#define		CLRLQIBADLQT    	0x04
-#define		CLRLQIATNLQ     	0x02
-#define		CLRLQIATNCMD    	0x01
-
 #define	LQIMODE0        		0x50
 #define		ENLQIATNQASK    	0x20
 #define		ENLQICRCT1      	0x10
@@ -2854,6 +2006,14 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		ENLQIATNLQ      	0x02
 #define		ENLQIATNCMD     	0x01
 
+#define	CLRLQIINT0      		0x50
+#define		CLRLQIATNQAS    	0x20
+#define		CLRLQICRCT1     	0x10
+#define		CLRLQICRCT2     	0x08
+#define		CLRLQIBADLQT    	0x04
+#define		CLRLQIATNLQ     	0x02
+#define		CLRLQIATNCMD    	0x01
+
 #define	LQIMODE1        		0x51
 #define		ENLQIPHASE_LQ   	0x80
 #define		ENLQIPHASE_NLQ  	0x40
@@ -2976,6 +2136,8 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 
 #define	LQOSCSCTL       		0x5a
 #define		LQOH2A_VERSION  	0x80
+#define		LQOBUSETDLY     	0x40
+#define		LQONOHOLDLACK   	0x02
 #define		LQONOCHKOVER    	0x01
 
 #define	NEXTSCB         		0x5a
@@ -2998,8 +2160,6 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		CFG4ICMD        	0x02
 #define		CFG4TCMD        	0x01
 
-#define	CURRSCB         		0x5c
-
 #define	SEQIMODE        		0x5c
 #define		ENCTXTDONE      	0x40
 #define		ENSAVEPTRS      	0x20
@@ -3009,6 +2169,8 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		ENCFG4ICMD      	0x02
 #define		ENCFG4TCMD      	0x01
 
+#define	CURRSCB         		0x5c
+
 #define	MDFFSTAT        		0x5d
 #define		SHCNTNEGATIVE   	0x40
 #define		SHCNTMINUS1     	0x20
@@ -3023,29 +2185,29 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 
 #define	DFFTAG          		0x5e
 
-#define	LASTSCB         		0x5e
-
 #define	SCSITEST        		0x5e
 #define		CNTRTEST        	0x08
 #define		SEL_TXPLL_DEBUG 	0x04
 
+#define	LASTSCB         		0x5e
+
 #define	IOPDNCTL        		0x5f
 #define		DISABLE_OE      	0x80
 #define		PDN_IDIST       	0x04
 #define		PDN_DIFFSENSE   	0x01
 
+#define	DGRPCRCI        		0x60
+
 #define	SHADDR          		0x60
 
 #define	NEGOADDR        		0x60
 
-#define	DGRPCRCI        		0x60
-
 #define	NEGPERIOD       		0x61
 
-#define	PACKCRCI        		0x62
-
 #define	NEGOFFSET       		0x62
 
+#define	PACKCRCI        		0x62
+
 #define	NEGPPROPTS      		0x63
 #define		PPROPT_PACE     	0x08
 #define		PPROPT_QAS      	0x04
@@ -3066,6 +2228,7 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define	ANNEXDAT        		0x66
 
 #define	SCSCHKN         		0x66
+#define		BIDICHKDIS      	0x80
 #define		STSELSKIDDIS    	0x40
 #define		CURRFIFODEF     	0x20
 #define		WIDERESEN       	0x10
@@ -3090,6 +2253,8 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 
 #define	SELOID          		0x6b
 
+#define	FAIRNESS        		0x6c
+
 #define	PLL400CTL0      		0x6c
 #define		PLL_VCOSEL      	0x80
 #define		PLL_PWDN        	0x40
@@ -3099,8 +2264,6 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		PLL_DLPF        	0x02
 #define		PLL_ENFBM       	0x01
 
-#define	FAIRNESS        		0x6c
-
 #define	PLL400CTL1      		0x6d
 #define		PLL_CNTEN       	0x80
 #define		PLL_CNTCLR      	0x40
@@ -3112,25 +2275,25 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 
 #define	HADDR           		0x70
 
+#define	HODMAADR        		0x70
+
 #define	PLLDELAY        		0x70
 #define		SPLIT_DROP_REQ  	0x80
 
-#define	HODMAADR        		0x70
+#define	HCNT            		0x78
 
 #define	HODMACNT        		0x78
 
-#define	HCNT            		0x78
-
 #define	HODMAEN         		0x7a
 
-#define	SCBHADDR        		0x7c
-
 #define	SGHADDR         		0x7c
 
-#define	SCBHCNT         		0x84
+#define	SCBHADDR        		0x7c
 
 #define	SGHCNT          		0x84
 
+#define	SCBHCNT         		0x84
+
 #define	DFF_THRSH       		0x88
 #define		WR_DFTHRSH      	0x70
 #define		RD_DFTHRSH      	0x07
@@ -3163,6 +2326,10 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 
 #define	CMCRXMSG0       		0x90
 
+#define	OVLYRXMSG0      		0x90
+
+#define	DCHRXMSG0       		0x90
+
 #define	ROENABLE        		0x90
 #define		MSIROEN         	0x20
 #define		OVLYROEN        	0x10
@@ -3171,11 +2338,11 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		DCH1ROEN        	0x02
 #define		DCH0ROEN        	0x01
 
-#define	OVLYRXMSG0      		0x90
+#define	OVLYRXMSG1      		0x91
 
-#define	DCHRXMSG0       		0x90
+#define	CMCRXMSG1       		0x91
 
-#define	OVLYRXMSG1      		0x91
+#define	DCHRXMSG1       		0x91
 
 #define	NSENABLE        		0x91
 #define		MSINSEN         	0x20
@@ -3185,10 +2352,6 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		DCH1NSEN        	0x02
 #define		DCH0NSEN        	0x01
 
-#define	CMCRXMSG1       		0x91
-
-#define	DCHRXMSG1       		0x91
-
 #define	DCHRXMSG2       		0x92
 
 #define	CMCRXMSG2       		0x92
@@ -3212,24 +2375,24 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		TSCSERREN       	0x02
 #define		CMPABCDIS       	0x01
 
+#define	CMCSEQBCNT      		0x94
+
 #define	OVLYSEQBCNT     		0x94
 
 #define	DCHSEQBCNT      		0x94
 
-#define	CMCSEQBCNT      		0x94
-
-#define	CMCSPLTSTAT0    		0x96
-
 #define	DCHSPLTSTAT0    		0x96
 
 #define	OVLYSPLTSTAT0   		0x96
 
-#define	CMCSPLTSTAT1    		0x97
+#define	CMCSPLTSTAT0    		0x96
 
 #define	OVLYSPLTSTAT1   		0x97
 
 #define	DCHSPLTSTAT1    		0x97
 
+#define	CMCSPLTSTAT1    		0x97
+
 #define	SGRXMSG0        		0x98
 #define		CDNUM           	0xf8
 #define		CFNUM           	0x07
@@ -3257,18 +2420,15 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		TAG_NUM         	0x1f
 #define		RLXORD          	0x10
 
-#define	SGSEQBCNT       		0x9c
-
 #define	SLVSPLTOUTATTR0 		0x9c
 #define		LOWER_BCNT      	0xff
 
+#define	SGSEQBCNT       		0x9c
+
 #define	SLVSPLTOUTATTR1 		0x9d
 #define		CMPLT_DNUM      	0xf8
 #define		CMPLT_FNUM      	0x07
 
-#define	SLVSPLTOUTATTR2 		0x9e
-#define		CMPLT_BNUM      	0xff
-
 #define	SGSPLTSTAT0     		0x9e
 #define		STAETERM        	0x80
 #define		SCBCERR         	0x40
@@ -3279,6 +2439,9 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		RXSCEMSG        	0x02
 #define		RXSPLTRSP       	0x01
 
+#define	SLVSPLTOUTATTR2 		0x9e
+#define		CMPLT_BNUM      	0xff
+
 #define	SGSPLTSTAT1     		0x9f
 #define		RXDATABUCKET    	0x01
 
@@ -3334,10 +2497,10 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 
 #define	CCSGADDR        		0xac
 
-#define	CCSCBADR_BK     		0xac
-
 #define	CCSCBADDR       		0xac
 
+#define	CCSCBADR_BK     		0xac
+
 #define	CMC_RAMBIST     		0xad
 #define		SG_ELEMENT_SIZE 	0x80
 #define		SCBRAMBIST_FAIL 	0x40
@@ -3391,9 +2554,9 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define	SEEDAT          		0xbc
 
 #define	SEECTL          		0xbe
+#define		SEEOP_EWDS      	0x40
 #define		SEEOP_WALL      	0x40
 #define		SEEOP_EWEN      	0x40
-#define		SEEOP_EWDS      	0x40
 #define		SEEOPCODE       	0x70
 #define		SEERST          	0x02
 #define		SEESTART        	0x01
@@ -3410,25 +2573,25 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 
 #define	SCBCNT          		0xbf
 
-#define	DFWADDR         		0xc0
-
 #define	DSPFLTRCTL      		0xc0
 #define		FLTRDISABLE     	0x20
 #define		EDGESENSE       	0x10
 #define		DSPFCNTSEL      	0x0f
 
+#define	DFWADDR         		0xc0
+
 #define	DSPDATACTL      		0xc1
 #define		BYPASSENAB      	0x80
 #define		DESQDIS         	0x10
 #define		RCVROFFSTDIS    	0x04
 #define		XMITOFFSTDIS    	0x02
 
-#define	DFRADDR         		0xc2
-
 #define	DSPREQCTL       		0xc2
 #define		MANREQCTL       	0xc0
 #define		MANREQDLY       	0x3f
 
+#define	DFRADDR         		0xc2
+
 #define	DSPACKCTL       		0xc3
 #define		MANACKCTL       	0xc0
 #define		MANACKDLY       	0x3f
@@ -3449,14 +2612,14 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 
 #define	WRTBIASCALC     		0xc7
 
-#define	RCVRBIASCALC    		0xc8
-
 #define	DFPTRS          		0xc8
 
-#define	SKEWCALC        		0xc9
+#define	RCVRBIASCALC    		0xc8
 
 #define	DFBKPTR         		0xc9
 
+#define	SKEWCALC        		0xc9
+
 #define	DFDBCTL         		0xcb
 #define		DFF_CIO_WR_RDY  	0x20
 #define		DFF_CIO_RD_RDY  	0x10
@@ -3541,12 +2704,12 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 
 #define	ACCUM_SAVE      		0xfa
 
-#define	WAITING_SCB_TAILS		0x100
-
 #define	AHD_PCI_CONFIG_BASE		0x100
 
 #define	SRAM_BASE       		0x100
 
+#define	WAITING_SCB_TAILS		0x100
+
 #define	WAITING_TID_HEAD		0x120
 
 #define	WAITING_TID_TAIL		0x122
@@ -3575,8 +2738,8 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define		PRELOADEN       	0x80
 #define		WIDEODD         	0x40
 #define		SCSIEN          	0x20
-#define		SDMAEN          	0x10
 #define		SDMAENACK       	0x10
+#define		SDMAEN          	0x10
 #define		HDMAEN          	0x08
 #define		HDMAENACK       	0x08
 #define		DIRECTION       	0x04
@@ -3674,12 +2837,12 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 
 #define	MK_MESSAGE_SCSIID		0x162
 
-#define	SCB_BASE        		0x180
-
 #define	SCB_RESIDUAL_DATACNT		0x180
 #define	SCB_CDB_STORE   		0x180
 #define	SCB_HOST_CDB_PTR		0x180
 
+#define	SCB_BASE        		0x180
+
 #define	SCB_RESIDUAL_SGPTR		0x184
 #define		SG_ADDR_MASK    	0xf8
 #define		SG_OVERRUN_RESID	0x02
@@ -3747,6 +2910,17 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define	SCB_DISCONNECTED_LISTS		0x1b8
 
 
+#define	CMD_GROUP_CODE_SHIFT	0x05
+#define	STIMESEL_MIN	0x18
+#define	STIMESEL_SHIFT	0x03
+#define	INVALID_ADDR	0x80
+#define	AHD_PRECOMP_MASK	0x07
+#define	TARGET_DATA_IN	0x01
+#define	CCSCBADDR_MAX	0x80
+#define	NUMDSPS 	0x14
+#define	SEEOP_EWEN_ADDR	0xc0
+#define	AHD_ANNEXCOL_PER_DEV0	0x04
+#define	DST_MODE_SHIFT	0x04
 #define	AHD_TIMER_MAX_US	0x18ffe7
 #define	AHD_TIMER_MAX_TICKS	0xffff
 #define	AHD_SENSE_BUFSIZE	0x100
@@ -3781,43 +2955,32 @@ ahd_reg_print_t ahd_scb_disconnected_lists_print;
 #define	LUNLEN_SINGLE_LEVEL_LUN	0x0f
 #define	NVRAM_SCB_OFFSET	0x2c
 #define	STATUS_PKT_SENSE	0xff
-#define	CMD_GROUP_CODE_SHIFT	0x05
 #define	MAX_OFFSET_PACED_BUG	0x7f
 #define	STIMESEL_BUG_ADJ	0x08
-#define	STIMESEL_MIN	0x18
-#define	STIMESEL_SHIFT	0x03
 #define	CCSGRAM_MAXSEGS	0x10
-#define	INVALID_ADDR	0x80
 #define	SEEOP_ERAL_ADDR	0x80
 #define	AHD_SLEWRATE_DEF_REVB	0x08
 #define	AHD_PRECOMP_CUTBACK_17	0x04
-#define	AHD_PRECOMP_MASK	0x07
 #define	SRC_MODE_SHIFT	0x00
 #define	PKT_OVERRUN_BUFSIZE	0x200
 #define	SCB_TRANSFER_SIZE_1BYTE_LUN	0x30
-#define	TARGET_DATA_IN	0x01
 #define	HOST_MSG	0xff
 #define	MAX_OFFSET	0xfe
 #define	BUS_16_BIT	0x01
-#define	CCSCBADDR_MAX	0x80
-#define	NUMDSPS 	0x14
-#define	SEEOP_EWEN_ADDR	0xc0
-#define	AHD_ANNEXCOL_PER_DEV0	0x04
-#define	DST_MODE_SHIFT	0x04
 
 
 /* Downloaded Constant Definitions */
+#define	SG_SIZEOF	0x04
+#define	SG_PREFETCH_ALIGN_MASK	0x02
+#define	SG_PREFETCH_CNT_LIMIT	0x01
 #define	CACHELINE_MASK	0x07
 #define	SCB_TRANSFER_SIZE	0x06
 #define	PKT_OVERRUN_BUFOFFSET	0x05
-#define	SG_SIZEOF	0x04
 #define	SG_PREFETCH_ADDR_MASK	0x03
-#define	SG_PREFETCH_ALIGN_MASK	0x02
-#define	SG_PREFETCH_CNT_LIMIT	0x01
 #define	SG_PREFETCH_CNT	0x00
 #define	DOWNLOAD_CONST_COUNT	0x08
 
 
 /* Exported Labels */
-#define	LABEL_seq_isr 	0x28f
 #define	LABEL_timer_isr	0x28b
+#define	LABEL_seq_isr 	0x28f
diff --git a/trunk/drivers/scsi/aic7xxx/aic79xx_reg_print.c_shipped b/trunk/drivers/scsi/aic7xxx/aic79xx_reg_print.c_shipped
index db38a61a8cb4..c4c8a96bf5a3 100644
--- a/trunk/drivers/scsi/aic7xxx/aic79xx_reg_print.c_shipped
+++ b/trunk/drivers/scsi/aic7xxx/aic79xx_reg_print.c_shipped
@@ -8,7 +8,7 @@
 
 #include "aic79xx_osm.h"
 
-static ahd_reg_parse_entry_t MODE_PTR_parse_table[] = {
+static const ahd_reg_parse_entry_t MODE_PTR_parse_table[] = {
 	{ "SRC_MODE",		0x07, 0x07 },
 	{ "DST_MODE",		0x70, 0x70 }
 };
@@ -20,7 +20,7 @@ ahd_mode_ptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x00, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t INTSTAT_parse_table[] = {
+static const ahd_reg_parse_entry_t INTSTAT_parse_table[] = {
 	{ "SPLTINT",		0x01, 0x01 },
 	{ "CMDCMPLT",		0x02, 0x02 },
 	{ "SEQINT",		0x04, 0x04 },
@@ -39,7 +39,7 @@ ahd_intstat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x01, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SEQINTCODE_parse_table[] = {
+static const ahd_reg_parse_entry_t SEQINTCODE_parse_table[] = {
 	{ "NO_SEQINT",		0x00, 0xff },
 	{ "BAD_PHASE",		0x01, 0xff },
 	{ "SEND_REJECT",	0x02, 0xff },
@@ -76,7 +76,7 @@ ahd_seqintcode_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x02, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t CLRINT_parse_table[] = {
+static const ahd_reg_parse_entry_t CLRINT_parse_table[] = {
 	{ "CLRSPLTINT",		0x01, 0x01 },
 	{ "CLRCMDINT",		0x02, 0x02 },
 	{ "CLRSEQINT",		0x04, 0x04 },
@@ -94,7 +94,7 @@ ahd_clrint_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x03, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t ERROR_parse_table[] = {
+static const ahd_reg_parse_entry_t ERROR_parse_table[] = {
 	{ "DSCTMOUT",		0x02, 0x02 },
 	{ "ILLOPCODE",		0x04, 0x04 },
 	{ "SQPARERR",		0x08, 0x08 },
@@ -111,24 +111,7 @@ ahd_error_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x04, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t CLRERR_parse_table[] = {
-	{ "CLRDSCTMOUT",	0x02, 0x02 },
-	{ "CLRILLOPCODE",	0x04, 0x04 },
-	{ "CLRSQPARERR",	0x08, 0x08 },
-	{ "CLRDPARERR",		0x10, 0x10 },
-	{ "CLRMPARERR",		0x20, 0x20 },
-	{ "CLRCIOACCESFAIL",	0x40, 0x40 },
-	{ "CLRCIOPARERR",	0x80, 0x80 }
-};
-
-int
-ahd_clrerr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(CLRERR_parse_table, 7, "CLRERR",
-	    0x04, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t HCNTRL_parse_table[] = {
+static const ahd_reg_parse_entry_t HCNTRL_parse_table[] = {
 	{ "CHIPRST",		0x01, 0x01 },
 	{ "CHIPRSTACK",		0x01, 0x01 },
 	{ "INTEN",		0x02, 0x02 },
@@ -160,7 +143,7 @@ ahd_hescb_qoff_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x08, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t HS_MAILBOX_parse_table[] = {
+static const ahd_reg_parse_entry_t HS_MAILBOX_parse_table[] = {
 	{ "ENINT_COALESCE",	0x40, 0x40 },
 	{ "HOST_TQINPOS",	0x80, 0x80 }
 };
@@ -172,7 +155,7 @@ ahd_hs_mailbox_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x0b, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SEQINTSTAT_parse_table[] = {
+static const ahd_reg_parse_entry_t SEQINTSTAT_parse_table[] = {
 	{ "SEQ_SPLTINT",	0x01, 0x01 },
 	{ "SEQ_PCIINT",		0x02, 0x02 },
 	{ "SEQ_SCSIINT",	0x04, 0x04 },
@@ -187,7 +170,7 @@ ahd_seqintstat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x0c, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t CLRSEQINTSTAT_parse_table[] = {
+static const ahd_reg_parse_entry_t CLRSEQINTSTAT_parse_table[] = {
 	{ "CLRSEQ_SPLTINT",	0x01, 0x01 },
 	{ "CLRSEQ_PCIINT",	0x02, 0x02 },
 	{ "CLRSEQ_SCSIINT",	0x04, 0x04 },
@@ -230,7 +213,7 @@ ahd_sdscb_qoff_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x14, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t QOFF_CTLSTA_parse_table[] = {
+static const ahd_reg_parse_entry_t QOFF_CTLSTA_parse_table[] = {
 	{ "SCB_QSIZE_4",	0x00, 0x0f },
 	{ "SCB_QSIZE_8",	0x01, 0x0f },
 	{ "SCB_QSIZE_16",	0x02, 0x0f },
@@ -258,7 +241,7 @@ ahd_qoff_ctlsta_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x16, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t INTCTL_parse_table[] = {
+static const ahd_reg_parse_entry_t INTCTL_parse_table[] = {
 	{ "SPLTINTEN",		0x01, 0x01 },
 	{ "SEQINTEN",		0x02, 0x02 },
 	{ "SCSIINTEN",		0x04, 0x04 },
@@ -276,7 +259,7 @@ ahd_intctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x18, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t DFCNTRL_parse_table[] = {
+static const ahd_reg_parse_entry_t DFCNTRL_parse_table[] = {
 	{ "DIRECTIONEN",	0x01, 0x01 },
 	{ "FIFOFLUSH",		0x02, 0x02 },
 	{ "FIFOFLUSHACK",	0x02, 0x02 },
@@ -297,7 +280,7 @@ ahd_dfcntrl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x19, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t DSCOMMAND0_parse_table[] = {
+static const ahd_reg_parse_entry_t DSCOMMAND0_parse_table[] = {
 	{ "CIOPARCKEN",		0x01, 0x01 },
 	{ "DISABLE_TWATE",	0x02, 0x02 },
 	{ "EXTREQLCK",		0x10, 0x10 },
@@ -313,7 +296,7 @@ ahd_dscommand0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x19, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t DFSTATUS_parse_table[] = {
+static const ahd_reg_parse_entry_t DFSTATUS_parse_table[] = {
 	{ "FIFOEMP",		0x01, 0x01 },
 	{ "FIFOFULL",		0x02, 0x02 },
 	{ "DFTHRESH",		0x04, 0x04 },
@@ -330,7 +313,7 @@ ahd_dfstatus_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x1a, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SG_CACHE_SHADOW_parse_table[] = {
+static const ahd_reg_parse_entry_t SG_CACHE_SHADOW_parse_table[] = {
 	{ "LAST_SEG_DONE",	0x01, 0x01 },
 	{ "LAST_SEG",		0x02, 0x02 },
 	{ "ODD_SEG",		0x04, 0x04 },
@@ -344,20 +327,7 @@ ahd_sg_cache_shadow_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x1b, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t ARBCTL_parse_table[] = {
-	{ "USE_TIME",		0x07, 0x07 },
-	{ "RETRY_SWEN",		0x08, 0x08 },
-	{ "RESET_HARB",		0x80, 0x80 }
-};
-
-int
-ahd_arbctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(ARBCTL_parse_table, 3, "ARBCTL",
-	    0x1b, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SG_CACHE_PRE_parse_table[] = {
+static const ahd_reg_parse_entry_t SG_CACHE_PRE_parse_table[] = {
 	{ "LAST_SEG",		0x02, 0x02 },
 	{ "ODD_SEG",		0x04, 0x04 },
 	{ "SG_ADDR_MASK",	0xf8, 0xf8 }
@@ -377,20 +347,6 @@ ahd_lqin_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x20, regvalue, cur_col, wrap));
 }
 
-int
-ahd_typeptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "TYPEPTR",
-	    0x20, regvalue, cur_col, wrap));
-}
-
-int
-ahd_tagptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "TAGPTR",
-	    0x21, regvalue, cur_col, wrap));
-}
-
 int
 ahd_lunptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -398,20 +354,6 @@ ahd_lunptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x22, regvalue, cur_col, wrap));
 }
 
-int
-ahd_datalenptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "DATALENPTR",
-	    0x23, regvalue, cur_col, wrap));
-}
-
-int
-ahd_statlenptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "STATLENPTR",
-	    0x24, regvalue, cur_col, wrap));
-}
-
 int
 ahd_cmdlenptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -447,13 +389,6 @@ ahd_qnextptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x29, regvalue, cur_col, wrap));
 }
 
-int
-ahd_idptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "IDPTR",
-	    0x2a, regvalue, cur_col, wrap));
-}
-
 int
 ahd_abrtbyteptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -468,28 +403,7 @@ ahd_abrtbitptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x2c, regvalue, cur_col, wrap));
 }
 
-int
-ahd_maxcmdbytes_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "MAXCMDBYTES",
-	    0x2d, regvalue, cur_col, wrap));
-}
-
-int
-ahd_maxcmd2rcv_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "MAXCMD2RCV",
-	    0x2e, regvalue, cur_col, wrap));
-}
-
-int
-ahd_shortthresh_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "SHORTTHRESH",
-	    0x2f, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t LUNLEN_parse_table[] = {
+static const ahd_reg_parse_entry_t LUNLEN_parse_table[] = {
 	{ "ILUNLEN",		0x0f, 0x0f },
 	{ "TLUNLEN",		0xf0, 0xf0 }
 };
@@ -522,49 +436,7 @@ ahd_maxcmdcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x33, regvalue, cur_col, wrap));
 }
 
-int
-ahd_lqrsvd01_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "LQRSVD01",
-	    0x34, regvalue, cur_col, wrap));
-}
-
-int
-ahd_lqrsvd16_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "LQRSVD16",
-	    0x35, regvalue, cur_col, wrap));
-}
-
-int
-ahd_lqrsvd17_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "LQRSVD17",
-	    0x36, regvalue, cur_col, wrap));
-}
-
-int
-ahd_cmdrsvd0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "CMDRSVD0",
-	    0x37, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t LQCTL0_parse_table[] = {
-	{ "LQ0INITGCLT",	0x03, 0x03 },
-	{ "LQ0TARGCLT",		0x0c, 0x0c },
-	{ "LQIINITGCLT",	0x30, 0x30 },
-	{ "LQITARGCLT",		0xc0, 0xc0 }
-};
-
-int
-ahd_lqctl0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(LQCTL0_parse_table, 4, "LQCTL0",
-	    0x38, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t LQCTL1_parse_table[] = {
+static const ahd_reg_parse_entry_t LQCTL1_parse_table[] = {
 	{ "ABORTPENDING",	0x01, 0x01 },
 	{ "SINGLECMD",		0x02, 0x02 },
 	{ "PCI2PCI",		0x04, 0x04 }
@@ -577,23 +449,7 @@ ahd_lqctl1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x38, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCSBIST0_parse_table[] = {
-	{ "OSBISTRUN",		0x01, 0x01 },
-	{ "OSBISTDONE",		0x02, 0x02 },
-	{ "OSBISTERR",		0x04, 0x04 },
-	{ "GSBISTRUN",		0x10, 0x10 },
-	{ "GSBISTDONE",		0x20, 0x20 },
-	{ "GSBISTERR",		0x40, 0x40 }
-};
-
-int
-ahd_scsbist0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SCSBIST0_parse_table, 6, "SCSBIST0",
-	    0x39, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t LQCTL2_parse_table[] = {
+static const ahd_reg_parse_entry_t LQCTL2_parse_table[] = {
 	{ "LQOPAUSE",		0x01, 0x01 },
 	{ "LQOTOIDLE",		0x02, 0x02 },
 	{ "LQOCONTINUE",	0x04, 0x04 },
@@ -611,20 +467,7 @@ ahd_lqctl2_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x39, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCSBIST1_parse_table[] = {
-	{ "NTBISTRUN",		0x01, 0x01 },
-	{ "NTBISTDONE",		0x02, 0x02 },
-	{ "NTBISTERR",		0x04, 0x04 }
-};
-
-int
-ahd_scsbist1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SCSBIST1_parse_table, 3, "SCSBIST1",
-	    0x3a, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SCSISEQ0_parse_table[] = {
+static const ahd_reg_parse_entry_t SCSISEQ0_parse_table[] = {
 	{ "SCSIRSTO",		0x01, 0x01 },
 	{ "FORCEBUSFREE",	0x10, 0x10 },
 	{ "ENARBO",		0x20, 0x20 },
@@ -639,7 +482,7 @@ ahd_scsiseq0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x3a, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCSISEQ1_parse_table[] = {
+static const ahd_reg_parse_entry_t SCSISEQ1_parse_table[] = {
 	{ "ALTSTIM",		0x01, 0x01 },
 	{ "ENAUTOATNP",		0x02, 0x02 },
 	{ "MANUALP",		0x0c, 0x0c },
@@ -655,7 +498,7 @@ ahd_scsiseq1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x3b, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SXFRCTL0_parse_table[] = {
+static const ahd_reg_parse_entry_t SXFRCTL0_parse_table[] = {
 	{ "SPIOEN",		0x08, 0x08 },
 	{ "BIOSCANCELEN",	0x10, 0x10 },
 	{ "DFPEXP",		0x40, 0x40 },
@@ -669,21 +512,7 @@ ahd_sxfrctl0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x3c, regvalue, cur_col, wrap));
 }
 
-int
-ahd_dlcount_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "DLCOUNT",
-	    0x3c, regvalue, cur_col, wrap));
-}
-
-int
-ahd_businitid_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "BUSINITID",
-	    0x3c, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SXFRCTL1_parse_table[] = {
+static const ahd_reg_parse_entry_t SXFRCTL1_parse_table[] = {
 	{ "STPWEN",		0x01, 0x01 },
 	{ "ACTNEGEN",		0x02, 0x02 },
 	{ "ENSTIMER",		0x04, 0x04 },
@@ -700,27 +529,7 @@ ahd_sxfrctl1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x3d, regvalue, cur_col, wrap));
 }
 
-int
-ahd_bustargid_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "BUSTARGID",
-	    0x3e, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SXFRCTL2_parse_table[] = {
-	{ "ASU",		0x07, 0x07 },
-	{ "CMDDMAEN",		0x08, 0x08 },
-	{ "AUTORSTDIS",		0x10, 0x10 }
-};
-
-int
-ahd_sxfrctl2_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SXFRCTL2_parse_table, 3, "SXFRCTL2",
-	    0x3e, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t DFFSTAT_parse_table[] = {
+static const ahd_reg_parse_entry_t DFFSTAT_parse_table[] = {
 	{ "CURRFIFO_0",		0x00, 0x03 },
 	{ "CURRFIFO_1",		0x01, 0x03 },
 	{ "CURRFIFO_NONE",	0x03, 0x03 },
@@ -736,7 +545,14 @@ ahd_dffstat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x3f, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCSISIGO_parse_table[] = {
+int
+ahd_multargid_print(u_int regvalue, u_int *cur_col, u_int wrap)
+{
+	return (ahd_print_register(NULL, 0, "MULTARGID",
+	    0x40, regvalue, cur_col, wrap));
+}
+
+static const ahd_reg_parse_entry_t SCSISIGO_parse_table[] = {
 	{ "P_DATAOUT",		0x00, 0xe0 },
 	{ "P_DATAOUT_DT",	0x20, 0xe0 },
 	{ "P_DATAIN",		0x40, 0xe0 },
@@ -763,14 +579,7 @@ ahd_scsisigo_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x40, regvalue, cur_col, wrap));
 }
 
-int
-ahd_multargid_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "MULTARGID",
-	    0x40, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SCSISIGI_parse_table[] = {
+static const ahd_reg_parse_entry_t SCSISIGI_parse_table[] = {
 	{ "P_DATAOUT",		0x00, 0xe0 },
 	{ "P_DATAOUT_DT",	0x20, 0xe0 },
 	{ "P_DATAIN",		0x40, 0xe0 },
@@ -797,7 +606,7 @@ ahd_scsisigi_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x41, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCSIPHASE_parse_table[] = {
+static const ahd_reg_parse_entry_t SCSIPHASE_parse_table[] = {
 	{ "DATA_OUT_PHASE",	0x01, 0x03 },
 	{ "DATA_IN_PHASE",	0x02, 0x03 },
 	{ "DATA_PHASE_MASK",	0x03, 0x03 },
@@ -814,13 +623,6 @@ ahd_scsiphase_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x42, regvalue, cur_col, wrap));
 }
 
-int
-ahd_scsidat0_img_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "SCSIDAT0_IMG",
-	    0x43, regvalue, cur_col, wrap));
-}
-
 int
 ahd_scsidat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -835,7 +637,7 @@ ahd_scsibus_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x46, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t TARGIDIN_parse_table[] = {
+static const ahd_reg_parse_entry_t TARGIDIN_parse_table[] = {
 	{ "TARGID",		0x0f, 0x0f },
 	{ "CLKOUT",		0x80, 0x80 }
 };
@@ -847,7 +649,7 @@ ahd_targidin_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x48, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SELID_parse_table[] = {
+static const ahd_reg_parse_entry_t SELID_parse_table[] = {
 	{ "ONEBIT",		0x08, 0x08 },
 	{ "SELID_MASK",		0xf0, 0xf0 }
 };
@@ -859,7 +661,7 @@ ahd_selid_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x49, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t OPTIONMODE_parse_table[] = {
+static const ahd_reg_parse_entry_t OPTIONMODE_parse_table[] = {
 	{ "AUTO_MSGOUT_DE",	0x02, 0x02 },
 	{ "ENDGFORMCHK",	0x04, 0x04 },
 	{ "BUSFREEREV",		0x10, 0x10 },
@@ -876,7 +678,7 @@ ahd_optionmode_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x4a, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SBLKCTL_parse_table[] = {
+static const ahd_reg_parse_entry_t SBLKCTL_parse_table[] = {
 	{ "SELWIDE",		0x02, 0x02 },
 	{ "ENAB20",		0x04, 0x04 },
 	{ "ENAB40",		0x08, 0x08 },
@@ -891,24 +693,7 @@ ahd_sblkctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x4a, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t CLRSINT0_parse_table[] = {
-	{ "CLRARBDO",		0x01, 0x01 },
-	{ "CLRSPIORDY",		0x02, 0x02 },
-	{ "CLROVERRUN",		0x04, 0x04 },
-	{ "CLRIOERR",		0x08, 0x08 },
-	{ "CLRSELINGO",		0x10, 0x10 },
-	{ "CLRSELDI",		0x20, 0x20 },
-	{ "CLRSELDO",		0x40, 0x40 }
-};
-
-int
-ahd_clrsint0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(CLRSINT0_parse_table, 7, "CLRSINT0",
-	    0x4b, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SSTAT0_parse_table[] = {
+static const ahd_reg_parse_entry_t SSTAT0_parse_table[] = {
 	{ "ARBDO",		0x01, 0x01 },
 	{ "SPIORDY",		0x02, 0x02 },
 	{ "OVERRUN",		0x04, 0x04 },
@@ -926,7 +711,7 @@ ahd_sstat0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x4b, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SIMODE0_parse_table[] = {
+static const ahd_reg_parse_entry_t SIMODE0_parse_table[] = {
 	{ "ENARBDO",		0x01, 0x01 },
 	{ "ENSPIORDY",		0x02, 0x02 },
 	{ "ENOVERRUN",		0x04, 0x04 },
@@ -943,24 +728,24 @@ ahd_simode0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x4b, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t CLRSINT1_parse_table[] = {
-	{ "CLRREQINIT",		0x01, 0x01 },
-	{ "CLRSTRB2FAST",	0x02, 0x02 },
-	{ "CLRSCSIPERR",	0x04, 0x04 },
-	{ "CLRBUSFREE",		0x08, 0x08 },
-	{ "CLRSCSIRSTI",	0x20, 0x20 },
-	{ "CLRATNO",		0x40, 0x40 },
-	{ "CLRSELTIMEO",	0x80, 0x80 }
+static const ahd_reg_parse_entry_t CLRSINT0_parse_table[] = {
+	{ "CLRARBDO",		0x01, 0x01 },
+	{ "CLRSPIORDY",		0x02, 0x02 },
+	{ "CLROVERRUN",		0x04, 0x04 },
+	{ "CLRIOERR",		0x08, 0x08 },
+	{ "CLRSELINGO",		0x10, 0x10 },
+	{ "CLRSELDI",		0x20, 0x20 },
+	{ "CLRSELDO",		0x40, 0x40 }
 };
 
 int
-ahd_clrsint1_print(u_int regvalue, u_int *cur_col, u_int wrap)
+ahd_clrsint0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
-	return (ahd_print_register(CLRSINT1_parse_table, 7, "CLRSINT1",
-	    0x4c, regvalue, cur_col, wrap));
+	return (ahd_print_register(CLRSINT0_parse_table, 7, "CLRSINT0",
+	    0x4b, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SSTAT1_parse_table[] = {
+static const ahd_reg_parse_entry_t SSTAT1_parse_table[] = {
 	{ "REQINIT",		0x01, 0x01 },
 	{ "STRB2FAST",		0x02, 0x02 },
 	{ "SCSIPERR",		0x04, 0x04 },
@@ -978,7 +763,24 @@ ahd_sstat1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x4c, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SSTAT2_parse_table[] = {
+static const ahd_reg_parse_entry_t CLRSINT1_parse_table[] = {
+	{ "CLRREQINIT",		0x01, 0x01 },
+	{ "CLRSTRB2FAST",	0x02, 0x02 },
+	{ "CLRSCSIPERR",	0x04, 0x04 },
+	{ "CLRBUSFREE",		0x08, 0x08 },
+	{ "CLRSCSIRSTI",	0x20, 0x20 },
+	{ "CLRATNO",		0x40, 0x40 },
+	{ "CLRSELTIMEO",	0x80, 0x80 }
+};
+
+int
+ahd_clrsint1_print(u_int regvalue, u_int *cur_col, u_int wrap)
+{
+	return (ahd_print_register(CLRSINT1_parse_table, 7, "CLRSINT1",
+	    0x4c, regvalue, cur_col, wrap));
+}
+
+static const ahd_reg_parse_entry_t SSTAT2_parse_table[] = {
 	{ "BUSFREE_LQO",	0x40, 0xc0 },
 	{ "BUSFREE_DFF0",	0x80, 0xc0 },
 	{ "BUSFREE_DFF1",	0xc0, 0xc0 },
@@ -998,20 +800,7 @@ ahd_sstat2_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x4d, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SIMODE2_parse_table[] = {
-	{ "ENDMADONE",		0x01, 0x01 },
-	{ "ENSDONE",		0x02, 0x02 },
-	{ "ENWIDE_RES",		0x04, 0x04 }
-};
-
-int
-ahd_simode2_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SIMODE2_parse_table, 3, "SIMODE2",
-	    0x4d, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t CLRSINT2_parse_table[] = {
+static const ahd_reg_parse_entry_t CLRSINT2_parse_table[] = {
 	{ "CLRDMADONE",		0x01, 0x01 },
 	{ "CLRSDONE",		0x02, 0x02 },
 	{ "CLRWIDE_RES",	0x04, 0x04 },
@@ -1025,7 +814,7 @@ ahd_clrsint2_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x4d, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t PERRDIAG_parse_table[] = {
+static const ahd_reg_parse_entry_t PERRDIAG_parse_table[] = {
 	{ "DTERR",		0x01, 0x01 },
 	{ "DGFORMERR",		0x02, 0x02 },
 	{ "CRCERR",		0x04, 0x04 },
@@ -1064,7 +853,7 @@ ahd_lqostate_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x4f, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t LQISTAT0_parse_table[] = {
+static const ahd_reg_parse_entry_t LQISTAT0_parse_table[] = {
 	{ "LQIATNCMD",		0x01, 0x01 },
 	{ "LQIATNLQ",		0x02, 0x02 },
 	{ "LQIBADLQT",		0x04, 0x04 },
@@ -1080,23 +869,7 @@ ahd_lqistat0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x50, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t CLRLQIINT0_parse_table[] = {
-	{ "CLRLQIATNCMD",	0x01, 0x01 },
-	{ "CLRLQIATNLQ",	0x02, 0x02 },
-	{ "CLRLQIBADLQT",	0x04, 0x04 },
-	{ "CLRLQICRCT2",	0x08, 0x08 },
-	{ "CLRLQICRCT1",	0x10, 0x10 },
-	{ "CLRLQIATNQAS",	0x20, 0x20 }
-};
-
-int
-ahd_clrlqiint0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(CLRLQIINT0_parse_table, 6, "CLRLQIINT0",
-	    0x50, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t LQIMODE0_parse_table[] = {
+static const ahd_reg_parse_entry_t LQIMODE0_parse_table[] = {
 	{ "ENLQIATNCMD",	0x01, 0x01 },
 	{ "ENLQIATNLQ",		0x02, 0x02 },
 	{ "ENLQIBADLQT",	0x04, 0x04 },
@@ -1112,7 +885,23 @@ ahd_lqimode0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x50, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t LQIMODE1_parse_table[] = {
+static const ahd_reg_parse_entry_t CLRLQIINT0_parse_table[] = {
+	{ "CLRLQIATNCMD",	0x01, 0x01 },
+	{ "CLRLQIATNLQ",	0x02, 0x02 },
+	{ "CLRLQIBADLQT",	0x04, 0x04 },
+	{ "CLRLQICRCT2",	0x08, 0x08 },
+	{ "CLRLQICRCT1",	0x10, 0x10 },
+	{ "CLRLQIATNQAS",	0x20, 0x20 }
+};
+
+int
+ahd_clrlqiint0_print(u_int regvalue, u_int *cur_col, u_int wrap)
+{
+	return (ahd_print_register(CLRLQIINT0_parse_table, 6, "CLRLQIINT0",
+	    0x50, regvalue, cur_col, wrap));
+}
+
+static const ahd_reg_parse_entry_t LQIMODE1_parse_table[] = {
 	{ "ENLQIOVERI_NLQ",	0x01, 0x01 },
 	{ "ENLQIOVERI_LQ",	0x02, 0x02 },
 	{ "ENLQIBADLQI",	0x04, 0x04 },
@@ -1130,7 +919,7 @@ ahd_lqimode1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x51, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t LQISTAT1_parse_table[] = {
+static const ahd_reg_parse_entry_t LQISTAT1_parse_table[] = {
 	{ "LQIOVERI_NLQ",	0x01, 0x01 },
 	{ "LQIOVERI_LQ",	0x02, 0x02 },
 	{ "LQIBADLQI",		0x04, 0x04 },
@@ -1148,7 +937,7 @@ ahd_lqistat1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x51, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t CLRLQIINT1_parse_table[] = {
+static const ahd_reg_parse_entry_t CLRLQIINT1_parse_table[] = {
 	{ "CLRLQIOVERI_NLQ",	0x01, 0x01 },
 	{ "CLRLQIOVERI_LQ",	0x02, 0x02 },
 	{ "CLRLQIBADLQI",	0x04, 0x04 },
@@ -1166,7 +955,7 @@ ahd_clrlqiint1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x51, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t LQISTAT2_parse_table[] = {
+static const ahd_reg_parse_entry_t LQISTAT2_parse_table[] = {
 	{ "LQIGSAVAIL",		0x01, 0x01 },
 	{ "LQISTOPCMD",		0x02, 0x02 },
 	{ "LQISTOPLQ",		0x04, 0x04 },
@@ -1184,7 +973,7 @@ ahd_lqistat2_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x52, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SSTAT3_parse_table[] = {
+static const ahd_reg_parse_entry_t SSTAT3_parse_table[] = {
 	{ "OSRAMPERR",		0x01, 0x01 },
 	{ "NTRAMPERR",		0x02, 0x02 }
 };
@@ -1196,7 +985,7 @@ ahd_sstat3_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x53, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SIMODE3_parse_table[] = {
+static const ahd_reg_parse_entry_t SIMODE3_parse_table[] = {
 	{ "ENOSRAMPERR",	0x01, 0x01 },
 	{ "ENNTRAMPERR",	0x02, 0x02 }
 };
@@ -1208,7 +997,7 @@ ahd_simode3_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x53, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t CLRSINT3_parse_table[] = {
+static const ahd_reg_parse_entry_t CLRSINT3_parse_table[] = {
 	{ "CLROSRAMPERR",	0x01, 0x01 },
 	{ "CLRNTRAMPERR",	0x02, 0x02 }
 };
@@ -1220,7 +1009,7 @@ ahd_clrsint3_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x53, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t LQOSTAT0_parse_table[] = {
+static const ahd_reg_parse_entry_t LQOSTAT0_parse_table[] = {
 	{ "LQOTCRC",		0x01, 0x01 },
 	{ "LQOATNPKT",		0x02, 0x02 },
 	{ "LQOATNLQ",		0x04, 0x04 },
@@ -1235,7 +1024,7 @@ ahd_lqostat0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x54, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t CLRLQOINT0_parse_table[] = {
+static const ahd_reg_parse_entry_t CLRLQOINT0_parse_table[] = {
 	{ "CLRLQOTCRC",		0x01, 0x01 },
 	{ "CLRLQOATNPKT",	0x02, 0x02 },
 	{ "CLRLQOATNLQ",	0x04, 0x04 },
@@ -1250,7 +1039,7 @@ ahd_clrlqoint0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x54, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t LQOMODE0_parse_table[] = {
+static const ahd_reg_parse_entry_t LQOMODE0_parse_table[] = {
 	{ "ENLQOTCRC",		0x01, 0x01 },
 	{ "ENLQOATNPKT",	0x02, 0x02 },
 	{ "ENLQOATNLQ",		0x04, 0x04 },
@@ -1265,7 +1054,7 @@ ahd_lqomode0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x54, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t LQOMODE1_parse_table[] = {
+static const ahd_reg_parse_entry_t LQOMODE1_parse_table[] = {
 	{ "ENLQOPHACHGINPKT",	0x01, 0x01 },
 	{ "ENLQOBUSFREE",	0x02, 0x02 },
 	{ "ENLQOBADQAS",	0x04, 0x04 },
@@ -1280,7 +1069,7 @@ ahd_lqomode1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x55, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t LQOSTAT1_parse_table[] = {
+static const ahd_reg_parse_entry_t LQOSTAT1_parse_table[] = {
 	{ "LQOPHACHGINPKT",	0x01, 0x01 },
 	{ "LQOBUSFREE",		0x02, 0x02 },
 	{ "LQOBADQAS",		0x04, 0x04 },
@@ -1295,7 +1084,7 @@ ahd_lqostat1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x55, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t CLRLQOINT1_parse_table[] = {
+static const ahd_reg_parse_entry_t CLRLQOINT1_parse_table[] = {
 	{ "CLRLQOPHACHGINPKT",	0x01, 0x01 },
 	{ "CLRLQOBUSFREE",	0x02, 0x02 },
 	{ "CLRLQOBADQAS",	0x04, 0x04 },
@@ -1310,7 +1099,7 @@ ahd_clrlqoint1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x55, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t LQOSTAT2_parse_table[] = {
+static const ahd_reg_parse_entry_t LQOSTAT2_parse_table[] = {
 	{ "LQOSTOP0",		0x01, 0x01 },
 	{ "LQOPHACHGOUTPKT",	0x02, 0x02 },
 	{ "LQOWAITFIFO",	0x10, 0x10 },
@@ -1331,7 +1120,7 @@ ahd_os_space_cnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x56, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SIMODE1_parse_table[] = {
+static const ahd_reg_parse_entry_t SIMODE1_parse_table[] = {
 	{ "ENREQINIT",		0x01, 0x01 },
 	{ "ENSTRB2FAST",	0x02, 0x02 },
 	{ "ENSCSIPERR",		0x04, 0x04 },
@@ -1356,7 +1145,7 @@ ahd_gsfifo_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x58, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t DFFSXFRCTL_parse_table[] = {
+static const ahd_reg_parse_entry_t DFFSXFRCTL_parse_table[] = {
 	{ "RSTCHN",		0x01, 0x01 },
 	{ "CLRCHN",		0x02, 0x02 },
 	{ "CLRSHCNT",		0x04, 0x04 },
@@ -1370,15 +1159,17 @@ ahd_dffsxfrctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x5a, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t LQOSCSCTL_parse_table[] = {
+static const ahd_reg_parse_entry_t LQOSCSCTL_parse_table[] = {
 	{ "LQONOCHKOVER",	0x01, 0x01 },
+	{ "LQONOHOLDLACK",	0x02, 0x02 },
+	{ "LQOBUSETDLY",	0x40, 0x40 },
 	{ "LQOH2A_VERSION",	0x80, 0x80 }
 };
 
 int
 ahd_lqoscsctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
-	return (ahd_print_register(LQOSCSCTL_parse_table, 2, "LQOSCSCTL",
+	return (ahd_print_register(LQOSCSCTL_parse_table, 4, "LQOSCSCTL",
 	    0x5a, regvalue, cur_col, wrap));
 }
 
@@ -1389,7 +1180,7 @@ ahd_nextscb_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x5a, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t CLRSEQINTSRC_parse_table[] = {
+static const ahd_reg_parse_entry_t CLRSEQINTSRC_parse_table[] = {
 	{ "CLRCFG4TCMD",	0x01, 0x01 },
 	{ "CLRCFG4ICMD",	0x02, 0x02 },
 	{ "CLRCFG4TSTAT",	0x04, 0x04 },
@@ -1406,7 +1197,7 @@ ahd_clrseqintsrc_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x5b, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SEQINTSRC_parse_table[] = {
+static const ahd_reg_parse_entry_t SEQINTSRC_parse_table[] = {
 	{ "CFG4TCMD",		0x01, 0x01 },
 	{ "CFG4ICMD",		0x02, 0x02 },
 	{ "CFG4TSTAT",		0x04, 0x04 },
@@ -1423,14 +1214,7 @@ ahd_seqintsrc_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x5b, regvalue, cur_col, wrap));
 }
 
-int
-ahd_currscb_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "CURRSCB",
-	    0x5c, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SEQIMODE_parse_table[] = {
+static const ahd_reg_parse_entry_t SEQIMODE_parse_table[] = {
 	{ "ENCFG4TCMD",		0x01, 0x01 },
 	{ "ENCFG4ICMD",		0x02, 0x02 },
 	{ "ENCFG4TSTAT",	0x04, 0x04 },
@@ -1447,7 +1231,14 @@ ahd_seqimode_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x5c, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t MDFFSTAT_parse_table[] = {
+int
+ahd_currscb_print(u_int regvalue, u_int *cur_col, u_int wrap)
+{
+	return (ahd_print_register(NULL, 0, "CURRSCB",
+	    0x5c, regvalue, cur_col, wrap));
+}
+
+static const ahd_reg_parse_entry_t MDFFSTAT_parse_table[] = {
 	{ "FIFOFREE",		0x01, 0x01 },
 	{ "DATAINFIFO",		0x02, 0x02 },
 	{ "DLZERO",		0x04, 0x04 },
@@ -1464,24 +1255,6 @@ ahd_mdffstat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x5d, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t CRCCONTROL_parse_table[] = {
-	{ "CRCVALCHKEN",	0x40, 0x40 }
-};
-
-int
-ahd_crccontrol_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(CRCCONTROL_parse_table, 1, "CRCCONTROL",
-	    0x5d, regvalue, cur_col, wrap));
-}
-
-int
-ahd_dfftag_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "DFFTAG",
-	    0x5e, regvalue, cur_col, wrap));
-}
-
 int
 ahd_lastscb_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -1489,31 +1262,6 @@ ahd_lastscb_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x5e, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCSITEST_parse_table[] = {
-	{ "SEL_TXPLL_DEBUG",	0x04, 0x04 },
-	{ "CNTRTEST",		0x08, 0x08 }
-};
-
-int
-ahd_scsitest_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SCSITEST_parse_table, 2, "SCSITEST",
-	    0x5e, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t IOPDNCTL_parse_table[] = {
-	{ "PDN_DIFFSENSE",	0x01, 0x01 },
-	{ "PDN_IDIST",		0x04, 0x04 },
-	{ "DISABLE_OE",		0x80, 0x80 }
-};
-
-int
-ahd_iopdnctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(IOPDNCTL_parse_table, 3, "IOPDNCTL",
-	    0x5f, regvalue, cur_col, wrap));
-}
-
 int
 ahd_shaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -1528,13 +1276,6 @@ ahd_negoaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x60, regvalue, cur_col, wrap));
 }
 
-int
-ahd_dgrpcrci_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "DGRPCRCI",
-	    0x60, regvalue, cur_col, wrap));
-}
-
 int
 ahd_negperiod_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -1543,20 +1284,13 @@ ahd_negperiod_print(u_int regvalue, u_int *cur_col, u_int wrap)
 }
 
 int
-ahd_packcrci_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "PACKCRCI",
-	    0x62, regvalue, cur_col, wrap));
-}
-
-int
-ahd_negoffset_print(u_int regvalue, u_int *cur_col, u_int wrap)
+ahd_negoffset_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
 	return (ahd_print_register(NULL, 0, "NEGOFFSET",
 	    0x62, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t NEGPPROPTS_parse_table[] = {
+static const ahd_reg_parse_entry_t NEGPPROPTS_parse_table[] = {
 	{ "PPROPT_IUT",		0x01, 0x01 },
 	{ "PPROPT_DT",		0x02, 0x02 },
 	{ "PPROPT_QAS",		0x04, 0x04 },
@@ -1570,7 +1304,7 @@ ahd_negppropts_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x63, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t NEGCONOPTS_parse_table[] = {
+static const ahd_reg_parse_entry_t NEGCONOPTS_parse_table[] = {
 	{ "WIDEXFER",		0x01, 0x01 },
 	{ "ENAUTOATNO",		0x02, 0x02 },
 	{ "ENAUTOATNI",		0x04, 0x04 },
@@ -1601,20 +1335,21 @@ ahd_annexdat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x66, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCSCHKN_parse_table[] = {
+static const ahd_reg_parse_entry_t SCSCHKN_parse_table[] = {
 	{ "LSTSGCLRDIS",	0x01, 0x01 },
 	{ "SHVALIDSTDIS",	0x02, 0x02 },
 	{ "DFFACTCLR",		0x04, 0x04 },
 	{ "SDONEMSKDIS",	0x08, 0x08 },
 	{ "WIDERESEN",		0x10, 0x10 },
 	{ "CURRFIFODEF",	0x20, 0x20 },
-	{ "STSELSKIDDIS",	0x40, 0x40 }
+	{ "STSELSKIDDIS",	0x40, 0x40 },
+	{ "BIDICHKDIS",		0x80, 0x80 }
 };
 
 int
 ahd_scschkn_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
-	return (ahd_print_register(SCSCHKN_parse_table, 7, "SCSCHKN",
+	return (ahd_print_register(SCSCHKN_parse_table, 8, "SCSCHKN",
 	    0x66, regvalue, cur_col, wrap));
 }
 
@@ -1625,23 +1360,6 @@ ahd_iownid_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x67, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t PLL960CTL0_parse_table[] = {
-	{ "PLL_ENFBM",		0x01, 0x01 },
-	{ "PLL_DLPF",		0x02, 0x02 },
-	{ "PLL_ENLPF",		0x04, 0x04 },
-	{ "PLL_ENLUD",		0x08, 0x08 },
-	{ "PLL_NS",		0x30, 0x30 },
-	{ "PLL_PWDN",		0x40, 0x40 },
-	{ "PLL_VCOSEL",		0x80, 0x80 }
-};
-
-int
-ahd_pll960ctl0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(PLL960CTL0_parse_table, 7, "PLL960CTL0",
-	    0x68, regvalue, cur_col, wrap));
-}
-
 int
 ahd_shcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -1656,33 +1374,6 @@ ahd_townid_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x69, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t PLL960CTL1_parse_table[] = {
-	{ "PLL_RST",		0x01, 0x01 },
-	{ "PLL_CNTCLR",		0x40, 0x40 },
-	{ "PLL_CNTEN",		0x80, 0x80 }
-};
-
-int
-ahd_pll960ctl1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(PLL960CTL1_parse_table, 3, "PLL960CTL1",
-	    0x69, regvalue, cur_col, wrap));
-}
-
-int
-ahd_pll960cnt0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "PLL960CNT0",
-	    0x6a, regvalue, cur_col, wrap));
-}
-
-int
-ahd_xsig_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "XSIG",
-	    0x6a, regvalue, cur_col, wrap));
-}
-
 int
 ahd_seloid_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -1690,57 +1381,6 @@ ahd_seloid_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x6b, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t PLL400CTL0_parse_table[] = {
-	{ "PLL_ENFBM",		0x01, 0x01 },
-	{ "PLL_DLPF",		0x02, 0x02 },
-	{ "PLL_ENLPF",		0x04, 0x04 },
-	{ "PLL_ENLUD",		0x08, 0x08 },
-	{ "PLL_NS",		0x30, 0x30 },
-	{ "PLL_PWDN",		0x40, 0x40 },
-	{ "PLL_VCOSEL",		0x80, 0x80 }
-};
-
-int
-ahd_pll400ctl0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(PLL400CTL0_parse_table, 7, "PLL400CTL0",
-	    0x6c, regvalue, cur_col, wrap));
-}
-
-int
-ahd_fairness_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "FAIRNESS",
-	    0x6c, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t PLL400CTL1_parse_table[] = {
-	{ "PLL_RST",		0x01, 0x01 },
-	{ "PLL_CNTCLR",		0x40, 0x40 },
-	{ "PLL_CNTEN",		0x80, 0x80 }
-};
-
-int
-ahd_pll400ctl1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(PLL400CTL1_parse_table, 3, "PLL400CTL1",
-	    0x6d, regvalue, cur_col, wrap));
-}
-
-int
-ahd_unfairness_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "UNFAIRNESS",
-	    0x6e, regvalue, cur_col, wrap));
-}
-
-int
-ahd_pll400cnt0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "PLL400CNT0",
-	    0x6e, regvalue, cur_col, wrap));
-}
-
 int
 ahd_haddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -1748,31 +1388,6 @@ ahd_haddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x70, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t PLLDELAY_parse_table[] = {
-	{ "SPLIT_DROP_REQ",	0x80, 0x80 }
-};
-
-int
-ahd_plldelay_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(PLLDELAY_parse_table, 1, "PLLDELAY",
-	    0x70, regvalue, cur_col, wrap));
-}
-
-int
-ahd_hodmaadr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "HODMAADR",
-	    0x70, regvalue, cur_col, wrap));
-}
-
-int
-ahd_hodmacnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "HODMACNT",
-	    0x78, regvalue, cur_col, wrap));
-}
-
 int
 ahd_hcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -1781,10 +1396,10 @@ ahd_hcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
 }
 
 int
-ahd_hodmaen_print(u_int regvalue, u_int *cur_col, u_int wrap)
+ahd_sghaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
-	return (ahd_print_register(NULL, 0, "HODMAEN",
-	    0x7a, regvalue, cur_col, wrap));
+	return (ahd_print_register(NULL, 0, "SGHADDR",
+	    0x7c, regvalue, cur_col, wrap));
 }
 
 int
@@ -1795,10 +1410,10 @@ ahd_scbhaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 }
 
 int
-ahd_sghaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
+ahd_sghcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
-	return (ahd_print_register(NULL, 0, "SGHADDR",
-	    0x7c, regvalue, cur_col, wrap));
+	return (ahd_print_register(NULL, 0, "SGHCNT",
+	    0x84, regvalue, cur_col, wrap));
 }
 
 int
@@ -1808,14 +1423,7 @@ ahd_scbhcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x84, regvalue, cur_col, wrap));
 }
 
-int
-ahd_sghcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "SGHCNT",
-	    0x84, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t DFF_THRSH_parse_table[] = {
+static const ahd_reg_parse_entry_t DFF_THRSH_parse_table[] = {
 	{ "WR_DFTHRSH_MIN",	0x00, 0x70 },
 	{ "RD_DFTHRSH_MIN",	0x00, 0x07 },
 	{ "RD_DFTHRSH_25",	0x01, 0x07 },
@@ -1843,209 +1451,7 @@ ahd_dff_thrsh_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x88, regvalue, cur_col, wrap));
 }
 
-int
-ahd_romaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "ROMADDR",
-	    0x8a, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t ROMCNTRL_parse_table[] = {
-	{ "RDY",		0x01, 0x01 },
-	{ "REPEAT",		0x02, 0x02 },
-	{ "ROMSPD",		0x18, 0x18 },
-	{ "ROMOP",		0xe0, 0xe0 }
-};
-
-int
-ahd_romcntrl_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(ROMCNTRL_parse_table, 4, "ROMCNTRL",
-	    0x8d, regvalue, cur_col, wrap));
-}
-
-int
-ahd_romdata_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "ROMDATA",
-	    0x8e, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t CMCRXMSG0_parse_table[] = {
-	{ "CFNUM",		0x07, 0x07 },
-	{ "CDNUM",		0xf8, 0xf8 }
-};
-
-int
-ahd_cmcrxmsg0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(CMCRXMSG0_parse_table, 2, "CMCRXMSG0",
-	    0x90, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t ROENABLE_parse_table[] = {
-	{ "DCH0ROEN",		0x01, 0x01 },
-	{ "DCH1ROEN",		0x02, 0x02 },
-	{ "SGROEN",		0x04, 0x04 },
-	{ "CMCROEN",		0x08, 0x08 },
-	{ "OVLYROEN",		0x10, 0x10 },
-	{ "MSIROEN",		0x20, 0x20 }
-};
-
-int
-ahd_roenable_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(ROENABLE_parse_table, 6, "ROENABLE",
-	    0x90, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t OVLYRXMSG0_parse_table[] = {
-	{ "CFNUM",		0x07, 0x07 },
-	{ "CDNUM",		0xf8, 0xf8 }
-};
-
-int
-ahd_ovlyrxmsg0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(OVLYRXMSG0_parse_table, 2, "OVLYRXMSG0",
-	    0x90, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t DCHRXMSG0_parse_table[] = {
-	{ "CFNUM",		0x07, 0x07 },
-	{ "CDNUM",		0xf8, 0xf8 }
-};
-
-int
-ahd_dchrxmsg0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(DCHRXMSG0_parse_table, 2, "DCHRXMSG0",
-	    0x90, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t OVLYRXMSG1_parse_table[] = {
-	{ "CBNUM",		0xff, 0xff }
-};
-
-int
-ahd_ovlyrxmsg1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(OVLYRXMSG1_parse_table, 1, "OVLYRXMSG1",
-	    0x91, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t NSENABLE_parse_table[] = {
-	{ "DCH0NSEN",		0x01, 0x01 },
-	{ "DCH1NSEN",		0x02, 0x02 },
-	{ "SGNSEN",		0x04, 0x04 },
-	{ "CMCNSEN",		0x08, 0x08 },
-	{ "OVLYNSEN",		0x10, 0x10 },
-	{ "MSINSEN",		0x20, 0x20 }
-};
-
-int
-ahd_nsenable_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NSENABLE_parse_table, 6, "NSENABLE",
-	    0x91, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t CMCRXMSG1_parse_table[] = {
-	{ "CBNUM",		0xff, 0xff }
-};
-
-int
-ahd_cmcrxmsg1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(CMCRXMSG1_parse_table, 1, "CMCRXMSG1",
-	    0x91, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t DCHRXMSG1_parse_table[] = {
-	{ "CBNUM",		0xff, 0xff }
-};
-
-int
-ahd_dchrxmsg1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(DCHRXMSG1_parse_table, 1, "DCHRXMSG1",
-	    0x91, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t DCHRXMSG2_parse_table[] = {
-	{ "MINDEX",		0xff, 0xff }
-};
-
-int
-ahd_dchrxmsg2_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(DCHRXMSG2_parse_table, 1, "DCHRXMSG2",
-	    0x92, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t CMCRXMSG2_parse_table[] = {
-	{ "MINDEX",		0xff, 0xff }
-};
-
-int
-ahd_cmcrxmsg2_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(CMCRXMSG2_parse_table, 1, "CMCRXMSG2",
-	    0x92, regvalue, cur_col, wrap));
-}
-
-int
-ahd_ost_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "OST",
-	    0x92, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t OVLYRXMSG2_parse_table[] = {
-	{ "MINDEX",		0xff, 0xff }
-};
-
-int
-ahd_ovlyrxmsg2_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(OVLYRXMSG2_parse_table, 1, "OVLYRXMSG2",
-	    0x92, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t DCHRXMSG3_parse_table[] = {
-	{ "MCLASS",		0x0f, 0x0f }
-};
-
-int
-ahd_dchrxmsg3_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(DCHRXMSG3_parse_table, 1, "DCHRXMSG3",
-	    0x93, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t OVLYRXMSG3_parse_table[] = {
-	{ "MCLASS",		0x0f, 0x0f }
-};
-
-int
-ahd_ovlyrxmsg3_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(OVLYRXMSG3_parse_table, 1, "OVLYRXMSG3",
-	    0x93, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t CMCRXMSG3_parse_table[] = {
-	{ "MCLASS",		0x0f, 0x0f }
-};
-
-int
-ahd_cmcrxmsg3_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(CMCRXMSG3_parse_table, 1, "CMCRXMSG3",
-	    0x93, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t PCIXCTL_parse_table[] = {
+static const ahd_reg_parse_entry_t PCIXCTL_parse_table[] = {
 	{ "CMPABCDIS",		0x01, 0x01 },
 	{ "TSCSERREN",		0x02, 0x02 },
 	{ "SRSPDPEEN",		0x04, 0x04 },
@@ -2062,46 +1468,7 @@ ahd_pcixctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x93, regvalue, cur_col, wrap));
 }
 
-int
-ahd_ovlyseqbcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "OVLYSEQBCNT",
-	    0x94, regvalue, cur_col, wrap));
-}
-
-int
-ahd_dchseqbcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "DCHSEQBCNT",
-	    0x94, regvalue, cur_col, wrap));
-}
-
-int
-ahd_cmcseqbcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "CMCSEQBCNT",
-	    0x94, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t CMCSPLTSTAT0_parse_table[] = {
-	{ "RXSPLTRSP",		0x01, 0x01 },
-	{ "RXSCEMSG",		0x02, 0x02 },
-	{ "RXOVRUN",		0x04, 0x04 },
-	{ "CNTNOTCMPLT",	0x08, 0x08 },
-	{ "SCDATBUCKET",	0x10, 0x10 },
-	{ "SCADERR",		0x20, 0x20 },
-	{ "SCBCERR",		0x40, 0x40 },
-	{ "STAETERM",		0x80, 0x80 }
-};
-
-int
-ahd_cmcspltstat0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(CMCSPLTSTAT0_parse_table, 8, "CMCSPLTSTAT0",
-	    0x96, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t DCHSPLTSTAT0_parse_table[] = {
+static const ahd_reg_parse_entry_t DCHSPLTSTAT0_parse_table[] = {
 	{ "RXSPLTRSP",		0x01, 0x01 },
 	{ "RXSCEMSG",		0x02, 0x02 },
 	{ "RXOVRUN",		0x04, 0x04 },
@@ -2119,190 +1486,18 @@ ahd_dchspltstat0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x96, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t OVLYSPLTSTAT0_parse_table[] = {
-	{ "RXSPLTRSP",		0x01, 0x01 },
-	{ "RXSCEMSG",		0x02, 0x02 },
-	{ "RXOVRUN",		0x04, 0x04 },
-	{ "CNTNOTCMPLT",	0x08, 0x08 },
-	{ "SCDATBUCKET",	0x10, 0x10 },
-	{ "SCADERR",		0x20, 0x20 },
-	{ "SCBCERR",		0x40, 0x40 },
-	{ "STAETERM",		0x80, 0x80 }
-};
-
-int
-ahd_ovlyspltstat0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(OVLYSPLTSTAT0_parse_table, 8, "OVLYSPLTSTAT0",
-	    0x96, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t CMCSPLTSTAT1_parse_table[] = {
-	{ "RXDATABUCKET",	0x01, 0x01 }
-};
-
-int
-ahd_cmcspltstat1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(CMCSPLTSTAT1_parse_table, 1, "CMCSPLTSTAT1",
-	    0x97, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t OVLYSPLTSTAT1_parse_table[] = {
-	{ "RXDATABUCKET",	0x01, 0x01 }
-};
-
-int
-ahd_ovlyspltstat1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(OVLYSPLTSTAT1_parse_table, 1, "OVLYSPLTSTAT1",
-	    0x97, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t DCHSPLTSTAT1_parse_table[] = {
+static const ahd_reg_parse_entry_t DCHSPLTSTAT1_parse_table[] = {
 	{ "RXDATABUCKET",	0x01, 0x01 }
 };
 
 int
 ahd_dchspltstat1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
-	return (ahd_print_register(DCHSPLTSTAT1_parse_table, 1, "DCHSPLTSTAT1",
-	    0x97, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SGRXMSG0_parse_table[] = {
-	{ "CFNUM",		0x07, 0x07 },
-	{ "CDNUM",		0xf8, 0xf8 }
-};
-
-int
-ahd_sgrxmsg0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SGRXMSG0_parse_table, 2, "SGRXMSG0",
-	    0x98, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SLVSPLTOUTADR0_parse_table[] = {
-	{ "LOWER_ADDR",		0x7f, 0x7f }
-};
-
-int
-ahd_slvspltoutadr0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SLVSPLTOUTADR0_parse_table, 1, "SLVSPLTOUTADR0",
-	    0x98, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SGRXMSG1_parse_table[] = {
-	{ "CBNUM",		0xff, 0xff }
-};
-
-int
-ahd_sgrxmsg1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SGRXMSG1_parse_table, 1, "SGRXMSG1",
-	    0x99, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SLVSPLTOUTADR1_parse_table[] = {
-	{ "REQ_FNUM",		0x07, 0x07 },
-	{ "REQ_DNUM",		0xf8, 0xf8 }
-};
-
-int
-ahd_slvspltoutadr1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SLVSPLTOUTADR1_parse_table, 2, "SLVSPLTOUTADR1",
-	    0x99, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SGRXMSG2_parse_table[] = {
-	{ "MINDEX",		0xff, 0xff }
-};
-
-int
-ahd_sgrxmsg2_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SGRXMSG2_parse_table, 1, "SGRXMSG2",
-	    0x9a, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SLVSPLTOUTADR2_parse_table[] = {
-	{ "REQ_BNUM",		0xff, 0xff }
-};
-
-int
-ahd_slvspltoutadr2_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SLVSPLTOUTADR2_parse_table, 1, "SLVSPLTOUTADR2",
-	    0x9a, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SGRXMSG3_parse_table[] = {
-	{ "MCLASS",		0x0f, 0x0f }
-};
-
-int
-ahd_sgrxmsg3_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SGRXMSG3_parse_table, 1, "SGRXMSG3",
-	    0x9b, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SLVSPLTOUTADR3_parse_table[] = {
-	{ "RLXORD",		0x10, 0x10 },
-	{ "TAG_NUM",		0x1f, 0x1f }
-};
-
-int
-ahd_slvspltoutadr3_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SLVSPLTOUTADR3_parse_table, 2, "SLVSPLTOUTADR3",
-	    0x9b, regvalue, cur_col, wrap));
-}
-
-int
-ahd_sgseqbcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "SGSEQBCNT",
-	    0x9c, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SLVSPLTOUTATTR0_parse_table[] = {
-	{ "LOWER_BCNT",		0xff, 0xff }
-};
-
-int
-ahd_slvspltoutattr0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SLVSPLTOUTATTR0_parse_table, 1, "SLVSPLTOUTATTR0",
-	    0x9c, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SLVSPLTOUTATTR1_parse_table[] = {
-	{ "CMPLT_FNUM",		0x07, 0x07 },
-	{ "CMPLT_DNUM",		0xf8, 0xf8 }
-};
-
-int
-ahd_slvspltoutattr1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SLVSPLTOUTATTR1_parse_table, 2, "SLVSPLTOUTATTR1",
-	    0x9d, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SLVSPLTOUTATTR2_parse_table[] = {
-	{ "CMPLT_BNUM",		0xff, 0xff }
-};
-
-int
-ahd_slvspltoutattr2_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SLVSPLTOUTATTR2_parse_table, 1, "SLVSPLTOUTATTR2",
-	    0x9e, regvalue, cur_col, wrap));
+	return (ahd_print_register(DCHSPLTSTAT1_parse_table, 1, "DCHSPLTSTAT1",
+	    0x97, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SGSPLTSTAT0_parse_table[] = {
+static const ahd_reg_parse_entry_t SGSPLTSTAT0_parse_table[] = {
 	{ "RXSPLTRSP",		0x01, 0x01 },
 	{ "RXSCEMSG",		0x02, 0x02 },
 	{ "RXOVRUN",		0x04, 0x04 },
@@ -2320,7 +1515,7 @@ ahd_sgspltstat0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x9e, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SGSPLTSTAT1_parse_table[] = {
+static const ahd_reg_parse_entry_t SGSPLTSTAT1_parse_table[] = {
 	{ "RXDATABUCKET",	0x01, 0x01 }
 };
 
@@ -2331,19 +1526,7 @@ ahd_sgspltstat1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x9f, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SFUNCT_parse_table[] = {
-	{ "TEST_NUM",		0x0f, 0x0f },
-	{ "TEST_GROUP",		0xf0, 0xf0 }
-};
-
-int
-ahd_sfunct_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SFUNCT_parse_table, 2, "SFUNCT",
-	    0x9f, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t DF0PCISTAT_parse_table[] = {
+static const ahd_reg_parse_entry_t DF0PCISTAT_parse_table[] = {
 	{ "DPR",		0x01, 0x01 },
 	{ "TWATERR",		0x02, 0x02 },
 	{ "RDPERR",		0x04, 0x04 },
@@ -2368,83 +1551,6 @@ ahd_reg0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xa0, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t DF1PCISTAT_parse_table[] = {
-	{ "DPR",		0x01, 0x01 },
-	{ "TWATERR",		0x02, 0x02 },
-	{ "RDPERR",		0x04, 0x04 },
-	{ "SCAAPERR",		0x08, 0x08 },
-	{ "RTA",		0x10, 0x10 },
-	{ "RMA",		0x20, 0x20 },
-	{ "SSE",		0x40, 0x40 },
-	{ "DPE",		0x80, 0x80 }
-};
-
-int
-ahd_df1pcistat_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(DF1PCISTAT_parse_table, 8, "DF1PCISTAT",
-	    0xa1, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SGPCISTAT_parse_table[] = {
-	{ "DPR",		0x01, 0x01 },
-	{ "RDPERR",		0x04, 0x04 },
-	{ "SCAAPERR",		0x08, 0x08 },
-	{ "RTA",		0x10, 0x10 },
-	{ "RMA",		0x20, 0x20 },
-	{ "SSE",		0x40, 0x40 },
-	{ "DPE",		0x80, 0x80 }
-};
-
-int
-ahd_sgpcistat_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SGPCISTAT_parse_table, 7, "SGPCISTAT",
-	    0xa2, regvalue, cur_col, wrap));
-}
-
-int
-ahd_reg1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "REG1",
-	    0xa2, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t CMCPCISTAT_parse_table[] = {
-	{ "DPR",		0x01, 0x01 },
-	{ "TWATERR",		0x02, 0x02 },
-	{ "RDPERR",		0x04, 0x04 },
-	{ "SCAAPERR",		0x08, 0x08 },
-	{ "RTA",		0x10, 0x10 },
-	{ "RMA",		0x20, 0x20 },
-	{ "SSE",		0x40, 0x40 },
-	{ "DPE",		0x80, 0x80 }
-};
-
-int
-ahd_cmcpcistat_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(CMCPCISTAT_parse_table, 8, "CMCPCISTAT",
-	    0xa3, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t OVLYPCISTAT_parse_table[] = {
-	{ "DPR",		0x01, 0x01 },
-	{ "RDPERR",		0x04, 0x04 },
-	{ "SCAAPERR",		0x08, 0x08 },
-	{ "RTA",		0x10, 0x10 },
-	{ "RMA",		0x20, 0x20 },
-	{ "SSE",		0x40, 0x40 },
-	{ "DPE",		0x80, 0x80 }
-};
-
-int
-ahd_ovlypcistat_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(OVLYPCISTAT_parse_table, 7, "OVLYPCISTAT",
-	    0xa4, regvalue, cur_col, wrap));
-}
-
 int
 ahd_reg_isr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -2452,7 +1558,7 @@ ahd_reg_isr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xa4, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SG_STATE_parse_table[] = {
+static const ahd_reg_parse_entry_t SG_STATE_parse_table[] = {
 	{ "SEGS_AVAIL",		0x01, 0x01 },
 	{ "LOADING_NEEDED",	0x02, 0x02 },
 	{ "FETCH_INPROG",	0x04, 0x04 }
@@ -2465,23 +1571,7 @@ ahd_sg_state_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xa6, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t MSIPCISTAT_parse_table[] = {
-	{ "DPR",		0x01, 0x01 },
-	{ "TWATERR",		0x02, 0x02 },
-	{ "CLRPENDMSI",		0x08, 0x08 },
-	{ "RTA",		0x10, 0x10 },
-	{ "RMA",		0x20, 0x20 },
-	{ "SSE",		0x40, 0x40 }
-};
-
-int
-ahd_msipcistat_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(MSIPCISTAT_parse_table, 6, "MSIPCISTAT",
-	    0xa6, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t TARGPCISTAT_parse_table[] = {
+static const ahd_reg_parse_entry_t TARGPCISTAT_parse_table[] = {
 	{ "TWATERR",		0x02, 0x02 },
 	{ "STA",		0x08, 0x08 },
 	{ "SSE",		0x40, 0x40 },
@@ -2495,13 +1585,6 @@ ahd_targpcistat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xa7, regvalue, cur_col, wrap));
 }
 
-int
-ahd_data_count_odd_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "DATA_COUNT_ODD",
-	    0xa7, regvalue, cur_col, wrap));
-}
-
 int
 ahd_scbptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -2509,14 +1592,7 @@ ahd_scbptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xa8, regvalue, cur_col, wrap));
 }
 
-int
-ahd_ccscbacnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "CCSCBACNT",
-	    0xab, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SCBAUTOPTR_parse_table[] = {
+static const ahd_reg_parse_entry_t SCBAUTOPTR_parse_table[] = {
 	{ "SCBPTR_OFF",		0x07, 0x07 },
 	{ "SCBPTR_ADDR",	0x38, 0x38 },
 	{ "AUSCBPTR_EN",	0x80, 0x80 }
@@ -2536,13 +1612,6 @@ ahd_ccsgaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xac, regvalue, cur_col, wrap));
 }
 
-int
-ahd_ccscbadr_bk_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "CCSCBADR_BK",
-	    0xac, regvalue, cur_col, wrap));
-}
-
 int
 ahd_ccscbaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -2550,23 +1619,7 @@ ahd_ccscbaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xac, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t CMC_RAMBIST_parse_table[] = {
-	{ "CMC_BUFFER_BIST_EN",	0x01, 0x01 },
-	{ "CMC_BUFFER_BIST_FAIL",0x02, 0x02 },
-	{ "SG_BIST_EN",		0x10, 0x10 },
-	{ "SG_BIST_FAIL",	0x20, 0x20 },
-	{ "SCBRAMBIST_FAIL",	0x40, 0x40 },
-	{ "SG_ELEMENT_SIZE",	0x80, 0x80 }
-};
-
-int
-ahd_cmc_rambist_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(CMC_RAMBIST_parse_table, 6, "CMC_RAMBIST",
-	    0xad, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t CCSCBCTL_parse_table[] = {
+static const ahd_reg_parse_entry_t CCSCBCTL_parse_table[] = {
 	{ "CCSCBRESET",		0x01, 0x01 },
 	{ "CCSCBDIR",		0x04, 0x04 },
 	{ "CCSCBEN",		0x08, 0x08 },
@@ -2582,7 +1635,7 @@ ahd_ccscbctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xad, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t CCSGCTL_parse_table[] = {
+static const ahd_reg_parse_entry_t CCSGCTL_parse_table[] = {
 	{ "CCSGRESET",		0x01, 0x01 },
 	{ "SG_FETCH_REQ",	0x02, 0x02 },
 	{ "CCSGENACK",		0x08, 0x08 },
@@ -2605,13 +1658,6 @@ ahd_ccsgram_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xb0, regvalue, cur_col, wrap));
 }
 
-int
-ahd_flexadr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "FLEXADR",
-	    0xb0, regvalue, cur_col, wrap));
-}
-
 int
 ahd_ccscbram_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -2619,32 +1665,6 @@ ahd_ccscbram_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xb0, regvalue, cur_col, wrap));
 }
 
-int
-ahd_flexcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "FLEXCNT",
-	    0xb3, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t FLEXDMASTAT_parse_table[] = {
-	{ "FLEXDMADONE",	0x01, 0x01 },
-	{ "FLEXDMAERR",		0x02, 0x02 }
-};
-
-int
-ahd_flexdmastat_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(FLEXDMASTAT_parse_table, 2, "FLEXDMASTAT",
-	    0xb5, regvalue, cur_col, wrap));
-}
-
-int
-ahd_flexdata_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "FLEXDATA",
-	    0xb6, regvalue, cur_col, wrap));
-}
-
 int
 ahd_brddat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -2652,7 +1672,7 @@ ahd_brddat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xb8, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t BRDCTL_parse_table[] = {
+static const ahd_reg_parse_entry_t BRDCTL_parse_table[] = {
 	{ "BRDSTB",		0x01, 0x01 },
 	{ "BRDRW",		0x02, 0x02 },
 	{ "BRDEN",		0x04, 0x04 },
@@ -2682,7 +1702,7 @@ ahd_seedat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xbc, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SEECTL_parse_table[] = {
+static const ahd_reg_parse_entry_t SEECTL_parse_table[] = {
 	{ "SEEOP_ERAL",		0x40, 0x70 },
 	{ "SEEOP_WRITE",	0x50, 0x70 },
 	{ "SEEOP_READ",		0x60, 0x70 },
@@ -2702,7 +1722,7 @@ ahd_seectl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xbe, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SEESTAT_parse_table[] = {
+static const ahd_reg_parse_entry_t SEESTAT_parse_table[] = {
 	{ "SEESTART",		0x01, 0x01 },
 	{ "SEEBUSY",		0x02, 0x02 },
 	{ "SEEARBACK",		0x04, 0x04 },
@@ -2718,34 +1738,7 @@ ahd_seestat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xbe, regvalue, cur_col, wrap));
 }
 
-int
-ahd_scbcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "SCBCNT",
-	    0xbf, regvalue, cur_col, wrap));
-}
-
-int
-ahd_dfwaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "DFWADDR",
-	    0xc0, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t DSPFLTRCTL_parse_table[] = {
-	{ "DSPFCNTSEL",		0x0f, 0x0f },
-	{ "EDGESENSE",		0x10, 0x10 },
-	{ "FLTRDISABLE",	0x20, 0x20 }
-};
-
-int
-ahd_dspfltrctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(DSPFLTRCTL_parse_table, 3, "DSPFLTRCTL",
-	    0xc0, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t DSPDATACTL_parse_table[] = {
+static const ahd_reg_parse_entry_t DSPDATACTL_parse_table[] = {
 	{ "XMITOFFSTDIS",	0x02, 0x02 },
 	{ "RCVROFFSTDIS",	0x04, 0x04 },
 	{ "DESQDIS",		0x10, 0x10 },
@@ -2759,37 +1752,6 @@ ahd_dspdatactl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xc1, regvalue, cur_col, wrap));
 }
 
-int
-ahd_dfraddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "DFRADDR",
-	    0xc2, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t DSPREQCTL_parse_table[] = {
-	{ "MANREQDLY",		0x3f, 0x3f },
-	{ "MANREQCTL",		0xc0, 0xc0 }
-};
-
-int
-ahd_dspreqctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(DSPREQCTL_parse_table, 2, "DSPREQCTL",
-	    0xc2, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t DSPACKCTL_parse_table[] = {
-	{ "MANACKDLY",		0x3f, 0x3f },
-	{ "MANACKCTL",		0xc0, 0xc0 }
-};
-
-int
-ahd_dspackctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(DSPACKCTL_parse_table, 2, "DSPACKCTL",
-	    0xc3, regvalue, cur_col, wrap));
-}
-
 int
 ahd_dfdat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -2797,7 +1759,7 @@ ahd_dfdat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xc4, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t DSPSELECT_parse_table[] = {
+static const ahd_reg_parse_entry_t DSPSELECT_parse_table[] = {
 	{ "DSPSEL",		0x1f, 0x1f },
 	{ "AUTOINCEN",		0x80, 0x80 }
 };
@@ -2809,7 +1771,7 @@ ahd_dspselect_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xc4, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t WRTBIASCTL_parse_table[] = {
+static const ahd_reg_parse_entry_t WRTBIASCTL_parse_table[] = {
 	{ "XMITMANVAL",		0x3f, 0x3f },
 	{ "AUTOXBCDIS",		0x80, 0x80 }
 };
@@ -2821,91 +1783,7 @@ ahd_wrtbiasctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xc5, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t RCVRBIOSCTL_parse_table[] = {
-	{ "RCVRMANVAL",		0x3f, 0x3f },
-	{ "AUTORBCDIS",		0x80, 0x80 }
-};
-
-int
-ahd_rcvrbiosctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(RCVRBIOSCTL_parse_table, 2, "RCVRBIOSCTL",
-	    0xc6, regvalue, cur_col, wrap));
-}
-
-int
-ahd_wrtbiascalc_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "WRTBIASCALC",
-	    0xc7, regvalue, cur_col, wrap));
-}
-
-int
-ahd_rcvrbiascalc_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "RCVRBIASCALC",
-	    0xc8, regvalue, cur_col, wrap));
-}
-
-int
-ahd_dfptrs_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "DFPTRS",
-	    0xc8, regvalue, cur_col, wrap));
-}
-
-int
-ahd_skewcalc_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "SKEWCALC",
-	    0xc9, regvalue, cur_col, wrap));
-}
-
-int
-ahd_dfbkptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "DFBKPTR",
-	    0xc9, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t DFDBCTL_parse_table[] = {
-	{ "DFF_RAMBIST_EN",	0x01, 0x01 },
-	{ "DFF_RAMBIST_DONE",	0x02, 0x02 },
-	{ "DFF_RAMBIST_FAIL",	0x04, 0x04 },
-	{ "DFF_DIR_ERR",	0x08, 0x08 },
-	{ "DFF_CIO_RD_RDY",	0x10, 0x10 },
-	{ "DFF_CIO_WR_RDY",	0x20, 0x20 }
-};
-
-int
-ahd_dfdbctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(DFDBCTL_parse_table, 6, "DFDBCTL",
-	    0xcb, regvalue, cur_col, wrap));
-}
-
-int
-ahd_dfscnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "DFSCNT",
-	    0xcc, regvalue, cur_col, wrap));
-}
-
-int
-ahd_dfbcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "DFBCNT",
-	    0xce, regvalue, cur_col, wrap));
-}
-
-int
-ahd_ovlyaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "OVLYADDR",
-	    0xd4, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t SEQCTL0_parse_table[] = {
+static const ahd_reg_parse_entry_t SEQCTL0_parse_table[] = {
 	{ "LOADRAM",		0x01, 0x01 },
 	{ "SEQRESET",		0x02, 0x02 },
 	{ "STEP",		0x04, 0x04 },
@@ -2923,21 +1801,7 @@ ahd_seqctl0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xd6, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SEQCTL1_parse_table[] = {
-	{ "RAMBIST_EN",		0x01, 0x01 },
-	{ "RAMBIST_FAIL",	0x02, 0x02 },
-	{ "RAMBIST_DONE",	0x04, 0x04 },
-	{ "OVRLAY_DATA_CHK",	0x08, 0x08 }
-};
-
-int
-ahd_seqctl1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(SEQCTL1_parse_table, 4, "SEQCTL1",
-	    0xd7, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t FLAGS_parse_table[] = {
+static const ahd_reg_parse_entry_t FLAGS_parse_table[] = {
 	{ "CARRY",		0x01, 0x01 },
 	{ "ZERO",		0x02, 0x02 }
 };
@@ -2949,7 +1813,7 @@ ahd_flags_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xd8, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SEQINTCTL_parse_table[] = {
+static const ahd_reg_parse_entry_t SEQINTCTL_parse_table[] = {
 	{ "IRET",		0x01, 0x01 },
 	{ "INTMASK1",		0x02, 0x02 },
 	{ "INTMASK2",		0x04, 0x04 },
@@ -3001,24 +1865,6 @@ ahd_dindex_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xe4, regvalue, cur_col, wrap));
 }
 
-int
-ahd_brkaddr0_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "BRKADDR0",
-	    0xe6, regvalue, cur_col, wrap));
-}
-
-static ahd_reg_parse_entry_t BRKADDR1_parse_table[] = {
-	{ "BRKDIS",		0x80, 0x80 }
-};
-
-int
-ahd_brkaddr1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(BRKADDR1_parse_table, 1, "BRKADDR1",
-	    0xe6, regvalue, cur_col, wrap));
-}
-
 int
 ahd_allones_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -3054,13 +1900,6 @@ ahd_dindir_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xed, regvalue, cur_col, wrap));
 }
 
-int
-ahd_function1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "FUNCTION1",
-	    0xf0, regvalue, cur_col, wrap));
-}
-
 int
 ahd_stack_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -3082,13 +1921,6 @@ ahd_curaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xf4, regvalue, cur_col, wrap));
 }
 
-int
-ahd_lastaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "LASTADDR",
-	    0xf6, regvalue, cur_col, wrap));
-}
-
 int
 ahd_intvec2_addr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -3111,23 +1943,16 @@ ahd_accum_save_print(u_int regvalue, u_int *cur_col, u_int wrap)
 }
 
 int
-ahd_waiting_scb_tails_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "WAITING_SCB_TAILS",
-	    0x100, regvalue, cur_col, wrap));
-}
-
-int
-ahd_ahd_pci_config_base_print(u_int regvalue, u_int *cur_col, u_int wrap)
+ahd_sram_base_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
-	return (ahd_print_register(NULL, 0, "AHD_PCI_CONFIG_BASE",
+	return (ahd_print_register(NULL, 0, "SRAM_BASE",
 	    0x100, regvalue, cur_col, wrap));
 }
 
 int
-ahd_sram_base_print(u_int regvalue, u_int *cur_col, u_int wrap)
+ahd_waiting_scb_tails_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
-	return (ahd_print_register(NULL, 0, "SRAM_BASE",
+	return (ahd_print_register(NULL, 0, "WAITING_SCB_TAILS",
 	    0x100, regvalue, cur_col, wrap));
 }
 
@@ -3215,7 +2040,7 @@ ahd_msg_out_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x137, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t DMAPARAMS_parse_table[] = {
+static const ahd_reg_parse_entry_t DMAPARAMS_parse_table[] = {
 	{ "FIFORESET",		0x01, 0x01 },
 	{ "FIFOFLUSH",		0x02, 0x02 },
 	{ "DIRECTION",		0x04, 0x04 },
@@ -3235,7 +2060,7 @@ ahd_dmaparams_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x138, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SEQ_FLAGS_parse_table[] = {
+static const ahd_reg_parse_entry_t SEQ_FLAGS_parse_table[] = {
 	{ "NO_DISCONNECT",	0x01, 0x01 },
 	{ "SPHASE_PENDING",	0x02, 0x02 },
 	{ "DPHASE_PENDING",	0x04, 0x04 },
@@ -3268,7 +2093,7 @@ ahd_saved_lun_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x13b, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t LASTPHASE_parse_table[] = {
+static const ahd_reg_parse_entry_t LASTPHASE_parse_table[] = {
 	{ "P_DATAOUT",		0x00, 0xe0 },
 	{ "P_DATAOUT_DT",	0x20, 0xe0 },
 	{ "P_DATAIN",		0x40, 0xe0 },
@@ -3326,7 +2151,7 @@ ahd_qoutfifo_next_addr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x144, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t ARG_1_parse_table[] = {
+static const ahd_reg_parse_entry_t ARG_1_parse_table[] = {
 	{ "CONT_MSG_LOOP_TARG",	0x02, 0x02 },
 	{ "CONT_MSG_LOOP_READ",	0x03, 0x03 },
 	{ "CONT_MSG_LOOP_WRITE",0x04, 0x04 },
@@ -3358,7 +2183,7 @@ ahd_last_msg_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x14a, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCSISEQ_TEMPLATE_parse_table[] = {
+static const ahd_reg_parse_entry_t SCSISEQ_TEMPLATE_parse_table[] = {
 	{ "ALTSTIM",		0x01, 0x01 },
 	{ "ENAUTOATNP",		0x02, 0x02 },
 	{ "MANUALP",		0x0c, 0x0c },
@@ -3381,7 +2206,7 @@ ahd_initiator_tag_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x14c, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SEQ_FLAGS2_parse_table[] = {
+static const ahd_reg_parse_entry_t SEQ_FLAGS2_parse_table[] = {
 	{ "PENDING_MK_MESSAGE",	0x01, 0x01 },
 	{ "TARGET_MSG_PENDING",	0x02, 0x02 },
 	{ "SELECTOUT_QFROZEN",	0x04, 0x04 }
@@ -3465,20 +2290,20 @@ ahd_mk_message_scsiid_print(u_int regvalue, u_int *cur_col, u_int wrap)
 }
 
 int
-ahd_scb_base_print(u_int regvalue, u_int *cur_col, u_int wrap)
+ahd_scb_residual_datacnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
-	return (ahd_print_register(NULL, 0, "SCB_BASE",
+	return (ahd_print_register(NULL, 0, "SCB_RESIDUAL_DATACNT",
 	    0x180, regvalue, cur_col, wrap));
 }
 
 int
-ahd_scb_residual_datacnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
+ahd_scb_base_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
-	return (ahd_print_register(NULL, 0, "SCB_RESIDUAL_DATACNT",
+	return (ahd_print_register(NULL, 0, "SCB_BASE",
 	    0x180, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCB_RESIDUAL_SGPTR_parse_table[] = {
+static const ahd_reg_parse_entry_t SCB_RESIDUAL_SGPTR_parse_table[] = {
 	{ "SG_LIST_NULL",	0x01, 0x01 },
 	{ "SG_OVERRUN_RESID",	0x02, 0x02 },
 	{ "SG_ADDR_MASK",	0xf8, 0xf8 }
@@ -3498,27 +2323,6 @@ ahd_scb_scsi_status_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x188, regvalue, cur_col, wrap));
 }
 
-int
-ahd_scb_target_phases_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "SCB_TARGET_PHASES",
-	    0x189, regvalue, cur_col, wrap));
-}
-
-int
-ahd_scb_target_data_dir_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "SCB_TARGET_DATA_DIR",
-	    0x18a, regvalue, cur_col, wrap));
-}
-
-int
-ahd_scb_target_itag_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "SCB_TARGET_ITAG",
-	    0x18b, regvalue, cur_col, wrap));
-}
-
 int
 ahd_scb_sense_busaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -3533,7 +2337,7 @@ ahd_scb_tag_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x190, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCB_CONTROL_parse_table[] = {
+static const ahd_reg_parse_entry_t SCB_CONTROL_parse_table[] = {
 	{ "SCB_TAG_TYPE",	0x03, 0x03 },
 	{ "DISCONNECTED",	0x04, 0x04 },
 	{ "STATUS_RCVD",	0x08, 0x08 },
@@ -3550,7 +2354,7 @@ ahd_scb_control_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x192, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCB_SCSIID_parse_table[] = {
+static const ahd_reg_parse_entry_t SCB_SCSIID_parse_table[] = {
 	{ "OID",		0x0f, 0x0f },
 	{ "TID",		0xf0, 0xf0 }
 };
@@ -3562,7 +2366,7 @@ ahd_scb_scsiid_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x193, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCB_LUN_parse_table[] = {
+static const ahd_reg_parse_entry_t SCB_LUN_parse_table[] = {
 	{ "LID",		0xff, 0xff }
 };
 
@@ -3573,7 +2377,7 @@ ahd_scb_lun_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x194, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCB_TASK_ATTRIBUTE_parse_table[] = {
+static const ahd_reg_parse_entry_t SCB_TASK_ATTRIBUTE_parse_table[] = {
 	{ "SCB_XFERLEN_ODD",	0x01, 0x01 }
 };
 
@@ -3584,7 +2388,7 @@ ahd_scb_task_attribute_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x195, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCB_CDB_LEN_parse_table[] = {
+static const ahd_reg_parse_entry_t SCB_CDB_LEN_parse_table[] = {
 	{ "SCB_CDB_LEN_PTR",	0x80, 0x80 }
 };
 
@@ -3609,7 +2413,7 @@ ahd_scb_dataptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x198, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCB_DATACNT_parse_table[] = {
+static const ahd_reg_parse_entry_t SCB_DATACNT_parse_table[] = {
 	{ "SG_HIGH_ADDR_BITS",	0x7f, 0x7f },
 	{ "SG_LAST_SEG",	0x80, 0x80 }
 };
@@ -3621,7 +2425,7 @@ ahd_scb_datacnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x1a0, regvalue, cur_col, wrap));
 }
 
-static ahd_reg_parse_entry_t SCB_SGPTR_parse_table[] = {
+static const ahd_reg_parse_entry_t SCB_SGPTR_parse_table[] = {
 	{ "SG_LIST_NULL",	0x01, 0x01 },
 	{ "SG_FULL_RESID",	0x02, 0x02 },
 	{ "SG_STATUS_VALID",	0x04, 0x04 }
@@ -3655,13 +2459,6 @@ ahd_scb_next2_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x1ae, regvalue, cur_col, wrap));
 }
 
-int
-ahd_scb_spare_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahd_print_register(NULL, 0, "SCB_SPARE",
-	    0x1b0, regvalue, cur_col, wrap));
-}
-
 int
 ahd_scb_disconnected_lists_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
diff --git a/trunk/drivers/scsi/aic7xxx/aic79xx_seq.h_shipped b/trunk/drivers/scsi/aic7xxx/aic79xx_seq.h_shipped
index 11bed07e90b7..4b51e232392f 100644
--- a/trunk/drivers/scsi/aic7xxx/aic79xx_seq.h_shipped
+++ b/trunk/drivers/scsi/aic7xxx/aic79xx_seq.h_shipped
@@ -5,7 +5,7 @@
  * $Id: //depot/aic7xxx/aic7xxx/aic79xx.seq#120 $
  * $Id: //depot/aic7xxx/aic7xxx/aic79xx.reg#77 $
  */
-static uint8_t seqprog[] = {
+static const uint8_t seqprog[] = {
 	0xff, 0x02, 0x06, 0x78,
 	0x00, 0xea, 0x6e, 0x59,
 	0x01, 0xea, 0x04, 0x30,
@@ -1027,7 +1027,7 @@ ahd_patch0_func(struct ahd_softc *ahd)
 	return (0);
 }
 
-static struct patch {
+static const struct patch {
 	ahd_patch_func_t		*patch_func;
 	uint32_t		 begin		:10,
 				 skip_instr	:10,
@@ -1166,7 +1166,7 @@ static struct patch {
 	{ ahd_patch23_func, 815, 11, 1 }
 };
 
-static struct cs {
+static const struct cs {
 	uint16_t	begin;
 	uint16_t	end;
 } critical_sections[] = {
diff --git a/trunk/drivers/scsi/aic7xxx/aic7xxx.h b/trunk/drivers/scsi/aic7xxx/aic7xxx.h
index c0344e617651..e4e651cca3e4 100644
--- a/trunk/drivers/scsi/aic7xxx/aic7xxx.h
+++ b/trunk/drivers/scsi/aic7xxx/aic7xxx.h
@@ -736,7 +736,7 @@ struct ahc_syncrate {
 #define		ST_SXFR	   0x010	/* Rate Single Transition Only */
 #define		DT_SXFR	   0x040	/* Rate Double Transition Only */
 	uint8_t period; /* Period to send to SCSI target */
-	char *rate;
+	const char *rate;
 };
 
 /* Safe and valid period for async negotiations. */
@@ -1114,7 +1114,7 @@ typedef int (ahc_device_setup_t)(struct ahc_softc *);
 struct ahc_pci_identity {
 	uint64_t		 full_id;
 	uint64_t		 id_mask;
-	char			*name;
+	const char		*name;
 	ahc_device_setup_t	*setup;
 };
 
@@ -1133,15 +1133,11 @@ extern const int ahc_num_aic7770_devs;
 
 /*************************** Function Declarations ****************************/
 /******************************************************************************/
-u_int			ahc_index_busy_tcl(struct ahc_softc *ahc, u_int tcl);
-void			ahc_unbusy_tcl(struct ahc_softc *ahc, u_int tcl);
-void			ahc_busy_tcl(struct ahc_softc *ahc,
-				     u_int tcl, u_int busyid);
 
 /***************************** PCI Front End *********************************/
-struct ahc_pci_identity	*ahc_find_pci_device(ahc_dev_softc_t);
+const struct ahc_pci_identity	*ahc_find_pci_device(ahc_dev_softc_t);
 int			 ahc_pci_config(struct ahc_softc *,
-					struct ahc_pci_identity *);
+					const struct ahc_pci_identity *);
 int			 ahc_pci_test_register_access(struct ahc_softc *);
 #ifdef CONFIG_PM
 void			 ahc_pci_resume(struct ahc_softc *ahc);
@@ -1155,9 +1151,6 @@ int			 aic7770_config(struct ahc_softc *ahc,
 
 /************************** SCB and SCB queue management **********************/
 int		ahc_probe_scbs(struct ahc_softc *);
-void		ahc_run_untagged_queues(struct ahc_softc *ahc);
-void		ahc_run_untagged_queue(struct ahc_softc *ahc,
-				       struct scb_tailq *queue);
 void		ahc_qinfifo_requeue_tail(struct ahc_softc *ahc,
 					 struct scb *scb);
 int		ahc_match_scb(struct ahc_softc *ahc, struct scb *scb,
@@ -1178,22 +1171,8 @@ int			 ahc_resume(struct ahc_softc *ahc);
 #endif
 void			 ahc_set_unit(struct ahc_softc *, int);
 void			 ahc_set_name(struct ahc_softc *, char *);
-void			 ahc_alloc_scbs(struct ahc_softc *ahc);
 void			 ahc_free(struct ahc_softc *ahc);
 int			 ahc_reset(struct ahc_softc *ahc, int reinit);
-void			 ahc_shutdown(void *arg);
-
-/*************************** Interrupt Services *******************************/
-void			ahc_clear_intstat(struct ahc_softc *ahc);
-void			ahc_run_qoutfifo(struct ahc_softc *ahc);
-#ifdef AHC_TARGET_MODE
-void			ahc_run_tqinfifo(struct ahc_softc *ahc, int paused);
-#endif
-void			ahc_handle_brkadrint(struct ahc_softc *ahc);
-void			ahc_handle_seqint(struct ahc_softc *ahc, u_int intstat);
-void			ahc_handle_scsiint(struct ahc_softc *ahc,
-					   u_int intstat);
-void			ahc_clear_critical_section(struct ahc_softc *ahc);
 
 /***************************** Error Recovery *********************************/
 typedef enum {
@@ -1214,36 +1193,19 @@ int			ahc_search_disc_list(struct ahc_softc *ahc, int target,
 					     char channel, int lun, u_int tag,
 					     int stop_on_first, int remove,
 					     int save_state);
-void			ahc_freeze_devq(struct ahc_softc *ahc, struct scb *scb);
 int			ahc_reset_channel(struct ahc_softc *ahc, char channel,
 					  int initiate_reset);
-int			ahc_abort_scbs(struct ahc_softc *ahc, int target,
-				       char channel, int lun, u_int tag,
-				       role_t role, uint32_t status);
-void			ahc_restart(struct ahc_softc *ahc);
-void			ahc_calc_residual(struct ahc_softc *ahc,
-					  struct scb *scb);
+
 /*************************** Utility Functions ********************************/
-struct ahc_phase_table_entry*
-			ahc_lookup_phase_entry(int phase);
 void			ahc_compile_devinfo(struct ahc_devinfo *devinfo,
 					    u_int our_id, u_int target,
 					    u_int lun, char channel,
 					    role_t role);
 /************************** Transfer Negotiation ******************************/
-struct ahc_syncrate*	ahc_find_syncrate(struct ahc_softc *ahc, u_int *period,
+const struct ahc_syncrate*	ahc_find_syncrate(struct ahc_softc *ahc, u_int *period,
 					  u_int *ppr_options, u_int maxsync);
 u_int			ahc_find_period(struct ahc_softc *ahc,
 					u_int scsirate, u_int maxsync);
-void			ahc_validate_offset(struct ahc_softc *ahc,
-					    struct ahc_initiator_tinfo *tinfo,
-					    struct ahc_syncrate *syncrate,
-					    u_int *offset, int wide,
-					    role_t role);
-void			ahc_validate_width(struct ahc_softc *ahc,
-					   struct ahc_initiator_tinfo *tinfo,
-					   u_int *bus_width,
-					   role_t role);
 /*
  * Negotiation types.  These are used to qualify if we should renegotiate
  * even if our goal and current transport parameters are identical.
@@ -1263,7 +1225,7 @@ void			ahc_set_width(struct ahc_softc *ahc,
 				      u_int width, u_int type, int paused);
 void			ahc_set_syncrate(struct ahc_softc *ahc,
 					 struct ahc_devinfo *devinfo,
-					 struct ahc_syncrate *syncrate,
+					 const struct ahc_syncrate *syncrate,
 					 u_int period, u_int offset,
 					 u_int ppr_options,
 					 u_int type, int paused);
@@ -1305,11 +1267,10 @@ extern uint32_t ahc_debug;
 #define AHC_SHOW_MASKED_ERRORS	0x1000
 #define AHC_DEBUG_SEQUENCER	0x2000
 #endif
-void			ahc_print_scb(struct scb *scb);
 void			ahc_print_devinfo(struct ahc_softc *ahc,
 					  struct ahc_devinfo *dev);
 void			ahc_dump_card_state(struct ahc_softc *ahc);
-int			ahc_print_register(ahc_reg_parse_entry_t *table,
+int			ahc_print_register(const ahc_reg_parse_entry_t *table,
 					   u_int num_entries,
 					   const char *name,
 					   u_int address,
diff --git a/trunk/drivers/scsi/aic7xxx/aic7xxx.reg b/trunk/drivers/scsi/aic7xxx/aic7xxx.reg
index e196d83b93c7..0d2f763c3427 100644
--- a/trunk/drivers/scsi/aic7xxx/aic7xxx.reg
+++ b/trunk/drivers/scsi/aic7xxx/aic7xxx.reg
@@ -238,6 +238,7 @@ register SXFRCTL2 {
 register OPTIONMODE {
 	address			0x008
 	access_mode RW
+	count		2
 	field	AUTORATEEN		0x80
 	field	AUTOACKEN		0x40
 	field	ATNMGMNTEN		0x20
@@ -254,6 +255,7 @@ register TARGCRCCNT {
 	address			0x00a
 	size	2
 	access_mode RW
+	count		2
 }
 
 /*
@@ -344,6 +346,7 @@ register SSTAT2 {
 register SSTAT3 {
 	address			0x00e
 	access_mode RO
+	count		2
 	mask	SCSICNT		0xf0
 	mask	OFFCNT		0x0f
 	mask	U2OFFCNT	0x7f
@@ -367,6 +370,7 @@ register SCSIID_ULTRA2 {
 register SIMODE0 {
 	address			0x010
 	access_mode RW
+	count		2
 	field	ENSELDO		0x40
 	field	ENSELDI		0x20
 	field	ENSELINGO	0x10
@@ -429,6 +433,7 @@ register SHADDR {
 register SELTIMER {
 	address			0x018
 	access_mode RW
+	count		1
 	field	STAGE6		0x20
 	field	STAGE5		0x10
 	field	STAGE4		0x08
@@ -467,6 +472,7 @@ register TARGID {
 	address			0x01b
 	size			2
 	access_mode RW
+	count		14
 }
 
 /*
@@ -480,6 +486,7 @@ register TARGID {
 register SPIOCAP {
 	address			0x01b
 	access_mode RW
+	count		10
 	field	SOFT1		0x80
 	field	SOFT0		0x40
 	field	SOFTCMDEN	0x20	
@@ -492,6 +499,7 @@ register SPIOCAP {
 
 register BRDCTL	{
 	address			0x01d
+	count		11
 	field	BRDDAT7		0x80
 	field	BRDDAT6		0x40
 	field	BRDDAT5		0x20
@@ -534,6 +542,7 @@ register BRDCTL	{
  */
 register SEECTL {
 	address			0x01e
+	count		11
 	field	EXTARBACK	0x80
 	field	EXTARBREQ	0x40
 	field	SEEMS		0x20
@@ -570,6 +579,7 @@ register SBLKCTL {
 register SEQCTL {
 	address			0x060
 	access_mode RW
+	count		15
 	field	PERRORDIS	0x80
 	field	PAUSEDIS	0x40
 	field	FAILDIS		0x20
@@ -590,6 +600,7 @@ register SEQCTL {
 register SEQRAM {
 	address			0x061
 	access_mode RW
+	count		2
 }
 
 /*
@@ -604,6 +615,7 @@ register SEQADDR0 {
 register SEQADDR1 {
 	address			0x063
 	access_mode RW
+	count		8
 	mask	SEQADDR1_MASK	0x01
 }
 
@@ -649,6 +661,7 @@ register NONE {
 register FLAGS {
 	address			0x06b
 	access_mode RO
+	count		18
 	field	ZERO		0x02
 	field	CARRY		0x01
 }
@@ -671,6 +684,7 @@ register FUNCTION1 {
 register STACK {
 	address			0x06f
 	access_mode RO
+	count		5
 }
 
 const	STACK_SIZE	4
@@ -692,6 +706,7 @@ register BCTL {
 register DSCOMMAND0 {
 	address			0x084
 	access_mode RW
+	count		7
 	field	CACHETHEN	0x80	/* Cache Threshold enable */
 	field	DPARCKEN	0x40	/* Data Parity Check Enable */
 	field	MPARCKEN	0x20	/* Memory Parity Check Enable */
@@ -717,6 +732,7 @@ register DSCOMMAND1 {
 register BUSTIME {
 	address			0x085
 	access_mode RW
+	count		2
 	mask	BOFF		0xf0
 	mask	BON		0x0f
 }
@@ -727,6 +743,7 @@ register BUSTIME {
 register BUSSPD {
 	address			0x086
 	access_mode RW
+	count		2
 	mask	DFTHRSH		0xc0
 	mask	STBOFF		0x38
 	mask	STBON		0x07
@@ -737,6 +754,7 @@ register BUSSPD {
 /* aic7850/55/60/70/80/95 only */
 register DSPCISTATUS {
 	address			0x086
+	count		4
 	mask	DFTHRSH_100	0xc0
 }
 
@@ -758,6 +776,7 @@ const	SEQ_MAILBOX_SHIFT	0
 register HCNTRL {
 	address			0x087
 	access_mode RW
+	count		14
 	field	POWRDN		0x40
 	field	SWINT		0x10
 	field	IRQMS		0x08
@@ -869,6 +888,7 @@ register INTSTAT {
 register ERROR {
 	address			0x092
 	access_mode RO
+	count		26
 	field	CIOPARERR	0x80	/* Ultra2 only */
 	field	PCIERRSTAT	0x40	/* PCI only */
 	field	MPARERR		0x20	/* PCI only */
@@ -885,6 +905,7 @@ register ERROR {
 register CLRINT {
 	address			0x092
 	access_mode WO
+	count		24
 	field	CLRPARERR	0x10	/* PCI only */
 	field	CLRBRKADRINT	0x08
 	field	CLRSCSIINT      0x04
@@ -943,6 +964,7 @@ register DFDAT {
 register SCBCNT {
 	address			0x09a
 	access_mode RW
+	count		1
 	field	SCBAUTO		0x80
 	mask	SCBCNT_MASK	0x1f
 }
@@ -954,6 +976,7 @@ register SCBCNT {
 register QINFIFO {
 	address			0x09b
 	access_mode RW
+	count		12
 }
 
 /*
@@ -972,11 +995,13 @@ register QINCNT	{
 register QOUTFIFO {
 	address			0x09d
 	access_mode WO
+	count		7
 }
 
 register CRCCONTROL1 {
 	address			0x09d
 	access_mode RW
+	count		3
 	field	CRCONSEEN		0x80
 	field	CRCVALCHKEN		0x40
 	field	CRCENDCHKEN		0x20
@@ -1013,6 +1038,7 @@ register SCSIPHASE {
 register SFUNCT {
 	address			0x09f
 	access_mode RW
+	count	    4
 	field	ALT_MODE	0x80
 }
 
@@ -1095,6 +1121,7 @@ scb {
 	}
 	SCB_SCSIOFFSET {
 		size	1
+		count	1
 	}
 	SCB_NEXT {
 		size	1
@@ -1118,6 +1145,7 @@ const	SG_SIZEOF	0x08		/* sizeof(struct ahc_dma) */
 register SEECTL_2840 {
 	address			0x0c0
 	access_mode RW
+	count		2
 	field	CS_2840		0x04
 	field	CK_2840		0x02
 	field	DO_2840		0x01
@@ -1126,6 +1154,7 @@ register SEECTL_2840 {
 register STATUS_2840 {
 	address			0x0c1
 	access_mode RW
+	count		4
 	field	EEPROM_TF	0x80
 	mask	BIOS_SEL	0x60
 	mask	ADSEL		0x1e
@@ -1161,6 +1190,7 @@ register CCSGCTL {
 
 register CCSCBCNT {
 	address			0xEF
+	count		1
 }
 
 register CCSCBCTL {
@@ -1187,6 +1217,7 @@ register CCSCBRAM {
 register SCBBADDR {
 	address			0x0F0
 	access_mode RW
+	count		3
 }
 
 register CCSCBPTR {
@@ -1195,6 +1226,7 @@ register CCSCBPTR {
 
 register HNSCB_QOFF {
 	address			0x0F4
+	count		4
 }
 
 register SNSCB_QOFF {
@@ -1234,6 +1266,7 @@ register DFF_THRSH {
 	mask	WR_DFTHRSH_85	0x50
 	mask	WR_DFTHRSH_90	0x60
 	mask	WR_DFTHRSH_MAX	0x70
+	count	4
 }
 
 register SG_CACHE_PRE {
@@ -1287,6 +1320,7 @@ scratch_ram {
 	ULTRA_ENB {
 		alias		CMDSIZE_TABLE
 		size		2
+		count		2
 	}
 	/*
 	 * Bit vector of targets that have disconnection disabled as set by
@@ -1296,6 +1330,7 @@ scratch_ram {
 	 */
 	DISC_DSB {
 		size		2
+		count		6
 	}
 	CMDSIZE_TABLE_TAIL {
 		size		4
@@ -1323,6 +1358,7 @@ scratch_ram {
 	/* Parameters for DMA Logic */
 	DMAPARAMS {
 		size		1
+		count		12
 		field	PRELOADEN	0x80
 		field	WIDEODD		0x40
 		field	SCSIEN		0x20
@@ -1436,11 +1472,12 @@ scratch_ram {
 	KERNEL_TQINPOS {
 		size		1
 	}
-	TQINPOS {                
+	TQINPOS {
 		size		1
 	}
 	ARG_1 {
 		size		1
+		count		1
 		mask	SEND_MSG		0x80
 		mask	SEND_SENSE		0x40
 		mask	SEND_REJ		0x20
@@ -1495,6 +1532,7 @@ scratch_ram {
 		size	1
 		field	HA_274_EXTENDED_TRANS	0x01
 		alias	INITIATOR_TAG
+		count		1
 	}
 
 	SEQ_FLAGS2 {
@@ -1518,6 +1556,7 @@ scratch_ram {
 	 */
 	SCSICONF {
 		size		1
+		count		12
 		field	TERM_ENB	0x80
 		field	RESET_SCSI	0x40
 		field	ENSPCHK		0x20
@@ -1527,16 +1566,19 @@ scratch_ram {
 	INTDEF {
 		address		0x05c
 		size		1
+		count		1
 		field	EDGE_TRIG	0x80
 		mask	VECTOR		0x0f
 	}
 	HOSTCONF {
 		address		0x05d
 		size		1
+		count		1
 	}
 	HA_274_BIOSCTRL	{
 		address		0x05f
 		size		1
+		count		1
 		mask	BIOSMODE		0x30
 		mask	BIOSDISABLED		0x30	
 		field	CHANNEL_B_PRIMARY	0x08
@@ -1552,6 +1594,7 @@ scratch_ram {
 	 */
 	TARG_OFFSET {
 		size		16
+		count		1
 	}
 }
 
diff --git a/trunk/drivers/scsi/aic7xxx/aic7xxx_93cx6.c b/trunk/drivers/scsi/aic7xxx/aic7xxx_93cx6.c
index 3cb07e114e89..dd11999b77b6 100644
--- a/trunk/drivers/scsi/aic7xxx/aic7xxx_93cx6.c
+++ b/trunk/drivers/scsi/aic7xxx/aic7xxx_93cx6.c
@@ -84,16 +84,16 @@ struct seeprom_cmd {
 };
 
 /* Short opcodes for the c46 */
-static struct seeprom_cmd seeprom_ewen = {9, {1, 0, 0, 1, 1, 0, 0, 0, 0}};
-static struct seeprom_cmd seeprom_ewds = {9, {1, 0, 0, 0, 0, 0, 0, 0, 0}};
+static const struct seeprom_cmd seeprom_ewen = {9, {1, 0, 0, 1, 1, 0, 0, 0, 0}};
+static const struct seeprom_cmd seeprom_ewds = {9, {1, 0, 0, 0, 0, 0, 0, 0, 0}};
 
 /* Long opcodes for the C56/C66 */
-static struct seeprom_cmd seeprom_long_ewen = {11, {1, 0, 0, 1, 1, 0, 0, 0, 0}};
-static struct seeprom_cmd seeprom_long_ewds = {11, {1, 0, 0, 0, 0, 0, 0, 0, 0}};
+static const struct seeprom_cmd seeprom_long_ewen = {11, {1, 0, 0, 1, 1, 0, 0, 0, 0}};
+static const struct seeprom_cmd seeprom_long_ewds = {11, {1, 0, 0, 0, 0, 0, 0, 0, 0}};
 
 /* Common opcodes */
-static struct seeprom_cmd seeprom_write = {3, {1, 0, 1}};
-static struct seeprom_cmd seeprom_read  = {3, {1, 1, 0}};
+static const struct seeprom_cmd seeprom_write = {3, {1, 0, 1}};
+static const struct seeprom_cmd seeprom_read  = {3, {1, 1, 0}};
 
 /*
  * Wait for the SEERDY to go high; about 800 ns.
@@ -108,7 +108,7 @@ static struct seeprom_cmd seeprom_read  = {3, {1, 1, 0}};
  * Send a START condition and the given command
  */
 static void
-send_seeprom_cmd(struct seeprom_descriptor *sd, struct seeprom_cmd *cmd)
+send_seeprom_cmd(struct seeprom_descriptor *sd, const struct seeprom_cmd *cmd)
 {
 	uint8_t temp;
 	int i = 0;
@@ -227,7 +227,7 @@ int
 ahc_write_seeprom(struct seeprom_descriptor *sd, uint16_t *buf,
 		  u_int start_addr, u_int count)
 {
-	struct seeprom_cmd *ewen, *ewds;
+	const struct seeprom_cmd *ewen, *ewds;
 	uint16_t v;
 	uint8_t temp;
 	int i, k;
diff --git a/trunk/drivers/scsi/aic7xxx/aic7xxx_core.c b/trunk/drivers/scsi/aic7xxx/aic7xxx_core.c
index 64e62ce59c15..0ae2b4605d09 100644
--- a/trunk/drivers/scsi/aic7xxx/aic7xxx_core.c
+++ b/trunk/drivers/scsi/aic7xxx/aic7xxx_core.c
@@ -51,8 +51,7 @@
 #endif
 
 /***************************** Lookup Tables **********************************/
-char *ahc_chip_names[] =
-{
+static const char *const ahc_chip_names[] = {
 	"NONE",
 	"aic7770",
 	"aic7850",
@@ -75,10 +74,10 @@ static const u_int num_chip_names = ARRAY_SIZE(ahc_chip_names);
  */
 struct ahc_hard_error_entry {
         uint8_t errno;
-	char *errmesg;
+	const char *errmesg;
 };
 
-static struct ahc_hard_error_entry ahc_hard_errors[] = {
+static const struct ahc_hard_error_entry ahc_hard_errors[] = {
 	{ ILLHADDR,	"Illegal Host Access" },
 	{ ILLSADDR,	"Illegal Sequencer Address referrenced" },
 	{ ILLOPCODE,	"Illegal Opcode in sequencer program" },
@@ -90,7 +89,7 @@ static struct ahc_hard_error_entry ahc_hard_errors[] = {
 };
 static const u_int num_errors = ARRAY_SIZE(ahc_hard_errors);
 
-static struct ahc_phase_table_entry ahc_phase_table[] =
+static const struct ahc_phase_table_entry ahc_phase_table[] =
 {
 	{ P_DATAOUT,	MSG_NOOP,		"in Data-out phase"	},
 	{ P_DATAIN,	MSG_INITIATOR_DET_ERR,	"in Data-in phase"	},
@@ -115,7 +114,7 @@ static const u_int num_phases = ARRAY_SIZE(ahc_phase_table) - 1;
  * Provides a mapping of tranfer periods in ns to the proper value to
  * stick in the scsixfer reg.
  */
-static struct ahc_syncrate ahc_syncrates[] =
+static const struct ahc_syncrate ahc_syncrates[] =
 {
       /* ultra2    fast/ultra  period     rate */
 	{ 0x42,      0x000,      9,      "80.0" },
@@ -148,7 +147,7 @@ static struct ahc_tmode_tstate*
 static void		ahc_free_tstate(struct ahc_softc *ahc,
 					u_int scsi_id, char channel, int force);
 #endif
-static struct ahc_syncrate*
+static const struct ahc_syncrate*
 			ahc_devlimited_syncrate(struct ahc_softc *ahc,
 					        struct ahc_initiator_tinfo *,
 						u_int *period,
@@ -204,9 +203,9 @@ static void		ahc_setup_target_msgin(struct ahc_softc *ahc,
 #endif
 
 static bus_dmamap_callback_t	ahc_dmamap_cb; 
-static void			ahc_build_free_scb_list(struct ahc_softc *ahc);
-static int			ahc_init_scbdata(struct ahc_softc *ahc);
-static void			ahc_fini_scbdata(struct ahc_softc *ahc);
+static void		ahc_build_free_scb_list(struct ahc_softc *ahc);
+static int		ahc_init_scbdata(struct ahc_softc *ahc);
+static void		ahc_fini_scbdata(struct ahc_softc *ahc);
 static void		ahc_qinfifo_requeue(struct ahc_softc *ahc,
 					    struct scb *prev_scb,
 					    struct scb *scb);
@@ -222,7 +221,7 @@ static void		ahc_dumpseq(struct ahc_softc *ahc);
 #endif
 static int		ahc_loadseq(struct ahc_softc *ahc);
 static int		ahc_check_patch(struct ahc_softc *ahc,
-					struct patch **start_patch,
+					const struct patch **start_patch,
 					u_int start_instr, u_int *skip_addr);
 static void		ahc_download_instr(struct ahc_softc *ahc,
 					   u_int instrptr, uint8_t *dconsts);
@@ -237,11 +236,582 @@ static void		ahc_update_scsiid(struct ahc_softc *ahc,
 static int		ahc_handle_target_cmd(struct ahc_softc *ahc,
 					      struct target_cmd *cmd);
 #endif
+
+static u_int		ahc_index_busy_tcl(struct ahc_softc *ahc, u_int tcl);
+static void		ahc_unbusy_tcl(struct ahc_softc *ahc, u_int tcl);
+static void		ahc_busy_tcl(struct ahc_softc *ahc,
+				     u_int tcl, u_int busyid);
+
+/************************** SCB and SCB queue management **********************/
+static void		ahc_run_untagged_queues(struct ahc_softc *ahc);
+static void		ahc_run_untagged_queue(struct ahc_softc *ahc,
+					       struct scb_tailq *queue);
+
+/****************************** Initialization ********************************/
+static void		 ahc_alloc_scbs(struct ahc_softc *ahc);
+static void		 ahc_shutdown(void *arg);
+
+/*************************** Interrupt Services *******************************/
+static void		ahc_clear_intstat(struct ahc_softc *ahc);
+static void		ahc_run_qoutfifo(struct ahc_softc *ahc);
+#ifdef AHC_TARGET_MODE
+static void		ahc_run_tqinfifo(struct ahc_softc *ahc, int paused);
+#endif
+static void		ahc_handle_brkadrint(struct ahc_softc *ahc);
+static void		ahc_handle_seqint(struct ahc_softc *ahc, u_int intstat);
+static void		ahc_handle_scsiint(struct ahc_softc *ahc,
+					   u_int intstat);
+static void		ahc_clear_critical_section(struct ahc_softc *ahc);
+
+/***************************** Error Recovery *********************************/
+static void		ahc_freeze_devq(struct ahc_softc *ahc, struct scb *scb);
+static int		ahc_abort_scbs(struct ahc_softc *ahc, int target,
+				       char channel, int lun, u_int tag,
+				       role_t role, uint32_t status);
+static void		ahc_calc_residual(struct ahc_softc *ahc,
+					  struct scb *scb);
+
+/*********************** Untagged Transaction Routines ************************/
+static inline void	ahc_freeze_untagged_queues(struct ahc_softc *ahc);
+static inline void	ahc_release_untagged_queues(struct ahc_softc *ahc);
+
+/*
+ * Block our completion routine from starting the next untagged
+ * transaction for this target or target lun.
+ */
+static inline void
+ahc_freeze_untagged_queues(struct ahc_softc *ahc)
+{
+	if ((ahc->flags & AHC_SCB_BTT) == 0)
+		ahc->untagged_queue_lock++;
+}
+
+/*
+ * Allow the next untagged transaction for this target or target lun
+ * to be executed.  We use a counting semaphore to allow the lock
+ * to be acquired recursively.  Once the count drops to zero, the
+ * transaction queues will be run.
+ */
+static inline void
+ahc_release_untagged_queues(struct ahc_softc *ahc)
+{
+	if ((ahc->flags & AHC_SCB_BTT) == 0) {
+		ahc->untagged_queue_lock--;
+		if (ahc->untagged_queue_lock == 0)
+			ahc_run_untagged_queues(ahc);
+	}
+}
+
 /************************* Sequencer Execution Control ************************/
 /*
- * Restart the sequencer program from address zero
+ * Work around any chip bugs related to halting sequencer execution.
+ * On Ultra2 controllers, we must clear the CIOBUS stretch signal by
+ * reading a register that will set this signal and deassert it.
+ * Without this workaround, if the chip is paused, by an interrupt or
+ * manual pause while accessing scb ram, accesses to certain registers
+ * will hang the system (infinite pci retries).
+ */
+static void
+ahc_pause_bug_fix(struct ahc_softc *ahc)
+{
+	if ((ahc->features & AHC_ULTRA2) != 0)
+		(void)ahc_inb(ahc, CCSCBCTL);
+}
+
+/*
+ * Determine whether the sequencer has halted code execution.
+ * Returns non-zero status if the sequencer is stopped.
+ */
+int
+ahc_is_paused(struct ahc_softc *ahc)
+{
+	return ((ahc_inb(ahc, HCNTRL) & PAUSE) != 0);
+}
+
+/*
+ * Request that the sequencer stop and wait, indefinitely, for it
+ * to stop.  The sequencer will only acknowledge that it is paused
+ * once it has reached an instruction boundary and PAUSEDIS is
+ * cleared in the SEQCTL register.  The sequencer may use PAUSEDIS
+ * for critical sections.
+ */
+void
+ahc_pause(struct ahc_softc *ahc)
+{
+	ahc_outb(ahc, HCNTRL, ahc->pause);
+
+	/*
+	 * Since the sequencer can disable pausing in a critical section, we
+	 * must loop until it actually stops.
+	 */
+	while (ahc_is_paused(ahc) == 0)
+		;
+
+	ahc_pause_bug_fix(ahc);
+}
+
+/*
+ * Allow the sequencer to continue program execution.
+ * We check here to ensure that no additional interrupt
+ * sources that would cause the sequencer to halt have been
+ * asserted.  If, for example, a SCSI bus reset is detected
+ * while we are fielding a different, pausing, interrupt type,
+ * we don't want to release the sequencer before going back
+ * into our interrupt handler and dealing with this new
+ * condition.
+ */
+void
+ahc_unpause(struct ahc_softc *ahc)
+{
+	if ((ahc_inb(ahc, INTSTAT) & (SCSIINT | SEQINT | BRKADRINT)) == 0)
+		ahc_outb(ahc, HCNTRL, ahc->unpause);
+}
+
+/************************** Memory mapping routines ***************************/
+static struct ahc_dma_seg *
+ahc_sg_bus_to_virt(struct scb *scb, uint32_t sg_busaddr)
+{
+	int sg_index;
+
+	sg_index = (sg_busaddr - scb->sg_list_phys)/sizeof(struct ahc_dma_seg);
+	/* sg_list_phys points to entry 1, not 0 */
+	sg_index++;
+
+	return (&scb->sg_list[sg_index]);
+}
+
+static uint32_t
+ahc_sg_virt_to_bus(struct scb *scb, struct ahc_dma_seg *sg)
+{
+	int sg_index;
+
+	/* sg_list_phys points to entry 1, not 0 */
+	sg_index = sg - &scb->sg_list[1];
+
+	return (scb->sg_list_phys + (sg_index * sizeof(*scb->sg_list)));
+}
+
+static uint32_t
+ahc_hscb_busaddr(struct ahc_softc *ahc, u_int index)
+{
+	return (ahc->scb_data->hscb_busaddr
+		+ (sizeof(struct hardware_scb) * index));
+}
+
+static void
+ahc_sync_scb(struct ahc_softc *ahc, struct scb *scb, int op)
+{
+	ahc_dmamap_sync(ahc, ahc->scb_data->hscb_dmat,
+			ahc->scb_data->hscb_dmamap,
+			/*offset*/(scb->hscb - ahc->hscbs) * sizeof(*scb->hscb),
+			/*len*/sizeof(*scb->hscb), op);
+}
+
+void
+ahc_sync_sglist(struct ahc_softc *ahc, struct scb *scb, int op)
+{
+	if (scb->sg_count == 0)
+		return;
+
+	ahc_dmamap_sync(ahc, ahc->scb_data->sg_dmat, scb->sg_map->sg_dmamap,
+			/*offset*/(scb->sg_list - scb->sg_map->sg_vaddr)
+				* sizeof(struct ahc_dma_seg),
+			/*len*/sizeof(struct ahc_dma_seg) * scb->sg_count, op);
+}
+
+#ifdef AHC_TARGET_MODE
+static uint32_t
+ahc_targetcmd_offset(struct ahc_softc *ahc, u_int index)
+{
+	return (((uint8_t *)&ahc->targetcmds[index]) - ahc->qoutfifo);
+}
+#endif
+
+/*********************** Miscelaneous Support Functions ***********************/
+/*
+ * Determine whether the sequencer reported a residual
+ * for this SCB/transaction.
+ */
+static void
+ahc_update_residual(struct ahc_softc *ahc, struct scb *scb)
+{
+	uint32_t sgptr;
+
+	sgptr = ahc_le32toh(scb->hscb->sgptr);
+	if ((sgptr & SG_RESID_VALID) != 0)
+		ahc_calc_residual(ahc, scb);
+}
+
+/*
+ * Return pointers to the transfer negotiation information
+ * for the specified our_id/remote_id pair.
+ */
+struct ahc_initiator_tinfo *
+ahc_fetch_transinfo(struct ahc_softc *ahc, char channel, u_int our_id,
+		    u_int remote_id, struct ahc_tmode_tstate **tstate)
+{
+	/*
+	 * Transfer data structures are stored from the perspective
+	 * of the target role.  Since the parameters for a connection
+	 * in the initiator role to a given target are the same as
+	 * when the roles are reversed, we pretend we are the target.
+	 */
+	if (channel == 'B')
+		our_id += 8;
+	*tstate = ahc->enabled_targets[our_id];
+	return (&(*tstate)->transinfo[remote_id]);
+}
+
+uint16_t
+ahc_inw(struct ahc_softc *ahc, u_int port)
+{
+	uint16_t r = ahc_inb(ahc, port+1) << 8;
+	return r | ahc_inb(ahc, port);
+}
+
+void
+ahc_outw(struct ahc_softc *ahc, u_int port, u_int value)
+{
+	ahc_outb(ahc, port, value & 0xFF);
+	ahc_outb(ahc, port+1, (value >> 8) & 0xFF);
+}
+
+uint32_t
+ahc_inl(struct ahc_softc *ahc, u_int port)
+{
+	return ((ahc_inb(ahc, port))
+	      | (ahc_inb(ahc, port+1) << 8)
+	      | (ahc_inb(ahc, port+2) << 16)
+	      | (ahc_inb(ahc, port+3) << 24));
+}
+
+void
+ahc_outl(struct ahc_softc *ahc, u_int port, uint32_t value)
+{
+	ahc_outb(ahc, port, (value) & 0xFF);
+	ahc_outb(ahc, port+1, ((value) >> 8) & 0xFF);
+	ahc_outb(ahc, port+2, ((value) >> 16) & 0xFF);
+	ahc_outb(ahc, port+3, ((value) >> 24) & 0xFF);
+}
+
+uint64_t
+ahc_inq(struct ahc_softc *ahc, u_int port)
+{
+	return ((ahc_inb(ahc, port))
+	      | (ahc_inb(ahc, port+1) << 8)
+	      | (ahc_inb(ahc, port+2) << 16)
+	      | (ahc_inb(ahc, port+3) << 24)
+	      | (((uint64_t)ahc_inb(ahc, port+4)) << 32)
+	      | (((uint64_t)ahc_inb(ahc, port+5)) << 40)
+	      | (((uint64_t)ahc_inb(ahc, port+6)) << 48)
+	      | (((uint64_t)ahc_inb(ahc, port+7)) << 56));
+}
+
+void
+ahc_outq(struct ahc_softc *ahc, u_int port, uint64_t value)
+{
+	ahc_outb(ahc, port, value & 0xFF);
+	ahc_outb(ahc, port+1, (value >> 8) & 0xFF);
+	ahc_outb(ahc, port+2, (value >> 16) & 0xFF);
+	ahc_outb(ahc, port+3, (value >> 24) & 0xFF);
+	ahc_outb(ahc, port+4, (value >> 32) & 0xFF);
+	ahc_outb(ahc, port+5, (value >> 40) & 0xFF);
+	ahc_outb(ahc, port+6, (value >> 48) & 0xFF);
+	ahc_outb(ahc, port+7, (value >> 56) & 0xFF);
+}
+
+/*
+ * Get a free scb. If there are none, see if we can allocate a new SCB.
+ */
+struct scb *
+ahc_get_scb(struct ahc_softc *ahc)
+{
+	struct scb *scb;
+
+	if ((scb = SLIST_FIRST(&ahc->scb_data->free_scbs)) == NULL) {
+		ahc_alloc_scbs(ahc);
+		scb = SLIST_FIRST(&ahc->scb_data->free_scbs);
+		if (scb == NULL)
+			return (NULL);
+	}
+	SLIST_REMOVE_HEAD(&ahc->scb_data->free_scbs, links.sle);
+	return (scb);
+}
+
+/*
+ * Return an SCB resource to the free list.
+ */
+void
+ahc_free_scb(struct ahc_softc *ahc, struct scb *scb)
+{
+	struct hardware_scb *hscb;
+
+	hscb = scb->hscb;
+	/* Clean up for the next user */
+	ahc->scb_data->scbindex[hscb->tag] = NULL;
+	scb->flags = SCB_FREE;
+	hscb->control = 0;
+
+	SLIST_INSERT_HEAD(&ahc->scb_data->free_scbs, scb, links.sle);
+
+	/* Notify the OSM that a resource is now available. */
+	ahc_platform_scb_free(ahc, scb);
+}
+
+struct scb *
+ahc_lookup_scb(struct ahc_softc *ahc, u_int tag)
+{
+	struct scb* scb;
+
+	scb = ahc->scb_data->scbindex[tag];
+	if (scb != NULL)
+		ahc_sync_scb(ahc, scb,
+			     BUS_DMASYNC_POSTREAD|BUS_DMASYNC_POSTWRITE);
+	return (scb);
+}
+
+static void
+ahc_swap_with_next_hscb(struct ahc_softc *ahc, struct scb *scb)
+{
+	struct hardware_scb *q_hscb;
+	u_int  saved_tag;
+
+	/*
+	 * Our queuing method is a bit tricky.  The card
+	 * knows in advance which HSCB to download, and we
+	 * can't disappoint it.  To achieve this, the next
+	 * SCB to download is saved off in ahc->next_queued_scb.
+	 * When we are called to queue "an arbitrary scb",
+	 * we copy the contents of the incoming HSCB to the one
+	 * the sequencer knows about, swap HSCB pointers and
+	 * finally assign the SCB to the tag indexed location
+	 * in the scb_array.  This makes sure that we can still
+	 * locate the correct SCB by SCB_TAG.
+	 */
+	q_hscb = ahc->next_queued_scb->hscb;
+	saved_tag = q_hscb->tag;
+	memcpy(q_hscb, scb->hscb, sizeof(*scb->hscb));
+	if ((scb->flags & SCB_CDB32_PTR) != 0) {
+		q_hscb->shared_data.cdb_ptr =
+		    ahc_htole32(ahc_hscb_busaddr(ahc, q_hscb->tag)
+			      + offsetof(struct hardware_scb, cdb32));
+	}
+	q_hscb->tag = saved_tag;
+	q_hscb->next = scb->hscb->tag;
+
+	/* Now swap HSCB pointers. */
+	ahc->next_queued_scb->hscb = scb->hscb;
+	scb->hscb = q_hscb;
+
+	/* Now define the mapping from tag to SCB in the scbindex */
+	ahc->scb_data->scbindex[scb->hscb->tag] = scb;
+}
+
+/*
+ * Tell the sequencer about a new transaction to execute.
  */
 void
+ahc_queue_scb(struct ahc_softc *ahc, struct scb *scb)
+{
+	ahc_swap_with_next_hscb(ahc, scb);
+
+	if (scb->hscb->tag == SCB_LIST_NULL
+	 || scb->hscb->next == SCB_LIST_NULL)
+		panic("Attempt to queue invalid SCB tag %x:%x\n",
+		      scb->hscb->tag, scb->hscb->next);
+
+	/*
+	 * Setup data "oddness".
+	 */
+	scb->hscb->lun &= LID;
+	if (ahc_get_transfer_length(scb) & 0x1)
+		scb->hscb->lun |= SCB_XFERLEN_ODD;
+
+	/*
+	 * Keep a history of SCBs we've downloaded in the qinfifo.
+	 */
+	ahc->qinfifo[ahc->qinfifonext++] = scb->hscb->tag;
+
+	/*
+	 * Make sure our data is consistent from the
+	 * perspective of the adapter.
+	 */
+	ahc_sync_scb(ahc, scb, BUS_DMASYNC_PREREAD|BUS_DMASYNC_PREWRITE);
+
+	/* Tell the adapter about the newly queued SCB */
+	if ((ahc->features & AHC_QUEUE_REGS) != 0) {
+		ahc_outb(ahc, HNSCB_QOFF, ahc->qinfifonext);
+	} else {
+		if ((ahc->features & AHC_AUTOPAUSE) == 0)
+			ahc_pause(ahc);
+		ahc_outb(ahc, KERNEL_QINPOS, ahc->qinfifonext);
+		if ((ahc->features & AHC_AUTOPAUSE) == 0)
+			ahc_unpause(ahc);
+	}
+}
+
+struct scsi_sense_data *
+ahc_get_sense_buf(struct ahc_softc *ahc, struct scb *scb)
+{
+	int offset;
+
+	offset = scb - ahc->scb_data->scbarray;
+	return (&ahc->scb_data->sense[offset]);
+}
+
+static uint32_t
+ahc_get_sense_bufaddr(struct ahc_softc *ahc, struct scb *scb)
+{
+	int offset;
+
+	offset = scb - ahc->scb_data->scbarray;
+	return (ahc->scb_data->sense_busaddr
+	      + (offset * sizeof(struct scsi_sense_data)));
+}
+
+/************************** Interrupt Processing ******************************/
+static void
+ahc_sync_qoutfifo(struct ahc_softc *ahc, int op)
+{
+	ahc_dmamap_sync(ahc, ahc->shared_data_dmat, ahc->shared_data_dmamap,
+			/*offset*/0, /*len*/256, op);
+}
+
+static void
+ahc_sync_tqinfifo(struct ahc_softc *ahc, int op)
+{
+#ifdef AHC_TARGET_MODE
+	if ((ahc->flags & AHC_TARGETROLE) != 0) {
+		ahc_dmamap_sync(ahc, ahc->shared_data_dmat,
+				ahc->shared_data_dmamap,
+				ahc_targetcmd_offset(ahc, 0),
+				sizeof(struct target_cmd) * AHC_TMODE_CMDS,
+				op);
+	}
+#endif
+}
+
+/*
+ * See if the firmware has posted any completed commands
+ * into our in-core command complete fifos.
+ */
+#define AHC_RUN_QOUTFIFO 0x1
+#define AHC_RUN_TQINFIFO 0x2
+static u_int
+ahc_check_cmdcmpltqueues(struct ahc_softc *ahc)
+{
+	u_int retval;
+
+	retval = 0;
+	ahc_dmamap_sync(ahc, ahc->shared_data_dmat, ahc->shared_data_dmamap,
+			/*offset*/ahc->qoutfifonext, /*len*/1,
+			BUS_DMASYNC_POSTREAD);
+	if (ahc->qoutfifo[ahc->qoutfifonext] != SCB_LIST_NULL)
+		retval |= AHC_RUN_QOUTFIFO;
+#ifdef AHC_TARGET_MODE
+	if ((ahc->flags & AHC_TARGETROLE) != 0
+	 && (ahc->flags & AHC_TQINFIFO_BLOCKED) == 0) {
+		ahc_dmamap_sync(ahc, ahc->shared_data_dmat,
+				ahc->shared_data_dmamap,
+				ahc_targetcmd_offset(ahc, ahc->tqinfifofnext),
+				/*len*/sizeof(struct target_cmd),
+				BUS_DMASYNC_POSTREAD);
+		if (ahc->targetcmds[ahc->tqinfifonext].cmd_valid != 0)
+			retval |= AHC_RUN_TQINFIFO;
+	}
+#endif
+	return (retval);
+}
+
+/*
+ * Catch an interrupt from the adapter
+ */
+int
+ahc_intr(struct ahc_softc *ahc)
+{
+	u_int	intstat;
+
+	if ((ahc->pause & INTEN) == 0) {
+		/*
+		 * Our interrupt is not enabled on the chip
+		 * and may be disabled for re-entrancy reasons,
+		 * so just return.  This is likely just a shared
+		 * interrupt.
+		 */
+		return (0);
+	}
+	/*
+	 * Instead of directly reading the interrupt status register,
+	 * infer the cause of the interrupt by checking our in-core
+	 * completion queues.  This avoids a costly PCI bus read in
+	 * most cases.
+	 */
+	if ((ahc->flags & (AHC_ALL_INTERRUPTS|AHC_EDGE_INTERRUPT)) == 0
+	 && (ahc_check_cmdcmpltqueues(ahc) != 0))
+		intstat = CMDCMPLT;
+	else {
+		intstat = ahc_inb(ahc, INTSTAT);
+	}
+
+	if ((intstat & INT_PEND) == 0) {
+#if AHC_PCI_CONFIG > 0
+		if (ahc->unsolicited_ints > 500) {
+			ahc->unsolicited_ints = 0;
+			if ((ahc->chip & AHC_PCI) != 0
+			 && (ahc_inb(ahc, ERROR) & PCIERRSTAT) != 0)
+				ahc->bus_intr(ahc);
+		}
+#endif
+		ahc->unsolicited_ints++;
+		return (0);
+	}
+	ahc->unsolicited_ints = 0;
+
+	if (intstat & CMDCMPLT) {
+		ahc_outb(ahc, CLRINT, CLRCMDINT);
+
+		/*
+		 * Ensure that the chip sees that we've cleared
+		 * this interrupt before we walk the output fifo.
+		 * Otherwise, we may, due to posted bus writes,
+		 * clear the interrupt after we finish the scan,
+		 * and after the sequencer has added new entries
+		 * and asserted the interrupt again.
+		 */
+		ahc_flush_device_writes(ahc);
+		ahc_run_qoutfifo(ahc);
+#ifdef AHC_TARGET_MODE
+		if ((ahc->flags & AHC_TARGETROLE) != 0)
+			ahc_run_tqinfifo(ahc, /*paused*/FALSE);
+#endif
+	}
+
+	/*
+	 * Handle statuses that may invalidate our cached
+	 * copy of INTSTAT separately.
+	 */
+	if (intstat == 0xFF && (ahc->features & AHC_REMOVABLE) != 0) {
+		/* Hot eject.  Do nothing */
+	} else if (intstat & BRKADRINT) {
+		ahc_handle_brkadrint(ahc);
+	} else if ((intstat & (SEQINT|SCSIINT)) != 0) {
+
+		ahc_pause_bug_fix(ahc);
+
+		if ((intstat & SEQINT) != 0)
+			ahc_handle_seqint(ahc, intstat);
+
+		if ((intstat & SCSIINT) != 0)
+			ahc_handle_scsiint(ahc, intstat);
+	}
+	return (1);
+}
+
+/************************* Sequencer Execution Control ************************/
+/*
+ * Restart the sequencer program from address zero
+ */
+static void
 ahc_restart(struct ahc_softc *ahc)
 {
 
@@ -302,7 +872,7 @@ ahc_restart(struct ahc_softc *ahc)
 }
 
 /************************* Input/Output Queues ********************************/
-void
+static void
 ahc_run_qoutfifo(struct ahc_softc *ahc)
 {
 	struct scb *scb;
@@ -349,7 +919,7 @@ ahc_run_qoutfifo(struct ahc_softc *ahc)
 	}
 }
 
-void
+static void
 ahc_run_untagged_queues(struct ahc_softc *ahc)
 {
 	int i;
@@ -358,7 +928,7 @@ ahc_run_untagged_queues(struct ahc_softc *ahc)
 		ahc_run_untagged_queue(ahc, &ahc->untagged_queues[i]);
 }
 
-void
+static void
 ahc_run_untagged_queue(struct ahc_softc *ahc, struct scb_tailq *queue)
 {
 	struct scb *scb;
@@ -374,7 +944,7 @@ ahc_run_untagged_queue(struct ahc_softc *ahc, struct scb_tailq *queue)
 }
 
 /************************* Interrupt Handling *********************************/
-void
+static void
 ahc_handle_brkadrint(struct ahc_softc *ahc)
 {
 	/*
@@ -403,7 +973,7 @@ ahc_handle_brkadrint(struct ahc_softc *ahc)
 	ahc_shutdown(ahc);
 }
 
-void
+static void
 ahc_handle_seqint(struct ahc_softc *ahc, u_int intstat)
 {
 	struct scb *scb;
@@ -954,7 +1524,7 @@ ahc_handle_seqint(struct ahc_softc *ahc, u_int intstat)
 	ahc_unpause(ahc);
 }
 
-void
+static void
 ahc_handle_scsiint(struct ahc_softc *ahc, u_int intstat)
 {
 	u_int	scb_index;
@@ -1407,7 +1977,7 @@ ahc_force_renegotiation(struct ahc_softc *ahc, struct ahc_devinfo *devinfo)
 }
 
 #define AHC_MAX_STEPS 2000
-void
+static void
 ahc_clear_critical_section(struct ahc_softc *ahc)
 {
 	int	stepping;
@@ -1500,7 +2070,7 @@ ahc_clear_critical_section(struct ahc_softc *ahc)
 /*
  * Clear any pending interrupt status.
  */
-void
+static void
 ahc_clear_intstat(struct ahc_softc *ahc)
 {
 	/* Clear any interrupt conditions this may have caused */
@@ -1519,7 +2089,8 @@ ahc_clear_intstat(struct ahc_softc *ahc)
 uint32_t ahc_debug = AHC_DEBUG_OPTS;
 #endif
 
-void
+#if 0 /* unused */
+static void
 ahc_print_scb(struct scb *scb)
 {
 	int i;
@@ -1551,6 +2122,7 @@ ahc_print_scb(struct scb *scb)
 		}
 	}
 }
+#endif
 
 /************************* Transfer Negotiation *******************************/
 /*
@@ -1634,7 +2206,7 @@ ahc_free_tstate(struct ahc_softc *ahc, u_int scsi_id, char channel, int force)
  * by the capabilities of the bus connectivity of and sync settings for
  * the target.
  */
-struct ahc_syncrate *
+const struct ahc_syncrate *
 ahc_devlimited_syncrate(struct ahc_softc *ahc,
 			struct ahc_initiator_tinfo *tinfo,
 			u_int *period, u_int *ppr_options, role_t role)
@@ -1689,11 +2261,11 @@ ahc_devlimited_syncrate(struct ahc_softc *ahc,
  * Return the period and offset that should be sent to the target
  * if this was the beginning of an SDTR.
  */
-struct ahc_syncrate *
+const struct ahc_syncrate *
 ahc_find_syncrate(struct ahc_softc *ahc, u_int *period,
 		  u_int *ppr_options, u_int maxsync)
 {
-	struct ahc_syncrate *syncrate;
+	const struct ahc_syncrate *syncrate;
 
 	if ((ahc->features & AHC_DT) == 0)
 		*ppr_options &= ~MSG_EXT_PPR_DT_REQ;
@@ -1768,7 +2340,7 @@ ahc_find_syncrate(struct ahc_softc *ahc, u_int *period,
 u_int
 ahc_find_period(struct ahc_softc *ahc, u_int scsirate, u_int maxsync)
 {
-	struct ahc_syncrate *syncrate;
+	const struct ahc_syncrate *syncrate;
 
 	if ((ahc->features & AHC_ULTRA2) != 0)
 		scsirate &= SXFR_ULTRA2;
@@ -1806,10 +2378,10 @@ ahc_find_period(struct ahc_softc *ahc, u_int scsirate, u_int maxsync)
  * Truncate the given synchronous offset to a value the
  * current adapter type and syncrate are capable of.
  */
-void
+static void
 ahc_validate_offset(struct ahc_softc *ahc,
 		    struct ahc_initiator_tinfo *tinfo,
-		    struct ahc_syncrate *syncrate,
+		    const struct ahc_syncrate *syncrate,
 		    u_int *offset, int wide, role_t role)
 {
 	u_int maxoffset;
@@ -1838,7 +2410,7 @@ ahc_validate_offset(struct ahc_softc *ahc,
  * Truncate the given transfer width parameter to a value the
  * current adapter type is capable of.
  */
-void
+static void
 ahc_validate_width(struct ahc_softc *ahc, struct ahc_initiator_tinfo *tinfo,
 		   u_int *bus_width, role_t role)
 {
@@ -1913,7 +2485,7 @@ ahc_update_neg_request(struct ahc_softc *ahc, struct ahc_devinfo *devinfo,
  */
 void
 ahc_set_syncrate(struct ahc_softc *ahc, struct ahc_devinfo *devinfo,
-		 struct ahc_syncrate *syncrate, u_int period,
+		 const struct ahc_syncrate *syncrate, u_int period,
 		 u_int offset, u_int ppr_options, u_int type, int paused)
 {
 	struct	ahc_initiator_tinfo *tinfo;
@@ -2220,11 +2792,11 @@ ahc_fetch_devinfo(struct ahc_softc *ahc, struct ahc_devinfo *devinfo)
 			    role);
 }
 
-struct ahc_phase_table_entry*
+static const struct ahc_phase_table_entry*
 ahc_lookup_phase_entry(int phase)
 {
-	struct ahc_phase_table_entry *entry;
-	struct ahc_phase_table_entry *last_entry;
+	const struct ahc_phase_table_entry *entry;
+	const struct ahc_phase_table_entry *last_entry;
 
 	/*
 	 * num_phases doesn't include the default entry which
@@ -2390,7 +2962,7 @@ ahc_build_transfer_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo)
 	 */
 	struct	ahc_initiator_tinfo *tinfo;
 	struct	ahc_tmode_tstate *tstate;
-	struct	ahc_syncrate *rate;
+	const struct ahc_syncrate *rate;
 	int	dowide;
 	int	dosync;
 	int	doppr;
@@ -2655,7 +3227,7 @@ ahc_handle_proto_violation(struct ahc_softc *ahc)
  */
 static void
 ahc_handle_message_phase(struct ahc_softc *ahc)
-{ 
+{
 	struct	ahc_devinfo devinfo;
 	u_int	bus_phase;
 	int	end_session;
@@ -3056,7 +3628,7 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo)
 		switch (ahc->msgin_buf[2]) {
 		case MSG_EXT_SDTR:
 		{
-			struct	 ahc_syncrate *syncrate;
+			const struct ahc_syncrate *syncrate;
 			u_int	 period;
 			u_int	 ppr_options;
 			u_int	 offset;
@@ -3231,7 +3803,7 @@ ahc_parse_msg(struct ahc_softc *ahc, struct ahc_devinfo *devinfo)
 		}
 		case MSG_EXT_PPR:
 		{
-			struct	ahc_syncrate *syncrate;
+			const struct ahc_syncrate *syncrate;
 			u_int	period;
 			u_int	offset;
 			u_int	bus_width;
@@ -3984,7 +4556,7 @@ ahc_free(struct ahc_softc *ahc)
 	return;
 }
 
-void
+static void
 ahc_shutdown(void *arg)
 {
 	struct	ahc_softc *ahc;
@@ -4388,7 +4960,7 @@ ahc_fini_scbdata(struct ahc_softc *ahc)
 		free(scb_data->scbarray, M_DEVBUF);
 }
 
-void
+static void
 ahc_alloc_scbs(struct ahc_softc *ahc)
 {
 	struct scb_data *scb_data;
@@ -5121,7 +5693,7 @@ ahc_resume(struct ahc_softc *ahc)
  * Return the untagged transaction id for a given target/channel lun.
  * Optionally, clear the entry.
  */
-u_int
+static u_int
 ahc_index_busy_tcl(struct ahc_softc *ahc, u_int tcl)
 {
 	u_int scbid;
@@ -5142,7 +5714,7 @@ ahc_index_busy_tcl(struct ahc_softc *ahc, u_int tcl)
 	return (scbid);
 }
 
-void
+static void
 ahc_unbusy_tcl(struct ahc_softc *ahc, u_int tcl)
 {
 	u_int target_offset;
@@ -5160,7 +5732,7 @@ ahc_unbusy_tcl(struct ahc_softc *ahc, u_int tcl)
 	}
 }
 
-void
+static void
 ahc_busy_tcl(struct ahc_softc *ahc, u_int tcl, u_int scbid)
 {
 	u_int target_offset;
@@ -5215,7 +5787,7 @@ ahc_match_scb(struct ahc_softc *ahc, struct scb *scb, int target,
 	return match;
 }
 
-void
+static void
 ahc_freeze_devq(struct ahc_softc *ahc, struct scb *scb)
 {
 	int	target;
@@ -5707,7 +6279,7 @@ ahc_add_curscb_to_free_list(struct ahc_softc *ahc)
  */
 static u_int
 ahc_rem_wscb(struct ahc_softc *ahc, u_int scbpos, u_int prev)
-{       
+{
 	u_int curscb, next;
 
 	/*
@@ -5756,7 +6328,7 @@ ahc_rem_wscb(struct ahc_softc *ahc, u_int scbpos, u_int prev)
  * been modified from CAM_REQ_INPROG.  This routine assumes that the sequencer
  * is paused before it is called.
  */
-int
+static int
 ahc_abort_scbs(struct ahc_softc *ahc, int target, char channel,
 	       int lun, u_int tag, role_t role, uint32_t status)
 {
@@ -6078,7 +6650,7 @@ ahc_reset_channel(struct ahc_softc *ahc, char channel, int initiate_reset)
 /*
  * Calculate the residual for a just completed SCB.
  */
-void
+static void
 ahc_calc_residual(struct ahc_softc *ahc, struct scb *scb)
 {
 	struct hardware_scb *hscb;
@@ -6279,7 +6851,7 @@ ahc_loadseq(struct ahc_softc *ahc)
 	struct	cs cs_table[num_critical_sections];
 	u_int	begin_set[num_critical_sections];
 	u_int	end_set[num_critical_sections];
-	struct	patch *cur_patch;
+	const struct patch *cur_patch;
 	u_int	cs_count;
 	u_int	cur_cs;
 	u_int	i;
@@ -6384,11 +6956,11 @@ ahc_loadseq(struct ahc_softc *ahc)
 }
 
 static int
-ahc_check_patch(struct ahc_softc *ahc, struct patch **start_patch,
+ahc_check_patch(struct ahc_softc *ahc, const struct patch **start_patch,
 		u_int start_instr, u_int *skip_addr)
 {
-	struct	patch *cur_patch;
-	struct	patch *last_patch;
+	const struct patch *cur_patch;
+	const struct patch *last_patch;
 	u_int	num_patches;
 
 	num_patches = ARRAY_SIZE(patches);
@@ -6447,7 +7019,7 @@ ahc_download_instr(struct ahc_softc *ahc, u_int instrptr, uint8_t *dconsts)
 	case AIC_OP_JE:
 	case AIC_OP_JZ:
 	{
-		struct patch *cur_patch;
+		const struct patch *cur_patch;
 		int address_offset;
 		u_int address;
 		u_int skip_addr;
@@ -6545,7 +7117,7 @@ ahc_download_instr(struct ahc_softc *ahc, u_int instrptr, uint8_t *dconsts)
 }
 
 int
-ahc_print_register(ahc_reg_parse_entry_t *table, u_int num_entries,
+ahc_print_register(const ahc_reg_parse_entry_t *table, u_int num_entries,
 		   const char *name, u_int address, u_int value,
 		   u_int *cur_column, u_int wrap_point)
 {
@@ -7229,7 +7801,7 @@ ahc_update_scsiid(struct ahc_softc *ahc, u_int targid_mask)
 		ahc_outb(ahc, SCSIID, scsiid);
 }
 
-void
+static void
 ahc_run_tqinfifo(struct ahc_softc *ahc, int paused)
 {
 	struct target_cmd *cmd;
diff --git a/trunk/drivers/scsi/aic7xxx/aic7xxx_inline.h b/trunk/drivers/scsi/aic7xxx/aic7xxx_inline.h
index cba2f23bbe79..09bf2f4d78d5 100644
--- a/trunk/drivers/scsi/aic7xxx/aic7xxx_inline.h
+++ b/trunk/drivers/scsi/aic7xxx/aic7xxx_inline.h
@@ -46,179 +46,13 @@
 #define _AIC7XXX_INLINE_H_
 
 /************************* Sequencer Execution Control ************************/
-static __inline void ahc_pause_bug_fix(struct ahc_softc *ahc);
-static __inline int  ahc_is_paused(struct ahc_softc *ahc);
-static __inline void ahc_pause(struct ahc_softc *ahc);
-static __inline void ahc_unpause(struct ahc_softc *ahc);
-
-/*
- * Work around any chip bugs related to halting sequencer execution.
- * On Ultra2 controllers, we must clear the CIOBUS stretch signal by
- * reading a register that will set this signal and deassert it.
- * Without this workaround, if the chip is paused, by an interrupt or
- * manual pause while accessing scb ram, accesses to certain registers
- * will hang the system (infinite pci retries).
- */
-static __inline void
-ahc_pause_bug_fix(struct ahc_softc *ahc)
-{
-	if ((ahc->features & AHC_ULTRA2) != 0)
-		(void)ahc_inb(ahc, CCSCBCTL);
-}
-
-/*
- * Determine whether the sequencer has halted code execution.
- * Returns non-zero status if the sequencer is stopped.
- */
-static __inline int
-ahc_is_paused(struct ahc_softc *ahc)
-{
-	return ((ahc_inb(ahc, HCNTRL) & PAUSE) != 0);
-}
-
-/*
- * Request that the sequencer stop and wait, indefinitely, for it
- * to stop.  The sequencer will only acknowledge that it is paused
- * once it has reached an instruction boundary and PAUSEDIS is
- * cleared in the SEQCTL register.  The sequencer may use PAUSEDIS
- * for critical sections.
- */
-static __inline void
-ahc_pause(struct ahc_softc *ahc)
-{
-	ahc_outb(ahc, HCNTRL, ahc->pause);
-
-	/*
-	 * Since the sequencer can disable pausing in a critical section, we
-	 * must loop until it actually stops.
-	 */
-	while (ahc_is_paused(ahc) == 0)
-		;
-
-	ahc_pause_bug_fix(ahc);
-}
-
-/*
- * Allow the sequencer to continue program execution.
- * We check here to ensure that no additional interrupt
- * sources that would cause the sequencer to halt have been
- * asserted.  If, for example, a SCSI bus reset is detected
- * while we are fielding a different, pausing, interrupt type,
- * we don't want to release the sequencer before going back
- * into our interrupt handler and dealing with this new
- * condition.
- */
-static __inline void
-ahc_unpause(struct ahc_softc *ahc)
-{
-	if ((ahc_inb(ahc, INTSTAT) & (SCSIINT | SEQINT | BRKADRINT)) == 0)
-		ahc_outb(ahc, HCNTRL, ahc->unpause);
-}
-
-/*********************** Untagged Transaction Routines ************************/
-static __inline void	ahc_freeze_untagged_queues(struct ahc_softc *ahc);
-static __inline void	ahc_release_untagged_queues(struct ahc_softc *ahc);
-
-/*
- * Block our completion routine from starting the next untagged
- * transaction for this target or target lun.
- */
-static __inline void
-ahc_freeze_untagged_queues(struct ahc_softc *ahc)
-{
-	if ((ahc->flags & AHC_SCB_BTT) == 0)
-		ahc->untagged_queue_lock++;
-}
-
-/*
- * Allow the next untagged transaction for this target or target lun
- * to be executed.  We use a counting semaphore to allow the lock
- * to be acquired recursively.  Once the count drops to zero, the
- * transaction queues will be run.
- */
-static __inline void
-ahc_release_untagged_queues(struct ahc_softc *ahc)
-{
-	if ((ahc->flags & AHC_SCB_BTT) == 0) {
-		ahc->untagged_queue_lock--;
-		if (ahc->untagged_queue_lock == 0)
-			ahc_run_untagged_queues(ahc);
-	}
-}
+int  ahc_is_paused(struct ahc_softc *ahc);
+void ahc_pause(struct ahc_softc *ahc);
+void ahc_unpause(struct ahc_softc *ahc);
 
 /************************** Memory mapping routines ***************************/
-static __inline struct ahc_dma_seg *
-			ahc_sg_bus_to_virt(struct scb *scb,
-					   uint32_t sg_busaddr);
-static __inline uint32_t
-			ahc_sg_virt_to_bus(struct scb *scb,
-					   struct ahc_dma_seg *sg);
-static __inline uint32_t
-			ahc_hscb_busaddr(struct ahc_softc *ahc, u_int index);
-static __inline void	ahc_sync_scb(struct ahc_softc *ahc,
-				     struct scb *scb, int op);
-static __inline void	ahc_sync_sglist(struct ahc_softc *ahc,
-					struct scb *scb, int op);
-static __inline uint32_t
-			ahc_targetcmd_offset(struct ahc_softc *ahc,
-					     u_int index);
-
-static __inline struct ahc_dma_seg *
-ahc_sg_bus_to_virt(struct scb *scb, uint32_t sg_busaddr)
-{
-	int sg_index;
-
-	sg_index = (sg_busaddr - scb->sg_list_phys)/sizeof(struct ahc_dma_seg);
-	/* sg_list_phys points to entry 1, not 0 */
-	sg_index++;
-
-	return (&scb->sg_list[sg_index]);
-}
-
-static __inline uint32_t
-ahc_sg_virt_to_bus(struct scb *scb, struct ahc_dma_seg *sg)
-{
-	int sg_index;
-
-	/* sg_list_phys points to entry 1, not 0 */
-	sg_index = sg - &scb->sg_list[1];
-
-	return (scb->sg_list_phys + (sg_index * sizeof(*scb->sg_list)));
-}
-
-static __inline uint32_t
-ahc_hscb_busaddr(struct ahc_softc *ahc, u_int index)
-{
-	return (ahc->scb_data->hscb_busaddr
-		+ (sizeof(struct hardware_scb) * index));
-}
-
-static __inline void
-ahc_sync_scb(struct ahc_softc *ahc, struct scb *scb, int op)
-{
-	ahc_dmamap_sync(ahc, ahc->scb_data->hscb_dmat,
-			ahc->scb_data->hscb_dmamap,
-			/*offset*/(scb->hscb - ahc->hscbs) * sizeof(*scb->hscb),
-			/*len*/sizeof(*scb->hscb), op);
-}
-
-static __inline void
-ahc_sync_sglist(struct ahc_softc *ahc, struct scb *scb, int op)
-{
-	if (scb->sg_count == 0)
-		return;
-
-	ahc_dmamap_sync(ahc, ahc->scb_data->sg_dmat, scb->sg_map->sg_dmamap,
-			/*offset*/(scb->sg_list - scb->sg_map->sg_vaddr)
-				* sizeof(struct ahc_dma_seg),
-			/*len*/sizeof(struct ahc_dma_seg) * scb->sg_count, op);
-}
-
-static __inline uint32_t
-ahc_targetcmd_offset(struct ahc_softc *ahc, u_int index)
-{
-	return (((uint8_t *)&ahc->targetcmds[index]) - ahc->qoutfifo);
-}
+void	ahc_sync_sglist(struct ahc_softc *ahc,
+			struct scb *scb, int op);
 
 /******************************** Debugging ***********************************/
 static __inline char *ahc_name(struct ahc_softc *ahc);
@@ -231,420 +65,34 @@ ahc_name(struct ahc_softc *ahc)
 
 /*********************** Miscellaneous Support Functions ***********************/
 
-static __inline void	ahc_update_residual(struct ahc_softc *ahc,
-					    struct scb *scb);
-static __inline struct ahc_initiator_tinfo *
-			ahc_fetch_transinfo(struct ahc_softc *ahc,
-					    char channel, u_int our_id,
-					    u_int remote_id,
-					    struct ahc_tmode_tstate **tstate);
-static __inline uint16_t
-			ahc_inw(struct ahc_softc *ahc, u_int port);
-static __inline void	ahc_outw(struct ahc_softc *ahc, u_int port,
-				 u_int value);
-static __inline uint32_t
-			ahc_inl(struct ahc_softc *ahc, u_int port);
-static __inline void	ahc_outl(struct ahc_softc *ahc, u_int port,
-				 uint32_t value);
-static __inline uint64_t
-			ahc_inq(struct ahc_softc *ahc, u_int port);
-static __inline void	ahc_outq(struct ahc_softc *ahc, u_int port,
-				 uint64_t value);
-static __inline struct scb*
-			ahc_get_scb(struct ahc_softc *ahc);
-static __inline void	ahc_free_scb(struct ahc_softc *ahc, struct scb *scb);
-static __inline void	ahc_swap_with_next_hscb(struct ahc_softc *ahc,
-						struct scb *scb);
-static __inline void	ahc_queue_scb(struct ahc_softc *ahc, struct scb *scb);
-static __inline struct scsi_sense_data *
-			ahc_get_sense_buf(struct ahc_softc *ahc,
-					  struct scb *scb);
-static __inline uint32_t
-			ahc_get_sense_bufaddr(struct ahc_softc *ahc,
-					      struct scb *scb);
-
-/*
- * Determine whether the sequencer reported a residual
- * for this SCB/transaction.
- */
-static __inline void
-ahc_update_residual(struct ahc_softc *ahc, struct scb *scb)
-{
-	uint32_t sgptr;
-
-	sgptr = ahc_le32toh(scb->hscb->sgptr);
-	if ((sgptr & SG_RESID_VALID) != 0)
-		ahc_calc_residual(ahc, scb);
-}
-
-/*
- * Return pointers to the transfer negotiation information
- * for the specified our_id/remote_id pair.
- */
-static __inline struct ahc_initiator_tinfo *
-ahc_fetch_transinfo(struct ahc_softc *ahc, char channel, u_int our_id,
-		    u_int remote_id, struct ahc_tmode_tstate **tstate)
-{
-	/*
-	 * Transfer data structures are stored from the perspective
-	 * of the target role.  Since the parameters for a connection
-	 * in the initiator role to a given target are the same as
-	 * when the roles are reversed, we pretend we are the target.
-	 */
-	if (channel == 'B')
-		our_id += 8;
-	*tstate = ahc->enabled_targets[our_id];
-	return (&(*tstate)->transinfo[remote_id]);
-}
-
-static __inline uint16_t
-ahc_inw(struct ahc_softc *ahc, u_int port)
-{
-	uint16_t r = ahc_inb(ahc, port+1) << 8;
-	return r | ahc_inb(ahc, port);
-}
-
-static __inline void
-ahc_outw(struct ahc_softc *ahc, u_int port, u_int value)
-{
-	ahc_outb(ahc, port, value & 0xFF);
-	ahc_outb(ahc, port+1, (value >> 8) & 0xFF);
-}
-
-static __inline uint32_t
-ahc_inl(struct ahc_softc *ahc, u_int port)
-{
-	return ((ahc_inb(ahc, port))
-	      | (ahc_inb(ahc, port+1) << 8)
-	      | (ahc_inb(ahc, port+2) << 16)
-	      | (ahc_inb(ahc, port+3) << 24));
-}
-
-static __inline void
-ahc_outl(struct ahc_softc *ahc, u_int port, uint32_t value)
-{
-	ahc_outb(ahc, port, (value) & 0xFF);
-	ahc_outb(ahc, port+1, ((value) >> 8) & 0xFF);
-	ahc_outb(ahc, port+2, ((value) >> 16) & 0xFF);
-	ahc_outb(ahc, port+3, ((value) >> 24) & 0xFF);
-}
-
-static __inline uint64_t
-ahc_inq(struct ahc_softc *ahc, u_int port)
-{
-	return ((ahc_inb(ahc, port))
-	      | (ahc_inb(ahc, port+1) << 8)
-	      | (ahc_inb(ahc, port+2) << 16)
-	      | (ahc_inb(ahc, port+3) << 24)
-	      | (((uint64_t)ahc_inb(ahc, port+4)) << 32)
-	      | (((uint64_t)ahc_inb(ahc, port+5)) << 40)
-	      | (((uint64_t)ahc_inb(ahc, port+6)) << 48)
-	      | (((uint64_t)ahc_inb(ahc, port+7)) << 56));
-}
-
-static __inline void
-ahc_outq(struct ahc_softc *ahc, u_int port, uint64_t value)
-{
-	ahc_outb(ahc, port, value & 0xFF);
-	ahc_outb(ahc, port+1, (value >> 8) & 0xFF);
-	ahc_outb(ahc, port+2, (value >> 16) & 0xFF);
-	ahc_outb(ahc, port+3, (value >> 24) & 0xFF);
-	ahc_outb(ahc, port+4, (value >> 32) & 0xFF);
-	ahc_outb(ahc, port+5, (value >> 40) & 0xFF);
-	ahc_outb(ahc, port+6, (value >> 48) & 0xFF);
-	ahc_outb(ahc, port+7, (value >> 56) & 0xFF);
-}
-
-/*
- * Get a free scb. If there are none, see if we can allocate a new SCB.
- */
-static __inline struct scb *
-ahc_get_scb(struct ahc_softc *ahc)
-{
-	struct scb *scb;
-
-	if ((scb = SLIST_FIRST(&ahc->scb_data->free_scbs)) == NULL) {
-		ahc_alloc_scbs(ahc);
-		scb = SLIST_FIRST(&ahc->scb_data->free_scbs);
-		if (scb == NULL)
-			return (NULL);
-	}
-	SLIST_REMOVE_HEAD(&ahc->scb_data->free_scbs, links.sle);
-	return (scb);
-}
-
-/*
- * Return an SCB resource to the free list.
- */
-static __inline void
-ahc_free_scb(struct ahc_softc *ahc, struct scb *scb)
-{       
-	struct hardware_scb *hscb;
-
-	hscb = scb->hscb;
-	/* Clean up for the next user */
-	ahc->scb_data->scbindex[hscb->tag] = NULL;
-	scb->flags = SCB_FREE;
-	hscb->control = 0;
-
-	SLIST_INSERT_HEAD(&ahc->scb_data->free_scbs, scb, links.sle);
-
-	/* Notify the OSM that a resource is now available. */
-	ahc_platform_scb_free(ahc, scb);
-}
-
-static __inline struct scb *
-ahc_lookup_scb(struct ahc_softc *ahc, u_int tag)
-{
-	struct scb* scb;
-
-	scb = ahc->scb_data->scbindex[tag];
-	if (scb != NULL)
-		ahc_sync_scb(ahc, scb,
-			     BUS_DMASYNC_POSTREAD|BUS_DMASYNC_POSTWRITE);
-	return (scb);
-}
-
-static __inline void
-ahc_swap_with_next_hscb(struct ahc_softc *ahc, struct scb *scb)
-{
-	struct hardware_scb *q_hscb;
-	u_int  saved_tag;
-
-	/*
-	 * Our queuing method is a bit tricky.  The card
-	 * knows in advance which HSCB to download, and we
-	 * can't disappoint it.  To achieve this, the next
-	 * SCB to download is saved off in ahc->next_queued_scb.
-	 * When we are called to queue "an arbitrary scb",
-	 * we copy the contents of the incoming HSCB to the one
-	 * the sequencer knows about, swap HSCB pointers and
-	 * finally assign the SCB to the tag indexed location
-	 * in the scb_array.  This makes sure that we can still
-	 * locate the correct SCB by SCB_TAG.
-	 */
-	q_hscb = ahc->next_queued_scb->hscb;
-	saved_tag = q_hscb->tag;
-	memcpy(q_hscb, scb->hscb, sizeof(*scb->hscb));
-	if ((scb->flags & SCB_CDB32_PTR) != 0) {
-		q_hscb->shared_data.cdb_ptr =
-		    ahc_htole32(ahc_hscb_busaddr(ahc, q_hscb->tag)
-			      + offsetof(struct hardware_scb, cdb32));
-	}
-	q_hscb->tag = saved_tag;
-	q_hscb->next = scb->hscb->tag;
-
-	/* Now swap HSCB pointers. */
-	ahc->next_queued_scb->hscb = scb->hscb;
-	scb->hscb = q_hscb;
-
-	/* Now define the mapping from tag to SCB in the scbindex */
-	ahc->scb_data->scbindex[scb->hscb->tag] = scb;
-}
-
-/*
- * Tell the sequencer about a new transaction to execute.
- */
-static __inline void
-ahc_queue_scb(struct ahc_softc *ahc, struct scb *scb)
-{
-	ahc_swap_with_next_hscb(ahc, scb);
-
-	if (scb->hscb->tag == SCB_LIST_NULL
-	 || scb->hscb->next == SCB_LIST_NULL)
-		panic("Attempt to queue invalid SCB tag %x:%x\n",
-		      scb->hscb->tag, scb->hscb->next);
-
-	/*
-	 * Setup data "oddness".
-	 */
-	scb->hscb->lun &= LID;
-	if (ahc_get_transfer_length(scb) & 0x1)
-		scb->hscb->lun |= SCB_XFERLEN_ODD;
-
-	/*
-	 * Keep a history of SCBs we've downloaded in the qinfifo.
-	 */
-	ahc->qinfifo[ahc->qinfifonext++] = scb->hscb->tag;
-
-	/*
-	 * Make sure our data is consistent from the
-	 * perspective of the adapter.
-	 */
-	ahc_sync_scb(ahc, scb, BUS_DMASYNC_PREREAD|BUS_DMASYNC_PREWRITE);
-
-	/* Tell the adapter about the newly queued SCB */
-	if ((ahc->features & AHC_QUEUE_REGS) != 0) {
-		ahc_outb(ahc, HNSCB_QOFF, ahc->qinfifonext);
-	} else {
-		if ((ahc->features & AHC_AUTOPAUSE) == 0)
-			ahc_pause(ahc);
-		ahc_outb(ahc, KERNEL_QINPOS, ahc->qinfifonext);
-		if ((ahc->features & AHC_AUTOPAUSE) == 0)
-			ahc_unpause(ahc);
-	}
-}
-
-static __inline struct scsi_sense_data *
-ahc_get_sense_buf(struct ahc_softc *ahc, struct scb *scb)
-{
-	int offset;
-
-	offset = scb - ahc->scb_data->scbarray;
-	return (&ahc->scb_data->sense[offset]);
-}
-
-static __inline uint32_t
-ahc_get_sense_bufaddr(struct ahc_softc *ahc, struct scb *scb)
-{
-	int offset;
-
-	offset = scb - ahc->scb_data->scbarray;
-	return (ahc->scb_data->sense_busaddr
-	      + (offset * sizeof(struct scsi_sense_data)));
-}
+struct ahc_initiator_tinfo *
+	ahc_fetch_transinfo(struct ahc_softc *ahc,
+			    char channel, u_int our_id,
+			    u_int remote_id,
+			    struct ahc_tmode_tstate **tstate);
+uint16_t
+	ahc_inw(struct ahc_softc *ahc, u_int port);
+void	ahc_outw(struct ahc_softc *ahc, u_int port,
+		 u_int value);
+uint32_t
+	ahc_inl(struct ahc_softc *ahc, u_int port);
+void	ahc_outl(struct ahc_softc *ahc, u_int port,
+		 uint32_t value);
+uint64_t
+	ahc_inq(struct ahc_softc *ahc, u_int port);
+void	ahc_outq(struct ahc_softc *ahc, u_int port,
+		 uint64_t value);
+struct scb*
+	ahc_get_scb(struct ahc_softc *ahc);
+void	ahc_free_scb(struct ahc_softc *ahc, struct scb *scb);
+struct scb *
+	ahc_lookup_scb(struct ahc_softc *ahc, u_int tag);
+void	ahc_queue_scb(struct ahc_softc *ahc, struct scb *scb);
+struct scsi_sense_data *
+	ahc_get_sense_buf(struct ahc_softc *ahc,
+			  struct scb *scb);
 
 /************************** Interrupt Processing ******************************/
-static __inline void	ahc_sync_qoutfifo(struct ahc_softc *ahc, int op);
-static __inline void	ahc_sync_tqinfifo(struct ahc_softc *ahc, int op);
-static __inline u_int	ahc_check_cmdcmpltqueues(struct ahc_softc *ahc);
-static __inline int	ahc_intr(struct ahc_softc *ahc);
-
-static __inline void
-ahc_sync_qoutfifo(struct ahc_softc *ahc, int op)
-{
-	ahc_dmamap_sync(ahc, ahc->shared_data_dmat, ahc->shared_data_dmamap,
-			/*offset*/0, /*len*/256, op);
-}
-
-static __inline void
-ahc_sync_tqinfifo(struct ahc_softc *ahc, int op)
-{
-#ifdef AHC_TARGET_MODE
-	if ((ahc->flags & AHC_TARGETROLE) != 0) {
-		ahc_dmamap_sync(ahc, ahc->shared_data_dmat,
-				ahc->shared_data_dmamap,
-				ahc_targetcmd_offset(ahc, 0),
-				sizeof(struct target_cmd) * AHC_TMODE_CMDS,
-				op);
-	}
-#endif
-}
-
-/*
- * See if the firmware has posted any completed commands
- * into our in-core command complete fifos.
- */
-#define AHC_RUN_QOUTFIFO 0x1
-#define AHC_RUN_TQINFIFO 0x2
-static __inline u_int
-ahc_check_cmdcmpltqueues(struct ahc_softc *ahc)
-{
-	u_int retval;
-
-	retval = 0;
-	ahc_dmamap_sync(ahc, ahc->shared_data_dmat, ahc->shared_data_dmamap,
-			/*offset*/ahc->qoutfifonext, /*len*/1,
-			BUS_DMASYNC_POSTREAD);
-	if (ahc->qoutfifo[ahc->qoutfifonext] != SCB_LIST_NULL)
-		retval |= AHC_RUN_QOUTFIFO;
-#ifdef AHC_TARGET_MODE
-	if ((ahc->flags & AHC_TARGETROLE) != 0
-	 && (ahc->flags & AHC_TQINFIFO_BLOCKED) == 0) {
-		ahc_dmamap_sync(ahc, ahc->shared_data_dmat,
-				ahc->shared_data_dmamap,
-				ahc_targetcmd_offset(ahc, ahc->tqinfifofnext),
-				/*len*/sizeof(struct target_cmd),
-				BUS_DMASYNC_POSTREAD);
-		if (ahc->targetcmds[ahc->tqinfifonext].cmd_valid != 0)
-			retval |= AHC_RUN_TQINFIFO;
-	}
-#endif
-	return (retval);
-}
-
-/*
- * Catch an interrupt from the adapter
- */
-static __inline int
-ahc_intr(struct ahc_softc *ahc)
-{
-	u_int	intstat;
-
-	if ((ahc->pause & INTEN) == 0) {
-		/*
-		 * Our interrupt is not enabled on the chip
-		 * and may be disabled for re-entrancy reasons,
-		 * so just return.  This is likely just a shared
-		 * interrupt.
-		 */
-		return (0);
-	}
-	/*
-	 * Instead of directly reading the interrupt status register,
-	 * infer the cause of the interrupt by checking our in-core
-	 * completion queues.  This avoids a costly PCI bus read in
-	 * most cases.
-	 */
-	if ((ahc->flags & (AHC_ALL_INTERRUPTS|AHC_EDGE_INTERRUPT)) == 0
-	 && (ahc_check_cmdcmpltqueues(ahc) != 0))
-		intstat = CMDCMPLT;
-	else {
-		intstat = ahc_inb(ahc, INTSTAT);
-	}
-
-	if ((intstat & INT_PEND) == 0) {
-#if AHC_PCI_CONFIG > 0
-		if (ahc->unsolicited_ints > 500) {
-			ahc->unsolicited_ints = 0;
-			if ((ahc->chip & AHC_PCI) != 0
-			 && (ahc_inb(ahc, ERROR) & PCIERRSTAT) != 0)
-				ahc->bus_intr(ahc);
-		}
-#endif
-		ahc->unsolicited_ints++;
-		return (0);
-	}
-	ahc->unsolicited_ints = 0;
-
-	if (intstat & CMDCMPLT) {
-		ahc_outb(ahc, CLRINT, CLRCMDINT);
-
-		/*
-		 * Ensure that the chip sees that we've cleared
-		 * this interrupt before we walk the output fifo.
-		 * Otherwise, we may, due to posted bus writes,
-		 * clear the interrupt after we finish the scan,
-		 * and after the sequencer has added new entries
-		 * and asserted the interrupt again.
-		 */
-		ahc_flush_device_writes(ahc);
-		ahc_run_qoutfifo(ahc);
-#ifdef AHC_TARGET_MODE
-		if ((ahc->flags & AHC_TARGETROLE) != 0)
-			ahc_run_tqinfifo(ahc, /*paused*/FALSE);
-#endif
-	}
-
-	/*
-	 * Handle statuses that may invalidate our cached
-	 * copy of INTSTAT separately.
-	 */
-	if (intstat == 0xFF && (ahc->features & AHC_REMOVABLE) != 0) {
-		/* Hot eject.  Do nothing */
-	} else if (intstat & BRKADRINT) {
-		ahc_handle_brkadrint(ahc);
-	} else if ((intstat & (SEQINT|SCSIINT)) != 0) {
-
-		ahc_pause_bug_fix(ahc);
-
-		if ((intstat & SEQINT) != 0)
-			ahc_handle_seqint(ahc, intstat);
-
-		if ((intstat & SCSIINT) != 0)
-			ahc_handle_scsiint(ahc, intstat);
-	}
-	return (1);
-}
+int	ahc_intr(struct ahc_softc *ahc);
 
 #endif  /* _AIC7XXX_INLINE_H_ */
diff --git a/trunk/drivers/scsi/aic7xxx/aic7xxx_osm.c b/trunk/drivers/scsi/aic7xxx/aic7xxx_osm.c
index 42ad48e09f02..fd2b9785ff4f 100644
--- a/trunk/drivers/scsi/aic7xxx/aic7xxx_osm.c
+++ b/trunk/drivers/scsi/aic7xxx/aic7xxx_osm.c
@@ -388,14 +388,83 @@ static int  aic7xxx_setup(char *s);
 static int ahc_linux_unit;
 
 
+/************************** OS Utility Wrappers *******************************/
+void
+ahc_delay(long usec)
+{
+	/*
+	 * udelay on Linux can have problems for
+	 * multi-millisecond waits.  Wait at most
+	 * 1024us per call.
+	 */
+	while (usec > 0) {
+		udelay(usec % 1024);
+		usec -= 1024;
+	}
+}
+
+/***************************** Low Level I/O **********************************/
+uint8_t
+ahc_inb(struct ahc_softc * ahc, long port)
+{
+	uint8_t x;
+
+	if (ahc->tag == BUS_SPACE_MEMIO) {
+		x = readb(ahc->bsh.maddr + port);
+	} else {
+		x = inb(ahc->bsh.ioport + port);
+	}
+	mb();
+	return (x);
+}
+
+void
+ahc_outb(struct ahc_softc * ahc, long port, uint8_t val)
+{
+	if (ahc->tag == BUS_SPACE_MEMIO) {
+		writeb(val, ahc->bsh.maddr + port);
+	} else {
+		outb(val, ahc->bsh.ioport + port);
+	}
+	mb();
+}
+
+void
+ahc_outsb(struct ahc_softc * ahc, long port, uint8_t *array, int count)
+{
+	int i;
+
+	/*
+	 * There is probably a more efficient way to do this on Linux
+	 * but we don't use this for anything speed critical and this
+	 * should work.
+	 */
+	for (i = 0; i < count; i++)
+		ahc_outb(ahc, port, *array++);
+}
+
+void
+ahc_insb(struct ahc_softc * ahc, long port, uint8_t *array, int count)
+{
+	int i;
+
+	/*
+	 * There is probably a more efficient way to do this on Linux
+	 * but we don't use this for anything speed critical and this
+	 * should work.
+	 */
+	for (i = 0; i < count; i++)
+		*array++ = ahc_inb(ahc, port);
+}
+
 /********************************* Inlines ************************************/
-static __inline void ahc_linux_unmap_scb(struct ahc_softc*, struct scb*);
+static void ahc_linux_unmap_scb(struct ahc_softc*, struct scb*);
 
-static __inline int ahc_linux_map_seg(struct ahc_softc *ahc, struct scb *scb,
+static int ahc_linux_map_seg(struct ahc_softc *ahc, struct scb *scb,
 		 		      struct ahc_dma_seg *sg,
 				      dma_addr_t addr, bus_size_t len);
 
-static __inline void
+static void
 ahc_linux_unmap_scb(struct ahc_softc *ahc, struct scb *scb)
 {
 	struct scsi_cmnd *cmd;
@@ -406,7 +475,7 @@ ahc_linux_unmap_scb(struct ahc_softc *ahc, struct scb *scb)
 	scsi_dma_unmap(cmd);
 }
 
-static __inline int
+static int
 ahc_linux_map_seg(struct ahc_softc *ahc, struct scb *scb,
 		  struct ahc_dma_seg *sg, dma_addr_t addr, bus_size_t len)
 {
@@ -442,13 +511,11 @@ ahc_linux_info(struct Scsi_Host *host)
 	bp = &buffer[0];
 	ahc = *(struct ahc_softc **)host->hostdata;
 	memset(bp, 0, sizeof(buffer));
-	strcpy(bp, "Adaptec AIC7XXX EISA/VLB/PCI SCSI HBA DRIVER, Rev ");
-	strcat(bp, AIC7XXX_DRIVER_VERSION);
-	strcat(bp, "\n");
-	strcat(bp, "        <");
+	strcpy(bp, "Adaptec AIC7XXX EISA/VLB/PCI SCSI HBA DRIVER, Rev " AIC7XXX_DRIVER_VERSION "\n"
+			"        <");
 	strcat(bp, ahc->description);
-	strcat(bp, ">\n");
-	strcat(bp, "        ");
+	strcat(bp, ">\n"
+			"        ");
 	ahc_controller_info(ahc, ahc_info);
 	strcat(bp, ahc_info);
 	strcat(bp, "\n");
@@ -964,7 +1031,7 @@ aic7xxx_setup(char *s)
 	char   *p;
 	char   *end;
 
-	static struct {
+	static const struct {
 		const char *name;
 		uint32_t *flag;
 	} options[] = {
@@ -2317,7 +2384,7 @@ static void ahc_linux_set_period(struct scsi_target *starget, int period)
 	unsigned int ppr_options = tinfo->goal.ppr_options;
 	unsigned long flags;
 	unsigned long offset = tinfo->goal.offset;
-	struct ahc_syncrate *syncrate;
+	const struct ahc_syncrate *syncrate;
 
 	if (offset == 0)
 		offset = MAX_OFFSET;
@@ -2361,7 +2428,7 @@ static void ahc_linux_set_offset(struct scsi_target *starget, int offset)
 	unsigned int ppr_options = 0;
 	unsigned int period = 0;
 	unsigned long flags;
-	struct ahc_syncrate *syncrate = NULL;
+	const struct ahc_syncrate *syncrate = NULL;
 
 	ahc_compile_devinfo(&devinfo, shost->this_id, starget->id, 0,
 			    starget->channel + 'A', ROLE_INITIATOR);
@@ -2391,7 +2458,7 @@ static void ahc_linux_set_dt(struct scsi_target *starget, int dt)
 	unsigned int period = tinfo->goal.period;
 	unsigned int width = tinfo->goal.width;
 	unsigned long flags;
-	struct ahc_syncrate *syncrate;
+	const struct ahc_syncrate *syncrate;
 
 	if (dt && spi_max_width(starget)) {
 		ppr_options |= MSG_EXT_PPR_DT_REQ;
diff --git a/trunk/drivers/scsi/aic7xxx/aic7xxx_osm.h b/trunk/drivers/scsi/aic7xxx/aic7xxx_osm.h
index b48dab447bde..3f7238db35e5 100644
--- a/trunk/drivers/scsi/aic7xxx/aic7xxx_osm.h
+++ b/trunk/drivers/scsi/aic7xxx/aic7xxx_osm.h
@@ -365,7 +365,7 @@ struct ahc_platform_data {
 #define AHC_LINUX_NOIRQ	((uint32_t)~0)
 	uint32_t		 irq;		/* IRQ for this adapter */
 	uint32_t		 bios_address;
-	uint32_t		 mem_busaddr;	/* Mem Base Addr */
+	resource_size_t 	 mem_busaddr;	/* Mem Base Addr */
 };
 
 /************************** OS Utility Wrappers *******************************/
@@ -375,82 +375,16 @@ struct ahc_platform_data {
 #define malloc(size, type, flags) kmalloc(size, flags)
 #define free(ptr, type) kfree(ptr)
 
-static __inline void ahc_delay(long);
-static __inline void
-ahc_delay(long usec)
-{
-	/*
-	 * udelay on Linux can have problems for
-	 * multi-millisecond waits.  Wait at most
-	 * 1024us per call.
-	 */
-	while (usec > 0) {
-		udelay(usec % 1024);
-		usec -= 1024;
-	}
-}
+void ahc_delay(long);
 
 
 /***************************** Low Level I/O **********************************/
-static __inline uint8_t ahc_inb(struct ahc_softc * ahc, long port);
-static __inline void ahc_outb(struct ahc_softc * ahc, long port, uint8_t val);
-static __inline void ahc_outsb(struct ahc_softc * ahc, long port,
-			       uint8_t *, int count);
-static __inline void ahc_insb(struct ahc_softc * ahc, long port,
-			       uint8_t *, int count);
-
-static __inline uint8_t
-ahc_inb(struct ahc_softc * ahc, long port)
-{
-	uint8_t x;
-
-	if (ahc->tag == BUS_SPACE_MEMIO) {
-		x = readb(ahc->bsh.maddr + port);
-	} else {
-		x = inb(ahc->bsh.ioport + port);
-	}
-	mb();
-	return (x);
-}
-
-static __inline void
-ahc_outb(struct ahc_softc * ahc, long port, uint8_t val)
-{
-	if (ahc->tag == BUS_SPACE_MEMIO) {
-		writeb(val, ahc->bsh.maddr + port);
-	} else {
-		outb(val, ahc->bsh.ioport + port);
-	}
-	mb();
-}
-
-static __inline void
-ahc_outsb(struct ahc_softc * ahc, long port, uint8_t *array, int count)
-{
-	int i;
-
-	/*
-	 * There is probably a more efficient way to do this on Linux
-	 * but we don't use this for anything speed critical and this
-	 * should work.
-	 */
-	for (i = 0; i < count; i++)
-		ahc_outb(ahc, port, *array++);
-}
-
-static __inline void
-ahc_insb(struct ahc_softc * ahc, long port, uint8_t *array, int count)
-{
-	int i;
-
-	/*
-	 * There is probably a more efficient way to do this on Linux
-	 * but we don't use this for anything speed critical and this
-	 * should work.
-	 */
-	for (i = 0; i < count; i++)
-		*array++ = ahc_inb(ahc, port);
-}
+uint8_t ahc_inb(struct ahc_softc * ahc, long port);
+void ahc_outb(struct ahc_softc * ahc, long port, uint8_t val);
+void ahc_outsb(struct ahc_softc * ahc, long port,
+	       uint8_t *, int count);
+void ahc_insb(struct ahc_softc * ahc, long port,
+	       uint8_t *, int count);
 
 /**************************** Initialization **********************************/
 int		ahc_linux_register_host(struct ahc_softc *,
@@ -464,9 +398,6 @@ struct info_str {
 	int pos;
 };
 
-void	ahc_format_transinfo(struct info_str *info,
-			     struct ahc_transinfo *tinfo);
-
 /******************************** Locking *************************************/
 /* Lock protecting internal data structures */
 
@@ -555,61 +486,12 @@ void			 ahc_linux_pci_exit(void);
 int			 ahc_pci_map_registers(struct ahc_softc *ahc);
 int			 ahc_pci_map_int(struct ahc_softc *ahc);
 
-static __inline uint32_t ahc_pci_read_config(ahc_dev_softc_t pci,
+uint32_t		 ahc_pci_read_config(ahc_dev_softc_t pci,
 					     int reg, int width);
 
-static __inline uint32_t
-ahc_pci_read_config(ahc_dev_softc_t pci, int reg, int width)
-{
-	switch (width) {
-	case 1:
-	{
-		uint8_t retval;
-
-		pci_read_config_byte(pci, reg, &retval);
-		return (retval);
-	}
-	case 2:
-	{
-		uint16_t retval;
-		pci_read_config_word(pci, reg, &retval);
-		return (retval);
-	}
-	case 4:
-	{
-		uint32_t retval;
-		pci_read_config_dword(pci, reg, &retval);
-		return (retval);
-	}
-	default:
-		panic("ahc_pci_read_config: Read size too big");
-		/* NOTREACHED */
-		return (0);
-	}
-}
-
-static __inline void ahc_pci_write_config(ahc_dev_softc_t pci,
-					  int reg, uint32_t value,
-					  int width);
-
-static __inline void
-ahc_pci_write_config(ahc_dev_softc_t pci, int reg, uint32_t value, int width)
-{
-	switch (width) {
-	case 1:
-		pci_write_config_byte(pci, reg, value);
-		break;
-	case 2:
-		pci_write_config_word(pci, reg, value);
-		break;
-	case 4:
-		pci_write_config_dword(pci, reg, value);
-		break;
-	default:
-		panic("ahc_pci_write_config: Write size too big");
-		/* NOTREACHED */
-	}
-}
+void			 ahc_pci_write_config(ahc_dev_softc_t pci,
+					      int reg, uint32_t value,
+					      int width);
 
 static __inline int ahc_get_pci_function(ahc_dev_softc_t);
 static __inline int
diff --git a/trunk/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c b/trunk/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c
index 3d3eaef65fb3..00f5b9868574 100644
--- a/trunk/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c
+++ b/trunk/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c
@@ -46,7 +46,7 @@
 */
 #define ID(x)	ID_C(x, PCI_CLASS_STORAGE_SCSI)
 
-static struct pci_device_id ahc_linux_pci_id_table[] = {
+static const struct pci_device_id ahc_linux_pci_id_table[] = {
 	/* aic7850 based controllers */
 	ID(ID_AHA_2902_04_10_15_20C_30C),
 	/* aic7860 based controllers */
@@ -206,7 +206,7 @@ ahc_linux_pci_dev_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	const uint64_t	 mask_39bit = 0x7FFFFFFFFFULL;
 	struct		 ahc_softc *ahc;
 	ahc_dev_softc_t	 pci;
-	struct		 ahc_pci_identity *entry;
+	const struct ahc_pci_identity *entry;
 	char		*name;
 	int		 error;
 	struct device	*dev = &pdev->dev;
@@ -269,6 +269,57 @@ ahc_linux_pci_dev_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return (0);
 }
 
+/******************************* PCI Routines *********************************/
+uint32_t
+ahc_pci_read_config(ahc_dev_softc_t pci, int reg, int width)
+{
+	switch (width) {
+	case 1:
+	{
+		uint8_t retval;
+
+		pci_read_config_byte(pci, reg, &retval);
+		return (retval);
+	}
+	case 2:
+	{
+		uint16_t retval;
+		pci_read_config_word(pci, reg, &retval);
+		return (retval);
+	}
+	case 4:
+	{
+		uint32_t retval;
+		pci_read_config_dword(pci, reg, &retval);
+		return (retval);
+	}
+	default:
+		panic("ahc_pci_read_config: Read size too big");
+		/* NOTREACHED */
+		return (0);
+	}
+}
+
+void
+ahc_pci_write_config(ahc_dev_softc_t pci, int reg, uint32_t value, int width)
+{
+	switch (width) {
+	case 1:
+		pci_write_config_byte(pci, reg, value);
+		break;
+	case 2:
+		pci_write_config_word(pci, reg, value);
+		break;
+	case 4:
+		pci_write_config_dword(pci, reg, value);
+		break;
+	default:
+		panic("ahc_pci_write_config: Write size too big");
+		/* NOTREACHED */
+	}
+}
+
+
 static struct pci_driver aic7xxx_pci_driver = {
 	.name		= "aic7xxx",
 	.probe		= ahc_linux_pci_dev_probe,
@@ -293,7 +344,7 @@ ahc_linux_pci_exit(void)
 }
 
 static int
-ahc_linux_pci_reserve_io_region(struct ahc_softc *ahc, u_long *base)
+ahc_linux_pci_reserve_io_region(struct ahc_softc *ahc, resource_size_t *base)
 {
 	if (aic7xxx_allow_memio == 0)
 		return (ENOMEM);
@@ -301,24 +352,24 @@ ahc_linux_pci_reserve_io_region(struct ahc_softc *ahc, u_long *base)
 	*base = pci_resource_start(ahc->dev_softc, 0);
 	if (*base == 0)
 		return (ENOMEM);
-	if (request_region(*base, 256, "aic7xxx") == 0)
+	if (!request_region(*base, 256, "aic7xxx"))
 		return (ENOMEM);
 	return (0);
 }
 
 static int
 ahc_linux_pci_reserve_mem_region(struct ahc_softc *ahc,
-				 u_long *bus_addr,
+				 resource_size_t *bus_addr,
 				 uint8_t __iomem **maddr)
 {
-	u_long	start;
+	resource_size_t	start;
 	int	error;
 
 	error = 0;
 	start = pci_resource_start(ahc->dev_softc, 1);
 	if (start != 0) {
 		*bus_addr = start;
-		if (request_mem_region(start, 0x1000, "aic7xxx") == 0)
+		if (!request_mem_region(start, 0x1000, "aic7xxx"))
 			error = ENOMEM;
 		if (error == 0) {
 			*maddr = ioremap_nocache(start, 256);
@@ -336,7 +387,7 @@ int
 ahc_pci_map_registers(struct ahc_softc *ahc)
 {
 	uint32_t command;
-	u_long	 base;
+	resource_size_t	base;
 	uint8_t	__iomem *maddr;
 	int	 error;
 
@@ -374,12 +425,12 @@ ahc_pci_map_registers(struct ahc_softc *ahc)
 		} else
 			command |= PCIM_CMD_MEMEN;
 	} else {
-		printf("aic7xxx: PCI%d:%d:%d MEM region 0x%lx "
+		printf("aic7xxx: PCI%d:%d:%d MEM region 0x%llx "
 		       "unavailable. Cannot memory map device.\n",
 		       ahc_get_pci_bus(ahc->dev_softc),
 		       ahc_get_pci_slot(ahc->dev_softc),
 		       ahc_get_pci_function(ahc->dev_softc),
-		       base);
+		       (unsigned long long)base);
 	}
 
 	/*
@@ -390,15 +441,15 @@ ahc_pci_map_registers(struct ahc_softc *ahc)
 		error = ahc_linux_pci_reserve_io_region(ahc, &base);
 		if (error == 0) {
 			ahc->tag = BUS_SPACE_PIO;
-			ahc->bsh.ioport = base;
+			ahc->bsh.ioport = (u_long)base;
 			command |= PCIM_CMD_PORTEN;
 		} else {
-			printf("aic7xxx: PCI%d:%d:%d IO region 0x%lx[0..255] "
+			printf("aic7xxx: PCI%d:%d:%d IO region 0x%llx[0..255] "
 			       "unavailable. Cannot map device.\n",
 			       ahc_get_pci_bus(ahc->dev_softc),
 			       ahc_get_pci_slot(ahc->dev_softc),
 			       ahc_get_pci_function(ahc->dev_softc),
-			       base);
+			       (unsigned long long)base);
 		}
 	}
 	ahc_pci_write_config(ahc->dev_softc, PCIR_COMMAND, command, 4);
diff --git a/trunk/drivers/scsi/aic7xxx/aic7xxx_pci.c b/trunk/drivers/scsi/aic7xxx/aic7xxx_pci.c
index 56848f41e4f9..c07cb6eebb02 100644
--- a/trunk/drivers/scsi/aic7xxx/aic7xxx_pci.c
+++ b/trunk/drivers/scsi/aic7xxx/aic7xxx_pci.c
@@ -168,8 +168,7 @@ static ahc_device_setup_t ahc_aha394XX_setup;
 static ahc_device_setup_t ahc_aha494XX_setup;
 static ahc_device_setup_t ahc_aha398XX_setup;
 
-static struct ahc_pci_identity ahc_pci_ident_table [] =
-{
+static const struct ahc_pci_identity ahc_pci_ident_table[] = {
 	/* aic7850 based controllers */
 	{
 		ID_AHA_2902_04_10_15_20C_30C,
@@ -668,7 +667,7 @@ ahc_9005_subdevinfo_valid(uint16_t device, uint16_t vendor,
 	return (result);
 }
 
-struct ahc_pci_identity *
+const struct ahc_pci_identity *
 ahc_find_pci_device(ahc_dev_softc_t pci)
 {
 	uint64_t  full_id;
@@ -676,7 +675,7 @@ ahc_find_pci_device(ahc_dev_softc_t pci)
 	uint16_t  vendor;
 	uint16_t  subdevice;
 	uint16_t  subvendor;
-	struct	  ahc_pci_identity *entry;
+	const struct ahc_pci_identity *entry;
 	u_int	  i;
 
 	vendor = ahc_pci_read_config(pci, PCIR_DEVVENDOR, /*bytes*/2);
@@ -710,7 +709,7 @@ ahc_find_pci_device(ahc_dev_softc_t pci)
 }
 
 int
-ahc_pci_config(struct ahc_softc *ahc, struct ahc_pci_identity *entry)
+ahc_pci_config(struct ahc_softc *ahc, const struct ahc_pci_identity *entry)
 {
 	u_int	 command;
 	u_int	 our_id;
diff --git a/trunk/drivers/scsi/aic7xxx/aic7xxx_proc.c b/trunk/drivers/scsi/aic7xxx/aic7xxx_proc.c
index 99e5443e7535..e92991a7c485 100644
--- a/trunk/drivers/scsi/aic7xxx/aic7xxx_proc.c
+++ b/trunk/drivers/scsi/aic7xxx/aic7xxx_proc.c
@@ -58,7 +58,7 @@ static int	ahc_proc_write_seeprom(struct ahc_softc *ahc,
  * Table of syncrates that don't follow the "divisible by 4"
  * rule. This table will be expanded in future SCSI specs.
  */
-static struct {
+static const struct {
 	u_int period_factor;
 	u_int period;	/* in 100ths of ns */
 } scsi_syncrates[] = {
@@ -137,7 +137,7 @@ copy_info(struct info_str *info, char *fmt, ...)
 	return (len);
 }
 
-void
+static void
 ahc_format_transinfo(struct info_str *info, struct ahc_transinfo *tinfo)
 {
 	u_int speed;
diff --git a/trunk/drivers/scsi/aic7xxx/aic7xxx_reg_print.c_shipped b/trunk/drivers/scsi/aic7xxx/aic7xxx_reg_print.c_shipped
index 88bfd767c51c..309a562b009e 100644
--- a/trunk/drivers/scsi/aic7xxx/aic7xxx_reg_print.c_shipped
+++ b/trunk/drivers/scsi/aic7xxx/aic7xxx_reg_print.c_shipped
@@ -8,7 +8,7 @@
 
 #include "aic7xxx_osm.h"
 
-static ahc_reg_parse_entry_t SCSISEQ_parse_table[] = {
+static const ahc_reg_parse_entry_t SCSISEQ_parse_table[] = {
 	{ "SCSIRSTO",		0x01, 0x01 },
 	{ "ENAUTOATNP",		0x02, 0x02 },
 	{ "ENAUTOATNI",		0x04, 0x04 },
@@ -26,7 +26,7 @@ ahc_scsiseq_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x00, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SXFRCTL0_parse_table[] = {
+static const ahc_reg_parse_entry_t SXFRCTL0_parse_table[] = {
 	{ "CLRCHN",		0x02, 0x02 },
 	{ "SCAMEN",		0x04, 0x04 },
 	{ "SPIOEN",		0x08, 0x08 },
@@ -43,7 +43,7 @@ ahc_sxfrctl0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x01, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SXFRCTL1_parse_table[] = {
+static const ahc_reg_parse_entry_t SXFRCTL1_parse_table[] = {
 	{ "STPWEN",		0x01, 0x01 },
 	{ "ACTNEGEN",		0x02, 0x02 },
 	{ "ENSTIMER",		0x04, 0x04 },
@@ -60,7 +60,7 @@ ahc_sxfrctl1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x02, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SCSISIGO_parse_table[] = {
+static const ahc_reg_parse_entry_t SCSISIGO_parse_table[] = {
 	{ "ACKO",		0x01, 0x01 },
 	{ "REQO",		0x02, 0x02 },
 	{ "BSYO",		0x04, 0x04 },
@@ -85,7 +85,7 @@ ahc_scsisigo_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x03, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SCSISIGI_parse_table[] = {
+static const ahc_reg_parse_entry_t SCSISIGI_parse_table[] = {
 	{ "ACKI",		0x01, 0x01 },
 	{ "REQI",		0x02, 0x02 },
 	{ "BSYI",		0x04, 0x04 },
@@ -112,7 +112,7 @@ ahc_scsisigi_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x03, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SCSIRATE_parse_table[] = {
+static const ahc_reg_parse_entry_t SCSIRATE_parse_table[] = {
 	{ "SINGLE_EDGE",	0x10, 0x10 },
 	{ "ENABLE_CRC",		0x40, 0x40 },
 	{ "WIDEXFER",		0x80, 0x80 },
@@ -128,7 +128,7 @@ ahc_scsirate_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x04, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SCSIID_parse_table[] = {
+static const ahc_reg_parse_entry_t SCSIID_parse_table[] = {
 	{ "TWIN_CHNLB",		0x80, 0x80 },
 	{ "OID",		0x0f, 0x0f },
 	{ "TWIN_TID",		0x70, 0x70 },
@@ -150,13 +150,6 @@ ahc_scsidatl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x06, regvalue, cur_col, wrap));
 }
 
-int
-ahc_scsidath_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahc_print_register(NULL, 0, "SCSIDATH",
-	    0x07, regvalue, cur_col, wrap));
-}
-
 int
 ahc_stcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -164,7 +157,7 @@ ahc_stcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x08, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t OPTIONMODE_parse_table[] = {
+static const ahc_reg_parse_entry_t OPTIONMODE_parse_table[] = {
 	{ "DIS_MSGIN_DUALEDGE",	0x01, 0x01 },
 	{ "AUTO_MSGOUT_DE",	0x02, 0x02 },
 	{ "SCSIDATL_IMGEN",	0x04, 0x04 },
@@ -190,7 +183,7 @@ ahc_targcrccnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x0a, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t CLRSINT0_parse_table[] = {
+static const ahc_reg_parse_entry_t CLRSINT0_parse_table[] = {
 	{ "CLRSPIORDY",		0x02, 0x02 },
 	{ "CLRSWRAP",		0x08, 0x08 },
 	{ "CLRIOERR",		0x08, 0x08 },
@@ -206,7 +199,7 @@ ahc_clrsint0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x0b, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SSTAT0_parse_table[] = {
+static const ahc_reg_parse_entry_t SSTAT0_parse_table[] = {
 	{ "DMADONE",		0x01, 0x01 },
 	{ "SPIORDY",		0x02, 0x02 },
 	{ "SDONE",		0x04, 0x04 },
@@ -225,7 +218,7 @@ ahc_sstat0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x0b, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t CLRSINT1_parse_table[] = {
+static const ahc_reg_parse_entry_t CLRSINT1_parse_table[] = {
 	{ "CLRREQINIT",		0x01, 0x01 },
 	{ "CLRPHASECHG",	0x02, 0x02 },
 	{ "CLRSCSIPERR",	0x04, 0x04 },
@@ -242,7 +235,7 @@ ahc_clrsint1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x0c, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SSTAT1_parse_table[] = {
+static const ahc_reg_parse_entry_t SSTAT1_parse_table[] = {
 	{ "REQINIT",		0x01, 0x01 },
 	{ "PHASECHG",		0x02, 0x02 },
 	{ "SCSIPERR",		0x04, 0x04 },
@@ -260,7 +253,7 @@ ahc_sstat1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x0c, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SSTAT2_parse_table[] = {
+static const ahc_reg_parse_entry_t SSTAT2_parse_table[] = {
 	{ "DUAL_EDGE_ERR",	0x01, 0x01 },
 	{ "CRCREQERR",		0x02, 0x02 },
 	{ "CRCENDERR",		0x04, 0x04 },
@@ -278,7 +271,7 @@ ahc_sstat2_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x0d, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SSTAT3_parse_table[] = {
+static const ahc_reg_parse_entry_t SSTAT3_parse_table[] = {
 	{ "OFFCNT",		0x0f, 0x0f },
 	{ "U2OFFCNT",		0x7f, 0x7f },
 	{ "SCSICNT",		0xf0, 0xf0 }
@@ -291,7 +284,7 @@ ahc_sstat3_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x0e, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SCSIID_ULTRA2_parse_table[] = {
+static const ahc_reg_parse_entry_t SCSIID_ULTRA2_parse_table[] = {
 	{ "OID",		0x0f, 0x0f },
 	{ "TID",		0xf0, 0xf0 }
 };
@@ -303,7 +296,7 @@ ahc_scsiid_ultra2_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x0f, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SIMODE0_parse_table[] = {
+static const ahc_reg_parse_entry_t SIMODE0_parse_table[] = {
 	{ "ENDMADONE",		0x01, 0x01 },
 	{ "ENSPIORDY",		0x02, 0x02 },
 	{ "ENSDONE",		0x04, 0x04 },
@@ -321,7 +314,7 @@ ahc_simode0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x10, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SIMODE1_parse_table[] = {
+static const ahc_reg_parse_entry_t SIMODE1_parse_table[] = {
 	{ "ENREQINIT",		0x01, 0x01 },
 	{ "ENPHASECHG",		0x02, 0x02 },
 	{ "ENSCSIPERR",		0x04, 0x04 },
@@ -346,26 +339,6 @@ ahc_scsibusl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x12, regvalue, cur_col, wrap));
 }
 
-int
-ahc_scsibush_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahc_print_register(NULL, 0, "SCSIBUSH",
-	    0x13, regvalue, cur_col, wrap));
-}
-
-static ahc_reg_parse_entry_t SXFRCTL2_parse_table[] = {
-	{ "CMDDMAEN",		0x08, 0x08 },
-	{ "AUTORSTDIS",		0x10, 0x10 },
-	{ "ASYNC_SETUP",	0x07, 0x07 }
-};
-
-int
-ahc_sxfrctl2_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahc_print_register(SXFRCTL2_parse_table, 3, "SXFRCTL2",
-	    0x13, regvalue, cur_col, wrap));
-}
-
 int
 ahc_shaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -373,7 +346,7 @@ ahc_shaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x14, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SELTIMER_parse_table[] = {
+static const ahc_reg_parse_entry_t SELTIMER_parse_table[] = {
 	{ "STAGE1",		0x01, 0x01 },
 	{ "STAGE2",		0x02, 0x02 },
 	{ "STAGE3",		0x04, 0x04 },
@@ -389,7 +362,7 @@ ahc_seltimer_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x18, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SELID_parse_table[] = {
+static const ahc_reg_parse_entry_t SELID_parse_table[] = {
 	{ "ONEBIT",		0x08, 0x08 },
 	{ "SELID_MASK",		0xf0, 0xf0 }
 };
@@ -401,21 +374,6 @@ ahc_selid_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x19, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SCAMCTL_parse_table[] = {
-	{ "DFLTTID",		0x10, 0x10 },
-	{ "ALTSTIM",		0x20, 0x20 },
-	{ "CLRSCAMSELID",	0x40, 0x40 },
-	{ "ENSCAMSELO",		0x80, 0x80 },
-	{ "SCAMLVL",		0x03, 0x03 }
-};
-
-int
-ahc_scamctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahc_print_register(SCAMCTL_parse_table, 5, "SCAMCTL",
-	    0x1a, regvalue, cur_col, wrap));
-}
-
 int
 ahc_targid_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -423,7 +381,7 @@ ahc_targid_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x1b, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SPIOCAP_parse_table[] = {
+static const ahc_reg_parse_entry_t SPIOCAP_parse_table[] = {
 	{ "SSPIOCPS",		0x01, 0x01 },
 	{ "ROM",		0x02, 0x02 },
 	{ "EEPROM",		0x04, 0x04 },
@@ -441,7 +399,7 @@ ahc_spiocap_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x1b, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t BRDCTL_parse_table[] = {
+static const ahc_reg_parse_entry_t BRDCTL_parse_table[] = {
 	{ "BRDCTL0",		0x01, 0x01 },
 	{ "BRDSTB_ULTRA2",	0x01, 0x01 },
 	{ "BRDCTL1",		0x02, 0x02 },
@@ -464,7 +422,7 @@ ahc_brdctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x1d, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SEECTL_parse_table[] = {
+static const ahc_reg_parse_entry_t SEECTL_parse_table[] = {
 	{ "SEEDI",		0x01, 0x01 },
 	{ "SEEDO",		0x02, 0x02 },
 	{ "SEECK",		0x04, 0x04 },
@@ -482,7 +440,7 @@ ahc_seectl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x1e, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SBLKCTL_parse_table[] = {
+static const ahc_reg_parse_entry_t SBLKCTL_parse_table[] = {
 	{ "XCVR",		0x01, 0x01 },
 	{ "SELWIDE",		0x02, 0x02 },
 	{ "ENAB20",		0x04, 0x04 },
@@ -521,13 +479,6 @@ ahc_disc_dsb_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x32, regvalue, cur_col, wrap));
 }
 
-int
-ahc_cmdsize_table_tail_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahc_print_register(NULL, 0, "CMDSIZE_TABLE_TAIL",
-	    0x34, regvalue, cur_col, wrap));
-}
-
 int
 ahc_mwi_residual_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -549,7 +500,7 @@ ahc_msg_out_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x3a, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t DMAPARAMS_parse_table[] = {
+static const ahc_reg_parse_entry_t DMAPARAMS_parse_table[] = {
 	{ "FIFORESET",		0x01, 0x01 },
 	{ "FIFOFLUSH",		0x02, 0x02 },
 	{ "DIRECTION",		0x04, 0x04 },
@@ -569,7 +520,7 @@ ahc_dmaparams_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x3b, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SEQ_FLAGS_parse_table[] = {
+static const ahc_reg_parse_entry_t SEQ_FLAGS_parse_table[] = {
 	{ "NO_DISCONNECT",	0x01, 0x01 },
 	{ "SPHASE_PENDING",	0x02, 0x02 },
 	{ "DPHASE_PENDING",	0x04, 0x04 },
@@ -602,7 +553,7 @@ ahc_saved_lun_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x3e, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t LASTPHASE_parse_table[] = {
+static const ahc_reg_parse_entry_t LASTPHASE_parse_table[] = {
 	{ "MSGI",		0x20, 0x20 },
 	{ "IOI",		0x40, 0x40 },
 	{ "CDI",		0x80, 0x80 },
@@ -644,13 +595,6 @@ ahc_free_scbh_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x42, regvalue, cur_col, wrap));
 }
 
-int
-ahc_complete_scbh_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahc_print_register(NULL, 0, "COMPLETE_SCBH",
-	    0x43, regvalue, cur_col, wrap));
-}
-
 int
 ahc_hscb_addr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -700,7 +644,7 @@ ahc_tqinpos_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x50, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t ARG_1_parse_table[] = {
+static const ahc_reg_parse_entry_t ARG_1_parse_table[] = {
 	{ "CONT_TARG_SESSION",	0x02, 0x02 },
 	{ "CONT_MSG_LOOP",	0x04, 0x04 },
 	{ "EXIT_MSG_LOOP",	0x08, 0x08 },
@@ -731,7 +675,7 @@ ahc_last_msg_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x53, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SCSISEQ_TEMPLATE_parse_table[] = {
+static const ahc_reg_parse_entry_t SCSISEQ_TEMPLATE_parse_table[] = {
 	{ "ENAUTOATNP",		0x02, 0x02 },
 	{ "ENAUTOATNI",		0x04, 0x04 },
 	{ "ENAUTOATNO",		0x08, 0x08 },
@@ -747,7 +691,7 @@ ahc_scsiseq_template_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x54, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t HA_274_BIOSGLOBAL_parse_table[] = {
+static const ahc_reg_parse_entry_t HA_274_BIOSGLOBAL_parse_table[] = {
 	{ "HA_274_EXTENDED_TRANS",0x01, 0x01 }
 };
 
@@ -758,7 +702,7 @@ ahc_ha_274_biosglobal_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x56, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SEQ_FLAGS2_parse_table[] = {
+static const ahc_reg_parse_entry_t SEQ_FLAGS2_parse_table[] = {
 	{ "SCB_DMA",		0x01, 0x01 },
 	{ "TARGET_MSG_PENDING",	0x02, 0x02 }
 };
@@ -770,7 +714,7 @@ ahc_seq_flags2_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x57, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SCSICONF_parse_table[] = {
+static const ahc_reg_parse_entry_t SCSICONF_parse_table[] = {
 	{ "ENSPCHK",		0x20, 0x20 },
 	{ "RESET_SCSI",		0x40, 0x40 },
 	{ "TERM_ENB",		0x80, 0x80 },
@@ -785,7 +729,7 @@ ahc_scsiconf_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x5a, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t INTDEF_parse_table[] = {
+static const ahc_reg_parse_entry_t INTDEF_parse_table[] = {
 	{ "EDGE_TRIG",		0x80, 0x80 },
 	{ "VECTOR",		0x0f, 0x0f }
 };
@@ -804,7 +748,7 @@ ahc_hostconf_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x5d, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t HA_274_BIOSCTRL_parse_table[] = {
+static const ahc_reg_parse_entry_t HA_274_BIOSCTRL_parse_table[] = {
 	{ "CHANNEL_B_PRIMARY",	0x08, 0x08 },
 	{ "BIOSMODE",		0x30, 0x30 },
 	{ "BIOSDISABLED",	0x30, 0x30 }
@@ -817,7 +761,7 @@ ahc_ha_274_biosctrl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x5f, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SEQCTL_parse_table[] = {
+static const ahc_reg_parse_entry_t SEQCTL_parse_table[] = {
 	{ "LOADRAM",		0x01, 0x01 },
 	{ "SEQRESET",		0x02, 0x02 },
 	{ "STEP",		0x04, 0x04 },
@@ -849,7 +793,7 @@ ahc_seqaddr0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x62, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SEQADDR1_parse_table[] = {
+static const ahc_reg_parse_entry_t SEQADDR1_parse_table[] = {
 	{ "SEQADDR1_MASK",	0x01, 0x01 }
 };
 
@@ -902,7 +846,7 @@ ahc_none_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x6a, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t FLAGS_parse_table[] = {
+static const ahc_reg_parse_entry_t FLAGS_parse_table[] = {
 	{ "CARRY",		0x01, 0x01 },
 	{ "ZERO",		0x02, 0x02 }
 };
@@ -928,13 +872,6 @@ ahc_dindir_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x6d, regvalue, cur_col, wrap));
 }
 
-int
-ahc_function1_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahc_print_register(NULL, 0, "FUNCTION1",
-	    0x6e, regvalue, cur_col, wrap));
-}
-
 int
 ahc_stack_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -956,19 +893,7 @@ ahc_sram_base_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x70, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t BCTL_parse_table[] = {
-	{ "ENABLE",		0x01, 0x01 },
-	{ "ACE",		0x08, 0x08 }
-};
-
-int
-ahc_bctl_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahc_print_register(BCTL_parse_table, 2, "BCTL",
-	    0x84, regvalue, cur_col, wrap));
-}
-
-static ahc_reg_parse_entry_t DSCOMMAND0_parse_table[] = {
+static const ahc_reg_parse_entry_t DSCOMMAND0_parse_table[] = {
 	{ "CIOPARCKEN",		0x01, 0x01 },
 	{ "USCBSIZE32",		0x02, 0x02 },
 	{ "RAMPS",		0x04, 0x04 },
@@ -986,7 +911,7 @@ ahc_dscommand0_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x84, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t BUSTIME_parse_table[] = {
+static const ahc_reg_parse_entry_t BUSTIME_parse_table[] = {
 	{ "BON",		0x0f, 0x0f },
 	{ "BOFF",		0xf0, 0xf0 }
 };
@@ -998,7 +923,7 @@ ahc_bustime_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x85, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t DSCOMMAND1_parse_table[] = {
+static const ahc_reg_parse_entry_t DSCOMMAND1_parse_table[] = {
 	{ "HADDLDSEL0",		0x01, 0x01 },
 	{ "HADDLDSEL1",		0x02, 0x02 },
 	{ "DSLATT",		0xfc, 0xfc }
@@ -1011,7 +936,7 @@ ahc_dscommand1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x85, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t BUSSPD_parse_table[] = {
+static const ahc_reg_parse_entry_t BUSSPD_parse_table[] = {
 	{ "STBON",		0x07, 0x07 },
 	{ "STBOFF",		0x38, 0x38 },
 	{ "DFTHRSH_75",		0x80, 0x80 },
@@ -1026,7 +951,7 @@ ahc_busspd_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x86, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t HS_MAILBOX_parse_table[] = {
+static const ahc_reg_parse_entry_t HS_MAILBOX_parse_table[] = {
 	{ "SEQ_MAILBOX",	0x0f, 0x0f },
 	{ "HOST_TQINPOS",	0x80, 0x80 },
 	{ "HOST_MAILBOX",	0xf0, 0xf0 }
@@ -1039,7 +964,7 @@ ahc_hs_mailbox_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x86, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t DSPCISTATUS_parse_table[] = {
+static const ahc_reg_parse_entry_t DSPCISTATUS_parse_table[] = {
 	{ "DFTHRSH_100",	0xc0, 0xc0 }
 };
 
@@ -1050,7 +975,7 @@ ahc_dspcistatus_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x86, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t HCNTRL_parse_table[] = {
+static const ahc_reg_parse_entry_t HCNTRL_parse_table[] = {
 	{ "CHIPRST",		0x01, 0x01 },
 	{ "CHIPRSTACK",		0x01, 0x01 },
 	{ "INTEN",		0x02, 0x02 },
@@ -1088,7 +1013,7 @@ ahc_scbptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x90, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t INTSTAT_parse_table[] = {
+static const ahc_reg_parse_entry_t INTSTAT_parse_table[] = {
 	{ "SEQINT",		0x01, 0x01 },
 	{ "CMDCMPLT",		0x02, 0x02 },
 	{ "SCSIINT",		0x04, 0x04 },
@@ -1119,7 +1044,7 @@ ahc_intstat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x91, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t CLRINT_parse_table[] = {
+static const ahc_reg_parse_entry_t CLRINT_parse_table[] = {
 	{ "CLRSEQINT",		0x01, 0x01 },
 	{ "CLRCMDINT",		0x02, 0x02 },
 	{ "CLRSCSIINT",		0x04, 0x04 },
@@ -1134,7 +1059,7 @@ ahc_clrint_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x92, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t ERROR_parse_table[] = {
+static const ahc_reg_parse_entry_t ERROR_parse_table[] = {
 	{ "ILLHADDR",		0x01, 0x01 },
 	{ "ILLSADDR",		0x02, 0x02 },
 	{ "ILLOPCODE",		0x04, 0x04 },
@@ -1152,7 +1077,7 @@ ahc_error_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x92, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t DFCNTRL_parse_table[] = {
+static const ahc_reg_parse_entry_t DFCNTRL_parse_table[] = {
 	{ "FIFORESET",		0x01, 0x01 },
 	{ "FIFOFLUSH",		0x02, 0x02 },
 	{ "DIRECTION",		0x04, 0x04 },
@@ -1172,7 +1097,7 @@ ahc_dfcntrl_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x93, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t DFSTATUS_parse_table[] = {
+static const ahc_reg_parse_entry_t DFSTATUS_parse_table[] = {
 	{ "FIFOEMP",		0x01, 0x01 },
 	{ "FIFOFULL",		0x02, 0x02 },
 	{ "DFTHRESH",		0x04, 0x04 },
@@ -1197,13 +1122,6 @@ ahc_dfwaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x95, regvalue, cur_col, wrap));
 }
 
-int
-ahc_dfraddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahc_print_register(NULL, 0, "DFRADDR",
-	    0x97, regvalue, cur_col, wrap));
-}
-
 int
 ahc_dfdat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -1211,7 +1129,7 @@ ahc_dfdat_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x99, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SCBCNT_parse_table[] = {
+static const ahc_reg_parse_entry_t SCBCNT_parse_table[] = {
 	{ "SCBAUTO",		0x80, 0x80 },
 	{ "SCBCNT_MASK",	0x1f, 0x1f }
 };
@@ -1230,13 +1148,6 @@ ahc_qinfifo_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x9b, regvalue, cur_col, wrap));
 }
 
-int
-ahc_qincnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahc_print_register(NULL, 0, "QINCNT",
-	    0x9c, regvalue, cur_col, wrap));
-}
-
 int
 ahc_qoutfifo_print(u_int regvalue, u_int *cur_col, u_int wrap)
 {
@@ -1244,7 +1155,7 @@ ahc_qoutfifo_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x9d, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t CRCCONTROL1_parse_table[] = {
+static const ahc_reg_parse_entry_t CRCCONTROL1_parse_table[] = {
 	{ "TARGCRCCNTEN",	0x04, 0x04 },
 	{ "TARGCRCENDEN",	0x08, 0x08 },
 	{ "CRCREQCHKEN",	0x10, 0x10 },
@@ -1260,14 +1171,7 @@ ahc_crccontrol1_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x9d, regvalue, cur_col, wrap));
 }
 
-int
-ahc_qoutcnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahc_print_register(NULL, 0, "QOUTCNT",
-	    0x9e, regvalue, cur_col, wrap));
-}
-
-static ahc_reg_parse_entry_t SCSIPHASE_parse_table[] = {
+static const ahc_reg_parse_entry_t SCSIPHASE_parse_table[] = {
 	{ "DATA_OUT_PHASE",	0x01, 0x01 },
 	{ "DATA_IN_PHASE",	0x02, 0x02 },
 	{ "MSG_OUT_PHASE",	0x04, 0x04 },
@@ -1284,7 +1188,7 @@ ahc_scsiphase_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0x9e, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SFUNCT_parse_table[] = {
+static const ahc_reg_parse_entry_t SFUNCT_parse_table[] = {
 	{ "ALT_MODE",		0x80, 0x80 }
 };
 
@@ -1351,7 +1255,7 @@ ahc_scb_dataptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xac, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SCB_DATACNT_parse_table[] = {
+static const ahc_reg_parse_entry_t SCB_DATACNT_parse_table[] = {
 	{ "SG_LAST_SEG",	0x80, 0x80 },
 	{ "SG_HIGH_ADDR_BITS",	0x7f, 0x7f }
 };
@@ -1363,7 +1267,7 @@ ahc_scb_datacnt_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xb0, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SCB_SGPTR_parse_table[] = {
+static const ahc_reg_parse_entry_t SCB_SGPTR_parse_table[] = {
 	{ "SG_LIST_NULL",	0x01, 0x01 },
 	{ "SG_FULL_RESID",	0x02, 0x02 },
 	{ "SG_RESID_VALID",	0x04, 0x04 }
@@ -1376,7 +1280,7 @@ ahc_scb_sgptr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xb4, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SCB_CONTROL_parse_table[] = {
+static const ahc_reg_parse_entry_t SCB_CONTROL_parse_table[] = {
 	{ "DISCONNECTED",	0x04, 0x04 },
 	{ "ULTRAENB",		0x08, 0x08 },
 	{ "MK_MESSAGE",		0x10, 0x10 },
@@ -1394,7 +1298,7 @@ ahc_scb_control_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xb8, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SCB_SCSIID_parse_table[] = {
+static const ahc_reg_parse_entry_t SCB_SCSIID_parse_table[] = {
 	{ "TWIN_CHNLB",		0x80, 0x80 },
 	{ "OID",		0x0f, 0x0f },
 	{ "TWIN_TID",		0x70, 0x70 },
@@ -1408,7 +1312,7 @@ ahc_scb_scsiid_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xb9, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SCB_LUN_parse_table[] = {
+static const ahc_reg_parse_entry_t SCB_LUN_parse_table[] = {
 	{ "SCB_XFERLEN_ODD",	0x80, 0x80 },
 	{ "LID",		0x3f, 0x3f }
 };
@@ -1455,14 +1359,7 @@ ahc_scb_next_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xbf, regvalue, cur_col, wrap));
 }
 
-int
-ahc_scb_64_spare_print(u_int regvalue, u_int *cur_col, u_int wrap)
-{
-	return (ahc_print_register(NULL, 0, "SCB_64_SPARE",
-	    0xc0, regvalue, cur_col, wrap));
-}
-
-static ahc_reg_parse_entry_t SEECTL_2840_parse_table[] = {
+static const ahc_reg_parse_entry_t SEECTL_2840_parse_table[] = {
 	{ "DO_2840",		0x01, 0x01 },
 	{ "CK_2840",		0x02, 0x02 },
 	{ "CS_2840",		0x04, 0x04 }
@@ -1475,7 +1372,7 @@ ahc_seectl_2840_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xc0, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t STATUS_2840_parse_table[] = {
+static const ahc_reg_parse_entry_t STATUS_2840_parse_table[] = {
 	{ "DI_2840",		0x01, 0x01 },
 	{ "EEPROM_TF",		0x80, 0x80 },
 	{ "ADSEL",		0x1e, 0x1e },
@@ -1524,7 +1421,7 @@ ahc_ccsgaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xea, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t CCSGCTL_parse_table[] = {
+static const ahc_reg_parse_entry_t CCSGCTL_parse_table[] = {
 	{ "CCSGRESET",		0x01, 0x01 },
 	{ "SG_FETCH_NEEDED",	0x02, 0x02 },
 	{ "CCSGEN",		0x08, 0x08 },
@@ -1552,7 +1449,7 @@ ahc_ccscbaddr_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xed, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t CCSCBCTL_parse_table[] = {
+static const ahc_reg_parse_entry_t CCSCBCTL_parse_table[] = {
 	{ "CCSCBRESET",		0x01, 0x01 },
 	{ "CCSCBDIR",		0x04, 0x04 },
 	{ "CCSCBEN",		0x08, 0x08 },
@@ -1610,7 +1507,7 @@ ahc_sdscb_qoff_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xf8, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t QOFF_CTLSTA_parse_table[] = {
+static const ahc_reg_parse_entry_t QOFF_CTLSTA_parse_table[] = {
 	{ "SDSCB_ROLLOVER",	0x10, 0x10 },
 	{ "SNSCB_ROLLOVER",	0x20, 0x20 },
 	{ "SCB_AVAIL",		0x40, 0x40 },
@@ -1625,7 +1522,7 @@ ahc_qoff_ctlsta_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xfa, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t DFF_THRSH_parse_table[] = {
+static const ahc_reg_parse_entry_t DFF_THRSH_parse_table[] = {
 	{ "RD_DFTHRSH_MIN",	0x00, 0x00 },
 	{ "WR_DFTHRSH_MIN",	0x00, 0x00 },
 	{ "RD_DFTHRSH_25",	0x01, 0x01 },
@@ -1653,7 +1550,7 @@ ahc_dff_thrsh_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xfb, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SG_CACHE_SHADOW_parse_table[] = {
+static const ahc_reg_parse_entry_t SG_CACHE_SHADOW_parse_table[] = {
 	{ "LAST_SEG_DONE",	0x01, 0x01 },
 	{ "LAST_SEG",		0x02, 0x02 },
 	{ "SG_ADDR_MASK",	0xf8, 0xf8 }
@@ -1666,7 +1563,7 @@ ahc_sg_cache_shadow_print(u_int regvalue, u_int *cur_col, u_int wrap)
 	    0xfc, regvalue, cur_col, wrap));
 }
 
-static ahc_reg_parse_entry_t SG_CACHE_PRE_parse_table[] = {
+static const ahc_reg_parse_entry_t SG_CACHE_PRE_parse_table[] = {
 	{ "LAST_SEG_DONE",	0x01, 0x01 },
 	{ "LAST_SEG",		0x02, 0x02 },
 	{ "SG_ADDR_MASK",	0xf8, 0xf8 }
diff --git a/trunk/drivers/scsi/aic7xxx/aic7xxx_seq.h_shipped b/trunk/drivers/scsi/aic7xxx/aic7xxx_seq.h_shipped
index 4cee08521e75..07e93fbae706 100644
--- a/trunk/drivers/scsi/aic7xxx/aic7xxx_seq.h_shipped
+++ b/trunk/drivers/scsi/aic7xxx/aic7xxx_seq.h_shipped
@@ -5,7 +5,7 @@
  * $Id: //depot/aic7xxx/aic7xxx/aic7xxx.seq#58 $
  * $Id: //depot/aic7xxx/aic7xxx/aic7xxx.reg#40 $
  */
-static uint8_t seqprog[] = {
+static const uint8_t seqprog[] = {
 	0xb2, 0x00, 0x00, 0x08,
 	0xf7, 0x11, 0x22, 0x08,
 	0x00, 0x65, 0xee, 0x59,
@@ -1081,7 +1081,7 @@ ahc_patch0_func(struct ahc_softc *ahc)
 	return (0);
 }
 
-static struct patch {
+static const struct patch {
 	ahc_patch_func_t		*patch_func;
 	uint32_t		 begin		:10,
 				 skip_instr	:10,
@@ -1291,7 +1291,7 @@ static struct patch {
 	{ ahc_patch4_func, 865, 12, 1 }
 };
 
-static struct cs {
+static const struct cs {
 	uint16_t	begin;
 	uint16_t	end;
 } critical_sections[] = {
diff --git a/trunk/drivers/scsi/aic7xxx/aicasm/aicasm.c b/trunk/drivers/scsi/aic7xxx/aicasm/aicasm.c
index 924102720b14..e4a778720301 100644
--- a/trunk/drivers/scsi/aic7xxx/aicasm/aicasm.c
+++ b/trunk/drivers/scsi/aic7xxx/aicasm/aicasm.c
@@ -362,7 +362,7 @@ output_code()
 " *\n"
 "%s */\n", versions);
 
-	fprintf(ofile, "static uint8_t seqprog[] = {\n");
+	fprintf(ofile, "static const uint8_t seqprog[] = {\n");
 	for (cur_instr = STAILQ_FIRST(&seq_program);
 	     cur_instr != NULL;
 	     cur_instr = STAILQ_NEXT(cur_instr, links)) {
@@ -415,7 +415,7 @@ output_code()
 	}
 
 	fprintf(ofile,
-"static struct patch {\n"
+"static const struct patch {\n"
 "	%spatch_func_t		*patch_func;\n"
 "	uint32_t		 begin		:10,\n"
 "				 skip_instr	:10,\n"
@@ -435,7 +435,7 @@ output_code()
 	fprintf(ofile, "\n};\n\n");
 
 	fprintf(ofile,
-"static struct cs {\n"
+"static const struct cs {\n"
 "	uint16_t	begin;\n"
 "	uint16_t	end;\n"
 "} critical_sections[] = {\n");
diff --git a/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y b/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y
index 702e2dbd11fb..81be6a261cc8 100644
--- a/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y
+++ b/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y
@@ -101,11 +101,12 @@ static void format_3_instr(int opcode, symbol_ref_t *src,
 			   expression_t *immed, symbol_ref_t *address);
 static void test_readable_symbol(symbol_t *symbol);
 static void test_writable_symbol(symbol_t *symbol);
-static void type_check(symbol_t *symbol, expression_t *expression, int and_op);
+static void type_check(symbol_ref_t *sym, expression_t *expression, int and_op);
 static void make_expression(expression_t *immed, int value);
 static void add_conditional(symbol_t *symbol);
 static void add_version(const char *verstring);
 static int  is_download_const(expression_t *immed);
+static int  is_location_address(symbol_t *symbol);
 void yyerror(const char *string);
 
 #define SRAM_SYMNAME "SRAM_BASE"
@@ -142,6 +143,8 @@ void yyerror(const char *string);
 
 %token <value> T_ADDRESS
 
+%token T_COUNT
+
 %token T_ACCESS_MODE
 
 %token T_MODES
@@ -192,10 +195,10 @@ void yyerror(const char *string);
 
 %token <value> T_OR
 
-/* 16 bit extensions */
-%token <value> T_OR16 T_AND16 T_XOR16 T_ADD16
-%token <value> T_ADC16 T_MVI16 T_TEST16 T_CMP16 T_CMPXCHG
-
+/* 16 bit extensions, not implemented
+ * %token <value> T_OR16 T_AND16 T_XOR16 T_ADD16
+ * %token <value> T_ADC16 T_MVI16 T_TEST16 T_CMP16 T_CMPXCHG
+ */
 %token T_RET
 
 %token T_NOP
@@ -214,7 +217,7 @@ void yyerror(const char *string);
 
 %type <expression> expression immediate immediate_or_a
 
-%type <value> export ret f1_opcode f2_opcode f4_opcode jmp_jc_jnc_call jz_jnz je_jne
+%type <value> export ret f1_opcode f2_opcode jmp_jc_jnc_call jz_jnz je_jne
 
 %type <value> mode_value mode_list macro_arglist
 
@@ -313,13 +316,13 @@ reg_definition:
 				stop("Register multiply defined", EX_DATAERR);
 				/* NOTREACHED */
 			}
-			cur_symbol = $1; 
+			cur_symbol = $1;
 			cur_symbol->type = cur_symtype;
 			initialize_symbol(cur_symbol);
 		}
 		reg_attribute_list
 	'}'
-		{                    
+		{
 			/*
 			 * Default to allowing everything in for registers
 			 * with no bit or mask definitions.
@@ -349,9 +352,10 @@ reg_attribute_list:
 |	reg_attribute_list reg_attribute
 ;
 
-reg_attribute:		
+reg_attribute:
 	reg_address
 |	size
+|	count
 |	access_mode
 |	modes
 |	field_defn
@@ -392,6 +396,13 @@ size:
 	}
 ;
 
+count:
+	T_COUNT T_NUMBER
+	{
+		cur_symbol->count += $2;
+	}
+;
+
 access_mode:
 	T_ACCESS_MODE T_MODE
 	{
@@ -641,14 +652,14 @@ expression:
 			       &($1.referenced_syms),
 			       &($3.referenced_syms));
 	}
-| 	expression T_EXPR_LSHIFT expression
+|	expression T_EXPR_LSHIFT expression
 	{
 		$$.value = $1.value << $3.value;
 		symlist_merge(&$$.referenced_syms,
 			       &$1.referenced_syms,
 			       &$3.referenced_syms);
 	}
-| 	expression T_EXPR_RSHIFT expression
+|	expression T_EXPR_RSHIFT expression
 	{
 		$$.value = $1.value >> $3.value;
 		symlist_merge(&$$.referenced_syms,
@@ -714,7 +725,7 @@ expression:
 ;
 
 constant:
-	T_CONST T_SYMBOL expression 
+	T_CONST T_SYMBOL expression
 	{
 		if ($2->type != UNINITIALIZED) {
 			stop("Re-definition of symbol as a constant",
@@ -800,6 +811,7 @@ scratch_ram:
 			cur_symtype = SRAMLOC;
 			cur_symbol->type = SRAMLOC;
 			initialize_symbol(cur_symbol);
+			cur_symbol->count += 1;
 		}
 		reg_address
 		{
@@ -831,6 +843,7 @@ scb:
 			initialize_symbol(cur_symbol);
 			/* 64 bytes of SCB space */
 			cur_symbol->info.rinfo->size = 64;
+			cur_symbol->count += 1;
 		}
 		reg_address
 		{
@@ -1311,14 +1324,18 @@ f2_opcode:
 |	T_ROR { $$ = AIC_OP_ROR; }
 ;
 
-f4_opcode:
-	T_OR16	{ $$ = AIC_OP_OR16; }
-|	T_AND16 { $$ = AIC_OP_AND16; }
-|	T_XOR16 { $$ = AIC_OP_XOR16; }
-|	T_ADD16 { $$ = AIC_OP_ADD16; }
-|	T_ADC16 { $$ = AIC_OP_ADC16; }
-|	T_MVI16 { $$ = AIC_OP_MVI16; }
-;
+/*
+ * 16bit opcodes, not used
+ *
+ *f4_opcode:
+ *	T_OR16	{ $$ = AIC_OP_OR16; }
+ *|	T_AND16 { $$ = AIC_OP_AND16; }
+ *|	T_XOR16 { $$ = AIC_OP_XOR16; }
+ *|	T_ADD16 { $$ = AIC_OP_ADD16; }
+ *|	T_ADC16 { $$ = AIC_OP_ADC16; }
+ *|	T_MVI16 { $$ = AIC_OP_MVI16; }
+ *;
+ */
 
 code:
 	f2_opcode destination ',' expression opt_source ret ';'
@@ -1357,6 +1374,7 @@ code:
 code:
 	T_OR reg_symbol ',' immediate jmp_jc_jnc_call address ';'
 	{
+		type_check(&$2, &$4, AIC_OP_OR);
 		format_3_instr($5, &$2, &$4, &$6);
 	}
 ;
@@ -1528,7 +1546,7 @@ initialize_symbol(symbol_t *symbol)
 		       sizeof(struct cond_info));
 		break;
 	case MACRO:
-		symbol->info.macroinfo = 
+		symbol->info.macroinfo =
 		    (struct macro_info *)malloc(sizeof(struct macro_info));
 		if (symbol->info.macroinfo == NULL) {
 			stop("Can't create macro info", EX_SOFTWARE);
@@ -1552,7 +1570,6 @@ add_macro_arg(const char *argtext, int argnum)
 	struct macro_arg *marg;
 	int i;
 	int retval;
-		
 
 	if (cur_symbol == NULL || cur_symbol->type != MACRO) {
 		stop("Invalid current symbol for adding macro arg",
@@ -1633,8 +1650,10 @@ format_1_instr(int opcode, symbol_ref_t *dest, expression_t *immed,
 	test_writable_symbol(dest->symbol);
 	test_readable_symbol(src->symbol);
 
-	/* Ensure that immediate makes sense for this destination */
-	type_check(dest->symbol, immed, opcode);
+	if (!is_location_address(dest->symbol)) {
+		/* Ensure that immediate makes sense for this destination */
+		type_check(dest, immed, opcode);
+	}
 
 	/* Allocate sequencer space for the instruction and fill it out */
 	instr = seq_alloc();
@@ -1766,9 +1785,6 @@ format_3_instr(int opcode, symbol_ref_t *src,
 	/* Test register permissions */
 	test_readable_symbol(src->symbol);
 
-	/* Ensure that immediate makes sense for this source */
-	type_check(src->symbol, immed, opcode);
-
 	/* Allocate sequencer space for the instruction and fill it out */
 	instr = seq_alloc();
 	f3_instr = &instr->format.format3;
@@ -1797,7 +1813,6 @@ format_3_instr(int opcode, symbol_ref_t *src,
 static void
 test_readable_symbol(symbol_t *symbol)
 {
-	
 	if ((symbol->info.rinfo->modes & (0x1 << src_mode)) == 0) {
 		snprintf(errbuf, sizeof(errbuf),
 			"Register %s unavailable in source reg mode %d",
@@ -1815,7 +1830,6 @@ test_readable_symbol(symbol_t *symbol)
 static void
 test_writable_symbol(symbol_t *symbol)
 {
-	
 	if ((symbol->info.rinfo->modes & (0x1 << dst_mode)) == 0) {
 		snprintf(errbuf, sizeof(errbuf),
 			"Register %s unavailable in destination reg mode %d",
@@ -1831,25 +1845,34 @@ test_writable_symbol(symbol_t *symbol)
 }
 
 static void
-type_check(symbol_t *symbol, expression_t *expression, int opcode)
+type_check(symbol_ref_t *sym, expression_t *expression, int opcode)
 {
+	symbol_t *symbol = sym->symbol;
 	symbol_node_t *node;
 	int and_op;
+	int8_t value, mask;
 
 	and_op = FALSE;
-	if (opcode == AIC_OP_AND || opcode == AIC_OP_JNZ || opcode == AIC_OP_JZ)
-		and_op = TRUE;
-
 	/*
 	 * Make sure that we aren't attempting to write something
 	 * that hasn't been defined.  If this is an and operation,
 	 * this is a mask, so "undefined" bits are okay.
 	 */
-	if (and_op == FALSE
-	 && (expression->value & ~symbol->info.rinfo->valid_bitmask) != 0) {
+	if (opcode == AIC_OP_AND || opcode == AIC_OP_JNZ ||
+	    opcode == AIC_OP_JZ  || opcode == AIC_OP_JNE ||
+	    opcode == AIC_OP_BMOV)
+		and_op = TRUE;
+
+	/*
+	 * Defaulting to 8 bit logic
+	 */
+	mask = (int8_t)~symbol->info.rinfo->valid_bitmask;
+	value = (int8_t)expression->value;
+
+	if (and_op == FALSE && (mask & value) != 0 ) {
 		snprintf(errbuf, sizeof(errbuf),
 			 "Invalid bit(s) 0x%x in immediate written to %s",
-			 expression->value & ~symbol->info.rinfo->valid_bitmask,
+			 (mask & value),
 			 symbol->name);
 		stop(errbuf, EX_DATAERR);
 		/* NOTREACHED */
@@ -1959,3 +1982,13 @@ is_download_const(expression_t *immed)
 
 	return (FALSE);
 }
+
+static int
+is_location_address(symbol_t *sym)
+{
+	if (sym->type == SCBLOC ||
+	    sym->type == SRAMLOC)
+		return (TRUE);
+	return (FALSE);
+}
+
diff --git a/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_scan.l b/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_scan.l
index 7c3983f868a9..2c7f02daf88d 100644
--- a/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_scan.l
+++ b/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_scan.l
@@ -162,6 +162,7 @@ register		{ return T_REGISTER; }
 const			{ yylval.value = FALSE; return T_CONST; }
 download		{ return T_DOWNLOAD; }
 address			{ return T_ADDRESS; }
+count			{ return T_COUNT; }
 access_mode		{ return T_ACCESS_MODE; }
 modes			{ return T_MODES; }
 RW|RO|WO		{
@@ -228,15 +229,15 @@ ret			{ return T_RET; }
 nop			{ return T_NOP; }
 
 	/* ARP2 16bit extensions */
-or16			{ return T_OR16; }
-and16			{ return T_AND16; }
-xor16			{ return T_XOR16; }
-add16			{ return T_ADD16; }
-adc16			{ return T_ADC16; }
-mvi16			{ return T_MVI16; }
-test16			{ return T_TEST16; }
-cmp16			{ return T_CMP16; }
-cmpxchg			{ return T_CMPXCHG; }
+	/* or16			{ return T_OR16; } */
+	/* and16			{ return T_AND16; }*/
+	/* xor16			{ return T_XOR16; }*/
+	/* add16			{ return T_ADD16; }*/
+	/* adc16			{ return T_ADC16; }*/
+	/* mvi16			{ return T_MVI16; }*/
+	/* test16			{ return T_TEST16; }*/
+	/* cmp16			{ return T_CMP16; }*/
+	/* cmpxchg			{ return T_CMPXCHG; }*/
 
 	/* Allowed Symbols */
 \<\<			{ return T_EXPR_LSHIFT; }
diff --git a/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.c b/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.c
index f1f448dff569..fcd357872b43 100644
--- a/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.c
+++ b/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.c
@@ -77,6 +77,7 @@ symbol_create(char *name)
 	if (new_symbol->name == NULL)
 		 stop("Unable to strdup symbol name", EX_SOFTWARE);
 	new_symbol->type = UNINITIALIZED;
+	new_symbol->count = 1;
 	return (new_symbol);
 }
 
@@ -198,6 +199,12 @@ symtable_get(char *name)
 		}
 	}
 	memcpy(&stored_ptr, data.data, sizeof(stored_ptr));
+	stored_ptr->count++;
+	data.data = &stored_ptr;
+	if (symtable->put(symtable, &key, &data, /*flags*/0) !=0) {
+		perror("Symtable put failed");
+		exit(EX_SOFTWARE);
+	}
 	return (stored_ptr);
 }
 
@@ -256,7 +263,7 @@ symlist_add(symlist_t *symlist, symbol_t *symbol, int how)
 		    && (curnode->symbol->info.finfo->value >
 			newnode->symbol->info.finfo->value))))
 		 || (!field && (curnode->symbol->info.rinfo->address >
-		               newnode->symbol->info.rinfo->address))) {
+				newnode->symbol->info.rinfo->address))) {
 			SLIST_INSERT_HEAD(symlist, newnode, links);
 			return;
 		}
@@ -271,7 +278,7 @@ symlist_add(symlist_t *symlist, symbol_t *symbol, int how)
 
 				cursymbol = SLIST_NEXT(curnode, links)->symbol;
 				if ((field
-		  		  && (cursymbol->type > symbol->type
+				  && (cursymbol->type > symbol->type
 				   || (cursymbol->type == symbol->type
 				    && (cursymbol->info.finfo->value >
 					symbol->info.finfo->value))))
@@ -351,7 +358,7 @@ aic_print_reg_dump_types(FILE *ofile)
 {
 	if (ofile == NULL)
 		return;
-		
+
 	fprintf(ofile,
 "typedef int (%sreg_print_t)(u_int, u_int *, u_int);\n"
 "typedef struct %sreg_parse_entry {\n"
@@ -370,7 +377,7 @@ aic_print_reg_dump_start(FILE *dfile, symbol_node_t *regnode)
 		return;
 
 	fprintf(dfile,
-"static %sreg_parse_entry_t %s_parse_table[] = {\n",
+"static const %sreg_parse_entry_t %s_parse_table[] = {\n",
 		prefix,
 		regnode->symbol->name);
 }
@@ -385,7 +392,7 @@ aic_print_reg_dump_end(FILE *ofile, FILE *dfile,
 	lower_name = strdup(regnode->symbol->name);
 	if (lower_name == NULL)
 		 stop("Unable to strdup symbol name", EX_SOFTWARE);
-	
+
 	for (letter = lower_name; *letter != '\0'; letter++)
 		*letter = tolower(*letter);
 
@@ -472,6 +479,7 @@ symtable_dump(FILE *ofile, FILE *dfile)
 	DBT		 key;
 	DBT		 data;
 	int		 flag;
+	int		 reg_count = 0, reg_used = 0;
 	u_int		 i;
 
 	if (symtable == NULL)
@@ -541,6 +549,9 @@ symtable_dump(FILE *ofile, FILE *dfile)
 			int		 num_entries;
 
 			num_entries = 0;
+			reg_count++;
+			if (curnode->symbol->count == 1)
+				break;
 			fields = &curnode->symbol->info.rinfo->fields;
 			SLIST_FOREACH(fieldnode, fields, links) {
 				if (num_entries == 0)
@@ -553,11 +564,14 @@ symtable_dump(FILE *ofile, FILE *dfile)
 			}
 			aic_print_reg_dump_end(ofile, dfile,
 					       curnode, num_entries);
+			reg_used++;
 		}
 		default:
 			break;
 		}
 	}
+	fprintf(stderr, "%s: %d of %d register definitions used\n", appname,
+		reg_used, reg_count);
 
 	/* Fold in the masks and bits */
 	while (SLIST_FIRST(&masks) != NULL) {
@@ -646,7 +660,6 @@ symtable_dump(FILE *ofile, FILE *dfile)
 		free(curnode);
 	}
 
-	
 	fprintf(ofile, "\n\n/* Downloaded Constant Definitions */\n");
 
 	for (i = 0; SLIST_FIRST(&download_constants) != NULL; i++) {
diff --git a/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.h b/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.h
index afc22e8b4903..05190c1a2fb7 100644
--- a/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.h
+++ b/trunk/drivers/scsi/aic7xxx/aicasm/aicasm_symbol.h
@@ -128,6 +128,7 @@ typedef struct expression_info {
 typedef struct symbol {
 	char	*name;
 	symtype	type;
+	int	count;
 	union	{
 		struct reg_info	  *rinfo;
 		struct field_info *finfo;
diff --git a/trunk/drivers/scsi/dpt_i2o.c b/trunk/drivers/scsi/dpt_i2o.c
index c9dd8392aab2..ac92ac143b46 100644
--- a/trunk/drivers/scsi/dpt_i2o.c
+++ b/trunk/drivers/scsi/dpt_i2o.c
@@ -153,7 +153,7 @@ static DEFINE_SPINLOCK(adpt_post_wait_lock);
 
 static u8 adpt_read_blink_led(adpt_hba* host)
 {
-	if(host->FwDebugBLEDflag_P != 0) {
+	if (host->FwDebugBLEDflag_P) {
 		if( readb(host->FwDebugBLEDflag_P) == 0xbc ){
 			return readb(host->FwDebugBLEDvalue_P);
 		}
diff --git a/trunk/drivers/scsi/eata.c b/trunk/drivers/scsi/eata.c
index 8be3d76656fa..a73a6bbb1b2b 100644
--- a/trunk/drivers/scsi/eata.c
+++ b/trunk/drivers/scsi/eata.c
@@ -2286,17 +2286,14 @@ static void flush_dev(struct scsi_device *dev, unsigned long cursec,
 	}
 }
 
-static irqreturn_t ihdlr(int irq, struct Scsi_Host *shost)
+static irqreturn_t ihdlr(struct Scsi_Host *shost)
 {
 	struct scsi_cmnd *SCpnt;
 	unsigned int i, k, c, status, tstatus, reg;
 	struct mssp *spp;
 	struct mscp *cpp;
 	struct hostdata *ha = (struct hostdata *)shost->hostdata;
-
-	if (shost->irq != irq)
-		panic("%s: ihdlr, irq %d, shost->irq %d.\n", ha->board_name, irq,
-		      shost->irq);
+	int irq = shost->irq;
 
 	/* Check if this board need to be serviced */
 	if (!(inb(shost->io_port + REG_AUX_STATUS) & IRQ_ASSERTED))
@@ -2535,7 +2532,7 @@ static irqreturn_t ihdlr(int irq, struct Scsi_Host *shost)
 	return IRQ_NONE;
 }
 
-static irqreturn_t do_interrupt_handler(int irq, void *shap)
+static irqreturn_t do_interrupt_handler(int dummy, void *shap)
 {
 	struct Scsi_Host *shost;
 	unsigned int j;
@@ -2548,7 +2545,7 @@ static irqreturn_t do_interrupt_handler(int irq, void *shap)
 	shost = sh[j];
 
 	spin_lock_irqsave(shost->host_lock, spin_flags);
-	ret = ihdlr(irq, shost);
+	ret = ihdlr(shost);
 	spin_unlock_irqrestore(shost->host_lock, spin_flags);
 	return ret;
 }
diff --git a/trunk/drivers/scsi/esp_scsi.c b/trunk/drivers/scsi/esp_scsi.c
index bfdee5968892..a0b6d414953d 100644
--- a/trunk/drivers/scsi/esp_scsi.c
+++ b/trunk/drivers/scsi/esp_scsi.c
@@ -978,7 +978,7 @@ static int esp_check_spur_intr(struct esp *esp)
 			 */
 			if (!esp->ops->dma_error(esp)) {
 				printk(KERN_ERR PFX "esp%d: Spurious irq, "
-				       "sreg=%x.\n",
+				       "sreg=%02x.\n",
 				       esp->host->unique_id, esp->sreg);
 				return -1;
 			}
@@ -1447,6 +1447,9 @@ static void esp_msgin_sdtr(struct esp *esp, struct esp_target_data *tp)
 	if (offset > 15)
 		goto do_reject;
 
+	if (esp->flags & ESP_FLAG_DISABLE_SYNC)
+		offset = 0;
+
 	if (offset) {
 		int rounded_up, one_clock;
 
@@ -1697,7 +1700,12 @@ static int esp_process_event(struct esp *esp)
 		else
 			ent->flags &= ~ESP_CMD_FLAG_WRITE;
 
-		dma_len = esp_dma_length_limit(esp, dma_addr, dma_len);
+		if (esp->ops->dma_length_limit)
+			dma_len = esp->ops->dma_length_limit(esp, dma_addr,
+							     dma_len);
+		else
+			dma_len = esp_dma_length_limit(esp, dma_addr, dma_len);
+
 		esp->data_dma_len = dma_len;
 
 		if (!dma_len) {
@@ -1761,7 +1769,6 @@ static int esp_process_event(struct esp *esp)
 		esp_advance_dma(esp, ent, cmd, bytes_sent);
 		esp_event(esp, ESP_EVENT_CHECK_PHASE);
 		goto again;
-		break;
 	}
 
 	case ESP_EVENT_STATUS: {
@@ -2235,7 +2242,7 @@ static void esp_bootup_reset(struct esp *esp)
 
 static void esp_set_clock_params(struct esp *esp)
 {
-	int fmhz;
+	int fhz;
 	u8 ccf;
 
 	/* This is getting messy but it has to be done correctly or else
@@ -2270,9 +2277,9 @@ static void esp_set_clock_params(struct esp *esp)
 	 *    This entails the smallest and largest sync period we could ever
 	 *    handle on this ESP.
 	 */
-	fmhz = esp->cfreq;
+	fhz = esp->cfreq;
 
-	ccf = ((fmhz / 1000000) + 4) / 5;
+	ccf = ((fhz / 1000000) + 4) / 5;
 	if (ccf == 1)
 		ccf = 2;
 
@@ -2281,16 +2288,16 @@ static void esp_set_clock_params(struct esp *esp)
 	 * been unable to find the clock-frequency PROM property.  All
 	 * other machines provide useful values it seems.
 	 */
-	if (fmhz <= 5000000 || ccf < 1 || ccf > 8) {
-		fmhz = 20000000;
+	if (fhz <= 5000000 || ccf < 1 || ccf > 8) {
+		fhz = 20000000;
 		ccf = 4;
 	}
 
 	esp->cfact = (ccf == 8 ? 0 : ccf);
-	esp->cfreq = fmhz;
-	esp->ccycle = ESP_MHZ_TO_CYCLE(fmhz);
+	esp->cfreq = fhz;
+	esp->ccycle = ESP_HZ_TO_CYCLE(fhz);
 	esp->ctick = ESP_TICK(ccf, esp->ccycle);
-	esp->neg_defp = ESP_NEG_DEFP(fmhz, ccf);
+	esp->neg_defp = ESP_NEG_DEFP(fhz, ccf);
 	esp->sync_defp = SYNC_DEFP_SLOW;
 }
 
@@ -2382,6 +2389,12 @@ static int esp_slave_configure(struct scsi_device *dev)
 	struct esp_target_data *tp = &esp->target[dev->id];
 	int goal_tags, queue_depth;
 
+	if (esp->flags & ESP_FLAG_DISABLE_SYNC) {
+		/* Bypass async domain validation */
+		dev->ppr  = 0;
+		dev->sdtr = 0;
+	}
+
 	goal_tags = 0;
 
 	if (dev->tagged_supported) {
diff --git a/trunk/drivers/scsi/esp_scsi.h b/trunk/drivers/scsi/esp_scsi.h
index d5576d54ce76..bb43a1388188 100644
--- a/trunk/drivers/scsi/esp_scsi.h
+++ b/trunk/drivers/scsi/esp_scsi.h
@@ -224,7 +224,7 @@
 #define ESP_TIMEO_CONST       8192
 #define ESP_NEG_DEFP(mhz, cfact) \
         ((ESP_BUS_TIMEOUT * ((mhz) / 1000)) / (8192 * (cfact)))
-#define ESP_MHZ_TO_CYCLE(mhertz)  ((1000000000) / ((mhertz) / 1000))
+#define ESP_HZ_TO_CYCLE(hertz)  ((1000000000) / ((hertz) / 1000))
 #define ESP_TICK(ccf, cycle)  ((7682 * (ccf) * (cycle) / 1000))
 
 /* For slow to medium speed input clock rates we shoot for 5mb/s, but for high
@@ -240,9 +240,9 @@ struct esp_cmd_priv {
 		int		num_sg;
 	} u;
 
-	unsigned int		cur_residue;
+	int			cur_residue;
 	struct scatterlist	*cur_sg;
-	unsigned int		tot_residue;
+	int			tot_residue;
 };
 #define ESP_CMD_PRIV(CMD)	((struct esp_cmd_priv *)(&(CMD)->SCp))
 
@@ -368,6 +368,12 @@ struct esp_driver_ops {
 	 */
 	int (*irq_pending)(struct esp *esp);
 
+	/* Return the maximum allowable size of a DMA transfer for a
+	 * given buffer.
+	 */
+	u32 (*dma_length_limit)(struct esp *esp, u32 dma_addr,
+				u32 dma_len);
+
 	/* Reset the DMA engine entirely.  On return, ESP interrupts
 	 * should be enabled.  Often the interrupt enabling is
 	 * controlled in the DMA engine.
@@ -471,6 +477,7 @@ struct esp {
 #define ESP_FLAG_DOING_SLOWCMD	0x00000004
 #define ESP_FLAG_WIDE_CAPABLE	0x00000008
 #define ESP_FLAG_QUICKIRQ_CHECK	0x00000010
+#define ESP_FLAG_DISABLE_SYNC	0x00000020
 
 	u8			select_state;
 #define ESP_SELECT_NONE		0x00 /* Not selecting */
diff --git a/trunk/drivers/scsi/fdomain.c b/trunk/drivers/scsi/fdomain.c
index 2cd6b4959eb2..c33bcb284df7 100644
--- a/trunk/drivers/scsi/fdomain.c
+++ b/trunk/drivers/scsi/fdomain.c
@@ -1443,7 +1443,7 @@ static int fdomain_16x0_queue(struct scsi_cmnd *SCpnt,
 	   current_SC->SCp.this_residual    = current_SC->SCp.buffer->length;
 	   current_SC->SCp.buffers_residual = scsi_sg_count(current_SC) - 1;
    } else {
-	   current_SC->SCp.ptr              = 0;
+	   current_SC->SCp.ptr              = NULL;
 	   current_SC->SCp.this_residual    = 0;
 	   current_SC->SCp.buffer           = NULL;
 	   current_SC->SCp.buffers_residual = 0;
diff --git a/trunk/drivers/scsi/hosts.c b/trunk/drivers/scsi/hosts.c
index c264a8c5f01e..3690360d7a79 100644
--- a/trunk/drivers/scsi/hosts.c
+++ b/trunk/drivers/scsi/hosts.c
@@ -199,9 +199,13 @@ int scsi_add_host(struct Scsi_Host *shost, struct device *dev)
 	if (!shost->can_queue) {
 		printk(KERN_ERR "%s: can_queue = 0 no longer supported\n",
 				sht->name);
-		goto out;
+		goto fail;
 	}
 
+	error = scsi_setup_command_freelist(shost);
+	if (error)
+		goto fail;
+
 	if (!shost->shost_gendev.parent)
 		shost->shost_gendev.parent = dev ? dev : &platform_bus;
 
@@ -255,6 +259,8 @@ int scsi_add_host(struct Scsi_Host *shost, struct device *dev)
  out_del_gendev:
 	device_del(&shost->shost_gendev);
  out:
+	scsi_destroy_command_freelist(shost);
+ fail:
 	return error;
 }
 EXPORT_SYMBOL(scsi_add_host);
@@ -284,6 +290,11 @@ static void scsi_host_dev_release(struct device *dev)
 	kfree(shost);
 }
 
+struct device_type scsi_host_type = {
+	.name =		"scsi_host",
+	.release =	scsi_host_dev_release,
+};
+
 /**
  * scsi_host_alloc - register a scsi host adapter instance.
  * @sht:	pointer to scsi host template
@@ -376,33 +387,31 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	else
 		shost->dma_boundary = 0xffffffff;
 
-	rval = scsi_setup_command_freelist(shost);
-	if (rval)
-		goto fail_kfree;
-
 	device_initialize(&shost->shost_gendev);
 	snprintf(shost->shost_gendev.bus_id, BUS_ID_SIZE, "host%d",
 		shost->host_no);
-	shost->shost_gendev.release = scsi_host_dev_release;
+#ifndef CONFIG_SYSFS_DEPRECATED
+	shost->shost_gendev.bus = &scsi_bus_type;
+#endif
+	shost->shost_gendev.type = &scsi_host_type;
 
 	device_initialize(&shost->shost_dev);
 	shost->shost_dev.parent = &shost->shost_gendev;
 	shost->shost_dev.class = &shost_class;
 	snprintf(shost->shost_dev.bus_id, BUS_ID_SIZE, "host%d",
 		 shost->host_no);
+	shost->shost_dev.groups = scsi_sysfs_shost_attr_groups;
 
 	shost->ehandler = kthread_run(scsi_error_handler, shost,
 			"scsi_eh_%d", shost->host_no);
 	if (IS_ERR(shost->ehandler)) {
 		rval = PTR_ERR(shost->ehandler);
-		goto fail_destroy_freelist;
+		goto fail_kfree;
 	}
 
 	scsi_proc_hostdir_add(shost->hostt);
 	return shost;
 
- fail_destroy_freelist:
-	scsi_destroy_command_freelist(shost);
  fail_kfree:
 	kfree(shost);
 	return NULL;
@@ -496,7 +505,7 @@ void scsi_exit_hosts(void)
 
 int scsi_is_host_device(const struct device *dev)
 {
-	return dev->release == scsi_host_dev_release;
+	return dev->type == &scsi_host_type;
 }
 EXPORT_SYMBOL(scsi_is_host_device);
 
diff --git a/trunk/drivers/scsi/ide-scsi.c b/trunk/drivers/scsi/ide-scsi.c
index 3638fa808ded..44d8d5163a1a 100644
--- a/trunk/drivers/scsi/ide-scsi.c
+++ b/trunk/drivers/scsi/ide-scsi.c
@@ -134,6 +134,7 @@ static inline idescsi_scsi_t *drive_to_idescsi(ide_drive_t *ide_drive)
 static void idescsi_input_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
 		unsigned int bcount)
 {
+	ide_hwif_t *hwif = drive->hwif;
 	int count;
 	char *buf;
 
@@ -145,14 +146,12 @@ static void idescsi_input_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
 			local_irq_save(flags);
 			buf = kmap_atomic(sg_page(pc->sg), KM_IRQ0) +
 					pc->sg->offset;
-			drive->hwif->atapi_input_bytes(drive,
-						buf + pc->b_count, count);
+			hwif->input_data(drive, NULL, buf + pc->b_count, count);
 			kunmap_atomic(buf - pc->sg->offset, KM_IRQ0);
 			local_irq_restore(flags);
 		} else {
 			buf = sg_virt(pc->sg);
-			drive->hwif->atapi_input_bytes(drive,
-						buf + pc->b_count, count);
+			hwif->input_data(drive, NULL, buf + pc->b_count, count);
 		}
 		bcount -= count; pc->b_count += count;
 		if (pc->b_count == pc->sg->length) {
@@ -165,13 +164,14 @@ static void idescsi_input_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
 
 	if (bcount) {
 		printk (KERN_ERR "ide-scsi: scatter gather table too small, discarding data\n");
-		ide_atapi_discard_data(drive, bcount);
+		ide_pad_transfer(drive, 0, bcount);
 	}
 }
 
 static void idescsi_output_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
 		unsigned int bcount)
 {
+	ide_hwif_t *hwif = drive->hwif;
 	int count;
 	char *buf;
 
@@ -183,14 +183,12 @@ static void idescsi_output_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
 			local_irq_save(flags);
 			buf = kmap_atomic(sg_page(pc->sg), KM_IRQ0) +
 						pc->sg->offset;
-			drive->hwif->atapi_output_bytes(drive,
-						buf + pc->b_count, count);
+			hwif->output_data(drive, NULL, buf + pc->b_count, count);
 			kunmap_atomic(buf - pc->sg->offset, KM_IRQ0);
 			local_irq_restore(flags);
 		} else {
 			buf = sg_virt(pc->sg);
-			drive->hwif->atapi_output_bytes(drive,
-						buf + pc->b_count, count);
+			hwif->output_data(drive, NULL, buf + pc->b_count, count);
 		}
 		bcount -= count; pc->b_count += count;
 		if (pc->b_count == pc->sg->length) {
@@ -203,7 +201,7 @@ static void idescsi_output_buffers(ide_drive_t *drive, struct ide_atapi_pc *pc,
 
 	if (bcount) {
 		printk (KERN_ERR "ide-scsi: scatter gather table too small, padding with zeros\n");
-		ide_atapi_write_zeros(drive, bcount);
+		ide_pad_transfer(drive, 1, bcount);
 	}
 }
 
@@ -258,8 +256,8 @@ idescsi_atapi_error(ide_drive_t *drive, struct request *rq, u8 stat, u8 err)
 
 	if (ide_read_status(drive) & (BUSY_STAT | DRQ_STAT))
 		/* force an abort */
-		hwif->OUTB(WIN_IDLEIMMEDIATE,
-			   hwif->io_ports[IDE_COMMAND_OFFSET]);
+		hwif->OUTBSYNC(drive, WIN_IDLEIMMEDIATE,
+			       hwif->io_ports.command_addr);
 
 	rq->errors++;
 
@@ -410,9 +408,9 @@ static ide_startstop_t idescsi_pc_intr (ide_drive_t *drive)
 		idescsi_end_request (drive, 1, 0);
 		return ide_stopped;
 	}
-	bcount = (hwif->INB(hwif->io_ports[IDE_BCOUNTH_OFFSET]) << 8) |
-		  hwif->INB(hwif->io_ports[IDE_BCOUNTL_OFFSET]);
-	ireason = hwif->INB(hwif->io_ports[IDE_IREASON_OFFSET]);
+	bcount = (hwif->INB(hwif->io_ports.lbah_addr) << 8) |
+		  hwif->INB(hwif->io_ports.lbam_addr);
+	ireason = hwif->INB(hwif->io_ports.nsect_addr);
 
 	if (ireason & CD) {
 		printk(KERN_ERR "ide-scsi: CoD != 0 in idescsi_pc_intr\n");
@@ -432,14 +430,15 @@ static ide_startstop_t idescsi_pc_intr (ide_drive_t *drive)
 						idescsi_input_buffers(drive, pc,
 									temp);
 					else
-						drive->hwif->atapi_input_bytes(drive, pc->cur_pos, temp);
+						hwif->input_data(drive, NULL,
+							pc->cur_pos, temp);
 					printk(KERN_ERR "ide-scsi: transferred"
 							" %d of %d bytes\n",
 							temp, bcount);
 				}
 				pc->xferred += temp;
 				pc->cur_pos += temp;
-				ide_atapi_discard_data(drive, bcount - temp);
+				ide_pad_transfer(drive, 0, bcount - temp);
 				ide_set_handler(drive, &idescsi_pc_intr, get_timeout(pc), idescsi_expiry);
 				return ide_started;
 			}
@@ -453,15 +452,13 @@ static ide_startstop_t idescsi_pc_intr (ide_drive_t *drive)
 		if (pc->sg)
 			idescsi_input_buffers(drive, pc, bcount);
 		else
-			hwif->atapi_input_bytes(drive, pc->cur_pos,
-						bcount);
+			hwif->input_data(drive, NULL, pc->cur_pos, bcount);
 	} else {
 		pc->flags |= PC_FLAG_WRITING;
 		if (pc->sg)
 			idescsi_output_buffers(drive, pc, bcount);
 		else
-			hwif->atapi_output_bytes(drive, pc->cur_pos,
-						 bcount);
+			hwif->output_data(drive, NULL, pc->cur_pos, bcount);
 	}
 	/* Update the current position */
 	pc->xferred += bcount;
@@ -485,7 +482,7 @@ static ide_startstop_t idescsi_transfer_pc(ide_drive_t *drive)
 			"initiated yet DRQ isn't asserted\n");
 		return startstop;
 	}
-	ireason = hwif->INB(hwif->io_ports[IDE_IREASON_OFFSET]);
+	ireason = hwif->INB(hwif->io_ports.nsect_addr);
 	if ((ireason & CD) == 0 || (ireason & IO)) {
 		printk(KERN_ERR "ide-scsi: (IO,CoD) != (0,1) while "
 				"issuing a packet command\n");
@@ -494,8 +491,10 @@ static ide_startstop_t idescsi_transfer_pc(ide_drive_t *drive)
 	BUG_ON(HWGROUP(drive)->handler != NULL);
 	/* Set the interrupt routine */
 	ide_set_handler(drive, &idescsi_pc_intr, get_timeout(pc), idescsi_expiry);
+
 	/* Send the actual packet */
-	drive->hwif->atapi_output_bytes(drive, scsi->pc->c, 12);
+	hwif->output_data(drive, NULL, scsi->pc->c, 12);
+
 	if (pc->flags & PC_FLAG_DMA_OK) {
 		pc->flags |= PC_FLAG_DMA_IN_PROGRESS;
 		hwif->dma_ops->dma_start(drive);
@@ -575,7 +574,7 @@ static ide_startstop_t idescsi_issue_pc(ide_drive_t *drive,
 		return ide_started;
 	} else {
 		/* Issue the packet command */
-		hwif->OUTB(WIN_PACKETCMD, hwif->io_ports[IDE_COMMAND_OFFSET]);
+		ide_execute_pkt_cmd(drive);
 		return idescsi_transfer_pc(drive);
 	}
 }
diff --git a/trunk/drivers/scsi/jazz_esp.c b/trunk/drivers/scsi/jazz_esp.c
index 5d231015bb20..b2d481dd3750 100644
--- a/trunk/drivers/scsi/jazz_esp.c
+++ b/trunk/drivers/scsi/jazz_esp.c
@@ -217,11 +217,15 @@ static int __devexit esp_jazz_remove(struct platform_device *dev)
 	return 0;
 }
 
+/* work with hotplug and coldplug */
+MODULE_ALIAS("platform:jazz_esp");
+
 static struct platform_driver esp_jazz_driver = {
 	.probe		= esp_jazz_probe,
 	.remove		= __devexit_p(esp_jazz_remove),
 	.driver	= {
 		.name	= "jazz_esp",
+		.owner	= THIS_MODULE,
 	},
 };
 
diff --git a/trunk/drivers/scsi/lpfc/lpfc_attr.c b/trunk/drivers/scsi/lpfc/lpfc_attr.c
index a9fbb3f88659..960baaf11fb1 100644
--- a/trunk/drivers/scsi/lpfc/lpfc_attr.c
+++ b/trunk/drivers/scsi/lpfc/lpfc_attr.c
@@ -182,8 +182,8 @@ lpfc_option_rom_version_show(struct device *dev, struct device_attribute *attr,
 	return snprintf(buf, PAGE_SIZE, "%s\n", phba->OptionROMVersion);
 }
 static ssize_t
-lpfc_state_show(struct device *dev, struct device_attribute *attr,
-		char *buf)
+lpfc_link_state_show(struct device *dev, struct device_attribute *attr,
+		     char *buf)
 {
 	struct Scsi_Host  *shost = class_to_shost(dev);
 	struct lpfc_vport *vport = (struct lpfc_vport *) shost->hostdata;
@@ -936,7 +936,7 @@ static DEVICE_ATTR(programtype, S_IRUGO, lpfc_programtype_show, NULL);
 static DEVICE_ATTR(portnum, S_IRUGO, lpfc_vportnum_show, NULL);
 static DEVICE_ATTR(fwrev, S_IRUGO, lpfc_fwrev_show, NULL);
 static DEVICE_ATTR(hdw, S_IRUGO, lpfc_hdw_show, NULL);
-static DEVICE_ATTR(state, S_IRUGO, lpfc_state_show, NULL);
+static DEVICE_ATTR(link_state, S_IRUGO, lpfc_link_state_show, NULL);
 static DEVICE_ATTR(option_rom_version, S_IRUGO,
 		   lpfc_option_rom_version_show, NULL);
 static DEVICE_ATTR(num_discovered_ports, S_IRUGO,
@@ -1666,7 +1666,7 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_fwrev,
 	&dev_attr_hdw,
 	&dev_attr_option_rom_version,
-	&dev_attr_state,
+	&dev_attr_link_state,
 	&dev_attr_num_discovered_ports,
 	&dev_attr_lpfc_drvr_version,
 	&dev_attr_lpfc_temp_sensor,
@@ -1714,7 +1714,7 @@ struct device_attribute *lpfc_hba_attrs[] = {
 
 struct device_attribute *lpfc_vport_attrs[] = {
 	&dev_attr_info,
-	&dev_attr_state,
+	&dev_attr_link_state,
 	&dev_attr_num_discovered_ports,
 	&dev_attr_lpfc_drvr_version,
 	&dev_attr_lpfc_log_verbose,
diff --git a/trunk/drivers/scsi/mac_esp.c b/trunk/drivers/scsi/mac_esp.c
new file mode 100644
index 000000000000..cd37bd69a115
--- /dev/null
+++ b/trunk/drivers/scsi/mac_esp.c
@@ -0,0 +1,657 @@
+/* mac_esp.c: ESP front-end for Macintosh Quadra systems.
+ *
+ * Adapted from jazz_esp.c and the old mac_esp.c.
+ *
+ * The pseudo DMA algorithm is based on the one used in NetBSD.
+ * See sys/arch/mac68k/obio/esp.c for some background information.
+ *
+ * Copyright (C) 2007-2008 Finn Thain
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/nubus.h>
+
+#include <asm/irq.h>
+#include <asm/dma.h>
+
+#include <asm/macints.h>
+#include <asm/macintosh.h>
+
+#include <scsi/scsi_host.h>
+
+#include "esp_scsi.h"
+
+#define DRV_MODULE_NAME     "mac_esp"
+#define PFX                 DRV_MODULE_NAME ": "
+#define DRV_VERSION         "1.000"
+#define DRV_MODULE_RELDATE  "Sept 15, 2007"
+
+#define MAC_ESP_IO_BASE          0x50F00000
+#define MAC_ESP_REGS_QUADRA      (MAC_ESP_IO_BASE + 0x10000)
+#define MAC_ESP_REGS_QUADRA2     (MAC_ESP_IO_BASE + 0xF000)
+#define MAC_ESP_REGS_QUADRA3     (MAC_ESP_IO_BASE + 0x18000)
+#define MAC_ESP_REGS_SPACING     0x402
+#define MAC_ESP_PDMA_REG         0xF9800024
+#define MAC_ESP_PDMA_REG_SPACING 0x4
+#define MAC_ESP_PDMA_IO_OFFSET   0x100
+
+#define esp_read8(REG)		mac_esp_read8(esp, REG)
+#define esp_write8(VAL, REG)	mac_esp_write8(esp, VAL, REG)
+
+struct mac_esp_priv {
+	struct esp *esp;
+	void __iomem *pdma_regs;
+	void __iomem *pdma_io;
+	int error;
+};
+static struct platform_device *internal_esp, *external_esp;
+
+#define MAC_ESP_GET_PRIV(esp) ((struct mac_esp_priv *) \
+			       platform_get_drvdata((struct platform_device *) \
+						    (esp->dev)))
+
+static inline void mac_esp_write8(struct esp *esp, u8 val, unsigned long reg)
+{
+	nubus_writeb(val, esp->regs + reg * 16);
+}
+
+static inline u8 mac_esp_read8(struct esp *esp, unsigned long reg)
+{
+	return nubus_readb(esp->regs + reg * 16);
+}
+
+/* For pseudo DMA and PIO we need the virtual address
+ * so this address mapping is the identity mapping.
+ */
+
+static dma_addr_t mac_esp_map_single(struct esp *esp, void *buf,
+				     size_t sz, int dir)
+{
+	return (dma_addr_t)buf;
+}
+
+static int mac_esp_map_sg(struct esp *esp, struct scatterlist *sg,
+			  int num_sg, int dir)
+{
+	int i;
+
+	for (i = 0; i < num_sg; i++)
+		sg[i].dma_address = (u32)sg_virt(&sg[i]);
+	return num_sg;
+}
+
+static void mac_esp_unmap_single(struct esp *esp, dma_addr_t addr,
+				 size_t sz, int dir)
+{
+	/* Nothing to do. */
+}
+
+static void mac_esp_unmap_sg(struct esp *esp, struct scatterlist *sg,
+			     int num_sg, int dir)
+{
+	/* Nothing to do. */
+}
+
+static void mac_esp_reset_dma(struct esp *esp)
+{
+	/* Nothing to do. */
+}
+
+static void mac_esp_dma_drain(struct esp *esp)
+{
+	/* Nothing to do. */
+}
+
+static void mac_esp_dma_invalidate(struct esp *esp)
+{
+	/* Nothing to do. */
+}
+
+static int mac_esp_dma_error(struct esp *esp)
+{
+	return MAC_ESP_GET_PRIV(esp)->error;
+}
+
+static inline int mac_esp_wait_for_empty_fifo(struct esp *esp)
+{
+	struct mac_esp_priv *mep = MAC_ESP_GET_PRIV(esp);
+	int i = 500000;
+
+	do {
+		if (!(esp_read8(ESP_FFLAGS) & ESP_FF_FBYTES))
+			return 0;
+
+		if (esp_read8(ESP_STATUS) & ESP_STAT_INTR)
+			return 1;
+
+		udelay(2);
+	} while (--i);
+
+	printk(KERN_ERR PFX "FIFO is not empty (sreg %02x)\n",
+	       esp_read8(ESP_STATUS));
+	mep->error = 1;
+	return 1;
+}
+
+static inline int mac_esp_wait_for_dreq(struct esp *esp)
+{
+	struct mac_esp_priv *mep = MAC_ESP_GET_PRIV(esp);
+	int i = 500000;
+
+	do {
+		if (mep->pdma_regs == NULL) {
+			if (mac_irq_pending(IRQ_MAC_SCSIDRQ))
+				return 0;
+		} else {
+			if (nubus_readl(mep->pdma_regs) & 0x200)
+				return 0;
+		}
+
+		if (esp_read8(ESP_STATUS) & ESP_STAT_INTR)
+			return 1;
+
+		udelay(2);
+	} while (--i);
+
+	printk(KERN_ERR PFX "PDMA timeout (sreg %02x)\n",
+	       esp_read8(ESP_STATUS));
+	mep->error = 1;
+	return 1;
+}
+
+#define MAC_ESP_PDMA_LOOP(operands) \
+	asm volatile ( \
+	     "       tstw %2                   \n" \
+	     "       jbeq 20f                  \n" \
+	     "1:     movew " operands "        \n" \
+	     "2:     movew " operands "        \n" \
+	     "3:     movew " operands "        \n" \
+	     "4:     movew " operands "        \n" \
+	     "5:     movew " operands "        \n" \
+	     "6:     movew " operands "        \n" \
+	     "7:     movew " operands "        \n" \
+	     "8:     movew " operands "        \n" \
+	     "9:     movew " operands "        \n" \
+	     "10:    movew " operands "        \n" \
+	     "11:    movew " operands "        \n" \
+	     "12:    movew " operands "        \n" \
+	     "13:    movew " operands "        \n" \
+	     "14:    movew " operands "        \n" \
+	     "15:    movew " operands "        \n" \
+	     "16:    movew " operands "        \n" \
+	     "       subqw #1,%2               \n" \
+	     "       jbne 1b                   \n" \
+	     "20:    tstw %3                   \n" \
+	     "       jbeq 30f                  \n" \
+	     "21:    movew " operands "        \n" \
+	     "       subqw #1,%3               \n" \
+	     "       jbne 21b                  \n" \
+	     "30:    tstw %4                   \n" \
+	     "       jbeq 40f                  \n" \
+	     "31:    moveb " operands "        \n" \
+	     "32:    nop                       \n" \
+	     "40:                              \n" \
+	     "                                 \n" \
+	     "       .section __ex_table,\"a\" \n" \
+	     "       .align  4                 \n" \
+	     "       .long   1b,40b            \n" \
+	     "       .long   2b,40b            \n" \
+	     "       .long   3b,40b            \n" \
+	     "       .long   4b,40b            \n" \
+	     "       .long   5b,40b            \n" \
+	     "       .long   6b,40b            \n" \
+	     "       .long   7b,40b            \n" \
+	     "       .long   8b,40b            \n" \
+	     "       .long   9b,40b            \n" \
+	     "       .long  10b,40b            \n" \
+	     "       .long  11b,40b            \n" \
+	     "       .long  12b,40b            \n" \
+	     "       .long  13b,40b            \n" \
+	     "       .long  14b,40b            \n" \
+	     "       .long  15b,40b            \n" \
+	     "       .long  16b,40b            \n" \
+	     "       .long  21b,40b            \n" \
+	     "       .long  31b,40b            \n" \
+	     "       .long  32b,40b            \n" \
+	     "       .previous                 \n" \
+	     : "+a" (addr) \
+	     : "a" (mep->pdma_io), "r" (count32), "r" (count2), "g" (esp_count))
+
+static void mac_esp_send_pdma_cmd(struct esp *esp, u32 addr, u32 esp_count,
+				  u32 dma_count, int write, u8 cmd)
+{
+	struct mac_esp_priv *mep = MAC_ESP_GET_PRIV(esp);
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	mep->error = 0;
+
+	if (!write)
+		scsi_esp_cmd(esp, ESP_CMD_FLUSH);
+
+	esp_write8((esp_count >> 0) & 0xFF, ESP_TCLOW);
+	esp_write8((esp_count >> 8) & 0xFF, ESP_TCMED);
+
+	scsi_esp_cmd(esp, cmd);
+
+	do {
+		unsigned int count32 = esp_count >> 5;
+		unsigned int count2 = (esp_count & 0x1F) >> 1;
+		unsigned int start_addr = addr;
+
+		if (mac_esp_wait_for_dreq(esp))
+			break;
+
+		if (write) {
+			MAC_ESP_PDMA_LOOP("%1@,%0@+");
+
+			esp_count -= addr - start_addr;
+		} else {
+			unsigned int n;
+
+			MAC_ESP_PDMA_LOOP("%0@+,%1@");
+
+			if (mac_esp_wait_for_empty_fifo(esp))
+				break;
+
+			n = (esp_read8(ESP_TCMED) << 8) + esp_read8(ESP_TCLOW);
+			addr = start_addr + esp_count - n;
+			esp_count = n;
+		}
+	} while (esp_count);
+
+	local_irq_restore(flags);
+}
+
+/*
+ * Programmed IO routines follow.
+ */
+
+static inline int mac_esp_wait_for_fifo(struct esp *esp)
+{
+	int i = 500000;
+
+	do {
+		if (esp_read8(ESP_FFLAGS) & ESP_FF_FBYTES)
+			return 0;
+
+		udelay(2);
+	} while (--i);
+
+	printk(KERN_ERR PFX "FIFO is empty (sreg %02x)\n",
+	       esp_read8(ESP_STATUS));
+	return 1;
+}
+
+static inline int mac_esp_wait_for_intr(struct esp *esp)
+{
+	int i = 500000;
+
+	do {
+		esp->sreg = esp_read8(ESP_STATUS);
+		if (esp->sreg & ESP_STAT_INTR)
+			return 0;
+
+		udelay(2);
+	} while (--i);
+
+	printk(KERN_ERR PFX "IRQ timeout (sreg %02x)\n", esp->sreg);
+	return 1;
+}
+
+#define MAC_ESP_PIO_LOOP(operands, reg1) \
+	asm volatile ( \
+	     "1:     moveb " operands " \n" \
+	     "       subqw #1,%1        \n" \
+	     "       jbne 1b            \n" \
+	     : "+a" (addr), "+r" (reg1) \
+	     : "a" (fifo))
+
+#define MAC_ESP_PIO_FILL(operands, reg1) \
+	asm volatile ( \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       moveb " operands " \n" \
+	     "       subqw #8,%1        \n" \
+	     "       subqw #8,%1        \n" \
+	     : "+a" (addr), "+r" (reg1) \
+	     : "a" (fifo))
+
+#define MAC_ESP_FIFO_SIZE 16
+
+static void mac_esp_send_pio_cmd(struct esp *esp, u32 addr, u32 esp_count,
+				 u32 dma_count, int write, u8 cmd)
+{
+	unsigned long flags;
+	struct mac_esp_priv *mep = MAC_ESP_GET_PRIV(esp);
+	u8 *fifo = esp->regs + ESP_FDATA * 16;
+
+	local_irq_save(flags);
+
+	cmd &= ~ESP_CMD_DMA;
+	mep->error = 0;
+
+	if (write) {
+		scsi_esp_cmd(esp, cmd);
+
+		if (!mac_esp_wait_for_intr(esp)) {
+			if (mac_esp_wait_for_fifo(esp))
+				esp_count = 0;
+		} else {
+			esp_count = 0;
+		}
+	} else {
+		scsi_esp_cmd(esp, ESP_CMD_FLUSH);
+
+		if (esp_count >= MAC_ESP_FIFO_SIZE)
+			MAC_ESP_PIO_FILL("%0@+,%2@", esp_count);
+		else
+			MAC_ESP_PIO_LOOP("%0@+,%2@", esp_count);
+
+		scsi_esp_cmd(esp, cmd);
+	}
+
+	while (esp_count) {
+		unsigned int n;
+
+		if (mac_esp_wait_for_intr(esp)) {
+			mep->error = 1;
+			break;
+		}
+
+		if (esp->sreg & ESP_STAT_SPAM) {
+			printk(KERN_ERR PFX "gross error\n");
+			mep->error = 1;
+			break;
+		}
+
+		n = esp_read8(ESP_FFLAGS) & ESP_FF_FBYTES;
+
+		if (write) {
+			if (n > esp_count)
+				n = esp_count;
+			esp_count -= n;
+
+			MAC_ESP_PIO_LOOP("%2@,%0@+", n);
+
+			if ((esp->sreg & ESP_STAT_PMASK) == ESP_STATP)
+				break;
+
+			if (esp_count) {
+				esp->ireg = esp_read8(ESP_INTRPT);
+				if (esp->ireg & ESP_INTR_DC)
+					break;
+
+				scsi_esp_cmd(esp, ESP_CMD_TI);
+			}
+		} else {
+			esp->ireg = esp_read8(ESP_INTRPT);
+			if (esp->ireg & ESP_INTR_DC)
+				break;
+
+			n = MAC_ESP_FIFO_SIZE - n;
+			if (n > esp_count)
+				n = esp_count;
+
+			if (n == MAC_ESP_FIFO_SIZE) {
+				MAC_ESP_PIO_FILL("%0@+,%2@", esp_count);
+			} else {
+				esp_count -= n;
+				MAC_ESP_PIO_LOOP("%0@+,%2@", n);
+			}
+
+			scsi_esp_cmd(esp, ESP_CMD_TI);
+		}
+	}
+
+	local_irq_restore(flags);
+}
+
+static int mac_esp_irq_pending(struct esp *esp)
+{
+	if (esp_read8(ESP_STATUS) & ESP_STAT_INTR)
+		return 1;
+	return 0;
+}
+
+static u32 mac_esp_dma_length_limit(struct esp *esp, u32 dma_addr, u32 dma_len)
+{
+	return dma_len > 0xFFFF ? 0xFFFF : dma_len;
+}
+
+static struct esp_driver_ops mac_esp_ops = {
+	.esp_write8       = mac_esp_write8,
+	.esp_read8        = mac_esp_read8,
+	.map_single       = mac_esp_map_single,
+	.map_sg           = mac_esp_map_sg,
+	.unmap_single     = mac_esp_unmap_single,
+	.unmap_sg         = mac_esp_unmap_sg,
+	.irq_pending      = mac_esp_irq_pending,
+	.dma_length_limit = mac_esp_dma_length_limit,
+	.reset_dma        = mac_esp_reset_dma,
+	.dma_drain        = mac_esp_dma_drain,
+	.dma_invalidate   = mac_esp_dma_invalidate,
+	.send_dma_cmd     = mac_esp_send_pdma_cmd,
+	.dma_error        = mac_esp_dma_error,
+};
+
+static int __devinit esp_mac_probe(struct platform_device *dev)
+{
+	struct scsi_host_template *tpnt = &scsi_esp_template;
+	struct Scsi_Host *host;
+	struct esp *esp;
+	int err;
+	int chips_present;
+	struct mac_esp_priv *mep;
+
+	if (!MACH_IS_MAC)
+		return -ENODEV;
+
+	switch (macintosh_config->scsi_type) {
+	case MAC_SCSI_QUADRA:
+	case MAC_SCSI_QUADRA3:
+		chips_present = 1;
+		break;
+	case MAC_SCSI_QUADRA2:
+		if ((macintosh_config->ident == MAC_MODEL_Q900) ||
+		    (macintosh_config->ident == MAC_MODEL_Q950))
+			chips_present = 2;
+		else
+			chips_present = 1;
+		break;
+	default:
+		chips_present = 0;
+	}
+
+	if (dev->id + 1 > chips_present)
+		return -ENODEV;
+
+	host = scsi_host_alloc(tpnt, sizeof(struct esp));
+
+	err = -ENOMEM;
+	if (!host)
+		goto fail;
+
+	host->max_id = 8;
+	host->use_clustering = DISABLE_CLUSTERING;
+	esp = shost_priv(host);
+
+	esp->host = host;
+	esp->dev = dev;
+
+	esp->command_block = kzalloc(16, GFP_KERNEL);
+	if (!esp->command_block)
+		goto fail_unlink;
+	esp->command_block_dma = (dma_addr_t)esp->command_block;
+
+	esp->scsi_id = 7;
+	host->this_id = esp->scsi_id;
+	esp->scsi_id_mask = 1 << esp->scsi_id;
+
+	mep = kzalloc(sizeof(struct mac_esp_priv), GFP_KERNEL);
+	if (!mep)
+		goto fail_free_command_block;
+	mep->esp = esp;
+	platform_set_drvdata(dev, mep);
+
+	switch (macintosh_config->scsi_type) {
+	case MAC_SCSI_QUADRA:
+		esp->cfreq     = 16500000;
+		esp->regs      = (void __iomem *)MAC_ESP_REGS_QUADRA;
+		mep->pdma_io   = esp->regs + MAC_ESP_PDMA_IO_OFFSET;
+		mep->pdma_regs = NULL;
+		break;
+	case MAC_SCSI_QUADRA2:
+		esp->cfreq     = 25000000;
+		esp->regs      = (void __iomem *)(MAC_ESP_REGS_QUADRA2 +
+				 dev->id * MAC_ESP_REGS_SPACING);
+		mep->pdma_io   = esp->regs + MAC_ESP_PDMA_IO_OFFSET;
+		mep->pdma_regs = (void __iomem *)(MAC_ESP_PDMA_REG +
+				 dev->id * MAC_ESP_PDMA_REG_SPACING);
+		nubus_writel(0x1d1, mep->pdma_regs);
+		break;
+	case MAC_SCSI_QUADRA3:
+		/* These quadras have a real DMA controller (the PSC) but we
+		 * don't know how to drive it so we must use PIO instead.
+		 */
+		esp->cfreq     = 25000000;
+		esp->regs      = (void __iomem *)MAC_ESP_REGS_QUADRA3;
+		mep->pdma_io   = NULL;
+		mep->pdma_regs = NULL;
+		break;
+	}
+
+	esp->ops = &mac_esp_ops;
+	if (mep->pdma_io == NULL) {
+		printk(KERN_INFO PFX "using PIO for controller %d\n", dev->id);
+		esp_write8(0, ESP_TCLOW);
+		esp_write8(0, ESP_TCMED);
+		esp->flags = ESP_FLAG_DISABLE_SYNC;
+		mac_esp_ops.send_dma_cmd = mac_esp_send_pio_cmd;
+	} else {
+		printk(KERN_INFO PFX "using PDMA for controller %d\n", dev->id);
+	}
+
+	host->irq = IRQ_MAC_SCSI;
+	err = request_irq(host->irq, scsi_esp_intr, IRQF_SHARED, "Mac ESP",
+			  esp);
+	if (err < 0)
+		goto fail_free_priv;
+
+	err = scsi_esp_register(esp, &dev->dev);
+	if (err)
+		goto fail_free_irq;
+
+	return 0;
+
+fail_free_irq:
+	free_irq(host->irq, esp);
+fail_free_priv:
+	kfree(mep);
+fail_free_command_block:
+	kfree(esp->command_block);
+fail_unlink:
+	scsi_host_put(host);
+fail:
+	return err;
+}
+
+static int __devexit esp_mac_remove(struct platform_device *dev)
+{
+	struct mac_esp_priv *mep = platform_get_drvdata(dev);
+	struct esp *esp = mep->esp;
+	unsigned int irq = esp->host->irq;
+
+	scsi_esp_unregister(esp);
+
+	free_irq(irq, esp);
+
+	kfree(mep);
+
+	kfree(esp->command_block);
+
+	scsi_host_put(esp->host);
+
+	return 0;
+}
+
+static struct platform_driver esp_mac_driver = {
+	.probe    = esp_mac_probe,
+	.remove   = __devexit_p(esp_mac_remove),
+	.driver   = {
+		.name     = DRV_MODULE_NAME,
+	},
+};
+
+static int __init mac_esp_init(void)
+{
+	int err;
+
+	err = platform_driver_register(&esp_mac_driver);
+	if (err)
+		return err;
+
+	internal_esp = platform_device_alloc(DRV_MODULE_NAME, 0);
+	if (internal_esp && platform_device_add(internal_esp)) {
+		platform_device_put(internal_esp);
+		internal_esp = NULL;
+	}
+
+	external_esp = platform_device_alloc(DRV_MODULE_NAME, 1);
+	if (external_esp && platform_device_add(external_esp)) {
+		platform_device_put(external_esp);
+		external_esp = NULL;
+	}
+
+	if (internal_esp || external_esp) {
+		return 0;
+	} else {
+		platform_driver_unregister(&esp_mac_driver);
+		return -ENOMEM;
+	}
+}
+
+static void __exit mac_esp_exit(void)
+{
+	platform_driver_unregister(&esp_mac_driver);
+
+	if (internal_esp) {
+		platform_device_unregister(internal_esp);
+		internal_esp = NULL;
+	}
+	if (external_esp) {
+		platform_device_unregister(external_esp);
+		external_esp = NULL;
+	}
+}
+
+MODULE_DESCRIPTION("Mac ESP SCSI driver");
+MODULE_AUTHOR("Finn Thain <fthain@telegraphics.com.au>");
+MODULE_LICENSE("GPLv2");
+MODULE_VERSION(DRV_VERSION);
+
+module_init(mac_esp_init);
+module_exit(mac_esp_exit);
diff --git a/trunk/drivers/scsi/megaraid.c b/trunk/drivers/scsi/megaraid.c
index b135a1ed4b2c..18551aaf5e09 100644
--- a/trunk/drivers/scsi/megaraid.c
+++ b/trunk/drivers/scsi/megaraid.c
@@ -4996,7 +4996,7 @@ static int __init megaraid_init(void)
 		max_mbox_busy_wait = MBOX_BUSY_WAIT;
 
 #ifdef CONFIG_PROC_FS
-	mega_proc_dir_entry = proc_mkdir("megaraid", &proc_root);
+	mega_proc_dir_entry = proc_mkdir("megaraid", NULL);
 	if (!mega_proc_dir_entry) {
 		printk(KERN_WARNING
 				"megaraid: failed to create megaraid root\n");
@@ -5005,7 +5005,7 @@ static int __init megaraid_init(void)
 	error = pci_register_driver(&megaraid_pci_driver);
 	if (error) {
 #ifdef CONFIG_PROC_FS
-		remove_proc_entry("megaraid", &proc_root);
+		remove_proc_entry("megaraid", NULL);
 #endif
 		return error;
 	}
@@ -5035,7 +5035,7 @@ static void __exit megaraid_exit(void)
 	pci_unregister_driver(&megaraid_pci_driver);
 
 #ifdef CONFIG_PROC_FS
-	remove_proc_entry("megaraid", &proc_root);
+	remove_proc_entry("megaraid", NULL);
 #endif
 }
 
diff --git a/trunk/drivers/scsi/ncr53c8xx.c b/trunk/drivers/scsi/ncr53c8xx.c
index d89289400425..ceab4f73caf1 100644
--- a/trunk/drivers/scsi/ncr53c8xx.c
+++ b/trunk/drivers/scsi/ncr53c8xx.c
@@ -8186,7 +8186,7 @@ static void insert_into_waiting_list(struct ncb *np, struct scsi_cmnd *cmd)
 	cmd->next_wcmd = NULL;
 	if (!(wcmd = np->waiting_list)) np->waiting_list = cmd;
 	else {
-		while ((wcmd->next_wcmd) != 0)
+		while (wcmd->next_wcmd)
 			wcmd = (struct scsi_cmnd *) wcmd->next_wcmd;
 		wcmd->next_wcmd = (char *) cmd;
 	}
@@ -8222,7 +8222,7 @@ static void process_waiting_list(struct ncb *np, int sts)
 #ifdef DEBUG_WAITING_LIST
 	if (waiting_list) printk("%s: waiting_list=%lx processing sts=%d\n", ncr_name(np), (u_long) waiting_list, sts);
 #endif
-	while ((wcmd = waiting_list) != 0) {
+	while (wcmd = waiting_list) {
 		waiting_list = (struct scsi_cmnd *) wcmd->next_wcmd;
 		wcmd->next_wcmd = NULL;
 		if (sts == DID_OK) {
diff --git a/trunk/drivers/scsi/qla2xxx/qla_attr.c b/trunk/drivers/scsi/qla2xxx/qla_attr.c
index d61df036910c..287690853caf 100644
--- a/trunk/drivers/scsi/qla2xxx/qla_attr.c
+++ b/trunk/drivers/scsi/qla2xxx/qla_attr.c
@@ -609,8 +609,8 @@ qla2x00_pci_info_show(struct device *dev, struct device_attribute *attr,
 }
 
 static ssize_t
-qla2x00_state_show(struct device *dev, struct device_attribute *attr,
-		   char *buf)
+qla2x00_link_state_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
 {
 	scsi_qla_host_t *ha = shost_priv(class_to_shost(dev));
 	int len = 0;
@@ -814,7 +814,7 @@ static DEVICE_ATTR(isp_id, S_IRUGO, qla2x00_isp_id_show, NULL);
 static DEVICE_ATTR(model_name, S_IRUGO, qla2x00_model_name_show, NULL);
 static DEVICE_ATTR(model_desc, S_IRUGO, qla2x00_model_desc_show, NULL);
 static DEVICE_ATTR(pci_info, S_IRUGO, qla2x00_pci_info_show, NULL);
-static DEVICE_ATTR(state, S_IRUGO, qla2x00_state_show, NULL);
+static DEVICE_ATTR(link_state, S_IRUGO, qla2x00_link_state_show, NULL);
 static DEVICE_ATTR(zio, S_IRUGO | S_IWUSR, qla2x00_zio_show, qla2x00_zio_store);
 static DEVICE_ATTR(zio_timer, S_IRUGO | S_IWUSR, qla2x00_zio_timer_show,
 		   qla2x00_zio_timer_store);
@@ -838,7 +838,7 @@ struct device_attribute *qla2x00_host_attrs[] = {
 	&dev_attr_model_name,
 	&dev_attr_model_desc,
 	&dev_attr_pci_info,
-	&dev_attr_state,
+	&dev_attr_link_state,
 	&dev_attr_zio,
 	&dev_attr_zio_timer,
 	&dev_attr_beacon,
diff --git a/trunk/drivers/scsi/qla2xxx/qla_dbg.c b/trunk/drivers/scsi/qla2xxx/qla_dbg.c
index 9d12d9f26209..cbef785765cf 100644
--- a/trunk/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/trunk/drivers/scsi/qla2xxx/qla_dbg.c
@@ -38,78 +38,38 @@ qla2xxx_copy_queues(scsi_qla_host_t *ha, void *ptr)
 }
 
 static int
-qla24xx_dump_memory(scsi_qla_host_t *ha, uint32_t *code_ram,
-    uint32_t cram_size, uint32_t *ext_mem, void **nxt)
+qla24xx_dump_ram(scsi_qla_host_t *ha, uint32_t addr, uint32_t *ram,
+    uint32_t ram_dwords, void **nxt)
 {
 	int rval;
-	uint32_t cnt, stat, timer, risc_address, ext_mem_cnt;
-	uint16_t mb[4];
+	uint32_t cnt, stat, timer, dwords, idx;
+	uint16_t mb0;
 	struct device_reg_24xx __iomem *reg = &ha->iobase->isp24;
+	dma_addr_t dump_dma = ha->gid_list_dma;
+	uint32_t *dump = (uint32_t *)ha->gid_list;
 
 	rval = QLA_SUCCESS;
-	risc_address = ext_mem_cnt = 0;
-	memset(mb, 0, sizeof(mb));
+	mb0 = 0;
 
-	/* Code RAM. */
-	risc_address = 0x20000;
-	WRT_REG_WORD(&reg->mailbox0, MBC_READ_RAM_EXTENDED);
+	WRT_REG_WORD(&reg->mailbox0, MBC_DUMP_RISC_RAM_EXTENDED);
 	clear_bit(MBX_INTERRUPT, &ha->mbx_cmd_flags);
 
-	for (cnt = 0; cnt < cram_size / 4 && rval == QLA_SUCCESS;
-	    cnt++, risc_address++) {
-		WRT_REG_WORD(&reg->mailbox1, LSW(risc_address));
-		WRT_REG_WORD(&reg->mailbox8, MSW(risc_address));
-		RD_REG_WORD(&reg->mailbox8);
-		WRT_REG_DWORD(&reg->hccr, HCCRX_SET_HOST_INT);
-
-		for (timer = 6000000; timer; timer--) {
-			/* Check for pending interrupts. */
-			stat = RD_REG_DWORD(&reg->host_status);
-			if (stat & HSRX_RISC_INT) {
-				stat &= 0xff;
+	dwords = GID_LIST_SIZE / 4;
+	for (cnt = 0; cnt < ram_dwords && rval == QLA_SUCCESS;
+	    cnt += dwords, addr += dwords) {
+		if (cnt + dwords > ram_dwords)
+			dwords = ram_dwords - cnt;
 
-				if (stat == 0x1 || stat == 0x2 ||
-				    stat == 0x10 || stat == 0x11) {
-					set_bit(MBX_INTERRUPT,
-					    &ha->mbx_cmd_flags);
+		WRT_REG_WORD(&reg->mailbox1, LSW(addr));
+		WRT_REG_WORD(&reg->mailbox8, MSW(addr));
 
-					mb[0] = RD_REG_WORD(&reg->mailbox0);
-					mb[2] = RD_REG_WORD(&reg->mailbox2);
-					mb[3] = RD_REG_WORD(&reg->mailbox3);
+		WRT_REG_WORD(&reg->mailbox2, MSW(dump_dma));
+		WRT_REG_WORD(&reg->mailbox3, LSW(dump_dma));
+		WRT_REG_WORD(&reg->mailbox6, MSW(MSD(dump_dma)));
+		WRT_REG_WORD(&reg->mailbox7, LSW(MSD(dump_dma)));
 
-					WRT_REG_DWORD(&reg->hccr,
-					    HCCRX_CLR_RISC_INT);
-					RD_REG_DWORD(&reg->hccr);
-					break;
-				}
-
-				/* Clear this intr; it wasn't a mailbox intr */
-				WRT_REG_DWORD(&reg->hccr, HCCRX_CLR_RISC_INT);
-				RD_REG_DWORD(&reg->hccr);
-			}
-			udelay(5);
-		}
-
-		if (test_and_clear_bit(MBX_INTERRUPT, &ha->mbx_cmd_flags)) {
-			rval = mb[0] & MBS_MASK;
-			code_ram[cnt] = htonl((mb[3] << 16) | mb[2]);
-		} else {
-			rval = QLA_FUNCTION_FAILED;
-		}
-	}
-
-	if (rval == QLA_SUCCESS) {
-		/* External Memory. */
-		risc_address = 0x100000;
-		ext_mem_cnt = ha->fw_memory_size - 0x100000 + 1;
-		WRT_REG_WORD(&reg->mailbox0, MBC_READ_RAM_EXTENDED);
-		clear_bit(MBX_INTERRUPT, &ha->mbx_cmd_flags);
-	}
-	for (cnt = 0; cnt < ext_mem_cnt && rval == QLA_SUCCESS;
-	    cnt++, risc_address++) {
-		WRT_REG_WORD(&reg->mailbox1, LSW(risc_address));
-		WRT_REG_WORD(&reg->mailbox8, MSW(risc_address));
-		RD_REG_WORD(&reg->mailbox8);
+		WRT_REG_WORD(&reg->mailbox4, MSW(dwords));
+		WRT_REG_WORD(&reg->mailbox5, LSW(dwords));
 		WRT_REG_DWORD(&reg->hccr, HCCRX_SET_HOST_INT);
 
 		for (timer = 6000000; timer; timer--) {
@@ -123,9 +83,7 @@ qla24xx_dump_memory(scsi_qla_host_t *ha, uint32_t *code_ram,
 					set_bit(MBX_INTERRUPT,
 					    &ha->mbx_cmd_flags);
 
-					mb[0] = RD_REG_WORD(&reg->mailbox0);
-					mb[2] = RD_REG_WORD(&reg->mailbox2);
-					mb[3] = RD_REG_WORD(&reg->mailbox3);
+					mb0 = RD_REG_WORD(&reg->mailbox0);
 
 					WRT_REG_DWORD(&reg->hccr,
 					    HCCRX_CLR_RISC_INT);
@@ -141,17 +99,34 @@ qla24xx_dump_memory(scsi_qla_host_t *ha, uint32_t *code_ram,
 		}
 
 		if (test_and_clear_bit(MBX_INTERRUPT, &ha->mbx_cmd_flags)) {
-			rval = mb[0] & MBS_MASK;
-			ext_mem[cnt] = htonl((mb[3] << 16) | mb[2]);
+			rval = mb0 & MBS_MASK;
+			for (idx = 0; idx < dwords; idx++)
+				ram[cnt + idx] = swab32(dump[idx]);
 		} else {
 			rval = QLA_FUNCTION_FAILED;
 		}
 	}
 
-	*nxt = rval == QLA_SUCCESS ? &ext_mem[cnt]: NULL;
+	*nxt = rval == QLA_SUCCESS ? &ram[cnt]: NULL;
 	return rval;
 }
 
+static int
+qla24xx_dump_memory(scsi_qla_host_t *ha, uint32_t *code_ram,
+    uint32_t cram_size, void **nxt)
+{
+	int rval;
+
+	/* Code RAM. */
+	rval = qla24xx_dump_ram(ha, 0x20000, code_ram, cram_size / 4, nxt);
+	if (rval != QLA_SUCCESS)
+		return rval;
+
+	/* External Memory. */
+	return qla24xx_dump_ram(ha, 0x100000, *nxt,
+	    ha->fw_memory_size - 0x100000 + 1, nxt);
+}
+
 static uint32_t *
 qla24xx_read_window(struct device_reg_24xx __iomem *reg, uint32_t iobase,
     uint32_t count, uint32_t *buf)
@@ -239,6 +214,90 @@ qla24xx_soft_reset(scsi_qla_host_t *ha)
 	return rval;
 }
 
+static int
+qla2xxx_dump_ram(scsi_qla_host_t *ha, uint32_t addr, uint16_t *ram,
+    uint16_t ram_words, void **nxt)
+{
+	int rval;
+	uint32_t cnt, stat, timer, words, idx;
+	uint16_t mb0;
+	struct device_reg_2xxx __iomem *reg = &ha->iobase->isp;
+	dma_addr_t dump_dma = ha->gid_list_dma;
+	uint16_t *dump = (uint16_t *)ha->gid_list;
+
+	rval = QLA_SUCCESS;
+	mb0 = 0;
+
+	WRT_MAILBOX_REG(ha, reg, 0, MBC_DUMP_RISC_RAM_EXTENDED);
+	clear_bit(MBX_INTERRUPT, &ha->mbx_cmd_flags);
+
+	words = GID_LIST_SIZE / 2;
+	for (cnt = 0; cnt < ram_words && rval == QLA_SUCCESS;
+	    cnt += words, addr += words) {
+		if (cnt + words > ram_words)
+			words = ram_words - cnt;
+
+		WRT_MAILBOX_REG(ha, reg, 1, LSW(addr));
+		WRT_MAILBOX_REG(ha, reg, 8, MSW(addr));
+
+		WRT_MAILBOX_REG(ha, reg, 2, MSW(dump_dma));
+		WRT_MAILBOX_REG(ha, reg, 3, LSW(dump_dma));
+		WRT_MAILBOX_REG(ha, reg, 6, MSW(MSD(dump_dma)));
+		WRT_MAILBOX_REG(ha, reg, 7, LSW(MSD(dump_dma)));
+
+		WRT_MAILBOX_REG(ha, reg, 4, words);
+		WRT_REG_WORD(&reg->hccr, HCCR_SET_HOST_INT);
+
+		for (timer = 6000000; timer; timer--) {
+			/* Check for pending interrupts. */
+			stat = RD_REG_DWORD(&reg->u.isp2300.host_status);
+			if (stat & HSR_RISC_INT) {
+				stat &= 0xff;
+
+				if (stat == 0x1 || stat == 0x2) {
+					set_bit(MBX_INTERRUPT,
+					    &ha->mbx_cmd_flags);
+
+					mb0 = RD_MAILBOX_REG(ha, reg, 0);
+
+					/* Release mailbox registers. */
+					WRT_REG_WORD(&reg->semaphore, 0);
+					WRT_REG_WORD(&reg->hccr,
+					    HCCR_CLR_RISC_INT);
+					RD_REG_WORD(&reg->hccr);
+					break;
+				} else if (stat == 0x10 || stat == 0x11) {
+					set_bit(MBX_INTERRUPT,
+					    &ha->mbx_cmd_flags);
+
+					mb0 = RD_MAILBOX_REG(ha, reg, 0);
+
+					WRT_REG_WORD(&reg->hccr,
+					    HCCR_CLR_RISC_INT);
+					RD_REG_WORD(&reg->hccr);
+					break;
+				}
+
+				/* clear this intr; it wasn't a mailbox intr */
+				WRT_REG_WORD(&reg->hccr, HCCR_CLR_RISC_INT);
+				RD_REG_WORD(&reg->hccr);
+			}
+			udelay(5);
+		}
+
+		if (test_and_clear_bit(MBX_INTERRUPT, &ha->mbx_cmd_flags)) {
+			rval = mb0 & MBS_MASK;
+			for (idx = 0; idx < words; idx++)
+				ram[cnt + idx] = swab16(dump[idx]);
+		} else {
+			rval = QLA_FUNCTION_FAILED;
+		}
+	}
+
+	*nxt = rval == QLA_SUCCESS ? &ram[cnt]: NULL;
+	return rval;
+}
+
 static inline void
 qla2xxx_read_window(struct device_reg_2xxx __iomem *reg, uint32_t count,
     uint16_t *buf)
@@ -258,19 +317,14 @@ void
 qla2300_fw_dump(scsi_qla_host_t *ha, int hardware_locked)
 {
 	int		rval;
-	uint32_t	cnt, timer;
-	uint32_t	risc_address;
-	uint16_t	mb0, mb2;
+	uint32_t	cnt;
 
-	uint32_t	stat;
 	struct device_reg_2xxx __iomem *reg = &ha->iobase->isp;
 	uint16_t __iomem *dmp_reg;
 	unsigned long	flags;
 	struct qla2300_fw_dump	*fw;
-	uint32_t	data_ram_cnt;
+	void		*nxt;
 
-	risc_address = data_ram_cnt = 0;
-	mb0 = mb2 = 0;
 	flags = 0;
 
 	if (!hardware_locked)
@@ -388,185 +442,23 @@ qla2300_fw_dump(scsi_qla_host_t *ha, int hardware_locked)
 		}
 	}
 
-	if (rval == QLA_SUCCESS) {
-		/* Get RISC SRAM. */
-		risc_address = 0x800;
- 		WRT_MAILBOX_REG(ha, reg, 0, MBC_READ_RAM_WORD);
-		clear_bit(MBX_INTERRUPT, &ha->mbx_cmd_flags);
-	}
-	for (cnt = 0; cnt < sizeof(fw->risc_ram) / 2 && rval == QLA_SUCCESS;
-	    cnt++, risc_address++) {
- 		WRT_MAILBOX_REG(ha, reg, 1, (uint16_t)risc_address);
-		WRT_REG_WORD(&reg->hccr, HCCR_SET_HOST_INT);
-
-		for (timer = 6000000; timer; timer--) {
-			/* Check for pending interrupts. */
- 			stat = RD_REG_DWORD(&reg->u.isp2300.host_status);
-			if (stat & HSR_RISC_INT) {
-				stat &= 0xff;
-
-				if (stat == 0x1 || stat == 0x2) {
-					set_bit(MBX_INTERRUPT,
-					    &ha->mbx_cmd_flags);
-
-					mb0 = RD_MAILBOX_REG(ha, reg, 0);
-					mb2 = RD_MAILBOX_REG(ha, reg, 2);
-
-					/* Release mailbox registers. */
-					WRT_REG_WORD(&reg->semaphore, 0);
-					WRT_REG_WORD(&reg->hccr,
-					    HCCR_CLR_RISC_INT);
-					RD_REG_WORD(&reg->hccr);
-					break;
-				} else if (stat == 0x10 || stat == 0x11) {
-					set_bit(MBX_INTERRUPT,
-					    &ha->mbx_cmd_flags);
-
-					mb0 = RD_MAILBOX_REG(ha, reg, 0);
-					mb2 = RD_MAILBOX_REG(ha, reg, 2);
-
-					WRT_REG_WORD(&reg->hccr,
-					    HCCR_CLR_RISC_INT);
-					RD_REG_WORD(&reg->hccr);
-					break;
-				}
-
-				/* clear this intr; it wasn't a mailbox intr */
-				WRT_REG_WORD(&reg->hccr, HCCR_CLR_RISC_INT);
-				RD_REG_WORD(&reg->hccr);
-			}
-			udelay(5);
-		}
-
-		if (test_and_clear_bit(MBX_INTERRUPT, &ha->mbx_cmd_flags)) {
-			rval = mb0 & MBS_MASK;
-			fw->risc_ram[cnt] = htons(mb2);
-		} else {
-			rval = QLA_FUNCTION_FAILED;
-		}
-	}
-
-	if (rval == QLA_SUCCESS) {
-		/* Get stack SRAM. */
-		risc_address = 0x10000;
- 		WRT_MAILBOX_REG(ha, reg, 0, MBC_READ_RAM_EXTENDED);
-		clear_bit(MBX_INTERRUPT, &ha->mbx_cmd_flags);
-	}
-	for (cnt = 0; cnt < sizeof(fw->stack_ram) / 2 && rval == QLA_SUCCESS;
-	    cnt++, risc_address++) {
- 		WRT_MAILBOX_REG(ha, reg, 1, LSW(risc_address));
- 		WRT_MAILBOX_REG(ha, reg, 8, MSW(risc_address));
-		WRT_REG_WORD(&reg->hccr, HCCR_SET_HOST_INT);
-
-		for (timer = 6000000; timer; timer--) {
-			/* Check for pending interrupts. */
- 			stat = RD_REG_DWORD(&reg->u.isp2300.host_status);
-			if (stat & HSR_RISC_INT) {
-				stat &= 0xff;
-
-				if (stat == 0x1 || stat == 0x2) {
-					set_bit(MBX_INTERRUPT,
-					    &ha->mbx_cmd_flags);
-
-					mb0 = RD_MAILBOX_REG(ha, reg, 0);
-					mb2 = RD_MAILBOX_REG(ha, reg, 2);
-
-					/* Release mailbox registers. */
-					WRT_REG_WORD(&reg->semaphore, 0);
-					WRT_REG_WORD(&reg->hccr,
-					    HCCR_CLR_RISC_INT);
-					RD_REG_WORD(&reg->hccr);
-					break;
-				} else if (stat == 0x10 || stat == 0x11) {
-					set_bit(MBX_INTERRUPT,
-					    &ha->mbx_cmd_flags);
-
-					mb0 = RD_MAILBOX_REG(ha, reg, 0);
-					mb2 = RD_MAILBOX_REG(ha, reg, 2);
-
-					WRT_REG_WORD(&reg->hccr,
-					    HCCR_CLR_RISC_INT);
-					RD_REG_WORD(&reg->hccr);
-					break;
-				}
-
-				/* clear this intr; it wasn't a mailbox intr */
-				WRT_REG_WORD(&reg->hccr, HCCR_CLR_RISC_INT);
-				RD_REG_WORD(&reg->hccr);
-			}
-			udelay(5);
-		}
-
-		if (test_and_clear_bit(MBX_INTERRUPT, &ha->mbx_cmd_flags)) {
-			rval = mb0 & MBS_MASK;
-			fw->stack_ram[cnt] = htons(mb2);
-		} else {
-			rval = QLA_FUNCTION_FAILED;
-		}
-	}
-
-	if (rval == QLA_SUCCESS) {
-		/* Get data SRAM. */
-		risc_address = 0x11000;
-		data_ram_cnt = ha->fw_memory_size - risc_address + 1;
- 		WRT_MAILBOX_REG(ha, reg, 0, MBC_READ_RAM_EXTENDED);
-		clear_bit(MBX_INTERRUPT, &ha->mbx_cmd_flags);
-	}
-	for (cnt = 0; cnt < data_ram_cnt && rval == QLA_SUCCESS;
-	    cnt++, risc_address++) {
- 		WRT_MAILBOX_REG(ha, reg, 1, LSW(risc_address));
- 		WRT_MAILBOX_REG(ha, reg, 8, MSW(risc_address));
-		WRT_REG_WORD(&reg->hccr, HCCR_SET_HOST_INT);
-
-		for (timer = 6000000; timer; timer--) {
-			/* Check for pending interrupts. */
- 			stat = RD_REG_DWORD(&reg->u.isp2300.host_status);
-			if (stat & HSR_RISC_INT) {
-				stat &= 0xff;
-
-				if (stat == 0x1 || stat == 0x2) {
-					set_bit(MBX_INTERRUPT,
-					    &ha->mbx_cmd_flags);
-
-					mb0 = RD_MAILBOX_REG(ha, reg, 0);
-					mb2 = RD_MAILBOX_REG(ha, reg, 2);
-
-					/* Release mailbox registers. */
-					WRT_REG_WORD(&reg->semaphore, 0);
-					WRT_REG_WORD(&reg->hccr,
-					    HCCR_CLR_RISC_INT);
-					RD_REG_WORD(&reg->hccr);
-					break;
-				} else if (stat == 0x10 || stat == 0x11) {
-					set_bit(MBX_INTERRUPT,
-					    &ha->mbx_cmd_flags);
-
-					mb0 = RD_MAILBOX_REG(ha, reg, 0);
-					mb2 = RD_MAILBOX_REG(ha, reg, 2);
-
-					WRT_REG_WORD(&reg->hccr,
-					    HCCR_CLR_RISC_INT);
-					RD_REG_WORD(&reg->hccr);
-					break;
-				}
+	/* Get RISC SRAM. */
+	if (rval == QLA_SUCCESS)
+		rval = qla2xxx_dump_ram(ha, 0x800, fw->risc_ram,
+		    sizeof(fw->risc_ram) / 2, &nxt);
 
-				/* clear this intr; it wasn't a mailbox intr */
-				WRT_REG_WORD(&reg->hccr, HCCR_CLR_RISC_INT);
-				RD_REG_WORD(&reg->hccr);
-			}
-			udelay(5);
-		}
+	/* Get stack SRAM. */
+	if (rval == QLA_SUCCESS)
+		rval = qla2xxx_dump_ram(ha, 0x10000, fw->stack_ram,
+		    sizeof(fw->stack_ram) / 2, &nxt);
 
-		if (test_and_clear_bit(MBX_INTERRUPT, &ha->mbx_cmd_flags)) {
-			rval = mb0 & MBS_MASK;
-			fw->data_ram[cnt] = htons(mb2);
-		} else {
-			rval = QLA_FUNCTION_FAILED;
-		}
-	}
+	/* Get data SRAM. */
+	if (rval == QLA_SUCCESS)
+		rval = qla2xxx_dump_ram(ha, 0x11000, fw->data_ram,
+		    ha->fw_memory_size - 0x11000 + 1, &nxt);
 
 	if (rval == QLA_SUCCESS)
-		qla2xxx_copy_queues(ha, &fw->data_ram[cnt]);
+		qla2xxx_copy_queues(ha, nxt);
 
 	if (rval != QLA_SUCCESS) {
 		qla_printk(KERN_WARNING, ha,
@@ -1010,7 +902,7 @@ qla24xx_fw_dump(scsi_qla_host_t *ha, int hardware_locked)
 		goto qla24xx_fw_dump_failed_0;
 
 	rval = qla24xx_dump_memory(ha, fw->code_ram, sizeof(fw->code_ram),
-	    fw->ext_mem, &nxt);
+	    &nxt);
 	if (rval != QLA_SUCCESS)
 		goto qla24xx_fw_dump_failed_0;
 
@@ -1318,7 +1210,7 @@ qla25xx_fw_dump(scsi_qla_host_t *ha, int hardware_locked)
 		goto qla25xx_fw_dump_failed_0;
 
 	rval = qla24xx_dump_memory(ha, fw->code_ram, sizeof(fw->code_ram),
-	    fw->ext_mem, &nxt);
+	    &nxt);
 	if (rval != QLA_SUCCESS)
 		goto qla25xx_fw_dump_failed_0;
 
diff --git a/trunk/drivers/scsi/qla2xxx/qla_fw.h b/trunk/drivers/scsi/qla2xxx/qla_fw.h
index 078f2a15f40b..cf194517400d 100644
--- a/trunk/drivers/scsi/qla2xxx/qla_fw.h
+++ b/trunk/drivers/scsi/qla2xxx/qla_fw.h
@@ -1036,22 +1036,6 @@ struct mid_db_entry_24xx {
 	uint8_t reserved_1;
 };
 
- /*
- * Virtual Fabric ID type definition.
- */
-typedef struct vf_id {
-        uint16_t id : 12;
-        uint16_t priority : 4;
-} vf_id_t;
-
-/*
- * Virtual Fabric HopCt type definition.
- */
-typedef struct vf_hopct {
-        uint16_t reserved : 8;
-        uint16_t hopct : 8;
-} vf_hopct_t;
-
 /*
  * Virtual Port Control IOCB
  */
@@ -1082,10 +1066,10 @@ struct vp_ctrl_entry_24xx {
 
 	uint8_t vp_idx_map[16];
 	uint16_t flags;
-	struct vf_id    id;
+	uint16_t id;
 	uint16_t reserved_4;
-	struct vf_hopct  hopct;
-	uint8_t reserved_5[8];
+	uint16_t hopct;
+	uint8_t reserved_5[24];
 };
 
 /*
@@ -1132,9 +1116,9 @@ struct vp_config_entry_24xx {
 	uint16_t reserved_vp2;
 	uint8_t port_name_idx2[WWN_SIZE];
 	uint8_t node_name_idx2[WWN_SIZE];
-	struct vf_id    id;
+	uint16_t id;
 	uint16_t reserved_4;
-	struct vf_hopct  hopct;
+	uint16_t hopct;
 	uint8_t reserved_5;
 };
 
diff --git a/trunk/drivers/scsi/qla2xxx/qla_gbl.h b/trunk/drivers/scsi/qla2xxx/qla_gbl.h
index 76eb4fecce65..f8827068d30f 100644
--- a/trunk/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/trunk/drivers/scsi/qla2xxx/qla_gbl.h
@@ -151,10 +151,6 @@ qla2x00_verify_checksum(scsi_qla_host_t *, uint32_t);
 extern int
 qla2x00_issue_iocb(scsi_qla_host_t *, void *, dma_addr_t, size_t);
 
-extern int
-qla2x00_issue_iocb_timeout(scsi_qla_host_t *, void *, dma_addr_t, size_t,
-    uint32_t);
-
 extern int
 qla2x00_abort_command(scsi_qla_host_t *, srb_t *);
 
diff --git a/trunk/drivers/scsi/qla2xxx/qla_gs.c b/trunk/drivers/scsi/qla2xxx/qla_gs.c
index 750d7ef83aae..4cb80b476c85 100644
--- a/trunk/drivers/scsi/qla2xxx/qla_gs.c
+++ b/trunk/drivers/scsi/qla2xxx/qla_gs.c
@@ -1583,8 +1583,8 @@ qla2x00_fdmi_rpa(scsi_qla_host_t *ha)
 	eiter->type = __constant_cpu_to_be16(FDMI_PORT_MAX_FRAME_SIZE);
 	eiter->len = __constant_cpu_to_be16(4 + 4);
 	max_frame_size = IS_FWI2_CAPABLE(ha) ?
-		(uint32_t) icb24->frame_payload_size:
-		(uint32_t) ha->init_cb->frame_payload_size;
+	    le16_to_cpu(icb24->frame_payload_size):
+	    le16_to_cpu(ha->init_cb->frame_payload_size);
 	eiter->a.max_frame_size = cpu_to_be32(max_frame_size);
 	size += 4 + 4;
 
diff --git a/trunk/drivers/scsi/qla2xxx/qla_init.c b/trunk/drivers/scsi/qla2xxx/qla_init.c
index 01e26087c1dd..bbbc5a632a1d 100644
--- a/trunk/drivers/scsi/qla2xxx/qla_init.c
+++ b/trunk/drivers/scsi/qla2xxx/qla_init.c
@@ -3645,7 +3645,7 @@ qla24xx_nvram_config(scsi_qla_host_t *ha)
 	if (le16_to_cpu(nv->login_timeout) < 4)
 		nv->login_timeout = __constant_cpu_to_le16(4);
 	ha->login_timeout = le16_to_cpu(nv->login_timeout);
-	icb->login_timeout = cpu_to_le16(nv->login_timeout);
+	icb->login_timeout = nv->login_timeout;
 
 	/* Set minimum RATOV to 100 tenths of a second. */
 	ha->r_a_tov = 100;
diff --git a/trunk/drivers/scsi/qla2xxx/qla_isr.c b/trunk/drivers/scsi/qla2xxx/qla_isr.c
index 285479b62d8f..5d9a64a7879b 100644
--- a/trunk/drivers/scsi/qla2xxx/qla_isr.c
+++ b/trunk/drivers/scsi/qla2xxx/qla_isr.c
@@ -409,6 +409,7 @@ qla2x00_async_event(scsi_qla_host_t *ha, uint16_t *mb)
 		}
 
 		set_bit(REGISTER_FC4_NEEDED, &ha->dpc_flags);
+		set_bit(REGISTER_FDMI_NEEDED, &ha->dpc_flags);
 
 		ha->flags.management_server_logged_in = 0;
 		qla2x00_post_aen_work(ha, FCH_EVT_LIP, mb[1]);
@@ -454,8 +455,6 @@ qla2x00_async_event(scsi_qla_host_t *ha, uint16_t *mb)
 
 		ha->flags.management_server_logged_in = 0;
 		ha->link_data_rate = PORT_SPEED_UNKNOWN;
-		if (ql2xfdmienable)
-			set_bit(REGISTER_FDMI_NEEDED, &ha->dpc_flags);
 		qla2x00_post_aen_work(ha, FCH_EVT_LINKDOWN, 0);
 		break;
 
@@ -511,6 +510,7 @@ qla2x00_async_event(scsi_qla_host_t *ha, uint16_t *mb)
 			set_bit(RESET_MARKER_NEEDED, &ha->dpc_flags);
 		}
 		set_bit(REGISTER_FC4_NEEDED, &ha->dpc_flags);
+		set_bit(REGISTER_FDMI_NEEDED, &ha->dpc_flags);
 
 		ha->flags.gpsc_supported = 1;
 		ha->flags.management_server_logged_in = 0;
diff --git a/trunk/drivers/scsi/qla2xxx/qla_mbx.c b/trunk/drivers/scsi/qla2xxx/qla_mbx.c
index 7d0a8a4c7719..210060420809 100644
--- a/trunk/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/trunk/drivers/scsi/qla2xxx/qla_mbx.c
@@ -681,7 +681,7 @@ qla2x00_verify_checksum(scsi_qla_host_t *ha, uint32_t risc_addr)
  * Context:
  *	Kernel context.
  */
-int
+static int
 qla2x00_issue_iocb_timeout(scsi_qla_host_t *ha, void *buffer,
     dma_addr_t phys_addr, size_t size, uint32_t tov)
 {
@@ -784,7 +784,6 @@ qla2x00_abort_command(scsi_qla_host_t *ha, srb_t *sp)
 		DEBUG2_3_11(printk("qla2x00_abort_command(%ld): failed=%x.\n",
 		    ha->host_no, rval));
 	} else {
-		sp->flags |= SRB_ABORT_PENDING;
 		DEBUG11(printk("qla2x00_abort_command(%ld): done.\n",
 		    ha->host_no));
 	}
@@ -1469,7 +1468,7 @@ qla24xx_login_fabric(scsi_qla_host_t *ha, uint16_t loop_id, uint8_t domain,
 	lg->port_id[0] = al_pa;
 	lg->port_id[1] = area;
 	lg->port_id[2] = domain;
-	lg->vp_index = cpu_to_le16(ha->vp_idx);
+	lg->vp_index = ha->vp_idx;
 	rval = qla2x00_issue_iocb(ha, lg, lg_dma, 0);
 	if (rval != QLA_SUCCESS) {
 		DEBUG2_3_11(printk("%s(%ld): failed to issue Login IOCB "
@@ -1724,7 +1723,7 @@ qla24xx_fabric_logout(scsi_qla_host_t *ha, uint16_t loop_id, uint8_t domain,
 	lg->port_id[0] = al_pa;
 	lg->port_id[1] = area;
 	lg->port_id[2] = domain;
-	lg->vp_index = cpu_to_le16(ha->vp_idx);
+	lg->vp_index = ha->vp_idx;
 	rval = qla2x00_issue_iocb(ha, lg, lg_dma, 0);
 	if (rval != QLA_SUCCESS) {
 		DEBUG2_3_11(printk("%s(%ld): failed to issue Logout IOCB "
@@ -2210,7 +2209,6 @@ qla24xx_abort_command(scsi_qla_host_t *ha, srb_t *sp)
 		rval = QLA_FUNCTION_FAILED;
 	} else {
 		DEBUG11(printk("%s(%ld): done.\n", __func__, ha->host_no));
-		sp->flags |= SRB_ABORT_PENDING;
 	}
 
 	dma_pool_free(ha->s_dma_pool, abt, abt_dma);
@@ -2644,12 +2642,11 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *ha,
 	struct vp_rpt_id_entry_24xx *rptid_entry)
 {
 	uint8_t vp_idx;
+	uint16_t stat = le16_to_cpu(rptid_entry->vp_idx);
 	scsi_qla_host_t *vha;
 
 	if (rptid_entry->entry_status != 0)
 		return;
-	if (rptid_entry->entry_status != __constant_cpu_to_le16(CS_COMPLETE))
-		return;
 
 	if (rptid_entry->format == 0) {
 		DEBUG15(printk("%s:format 0 : scsi(%ld) number of VPs setup %d,"
@@ -2659,17 +2656,17 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *ha,
 			rptid_entry->port_id[2], rptid_entry->port_id[1],
 			rptid_entry->port_id[0]));
 	} else if (rptid_entry->format == 1) {
-		vp_idx = LSB(rptid_entry->vp_idx);
+		vp_idx = LSB(stat);
 		DEBUG15(printk("%s:format 1: scsi(%ld): VP[%d] enabled "
 		    "- status %d - "
 		    "with port id %02x%02x%02x\n",__func__,ha->host_no,
-		    vp_idx, MSB(rptid_entry->vp_idx),
+		    vp_idx, MSB(stat),
 		    rptid_entry->port_id[2], rptid_entry->port_id[1],
 		    rptid_entry->port_id[0]));
 		if (vp_idx == 0)
 			return;
 
-		if (MSB(rptid_entry->vp_idx) == 1)
+		if (MSB(stat) == 1)
 			return;
 
 		list_for_each_entry(vha, &ha->vp_list, vp_list)
@@ -2982,8 +2979,8 @@ qla84xx_verify_chip(struct scsi_qla_host *ha, uint16_t *status)
 	/* We update the firmware with only one data sequence. */
 	options |= VCO_END_OF_DATA;
 
-	retry = 0;
 	do {
+		retry = 0;
 		memset(mn, 0, sizeof(*mn));
 		mn->p.req.entry_type = VERIFY_CHIP_IOCB_TYPE;
 		mn->p.req.entry_count = 1;
diff --git a/trunk/drivers/scsi/qla2xxx/qla_os.c b/trunk/drivers/scsi/qla2xxx/qla_os.c
index 8b33b163b1d4..3223fd16bcfe 100644
--- a/trunk/drivers/scsi/qla2xxx/qla_os.c
+++ b/trunk/drivers/scsi/qla2xxx/qla_os.c
@@ -67,7 +67,7 @@ static void qla2x00_free_device(scsi_qla_host_t *);
 
 static void qla2x00_config_dma_addressing(scsi_qla_host_t *ha);
 
-int ql2xfdmienable;
+int ql2xfdmienable=1;
 module_param(ql2xfdmienable, int, S_IRUGO|S_IRUSR);
 MODULE_PARM_DESC(ql2xfdmienable,
 		"Enables FDMI registratons "
@@ -2135,7 +2135,7 @@ qla2x00_mem_free(scsi_qla_host_t *ha)
 	kfree(ha->nvram);
 }
 
-struct qla_work_evt *
+static struct qla_work_evt *
 qla2x00_alloc_work(struct scsi_qla_host *ha, enum qla_work_type type,
     int locked)
 {
@@ -2152,7 +2152,7 @@ qla2x00_alloc_work(struct scsi_qla_host *ha, enum qla_work_type type,
 	return e;
 }
 
-int
+static int
 qla2x00_post_work(struct scsi_qla_host *ha, struct qla_work_evt *e, int locked)
 {
 	unsigned long flags;
@@ -2373,7 +2373,7 @@ qla2x00_do_dpc(void *data)
 					} else {
 						fcport->login_retry = 0;
 					}
-					if (fcport->login_retry == 0)
+					if (fcport->login_retry == 0 && status != QLA_SUCCESS)
 						fcport->loop_id = FC_NO_LOOP_ID;
 				}
 				if (test_bit(LOOP_RESYNC_NEEDED, &ha->dpc_flags))
@@ -2599,6 +2599,10 @@ qla2x00_timer(scsi_qla_host_t *ha)
 		start_dpc++;
 	}
 
+	/* Process any deferred work. */
+	if (!list_empty(&ha->work_list))
+		start_dpc++;
+
 	/* Schedule the DPC routine if needed */
 	if ((test_bit(ISP_ABORT_NEEDED, &ha->dpc_flags) ||
 	    test_bit(LOOP_RESYNC_NEEDED, &ha->dpc_flags) ||
diff --git a/trunk/drivers/scsi/qla2xxx/qla_version.h b/trunk/drivers/scsi/qla2xxx/qla_version.h
index f42f17acf2cf..afeae2bfe7eb 100644
--- a/trunk/drivers/scsi/qla2xxx/qla_version.h
+++ b/trunk/drivers/scsi/qla2xxx/qla_version.h
@@ -7,7 +7,7 @@
 /*
  * Driver version
  */
-#define QLA2XXX_VERSION      "8.02.01-k1"
+#define QLA2XXX_VERSION      "8.02.01-k2"
 
 #define QLA_DRIVER_MAJOR_VER	8
 #define QLA_DRIVER_MINOR_VER	2
diff --git a/trunk/drivers/scsi/scsi_debug.c b/trunk/drivers/scsi/scsi_debug.c
index 07103c399fe0..f6600bfb5bde 100644
--- a/trunk/drivers/scsi/scsi_debug.c
+++ b/trunk/drivers/scsi/scsi_debug.c
@@ -1773,7 +1773,7 @@ static int scsi_debug_slave_alloc(struct scsi_device *sdp)
 	if (SCSI_DEBUG_OPT_NOISE & scsi_debug_opts)
 		printk(KERN_INFO "scsi_debug: slave_alloc <%u %u %u %u>\n",
 		       sdp->host->host_no, sdp->channel, sdp->id, sdp->lun);
-	set_bit(QUEUE_FLAG_BIDI, &sdp->request_queue->queue_flags);
+	queue_flag_set_unlocked(QUEUE_FLAG_BIDI, sdp->request_queue);
 	return 0;
 }
 
diff --git a/trunk/drivers/scsi/scsi_devinfo.c b/trunk/drivers/scsi/scsi_devinfo.c
index b8de041bc0ae..a235802f2981 100644
--- a/trunk/drivers/scsi/scsi_devinfo.c
+++ b/trunk/drivers/scsi/scsi_devinfo.c
@@ -449,37 +449,40 @@ int scsi_get_device_flags(struct scsi_device *sdev,
 }
 
 #ifdef CONFIG_SCSI_PROC_FS
-/* 
- * proc_scsi_dev_info_read: dump the scsi_dev_info_list via
- * /proc/scsi/device_info
- */
-static int proc_scsi_devinfo_read(char *buffer, char **start,
-				  off_t offset, int length)
+static int devinfo_seq_show(struct seq_file *m, void *v)
 {
-	struct scsi_dev_info_list *devinfo;
-	int size, len = 0;
-	off_t begin = 0;
-	off_t pos = 0;
+	struct scsi_dev_info_list *devinfo =
+		list_entry(v, struct scsi_dev_info_list, dev_info_list);
 
-	list_for_each_entry(devinfo, &scsi_dev_info_list, dev_info_list) {
-		size = sprintf(buffer + len, "'%.8s' '%.16s' 0x%x\n",
+	seq_printf(m, "'%.8s' '%.16s' 0x%x\n",
 			devinfo->vendor, devinfo->model, devinfo->flags);
-		len += size;
-		pos = begin + len;
-		if (pos < offset) {
-			len = 0;
-			begin = pos;
-		}
-		if (pos > offset + length)
-			goto stop_output;
-	}
+	return 0;
+}
+
+static void * devinfo_seq_start(struct seq_file *m, loff_t *pos)
+{
+	return seq_list_start(&scsi_dev_info_list, *pos);
+}
 
-stop_output:
-	*start = buffer + (offset - begin);	/* Start of wanted data */
-	len -= (offset - begin);	/* Start slop */
-	if (len > length)
-		len = length;	/* Ending slop */
-	return (len);
+static void * devinfo_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	return seq_list_next(v, &scsi_dev_info_list, pos);
+}
+
+static void devinfo_seq_stop(struct seq_file *m, void *v)
+{
+}
+
+static const struct seq_operations scsi_devinfo_seq_ops = {
+	.start	= devinfo_seq_start,
+	.next	= devinfo_seq_next,
+	.stop	= devinfo_seq_stop,
+	.show	= devinfo_seq_show,
+};
+
+static int proc_scsi_devinfo_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &scsi_devinfo_seq_ops);
 }
 
 /* 
@@ -489,11 +492,12 @@ static int proc_scsi_devinfo_read(char *buffer, char **start,
  * integer value of flag to the scsi device info list.
  * To use, echo "vendor:model:flag" > /proc/scsi/device_info
  */
-static int proc_scsi_devinfo_write(struct file *file, const char __user *buf,
-				   unsigned long length, void *data)
+static ssize_t proc_scsi_devinfo_write(struct file *file,
+				       const char __user *buf,
+				       size_t length, loff_t *ppos)
 {
 	char *buffer;
-	int err = length;
+	ssize_t err = length;
 
 	if (!buf || length>PAGE_SIZE)
 		return -EINVAL;
@@ -517,6 +521,15 @@ static int proc_scsi_devinfo_write(struct file *file, const char __user *buf,
 	free_page((unsigned long)buffer);
 	return err;
 }
+
+static const struct file_operations scsi_devinfo_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= proc_scsi_devinfo_open,
+	.read		= seq_read,
+	.write		= proc_scsi_devinfo_write,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
 #endif /* CONFIG_SCSI_PROC_FS */
 
 module_param_string(dev_flags, scsi_dev_flags, sizeof(scsi_dev_flags), 0);
@@ -577,15 +590,13 @@ int __init scsi_init_devinfo(void)
 	}
 
 #ifdef CONFIG_SCSI_PROC_FS
-	p = create_proc_entry("scsi/device_info", 0, NULL);
+	p = proc_create("scsi/device_info", 0, NULL, &scsi_devinfo_proc_fops);
 	if (!p) {
 		error = -ENOMEM;
 		goto out;
 	}
 
 	p->owner = THIS_MODULE;
-	p->get_info = proc_scsi_devinfo_read;
-	p->write_proc = proc_scsi_devinfo_write;
 #endif /* CONFIG_SCSI_PROC_FS */
 
  out:
diff --git a/trunk/drivers/scsi/scsi_error.c b/trunk/drivers/scsi/scsi_error.c
index 221f31e36d26..1eaba6cd80f4 100644
--- a/trunk/drivers/scsi/scsi_error.c
+++ b/trunk/drivers/scsi/scsi_error.c
@@ -1771,6 +1771,7 @@ scsi_reset_provider(struct scsi_device *dev, int flag)
 	unsigned long flags;
 	int rtn;
 
+	blk_rq_init(NULL, &req);
 	scmd->request = &req;
 	memset(&scmd->eh_timeout, 0, sizeof(scmd->eh_timeout));
 
diff --git a/trunk/drivers/scsi/scsi_lib.c b/trunk/drivers/scsi/scsi_lib.c
index 67f412bb4974..d545ad1cf47a 100644
--- a/trunk/drivers/scsi/scsi_lib.c
+++ b/trunk/drivers/scsi/scsi_lib.c
@@ -536,6 +536,9 @@ static void scsi_run_queue(struct request_queue *q)
 	       !shost->host_blocked && !shost->host_self_blocked &&
 		!((shost->can_queue > 0) &&
 		  (shost->host_busy >= shost->can_queue))) {
+
+		int flagset;
+
 		/*
 		 * As long as shost is accepting commands and we have
 		 * starved queues, call blk_run_queue. scsi_request_fn
@@ -549,19 +552,20 @@ static void scsi_run_queue(struct request_queue *q)
 		sdev = list_entry(shost->starved_list.next,
 					  struct scsi_device, starved_entry);
 		list_del_init(&sdev->starved_entry);
-		spin_unlock_irqrestore(shost->host_lock, flags);
-
+		spin_unlock(shost->host_lock);
+
+		spin_lock(sdev->request_queue->queue_lock);
+		flagset = test_bit(QUEUE_FLAG_REENTER, &q->queue_flags) &&
+				!test_bit(QUEUE_FLAG_REENTER,
+					&sdev->request_queue->queue_flags);
+		if (flagset)
+			queue_flag_set(QUEUE_FLAG_REENTER, sdev->request_queue);
+		__blk_run_queue(sdev->request_queue);
+		if (flagset)
+			queue_flag_clear(QUEUE_FLAG_REENTER, sdev->request_queue);
+		spin_unlock(sdev->request_queue->queue_lock);
 
-		if (test_bit(QUEUE_FLAG_REENTER, &q->queue_flags) &&
-		    !test_and_set_bit(QUEUE_FLAG_REENTER,
-				      &sdev->request_queue->queue_flags)) {
-			blk_run_queue(sdev->request_queue);
-			clear_bit(QUEUE_FLAG_REENTER,
-				  &sdev->request_queue->queue_flags);
-		} else
-			blk_run_queue(sdev->request_queue);
-
-		spin_lock_irqsave(shost->host_lock, flags);
+		spin_lock(shost->host_lock);
 		if (unlikely(!list_empty(&sdev->starved_entry)))
 			/*
 			 * sdev lost a race, and was put back on the
@@ -1585,8 +1589,9 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost,
 
 	blk_queue_max_segment_size(q, dma_get_max_seg_size(dev));
 
+	/* New queue, no concurrency on queue_flags */
 	if (!shost->use_clustering)
-		clear_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
+		queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q);
 
 	/*
 	 * set a reasonable default alignment on word boundaries: the
diff --git a/trunk/drivers/scsi/scsi_priv.h b/trunk/drivers/scsi/scsi_priv.h
index 3f34e9376b0a..b33e72516ef8 100644
--- a/trunk/drivers/scsi/scsi_priv.h
+++ b/trunk/drivers/scsi/scsi_priv.h
@@ -121,6 +121,7 @@ extern struct scsi_transport_template blank_transport_template;
 extern void __scsi_remove_device(struct scsi_device *);
 
 extern struct bus_type scsi_bus_type;
+extern struct attribute_group *scsi_sysfs_shost_attr_groups[];
 
 /* scsi_netlink.c */
 #ifdef CONFIG_SCSI_NETLINK
diff --git a/trunk/drivers/scsi/scsi_proc.c b/trunk/drivers/scsi/scsi_proc.c
index ed395154a5b1..e4a0d2f9b357 100644
--- a/trunk/drivers/scsi/scsi_proc.c
+++ b/trunk/drivers/scsi/scsi_proc.c
@@ -190,10 +190,14 @@ void scsi_proc_host_rm(struct Scsi_Host *shost)
  */
 static int proc_print_scsidevice(struct device *dev, void *data)
 {
-	struct scsi_device *sdev = to_scsi_device(dev);
+	struct scsi_device *sdev;
 	struct seq_file *s = data;
 	int i;
 
+	if (!scsi_is_sdev_device(dev))
+		goto out;
+
+	sdev = to_scsi_device(dev);
 	seq_printf(s,
 		"Host: scsi%d Channel: %02d Id: %02d Lun: %02d\n  Vendor: ",
 		sdev->host->host_no, sdev->channel, sdev->id, sdev->lun);
@@ -230,6 +234,7 @@ static int proc_print_scsidevice(struct device *dev, void *data)
 	else
 		seq_printf(s, "\n");
 
+out:
 	return 0;
 }
 
@@ -408,6 +413,7 @@ static int proc_scsi_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations proc_scsi_operations = {
+	.owner		= THIS_MODULE,
 	.open		= proc_scsi_open,
 	.read		= seq_read,
 	.write		= proc_scsi_write,
@@ -426,10 +432,9 @@ int __init scsi_init_procfs(void)
 	if (!proc_scsi)
 		goto err1;
 
-	pde = create_proc_entry("scsi/scsi", 0, NULL);
+	pde = proc_create("scsi/scsi", 0, NULL, &proc_scsi_operations);
 	if (!pde)
 		goto err2;
-	pde->proc_fops = &proc_scsi_operations;
 
 	return 0;
 
diff --git a/trunk/drivers/scsi/scsi_scan.c b/trunk/drivers/scsi/scsi_scan.c
index e67c14e31bab..a00eee6f7be9 100644
--- a/trunk/drivers/scsi/scsi_scan.c
+++ b/trunk/drivers/scsi/scsi_scan.c
@@ -322,6 +322,21 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	return NULL;
 }
 
+static void scsi_target_destroy(struct scsi_target *starget)
+{
+	struct device *dev = &starget->dev;
+	struct Scsi_Host *shost = dev_to_shost(dev->parent);
+	unsigned long flags;
+
+	transport_destroy_device(dev);
+	spin_lock_irqsave(shost->host_lock, flags);
+	if (shost->hostt->target_destroy)
+		shost->hostt->target_destroy(starget);
+	list_del_init(&starget->siblings);
+	spin_unlock_irqrestore(shost->host_lock, flags);
+	put_device(dev);
+}
+
 static void scsi_target_dev_release(struct device *dev)
 {
 	struct device *parent = dev->parent;
@@ -331,9 +346,14 @@ static void scsi_target_dev_release(struct device *dev)
 	put_device(parent);
 }
 
+struct device_type scsi_target_type = {
+	.name =		"scsi_target",
+	.release =	scsi_target_dev_release,
+};
+
 int scsi_is_target_device(const struct device *dev)
 {
-	return dev->release == scsi_target_dev_release;
+	return dev->type == &scsi_target_type;
 }
 EXPORT_SYMBOL(scsi_is_target_device);
 
@@ -391,14 +411,17 @@ static struct scsi_target *scsi_alloc_target(struct device *parent,
 	device_initialize(dev);
 	starget->reap_ref = 1;
 	dev->parent = get_device(parent);
-	dev->release = scsi_target_dev_release;
 	sprintf(dev->bus_id, "target%d:%d:%d",
 		shost->host_no, channel, id);
+#ifndef CONFIG_SYSFS_DEPRECATED
+	dev->bus = &scsi_bus_type;
+#endif
+	dev->type = &scsi_target_type;
 	starget->id = id;
 	starget->channel = channel;
 	INIT_LIST_HEAD(&starget->siblings);
 	INIT_LIST_HEAD(&starget->devices);
-	starget->state = STARGET_RUNNING;
+	starget->state = STARGET_CREATED;
 	starget->scsi_level = SCSI_2;
  retry:
 	spin_lock_irqsave(shost->host_lock, flags);
@@ -411,18 +434,6 @@ static struct scsi_target *scsi_alloc_target(struct device *parent,
 	spin_unlock_irqrestore(shost->host_lock, flags);
 	/* allocate and add */
 	transport_setup_device(dev);
-	error = device_add(dev);
-	if (error) {
-		dev_err(dev, "target device_add failed, error %d\n", error);
-		spin_lock_irqsave(shost->host_lock, flags);
-		list_del_init(&starget->siblings);
-		spin_unlock_irqrestore(shost->host_lock, flags);
-		transport_destroy_device(dev);
-		put_device(parent);
-		kfree(starget);
-		return NULL;
-	}
-	transport_add_device(dev);
 	if (shost->hostt->target_alloc) {
 		error = shost->hostt->target_alloc(starget);
 
@@ -430,9 +441,7 @@ static struct scsi_target *scsi_alloc_target(struct device *parent,
 			dev_printk(KERN_ERR, dev, "target allocation failed, error %d\n", error);
 			/* don't want scsi_target_reap to do the final
 			 * put because it will be under the host lock */
-			get_device(dev);
-			scsi_target_reap(starget);
-			put_device(dev);
+			scsi_target_destroy(starget);
 			return NULL;
 		}
 	}
@@ -459,18 +468,10 @@ static void scsi_target_reap_usercontext(struct work_struct *work)
 {
 	struct scsi_target *starget =
 		container_of(work, struct scsi_target, ew.work);
-	struct Scsi_Host *shost = dev_to_shost(starget->dev.parent);
-	unsigned long flags;
 
 	transport_remove_device(&starget->dev);
 	device_del(&starget->dev);
-	transport_destroy_device(&starget->dev);
-	spin_lock_irqsave(shost->host_lock, flags);
-	if (shost->hostt->target_destroy)
-		shost->hostt->target_destroy(starget);
-	list_del_init(&starget->siblings);
-	spin_unlock_irqrestore(shost->host_lock, flags);
-	put_device(&starget->dev);
+	scsi_target_destroy(starget);
 }
 
 /**
@@ -485,21 +486,25 @@ void scsi_target_reap(struct scsi_target *starget)
 {
 	struct Scsi_Host *shost = dev_to_shost(starget->dev.parent);
 	unsigned long flags;
+	enum scsi_target_state state;
+	int empty;
 
 	spin_lock_irqsave(shost->host_lock, flags);
+	state = starget->state;
+	empty = --starget->reap_ref == 0 &&
+		list_empty(&starget->devices) ? 1 : 0;
+	spin_unlock_irqrestore(shost->host_lock, flags);
 
-	if (--starget->reap_ref == 0 && list_empty(&starget->devices)) {
-		BUG_ON(starget->state == STARGET_DEL);
-		starget->state = STARGET_DEL;
-		spin_unlock_irqrestore(shost->host_lock, flags);
-		execute_in_process_context(scsi_target_reap_usercontext,
-					   &starget->ew);
+	if (!empty)
 		return;
 
-	}
-	spin_unlock_irqrestore(shost->host_lock, flags);
-
-	return;
+	BUG_ON(state == STARGET_DEL);
+	starget->state = STARGET_DEL;
+	if (state == STARGET_CREATED)
+		scsi_target_destroy(starget);
+	else
+		execute_in_process_context(scsi_target_reap_usercontext,
+					   &starget->ew);
 }
 
 /**
@@ -1048,8 +1053,9 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget,
 					scsi_inq_str(vend, result, 8, 16),
 					scsi_inq_str(mod, result, 16, 32));
 			});
+
 		}
-		
+
 		res = SCSI_SCAN_TARGET_PRESENT;
 		goto out_free_result;
 	}
@@ -1489,7 +1495,6 @@ struct scsi_device *__scsi_add_device(struct Scsi_Host *shost, uint channel,
 	if (scsi_host_scan_allowed(shost))
 		scsi_probe_and_add_lun(starget, lun, NULL, &sdev, 1, hostdata);
 	mutex_unlock(&shost->scan_mutex);
-	transport_configure_device(&starget->dev);
 	scsi_target_reap(starget);
 	put_device(&starget->dev);
 
@@ -1570,7 +1575,6 @@ static void __scsi_scan_target(struct device *parent, unsigned int channel,
  out_reap:
 	/* now determine if the target has any children at all
 	 * and if not, nuke it */
-	transport_configure_device(&starget->dev);
 	scsi_target_reap(starget);
 
 	put_device(&starget->dev);
@@ -1824,7 +1828,7 @@ void scsi_scan_host(struct Scsi_Host *shost)
 	}
 
 	p = kthread_run(do_scan_async, data, "scsi_scan_%d", shost->host_no);
-	if (unlikely(IS_ERR(p)))
+	if (IS_ERR(p))
 		do_scan_async(data);
 }
 EXPORT_SYMBOL(scsi_scan_host);
diff --git a/trunk/drivers/scsi/scsi_sysfs.c b/trunk/drivers/scsi/scsi_sysfs.c
index 67bb20ed45d2..049103f1d16f 100644
--- a/trunk/drivers/scsi/scsi_sysfs.c
+++ b/trunk/drivers/scsi/scsi_sysfs.c
@@ -21,6 +21,8 @@
 #include "scsi_priv.h"
 #include "scsi_logging.h"
 
+static struct device_type scsi_dev_type;
+
 static const struct {
 	enum scsi_device_state	value;
 	char			*name;
@@ -249,18 +251,27 @@ shost_rd_attr(sg_tablesize, "%hu\n");
 shost_rd_attr(unchecked_isa_dma, "%d\n");
 shost_rd_attr2(proc_name, hostt->proc_name, "%s\n");
 
-static struct device_attribute *scsi_sysfs_shost_attrs[] = {
-	&dev_attr_unique_id,
-	&dev_attr_host_busy,
-	&dev_attr_cmd_per_lun,
-	&dev_attr_can_queue,
-	&dev_attr_sg_tablesize,
-	&dev_attr_unchecked_isa_dma,
-	&dev_attr_proc_name,
-	&dev_attr_scan,
-	&dev_attr_hstate,
-	&dev_attr_supported_mode,
-	&dev_attr_active_mode,
+static struct attribute *scsi_sysfs_shost_attrs[] = {
+	&dev_attr_unique_id.attr,
+	&dev_attr_host_busy.attr,
+	&dev_attr_cmd_per_lun.attr,
+	&dev_attr_can_queue.attr,
+	&dev_attr_sg_tablesize.attr,
+	&dev_attr_unchecked_isa_dma.attr,
+	&dev_attr_proc_name.attr,
+	&dev_attr_scan.attr,
+	&dev_attr_hstate.attr,
+	&dev_attr_supported_mode.attr,
+	&dev_attr_active_mode.attr,
+	NULL
+};
+
+struct attribute_group scsi_shost_attr_group = {
+	.attrs =	scsi_sysfs_shost_attrs,
+};
+
+struct attribute_group *scsi_sysfs_shost_attr_groups[] = {
+	&scsi_shost_attr_group,
 	NULL
 };
 
@@ -335,7 +346,12 @@ static struct class sdev_class = {
 /* all probing is done in the individual ->probe routines */
 static int scsi_bus_match(struct device *dev, struct device_driver *gendrv)
 {
-	struct scsi_device *sdp = to_scsi_device(dev);
+	struct scsi_device *sdp;
+
+	if (dev->type != &scsi_dev_type)
+		return 0;
+
+	sdp = to_scsi_device(dev);
 	if (sdp->no_uld_attach)
 		return 0;
 	return (sdp->inq_periph_qual == SCSI_INQ_PQ_CON)? 1: 0;
@@ -351,10 +367,16 @@ static int scsi_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
 
 static int scsi_bus_suspend(struct device * dev, pm_message_t state)
 {
-	struct device_driver *drv = dev->driver;
-	struct scsi_device *sdev = to_scsi_device(dev);
+	struct device_driver *drv;
+	struct scsi_device *sdev;
 	int err;
 
+	if (dev->type != &scsi_dev_type)
+		return 0;
+
+	drv = dev->driver;
+	sdev = to_scsi_device(dev);
+
 	err = scsi_device_quiesce(sdev);
 	if (err)
 		return err;
@@ -370,10 +392,16 @@ static int scsi_bus_suspend(struct device * dev, pm_message_t state)
 
 static int scsi_bus_resume(struct device * dev)
 {
-	struct device_driver *drv = dev->driver;
-	struct scsi_device *sdev = to_scsi_device(dev);
+	struct device_driver *drv;
+	struct scsi_device *sdev;
 	int err = 0;
 
+	if (dev->type != &scsi_dev_type)
+		return 0;
+
+	drv = dev->driver;
+	sdev = to_scsi_device(dev);
+
 	if (drv && drv->resume)
 		err = drv->resume(dev);
 
@@ -781,6 +809,27 @@ sdev_store_queue_type_rw(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
+static int scsi_target_add(struct scsi_target *starget)
+{
+	int error;
+
+	if (starget->state != STARGET_CREATED)
+		return 0;
+
+	error = device_add(&starget->dev);
+	if (error) {
+		dev_err(&starget->dev, "target device_add failed, error %d\n", error);
+		get_device(&starget->dev);
+		scsi_target_reap(starget);
+		put_device(&starget->dev);
+		return error;
+	}
+	transport_add_device(&starget->dev);
+	starget->state = STARGET_RUNNING;
+
+	return 0;
+}
+
 static struct device_attribute sdev_attr_queue_type_rw =
 	__ATTR(queue_type, S_IRUGO | S_IWUSR, show_queue_type_field,
 	       sdev_store_queue_type_rw);
@@ -796,10 +845,16 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev)
 {
 	int error, i;
 	struct request_queue *rq = sdev->request_queue;
+	struct scsi_target *starget = sdev->sdev_target;
 
 	if ((error = scsi_device_set_state(sdev, SDEV_RUNNING)) != 0)
 		return error;
 
+	error = scsi_target_add(starget);
+	if (error)
+		return error;
+
+	transport_configure_device(&starget->dev);
 	error = device_add(&sdev->sdev_gendev);
 	if (error) {
 		put_device(sdev->sdev_gendev.parent);
@@ -834,7 +889,7 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev)
 		goto out;
 	}
 
-	error = bsg_register_queue(rq, &sdev->sdev_gendev, NULL);
+	error = bsg_register_queue(rq, &sdev->sdev_gendev, NULL, NULL);
 
 	if (error)
 		sdev_printk(KERN_INFO, sdev,
@@ -971,44 +1026,6 @@ int scsi_register_interface(struct class_interface *intf)
 }
 EXPORT_SYMBOL(scsi_register_interface);
 
-
-static struct device_attribute *class_attr_overridden(
-		struct device_attribute **attrs,
-		struct device_attribute *attr)
-{
-	int i;
-
-	if (!attrs)
-		return NULL;
-	for (i = 0; attrs[i]; i++)
-		if (!strcmp(attrs[i]->attr.name, attr->attr.name))
-			return attrs[i];
-	return NULL;
-}
-
-static int class_attr_add(struct device *classdev,
-		struct device_attribute *attr)
-{
-	struct device_attribute *base_attr;
-
-	/*
-	 * Spare the caller from having to copy things it's not interested in.
-	 */
-	base_attr = class_attr_overridden(scsi_sysfs_shost_attrs, attr);
-	if (base_attr) {
-		/* extend permissions */
-		attr->attr.mode |= base_attr->attr.mode;
-
-		/* override null show/store with default */
-		if (!attr->show)
-			attr->show = base_attr->show;
-		if (!attr->store)
-			attr->store = base_attr->store;
-	}
-
-	return device_create_file(classdev, attr);
-}
-
 /**
  * scsi_sysfs_add_host - add scsi host to subsystem
  * @shost:     scsi host struct to add to subsystem
@@ -1018,20 +1035,11 @@ int scsi_sysfs_add_host(struct Scsi_Host *shost)
 {
 	int error, i;
 
+	/* add host specific attributes */
 	if (shost->hostt->shost_attrs) {
 		for (i = 0; shost->hostt->shost_attrs[i]; i++) {
-			error = class_attr_add(&shost->shost_dev,
-					shost->hostt->shost_attrs[i]);
-			if (error)
-				return error;
-		}
-	}
-
-	for (i = 0; scsi_sysfs_shost_attrs[i]; i++) {
-		if (!class_attr_overridden(shost->hostt->shost_attrs,
-					scsi_sysfs_shost_attrs[i])) {
 			error = device_create_file(&shost->shost_dev,
-					scsi_sysfs_shost_attrs[i]);
+					shost->hostt->shost_attrs[i]);
 			if (error)
 				return error;
 		}
diff --git a/trunk/drivers/scsi/scsi_transport_fc.c b/trunk/drivers/scsi/scsi_transport_fc.c
index 6b092a6c295d..5fd64e70029d 100644
--- a/trunk/drivers/scsi/scsi_transport_fc.c
+++ b/trunk/drivers/scsi/scsi_transport_fc.c
@@ -1961,12 +1961,17 @@ fc_timed_out(struct scsi_cmnd *scmd)
 }
 
 /*
- * Must be called with shost->host_lock held
+ * Called by fc_user_scan to locate an rport on the shost that
+ * matches the channel and target id, and invoke scsi_scan_target()
+ * on the rport.
  */
-static int fc_user_scan(struct Scsi_Host *shost, uint channel,
-		uint id, uint lun)
+static void
+fc_user_scan_tgt(struct Scsi_Host *shost, uint channel, uint id, uint lun)
 {
 	struct fc_rport *rport;
+	unsigned long flags;
+
+	spin_lock_irqsave(shost->host_lock, flags);
 
 	list_for_each_entry(rport, &fc_host_rports(shost), peers) {
 		if (rport->scsi_target_id == -1)
@@ -1975,13 +1980,54 @@ static int fc_user_scan(struct Scsi_Host *shost, uint channel,
 		if (rport->port_state != FC_PORTSTATE_ONLINE)
 			continue;
 
-		if ((channel == SCAN_WILD_CARD || channel == rport->channel) &&
-		    (id == SCAN_WILD_CARD || id == rport->scsi_target_id)) {
-			scsi_scan_target(&rport->dev, rport->channel,
-					 rport->scsi_target_id, lun, 1);
+		if ((channel == rport->channel) &&
+		    (id == rport->scsi_target_id)) {
+			spin_unlock_irqrestore(shost->host_lock, flags);
+			scsi_scan_target(&rport->dev, channel, id, lun, 1);
+			return;
 		}
 	}
 
+	spin_unlock_irqrestore(shost->host_lock, flags);
+}
+
+/*
+ * Called via sysfs scan routines. Necessary, as the FC transport
+ * wants to place all target objects below the rport object. So this
+ * routine must invoke the scsi_scan_target() routine with the rport
+ * object as the parent.
+ */
+static int
+fc_user_scan(struct Scsi_Host *shost, uint channel, uint id, uint lun)
+{
+	uint chlo, chhi;
+	uint tgtlo, tgthi;
+
+	if (((channel != SCAN_WILD_CARD) && (channel > shost->max_channel)) ||
+	    ((id != SCAN_WILD_CARD) && (id >= shost->max_id)) ||
+	    ((lun != SCAN_WILD_CARD) && (lun > shost->max_lun)))
+		return -EINVAL;
+
+	if (channel == SCAN_WILD_CARD) {
+		chlo = 0;
+		chhi = shost->max_channel + 1;
+	} else {
+		chlo = channel;
+		chhi = channel + 1;
+	}
+
+	if (id == SCAN_WILD_CARD) {
+		tgtlo = 0;
+		tgthi = shost->max_id;
+	} else {
+		tgtlo = id;
+		tgthi = id + 1;
+	}
+
+	for ( ; chlo < chhi; chlo++)
+		for ( ; tgtlo < tgthi; tgtlo++)
+			fc_user_scan_tgt(shost, chlo, tgtlo, lun);
+
 	return 0;
 }
 
diff --git a/trunk/drivers/scsi/scsi_transport_sas.c b/trunk/drivers/scsi/scsi_transport_sas.c
index 27ec625ab771..f4461d35ffb9 100644
--- a/trunk/drivers/scsi/scsi_transport_sas.c
+++ b/trunk/drivers/scsi/scsi_transport_sas.c
@@ -192,6 +192,16 @@ static void sas_non_host_smp_request(struct request_queue *q)
 	sas_smp_request(q, rphy_to_shost(rphy), rphy);
 }
 
+static void sas_host_release(struct device *dev)
+{
+	struct Scsi_Host *shost = dev_to_shost(dev);
+	struct sas_host_attrs *sas_host = to_sas_host_attrs(shost);
+	struct request_queue *q = sas_host->q;
+
+	if (q)
+		blk_cleanup_queue(q);
+}
+
 static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
 {
 	struct request_queue *q;
@@ -199,6 +209,7 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
 	struct device *dev;
 	char namebuf[BUS_ID_SIZE];
 	const char *name;
+	void (*release)(struct device *);
 
 	if (!to_sas_internal(shost->transportt)->f->smp_handler) {
 		printk("%s can't handle SMP requests\n", shost->hostt->name);
@@ -209,17 +220,19 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
 		q = blk_init_queue(sas_non_host_smp_request, NULL);
 		dev = &rphy->dev;
 		name = dev->bus_id;
+		release = NULL;
 	} else {
 		q = blk_init_queue(sas_host_smp_request, NULL);
 		dev = &shost->shost_gendev;
 		snprintf(namebuf, sizeof(namebuf),
 			 "sas_host%d", shost->host_no);
 		name = namebuf;
+		release = sas_host_release;
 	}
 	if (!q)
 		return -ENOMEM;
 
-	error = bsg_register_queue(q, dev, name);
+	error = bsg_register_queue(q, dev, name, release);
 	if (error) {
 		blk_cleanup_queue(q);
 		return -ENOMEM;
@@ -235,8 +248,7 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
 	else
 		q->queuedata = shost;
 
-	set_bit(QUEUE_FLAG_BIDI, &q->queue_flags);
-
+	queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q);
 	return 0;
 }
 
@@ -253,7 +265,6 @@ static void sas_bsg_remove(struct Scsi_Host *shost, struct sas_rphy *rphy)
 		return;
 
 	bsg_unregister_queue(q);
-	blk_cleanup_queue(q);
 }
 
 /*
@@ -1301,6 +1312,9 @@ static void sas_expander_release(struct device *dev)
 	struct sas_rphy *rphy = dev_to_rphy(dev);
 	struct sas_expander_device *edev = rphy_to_expander_device(rphy);
 
+	if (rphy->q)
+		blk_cleanup_queue(rphy->q);
+
 	put_device(dev->parent);
 	kfree(edev);
 }
@@ -1310,6 +1324,9 @@ static void sas_end_device_release(struct device *dev)
 	struct sas_rphy *rphy = dev_to_rphy(dev);
 	struct sas_end_device *edev = rphy_to_end_device(rphy);
 
+	if (rphy->q)
+		blk_cleanup_queue(rphy->q);
+
 	put_device(dev->parent);
 	kfree(edev);
 }
diff --git a/trunk/drivers/scsi/scsi_transport_spi.c b/trunk/drivers/scsi/scsi_transport_spi.c
index bc12b5d5d676..75a64a6cae8c 100644
--- a/trunk/drivers/scsi/scsi_transport_spi.c
+++ b/trunk/drivers/scsi/scsi_transport_spi.c
@@ -24,6 +24,7 @@
 #include <linux/workqueue.h>
 #include <linux/blkdev.h>
 #include <linux/mutex.h>
+#include <linux/sysfs.h>
 #include <scsi/scsi.h>
 #include "scsi_priv.h"
 #include <scsi/scsi_device.h>
@@ -1374,11 +1375,11 @@ static int spi_host_configure(struct transport_container *tc,
  * overloads the return by setting 1<<1 if the attribute should
  * be writeable */
 #define TARGET_ATTRIBUTE_HELPER(name) \
-	(si->f->show_##name ? 1 : 0) + \
-	(si->f->set_##name ? 2 : 0)
+	(si->f->show_##name ? S_IRUGO : 0) | \
+	(si->f->set_##name ? S_IWUSR : 0)
 
-static int target_attribute_is_visible(struct kobject *kobj,
-				       struct attribute *attr, int i)
+static mode_t target_attribute_is_visible(struct kobject *kobj,
+					  struct attribute *attr, int i)
 {
 	struct device *cdev = container_of(kobj, struct device, kobj);
 	struct scsi_target *starget = transport_class_to_starget(cdev);
@@ -1428,7 +1429,7 @@ static int target_attribute_is_visible(struct kobject *kobj,
 		 spi_support_ius(starget))
 		return TARGET_ATTRIBUTE_HELPER(hold_mcs);
 	else if (attr == &dev_attr_revalidate.attr)
-		return 1;
+		return S_IWUSR;
 
 	return 0;
 }
@@ -1462,25 +1463,9 @@ static int spi_target_configure(struct transport_container *tc,
 				struct device *cdev)
 {
 	struct kobject *kobj = &cdev->kobj;
-	int i;
-	struct attribute *attr;
-	int rc;
-
-	for (i = 0; (attr = target_attributes[i]) != NULL; i++) {
-		int j = target_attribute_group.is_visible(kobj, attr, i);
-
-		/* FIXME: as well as returning -EEXIST, which we'd like
-		 * to ignore, sysfs also does a WARN_ON and dumps a trace,
-		 * which is bad, so temporarily, skip attributes that are
-		 * already visible (the revalidate one) */
-		if (j && attr != &dev_attr_revalidate.attr)
-			rc = sysfs_add_file_to_group(kobj, attr,
-						target_attribute_group.name);
-		/* and make the attribute writeable if we have a set
-		 * function */
-		if ((j & 1))
-			rc = sysfs_chmod_file(kobj, attr, attr->mode | S_IWUSR);
-	}
+
+	/* force an update based on parameters read from the device */
+	sysfs_update_group(kobj, &target_attribute_group);
 
 	return 0;
 }
diff --git a/trunk/drivers/scsi/sd.c b/trunk/drivers/scsi/sd.c
index 3cea17dd5dba..01cefbb2d539 100644
--- a/trunk/drivers/scsi/sd.c
+++ b/trunk/drivers/scsi/sd.c
@@ -860,7 +860,6 @@ static int sd_sync_cache(struct scsi_disk *sdkp)
 
 static void sd_prepare_flush(struct request_queue *q, struct request *rq)
 {
-	memset(rq->cmd, 0, sizeof(rq->cmd));
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 	rq->timeout = SD_TIMEOUT;
 	rq->cmd[0] = SYNCHRONIZE_CACHE;
diff --git a/trunk/drivers/scsi/sg.c b/trunk/drivers/scsi/sg.c
index 2029422bc04d..c9d7f721b9e2 100644
--- a/trunk/drivers/scsi/sg.c
+++ b/trunk/drivers/scsi/sg.c
@@ -2667,7 +2667,6 @@ sg_proc_init(void)
 {
 	int k, mask;
 	int num_leaves = ARRAY_SIZE(sg_proc_leaf_arr);
-	struct proc_dir_entry *pdep;
 	struct sg_proc_leaf * leaf;
 
 	sg_proc_sgp = proc_mkdir(sg_proc_sg_dirname, NULL);
@@ -2676,13 +2675,10 @@ sg_proc_init(void)
 	for (k = 0; k < num_leaves; ++k) {
 		leaf = &sg_proc_leaf_arr[k];
 		mask = leaf->fops->write ? S_IRUGO | S_IWUSR : S_IRUGO;
-		pdep = create_proc_entry(leaf->name, mask, sg_proc_sgp);
-		if (pdep) {
-			leaf->fops->owner = THIS_MODULE,
-			leaf->fops->read = seq_read,
-			leaf->fops->llseek = seq_lseek,
-			pdep->proc_fops = leaf->fops;
-		}
+		leaf->fops->owner = THIS_MODULE;
+		leaf->fops->read = seq_read;
+		leaf->fops->llseek = seq_lseek;
+		proc_create(leaf->name, mask, sg_proc_sgp, leaf->fops);
 	}
 	return 0;
 }
diff --git a/trunk/drivers/scsi/sgiwd93.c b/trunk/drivers/scsi/sgiwd93.c
index 03e359670506..31fe6051c799 100644
--- a/trunk/drivers/scsi/sgiwd93.c
+++ b/trunk/drivers/scsi/sgiwd93.c
@@ -313,7 +313,8 @@ static struct platform_driver sgiwd93_driver = {
 	.probe  = sgiwd93_probe,
 	.remove = __devexit_p(sgiwd93_remove),
 	.driver = {
-		.name   = "sgiwd93"
+		.name   = "sgiwd93",
+		.owner	= THIS_MODULE,
 	}
 };
 
@@ -333,3 +334,4 @@ module_exit(sgiwd93_module_exit);
 MODULE_DESCRIPTION("SGI WD33C93 driver");
 MODULE_AUTHOR("Ralf Baechle <ralf@linux-mips.org>");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:sgiwd93");
diff --git a/trunk/drivers/scsi/sni_53c710.c b/trunk/drivers/scsi/sni_53c710.c
index 0a6b45b1b003..2bbef4c45a0d 100644
--- a/trunk/drivers/scsi/sni_53c710.c
+++ b/trunk/drivers/scsi/sni_53c710.c
@@ -53,6 +53,7 @@
 MODULE_AUTHOR("Thomas Bogendörfer");
 MODULE_DESCRIPTION("SNI RM 53c710 SCSI Driver");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:snirm_53c710");
 
 #define SNIRM710_CLOCK	32
 
@@ -136,6 +137,7 @@ static struct platform_driver snirm710_driver = {
 	.remove	= __devexit_p(snirm710_driver_remove),
 	.driver	= {
 		.name	= "snirm_53c710",
+		.owner	= THIS_MODULE,
 	},
 };
 
diff --git a/trunk/drivers/scsi/st.c b/trunk/drivers/scsi/st.c
index a860c3a9ae99..e8db66ad0bde 100644
--- a/trunk/drivers/scsi/st.c
+++ b/trunk/drivers/scsi/st.c
@@ -4322,7 +4322,7 @@ static void do_remove_sysfs_files(void)
 static ssize_t
 st_defined_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	struct st_modedef *STm = (struct st_modedef *)dev_get_drvdata(dev);
+	struct st_modedef *STm = dev_get_drvdata(dev);
 	ssize_t l = 0;
 
 	l = snprintf(buf, PAGE_SIZE, "%d\n", STm->defined);
@@ -4334,7 +4334,7 @@ DEVICE_ATTR(defined, S_IRUGO, st_defined_show, NULL);
 static ssize_t
 st_defblk_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	struct st_modedef *STm = (struct st_modedef *)dev_get_drvdata(dev);
+	struct st_modedef *STm = dev_get_drvdata(dev);
 	ssize_t l = 0;
 
 	l = snprintf(buf, PAGE_SIZE, "%d\n", STm->default_blksize);
@@ -4346,7 +4346,7 @@ DEVICE_ATTR(default_blksize, S_IRUGO, st_defblk_show, NULL);
 static ssize_t
 st_defdensity_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	struct st_modedef *STm = (struct st_modedef *)dev_get_drvdata(dev);
+	struct st_modedef *STm = dev_get_drvdata(dev);
 	ssize_t l = 0;
 	char *fmt;
 
@@ -4361,7 +4361,7 @@ static ssize_t
 st_defcompression_show(struct device *dev, struct device_attribute *attr,
 		       char *buf)
 {
-	struct st_modedef *STm = (struct st_modedef *)dev_get_drvdata(dev);
+	struct st_modedef *STm = dev_get_drvdata(dev);
 	ssize_t l = 0;
 
 	l = snprintf(buf, PAGE_SIZE, "%d\n", STm->default_compression - 1);
@@ -4373,7 +4373,7 @@ DEVICE_ATTR(default_compression, S_IRUGO, st_defcompression_show, NULL);
 static ssize_t
 st_options_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	struct st_modedef *STm = (struct st_modedef *)dev_get_drvdata(dev);
+	struct st_modedef *STm = dev_get_drvdata(dev);
 	struct scsi_tape *STp;
 	int i, j, options;
 	ssize_t l = 0;
diff --git a/trunk/drivers/scsi/sun3x_esp.c b/trunk/drivers/scsi/sun3x_esp.c
index 06152c7fa689..7514b3a0390e 100644
--- a/trunk/drivers/scsi/sun3x_esp.c
+++ b/trunk/drivers/scsi/sun3x_esp.c
@@ -294,6 +294,7 @@ static struct platform_driver esp_sun3x_driver = {
 	.remove         = __devexit_p(esp_sun3x_remove),
 	.driver = {
 		.name   = "sun3x_esp",
+		.owner	= THIS_MODULE,
 	},
 };
 
@@ -314,3 +315,4 @@ MODULE_VERSION(DRV_VERSION);
 
 module_init(sun3x_esp_init);
 module_exit(sun3x_esp_exit);
+MODULE_ALIAS("platform:sun3x_esp");
diff --git a/trunk/drivers/scsi/sym53c8xx_2/sym_hipd.c b/trunk/drivers/scsi/sym53c8xx_2/sym_hipd.c
index 35142b5341b5..22a6aae78699 100644
--- a/trunk/drivers/scsi/sym53c8xx_2/sym_hipd.c
+++ b/trunk/drivers/scsi/sym53c8xx_2/sym_hipd.c
@@ -1647,7 +1647,7 @@ static void sym_flush_comp_queue(struct sym_hcb *np, int cam_status)
 	SYM_QUEHEAD *qp;
 	struct sym_ccb *cp;
 
-	while ((qp = sym_remque_head(&np->comp_ccbq)) != 0) {
+	while ((qp = sym_remque_head(&np->comp_ccbq)) != NULL) {
 		struct scsi_cmnd *cmd;
 		cp = sym_que_entry(qp, struct sym_ccb, link_ccbq);
 		sym_insque_tail(&cp->link_ccbq, &np->busy_ccbq);
@@ -3168,7 +3168,7 @@ int sym_clear_tasks(struct sym_hcb *np, int cam_status, int target, int lun, int
 	 *  the COMP queue and put back other ones into 
 	 *  the BUSY queue.
 	 */
-	while ((qp = sym_remque_head(&qtmp)) != 0) {
+	while ((qp = sym_remque_head(&qtmp)) != NULL) {
 		struct scsi_cmnd *cmd;
 		cp = sym_que_entry(qp, struct sym_ccb, link_ccbq);
 		cmd = cp->cmd;
@@ -5729,7 +5729,7 @@ void sym_hcb_free(struct sym_hcb *np)
 		sym_mfree_dma(np->dqueue, sizeof(u32)*(MAX_QUEUE*2), "DQUEUE");
 
 	if (np->actccbs) {
-		while ((qp = sym_remque_head(&np->free_ccbq)) != 0) {
+		while ((qp = sym_remque_head(&np->free_ccbq)) != NULL) {
 			cp = sym_que_entry(qp, struct sym_ccb, link_ccbq);
 			sym_mfree_dma(cp, sizeof(*cp), "CCB");
 		}
diff --git a/trunk/drivers/scsi/u14-34f.c b/trunk/drivers/scsi/u14-34f.c
index 58d7eee4fe81..640333b1e75c 100644
--- a/trunk/drivers/scsi/u14-34f.c
+++ b/trunk/drivers/scsi/u14-34f.c
@@ -1715,13 +1715,12 @@ static void flush_dev(struct scsi_device *dev, unsigned long cursec, unsigned in
 
 }
 
-static irqreturn_t ihdlr(int irq, unsigned int j) {
+static irqreturn_t ihdlr(unsigned int j)
+{
    struct scsi_cmnd *SCpnt;
    unsigned int i, k, c, status, tstatus, reg, ret;
    struct mscp *spp, *cpp;
-
-   if (sh[j]->irq != irq)
-       panic("%s: ihdlr, irq %d, sh[j]->irq %d.\n", BN(j), irq, sh[j]->irq);
+   int irq = sh[j]->irq;
 
    /* Check if this board need to be serviced */
    if (!((reg = inb(sh[j]->io_port + REG_SYS_INTR)) & IRQ_ASSERTED)) goto none;
@@ -1935,7 +1934,7 @@ static irqreturn_t do_interrupt_handler(int irq, void *shap) {
    if ((j = (unsigned int)((char *)shap - sha)) >= num_boards) return IRQ_NONE;
 
    spin_lock_irqsave(sh[j]->host_lock, spin_flags);
-   ret = ihdlr(irq, j);
+   ret = ihdlr(j);
    spin_unlock_irqrestore(sh[j]->host_lock, spin_flags);
    return ret;
 }
diff --git a/trunk/drivers/scsi/ultrastor.c b/trunk/drivers/scsi/ultrastor.c
index f385dce8dfbe..27aa40f3980e 100644
--- a/trunk/drivers/scsi/ultrastor.c
+++ b/trunk/drivers/scsi/ultrastor.c
@@ -951,7 +951,7 @@ static int ultrastor_abort(struct scsi_cmnd *SCpnt)
 	printk("abort: command mismatch, %p != %p\n",
 	       config.mscp[mscp_index].SCint, SCpnt);
 #endif
-    if (config.mscp[mscp_index].SCint == 0)
+    if (config.mscp[mscp_index].SCint == NULL)
 	return FAILED;
 
     if (config.mscp[mscp_index].SCint != SCpnt) panic("Bad abort");
@@ -1101,7 +1101,7 @@ static void ultrastor_interrupt(void *dev_id)
     SCtmp = mscp->SCint;
     mscp->SCint = NULL;
 
-    if (SCtmp == 0)
+    if (!SCtmp)
       {
 #if ULTRASTOR_DEBUG & (UD_ABORT|UD_INTERRUPT)
 	printk("MSCP %d (%x): no command\n", mscp_index, (unsigned int) mscp);
diff --git a/trunk/drivers/serial/68360serial.c b/trunk/drivers/serial/68360serial.c
index 2aa6bfe8fdb3..f59463601874 100644
--- a/trunk/drivers/serial/68360serial.c
+++ b/trunk/drivers/serial/68360serial.c
@@ -51,6 +51,7 @@ extern int  kgdb_output_string (const char* s, unsigned int count);
 
 /* #ifdef CONFIG_SERIAL_CONSOLE */ /* This seems to be a post 2.0 thing - mles */
 #include <linux/console.h>
+#include <linux/jiffies.h>
 
 /* this defines the index into rs_table for the port to use
  */
@@ -1729,7 +1730,7 @@ static void rs_360_wait_until_sent(struct tty_struct *tty, int timeout)
 		msleep_interruptible(jiffies_to_msecs(char_time));
 		if (signal_pending(current))
 			break;
-		if (timeout && ((orig_jiffies + timeout) < jiffies))
+		if (timeout && (time_after(jiffies, orig_jiffies + timeout)))
 			break;
 		/* The 'tx_cur' is really the next buffer to send.  We
 		 * have to back up to the previous BD and wait for it
diff --git a/trunk/drivers/serial/8250.c b/trunk/drivers/serial/8250.c
index 96a585e1cee8..ea41f2626458 100644
--- a/trunk/drivers/serial/8250.c
+++ b/trunk/drivers/serial/8250.c
@@ -1868,6 +1868,7 @@ static int serial8250_startup(struct uart_port *port)
 	}
 
 	if (is_real_interrupt(up->port.irq)) {
+		unsigned char iir1;
 		/*
 		 * Test for UARTs that do not reassert THRE when the
 		 * transmitter is idle and the interrupt has already
@@ -1881,7 +1882,7 @@ static int serial8250_startup(struct uart_port *port)
 		wait_for_xmitr(up, UART_LSR_THRE);
 		serial_out_sync(up, UART_IER, UART_IER_THRI);
 		udelay(1); /* allow THRE to set */
-		serial_in(up, UART_IIR);
+		iir1 = serial_in(up, UART_IIR);
 		serial_out(up, UART_IER, 0);
 		serial_out_sync(up, UART_IER, UART_IER_THRI);
 		udelay(1); /* allow a working UART time to re-assert THRE */
@@ -1894,7 +1895,7 @@ static int serial8250_startup(struct uart_port *port)
 		 * If the interrupt is not reasserted, setup a timer to
 		 * kick the UART on a regular basis.
 		 */
-		if (iir & UART_IIR_NO_INT) {
+		if (!(iir1 & UART_IIR_NO_INT) && (iir & UART_IIR_NO_INT)) {
 			pr_debug("ttyS%d - using backup timer\n", port->line);
 			up->timer.function = serial8250_backup_timeout;
 			up->timer.data = (unsigned long)up;
@@ -2228,7 +2229,9 @@ serial8250_set_termios(struct uart_port *port, struct ktermios *termios,
 	}
 	serial8250_set_mctrl(&up->port, up->port.mctrl);
 	spin_unlock_irqrestore(&up->port.lock, flags);
-	tty_termios_encode_baud_rate(termios, baud, baud);
+	/* Don't rewrite B0 */
+	if (tty_termios_baud_rate(termios))
+		tty_termios_encode_baud_rate(termios, baud, baud);
 }
 
 static void
diff --git a/trunk/drivers/serial/8250_au1x00.c b/trunk/drivers/serial/8250_au1x00.c
deleted file mode 100644
index 58015fd14be9..000000000000
--- a/trunk/drivers/serial/8250_au1x00.c
+++ /dev/null
@@ -1,100 +0,0 @@
-/*
- * Serial Device Initialisation for Au1x00
- *
- * (C) Copyright Embedded Alley Solutions, Inc 2005
- * Author: Pantelis Antoniou <pantelis@embeddedalley.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/module.h>
-#include <linux/serial_core.h>
-#include <linux/signal.h>
-#include <linux/slab.h>
-#include <linux/types.h>
-
-#include <linux/serial_8250.h>
-
-#include <asm/mach-au1x00/au1000.h>
-
-#include "8250.h"
-
-#define PORT(_base, _irq)				\
-	{						\
-		.iobase		= _base,		\
-		.membase	= (void __iomem *)_base,\
-		.mapbase	= CPHYSADDR(_base),	\
-		.irq		= _irq,			\
-		.uartclk	= 0,	/* filled */	\
-		.regshift	= 2,			\
-		.iotype		= UPIO_AU,		\
-		.flags		= UPF_SKIP_TEST 	\
-	}
-
-static struct plat_serial8250_port au1x00_data[] = {
-#if defined(CONFIG_SOC_AU1000)
-	PORT(UART0_ADDR, AU1000_UART0_INT),
-	PORT(UART1_ADDR, AU1000_UART1_INT),
-	PORT(UART2_ADDR, AU1000_UART2_INT),
-	PORT(UART3_ADDR, AU1000_UART3_INT),
-#elif defined(CONFIG_SOC_AU1500)
-	PORT(UART0_ADDR, AU1500_UART0_INT),
-	PORT(UART3_ADDR, AU1500_UART3_INT),
-#elif defined(CONFIG_SOC_AU1100)
-	PORT(UART0_ADDR, AU1100_UART0_INT),
-	PORT(UART1_ADDR, AU1100_UART1_INT),
-	/* The internal UART2 does not exist on the AU1100 processor. */
-	PORT(UART3_ADDR, AU1100_UART3_INT),
-#elif defined(CONFIG_SOC_AU1550)
-	PORT(UART0_ADDR, AU1550_UART0_INT),
-	PORT(UART1_ADDR, AU1550_UART1_INT),
-	PORT(UART3_ADDR, AU1550_UART3_INT),
-#elif defined(CONFIG_SOC_AU1200)
-	PORT(UART0_ADDR, AU1200_UART0_INT),
-	PORT(UART1_ADDR, AU1200_UART1_INT),
-#endif
-	{ },
-};
-
-static struct platform_device au1x00_device = {
-	.name			= "serial8250",
-	.id			= PLAT8250_DEV_AU1X00,
-	.dev			= {
-		.platform_data	= au1x00_data,
-	},
-};
-
-static int __init au1x00_init(void)
-{
-	int i;
-	unsigned int uartclk;
-
-	/* get uart clock */
-	uartclk = get_au1x00_uart_baud_base() * 16;
-
-	/* fill up uartclk */
-	for (i = 0; au1x00_data[i].flags ; i++)
-		au1x00_data[i].uartclk = uartclk;
-
-	return platform_device_register(&au1x00_device);
-}
-
-/* XXX: Yes, I know this doesn't yet work. */
-static void __exit au1x00_exit(void)
-{
-	platform_device_unregister(&au1x00_device);
-}
-
-module_init(au1x00_init);
-module_exit(au1x00_exit);
-
-MODULE_AUTHOR("Pantelis Antoniou <pantelis@embeddedalley.com>");
-MODULE_DESCRIPTION("8250 serial probe module for Au1x000 cards");
-MODULE_LICENSE("GPL");
diff --git a/trunk/drivers/serial/8250_pci.c b/trunk/drivers/serial/8250_pci.c
index f97224ce59da..6e57382b9137 100644
--- a/trunk/drivers/serial/8250_pci.c
+++ b/trunk/drivers/serial/8250_pci.c
@@ -775,7 +775,7 @@ pci_default_setup(struct serial_private *priv, struct pciserial_board *board,
  * This list is ordered alphabetically by vendor then device.
  * Specific entries must come before more generic entries.
  */
-static struct pci_serial_quirk pci_serial_quirks[] = {
+static struct pci_serial_quirk pci_serial_quirks[] __refdata = {
 	/*
 	* ADDI-DATA GmbH communication cards <info@addi-data.com>
 	*/
diff --git a/trunk/drivers/serial/Kconfig b/trunk/drivers/serial/Kconfig
index f7cd9504d811..34b809e3b596 100644
--- a/trunk/drivers/serial/Kconfig
+++ b/trunk/drivers/serial/Kconfig
@@ -262,12 +262,12 @@ config SERIAL_8250_ACORN
 	  cards.  If unsure, say N.
 
 config SERIAL_8250_AU1X00
-	bool "AU1X00 serial port support"
+	bool "Au1x00 serial port support"
 	depends on SERIAL_8250 != n && SOC_AU1X00
 	help
-	  If you have an Au1x00 board and want to use the serial port, say Y
-	  to this option.  The driver can handle 1 or 2 serial ports.
-	  If unsure, say N.
+	  If you have an Au1x00 SOC based board and want to use the serial port,
+	  say Y to this option. The driver can handle up to 4 serial ports,
+	  depending on the SOC. If unsure, say N.
 
 config SERIAL_8250_RM9K
 	bool "Support for MIPS RM9xxx integrated serial port"
diff --git a/trunk/drivers/serial/Makefile b/trunk/drivers/serial/Makefile
index 3cbea5494724..f02ff9fad017 100644
--- a/trunk/drivers/serial/Makefile
+++ b/trunk/drivers/serial/Makefile
@@ -20,7 +20,6 @@ obj-$(CONFIG_SERIAL_8250_BOCA) += 8250_boca.o
 obj-$(CONFIG_SERIAL_8250_EXAR_ST16C554) += 8250_exar_st16c554.o
 obj-$(CONFIG_SERIAL_8250_HUB6) += 8250_hub6.o
 obj-$(CONFIG_SERIAL_8250_MCA) += 8250_mca.o
-obj-$(CONFIG_SERIAL_8250_AU1X00) += 8250_au1x00.o
 obj-$(CONFIG_SERIAL_AMBA_PL010) += amba-pl010.o
 obj-$(CONFIG_SERIAL_AMBA_PL011) += amba-pl011.o
 obj-$(CONFIG_SERIAL_CLPS711X) += clps711x.o
diff --git a/trunk/drivers/serial/atmel_serial.c b/trunk/drivers/serial/atmel_serial.c
index 55492fa095a2..c065a704a93a 100644
--- a/trunk/drivers/serial/atmel_serial.c
+++ b/trunk/drivers/serial/atmel_serial.c
@@ -96,7 +96,6 @@
 
  /* PDC registers */
 #define UART_PUT_PTCR(port,v)	__raw_writel(v, (port)->membase + ATMEL_PDC_PTCR)
-#define UART_GET_TCR(port)      __raw_readl((port)->membase + ATMEL_PDC_TCR)
 #define UART_GET_PTSR(port)	__raw_readl((port)->membase + ATMEL_PDC_PTSR)
 
 #define UART_PUT_RPR(port,v)	__raw_writel(v, (port)->membase + ATMEL_PDC_RPR)
diff --git a/trunk/drivers/serial/crisv10.c b/trunk/drivers/serial/crisv10.c
index 383c4e660cd5..88e7c1d5b919 100644
--- a/trunk/drivers/serial/crisv10.c
+++ b/trunk/drivers/serial/crisv10.c
@@ -3582,6 +3582,8 @@ rs_tiocmset(struct tty_struct *tty, struct file *file,
 {
 	struct e100_serial *info = (struct e100_serial *)tty->driver_data;
 
+	lock_kernel();
+
 	if (clear & TIOCM_RTS)
 		e100_rts(info, 0);
 	if (clear & TIOCM_DTR)
@@ -3601,6 +3603,8 @@ rs_tiocmset(struct tty_struct *tty, struct file *file,
 		e100_ri_out(info, 1);
 	if (set & TIOCM_CD)
 		e100_cd_out(info, 1);
+
+	unlock_kernel();
 	return 0;
 }
 
@@ -3610,6 +3614,7 @@ rs_tiocmget(struct tty_struct *tty, struct file *file)
 	struct e100_serial *info = (struct e100_serial *)tty->driver_data;
 	unsigned int result;
 
+	lock_kernel();
 	result =
 		(!E100_RTS_GET(info) ? TIOCM_RTS : 0)
 		| (!E100_DTR_GET(info) ? TIOCM_DTR : 0)
@@ -3618,6 +3623,8 @@ rs_tiocmget(struct tty_struct *tty, struct file *file)
 		| (!E100_CD_GET(info) ? TIOCM_CAR : 0)
 		| (!E100_CTS_GET(info) ? TIOCM_CTS : 0);
 
+	unlock_kernel();
+
 #ifdef SERIAL_DEBUG_IO
 	printk(KERN_DEBUG "ser%i: modem state: %i 0x%08X\n",
 		info->line, result, result);
diff --git a/trunk/drivers/serial/dz.c b/trunk/drivers/serial/dz.c
index 116211fcd36f..0dddd68b20d2 100644
--- a/trunk/drivers/serial/dz.c
+++ b/trunk/drivers/serial/dz.c
@@ -819,7 +819,7 @@ static void dz_console_putchar(struct uart_port *uport, int ch)
 		dz_out(dport, DZ_TCR, mask);
 		iob();
 		udelay(2);
-	} while (loops--);
+	} while (--loops);
 
 	if (loops)				/* Cannot send otherwise. */
 		dz_out(dport, DZ_TDR, ch);
diff --git a/trunk/drivers/serial/serial_core.c b/trunk/drivers/serial/serial_core.c
index a9ca03ead3e5..977ce820ce30 100644
--- a/trunk/drivers/serial/serial_core.c
+++ b/trunk/drivers/serial/serial_core.c
@@ -329,13 +329,15 @@ EXPORT_SYMBOL(uart_update_timeout);
  *	If it's still invalid, we try 9600 baud.
  *
  *	Update the @termios structure to reflect the baud rate
- *	we're actually going to be using.
+ *	we're actually going to be using. Don't do this for the case
+ *	where B0 is requested ("hang up").
  */
 unsigned int
 uart_get_baud_rate(struct uart_port *port, struct ktermios *termios,
 		   struct ktermios *old, unsigned int min, unsigned int max)
 {
 	unsigned int try, baud, altbaud = 38400;
+	int hung_up = 0;
 	upf_t flags = port->flags & UPF_SPD_MASK;
 
 	if (flags == UPF_SPD_HI)
@@ -360,8 +362,10 @@ uart_get_baud_rate(struct uart_port *port, struct ktermios *termios,
 		/*
 		 * Special case: B0 rate.
 		 */
-		if (baud == 0)
+		if (baud == 0) {
+			hung_up = 1;
 			baud = 9600;
+		}
 
 		if (baud >= min && baud <= max)
 			return baud;
@@ -373,7 +377,9 @@ uart_get_baud_rate(struct uart_port *port, struct ktermios *termios,
 		termios->c_cflag &= ~CBAUD;
 		if (old) {
 			baud = tty_termios_baud_rate(old);
-			tty_termios_encode_baud_rate(termios, baud, baud);
+			if (!hung_up)
+				tty_termios_encode_baud_rate(termios,
+								baud, baud);
 			old = NULL;
 			continue;
 		}
@@ -382,7 +388,8 @@ uart_get_baud_rate(struct uart_port *port, struct ktermios *termios,
 		 * As a last resort, if the quotient is zero,
 		 * default to 9600 bps
 		 */
-		tty_termios_encode_baud_rate(termios, 9600, 9600);
+		if (!hung_up)
+			tty_termios_encode_baud_rate(termios, 9600, 9600);
 	}
 
 	return 0;
diff --git a/trunk/drivers/serial/sunzilog.c b/trunk/drivers/serial/sunzilog.c
index 3271379a36db..90a20a152ebf 100644
--- a/trunk/drivers/serial/sunzilog.c
+++ b/trunk/drivers/serial/sunzilog.c
@@ -1231,7 +1231,7 @@ static inline struct console *SUNZILOG_CONSOLE(void)
 #define SUNZILOG_CONSOLE()	(NULL)
 #endif
 
-static void __devinit sunzilog_init_kbdms(struct uart_sunzilog_port *up, int channel)
+static void __devinit sunzilog_init_kbdms(struct uart_sunzilog_port *up)
 {
 	int baud, brg;
 
@@ -1305,7 +1305,7 @@ static void __devinit sunzilog_init_hw(struct uart_sunzilog_port *up)
 		up->curregs[R7] = 0x7E; /* SDLC Flag    */
 		up->curregs[R9] = NV;
 		up->curregs[R7p] = 0x00;
-		sunzilog_init_kbdms(up, up->port.line);
+		sunzilog_init_kbdms(up);
 		/* Only enable interrupts if an ISR handler available */
 		if (up->flags & SUNZILOG_FLAG_ISR_HANDLER)
 			up->curregs[R9] |= MIE;
diff --git a/trunk/drivers/serial/vr41xx_siu.c b/trunk/drivers/serial/vr41xx_siu.c
index 98ab649c1ff9..bb6ce6bba32f 100644
--- a/trunk/drivers/serial/vr41xx_siu.c
+++ b/trunk/drivers/serial/vr41xx_siu.c
@@ -1,7 +1,7 @@
 /*
  *  Driver for NEC VR4100 series Serial Interface Unit.
  *
- *  Copyright (C) 2004-2007  Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
+ *  Copyright (C) 2004-2008  Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
  *
  *  Based on drivers/serial/8250.c, by Russell King.
  *
@@ -840,6 +840,19 @@ static int __devinit siu_console_init(void)
 
 console_initcall(siu_console_init);
 
+void __init vr41xx_siu_early_setup(struct uart_port *port)
+{
+	if (port->type == PORT_UNKNOWN)
+		return;
+
+	siu_uart_ports[port->line].line = port->line;
+	siu_uart_ports[port->line].type = port->type;
+	siu_uart_ports[port->line].uartclk = SIU_BAUD_BASE * 16;
+	siu_uart_ports[port->line].mapbase = port->mapbase;
+	siu_uart_ports[port->line].mapbase = port->mapbase;
+	siu_uart_ports[port->line].ops = &siu_uart_ops;
+}
+
 #define SERIAL_VR41XX_CONSOLE	&siu_console
 #else
 #define SERIAL_VR41XX_CONSOLE	NULL
diff --git a/trunk/drivers/spi/Kconfig b/trunk/drivers/spi/Kconfig
index d8107890db15..fae9e8f3d092 100644
--- a/trunk/drivers/spi/Kconfig
+++ b/trunk/drivers/spi/Kconfig
@@ -5,11 +5,9 @@
 # nobody's needed a slave side API yet.  The master-role API is not
 # fully appropriate there, so it'd need some thought to do well.
 #
-menu "SPI support"
-	depends on HAS_IOMEM
-
-config SPI
+menuconfig SPI
 	bool "SPI support"
+	depends on HAS_IOMEM
 	help
 	  The "Serial Peripheral Interface" is a low level synchronous
 	  protocol.  Chips that support SPI can have data transfer rates
@@ -28,9 +26,11 @@ config SPI
 	  (half duplex), SSP, SSI, and PSP.  This driver framework should
 	  work with most such devices and controllers.
 
+if SPI
+
 config SPI_DEBUG
 	boolean "Debug support for SPI drivers"
-	depends on SPI && DEBUG_KERNEL
+	depends on DEBUG_KERNEL
 	help
 	  Say "yes" to enable debug messaging (like dev_dbg and pr_debug),
 	  sysfs, and debugfs support in SPI controller and protocol drivers.
@@ -245,5 +245,4 @@ config SPI_TLE62X0
 
 # (slave support would go here)
 
-endmenu # "SPI support"
-
+endif # SPI
diff --git a/trunk/drivers/spi/atmel_spi.c b/trunk/drivers/spi/atmel_spi.c
index 1749a27be066..02c8e305b14f 100644
--- a/trunk/drivers/spi/atmel_spi.c
+++ b/trunk/drivers/spi/atmel_spi.c
@@ -616,7 +616,7 @@ static int atmel_spi_transfer(struct spi_device *spi, struct spi_message *msg)
 		return -ESHUTDOWN;
 
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
-		if (!(xfer->tx_buf || xfer->rx_buf)) {
+		if (!(xfer->tx_buf || xfer->rx_buf) && xfer->len) {
 			dev_dbg(&spi->dev, "missing rx or tx buf\n");
 			return -EINVAL;
 		}
diff --git a/trunk/drivers/spi/omap_uwire.c b/trunk/drivers/spi/omap_uwire.c
index 5f00bd6500ef..d9ae111c27ae 100644
--- a/trunk/drivers/spi/omap_uwire.c
+++ b/trunk/drivers/spi/omap_uwire.c
@@ -151,7 +151,7 @@ static int wait_uwire_csr_flag(u16 mask, u16 val, int might_not_catch)
 		if (time_after(jiffies, max_jiffies)) {
 			printk(KERN_ERR "%s: timeout. reg=%#06x "
 					"mask=%#06x val=%#06x\n",
-			       __FUNCTION__, w, mask, val);
+			       __func__, w, mask, val);
 			return -1;
 		}
 		c++;
@@ -437,7 +437,7 @@ static int uwire_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
 	}
 	omap_uwire_configure_mode(spi->chip_select, flags);
 	pr_debug("%s: uwire flags %02x, armxor %lu KHz, SCK %lu KHz\n",
-			__FUNCTION__, flags,
+			__func__, flags,
 			clk_get_rate(uwire->ck) / 1000,
 			rate / 1000);
 	status = 0;
diff --git a/trunk/drivers/spi/pxa2xx_spi.c b/trunk/drivers/spi/pxa2xx_spi.c
index 147e26a78d64..654bb58be630 100644
--- a/trunk/drivers/spi/pxa2xx_spi.c
+++ b/trunk/drivers/spi/pxa2xx_spi.c
@@ -67,8 +67,11 @@ MODULE_ALIAS("platform:pxa2xx-spi");
 				| SSCR1_SPH | SSCR1_SPO | SSCR1_LBM)
 
 #define DEFINE_SSP_REG(reg, off) \
-static inline u32 read_##reg(void *p) { return __raw_readl(p + (off)); } \
-static inline void write_##reg(u32 v, void *p) { __raw_writel(v, p + (off)); }
+static inline u32 read_##reg(void const __iomem *p) \
+{ return __raw_readl(p + (off)); } \
+\
+static inline void write_##reg(u32 v, void __iomem *p) \
+{ __raw_writel(v, p + (off)); }
 
 DEFINE_SSP_REG(SSCR0, 0x00)
 DEFINE_SSP_REG(SSCR1, 0x04)
@@ -106,7 +109,7 @@ struct driver_data {
 	u32 *null_dma_buf;
 
 	/* SSP register addresses */
-	void *ioaddr;
+	void __iomem *ioaddr;
 	u32 ssdr_physical;
 
 	/* SSP masks*/
@@ -173,7 +176,7 @@ static int flush(struct driver_data *drv_data)
 {
 	unsigned long limit = loops_per_jiffy << 1;
 
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 
 	do {
 		while (read_SSSR(reg) & SSSR_RNE) {
@@ -191,7 +194,7 @@ static void null_cs_control(u32 command)
 
 static int null_writer(struct driver_data *drv_data)
 {
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 	u8 n_bytes = drv_data->n_bytes;
 
 	if (((read_SSSR(reg) & 0x00000f00) == 0x00000f00)
@@ -206,7 +209,7 @@ static int null_writer(struct driver_data *drv_data)
 
 static int null_reader(struct driver_data *drv_data)
 {
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 	u8 n_bytes = drv_data->n_bytes;
 
 	while ((read_SSSR(reg) & SSSR_RNE)
@@ -220,7 +223,7 @@ static int null_reader(struct driver_data *drv_data)
 
 static int u8_writer(struct driver_data *drv_data)
 {
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 
 	if (((read_SSSR(reg) & 0x00000f00) == 0x00000f00)
 		|| (drv_data->tx == drv_data->tx_end))
@@ -234,7 +237,7 @@ static int u8_writer(struct driver_data *drv_data)
 
 static int u8_reader(struct driver_data *drv_data)
 {
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 
 	while ((read_SSSR(reg) & SSSR_RNE)
 		&& (drv_data->rx < drv_data->rx_end)) {
@@ -247,7 +250,7 @@ static int u8_reader(struct driver_data *drv_data)
 
 static int u16_writer(struct driver_data *drv_data)
 {
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 
 	if (((read_SSSR(reg) & 0x00000f00) == 0x00000f00)
 		|| (drv_data->tx == drv_data->tx_end))
@@ -261,7 +264,7 @@ static int u16_writer(struct driver_data *drv_data)
 
 static int u16_reader(struct driver_data *drv_data)
 {
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 
 	while ((read_SSSR(reg) & SSSR_RNE)
 		&& (drv_data->rx < drv_data->rx_end)) {
@@ -274,7 +277,7 @@ static int u16_reader(struct driver_data *drv_data)
 
 static int u32_writer(struct driver_data *drv_data)
 {
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 
 	if (((read_SSSR(reg) & 0x00000f00) == 0x00000f00)
 		|| (drv_data->tx == drv_data->tx_end))
@@ -288,7 +291,7 @@ static int u32_writer(struct driver_data *drv_data)
 
 static int u32_reader(struct driver_data *drv_data)
 {
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 
 	while ((read_SSSR(reg) & SSSR_RNE)
 		&& (drv_data->rx < drv_data->rx_end)) {
@@ -412,7 +415,7 @@ static void giveback(struct driver_data *drv_data)
 		msg->complete(msg->context);
 }
 
-static int wait_ssp_rx_stall(void *ioaddr)
+static int wait_ssp_rx_stall(void const __iomem *ioaddr)
 {
 	unsigned long limit = loops_per_jiffy << 1;
 
@@ -432,9 +435,9 @@ static int wait_dma_channel_stop(int channel)
 	return limit;
 }
 
-void dma_error_stop(struct driver_data *drv_data, const char *msg)
+static void dma_error_stop(struct driver_data *drv_data, const char *msg)
 {
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 
 	/* Stop and reset */
 	DCSR(drv_data->rx_channel) = RESET_DMA_CHANNEL;
@@ -456,7 +459,7 @@ void dma_error_stop(struct driver_data *drv_data, const char *msg)
 
 static void dma_transfer_complete(struct driver_data *drv_data)
 {
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 	struct spi_message *msg = drv_data->cur_msg;
 
 	/* Clear and disable interrupts on SSP and DMA channels*/
@@ -536,7 +539,7 @@ static void dma_handler(int channel, void *data)
 static irqreturn_t dma_transfer(struct driver_data *drv_data)
 {
 	u32 irq_status;
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 
 	irq_status = read_SSSR(reg) & drv_data->mask_sr;
 	if (irq_status & SSSR_ROR) {
@@ -570,7 +573,7 @@ static irqreturn_t dma_transfer(struct driver_data *drv_data)
 
 static void int_error_stop(struct driver_data *drv_data, const char* msg)
 {
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 
 	/* Stop and reset SSP */
 	write_SSSR(drv_data->clear_sr, reg);
@@ -588,7 +591,7 @@ static void int_error_stop(struct driver_data *drv_data, const char* msg)
 
 static void int_transfer_complete(struct driver_data *drv_data)
 {
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 
 	/* Stop SSP */
 	write_SSSR(drv_data->clear_sr, reg);
@@ -614,7 +617,7 @@ static void int_transfer_complete(struct driver_data *drv_data)
 
 static irqreturn_t interrupt_transfer(struct driver_data *drv_data)
 {
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 
 	u32 irq_mask = (read_SSCR1(reg) & SSCR1_TIE) ?
 			drv_data->mask_sr : drv_data->mask_sr & ~SSSR_TFS;
@@ -675,7 +678,7 @@ static irqreturn_t interrupt_transfer(struct driver_data *drv_data)
 static irqreturn_t ssp_int(int irq, void *dev_id)
 {
 	struct driver_data *drv_data = dev_id;
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 
 	if (!drv_data->cur_msg) {
 
@@ -695,7 +698,8 @@ static irqreturn_t ssp_int(int irq, void *dev_id)
 	return drv_data->transfer_handler(drv_data);
 }
 
-int set_dma_burst_and_threshold(struct chip_data *chip, struct spi_device *spi,
+static int set_dma_burst_and_threshold(struct chip_data *chip,
+				struct spi_device *spi,
 				u8 bits_per_word, u32 *burst_code,
 				u32 *threshold)
 {
@@ -809,7 +813,7 @@ static void pump_transfers(unsigned long data)
 	struct spi_transfer *previous = NULL;
 	struct chip_data *chip = NULL;
 	struct ssp_device *ssp = drv_data->ssp;
-	void *reg = drv_data->ioaddr;
+	void __iomem *reg = drv_data->ioaddr;
 	u32 clk_div = 0;
 	u8 bits = 0;
 	u32 speed = 0;
@@ -1338,7 +1342,7 @@ static int __init pxa2xx_spi_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct pxa2xx_spi_master *platform_info;
 	struct spi_master *master;
-	struct driver_data *drv_data = 0;
+	struct driver_data *drv_data = NULL;
 	struct ssp_device *ssp;
 	int status = 0;
 
diff --git a/trunk/drivers/spi/spi_bitbang.c b/trunk/drivers/spi/spi_bitbang.c
index 71e881419cdd..96cc39ecb6e2 100644
--- a/trunk/drivers/spi/spi_bitbang.c
+++ b/trunk/drivers/spi/spi_bitbang.c
@@ -214,7 +214,7 @@ int spi_bitbang_setup(struct spi_device *spi)
 		return retval;
 
 	dev_dbg(&spi->dev, "%s, mode %d, %u bits/w, %u nsec/bit\n",
-			__FUNCTION__, spi->mode & (SPI_CPOL | SPI_CPHA),
+			__func__, spi->mode & (SPI_CPOL | SPI_CPHA),
 			spi->bits_per_word, 2 * cs->nsecs);
 
 	/* NOTE we _need_ to call chipselect() early, ideally with adapter
diff --git a/trunk/drivers/spi/spi_imx.c b/trunk/drivers/spi/spi_imx.c
index d4ba640366b6..c730d05bfeb6 100644
--- a/trunk/drivers/spi/spi_imx.c
+++ b/trunk/drivers/spi/spi_imx.c
@@ -270,19 +270,26 @@ struct chip_data {
 
 static void pump_messages(struct work_struct *work);
 
-static int flush(struct driver_data *drv_data)
+static void flush(struct driver_data *drv_data)
 {
-	unsigned long limit = loops_per_jiffy << 1;
 	void __iomem *regs = drv_data->regs;
-	volatile u32 d;
+	u32 control;
 
 	dev_dbg(&drv_data->pdev->dev, "flush\n");
+
+	/* Wait for end of transaction */
 	do {
-		while (readl(regs + SPI_INT_STATUS) & SPI_STATUS_RR)
-			d = readl(regs + SPI_RXDATA);
-	} while ((readl(regs + SPI_CONTROL) & SPI_CONTROL_XCH) && limit--);
+		control = readl(regs + SPI_CONTROL);
+	} while (control & SPI_CONTROL_XCH);
+
+	/* Release chip select if requested, transfer delays are
+	   handled in pump_transfers */
+	if (drv_data->cs_change)
+		drv_data->cs_control(SPI_CS_DEASSERT);
 
-	return limit;
+	/* Disable SPI to flush FIFOs */
+	writel(control & ~SPI_CONTROL_SPIEN, regs + SPI_CONTROL);
+	writel(control, regs + SPI_CONTROL);
 }
 
 static void restore_state(struct driver_data *drv_data)
@@ -570,6 +577,7 @@ static void giveback(struct spi_message *message, struct driver_data *drv_data)
 	writel(0, regs + SPI_INT_STATUS);
 	writel(0, regs + SPI_DMA);
 
+	/* Unconditioned deselct */
 	drv_data->cs_control(SPI_CS_DEASSERT);
 
 	message->state = NULL;
@@ -592,13 +600,10 @@ static void dma_err_handler(int channel, void *data, int errcode)
 	/* Disable both rx and tx dma channels */
 	imx_dma_disable(drv_data->rx_channel);
 	imx_dma_disable(drv_data->tx_channel);
-
-	if (flush(drv_data) == 0)
-		dev_err(&drv_data->pdev->dev,
-				"dma_err_handler - flush failed\n");
-
 	unmap_dma_buffers(drv_data);
 
+	flush(drv_data);
+
 	msg->state = ERROR_STATE;
 	tasklet_schedule(&drv_data->pump_transfers);
 }
@@ -612,8 +617,7 @@ static void dma_tx_handler(int channel, void *data)
 	imx_dma_disable(channel);
 
 	/* Now waits for TX FIFO empty */
-	writel(readl(drv_data->regs + SPI_INT_STATUS) | SPI_INTEN_TE,
-			drv_data->regs + SPI_INT_STATUS);
+	writel(SPI_INTEN_TE, drv_data->regs + SPI_INT_STATUS);
 }
 
 static irqreturn_t dma_transfer(struct driver_data *drv_data)
@@ -621,19 +625,18 @@ static irqreturn_t dma_transfer(struct driver_data *drv_data)
 	u32 status;
 	struct spi_message *msg = drv_data->cur_msg;
 	void __iomem *regs = drv_data->regs;
-	unsigned long limit;
 
 	status = readl(regs + SPI_INT_STATUS);
 
-	if ((status & SPI_INTEN_RO) && (status & SPI_STATUS_RO)) {
+	if ((status & (SPI_INTEN_RO | SPI_STATUS_RO))
+			== (SPI_INTEN_RO | SPI_STATUS_RO)) {
 		writel(status & ~SPI_INTEN, regs + SPI_INT_STATUS);
 
+		imx_dma_disable(drv_data->tx_channel);
 		imx_dma_disable(drv_data->rx_channel);
 		unmap_dma_buffers(drv_data);
 
-		if (flush(drv_data) == 0)
-			dev_err(&drv_data->pdev->dev,
-				"dma_transfer - flush failed\n");
+		flush(drv_data);
 
 		dev_warn(&drv_data->pdev->dev,
 				"dma_transfer - fifo overun\n");
@@ -649,20 +652,17 @@ static irqreturn_t dma_transfer(struct driver_data *drv_data)
 
 		if (drv_data->rx) {
 			/* Wait end of transfer before read trailing data */
-			limit = loops_per_jiffy << 1;
-			while ((readl(regs + SPI_CONTROL) & SPI_CONTROL_XCH) &&
-					limit--);
-
-			if (limit == 0)
-				dev_err(&drv_data->pdev->dev,
-					"dma_transfer - end of tx failed\n");
-			else
-				dev_dbg(&drv_data->pdev->dev,
-					"dma_transfer - end of tx\n");
+			while (readl(regs + SPI_CONTROL) & SPI_CONTROL_XCH)
+				cpu_relax();
 
 			imx_dma_disable(drv_data->rx_channel);
 			unmap_dma_buffers(drv_data);
 
+			/* Release chip select if requested, transfer delays are
+			   handled in pump_transfers() */
+			if (drv_data->cs_change)
+				drv_data->cs_control(SPI_CS_DEASSERT);
+
 			/* Calculate number of trailing data and read them */
 			dev_dbg(&drv_data->pdev->dev,
 				"dma_transfer - test = 0x%08X\n",
@@ -676,19 +676,12 @@ static irqreturn_t dma_transfer(struct driver_data *drv_data)
 			/* Write only transfer */
 			unmap_dma_buffers(drv_data);
 
-			if (flush(drv_data) == 0)
-				dev_err(&drv_data->pdev->dev,
-					"dma_transfer - flush failed\n");
+			flush(drv_data);
 		}
 
 		/* End of transfer, update total byte transfered */
 		msg->actual_length += drv_data->len;
 
-		/* Release chip select if requested, transfer delays are
-		   handled in pump_transfers() */
-		if (drv_data->cs_change)
-			drv_data->cs_control(SPI_CS_DEASSERT);
-
 		/* Move to next transfer */
 		msg->state = next_transfer(drv_data);
 
@@ -711,44 +704,43 @@ static irqreturn_t interrupt_wronly_transfer(struct driver_data *drv_data)
 
 	status = readl(regs + SPI_INT_STATUS);
 
-	while (status & SPI_STATUS_TH) {
+	if (status & SPI_INTEN_TE) {
+		/* TXFIFO Empty Interrupt on the last transfered word */
+		writel(status & ~SPI_INTEN, regs + SPI_INT_STATUS);
 		dev_dbg(&drv_data->pdev->dev,
-			"interrupt_wronly_transfer - status = 0x%08X\n", status);
+			"interrupt_wronly_transfer - end of tx\n");
 
-		/* Pump data */
-		if (write(drv_data)) {
-			writel(readl(regs + SPI_INT_STATUS) & ~SPI_INTEN,
-				regs + SPI_INT_STATUS);
+		flush(drv_data);
 
-			dev_dbg(&drv_data->pdev->dev,
-				"interrupt_wronly_transfer - end of tx\n");
+		/* Update total byte transfered */
+		msg->actual_length += drv_data->len;
 
-			if (flush(drv_data) == 0)
-				dev_err(&drv_data->pdev->dev,
-					"interrupt_wronly_transfer - "
-					"flush failed\n");
+		/* Move to next transfer */
+		msg->state = next_transfer(drv_data);
 
-			/* End of transfer, update total byte transfered */
-			msg->actual_length += drv_data->len;
+		/* Schedule transfer tasklet */
+		tasklet_schedule(&drv_data->pump_transfers);
 
-			/* Release chip select if requested, transfer delays are
-			   handled in pump_transfers */
-			if (drv_data->cs_change)
-				drv_data->cs_control(SPI_CS_DEASSERT);
+		return IRQ_HANDLED;
+	} else {
+		while (status & SPI_STATUS_TH) {
+			dev_dbg(&drv_data->pdev->dev,
+				"interrupt_wronly_transfer - status = 0x%08X\n",
+				status);
 
-			/* Move to next transfer */
-			msg->state = next_transfer(drv_data);
+			/* Pump data */
+			if (write(drv_data)) {
+				/* End of TXFIFO writes,
+				   now wait until TXFIFO is empty */
+				writel(SPI_INTEN_TE, regs + SPI_INT_STATUS);
+				return IRQ_HANDLED;
+			}
 
-			/* Schedule transfer tasklet */
-			tasklet_schedule(&drv_data->pump_transfers);
+			status = readl(regs + SPI_INT_STATUS);
 
-			return IRQ_HANDLED;
+			/* We did something */
+			handled = IRQ_HANDLED;
 		}
-
-		status = readl(regs + SPI_INT_STATUS);
-
-		/* We did something */
-		handled = IRQ_HANDLED;
 	}
 
 	return handled;
@@ -758,45 +750,31 @@ static irqreturn_t interrupt_transfer(struct driver_data *drv_data)
 {
 	struct spi_message *msg = drv_data->cur_msg;
 	void __iomem *regs = drv_data->regs;
-	u32 status;
+	u32 status, control;
 	irqreturn_t handled = IRQ_NONE;
 	unsigned long limit;
 
 	status = readl(regs + SPI_INT_STATUS);
 
-	while (status & (SPI_STATUS_TH | SPI_STATUS_RO)) {
+	if (status & SPI_INTEN_TE) {
+		/* TXFIFO Empty Interrupt on the last transfered word */
+		writel(status & ~SPI_INTEN, regs + SPI_INT_STATUS);
 		dev_dbg(&drv_data->pdev->dev,
-			"interrupt_transfer - status = 0x%08X\n", status);
-
-		if (status & SPI_STATUS_RO) {
-			writel(readl(regs + SPI_INT_STATUS) & ~SPI_INTEN,
-				regs + SPI_INT_STATUS);
-
-			dev_warn(&drv_data->pdev->dev,
-				"interrupt_transfer - fifo overun\n"
-				"    data not yet written = %d\n"
-				"    data not yet read    = %d\n",
-				data_to_write(drv_data),
-				data_to_read(drv_data));
-
-			if (flush(drv_data) == 0)
-				dev_err(&drv_data->pdev->dev,
-					"interrupt_transfer - flush failed\n");
-
-			msg->state = ERROR_STATE;
-			tasklet_schedule(&drv_data->pump_transfers);
+			"interrupt_transfer - end of tx\n");
 
-			return IRQ_HANDLED;
-		}
-
-		/* Pump data */
-		read(drv_data);
-		if (write(drv_data)) {
-			writel(readl(regs + SPI_INT_STATUS) & ~SPI_INTEN,
-				regs + SPI_INT_STATUS);
+		if (msg->state == ERROR_STATE) {
+			/* RXFIFO overrun was detected and message aborted */
+			flush(drv_data);
+		} else {
+			/* Wait for end of transaction */
+			do {
+				control = readl(regs + SPI_CONTROL);
+			} while (control & SPI_CONTROL_XCH);
 
-			dev_dbg(&drv_data->pdev->dev,
-				"interrupt_transfer - end of tx\n");
+			/* Release chip select if requested, transfer delays are
+			   handled in pump_transfers */
+			if (drv_data->cs_change)
+				drv_data->cs_control(SPI_CS_DEASSERT);
 
 			/* Read trailing bytes */
 			limit = loops_per_jiffy << 1;
@@ -810,27 +788,54 @@ static irqreturn_t interrupt_transfer(struct driver_data *drv_data)
 				dev_dbg(&drv_data->pdev->dev,
 					"interrupt_transfer - end of rx\n");
 
-			/* End of transfer, update total byte transfered */
+			/* Update total byte transfered */
 			msg->actual_length += drv_data->len;
 
-			/* Release chip select if requested, transfer delays are
-			   handled in pump_transfers */
-			if (drv_data->cs_change)
-				drv_data->cs_control(SPI_CS_DEASSERT);
-
 			/* Move to next transfer */
 			msg->state = next_transfer(drv_data);
+		}
 
-			/* Schedule transfer tasklet */
-			tasklet_schedule(&drv_data->pump_transfers);
+		/* Schedule transfer tasklet */
+		tasklet_schedule(&drv_data->pump_transfers);
 
-			return IRQ_HANDLED;
-		}
+		return IRQ_HANDLED;
+	} else {
+		while (status & (SPI_STATUS_TH | SPI_STATUS_RO)) {
+			dev_dbg(&drv_data->pdev->dev,
+				"interrupt_transfer - status = 0x%08X\n",
+				status);
+
+			if (status & SPI_STATUS_RO) {
+				/* RXFIFO overrun, abort message end wait
+				   until TXFIFO is empty */
+				writel(SPI_INTEN_TE, regs + SPI_INT_STATUS);
+
+				dev_warn(&drv_data->pdev->dev,
+					"interrupt_transfer - fifo overun\n"
+					"    data not yet written = %d\n"
+					"    data not yet read    = %d\n",
+					data_to_write(drv_data),
+					data_to_read(drv_data));
+
+				msg->state = ERROR_STATE;
+
+				return IRQ_HANDLED;
+			}
 
-		status = readl(regs + SPI_INT_STATUS);
+			/* Pump data */
+			read(drv_data);
+			if (write(drv_data)) {
+				/* End of TXFIFO writes,
+				   now wait until TXFIFO is empty */
+				writel(SPI_INTEN_TE, regs + SPI_INT_STATUS);
+				return IRQ_HANDLED;
+			}
 
-		/* We did something */
-		handled = IRQ_HANDLED;
+			status = readl(regs + SPI_INT_STATUS);
+
+			/* We did something */
+			handled = IRQ_HANDLED;
+		}
 	}
 
 	return handled;
diff --git a/trunk/drivers/spi/spi_mpc83xx.c b/trunk/drivers/spi/spi_mpc83xx.c
index be15a6213205..189f706b9e4b 100644
--- a/trunk/drivers/spi/spi_mpc83xx.c
+++ b/trunk/drivers/spi/spi_mpc83xx.c
@@ -310,7 +310,7 @@ static int mpc83xx_spi_setup(struct spi_device *spi)
 		return retval;
 
 	dev_dbg(&spi->dev, "%s, mode %d, %u bits/w, %u nsec\n",
-		__FUNCTION__, spi->mode & (SPI_CPOL | SPI_CPHA),
+		__func__, spi->mode & (SPI_CPOL | SPI_CPHA),
 		spi->bits_per_word, 2 * mpc83xx_spi->nsecs);
 
 	/* NOTE we _need_ to call chipselect() early, ideally with adapter
diff --git a/trunk/drivers/spi/spi_s3c24xx.c b/trunk/drivers/spi/spi_s3c24xx.c
index b7476b888197..34bfb7dd7764 100644
--- a/trunk/drivers/spi/spi_s3c24xx.c
+++ b/trunk/drivers/spi/spi_s3c24xx.c
@@ -169,7 +169,7 @@ static int s3c24xx_spi_setup(struct spi_device *spi)
 	}
 
 	dev_dbg(&spi->dev, "%s: mode %d, %u bpw, %d hz\n",
-		__FUNCTION__, spi->mode, spi->bits_per_word,
+		__func__, spi->mode, spi->bits_per_word,
 		spi->max_speed_hz);
 
 	return 0;
diff --git a/trunk/drivers/spi/xilinx_spi.c b/trunk/drivers/spi/xilinx_spi.c
index cf6aef34fe25..113a0468ffcb 100644
--- a/trunk/drivers/spi/xilinx_spi.c
+++ b/trunk/drivers/spi/xilinx_spi.c
@@ -151,13 +151,13 @@ static int xilinx_spi_setup_transfer(struct spi_device *spi,
 	hz = (t) ? t->speed_hz : spi->max_speed_hz;
 	if (bits_per_word != 8) {
 		dev_err(&spi->dev, "%s, unsupported bits_per_word=%d\n",
-			__FUNCTION__, bits_per_word);
+			__func__, bits_per_word);
 		return -EINVAL;
 	}
 
 	if (hz && xspi->speed_hz > hz) {
 		dev_err(&spi->dev, "%s, unsupported clock rate %uHz\n",
-			__FUNCTION__, hz);
+			__func__, hz);
 		return -EINVAL;
 	}
 
@@ -181,7 +181,7 @@ static int xilinx_spi_setup(struct spi_device *spi)
 
 	if (spi->mode & ~MODEBITS) {
 		dev_err(&spi->dev, "%s, unsupported mode bits %x\n",
-			__FUNCTION__, spi->mode & ~MODEBITS);
+			__func__, spi->mode & ~MODEBITS);
 		return -EINVAL;
 	}
 
@@ -190,7 +190,7 @@ static int xilinx_spi_setup(struct spi_device *spi)
 		return retval;
 
 	dev_dbg(&spi->dev, "%s, mode %d, %u bits/w, %u nsec/bit\n",
-		__FUNCTION__, spi->mode & MODEBITS, spi->bits_per_word, 0);
+		__func__, spi->mode & MODEBITS, spi->bits_per_word, 0);
 
 	return 0;
 }
diff --git a/trunk/drivers/usb/atm/cxacru.c b/trunk/drivers/usb/atm/cxacru.c
index d470c72b737e..5ea3093bc40f 100644
--- a/trunk/drivers/usb/atm/cxacru.c
+++ b/trunk/drivers/usb/atm/cxacru.c
@@ -38,6 +38,7 @@
 #include <linux/device.h>
 #include <linux/firmware.h>
 #include <linux/mutex.h>
+#include <asm/unaligned.h>
 
 #include "usbatm.h"
 
@@ -573,7 +574,7 @@ static int cxacru_cm_get_array(struct cxacru_data *instance, enum cxacru_cm_requ
 			       u32 *data, int size)
 {
 	int ret, len;
-	u32 *buf;
+	__le32 *buf;
 	int offb, offd;
 	const int stride = CMD_PACKET_SIZE / (4 * 2) - 1;
 	int buflen =  ((size - 1) / stride + 1 + size * 2) * 4;
@@ -837,7 +838,7 @@ static int cxacru_fw(struct usb_device *usb_dev, enum cxacru_fw_request fw,
 		buf[offb++] = l;
 		buf[offb++] = code1;
 		buf[offb++] = code2;
-		*((u32 *) (buf + offb)) = cpu_to_le32(addr);
+		put_unaligned(cpu_to_le32(addr), (__le32 *)(buf + offb));
 		offb += 4;
 		addr += l;
 		if(l)
@@ -874,8 +875,9 @@ static void cxacru_upload_firmware(struct cxacru_data *instance,
 	int off;
 	struct usbatm_data *usbatm = instance->usbatm;
 	struct usb_device *usb_dev = usbatm->usb_dev;
-	u16 signature[] = { usb_dev->descriptor.idVendor, usb_dev->descriptor.idProduct };
-	u32 val;
+	__le16 signature[] = { usb_dev->descriptor.idVendor,
+			       usb_dev->descriptor.idProduct };
+	__le32 val;
 
 	dbg("cxacru_upload_firmware");
 
@@ -955,7 +957,7 @@ static void cxacru_upload_firmware(struct cxacru_data *instance,
 	/* Load config data (le32), doing one packet at a time */
 	if (cf)
 		for (off = 0; off < cf->size / 4; ) {
-			u32 buf[CMD_PACKET_SIZE / 4 - 1];
+			__le32 buf[CMD_PACKET_SIZE / 4 - 1];
 			int i, len = min_t(int, cf->size / 4 - off, CMD_PACKET_SIZE / 4 / 2 - 1);
 			buf[0] = cpu_to_le32(len);
 			for (i = 0; i < len; i++, off++) {
diff --git a/trunk/drivers/usb/atm/ueagle-atm.c b/trunk/drivers/usb/atm/ueagle-atm.c
index abb7d7410e63..5f71ff3aee35 100644
--- a/trunk/drivers/usb/atm/ueagle-atm.c
+++ b/trunk/drivers/usb/atm/ueagle-atm.c
@@ -305,8 +305,6 @@ enum {
  */
 
 #define FW_GET_BYTE(p)	*((__u8 *) (p))
-#define FW_GET_WORD(p)	le16_to_cpu(get_unaligned((__le16 *) (p)))
-#define FW_GET_LONG(p)	le32_to_cpu(get_unaligned((__le32 *) (p)))
 
 #define FW_DIR "ueagle-atm/"
 #define NB_MODEM 4
@@ -621,7 +619,7 @@ static void uea_upload_pre_firmware(const struct firmware *fw_entry, void *conte
 	if (size < 4)
 		goto err_fw_corrupted;
 
-	crc = FW_GET_LONG(pfw);
+	crc = get_unaligned_le32(pfw);
 	pfw += 4;
 	size -= 4;
 	if (crc32_be(0, pfw, size) != crc)
@@ -640,7 +638,7 @@ static void uea_upload_pre_firmware(const struct firmware *fw_entry, void *conte
 
 	while (size > 3) {
 		u8 len = FW_GET_BYTE(pfw);
-		u16 add = FW_GET_WORD(pfw + 1);
+		u16 add = get_unaligned_le16(pfw + 1);
 
 		size -= len + 3;
 		if (size < 0)
@@ -738,7 +736,7 @@ static int check_dsp_e1(u8 *dsp, unsigned int len)
 
 	for (i = 0; i < pagecount; i++) {
 
-		pageoffset = FW_GET_LONG(dsp + p);
+		pageoffset = get_unaligned_le32(dsp + p);
 		p += 4;
 
 		if (pageoffset == 0)
@@ -759,7 +757,7 @@ static int check_dsp_e1(u8 *dsp, unsigned int len)
 				return 1;
 
 			pp += 2;	/* skip blockaddr */
-			blocksize = FW_GET_WORD(dsp + pp);
+			blocksize = get_unaligned_le16(dsp + pp);
 			pp += 2;
 
 			/* enough space for block data? */
@@ -928,7 +926,7 @@ static void uea_load_page_e1(struct work_struct *work)
 		goto bad1;
 
 	p += 4 * pageno;
-	pageoffset = FW_GET_LONG(p);
+	pageoffset = get_unaligned_le32(p);
 
 	if (pageoffset == 0)
 		goto bad1;
@@ -945,10 +943,10 @@ static void uea_load_page_e1(struct work_struct *work)
 	bi.wOvlOffset = cpu_to_le16(ovl | 0x8000);
 
 	for (i = 0; i < blockcount; i++) {
-		blockaddr = FW_GET_WORD(p);
+		blockaddr = get_unaligned_le16(p);
 		p += 2;
 
-		blocksize = FW_GET_WORD(p);
+		blocksize = get_unaligned_le16(p);
 		p += 2;
 
 		bi.wSize = cpu_to_le16(blocksize);
@@ -996,7 +994,7 @@ static void __uea_load_page_e4(struct uea_softc *sc, u8 pageno, int boot)
 		blockoffset = sc->dsp_firm->data + le32_to_cpu(blockidx->PageOffset);
 
 		bi.dwSize = cpu_to_be32(blocksize);
-		bi.dwAddress = swab32(blockidx->PageAddress);
+		bi.dwAddress = cpu_to_be32(le32_to_cpu(blockidx->PageAddress));
 
 		uea_dbg(INS_TO_USBDEV(sc),
 		       "sending block %u for DSP page %u size %u address %x\n",
@@ -1040,7 +1038,7 @@ static void uea_load_page_e4(struct work_struct *work)
 		return;
 
 	p = (struct l1_code *) sc->dsp_firm->data;
-	if (pageno >= p->page_header[0].PageNumber) {
+	if (pageno >= le16_to_cpu(p->page_header[0].PageNumber)) {
 		uea_err(INS_TO_USBDEV(sc), "invalid DSP page %u requested\n", pageno);
 		return;
 	}
@@ -1065,7 +1063,7 @@ static void uea_load_page_e4(struct work_struct *work)
 	bi.bPageNumber = 0xff;
 	bi.wReserved = cpu_to_be16(UEA_RESERVED);
 	bi.dwSize = cpu_to_be32(E4_PAGE_BYTES(p->page_header[0].PageSize));
-	bi.dwAddress = swab32(p->page_header[0].PageAddress);
+	bi.dwAddress = cpu_to_be32(le32_to_cpu(p->page_header[0].PageAddress));
 
 	/* send block info through the IDMA pipe */
 	if (uea_idma_write(sc, &bi, E4_BLOCK_INFO_SIZE))
@@ -1152,9 +1150,9 @@ static int uea_cmv_e1(struct uea_softc *sc,
 	cmv.bDirection = E1_HOSTTOMODEM;
 	cmv.bFunction = function;
 	cmv.wIndex = cpu_to_le16(sc->cmv_dsc.e1.idx);
-	put_unaligned(cpu_to_le32(address), &cmv.dwSymbolicAddress);
+	put_unaligned_le32(address, &cmv.dwSymbolicAddress);
 	cmv.wOffsetAddress = cpu_to_le16(offset);
-	put_unaligned(cpu_to_le32(data >> 16 | data << 16), &cmv.dwData);
+	put_unaligned_le32(data >> 16 | data << 16, &cmv.dwData);
 
 	ret = uea_request(sc, UEA_E1_SET_BLOCK, UEA_MPTX_START, sizeof(cmv), &cmv);
 	if (ret < 0)
@@ -1646,7 +1644,7 @@ static int request_cmvs(struct uea_softc *sc,
 	if (size < 5)
 		goto err_fw_corrupted;
 
-	crc = FW_GET_LONG(data);
+	crc = get_unaligned_le32(data);
 	data += 4;
 	size -= 4;
 	if (crc32_be(0, data, size) != crc)
@@ -1696,9 +1694,9 @@ static int uea_send_cmvs_e1(struct uea_softc *sc)
 			"please update your firmware\n");
 
 		for (i = 0; i < len; i++) {
-			ret = uea_write_cmv_e1(sc, FW_GET_LONG(&cmvs_v1[i].address),
-						FW_GET_WORD(&cmvs_v1[i].offset),
-						FW_GET_LONG(&cmvs_v1[i].data));
+			ret = uea_write_cmv_e1(sc, get_unaligned_le32(&cmvs_v1[i].address),
+						get_unaligned_le16(&cmvs_v1[i].offset),
+						get_unaligned_le32(&cmvs_v1[i].data));
 			if (ret < 0)
 				goto out;
 		}
@@ -1706,9 +1704,9 @@ static int uea_send_cmvs_e1(struct uea_softc *sc)
 		struct uea_cmvs_v2 *cmvs_v2 = cmvs_ptr;
 
 		for (i = 0; i < len; i++) {
-			ret = uea_write_cmv_e1(sc, FW_GET_LONG(&cmvs_v2[i].address),
-						(u16) FW_GET_LONG(&cmvs_v2[i].offset),
-						FW_GET_LONG(&cmvs_v2[i].data));
+			ret = uea_write_cmv_e1(sc, get_unaligned_le32(&cmvs_v2[i].address),
+						(u16) get_unaligned_le32(&cmvs_v2[i].offset),
+						get_unaligned_le32(&cmvs_v2[i].data));
 			if (ret < 0)
 				goto out;
 		}
@@ -1759,10 +1757,10 @@ static int uea_send_cmvs_e4(struct uea_softc *sc)
 
 		for (i = 0; i < len; i++) {
 			ret = uea_write_cmv_e4(sc, 1,
-						FW_GET_LONG(&cmvs_v2[i].group),
-						FW_GET_LONG(&cmvs_v2[i].address),
-						FW_GET_LONG(&cmvs_v2[i].offset),
-						FW_GET_LONG(&cmvs_v2[i].data));
+						get_unaligned_le32(&cmvs_v2[i].group),
+						get_unaligned_le32(&cmvs_v2[i].address),
+						get_unaligned_le32(&cmvs_v2[i].offset),
+						get_unaligned_le32(&cmvs_v2[i].data));
 			if (ret < 0)
 				goto out;
 		}
@@ -1964,7 +1962,7 @@ static void uea_dispatch_cmv_e1(struct uea_softc *sc, struct intr_pkt *intr)
 		if (UEA_CHIP_VERSION(sc) == ADI930
 				&& cmv->bFunction ==  E1_MAKEFUNCTION(2, 2)) {
 			cmv->wIndex = cpu_to_le16(dsc->idx);
-			put_unaligned(cpu_to_le32(dsc->address), &cmv->dwSymbolicAddress);
+			put_unaligned_le32(dsc->address, &cmv->dwSymbolicAddress);
 			cmv->wOffsetAddress = cpu_to_le16(dsc->offset);
 		} else
 			goto bad2;
@@ -1978,11 +1976,11 @@ static void uea_dispatch_cmv_e1(struct uea_softc *sc, struct intr_pkt *intr)
 
 	/* in case of MEMACCESS */
 	if (le16_to_cpu(cmv->wIndex) != dsc->idx ||
-	    le32_to_cpu(get_unaligned(&cmv->dwSymbolicAddress)) != dsc->address ||
+	    get_unaligned_le32(&cmv->dwSymbolicAddress) != dsc->address ||
 	    le16_to_cpu(cmv->wOffsetAddress) != dsc->offset)
 		goto bad2;
 
-	sc->data = le32_to_cpu(get_unaligned(&cmv->dwData));
+	sc->data = get_unaligned_le32(&cmv->dwData);
 	sc->data = sc->data << 16 | sc->data >> 16;
 
 	wake_up_cmv_ack(sc);
diff --git a/trunk/drivers/usb/class/cdc-acm.c b/trunk/drivers/usb/class/cdc-acm.c
index 7b572e75e73c..cefe7f2c6f75 100644
--- a/trunk/drivers/usb/class/cdc-acm.c
+++ b/trunk/drivers/usb/class/cdc-acm.c
@@ -280,7 +280,7 @@ static void acm_ctrl_irq(struct urb *urb)
 
 		case USB_CDC_NOTIFY_SERIAL_STATE:
 
-			newctrl = le16_to_cpu(get_unaligned((__le16 *) data));
+			newctrl = get_unaligned_le16(data);
 
 			if (acm->tty && !acm->clocal && (acm->ctrlin & ~newctrl & ACM_CTRL_DCD)) {
 				dbg("calling hangup");
diff --git a/trunk/drivers/usb/core/inode.c b/trunk/drivers/usb/core/inode.c
index 8607846e3c3f..1d253dd4ea81 100644
--- a/trunk/drivers/usb/core/inode.c
+++ b/trunk/drivers/usb/core/inode.c
@@ -773,7 +773,7 @@ int __init usbfs_init(void)
 	usb_register_notify(&usbfs_nb);
 
 	/* create mount point for usbfs */
-	usbdir = proc_mkdir("usb", proc_bus);
+	usbdir = proc_mkdir("bus/usb", NULL);
 
 	return 0;
 }
@@ -783,6 +783,6 @@ void usbfs_cleanup(void)
 	usb_unregister_notify(&usbfs_nb);
 	unregister_filesystem(&usb_fs_type);
 	if (usbdir)
-		remove_proc_entry("usb", proc_bus);
+		remove_proc_entry("bus/usb", NULL);
 }
 
diff --git a/trunk/drivers/usb/gadget/amd5536udc.c b/trunk/drivers/usb/gadget/amd5536udc.c
index fc6f3483be44..ce337cb5d137 100644
--- a/trunk/drivers/usb/gadget/amd5536udc.c
+++ b/trunk/drivers/usb/gadget/amd5536udc.c
@@ -328,6 +328,7 @@ udc_ep_enable(struct usb_ep *usbep, const struct usb_endpoint_descriptor *desc)
 	u32			tmp;
 	unsigned long		iflags;
 	u8 udc_csr_epix;
+	unsigned		maxpacket;
 
 	if (!usbep
 			|| usbep->name == ep0_string
@@ -354,9 +355,10 @@ udc_ep_enable(struct usb_ep *usbep, const struct usb_endpoint_descriptor *desc)
 	writel(tmp, &dev->ep[ep->num].regs->ctl);
 
 	/* set max packet size */
+	maxpacket = le16_to_cpu(desc->wMaxPacketSize);
 	tmp = readl(&dev->ep[ep->num].regs->bufout_maxpkt);
-	tmp = AMD_ADDBITS(tmp, desc->wMaxPacketSize, UDC_EP_MAX_PKT_SIZE);
-	ep->ep.maxpacket = desc->wMaxPacketSize;
+	tmp = AMD_ADDBITS(tmp, maxpacket, UDC_EP_MAX_PKT_SIZE);
+	ep->ep.maxpacket = maxpacket;
 	writel(tmp, &dev->ep[ep->num].regs->bufout_maxpkt);
 
 	/* IN ep */
@@ -370,8 +372,8 @@ udc_ep_enable(struct usb_ep *usbep, const struct usb_endpoint_descriptor *desc)
 		/* double buffering: fifo size = 2 x max packet size */
 		tmp = AMD_ADDBITS(
 				tmp,
-				desc->wMaxPacketSize * UDC_EPIN_BUFF_SIZE_MULT
-						/ UDC_DWORD_BYTES,
+				maxpacket * UDC_EPIN_BUFF_SIZE_MULT
+					  / UDC_DWORD_BYTES,
 				UDC_EPIN_BUFF_SIZE);
 		writel(tmp, &dev->ep[ep->num].regs->bufin_framenum);
 
@@ -390,7 +392,7 @@ udc_ep_enable(struct usb_ep *usbep, const struct usb_endpoint_descriptor *desc)
 
 		/* set max packet size UDC CSR	*/
 		tmp = readl(&dev->csr->ne[ep->num - UDC_CSR_EP_OUT_IX_OFS]);
-		tmp = AMD_ADDBITS(tmp, desc->wMaxPacketSize,
+		tmp = AMD_ADDBITS(tmp, maxpacket,
 					UDC_CSR_NE_MAX_PKT);
 		writel(tmp, &dev->csr->ne[ep->num - UDC_CSR_EP_OUT_IX_OFS]);
 
@@ -407,7 +409,7 @@ udc_ep_enable(struct usb_ep *usbep, const struct usb_endpoint_descriptor *desc)
 	/* set ep values */
 	tmp = readl(&dev->csr->ne[udc_csr_epix]);
 	/* max packet */
-	tmp = AMD_ADDBITS(tmp, desc->wMaxPacketSize, UDC_CSR_NE_MAX_PKT);
+	tmp = AMD_ADDBITS(tmp, maxpacket, UDC_CSR_NE_MAX_PKT);
 	/* ep number */
 	tmp = AMD_ADDBITS(tmp, desc->bEndpointAddress, UDC_CSR_NE_NUM);
 	/* ep direction */
@@ -2832,7 +2834,7 @@ __acquires(dev->lock)
 		/* make usb request for gadget driver */
 		memset(&setup_data, 0 , sizeof(union udc_setup_data));
 		setup_data.request.bRequest = USB_REQ_SET_CONFIGURATION;
-		setup_data.request.wValue = dev->cur_config;
+		setup_data.request.wValue = cpu_to_le16(dev->cur_config);
 
 		/* programm the NE registers */
 		for (i = 0; i < UDC_EP_NUM; i++) {
@@ -2881,8 +2883,8 @@ __acquires(dev->lock)
 		memset(&setup_data, 0 , sizeof(union udc_setup_data));
 		setup_data.request.bRequest = USB_REQ_SET_INTERFACE;
 		setup_data.request.bRequestType = USB_RECIP_INTERFACE;
-		setup_data.request.wValue = dev->cur_alt;
-		setup_data.request.wIndex = dev->cur_intf;
+		setup_data.request.wValue = cpu_to_le16(dev->cur_alt);
+		setup_data.request.wIndex = cpu_to_le16(dev->cur_intf);
 
 		DBG(dev, "SET_INTERFACE interrupt: alt=%d intf=%d\n",
 				dev->cur_alt, dev->cur_intf);
diff --git a/trunk/drivers/usb/gadget/at91_udc.c b/trunk/drivers/usb/gadget/at91_udc.c
index 9b913afb2e6d..274c60a970cd 100644
--- a/trunk/drivers/usb/gadget/at91_udc.c
+++ b/trunk/drivers/usb/gadget/at91_udc.c
@@ -231,6 +231,7 @@ static int proc_udc_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations proc_ops = {
+	.owner		= THIS_MODULE,
 	.open		= proc_udc_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -239,15 +240,7 @@ static const struct file_operations proc_ops = {
 
 static void create_debug_file(struct at91_udc *udc)
 {
-	struct proc_dir_entry *pde;
-
-	pde = create_proc_entry (debug_filename, 0, NULL);
-	udc->pde = pde;
-	if (pde == NULL)
-		return;
-
-	pde->proc_fops = &proc_ops;
-	pde->data = udc;
+	udc->pde = proc_create_data(debug_filename, 0, NULL, &proc_ops, udc);
 }
 
 static void remove_debug_file(struct at91_udc *udc)
diff --git a/trunk/drivers/usb/gadget/dummy_hcd.c b/trunk/drivers/usb/gadget/dummy_hcd.c
index 66293105d136..42036192a03c 100644
--- a/trunk/drivers/usb/gadget/dummy_hcd.c
+++ b/trunk/drivers/usb/gadget/dummy_hcd.c
@@ -1555,8 +1555,7 @@ hub_descriptor (struct usb_hub_descriptor *desc)
 	memset (desc, 0, sizeof *desc);
 	desc->bDescriptorType = 0x29;
 	desc->bDescLength = 9;
-	desc->wHubCharacteristics = (__force __u16)
-			(__constant_cpu_to_le16 (0x0001));
+	desc->wHubCharacteristics = cpu_to_le16(0x0001);
 	desc->bNbrPorts = 1;
 	desc->bitmap [0] = 0xff;
 	desc->bitmap [1] = 0xff;
diff --git a/trunk/drivers/usb/gadget/gmidi.c b/trunk/drivers/usb/gadget/gmidi.c
index ff3a8513e64d..7f4d4828e3aa 100644
--- a/trunk/drivers/usb/gadget/gmidi.c
+++ b/trunk/drivers/usb/gadget/gmidi.c
@@ -229,7 +229,7 @@ static const struct usb_ac_header_descriptor_1 ac_header_desc = {
 	.bDescriptorType =	USB_DT_CS_INTERFACE,
 	.bDescriptorSubtype =	USB_MS_HEADER,
 	.bcdADC =		__constant_cpu_to_le16(0x0100),
-	.wTotalLength =		USB_DT_AC_HEADER_SIZE(1),
+	.wTotalLength =		__constant_cpu_to_le16(USB_DT_AC_HEADER_SIZE(1)),
 	.bInCollection =	1,
 	.baInterfaceNr = {
 		[0] =		GMIDI_MS_INTERFACE,
@@ -253,9 +253,9 @@ static const struct usb_ms_header_descriptor ms_header_desc = {
 	.bDescriptorType =	USB_DT_CS_INTERFACE,
 	.bDescriptorSubtype =	USB_MS_HEADER,
 	.bcdMSC =		__constant_cpu_to_le16(0x0100),
-	.wTotalLength =		USB_DT_MS_HEADER_SIZE
+	.wTotalLength =		__constant_cpu_to_le16(USB_DT_MS_HEADER_SIZE
 				+ 2*USB_DT_MIDI_IN_SIZE
-				+ 2*USB_DT_MIDI_OUT_SIZE(1),
+				+ 2*USB_DT_MIDI_OUT_SIZE(1)),
 };
 
 #define JACK_IN_EMB	1
diff --git a/trunk/drivers/usb/gadget/goku_udc.c b/trunk/drivers/usb/gadget/goku_udc.c
index 64a592cbbe7b..be6613afedbf 100644
--- a/trunk/drivers/usb/gadget/goku_udc.c
+++ b/trunk/drivers/usb/gadget/goku_udc.c
@@ -127,7 +127,7 @@ goku_ep_enable(struct usb_ep *_ep, const struct usb_endpoint_descriptor *desc)
 
 	/* enabling the no-toggle interrupt mode would need an api hook */
 	mode = 0;
-	max = le16_to_cpu(get_unaligned(&desc->wMaxPacketSize));
+	max = get_unaligned_le16(&desc->wMaxPacketSize);
 	switch (max) {
 	case 64:	mode++;
 	case 32:	mode++;
diff --git a/trunk/drivers/usb/gadget/m66592-udc.h b/trunk/drivers/usb/gadget/m66592-udc.h
index be0a4c1f80a2..f118f00f1466 100644
--- a/trunk/drivers/usb/gadget/m66592-udc.h
+++ b/trunk/drivers/usb/gadget/m66592-udc.h
@@ -485,7 +485,7 @@ struct m66592 {
 	struct m66592_ep	*epaddr2ep[16];
 
 	struct usb_request	*ep0_req;	/* for internal request */
-	u16			ep0_data;	/* for internal request */
+	__le16			ep0_data;	/* for internal request */
 	u16			old_vbus;
 
 	struct timer_list	timer;
diff --git a/trunk/drivers/usb/gadget/omap_udc.c b/trunk/drivers/usb/gadget/omap_udc.c
index 95f7662376f1..881d74c3d964 100644
--- a/trunk/drivers/usb/gadget/omap_udc.c
+++ b/trunk/drivers/usb/gadget/omap_udc.c
@@ -2504,6 +2504,7 @@ static int proc_udc_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations proc_ops = {
+	.owner		= THIS_MODULE,
 	.open		= proc_udc_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -2512,11 +2513,7 @@ static const struct file_operations proc_ops = {
 
 static void create_proc_file(void)
 {
-	struct proc_dir_entry *pde;
-
-	pde = create_proc_entry (proc_filename, 0, NULL);
-	if (pde)
-		pde->proc_fops = &proc_ops;
+	proc_create(proc_filename, 0, NULL, &proc_ops);
 }
 
 static void remove_proc_file(void)
diff --git a/trunk/drivers/usb/gadget/rndis.c b/trunk/drivers/usb/gadget/rndis.c
index bd58dd504f6f..d0677f5d3cd5 100644
--- a/trunk/drivers/usb/gadget/rndis.c
+++ b/trunk/drivers/usb/gadget/rndis.c
@@ -183,14 +183,10 @@ gen_ndis_query_resp (int configNr, u32 OID, u8 *buf, unsigned buf_len,
 		DBG("query OID %08x value, len %d:\n", OID, buf_len);
 		for (i = 0; i < buf_len; i += 16) {
 			DBG("%03d: %08x %08x %08x %08x\n", i,
-				le32_to_cpu(get_unaligned((__le32 *)
-					&buf[i])),
-				le32_to_cpu(get_unaligned((__le32 *)
-					&buf[i + 4])),
-				le32_to_cpu(get_unaligned((__le32 *)
-					&buf[i + 8])),
-				le32_to_cpu(get_unaligned((__le32 *)
-					&buf[i + 12])));
+				get_unaligned_le32(&buf[i]),
+				get_unaligned_le32(&buf[i + 4]),
+				get_unaligned_le32(&buf[i + 8]),
+				get_unaligned_le32(&buf[i + 12]));
 		}
 	}
 
@@ -666,7 +662,7 @@ gen_ndis_query_resp (int configNr, u32 OID, u8 *buf, unsigned buf_len,
 		break;
 	case OID_PNP_QUERY_POWER:
 		DBG("%s: OID_PNP_QUERY_POWER D%d\n", __func__,
-				le32_to_cpu(get_unaligned((__le32 *)buf)) - 1);
+				get_unaligned_le32(buf) - 1);
 		/* only suspend is a real power state, and
 		 * it can't be entered by OID_PNP_SET_POWER...
 		 */
@@ -705,14 +701,10 @@ static int gen_ndis_set_resp (u8 configNr, u32 OID, u8 *buf, u32 buf_len,
 		DBG("set OID %08x value, len %d:\n", OID, buf_len);
 		for (i = 0; i < buf_len; i += 16) {
 			DBG("%03d: %08x %08x %08x %08x\n", i,
-				le32_to_cpu(get_unaligned((__le32 *)
-					&buf[i])),
-				le32_to_cpu(get_unaligned((__le32 *)
-					&buf[i + 4])),
-				le32_to_cpu(get_unaligned((__le32 *)
-					&buf[i + 8])),
-				le32_to_cpu(get_unaligned((__le32 *)
-					&buf[i + 12])));
+				get_unaligned_le32(&buf[i]),
+				get_unaligned_le32(&buf[i + 4]),
+				get_unaligned_le32(&buf[i + 8]),
+				get_unaligned_le32(&buf[i + 12]));
 		}
 	}
 
@@ -726,8 +718,7 @@ static int gen_ndis_set_resp (u8 configNr, u32 OID, u8 *buf, u32 buf_len,
 		 *	PROMISCUOUS, DIRECTED,
 		 *	MULTICAST, ALL_MULTICAST, BROADCAST
 		 */
-		*params->filter = (u16) le32_to_cpu(get_unaligned(
-				(__le32 *)buf));
+		*params->filter = (u16)get_unaligned_le32(buf);
 		DBG("%s: OID_GEN_CURRENT_PACKET_FILTER %08x\n",
 			__func__, *params->filter);
 
@@ -777,7 +768,7 @@ static int gen_ndis_set_resp (u8 configNr, u32 OID, u8 *buf, u32 buf_len,
 		 * resuming, Windows forces a reset, and then SET_POWER D0.
 		 * FIXME ... then things go batty; Windows wedges itself.
 		 */
-		i = le32_to_cpu(get_unaligned((__le32 *)buf));
+		i = get_unaligned_le32(buf);
 		DBG("%s: OID_PNP_SET_POWER D%d\n", __func__, i - 1);
 		switch (i) {
 		case NdisDeviceStateD0:
@@ -1064,8 +1055,8 @@ int rndis_msg_parser (u8 configNr, u8 *buf)
 		return -ENOMEM;
 
 	tmp = (__le32 *) buf;
-	MsgType   = le32_to_cpu(get_unaligned(tmp++));
-	MsgLength = le32_to_cpu(get_unaligned(tmp++));
+	MsgType   = get_unaligned_le32(tmp++);
+	MsgLength = get_unaligned_le32(tmp++);
 
 	if (configNr >= RNDIS_MAX_CONFIGS)
 		return -ENOTSUPP;
@@ -1296,10 +1287,9 @@ int rndis_rm_hdr(struct sk_buff *skb)
 	tmp++;
 
 	/* DataOffset, DataLength */
-	if (!skb_pull(skb, le32_to_cpu(get_unaligned(tmp++))
-			+ 8 /* offset of DataOffset */))
+	if (!skb_pull(skb, get_unaligned_le32(tmp++) + 8))
 		return -EOVERFLOW;
-	skb_trim(skb, le32_to_cpu(get_unaligned(tmp++)));
+	skb_trim(skb, get_unaligned_le32(tmp++));
 
 	return 0;
 }
diff --git a/trunk/drivers/usb/gadget/usbstring.c b/trunk/drivers/usb/gadget/usbstring.c
index 878e428a0ec1..4154be375c7a 100644
--- a/trunk/drivers/usb/gadget/usbstring.c
+++ b/trunk/drivers/usb/gadget/usbstring.c
@@ -74,7 +74,7 @@ static int utf8_to_utf16le(const char *s, __le16 *cp, unsigned len)
 				goto fail;
 		} else
 			uchar = c;
-		put_unaligned (cpu_to_le16 (uchar), cp++);
+		put_unaligned_le16(uchar, cp++);
 		count++;
 		len--;
 	}
diff --git a/trunk/drivers/usb/host/ehci-dbg.c b/trunk/drivers/usb/host/ehci-dbg.c
index 4af90df8e7de..0f82fdcaef09 100644
--- a/trunk/drivers/usb/host/ehci-dbg.c
+++ b/trunk/drivers/usb/host/ehci-dbg.c
@@ -398,7 +398,7 @@ static void qh_lines (
 	unsigned		size = *sizep;
 	char			*next = *nextp;
 	char			mark;
-	u32			list_end = EHCI_LIST_END(ehci);
+	__le32			list_end = EHCI_LIST_END(ehci);
 
 	if (qh->hw_qtd_next == list_end)	/* NEC does this */
 		mark = '@';
diff --git a/trunk/drivers/usb/host/ehci-hub.c b/trunk/drivers/usb/host/ehci-hub.c
index efffef64f59d..382587c4457c 100644
--- a/trunk/drivers/usb/host/ehci-hub.c
+++ b/trunk/drivers/usb/host/ehci-hub.c
@@ -530,7 +530,7 @@ ehci_hub_descriptor (
 	if (HCS_INDICATOR (ehci->hcs_params))
 		temp |= 0x0080;		/* per-port indicators (LEDs) */
 #endif
-	desc->wHubCharacteristics = (__force __u16)cpu_to_le16 (temp);
+	desc->wHubCharacteristics = cpu_to_le16(temp);
 }
 
 /*-------------------------------------------------------------------------*/
@@ -770,7 +770,7 @@ static int ehci_hub_control (
 	if (status & ~0xffff)	/* only if wPortChange is interesting */
 #endif
 		dbg_port (ehci, "GetStatus", wIndex + 1, temp);
-		put_unaligned(cpu_to_le32 (status), (__le32 *) buf);
+		put_unaligned_le32(status, buf);
 		break;
 	case SetHubFeature:
 		switch (wValue) {
diff --git a/trunk/drivers/usb/host/ehci-q.c b/trunk/drivers/usb/host/ehci-q.c
index 5ae689139dd0..b85b54160cda 100644
--- a/trunk/drivers/usb/host/ehci-q.c
+++ b/trunk/drivers/usb/host/ehci-q.c
@@ -285,7 +285,7 @@ qh_completions (struct ehci_hcd *ehci, struct ehci_qh *qh)
 	int			stopped;
 	unsigned		count = 0;
 	u8			state;
-	u32			halt = HALT_BIT(ehci);
+	__le32			halt = HALT_BIT(ehci);
 
 	if (unlikely (list_empty (&qh->qtd_list)))
 		return count;
@@ -883,7 +883,7 @@ static struct ehci_qh *qh_append_tds (
 )
 {
 	struct ehci_qh		*qh = NULL;
-	u32			qh_addr_mask = cpu_to_hc32(ehci, 0x7f);
+	__hc32			qh_addr_mask = cpu_to_hc32(ehci, 0x7f);
 
 	qh = (struct ehci_qh *) *ptr;
 	if (unlikely (qh == NULL)) {
diff --git a/trunk/drivers/usb/host/ohci-hub.c b/trunk/drivers/usb/host/ohci-hub.c
index 5be3bb3e6a9d..17dc2eccda83 100644
--- a/trunk/drivers/usb/host/ohci-hub.c
+++ b/trunk/drivers/usb/host/ohci-hub.c
@@ -736,14 +736,14 @@ static int ohci_hub_control (
 		break;
 	case GetHubStatus:
 		temp = roothub_status (ohci) & ~(RH_HS_CRWE | RH_HS_DRWE);
-		put_unaligned(cpu_to_le32 (temp), (__le32 *) buf);
+		put_unaligned_le32(temp, buf);
 		break;
 	case GetPortStatus:
 		if (!wIndex || wIndex > ports)
 			goto error;
 		wIndex--;
 		temp = roothub_portstatus (ohci, wIndex);
-		put_unaligned(cpu_to_le32 (temp), (__le32 *) buf);
+		put_unaligned_le32(temp, buf);
 
 #ifndef	OHCI_VERBOSE_DEBUG
 	if (*(u16*)(buf+2))	/* only if wPortChange is interesting */
diff --git a/trunk/drivers/usb/host/r8a66597-hcd.c b/trunk/drivers/usb/host/r8a66597-hcd.c
index f4fa93dabdde..16667342b3c3 100644
--- a/trunk/drivers/usb/host/r8a66597-hcd.c
+++ b/trunk/drivers/usb/host/r8a66597-hcd.c
@@ -993,7 +993,7 @@ static void prepare_setup_packet(struct r8a66597 *r8a66597,
 				 struct r8a66597_td *td)
 {
 	int i;
-	u16 *p = (u16 *)td->urb->setup_packet;
+	__le16 *p = (__le16 *)td->urb->setup_packet;
 	unsigned long setup_addr = USBREQ;
 
 	r8a66597_write(r8a66597, make_devsel(td->address) | td->maxpacket,
@@ -1001,7 +1001,7 @@ static void prepare_setup_packet(struct r8a66597 *r8a66597,
 	r8a66597_write(r8a66597, ~(SIGN | SACK), INTSTS1);
 
 	for (i = 0; i < 4; i++) {
-		r8a66597_write(r8a66597, cpu_to_le16(p[i]), setup_addr);
+		r8a66597_write(r8a66597, le16_to_cpu(p[i]), setup_addr);
 		setup_addr += 2;
 	}
 	r8a66597_write(r8a66597, SUREQ, DCPCTR);
@@ -2131,7 +2131,7 @@ static int r8a66597_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 	case GetPortStatus:
 		if (wIndex > R8A66597_MAX_ROOT_HUB)
 			goto error;
-		*(u32 *)buf = cpu_to_le32(rh->port);
+		*(__le32 *)buf = cpu_to_le32(rh->port);
 		break;
 	case SetPortFeature:
 		if (wIndex > R8A66597_MAX_ROOT_HUB)
diff --git a/trunk/drivers/usb/host/sl811-hcd.c b/trunk/drivers/usb/host/sl811-hcd.c
index 274276cf8621..426575247b23 100644
--- a/trunk/drivers/usb/host/sl811-hcd.c
+++ b/trunk/drivers/usb/host/sl811-hcd.c
@@ -1100,7 +1100,7 @@ sl811h_hub_descriptor (
 	/* no overcurrent errors detection/handling */
 	temp |= 0x0010;
 
-	desc->wHubCharacteristics = (__force __u16)cpu_to_le16(temp);
+	desc->wHubCharacteristics = cpu_to_le16(temp);
 
 	/* two bitmaps:  ports removable, and legacy PortPwrCtrlMask */
 	desc->bitmap[0] = 0 << 1;
@@ -1506,15 +1506,7 @@ static const char proc_filename[] = "driver/sl811h";
 
 static void create_debug_file(struct sl811 *sl811)
 {
-	struct proc_dir_entry *pde;
-
-	pde = create_proc_entry(proc_filename, 0, NULL);
-	if (pde == NULL)
-		return;
-
-	pde->proc_fops = &proc_ops;
-	pde->data = sl811;
-	sl811->pde = pde;
+	sl811->pde = proc_create_data(proc_filename, 0, NULL, &proc_ops, sl811);
 }
 
 static void remove_debug_file(struct sl811 *sl811)
diff --git a/trunk/drivers/usb/serial/aircable.c b/trunk/drivers/usb/serial/aircable.c
index a238817762ad..9b1bb347dc2d 100644
--- a/trunk/drivers/usb/serial/aircable.c
+++ b/trunk/drivers/usb/serial/aircable.c
@@ -209,7 +209,7 @@ static void aircable_send(struct usb_serial_port *port)
 	int count, result;
 	struct aircable_private *priv = usb_get_serial_port_data(port);
 	unsigned char* buf;
-	u16 *dbuf;
+	__le16 *dbuf;
 	dbg("%s - port %d", __func__, port->number);
 	if (port->write_urb_busy)
 		return;
@@ -227,7 +227,7 @@ static void aircable_send(struct usb_serial_port *port)
 
 	buf[0] = TX_HEADER_0;
 	buf[1] = TX_HEADER_1;
-	dbuf = (u16 *)&buf[2];
+	dbuf = (__le16 *)&buf[2];
 	*dbuf = cpu_to_le16((u16)count);
 	serial_buf_get(priv->tx_buf,buf + HCI_HEADER_LENGTH, MAX_HCI_FRAMESIZE);
 
diff --git a/trunk/drivers/usb/serial/cypress_m8.c b/trunk/drivers/usb/serial/cypress_m8.c
index 32121794808d..0230d3c0888a 100644
--- a/trunk/drivers/usb/serial/cypress_m8.c
+++ b/trunk/drivers/usb/serial/cypress_m8.c
@@ -541,7 +541,7 @@ static int cypress_earthmate_startup (struct usb_serial *serial)
 	/* All Earthmate devices use the separated-count packet
 	   format!  Idiotic. */
 	priv->pkt_fmt = packet_format_1;
-	if (serial->dev->descriptor.idProduct != PRODUCT_ID_EARTHMATEUSB) {
+	if (serial->dev->descriptor.idProduct != cpu_to_le16(PRODUCT_ID_EARTHMATEUSB)) {
 		/* The old original USB Earthmate seemed able to
 		   handle GET_CONFIG requests; everything they've
 		   produced since that time crashes if this command is
diff --git a/trunk/drivers/usb/serial/ftdi_sio.c b/trunk/drivers/usb/serial/ftdi_sio.c
index 23f51a41093e..c7329f43d9c9 100644
--- a/trunk/drivers/usb/serial/ftdi_sio.c
+++ b/trunk/drivers/usb/serial/ftdi_sio.c
@@ -1104,7 +1104,7 @@ static int ftdi_mtxorb_hack_setup(struct usb_serial *serial)
 	struct usb_endpoint_descriptor *ep_desc = &ep->desc;
 
 	if (ep->enabled && ep_desc->wMaxPacketSize == 0) {
-		ep_desc->wMaxPacketSize = 0x40;
+		ep_desc->wMaxPacketSize = cpu_to_le16(0x40);
 		info("Fixing invalid wMaxPacketSize on read pipe");
 	}
 
diff --git a/trunk/drivers/usb/serial/io_edgeport.c b/trunk/drivers/usb/serial/io_edgeport.c
index ce2e487f3240..06b52f4098f1 100644
--- a/trunk/drivers/usb/serial/io_edgeport.c
+++ b/trunk/drivers/usb/serial/io_edgeport.c
@@ -2993,7 +2993,7 @@ static int edge_startup (struct usb_serial *serial)
 				usb_fill_bulk_urb(edge_serial->read_urb, dev,
 						  usb_rcvbulkpipe(dev, endpoint->bEndpointAddress),
 						  edge_serial->bulk_in_buffer,
-						  endpoint->wMaxPacketSize,
+						  le16_to_cpu(endpoint->wMaxPacketSize),
 						  edge_bulk_in_callback,
 						  edge_serial);
 				bulk_in_found = true;
diff --git a/trunk/drivers/usb/serial/kl5kusb105.c b/trunk/drivers/usb/serial/kl5kusb105.c
index b395ac759888..f328948d74e3 100644
--- a/trunk/drivers/usb/serial/kl5kusb105.c
+++ b/trunk/drivers/usb/serial/kl5kusb105.c
@@ -54,6 +54,7 @@
 #include <linux/tty_flip.h>
 #include <linux/module.h>
 #include <asm/uaccess.h>
+#include <asm/unaligned.h>
 #include <linux/usb.h>
 #include <linux/usb/serial.h>
 #include "kl5kusb105.h"
@@ -235,7 +236,7 @@ static int klsi_105_get_line_state(struct usb_serial_port *port,
 	if (rc < 0)
 		err("Reading line status failed (error = %d)", rc);
 	else {
-		status = le16_to_cpu(*(u16 *)status_buf);
+		status = le16_to_cpu(get_unaligned((__le16 *)status_buf));
 
 		info("%s - read status %x %x", __func__,
 		     status_buf[0], status_buf[1]);
diff --git a/trunk/drivers/usb/serial/oti6858.c b/trunk/drivers/usb/serial/oti6858.c
index d92bb6501c84..a9625c180dc3 100644
--- a/trunk/drivers/usb/serial/oti6858.c
+++ b/trunk/drivers/usb/serial/oti6858.c
@@ -98,7 +98,7 @@ struct oti6858_buf {
 
 /* format of the control packet */
 struct oti6858_control_pkt {
-	u16	divisor;	/* baud rate = 96000000 / (16 * divisor), LE */
+	__le16	divisor;	/* baud rate = 96000000 / (16 * divisor), LE */
 #define OTI6858_MAX_BAUD_RATE	3000000
 	u8	frame_fmt;
 #define FMT_STOP_BITS_MASK	0xc0
@@ -211,7 +211,7 @@ struct oti6858_private {
 	struct delayed_work delayed_write_work;
 
 	struct {
-		u16 divisor;
+		__le16 divisor;
 		u8 frame_fmt;
 		u8 control;
 	} pending_setup;
@@ -450,7 +450,7 @@ static void oti6858_set_termios(struct usb_serial_port *port,
 	unsigned long flags;
 	unsigned int cflag;
 	u8 frame_fmt, control;
-	u16 divisor;
+	__le16 divisor;
 	int br;
 
 	dbg("%s(port = %d)", __func__, port->number);
@@ -505,11 +505,12 @@ static void oti6858_set_termios(struct usb_serial_port *port,
 		divisor = 0;
 	} else {
 		int real_br;
+		int new_divisor;
 		br = min(br, OTI6858_MAX_BAUD_RATE);
 
-		divisor = (96000000 + 8 * br) / (16 * br);
-		real_br = 96000000 / (16 * divisor);
-		divisor = cpu_to_le16(divisor);
+		new_divisor = (96000000 + 8 * br) / (16 * br);
+		real_br = 96000000 / (16 * new_divisor);
+		divisor = cpu_to_le16(new_divisor);
 		tty_encode_baud_rate(port->tty, real_br, real_br);
 	}
 
diff --git a/trunk/drivers/usb/serial/spcp8x5.c b/trunk/drivers/usb/serial/spcp8x5.c
index 2282d620186e..55b2570b8b8b 100644
--- a/trunk/drivers/usb/serial/spcp8x5.c
+++ b/trunk/drivers/usb/serial/spcp8x5.c
@@ -310,17 +310,18 @@ static int spcp8x5_startup(struct usb_serial *serial)
 	struct spcp8x5_private *priv;
 	int i;
 	enum spcp8x5_type type = SPCP825_007_TYPE;
+	u16 product = le16_to_cpu(serial->dev->descriptor.idProduct);
 
-	if (serial->dev->descriptor.idProduct == 0x0201)
+	if (product == 0x0201)
 		type = SPCP825_007_TYPE;
-	else if (serial->dev->descriptor.idProduct == 0x0231)
+	else if (product == 0x0231)
 		type = SPCP835_TYPE;
-	else if (serial->dev->descriptor.idProduct == 0x0235)
+	else if (product == 0x0235)
 		type = SPCP825_008_TYPE;
-	else if (serial->dev->descriptor.idProduct == 0x0204)
+	else if (product == 0x0204)
 		type = SPCP825_INTERMATIC_TYPE;
-	else if (serial->dev->descriptor.idProduct == 0x0471 &&
-		 serial->dev->descriptor.idVendor == 0x081e)
+	else if (product == 0x0471 &&
+		 serial->dev->descriptor.idVendor == cpu_to_le16(0x081e))
 		type = SPCP825_PHILIP_TYPE;
 	dev_dbg(&serial->dev->dev, "device type = %d\n", (int)type);
 
diff --git a/trunk/drivers/video/Kconfig b/trunk/drivers/video/Kconfig
index e3dc8f8d0c3e..a576dc261732 100644
--- a/trunk/drivers/video/Kconfig
+++ b/trunk/drivers/video/Kconfig
@@ -139,6 +139,30 @@ config FB_SYS_IMAGEBLIT
 	  blitting. This is used by drivers that don't provide their own
 	  (accelerated) version and the framebuffer is in system RAM.
 
+menuconfig FB_FOREIGN_ENDIAN
+	bool "Framebuffer foreign endianness support"
+	depends on FB
+	---help---
+	  This menu will let you enable support for the framebuffers with
+	  non-native endianness (e.g. Little-Endian framebuffer on a
+	  Big-Endian machine). Most probably you don't have such hardware,
+	  so it's safe to say "n" here.
+
+choice
+	prompt "Choice endianness support"
+	depends on FB_FOREIGN_ENDIAN
+
+config FB_BOTH_ENDIAN
+	bool "Support for Big- and Little-Endian framebuffers"
+
+config FB_BIG_ENDIAN
+	bool "Support for Big-Endian framebuffers only"
+
+config FB_LITTLE_ENDIAN
+	bool "Support for Little-Endian framebuffers only"
+
+endchoice
+
 config FB_SYS_FOPS
        tristate
        depends on FB
@@ -149,6 +173,16 @@ config FB_DEFERRED_IO
 	depends on FB
 	default y
 
+config FB_METRONOME
+	tristate
+	depends on FB
+	depends on FB_DEFERRED_IO
+
+config FB_HECUBA
+	tristate
+	depends on FB
+	depends on FB_DEFERRED_IO
+
 config FB_SVGALIB
 	tristate
 	depends on FB
@@ -546,7 +580,7 @@ config FB_VGA16
 
 config FB_BF54X_LQ043
 	tristate "SHARP LQ043 TFT LCD (BF548 EZKIT)"
-	depends on FB && (BF54x)
+	depends on FB && (BF54x) && !BF542
 	select FB_CFB_FILLRECT
 	select FB_CFB_COPYAREA
 	select FB_CFB_IMAGEBLIT
@@ -674,20 +708,18 @@ config FB_IMAC
 	help
 	  This is the frame buffer device driver for the Intel-based Macintosh
 
-config FB_HECUBA
-       tristate "Hecuba board support"
+config FB_N411
+       tristate "N411 Apollo/Hecuba devkit support"
        depends on FB && X86 && MMU
        select FB_SYS_FILLRECT
        select FB_SYS_COPYAREA
        select FB_SYS_IMAGEBLIT
        select FB_SYS_FOPS
        select FB_DEFERRED_IO
+       select FB_HECUBA
        help
-         This enables support for the Hecuba board. This driver was tested
-         with an E-Ink 800x600 display and x86 SBCs through a 16 bit GPIO
-         interface (8 bit data, 4 bit control). If you anticipate using
-         this driver, say Y or M; otherwise say N. You must specify the
-         GPIO IO address to be used for setting control and data.
+         This enables support for the Apollo display controller in its
+         Hecuba form using the n411 devkit.
 
 config FB_HGA
 	tristate "Hercules mono graphics support"
@@ -1087,7 +1119,7 @@ config FB_CARILLO_RANCH
 	  This driver supports the LE80578 (Carillo Ranch) board
 
 config FB_INTEL
-	tristate "Intel 830M/845G/852GM/855GM/865G/915G/945G support (EXPERIMENTAL)"
+	tristate "Intel 830M/845G/852GM/855GM/865G/915G/945G/945GM/965G/965GM support (EXPERIMENTAL)"
 	depends on FB && EXPERIMENTAL && PCI && X86
 	select AGP
 	select AGP_INTEL
@@ -1097,7 +1129,7 @@ config FB_INTEL
 	select FB_CFB_IMAGEBLIT
 	help
 	  This driver supports the on-board graphics built in to the Intel
-          830M/845G/852GM/855GM/865G/915G/915GM/945G/945GM chipsets.
+          830M/845G/852GM/855GM/865G/915G/915GM/945G/945GM/965G/965GM chipsets.
           Say Y if you have and plan to use such a board.
 
 	  If you say Y here and want DDC/I2C support you must first say Y to
@@ -1779,6 +1811,16 @@ config FB_MBX_DEBUG
 
          If unsure, say N.
 
+config FB_FSL_DIU
+	tristate "Freescale DIU framebuffer support"
+	depends on FB && FSL_SOC
+	select FB_CFB_FILLRECT
+	select FB_CFB_COPYAREA
+	select FB_CFB_IMAGEBLIT
+	select PPC_LIB_RHEAP
+	---help---
+	  Framebuffer driver for the Freescale SoC DIU
+
 config FB_W100
 	tristate "W100 frame buffer support"
 	depends on FB && PXA_SHARPSL
@@ -1893,19 +1935,18 @@ config FB_XILINX
 	  framebuffer. ML300 carries a 640*480 LCD display on the board,
 	  ML403 uses a standard DB15 VGA connector.
 
-config FB_METRONOME
-       tristate "Metronome display controller support"
+config FB_AM200EPD
+       tristate "AM-200 E-Ink EPD devkit support"
        depends on FB && ARCH_PXA && MMU
        select FB_SYS_FILLRECT
        select FB_SYS_COPYAREA
        select FB_SYS_IMAGEBLIT
        select FB_SYS_FOPS
        select FB_DEFERRED_IO
+       select FB_METRONOME
        help
-         This enables support for the Metronome display controller. Tested
-         with an E-Ink 800x600 display and Gumstix Connex through an AMLCD
-         interface. Please read <file:Documentation/fb/metronomefb.txt>
-         for more information.
+         This enables support for the Metronome display controller used on
+         the E-Ink AM-200 EPD devkit.
 
 config FB_VIRTUAL
 	tristate "Virtual Frame Buffer support (ONLY FOR TESTING!)"
diff --git a/trunk/drivers/video/Makefile b/trunk/drivers/video/Makefile
index f172b9b73314..04bca35403ff 100644
--- a/trunk/drivers/video/Makefile
+++ b/trunk/drivers/video/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_FB_DEFERRED_IO)   += fb_defio.o
 
 # Hardware specific drivers go first
 obj-$(CONFIG_FB_AMIGA)            += amifb.o c2p.o
+obj-$(CONFIG_FB_AM200EPD)         += am200epd.o
 obj-$(CONFIG_FB_ARC)              += arcfb.o
 obj-$(CONFIG_FB_CLPS711X)         += clps711xfb.o
 obj-$(CONFIG_FB_CYBER2000)        += cyber2000fb.o
@@ -107,6 +108,7 @@ obj-$(CONFIG_FB_METRONOME)        += metronomefb.o
 obj-$(CONFIG_FB_S1D13XXX)	  += s1d13xxxfb.o
 obj-$(CONFIG_FB_IMX)              += imxfb.o
 obj-$(CONFIG_FB_S3C2410)	  += s3c2410fb.o
+obj-$(CONFIG_FB_FSL_DIU)	  += fsl-diu-fb.o
 obj-$(CONFIG_FB_PNX4008_DUM)	  += pnx4008/
 obj-$(CONFIG_FB_PNX4008_DUM_RGB)  += pnx4008/
 obj-$(CONFIG_FB_IBM_GXT4500)	  += gxt4500.o
diff --git a/trunk/drivers/video/am200epd.c b/trunk/drivers/video/am200epd.c
new file mode 100644
index 000000000000..51e26c1f5e8b
--- /dev/null
+++ b/trunk/drivers/video/am200epd.c
@@ -0,0 +1,295 @@
+/*
+ * linux/drivers/video/am200epd.c -- Platform device for AM200 EPD kit
+ *
+ * Copyright (C) 2008, Jaya Kumar
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file COPYING in the main directory of this archive for
+ * more details.
+ *
+ * Layout is based on skeletonfb.c by James Simmons and Geert Uytterhoeven.
+ *
+ * This work was made possible by help and equipment support from E-Ink
+ * Corporation. http://support.eink.com/community
+ *
+ * This driver is written to be used with the Metronome display controller.
+ * on the AM200 EPD prototype kit/development kit with an E-Ink 800x600
+ * Vizplex EPD on a Gumstix board using the Lyre interface board.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/fb.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/list.h>
+#include <linux/uaccess.h>
+#include <linux/irq.h>
+
+#include <video/metronomefb.h>
+
+#include <asm/arch/pxa-regs.h>
+
+/* register offsets for gpio control */
+#define LED_GPIO_PIN 51
+#define STDBY_GPIO_PIN 48
+#define RST_GPIO_PIN 49
+#define RDY_GPIO_PIN 32
+#define ERR_GPIO_PIN 17
+#define PCBPWR_GPIO_PIN 16
+
+#define AF_SEL_GPIO_N 0x3
+#define GAFR0_U_OFFSET(pin) ((pin - 16) * 2)
+#define GAFR1_L_OFFSET(pin) ((pin - 32) * 2)
+#define GAFR1_U_OFFSET(pin) ((pin - 48) * 2)
+#define GPDR1_OFFSET(pin) (pin - 32)
+#define GPCR1_OFFSET(pin) (pin - 32)
+#define GPSR1_OFFSET(pin) (pin - 32)
+#define GPCR0_OFFSET(pin) (pin)
+#define GPSR0_OFFSET(pin) (pin)
+
+static void am200_set_gpio_output(int pin, int val)
+{
+	u8 index;
+
+	index = pin >> 4;
+
+	switch (index) {
+	case 1:
+		if (val)
+			GPSR0 |= (1 << GPSR0_OFFSET(pin));
+		else
+			GPCR0 |= (1 << GPCR0_OFFSET(pin));
+		break;
+	case 2:
+		break;
+	case 3:
+		if (val)
+			GPSR1 |= (1 << GPSR1_OFFSET(pin));
+		else
+			GPCR1 |= (1 << GPCR1_OFFSET(pin));
+		break;
+	default:
+		printk(KERN_ERR "unimplemented\n");
+	}
+}
+
+static void __devinit am200_init_gpio_pin(int pin, int dir)
+{
+	u8 index;
+	/* dir 0 is output, 1 is input
+	- do 2 things here:
+	- set gpio alternate function to standard gpio
+	- set gpio direction to input or output  */
+
+	index = pin >> 4;
+	switch (index) {
+	case 1:
+		GAFR0_U &= ~(AF_SEL_GPIO_N << GAFR0_U_OFFSET(pin));
+
+		if (dir)
+			GPDR0 &= ~(1 << pin);
+		else
+			GPDR0 |= (1 << pin);
+		break;
+	case 2:
+		GAFR1_L &= ~(AF_SEL_GPIO_N << GAFR1_L_OFFSET(pin));
+
+		if (dir)
+			GPDR1 &= ~(1 << GPDR1_OFFSET(pin));
+		else
+			GPDR1 |= (1 << GPDR1_OFFSET(pin));
+		break;
+	case 3:
+		GAFR1_U &= ~(AF_SEL_GPIO_N << GAFR1_U_OFFSET(pin));
+
+		if (dir)
+			GPDR1 &= ~(1 << GPDR1_OFFSET(pin));
+		else
+			GPDR1 |= (1 << GPDR1_OFFSET(pin));
+		break;
+	default:
+		printk(KERN_ERR "unimplemented\n");
+	}
+}
+
+static void am200_init_gpio_regs(struct metronomefb_par *par)
+{
+	am200_init_gpio_pin(LED_GPIO_PIN, 0);
+	am200_set_gpio_output(LED_GPIO_PIN, 0);
+
+	am200_init_gpio_pin(STDBY_GPIO_PIN, 0);
+	am200_set_gpio_output(STDBY_GPIO_PIN, 0);
+
+	am200_init_gpio_pin(RST_GPIO_PIN, 0);
+	am200_set_gpio_output(RST_GPIO_PIN, 0);
+
+	am200_init_gpio_pin(RDY_GPIO_PIN, 1);
+
+	am200_init_gpio_pin(ERR_GPIO_PIN, 1);
+
+	am200_init_gpio_pin(PCBPWR_GPIO_PIN, 0);
+	am200_set_gpio_output(PCBPWR_GPIO_PIN, 0);
+}
+
+static void am200_disable_lcd_controller(struct metronomefb_par *par)
+{
+	LCSR = 0xffffffff;	/* Clear LCD Status Register */
+	LCCR0 |= LCCR0_DIS;	/* Disable LCD Controller */
+
+	/* we reset and just wait for things to settle */
+	msleep(200);
+}
+
+static void am200_enable_lcd_controller(struct metronomefb_par *par)
+{
+	LCSR = 0xffffffff;
+	FDADR0 = par->metromem_desc_dma;
+	LCCR0 |= LCCR0_ENB;
+}
+
+static void am200_init_lcdc_regs(struct metronomefb_par *par)
+{
+	/* here we do:
+	- disable the lcd controller
+	- setup lcd control registers
+	- setup dma descriptor
+	- reenable lcd controller
+	*/
+
+	/* disable the lcd controller */
+	am200_disable_lcd_controller(par);
+
+	/* setup lcd control registers */
+	LCCR0 = LCCR0_LDM | LCCR0_SFM | LCCR0_IUM | LCCR0_EFM | LCCR0_PAS
+		| LCCR0_QDM | LCCR0_BM | LCCR0_OUM;
+
+	LCCR1 = (par->info->var.xres/2 - 1) /* pixels per line */
+		| (27 << 10) /* hsync pulse width - 1 */
+		| (33 << 16) /* eol pixel count */
+		| (33 << 24); /* bol pixel count */
+
+	LCCR2 = (par->info->var.yres - 1) /* lines per panel */
+		| (24 << 10) /* vsync pulse width - 1 */
+		| (2 << 16) /* eof pixel count */
+		| (0 << 24); /* bof pixel count */
+
+	LCCR3 = 2 /* pixel clock divisor */
+		| (24 << 8) /* AC Bias pin freq */
+		| LCCR3_16BPP /* BPP */
+		| LCCR3_PCP;  /* PCP falling edge */
+
+}
+
+static void am200_post_dma_setup(struct metronomefb_par *par)
+{
+	par->metromem_desc->mFDADR0 = par->metromem_desc_dma;
+	par->metromem_desc->mFSADR0 = par->metromem_dma;
+	par->metromem_desc->mFIDR0 = 0;
+	par->metromem_desc->mLDCMD0 = par->info->var.xres
+					* par->info->var.yres;
+	am200_enable_lcd_controller(par);
+}
+
+static void am200_free_irq(struct fb_info *info)
+{
+	free_irq(IRQ_GPIO(RDY_GPIO_PIN), info);
+}
+
+static irqreturn_t am200_handle_irq(int irq, void *dev_id)
+{
+	struct fb_info *info = dev_id;
+	struct metronomefb_par *par = info->par;
+
+	wake_up_interruptible(&par->waitq);
+	return IRQ_HANDLED;
+}
+
+static int am200_setup_irq(struct fb_info *info)
+{
+	int retval;
+
+	retval = request_irq(IRQ_GPIO(RDY_GPIO_PIN), am200_handle_irq,
+				IRQF_DISABLED, "AM200", info);
+	if (retval) {
+		printk(KERN_ERR "am200epd: request_irq failed: %d\n", retval);
+		return retval;
+	}
+
+	return set_irq_type(IRQ_GPIO(RDY_GPIO_PIN), IRQT_FALLING);
+}
+
+static void am200_set_rst(struct metronomefb_par *par, int state)
+{
+	am200_set_gpio_output(RST_GPIO_PIN, state);
+}
+
+static void am200_set_stdby(struct metronomefb_par *par, int state)
+{
+	am200_set_gpio_output(STDBY_GPIO_PIN, state);
+}
+
+static int am200_wait_event(struct metronomefb_par *par)
+{
+	return wait_event_timeout(par->waitq, (GPLR1 & 0x01), HZ);
+}
+
+static int am200_wait_event_intr(struct metronomefb_par *par)
+{
+	return wait_event_interruptible_timeout(par->waitq, (GPLR1 & 0x01), HZ);
+}
+
+static struct metronome_board am200_board = {
+	.owner			= THIS_MODULE,
+	.free_irq		= am200_free_irq,
+	.setup_irq		= am200_setup_irq,
+	.init_gpio_regs		= am200_init_gpio_regs,
+	.init_lcdc_regs		= am200_init_lcdc_regs,
+	.post_dma_setup		= am200_post_dma_setup,
+	.set_rst		= am200_set_rst,
+	.set_stdby		= am200_set_stdby,
+	.met_wait_event		= am200_wait_event,
+	.met_wait_event_intr	= am200_wait_event_intr,
+};
+
+static struct platform_device *am200_device;
+
+static int __init am200_init(void)
+{
+	int ret;
+
+	/* request our platform independent driver */
+	request_module("metronomefb");
+
+	am200_device = platform_device_alloc("metronomefb", -1);
+	if (!am200_device)
+		return -ENOMEM;
+
+	platform_device_add_data(am200_device, &am200_board,
+					sizeof(am200_board));
+
+	/* this _add binds metronomefb to am200. metronomefb refcounts am200 */
+	ret = platform_device_add(am200_device);
+
+	if (ret)
+		platform_device_put(am200_device);
+
+	return ret;
+}
+
+static void __exit am200_exit(void)
+{
+	platform_device_unregister(am200_device);
+}
+
+module_init(am200_init);
+module_exit(am200_exit);
+
+MODULE_DESCRIPTION("board driver for am200 metronome epd kit");
+MODULE_AUTHOR("Jaya Kumar");
+MODULE_LICENSE("GPL");
diff --git a/trunk/drivers/video/amifb.c b/trunk/drivers/video/amifb.c
index 4c9ec3f58c52..e6492c1048bf 100644
--- a/trunk/drivers/video/amifb.c
+++ b/trunk/drivers/video/amifb.c
@@ -96,7 +96,7 @@
 #endif
 
 #ifdef DEBUG
-#  define DPRINTK(fmt, args...)	printk(KERN_DEBUG "%s: " fmt, __FUNCTION__ , ## args)
+#  define DPRINTK(fmt, args...)	printk(KERN_DEBUG "%s: " fmt, __func__ , ## args)
 #else
 #  define DPRINTK(fmt, args...)
 #endif
diff --git a/trunk/drivers/video/arkfb.c b/trunk/drivers/video/arkfb.c
index 8a1b07c74394..5001bd4ef466 100644
--- a/trunk/drivers/video/arkfb.c
+++ b/trunk/drivers/video/arkfb.c
@@ -101,7 +101,7 @@ static const struct svga_timing_regs ark_timing_regs     = {
 
 /* Module parameters */
 
-static char *mode = "640x480-8@60";
+static char *mode_option __devinitdata = "640x480-8@60";
 
 #ifdef CONFIG_MTRR
 static int mtrr = 1;
@@ -111,8 +111,10 @@ MODULE_AUTHOR("(c) 2007 Ondrej Zajicek <santiago@crfreenet.org>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("fbdev driver for ARK 2000PV");
 
-module_param(mode, charp, 0444);
-MODULE_PARM_DESC(mode, "Default video mode ('640x480-8@60', etc)");
+module_param(mode_option, charp, 0444);
+MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
+module_param_named(mode, mode_option, charp, 0444);
+MODULE_PARM_DESC(mode, "Default video mode ('640x480-8@60', etc) (deprecated)");
 
 #ifdef CONFIG_MTRR
 module_param(mtrr, int, 0444);
@@ -941,7 +943,7 @@ static int __devinit ark_pci_probe(struct pci_dev *dev, const struct pci_device_
 	}
 
 	/* Allocate and fill driver data structure */
-	info = framebuffer_alloc(sizeof(struct arkfb_info), NULL);
+	info = framebuffer_alloc(sizeof(struct arkfb_info), &(dev->dev));
 	if (! info) {
 		dev_err(&(dev->dev), "cannot allocate memory\n");
 		return -ENOMEM;
@@ -956,20 +958,20 @@ static int __devinit ark_pci_probe(struct pci_dev *dev, const struct pci_device_
 	/* Prepare PCI device */
 	rc = pci_enable_device(dev);
 	if (rc < 0) {
-		dev_err(&(dev->dev), "cannot enable PCI device\n");
+		dev_err(info->dev, "cannot enable PCI device\n");
 		goto err_enable_device;
 	}
 
 	rc = pci_request_regions(dev, "arkfb");
 	if (rc < 0) {
-		dev_err(&(dev->dev), "cannot reserve framebuffer region\n");
+		dev_err(info->dev, "cannot reserve framebuffer region\n");
 		goto err_request_regions;
 	}
 
 	par->dac = ics5342_init(ark_dac_read_regs, ark_dac_write_regs, info);
 	if (! par->dac) {
 		rc = -ENOMEM;
-		dev_err(&(dev->dev), "RAMDAC initialization failed\n");
+		dev_err(info->dev, "RAMDAC initialization failed\n");
 		goto err_dac;
 	}
 
@@ -980,7 +982,7 @@ static int __devinit ark_pci_probe(struct pci_dev *dev, const struct pci_device_
 	info->screen_base = pci_iomap(dev, 0, 0);
 	if (! info->screen_base) {
 		rc = -ENOMEM;
-		dev_err(&(dev->dev), "iomap for framebuffer failed\n");
+		dev_err(info->dev, "iomap for framebuffer failed\n");
 		goto err_iomap;
 	}
 
@@ -999,22 +1001,22 @@ static int __devinit ark_pci_probe(struct pci_dev *dev, const struct pci_device_
 	info->pseudo_palette = (void*) (par->pseudo_palette);
 
 	/* Prepare startup mode */
-	rc = fb_find_mode(&(info->var), info, mode, NULL, 0, NULL, 8);
+	rc = fb_find_mode(&(info->var), info, mode_option, NULL, 0, NULL, 8);
 	if (! ((rc == 1) || (rc == 2))) {
 		rc = -EINVAL;
-		dev_err(&(dev->dev), "mode %s not found\n", mode);
+		dev_err(info->dev, "mode %s not found\n", mode_option);
 		goto err_find_mode;
 	}
 
 	rc = fb_alloc_cmap(&info->cmap, 256, 0);
 	if (rc < 0) {
-		dev_err(&(dev->dev), "cannot allocate colormap\n");
+		dev_err(info->dev, "cannot allocate colormap\n");
 		goto err_alloc_cmap;
 	}
 
 	rc = register_framebuffer(info);
 	if (rc < 0) {
-		dev_err(&(dev->dev), "cannot register framebugger\n");
+		dev_err(info->dev, "cannot register framebugger\n");
 		goto err_reg_fb;
 	}
 
@@ -1088,7 +1090,7 @@ static int ark_pci_suspend (struct pci_dev* dev, pm_message_t state)
 	struct fb_info *info = pci_get_drvdata(dev);
 	struct arkfb_info *par = info->par;
 
-	dev_info(&(dev->dev), "suspend\n");
+	dev_info(info->dev, "suspend\n");
 
 	acquire_console_sem();
 	mutex_lock(&(par->open_lock));
@@ -1119,7 +1121,7 @@ static int ark_pci_resume (struct pci_dev* dev)
 	struct fb_info *info = pci_get_drvdata(dev);
 	struct arkfb_info *par = info->par;
 
-	dev_info(&(dev->dev), "resume\n");
+	dev_info(info->dev, "resume\n");
 
 	acquire_console_sem();
 	mutex_lock(&(par->open_lock));
@@ -1190,7 +1192,7 @@ static int __init arkfb_init(void)
 		return -ENODEV;
 
 	if (option && *option)
-		mode = option;
+		mode_option = option;
 #endif
 
 	pr_debug("arkfb: initializing\n");
diff --git a/trunk/drivers/video/atafb.c b/trunk/drivers/video/atafb.c
index 5d4fbaa53a6c..dff35474b854 100644
--- a/trunk/drivers/video/atafb.c
+++ b/trunk/drivers/video/atafb.c
@@ -1270,7 +1270,7 @@ static int falcon_decode_var(struct fb_var_screeninfo *var,
 
 	gstart = (prescale / 2 + plen * left_margin) / prescale;
 	/* gend1 is for hde (gend-gstart multiple of align), shifter's xres */
-	gend1 = gstart + ((xres + align - 1) / align) * align * plen / prescale;
+	gend1 = gstart + roundup(xres, align) * plen / prescale;
 	/* gend2 is for hbb, visible xres (rest to gend1 is cut off by hblank) */
 	gend2 = gstart + xres * plen / prescale;
 	par->HHT = plen * (left_margin + xres + right_margin) /
diff --git a/trunk/drivers/video/atmel_lcdfb.c b/trunk/drivers/video/atmel_lcdfb.c
index fc65c02306dd..8ffdf3578768 100644
--- a/trunk/drivers/video/atmel_lcdfb.c
+++ b/trunk/drivers/video/atmel_lcdfb.c
@@ -31,7 +31,8 @@
 #define ATMEL_LCDC_CVAL_DEFAULT		0xc8
 #define ATMEL_LCDC_DMA_BURST_LEN	8
 
-#if defined(CONFIG_ARCH_AT91SAM9263) || defined(CONFIG_ARCH_AT91CAP9)
+#if defined(CONFIG_ARCH_AT91SAM9263) || defined(CONFIG_ARCH_AT91CAP9) || \
+	defined(CONFIG_ARCH_AT91SAM9RL)
 #define ATMEL_LCDC_FIFO_SIZE		2048
 #else
 #define ATMEL_LCDC_FIFO_SIZE		512
@@ -250,6 +251,8 @@ static int atmel_lcdfb_alloc_video_memory(struct atmel_lcdfb_info *sinfo)
 		return -ENOMEM;
 	}
 
+	memset(info->screen_base, 0, info->fix.smem_len);
+
 	return 0;
 }
 
@@ -336,19 +339,35 @@ static int atmel_lcdfb_check_var(struct fb_var_screeninfo *var,
 		break;
 	case 15:
 	case 16:
-		var->red.offset = 0;
+		if (sinfo->lcd_wiring_mode == ATMEL_LCDC_WIRING_RGB) {
+			/* RGB:565 mode */
+			var->red.offset = 11;
+			var->blue.offset = 0;
+			var->green.length = 6;
+		} else {
+			/* BGR:555 mode */
+			var->red.offset = 0;
+			var->blue.offset = 10;
+			var->green.length = 5;
+		}
 		var->green.offset = 5;
-		var->blue.offset = 10;
-		var->red.length = var->green.length = var->blue.length = 5;
+		var->red.length = var->blue.length = 5;
 		break;
 	case 32:
 		var->transp.offset = 24;
 		var->transp.length = 8;
 		/* fall through */
 	case 24:
-		var->red.offset = 0;
+		if (sinfo->lcd_wiring_mode == ATMEL_LCDC_WIRING_RGB) {
+			/* RGB:888 mode */
+			var->red.offset = 16;
+			var->blue.offset = 0;
+		} else {
+			/* BGR:888 mode */
+			var->red.offset = 0;
+			var->blue.offset = 16;
+		}
 		var->green.offset = 8;
-		var->blue.offset = 16;
 		var->red.length = var->green.length = var->blue.length = 8;
 		break;
 	default:
@@ -634,7 +653,6 @@ static int __init atmel_lcdfb_init_fbinfo(struct atmel_lcdfb_info *sinfo)
 	struct fb_info *info = sinfo->info;
 	int ret = 0;
 
-	memset_io(info->screen_base, 0, info->fix.smem_len);
 	info->var.activate |= FB_ACTIVATE_FORCE | FB_ACTIVATE_NOW;
 
 	dev_info(info->device,
@@ -696,6 +714,7 @@ static int __init atmel_lcdfb_probe(struct platform_device *pdev)
 		sinfo->atmel_lcdfb_power_control = pdata_sinfo->atmel_lcdfb_power_control;
 		sinfo->guard_time = pdata_sinfo->guard_time;
 		sinfo->lcdcon_is_backlight = pdata_sinfo->lcdcon_is_backlight;
+		sinfo->lcd_wiring_mode = pdata_sinfo->lcd_wiring_mode;
 	} else {
 		dev_err(dev, "cannot get default configuration\n");
 		goto free_info;
@@ -764,6 +783,11 @@ static int __init atmel_lcdfb_probe(struct platform_device *pdev)
 		info->screen_base = ioremap(info->fix.smem_start, info->fix.smem_len);
 		if (!info->screen_base)
 			goto release_intmem;
+
+		/*
+		 * Don't clear the framebuffer -- someone may have set
+		 * up a splash image.
+		 */
 	} else {
 		/* alocate memory buffer */
 		ret = atmel_lcdfb_alloc_video_memory(sinfo);
@@ -903,10 +927,42 @@ static int __exit atmel_lcdfb_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM
+
+static int atmel_lcdfb_suspend(struct platform_device *pdev, pm_message_t mesg)
+{
+	struct fb_info *info = platform_get_drvdata(pdev);
+	struct atmel_lcdfb_info *sinfo = info->par;
+
+	sinfo->saved_lcdcon = lcdc_readl(sinfo, ATMEL_LCDC_CONTRAST_VAL);
+	lcdc_writel(sinfo, ATMEL_LCDC_CONTRAST_CTR, 0);
+	if (sinfo->atmel_lcdfb_power_control)
+		sinfo->atmel_lcdfb_power_control(0);
+	atmel_lcdfb_stop_clock(sinfo);
+	return 0;
+}
+
+static int atmel_lcdfb_resume(struct platform_device *pdev)
+{
+	struct fb_info *info = platform_get_drvdata(pdev);
+	struct atmel_lcdfb_info *sinfo = info->par;
+
+	atmel_lcdfb_start_clock(sinfo);
+	if (sinfo->atmel_lcdfb_power_control)
+		sinfo->atmel_lcdfb_power_control(1);
+	lcdc_writel(sinfo, ATMEL_LCDC_CONTRAST_CTR, sinfo->saved_lcdcon);
+	return 0;
+}
+
+#else
+#define atmel_lcdfb_suspend	NULL
+#define atmel_lcdfb_resume	NULL
+#endif
+
 static struct platform_driver atmel_lcdfb_driver = {
 	.remove		= __exit_p(atmel_lcdfb_remove),
-
-// FIXME need suspend, resume
+	.suspend	= atmel_lcdfb_suspend,
+	.resume		= atmel_lcdfb_resume,
 
 	.driver		= {
 		.name	= "atmel_lcdfb",
diff --git a/trunk/drivers/video/aty/aty128fb.c b/trunk/drivers/video/aty/aty128fb.c
index cbd3308b6690..24ee96c4e9e9 100644
--- a/trunk/drivers/video/aty/aty128fb.c
+++ b/trunk/drivers/video/aty/aty128fb.c
@@ -91,7 +91,7 @@
 #undef DEBUG
 
 #ifdef DEBUG
-#define DBG(fmt, args...)		printk(KERN_DEBUG "aty128fb: %s " fmt, __FUNCTION__, ##args);
+#define DBG(fmt, args...)		printk(KERN_DEBUG "aty128fb: %s " fmt, __func__, ##args);
 #else
 #define DBG(fmt, args...)
 #endif
@@ -1885,7 +1885,7 @@ static int __devinit aty128_init(struct pci_dev *pdev, const struct pci_device_i
 
 	/* range check to make sure */
 	if (ent->driver_data < ARRAY_SIZE(r128_family))
-	    strncat(video_card, r128_family[ent->driver_data], sizeof(video_card));
+	    strlcat(video_card, r128_family[ent->driver_data], sizeof(video_card));
 
 	printk(KERN_INFO "aty128fb: %s [chip rev 0x%x] ", video_card, chip_rev);
 
diff --git a/trunk/drivers/video/aty/atyfb_base.c b/trunk/drivers/video/aty/atyfb_base.c
index 62f9c6e387cc..e4bcf5376a99 100644
--- a/trunk/drivers/video/aty/atyfb_base.c
+++ b/trunk/drivers/video/aty/atyfb_base.c
@@ -2621,10 +2621,13 @@ static int __devinit aty_init(struct fb_info *info)
 #endif /* CONFIG_FB_ATY_CT */
 	info->var = var;
 
-	fb_alloc_cmap(&info->cmap, 256, 0);
+	if (fb_alloc_cmap(&info->cmap, 256, 0) < 0)
+		goto aty_init_exit;
 
-	if (register_framebuffer(info) < 0)
+	if (register_framebuffer(info) < 0) {
+		fb_dealloc_cmap(&info->cmap);
 		goto aty_init_exit;
+	}
 
 	fb_list = info;
 
diff --git a/trunk/drivers/video/aty/mach64_ct.c b/trunk/drivers/video/aty/mach64_ct.c
index cc9e9779b75f..c50c7cf26fe9 100644
--- a/trunk/drivers/video/aty/mach64_ct.c
+++ b/trunk/drivers/video/aty/mach64_ct.c
@@ -197,7 +197,7 @@ static int aty_dsp_gt(const struct fb_info *info, u32 bpp, struct pll_ct *pll)
 	pll->dsp_config = (dsp_precision << 20) | (pll->dsp_loop_latency << 16) | dsp_xclks;
 #ifdef DEBUG
 	printk("atyfb(%s): dsp_config 0x%08x, dsp_on_off 0x%08x\n",
-		__FUNCTION__, pll->dsp_config, pll->dsp_on_off);
+		__func__, pll->dsp_config, pll->dsp_on_off);
 #endif
 	return 0;
 }
@@ -225,7 +225,7 @@ static int aty_valid_pll_ct(const struct fb_info *info, u32 vclk_per, struct pll
 		(par->ref_clk_per * pll->pll_ref_div);
 #ifdef DEBUG
 	printk("atyfb(%s): pllvclk=%d MHz, vclk=%d MHz\n",
-		__FUNCTION__, pllvclk, pllvclk / pll->vclk_post_div_real);
+		__func__, pllvclk, pllvclk / pll->vclk_post_div_real);
 #endif
 	pll->pll_vclk_cntl = 0x03; /* VCLK = PLL_VCLK/VCLKx_POST */
 
@@ -269,7 +269,7 @@ static u32 aty_pll_to_var_ct(const struct fb_info *info, const union aty_pll *pl
 	}
 #endif
 #ifdef DEBUG
-	printk("atyfb(%s): calculated 0x%08X(%i)\n", __FUNCTION__, ret, ret);
+	printk("atyfb(%s): calculated 0x%08X(%i)\n", __func__, ret, ret);
 #endif
 	return ret;
 }
@@ -284,11 +284,11 @@ void aty_set_pll_ct(const struct fb_info *info, const union aty_pll *pll)
 #ifdef DEBUG
 	printk("atyfb(%s): about to program:\n"
 		"pll_ext_cntl=0x%02x pll_gen_cntl=0x%02x pll_vclk_cntl=0x%02x\n",
-		__FUNCTION__,
+		__func__,
 		pll->ct.pll_ext_cntl, pll->ct.pll_gen_cntl, pll->ct.pll_vclk_cntl);
 
 	printk("atyfb(%s): setting clock %lu for FeedBackDivider %i, ReferenceDivider %i, PostDivider %i(%i)\n",
-		__FUNCTION__,
+		__func__,
 		par->clk_wr_offset, pll->ct.vclk_fb_div,
 		pll->ct.pll_ref_div, pll->ct.vclk_post_div, pll->ct.vclk_post_div_real);
 #endif
@@ -428,7 +428,7 @@ static int __devinit aty_init_pll_ct(const struct fb_info *info,
 
 #ifdef DEBUG
 	printk("atyfb(%s): mclk_fb_mult=%d, xclk_post_div=%d\n",
-		__FUNCTION__, pll->ct.mclk_fb_mult, pll->ct.xclk_post_div);
+		__func__, pll->ct.mclk_fb_mult, pll->ct.xclk_post_div);
 #endif
 
 	memcntl = aty_ld_le32(MEM_CNTL, par);
@@ -540,7 +540,7 @@ static int __devinit aty_init_pll_ct(const struct fb_info *info,
 	pllmclk = (1000000 * pll->ct.mclk_fb_mult * pll->ct.mclk_fb_div) /
 			(par->ref_clk_per * pll->ct.pll_ref_div);
 	printk("atyfb(%s): pllmclk=%d MHz, xclk=%d MHz\n",
-		__FUNCTION__, pllmclk, pllmclk / pll->ct.xclk_post_div_real);
+		__func__, pllmclk, pllmclk / pll->ct.xclk_post_div_real);
 #endif
 
 	if (M64_HAS(SDRAM_MAGIC_PLL) && (par->ram_type >= SDRAM))
@@ -581,7 +581,7 @@ static int __devinit aty_init_pll_ct(const struct fb_info *info,
 		pllsclk = (1000000 * 2 * pll->ct.sclk_fb_div) /
 			(par->ref_clk_per * pll->ct.pll_ref_div);
 		printk("atyfb(%s): use sclk, pllsclk=%d MHz, sclk=mclk=%d MHz\n",
-			__FUNCTION__, pllsclk, pllsclk / sclk_post_div_real);
+			__func__, pllsclk, pllsclk / sclk_post_div_real);
 #endif
 	}
 
diff --git a/trunk/drivers/video/aty/radeon_base.c b/trunk/drivers/video/aty/radeon_base.c
index 62867cb63fef..72cd0d2f14ec 100644
--- a/trunk/drivers/video/aty/radeon_base.c
+++ b/trunk/drivers/video/aty/radeon_base.c
@@ -52,11 +52,14 @@
 
 #define RADEON_VERSION	"0.2.0"
 
+#include "radeonfb.h"
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/ctype.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
@@ -91,7 +94,6 @@
 
 #include "../edid.h" // MOVE THAT TO include/video
 #include "ati_ids.h"
-#include "radeonfb.h"		    
 
 #define MAX_MAPPED_VRAM	(2048*2048*4)
 #define MIN_MAPPED_VRAM	(1024*768*1)
@@ -1488,7 +1490,7 @@ static void radeon_calc_pll_regs(struct radeonfb_info *rinfo, struct radeon_regs
 		freq = rinfo->pll.ppll_max;
 	if (freq*12 < rinfo->pll.ppll_min)
 		freq = rinfo->pll.ppll_min / 12;
-	RTRACE("freq = %lu, PLL min = %u, PLL max = %u\n",
+	pr_debug("freq = %lu, PLL min = %u, PLL max = %u\n",
 	       freq, rinfo->pll.ppll_min, rinfo->pll.ppll_max);
 
 	for (post_div = &post_divs[0]; post_div->divider; ++post_div) {
@@ -1509,7 +1511,7 @@ static void radeon_calc_pll_regs(struct radeonfb_info *rinfo, struct radeon_regs
 		post_div = &post_divs[post_div->bitvalue];
 		pll_output_freq = post_div->divider * freq;
 	}
-	RTRACE("ref_div = %d, ref_clk = %d, output_freq = %d\n",
+	pr_debug("ref_div = %d, ref_clk = %d, output_freq = %d\n",
 	       rinfo->pll.ref_div, rinfo->pll.ref_clk,
 	       pll_output_freq);
 
@@ -1519,7 +1521,7 @@ static void radeon_calc_pll_regs(struct radeonfb_info *rinfo, struct radeon_regs
 		post_div = &post_divs[post_div->bitvalue];
 		pll_output_freq = post_div->divider * freq;
 	}
-	RTRACE("ref_div = %d, ref_clk = %d, output_freq = %d\n",
+	pr_debug("ref_div = %d, ref_clk = %d, output_freq = %d\n",
 	       rinfo->pll.ref_div, rinfo->pll.ref_clk,
 	       pll_output_freq);
 
@@ -1528,9 +1530,9 @@ static void radeon_calc_pll_regs(struct radeonfb_info *rinfo, struct radeon_regs
 	regs->ppll_ref_div = rinfo->pll.ref_div;
 	regs->ppll_div_3 = fb_div | (post_div->bitvalue << 16);
 
-	RTRACE("post div = 0x%x\n", post_div->bitvalue);
-	RTRACE("fb_div = 0x%x\n", fb_div);
-	RTRACE("ppll_div_3 = 0x%x\n", regs->ppll_div_3);
+	pr_debug("post div = 0x%x\n", post_div->bitvalue);
+	pr_debug("fb_div = 0x%x\n", fb_div);
+	pr_debug("ppll_div_3 = 0x%x\n", regs->ppll_div_3);
 }
 
 static int radeonfb_set_par(struct fb_info *info)
@@ -1602,9 +1604,9 @@ static int radeonfb_set_par(struct fb_info *info)
 	dotClock = 1000000000 / pixClock;
 	freq = dotClock / 10; /* x100 */
 
-	RTRACE("hStart = %d, hEnd = %d, hTotal = %d\n",
+	pr_debug("hStart = %d, hEnd = %d, hTotal = %d\n",
 		hSyncStart, hSyncEnd, hTotal);
-	RTRACE("vStart = %d, vEnd = %d, vTotal = %d\n",
+	pr_debug("vStart = %d, vEnd = %d, vTotal = %d\n",
 		vSyncStart, vSyncEnd, vTotal);
 
 	hsync_wid = (hSyncEnd - hSyncStart) / 8;
@@ -1713,16 +1715,16 @@ static int radeonfb_set_par(struct fb_info *info)
 		newmode->surf_info[i] = 0;
 	}
 
-	RTRACE("h_total_disp = 0x%x\t   hsync_strt_wid = 0x%x\n",
+	pr_debug("h_total_disp = 0x%x\t   hsync_strt_wid = 0x%x\n",
 		newmode->crtc_h_total_disp, newmode->crtc_h_sync_strt_wid);
-	RTRACE("v_total_disp = 0x%x\t   vsync_strt_wid = 0x%x\n",
+	pr_debug("v_total_disp = 0x%x\t   vsync_strt_wid = 0x%x\n",
 		newmode->crtc_v_total_disp, newmode->crtc_v_sync_strt_wid);
 
 	rinfo->bpp = mode->bits_per_pixel;
 	rinfo->depth = depth;
 
-	RTRACE("pixclock = %lu\n", (unsigned long)pixClock);
-	RTRACE("freq = %lu\n", (unsigned long)freq);
+	pr_debug("pixclock = %lu\n", (unsigned long)pixClock);
+	pr_debug("freq = %lu\n", (unsigned long)freq);
 
 	/* We use PPLL_DIV_3 */
 	newmode->clk_cntl_index = 0x300;
@@ -1986,7 +1988,7 @@ static void fixup_memory_mappings(struct radeonfb_info *rinfo)
 	if (rinfo->has_CRTC2)
 		OUTREG(CRTC2_GEN_CNTL, save_crtc2_gen_cntl);	
 
-	RTRACE("aper_base: %08x MC_FB_LOC to: %08x, MC_AGP_LOC to: %08x\n",
+	pr_debug("aper_base: %08x MC_FB_LOC to: %08x, MC_AGP_LOC to: %08x\n",
 		aper_base,
 		((aper_base + aper_size - 1) & 0xffff0000) | (aper_base >> 16),
 		0xffff0000 | (agp_base >> 16));
@@ -2083,7 +2085,7 @@ static void radeon_identify_vram(struct radeonfb_info *rinfo)
 	 * ToDo: identify these cases
 	 */
 
-	RTRACE("radeonfb (%s): Found %ldk of %s %d bits wide videoram\n",
+	pr_debug("radeonfb (%s): Found %ldk of %s %d bits wide videoram\n",
 	       pci_name(rinfo->pdev),
 	       rinfo->video_ram / 1024,
 	       rinfo->vram_ddr ? "DDR" : "SDRAM",
@@ -2158,8 +2160,9 @@ static int __devinit radeonfb_pci_register (struct pci_dev *pdev,
 	struct fb_info *info;
 	struct radeonfb_info *rinfo;
 	int ret;
+	unsigned char c1, c2;
 
-	RTRACE("radeonfb_pci_register BEGIN\n");
+	pr_debug("radeonfb_pci_register BEGIN\n");
 	
 	/* Enable device in PCI config */
 	ret = pci_enable_device(pdev);
@@ -2185,9 +2188,15 @@ static int __devinit radeonfb_pci_register (struct pci_dev *pdev,
 	rinfo->lvds_timer.function = radeon_lvds_timer_func;
 	rinfo->lvds_timer.data = (unsigned long)rinfo;
 
-	strcpy(rinfo->name, "ATI Radeon XX ");
-	rinfo->name[11] = ent->device >> 8;
-	rinfo->name[12] = ent->device & 0xFF;
+	c1 = ent->device >> 8;
+	c2 = ent->device & 0xff;
+	if (isprint(c1) && isprint(c2))
+		snprintf(rinfo->name, sizeof(rinfo->name),
+			 "ATI Radeon %x \"%c%c\"", ent->device & 0xffff, c1, c2);
+	else
+		snprintf(rinfo->name, sizeof(rinfo->name),
+			 "ATI Radeon %x", ent->device & 0xffff);
+
 	rinfo->family = ent->driver_data & CHIP_FAMILY_MASK;
 	rinfo->chipset = pdev->device;
 	rinfo->has_CRTC2 = (ent->driver_data & CHIP_HAS_CRTC2) != 0;
@@ -2278,7 +2287,7 @@ static int __devinit radeonfb_pci_register (struct pci_dev *pdev,
 		goto err_unmap_rom;
 	}
 
-	RTRACE("radeonfb (%s): mapped %ldk videoram\n", pci_name(rinfo->pdev),
+	pr_debug("radeonfb (%s): mapped %ldk videoram\n", pci_name(rinfo->pdev),
 	       rinfo->mapped_vram/1024);
 
 	/*
@@ -2373,7 +2382,7 @@ static int __devinit radeonfb_pci_register (struct pci_dev *pdev,
 
 	if (rinfo->bios_seg)
 		radeon_unmap_ROM(rinfo, pdev);
-	RTRACE("radeonfb_pci_register END\n");
+	pr_debug("radeonfb_pci_register END\n");
 
 	return 0;
 err_unmap_fb:
diff --git a/trunk/drivers/video/aty/radeon_i2c.c b/trunk/drivers/video/aty/radeon_i2c.c
index 7db9de681716..f9e7c29ad9bf 100644
--- a/trunk/drivers/video/aty/radeon_i2c.c
+++ b/trunk/drivers/video/aty/radeon_i2c.c
@@ -1,3 +1,5 @@
+#include "radeonfb.h"
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
@@ -11,7 +13,6 @@
 #include <asm/io.h>
 
 #include <video/radeon.h>
-#include "radeonfb.h"
 #include "../edid.h"
 
 static void radeon_gpio_setscl(void* data, int state)
@@ -77,7 +78,7 @@ static int radeon_setup_i2c_bus(struct radeon_i2c_chan *chan, const char *name)
 	chan->algo.setscl		= radeon_gpio_setscl;
 	chan->algo.getsda		= radeon_gpio_getsda;
 	chan->algo.getscl		= radeon_gpio_getscl;
-	chan->algo.udelay		= 40;
+	chan->algo.udelay		= 10;
 	chan->algo.timeout		= 20;
 	chan->algo.data 		= chan;	
 	
@@ -148,21 +149,21 @@ int radeon_probe_i2c_connector(struct radeonfb_info *rinfo, int conn,
 	if (out_edid)
 		*out_edid = edid;
 	if (!edid) {
-		RTRACE("radeonfb: I2C (port %d) ... not found\n", conn);
+		pr_debug("radeonfb: I2C (port %d) ... not found\n", conn);
 		return MT_NONE;
 	}
 	if (edid[0x14] & 0x80) {
 		/* Fix detection using BIOS tables */
 		if (rinfo->is_mobility /*&& conn == ddc_dvi*/ &&
 		    (INREG(LVDS_GEN_CNTL) & LVDS_ON)) {
-			RTRACE("radeonfb: I2C (port %d) ... found LVDS panel\n", conn);
+			pr_debug("radeonfb: I2C (port %d) ... found LVDS panel\n", conn);
 			return MT_LCD;
 		} else {
-			RTRACE("radeonfb: I2C (port %d) ... found TMDS panel\n", conn);
+			pr_debug("radeonfb: I2C (port %d) ... found TMDS panel\n", conn);
 			return MT_DFP;
 		}
 	}
-       	RTRACE("radeonfb: I2C (port %d) ... found CRT display\n", conn);
+	pr_debug("radeonfb: I2C (port %d) ... found CRT display\n", conn);
 	return MT_CRT;
 }
 
diff --git a/trunk/drivers/video/aty/radeon_monitor.c b/trunk/drivers/video/aty/radeon_monitor.c
index 2030ed813429..b4d4b88afc09 100644
--- a/trunk/drivers/video/aty/radeon_monitor.c
+++ b/trunk/drivers/video/aty/radeon_monitor.c
@@ -69,11 +69,11 @@ static int __devinit radeon_parse_montype_prop(struct device_node *dp, u8 **out_
 	u8 *tmp;
         int i, mt = MT_NONE;  
 	
-	RTRACE("analyzing OF properties...\n");
+	pr_debug("analyzing OF properties...\n");
 	pmt = of_get_property(dp, "display-type", NULL);
 	if (!pmt)
 		return MT_NONE;
-	RTRACE("display-type: %s\n", pmt);
+	pr_debug("display-type: %s\n", pmt);
 	/* OF says "LCD" for DFP as well, we discriminate from the caller of this
 	 * function
 	 */
@@ -117,7 +117,7 @@ static int __devinit radeon_probe_OF_head(struct radeonfb_info *rinfo, int head_
 {
         struct device_node *dp;
 
-	RTRACE("radeon_probe_OF_head\n");
+	pr_debug("radeon_probe_OF_head\n");
 
         dp = rinfo->of_node;
         while (dp == NULL)
@@ -135,7 +135,7 @@ static int __devinit radeon_probe_OF_head(struct radeonfb_info *rinfo, int head_
 			if (!pname)
 				return MT_NONE;
 			len = strlen(pname);
-			RTRACE("head: %s (letter: %c, head_no: %d)\n",
+			pr_debug("head: %s (letter: %c, head_no: %d)\n",
 			       pname, pname[len-1], head_no);
 			if (pname[len-1] == 'A' && head_no == 0) {
 				int mt = radeon_parse_montype_prop(dp, out_EDID, 0);
@@ -185,7 +185,7 @@ static int __devinit radeon_get_panel_info_BIOS(struct radeonfb_info *rinfo)
 		rinfo->panel_info.xres, rinfo->panel_info.yres);
 
 	rinfo->panel_info.pwr_delay = BIOS_IN16(tmp + 44);
-	RTRACE("BIOS provided panel power delay: %d\n", rinfo->panel_info.pwr_delay);
+	pr_debug("BIOS provided panel power delay: %d\n", rinfo->panel_info.pwr_delay);
 	if (rinfo->panel_info.pwr_delay > 2000 || rinfo->panel_info.pwr_delay <= 0)
 		rinfo->panel_info.pwr_delay = 2000;
 
@@ -199,16 +199,16 @@ static int __devinit radeon_get_panel_info_BIOS(struct radeonfb_info *rinfo)
 	    rinfo->panel_info.fbk_divider > 3) {
 		rinfo->panel_info.use_bios_dividers = 1;
 		printk(KERN_INFO "radeondb: BIOS provided dividers will be used\n");
-		RTRACE("ref_divider = %x\n", rinfo->panel_info.ref_divider);
-		RTRACE("post_divider = %x\n", rinfo->panel_info.post_divider);
-		RTRACE("fbk_divider = %x\n", rinfo->panel_info.fbk_divider);
+		pr_debug("ref_divider = %x\n", rinfo->panel_info.ref_divider);
+		pr_debug("post_divider = %x\n", rinfo->panel_info.post_divider);
+		pr_debug("fbk_divider = %x\n", rinfo->panel_info.fbk_divider);
 	}
-	RTRACE("Scanning BIOS table ...\n");
+	pr_debug("Scanning BIOS table ...\n");
 	for(i=0; i<32; i++) {
 		tmp0 = BIOS_IN16(tmp+64+i*2);
 		if (tmp0 == 0)
 			break;
-		RTRACE(" %d x %d\n", BIOS_IN16(tmp0), BIOS_IN16(tmp0+2));
+		pr_debug(" %d x %d\n", BIOS_IN16(tmp0), BIOS_IN16(tmp0+2));
 		if ((BIOS_IN16(tmp0) == rinfo->panel_info.xres) &&
 		    (BIOS_IN16(tmp0+2) == rinfo->panel_info.yres)) {
 			rinfo->panel_info.hblank = (BIOS_IN16(tmp0+17) - BIOS_IN16(tmp0+19)) * 8;
@@ -227,19 +227,19 @@ static int __devinit radeon_get_panel_info_BIOS(struct radeonfb_info *rinfo)
 			/* Mark panel infos valid */
 			rinfo->panel_info.valid = 1;
 
-			RTRACE("Found panel in BIOS table:\n");
-			RTRACE("  hblank: %d\n", rinfo->panel_info.hblank);
-			RTRACE("  hOver_plus: %d\n", rinfo->panel_info.hOver_plus);
-			RTRACE("  hSync_width: %d\n", rinfo->panel_info.hSync_width);
-			RTRACE("  vblank: %d\n", rinfo->panel_info.vblank);
-			RTRACE("  vOver_plus: %d\n", rinfo->panel_info.vOver_plus);
-			RTRACE("  vSync_width: %d\n", rinfo->panel_info.vSync_width);
-			RTRACE("  clock: %d\n", rinfo->panel_info.clock);
+			pr_debug("Found panel in BIOS table:\n");
+			pr_debug("  hblank: %d\n", rinfo->panel_info.hblank);
+			pr_debug("  hOver_plus: %d\n", rinfo->panel_info.hOver_plus);
+			pr_debug("  hSync_width: %d\n", rinfo->panel_info.hSync_width);
+			pr_debug("  vblank: %d\n", rinfo->panel_info.vblank);
+			pr_debug("  vOver_plus: %d\n", rinfo->panel_info.vOver_plus);
+			pr_debug("  vSync_width: %d\n", rinfo->panel_info.vSync_width);
+			pr_debug("  clock: %d\n", rinfo->panel_info.clock);
 				
 			return 1;
 		}
 	}
-	RTRACE("Didn't find panel in BIOS table !\n");
+	pr_debug("Didn't find panel in BIOS table !\n");
 
 	return 0;
 }
@@ -271,18 +271,18 @@ static void __devinit radeon_parse_connector_info(struct radeonfb_info *rinfo)
 	 * DEBUG is enabled
 	 */
 	chips = BIOS_IN8(offset++) >> 4;
-	RTRACE("%d chips in connector info\n", chips);
+	pr_debug("%d chips in connector info\n", chips);
 	for (i = 0; i < chips; i++) {
 		tmp = BIOS_IN8(offset++);
 		connectors = tmp & 0x0f;
-		RTRACE(" - chip %d has %d connectors\n", tmp >> 4, connectors);
+		pr_debug(" - chip %d has %d connectors\n", tmp >> 4, connectors);
 		for (conn = 0; ; conn++) {
 			tmp = BIOS_IN16(offset);
 			if (tmp == 0)
 				break;
 			offset += 2;
 			type = (tmp >> 12) & 0x0f;
-			RTRACE("  * connector %d of type %d (%s) : %04x\n",
+			pr_debug("  * connector %d of type %d (%s) : %04x\n",
 			       conn, type, __conn_type_table[type], tmp);
 		}
 	}
@@ -449,7 +449,7 @@ void __devinit radeon_probe_screens(struct radeonfb_info *rinfo,
 		 * a layout for each card ?
 		 */
 
-		RTRACE("Using specified monitor layout: %s", monitor_layout);
+		pr_debug("Using specified monitor layout: %s", monitor_layout);
 #ifdef CONFIG_FB_RADEON_I2C
 		if (!ignore_edid) {
 			if (rinfo->mon1_type != MT_NONE)
@@ -479,9 +479,9 @@ void __devinit radeon_probe_screens(struct radeonfb_info *rinfo,
 		 * Auto-detecting display type (well... trying to ...)
 		 */
 		
-		RTRACE("Starting monitor auto detection...\n");
+		pr_debug("Starting monitor auto detection...\n");
 
-#if DEBUG && defined(CONFIG_FB_RADEON_I2C)
+#if defined(DEBUG) && defined(CONFIG_FB_RADEON_I2C)
 		{
 			u8 *EDIDs[4] = { NULL, NULL, NULL, NULL };
 			int mon_types[4] = {MT_NONE, MT_NONE, MT_NONE, MT_NONE};
@@ -756,7 +756,7 @@ void __devinit radeon_check_modes(struct radeonfb_info *rinfo, const char *mode_
 	if (!rinfo->panel_info.use_bios_dividers && rinfo->mon1_type != MT_CRT
 	    && rinfo->mon1_EDID) {
 		struct fb_var_screeninfo var;
-		RTRACE("Parsing EDID data for panel info\n");
+		pr_debug("Parsing EDID data for panel info\n");
 		if (fb_parse_edid(rinfo->mon1_EDID, &var) == 0) {
 			if (var.xres >= rinfo->panel_info.xres &&
 			    var.yres >= rinfo->panel_info.yres)
@@ -776,7 +776,7 @@ void __devinit radeon_check_modes(struct radeonfb_info *rinfo, const char *mode_
 	if (rinfo->mon1_type != MT_CRT && rinfo->panel_info.valid) {
 		struct fb_var_screeninfo *var = &info->var;
 
-		RTRACE("Setting up default mode based on panel info\n");
+		pr_debug("Setting up default mode based on panel info\n");
 		var->xres = rinfo->panel_info.xres;
 		var->yres = rinfo->panel_info.yres;
 		var->xres_virtual = rinfo->panel_info.xres;
@@ -824,7 +824,7 @@ void __devinit radeon_check_modes(struct radeonfb_info *rinfo, const char *mode_
 		int			dbsize;
 		char			modename[32];
 
-		RTRACE("Guessing panel info...\n");
+		pr_debug("Guessing panel info...\n");
 		if (rinfo->panel_info.xres == 0 || rinfo->panel_info.yres == 0) {
 			u32 tmp = INREG(FP_HORZ_STRETCH) & HORZ_PANEL_SIZE;
 			rinfo->panel_info.xres = ((tmp >> HORZ_PANEL_SHIFT) + 1) * 8;
diff --git a/trunk/drivers/video/aty/radeonfb.h b/trunk/drivers/video/aty/radeonfb.h
index 5eac1ce52e72..c347e38cd0b0 100644
--- a/trunk/drivers/video/aty/radeonfb.h
+++ b/trunk/drivers/video/aty/radeonfb.h
@@ -1,6 +1,10 @@
 #ifndef __RADEONFB_H__
 #define __RADEONFB_H__
 
+#ifdef CONFIG_FB_RADEON_DEBUG
+#define DEBUG		1
+#endif
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
@@ -364,22 +368,6 @@ struct radeonfb_info {
 #define PRIMARY_MONITOR(rinfo)	(rinfo->mon1_type)
 
 
-/*
- * Debugging stuffs
- */
-#ifdef CONFIG_FB_RADEON_DEBUG
-#define DEBUG		1
-#else
-#define DEBUG		0
-#endif
-
-#if DEBUG
-#define RTRACE		printk
-#else
-#define RTRACE		if(0) printk
-#endif
-
-
 /*
  * IO macros
  */
diff --git a/trunk/drivers/video/bf54x-lq043fb.c b/trunk/drivers/video/bf54x-lq043fb.c
index eefba3d0e4b9..49834a67a623 100644
--- a/trunk/drivers/video/bf54x-lq043fb.c
+++ b/trunk/drivers/video/bf54x-lq043fb.c
@@ -336,7 +336,7 @@ static int bfin_bf54x_fb_check_var(struct fb_var_screeninfo *var,
 {
 
 	if (var->bits_per_pixel != LCD_BPP) {
-		pr_debug("%s: depth not supported: %u BPP\n", __FUNCTION__,
+		pr_debug("%s: depth not supported: %u BPP\n", __func__,
 			 var->bits_per_pixel);
 		return -EINVAL;
 	}
@@ -345,7 +345,7 @@ static int bfin_bf54x_fb_check_var(struct fb_var_screeninfo *var,
 	    info->var.xres_virtual != var->xres_virtual ||
 	    info->var.yres_virtual != var->yres_virtual) {
 		pr_debug("%s: Resolution not supported: X%u x Y%u \n",
-			 __FUNCTION__, var->xres, var->yres);
+			 __func__, var->xres, var->yres);
 		return -EINVAL;
 	}
 
@@ -355,7 +355,7 @@ static int bfin_bf54x_fb_check_var(struct fb_var_screeninfo *var,
 
 	if ((info->fix.line_length * var->yres_virtual) > info->fix.smem_len) {
 		pr_debug("%s: Memory Limit requested yres_virtual = %u\n",
-			 __FUNCTION__, var->yres_virtual);
+			 __func__, var->yres_virtual);
 		return -ENOMEM;
 	}
 
@@ -652,7 +652,7 @@ static int __init bfin_bf54x_probe(struct platform_device *pdev)
 		goto out7;
 	}
 
-	if (request_irq(info->irq, (void *)bfin_bf54x_irq_error, IRQF_DISABLED,
+	if (request_irq(info->irq, bfin_bf54x_irq_error, IRQF_DISABLED,
 			"PPI ERROR", info) < 0) {
 		printk(KERN_ERR DRIVER_NAME
 		       ": unable to request PPI ERROR IRQ\n");
diff --git a/trunk/drivers/video/bw2.c b/trunk/drivers/video/bw2.c
index 833b10c84064..275d9dab0c61 100644
--- a/trunk/drivers/video/bw2.c
+++ b/trunk/drivers/video/bw2.c
@@ -339,7 +339,7 @@ static int __devinit bw2_probe(struct of_device *op, const struct of_device_id *
 
 	dev_set_drvdata(&op->dev, info);
 
-	printk("%s: bwtwo at %lx:%lx\n",
+	printk(KERN_INFO "%s: bwtwo at %lx:%lx\n",
 	       dp->full_name, par->which_io, par->physbase);
 
 	return 0;
@@ -399,10 +399,9 @@ static int __init bw2_init(void)
 
 static void __exit bw2_exit(void)
 {
-	return of_unregister_driver(&bw2_driver);
+	of_unregister_driver(&bw2_driver);
 }
 
-
 module_init(bw2_init);
 module_exit(bw2_exit);
 
diff --git a/trunk/drivers/video/cfbcopyarea.c b/trunk/drivers/video/cfbcopyarea.c
index b07e419b12d2..df03f3776dcc 100644
--- a/trunk/drivers/video/cfbcopyarea.c
+++ b/trunk/drivers/video/cfbcopyarea.c
@@ -44,15 +44,16 @@
      */
 
 static void
-bitcpy(unsigned long __iomem *dst, int dst_idx, const unsigned long __iomem *src,
-	int src_idx, int bits, unsigned n, u32 bswapmask)
+bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
+		const unsigned long __iomem *src, int src_idx, int bits,
+		unsigned n, u32 bswapmask)
 {
 	unsigned long first, last;
 	int const shift = dst_idx-src_idx;
 	int left, right;
 
-	first = fb_shifted_pixels_mask_long(dst_idx, bswapmask);
-	last = ~fb_shifted_pixels_mask_long((dst_idx+n) % bits, bswapmask);
+	first = fb_shifted_pixels_mask_long(p, dst_idx, bswapmask);
+	last = ~fb_shifted_pixels_mask_long(p, (dst_idx+n) % bits, bswapmask);
 
 	if (!shift) {
 		// Same alignment for source and dest
@@ -202,8 +203,9 @@ bitcpy(unsigned long __iomem *dst, int dst_idx, const unsigned long __iomem *src
      */
 
 static void
-bitcpy_rev(unsigned long __iomem *dst, int dst_idx, const unsigned long __iomem *src,
-		int src_idx, int bits, unsigned n, u32 bswapmask)
+bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
+		const unsigned long __iomem *src, int src_idx, int bits,
+		unsigned n, u32 bswapmask)
 {
 	unsigned long first, last;
 	int shift;
@@ -221,8 +223,9 @@ bitcpy_rev(unsigned long __iomem *dst, int dst_idx, const unsigned long __iomem
 
 	shift = dst_idx-src_idx;
 
-	first = fb_shifted_pixels_mask_long(bits - 1 - dst_idx, bswapmask);
-	last = ~fb_shifted_pixels_mask_long(bits - 1 - ((dst_idx-n) % bits), bswapmask);
+	first = fb_shifted_pixels_mask_long(p, bits - 1 - dst_idx, bswapmask);
+	last = ~fb_shifted_pixels_mask_long(p, bits - 1 - ((dst_idx-n) % bits),
+					    bswapmask);
 
 	if (!shift) {
 		// Same alignment for source and dest
@@ -404,7 +407,7 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area)
 			dst_idx &= (bytes - 1);
 			src += src_idx >> (ffs(bits) - 1);
 			src_idx &= (bytes - 1);
-			bitcpy_rev(dst, dst_idx, src, src_idx, bits,
+			bitcpy_rev(p, dst, dst_idx, src, src_idx, bits,
 				width*p->var.bits_per_pixel, bswapmask);
 		}
 	} else {
@@ -413,7 +416,7 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area)
 			dst_idx &= (bytes - 1);
 			src += src_idx >> (ffs(bits) - 1);
 			src_idx &= (bytes - 1);
-			bitcpy(dst, dst_idx, src, src_idx, bits,
+			bitcpy(p, dst, dst_idx, src, src_idx, bits,
 				width*p->var.bits_per_pixel, bswapmask);
 			dst_idx += bits_per_line;
 			src_idx += bits_per_line;
diff --git a/trunk/drivers/video/cfbfillrect.c b/trunk/drivers/video/cfbfillrect.c
index 23d70a12e4da..64b35766b2a2 100644
--- a/trunk/drivers/video/cfbfillrect.c
+++ b/trunk/drivers/video/cfbfillrect.c
@@ -36,16 +36,16 @@
      */
 
 static void
-bitfill_aligned(unsigned long __iomem *dst, int dst_idx, unsigned long pat,
-		unsigned n, int bits, u32 bswapmask)
+bitfill_aligned(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
+		unsigned long pat, unsigned n, int bits, u32 bswapmask)
 {
 	unsigned long first, last;
 
 	if (!n)
 		return;
 
-	first = fb_shifted_pixels_mask_long(dst_idx, bswapmask);
-	last = ~fb_shifted_pixels_mask_long((dst_idx+n) % bits, bswapmask);
+	first = fb_shifted_pixels_mask_long(p, dst_idx, bswapmask);
+	last = ~fb_shifted_pixels_mask_long(p, (dst_idx+n) % bits, bswapmask);
 
 	if (dst_idx+n <= bits) {
 		// Single word
@@ -93,16 +93,16 @@ bitfill_aligned(unsigned long __iomem *dst, int dst_idx, unsigned long pat,
      */
 
 static void
-bitfill_unaligned(unsigned long __iomem *dst, int dst_idx, unsigned long pat,
-			int left, int right, unsigned n, int bits)
+bitfill_unaligned(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
+		  unsigned long pat, int left, int right, unsigned n, int bits)
 {
 	unsigned long first, last;
 
 	if (!n)
 		return;
 
-	first = FB_SHIFT_HIGH(~0UL, dst_idx);
-	last = ~(FB_SHIFT_HIGH(~0UL, (dst_idx+n) % bits));
+	first = FB_SHIFT_HIGH(p, ~0UL, dst_idx);
+	last = ~(FB_SHIFT_HIGH(p, ~0UL, (dst_idx+n) % bits));
 
 	if (dst_idx+n <= bits) {
 		// Single word
@@ -147,8 +147,9 @@ bitfill_unaligned(unsigned long __iomem *dst, int dst_idx, unsigned long pat,
      *  Aligned pattern invert using 32/64-bit memory accesses
      */
 static void
-bitfill_aligned_rev(unsigned long __iomem *dst, int dst_idx, unsigned long pat,
-		unsigned n, int bits, u32 bswapmask)
+bitfill_aligned_rev(struct fb_info *p, unsigned long __iomem *dst,
+		    int dst_idx, unsigned long pat, unsigned n, int bits,
+		    u32 bswapmask)
 {
 	unsigned long val = pat, dat;
 	unsigned long first, last;
@@ -156,8 +157,8 @@ bitfill_aligned_rev(unsigned long __iomem *dst, int dst_idx, unsigned long pat,
 	if (!n)
 		return;
 
-	first = fb_shifted_pixels_mask_long(dst_idx, bswapmask);
-	last = ~fb_shifted_pixels_mask_long((dst_idx+n) % bits, bswapmask);
+	first = fb_shifted_pixels_mask_long(p, dst_idx, bswapmask);
+	last = ~fb_shifted_pixels_mask_long(p, (dst_idx+n) % bits, bswapmask);
 
 	if (dst_idx+n <= bits) {
 		// Single word
@@ -217,16 +218,17 @@ bitfill_aligned_rev(unsigned long __iomem *dst, int dst_idx, unsigned long pat,
      */
 
 static void
-bitfill_unaligned_rev(unsigned long __iomem *dst, int dst_idx, unsigned long pat,
-			int left, int right, unsigned n, int bits)
+bitfill_unaligned_rev(struct fb_info *p, unsigned long __iomem *dst,
+		      int dst_idx, unsigned long pat, int left, int right,
+		      unsigned n, int bits)
 {
 	unsigned long first, last, dat;
 
 	if (!n)
 		return;
 
-	first = FB_SHIFT_HIGH(~0UL, dst_idx);
-	last = ~(FB_SHIFT_HIGH(~0UL, (dst_idx+n) % bits));
+	first = FB_SHIFT_HIGH(p, ~0UL, dst_idx);
+	last = ~(FB_SHIFT_HIGH(p, ~0UL, (dst_idx+n) % bits));
 
 	if (dst_idx+n <= bits) {
 		// Single word
@@ -306,7 +308,8 @@ void cfb_fillrect(struct fb_info *p, const struct fb_fillrect *rect)
 		p->fbops->fb_sync(p);
 	if (!left) {
 		u32 bswapmask = fb_compute_bswapmask(p);
-		void (*fill_op32)(unsigned long __iomem *dst, int dst_idx,
+		void (*fill_op32)(struct fb_info *p,
+				  unsigned long __iomem *dst, int dst_idx,
 		                  unsigned long pat, unsigned n, int bits,
 				  u32 bswapmask) = NULL;
 
@@ -325,16 +328,17 @@ void cfb_fillrect(struct fb_info *p, const struct fb_fillrect *rect)
 		while (height--) {
 			dst += dst_idx >> (ffs(bits) - 1);
 			dst_idx &= (bits - 1);
-			fill_op32(dst, dst_idx, pat, width*bpp, bits, bswapmask);
+			fill_op32(p, dst, dst_idx, pat, width*bpp, bits,
+				  bswapmask);
 			dst_idx += p->fix.line_length*8;
 		}
 	} else {
 		int right;
 		int r;
 		int rot = (left-dst_idx) % bpp;
-		void (*fill_op)(unsigned long __iomem *dst, int dst_idx,
-		                unsigned long pat, int left, int right,
-		                unsigned n, int bits) = NULL;
+		void (*fill_op)(struct fb_info *p, unsigned long __iomem *dst,
+				int dst_idx, unsigned long pat, int left,
+				int right, unsigned n, int bits) = NULL;
 
 		/* rotate pattern to correct start position */
 		pat = pat << rot | pat >> (bpp-rot);
@@ -355,7 +359,7 @@ void cfb_fillrect(struct fb_info *p, const struct fb_fillrect *rect)
 		while (height--) {
 			dst += dst_idx >> (ffs(bits) - 1);
 			dst_idx &= (bits - 1);
-			fill_op(dst, dst_idx, pat, left, right,
+			fill_op(p, dst, dst_idx, pat, left, right,
 				width*bpp, bits);
 			r = (p->fix.line_length*8) % bpp;
 			pat = pat << (bpp-r) | pat >> r;
diff --git a/trunk/drivers/video/cfbimgblt.c b/trunk/drivers/video/cfbimgblt.c
index f598907b42ad..baed57d3cfff 100644
--- a/trunk/drivers/video/cfbimgblt.c
+++ b/trunk/drivers/video/cfbimgblt.c
@@ -38,35 +38,31 @@
 #define DEBUG
 
 #ifdef DEBUG
-#define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt,__FUNCTION__,## args)
+#define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt,__func__,## args)
 #else
 #define DPRINTK(fmt, args...)
 #endif
 
-static const u32 cfb_tab8[] = {
-#if defined(__BIG_ENDIAN)
+static const u32 cfb_tab8_be[] = {
     0x00000000,0x000000ff,0x0000ff00,0x0000ffff,
     0x00ff0000,0x00ff00ff,0x00ffff00,0x00ffffff,
     0xff000000,0xff0000ff,0xff00ff00,0xff00ffff,
     0xffff0000,0xffff00ff,0xffffff00,0xffffffff
-#elif defined(__LITTLE_ENDIAN)
+};
+
+static const u32 cfb_tab8_le[] = {
     0x00000000,0xff000000,0x00ff0000,0xffff0000,
     0x0000ff00,0xff00ff00,0x00ffff00,0xffffff00,
     0x000000ff,0xff0000ff,0x00ff00ff,0xffff00ff,
     0x0000ffff,0xff00ffff,0x00ffffff,0xffffffff
-#else
-#error FIXME: No endianness??
-#endif
 };
 
-static const u32 cfb_tab16[] = {
-#if defined(__BIG_ENDIAN)
+static const u32 cfb_tab16_be[] = {
     0x00000000, 0x0000ffff, 0xffff0000, 0xffffffff
-#elif defined(__LITTLE_ENDIAN)
+};
+
+static const u32 cfb_tab16_le[] = {
     0x00000000, 0xffff0000, 0x0000ffff, 0xffffffff
-#else
-#error FIXME: No endianness??
-#endif
 };
 
 static const u32 cfb_tab32[] = {
@@ -98,7 +94,8 @@ static inline void color_imageblit(const struct fb_image *image,
 		val = 0;
 		
 		if (start_index) {
-			u32 start_mask = ~fb_shifted_pixels_mask_u32(start_index, bswapmask);
+			u32 start_mask = ~fb_shifted_pixels_mask_u32(p,
+						start_index, bswapmask);
 			val = FB_READL(dst) & start_mask;
 			shift = start_index;
 		}
@@ -108,20 +105,21 @@ static inline void color_imageblit(const struct fb_image *image,
 				color = palette[*src];
 			else
 				color = *src;
-			color <<= FB_LEFT_POS(bpp);
-			val |= FB_SHIFT_HIGH(color, shift ^ bswapmask);
+			color <<= FB_LEFT_POS(p, bpp);
+			val |= FB_SHIFT_HIGH(p, color, shift ^ bswapmask);
 			if (shift >= null_bits) {
 				FB_WRITEL(val, dst++);
 	
 				val = (shift == null_bits) ? 0 : 
-					FB_SHIFT_LOW(color, 32 - shift);
+					FB_SHIFT_LOW(p, color, 32 - shift);
 			}
 			shift += bpp;
 			shift &= (32 - 1);
 			src++;
 		}
 		if (shift) {
-			u32 end_mask = fb_shifted_pixels_mask_u32(shift, bswapmask);
+			u32 end_mask = fb_shifted_pixels_mask_u32(p, shift,
+						bswapmask);
 
 			FB_WRITEL((FB_READL(dst) & end_mask) | val, dst);
 		}
@@ -152,8 +150,8 @@ static inline void slow_imageblit(const struct fb_image *image, struct fb_info *
 	u32 bswapmask = fb_compute_bswapmask(p);
 
 	dst2 = (u32 __iomem *) dst1;
-	fgcolor <<= FB_LEFT_POS(bpp);
-	bgcolor <<= FB_LEFT_POS(bpp);
+	fgcolor <<= FB_LEFT_POS(p, bpp);
+	bgcolor <<= FB_LEFT_POS(p, bpp);
 
 	for (i = image->height; i--; ) {
 		shift = val = 0;
@@ -164,7 +162,8 @@ static inline void slow_imageblit(const struct fb_image *image, struct fb_info *
 
 		/* write leading bits */
 		if (start_index) {
-			u32 start_mask = ~fb_shifted_pixels_mask_u32(start_index, bswapmask);
+			u32 start_mask = ~fb_shifted_pixels_mask_u32(p,
+						start_index, bswapmask);
 			val = FB_READL(dst) & start_mask;
 			shift = start_index;
 		}
@@ -172,13 +171,13 @@ static inline void slow_imageblit(const struct fb_image *image, struct fb_info *
 		while (j--) {
 			l--;
 			color = (*s & (1 << l)) ? fgcolor : bgcolor;
-			val |= FB_SHIFT_HIGH(color, shift ^ bswapmask);
+			val |= FB_SHIFT_HIGH(p, color, shift ^ bswapmask);
 			
 			/* Did the bitshift spill bits to the next long? */
 			if (shift >= null_bits) {
 				FB_WRITEL(val, dst++);
 				val = (shift == null_bits) ? 0 :
-					FB_SHIFT_LOW(color,32 - shift);
+					FB_SHIFT_LOW(p, color, 32 - shift);
 			}
 			shift += bpp;
 			shift &= (32 - 1);
@@ -187,7 +186,8 @@ static inline void slow_imageblit(const struct fb_image *image, struct fb_info *
 
 		/* write trailing bits */
  		if (shift) {
-			u32 end_mask = fb_shifted_pixels_mask_u32(shift, bswapmask);
+			u32 end_mask = fb_shifted_pixels_mask_u32(p, shift,
+						bswapmask);
 
 			FB_WRITEL((FB_READL(dst) & end_mask) | val, dst);
 		}
@@ -223,13 +223,13 @@ static inline void fast_imageblit(const struct fb_image *image, struct fb_info *
 	u32 __iomem *dst;
 	const u32 *tab = NULL;
 	int i, j, k;
-		
+
 	switch (bpp) {
 	case 8:
-		tab = cfb_tab8;
+		tab = fb_be_math(p) ? cfb_tab8_be : cfb_tab8_le;
 		break;
 	case 16:
-		tab = cfb_tab16;
+		tab = fb_be_math(p) ? cfb_tab16_be : cfb_tab16_le;
 		break;
 	case 32:
 	default:
diff --git a/trunk/drivers/video/cg14.c b/trunk/drivers/video/cg14.c
index fdc9f43ec30a..0db0fecba93b 100644
--- a/trunk/drivers/video/cg14.c
+++ b/trunk/drivers/video/cg14.c
@@ -556,7 +556,7 @@ static int __devinit cg14_probe(struct of_device *op, const struct of_device_id
 
 	dev_set_drvdata(&op->dev, info);
 
-	printk("%s: cgfourteen at %lx:%lx, %dMB\n",
+	printk(KERN_INFO "%s: cgfourteen at %lx:%lx, %dMB\n",
 	       dp->full_name,
 	       par->iospace, par->physbase,
 	       par->ramsize >> 20);
@@ -605,7 +605,7 @@ static struct of_platform_driver cg14_driver = {
 	.remove		= __devexit_p(cg14_remove),
 };
 
-int __init cg14_init(void)
+static int __init cg14_init(void)
 {
 	if (fb_get_options("cg14fb", NULL))
 		return -ENODEV;
@@ -613,7 +613,7 @@ int __init cg14_init(void)
 	return of_register_driver(&cg14_driver, &of_bus_type);
 }
 
-void __exit cg14_exit(void)
+static void __exit cg14_exit(void)
 {
 	of_unregister_driver(&cg14_driver);
 }
diff --git a/trunk/drivers/video/cg3.c b/trunk/drivers/video/cg3.c
index a5c7fb331527..010ea53978f8 100644
--- a/trunk/drivers/video/cg3.c
+++ b/trunk/drivers/video/cg3.c
@@ -419,7 +419,7 @@ static int __devinit cg3_probe(struct of_device *op,
 
 	dev_set_drvdata(&op->dev, info);
 
-	printk("%s: cg3 at %lx:%lx\n",
+	printk(KERN_INFO "%s: cg3 at %lx:%lx\n",
 	       dp->full_name, par->which_io, par->physbase);
 
 	return 0;
diff --git a/trunk/drivers/video/cg6.c b/trunk/drivers/video/cg6.c
index 549891d76ef5..fc90db6da65a 100644
--- a/trunk/drivers/video/cg6.c
+++ b/trunk/drivers/video/cg6.c
@@ -781,7 +781,7 @@ static int __devinit cg6_probe(struct of_device *op,
 
 	dev_set_drvdata(&op->dev, info);
 
-	printk("%s: CGsix [%s] at %lx:%lx\n",
+	printk(KERN_INFO "%s: CGsix [%s] at %lx:%lx\n",
 	       dp->full_name, info->fix.id,
 	       par->which_io, par->physbase);
 
diff --git a/trunk/drivers/video/cirrusfb.c b/trunk/drivers/video/cirrusfb.c
index f7e2d5add831..35ac9d956b3d 100644
--- a/trunk/drivers/video/cirrusfb.c
+++ b/trunk/drivers/video/cirrusfb.c
@@ -81,7 +81,7 @@
 /* debug output */
 #ifdef CIRRUSFB_DEBUG
 #define DPRINTK(fmt, args...) \
-	printk(KERN_DEBUG "%s: " fmt, __FUNCTION__ , ## args)
+	printk(KERN_DEBUG "%s: " fmt, __func__ , ## args)
 #else
 #define DPRINTK(fmt, args...)
 #endif
@@ -91,7 +91,7 @@
 #define assert(expr) \
 	if (!(expr)) { \
 		printk("Assertion failed! %s,%s,%s,line=%d\n", \
-		#expr, __FILE__, __FUNCTION__, __LINE__); \
+		#expr, __FILE__, __func__, __LINE__); \
 	}
 #else
 #define assert(expr)
@@ -3117,7 +3117,7 @@ static void bestclock(long freq, long *best, long *nom,
 				}
 			}
 		}
-		d = ((143181 * n) + f - 1) / f;
+		d = DIV_ROUND_UP(143181 * n, f);
 		if ((d >= 7) && (d <= 63)) {
 			if (d > 31)
 				d = (d / 2) * 2;
diff --git a/trunk/drivers/video/clps711xfb.c b/trunk/drivers/video/clps711xfb.c
index 17b5267f44d7..9f8a389dc7ae 100644
--- a/trunk/drivers/video/clps711xfb.c
+++ b/trunk/drivers/video/clps711xfb.c
@@ -381,7 +381,7 @@ int __init clps711xfb_init(void)
 
 	/* Register the /proc entries. */
 	clps7111fb_backlight_proc_entry = create_proc_entry("backlight", 0444,
-		&proc_root);
+		NULL);
 	if (clps7111fb_backlight_proc_entry == NULL) {
 		printk("Couldn't create the /proc entry for the backlight.\n");
 		return -EINVAL;
diff --git a/trunk/drivers/video/console/fbcon.c b/trunk/drivers/video/console/fbcon.c
index 022282494d3f..ad31983b43eb 100644
--- a/trunk/drivers/video/console/fbcon.c
+++ b/trunk/drivers/video/console/fbcon.c
@@ -92,7 +92,7 @@
 #include "fbcon.h"
 
 #ifdef FBCONDEBUG
-#  define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt, __FUNCTION__ , ## args)
+#  define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt, __func__ , ## args)
 #else
 #  define DPRINTK(fmt, args...)
 #endif
@@ -620,8 +620,7 @@ static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info,
 	if (fb_get_color_depth(&info->var, &info->fix) == 1)
 		erase &= ~0x400;
 	logo_height = fb_prepare_logo(info, ops->rotate);
-	logo_lines = (logo_height + vc->vc_font.height - 1) /
-		vc->vc_font.height;
+	logo_lines = DIV_ROUND_UP(logo_height, vc->vc_font.height);
 	q = (unsigned short *) (vc->vc_origin +
 				vc->vc_size_row * rows);
 	step = logo_lines * cols;
@@ -1882,7 +1881,7 @@ static int fbcon_scroll(struct vc_data *vc, int t, int b, int dir,
 			scr_memsetw((unsigned short *) (vc->vc_origin +
 							vc->vc_size_row *
 							(b - count)),
-				    vc->vc_video_erase_char,
+				    vc->vc_scrl_erase_char,
 				    vc->vc_size_row * count);
 			return 1;
 			break;
@@ -1954,7 +1953,7 @@ static int fbcon_scroll(struct vc_data *vc, int t, int b, int dir,
 			scr_memsetw((unsigned short *) (vc->vc_origin +
 							vc->vc_size_row *
 							(b - count)),
-				    vc->vc_video_erase_char,
+				    vc->vc_scrl_erase_char,
 				    vc->vc_size_row * count);
 			return 1;
 		}
@@ -1973,7 +1972,7 @@ static int fbcon_scroll(struct vc_data *vc, int t, int b, int dir,
 			scr_memsetw((unsigned short *) (vc->vc_origin +
 							vc->vc_size_row *
 							t),
-				    vc->vc_video_erase_char,
+				    vc->vc_scrl_erase_char,
 				    vc->vc_size_row * count);
 			return 1;
 			break;
@@ -2043,7 +2042,7 @@ static int fbcon_scroll(struct vc_data *vc, int t, int b, int dir,
 			scr_memsetw((unsigned short *) (vc->vc_origin +
 							vc->vc_size_row *
 							t),
-				    vc->vc_video_erase_char,
+				    vc->vc_scrl_erase_char,
 				    vc->vc_size_row * count);
 			return 1;
 		}
diff --git a/trunk/drivers/video/console/fbcon.h b/trunk/drivers/video/console/fbcon.h
index 3706307e70ed..0135e0395456 100644
--- a/trunk/drivers/video/console/fbcon.h
+++ b/trunk/drivers/video/console/fbcon.h
@@ -104,10 +104,14 @@ struct fbcon_ops {
 #define attr_blink(s) \
 	((s) & 0x8000)
 	
-#define mono_col(info)							\
-	(~(0xfff << (max((info)->var.green.length,			\
-			 max((info)->var.red.length,			\
-			     (info)->var.blue.length)))) & 0xff)
+
+static inline int mono_col(const struct fb_info *info)
+{
+	__u32 max_len;
+	max_len = max(info->var.green.length, info->var.red.length);
+	max_len = max(info->var.blue.length, max_len);
+	return ~(0xfff << (max_len & 0xff));
+}
 
 static inline int attr_col_ec(int shift, struct vc_data *vc,
 			      struct fb_info *info, int is_fg)
diff --git a/trunk/drivers/video/console/mdacon.c b/trunk/drivers/video/console/mdacon.c
index bd8d995fe25d..38a296bbdfc9 100644
--- a/trunk/drivers/video/console/mdacon.c
+++ b/trunk/drivers/video/console/mdacon.c
@@ -531,7 +531,7 @@ static void mdacon_cursor(struct vc_data *c, int mode)
 
 static int mdacon_scroll(struct vc_data *c, int t, int b, int dir, int lines)
 {
-	u16 eattr = mda_convert_attr(c->vc_video_erase_char);
+	u16 eattr = mda_convert_attr(c->vc_scrl_erase_char);
 
 	if (!lines)
 		return 0;
diff --git a/trunk/drivers/video/console/sticon.c b/trunk/drivers/video/console/sticon.c
index 67a682d6cc7b..a11cc2fdd4cd 100644
--- a/trunk/drivers/video/console/sticon.c
+++ b/trunk/drivers/video/console/sticon.c
@@ -170,12 +170,12 @@ static int sticon_scroll(struct vc_data *conp, int t, int b, int dir, int count)
     switch (dir) {
     case SM_UP:
 	sti_bmove(sti, t + count, 0, t, 0, b - t - count, conp->vc_cols);
-	sti_clear(sti, b - count, 0, count, conp->vc_cols, conp->vc_video_erase_char);
+	sti_clear(sti, b - count, 0, count, conp->vc_cols, conp->vc_scrl_erase_char);
 	break;
 
     case SM_DOWN:
 	sti_bmove(sti, t, 0, t + count, 0, b - t - count, conp->vc_cols);
-	sti_clear(sti, t, 0, count, conp->vc_cols, conp->vc_video_erase_char);
+	sti_clear(sti, t, 0, count, conp->vc_cols, conp->vc_scrl_erase_char);
 	break;
     }
 
diff --git a/trunk/drivers/video/console/vgacon.c b/trunk/drivers/video/console/vgacon.c
index 6df29a62d720..bd1f57b259d9 100644
--- a/trunk/drivers/video/console/vgacon.c
+++ b/trunk/drivers/video/console/vgacon.c
@@ -1350,7 +1350,7 @@ static int vgacon_scroll(struct vc_data *c, int t, int b, int dir,
 		} else
 			c->vc_origin += delta;
 		scr_memsetw((u16 *) (c->vc_origin + c->vc_screenbuf_size -
-				     delta), c->vc_video_erase_char,
+				     delta), c->vc_scrl_erase_char,
 			    delta);
 	} else {
 		if (oldo - delta < vga_vram_base) {
@@ -1363,7 +1363,7 @@ static int vgacon_scroll(struct vc_data *c, int t, int b, int dir,
 		} else
 			c->vc_origin -= delta;
 		c->vc_scr_end = c->vc_origin + c->vc_screenbuf_size;
-		scr_memsetw((u16 *) (c->vc_origin), c->vc_video_erase_char,
+		scr_memsetw((u16 *) (c->vc_origin), c->vc_scrl_erase_char,
 			    delta);
 	}
 	c->vc_scr_end = c->vc_origin + c->vc_screenbuf_size;
diff --git a/trunk/drivers/video/fb_draw.h b/trunk/drivers/video/fb_draw.h
index a2a0618d86a5..1db622192bde 100644
--- a/trunk/drivers/video/fb_draw.h
+++ b/trunk/drivers/video/fb_draw.h
@@ -94,41 +94,44 @@ static inline unsigned long fb_rev_pixels_in_long(unsigned long val,
 	return val;
 }
 
-static inline u32 fb_shifted_pixels_mask_u32(u32 index, u32 bswapmask)
+static inline u32 fb_shifted_pixels_mask_u32(struct fb_info *p, u32 index,
+					     u32 bswapmask)
 {
 	u32 mask;
 
 	if (!bswapmask) {
-		mask = FB_SHIFT_HIGH(~(u32)0, index);
+		mask = FB_SHIFT_HIGH(p, ~(u32)0, index);
 	} else {
-		mask = 0xff << FB_LEFT_POS(8);
-		mask = FB_SHIFT_LOW(mask, index & (bswapmask)) & mask;
-		mask = FB_SHIFT_HIGH(mask, index & ~(bswapmask));
+		mask = 0xff << FB_LEFT_POS(p, 8);
+		mask = FB_SHIFT_LOW(p, mask, index & (bswapmask)) & mask;
+		mask = FB_SHIFT_HIGH(p, mask, index & ~(bswapmask));
 #if defined(__i386__) || defined(__x86_64__)
 		/* Shift argument is limited to 0 - 31 on x86 based CPU's */
 		if(index + bswapmask < 32)
 #endif
-			mask |= FB_SHIFT_HIGH(~(u32)0,
+			mask |= FB_SHIFT_HIGH(p, ~(u32)0,
 					(index + bswapmask) & ~(bswapmask));
 	}
 	return mask;
 }
 
-static inline unsigned long fb_shifted_pixels_mask_long(u32 index, u32 bswapmask)
+static inline unsigned long fb_shifted_pixels_mask_long(struct fb_info *p,
+							u32 index,
+							u32 bswapmask)
 {
 	unsigned long mask;
 
 	if (!bswapmask) {
-		mask = FB_SHIFT_HIGH(~0UL, index);
+		mask = FB_SHIFT_HIGH(p, ~0UL, index);
 	} else {
-		mask = 0xff << FB_LEFT_POS(8);
-		mask = FB_SHIFT_LOW(mask, index & (bswapmask)) & mask;
-		mask = FB_SHIFT_HIGH(mask, index & ~(bswapmask));
+		mask = 0xff << FB_LEFT_POS(p, 8);
+		mask = FB_SHIFT_LOW(p, mask, index & (bswapmask)) & mask;
+		mask = FB_SHIFT_HIGH(p, mask, index & ~(bswapmask));
 #if defined(__i386__) || defined(__x86_64__)
 		/* Shift argument is limited to 0 - 31 on x86 based CPU's */
 		if(index + bswapmask < BITS_PER_LONG)
 #endif
-			mask |= FB_SHIFT_HIGH(~0UL,
+			mask |= FB_SHIFT_HIGH(p, ~0UL,
 					(index + bswapmask) & ~(bswapmask));
 	}
 	return mask;
@@ -158,8 +161,8 @@ static inline unsigned long fb_rev_pixels_in_long(unsigned long val,
 	return val;
 }
 
-#define fb_shifted_pixels_mask_u32(i, b) FB_SHIFT_HIGH(~(u32)0, (i))
-#define fb_shifted_pixels_mask_long(i, b) FB_SHIFT_HIGH(~0UL, (i))
+#define fb_shifted_pixels_mask_u32(p, i, b) FB_SHIFT_HIGH((p), ~(u32)0, (i))
+#define fb_shifted_pixels_mask_long(p, i, b) FB_SHIFT_HIGH((p), ~0UL, (i))
 #define fb_compute_bswapmask(...) 0
 
 #endif  /* CONFIG_FB_CFB_REV_PIXELS_IN_BYTE */
diff --git a/trunk/drivers/video/fbmem.c b/trunk/drivers/video/fbmem.c
index 01072f4b3e8f..776f7fcd2fbf 100644
--- a/trunk/drivers/video/fbmem.c
+++ b/trunk/drivers/video/fbmem.c
@@ -26,6 +26,7 @@
 #include <linux/init.h>
 #include <linux/linux_logo.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/console.h>
 #ifdef CONFIG_KMOD
 #include <linux/kmod.h>
@@ -632,27 +633,51 @@ int fb_prepare_logo(struct fb_info *info, int rotate) { return 0; }
 int fb_show_logo(struct fb_info *info, int rotate) { return 0; }
 #endif /* CONFIG_LOGO */
 
-static int fbmem_read_proc(char *buf, char **start, off_t offset,
-			   int len, int *eof, void *private)
+static void *fb_seq_start(struct seq_file *m, loff_t *pos)
 {
-	struct fb_info **fi;
-	int clen;
-
-	clen = 0;
-	for (fi = registered_fb; fi < &registered_fb[FB_MAX] && clen < 4000;
-	     fi++)
-		if (*fi)
-			clen += sprintf(buf + clen, "%d %s\n",
-				        (*fi)->node,
-				        (*fi)->fix.id);
-	*start = buf + offset;
-	if (clen > offset)
-		clen -= offset;
-	else
-		clen = 0;
-	return clen < len ? clen : len;
+	return (*pos < FB_MAX) ? pos : NULL;
+}
+
+static void *fb_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return (*pos < FB_MAX) ? pos : NULL;
+}
+
+static void fb_seq_stop(struct seq_file *m, void *v)
+{
+}
+
+static int fb_seq_show(struct seq_file *m, void *v)
+{
+	int i = *(loff_t *)v;
+	struct fb_info *fi = registered_fb[i];
+
+	if (fi)
+		seq_printf(m, "%d %s\n", fi->node, fi->fix.id);
+	return 0;
+}
+
+static const struct seq_operations proc_fb_seq_ops = {
+	.start	= fb_seq_start,
+	.next	= fb_seq_next,
+	.stop	= fb_seq_stop,
+	.show	= fb_seq_show,
+};
+
+static int proc_fb_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &proc_fb_seq_ops);
 }
 
+static const struct file_operations fb_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= proc_fb_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
 static ssize_t
 fb_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 {
@@ -1057,7 +1082,7 @@ fb_ioctl(struct inode *inode, struct file *file, unsigned int cmd,
 	case FBIOPUT_CON2FBMAP:
 		if (copy_from_user(&con2fb, argp, sizeof(con2fb)))
 			return - EFAULT;
-		if (con2fb.console < 0 || con2fb.console > MAX_NR_CONSOLES)
+		if (con2fb.console < 1 || con2fb.console > MAX_NR_CONSOLES)
 		    return -EINVAL;
 		if (con2fb.framebuffer < 0 || con2fb.framebuffer >= FB_MAX)
 		    return -EINVAL;
@@ -1352,6 +1377,32 @@ static const struct file_operations fb_fops = {
 
 struct class *fb_class;
 EXPORT_SYMBOL(fb_class);
+
+static int fb_check_foreignness(struct fb_info *fi)
+{
+	const bool foreign_endian = fi->flags & FBINFO_FOREIGN_ENDIAN;
+
+	fi->flags &= ~FBINFO_FOREIGN_ENDIAN;
+
+#ifdef __BIG_ENDIAN
+	fi->flags |= foreign_endian ? 0 : FBINFO_BE_MATH;
+#else
+	fi->flags |= foreign_endian ? FBINFO_BE_MATH : 0;
+#endif /* __BIG_ENDIAN */
+
+	if (fi->flags & FBINFO_BE_MATH && !fb_be_math(fi)) {
+		pr_err("%s: enable CONFIG_FB_BIG_ENDIAN to "
+		       "support this framebuffer\n", fi->fix.id);
+		return -ENOSYS;
+	} else if (!(fi->flags & FBINFO_BE_MATH) && fb_be_math(fi)) {
+		pr_err("%s: enable CONFIG_FB_LITTLE_ENDIAN to "
+		       "support this framebuffer\n", fi->fix.id);
+		return -ENOSYS;
+	}
+
+	return 0;
+}
+
 /**
  *	register_framebuffer - registers a frame buffer device
  *	@fb_info: frame buffer info structure
@@ -1371,6 +1422,10 @@ register_framebuffer(struct fb_info *fb_info)
 
 	if (num_registered_fb == FB_MAX)
 		return -ENXIO;
+
+	if (fb_check_foreignness(fb_info))
+		return -ENOSYS;
+
 	num_registered_fb++;
 	for (i = 0 ; i < FB_MAX; i++)
 		if (!registered_fb[i])
@@ -1503,7 +1558,7 @@ void fb_set_suspend(struct fb_info *info, int state)
 static int __init
 fbmem_init(void)
 {
-	create_proc_read_entry("fb", 0, NULL, fbmem_read_proc, NULL);
+	proc_create("fb", 0, NULL, &fb_proc_fops);
 
 	if (register_chrdev(FB_MAJOR,"fb",&fb_fops))
 		printk("unable to get major %d for fb devs\n", FB_MAJOR);
diff --git a/trunk/drivers/video/ffb.c b/trunk/drivers/video/ffb.c
index d7e24889650e..93dca3e2aa50 100644
--- a/trunk/drivers/video/ffb.c
+++ b/trunk/drivers/video/ffb.c
@@ -32,7 +32,6 @@
 static int ffb_setcolreg(unsigned, unsigned, unsigned, unsigned,
 			 unsigned, struct fb_info *);
 static int ffb_blank(int, struct fb_info *);
-static void ffb_init_fix(struct fb_info *);
 
 static void ffb_imageblit(struct fb_info *, const struct fb_image *);
 static void ffb_fillrect(struct fb_info *, const struct fb_fillrect *);
@@ -1001,7 +1000,7 @@ static int __devinit ffb_probe(struct of_device *op,
 
 	dev_set_drvdata(&op->dev, info);
 
-	printk("%s: %s at %016lx, type %d, "
+	printk(KERN_INFO "%s: %s at %016lx, type %d, "
 	       "DAC pnum[%x] rev[%d] manuf_rev[%d]\n",
 	       dp->full_name,
 	       ((par->flags & FFB_FLAG_AFB) ? "AFB" : "FFB"),
@@ -1062,7 +1061,7 @@ static struct of_platform_driver ffb_driver = {
 	.remove		= __devexit_p(ffb_remove),
 };
 
-int __init ffb_init(void)
+static int __init ffb_init(void)
 {
 	if (fb_get_options("ffb", NULL))
 		return -ENODEV;
@@ -1070,7 +1069,7 @@ int __init ffb_init(void)
 	return of_register_driver(&ffb_driver, &of_bus_type);
 }
 
-void __exit ffb_exit(void)
+static void __exit ffb_exit(void)
 {
 	of_unregister_driver(&ffb_driver);
 }
diff --git a/trunk/drivers/video/fsl-diu-fb.c b/trunk/drivers/video/fsl-diu-fb.c
new file mode 100644
index 000000000000..b50bb03cb5ab
--- /dev/null
+++ b/trunk/drivers/video/fsl-diu-fb.c
@@ -0,0 +1,1721 @@
+/*
+ * Copyright 2008 Freescale Semiconductor, Inc. All Rights Reserved.
+ *
+ *  Freescale DIU Frame Buffer device driver
+ *
+ *  Authors: Hongjun Chen <hong-jun.chen@freescale.com>
+ *           Paul Widmer <paul.widmer@freescale.com>
+ *           Srikanth Srinivasan <srikanth.srinivasan@freescale.com>
+ *           York Sun <yorksun@freescale.com>
+ *
+ *   Based on imxfb.c Copyright (C) 2004 S.Hauer, Pengutronix
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/fb.h>
+#include <linux/init.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/clk.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+
+#include <linux/of_platform.h>
+
+#include <sysdev/fsl_soc.h>
+#include "fsl-diu-fb.h"
+
+/*
+ * These parameters give default parameters
+ * for video output 1024x768,
+ * FIXME - change timing to proper amounts
+ * hsync 31.5kHz, vsync 60Hz
+ */
+static struct fb_videomode __devinitdata fsl_diu_default_mode = {
+	.refresh	= 60,
+	.xres		= 1024,
+	.yres		= 768,
+	.pixclock	= 15385,
+	.left_margin	= 160,
+	.right_margin	= 24,
+	.upper_margin	= 29,
+	.lower_margin	= 3,
+	.hsync_len	= 136,
+	.vsync_len	= 6,
+	.sync		= FB_SYNC_COMP_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+	.vmode		= FB_VMODE_NONINTERLACED
+};
+
+static struct fb_videomode __devinitdata fsl_diu_mode_db[] = {
+	{
+		.name		= "1024x768-60",
+		.refresh	= 60,
+		.xres		= 1024,
+		.yres		= 768,
+		.pixclock	= 15385,
+		.left_margin	= 160,
+		.right_margin	= 24,
+		.upper_margin	= 29,
+		.lower_margin	= 3,
+		.hsync_len	= 136,
+		.vsync_len	= 6,
+		.sync		= FB_SYNC_COMP_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.vmode		= FB_VMODE_NONINTERLACED
+	},
+	{
+		.name		= "1024x768-70",
+		.refresh	= 70,
+		.xres		= 1024,
+		.yres		= 768,
+		.pixclock	= 16886,
+		.left_margin	= 3,
+		.right_margin	= 3,
+		.upper_margin	= 2,
+		.lower_margin	= 2,
+		.hsync_len	= 40,
+		.vsync_len	= 18,
+		.sync		= FB_SYNC_COMP_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.vmode		= FB_VMODE_NONINTERLACED
+	},
+	{
+		.name		= "1024x768-75",
+		.refresh	= 75,
+		.xres		= 1024,
+		.yres		= 768,
+		.pixclock	= 15009,
+		.left_margin	= 3,
+		.right_margin	= 3,
+		.upper_margin	= 2,
+		.lower_margin	= 2,
+		.hsync_len	= 80,
+		.vsync_len	= 32,
+		.sync		= FB_SYNC_COMP_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.vmode		= FB_VMODE_NONINTERLACED
+	},
+	{
+		.name		= "1280x1024-60",
+		.refresh	= 60,
+		.xres		= 1280,
+		.yres		= 1024,
+		.pixclock	= 9375,
+		.left_margin	= 38,
+		.right_margin	= 128,
+		.upper_margin	= 2,
+		.lower_margin	= 7,
+		.hsync_len	= 216,
+		.vsync_len	= 37,
+		.sync		= FB_SYNC_COMP_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.vmode		= FB_VMODE_NONINTERLACED
+	},
+	{
+		.name		= "1280x1024-70",
+		.refresh	= 70,
+		.xres		= 1280,
+		.yres		= 1024,
+		.pixclock	= 9380,
+		.left_margin	= 6,
+		.right_margin	= 6,
+		.upper_margin	= 4,
+		.lower_margin	= 4,
+		.hsync_len	= 60,
+		.vsync_len	= 94,
+		.sync		= FB_SYNC_COMP_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.vmode		= FB_VMODE_NONINTERLACED
+	},
+	{
+		.name		= "1280x1024-75",
+		.refresh	= 75,
+		.xres		= 1280,
+		.yres		= 1024,
+		.pixclock	= 9380,
+		.left_margin	= 6,
+		.right_margin	= 6,
+		.upper_margin	= 4,
+		.lower_margin	= 4,
+		.hsync_len	= 60,
+		.vsync_len	= 15,
+		.sync		= FB_SYNC_COMP_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.vmode		= FB_VMODE_NONINTERLACED
+	},
+	{
+		.name		= "320x240",		/* for AOI only */
+		.refresh	= 60,
+		.xres		= 320,
+		.yres		= 240,
+		.pixclock	= 15385,
+		.left_margin	= 0,
+		.right_margin	= 0,
+		.upper_margin	= 0,
+		.lower_margin	= 0,
+		.hsync_len	= 0,
+		.vsync_len	= 0,
+		.sync		= FB_SYNC_COMP_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.vmode		= FB_VMODE_NONINTERLACED
+	},
+	{
+		.name		= "1280x480-60",
+		.refresh	= 60,
+		.xres		= 1280,
+		.yres		= 480,
+		.pixclock	= 18939,
+		.left_margin	= 353,
+		.right_margin	= 47,
+		.upper_margin	= 39,
+		.lower_margin	= 4,
+		.hsync_len	= 8,
+		.vsync_len	= 2,
+		.sync		= FB_SYNC_COMP_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.vmode		= FB_VMODE_NONINTERLACED
+	},
+};
+
+static char *fb_mode = "1024x768-32@60";
+static unsigned long default_bpp = 32;
+static int monitor_port;
+
+#if defined(CONFIG_NOT_COHERENT_CACHE)
+static u8 *coherence_data;
+static size_t coherence_data_size;
+static unsigned int d_cache_line_size;
+#endif
+
+static DEFINE_SPINLOCK(diu_lock);
+
+struct fsl_diu_data {
+	struct fb_info *fsl_diu_info[FSL_AOI_NUM - 1];
+				/*FSL_AOI_NUM has one dummy AOI */
+	struct device_attribute dev_attr;
+	struct diu_ad *dummy_ad;
+	void *dummy_aoi_virt;
+	unsigned int irq;
+	int fb_enabled;
+	int monitor_port;
+};
+
+struct mfb_info {
+	int index;
+	int type;
+	char *id;
+	int registered;
+	int blank;
+	unsigned long pseudo_palette[16];
+	struct diu_ad *ad;
+	int cursor_reset;
+	unsigned char g_alpha;
+	unsigned int count;
+	int x_aoi_d;		/* aoi display x offset to physical screen */
+	int y_aoi_d;		/* aoi display y offset to physical screen */
+	struct fsl_diu_data *parent;
+};
+
+
+static struct mfb_info mfb_template[] = {
+	{		/* AOI 0 for plane 0 */
+	.index = 0,
+	.type = MFB_TYPE_OUTPUT,
+	.id = "Panel0",
+	.registered = 0,
+	.count = 0,
+	.x_aoi_d = 0,
+	.y_aoi_d = 0,
+	},
+	{		/* AOI 0 for plane 1 */
+	.index = 1,
+	.type = MFB_TYPE_OUTPUT,
+	.id = "Panel1 AOI0",
+	.registered = 0,
+	.g_alpha = 0xff,
+	.count = 0,
+	.x_aoi_d = 0,
+	.y_aoi_d = 0,
+	},
+	{		/* AOI 1 for plane 1 */
+	.index = 2,
+	.type = MFB_TYPE_OUTPUT,
+	.id = "Panel1 AOI1",
+	.registered = 0,
+	.g_alpha = 0xff,
+	.count = 0,
+	.x_aoi_d = 0,
+	.y_aoi_d = 480,
+	},
+	{		/* AOI 0 for plane 2 */
+	.index = 3,
+	.type = MFB_TYPE_OUTPUT,
+	.id = "Panel2 AOI0",
+	.registered = 0,
+	.g_alpha = 0xff,
+	.count = 0,
+	.x_aoi_d = 640,
+	.y_aoi_d = 0,
+	},
+	{		/* AOI 1 for plane 2 */
+	.index = 4,
+	.type = MFB_TYPE_OUTPUT,
+	.id = "Panel2 AOI1",
+	.registered = 0,
+	.g_alpha = 0xff,
+	.count = 0,
+	.x_aoi_d = 640,
+	.y_aoi_d = 480,
+	},
+};
+
+static struct diu_hw dr = {
+	.mode = MFB_MODE1,
+	.reg_lock = __SPIN_LOCK_UNLOCKED(diu_hw.reg_lock),
+};
+
+static struct diu_pool pool;
+
+/*	To allocate memory for framebuffer. First try __get_free_pages(). If it
+ *	fails, try rh_alloc. The reason is __get_free_pages() cannot allocate
+ *	very large memory (more than 4MB). We don't want to allocate all memory
+ *	in rheap since small memory allocation/deallocation will fragment the
+ *	rheap and make the furture large allocation fail.
+ */
+
+void *fsl_diu_alloc(unsigned long size, phys_addr_t *phys)
+{
+	void *virt;
+
+	pr_debug("size=%lu\n", size);
+
+	virt = (void *)__get_free_pages(GFP_DMA | __GFP_ZERO, get_order(size));
+	if (virt) {
+		*phys = virt_to_phys(virt);
+		pr_debug("virt %p, phys=%llx\n", virt, (uint64_t) *phys);
+		return virt;
+	}
+	if (!diu_ops.diu_mem) {
+		printk(KERN_INFO "%s: no diu_mem."
+			" To reserve more memory, put 'diufb=15M' "
+			"in the command line\n", __func__);
+		return NULL;
+	}
+
+	virt = (void *)rh_alloc(&diu_ops.diu_rh_info, size, "DIU");
+	if (virt) {
+		*phys = virt_to_bus(virt);
+		memset(virt, 0, size);
+	}
+
+	pr_debug("rh virt=%p phys=%lx\n", virt, *phys);
+
+	return virt;
+}
+
+void fsl_diu_free(void *p, unsigned long size)
+{
+	pr_debug("p=%p size=%lu\n", p, size);
+
+	if (!p)
+		return;
+
+	if ((p >= diu_ops.diu_mem) &&
+	    (p < (diu_ops.diu_mem + diu_ops.diu_size))) {
+		pr_debug("rh\n");
+		rh_free(&diu_ops.diu_rh_info, (unsigned long) p);
+	} else {
+		pr_debug("dma\n");
+		free_pages((unsigned long)p, get_order(size));
+	}
+}
+
+static int fsl_diu_enable_panel(struct fb_info *info)
+{
+	struct mfb_info *pmfbi, *cmfbi, *mfbi = info->par;
+	struct diu *hw = dr.diu_reg;
+	struct diu_ad *ad = mfbi->ad;
+	struct fsl_diu_data *machine_data = mfbi->parent;
+	int res = 0;
+
+	pr_debug("enable_panel index %d\n", mfbi->index);
+	if (mfbi->type != MFB_TYPE_OFF) {
+		switch (mfbi->index) {
+		case 0:				/* plane 0 */
+			if (hw->desc[0] != ad->paddr)
+				out_be32(&hw->desc[0], ad->paddr);
+			break;
+		case 1:				/* plane 1 AOI 0 */
+			cmfbi = machine_data->fsl_diu_info[2]->par;
+			if (hw->desc[1] != ad->paddr) {	/* AOI0 closed */
+				if (cmfbi->count > 0)	/* AOI1 open */
+					ad->next_ad =
+						cpu_to_le32(cmfbi->ad->paddr);
+				else
+					ad->next_ad = 0;
+				out_be32(&hw->desc[1], ad->paddr);
+			}
+			break;
+		case 3:				/* plane 2 AOI 0 */
+			cmfbi = machine_data->fsl_diu_info[4]->par;
+			if (hw->desc[2] != ad->paddr) {	/* AOI0 closed */
+				if (cmfbi->count > 0)	/* AOI1 open */
+					ad->next_ad =
+						cpu_to_le32(cmfbi->ad->paddr);
+				else
+					ad->next_ad = 0;
+				out_be32(&hw->desc[2], ad->paddr);
+			}
+			break;
+		case 2:				/* plane 1 AOI 1 */
+			pmfbi = machine_data->fsl_diu_info[1]->par;
+			ad->next_ad = 0;
+			if (hw->desc[1] == machine_data->dummy_ad->paddr)
+				out_be32(&hw->desc[1], ad->paddr);
+			else					/* AOI0 open */
+				pmfbi->ad->next_ad = cpu_to_le32(ad->paddr);
+			break;
+		case 4:				/* plane 2 AOI 1 */
+			pmfbi = machine_data->fsl_diu_info[3]->par;
+			ad->next_ad = 0;
+			if (hw->desc[2] == machine_data->dummy_ad->paddr)
+				out_be32(&hw->desc[2], ad->paddr);
+			else				/* AOI0 was open */
+				pmfbi->ad->next_ad = cpu_to_le32(ad->paddr);
+			break;
+		default:
+			res = -EINVAL;
+			break;
+		}
+	} else
+		res = -EINVAL;
+	return res;
+}
+
+static int fsl_diu_disable_panel(struct fb_info *info)
+{
+	struct mfb_info *pmfbi, *cmfbi, *mfbi = info->par;
+	struct diu *hw = dr.diu_reg;
+	struct diu_ad *ad = mfbi->ad;
+	struct fsl_diu_data *machine_data = mfbi->parent;
+	int res = 0;
+
+	switch (mfbi->index) {
+	case 0:					/* plane 0 */
+		if (hw->desc[0] != machine_data->dummy_ad->paddr)
+			out_be32(&hw->desc[0],
+				machine_data->dummy_ad->paddr);
+		break;
+	case 1:					/* plane 1 AOI 0 */
+		cmfbi = machine_data->fsl_diu_info[2]->par;
+		if (cmfbi->count > 0)	/* AOI1 is open */
+			out_be32(&hw->desc[1], cmfbi->ad->paddr);
+					/* move AOI1 to the first */
+		else			/* AOI1 was closed */
+			out_be32(&hw->desc[1],
+				machine_data->dummy_ad->paddr);
+					/* close AOI 0 */
+		break;
+	case 3:					/* plane 2 AOI 0 */
+		cmfbi = machine_data->fsl_diu_info[4]->par;
+		if (cmfbi->count > 0)	/* AOI1 is open */
+			out_be32(&hw->desc[2], cmfbi->ad->paddr);
+					/* move AOI1 to the first */
+		else			/* AOI1 was closed */
+			out_be32(&hw->desc[2],
+				machine_data->dummy_ad->paddr);
+					/* close AOI 0 */
+		break;
+	case 2:					/* plane 1 AOI 1 */
+		pmfbi = machine_data->fsl_diu_info[1]->par;
+		if (hw->desc[1] != ad->paddr) {
+				/* AOI1 is not the first in the chain */
+			if (pmfbi->count > 0)
+					/* AOI0 is open, must be the first */
+				pmfbi->ad->next_ad = 0;
+		} else			/* AOI1 is the first in the chain */
+			out_be32(&hw->desc[1], machine_data->dummy_ad->paddr);
+					/* close AOI 1 */
+		break;
+	case 4:					/* plane 2 AOI 1 */
+		pmfbi = machine_data->fsl_diu_info[3]->par;
+		if (hw->desc[2] != ad->paddr) {
+				/* AOI1 is not the first in the chain */
+			if (pmfbi->count > 0)
+				/* AOI0 is open, must be the first */
+				pmfbi->ad->next_ad = 0;
+		} else		/* AOI1 is the first in the chain */
+			out_be32(&hw->desc[2], machine_data->dummy_ad->paddr);
+				/* close AOI 1 */
+		break;
+	default:
+		res = -EINVAL;
+		break;
+	}
+
+	return res;
+}
+
+static void enable_lcdc(struct fb_info *info)
+{
+	struct diu *hw = dr.diu_reg;
+	struct mfb_info *mfbi = info->par;
+	struct fsl_diu_data *machine_data = mfbi->parent;
+
+	if (!machine_data->fb_enabled) {
+		out_be32(&hw->diu_mode, dr.mode);
+		machine_data->fb_enabled++;
+	}
+}
+
+static void disable_lcdc(struct fb_info *info)
+{
+	struct diu *hw = dr.diu_reg;
+	struct mfb_info *mfbi = info->par;
+	struct fsl_diu_data *machine_data = mfbi->parent;
+
+	if (machine_data->fb_enabled) {
+		out_be32(&hw->diu_mode, 0);
+		machine_data->fb_enabled = 0;
+	}
+}
+
+static void adjust_aoi_size_position(struct fb_var_screeninfo *var,
+				struct fb_info *info)
+{
+	struct mfb_info *lower_aoi_mfbi, *upper_aoi_mfbi, *mfbi = info->par;
+	struct fsl_diu_data *machine_data = mfbi->parent;
+	int available_height, upper_aoi_bottom, index = mfbi->index;
+	int lower_aoi_is_open, upper_aoi_is_open;
+	__u32 base_plane_width, base_plane_height, upper_aoi_height;
+
+	base_plane_width = machine_data->fsl_diu_info[0]->var.xres;
+	base_plane_height = machine_data->fsl_diu_info[0]->var.yres;
+
+	switch (index) {
+	case 0:
+		if (mfbi->x_aoi_d != 0)
+			mfbi->x_aoi_d = 0;
+		if (mfbi->y_aoi_d != 0)
+			mfbi->y_aoi_d = 0;
+		break;
+	case 1:			/* AOI 0 */
+	case 3:
+		lower_aoi_mfbi = machine_data->fsl_diu_info[index+1]->par;
+		lower_aoi_is_open = lower_aoi_mfbi->count > 0 ? 1 : 0;
+		if (var->xres > base_plane_width)
+			var->xres = base_plane_width;
+		if ((mfbi->x_aoi_d + var->xres) > base_plane_width)
+			mfbi->x_aoi_d = base_plane_width - var->xres;
+
+		if (lower_aoi_is_open)
+			available_height = lower_aoi_mfbi->y_aoi_d;
+		else
+			available_height = base_plane_height;
+		if (var->yres > available_height)
+			var->yres = available_height;
+		if ((mfbi->y_aoi_d + var->yres) > available_height)
+			mfbi->y_aoi_d = available_height - var->yres;
+		break;
+	case 2:			/* AOI 1 */
+	case 4:
+		upper_aoi_mfbi = machine_data->fsl_diu_info[index-1]->par;
+		upper_aoi_height =
+				machine_data->fsl_diu_info[index-1]->var.yres;
+		upper_aoi_bottom = upper_aoi_mfbi->y_aoi_d + upper_aoi_height;
+		upper_aoi_is_open = upper_aoi_mfbi->count > 0 ? 1 : 0;
+		if (var->xres > base_plane_width)
+			var->xres = base_plane_width;
+		if ((mfbi->x_aoi_d + var->xres) > base_plane_width)
+			mfbi->x_aoi_d = base_plane_width - var->xres;
+		if (mfbi->y_aoi_d < 0)
+			mfbi->y_aoi_d = 0;
+		if (upper_aoi_is_open) {
+			if (mfbi->y_aoi_d < upper_aoi_bottom)
+				mfbi->y_aoi_d = upper_aoi_bottom;
+			available_height = base_plane_height
+						- upper_aoi_bottom;
+		} else
+			available_height = base_plane_height;
+		if (var->yres > available_height)
+			var->yres = available_height;
+		if ((mfbi->y_aoi_d + var->yres) > base_plane_height)
+			mfbi->y_aoi_d = base_plane_height - var->yres;
+		break;
+	}
+}
+/*
+ * Checks to see if the hardware supports the state requested by var passed
+ * in. This function does not alter the hardware state! If the var passed in
+ * is slightly off by what the hardware can support then we alter the var
+ * PASSED in to what we can do. If the hardware doesn't support mode change
+ * a -EINVAL will be returned by the upper layers.
+ */
+static int fsl_diu_check_var(struct fb_var_screeninfo *var,
+				struct fb_info *info)
+{
+	unsigned long htotal, vtotal;
+
+	pr_debug("check_var xres: %d\n", var->xres);
+	pr_debug("check_var yres: %d\n", var->yres);
+
+	if (var->xres_virtual < var->xres)
+		var->xres_virtual = var->xres;
+	if (var->yres_virtual < var->yres)
+		var->yres_virtual = var->yres;
+
+	if (var->xoffset < 0)
+		var->xoffset = 0;
+
+	if (var->yoffset < 0)
+		var->yoffset = 0;
+
+	if (var->xoffset + info->var.xres > info->var.xres_virtual)
+		var->xoffset = info->var.xres_virtual - info->var.xres;
+
+	if (var->yoffset + info->var.yres > info->var.yres_virtual)
+		var->yoffset = info->var.yres_virtual - info->var.yres;
+
+	if ((var->bits_per_pixel != 32) && (var->bits_per_pixel != 24) &&
+	    (var->bits_per_pixel != 16))
+		var->bits_per_pixel = default_bpp;
+
+	switch (var->bits_per_pixel) {
+	case 16:
+		var->red.length = 5;
+		var->red.offset = 11;
+		var->red.msb_right = 0;
+
+		var->green.length = 6;
+		var->green.offset = 5;
+		var->green.msb_right = 0;
+
+		var->blue.length = 5;
+		var->blue.offset = 0;
+		var->blue.msb_right = 0;
+
+		var->transp.length = 0;
+		var->transp.offset = 0;
+		var->transp.msb_right = 0;
+		break;
+	case 24:
+		var->red.length = 8;
+		var->red.offset = 0;
+		var->red.msb_right = 0;
+
+		var->green.length = 8;
+		var->green.offset = 8;
+		var->green.msb_right = 0;
+
+		var->blue.length = 8;
+		var->blue.offset = 16;
+		var->blue.msb_right = 0;
+
+		var->transp.length = 0;
+		var->transp.offset = 0;
+		var->transp.msb_right = 0;
+		break;
+	case 32:
+		var->red.length = 8;
+		var->red.offset = 16;
+		var->red.msb_right = 0;
+
+		var->green.length = 8;
+		var->green.offset = 8;
+		var->green.msb_right = 0;
+
+		var->blue.length = 8;
+		var->blue.offset = 0;
+		var->blue.msb_right = 0;
+
+		var->transp.length = 8;
+		var->transp.offset = 24;
+		var->transp.msb_right = 0;
+
+		break;
+	}
+	/* If the pixclock is below the minimum spec'd value then set to
+	 * refresh rate for 60Hz since this is supported by most monitors.
+	 * Refer to Documentation/fb/ for calculations.
+	 */
+	if ((var->pixclock < MIN_PIX_CLK) || (var->pixclock > MAX_PIX_CLK)) {
+		htotal = var->xres + var->right_margin + var->hsync_len +
+		    var->left_margin;
+		vtotal = var->yres + var->lower_margin + var->vsync_len +
+		    var->upper_margin;
+		var->pixclock = (vtotal * htotal * 6UL) / 100UL;
+		var->pixclock = KHZ2PICOS(var->pixclock);
+		pr_debug("pixclock set for 60Hz refresh = %u ps\n",
+			var->pixclock);
+	}
+
+	var->height = -1;
+	var->width = -1;
+	var->grayscale = 0;
+
+	/* Copy nonstd field to/from sync for fbset usage */
+	var->sync |= var->nonstd;
+	var->nonstd |= var->sync;
+
+	adjust_aoi_size_position(var, info);
+	return 0;
+}
+
+static void set_fix(struct fb_info *info)
+{
+	struct fb_fix_screeninfo *fix = &info->fix;
+	struct fb_var_screeninfo *var = &info->var;
+	struct mfb_info *mfbi = info->par;
+
+	strncpy(fix->id, mfbi->id, strlen(mfbi->id));
+	fix->line_length = var->xres_virtual * var->bits_per_pixel / 8;
+	fix->type = FB_TYPE_PACKED_PIXELS;
+	fix->accel = FB_ACCEL_NONE;
+	fix->visual = FB_VISUAL_TRUECOLOR;
+	fix->xpanstep = 1;
+	fix->ypanstep = 1;
+}
+
+static void update_lcdc(struct fb_info *info)
+{
+	struct fb_var_screeninfo *var = &info->var;
+	struct mfb_info *mfbi = info->par;
+	struct fsl_diu_data *machine_data = mfbi->parent;
+	struct diu *hw;
+	int i, j;
+	char __iomem *cursor_base, *gamma_table_base;
+
+	u32 temp;
+
+	hw = dr.diu_reg;
+
+	if (mfbi->type == MFB_TYPE_OFF) {
+		fsl_diu_disable_panel(info);
+		return;
+	}
+
+	diu_ops.set_monitor_port(machine_data->monitor_port);
+	gamma_table_base = pool.gamma.vaddr;
+	cursor_base = pool.cursor.vaddr;
+	/* Prep for DIU init  - gamma table, cursor table */
+
+	for (i = 0; i <= 2; i++)
+	   for (j = 0; j <= 255; j++)
+	      *gamma_table_base++ = j;
+
+	diu_ops.set_gamma_table(machine_data->monitor_port, pool.gamma.vaddr);
+
+	pr_debug("update-lcdc: HW - %p\n Disabling DIU\n", hw);
+	disable_lcdc(info);
+
+	/* Program DIU registers */
+
+	out_be32(&hw->gamma, pool.gamma.paddr);
+	out_be32(&hw->cursor, pool.cursor.paddr);
+
+	out_be32(&hw->bgnd, 0x007F7F7F); 	/* BGND */
+	out_be32(&hw->bgnd_wb, 0); 		/* BGND_WB */
+	out_be32(&hw->disp_size, (var->yres << 16 | var->xres));
+						/* DISP SIZE */
+	pr_debug("DIU xres: %d\n", var->xres);
+	pr_debug("DIU yres: %d\n", var->yres);
+
+	out_be32(&hw->wb_size, 0); /* WB SIZE */
+	out_be32(&hw->wb_mem_addr, 0); /* WB MEM ADDR */
+
+	/* Horizontal and vertical configuration register */
+	temp = var->left_margin << 22 | /* BP_H */
+	       var->hsync_len << 11 |   /* PW_H */
+	       var->right_margin;       /* FP_H */
+
+	out_be32(&hw->hsyn_para, temp);
+
+	temp = var->upper_margin << 22 | /* BP_V */
+	       var->vsync_len << 11 |    /* PW_V  */
+	       var->lower_margin;        /* FP_V  */
+
+	out_be32(&hw->vsyn_para, temp);
+
+	pr_debug("DIU right_margin - %d\n", var->right_margin);
+	pr_debug("DIU left_margin - %d\n", var->left_margin);
+	pr_debug("DIU hsync_len - %d\n", var->hsync_len);
+	pr_debug("DIU upper_margin - %d\n", var->upper_margin);
+	pr_debug("DIU lower_margin - %d\n", var->lower_margin);
+	pr_debug("DIU vsync_len - %d\n", var->vsync_len);
+	pr_debug("DIU HSYNC - 0x%08x\n", hw->hsyn_para);
+	pr_debug("DIU VSYNC - 0x%08x\n", hw->vsyn_para);
+
+	diu_ops.set_pixel_clock(var->pixclock);
+
+	out_be32(&hw->syn_pol, 0);	/* SYNC SIGNALS POLARITY */
+	out_be32(&hw->thresholds, 0x00037800); /* The Thresholds */
+	out_be32(&hw->int_status, 0);	/* INTERRUPT STATUS */
+	out_be32(&hw->plut, 0x01F5F666);
+
+	/* Enable the DIU */
+	enable_lcdc(info);
+}
+
+static int map_video_memory(struct fb_info *info)
+{
+	phys_addr_t phys;
+
+	pr_debug("info->var.xres_virtual = %d\n", info->var.xres_virtual);
+	pr_debug("info->var.yres_virtual = %d\n", info->var.yres_virtual);
+	pr_debug("info->fix.line_length  = %d\n", info->fix.line_length);
+
+	info->fix.smem_len = info->fix.line_length * info->var.yres_virtual;
+	pr_debug("MAP_VIDEO_MEMORY: smem_len = %d\n", info->fix.smem_len);
+	info->screen_base = fsl_diu_alloc(info->fix.smem_len, &phys);
+	if (info->screen_base == 0) {
+		printk(KERN_ERR "Unable to allocate fb memory\n");
+		return -ENOMEM;
+	}
+	info->fix.smem_start = (unsigned long) phys;
+	info->screen_size = info->fix.smem_len;
+
+	pr_debug("Allocated fb @ paddr=0x%08lx, size=%d.\n",
+				info->fix.smem_start,
+		info->fix.smem_len);
+	pr_debug("screen base %p\n", info->screen_base);
+
+	return 0;
+}
+
+static void unmap_video_memory(struct fb_info *info)
+{
+	fsl_diu_free(info->screen_base, info->fix.smem_len);
+	info->screen_base = 0;
+	info->fix.smem_start = 0;
+	info->fix.smem_len = 0;
+}
+
+/*
+ * Using the fb_var_screeninfo in fb_info we set the resolution of this
+ * particular framebuffer. This function alters the fb_fix_screeninfo stored
+ * in fb_info. It does not alter var in fb_info since we are using that
+ * data. This means we depend on the data in var inside fb_info to be
+ * supported by the hardware. fsl_diu_check_var is always called before
+ * fsl_diu_set_par to ensure this.
+ */
+static int fsl_diu_set_par(struct fb_info *info)
+{
+	unsigned long len;
+	struct fb_var_screeninfo *var = &info->var;
+	struct mfb_info *mfbi = info->par;
+	struct fsl_diu_data *machine_data = mfbi->parent;
+	struct diu_ad *ad = mfbi->ad;
+	struct diu *hw;
+
+	hw = dr.diu_reg;
+
+	set_fix(info);
+	mfbi->cursor_reset = 1;
+
+	len = info->var.yres_virtual * info->fix.line_length;
+	/* Alloc & dealloc each time resolution/bpp change */
+	if (len != info->fix.smem_len) {
+		if (info->fix.smem_start)
+			unmap_video_memory(info);
+		pr_debug("SET PAR: smem_len = %d\n", info->fix.smem_len);
+
+		/* Memory allocation for framebuffer */
+		if (map_video_memory(info)) {
+			printk(KERN_ERR "Unable to allocate fb memory 1\n");
+			return -ENOMEM;
+		}
+	}
+
+	ad->pix_fmt =
+		diu_ops.get_pixel_format(var->bits_per_pixel,
+					 machine_data->monitor_port);
+	ad->addr    = cpu_to_le32(info->fix.smem_start);
+	ad->src_size_g_alpha = cpu_to_le32((var->yres << 12) |
+				var->xres) | mfbi->g_alpha;
+	/* fix me. AOI should not be greater than display size */
+	ad->aoi_size 	= cpu_to_le32((var->yres << 16) | var->xres);
+	ad->offset_xyi = 0;
+	ad->offset_xyd = cpu_to_le32((mfbi->y_aoi_d << 16) | mfbi->x_aoi_d);
+
+	/* Disable chroma keying function */
+	ad->ckmax_r = 0;
+	ad->ckmax_g = 0;
+	ad->ckmax_b = 0;
+
+	ad->ckmin_r = 255;
+	ad->ckmin_g = 255;
+	ad->ckmin_b = 255;
+
+	if (mfbi->index == 0)
+		update_lcdc(info);
+	return 0;
+}
+
+static inline __u32 CNVT_TOHW(__u32 val, __u32 width)
+{
+	return ((val<<width) + 0x7FFF - val)>>16;
+}
+
+/*
+ * Set a single color register. The values supplied have a 16 bit magnitude
+ * which needs to be scaled in this function for the hardware. Things to take
+ * into consideration are how many color registers, if any, are supported with
+ * the current color visual. With truecolor mode no color palettes are
+ * supported. Here a psuedo palette is created which we store the value in
+ * pseudo_palette in struct fb_info. For pseudocolor mode we have a limited
+ * color palette.
+ */
+static int fsl_diu_setcolreg(unsigned regno, unsigned red, unsigned green,
+			   unsigned blue, unsigned transp, struct fb_info *info)
+{
+	int ret = 1;
+
+	/*
+	 * If greyscale is true, then we convert the RGB value
+	 * to greyscale no matter what visual we are using.
+	 */
+	if (info->var.grayscale)
+		red = green = blue = (19595 * red + 38470 * green +
+				      7471 * blue) >> 16;
+	switch (info->fix.visual) {
+	case FB_VISUAL_TRUECOLOR:
+		/*
+		 * 16-bit True Colour.  We encode the RGB value
+		 * according to the RGB bitfield information.
+		 */
+		if (regno < 16) {
+			u32 *pal = info->pseudo_palette;
+			u32 v;
+
+			red = CNVT_TOHW(red, info->var.red.length);
+			green = CNVT_TOHW(green, info->var.green.length);
+			blue = CNVT_TOHW(blue, info->var.blue.length);
+			transp = CNVT_TOHW(transp, info->var.transp.length);
+
+			v = (red << info->var.red.offset) |
+			    (green << info->var.green.offset) |
+			    (blue << info->var.blue.offset) |
+			    (transp << info->var.transp.offset);
+
+			pal[regno] = v;
+			ret = 0;
+		}
+		break;
+	case FB_VISUAL_STATIC_PSEUDOCOLOR:
+	case FB_VISUAL_PSEUDOCOLOR:
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * Pan (or wrap, depending on the `vmode' field) the display using the
+ * 'xoffset' and 'yoffset' fields of the 'var' structure. If the values
+ * don't fit, return -EINVAL.
+ */
+static int fsl_diu_pan_display(struct fb_var_screeninfo *var,
+			     struct fb_info *info)
+{
+	if ((info->var.xoffset == var->xoffset) &&
+	    (info->var.yoffset == var->yoffset))
+		return 0;	/* No change, do nothing */
+
+	if (var->xoffset < 0 || var->yoffset < 0
+	    || var->xoffset + info->var.xres > info->var.xres_virtual
+	    || var->yoffset + info->var.yres > info->var.yres_virtual)
+		return -EINVAL;
+
+	info->var.xoffset = var->xoffset;
+	info->var.yoffset = var->yoffset;
+
+	if (var->vmode & FB_VMODE_YWRAP)
+		info->var.vmode |= FB_VMODE_YWRAP;
+	else
+		info->var.vmode &= ~FB_VMODE_YWRAP;
+
+	return 0;
+}
+
+/*
+ * Blank the screen if blank_mode != 0, else unblank. Return 0 if blanking
+ * succeeded, != 0 if un-/blanking failed.
+ * blank_mode == 2: suspend vsync
+ * blank_mode == 3: suspend hsync
+ * blank_mode == 4: powerdown
+ */
+static int fsl_diu_blank(int blank_mode, struct fb_info *info)
+{
+	struct mfb_info *mfbi = info->par;
+
+	mfbi->blank = blank_mode;
+
+	switch (blank_mode) {
+	case FB_BLANK_VSYNC_SUSPEND:
+	case FB_BLANK_HSYNC_SUSPEND:
+	/* FIXME: fixes to enable_panel and enable lcdc needed */
+	case FB_BLANK_NORMAL:
+	/*	fsl_diu_disable_panel(info);*/
+		break;
+	case FB_BLANK_POWERDOWN:
+	/*	disable_lcdc(info);	*/
+		break;
+	case FB_BLANK_UNBLANK:
+	/*	fsl_diu_enable_panel(info);*/
+		break;
+	}
+
+	return 0;
+}
+
+static int fsl_diu_ioctl(struct fb_info *info, unsigned int cmd,
+		       unsigned long arg)
+{
+	struct mfb_info *mfbi = info->par;
+	struct diu_ad *ad = mfbi->ad;
+	struct mfb_chroma_key ck;
+	unsigned char global_alpha;
+	struct aoi_display_offset aoi_d;
+	__u32 pix_fmt;
+	void __user *buf = (void __user *)arg;
+
+	if (!arg)
+		return -EINVAL;
+	switch (cmd) {
+	case MFB_SET_PIXFMT:
+		if (copy_from_user(&pix_fmt, buf, sizeof(pix_fmt)))
+			return -EFAULT;
+		ad->pix_fmt = pix_fmt;
+		pr_debug("Set pixel format to 0x%08x\n", ad->pix_fmt);
+		break;
+	case MFB_GET_PIXFMT:
+		pix_fmt = ad->pix_fmt;
+		if (copy_to_user(buf, &pix_fmt, sizeof(pix_fmt)))
+			return -EFAULT;
+		pr_debug("get pixel format 0x%08x\n", ad->pix_fmt);
+		break;
+	case MFB_SET_AOID:
+		if (copy_from_user(&aoi_d, buf, sizeof(aoi_d)))
+			return -EFAULT;
+		mfbi->x_aoi_d = aoi_d.x_aoi_d;
+		mfbi->y_aoi_d = aoi_d.y_aoi_d;
+		pr_debug("set AOI display offset of index %d to (%d,%d)\n",
+				 mfbi->index, aoi_d.x_aoi_d, aoi_d.y_aoi_d);
+		fsl_diu_check_var(&info->var, info);
+		fsl_diu_set_par(info);
+		break;
+	case MFB_GET_AOID:
+		aoi_d.x_aoi_d = mfbi->x_aoi_d;
+		aoi_d.y_aoi_d = mfbi->y_aoi_d;
+		if (copy_to_user(buf, &aoi_d, sizeof(aoi_d)))
+			return -EFAULT;
+		pr_debug("get AOI display offset of index %d (%d,%d)\n",
+				mfbi->index, aoi_d.x_aoi_d, aoi_d.y_aoi_d);
+		break;
+	case MFB_GET_ALPHA:
+		global_alpha = mfbi->g_alpha;
+		if (copy_to_user(buf, &global_alpha, sizeof(global_alpha)))
+			return -EFAULT;
+		pr_debug("get global alpha of index %d\n", mfbi->index);
+		break;
+	case MFB_SET_ALPHA:
+		/* set panel information */
+		if (copy_from_user(&global_alpha, buf, sizeof(global_alpha)))
+			return -EFAULT;
+		ad->src_size_g_alpha = (ad->src_size_g_alpha & (~0xff)) |
+							(global_alpha & 0xff);
+		mfbi->g_alpha = global_alpha;
+		pr_debug("set global alpha for index %d\n", mfbi->index);
+		break;
+	case MFB_SET_CHROMA_KEY:
+		/* set panel winformation */
+		if (copy_from_user(&ck, buf, sizeof(ck)))
+			return -EFAULT;
+
+		if (ck.enable &&
+		   (ck.red_max < ck.red_min ||
+		    ck.green_max < ck.green_min ||
+		    ck.blue_max < ck.blue_min))
+			return -EINVAL;
+
+		if (!ck.enable) {
+			ad->ckmax_r = 0;
+			ad->ckmax_g = 0;
+			ad->ckmax_b = 0;
+			ad->ckmin_r = 255;
+			ad->ckmin_g = 255;
+			ad->ckmin_b = 255;
+		} else {
+			ad->ckmax_r = ck.red_max;
+			ad->ckmax_g = ck.green_max;
+			ad->ckmax_b = ck.blue_max;
+			ad->ckmin_r = ck.red_min;
+			ad->ckmin_g = ck.green_min;
+			ad->ckmin_b = ck.blue_min;
+		}
+		pr_debug("set chroma key\n");
+		break;
+	case FBIOGET_GWINFO:
+		if (mfbi->type == MFB_TYPE_OFF)
+			return -ENODEV;
+		/* get graphic window information */
+		if (copy_to_user(buf, ad, sizeof(*ad)))
+			return -EFAULT;
+		break;
+	case FBIOGET_HWCINFO:
+		pr_debug("FBIOGET_HWCINFO:0x%08x\n", FBIOGET_HWCINFO);
+		break;
+	case FBIOPUT_MODEINFO:
+		pr_debug("FBIOPUT_MODEINFO:0x%08x\n", FBIOPUT_MODEINFO);
+		break;
+	case FBIOGET_DISPINFO:
+		pr_debug("FBIOGET_DISPINFO:0x%08x\n", FBIOGET_DISPINFO);
+		break;
+
+	default:
+		printk(KERN_ERR "Unknown ioctl command (0x%08X)\n", cmd);
+		return -ENOIOCTLCMD;
+	}
+
+	return 0;
+}
+
+/* turn on fb if count == 1
+ */
+static int fsl_diu_open(struct fb_info *info, int user)
+{
+	struct mfb_info *mfbi = info->par;
+	int res = 0;
+
+	spin_lock(&diu_lock);
+	mfbi->count++;
+	if (mfbi->count == 1) {
+		pr_debug("open plane index %d\n", mfbi->index);
+		fsl_diu_check_var(&info->var, info);
+		res = fsl_diu_set_par(info);
+		if (res < 0)
+			mfbi->count--;
+		else {
+			res = fsl_diu_enable_panel(info);
+			if (res < 0)
+				mfbi->count--;
+		}
+	}
+
+	spin_unlock(&diu_lock);
+	return res;
+}
+
+/* turn off fb if count == 0
+ */
+static int fsl_diu_release(struct fb_info *info, int user)
+{
+	struct mfb_info *mfbi = info->par;
+	int res = 0;
+
+	spin_lock(&diu_lock);
+	mfbi->count--;
+	if (mfbi->count == 0) {
+		pr_debug("release plane index %d\n", mfbi->index);
+		res = fsl_diu_disable_panel(info);
+		if (res < 0)
+			mfbi->count++;
+	}
+	spin_unlock(&diu_lock);
+	return res;
+}
+
+static struct fb_ops fsl_diu_ops = {
+	.owner = THIS_MODULE,
+	.fb_check_var = fsl_diu_check_var,
+	.fb_set_par = fsl_diu_set_par,
+	.fb_setcolreg = fsl_diu_setcolreg,
+	.fb_blank = fsl_diu_blank,
+	.fb_pan_display = fsl_diu_pan_display,
+	.fb_fillrect = cfb_fillrect,
+	.fb_copyarea = cfb_copyarea,
+	.fb_imageblit = cfb_imageblit,
+	.fb_ioctl = fsl_diu_ioctl,
+	.fb_open = fsl_diu_open,
+	.fb_release = fsl_diu_release,
+};
+
+static int init_fbinfo(struct fb_info *info)
+{
+	struct mfb_info *mfbi = info->par;
+
+	info->device = NULL;
+	info->var.activate = FB_ACTIVATE_NOW;
+	info->fbops = &fsl_diu_ops;
+	info->flags = FBINFO_FLAG_DEFAULT;
+	info->pseudo_palette = &mfbi->pseudo_palette;
+
+	/* Allocate colormap */
+	fb_alloc_cmap(&info->cmap, 16, 0);
+	return 0;
+}
+
+static int install_fb(struct fb_info *info)
+{
+	int rc;
+	struct mfb_info *mfbi = info->par;
+	const char *aoi_mode, *init_aoi_mode = "320x240";
+
+	if (init_fbinfo(info))
+		return -EINVAL;
+
+	if (mfbi->index == 0)	/* plane 0 */
+		aoi_mode = fb_mode;
+	else
+		aoi_mode = init_aoi_mode;
+	pr_debug("mode used = %s\n", aoi_mode);
+	rc = fb_find_mode(&info->var, info, aoi_mode, fsl_diu_mode_db,
+	     ARRAY_SIZE(fsl_diu_mode_db), &fsl_diu_default_mode, default_bpp);
+
+	switch (rc) {
+	case 1:
+		pr_debug("using mode specified in @mode\n");
+		break;
+	case 2:
+		pr_debug("using mode specified in @mode "
+			"with ignored refresh rate\n");
+		break;
+	case 3:
+		pr_debug("using mode default mode\n");
+		break;
+	case 4:
+		pr_debug("using mode from list\n");
+		break;
+	default:
+		pr_debug("rc = %d\n", rc);
+		pr_debug("failed to find mode\n");
+		return -EINVAL;
+		break;
+	}
+
+	pr_debug("xres_virtual %d\n", info->var.xres_virtual);
+	pr_debug("bits_per_pixel %d\n", info->var.bits_per_pixel);
+
+	pr_debug("info->var.yres_virtual = %d\n", info->var.yres_virtual);
+	pr_debug("info->fix.line_length = %d\n", info->fix.line_length);
+
+	if (mfbi->type == MFB_TYPE_OFF)
+		mfbi->blank = FB_BLANK_NORMAL;
+	else
+		mfbi->blank = FB_BLANK_UNBLANK;
+
+	if (fsl_diu_check_var(&info->var, info)) {
+		printk(KERN_ERR "fb_check_var failed");
+		fb_dealloc_cmap(&info->cmap);
+		return -EINVAL;
+	}
+
+	if (fsl_diu_set_par(info)) {
+		printk(KERN_ERR "fb_set_par failed");
+		fb_dealloc_cmap(&info->cmap);
+		return -EINVAL;
+	}
+
+	if (register_framebuffer(info) < 0) {
+		printk(KERN_ERR "register_framebuffer failed");
+		unmap_video_memory(info);
+		fb_dealloc_cmap(&info->cmap);
+		return -EINVAL;
+	}
+
+	mfbi->registered = 1;
+	printk(KERN_INFO "fb%d: %s fb device registered successfully.\n",
+		 info->node, info->fix.id);
+
+	return 0;
+}
+
+static void __exit uninstall_fb(struct fb_info *info)
+{
+	struct mfb_info *mfbi = info->par;
+
+	if (!mfbi->registered)
+		return;
+
+	unregister_framebuffer(info);
+	unmap_video_memory(info);
+	if (&info->cmap)
+		fb_dealloc_cmap(&info->cmap);
+
+	mfbi->registered = 0;
+}
+
+static irqreturn_t fsl_diu_isr(int irq, void *dev_id)
+{
+	struct diu *hw = dr.diu_reg;
+	unsigned int status = in_be32(&hw->int_status);
+
+	if (status) {
+		/* This is the workaround for underrun */
+		if (status & INT_UNDRUN) {
+			out_be32(&hw->diu_mode, 0);
+			pr_debug("Err: DIU occurs underrun!\n");
+			udelay(1);
+			out_be32(&hw->diu_mode, 1);
+		}
+#if defined(CONFIG_NOT_COHERENT_CACHE)
+		else if (status & INT_VSYNC) {
+			unsigned int i;
+			for (i = 0; i < coherence_data_size;
+				i += d_cache_line_size)
+				__asm__ __volatile__ (
+					"dcbz 0, %[input]"
+				::[input]"r"(&coherence_data[i]));
+		}
+#endif
+		return IRQ_HANDLED;
+	}
+	return IRQ_NONE;
+}
+
+static int request_irq_local(int irq)
+{
+	unsigned long status, ints;
+	struct diu *hw;
+	int ret;
+
+	hw = dr.diu_reg;
+
+	/* Read to clear the status */
+	status = in_be32(&hw->int_status);
+
+	ret = request_irq(irq, fsl_diu_isr, 0, "diu", 0);
+	if (ret)
+		pr_info("Request diu IRQ failed.\n");
+	else {
+		ints = INT_PARERR | INT_LS_BF_VS;
+#if !defined(CONFIG_NOT_COHERENT_CACHE)
+		ints |=	INT_VSYNC;
+#endif
+		if (dr.mode == MFB_MODE2 || dr.mode == MFB_MODE3)
+			ints |= INT_VSYNC_WB;
+
+		/* Read to clear the status */
+		status = in_be32(&hw->int_status);
+		out_be32(&hw->int_mask, ints);
+	}
+	return ret;
+}
+
+static void free_irq_local(int irq)
+{
+	struct diu *hw = dr.diu_reg;
+
+	/* Disable all LCDC interrupt */
+	out_be32(&hw->int_mask, 0x1f);
+
+	free_irq(irq, 0);
+}
+
+#ifdef CONFIG_PM
+/*
+ * Power management hooks. Note that we won't be called from IRQ context,
+ * unlike the blank functions above, so we may sleep.
+ */
+static int fsl_diu_suspend(struct of_device *dev, pm_message_t state)
+{
+	struct fsl_diu_data *machine_data;
+
+	machine_data = dev_get_drvdata(&ofdev->dev);
+	disable_lcdc(machine_data->fsl_diu_info[0]);
+
+	return 0;
+}
+
+static int fsl_diu_resume(struct of_device *dev)
+{
+	struct fsl_diu_data *machine_data;
+
+	machine_data = dev_get_drvdata(&ofdev->dev);
+	enable_lcdc(machine_data->fsl_diu_info[0]);
+
+	return 0;
+}
+
+#else
+#define fsl_diu_suspend NULL
+#define fsl_diu_resume NULL
+#endif				/* CONFIG_PM */
+
+/* Align to 64-bit(8-byte), 32-byte, etc. */
+static int allocate_buf(struct diu_addr *buf, u32 size, u32 bytes_align)
+{
+	u32 offset, ssize;
+	u32 mask;
+	dma_addr_t paddr = 0;
+
+	ssize = size + bytes_align;
+	buf->vaddr = dma_alloc_coherent(0, ssize, &paddr, GFP_DMA | __GFP_ZERO);
+	if (!buf->vaddr)
+		return -ENOMEM;
+
+	buf->paddr = (__u32) paddr;
+
+	mask = bytes_align - 1;
+	offset = (u32)buf->paddr & mask;
+	if (offset) {
+		buf->offset = bytes_align - offset;
+		buf->paddr = (u32)buf->paddr + offset;
+	} else
+		buf->offset = 0;
+	return 0;
+}
+
+static void free_buf(struct diu_addr *buf, u32 size, u32 bytes_align)
+{
+	dma_free_coherent(0, size + bytes_align,
+				buf->vaddr, (buf->paddr - buf->offset));
+	return;
+}
+
+static ssize_t store_monitor(struct device *device,
+	struct device_attribute *attr, const char *buf, size_t count)
+{
+	int old_monitor_port;
+	unsigned long val;
+	struct fsl_diu_data *machine_data =
+		container_of(attr, struct fsl_diu_data, dev_attr);
+
+	if (strict_strtoul(buf, 10, &val))
+		return 0;
+
+	old_monitor_port = machine_data->monitor_port;
+	machine_data->monitor_port = diu_ops.set_sysfs_monitor_port(val);
+
+	if (old_monitor_port != machine_data->monitor_port) {
+		/* All AOIs need adjust pixel format
+		 * fsl_diu_set_par only change the pixsel format here
+		 * unlikely to fail. */
+		fsl_diu_set_par(machine_data->fsl_diu_info[0]);
+		fsl_diu_set_par(machine_data->fsl_diu_info[1]);
+		fsl_diu_set_par(machine_data->fsl_diu_info[2]);
+		fsl_diu_set_par(machine_data->fsl_diu_info[3]);
+		fsl_diu_set_par(machine_data->fsl_diu_info[4]);
+	}
+	return count;
+}
+
+static ssize_t show_monitor(struct device *device,
+	struct device_attribute *attr, char *buf)
+{
+	struct fsl_diu_data *machine_data =
+		container_of(attr, struct fsl_diu_data, dev_attr);
+	return diu_ops.show_monitor_port(machine_data->monitor_port, buf);
+}
+
+static int fsl_diu_probe(struct of_device *ofdev,
+	const struct of_device_id *match)
+{
+	struct device_node *np = ofdev->node;
+	struct mfb_info *mfbi;
+	phys_addr_t dummy_ad_addr;
+	int ret, i, error = 0;
+	struct resource res;
+	struct fsl_diu_data *machine_data;
+
+	machine_data = kzalloc(sizeof(struct fsl_diu_data), GFP_KERNEL);
+	if (!machine_data)
+		return -ENOMEM;
+
+	for (i = 0; i < ARRAY_SIZE(machine_data->fsl_diu_info); i++) {
+		machine_data->fsl_diu_info[i] =
+			framebuffer_alloc(sizeof(struct mfb_info), &ofdev->dev);
+		if (!machine_data->fsl_diu_info[i]) {
+			dev_err(&ofdev->dev, "cannot allocate memory\n");
+			ret = -ENOMEM;
+			goto error2;
+		}
+		mfbi = machine_data->fsl_diu_info[i]->par;
+		memcpy(mfbi, &mfb_template[i], sizeof(struct mfb_info));
+		mfbi->parent = machine_data;
+	}
+
+	ret = of_address_to_resource(np, 0, &res);
+	if (ret) {
+		dev_err(&ofdev->dev, "could not obtain DIU address\n");
+		goto error;
+	}
+	if (!res.start) {
+		dev_err(&ofdev->dev, "invalid DIU address\n");
+		goto error;
+	}
+	dev_dbg(&ofdev->dev, "%s, res.start: 0x%08x\n", __func__, res.start);
+
+	dr.diu_reg = ioremap(res.start, sizeof(struct diu));
+	if (!dr.diu_reg) {
+		dev_err(&ofdev->dev, "Err: can't map DIU registers!\n");
+		ret = -EFAULT;
+		goto error2;
+	}
+
+	out_be32(&dr.diu_reg->diu_mode, 0);		/* disable DIU anyway*/
+
+	/* Get the IRQ of the DIU */
+	machine_data->irq = irq_of_parse_and_map(np, 0);
+
+	if (!machine_data->irq) {
+		dev_err(&ofdev->dev, "could not get DIU IRQ\n");
+		ret = -EINVAL;
+		goto error;
+	}
+	machine_data->monitor_port = monitor_port;
+
+	/* Area descriptor memory pool aligns to 64-bit boundary */
+	if (allocate_buf(&pool.ad, sizeof(struct diu_ad) * FSL_AOI_NUM, 8))
+		return -ENOMEM;
+
+	/* Get memory for Gamma Table  - 32-byte aligned memory */
+	if (allocate_buf(&pool.gamma, 768, 32)) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	/* For performance, cursor bitmap buffer aligns to 32-byte boundary */
+	if (allocate_buf(&pool.cursor, MAX_CURS * MAX_CURS * 2, 32)) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	i = ARRAY_SIZE(machine_data->fsl_diu_info);
+	machine_data->dummy_ad = (struct diu_ad *)
+			((u32)pool.ad.vaddr + pool.ad.offset) + i;
+	machine_data->dummy_ad->paddr = pool.ad.paddr +
+			i * sizeof(struct diu_ad);
+	machine_data->dummy_aoi_virt = fsl_diu_alloc(64, &dummy_ad_addr);
+	if (!machine_data->dummy_aoi_virt) {
+		ret = -ENOMEM;
+		goto error;
+	}
+	machine_data->dummy_ad->addr = cpu_to_le32(dummy_ad_addr);
+	machine_data->dummy_ad->pix_fmt = 0x88882317;
+	machine_data->dummy_ad->src_size_g_alpha = cpu_to_le32((4 << 12) | 4);
+	machine_data->dummy_ad->aoi_size = cpu_to_le32((4 << 16) |  2);
+	machine_data->dummy_ad->offset_xyi = 0;
+	machine_data->dummy_ad->offset_xyd = 0;
+	machine_data->dummy_ad->next_ad = 0;
+
+	out_be32(&dr.diu_reg->desc[0], machine_data->dummy_ad->paddr);
+	out_be32(&dr.diu_reg->desc[1], machine_data->dummy_ad->paddr);
+	out_be32(&dr.diu_reg->desc[2], machine_data->dummy_ad->paddr);
+
+	for (i = 0; i < ARRAY_SIZE(machine_data->fsl_diu_info); i++) {
+		machine_data->fsl_diu_info[i]->fix.smem_start = 0;
+		mfbi = machine_data->fsl_diu_info[i]->par;
+		mfbi->ad = (struct diu_ad *)((u32)pool.ad.vaddr
+					+ pool.ad.offset) + i;
+		mfbi->ad->paddr = pool.ad.paddr + i * sizeof(struct diu_ad);
+		ret = install_fb(machine_data->fsl_diu_info[i]);
+		if (ret) {
+			dev_err(&ofdev->dev,
+				"Failed to register framebuffer %d\n",
+				i);
+			goto error;
+		}
+	}
+
+	if (request_irq_local(machine_data->irq)) {
+		dev_err(machine_data->fsl_diu_info[0]->dev,
+			"could not request irq for diu.");
+		goto error;
+	}
+
+	machine_data->dev_attr.attr.name = "monitor";
+	machine_data->dev_attr.attr.mode = S_IRUGO|S_IWUSR;
+	machine_data->dev_attr.show = show_monitor;
+	machine_data->dev_attr.store = store_monitor;
+	error = device_create_file(machine_data->fsl_diu_info[0]->dev,
+				  &machine_data->dev_attr);
+	if (error) {
+		dev_err(machine_data->fsl_diu_info[0]->dev,
+			"could not create sysfs %s file\n",
+			machine_data->dev_attr.attr.name);
+	}
+
+	dev_set_drvdata(&ofdev->dev, machine_data);
+	return 0;
+
+error:
+	for (i = ARRAY_SIZE(machine_data->fsl_diu_info);
+		i > 0; i--)
+		uninstall_fb(machine_data->fsl_diu_info[i - 1]);
+	if (pool.ad.vaddr)
+		free_buf(&pool.ad, sizeof(struct diu_ad) * FSL_AOI_NUM, 8);
+	if (pool.gamma.vaddr)
+		free_buf(&pool.gamma, 768, 32);
+	if (pool.cursor.vaddr)
+		free_buf(&pool.cursor, MAX_CURS * MAX_CURS * 2, 32);
+	if (machine_data->dummy_aoi_virt)
+		fsl_diu_free(machine_data->dummy_aoi_virt, 64);
+	iounmap(dr.diu_reg);
+
+error2:
+	for (i = 0; i < ARRAY_SIZE(machine_data->fsl_diu_info); i++)
+		if (machine_data->fsl_diu_info[i])
+			framebuffer_release(machine_data->fsl_diu_info[i]);
+	kfree(machine_data);
+
+	return ret;
+}
+
+
+static int fsl_diu_remove(struct of_device *ofdev)
+{
+	struct fsl_diu_data *machine_data;
+	int i;
+
+	machine_data = dev_get_drvdata(&ofdev->dev);
+	disable_lcdc(machine_data->fsl_diu_info[0]);
+	free_irq_local(machine_data->irq);
+	for (i = ARRAY_SIZE(machine_data->fsl_diu_info); i > 0; i--)
+		uninstall_fb(machine_data->fsl_diu_info[i - 1]);
+	if (pool.ad.vaddr)
+		free_buf(&pool.ad, sizeof(struct diu_ad) * FSL_AOI_NUM, 8);
+	if (pool.gamma.vaddr)
+		free_buf(&pool.gamma, 768, 32);
+	if (pool.cursor.vaddr)
+		free_buf(&pool.cursor, MAX_CURS * MAX_CURS * 2, 32);
+	if (machine_data->dummy_aoi_virt)
+		fsl_diu_free(machine_data->dummy_aoi_virt, 64);
+	iounmap(dr.diu_reg);
+	for (i = 0; i < ARRAY_SIZE(machine_data->fsl_diu_info); i++)
+		if (machine_data->fsl_diu_info[i])
+			framebuffer_release(machine_data->fsl_diu_info[i]);
+	kfree(machine_data);
+
+	return 0;
+}
+
+#ifndef MODULE
+static int __init fsl_diu_setup(char *options)
+{
+	char *opt;
+	unsigned long val;
+
+	if (!options || !*options)
+		return 0;
+
+	while ((opt = strsep(&options, ",")) != NULL) {
+		if (!*opt)
+			continue;
+		if (!strncmp(opt, "monitor=", 8)) {
+			if (!strict_strtoul(opt + 8, 10, &val) && (val <= 2))
+				monitor_port = val;
+		} else if (!strncmp(opt, "bpp=", 4)) {
+			if (!strict_strtoul(opt + 4, 10, &val))
+				default_bpp = val;
+		} else
+			fb_mode = opt;
+	}
+
+	return 0;
+}
+#endif
+
+static struct of_device_id fsl_diu_match[] = {
+	{
+		.compatible = "fsl,diu",
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(of, fsl_diu_match);
+
+static struct of_platform_driver fsl_diu_driver = {
+	.owner  	= THIS_MODULE,
+	.name   	= "fsl_diu",
+	.match_table    = fsl_diu_match,
+	.probe  	= fsl_diu_probe,
+	.remove 	= fsl_diu_remove,
+	.suspend	= fsl_diu_suspend,
+	.resume		= fsl_diu_resume,
+};
+
+static int __init fsl_diu_init(void)
+{
+#ifdef CONFIG_NOT_COHERENT_CACHE
+	struct device_node *np;
+	const u32 *prop;
+#endif
+	int ret;
+#ifndef MODULE
+	char *option;
+
+	/*
+	 * For kernel boot options (in 'video=xxxfb:<options>' format)
+	 */
+	if (fb_get_options("fslfb", &option))
+		return -ENODEV;
+	fsl_diu_setup(option);
+#endif
+	printk(KERN_INFO "Freescale DIU driver\n");
+
+#ifdef CONFIG_NOT_COHERENT_CACHE
+	np = of_find_node_by_type(NULL, "cpu");
+	if (!np) {
+		printk(KERN_ERR "Err: can't find device node 'cpu'\n");
+		return -ENODEV;
+	}
+
+	prop = of_get_property(np, "d-cache-size", NULL);
+	if (prop == NULL)
+		return -ENODEV;
+
+	/* Freescale PLRU requires 13/8 times the cache size to do a proper
+	   displacement flush
+	 */
+	coherence_data_size = *prop * 13;
+	coherence_data_size /= 8;
+
+	prop = of_get_property(np, "d-cache-line-size", NULL);
+	if (prop == NULL)
+		return -ENODEV;
+	d_cache_line_size = *prop;
+
+	of_node_put(np);
+	coherence_data = vmalloc(coherence_data_size);
+	if (!coherence_data)
+		return -ENOMEM;
+#endif
+	ret = of_register_platform_driver(&fsl_diu_driver);
+	if (ret) {
+		printk(KERN_ERR
+			"fsl-diu: failed to register platform driver\n");
+#if defined(CONFIG_NOT_COHERENT_CACHE)
+		vfree(coherence_data);
+#endif
+		iounmap(dr.diu_reg);
+	}
+	return ret;
+}
+
+static void __exit fsl_diu_exit(void)
+{
+	of_unregister_platform_driver(&fsl_diu_driver);
+#if defined(CONFIG_NOT_COHERENT_CACHE)
+	vfree(coherence_data);
+#endif
+}
+
+module_init(fsl_diu_init);
+module_exit(fsl_diu_exit);
+
+MODULE_AUTHOR("York Sun <yorksun@freescale.com>");
+MODULE_DESCRIPTION("Freescale DIU framebuffer driver");
+MODULE_LICENSE("GPL");
+
+module_param_named(mode, fb_mode, charp, 0);
+MODULE_PARM_DESC(mode,
+	"Specify resolution as \"<xres>x<yres>[-<bpp>][@<refresh>]\" ");
+module_param_named(bpp, default_bpp, ulong, 0);
+MODULE_PARM_DESC(bpp, "Specify bit-per-pixel if not specified mode");
+module_param_named(monitor, monitor_port, int, 0);
+MODULE_PARM_DESC(monitor,
+	"Specify the monitor port (0, 1 or 2) if supported by the platform");
+
diff --git a/trunk/drivers/video/fsl-diu-fb.h b/trunk/drivers/video/fsl-diu-fb.h
new file mode 100644
index 000000000000..fc295d7ea463
--- /dev/null
+++ b/trunk/drivers/video/fsl-diu-fb.h
@@ -0,0 +1,223 @@
+/*
+ * Copyright 2008 Freescale Semiconductor, Inc. All Rights Reserved.
+ *
+ *  Freescale DIU Frame Buffer device driver
+ *
+ *  Authors: Hongjun Chen <hong-jun.chen@freescale.com>
+ *           Paul Widmer <paul.widmer@freescale.com>
+ *           Srikanth Srinivasan <srikanth.srinivasan@freescale.com>
+ *           York Sun <yorksun@freescale.com>
+ *
+ *   Based on imxfb.c Copyright (C) 2004 S.Hauer, Pengutronix
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ */
+
+#ifndef __FSL_DIU_FB_H__
+#define __FSL_DIU_FB_H__
+
+/* Arbitrary threshold to determine the allocation method
+ * See mpc8610fb_set_par(), map_video_memory(), and unmap_video_memory()
+ */
+#define MEM_ALLOC_THRESHOLD (1024*768*4+32)
+/* Minimum value that the pixel clock can be set to in pico seconds
+ * This is determined by platform clock/3 where the minimum platform
+ * clock is 533MHz. This gives 5629 pico seconds.
+ */
+#define MIN_PIX_CLK 5629
+#define MAX_PIX_CLK 96096
+
+#include <linux/types.h>
+
+struct mfb_alpha {
+	int enable;
+	int alpha;
+};
+
+struct mfb_chroma_key {
+	int enable;
+	__u8  red_max;
+	__u8  green_max;
+	__u8  blue_max;
+	__u8  red_min;
+	__u8  green_min;
+	__u8  blue_min;
+};
+
+struct aoi_display_offset {
+	int x_aoi_d;
+	int y_aoi_d;
+};
+
+#define MFB_SET_CHROMA_KEY	_IOW('M', 1, struct mfb_chroma_key)
+#define MFB_WAIT_FOR_VSYNC	_IOW('F', 0x20, u_int32_t)
+#define MFB_SET_BRIGHTNESS	_IOW('M', 3, __u8)
+
+#define MFB_SET_ALPHA		0x80014d00
+#define MFB_GET_ALPHA		0x40014d00
+#define MFB_SET_AOID		0x80084d04
+#define MFB_GET_AOID		0x40084d04
+#define MFB_SET_PIXFMT		0x80014d08
+#define MFB_GET_PIXFMT		0x40014d08
+
+#define FBIOGET_GWINFO		0x46E0
+#define FBIOPUT_GWINFO		0x46E1
+
+#ifdef __KERNEL__
+#include <linux/spinlock.h>
+
+/*
+ * These are the fields of area descriptor(in DDR memory) for every plane
+ */
+struct diu_ad {
+	/* Word 0(32-bit) in DDR memory */
+/* 	__u16 comp; */
+/* 	__u16 pixel_s:2; */
+/* 	__u16 pallete:1; */
+/* 	__u16 red_c:2; */
+/* 	__u16 green_c:2; */
+/* 	__u16 blue_c:2; */
+/* 	__u16 alpha_c:3; */
+/* 	__u16 byte_f:1; */
+/* 	__u16 res0:3; */
+
+	__be32 pix_fmt; /* hard coding pixel format */
+
+	/* Word 1(32-bit) in DDR memory */
+	__le32 addr;
+
+	/* Word 2(32-bit) in DDR memory */
+/* 	__u32 delta_xs:11; */
+/* 	__u32 res1:1; */
+/* 	__u32 delta_ys:11; */
+/* 	__u32 res2:1; */
+/* 	__u32 g_alpha:8; */
+	__le32 src_size_g_alpha;
+
+	/* Word 3(32-bit) in DDR memory */
+/* 	__u32 delta_xi:11; */
+/* 	__u32 res3:5; */
+/* 	__u32 delta_yi:11; */
+/* 	__u32 res4:3; */
+/* 	__u32 flip:2; */
+	__le32 aoi_size;
+
+	/* Word 4(32-bit) in DDR memory */
+	/*__u32 offset_xi:11;
+	__u32 res5:5;
+	__u32 offset_yi:11;
+	__u32 res6:5;
+	*/
+	__le32 offset_xyi;
+
+	/* Word 5(32-bit) in DDR memory */
+	/*__u32 offset_xd:11;
+	__u32 res7:5;
+	__u32 offset_yd:11;
+	__u32 res8:5; */
+	__le32 offset_xyd;
+
+
+	/* Word 6(32-bit) in DDR memory */
+	__u8 ckmax_r;
+	__u8 ckmax_g;
+	__u8 ckmax_b;
+	__u8 res9;
+
+	/* Word 7(32-bit) in DDR memory */
+	__u8 ckmin_r;
+	__u8 ckmin_g;
+	__u8 ckmin_b;
+	__u8 res10;
+/* 	__u32 res10:8; */
+
+	/* Word 8(32-bit) in DDR memory */
+	__le32 next_ad;
+
+	/* Word 9(32-bit) in DDR memory, just for 64-bit aligned */
+	__u32 paddr;
+} __attribute__ ((packed));
+
+/* DIU register map */
+struct diu {
+	__be32 desc[3];
+	__be32 gamma;
+	__be32 pallete;
+	__be32 cursor;
+	__be32 curs_pos;
+	__be32 diu_mode;
+	__be32 bgnd;
+	__be32 bgnd_wb;
+	__be32 disp_size;
+	__be32 wb_size;
+	__be32 wb_mem_addr;
+	__be32 hsyn_para;
+	__be32 vsyn_para;
+	__be32 syn_pol;
+	__be32 thresholds;
+	__be32 int_status;
+	__be32 int_mask;
+	__be32 colorbar[8];
+	__be32 filling;
+	__be32 plut;
+} __attribute__ ((packed));
+
+struct diu_hw {
+	struct diu *diu_reg;
+	spinlock_t reg_lock;
+
+	__u32 mode;		/* DIU operation mode */
+};
+
+struct diu_addr {
+	__u8 __iomem *vaddr;	/* Virtual address */
+	dma_addr_t paddr;	/* Physical address */
+	__u32 	   offset;
+};
+
+struct diu_pool {
+	struct diu_addr ad;
+	struct diu_addr gamma;
+	struct diu_addr pallete;
+	struct diu_addr cursor;
+};
+
+#define FSL_DIU_BASE_OFFSET	0x2C000	/* Offset of DIU */
+#define INT_LCDC		64	/* DIU interrupt number */
+
+#define FSL_AOI_NUM	6	/* 5 AOIs and one dummy AOI */
+				/* 1 for plane 0, 2 for plane 1&2 each */
+
+/* Minimum X and Y resolutions */
+#define MIN_XRES	64
+#define MIN_YRES	64
+
+/* HW cursor parameters */
+#define MAX_CURS		32
+
+/* Modes of operation of DIU */
+#define MFB_MODE0	0	/* DIU off */
+#define MFB_MODE1	1	/* All three planes output to display */
+#define MFB_MODE2	2	/* Plane 1 to display, planes 2+3 written back*/
+#define MFB_MODE3	3	/* All three planes written back to memory */
+#define MFB_MODE4	4	/* Color bar generation */
+
+/* INT_STATUS/INT_MASK field descriptions */
+#define INT_VSYNC	0x01	/* Vsync interrupt  */
+#define INT_VSYNC_WB	0x02	/* Vsync interrupt for write back operation */
+#define INT_UNDRUN	0x04	/* Under run exception interrupt */
+#define INT_PARERR	0x08	/* Display parameters error interrupt */
+#define INT_LS_BF_VS	0x10	/* Lines before vsync. interrupt */
+
+/* Panels'operation modes */
+#define MFB_TYPE_OUTPUT	0	/* Panel output to display */
+#define MFB_TYPE_OFF	1	/* Panel off */
+#define MFB_TYPE_WB	2	/* Panel written back to memory */
+#define MFB_TYPE_TEST	3	/* Panel generate color bar */
+
+#endif /* __KERNEL__ */
+#endif /* __FSL_DIU_FB_H__ */
diff --git a/trunk/drivers/video/geode/Kconfig b/trunk/drivers/video/geode/Kconfig
index 7608429b3943..c5d8ba4b9fc3 100644
--- a/trunk/drivers/video/geode/Kconfig
+++ b/trunk/drivers/video/geode/Kconfig
@@ -38,26 +38,6 @@ config FB_GEODE_GX
 
 	  If unsure, say N.
 
-config FB_GEODE_GX_SET_FBSIZE
-	bool "Manually specify the Geode GX framebuffer size"
-	depends on FB_GEODE_GX
-	default n
-	---help---
-	  If you want to manually specify the size of your GX framebuffer,
-	  say Y here, otherwise say N to dynamically probe it.
-
-	  Say N unless you know what you are doing.
-
-config FB_GEODE_GX_FBSIZE
-	hex "Size of the GX framebuffer, in bytes"
-	depends on FB_GEODE_GX_SET_FBSIZE
-	default "0x1600000"
-	---help---
-	  Specify the size of the GX framebuffer.  Normally, you will
-	  want this to be MB aligned.  Common values are 0x80000 (8MB)
-	  and 0x1600000 (16MB).  Don't change this unless you know what
-	  you are doing
-
 config FB_GEODE_GX1
 	tristate "AMD Geode GX1 framebuffer support (EXPERIMENTAL)"
 	depends on FB && FB_GEODE && EXPERIMENTAL
diff --git a/trunk/drivers/video/geode/Makefile b/trunk/drivers/video/geode/Makefile
index 957304b45fba..5c98da126883 100644
--- a/trunk/drivers/video/geode/Makefile
+++ b/trunk/drivers/video/geode/Makefile
@@ -5,5 +5,5 @@ obj-$(CONFIG_FB_GEODE_GX)  += gxfb.o
 obj-$(CONFIG_FB_GEODE_LX)  += lxfb.o
 
 gx1fb-objs := gx1fb_core.o display_gx1.o video_cs5530.o
-gxfb-objs  := gxfb_core.o display_gx.o video_gx.o
+gxfb-objs  := gxfb_core.o display_gx.o video_gx.o suspend_gx.o
 lxfb-objs  := lxfb_core.o lxfb_ops.o
diff --git a/trunk/drivers/video/geode/display_gx.c b/trunk/drivers/video/geode/display_gx.c
index 0f16e4bffc6c..e759895bf3d3 100644
--- a/trunk/drivers/video/geode/display_gx.c
+++ b/trunk/drivers/video/geode/display_gx.c
@@ -17,31 +17,40 @@
 #include <asm/io.h>
 #include <asm/div64.h>
 #include <asm/delay.h>
+#include <asm/geode.h>
 
-#include "geodefb.h"
-#include "display_gx.h"
+#include "gxfb.h"
 
-#ifdef CONFIG_FB_GEODE_GX_SET_FBSIZE
-unsigned int gx_frame_buffer_size(void)
-{
-	return CONFIG_FB_GEODE_GX_FBSIZE;
-}
-#else
 unsigned int gx_frame_buffer_size(void)
 {
 	unsigned int val;
 
-	/* FB size is reported by a virtual register */
+	if (!geode_has_vsa2()) {
+		uint32_t hi, lo;
+
+		/* The number of pages is (PMAX - PMIN)+1 */
+		rdmsr(MSR_GLIU_P2D_RO0, lo, hi);
+
+		/* PMAX */
+		val = ((hi & 0xff) << 12) | ((lo & 0xfff00000) >> 20);
+		/* PMIN */
+		val -= (lo & 0x000fffff);
+		val += 1;
+
+		/* The page size is 4k */
+		return (val << 12);
+	}
+
+	/* FB size can be obtained from the VSA II */
 	/* Virtual register class = 0x02 */
 	/* VG_MEM_SIZE(512Kb units) = 0x00 */
 
-	outw(0xFC53, 0xAC1C);
-	outw(0x0200, 0xAC1C);
+	outw(VSA_VR_UNLOCK, VSA_VRC_INDEX);
+	outw(VSA_VR_MEM_SIZE, VSA_VRC_INDEX);
 
-	val = (unsigned int)(inw(0xAC1E)) & 0xFFl;
+	val = (unsigned int)(inw(VSA_VRC_DATA)) & 0xFFl;
 	return (val << 19);
 }
-#endif
 
 int gx_line_delta(int xres, int bpp)
 {
@@ -49,75 +58,76 @@ int gx_line_delta(int xres, int bpp)
 	return (xres * (bpp >> 3) + 7) & ~0x7;
 }
 
-static void gx_set_mode(struct fb_info *info)
+void gx_set_mode(struct fb_info *info)
 {
-	struct geodefb_par *par = info->par;
+	struct gxfb_par *par = info->par;
 	u32 gcfg, dcfg;
 	int hactive, hblankstart, hsyncstart, hsyncend, hblankend, htotal;
 	int vactive, vblankstart, vsyncstart, vsyncend, vblankend, vtotal;
 
 	/* Unlock the display controller registers. */
-	readl(par->dc_regs + DC_UNLOCK);
-	writel(DC_UNLOCK_CODE, par->dc_regs + DC_UNLOCK);
+	write_dc(par, DC_UNLOCK, DC_UNLOCK_UNLOCK);
 
-	gcfg = readl(par->dc_regs + DC_GENERAL_CFG);
-	dcfg = readl(par->dc_regs + DC_DISPLAY_CFG);
+	gcfg = read_dc(par, DC_GENERAL_CFG);
+	dcfg = read_dc(par, DC_DISPLAY_CFG);
 
 	/* Disable the timing generator. */
-	dcfg &= ~(DC_DCFG_TGEN);
-	writel(dcfg, par->dc_regs + DC_DISPLAY_CFG);
+	dcfg &= ~DC_DISPLAY_CFG_TGEN;
+	write_dc(par, DC_DISPLAY_CFG, dcfg);
 
 	/* Wait for pending memory requests before disabling the FIFO load. */
 	udelay(100);
 
 	/* Disable FIFO load and compression. */
-	gcfg &= ~(DC_GCFG_DFLE | DC_GCFG_CMPE | DC_GCFG_DECE);
-	writel(gcfg, par->dc_regs + DC_GENERAL_CFG);
+	gcfg &= ~(DC_GENERAL_CFG_DFLE | DC_GENERAL_CFG_CMPE |
+			DC_GENERAL_CFG_DECE);
+	write_dc(par, DC_GENERAL_CFG, gcfg);
 
 	/* Setup DCLK and its divisor. */
-	par->vid_ops->set_dclk(info);
+	gx_set_dclk_frequency(info);
 
 	/*
 	 * Setup new mode.
 	 */
 
 	/* Clear all unused feature bits. */
-	gcfg &= DC_GCFG_YUVM | DC_GCFG_VDSE;
+	gcfg &= DC_GENERAL_CFG_YUVM | DC_GENERAL_CFG_VDSE;
 	dcfg = 0;
 
 	/* Set FIFO priority (default 6/5) and enable. */
 	/* FIXME: increase fifo priority for 1280x1024 and higher modes? */
-	gcfg |= (6 << DC_GCFG_DFHPEL_POS) | (5 << DC_GCFG_DFHPSL_POS) | DC_GCFG_DFLE;
+	gcfg |= (6 << DC_GENERAL_CFG_DFHPEL_SHIFT) |
+		(5 << DC_GENERAL_CFG_DFHPSL_SHIFT) | DC_GENERAL_CFG_DFLE;
 
 	/* Framebuffer start offset. */
-	writel(0, par->dc_regs + DC_FB_ST_OFFSET);
+	write_dc(par, DC_FB_ST_OFFSET, 0);
 
 	/* Line delta and line buffer length. */
-	writel(info->fix.line_length >> 3, par->dc_regs + DC_GFX_PITCH);
-	writel(((info->var.xres * info->var.bits_per_pixel/8) >> 3) + 2,
-	       par->dc_regs + DC_LINE_SIZE);
+	write_dc(par, DC_GFX_PITCH, info->fix.line_length >> 3);
+	write_dc(par, DC_LINE_SIZE,
+		((info->var.xres * info->var.bits_per_pixel/8) >> 3) + 2);
 
 
 	/* Enable graphics and video data and unmask address lines. */
-	dcfg |= DC_DCFG_GDEN | DC_DCFG_VDEN | DC_DCFG_A20M | DC_DCFG_A18M;
+	dcfg |= DC_DISPLAY_CFG_GDEN | DC_DISPLAY_CFG_VDEN |
+		DC_DISPLAY_CFG_A20M | DC_DISPLAY_CFG_A18M;
 
 	/* Set pixel format. */
 	switch (info->var.bits_per_pixel) {
 	case 8:
-		dcfg |= DC_DCFG_DISP_MODE_8BPP;
+		dcfg |= DC_DISPLAY_CFG_DISP_MODE_8BPP;
 		break;
 	case 16:
-		dcfg |= DC_DCFG_DISP_MODE_16BPP;
-		dcfg |= DC_DCFG_16BPP_MODE_565;
+		dcfg |= DC_DISPLAY_CFG_DISP_MODE_16BPP;
 		break;
 	case 32:
-		dcfg |= DC_DCFG_DISP_MODE_24BPP;
-		dcfg |= DC_DCFG_PALB;
+		dcfg |= DC_DISPLAY_CFG_DISP_MODE_24BPP;
+		dcfg |= DC_DISPLAY_CFG_PALB;
 		break;
 	}
 
 	/* Enable timing generator. */
-	dcfg |= DC_DCFG_TGEN;
+	dcfg |= DC_DISPLAY_CFG_TGEN;
 
 	/* Horizontal and vertical timings. */
 	hactive = info->var.xres;
@@ -134,28 +144,34 @@ static void gx_set_mode(struct fb_info *info)
 	vblankend = vsyncend + info->var.upper_margin;
 	vtotal = vblankend;
 
-	writel((hactive - 1)     | ((htotal - 1) << 16),    par->dc_regs + DC_H_ACTIVE_TIMING);
-	writel((hblankstart - 1) | ((hblankend - 1) << 16), par->dc_regs + DC_H_BLANK_TIMING);
-	writel((hsyncstart - 1)  | ((hsyncend - 1) << 16),  par->dc_regs + DC_H_SYNC_TIMING);
+	write_dc(par, DC_H_ACTIVE_TIMING, (hactive - 1)    |
+			((htotal - 1) << 16));
+	write_dc(par, DC_H_BLANK_TIMING, (hblankstart - 1) |
+			((hblankend - 1) << 16));
+	write_dc(par, DC_H_SYNC_TIMING, (hsyncstart - 1)   |
+			((hsyncend - 1) << 16));
 
-	writel((vactive - 1)     | ((vtotal - 1) << 16),    par->dc_regs + DC_V_ACTIVE_TIMING);
-	writel((vblankstart - 1) | ((vblankend - 1) << 16), par->dc_regs + DC_V_BLANK_TIMING);
-	writel((vsyncstart - 1)  | ((vsyncend - 1) << 16),  par->dc_regs + DC_V_SYNC_TIMING);
+	write_dc(par, DC_V_ACTIVE_TIMING, (vactive - 1)    |
+			((vtotal - 1) << 16));
+	write_dc(par, DC_V_BLANK_TIMING, (vblankstart - 1) |
+			((vblankend - 1) << 16));
+	write_dc(par, DC_V_SYNC_TIMING, (vsyncstart - 1)   |
+			((vsyncend - 1) << 16));
 
 	/* Write final register values. */
-	writel(dcfg, par->dc_regs + DC_DISPLAY_CFG);
-	writel(gcfg, par->dc_regs + DC_GENERAL_CFG);
+	write_dc(par, DC_DISPLAY_CFG, dcfg);
+	write_dc(par, DC_GENERAL_CFG, gcfg);
 
-	par->vid_ops->configure_display(info);
+	gx_configure_display(info);
 
 	/* Relock display controller registers */
-	writel(0, par->dc_regs + DC_UNLOCK);
+	write_dc(par, DC_UNLOCK, DC_UNLOCK_LOCK);
 }
 
-static void gx_set_hw_palette_reg(struct fb_info *info, unsigned regno,
-				   unsigned red, unsigned green, unsigned blue)
+void gx_set_hw_palette_reg(struct fb_info *info, unsigned regno,
+		unsigned red, unsigned green, unsigned blue)
 {
-	struct geodefb_par *par = info->par;
+	struct gxfb_par *par = info->par;
 	int val;
 
 	/* Hardware palette is in RGB 8-8-8 format. */
@@ -163,11 +179,6 @@ static void gx_set_hw_palette_reg(struct fb_info *info, unsigned regno,
 	val |= (green)      & 0x00ff00;
 	val |= (blue  >> 8) & 0x0000ff;
 
-	writel(regno, par->dc_regs + DC_PAL_ADDRESS);
-	writel(val, par->dc_regs + DC_PAL_DATA);
+	write_dc(par, DC_PAL_ADDRESS, regno);
+	write_dc(par, DC_PAL_DATA, val);
 }
-
-struct geode_dc_ops gx_dc_ops = {
-	.set_mode	 = gx_set_mode,
-	.set_palette_reg = gx_set_hw_palette_reg,
-};
diff --git a/trunk/drivers/video/geode/display_gx.h b/trunk/drivers/video/geode/display_gx.h
deleted file mode 100644
index 0af33f329e88..000000000000
--- a/trunk/drivers/video/geode/display_gx.h
+++ /dev/null
@@ -1,101 +0,0 @@
-/*
- * Geode GX display controller
- *
- * Copyright (C) 2006 Arcom Control Systems Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-#ifndef __DISPLAY_GX_H__
-#define __DISPLAY_GX_H__
-
-unsigned int gx_frame_buffer_size(void);
-int gx_line_delta(int xres, int bpp);
-
-extern struct geode_dc_ops gx_dc_ops;
-
-/* MSR that tells us if a TFT or CRT is attached */
-#define GLD_MSR_CONFIG   0xC0002001
-#define GLD_MSR_CONFIG_DM_FP 0x40
-
-/* Display controller registers */
-
-#define DC_UNLOCK 0x00
-#  define DC_UNLOCK_CODE 0x00004758
-
-#define DC_GENERAL_CFG 0x04
-#  define DC_GCFG_DFLE	      0x00000001
-#  define DC_GCFG_CURE	      0x00000002
-#  define DC_GCFG_ICNE	      0x00000004
-#  define DC_GCFG_VIDE	      0x00000008
-#  define DC_GCFG_CMPE	      0x00000020
-#  define DC_GCFG_DECE	      0x00000040
-#  define DC_GCFG_VGAE	      0x00000080
-#  define DC_GCFG_DFHPSL_MASK 0x00000F00
-#  define DC_GCFG_DFHPSL_POS	       8
-#  define DC_GCFG_DFHPEL_MASK 0x0000F000
-#  define DC_GCFG_DFHPEL_POS	      12
-#  define DC_GCFG_STFM	      0x00010000
-#  define DC_GCFG_FDTY	      0x00020000
-#  define DC_GCFG_VGAFT	      0x00040000
-#  define DC_GCFG_VDSE	      0x00080000
-#  define DC_GCFG_YUVM	      0x00100000
-#  define DC_GCFG_VFSL	      0x00800000
-#  define DC_GCFG_SIGE	      0x01000000
-#  define DC_GCFG_SGRE	      0x02000000
-#  define DC_GCFG_SGFR	      0x04000000
-#  define DC_GCFG_CRC_MODE    0x08000000
-#  define DC_GCFG_DIAG	      0x10000000
-#  define DC_GCFG_CFRW	      0x20000000
-
-#define DC_DISPLAY_CFG 0x08
-#  define DC_DCFG_TGEN            0x00000001
-#  define DC_DCFG_GDEN            0x00000008
-#  define DC_DCFG_VDEN            0x00000010
-#  define DC_DCFG_TRUP            0x00000040
-#  define DC_DCFG_DISP_MODE_MASK  0x00000300
-#  define DC_DCFG_DISP_MODE_8BPP  0x00000000
-#  define DC_DCFG_DISP_MODE_16BPP 0x00000100
-#  define DC_DCFG_DISP_MODE_24BPP 0x00000200
-#  define DC_DCFG_16BPP_MODE_MASK 0x00000c00
-#  define DC_DCFG_16BPP_MODE_565  0x00000000
-#  define DC_DCFG_16BPP_MODE_555  0x00000100
-#  define DC_DCFG_16BPP_MODE_444  0x00000200
-#  define DC_DCFG_DCEN            0x00080000
-#  define DC_DCFG_PALB            0x02000000
-#  define DC_DCFG_FRLK            0x04000000
-#  define DC_DCFG_VISL            0x08000000
-#  define DC_DCFG_FRSL            0x20000000
-#  define DC_DCFG_A18M            0x40000000
-#  define DC_DCFG_A20M            0x80000000
-
-#define DC_FB_ST_OFFSET 0x10
-
-#define DC_LINE_SIZE 0x30
-#  define DC_LINE_SIZE_FB_LINE_SIZE_MASK  0x000007ff
-#  define DC_LINE_SIZE_FB_LINE_SIZE_POS            0
-#  define DC_LINE_SIZE_CB_LINE_SIZE_MASK  0x007f0000
-#  define DC_LINE_SIZE_CB_LINE_SIZE_POS           16
-#  define DC_LINE_SIZE_VID_LINE_SIZE_MASK 0xff000000
-#  define DC_LINE_SIZE_VID_LINE_SIZE_POS          24
-
-#define DC_GFX_PITCH 0x34
-#  define DC_GFX_PITCH_FB_PITCH_MASK 0x0000ffff
-#  define DC_GFX_PITCH_FB_PITCH_POS           0
-#  define DC_GFX_PITCH_CB_PITCH_MASK 0xffff0000
-#  define DC_GFX_PITCH_CB_PITCH_POS          16
-
-#define DC_H_ACTIVE_TIMING 0x40
-#define DC_H_BLANK_TIMING  0x44
-#define DC_H_SYNC_TIMING   0x48
-#define DC_V_ACTIVE_TIMING 0x50
-#define DC_V_BLANK_TIMING  0x54
-#define DC_V_SYNC_TIMING   0x58
-
-#define DC_PAL_ADDRESS 0x70
-#define DC_PAL_DATA    0x74
-
-#define DC_GLIU0_MEM_OFFSET 0x84
-#endif /* !__DISPLAY_GX1_H__ */
diff --git a/trunk/drivers/video/geode/gxfb.h b/trunk/drivers/video/geode/gxfb.h
new file mode 100644
index 000000000000..16a96f8fd8c5
--- /dev/null
+++ b/trunk/drivers/video/geode/gxfb.h
@@ -0,0 +1,358 @@
+/*
+ * Copyright (C) 2008 Andres Salomon <dilinger@debian.org>
+ *
+ * Geode GX2 header information
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef _GXFB_H_
+#define _GXFB_H_
+
+#include <linux/io.h>
+
+#define GP_REG_COUNT   (0x50 / 4)
+#define DC_REG_COUNT   (0x90 / 4)
+#define VP_REG_COUNT   (0x138 / 8)
+#define FP_REG_COUNT   (0x68 / 8)
+
+#define DC_PAL_COUNT   0x104
+
+struct gxfb_par {
+	int enable_crt;
+	void __iomem *dc_regs;
+	void __iomem *vid_regs;
+	void __iomem *gp_regs;
+#ifdef CONFIG_PM
+	int powered_down;
+
+	/* register state, for power management functionality */
+	struct {
+		uint64_t padsel;
+		uint64_t dotpll;
+	} msr;
+
+	uint32_t gp[GP_REG_COUNT];
+	uint32_t dc[DC_REG_COUNT];
+	uint64_t vp[VP_REG_COUNT];
+	uint64_t fp[FP_REG_COUNT];
+
+	uint32_t pal[DC_PAL_COUNT];
+#endif
+};
+
+unsigned int gx_frame_buffer_size(void);
+int gx_line_delta(int xres, int bpp);
+void gx_set_mode(struct fb_info *info);
+void gx_set_hw_palette_reg(struct fb_info *info, unsigned regno,
+		unsigned red, unsigned green, unsigned blue);
+
+void gx_set_dclk_frequency(struct fb_info *info);
+void gx_configure_display(struct fb_info *info);
+int gx_blank_display(struct fb_info *info, int blank_mode);
+
+#ifdef CONFIG_PM
+int gx_powerdown(struct fb_info *info);
+int gx_powerup(struct fb_info *info);
+#endif
+
+
+/* Graphics Processor registers (table 6-23 from the data book) */
+enum gp_registers {
+	GP_DST_OFFSET = 0,
+	GP_SRC_OFFSET,
+	GP_STRIDE,
+	GP_WID_HEIGHT,
+
+	GP_SRC_COLOR_FG,
+	GP_SRC_COLOR_BG,
+	GP_PAT_COLOR_0,
+	GP_PAT_COLOR_1,
+
+	GP_PAT_COLOR_2,
+	GP_PAT_COLOR_3,
+	GP_PAT_COLOR_4,
+	GP_PAT_COLOR_5,
+
+	GP_PAT_DATA_0,
+	GP_PAT_DATA_1,
+	GP_RASTER_MODE,
+	GP_VECTOR_MODE,
+
+	GP_BLT_MODE,
+	GP_BLT_STATUS,
+	GP_HST_SRC,
+	GP_BASE_OFFSET, /* 0x4c */
+};
+
+#define GP_BLT_STATUS_BLT_PENDING	(1 << 2)
+#define GP_BLT_STATUS_BLT_BUSY		(1 << 0)
+
+
+/* Display Controller registers (table 6-38 from the data book) */
+enum dc_registers {
+	DC_UNLOCK = 0,
+	DC_GENERAL_CFG,
+	DC_DISPLAY_CFG,
+	DC_RSVD_0,
+
+	DC_FB_ST_OFFSET,
+	DC_CB_ST_OFFSET,
+	DC_CURS_ST_OFFSET,
+	DC_ICON_ST_OFFSET,
+
+	DC_VID_Y_ST_OFFSET,
+	DC_VID_U_ST_OFFSET,
+	DC_VID_V_ST_OFFSET,
+	DC_RSVD_1,
+
+	DC_LINE_SIZE,
+	DC_GFX_PITCH,
+	DC_VID_YUV_PITCH,
+	DC_RSVD_2,
+
+	DC_H_ACTIVE_TIMING,
+	DC_H_BLANK_TIMING,
+	DC_H_SYNC_TIMING,
+	DC_RSVD_3,
+
+	DC_V_ACTIVE_TIMING,
+	DC_V_BLANK_TIMING,
+	DC_V_SYNC_TIMING,
+	DC_RSVD_4,
+
+	DC_CURSOR_X,
+	DC_CURSOR_Y,
+	DC_ICON_X,
+	DC_LINE_CNT,
+
+	DC_PAL_ADDRESS,
+	DC_PAL_DATA,
+	DC_DFIFO_DIAG,
+	DC_CFIFO_DIAG,
+
+	DC_VID_DS_DELTA,
+	DC_GLIU0_MEM_OFFSET,
+	DC_RSVD_5,
+	DC_DV_ACC, /* 0x8c */
+};
+
+#define DC_UNLOCK_LOCK			0x00000000
+#define DC_UNLOCK_UNLOCK		0x00004758	/* magic value */
+
+#define DC_GENERAL_CFG_YUVM		(1 << 20)
+#define DC_GENERAL_CFG_VDSE		(1 << 19)
+#define DC_GENERAL_CFG_DFHPEL_SHIFT	12
+#define DC_GENERAL_CFG_DFHPSL_SHIFT	8
+#define DC_GENERAL_CFG_DECE		(1 << 6)
+#define DC_GENERAL_CFG_CMPE		(1 << 5)
+#define DC_GENERAL_CFG_VIDE		(1 << 3)
+#define DC_GENERAL_CFG_ICNE		(1 << 2)
+#define DC_GENERAL_CFG_CURE		(1 << 1)
+#define DC_GENERAL_CFG_DFLE		(1 << 0)
+
+#define DC_DISPLAY_CFG_A20M		(1 << 31)
+#define DC_DISPLAY_CFG_A18M		(1 << 30)
+#define DC_DISPLAY_CFG_PALB		(1 << 25)
+#define DC_DISPLAY_CFG_DISP_MODE_24BPP	(1 << 9)
+#define DC_DISPLAY_CFG_DISP_MODE_16BPP	(1 << 8)
+#define DC_DISPLAY_CFG_DISP_MODE_8BPP	(0)
+#define DC_DISPLAY_CFG_VDEN		(1 << 4)
+#define DC_DISPLAY_CFG_GDEN		(1 << 3)
+#define DC_DISPLAY_CFG_TGEN		(1 << 0)
+
+
+/*
+ * Video Processor registers (table 6-54).
+ * There is space for 64 bit values, but we never use more than the
+ * lower 32 bits.  The actual register save/restore code only bothers
+ * to restore those 32 bits.
+ */
+enum vp_registers {
+	VP_VCFG = 0,
+	VP_DCFG,
+
+	VP_VX,
+	VP_VY,
+
+	VP_VS,
+	VP_VCK,
+
+	VP_VCM,
+	VP_GAR,
+
+	VP_GDR,
+	VP_RSVD_0,
+
+	VP_MISC,
+	VP_CCS,
+
+	VP_RSVD_1,
+	VP_RSVD_2,
+
+	VP_RSVD_3,
+	VP_VDC,
+
+	VP_VCO,
+	VP_CRC,
+
+	VP_CRC32,
+	VP_VDE,
+
+	VP_CCK,
+	VP_CCM,
+
+	VP_CC1,
+	VP_CC2,
+
+	VP_A1X,
+	VP_A1Y,
+
+	VP_A1C,
+	VP_A1T,
+
+	VP_A2X,
+	VP_A2Y,
+
+	VP_A2C,
+	VP_A2T,
+
+	VP_A3X,
+	VP_A3Y,
+
+	VP_A3C,
+	VP_A3T,
+
+	VP_VRR,
+	VP_AWT,
+
+	VP_VTM, /* 0x130 */
+};
+
+#define VP_VCFG_VID_EN			(1 << 0)
+
+#define VP_DCFG_DAC_VREF		(1 << 26)
+#define VP_DCFG_GV_GAM			(1 << 21)
+#define VP_DCFG_VG_CK			(1 << 20)
+#define VP_DCFG_CRT_SYNC_SKW_DEFAULT	(1 << 16)
+#define VP_DCFG_CRT_SYNC_SKW		((1 << 14) | (1 << 15) | (1 << 16))
+#define VP_DCFG_CRT_VSYNC_POL		(1 << 9)
+#define VP_DCFG_CRT_HSYNC_POL		(1 << 8)
+#define VP_DCFG_FP_DATA_EN		(1 << 7)	/* undocumented */
+#define VP_DCFG_FP_PWR_EN		(1 << 6)	/* undocumented */
+#define VP_DCFG_DAC_BL_EN		(1 << 3)
+#define VP_DCFG_VSYNC_EN		(1 << 2)
+#define VP_DCFG_HSYNC_EN		(1 << 1)
+#define VP_DCFG_CRT_EN			(1 << 0)
+
+#define VP_MISC_GAM_EN			(1 << 0)
+#define VP_MISC_DACPWRDN		(1 << 10)
+#define VP_MISC_APWRDN			(1 << 11)
+
+
+/*
+ * Flat Panel registers (table 6-55).
+ * Also 64 bit registers; see above note about 32-bit handling.
+ */
+
+/* we're actually in the VP register space, starting at address 0x400 */
+#define VP_FP_START		0x400
+
+enum fp_registers {
+	FP_PT1 = 0,
+	FP_PT2,
+
+	FP_PM,
+	FP_DFC,
+
+	FP_BLFSR,
+	FP_RLFSR,
+
+	FP_FMI,
+	FP_FMD,
+
+	FP_RSVD_0,
+	FP_DCA,
+
+	FP_DMD,
+	FP_CRC,
+
+	FP_FBB, /* 0x460 */
+};
+
+#define FP_PT1_VSIZE_SHIFT		16		/* undocumented? */
+#define FP_PT1_VSIZE_MASK		0x7FF0000	/* undocumented? */
+
+#define FP_PT2_HSP			(1 << 22)
+#define FP_PT2_VSP			(1 << 23)
+
+#define FP_PM_P				(1 << 24)       /* panel power on */
+#define FP_PM_PANEL_PWR_UP		(1 << 3)        /* r/o */
+#define FP_PM_PANEL_PWR_DOWN		(1 << 2)        /* r/o */
+#define FP_PM_PANEL_OFF			(1 << 1)        /* r/o */
+#define FP_PM_PANEL_ON			(1 << 0)        /* r/o */
+
+#define FP_DFC_NFI			((1 << 4) | (1 << 5) | (1 << 6))
+
+
+/* register access functions */
+
+static inline uint32_t read_gp(struct gxfb_par *par, int reg)
+{
+	return readl(par->gp_regs + 4*reg);
+}
+
+static inline void write_gp(struct gxfb_par *par, int reg, uint32_t val)
+{
+	writel(val, par->gp_regs + 4*reg);
+}
+
+static inline uint32_t read_dc(struct gxfb_par *par, int reg)
+{
+	return readl(par->dc_regs + 4*reg);
+}
+
+static inline void write_dc(struct gxfb_par *par, int reg, uint32_t val)
+{
+	writel(val, par->dc_regs + 4*reg);
+}
+
+static inline uint32_t read_vp(struct gxfb_par *par, int reg)
+{
+	return readl(par->vid_regs + 8*reg);
+}
+
+static inline void write_vp(struct gxfb_par *par, int reg, uint32_t val)
+{
+	writel(val, par->vid_regs + 8*reg);
+}
+
+static inline uint32_t read_fp(struct gxfb_par *par, int reg)
+{
+	return readl(par->vid_regs + 8*reg + VP_FP_START);
+}
+
+static inline void write_fp(struct gxfb_par *par, int reg, uint32_t val)
+{
+	writel(val, par->vid_regs + 8*reg + VP_FP_START);
+}
+
+
+/* MSRs are defined in asm/geode.h; their bitfields are here */
+
+#define MSR_GLCP_SYS_RSTPLL_DOTPOSTDIV3	(1 << 3)
+#define MSR_GLCP_SYS_RSTPLL_DOTPREMULT2	(1 << 2)
+#define MSR_GLCP_SYS_RSTPLL_DOTPREDIV2	(1 << 1)
+
+#define MSR_GLCP_DOTPLL_LOCK		(1 << 25)	/* r/o */
+#define MSR_GLCP_DOTPLL_BYPASS		(1 << 15)
+#define MSR_GLCP_DOTPLL_DOTRESET	(1 << 0)
+
+#define MSR_GX_MSR_PADSEL_MASK		0x3FFFFFFF	/* undocumented? */
+#define MSR_GX_MSR_PADSEL_TFT		0x1FFFFFFF	/* undocumented? */
+
+#define MSR_GX_GLD_MSR_CONFIG_FP	(1 << 3)
+
+#endif
diff --git a/trunk/drivers/video/geode/gxfb_core.c b/trunk/drivers/video/geode/gxfb_core.c
index cf841efa229a..de2b8f9876a5 100644
--- a/trunk/drivers/video/geode/gxfb_core.c
+++ b/trunk/drivers/video/geode/gxfb_core.c
@@ -28,17 +28,20 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/fb.h>
+#include <linux/console.h>
+#include <linux/suspend.h>
 #include <linux/init.h>
 #include <linux/pci.h>
+#include <asm/geode.h>
 
-#include "geodefb.h"
-#include "display_gx.h"
-#include "video_gx.h"
+#include "gxfb.h"
 
 static char *mode_option;
+static int vram;
+static int vt_switch;
 
 /* Modes relevant to the GX (taken from modedb.c) */
-static const struct fb_videomode gx_modedb[] __initdata = {
+static struct fb_videomode gx_modedb[] __initdata = {
 	/* 640x480-60 VESA */
 	{ NULL, 60, 640, 480, 39682,  48, 16, 33, 10, 96, 2,
 	  0, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA },
@@ -105,6 +108,35 @@ static const struct fb_videomode gx_modedb[] __initdata = {
 	  FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA },
 };
 
+#ifdef CONFIG_OLPC
+#include <asm/olpc.h>
+
+static struct fb_videomode gx_dcon_modedb[] __initdata = {
+	/* The only mode the DCON has is 1200x900 */
+	{ NULL, 50, 1200, 900, 17460, 24, 8, 4, 5, 8, 3,
+	  FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+	  FB_VMODE_NONINTERLACED, 0 }
+};
+
+static void __init get_modedb(struct fb_videomode **modedb, unsigned int *size)
+{
+	if (olpc_has_dcon()) {
+		*modedb = (struct fb_videomode *) gx_dcon_modedb;
+		*size = ARRAY_SIZE(gx_dcon_modedb);
+	} else {
+		*modedb = (struct fb_videomode *) gx_modedb;
+		*size = ARRAY_SIZE(gx_modedb);
+	}
+}
+
+#else
+static void __init get_modedb(struct fb_videomode **modedb, unsigned int *size)
+{
+	*modedb = (struct fb_videomode *) gx_modedb;
+	*size = ARRAY_SIZE(gx_modedb);
+}
+#endif
+
 static int gxfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 {
 	if (var->xres > 1600 || var->yres > 1200)
@@ -139,8 +171,6 @@ static int gxfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 
 static int gxfb_set_par(struct fb_info *info)
 {
-	struct geodefb_par *par = info->par;
-
 	if (info->var.bits_per_pixel > 8) {
 		info->fix.visual = FB_VISUAL_TRUECOLOR;
 		fb_dealloc_cmap(&info->cmap);
@@ -151,7 +181,7 @@ static int gxfb_set_par(struct fb_info *info)
 
 	info->fix.line_length = gx_line_delta(info->var.xres, info->var.bits_per_pixel);
 
-	par->dc_ops->set_mode(info);
+	gx_set_mode(info);
 
 	return 0;
 }
@@ -167,8 +197,6 @@ static int gxfb_setcolreg(unsigned regno, unsigned red, unsigned green,
 			   unsigned blue, unsigned transp,
 			   struct fb_info *info)
 {
-	struct geodefb_par *par = info->par;
-
 	if (info->var.grayscale) {
 		/* grayscale = 0.30*R + 0.59*G + 0.11*B */
 		red = green = blue = (red * 77 + green * 151 + blue * 28) >> 8;
@@ -191,7 +219,7 @@ static int gxfb_setcolreg(unsigned regno, unsigned red, unsigned green,
 		if (regno >= 256)
 			return -EINVAL;
 
-		par->dc_ops->set_palette_reg(info, regno, red, green, blue);
+		gx_set_hw_palette_reg(info, regno, red, green, blue);
 	}
 
 	return 0;
@@ -199,15 +227,12 @@ static int gxfb_setcolreg(unsigned regno, unsigned red, unsigned green,
 
 static int gxfb_blank(int blank_mode, struct fb_info *info)
 {
-	struct geodefb_par *par = info->par;
-
-	return par->vid_ops->blank_display(info, blank_mode);
+	return gx_blank_display(info, blank_mode);
 }
 
 static int __init gxfb_map_video_memory(struct fb_info *info, struct pci_dev *dev)
 {
-	struct geodefb_par *par = info->par;
-	int fb_len;
+	struct gxfb_par *par = info->par;
 	int ret;
 
 	ret = pci_enable_device(dev);
@@ -229,24 +254,31 @@ static int __init gxfb_map_video_memory(struct fb_info *info, struct pci_dev *de
 	if (!par->dc_regs)
 		return -ENOMEM;
 
-	ret = pci_request_region(dev, 0, "gxfb (framebuffer)");
+	ret = pci_request_region(dev, 1, "gxfb (graphics processor)");
 	if (ret < 0)
 		return ret;
-	if ((fb_len = gx_frame_buffer_size()) < 0)
+	par->gp_regs = ioremap(pci_resource_start(dev, 1),
+	pci_resource_len(dev, 1));
+
+	if (!par->gp_regs)
 		return -ENOMEM;
+
+	ret = pci_request_region(dev, 0, "gxfb (framebuffer)");
+	if (ret < 0)
+		return ret;
+
 	info->fix.smem_start = pci_resource_start(dev, 0);
-	info->fix.smem_len = fb_len;
+	info->fix.smem_len = vram ? vram : gx_frame_buffer_size();
 	info->screen_base = ioremap(info->fix.smem_start, info->fix.smem_len);
 	if (!info->screen_base)
 		return -ENOMEM;
 
-	/* Set the 16MB aligned base address of the graphics memory region
+	/* Set the 16MiB aligned base address of the graphics memory region
 	 * in the display controller */
 
-	writel(info->fix.smem_start & 0xFF000000,
-			par->dc_regs + DC_GLIU0_MEM_OFFSET);
+	write_dc(par, DC_GLIU0_MEM_OFFSET, info->fix.smem_start & 0xFF000000);
 
-	dev_info(&dev->dev, "%d Kibyte of video memory at 0x%lx\n",
+	dev_info(&dev->dev, "%d KiB of video memory at 0x%lx\n",
 		 info->fix.smem_len / 1024, info->fix.smem_start);
 
 	return 0;
@@ -266,11 +298,12 @@ static struct fb_ops gxfb_ops = {
 
 static struct fb_info * __init gxfb_init_fbinfo(struct device *dev)
 {
-	struct geodefb_par *par;
+	struct gxfb_par *par;
 	struct fb_info *info;
 
 	/* Alloc enough space for the pseudo palette. */
-	info = framebuffer_alloc(sizeof(struct geodefb_par) + sizeof(u32) * 16, dev);
+	info = framebuffer_alloc(sizeof(struct gxfb_par) + sizeof(u32) * 16,
+			dev);
 	if (!info)
 		return NULL;
 
@@ -296,29 +329,64 @@ static struct fb_info * __init gxfb_init_fbinfo(struct device *dev)
 	info->flags		= FBINFO_DEFAULT;
 	info->node		= -1;
 
-	info->pseudo_palette	= (void *)par + sizeof(struct geodefb_par);
+	info->pseudo_palette	= (void *)par + sizeof(struct gxfb_par);
 
 	info->var.grayscale	= 0;
 
 	return info;
 }
 
+#ifdef CONFIG_PM
+static int gxfb_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	struct fb_info *info = pci_get_drvdata(pdev);
+
+	if (state.event == PM_EVENT_SUSPEND) {
+		acquire_console_sem();
+		gx_powerdown(info);
+		fb_set_suspend(info, 1);
+		release_console_sem();
+	}
+
+	/* there's no point in setting PCI states; we emulate PCI, so
+	 * we don't end up getting power savings anyways */
+
+	return 0;
+}
+
+static int gxfb_resume(struct pci_dev *pdev)
+{
+	struct fb_info *info = pci_get_drvdata(pdev);
+	int ret;
+
+	acquire_console_sem();
+	ret = gx_powerup(info);
+	if (ret) {
+		printk(KERN_ERR "gxfb:  power up failed!\n");
+		return ret;
+	}
+
+	fb_set_suspend(info, 0);
+	release_console_sem();
+	return 0;
+}
+#endif
+
 static int __init gxfb_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
-	struct geodefb_par *par;
+	struct gxfb_par *par;
 	struct fb_info *info;
 	int ret;
 	unsigned long val;
 
+	struct fb_videomode *modedb_ptr;
+	unsigned int modedb_size;
+
 	info = gxfb_init_fbinfo(&pdev->dev);
 	if (!info)
 		return -ENOMEM;
 	par = info->par;
 
-	/* GX display controller and GX video device. */
-	par->dc_ops  = &gx_dc_ops;
-	par->vid_ops = &gx_vid_ops;
-
 	if ((ret = gxfb_map_video_memory(info, pdev)) < 0) {
 		dev_err(&pdev->dev, "failed to map frame buffer or controller registers\n");
 		goto err;
@@ -326,15 +394,16 @@ static int __init gxfb_probe(struct pci_dev *pdev, const struct pci_device_id *i
 
 	/* Figure out if this is a TFT or CRT part */
 
-	rdmsrl(GLD_MSR_CONFIG, val);
+	rdmsrl(MSR_GX_GLD_MSR_CONFIG, val);
 
-	if ((val & GLD_MSR_CONFIG_DM_FP) == GLD_MSR_CONFIG_DM_FP)
+	if ((val & MSR_GX_GLD_MSR_CONFIG_FP) == MSR_GX_GLD_MSR_CONFIG_FP)
 		par->enable_crt = 0;
 	else
 		par->enable_crt = 1;
 
+	get_modedb(&modedb_ptr, &modedb_size);
 	ret = fb_find_mode(&info->var, info, mode_option,
-			   gx_modedb, ARRAY_SIZE(gx_modedb), NULL, 16);
+			   modedb_ptr, modedb_size, NULL, 16);
 	if (ret == 0 || ret == 4) {
 		dev_err(&pdev->dev, "could not find valid video mode\n");
 		ret = -EINVAL;
@@ -348,6 +417,8 @@ static int __init gxfb_probe(struct pci_dev *pdev, const struct pci_device_id *i
 	gxfb_check_var(&info->var, info);
 	gxfb_set_par(info);
 
+	pm_set_vt_switch(vt_switch);
+
 	if (register_framebuffer(info) < 0) {
 		ret = -EINVAL;
 		goto err;
@@ -369,6 +440,10 @@ static int __init gxfb_probe(struct pci_dev *pdev, const struct pci_device_id *i
 		iounmap(par->dc_regs);
 		pci_release_region(pdev, 2);
 	}
+	if (par->gp_regs) {
+		iounmap(par->gp_regs);
+		pci_release_region(pdev, 1);
+	}
 
 	if (info)
 		framebuffer_release(info);
@@ -378,7 +453,7 @@ static int __init gxfb_probe(struct pci_dev *pdev, const struct pci_device_id *i
 static void gxfb_remove(struct pci_dev *pdev)
 {
 	struct fb_info *info = pci_get_drvdata(pdev);
-	struct geodefb_par *par = info->par;
+	struct gxfb_par *par = info->par;
 
 	unregister_framebuffer(info);
 
@@ -391,15 +466,16 @@ static void gxfb_remove(struct pci_dev *pdev)
 	iounmap(par->dc_regs);
 	pci_release_region(pdev, 2);
 
+	iounmap(par->gp_regs);
+	pci_release_region(pdev, 1);
+
 	pci_set_drvdata(pdev, NULL);
 
 	framebuffer_release(info);
 }
 
 static struct pci_device_id gxfb_id_table[] = {
-	{ PCI_VENDOR_ID_NS, PCI_DEVICE_ID_NS_GX_VIDEO,
-	  PCI_ANY_ID, PCI_ANY_ID, PCI_BASE_CLASS_DISPLAY << 16,
-	  0xff0000, 0 },
+	{ PCI_DEVICE(PCI_VENDOR_ID_NS, PCI_DEVICE_ID_NS_GX_VIDEO) },
 	{ 0, }
 };
 
@@ -410,6 +486,10 @@ static struct pci_driver gxfb_driver = {
 	.id_table	= gxfb_id_table,
 	.probe		= gxfb_probe,
 	.remove		= gxfb_remove,
+#ifdef CONFIG_PM
+	.suspend	= gxfb_suspend,
+	.resume		= gxfb_resume,
+#endif
 };
 
 #ifndef MODULE
@@ -456,5 +536,11 @@ module_exit(gxfb_cleanup);
 module_param(mode_option, charp, 0);
 MODULE_PARM_DESC(mode_option, "video mode (<x>x<y>[-<bpp>][@<refr>])");
 
+module_param(vram, int, 0);
+MODULE_PARM_DESC(vram, "video memory size");
+
+module_param(vt_switch, int, 0);
+MODULE_PARM_DESC(vt_switch, "enable VT switch during suspend/resume");
+
 MODULE_DESCRIPTION("Framebuffer driver for the AMD Geode GX");
 MODULE_LICENSE("GPL");
diff --git a/trunk/drivers/video/geode/lxfb.h b/trunk/drivers/video/geode/lxfb.h
index ca13c48d19b0..3b9416f4ee20 100644
--- a/trunk/drivers/video/geode/lxfb.h
+++ b/trunk/drivers/video/geode/lxfb.h
@@ -3,17 +3,46 @@
 
 #include <linux/fb.h>
 
+#define GP_REG_COUNT	(0x7c / 4)
+#define DC_REG_COUNT	(0xf0 / 4)
+#define VP_REG_COUNT	(0x158 / 8)
+#define FP_REG_COUNT	(0x60 / 8)
+
+#define DC_PAL_COUNT	0x104
+#define DC_HFILT_COUNT	0x100
+#define DC_VFILT_COUNT	0x100
+#define VP_COEFF_SIZE	0x1000
+
 #define OUTPUT_CRT   0x01
 #define OUTPUT_PANEL 0x02
 
 struct lxfb_par {
 	int output;
-	int panel_width;
-	int panel_height;
 
 	void __iomem *gp_regs;
 	void __iomem *dc_regs;
-	void __iomem *df_regs;
+	void __iomem *vp_regs;
+#ifdef CONFIG_PM
+	int powered_down;
+
+	/* register state, for power mgmt functionality */
+	struct {
+		uint64_t padsel;
+		uint64_t dotpll;
+		uint64_t dfglcfg;
+		uint64_t dcspare;
+	} msr;
+
+	uint32_t gp[GP_REG_COUNT];
+	uint32_t dc[DC_REG_COUNT];
+	uint64_t vp[VP_REG_COUNT];
+	uint64_t fp[FP_REG_COUNT];
+
+	uint32_t pal[DC_PAL_COUNT];
+	uint32_t hcoeff[DC_HFILT_COUNT * 2];
+	uint32_t vcoeff[DC_VFILT_COUNT];
+	uint32_t vp_coeff[VP_COEFF_SIZE / 4];
+#endif
 };
 
 static inline unsigned int lx_get_pitch(unsigned int xres, int bpp)
@@ -29,171 +58,383 @@ int lx_blank_display(struct fb_info *, int);
 void lx_set_palette_reg(struct fb_info *, unsigned int, unsigned int,
 			unsigned int, unsigned int);
 
-/* MSRS */
+#ifdef CONFIG_PM
+int lx_powerdown(struct fb_info *info);
+int lx_powerup(struct fb_info *info);
+#endif
+
+
+/* Graphics Processor registers (table 6-29 from the data book) */
+enum gp_registers {
+	GP_DST_OFFSET = 0,
+	GP_SRC_OFFSET,
+	GP_STRIDE,
+	GP_WID_HEIGHT,
+
+	GP_SRC_COLOR_FG,
+	GP_SRC_COLOR_BG,
+	GP_PAT_COLOR_0,
+	GP_PAT_COLOR_1,
+
+	GP_PAT_COLOR_2,
+	GP_PAT_COLOR_3,
+	GP_PAT_COLOR_4,
+	GP_PAT_COLOR_5,
+
+	GP_PAT_DATA_0,
+	GP_PAT_DATA_1,
+	GP_RASTER_MODE,
+	GP_VECTOR_MODE,
+
+	GP_BLT_MODE,
+	GP_BLT_STATUS,
+	GP_HST_SRC,
+	GP_BASE_OFFSET,
+
+	GP_CMD_TOP,
+	GP_CMD_BOT,
+	GP_CMD_READ,
+	GP_CMD_WRITE,
+
+	GP_CH3_OFFSET,
+	GP_CH3_MODE_STR,
+	GP_CH3_WIDHI,
+	GP_CH3_HSRC,
+
+	GP_LUT_INDEX,
+	GP_LUT_DATA,
+	GP_INT_CNTRL, /* 0x78 */
+};
+
+#define GP_BLT_STATUS_CE		(1 << 4)	/* cmd buf empty */
+#define GP_BLT_STATUS_PB		(1 << 0)	/* primative busy */
+
+
+/* Display Controller registers (table 6-47 from the data book) */
+enum dc_registers {
+	DC_UNLOCK = 0,
+	DC_GENERAL_CFG,
+	DC_DISPLAY_CFG,
+	DC_ARB_CFG,
+
+	DC_FB_ST_OFFSET,
+	DC_CB_ST_OFFSET,
+	DC_CURS_ST_OFFSET,
+	DC_RSVD_0,
+
+	DC_VID_Y_ST_OFFSET,
+	DC_VID_U_ST_OFFSET,
+	DC_VID_V_ST_OFFSET,
+	DC_DV_TOP,
+
+	DC_LINE_SIZE,
+	DC_GFX_PITCH,
+	DC_VID_YUV_PITCH,
+	DC_RSVD_1,
+
+	DC_H_ACTIVE_TIMING,
+	DC_H_BLANK_TIMING,
+	DC_H_SYNC_TIMING,
+	DC_RSVD_2,
+
+	DC_V_ACTIVE_TIMING,
+	DC_V_BLANK_TIMING,
+	DC_V_SYNC_TIMING,
+	DC_FB_ACTIVE,
+
+	DC_CURSOR_X,
+	DC_CURSOR_Y,
+	DC_RSVD_3,
+	DC_LINE_CNT,
+
+	DC_PAL_ADDRESS,
+	DC_PAL_DATA,
+	DC_DFIFO_DIAG,
+	DC_CFIFO_DIAG,
+
+	DC_VID_DS_DELTA,
+	DC_GLIU0_MEM_OFFSET,
+	DC_DV_CTL,
+	DC_DV_ACCESS,
+
+	DC_GFX_SCALE,
+	DC_IRQ_FILT_CTL,
+	DC_FILT_COEFF1,
+	DC_FILT_COEFF2,
+
+	DC_VBI_EVEN_CTL,
+	DC_VBI_ODD_CTL,
+	DC_VBI_HOR,
+	DC_VBI_LN_ODD,
+
+	DC_VBI_LN_EVEN,
+	DC_VBI_PITCH,
+	DC_CLR_KEY,
+	DC_CLR_KEY_MASK,
+
+	DC_CLR_KEY_X,
+	DC_CLR_KEY_Y,
+	DC_IRQ,
+	DC_RSVD_4,
+
+	DC_RSVD_5,
+	DC_GENLK_CTL,
+	DC_VID_EVEN_Y_ST_OFFSET,
+	DC_VID_EVEN_U_ST_OFFSET,
+
+	DC_VID_EVEN_V_ST_OFFSET,
+	DC_V_ACTIVE_EVEN_TIMING,
+	DC_V_BLANK_EVEN_TIMING,
+	DC_V_SYNC_EVEN_TIMING,	/* 0xec */
+};
+
+#define DC_UNLOCK_LOCK			0x00000000
+#define DC_UNLOCK_UNLOCK		0x00004758	/* magic value */
+
+#define DC_GENERAL_CFG_FDTY		(1 << 17)
+#define DC_GENERAL_CFG_DFHPEL_SHIFT	(12)
+#define DC_GENERAL_CFG_DFHPSL_SHIFT	(8)
+#define DC_GENERAL_CFG_VGAE		(1 << 7)
+#define DC_GENERAL_CFG_DECE		(1 << 6)
+#define DC_GENERAL_CFG_CMPE		(1 << 5)
+#define DC_GENERAL_CFG_VIDE		(1 << 3)
+#define DC_GENERAL_CFG_DFLE		(1 << 0)
+
+#define DC_DISPLAY_CFG_VISL		(1 << 27)
+#define DC_DISPLAY_CFG_PALB		(1 << 25)
+#define DC_DISPLAY_CFG_DCEN		(1 << 24)
+#define DC_DISPLAY_CFG_DISP_MODE_24BPP	(1 << 9)
+#define DC_DISPLAY_CFG_DISP_MODE_16BPP	(1 << 8)
+#define DC_DISPLAY_CFG_DISP_MODE_8BPP	(0)
+#define DC_DISPLAY_CFG_TRUP		(1 << 6)
+#define DC_DISPLAY_CFG_VDEN		(1 << 4)
+#define DC_DISPLAY_CFG_GDEN		(1 << 3)
+#define DC_DISPLAY_CFG_TGEN		(1 << 0)
+
+#define DC_DV_TOP_DV_TOP_EN		(1 << 0)
+
+#define DC_DV_CTL_DV_LINE_SIZE		((1 << 10) | (1 << 11))
+#define DC_DV_CTL_DV_LINE_SIZE_1K	(0)
+#define DC_DV_CTL_DV_LINE_SIZE_2K	(1 << 10)
+#define DC_DV_CTL_DV_LINE_SIZE_4K	(1 << 11)
+#define DC_DV_CTL_DV_LINE_SIZE_8K	((1 << 10) | (1 << 11))
+#define DC_DV_CTL_CLEAR_DV_RAM		(1 << 0)
+
+#define DC_IRQ_FILT_CTL_H_FILT_SEL	(1 << 10)
+
+#define DC_CLR_KEY_CLR_KEY_EN		(1 << 24)
+
+#define DC_IRQ_VIP_VSYNC_IRQ_STATUS	(1 << 21)	/* undocumented? */
+#define DC_IRQ_STATUS			(1 << 20)	/* undocumented? */
+#define DC_IRQ_VIP_VSYNC_LOSS_IRQ_MASK	(1 << 1)
+#define DC_IRQ_MASK			(1 << 0)
 
-#define MSR_LX_GLD_CONFIG    0x48002001
-#define MSR_LX_GLCP_DOTPLL   0x4c000015
-#define MSR_LX_DF_PADSEL     0x48002011
-#define MSR_LX_DC_SPARE      0x80000011
-#define MSR_LX_DF_GLCONFIG   0x48002001
-
-#define MSR_LX_GLIU0_P2D_RO0 0x10000029
-
-#define GLCP_DOTPLL_RESET    (1 << 0)
-#define GLCP_DOTPLL_BYPASS   (1 << 15)
-#define GLCP_DOTPLL_HALFPIX  (1 << 24)
-#define GLCP_DOTPLL_LOCK     (1 << 25)
-
-#define DF_CONFIG_OUTPUT_MASK       0x38
-#define DF_OUTPUT_PANEL             0x08
-#define DF_OUTPUT_CRT               0x00
-#define DF_SIMULTANEOUS_CRT_AND_FP  (1 << 15)
-
-#define DF_DEFAULT_TFT_PAD_SEL_LOW  0xDFFFFFFF
-#define DF_DEFAULT_TFT_PAD_SEL_HIGH 0x0000003F
-
-#define DC_SPARE_DISABLE_CFIFO_HGO         0x00000800
-#define DC_SPARE_VFIFO_ARB_SELECT          0x00000400
-#define DC_SPARE_WM_LPEN_OVRD              0x00000200
-#define DC_SPARE_LOAD_WM_LPEN_MASK         0x00000100
-#define DC_SPARE_DISABLE_INIT_VID_PRI      0x00000080
-#define DC_SPARE_DISABLE_VFIFO_WM          0x00000040
-#define DC_SPARE_DISABLE_CWD_CHECK         0x00000020
-#define DC_SPARE_PIX8_PAN_FIX              0x00000010
-#define DC_SPARE_FIRST_REQ_MASK            0x00000002
-
-/* Registers */
-
-#define DC_UNLOCK         0x00
-#define  DC_UNLOCK_CODE   0x4758
+#define DC_GENLK_CTL_FLICK_SEL_MASK	(0x0F << 28)
+#define DC_GENLK_CTL_ALPHA_FLICK_EN	(1 << 25)
+#define DC_GENLK_CTL_FLICK_EN		(1 << 24)
+#define DC_GENLK_CTL_GENLK_EN		(1 << 18)
 
-#define DC_GENERAL_CFG    0x04
-#define  DC_GCFG_DFLE     (1 << 0)
-#define  DC_GCFG_VIDE     (1 << 3)
-#define  DC_GCFG_VGAE     (1 << 7)
-#define  DC_GCFG_CMPE     (1 << 5)
-#define  DC_GCFG_DECE     (1 << 6)
-#define  DC_GCFG_FDTY     (1 << 17)
 
-#define DC_DISPLAY_CFG    0x08
-#define  DC_DCFG_TGEN     (1 << 0)
-#define  DC_DCFG_GDEN     (1 << 3)
-#define  DC_DCFG_VDEN     (1 << 4)
-#define  DC_DCFG_TRUP     (1 << 6)
-#define  DC_DCFG_DCEN     (1 << 24)
-#define  DC_DCFG_PALB     (1 << 25)
-#define  DC_DCFG_VISL     (1 << 27)
+/*
+ * Video Processor registers (table 6-71).
+ * There is space for 64 bit values, but we never use more than the
+ * lower 32 bits.  The actual register save/restore code only bothers
+ * to restore those 32 bits.
+ */
+enum vp_registers {
+	VP_VCFG = 0,
+	VP_DCFG,
 
-#define  DC_DCFG_16BPP           0x0
+	VP_VX,
+	VP_VY,
 
-#define  DC_DCFG_DISP_MODE_MASK  0x00000300
-#define  DC_DCFG_DISP_MODE_8BPP  0x00000000
-#define  DC_DCFG_DISP_MODE_16BPP 0x00000100
-#define  DC_DCFG_DISP_MODE_24BPP 0x00000200
-#define  DC_DCFG_DISP_MODE_32BPP 0x00000300
+	VP_SCL,
+	VP_VCK,
 
+	VP_VCM,
+	VP_PAR,
 
-#define DC_ARB_CFG        0x0C
+	VP_PDR,
+	VP_SLR,
 
-#define DC_FB_START       0x10
-#define DC_CB_START       0x14
-#define DC_CURSOR_START   0x18
+	VP_MISC,
+	VP_CCS,
 
-#define DC_DV_TOP          0x2C
-#define DC_DV_TOP_ENABLE   (1 << 0)
+	VP_VYS,
+	VP_VXS,
 
-#define DC_LINE_SIZE       0x30
-#define DC_GRAPHICS_PITCH  0x34
-#define DC_H_ACTIVE_TIMING 0x40
-#define DC_H_BLANK_TIMING  0x44
-#define DC_H_SYNC_TIMING   0x48
-#define DC_V_ACTIVE_TIMING 0x50
-#define DC_V_BLANK_TIMING  0x54
-#define DC_V_SYNC_TIMING   0x58
-#define DC_FB_ACTIVE       0x5C
+	VP_RSVD_0,
+	VP_VDC,
+
+	VP_RSVD_1,
+	VP_CRC,
+
+	VP_CRC32,
+	VP_VDE,
+
+	VP_CCK,
+	VP_CCM,
+
+	VP_CC1,
+	VP_CC2,
+
+	VP_A1X,
+	VP_A1Y,
+
+	VP_A1C,
+	VP_A1T,
+
+	VP_A2X,
+	VP_A2Y,
+
+	VP_A2C,
+	VP_A2T,
+
+	VP_A3X,
+	VP_A3Y,
+
+	VP_A3C,
+	VP_A3T,
+
+	VP_VRR,
+	VP_AWT,
+
+	VP_VTM,
+	VP_VYE,
+
+	VP_A1YE,
+	VP_A2YE,
+
+	VP_A3YE,	/* 0x150 */
+
+	VP_VCR = 0x1000, /* 0x1000 - 0x1fff */
+};
 
-#define DC_PAL_ADDRESS     0x70
-#define DC_PAL_DATA        0x74
+#define VP_VCFG_VID_EN			(1 << 0)
 
-#define DC_PHY_MEM_OFFSET  0x84
+#define VP_DCFG_GV_GAM			(1 << 21)
+#define VP_DCFG_PWR_SEQ_DELAY		((1 << 17) | (1 << 18) | (1 << 19))
+#define VP_DCFG_PWR_SEQ_DELAY_DEFAULT	(1 << 19)	/* undocumented */
+#define VP_DCFG_CRT_SYNC_SKW		((1 << 14) | (1 << 15) | (1 << 16))
+#define VP_DCFG_CRT_SYNC_SKW_DEFAULT	(1 << 16)
+#define VP_DCFG_CRT_VSYNC_POL		(1 << 9)
+#define VP_DCFG_CRT_HSYNC_POL		(1 << 8)
+#define VP_DCFG_DAC_BL_EN		(1 << 3)
+#define VP_DCFG_VSYNC_EN		(1 << 2)
+#define VP_DCFG_HSYNC_EN		(1 << 1)
+#define VP_DCFG_CRT_EN			(1 << 0)
 
-#define DC_DV_CTL          0x88
-#define DC_DV_LINE_SIZE_MASK               0x00000C00
-#define DC_DV_LINE_SIZE_1024               0x00000000
-#define DC_DV_LINE_SIZE_2048               0x00000400
-#define DC_DV_LINE_SIZE_4096               0x00000800
-#define DC_DV_LINE_SIZE_8192               0x00000C00
+#define VP_MISC_APWRDN			(1 << 11)
+#define VP_MISC_DACPWRDN		(1 << 10)
+#define VP_MISC_BYP_BOTH		(1 << 0)
 
 
-#define DC_GFX_SCALE       0x90
-#define DC_IRQ_FILT_CTL    0x94
+/*
+ * Flat Panel registers (table 6-71).
+ * Also 64 bit registers; see above note about 32-bit handling.
+ */
 
+/* we're actually in the VP register space, starting at address 0x400 */
+#define VP_FP_START	0x400
 
-#define DC_IRQ               0xC8
-#define  DC_IRQ_MASK         (1 << 0)
-#define  DC_VSYNC_IRQ_MASK   (1 << 1)
-#define  DC_IRQ_STATUS       (1 << 20)
-#define  DC_VSYNC_IRQ_STATUS (1 << 21)
-
-#define DC_GENLCK_CTRL      0xD4
-#define  DC_GENLCK_ENABLE   (1 << 18)
-#define  DC_GC_ALPHA_FLICK_ENABLE  (1 << 25)
-#define  DC_GC_FLICKER_FILTER_ENABLE (1 << 24)
-#define  DC_GC_FLICKER_FILTER_MASK (0x0F << 28)
-
-#define DC_COLOR_KEY       0xB8
-#define DC_CLR_KEY_ENABLE (1 << 24)
-
-
-#define DC3_DV_LINE_SIZE_MASK               0x00000C00
-#define DC3_DV_LINE_SIZE_1024               0x00000000
-#define DC3_DV_LINE_SIZE_2048               0x00000400
-#define DC3_DV_LINE_SIZE_4096               0x00000800
-#define DC3_DV_LINE_SIZE_8192               0x00000C00
-
-#define DF_VIDEO_CFG       0x0
-#define  DF_VCFG_VID_EN    (1 << 0)
-
-#define DF_DISPLAY_CFG     0x08
-
-#define DF_DCFG_CRT_EN     (1 << 0)
-#define DF_DCFG_HSYNC_EN   (1 << 1)
-#define DF_DCFG_VSYNC_EN   (1 << 2)
-#define DF_DCFG_DAC_BL_EN  (1 << 3)
-#define DF_DCFG_CRT_HSYNC_POL  (1 << 8)
-#define DF_DCFG_CRT_VSYNC_POL  (1 << 9)
-#define DF_DCFG_GV_PAL_BYP     (1 << 21)
+enum fp_registers {
+	FP_PT1 = 0,
+	FP_PT2,
 
-#define DF_DCFG_CRT_SYNC_SKW_INIT 0x10000
-#define DF_DCFG_CRT_SYNC_SKW_MASK  0x1c000
+	FP_PM,
+	FP_DFC,
 
-#define DF_DCFG_PWR_SEQ_DLY_INIT     0x80000
-#define DF_DCFG_PWR_SEQ_DLY_MASK     0xe0000
+	FP_RSVD_0,
+	FP_RSVD_1,
 
-#define DF_MISC            0x50
+	FP_RSVD_2,
+	FP_RSVD_3,
+
+	FP_RSVD_4,
+	FP_DCA,
+
+	FP_DMD,
+	FP_CRC, /* 0x458 */
+};
+
+#define FP_PT2_SCRC			(1 << 27)	/* shfclk free */
+
+#define FP_PM_P				(1 << 24)	/* panel power ctl */
+#define FP_PM_PANEL_PWR_UP		(1 << 3)	/* r/o */
+#define FP_PM_PANEL_PWR_DOWN		(1 << 2)	/* r/o */
+#define FP_PM_PANEL_OFF			(1 << 1)	/* r/o */
+#define FP_PM_PANEL_ON			(1 << 0)	/* r/o */
+
+#define FP_DFC_BC			((1 << 4) | (1 << 5) | (1 << 6))
+
+
+/* register access functions */
+
+static inline uint32_t read_gp(struct lxfb_par *par, int reg)
+{
+	return readl(par->gp_regs + 4*reg);
+}
+
+static inline void write_gp(struct lxfb_par *par, int reg, uint32_t val)
+{
+	writel(val, par->gp_regs + 4*reg);
+}
+
+static inline uint32_t read_dc(struct lxfb_par *par, int reg)
+{
+	return readl(par->dc_regs + 4*reg);
+}
+
+static inline void write_dc(struct lxfb_par *par, int reg, uint32_t val)
+{
+	writel(val, par->dc_regs + 4*reg);
+}
+
+static inline uint32_t read_vp(struct lxfb_par *par, int reg)
+{
+	return readl(par->vp_regs + 8*reg);
+}
+
+static inline void write_vp(struct lxfb_par *par, int reg, uint32_t val)
+{
+	writel(val, par->vp_regs + 8*reg);
+}
+
+static inline uint32_t read_fp(struct lxfb_par *par, int reg)
+{
+	return readl(par->vp_regs + 8*reg + VP_FP_START);
+}
+
+static inline void write_fp(struct lxfb_par *par, int reg, uint32_t val)
+{
+	writel(val, par->vp_regs + 8*reg + VP_FP_START);
+}
 
-#define  DF_MISC_GAM_BYPASS (1 << 0)
-#define  DF_MISC_DAC_PWRDN  (1 << 10)
-#define  DF_MISC_A_PWRDN    (1 << 11)
 
-#define DF_PAR             0x38
-#define DF_PDR             0x40
-#define DF_ALPHA_CONTROL_1 0xD8
-#define DF_VIDEO_REQUEST   0x120
+/* MSRs are defined in asm/geode.h; their bitfields are here */
 
-#define DF_PANEL_TIM1      0x400
-#define DF_DEFAULT_TFT_PMTIM1 0x0
+#define MSR_GLCP_DOTPLL_LOCK		(1 << 25)	/* r/o */
+#define MSR_GLCP_DOTPLL_HALFPIX		(1 << 24)
+#define MSR_GLCP_DOTPLL_BYPASS		(1 << 15)
+#define MSR_GLCP_DOTPLL_DOTRESET	(1 << 0)
 
-#define DF_PANEL_TIM2      0x408
-#define DF_DEFAULT_TFT_PMTIM2 0x08000000
+/* note: this is actually the VP's GLD_MSR_CONFIG */
+#define MSR_LX_GLD_MSR_CONFIG_FMT	((1 << 3) | (1 << 4) | (1 << 5))
+#define MSR_LX_GLD_MSR_CONFIG_FMT_FP	(1 << 3)
+#define MSR_LX_GLD_MSR_CONFIG_FMT_CRT	(0)
+#define MSR_LX_GLD_MSR_CONFIG_FPC	(1 << 15)	/* FP *and* CRT */
 
-#define DF_FP_PM             0x410
-#define  DF_FP_PM_P          (1 << 24)
+#define MSR_LX_MSR_PADSEL_TFT_SEL_LOW	0xDFFFFFFF	/* ??? */
+#define MSR_LX_MSR_PADSEL_TFT_SEL_HIGH	0x0000003F	/* ??? */
 
-#define DF_DITHER_CONTROL    0x418
-#define DF_DEFAULT_TFT_DITHCTL                  0x00000070
-#define GP_BLT_STATUS      0x44
-#define  GP_BS_BLT_BUSY    (1 << 0)
-#define  GP_BS_CB_EMPTY    (1 << 4)
+#define MSR_LX_SPARE_MSR_DIS_CFIFO_HGO	(1 << 11)	/* undocumented */
+#define MSR_LX_SPARE_MSR_VFIFO_ARB_SEL	(1 << 10)	/* undocumented */
+#define MSR_LX_SPARE_MSR_WM_LPEN_OVRD	(1 << 9)	/* undocumented */
+#define MSR_LX_SPARE_MSR_LOAD_WM_LPEN_M	(1 << 8)	/* undocumented */
+#define MSR_LX_SPARE_MSR_DIS_INIT_V_PRI	(1 << 7)	/* undocumented */
+#define MSR_LX_SPARE_MSR_DIS_VIFO_WM	(1 << 6)
+#define MSR_LX_SPARE_MSR_DIS_CWD_CHECK	(1 << 5)	/* undocumented */
+#define MSR_LX_SPARE_MSR_PIX8_PAN_FIX	(1 << 4)	/* undocumented */
+#define MSR_LX_SPARE_MSR_FIRST_REQ_MASK	(1 << 1)	/* undocumented */
 
 #endif
diff --git a/trunk/drivers/video/geode/lxfb_core.c b/trunk/drivers/video/geode/lxfb_core.c
index eb6b88171538..2cd9b74d2225 100644
--- a/trunk/drivers/video/geode/lxfb_core.c
+++ b/trunk/drivers/video/geode/lxfb_core.c
@@ -17,6 +17,7 @@
 #include <linux/console.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
+#include <linux/suspend.h>
 #include <linux/delay.h>
 #include <linux/fb.h>
 #include <linux/init.h>
@@ -27,14 +28,15 @@
 
 static char *mode_option;
 static int noclear, nopanel, nocrt;
-static int fbsize;
+static int vram;
+static int vt_switch;
 
 /* Most of these modes are sorted in ascending order, but
  * since the first entry in this table is the "default" mode,
  * we try to make it something sane - 640x480-60 is sane
  */
 
-static const struct fb_videomode geode_modedb[] __initdata = {
+static struct fb_videomode geode_modedb[] __initdata = {
 	/* 640x480-60 */
 	{ NULL, 60, 640, 480, 39682, 48, 8, 25, 2, 88, 2,
 	  FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
@@ -215,6 +217,35 @@ static const struct fb_videomode geode_modedb[] __initdata = {
 	  0, FB_VMODE_NONINTERLACED, 0 },
 };
 
+#ifdef CONFIG_OLPC
+#include <asm/olpc.h>
+
+static struct fb_videomode olpc_dcon_modedb[] __initdata = {
+	/* The only mode the DCON has is 1200x900 */
+	{ NULL, 50, 1200, 900, 17460, 24, 8, 4, 5, 8, 3,
+	  FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+	  FB_VMODE_NONINTERLACED, 0 }
+};
+
+static void __init get_modedb(struct fb_videomode **modedb, unsigned int *size)
+{
+	if (olpc_has_dcon()) {
+		*modedb = (struct fb_videomode *) olpc_dcon_modedb;
+		*size = ARRAY_SIZE(olpc_dcon_modedb);
+	} else {
+		*modedb = (struct fb_videomode *) geode_modedb;
+		*size = ARRAY_SIZE(geode_modedb);
+	}
+}
+
+#else
+static void __init get_modedb(struct fb_videomode **modedb, unsigned int *size)
+{
+	*modedb = (struct fb_videomode *) geode_modedb;
+	*size = ARRAY_SIZE(geode_modedb);
+}
+#endif
+
 static int lxfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 {
 	if (var->xres > 1920 || var->yres > 1440)
@@ -333,13 +364,13 @@ static int __init lxfb_map_video_memory(struct fb_info *info,
 	if (ret)
 		return ret;
 
-	ret = pci_request_region(dev, 3, "lxfb-vip");
+	ret = pci_request_region(dev, 3, "lxfb-vp");
 
 	if (ret)
 		return ret;
 
 	info->fix.smem_start = pci_resource_start(dev, 0);
-	info->fix.smem_len = fbsize ? fbsize : lx_framebuffer_size();
+	info->fix.smem_len = vram ? vram : lx_framebuffer_size();
 
 	info->screen_base = ioremap(info->fix.smem_start, info->fix.smem_len);
 
@@ -360,18 +391,15 @@ static int __init lxfb_map_video_memory(struct fb_info *info,
 	if (par->dc_regs == NULL)
 		return ret;
 
-	par->df_regs = ioremap(pci_resource_start(dev, 3),
+	par->vp_regs = ioremap(pci_resource_start(dev, 3),
 			       pci_resource_len(dev, 3));
 
-	if (par->df_regs == NULL)
+	if (par->vp_regs == NULL)
 		return ret;
 
-	writel(DC_UNLOCK_CODE, par->dc_regs + DC_UNLOCK);
-
-	writel(info->fix.smem_start & 0xFF000000,
-	       par->dc_regs + DC_PHY_MEM_OFFSET);
-
-	writel(0, par->dc_regs + DC_UNLOCK);
+	write_dc(par, DC_UNLOCK, DC_UNLOCK_UNLOCK);
+	write_dc(par, DC_GLIU0_MEM_OFFSET, info->fix.smem_start & 0xFF000000);
+	write_dc(par, DC_UNLOCK, DC_UNLOCK_LOCK);
 
 	dev_info(&dev->dev, "%d KB of video memory at 0x%lx\n",
 		 info->fix.smem_len / 1024, info->fix.smem_start);
@@ -431,6 +459,45 @@ static struct fb_info * __init lxfb_init_fbinfo(struct device *dev)
 	return info;
 }
 
+#ifdef CONFIG_PM
+static int lxfb_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	struct fb_info *info = pci_get_drvdata(pdev);
+
+	if (state.event == PM_EVENT_SUSPEND) {
+		acquire_console_sem();
+		lx_powerdown(info);
+		fb_set_suspend(info, 1);
+		release_console_sem();
+	}
+
+	/* there's no point in setting PCI states; we emulate PCI, so
+	 * we don't end up getting power savings anyways */
+
+	return 0;
+}
+
+static int lxfb_resume(struct pci_dev *pdev)
+{
+	struct fb_info *info = pci_get_drvdata(pdev);
+	int ret;
+
+	acquire_console_sem();
+	ret = lx_powerup(info);
+	if (ret) {
+		printk(KERN_ERR "lxfb:  power up failed!\n");
+		return ret;
+	}
+
+	fb_set_suspend(info, 0);
+	release_console_sem();
+	return 0;
+}
+#else
+#define lxfb_suspend NULL
+#define lxfb_resume NULL
+#endif
+
 static int __init lxfb_probe(struct pci_dev *pdev,
 			     const struct pci_device_id *id)
 {
@@ -439,7 +506,7 @@ static int __init lxfb_probe(struct pci_dev *pdev,
 	int ret;
 
 	struct fb_videomode *modedb_ptr;
-	int modedb_size;
+	unsigned int modedb_size;
 
 	info = lxfb_init_fbinfo(&pdev->dev);
 
@@ -464,9 +531,7 @@ static int __init lxfb_probe(struct pci_dev *pdev,
 
 	/* Set up the mode database */
 
-	modedb_ptr = (struct fb_videomode *) geode_modedb;
-	modedb_size = ARRAY_SIZE(geode_modedb);
-
+	get_modedb(&modedb_ptr, &modedb_size);
 	ret = fb_find_mode(&info->var, info, mode_option,
 			   modedb_ptr, modedb_size, NULL, 16);
 
@@ -487,6 +552,8 @@ static int __init lxfb_probe(struct pci_dev *pdev,
 	lxfb_check_var(&info->var, info);
 	lxfb_set_par(info);
 
+	pm_set_vt_switch(vt_switch);
+
 	if (register_framebuffer(info) < 0) {
 		ret = -EINVAL;
 		goto err;
@@ -510,8 +577,8 @@ static int __init lxfb_probe(struct pci_dev *pdev,
 		iounmap(par->dc_regs);
 		pci_release_region(pdev, 2);
 	}
-	if (par->df_regs) {
-		iounmap(par->df_regs);
+	if (par->vp_regs) {
+		iounmap(par->vp_regs);
 		pci_release_region(pdev, 3);
 	}
 
@@ -537,7 +604,7 @@ static void lxfb_remove(struct pci_dev *pdev)
 	iounmap(par->dc_regs);
 	pci_release_region(pdev, 2);
 
-	iounmap(par->df_regs);
+	iounmap(par->vp_regs);
 	pci_release_region(pdev, 3);
 
 	pci_set_drvdata(pdev, NULL);
@@ -556,6 +623,8 @@ static struct pci_driver lxfb_driver = {
 	.id_table	= lxfb_id_table,
 	.probe		= lxfb_probe,
 	.remove		= lxfb_remove,
+	.suspend	= lxfb_suspend,
+	.resume		= lxfb_resume,
 };
 
 #ifndef MODULE
@@ -570,9 +639,7 @@ static int __init lxfb_setup(char *options)
 		if (!*opt)
 			continue;
 
-		if (!strncmp(opt, "fbsize:", 7))
-			fbsize = simple_strtoul(opt+7, NULL, 0);
-		else if (!strcmp(opt, "noclear"))
+		if (!strcmp(opt, "noclear"))
 			noclear = 1;
 		else if (!strcmp(opt, "nopanel"))
 			nopanel = 1;
@@ -609,8 +676,11 @@ module_exit(lxfb_cleanup);
 module_param(mode_option, charp, 0);
 MODULE_PARM_DESC(mode_option, "video mode (<x>x<y>[-<bpp>][@<refr>])");
 
-module_param(fbsize, int, 0);
-MODULE_PARM_DESC(fbsize, "video memory size");
+module_param(vram, int, 0);
+MODULE_PARM_DESC(vram, "video memory size");
+
+module_param(vt_switch, int, 0);
+MODULE_PARM_DESC(vt_switch, "enable VT switch during suspend/resume");
 
 MODULE_DESCRIPTION("Framebuffer driver for the AMD Geode LX");
 MODULE_LICENSE("GPL");
diff --git a/trunk/drivers/video/geode/lxfb_ops.c b/trunk/drivers/video/geode/lxfb_ops.c
index 4fbc99be96ef..cd9d4cc26954 100644
--- a/trunk/drivers/video/geode/lxfb_ops.c
+++ b/trunk/drivers/video/geode/lxfb_ops.c
@@ -13,6 +13,7 @@
 #include <linux/fb.h>
 #include <linux/uaccess.h>
 #include <linux/delay.h>
+#include <asm/geode.h>
 
 #include "lxfb.h"
 
@@ -34,35 +35,85 @@ static const struct {
   unsigned int pllval;
   unsigned int freq;
 } pll_table[] = {
-  { 0x000031AC, 24923 },
-  { 0x0000215D, 25175 },
-  { 0x00001087, 27000 },
-  { 0x0000216C, 28322 },
-  { 0x0000218D, 28560 },
-  { 0x000010C9, 31200 },
-  { 0x00003147, 31500 },
-  { 0x000010A7, 33032 },
-  { 0x00002159, 35112 },
-  { 0x00004249, 35500 },
-  { 0x00000057, 36000 },
-  { 0x0000219A, 37889 },
-  { 0x00002158, 39168 },
-  { 0x00000045, 40000 },
-  { 0x00000089, 43163 },
-  { 0x000010E7, 44900 },
-  { 0x00002136, 45720 },
-  { 0x00003207, 49500 },
-  { 0x00002187, 50000 },
-  { 0x00004286, 56250 },
-  { 0x000010E5, 60065 },
-  { 0x00004214, 65000 },
-  { 0x00001105, 68179 },
-  { 0x000031E4, 74250 },
-  { 0x00003183, 75000 },
-  { 0x00004284, 78750 },
-  { 0x00001104, 81600 },
-  { 0x00006363, 94500 },
-  { 0x00005303, 97520 },
+  { 0x000131AC,   6231 },
+  { 0x0001215D,   6294 },
+  { 0x00011087,   6750 },
+  { 0x0001216C,   7081 },
+  { 0x0001218D,   7140 },
+  { 0x000110C9,   7800 },
+  { 0x00013147,   7875 },
+  { 0x000110A7,   8258 },
+  { 0x00012159,   8778 },
+  { 0x00014249,   8875 },
+  { 0x00010057,   9000 },
+  { 0x0001219A,   9472 },
+  { 0x00012158,   9792 },
+  { 0x00010045,  10000 },
+  { 0x00010089,  10791 },
+  { 0x000110E7,  11225 },
+  { 0x00012136,  11430 },
+  { 0x00013207,  12375 },
+  { 0x00012187,  12500 },
+  { 0x00014286,  14063 },
+  { 0x000110E5,  15016 },
+  { 0x00014214,  16250 },
+  { 0x00011105,  17045 },
+  { 0x000131E4,  18563 },
+  { 0x00013183,  18750 },
+  { 0x00014284,  19688 },
+  { 0x00011104,  20400 },
+  { 0x00016363,  23625 },
+  { 0x00015303,  24380 },
+  { 0x000031AC,  24923 },
+  { 0x0000215D,  25175 },
+  { 0x00001087,  27000 },
+  { 0x0000216C,  28322 },
+  { 0x0000218D,  28560 },
+  { 0x00010041,  29913 },
+  { 0x000010C9,  31200 },
+  { 0x00003147,  31500 },
+  { 0x000141A1,  32400 },
+  { 0x000010A7,  33032 },
+  { 0x00012182,  33375 },
+  { 0x000141B1,  33750 },
+  { 0x00002159,  35112 },
+  { 0x00004249,  35500 },
+  { 0x00000057,  36000 },
+  { 0x000141E1,  37125 },
+  { 0x0000219A,  37889 },
+  { 0x00002158,  39168 },
+  { 0x00000045,  40000 },
+  { 0x000131A1,  40500 },
+  { 0x00010061,  42301 },
+  { 0x00000089,  43163 },
+  { 0x00012151,  43875 },
+  { 0x000010E7,  44900 },
+  { 0x00002136,  45720 },
+  { 0x000152E1,  47250 },
+  { 0x00010071,  48000 },
+  { 0x00003207,  49500 },
+  { 0x00002187,  50000 },
+  { 0x00014291,  50625 },
+  { 0x00011101,  51188 },
+  { 0x00017481,  54563 },
+  { 0x00004286,  56250 },
+  { 0x00014170,  57375 },
+  { 0x00016210,  58500 },
+  { 0x000010E5,  60065 },
+  { 0x00013140,  62796 },
+  { 0x00004214,  65000 },
+  { 0x00016250,  65250 },
+  { 0x00001105,  68179 },
+  { 0x000141C0,  69600 },
+  { 0x00015220,  70160 },
+  { 0x00010050,  72000 },
+  { 0x000031E4,  74250 },
+  { 0x00003183,  75000 },
+  { 0x00004284,  78750 },
+  { 0x00012130,  80052 },
+  { 0x00001104,  81600 },
+  { 0x00006363,  94500 },
+  { 0x00005303,  97520 },
   { 0x00002183, 100187 },
   { 0x00002122, 101420 },
   { 0x00001081, 108000 },
@@ -101,16 +152,16 @@ static void lx_set_dotpll(u32 pllval)
 	u32 dotpll_lo, dotpll_hi;
 	int i;
 
-	rdmsr(MSR_LX_GLCP_DOTPLL, dotpll_lo, dotpll_hi);
+	rdmsr(MSR_GLCP_DOTPLL, dotpll_lo, dotpll_hi);
 
-	if ((dotpll_lo & GLCP_DOTPLL_LOCK) && (dotpll_hi == pllval))
+	if ((dotpll_lo & MSR_GLCP_DOTPLL_LOCK) && (dotpll_hi == pllval))
 		return;
 
 	dotpll_hi = pllval;
-	dotpll_lo &= ~(GLCP_DOTPLL_BYPASS | GLCP_DOTPLL_HALFPIX);
-	dotpll_lo |= GLCP_DOTPLL_RESET;
+	dotpll_lo &= ~(MSR_GLCP_DOTPLL_BYPASS | MSR_GLCP_DOTPLL_HALFPIX);
+	dotpll_lo |= MSR_GLCP_DOTPLL_DOTRESET;
 
-	wrmsr(MSR_LX_GLCP_DOTPLL, dotpll_lo, dotpll_hi);
+	wrmsr(MSR_GLCP_DOTPLL, dotpll_lo, dotpll_hi);
 
 	/* Wait 100us for the PLL to lock */
 
@@ -119,15 +170,15 @@ static void lx_set_dotpll(u32 pllval)
 	/* Now, loop for the lock bit */
 
 	for (i = 0; i < 1000; i++) {
-		rdmsr(MSR_LX_GLCP_DOTPLL, dotpll_lo, dotpll_hi);
-		if (dotpll_lo & GLCP_DOTPLL_LOCK)
+		rdmsr(MSR_GLCP_DOTPLL, dotpll_lo, dotpll_hi);
+		if (dotpll_lo & MSR_GLCP_DOTPLL_LOCK)
 			break;
 	}
 
 	/* Clear the reset bit */
 
-	dotpll_lo &= ~GLCP_DOTPLL_RESET;
-	wrmsr(MSR_LX_GLCP_DOTPLL, dotpll_lo, dotpll_hi);
+	dotpll_lo &= ~MSR_GLCP_DOTPLL_DOTRESET;
+	wrmsr(MSR_GLCP_DOTPLL, dotpll_lo, dotpll_hi);
 }
 
 /* Set the clock based on the frequency specified by the current mode */
@@ -137,7 +188,7 @@ static void lx_set_clock(struct fb_info *info)
 	unsigned int diff, min, best = 0;
 	unsigned int freq, i;
 
-	freq = (unsigned int) (0x3b9aca00 / info->var.pixclock);
+	freq = (unsigned int) (1000000000 / info->var.pixclock);
 
 	min = abs(pll_table[0].freq - freq);
 
@@ -149,7 +200,7 @@ static void lx_set_clock(struct fb_info *info)
 		}
 	}
 
-	lx_set_dotpll(pll_table[best].pllval & 0x7FFF);
+	lx_set_dotpll(pll_table[best].pllval & 0x00017FFF);
 }
 
 static void lx_graphics_disable(struct fb_info *info)
@@ -159,63 +210,62 @@ static void lx_graphics_disable(struct fb_info *info)
 
 	/* Note:  This assumes that the video is in a quitet state */
 
-	writel(0, par->df_regs + DF_ALPHA_CONTROL_1);
-	writel(0, par->df_regs + DF_ALPHA_CONTROL_1 + 32);
-	writel(0, par->df_regs + DF_ALPHA_CONTROL_1 + 64);
+	write_vp(par, VP_A1T, 0);
+	write_vp(par, VP_A2T, 0);
+	write_vp(par, VP_A3T, 0);
 
 	/* Turn off the VGA and video enable */
-	val = readl (par->dc_regs + DC_GENERAL_CFG) &
-		~(DC_GCFG_VGAE | DC_GCFG_VIDE);
+	val = read_dc(par, DC_GENERAL_CFG) & ~(DC_GENERAL_CFG_VGAE |
+			DC_GENERAL_CFG_VIDE);
 
-	writel(val, par->dc_regs + DC_GENERAL_CFG);
+	write_dc(par, DC_GENERAL_CFG, val);
 
-	val = readl(par->df_regs + DF_VIDEO_CFG) & ~DF_VCFG_VID_EN;
-	writel(val, par->df_regs + DF_VIDEO_CFG);
+	val = read_vp(par, VP_VCFG) & ~VP_VCFG_VID_EN;
+	write_vp(par, VP_VCFG, val);
 
-	writel( DC_IRQ_MASK | DC_VSYNC_IRQ_MASK |
-		DC_IRQ_STATUS | DC_VSYNC_IRQ_STATUS,
-		par->dc_regs + DC_IRQ);
+	write_dc(par, DC_IRQ, DC_IRQ_MASK | DC_IRQ_VIP_VSYNC_LOSS_IRQ_MASK |
+			DC_IRQ_STATUS | DC_IRQ_VIP_VSYNC_IRQ_STATUS);
 
-	val = readl(par->dc_regs + DC_GENLCK_CTRL) & ~DC_GENLCK_ENABLE;
-	writel(val, par->dc_regs + DC_GENLCK_CTRL);
+	val = read_dc(par, DC_GENLK_CTL) & ~DC_GENLK_CTL_GENLK_EN;
+	write_dc(par, DC_GENLK_CTL, val);
 
-	val = readl(par->dc_regs + DC_COLOR_KEY) & ~DC_CLR_KEY_ENABLE;
-	writel(val & ~DC_CLR_KEY_ENABLE, par->dc_regs + DC_COLOR_KEY);
+	val = read_dc(par, DC_CLR_KEY);
+	write_dc(par, DC_CLR_KEY, val & ~DC_CLR_KEY_CLR_KEY_EN);
 
-	/* We don't actually blank the panel, due to the long latency
-	   involved with bringing it back */
+	/* turn off the panel */
+	write_fp(par, FP_PM, read_fp(par, FP_PM) & ~FP_PM_P);
 
-	val = readl(par->df_regs + DF_MISC) | DF_MISC_DAC_PWRDN;
-	writel(val, par->df_regs + DF_MISC);
+	val = read_vp(par, VP_MISC) | VP_MISC_DACPWRDN;
+	write_vp(par, VP_MISC, val);
 
 	/* Turn off the display */
 
-	val = readl(par->df_regs + DF_DISPLAY_CFG);
-	writel(val & ~(DF_DCFG_CRT_EN | DF_DCFG_HSYNC_EN | DF_DCFG_VSYNC_EN |
-		       DF_DCFG_DAC_BL_EN), par->df_regs + DF_DISPLAY_CFG);
+	val = read_vp(par, VP_DCFG);
+	write_vp(par, VP_DCFG, val & ~(VP_DCFG_CRT_EN | VP_DCFG_HSYNC_EN |
+			VP_DCFG_VSYNC_EN | VP_DCFG_DAC_BL_EN));
 
-	gcfg = readl(par->dc_regs + DC_GENERAL_CFG);
-	gcfg &= ~(DC_GCFG_CMPE | DC_GCFG_DECE);
-	writel(gcfg, par->dc_regs + DC_GENERAL_CFG);
+	gcfg = read_dc(par, DC_GENERAL_CFG);
+	gcfg &= ~(DC_GENERAL_CFG_CMPE | DC_GENERAL_CFG_DECE);
+	write_dc(par, DC_GENERAL_CFG, gcfg);
 
 	/* Turn off the TGEN */
-	val = readl(par->dc_regs + DC_DISPLAY_CFG);
-	val &= ~DC_DCFG_TGEN;
-	writel(val, par->dc_regs + DC_DISPLAY_CFG);
+	val = read_dc(par, DC_DISPLAY_CFG);
+	val &= ~DC_DISPLAY_CFG_TGEN;
+	write_dc(par, DC_DISPLAY_CFG, val);
 
 	/* Wait 1000 usecs to ensure that the TGEN is clear */
 	udelay(1000);
 
 	/* Turn off the FIFO loader */
 
-	gcfg &= ~DC_GCFG_DFLE;
-	writel(gcfg, par->dc_regs + DC_GENERAL_CFG);
+	gcfg &= ~DC_GENERAL_CFG_DFLE;
+	write_dc(par, DC_GENERAL_CFG, gcfg);
 
 	/* Lastly, wait for the GP to go idle */
 
 	do {
-		val = readl(par->gp_regs + GP_BLT_STATUS);
-	} while ((val & GP_BS_BLT_BUSY) || !(val & GP_BS_CB_EMPTY));
+		val = read_gp(par, GP_BLT_STATUS);
+	} while ((val & GP_BLT_STATUS_PB) || !(val & GP_BLT_STATUS_CE));
 }
 
 static void lx_graphics_enable(struct fb_info *info)
@@ -224,80 +274,85 @@ static void lx_graphics_enable(struct fb_info *info)
 	u32 temp, config;
 
 	/* Set the video request register */
-	writel(0, par->df_regs + DF_VIDEO_REQUEST);
+	write_vp(par, VP_VRR, 0);
 
 	/* Set up the polarities */
 
-	config = readl(par->df_regs + DF_DISPLAY_CFG);
+	config = read_vp(par, VP_DCFG);
 
-	config &= ~(DF_DCFG_CRT_SYNC_SKW_MASK | DF_DCFG_PWR_SEQ_DLY_MASK |
-		  DF_DCFG_CRT_HSYNC_POL     | DF_DCFG_CRT_VSYNC_POL);
+	config &= ~(VP_DCFG_CRT_SYNC_SKW | VP_DCFG_PWR_SEQ_DELAY |
+			VP_DCFG_CRT_HSYNC_POL | VP_DCFG_CRT_VSYNC_POL);
 
-	config |= (DF_DCFG_CRT_SYNC_SKW_INIT | DF_DCFG_PWR_SEQ_DLY_INIT  |
-		   DF_DCFG_GV_PAL_BYP);
+	config |= (VP_DCFG_CRT_SYNC_SKW_DEFAULT | VP_DCFG_PWR_SEQ_DELAY_DEFAULT
+			| VP_DCFG_GV_GAM);
 
 	if (info->var.sync & FB_SYNC_HOR_HIGH_ACT)
-		config |= DF_DCFG_CRT_HSYNC_POL;
+		config |= VP_DCFG_CRT_HSYNC_POL;
 
 	if (info->var.sync & FB_SYNC_VERT_HIGH_ACT)
-		config |= DF_DCFG_CRT_VSYNC_POL;
+		config |= VP_DCFG_CRT_VSYNC_POL;
 
 	if (par->output & OUTPUT_PANEL) {
 		u32 msrlo, msrhi;
 
-		writel(DF_DEFAULT_TFT_PMTIM1,
-		       par->df_regs + DF_PANEL_TIM1);
-		writel(DF_DEFAULT_TFT_PMTIM2,
-		       par->df_regs + DF_PANEL_TIM2);
-		writel(DF_DEFAULT_TFT_DITHCTL,
-		       par->df_regs + DF_DITHER_CONTROL);
+		write_fp(par, FP_PT1, 0);
+		write_fp(par, FP_PT2, FP_PT2_SCRC);
+		write_fp(par, FP_DFC, FP_DFC_BC);
 
-		msrlo = DF_DEFAULT_TFT_PAD_SEL_LOW;
-		msrhi = DF_DEFAULT_TFT_PAD_SEL_HIGH;
+		msrlo = MSR_LX_MSR_PADSEL_TFT_SEL_LOW;
+		msrhi = MSR_LX_MSR_PADSEL_TFT_SEL_HIGH;
 
-		wrmsr(MSR_LX_DF_PADSEL, msrlo, msrhi);
+		wrmsr(MSR_LX_MSR_PADSEL, msrlo, msrhi);
 	}
 
 	if (par->output & OUTPUT_CRT) {
-		config |= DF_DCFG_CRT_EN   | DF_DCFG_HSYNC_EN |
-			DF_DCFG_VSYNC_EN | DF_DCFG_DAC_BL_EN;
+		config |= VP_DCFG_CRT_EN | VP_DCFG_HSYNC_EN |
+				VP_DCFG_VSYNC_EN | VP_DCFG_DAC_BL_EN;
 	}
 
-	writel(config, par->df_regs + DF_DISPLAY_CFG);
+	write_vp(par, VP_DCFG, config);
 
 	/* Turn the CRT dacs back on */
 
 	if (par->output & OUTPUT_CRT) {
-		temp = readl(par->df_regs + DF_MISC);
-		temp &= ~(DF_MISC_DAC_PWRDN  | DF_MISC_A_PWRDN);
-		writel(temp, par->df_regs + DF_MISC);
+		temp = read_vp(par, VP_MISC);
+		temp &= ~(VP_MISC_DACPWRDN | VP_MISC_APWRDN);
+		write_vp(par, VP_MISC, temp);
 	}
 
 	/* Turn the panel on (if it isn't already) */
-
-	if (par->output & OUTPUT_PANEL) {
-		temp = readl(par->df_regs + DF_FP_PM);
-
-		if (!(temp & 0x09))
-			writel(temp | DF_FP_PM_P, par->df_regs + DF_FP_PM);
-	}
-
-	temp = readl(par->df_regs + DF_MISC);
-	temp = readl(par->df_regs + DF_DISPLAY_CFG);
+	if (par->output & OUTPUT_PANEL)
+		write_fp(par, FP_PM, read_fp(par, FP_PM) | FP_PM_P);
 }
 
 unsigned int lx_framebuffer_size(void)
 {
 	unsigned int val;
 
+	if (!geode_has_vsa2()) {
+		uint32_t hi, lo;
+
+		/* The number of pages is (PMAX - PMIN)+1 */
+		rdmsr(MSR_GLIU_P2D_RO0, lo, hi);
+
+		/* PMAX */
+		val = ((hi & 0xff) << 12) | ((lo & 0xfff00000) >> 20);
+		/* PMIN */
+		val -= (lo & 0x000fffff);
+		val += 1;
+
+		/* The page size is 4k */
+		return (val << 12);
+	}
+
 	/* The frame buffer size is reported by a VSM in VSA II */
 	/* Virtual Register Class    = 0x02                     */
 	/* VG_MEM_SIZE (1MB units)   = 0x00                     */
 
-	outw(0xFC53, 0xAC1C);
-	outw(0x0200, 0xAC1C);
+	outw(VSA_VR_UNLOCK, VSA_VRC_INDEX);
+	outw(VSA_VR_MEM_SIZE, VSA_VRC_INDEX);
 
-	val = (unsigned int)(inw(0xAC1E)) & 0xFE;
+	val = (unsigned int)(inw(VSA_VRC_DATA)) & 0xFE;
 	return (val << 20);
 }
 
@@ -313,7 +368,7 @@ void lx_set_mode(struct fb_info *info)
 	int vactive, vblankstart, vsyncstart, vsyncend, vblankend, vtotal;
 
 	/* Unlock the DC registers */
-	writel(DC_UNLOCK_CODE, par->dc_regs + DC_UNLOCK);
+	write_dc(par, DC_UNLOCK, DC_UNLOCK_UNLOCK);
 
 	lx_graphics_disable(info);
 
@@ -321,102 +376,104 @@ void lx_set_mode(struct fb_info *info)
 
 	/* Set output mode */
 
-	rdmsrl(MSR_LX_DF_GLCONFIG, msrval);
-	msrval &= ~DF_CONFIG_OUTPUT_MASK;
+	rdmsrl(MSR_LX_GLD_MSR_CONFIG, msrval);
+	msrval &= ~MSR_LX_GLD_MSR_CONFIG_FMT;
 
 	if (par->output & OUTPUT_PANEL) {
-		msrval |= DF_OUTPUT_PANEL;
+		msrval |= MSR_LX_GLD_MSR_CONFIG_FMT_FP;
 
 		if (par->output & OUTPUT_CRT)
-			msrval |= DF_SIMULTANEOUS_CRT_AND_FP;
+			msrval |= MSR_LX_GLD_MSR_CONFIG_FPC;
 		else
-			msrval &= ~DF_SIMULTANEOUS_CRT_AND_FP;
-	} else {
-		msrval |= DF_OUTPUT_CRT;
-	}
+			msrval &= ~MSR_LX_GLD_MSR_CONFIG_FPC;
+	} else
+		msrval |= MSR_LX_GLD_MSR_CONFIG_FMT_CRT;
 
-	wrmsrl(MSR_LX_DF_GLCONFIG, msrval);
+	wrmsrl(MSR_LX_GLD_MSR_CONFIG, msrval);
 
 	/* Clear the various buffers */
 	/* FIXME:  Adjust for panning here */
 
-	writel(0, par->dc_regs + DC_FB_START);
-	writel(0, par->dc_regs + DC_CB_START);
-	writel(0, par->dc_regs + DC_CURSOR_START);
+	write_dc(par, DC_FB_ST_OFFSET, 0);
+	write_dc(par, DC_CB_ST_OFFSET, 0);
+	write_dc(par, DC_CURS_ST_OFFSET, 0);
 
 	/* FIXME: Add support for interlacing */
 	/* FIXME: Add support for scaling */
 
-	val = readl(par->dc_regs + DC_GENLCK_CTRL);
-	val &= ~(DC_GC_ALPHA_FLICK_ENABLE |
-		 DC_GC_FLICKER_FILTER_ENABLE | DC_GC_FLICKER_FILTER_MASK);
+	val = read_dc(par, DC_GENLK_CTL);
+	val &= ~(DC_GENLK_CTL_ALPHA_FLICK_EN | DC_GENLK_CTL_FLICK_EN |
+			DC_GENLK_CTL_FLICK_SEL_MASK);
 
 	/* Default scaling params */
 
-	writel((0x4000 << 16) | 0x4000, par->dc_regs + DC_GFX_SCALE);
-	writel(0, par->dc_regs + DC_IRQ_FILT_CTL);
-	writel(val, par->dc_regs + DC_GENLCK_CTRL);
+	write_dc(par, DC_GFX_SCALE, (0x4000 << 16) | 0x4000);
+	write_dc(par, DC_IRQ_FILT_CTL, 0);
+	write_dc(par, DC_GENLK_CTL, val);
 
 	/* FIXME:  Support compression */
 
 	if (info->fix.line_length > 4096)
-		dv = DC_DV_LINE_SIZE_8192;
+		dv = DC_DV_CTL_DV_LINE_SIZE_8K;
 	else if (info->fix.line_length > 2048)
-		dv = DC_DV_LINE_SIZE_4096;
+		dv = DC_DV_CTL_DV_LINE_SIZE_4K;
 	else if (info->fix.line_length > 1024)
-		dv = DC_DV_LINE_SIZE_2048;
+		dv = DC_DV_CTL_DV_LINE_SIZE_2K;
 	else
-		dv = DC_DV_LINE_SIZE_1024;
+		dv = DC_DV_CTL_DV_LINE_SIZE_1K;
 
 	max = info->fix.line_length * info->var.yres;
 	max = (max + 0x3FF) & 0xFFFFFC00;
 
-	writel(max | DC_DV_TOP_ENABLE, par->dc_regs + DC_DV_TOP);
+	write_dc(par, DC_DV_TOP, max | DC_DV_TOP_DV_TOP_EN);
 
-	val = readl(par->dc_regs + DC_DV_CTL) & ~DC_DV_LINE_SIZE_MASK;
-	writel(val | dv, par->dc_regs + DC_DV_CTL);
+	val = read_dc(par, DC_DV_CTL) & ~DC_DV_CTL_DV_LINE_SIZE;
+	write_dc(par, DC_DV_CTL, val | dv);
 
 	size = info->var.xres * (info->var.bits_per_pixel >> 3);
 
-	writel(info->fix.line_length >> 3, par->dc_regs + DC_GRAPHICS_PITCH);
-	writel((size + 7) >> 3, par->dc_regs + DC_LINE_SIZE);
+	write_dc(par, DC_GFX_PITCH, info->fix.line_length >> 3);
+	write_dc(par, DC_LINE_SIZE, (size + 7) >> 3);
 
 	/* Set default watermark values */
 
-	rdmsrl(MSR_LX_DC_SPARE, msrval);
-
-	msrval &= ~(DC_SPARE_DISABLE_CFIFO_HGO | DC_SPARE_VFIFO_ARB_SELECT |
-		    DC_SPARE_LOAD_WM_LPEN_MASK | DC_SPARE_WM_LPEN_OVRD |
-		    DC_SPARE_DISABLE_INIT_VID_PRI | DC_SPARE_DISABLE_VFIFO_WM);
-	msrval |= DC_SPARE_DISABLE_VFIFO_WM | DC_SPARE_DISABLE_INIT_VID_PRI;
-	wrmsrl(MSR_LX_DC_SPARE, msrval);
-
-	gcfg = DC_GCFG_DFLE;   /* Display fifo enable */
-	gcfg |= 0xB600;         /* Set default priority */
-	gcfg |= DC_GCFG_FDTY;  /* Set the frame dirty mode */
-
-	dcfg  = DC_DCFG_VDEN;  /* Enable video data */
-	dcfg |= DC_DCFG_GDEN;  /* Enable graphics */
-	dcfg |= DC_DCFG_TGEN;  /* Turn on the timing generator */
-	dcfg |= DC_DCFG_TRUP;  /* Update timings immediately */
-	dcfg |= DC_DCFG_PALB;  /* Palette bypass in > 8 bpp modes */
-	dcfg |= DC_DCFG_VISL;
-	dcfg |= DC_DCFG_DCEN;  /* Always center the display */
+	rdmsrl(MSR_LX_SPARE_MSR, msrval);
+
+	msrval &= ~(MSR_LX_SPARE_MSR_DIS_CFIFO_HGO
+			| MSR_LX_SPARE_MSR_VFIFO_ARB_SEL
+			| MSR_LX_SPARE_MSR_LOAD_WM_LPEN_M
+			| MSR_LX_SPARE_MSR_WM_LPEN_OVRD);
+	msrval |= MSR_LX_SPARE_MSR_DIS_VIFO_WM |
+			MSR_LX_SPARE_MSR_DIS_INIT_V_PRI;
+	wrmsrl(MSR_LX_SPARE_MSR, msrval);
+
+	gcfg = DC_GENERAL_CFG_DFLE;   /* Display fifo enable */
+	gcfg |= (0x6 << DC_GENERAL_CFG_DFHPSL_SHIFT) | /* default priority */
+			(0xb << DC_GENERAL_CFG_DFHPEL_SHIFT);
+	gcfg |= DC_GENERAL_CFG_FDTY;  /* Set the frame dirty mode */
+
+	dcfg  = DC_DISPLAY_CFG_VDEN;  /* Enable video data */
+	dcfg |= DC_DISPLAY_CFG_GDEN;  /* Enable graphics */
+	dcfg |= DC_DISPLAY_CFG_TGEN;  /* Turn on the timing generator */
+	dcfg |= DC_DISPLAY_CFG_TRUP;  /* Update timings immediately */
+	dcfg |= DC_DISPLAY_CFG_PALB;  /* Palette bypass in > 8 bpp modes */
+	dcfg |= DC_DISPLAY_CFG_VISL;
+	dcfg |= DC_DISPLAY_CFG_DCEN;  /* Always center the display */
 
 	/* Set the current BPP mode */
 
 	switch (info->var.bits_per_pixel) {
 	case 8:
-		dcfg |= DC_DCFG_DISP_MODE_8BPP;
+		dcfg |= DC_DISPLAY_CFG_DISP_MODE_8BPP;
 		break;
 
 	case 16:
-		dcfg |= DC_DCFG_DISP_MODE_16BPP | DC_DCFG_16BPP;
+		dcfg |= DC_DISPLAY_CFG_DISP_MODE_16BPP;
 		break;
 
 	case 32:
 	case 24:
-		dcfg |= DC_DCFG_DISP_MODE_24BPP;
+		dcfg |= DC_DISPLAY_CFG_DISP_MODE_24BPP;
 		break;
 	}
 
@@ -436,35 +493,31 @@ void lx_set_mode(struct fb_info *info)
 	vblankend = vsyncend + info->var.upper_margin;
 	vtotal = vblankend;
 
-	writel((hactive - 1) | ((htotal - 1) << 16),
-	       par->dc_regs + DC_H_ACTIVE_TIMING);
-	writel((hblankstart - 1) | ((hblankend - 1) << 16),
-	       par->dc_regs + DC_H_BLANK_TIMING);
-	writel((hsyncstart - 1) | ((hsyncend - 1) << 16),
-	       par->dc_regs + DC_H_SYNC_TIMING);
-
-	writel((vactive - 1) | ((vtotal - 1) << 16),
-	       par->dc_regs + DC_V_ACTIVE_TIMING);
+	write_dc(par, DC_H_ACTIVE_TIMING, (hactive - 1) | ((htotal - 1) << 16));
+	write_dc(par, DC_H_BLANK_TIMING,
+			(hblankstart - 1) | ((hblankend - 1) << 16));
+	write_dc(par, DC_H_SYNC_TIMING,
+			(hsyncstart - 1) | ((hsyncend - 1) << 16));
 
-	writel((vblankstart - 1) | ((vblankend - 1) << 16),
-	       par->dc_regs + DC_V_BLANK_TIMING);
+	write_dc(par, DC_V_ACTIVE_TIMING, (vactive - 1) | ((vtotal - 1) << 16));
+	write_dc(par, DC_V_BLANK_TIMING,
+			(vblankstart - 1) | ((vblankend - 1) << 16));
+	write_dc(par, DC_V_SYNC_TIMING,
+			(vsyncstart - 1) | ((vsyncend - 1) << 16));
 
-	writel((vsyncstart - 1)  | ((vsyncend - 1) << 16),
-	       par->dc_regs + DC_V_SYNC_TIMING);
-
-	writel( (info->var.xres - 1) << 16 | (info->var.yres - 1),
-		par->dc_regs + DC_FB_ACTIVE);
+	write_dc(par, DC_FB_ACTIVE,
+			(info->var.xres - 1) << 16 | (info->var.yres - 1));
 
 	/* And re-enable the graphics output */
 	lx_graphics_enable(info);
 
 	/* Write the two main configuration registers */
-	writel(dcfg, par->dc_regs + DC_DISPLAY_CFG);
-	writel(0, par->dc_regs + DC_ARB_CFG);
-	writel(gcfg, par->dc_regs + DC_GENERAL_CFG);
+	write_dc(par, DC_DISPLAY_CFG, dcfg);
+	write_dc(par, DC_ARB_CFG, 0);
+	write_dc(par, DC_GENERAL_CFG, gcfg);
 
 	/* Lock the DC registers */
-	writel(0, par->dc_regs + DC_UNLOCK);
+	write_dc(par, DC_UNLOCK, DC_UNLOCK_LOCK);
 }
 
 void lx_set_palette_reg(struct fb_info *info, unsigned regno,
@@ -479,58 +532,310 @@ void lx_set_palette_reg(struct fb_info *info, unsigned regno,
 	val |= (green)      & 0x00ff00;
 	val |= (blue  >> 8) & 0x0000ff;
 
-	writel(regno, par->dc_regs + DC_PAL_ADDRESS);
-	writel(val, par->dc_regs + DC_PAL_DATA);
+	write_dc(par, DC_PAL_ADDRESS, regno);
+	write_dc(par, DC_PAL_DATA, val);
 }
 
 int lx_blank_display(struct fb_info *info, int blank_mode)
 {
 	struct lxfb_par *par = info->par;
 	u32 dcfg, fp_pm;
-	int blank, hsync, vsync;
+	int blank, hsync, vsync, crt;
 
 	/* CRT power saving modes. */
 	switch (blank_mode) {
 	case FB_BLANK_UNBLANK:
-		blank = 0; hsync = 1; vsync = 1;
+		blank = 0; hsync = 1; vsync = 1; crt = 1;
 		break;
 	case FB_BLANK_NORMAL:
-		blank = 1; hsync = 1; vsync = 1;
+		blank = 1; hsync = 1; vsync = 1; crt = 1;
 		break;
 	case FB_BLANK_VSYNC_SUSPEND:
-		blank = 1; hsync = 1; vsync = 0;
+		blank = 1; hsync = 1; vsync = 0; crt = 1;
 		break;
 	case FB_BLANK_HSYNC_SUSPEND:
-		blank = 1; hsync = 0; vsync = 1;
+		blank = 1; hsync = 0; vsync = 1; crt = 1;
 		break;
 	case FB_BLANK_POWERDOWN:
-		blank = 1; hsync = 0; vsync = 0;
+		blank = 1; hsync = 0; vsync = 0; crt = 0;
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	dcfg = readl(par->df_regs + DF_DISPLAY_CFG);
-	dcfg &= ~(DF_DCFG_DAC_BL_EN
-		  | DF_DCFG_HSYNC_EN | DF_DCFG_VSYNC_EN);
+	dcfg = read_vp(par, VP_DCFG);
+	dcfg &= ~(VP_DCFG_DAC_BL_EN | VP_DCFG_HSYNC_EN | VP_DCFG_VSYNC_EN |
+			VP_DCFG_CRT_EN);
 	if (!blank)
-		dcfg |= DF_DCFG_DAC_BL_EN;
+		dcfg |= VP_DCFG_DAC_BL_EN;
 	if (hsync)
-		dcfg |= DF_DCFG_HSYNC_EN;
+		dcfg |= VP_DCFG_HSYNC_EN;
 	if (vsync)
-		dcfg |= DF_DCFG_VSYNC_EN;
-	writel(dcfg, par->df_regs + DF_DISPLAY_CFG);
+		dcfg |= VP_DCFG_VSYNC_EN;
+	if (crt)
+		dcfg |= VP_DCFG_CRT_EN;
+	write_vp(par, VP_DCFG, dcfg);
 
 	/* Power on/off flat panel */
 
 	if (par->output & OUTPUT_PANEL) {
-		fp_pm = readl(par->df_regs + DF_FP_PM);
+		fp_pm = read_fp(par, FP_PM);
 		if (blank_mode == FB_BLANK_POWERDOWN)
-			fp_pm &= ~DF_FP_PM_P;
+			fp_pm &= ~FP_PM_P;
 		else
-			fp_pm |= DF_FP_PM_P;
-		writel(fp_pm, par->df_regs + DF_FP_PM);
+			fp_pm |= FP_PM_P;
+		write_fp(par, FP_PM, fp_pm);
 	}
 
 	return 0;
 }
+
+#ifdef CONFIG_PM
+
+static void lx_save_regs(struct lxfb_par *par)
+{
+	uint32_t filt;
+	int i;
+
+	/* wait for the BLT engine to stop being busy */
+	do {
+		i = read_gp(par, GP_BLT_STATUS);
+	} while ((i & GP_BLT_STATUS_PB) || !(i & GP_BLT_STATUS_CE));
+
+	/* save MSRs */
+	rdmsrl(MSR_LX_MSR_PADSEL, par->msr.padsel);
+	rdmsrl(MSR_GLCP_DOTPLL, par->msr.dotpll);
+	rdmsrl(MSR_LX_GLD_MSR_CONFIG, par->msr.dfglcfg);
+	rdmsrl(MSR_LX_SPARE_MSR, par->msr.dcspare);
+
+	write_dc(par, DC_UNLOCK, DC_UNLOCK_UNLOCK);
+
+	/* save registers */
+	memcpy(par->gp, par->gp_regs, sizeof(par->gp));
+	memcpy(par->dc, par->dc_regs, sizeof(par->dc));
+	memcpy(par->vp, par->vp_regs, sizeof(par->vp));
+	memcpy(par->fp, par->vp_regs + VP_FP_START, sizeof(par->fp));
+
+	/* save the palette */
+	write_dc(par, DC_PAL_ADDRESS, 0);
+	for (i = 0; i < ARRAY_SIZE(par->pal); i++)
+		par->pal[i] = read_dc(par, DC_PAL_DATA);
+
+	/* save the horizontal filter coefficients */
+	filt = par->dc[DC_IRQ_FILT_CTL] | DC_IRQ_FILT_CTL_H_FILT_SEL;
+	for (i = 0; i < ARRAY_SIZE(par->hcoeff); i += 2) {
+		write_dc(par, DC_IRQ_FILT_CTL, (filt & 0xffffff00) | i);
+		par->hcoeff[i] = read_dc(par, DC_FILT_COEFF1);
+		par->hcoeff[i + 1] = read_dc(par, DC_FILT_COEFF2);
+	}
+
+	/* save the vertical filter coefficients */
+	filt &= ~DC_IRQ_FILT_CTL_H_FILT_SEL;
+	for (i = 0; i < ARRAY_SIZE(par->vcoeff); i++) {
+		write_dc(par, DC_IRQ_FILT_CTL, (filt & 0xffffff00) | i);
+		par->vcoeff[i] = read_dc(par, DC_FILT_COEFF1);
+	}
+
+	/* save video coeff ram */
+	memcpy(par->vp_coeff, par->vp_regs + VP_VCR, sizeof(par->vp_coeff));
+}
+
+static void lx_restore_gfx_proc(struct lxfb_par *par)
+{
+	int i;
+
+	/* a bunch of registers require GP_RASTER_MODE to be set first */
+	write_gp(par, GP_RASTER_MODE, par->gp[GP_RASTER_MODE]);
+
+	for (i = 0; i < ARRAY_SIZE(par->gp); i++) {
+		switch (i) {
+		case GP_RASTER_MODE:
+		case GP_VECTOR_MODE:
+		case GP_BLT_MODE:
+		case GP_BLT_STATUS:
+		case GP_HST_SRC:
+			/* FIXME: restore LUT data */
+		case GP_LUT_INDEX:
+		case GP_LUT_DATA:
+			/* don't restore these registers */
+			break;
+
+		default:
+			write_gp(par, i, par->gp[i]);
+		}
+	}
+}
+
+static void lx_restore_display_ctlr(struct lxfb_par *par)
+{
+	uint32_t filt;
+	int i;
+
+	wrmsrl(MSR_LX_SPARE_MSR, par->msr.dcspare);
+
+	for (i = 0; i < ARRAY_SIZE(par->dc); i++) {
+		switch (i) {
+		case DC_UNLOCK:
+			/* unlock the DC; runs first */
+			write_dc(par, DC_UNLOCK, DC_UNLOCK_UNLOCK);
+			break;
+
+		case DC_GENERAL_CFG:
+		case DC_DISPLAY_CFG:
+			/* disable all while restoring */
+			write_dc(par, i, 0);
+			break;
+
+		case DC_DV_CTL:
+			/* set all ram to dirty */
+			write_dc(par, i, par->dc[i] | DC_DV_CTL_CLEAR_DV_RAM);
+
+		case DC_RSVD_1:
+		case DC_RSVD_2:
+		case DC_RSVD_3:
+		case DC_LINE_CNT:
+		case DC_PAL_ADDRESS:
+		case DC_PAL_DATA:
+		case DC_DFIFO_DIAG:
+		case DC_CFIFO_DIAG:
+		case DC_FILT_COEFF1:
+		case DC_FILT_COEFF2:
+		case DC_RSVD_4:
+		case DC_RSVD_5:
+			/* don't restore these registers */
+			break;
+
+		default:
+			write_dc(par, i, par->dc[i]);
+		}
+	}
+
+	/* restore the palette */
+	write_dc(par, DC_PAL_ADDRESS, 0);
+	for (i = 0; i < ARRAY_SIZE(par->pal); i++)
+		write_dc(par, DC_PAL_DATA, par->pal[i]);
+
+	/* restore the horizontal filter coefficients */
+	filt = par->dc[DC_IRQ_FILT_CTL] | DC_IRQ_FILT_CTL_H_FILT_SEL;
+	for (i = 0; i < ARRAY_SIZE(par->hcoeff); i += 2) {
+		write_dc(par, DC_IRQ_FILT_CTL, (filt & 0xffffff00) | i);
+		write_dc(par, DC_FILT_COEFF1, par->hcoeff[i]);
+		write_dc(par, DC_FILT_COEFF2, par->hcoeff[i + 1]);
+	}
+
+	/* restore the vertical filter coefficients */
+	filt &= ~DC_IRQ_FILT_CTL_H_FILT_SEL;
+	for (i = 0; i < ARRAY_SIZE(par->vcoeff); i++) {
+		write_dc(par, DC_IRQ_FILT_CTL, (filt & 0xffffff00) | i);
+		write_dc(par, DC_FILT_COEFF1, par->vcoeff[i]);
+	}
+}
+
+static void lx_restore_video_proc(struct lxfb_par *par)
+{
+	int i;
+
+	wrmsrl(MSR_LX_GLD_MSR_CONFIG, par->msr.dfglcfg);
+	wrmsrl(MSR_LX_MSR_PADSEL, par->msr.padsel);
+
+	for (i = 0; i < ARRAY_SIZE(par->vp); i++) {
+		switch (i) {
+		case VP_VCFG:
+		case VP_DCFG:
+		case VP_PAR:
+		case VP_PDR:
+		case VP_CCS:
+		case VP_RSVD_0:
+		/* case VP_VDC: */ /* why should this not be restored? */
+		case VP_RSVD_1:
+		case VP_CRC32:
+			/* don't restore these registers */
+			break;
+
+		default:
+			write_vp(par, i, par->vp[i]);
+		}
+	}
+
+	/* restore video coeff ram */
+	memcpy(par->vp_regs + VP_VCR, par->vp_coeff, sizeof(par->vp_coeff));
+}
+
+static void lx_restore_regs(struct lxfb_par *par)
+{
+	int i;
+
+	lx_set_dotpll((u32) (par->msr.dotpll >> 32));
+	lx_restore_gfx_proc(par);
+	lx_restore_display_ctlr(par);
+	lx_restore_video_proc(par);
+
+	/* Flat Panel */
+	for (i = 0; i < ARRAY_SIZE(par->fp); i++) {
+		switch (i) {
+		case FP_PM:
+		case FP_RSVD_0:
+		case FP_RSVD_1:
+		case FP_RSVD_2:
+		case FP_RSVD_3:
+		case FP_RSVD_4:
+			/* don't restore these registers */
+			break;
+
+		default:
+			write_fp(par, i, par->fp[i]);
+		}
+	}
+
+	/* control the panel */
+	if (par->fp[FP_PM] & FP_PM_P) {
+		/* power on the panel if not already power{ed,ing} on */
+		if (!(read_fp(par, FP_PM) &
+				(FP_PM_PANEL_ON|FP_PM_PANEL_PWR_UP)))
+			write_fp(par, FP_PM, par->fp[FP_PM]);
+	} else {
+		/* power down the panel if not already power{ed,ing} down */
+		if (!(read_fp(par, FP_PM) &
+				(FP_PM_PANEL_OFF|FP_PM_PANEL_PWR_DOWN)))
+			write_fp(par, FP_PM, par->fp[FP_PM]);
+	}
+
+	/* turn everything on */
+	write_vp(par, VP_VCFG, par->vp[VP_VCFG]);
+	write_vp(par, VP_DCFG, par->vp[VP_DCFG]);
+	write_dc(par, DC_DISPLAY_CFG, par->dc[DC_DISPLAY_CFG]);
+	/* do this last; it will enable the FIFO load */
+	write_dc(par, DC_GENERAL_CFG, par->dc[DC_GENERAL_CFG]);
+
+	/* lock the door behind us */
+	write_dc(par, DC_UNLOCK, DC_UNLOCK_LOCK);
+}
+
+int lx_powerdown(struct fb_info *info)
+{
+	struct lxfb_par *par = info->par;
+
+	if (par->powered_down)
+		return 0;
+
+	lx_save_regs(par);
+	lx_graphics_disable(info);
+
+	par->powered_down = 1;
+	return 0;
+}
+
+int lx_powerup(struct fb_info *info)
+{
+	struct lxfb_par *par = info->par;
+
+	if (!par->powered_down)
+		return 0;
+
+	lx_restore_regs(par);
+
+	par->powered_down = 0;
+	return 0;
+}
+
+#endif
diff --git a/trunk/drivers/video/geode/suspend_gx.c b/trunk/drivers/video/geode/suspend_gx.c
new file mode 100644
index 000000000000..9aff32ef8bb6
--- /dev/null
+++ b/trunk/drivers/video/geode/suspend_gx.c
@@ -0,0 +1,267 @@
+/*
+ *   Copyright (C) 2007 Advanced Micro Devices, Inc.
+ *   Copyright (C) 2008 Andres Salomon <dilinger@debian.org>
+ *
+ *   This program is free software; you can redistribute it and/or modify it
+ *   under the terms of the GNU General Public License as published by the
+ *   Free Software Foundation; either version 2 of the License, or (at your
+ *   option) any later version.
+ */
+#include <linux/fb.h>
+#include <asm/io.h>
+#include <asm/msr.h>
+#include <asm/geode.h>
+#include <asm/delay.h>
+
+#include "gxfb.h"
+
+#ifdef CONFIG_PM
+
+static void gx_save_regs(struct gxfb_par *par)
+{
+	int i;
+
+	/* wait for the BLT engine to stop being busy */
+	do {
+		i = read_gp(par, GP_BLT_STATUS);
+	} while (i & (GP_BLT_STATUS_BLT_PENDING | GP_BLT_STATUS_BLT_BUSY));
+
+	/* save MSRs */
+	rdmsrl(MSR_GX_MSR_PADSEL, par->msr.padsel);
+	rdmsrl(MSR_GLCP_DOTPLL, par->msr.dotpll);
+
+	write_dc(par, DC_UNLOCK, DC_UNLOCK_UNLOCK);
+
+	/* save registers */
+	memcpy(par->gp, par->gp_regs, sizeof(par->gp));
+	memcpy(par->dc, par->dc_regs, sizeof(par->dc));
+	memcpy(par->vp, par->vid_regs, sizeof(par->vp));
+	memcpy(par->fp, par->vid_regs + VP_FP_START, sizeof(par->fp));
+
+	/* save the palette */
+	write_dc(par, DC_PAL_ADDRESS, 0);
+	for (i = 0; i < ARRAY_SIZE(par->pal); i++)
+		par->pal[i] = read_dc(par, DC_PAL_DATA);
+}
+
+static void gx_set_dotpll(uint32_t dotpll_hi)
+{
+	uint32_t dotpll_lo;
+	int i;
+
+	rdmsrl(MSR_GLCP_DOTPLL, dotpll_lo);
+	dotpll_lo |= MSR_GLCP_DOTPLL_DOTRESET;
+	dotpll_lo &= ~MSR_GLCP_DOTPLL_BYPASS;
+	wrmsr(MSR_GLCP_DOTPLL, dotpll_lo, dotpll_hi);
+
+	/* wait for the PLL to lock */
+	for (i = 0; i < 200; i++) {
+		rdmsrl(MSR_GLCP_DOTPLL, dotpll_lo);
+		if (dotpll_lo & MSR_GLCP_DOTPLL_LOCK)
+			break;
+		udelay(1);
+	}
+
+	/* PLL set, unlock */
+	dotpll_lo &= ~MSR_GLCP_DOTPLL_DOTRESET;
+	wrmsr(MSR_GLCP_DOTPLL, dotpll_lo, dotpll_hi);
+}
+
+static void gx_restore_gfx_proc(struct gxfb_par *par)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(par->gp); i++) {
+		switch (i) {
+		case GP_VECTOR_MODE:
+		case GP_BLT_MODE:
+		case GP_BLT_STATUS:
+		case GP_HST_SRC:
+			/* don't restore these registers */
+			break;
+		default:
+			write_gp(par, i, par->gp[i]);
+		}
+	}
+}
+
+static void gx_restore_display_ctlr(struct gxfb_par *par)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(par->dc); i++) {
+		switch (i) {
+		case DC_UNLOCK:
+			/* unlock the DC; runs first */
+			write_dc(par, DC_UNLOCK, DC_UNLOCK_UNLOCK);
+			break;
+
+		case DC_GENERAL_CFG:
+			/* write without the enables */
+			write_dc(par, i, par->dc[i] & ~(DC_GENERAL_CFG_VIDE |
+					DC_GENERAL_CFG_ICNE |
+					DC_GENERAL_CFG_CURE |
+					DC_GENERAL_CFG_DFLE));
+			break;
+
+		case DC_DISPLAY_CFG:
+			/* write without the enables */
+			write_dc(par, i, par->dc[i] & ~(DC_DISPLAY_CFG_VDEN |
+					DC_DISPLAY_CFG_GDEN |
+					DC_DISPLAY_CFG_TGEN));
+			break;
+
+		case DC_RSVD_0:
+		case DC_RSVD_1:
+		case DC_RSVD_2:
+		case DC_RSVD_3:
+		case DC_RSVD_4:
+		case DC_LINE_CNT:
+		case DC_PAL_ADDRESS:
+		case DC_PAL_DATA:
+		case DC_DFIFO_DIAG:
+		case DC_CFIFO_DIAG:
+		case DC_RSVD_5:
+			/* don't restore these registers */
+			break;
+		default:
+			write_dc(par, i, par->dc[i]);
+		}
+	}
+
+	/* restore the palette */
+	write_dc(par, DC_PAL_ADDRESS, 0);
+	for (i = 0; i < ARRAY_SIZE(par->pal); i++)
+		write_dc(par, DC_PAL_DATA, par->pal[i]);
+}
+
+static void gx_restore_video_proc(struct gxfb_par *par)
+{
+	int i;
+
+	wrmsrl(MSR_GX_MSR_PADSEL, par->msr.padsel);
+
+	for (i = 0; i < ARRAY_SIZE(par->vp); i++) {
+		switch (i) {
+		case VP_VCFG:
+			/* don't enable video yet */
+			write_vp(par, i, par->vp[i] & ~VP_VCFG_VID_EN);
+			break;
+
+		case VP_DCFG:
+			/* don't enable CRT yet */
+			write_vp(par, i, par->vp[i] &
+					~(VP_DCFG_DAC_BL_EN | VP_DCFG_VSYNC_EN |
+					VP_DCFG_HSYNC_EN | VP_DCFG_CRT_EN));
+			break;
+
+		case VP_GAR:
+		case VP_GDR:
+		case VP_RSVD_0:
+		case VP_RSVD_1:
+		case VP_RSVD_2:
+		case VP_RSVD_3:
+		case VP_CRC32:
+		case VP_AWT:
+		case VP_VTM:
+			/* don't restore these registers */
+			break;
+		default:
+			write_vp(par, i, par->vp[i]);
+		}
+	}
+}
+
+static void gx_restore_regs(struct gxfb_par *par)
+{
+	int i;
+
+	gx_set_dotpll((uint32_t) (par->msr.dotpll >> 32));
+	gx_restore_gfx_proc(par);
+	gx_restore_display_ctlr(par);
+	gx_restore_video_proc(par);
+
+	/* Flat Panel */
+	for (i = 0; i < ARRAY_SIZE(par->fp); i++) {
+		if (i != FP_PM && i != FP_RSVD_0)
+			write_fp(par, i, par->fp[i]);
+	}
+}
+
+static void gx_disable_graphics(struct gxfb_par *par)
+{
+	/* shut down the engine */
+	write_vp(par, VP_VCFG, par->vp[VP_VCFG] & ~VP_VCFG_VID_EN);
+	write_vp(par, VP_DCFG, par->vp[VP_DCFG] & ~(VP_DCFG_DAC_BL_EN |
+			VP_DCFG_VSYNC_EN | VP_DCFG_HSYNC_EN | VP_DCFG_CRT_EN));
+
+	/* turn off the flat panel */
+	write_fp(par, FP_PM, par->fp[FP_PM] & ~FP_PM_P);
+
+
+	/* turn off display */
+	write_dc(par, DC_UNLOCK, DC_UNLOCK_UNLOCK);
+	write_dc(par, DC_GENERAL_CFG, par->dc[DC_GENERAL_CFG] &
+			~(DC_GENERAL_CFG_VIDE | DC_GENERAL_CFG_ICNE |
+			DC_GENERAL_CFG_CURE | DC_GENERAL_CFG_DFLE));
+	write_dc(par, DC_DISPLAY_CFG, par->dc[DC_DISPLAY_CFG] &
+			~(DC_DISPLAY_CFG_VDEN | DC_DISPLAY_CFG_GDEN |
+			DC_DISPLAY_CFG_TGEN));
+	write_dc(par, DC_UNLOCK, DC_UNLOCK_LOCK);
+}
+
+static void gx_enable_graphics(struct gxfb_par *par)
+{
+	uint32_t fp;
+
+	fp = read_fp(par, FP_PM);
+	if (par->fp[FP_PM] & FP_PM_P) {
+		/* power on the panel if not already power{ed,ing} on */
+		if (!(fp & (FP_PM_PANEL_ON|FP_PM_PANEL_PWR_UP)))
+			write_fp(par, FP_PM, par->fp[FP_PM]);
+	} else {
+		/* power down the panel if not already power{ed,ing} down */
+		if (!(fp & (FP_PM_PANEL_OFF|FP_PM_PANEL_PWR_DOWN)))
+			write_fp(par, FP_PM, par->fp[FP_PM]);
+	}
+
+	/* turn everything on */
+	write_vp(par, VP_VCFG, par->vp[VP_VCFG]);
+	write_vp(par, VP_DCFG, par->vp[VP_DCFG]);
+	write_dc(par, DC_DISPLAY_CFG, par->dc[DC_DISPLAY_CFG]);
+	/* do this last; it will enable the FIFO load */
+	write_dc(par, DC_GENERAL_CFG, par->dc[DC_GENERAL_CFG]);
+
+	/* lock the door behind us */
+	write_dc(par, DC_UNLOCK, DC_UNLOCK_LOCK);
+}
+
+int gx_powerdown(struct fb_info *info)
+{
+	struct gxfb_par *par = info->par;
+
+	if (par->powered_down)
+		return 0;
+
+	gx_save_regs(par);
+	gx_disable_graphics(par);
+
+	par->powered_down = 1;
+	return 0;
+}
+
+int gx_powerup(struct fb_info *info)
+{
+	struct gxfb_par *par = info->par;
+
+	if (!par->powered_down)
+		return 0;
+
+	gx_restore_regs(par);
+	gx_enable_graphics(par);
+
+	par->powered_down  = 0;
+	return 0;
+}
+
+#endif
diff --git a/trunk/drivers/video/geode/video_gx.c b/trunk/drivers/video/geode/video_gx.c
index febf09c63492..b8d52a8360db 100644
--- a/trunk/drivers/video/geode/video_gx.c
+++ b/trunk/drivers/video/geode/video_gx.c
@@ -16,9 +16,9 @@
 #include <asm/io.h>
 #include <asm/delay.h>
 #include <asm/msr.h>
+#include <asm/geode.h>
 
-#include "geodefb.h"
-#include "video_gx.h"
+#include "gxfb.h"
 
 
 /*
@@ -117,7 +117,7 @@ static const struct gx_pll_entry gx_pll_table_14MHz[] = {
 	{  4357, 0, 0x0000057D },	/* 229.5000 */
 };
 
-static void gx_set_dclk_frequency(struct fb_info *info)
+void gx_set_dclk_frequency(struct fb_info *info)
 {
 	const struct gx_pll_entry *pll_table;
 	int pll_table_len;
@@ -178,110 +178,116 @@ static void gx_set_dclk_frequency(struct fb_info *info)
 static void
 gx_configure_tft(struct fb_info *info)
 {
-	struct geodefb_par *par = info->par;
+	struct gxfb_par *par = info->par;
 	unsigned long val;
 	unsigned long fp;
 
 	/* Set up the DF pad select MSR */
 
-	rdmsrl(GX_VP_MSR_PAD_SELECT, val);
-	val &= ~GX_VP_PAD_SELECT_MASK;
-	val |= GX_VP_PAD_SELECT_TFT;
-	wrmsrl(GX_VP_MSR_PAD_SELECT, val);
+	rdmsrl(MSR_GX_MSR_PADSEL, val);
+	val &= ~MSR_GX_MSR_PADSEL_MASK;
+	val |= MSR_GX_MSR_PADSEL_TFT;
+	wrmsrl(MSR_GX_MSR_PADSEL, val);
 
 	/* Turn off the panel */
 
-	fp = readl(par->vid_regs + GX_FP_PM);
-	fp &= ~GX_FP_PM_P;
-	writel(fp, par->vid_regs + GX_FP_PM);
+	fp = read_fp(par, FP_PM);
+	fp &= ~FP_PM_P;
+	write_fp(par, FP_PM, fp);
 
 	/* Set timing 1 */
 
-	fp = readl(par->vid_regs + GX_FP_PT1);
-	fp &= GX_FP_PT1_VSIZE_MASK;
-	fp |= info->var.yres << GX_FP_PT1_VSIZE_SHIFT;
-	writel(fp, par->vid_regs + GX_FP_PT1);
+	fp = read_fp(par, FP_PT1);
+	fp &= FP_PT1_VSIZE_MASK;
+	fp |= info->var.yres << FP_PT1_VSIZE_SHIFT;
+	write_fp(par, FP_PT1, fp);
 
 	/* Timing 2 */
 	/* Set bits that are always on for TFT */
 
 	fp = 0x0F100000;
 
-	/* Add sync polarity */
+	/* Configure sync polarity */
 
 	if (!(info->var.sync & FB_SYNC_VERT_HIGH_ACT))
-		fp |= GX_FP_PT2_VSP;
+		fp |= FP_PT2_VSP;
 
 	if (!(info->var.sync & FB_SYNC_HOR_HIGH_ACT))
-		fp |= GX_FP_PT2_HSP;
+		fp |= FP_PT2_HSP;
 
-	writel(fp, par->vid_regs + GX_FP_PT2);
+	write_fp(par, FP_PT2, fp);
 
 	/*  Set the dither control */
-	writel(0x70, par->vid_regs + GX_FP_DFC);
+	write_fp(par, FP_DFC, FP_DFC_NFI);
 
 	/* Enable the FP data and power (in case the BIOS didn't) */
 
-	fp = readl(par->vid_regs + GX_DCFG);
-	fp |= GX_DCFG_FP_PWR_EN | GX_DCFG_FP_DATA_EN;
-	writel(fp, par->vid_regs + GX_DCFG);
+	fp = read_vp(par, VP_DCFG);
+	fp |= VP_DCFG_FP_PWR_EN | VP_DCFG_FP_DATA_EN;
+	write_vp(par, VP_DCFG, fp);
 
 	/* Unblank the panel */
 
-	fp = readl(par->vid_regs + GX_FP_PM);
-	fp |= GX_FP_PM_P;
-	writel(fp, par->vid_regs + GX_FP_PM);
+	fp = read_fp(par, FP_PM);
+	fp |= FP_PM_P;
+	write_fp(par, FP_PM, fp);
 }
 
-static void gx_configure_display(struct fb_info *info)
+void gx_configure_display(struct fb_info *info)
 {
-	struct geodefb_par *par = info->par;
+	struct gxfb_par *par = info->par;
 	u32 dcfg, misc;
 
-	/* Set up the MISC register */
-
-	misc = readl(par->vid_regs + GX_MISC);
-
-	/* Power up the DAC */
-	misc &= ~(GX_MISC_A_PWRDN | GX_MISC_DAC_PWRDN);
-
-	/* Disable gamma correction */
-	misc |= GX_MISC_GAM_EN;
-
-	writel(misc, par->vid_regs + GX_MISC);
-
 	/* Write the display configuration */
-	dcfg = readl(par->vid_regs + GX_DCFG);
+	dcfg = read_vp(par, VP_DCFG);
 
 	/* Disable hsync and vsync */
-	dcfg &= ~(GX_DCFG_VSYNC_EN | GX_DCFG_HSYNC_EN);
-	writel(dcfg, par->vid_regs + GX_DCFG);
+	dcfg &= ~(VP_DCFG_VSYNC_EN | VP_DCFG_HSYNC_EN);
+	write_vp(par, VP_DCFG, dcfg);
 
 	/* Clear bits from existing mode. */
-	dcfg &= ~(GX_DCFG_CRT_SYNC_SKW_MASK
-		  | GX_DCFG_CRT_HSYNC_POL   | GX_DCFG_CRT_VSYNC_POL
-		  | GX_DCFG_VSYNC_EN        | GX_DCFG_HSYNC_EN);
+	dcfg &= ~(VP_DCFG_CRT_SYNC_SKW
+		  | VP_DCFG_CRT_HSYNC_POL   | VP_DCFG_CRT_VSYNC_POL
+		  | VP_DCFG_VSYNC_EN        | VP_DCFG_HSYNC_EN);
 
 	/* Set default sync skew.  */
-	dcfg |= GX_DCFG_CRT_SYNC_SKW_DFLT;
+	dcfg |= VP_DCFG_CRT_SYNC_SKW_DEFAULT;
 
 	/* Enable hsync and vsync. */
-	dcfg |= GX_DCFG_HSYNC_EN | GX_DCFG_VSYNC_EN;
+	dcfg |= VP_DCFG_HSYNC_EN | VP_DCFG_VSYNC_EN;
 
-	/* Sync polarities. */
-	if (info->var.sync & FB_SYNC_HOR_HIGH_ACT)
-		dcfg |= GX_DCFG_CRT_HSYNC_POL;
-	if (info->var.sync & FB_SYNC_VERT_HIGH_ACT)
-		dcfg |= GX_DCFG_CRT_VSYNC_POL;
+	misc = read_vp(par, VP_MISC);
+
+	/* Disable gamma correction */
+	misc |= VP_MISC_GAM_EN;
+
+	if (par->enable_crt) {
+
+		/* Power up the CRT DACs */
+		misc &= ~(VP_MISC_APWRDN | VP_MISC_DACPWRDN);
+		write_vp(par, VP_MISC, misc);
+
+		/* Only change the sync polarities if we are running
+		 * in CRT mode.  The FP polarities will be handled in
+		 * gxfb_configure_tft */
+		if (!(info->var.sync & FB_SYNC_HOR_HIGH_ACT))
+			dcfg |= VP_DCFG_CRT_HSYNC_POL;
+		if (!(info->var.sync & FB_SYNC_VERT_HIGH_ACT))
+			dcfg |= VP_DCFG_CRT_VSYNC_POL;
+	} else {
+		/* Power down the CRT DACs if in FP mode */
+		misc |= (VP_MISC_APWRDN | VP_MISC_DACPWRDN);
+		write_vp(par, VP_MISC, misc);
+	}
 
 	/* Enable the display logic */
 	/* Set up the DACS to blank normally */
 
-	dcfg |= GX_DCFG_CRT_EN | GX_DCFG_DAC_BL_EN;
+	dcfg |= VP_DCFG_CRT_EN | VP_DCFG_DAC_BL_EN;
 
 	/* Enable the external DAC VREF? */
 
-	writel(dcfg, par->vid_regs + GX_DCFG);
+	write_vp(par, VP_DCFG, dcfg);
 
 	/* Set up the flat panel (if it is enabled) */
 
@@ -289,59 +295,55 @@ static void gx_configure_display(struct fb_info *info)
 		gx_configure_tft(info);
 }
 
-static int gx_blank_display(struct fb_info *info, int blank_mode)
+int gx_blank_display(struct fb_info *info, int blank_mode)
 {
-	struct geodefb_par *par = info->par;
+	struct gxfb_par *par = info->par;
 	u32 dcfg, fp_pm;
-	int blank, hsync, vsync;
+	int blank, hsync, vsync, crt;
 
 	/* CRT power saving modes. */
 	switch (blank_mode) {
 	case FB_BLANK_UNBLANK:
-		blank = 0; hsync = 1; vsync = 1;
+		blank = 0; hsync = 1; vsync = 1; crt = 1;
 		break;
 	case FB_BLANK_NORMAL:
-		blank = 1; hsync = 1; vsync = 1;
+		blank = 1; hsync = 1; vsync = 1; crt = 1;
 		break;
 	case FB_BLANK_VSYNC_SUSPEND:
-		blank = 1; hsync = 1; vsync = 0;
+		blank = 1; hsync = 1; vsync = 0; crt = 1;
 		break;
 	case FB_BLANK_HSYNC_SUSPEND:
-		blank = 1; hsync = 0; vsync = 1;
+		blank = 1; hsync = 0; vsync = 1; crt = 1;
 		break;
 	case FB_BLANK_POWERDOWN:
-		blank = 1; hsync = 0; vsync = 0;
+		blank = 1; hsync = 0; vsync = 0; crt = 0;
 		break;
 	default:
 		return -EINVAL;
 	}
-	dcfg = readl(par->vid_regs + GX_DCFG);
-	dcfg &= ~(GX_DCFG_DAC_BL_EN
-		  | GX_DCFG_HSYNC_EN | GX_DCFG_VSYNC_EN);
+	dcfg = read_vp(par, VP_DCFG);
+	dcfg &= ~(VP_DCFG_DAC_BL_EN | VP_DCFG_HSYNC_EN | VP_DCFG_VSYNC_EN |
+			VP_DCFG_CRT_EN);
 	if (!blank)
-		dcfg |= GX_DCFG_DAC_BL_EN;
+		dcfg |= VP_DCFG_DAC_BL_EN;
 	if (hsync)
-		dcfg |= GX_DCFG_HSYNC_EN;
+		dcfg |= VP_DCFG_HSYNC_EN;
 	if (vsync)
-		dcfg |= GX_DCFG_VSYNC_EN;
-	writel(dcfg, par->vid_regs + GX_DCFG);
+		dcfg |= VP_DCFG_VSYNC_EN;
+	if (crt)
+		dcfg |= VP_DCFG_CRT_EN;
+	write_vp(par, VP_DCFG, dcfg);
 
 	/* Power on/off flat panel. */
 
 	if (par->enable_crt == 0) {
-		fp_pm = readl(par->vid_regs + GX_FP_PM);
+		fp_pm = read_fp(par, FP_PM);
 		if (blank_mode == FB_BLANK_POWERDOWN)
-			fp_pm &= ~GX_FP_PM_P;
+			fp_pm &= ~FP_PM_P;
 		else
-			fp_pm |= GX_FP_PM_P;
-		writel(fp_pm, par->vid_regs + GX_FP_PM);
+			fp_pm |= FP_PM_P;
+		write_fp(par, FP_PM, fp_pm);
 	}
 
 	return 0;
 }
-
-struct geode_vid_ops gx_vid_ops = {
-	.set_dclk	   = gx_set_dclk_frequency,
-	.configure_display = gx_configure_display,
-	.blank_display	   = gx_blank_display,
-};
diff --git a/trunk/drivers/video/geode/video_gx.h b/trunk/drivers/video/geode/video_gx.h
deleted file mode 100644
index ce28d8f382dc..000000000000
--- a/trunk/drivers/video/geode/video_gx.h
+++ /dev/null
@@ -1,72 +0,0 @@
-/*
- * Geode GX video device
- *
- * Copyright (C) 2006 Arcom Control Systems Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-#ifndef __VIDEO_GX_H__
-#define __VIDEO_GX_H__
-
-extern struct geode_vid_ops gx_vid_ops;
-
-/* GX Flatpanel control MSR */
-#define GX_VP_MSR_PAD_SELECT           0xC0002011
-#define GX_VP_PAD_SELECT_MASK          0x3FFFFFFF
-#define GX_VP_PAD_SELECT_TFT           0x1FFFFFFF
-
-/* Geode GX video processor registers */
-
-#define GX_DCFG		0x0008
-#  define GX_DCFG_CRT_EN		0x00000001
-#  define GX_DCFG_HSYNC_EN		0x00000002
-#  define GX_DCFG_VSYNC_EN		0x00000004
-#  define GX_DCFG_DAC_BL_EN		0x00000008
-#  define GX_DCFG_FP_PWR_EN		0x00000040
-#  define GX_DCFG_FP_DATA_EN		0x00000080
-#  define GX_DCFG_CRT_HSYNC_POL		0x00000100
-#  define GX_DCFG_CRT_VSYNC_POL		0x00000200
-#  define GX_DCFG_CRT_SYNC_SKW_MASK	0x0001C000
-#  define GX_DCFG_CRT_SYNC_SKW_DFLT	0x00010000
-#  define GX_DCFG_VG_CK			0x00100000
-#  define GX_DCFG_GV_GAM		0x00200000
-#  define GX_DCFG_DAC_VREF		0x04000000
-
-/* Geode GX MISC video configuration */
-
-#define GX_MISC 0x50
-#define GX_MISC_GAM_EN     0x00000001
-#define GX_MISC_DAC_PWRDN  0x00000400
-#define GX_MISC_A_PWRDN    0x00000800
-
-/* Geode GX flat panel display control registers */
-
-#define GX_FP_PT1 0x0400
-#define GX_FP_PT1_VSIZE_MASK 0x7FF0000
-#define GX_FP_PT1_VSIZE_SHIFT 16
-
-#define GX_FP_PT2 0x408
-#define GX_FP_PT2_VSP (1 << 23)
-#define GX_FP_PT2_HSP (1 << 22)
-
-#define GX_FP_PM 0x410
-#  define GX_FP_PM_P 0x01000000
-
-#define GX_FP_DFC 0x418
-
-/* Geode GX clock control MSRs */
-
-#define MSR_GLCP_SYS_RSTPLL	0x4c000014
-#  define MSR_GLCP_SYS_RSTPLL_DOTPREDIV2	(0x0000000000000002ull)
-#  define MSR_GLCP_SYS_RSTPLL_DOTPREMULT2	(0x0000000000000004ull)
-#  define MSR_GLCP_SYS_RSTPLL_DOTPOSTDIV3	(0x0000000000000008ull)
-
-#define MSR_GLCP_DOTPLL		0x4c000015
-#  define MSR_GLCP_DOTPLL_DOTRESET		(0x0000000000000001ull)
-#  define MSR_GLCP_DOTPLL_BYPASS		(0x0000000000008000ull)
-#  define MSR_GLCP_DOTPLL_LOCK			(0x0000000002000000ull)
-
-#endif /* !__VIDEO_GX_H__ */
diff --git a/trunk/drivers/video/gxt4500.c b/trunk/drivers/video/gxt4500.c
index e92337bef50d..564557792bed 100644
--- a/trunk/drivers/video/gxt4500.c
+++ b/trunk/drivers/video/gxt4500.c
@@ -238,7 +238,7 @@ static int calc_pll(int period_ps, struct gxt4500_par *par)
 	for (pdiv1 = 1; pdiv1 <= 8; ++pdiv1) {
 		for (pdiv2 = 1; pdiv2 <= pdiv1; ++pdiv2) {
 			postdiv = pdiv1 * pdiv2;
-			pll_period = (period_ps + postdiv - 1) / postdiv;
+			pll_period = DIV_ROUND_UP(period_ps, postdiv);
 			/* keep pll in range 350..600 MHz */
 			if (pll_period < 1666 || pll_period > 2857)
 				continue;
diff --git a/trunk/drivers/video/hecubafb.c b/trunk/drivers/video/hecubafb.c
index 94e0df8a6f60..0b4bffbe67c8 100644
--- a/trunk/drivers/video/hecubafb.c
+++ b/trunk/drivers/video/hecubafb.c
@@ -1,5 +1,5 @@
 /*
- * linux/drivers/video/hecubafb.c -- FB driver for Hecuba controller
+ * linux/drivers/video/hecubafb.c -- FB driver for Hecuba/Apollo controller
  *
  * Copyright (C) 2006, Jaya Kumar
  * This work was sponsored by CIS(M) Sdn Bhd
@@ -17,18 +17,13 @@
  * values. There are other commands that the display is capable of,
  * beyond the 5 used here but they are more complex.
  *
- * This driver is written to be used with the Hecuba display controller
- * board, and tested with the EInk 800x600 display in 1 bit mode.
- * The interface between Hecuba and the host is TTL based GPIO. The
- * GPIO requirements are 8 writable data lines and 6 lines for control.
- * Only 4 of the controls are actually used here but 6 for future use.
- * The driver requires the IO addresses for data and control GPIO at
- * load time. It is also possible to use this display with a standard
- * PC parallel port.
+ * This driver is written to be used with the Hecuba display architecture.
+ * The actual display chip is called Apollo and the interface electronics
+ * it needs is called Hecuba.
  *
- * General notes:
- * - User must set hecubafb_enable=1 to enable it
- * - User must set dio_addr=0xIOADDR cio_addr=0xIOADDR c2io_addr=0xIOADDR
+ * It is intended to be architecture independent. A board specific driver
+ * must be used to perform all the physical IO interactions. An example
+ * is provided as n411.c
  *
  */
 
@@ -47,34 +42,12 @@
 #include <linux/list.h>
 #include <linux/uaccess.h>
 
-/* Apollo controller specific defines */
-#define APOLLO_START_NEW_IMG	0xA0
-#define APOLLO_STOP_IMG_DATA	0xA1
-#define APOLLO_DISPLAY_IMG	0xA2
-#define APOLLO_ERASE_DISPLAY	0xA3
-#define APOLLO_INIT_DISPLAY	0xA4
-
-/* Hecuba interface specific defines */
-/* WUP is inverted, CD is inverted, DS is inverted */
-#define HCB_NWUP_BIT	0x01
-#define HCB_NDS_BIT 	0x02
-#define HCB_RW_BIT 	0x04
-#define HCB_NCD_BIT 	0x08
-#define HCB_ACK_BIT 	0x80
+#include <video/hecubafb.h>
 
 /* Display specific information */
 #define DPY_W 600
 #define DPY_H 800
 
-struct hecubafb_par {
-	unsigned long dio_addr;
-	unsigned long cio_addr;
-	unsigned long c2io_addr;
-	unsigned char ctl;
-	struct fb_info *info;
-	unsigned int irq;
-};
-
 static struct fb_fix_screeninfo hecubafb_fix __devinitdata = {
 	.id =		"hecubafb",
 	.type =		FB_TYPE_PACKED_PIXELS,
@@ -82,6 +55,7 @@ static struct fb_fix_screeninfo hecubafb_fix __devinitdata = {
 	.xpanstep =	0,
 	.ypanstep =	0,
 	.ywrapstep =	0,
+	.line_length =	DPY_W,
 	.accel =	FB_ACCEL_NONE,
 };
 
@@ -94,136 +68,51 @@ static struct fb_var_screeninfo hecubafb_var __devinitdata = {
 	.nonstd		= 1,
 };
 
-static unsigned long dio_addr;
-static unsigned long cio_addr;
-static unsigned long c2io_addr;
-static unsigned long splashval;
-static unsigned int nosplash;
-static unsigned int hecubafb_enable;
-static unsigned int irq;
-
-static DECLARE_WAIT_QUEUE_HEAD(hecubafb_waitq);
-
-static void hcb_set_ctl(struct hecubafb_par *par)
-{
-	outb(par->ctl, par->cio_addr);
-}
-
-static unsigned char hcb_get_ctl(struct hecubafb_par *par)
-{
-	return inb(par->c2io_addr);
-}
-
-static void hcb_set_data(struct hecubafb_par *par, unsigned char value)
-{
-	outb(value, par->dio_addr);
-}
-
-static int __devinit apollo_init_control(struct hecubafb_par *par)
-{
-	unsigned char ctl;
-	/* for init, we want the following setup to be set:
-	WUP = lo
-	ACK = hi
-	DS = hi
-	RW = hi
-	CD = lo
-	*/
-
-	/* write WUP to lo, DS to hi, RW to hi, CD to lo */
-	par->ctl = HCB_NWUP_BIT | HCB_RW_BIT | HCB_NCD_BIT ;
-	par->ctl &= ~HCB_NDS_BIT;
-	hcb_set_ctl(par);
-
-	/* check ACK is not lo */
-	ctl = hcb_get_ctl(par);
-	if ((ctl & HCB_ACK_BIT)) {
-		printk(KERN_ERR "Fail because ACK is already low\n");
-		return -ENXIO;
-	}
-
-	return 0;
-}
-
-static void hcb_wait_for_ack(struct hecubafb_par *par)
-{
-
-	int timeout;
-	unsigned char ctl;
-
-	timeout=500;
-	do {
-		ctl = hcb_get_ctl(par);
-		if ((ctl & HCB_ACK_BIT))
-			return;
-		udelay(1);
-	} while (timeout--);
-	printk(KERN_ERR "timed out waiting for ack\n");
-}
-
-static void hcb_wait_for_ack_clear(struct hecubafb_par *par)
-{
-
-	int timeout;
-	unsigned char ctl;
-
-	timeout=500;
-	do {
-		ctl = hcb_get_ctl(par);
-		if (!(ctl & HCB_ACK_BIT))
-			return;
-		udelay(1);
-	} while (timeout--);
-	printk(KERN_ERR "timed out waiting for clear\n");
-}
+/* main hecubafb functions */
 
 static void apollo_send_data(struct hecubafb_par *par, unsigned char data)
 {
 	/* set data */
-	hcb_set_data(par, data);
+	par->board->set_data(par, data);
 
 	/* set DS low */
-	par->ctl |= HCB_NDS_BIT;
-	hcb_set_ctl(par);
+	par->board->set_ctl(par, HCB_DS_BIT, 0);
 
-	hcb_wait_for_ack(par);
+	/* wait for ack */
+	par->board->wait_for_ack(par, 0);
 
 	/* set DS hi */
-	par->ctl &= ~(HCB_NDS_BIT);
-	hcb_set_ctl(par);
+	par->board->set_ctl(par, HCB_DS_BIT, 1);
 
-	hcb_wait_for_ack_clear(par);
+	/* wait for ack to clear */
+	par->board->wait_for_ack(par, 1);
 }
 
 static void apollo_send_command(struct hecubafb_par *par, unsigned char data)
 {
 	/* command so set CD to high */
-	par->ctl &= ~(HCB_NCD_BIT);
-	hcb_set_ctl(par);
+	par->board->set_ctl(par, HCB_CD_BIT, 1);
 
 	/* actually strobe with command */
 	apollo_send_data(par, data);
 
 	/* clear CD back to low */
-	par->ctl |= (HCB_NCD_BIT);
-	hcb_set_ctl(par);
+	par->board->set_ctl(par, HCB_CD_BIT, 0);
 }
 
-/* main hecubafb functions */
-
 static void hecubafb_dpy_update(struct hecubafb_par *par)
 {
 	int i;
 	unsigned char *buf = (unsigned char __force *)par->info->screen_base;
 
-	apollo_send_command(par, 0xA0);
+	apollo_send_command(par, APOLLO_START_NEW_IMG);
 
 	for (i=0; i < (DPY_W*DPY_H/8); i++) {
 		apollo_send_data(par, *(buf++));
 	}
 
-	apollo_send_command(par, 0xA1);
-	apollo_send_command(par, 0xA2);
+	apollo_send_command(par, APOLLO_STOP_IMG_DATA);
+	apollo_send_command(par, APOLLO_DISPLAY_IMG);
 }
 
 /* this is called back from the deferred io workqueue */
@@ -270,41 +159,43 @@ static void hecubafb_imageblit(struct fb_info *info,
 static ssize_t hecubafb_write(struct fb_info *info, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
-	unsigned long p;
-	int err=-EINVAL;
-	struct hecubafb_par *par;
-	unsigned int xres;
-	unsigned int fbmemlength;
+	struct hecubafb_par *par = info->par;
+	unsigned long p = *ppos;
+	void *dst;
+	int err = 0;
+	unsigned long total_size;
 
-	p = *ppos;
-	par = info->par;
-	xres = info->var.xres;
-	fbmemlength = (xres * info->var.yres)/8;
+	if (info->state != FBINFO_STATE_RUNNING)
+		return -EPERM;
 
-	if (p > fbmemlength)
-		return -ENOSPC;
+	total_size = info->fix.smem_len;
 
-	err = 0;
-	if ((count + p) > fbmemlength) {
-		count = fbmemlength - p;
-		err = -ENOSPC;
+	if (p > total_size)
+		return -EFBIG;
+
+	if (count > total_size) {
+		err = -EFBIG;
+		count = total_size;
 	}
 
-	if (count) {
-		char *base_addr;
+	if (count + p > total_size) {
+		if (!err)
+			err = -ENOSPC;
 
-		base_addr = (char __force *)info->screen_base;
-		count -= copy_from_user(base_addr + p, buf, count);
-		*ppos += count;
-		err = -EFAULT;
+		count = total_size - p;
 	}
 
-	hecubafb_dpy_update(par);
+	dst = (void __force *) (info->screen_base + p);
+
+	if (copy_from_user(dst, buf, count))
+		err = -EFAULT;
 
-	if (count)
-		return count;
+	if  (!err)
+		*ppos += count;
 
-	return err;
+	hecubafb_dpy_update(par);
+
+	return (err) ? err : count;
 }
 
 static struct fb_ops hecubafb_ops = {
@@ -324,11 +215,21 @@ static struct fb_deferred_io hecubafb_defio = {
 static int __devinit hecubafb_probe(struct platform_device *dev)
 {
 	struct fb_info *info;
+	struct hecuba_board *board;
 	int retval = -ENOMEM;
 	int videomemorysize;
 	unsigned char *videomemory;
 	struct hecubafb_par *par;
 
+	/* pick up board specific routines */
+	board = dev->dev.platform_data;
+	if (!board)
+		return -EINVAL;
+
+	/* try to count device specific driver, if can't, platform recalls */
+	if (!try_module_get(board->owner))
+		return -ENODEV;
+
 	videomemorysize = (DPY_W*DPY_H)/8;
 
 	if (!(videomemory = vmalloc(videomemorysize)))
@@ -338,9 +239,9 @@ static int __devinit hecubafb_probe(struct platform_device *dev)
 
 	info = framebuffer_alloc(sizeof(struct hecubafb_par), &dev->dev);
 	if (!info)
-		goto err;
+		goto err_fballoc;
 
-	info->screen_base = (char __iomem *) videomemory;
+	info->screen_base = (char __force __iomem *)videomemory;
 	info->fbops = &hecubafb_ops;
 
 	info->var = hecubafb_var;
@@ -348,14 +249,10 @@ static int __devinit hecubafb_probe(struct platform_device *dev)
 	info->fix.smem_len = videomemorysize;
 	par = info->par;
 	par->info = info;
+	par->board = board;
+	par->send_command = apollo_send_command;
+	par->send_data = apollo_send_data;
 
-	if (!dio_addr || !cio_addr || !c2io_addr) {
-		printk(KERN_WARNING "no IO addresses supplied\n");
-		goto err1;
-	}
-	par->dio_addr = dio_addr;
-	par->cio_addr = cio_addr;
-	par->c2io_addr = c2io_addr;
 	info->flags = FBINFO_FLAG_DEFAULT;
 
 	info->fbdefio = &hecubafb_defio;
@@ -363,7 +260,7 @@ static int __devinit hecubafb_probe(struct platform_device *dev)
 
 	retval = register_framebuffer(info);
 	if (retval < 0)
-		goto err1;
+		goto err_fbreg;
 	platform_set_drvdata(dev, info);
 
 	printk(KERN_INFO
@@ -371,25 +268,16 @@ static int __devinit hecubafb_probe(struct platform_device *dev)
 	       info->node, videomemorysize >> 10);
 
 	/* this inits the dpy */
-	apollo_init_control(par);
-
-	apollo_send_command(par, APOLLO_INIT_DISPLAY);
-	apollo_send_data(par, 0x81);
-
-	/* have to wait while display resets */
-	udelay(1000);
-
-	/* if we were told to splash the screen, we just clear it */
-	if (!nosplash) {
-		apollo_send_command(par, APOLLO_ERASE_DISPLAY);
-		apollo_send_data(par, splashval);
-	}
+	retval = par->board->init(par);
+	if (retval < 0)
+		goto err_fbreg;
 
 	return 0;
-err1:
+err_fbreg:
 	framebuffer_release(info);
-err:
+err_fballoc:
 	vfree(videomemory);
+	module_put(board->owner);
 	return retval;
 }
 
@@ -398,9 +286,13 @@ static int __devexit hecubafb_remove(struct platform_device *dev)
 	struct fb_info *info = platform_get_drvdata(dev);
 
 	if (info) {
+		struct hecubafb_par *par = info->par;
 		fb_deferred_io_cleanup(info);
 		unregister_framebuffer(info);
 		vfree((void __force *)info->screen_base);
+		if (par->board->remove)
+			par->board->remove(par);
+		module_put(par->board->owner);
 		framebuffer_release(info);
 	}
 	return 0;
@@ -410,62 +302,24 @@ static struct platform_driver hecubafb_driver = {
 	.probe	= hecubafb_probe,
 	.remove = hecubafb_remove,
 	.driver	= {
+		.owner	= THIS_MODULE,
 		.name	= "hecubafb",
 	},
 };
 
-static struct platform_device *hecubafb_device;
-
 static int __init hecubafb_init(void)
 {
-	int ret;
-
-	if (!hecubafb_enable) {
-		printk(KERN_ERR "Use hecubafb_enable to enable the device\n");
-		return -ENXIO;
-	}
-
-	ret = platform_driver_register(&hecubafb_driver);
-	if (!ret) {
-		hecubafb_device = platform_device_alloc("hecubafb", 0);
-		if (hecubafb_device)
-			ret = platform_device_add(hecubafb_device);
-		else
-			ret = -ENOMEM;
-
-		if (ret) {
-			platform_device_put(hecubafb_device);
-			platform_driver_unregister(&hecubafb_driver);
-		}
-	}
-	return ret;
-
+	return platform_driver_register(&hecubafb_driver);
 }
 
 static void __exit hecubafb_exit(void)
 {
-	platform_device_unregister(hecubafb_device);
 	platform_driver_unregister(&hecubafb_driver);
 }
 
-module_param(nosplash, uint, 0);
-MODULE_PARM_DESC(nosplash, "Disable doing the splash screen");
-module_param(hecubafb_enable, uint, 0);
-MODULE_PARM_DESC(hecubafb_enable, "Enable communication with Hecuba board");
-module_param(dio_addr, ulong, 0);
-MODULE_PARM_DESC(dio_addr, "IO address for data, eg: 0x480");
-module_param(cio_addr, ulong, 0);
-MODULE_PARM_DESC(cio_addr, "IO address for control, eg: 0x400");
-module_param(c2io_addr, ulong, 0);
-MODULE_PARM_DESC(c2io_addr, "IO address for secondary control, eg: 0x408");
-module_param(splashval, ulong, 0);
-MODULE_PARM_DESC(splashval, "Splash pattern: 0x00 is black, 0x01 is white");
-module_param(irq, uint, 0);
-MODULE_PARM_DESC(irq, "IRQ for the Hecuba board");
-
 module_init(hecubafb_init);
 module_exit(hecubafb_exit);
 
-MODULE_DESCRIPTION("fbdev driver for Hecuba board");
+MODULE_DESCRIPTION("fbdev driver for Hecuba/Apollo controller");
 MODULE_AUTHOR("Jaya Kumar");
 MODULE_LICENSE("GPL");
diff --git a/trunk/drivers/video/imsttfb.c b/trunk/drivers/video/imsttfb.c
index 3ab91bf21576..15d50b9906ce 100644
--- a/trunk/drivers/video/imsttfb.c
+++ b/trunk/drivers/video/imsttfb.c
@@ -1151,8 +1151,10 @@ imsttfb_load_cursor_image(struct imstt_par *par, int width, int height, __u8 fgc
 				par->cmap_regs[TVPCRDAT] = 0xff;		eieio();
 			}
 		par->cmap_regs[TVPCADRW] = 0x00;	eieio();
-		for (x = 0; x < 12; x++)
-			par->cmap_regs[TVPCDATA] = fgc;	eieio();
+		for (x = 0; x < 12; x++) {
+			par->cmap_regs[TVPCDATA] = fgc;
+			eieio();
+		}
 	}
 	return 1;
 }
@@ -1476,7 +1478,7 @@ imsttfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	
 	dp = pci_device_to_OF_node(pdev);
 	if(dp)
-		printk(KERN_INFO "%s: OF name %s\n",__FUNCTION__, dp->name);
+		printk(KERN_INFO "%s: OF name %s\n",__func__, dp->name);
 	else
 		printk(KERN_ERR "imsttfb: no OF node for pci device\n");
 #endif /* CONFIG_PPC_OF */
diff --git a/trunk/drivers/video/imxfb.c b/trunk/drivers/video/imxfb.c
index 11609552a387..94e4d3ac1a05 100644
--- a/trunk/drivers/video/imxfb.c
+++ b/trunk/drivers/video/imxfb.c
@@ -415,7 +415,7 @@ static void imxfb_setup_gpio(struct imxfb_info *fbi)
 static int imxfb_suspend(struct platform_device *dev, pm_message_t state)
 {
 	struct imxfb_info *fbi = platform_get_drvdata(dev);
-	pr_debug("%s\n",__FUNCTION__);
+	pr_debug("%s\n",__func__);
 
 	imxfb_disable_controller(fbi);
 	return 0;
@@ -424,7 +424,7 @@ static int imxfb_suspend(struct platform_device *dev, pm_message_t state)
 static int imxfb_resume(struct platform_device *dev)
 {
 	struct imxfb_info *fbi = platform_get_drvdata(dev);
-	pr_debug("%s\n",__FUNCTION__);
+	pr_debug("%s\n",__func__);
 
 	imxfb_enable_controller(fbi);
 	return 0;
@@ -440,7 +440,7 @@ static int __init imxfb_init_fbinfo(struct device *dev)
 	struct fb_info *info = dev_get_drvdata(dev);
 	struct imxfb_info *fbi = info->par;
 
-	pr_debug("%s\n",__FUNCTION__);
+	pr_debug("%s\n",__func__);
 
 	info->pseudo_palette = kmalloc( sizeof(u32) * 16, GFP_KERNEL);
 	if (!info->pseudo_palette)
diff --git a/trunk/drivers/video/intelfb/intelfb.h b/trunk/drivers/video/intelfb/intelfb.h
index 836796177942..3325fbd68ab3 100644
--- a/trunk/drivers/video/intelfb/intelfb.h
+++ b/trunk/drivers/video/intelfb/intelfb.h
@@ -12,9 +12,9 @@
 #endif
 
 /*** Version/name ***/
-#define INTELFB_VERSION			"0.9.4"
+#define INTELFB_VERSION			"0.9.5"
 #define INTELFB_MODULE_NAME		"intelfb"
-#define SUPPORTED_CHIPSETS		"830M/845G/852GM/855GM/865G/915G/915GM/945G/945GM"
+#define SUPPORTED_CHIPSETS		"830M/845G/852GM/855GM/865G/915G/915GM/945G/945GM/965G/965GM"
 
 
 /*** Debug/feature defines ***/
@@ -58,6 +58,8 @@
 #define PCI_DEVICE_ID_INTEL_915GM	0x2592
 #define PCI_DEVICE_ID_INTEL_945G	0x2772
 #define PCI_DEVICE_ID_INTEL_945GM	0x27A2
+#define PCI_DEVICE_ID_INTEL_965G	0x29A2
+#define PCI_DEVICE_ID_INTEL_965GM	0x2A02
 
 /* Size of MMIO region */
 #define INTEL_REG_SIZE			0x80000
@@ -158,6 +160,8 @@ enum intel_chips {
 	INTEL_915GM,
 	INTEL_945G,
 	INTEL_945GM,
+	INTEL_965G,
+	INTEL_965GM,
 };
 
 struct intelfb_hwstate {
@@ -358,7 +362,9 @@ struct intelfb_info {
 #define IS_I9XX(dinfo) (((dinfo)->chipset == INTEL_915G) ||	\
 			((dinfo)->chipset == INTEL_915GM) ||	\
 			((dinfo)->chipset == INTEL_945G) ||	\
-			((dinfo)->chipset==INTEL_945GM))
+			((dinfo)->chipset == INTEL_945GM) ||	\
+			((dinfo)->chipset == INTEL_965G) ||	\
+			((dinfo)->chipset == INTEL_965GM))
 
 #ifndef FBIO_WAITFORVSYNC
 #define FBIO_WAITFORVSYNC	_IOW('F', 0x20, __u32)
diff --git a/trunk/drivers/video/intelfb/intelfb_i2c.c b/trunk/drivers/video/intelfb/intelfb_i2c.c
index 94c08bb5acf1..ca95f09d8b43 100644
--- a/trunk/drivers/video/intelfb/intelfb_i2c.c
+++ b/trunk/drivers/video/intelfb/intelfb_i2c.c
@@ -169,6 +169,8 @@ void intelfb_create_i2c_busses(struct intelfb_info *dinfo)
 		/* has some LVDS + tv-out */
 	case INTEL_945G:
 	case INTEL_945GM:
+	case INTEL_965G:
+	case INTEL_965GM:
 		/* SDVO ports have a single control bus - 2 devices */
 		dinfo->output[i].type = INTELFB_OUTPUT_SDVO;
 		intelfb_setup_i2c_bus(dinfo, &dinfo->output[i].i2c_bus,
diff --git a/trunk/drivers/video/intelfb/intelfbdrv.c b/trunk/drivers/video/intelfb/intelfbdrv.c
index 481d58f7535d..e44303f9bc52 100644
--- a/trunk/drivers/video/intelfb/intelfbdrv.c
+++ b/trunk/drivers/video/intelfb/intelfbdrv.c
@@ -2,7 +2,7 @@
  * intelfb
  *
  * Linux framebuffer driver for Intel(R) 830M/845G/852GM/855GM/865G/915G/915GM/
- * 945G/945GM integrated graphics chips.
+ * 945G/945GM/965G/965GM integrated graphics chips.
  *
  * Copyright © 2002, 2003 David Dawes <dawes@xfree86.org>
  *                   2004 Sylvain Meyer
@@ -99,6 +99,9 @@
  *              Add vram option to reserve more memory than stolen by BIOS
  *              Fix intelfbhw_pan_display typo
  *              Add __initdata annotations
+ *
+ *    04/2008 - Version 0.9.5
+ *              Add support for 965G/965GM. (Maik Broemme <mbroemme@plusserver.de>)
  */
 
 #include <linux/module.h>
@@ -180,6 +183,8 @@ static struct pci_device_id intelfb_pci_table[] __devinitdata = {
 	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_915GM, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, INTELFB_CLASS_MASK, INTEL_915GM },
 	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_945G, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, INTELFB_CLASS_MASK, INTEL_945G },
 	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_945GM, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, INTELFB_CLASS_MASK, INTEL_945GM },
+	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_965G, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, INTELFB_CLASS_MASK, INTEL_965G },
+	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_965GM, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA << 8, INTELFB_CLASS_MASK, INTEL_965GM },
 	{ 0, }
 };
 
@@ -549,7 +554,10 @@ static int __devinit intelfb_pci_register(struct pci_dev *pdev,
 	if ((ent->device == PCI_DEVICE_ID_INTEL_915G) ||
 	    (ent->device == PCI_DEVICE_ID_INTEL_915GM) ||
 	    (ent->device == PCI_DEVICE_ID_INTEL_945G)  ||
-	    (ent->device == PCI_DEVICE_ID_INTEL_945GM)) {
+	    (ent->device == PCI_DEVICE_ID_INTEL_945GM) ||
+	    (ent->device == PCI_DEVICE_ID_INTEL_965G) ||
+	    (ent->device == PCI_DEVICE_ID_INTEL_965GM)) {
+
 		aperture_bar = 2;
 		mmio_bar = 0;
 	}
diff --git a/trunk/drivers/video/intelfb/intelfbhw.c b/trunk/drivers/video/intelfb/intelfbhw.c
index fa1fff553565..8e6d6a4db0ad 100644
--- a/trunk/drivers/video/intelfb/intelfbhw.c
+++ b/trunk/drivers/video/intelfb/intelfbhw.c
@@ -143,6 +143,18 @@ int intelfbhw_get_chipset(struct pci_dev *pdev, struct intelfb_info *dinfo)
 		dinfo->mobile = 1;
 		dinfo->pll_index = PLLS_I9xx;
 		return 0;
+	case PCI_DEVICE_ID_INTEL_965G:
+		dinfo->name = "Intel(R) 965G";
+		dinfo->chipset = INTEL_965G;
+		dinfo->mobile = 0;
+		dinfo->pll_index = PLLS_I9xx;
+		return 0;
+	case PCI_DEVICE_ID_INTEL_965GM:
+		dinfo->name = "Intel(R) 965GM";
+		dinfo->chipset = INTEL_965GM;
+		dinfo->mobile = 1;
+		dinfo->pll_index = PLLS_I9xx;
+		return 0;
 	default:
 		return 1;
 	}
@@ -174,7 +186,9 @@ int intelfbhw_get_memory(struct pci_dev *pdev, int *aperture_size,
 	case PCI_DEVICE_ID_INTEL_915GM:
 	case PCI_DEVICE_ID_INTEL_945G:
 	case PCI_DEVICE_ID_INTEL_945GM:
-		/* 915 and 945 chipsets support a 256MB aperture.
+	case PCI_DEVICE_ID_INTEL_965G:
+	case PCI_DEVICE_ID_INTEL_965GM:
+		/* 915, 945 and 965 chipsets support a 256MB aperture.
 		   Aperture size is determined by inspected the
 		   base address of the aperture. */
 		if (pci_resource_start(pdev, 2) & 0x08000000)
diff --git a/trunk/drivers/video/leo.c b/trunk/drivers/video/leo.c
index 45b9a5d55dec..f3160fc29795 100644
--- a/trunk/drivers/video/leo.c
+++ b/trunk/drivers/video/leo.c
@@ -614,7 +614,7 @@ static int __devinit leo_probe(struct of_device *op, const struct of_device_id *
 
 	dev_set_drvdata(&op->dev, info);
 
-	printk("%s: leo at %lx:%lx\n",
+	printk(KERN_INFO "%s: leo at %lx:%lx\n",
 	       dp->full_name,
 	       par->which_io, par->physbase);
 
diff --git a/trunk/drivers/video/matrox/matroxfb_DAC1064.c b/trunk/drivers/video/matrox/matroxfb_DAC1064.c
index c4b570b4a4df..0ce3b0a89798 100644
--- a/trunk/drivers/video/matrox/matroxfb_DAC1064.c
+++ b/trunk/drivers/video/matrox/matroxfb_DAC1064.c
@@ -37,7 +37,7 @@ static void DAC1064_calcclock(CPMINFO unsigned int freq, unsigned int fmax, unsi
 	unsigned int fvco;
 	unsigned int p;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 	
 	/* only for devices older than G450 */
 
@@ -83,7 +83,7 @@ static const unsigned char MGA1064_DAC[] = {
 static void DAC1064_setpclk(WPMINFO unsigned long fout) {
 	unsigned int m, n, p;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	DAC1064_calcclock(PMINFO fout, ACCESS_FBINFO(max_pixel_clock), &m, &n, &p);
 	ACCESS_FBINFO(hw).DACclk[0] = m;
@@ -95,7 +95,7 @@ static void DAC1064_setmclk(WPMINFO int oscinfo, unsigned long fmem) {
 	u_int32_t mx;
 	struct matrox_hw_state* hw = &ACCESS_FBINFO(hw);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	if (ACCESS_FBINFO(devflags.noinit)) {
 		/* read MCLK and give up... */
@@ -338,7 +338,7 @@ void DAC1064_global_restore(WPMINFO2) {
 static int DAC1064_init_1(WPMINFO struct my_timming* m) {
 	struct matrox_hw_state* hw = &ACCESS_FBINFO(hw);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	memcpy(hw->DACreg, MGA1064_DAC, sizeof(MGA1064_DAC_regs));
 	switch (ACCESS_FBINFO(fbcon).var.bits_per_pixel) {
@@ -374,7 +374,7 @@ static int DAC1064_init_1(WPMINFO struct my_timming* m) {
 static int DAC1064_init_2(WPMINFO struct my_timming* m) {
 	struct matrox_hw_state* hw = &ACCESS_FBINFO(hw);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	if (ACCESS_FBINFO(fbcon).var.bits_per_pixel > 16) {	/* 256 entries */
 		int i;
@@ -418,7 +418,7 @@ static void DAC1064_restore_1(WPMINFO2) {
 
 	CRITFLAGS
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	CRITBEGIN
 
@@ -448,7 +448,7 @@ static void DAC1064_restore_2(WPMINFO2) {
 	unsigned int i;
 #endif
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 #ifdef DEBUG
 	dprintk(KERN_DEBUG "DAC1064regs ");
@@ -521,7 +521,7 @@ static struct matrox_altout g450out = {
 static int MGA1064_init(WPMINFO struct my_timming* m) {
 	struct matrox_hw_state* hw = &ACCESS_FBINFO(hw);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	if (DAC1064_init_1(PMINFO m)) return 1;
 	if (matroxfb_vgaHWinit(PMINFO m)) return 1;
@@ -543,7 +543,7 @@ static int MGA1064_init(WPMINFO struct my_timming* m) {
 static int MGAG100_init(WPMINFO struct my_timming* m) {
 	struct matrox_hw_state* hw = &ACCESS_FBINFO(hw);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	if (DAC1064_init_1(PMINFO m)) return 1;
 	hw->MXoptionReg &= ~0x2000;
@@ -565,7 +565,7 @@ static int MGAG100_init(WPMINFO struct my_timming* m) {
 #ifdef CONFIG_FB_MATROX_MYSTIQUE
 static void MGA1064_ramdac_init(WPMINFO2) {
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	/* ACCESS_FBINFO(features.DAC1064.vco_freq_min) = 120000; */
 	ACCESS_FBINFO(features.pll.vco_freq_min) = 62000;
@@ -594,7 +594,7 @@ static void MGAG100_progPixClock(CPMINFO int flags, int m, int n, int p) {
 	int selClk;
 	int clk;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	outDAC1064(PMINFO M1064_XPIXCLKCTRL, inDAC1064(PMINFO M1064_XPIXCLKCTRL) | M1064_XPIXCLKCTRL_DIS |
 		   M1064_XPIXCLKCTRL_PLL_UP);
@@ -636,7 +636,7 @@ static void MGAG100_progPixClock(CPMINFO int flags, int m, int n, int p) {
 static void MGAG100_setPixClock(CPMINFO int flags, int freq) {
 	unsigned int m, n, p;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	DAC1064_calcclock(PMINFO freq, ACCESS_FBINFO(max_pixel_clock), &m, &n, &p);
 	MGAG100_progPixClock(PMINFO flags, m, n, p);
@@ -650,7 +650,7 @@ static int MGA1064_preinit(WPMINFO2) {
 					     2048,    0};
 	struct matrox_hw_state* hw = &ACCESS_FBINFO(hw);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	/* ACCESS_FBINFO(capable.cfb4) = 0; ... preinitialized by 0 */
 	ACCESS_FBINFO(capable.text) = 1;
@@ -683,7 +683,7 @@ static int MGA1064_preinit(WPMINFO2) {
 
 static void MGA1064_reset(WPMINFO2) {
 
-	DBG(__FUNCTION__);
+	DBG(__func__);
 
 	MGA1064_ramdac_init(PMINFO2);
 }
@@ -819,7 +819,7 @@ static int MGAG100_preinit(WPMINFO2) {
 	u_int32_t q;
 #endif
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	/* there are some instabilities if in_div > 19 && vco < 61000 */
 	if (ACCESS_FBINFO(devflags.g450dac)) {
@@ -956,7 +956,7 @@ static void MGAG100_reset(WPMINFO2) {
 	u_int8_t b;
 	struct matrox_hw_state* hw = &ACCESS_FBINFO(hw);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	{
 #ifdef G100_BROKEN_IBM_82351
@@ -1015,7 +1015,7 @@ static void MGA1064_restore(WPMINFO2) {
 
 	CRITFLAGS
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	CRITBEGIN
 
@@ -1041,7 +1041,7 @@ static void MGAG100_restore(WPMINFO2) {
 
 	CRITFLAGS
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	CRITBEGIN
 
diff --git a/trunk/drivers/video/matrox/matroxfb_Ti3026.c b/trunk/drivers/video/matrox/matroxfb_Ti3026.c
index 9445cdb759b1..13524821e242 100644
--- a/trunk/drivers/video/matrox/matroxfb_Ti3026.c
+++ b/trunk/drivers/video/matrox/matroxfb_Ti3026.c
@@ -283,7 +283,7 @@ static int Ti3026_calcclock(CPMINFO unsigned int freq, unsigned int fmax, int* i
 	unsigned int fvco;
 	unsigned int lin, lfeed, lpost;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	fvco = PLL_calcclock(PMINFO freq, fmax, &lin, &lfeed, &lpost);
 	fvco >>= (*post = lpost);
@@ -297,7 +297,7 @@ static int Ti3026_setpclk(WPMINFO int clk) {
 	unsigned int pixfeed, pixin, pixpost;
 	struct matrox_hw_state* hw = &ACCESS_FBINFO(hw);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	f_pll = Ti3026_calcclock(PMINFO clk, ACCESS_FBINFO(max_pixel_clock), &pixin, &pixfeed, &pixpost);
 
@@ -365,7 +365,7 @@ static int Ti3026_init(WPMINFO struct my_timming* m) {
 	u_int8_t muxctrl = isInterleave(MINFO) ? TVP3026_XMUXCTRL_MEMORY_64BIT : TVP3026_XMUXCTRL_MEMORY_32BIT;
 	struct matrox_hw_state* hw = &ACCESS_FBINFO(hw);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	memcpy(hw->DACreg, MGADACbpp32, sizeof(hw->DACreg));
 	switch (ACCESS_FBINFO(fbcon).var.bits_per_pixel) {
@@ -440,7 +440,7 @@ static void ti3026_setMCLK(WPMINFO int fout){
 	unsigned int rfhcnt, mclk_ctl;
 	int tmout;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	f_pll = Ti3026_calcclock(PMINFO fout, ACCESS_FBINFO(max_pixel_clock), &mclk_n, &mclk_m, &mclk_p);
 
@@ -534,7 +534,7 @@ static void ti3026_setMCLK(WPMINFO int fout){
 
 static void ti3026_ramdac_init(WPMINFO2) {
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	ACCESS_FBINFO(features.pll.vco_freq_min) = 110000;
 	ACCESS_FBINFO(features.pll.ref_freq)	 = 114545;
@@ -554,7 +554,7 @@ static void Ti3026_restore(WPMINFO2) {
 	struct matrox_hw_state* hw = &ACCESS_FBINFO(hw);
 	CRITFLAGS
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 #ifdef DEBUG
 	dprintk(KERN_INFO "EXTVGA regs: ");
@@ -662,7 +662,7 @@ static void Ti3026_restore(WPMINFO2) {
 
 static void Ti3026_reset(WPMINFO2) {
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	ti3026_ramdac_init(PMINFO2);
 }
@@ -680,7 +680,7 @@ static int Ti3026_preinit(WPMINFO2) {
 					  2048, 0};
 	struct matrox_hw_state* hw = &ACCESS_FBINFO(hw);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	ACCESS_FBINFO(millenium) = 1;
 	ACCESS_FBINFO(milleniumII) = (ACCESS_FBINFO(pcidev)->device != PCI_DEVICE_ID_MATROX_MIL);
diff --git a/trunk/drivers/video/matrox/matroxfb_accel.c b/trunk/drivers/video/matrox/matroxfb_accel.c
index 3660d2673bdc..9c3aeee1cc4f 100644
--- a/trunk/drivers/video/matrox/matroxfb_accel.c
+++ b/trunk/drivers/video/matrox/matroxfb_accel.c
@@ -113,7 +113,7 @@ void matrox_cfbX_init(WPMINFO2) {
 	u_int32_t mopmode;
 	int accel;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	mpitch = ACCESS_FBINFO(fbcon).var.xres_virtual;
 
@@ -199,7 +199,7 @@ static void matrox_accel_bmove(WPMINFO int vxres, int sy, int sx, int dy, int dx
 	int start, end;
 	CRITFLAGS
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	CRITBEGIN
 
@@ -235,7 +235,7 @@ static void matrox_accel_bmove_lin(WPMINFO int vxres, int sy, int sx, int dy, in
 	int start, end;
 	CRITFLAGS
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	CRITBEGIN
 
@@ -287,7 +287,7 @@ static void matroxfb_accel_clear(WPMINFO u_int32_t color, int sy, int sx, int he
 		int width) {
 	CRITFLAGS
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	CRITBEGIN
 
@@ -315,7 +315,7 @@ static void matroxfb_cfb4_clear(WPMINFO u_int32_t bgx, int sy, int sx, int heigh
 	int whattodo;
 	CRITFLAGS
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	CRITBEGIN
 
@@ -388,7 +388,7 @@ static void matroxfb_1bpp_imageblit(WPMINFO u_int32_t fgx, u_int32_t bgx,
 	int easy;
 	CRITFLAGS
 
-	DBG_HEAVY(__FUNCTION__);
+	DBG_HEAVY(__func__);
 
 	step = (width + 7) >> 3;
 	charcell = height * step;
@@ -469,7 +469,7 @@ static void matroxfb_1bpp_imageblit(WPMINFO u_int32_t fgx, u_int32_t bgx,
 static void matroxfb_imageblit(struct fb_info* info, const struct fb_image* image) {
 	MINFO_FROM_INFO(info);
 
-	DBG_HEAVY(__FUNCTION__);
+	DBG_HEAVY(__func__);
 
 	if (image->depth == 1) {
 		u_int32_t fgx, bgx;
diff --git a/trunk/drivers/video/matrox/matroxfb_base.c b/trunk/drivers/video/matrox/matroxfb_base.c
index b25972ac6eeb..54e82f35353d 100644
--- a/trunk/drivers/video/matrox/matroxfb_base.c
+++ b/trunk/drivers/video/matrox/matroxfb_base.c
@@ -312,7 +312,7 @@ static void matrox_pan_var(WPMINFO struct fb_var_screeninfo *var) {
 
 	CRITFLAGS
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	if (ACCESS_FBINFO(dead))
 		return;
@@ -392,7 +392,7 @@ static int matroxfb_open(struct fb_info *info, int user)
 {
 	MINFO_FROM_INFO(info);
 
-	DBG_LOOP(__FUNCTION__)
+	DBG_LOOP(__func__)
 
 	if (ACCESS_FBINFO(dead)) {
 		return -ENXIO;
@@ -408,7 +408,7 @@ static int matroxfb_release(struct fb_info *info, int user)
 {
 	MINFO_FROM_INFO(info);
 
-	DBG_LOOP(__FUNCTION__)
+	DBG_LOOP(__func__)
 
 	if (user) {
 		if (0 == --ACCESS_FBINFO(userusecount)) {
@@ -425,7 +425,7 @@ static int matroxfb_pan_display(struct fb_var_screeninfo *var,
 		struct fb_info* info) {
 	MINFO_FROM_INFO(info);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	matrox_pan_var(PMINFO var);
 	return 0;
@@ -434,7 +434,7 @@ static int matroxfb_pan_display(struct fb_var_screeninfo *var,
 static int matroxfb_get_final_bppShift(CPMINFO int bpp) {
 	int bppshft2;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	bppshft2 = bpp;
 	if (!bppshft2) {
@@ -451,7 +451,7 @@ static int matroxfb_test_and_set_rounding(CPMINFO int xres, int bpp) {
 	int over;
 	int rounding;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	switch (bpp) {
 		case 0:		return xres;
@@ -482,7 +482,7 @@ static int matroxfb_pitch_adjust(CPMINFO int xres, int bpp) {
 	const int* width;
 	int xres_new;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	if (!bpp) return xres;
 
@@ -504,7 +504,7 @@ static int matroxfb_pitch_adjust(CPMINFO int xres, int bpp) {
 
 static int matroxfb_get_cmap_len(struct fb_var_screeninfo *var) {
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	switch (var->bits_per_pixel) {
 		case 4:
@@ -548,7 +548,7 @@ static int matroxfb_decode_var(CPMINFO struct fb_var_screeninfo *var, int *visua
 	unsigned int vramlen;
 	unsigned int memlen;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	switch (bpp) {
 		case 4:	 if (!ACCESS_FBINFO(capable.cfb4)) return -EINVAL;
@@ -648,7 +648,7 @@ static int matroxfb_setcolreg(unsigned regno, unsigned red, unsigned green,
 	struct matrox_fb_info* minfo = container_of(fb_info, struct matrox_fb_info, fbcon);
 #endif
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	/*
 	 *  Set a single color register. The values supplied are
@@ -707,7 +707,7 @@ static int matroxfb_setcolreg(unsigned regno, unsigned red, unsigned green,
 static void matroxfb_init_fix(WPMINFO2)
 {
 	struct fb_fix_screeninfo *fix = &ACCESS_FBINFO(fbcon).fix;
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	strcpy(fix->id,"MATROX");
 
@@ -722,7 +722,7 @@ static void matroxfb_init_fix(WPMINFO2)
 static void matroxfb_update_fix(WPMINFO2)
 {
 	struct fb_fix_screeninfo *fix = &ACCESS_FBINFO(fbcon).fix;
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	fix->smem_start = ACCESS_FBINFO(video.base) + ACCESS_FBINFO(curr.ydstorg.bytes);
 	fix->smem_len = ACCESS_FBINFO(video.len_usable) - ACCESS_FBINFO(curr.ydstorg.bytes);
@@ -753,7 +753,7 @@ static int matroxfb_set_par(struct fb_info *info)
 	struct fb_var_screeninfo *var;
 	MINFO_FROM_INFO(info);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	if (ACCESS_FBINFO(dead)) {
 		return -ENXIO;
@@ -876,7 +876,7 @@ static int matroxfb_ioctl(struct fb_info *info,
 	void __user *argp = (void __user *)arg;
 	MINFO_FROM_INFO(info);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	if (ACCESS_FBINFO(dead)) {
 		return -ENXIO;
@@ -1175,7 +1175,7 @@ static int matroxfb_blank(int blank, struct fb_info *info)
 	CRITFLAGS
 	MINFO_FROM_INFO(info);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	if (ACCESS_FBINFO(dead))
 		return 1;
@@ -1287,7 +1287,7 @@ static int matroxfb_getmemory(WPMINFO unsigned int maxSize, unsigned int *realSi
 	unsigned char bytes[32];
 	unsigned char* tmp;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	vm = ACCESS_FBINFO(video.vbase);
 	maxSize &= ~0x1FFFFF;	/* must be X*2MB (really it must be 2 or X*4MB) */
@@ -1593,7 +1593,7 @@ static int initMatrox2(WPMINFO struct board* b){
 		{ },
 	};
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	/* set default values... */
 	vesafb_defined.accel_flags = FB_ACCELF_TEXT;
@@ -2006,7 +2006,7 @@ static int matroxfb_probe(struct pci_dev* pdev, const struct pci_device_id* dumm
 #ifndef CONFIG_FB_MATROX_MULTIHEAD
 	static int registered = 0;
 #endif
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	svid = pdev->subsystem_vendor;
 	sid = pdev->subsystem_device;
@@ -2301,7 +2301,7 @@ static void __exit matrox_done(void) {
 static int __init matroxfb_setup(char *options) {
 	char *this_opt;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	if (!options || !*options)
 		return 0;
@@ -2444,7 +2444,7 @@ static int __init matroxfb_init(void)
 	char *option = NULL;
 	int err = 0;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	if (fb_get_options("matroxfb", &option))
 		return -ENODEV;
@@ -2556,7 +2556,7 @@ MODULE_PARM_DESC(cmode, "Specify the video depth that should be used (8bit defau
 
 int __init init_module(void){
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	if (disabled)
 		return -ENXIO;
diff --git a/trunk/drivers/video/matrox/matroxfb_crtc2.c b/trunk/drivers/video/matrox/matroxfb_crtc2.c
index a6ab5b6a58d0..7ac4c5f6145d 100644
--- a/trunk/drivers/video/matrox/matroxfb_crtc2.c
+++ b/trunk/drivers/video/matrox/matroxfb_crtc2.c
@@ -420,7 +420,7 @@ static int matroxfb_dh_ioctl(struct fb_info *info,
 #define m2info (container_of(info, struct matroxfb_dh_fb_info, fbcon))
 	MINFO_FROM(m2info->primary_dev);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	switch (cmd) {
 		case FBIOGET_VBLANK:
diff --git a/trunk/drivers/video/matrox/matroxfb_maven.c b/trunk/drivers/video/matrox/matroxfb_maven.c
index 0cd58f84fb46..89da27bd5c49 100644
--- a/trunk/drivers/video/matrox/matroxfb_maven.c
+++ b/trunk/drivers/video/matrox/matroxfb_maven.c
@@ -220,7 +220,7 @@ static int matroxfb_PLL_mavenclock(const struct matrox_pll_features2* pll,
 	unsigned int scrlen;
 	unsigned int fmax;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	scrlen = htotal * (vtotal - 1);
 	fwant = htotal * vtotal;
diff --git a/trunk/drivers/video/matrox/matroxfb_misc.c b/trunk/drivers/video/matrox/matroxfb_misc.c
index ab7fb50bc1de..5b5f072fc1a8 100644
--- a/trunk/drivers/video/matrox/matroxfb_misc.c
+++ b/trunk/drivers/video/matrox/matroxfb_misc.c
@@ -90,13 +90,13 @@
 #include <linux/matroxfb.h>
 
 void matroxfb_DAC_out(CPMINFO int reg, int val) {
-	DBG_REG(__FUNCTION__)
+	DBG_REG(__func__)
 	mga_outb(M_RAMDAC_BASE+M_X_INDEX, reg);
 	mga_outb(M_RAMDAC_BASE+M_X_DATAREG, val);
 }
 
 int matroxfb_DAC_in(CPMINFO int reg) {
-	DBG_REG(__FUNCTION__)
+	DBG_REG(__func__)
 	mga_outb(M_RAMDAC_BASE+M_X_INDEX, reg);
 	return mga_inb(M_RAMDAC_BASE+M_X_DATAREG);
 }
@@ -104,7 +104,7 @@ int matroxfb_DAC_in(CPMINFO int reg) {
 void matroxfb_var2my(struct fb_var_screeninfo* var, struct my_timming* mt) {
 	unsigned int pixclock = var->pixclock;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	if (!pixclock) pixclock = 10000;	/* 10ns = 100MHz */
 	mt->pixclock = 1000000000 / pixclock;
@@ -131,7 +131,7 @@ int matroxfb_PLL_calcclock(const struct matrox_pll_features* pll, unsigned int f
 	unsigned int fwant;
 	unsigned int p;
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	fwant = freq;
 
@@ -192,7 +192,7 @@ int matroxfb_vgaHWinit(WPMINFO struct my_timming* m) {
 	int i;
 	struct matrox_hw_state * const hw = &ACCESS_FBINFO(hw);
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	hw->SEQ[0] = 0x00;
 	hw->SEQ[1] = 0x01;	/* or 0x09 */
@@ -336,7 +336,7 @@ void matroxfb_vgaHWrestore(WPMINFO2) {
 	struct matrox_hw_state * const hw = &ACCESS_FBINFO(hw);
 	CRITFLAGS
 
-	DBG(__FUNCTION__)
+	DBG(__func__)
 
 	dprintk(KERN_INFO "MiscOutReg: %02X\n", hw->MiscOutReg);
 	dprintk(KERN_INFO "SEQ regs:   ");
@@ -522,8 +522,6 @@ static void parse_bios(unsigned char __iomem* vbios, struct matrox_bios* bd) {
 #endif
 }
 
-#define get_u16(x) (le16_to_cpu(get_unaligned((__u16*)(x))))
-#define get_u32(x) (le32_to_cpu(get_unaligned((__u32*)(x))))
 static int parse_pins1(WPMINFO const struct matrox_bios* bd) {
 	unsigned int maxdac;
 
@@ -532,11 +530,12 @@ static int parse_pins1(WPMINFO const struct matrox_bios* bd) {
 		case 1:		maxdac = 220000; break;
 		default:	maxdac = 240000; break;
 	}
-	if (get_u16(bd->pins + 24)) {
-		maxdac = get_u16(bd->pins + 24) * 10;
+	if (get_unaligned_le16(bd->pins + 24)) {
+		maxdac = get_unaligned_le16(bd->pins + 24) * 10;
 	}
 	MINFO->limits.pixel.vcomax = maxdac;
-	MINFO->values.pll.system = get_u16(bd->pins + 28) ? get_u16(bd->pins + 28) * 10 : 50000;
+	MINFO->values.pll.system = get_unaligned_le16(bd->pins + 28) ?
+		get_unaligned_le16(bd->pins + 28) * 10 : 50000;
 	/* ignore 4MB, 8MB, module clocks */
 	MINFO->features.pll.ref_freq = 14318;
 	MINFO->values.reg.mctlwtst	= 0x00030101;
@@ -575,7 +574,8 @@ static void default_pins2(WPMINFO2) {
 static int parse_pins3(WPMINFO const struct matrox_bios* bd) {
 	MINFO->limits.pixel.vcomax	=
 	MINFO->limits.system.vcomax	= (bd->pins[36] == 0xFF) ? 230000			: ((bd->pins[36] + 100) * 1000);
-	MINFO->values.reg.mctlwtst	= get_u32(bd->pins + 48) == 0xFFFFFFFF ? 0x01250A21	: get_u32(bd->pins + 48);
+	MINFO->values.reg.mctlwtst	= get_unaligned_le32(bd->pins + 48) == 0xFFFFFFFF ?
+		0x01250A21 : get_unaligned_le32(bd->pins + 48);
 	/* memory config */
 	MINFO->values.reg.memrdbk	= ((bd->pins[57] << 21) & 0x1E000000) |
 					  ((bd->pins[57] << 22) & 0x00C00000) |
@@ -601,7 +601,7 @@ static void default_pins3(WPMINFO2) {
 static int parse_pins4(WPMINFO const struct matrox_bios* bd) {
 	MINFO->limits.pixel.vcomax	= (bd->pins[ 39] == 0xFF) ? 230000			: bd->pins[ 39] * 4000;
 	MINFO->limits.system.vcomax	= (bd->pins[ 38] == 0xFF) ? MINFO->limits.pixel.vcomax	: bd->pins[ 38] * 4000;
-	MINFO->values.reg.mctlwtst	= get_u32(bd->pins + 71);
+	MINFO->values.reg.mctlwtst	= get_unaligned_le32(bd->pins + 71);
 	MINFO->values.reg.memrdbk	= ((bd->pins[87] << 21) & 0x1E000000) |
 					  ((bd->pins[87] << 22) & 0x00C00000) |
 					  ((bd->pins[86] <<  1) & 0x000001E0) |
@@ -609,7 +609,7 @@ static int parse_pins4(WPMINFO const struct matrox_bios* bd) {
 	MINFO->values.reg.opt		= ((bd->pins[53] << 15) & 0x00400000) |
 					  ((bd->pins[53] << 22) & 0x10000000) |
 					  ((bd->pins[53] <<  7) & 0x00001C00);
-	MINFO->values.reg.opt3		= get_u32(bd->pins + 67);
+	MINFO->values.reg.opt3		= get_unaligned_le32(bd->pins + 67);
 	MINFO->values.pll.system	= (bd->pins[ 65] == 0xFF) ? 200000 			: bd->pins[ 65] * 4000;
 	MINFO->features.pll.ref_freq	= (bd->pins[ 92] & 0x01) ? 14318 : 27000;
 	return 0;
@@ -640,12 +640,12 @@ static int parse_pins5(WPMINFO const struct matrox_bios* bd) {
 	MINFO->limits.video.vcomin	= (bd->pins[122] == 0xFF) ? MINFO->limits.system.vcomin	: bd->pins[122] * mult;
 	MINFO->values.pll.system	=
 	MINFO->values.pll.video		= (bd->pins[ 92] == 0xFF) ? 284000			: bd->pins[ 92] * 4000;
-	MINFO->values.reg.opt		= get_u32(bd->pins+ 48);
-	MINFO->values.reg.opt2		= get_u32(bd->pins+ 52);
-	MINFO->values.reg.opt3		= get_u32(bd->pins+ 94);
-	MINFO->values.reg.mctlwtst	= get_u32(bd->pins+ 98);
-	MINFO->values.reg.memmisc	= get_u32(bd->pins+102);
-	MINFO->values.reg.memrdbk	= get_u32(bd->pins+106);
+	MINFO->values.reg.opt		= get_unaligned_le32(bd->pins + 48);
+	MINFO->values.reg.opt2		= get_unaligned_le32(bd->pins + 52);
+	MINFO->values.reg.opt3		= get_unaligned_le32(bd->pins + 94);
+	MINFO->values.reg.mctlwtst	= get_unaligned_le32(bd->pins + 98);
+	MINFO->values.reg.memmisc	= get_unaligned_le32(bd->pins + 102);
+	MINFO->values.reg.memrdbk	= get_unaligned_le32(bd->pins + 106);
 	MINFO->features.pll.ref_freq	= (bd->pins[110] & 0x01) ? 14318 : 27000;
 	MINFO->values.memory.ddr	= (bd->pins[114] & 0x60) == 0x20;
 	MINFO->values.memory.dll	= (bd->pins[115] & 0x02) != 0;
diff --git a/trunk/drivers/video/metronomefb.c b/trunk/drivers/video/metronomefb.c
index e9a89fd82757..cc4c038a1b3f 100644
--- a/trunk/drivers/video/metronomefb.c
+++ b/trunk/drivers/video/metronomefb.c
@@ -13,12 +13,10 @@
  * Corporation. http://support.eink.com/community
  *
  * This driver is written to be used with the Metronome display controller.
- * It was tested with an E-Ink 800x600 Vizplex EPD on a Gumstix Connex board
- * using the Lyre interface board.
+ * It is intended to be architecture independent. A board specific driver
+ * must be used to perform all the physical IO interactions. An example
+ * is provided as am200epd.c
  *
- * General notes:
- * - User must set metronomefb_enable=1 to enable it.
- * - See Documentation/fb/metronomefb.txt for how metronome works.
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -38,9 +36,11 @@
 #include <linux/uaccess.h>
 #include <linux/irq.h>
 
-#include <asm/arch/pxa-regs.h>
+#include <video/metronomefb.h>
+
 #include <asm/unaligned.h>
 
+
 #define DEBUG 1
 #ifdef DEBUG
 #define DPRINTK(f, a...) printk(KERN_DEBUG "%s: " f, __func__ , ## a)
@@ -53,35 +53,6 @@
 #define DPY_W 832
 #define DPY_H 622
 
-struct metromem_desc {
-	u32 mFDADR0;
-	u32 mFSADR0;
-	u32 mFIDR0;
-	u32 mLDCMD0;
-};
-
-struct metromem_cmd {
-	u16 opcode;
-	u16 args[((64-2)/2)];
-	u16 csum;
-};
-
-struct metronomefb_par {
-	unsigned char *metromem;
-	struct metromem_desc *metromem_desc;
-	struct metromem_cmd *metromem_cmd;
-	unsigned char *metromem_wfm;
-	unsigned char *metromem_img;
-	u16 *metromem_img_csum;
-	u16 *csum_table;
-	int metromemsize;
-	dma_addr_t metromem_dma;
-	dma_addr_t metromem_desc_dma;
-	struct fb_info *info;
-	wait_queue_head_t waitq;
-	u8 frame_count;
-};
-
 /* frame differs from image. frame includes non-visible pixels */
 struct epd_frame {
 	int fw; /* frame width */
@@ -120,8 +91,7 @@ static struct fb_var_screeninfo metronomefb_var __devinitdata = {
 	.transp =	{ 0, 0, 0 },
 };
 
-static unsigned int metronomefb_enable;
-
+/* the waveform structure that is coming from userspace firmware */
 struct waveform_hdr {
 	u8 stuff[32];
 
@@ -236,8 +206,7 @@ static int load_waveform(u8 *mem, size_t size, u8 *metromem, int m, int t,
 	}
 
 	/* check waveform mode table address checksum */
-	wmta = le32_to_cpu(get_unaligned((__le32 *) wfm_hdr->wmta));
-	wmta &= 0x00FFFFFF;
+	wmta = get_unaligned_le32(wfm_hdr->wmta) & 0x00FFFFFF;
 	cksum_idx = wmta + m*4 + 3;
 	if (cksum_idx > size)
 		return -EINVAL;
@@ -249,8 +218,7 @@ static int load_waveform(u8 *mem, size_t size, u8 *metromem, int m, int t,
 	}
 
 	/* check waveform temperature table address checksum */
-	tta = le32_to_cpu(get_unaligned((int *) (mem + wmta + m*4)));
-	tta &= 0x00FFFFFF;
+	tta = get_unaligned_le32(mem + wmta + m * 4) & 0x00FFFFFF;
 	cksum_idx = tta + trn*4 + 3;
 	if (cksum_idx > size)
 		return -EINVAL;
@@ -263,8 +231,7 @@ static int load_waveform(u8 *mem, size_t size, u8 *metromem, int m, int t,
 
 	/* here we do the real work of putting the waveform into the
 	metromem buffer. this does runlength decoding of the waveform */
-	wfm_idx = le32_to_cpu(get_unaligned((__le32 *) (mem + tta + trn*4)));
-	wfm_idx &= 0x00FFFFFF;
+	wfm_idx = get_unaligned_le32(mem + tta + trn * 4) & 0x00FFFFFF;
 	owfm_idx = wfm_idx;
 	if (wfm_idx > size)
 		return -EINVAL;
@@ -301,165 +268,6 @@ static int load_waveform(u8 *mem, size_t size, u8 *metromem, int m, int t,
 	return 0;
 }
 
-/* register offsets for gpio control */
-#define LED_GPIO_PIN 51
-#define STDBY_GPIO_PIN 48
-#define RST_GPIO_PIN 49
-#define RDY_GPIO_PIN 32
-#define ERR_GPIO_PIN 17
-#define PCBPWR_GPIO_PIN 16
-
-#define AF_SEL_GPIO_N 0x3
-#define GAFR0_U_OFFSET(pin) ((pin - 16) * 2)
-#define GAFR1_L_OFFSET(pin) ((pin - 32) * 2)
-#define GAFR1_U_OFFSET(pin) ((pin - 48) * 2)
-#define GPDR1_OFFSET(pin) (pin - 32)
-#define GPCR1_OFFSET(pin) (pin - 32)
-#define GPSR1_OFFSET(pin) (pin - 32)
-#define GPCR0_OFFSET(pin) (pin)
-#define GPSR0_OFFSET(pin) (pin)
-
-static void metronome_set_gpio_output(int pin, int val)
-{
-	u8 index;
-
-	index = pin >> 4;
-
-	switch (index) {
-	case 1:
-		if (val)
-			GPSR0 |= (1 << GPSR0_OFFSET(pin));
-		else
-			GPCR0 |= (1 << GPCR0_OFFSET(pin));
-		break;
-	case 2:
-		break;
-	case 3:
-		if (val)
-			GPSR1 |= (1 << GPSR1_OFFSET(pin));
-		else
-			GPCR1 |= (1 << GPCR1_OFFSET(pin));
-		break;
-	default:
-		printk(KERN_ERR "unimplemented\n");
-	}
-}
-
-static void __devinit metronome_init_gpio_pin(int pin, int dir)
-{
-	u8 index;
-	/* dir 0 is output, 1 is input
-	- do 2 things here:
-	- set gpio alternate function to standard gpio
-	- set gpio direction to input or output  */
-
-	index = pin >> 4;
-	switch (index) {
-	case 1:
-		GAFR0_U &= ~(AF_SEL_GPIO_N << GAFR0_U_OFFSET(pin));
-
-		if (dir)
-			GPDR0 &= ~(1 << pin);
-		else
-			GPDR0 |= (1 << pin);
-		break;
-	case 2:
-		GAFR1_L &= ~(AF_SEL_GPIO_N << GAFR1_L_OFFSET(pin));
-
-		if (dir)
-			GPDR1 &= ~(1 << GPDR1_OFFSET(pin));
-		else
-			GPDR1 |= (1 << GPDR1_OFFSET(pin));
-		break;
-	case 3:
-		GAFR1_U &= ~(AF_SEL_GPIO_N << GAFR1_U_OFFSET(pin));
-
-		if (dir)
-			GPDR1 &= ~(1 << GPDR1_OFFSET(pin));
-		else
-			GPDR1 |= (1 << GPDR1_OFFSET(pin));
-		break;
-	default:
-		printk(KERN_ERR "unimplemented\n");
-	}
-}
-
-static void __devinit metronome_init_gpio_regs(void)
-{
-	metronome_init_gpio_pin(LED_GPIO_PIN, 0);
-	metronome_set_gpio_output(LED_GPIO_PIN, 0);
-
-	metronome_init_gpio_pin(STDBY_GPIO_PIN, 0);
-	metronome_set_gpio_output(STDBY_GPIO_PIN, 0);
-
-	metronome_init_gpio_pin(RST_GPIO_PIN, 0);
-	metronome_set_gpio_output(RST_GPIO_PIN, 0);
-
-	metronome_init_gpio_pin(RDY_GPIO_PIN, 1);
-
-	metronome_init_gpio_pin(ERR_GPIO_PIN, 1);
-
-	metronome_init_gpio_pin(PCBPWR_GPIO_PIN, 0);
-	metronome_set_gpio_output(PCBPWR_GPIO_PIN, 0);
-}
-
-static void metronome_disable_lcd_controller(struct metronomefb_par *par)
-{
-	LCSR = 0xffffffff;	/* Clear LCD Status Register */
-	LCCR0 |= LCCR0_DIS;	/* Disable LCD Controller */
-
-	/* we reset and just wait for things to settle */
-	msleep(200);
-}
-
-static void metronome_enable_lcd_controller(struct metronomefb_par *par)
-{
-	LCSR = 0xffffffff;
-	FDADR0 = par->metromem_desc_dma;
-	LCCR0 |= LCCR0_ENB;
-}
-
-static void __devinit metronome_init_lcdc_regs(struct metronomefb_par *par)
-{
-	/* here we do:
-	- disable the lcd controller
-	- setup lcd control registers
-	- setup dma descriptor
-	- reenable lcd controller
-	*/
-
-	/* disable the lcd controller */
-	metronome_disable_lcd_controller(par);
-
-	/* setup lcd control registers */
-	LCCR0 = LCCR0_LDM | LCCR0_SFM | LCCR0_IUM | LCCR0_EFM | LCCR0_PAS
-		| LCCR0_QDM | LCCR0_BM | LCCR0_OUM;
-
-	LCCR1 = (epd_frame_table[0].fw/2 - 1) /* pixels per line */
-		| (27 << 10) /* hsync pulse width - 1 */
-		| (33 << 16) /* eol pixel count */
-		| (33 << 24); /* bol pixel count */
-
-	LCCR2 = (epd_frame_table[0].fh - 1) /* lines per panel */
-		| (24 << 10) /* vsync pulse width - 1 */
-		| (2 << 16) /* eof pixel count */
-		| (0 << 24); /* bof pixel count */
-
-	LCCR3 = 2 /* pixel clock divisor */
-		| (24 << 8) /* AC Bias pin freq */
-		| LCCR3_16BPP /* BPP */
-		| LCCR3_PCP;  /* PCP falling edge */
-
-	/* setup dma descriptor */
-	par->metromem_desc->mFDADR0 = par->metromem_desc_dma;
-	par->metromem_desc->mFSADR0 = par->metromem_dma;
-	par->metromem_desc->mFIDR0 = 0;
-	par->metromem_desc->mLDCMD0 = epd_frame_table[0].fw
-					* epd_frame_table[0].fh;
-	/* reenable lcd controller */
-	metronome_enable_lcd_controller(par);
-}
-
 static int metronome_display_cmd(struct metronomefb_par *par)
 {
 	int i;
@@ -493,8 +301,7 @@ static int metronome_display_cmd(struct metronomefb_par *par)
 	par->metromem_cmd->csum = cs;
 	par->metromem_cmd->opcode = opcode; /* display cmd */
 
-	i = wait_event_interruptible_timeout(par->waitq, (GPLR1 & 0x01), HZ);
-	return i;
+	return par->board->met_wait_event_intr(par);
 }
 
 static int __devinit metronome_powerup_cmd(struct metronomefb_par *par)
@@ -518,13 +325,12 @@ static int __devinit metronome_powerup_cmd(struct metronomefb_par *par)
 	par->metromem_cmd->csum = cs;
 
 	msleep(1);
-	metronome_set_gpio_output(RST_GPIO_PIN, 1);
+	par->board->set_rst(par, 1);
 
 	msleep(1);
-	metronome_set_gpio_output(STDBY_GPIO_PIN, 1);
+	par->board->set_stdby(par, 1);
 
-	i = wait_event_timeout(par->waitq, (GPLR1 & 0x01), HZ);
-	return i;
+	return par->board->met_wait_event(par);
 }
 
 static int __devinit metronome_config_cmd(struct metronomefb_par *par)
@@ -569,8 +375,7 @@ static int __devinit metronome_config_cmd(struct metronomefb_par *par)
 	par->metromem_cmd->csum = cs;
 	par->metromem_cmd->opcode = 0xCC10; /* config cmd */
 
-	i = wait_event_timeout(par->waitq, (GPLR1 & 0x01), HZ);
-	return i;
+	return par->board->met_wait_event(par);
 }
 
 static int __devinit metronome_init_cmd(struct metronomefb_par *par)
@@ -596,16 +401,19 @@ static int __devinit metronome_init_cmd(struct metronomefb_par *par)
 	par->metromem_cmd->csum = cs;
 	par->metromem_cmd->opcode = 0xCC20; /* init cmd */
 
-	i = wait_event_timeout(par->waitq, (GPLR1 & 0x01), HZ);
-	return i;
+	return par->board->met_wait_event(par);
 }
 
 static int __devinit metronome_init_regs(struct metronomefb_par *par)
 {
 	int res;
 
-	metronome_init_gpio_regs();
-	metronome_init_lcdc_regs(par);
+	par->board->init_gpio_regs(par);
+
+	par->board->init_lcdc_regs(par);
+
+	/* now that lcd is setup, setup dma descriptor */
+	par->board->post_dma_setup(par);
 
 	res = metronome_powerup_cmd(par);
 	if (res)
@@ -616,8 +424,6 @@ static int __devinit metronome_init_regs(struct metronomefb_par *par)
 		return res;
 
 	res = metronome_init_cmd(par);
-	if (res)
-		return res;
 
 	return res;
 }
@@ -632,7 +438,7 @@ static void metronomefb_dpy_update(struct metronomefb_par *par)
 
 	cksum = calc_img_cksum((u16 *) par->metromem_img,
 				(epd_frame_table[0].fw * DPY_H)/2);
-	*((u16 *) (par->metromem_img) +
+	*((u16 *)(par->metromem_img) +
 			(epd_frame_table[0].fw * DPY_H)/2) = cksum;
 	metronome_display_cmd(par);
 }
@@ -641,8 +447,8 @@ static u16 metronomefb_dpy_update_page(struct metronomefb_par *par, int index)
 {
 	int i;
 	u16 csum = 0;
-	u16 *buf = (u16 __force *) (par->info->screen_base + index);
-	u16 *img = (u16 *) (par->metromem_img + index);
+	u16 *buf = (u16 __force *)(par->info->screen_base + index);
+	u16 *img = (u16 *)(par->metromem_img + index);
 
 	/* swizzle from vm to metromem and recalc cksum at the same time*/
 	for (i = 0; i < PAGE_SIZE/2; i++) {
@@ -678,7 +484,7 @@ static void metronomefb_fillrect(struct fb_info *info,
 {
 	struct metronomefb_par *par = info->par;
 
-	cfb_fillrect(info, rect);
+	sys_fillrect(info, rect);
 	metronomefb_dpy_update(par);
 }
 
@@ -687,7 +493,7 @@ static void metronomefb_copyarea(struct fb_info *info,
 {
 	struct metronomefb_par *par = info->par;
 
-	cfb_copyarea(info, area);
+	sys_copyarea(info, area);
 	metronomefb_dpy_update(par);
 }
 
@@ -696,7 +502,7 @@ static void metronomefb_imageblit(struct fb_info *info,
 {
 	struct metronomefb_par *par = info->par;
 
-	cfb_imageblit(info, image);
+	sys_imageblit(info, image);
 	metronomefb_dpy_update(par);
 }
 
@@ -733,7 +539,7 @@ static ssize_t metronomefb_write(struct fb_info *info, const char __user *buf,
 		count = total_size - p;
 	}
 
-	dst = (void __force *) (info->screen_base + p);
+	dst = (void __force *)(info->screen_base + p);
 
 	if (copy_from_user(dst, buf, count))
 		err = -EFAULT;
@@ -759,18 +565,10 @@ static struct fb_deferred_io metronomefb_defio = {
 	.deferred_io	= metronomefb_dpy_deferred_io,
 };
 
-static irqreturn_t metronome_handle_irq(int irq, void *dev_id)
-{
-	struct fb_info *info = dev_id;
-	struct metronomefb_par *par = info->par;
-
-	wake_up_interruptible(&par->waitq);
-	return IRQ_HANDLED;
-}
-
 static int __devinit metronomefb_probe(struct platform_device *dev)
 {
 	struct fb_info *info;
+	struct metronome_board *board;
 	int retval = -ENOMEM;
 	int videomemorysize;
 	unsigned char *videomemory;
@@ -779,17 +577,26 @@ static int __devinit metronomefb_probe(struct platform_device *dev)
 	int cmd_size, wfm_size, img_size, padding_size, totalsize;
 	int i;
 
+	/* pick up board specific routines */
+	board = dev->dev.platform_data;
+	if (!board)
+		return -EINVAL;
+
+	/* try to count device specific driver, if can't, platform recalls */
+	if (!try_module_get(board->owner))
+		return -ENODEV;
+
 	/* we have two blocks of memory.
 	info->screen_base which is vm, and is the fb used by apps.
 	par->metromem which is physically contiguous memory and
 	contains the display controller commands, waveform,
 	processed image data and padding. this is the data pulled
-	by the pxa255's LCD controller and pushed to Metronome */
+	by the device's LCD controller and pushed to Metronome */
 
 	videomemorysize = (DPY_W*DPY_H);
 	videomemory = vmalloc(videomemorysize);
 	if (!videomemory)
-		return retval;
+		return -ENOMEM;
 
 	memset(videomemory, 0, videomemorysize);
 
@@ -797,7 +604,7 @@ static int __devinit metronomefb_probe(struct platform_device *dev)
 	if (!info)
 		goto err_vfree;
 
-	info->screen_base = (char __iomem *) videomemory;
+	info->screen_base = (char __force __iomem *)videomemory;
 	info->fbops = &metronomefb_ops;
 
 	info->var = metronomefb_var;
@@ -805,6 +612,7 @@ static int __devinit metronomefb_probe(struct platform_device *dev)
 	info->fix.smem_len = videomemorysize;
 	par = info->par;
 	par->info = info;
+	par->board = board;
 	init_waitqueue_head(&par->waitq);
 
 	/* this table caches per page csum values. */
@@ -849,11 +657,10 @@ static int __devinit metronomefb_probe(struct platform_device *dev)
 	par->metromem_desc_dma = par->metromem_dma + cmd_size + wfm_size
 				 + img_size + padding_size;
 
-	/* load the waveform in. assume mode 3, temp 31 for now */
-	/* 	a) request the waveform file from userspace
+	/* load the waveform in. assume mode 3, temp 31 for now
+		a) request the waveform file from userspace
 		b) process waveform and decode into metromem */
-
-	retval = request_firmware(&fw_entry, "waveform.wbf", &dev->dev);
+	retval = request_firmware(&fw_entry, "metronome.wbf", &dev->dev);
 	if (retval < 0) {
 		printk(KERN_ERR "metronomefb: couldn't get waveform\n");
 		goto err_dma_free;
@@ -861,19 +668,14 @@ static int __devinit metronomefb_probe(struct platform_device *dev)
 
 	retval = load_waveform((u8 *) fw_entry->data, fw_entry->size,
 				par->metromem_wfm, 3, 31, &par->frame_count);
+	release_firmware(fw_entry);
 	if (retval < 0) {
 		printk(KERN_ERR "metronomefb: couldn't process waveform\n");
-		goto err_ld_wfm;
+		goto err_dma_free;
 	}
-	release_firmware(fw_entry);
 
-	retval = request_irq(IRQ_GPIO(RDY_GPIO_PIN), metronome_handle_irq,
-				IRQF_DISABLED, "Metronome", info);
-	if (retval) {
-		dev_err(&dev->dev, "request_irq failed: %d\n", retval);
-		goto err_ld_wfm;
-	}
-	set_irq_type(IRQ_GPIO(RDY_GPIO_PIN), IRQT_FALLING);
+	if (board->setup_irq(info))
+		goto err_dma_free;
 
 	retval = metronome_init_regs(par);
 	if (retval < 0)
@@ -913,9 +715,7 @@ static int __devinit metronomefb_probe(struct platform_device *dev)
 err_fb_rel:
 	framebuffer_release(info);
 err_free_irq:
-	free_irq(IRQ_GPIO(RDY_GPIO_PIN), info);
-err_ld_wfm:
-	release_firmware(fw_entry);
+	board->free_irq(info);
 err_dma_free:
 	dma_free_writecombine(&dev->dev, par->metromemsize, par->metromem,
 				par->metromem_dma);
@@ -923,6 +723,7 @@ static int __devinit metronomefb_probe(struct platform_device *dev)
 	vfree(par->csum_table);
 err_vfree:
 	vfree(videomemory);
+	module_put(board->owner);
 	return retval;
 }
 
@@ -939,7 +740,8 @@ static int __devexit metronomefb_remove(struct platform_device *dev)
 		vfree(par->csum_table);
 		unregister_framebuffer(info);
 		vfree((void __force *)info->screen_base);
-		free_irq(IRQ_GPIO(RDY_GPIO_PIN), info);
+		par->board->free_irq(info);
+		module_put(par->board->owner);
 		framebuffer_release(info);
 	}
 	return 0;
@@ -949,48 +751,21 @@ static struct platform_driver metronomefb_driver = {
 	.probe	= metronomefb_probe,
 	.remove = metronomefb_remove,
 	.driver	= {
+		.owner	= THIS_MODULE,
 		.name	= "metronomefb",
 	},
 };
 
-static struct platform_device *metronomefb_device;
-
 static int __init metronomefb_init(void)
 {
-	int ret;
-
-	if (!metronomefb_enable) {
-		printk(KERN_ERR
-			"Use metronomefb_enable to enable the device\n");
-		return -ENXIO;
-	}
-
-	ret = platform_driver_register(&metronomefb_driver);
-	if (!ret) {
-		metronomefb_device = platform_device_alloc("metronomefb", 0);
-		if (metronomefb_device)
-			ret = platform_device_add(metronomefb_device);
-		else
-			ret = -ENOMEM;
-
-		if (ret) {
-			platform_device_put(metronomefb_device);
-			platform_driver_unregister(&metronomefb_driver);
-		}
-	}
-	return ret;
-
+	return platform_driver_register(&metronomefb_driver);
 }
 
 static void __exit metronomefb_exit(void)
 {
-	platform_device_unregister(metronomefb_device);
 	platform_driver_unregister(&metronomefb_driver);
 }
 
-module_param(metronomefb_enable, uint, 0);
-MODULE_PARM_DESC(metronomefb_enable, "Enable communication with Metronome");
-
 module_init(metronomefb_init);
 module_exit(metronomefb_exit);
 
diff --git a/trunk/drivers/video/modedb.c b/trunk/drivers/video/modedb.c
index 08d072552233..473562191586 100644
--- a/trunk/drivers/video/modedb.c
+++ b/trunk/drivers/video/modedb.c
@@ -22,7 +22,7 @@
     ((v).xres == (x) && (v).yres == (y))
 
 #ifdef DEBUG
-#define DPRINTK(fmt, args...)	printk("modedb %s: " fmt, __FUNCTION__ , ## args)
+#define DPRINTK(fmt, args...)	printk("modedb %s: " fmt, __func__ , ## args)
 #else
 #define DPRINTK(fmt, args...)
 #endif
@@ -522,7 +522,7 @@ int fb_find_mode(struct fb_var_screeninfo *var,
 	int res_specified = 0, bpp_specified = 0, refresh_specified = 0;
 	unsigned int xres = 0, yres = 0, bpp = default_bpp, refresh = 0;
 	int yres_specified = 0, cvt = 0, rb = 0, interlace = 0, margins = 0;
-	u32 best, diff;
+	u32 best, diff, tdiff;
 
 	for (i = namelen-1; i >= 0; i--) {
 	    switch (name[i]) {
@@ -651,19 +651,27 @@ int fb_find_mode(struct fb_var_screeninfo *var,
 		return (refresh_specified) ? 2 : 1;
 	}
 
-	diff = xres + yres;
+	diff = 2 * (xres + yres);
 	best = -1;
 	DPRINTK("Trying best-fit modes\n");
 	for (i = 0; i < dbsize; i++) {
-	    if (xres <= db[i].xres && yres <= db[i].yres) {
 		DPRINTK("Trying %ix%i\n", db[i].xres, db[i].yres);
 		if (!fb_try_mode(var, info, &db[i], bpp)) {
-		    if (diff > (db[i].xres - xres) + (db[i].yres - yres)) {
-			diff = (db[i].xres - xres) + (db[i].yres - yres);
-			best = i;
-		    }
+			tdiff = abs(db[i].xres - xres) +
+				abs(db[i].yres - yres);
+
+			/*
+			 * Penalize modes with resolutions smaller
+			 * than requested.
+			 */
+			if (xres > db[i].xres || yres > db[i].yres)
+				tdiff += xres + yres;
+
+			if (diff > tdiff) {
+				diff = tdiff;
+				best = i;
+			}
 		}
-	    }
 	}
 	if (best != -1) {
 	    fb_try_mode(var, info, &db[best], bpp);
diff --git a/trunk/drivers/video/n411.c b/trunk/drivers/video/n411.c
new file mode 100644
index 000000000000..935830fea7b6
--- /dev/null
+++ b/trunk/drivers/video/n411.c
@@ -0,0 +1,202 @@
+/*
+ * linux/drivers/video/n411.c -- Platform device for N411 EPD kit
+ *
+ * Copyright (C) 2008, Jaya Kumar
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file COPYING in the main directory of this archive for
+ * more details.
+ *
+ * Layout is based on skeletonfb.c by James Simmons and Geert Uytterhoeven.
+ *
+ * This driver is written to be used with the Hecuba display controller
+ * board, and tested with the EInk 800x600 display in 1 bit mode.
+ * The interface between Hecuba and the host is TTL based GPIO. The
+ * GPIO requirements are 8 writable data lines and 6 lines for control.
+ * Only 4 of the controls are actually used here but 6 for future use.
+ * The driver requires the IO addresses for data and control GPIO at
+ * load time. It is also possible to use this display with a standard
+ * PC parallel port.
+ *
+ * General notes:
+ * - User must set dio_addr=0xIOADDR cio_addr=0xIOADDR c2io_addr=0xIOADDR
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/fb.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/list.h>
+#include <linux/uaccess.h>
+#include <linux/irq.h>
+
+#include <video/hecubafb.h>
+
+static unsigned long dio_addr;
+static unsigned long cio_addr;
+static unsigned long c2io_addr;
+static unsigned long splashval;
+static unsigned int nosplash;
+static unsigned char ctl;
+
+static void n411_set_ctl(struct hecubafb_par *par, unsigned char bit, unsigned
+							char state)
+{
+	switch (bit) {
+	case HCB_CD_BIT:
+		if (state)
+			ctl &= ~(HCB_CD_BIT);
+		else
+			ctl |= HCB_CD_BIT;
+		break;
+	case HCB_DS_BIT:
+		if (state)
+			ctl &= ~(HCB_DS_BIT);
+		else
+			ctl |= HCB_DS_BIT;
+		break;
+	}
+	outb(ctl, cio_addr);
+}
+
+static unsigned char n411_get_ctl(struct hecubafb_par *par)
+{
+	return inb(c2io_addr);
+}
+
+static void n411_set_data(struct hecubafb_par *par, unsigned char value)
+{
+	outb(value, dio_addr);
+}
+
+static void n411_wait_for_ack(struct hecubafb_par *par, int clear)
+{
+	int timeout;
+	unsigned char tmp;
+
+	timeout = 500;
+	do {
+		tmp = n411_get_ctl(par);
+		if ((tmp & HCB_ACK_BIT) && (!clear))
+			return;
+		else if (!(tmp & HCB_ACK_BIT) && (clear))
+			return;
+		udelay(1);
+	} while (timeout--);
+	printk(KERN_ERR "timed out waiting for ack\n");
+}
+
+static int n411_init_control(struct hecubafb_par *par)
+{
+	unsigned char tmp;
+	/* for init, we want the following setup to be set:
+	WUP = lo
+	ACK = hi
+	DS = hi
+	RW = hi
+	CD = lo
+	*/
+
+	/* write WUP to lo, DS to hi, RW to hi, CD to lo */
+	ctl = HCB_WUP_BIT | HCB_RW_BIT | HCB_CD_BIT ;
+	n411_set_ctl(par, HCB_DS_BIT, 1);
+
+	/* check ACK is not lo */
+	tmp = n411_get_ctl(par);
+	if (tmp & HCB_ACK_BIT) {
+		printk(KERN_ERR "Fail because ACK is already low\n");
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+
+static int n411_init_board(struct hecubafb_par *par)
+{
+	int retval;
+
+	retval = n411_init_control(par);
+	if (retval)
+		return retval;
+
+	par->send_command(par, APOLLO_INIT_DISPLAY);
+	par->send_data(par, 0x81);
+
+	/* have to wait while display resets */
+	udelay(1000);
+
+	/* if we were told to splash the screen, we just clear it */
+	if (!nosplash) {
+		par->send_command(par, APOLLO_ERASE_DISPLAY);
+		par->send_data(par, splashval);
+	}
+
+	return 0;
+}
+
+static struct hecuba_board n411_board = {
+	.owner			= THIS_MODULE,
+	.init			= n411_init_board,
+	.set_ctl		= n411_set_ctl,
+	.set_data		= n411_set_data,
+	.wait_for_ack		= n411_wait_for_ack,
+};
+
+static struct platform_device *n411_device;
+static int __init n411_init(void)
+{
+	int ret;
+	if (!dio_addr || !cio_addr || !c2io_addr) {
+		printk(KERN_WARNING "no IO addresses supplied\n");
+		return -EINVAL;
+	}
+
+	/* request our platform independent driver */
+	request_module("hecubafb");
+
+	n411_device = platform_device_alloc("hecubafb", -1);
+	if (!n411_device)
+		return -ENOMEM;
+
+	platform_device_add_data(n411_device, &n411_board, sizeof(n411_board));
+
+	/* this _add binds hecubafb to n411. hecubafb refcounts n411 */
+	ret = platform_device_add(n411_device);
+
+	if (ret)
+		platform_device_put(n411_device);
+
+	return ret;
+
+}
+
+static void __exit n411_exit(void)
+{
+	platform_device_unregister(n411_device);
+}
+
+module_init(n411_init);
+module_exit(n411_exit);
+
+module_param(nosplash, uint, 0);
+MODULE_PARM_DESC(nosplash, "Disable doing the splash screen");
+module_param(dio_addr, ulong, 0);
+MODULE_PARM_DESC(dio_addr, "IO address for data, eg: 0x480");
+module_param(cio_addr, ulong, 0);
+MODULE_PARM_DESC(cio_addr, "IO address for control, eg: 0x400");
+module_param(c2io_addr, ulong, 0);
+MODULE_PARM_DESC(c2io_addr, "IO address for secondary control, eg: 0x408");
+module_param(splashval, ulong, 0);
+MODULE_PARM_DESC(splashval, "Splash pattern: 0x00 is black, 0x01 is white");
+
+MODULE_DESCRIPTION("board driver for n411 hecuba/apollo epd kit");
+MODULE_AUTHOR("Jaya Kumar");
+MODULE_LICENSE("GPL");
+
diff --git a/trunk/drivers/video/nvidia/nv_hw.c b/trunk/drivers/video/nvidia/nv_hw.c
index d1a10549f543..ed20a9871b33 100644
--- a/trunk/drivers/video/nvidia/nv_hw.c
+++ b/trunk/drivers/video/nvidia/nv_hw.c
@@ -129,7 +129,7 @@ typedef struct {
 	int nvclk_khz;
 	char mem_page_miss;
 	char mem_latency;
-	int memory_type;
+	u32 memory_type;
 	int memory_width;
 	char enable_video;
 	char gr_during_vid;
@@ -719,7 +719,7 @@ static void nForceUpdateArbitrationSettings(unsigned VClk,
 	memctrl >>= 16;
 
 	if ((memctrl == 0x1A9) || (memctrl == 0x1AB) || (memctrl == 0x1ED)) {
-		int dimm[3];
+		u32 dimm[3];
 
 		dev = pci_get_bus_and_slot(0, 2);
 		pci_read_config_dword(dev, 0x40, &dimm[0]);
diff --git a/trunk/drivers/video/nvidia/nv_setup.c b/trunk/drivers/video/nvidia/nv_setup.c
index 82579d3a9970..d9627b57eb4d 100644
--- a/trunk/drivers/video/nvidia/nv_setup.c
+++ b/trunk/drivers/video/nvidia/nv_setup.c
@@ -265,12 +265,12 @@ static void nv10GetConfig(struct nvidia_par *par)
 
 	dev = pci_get_bus_and_slot(0, 1);
 	if ((par->Chipset & 0xffff) == 0x01a0) {
-		int amt = 0;
+		u32 amt;
 
 		pci_read_config_dword(dev, 0x7c, &amt);
 		par->RamAmountKBytes = (((amt >> 6) & 31) + 1) * 1024;
 	} else if ((par->Chipset & 0xffff) == 0x01f0) {
-		int amt = 0;
+		u32 amt;
 
 		pci_read_config_dword(dev, 0x84, &amt);
 		par->RamAmountKBytes = (((amt >> 4) & 127) + 1) * 1024;
diff --git a/trunk/drivers/video/nvidia/nvidia.c b/trunk/drivers/video/nvidia/nvidia.c
index 596652d2831f..9dbb5a5a267b 100644
--- a/trunk/drivers/video/nvidia/nvidia.c
+++ b/trunk/drivers/video/nvidia/nvidia.c
@@ -43,14 +43,14 @@
 #define NVTRACE          if (0) printk
 #endif
 
-#define NVTRACE_ENTER(...)  NVTRACE("%s START\n", __FUNCTION__)
-#define NVTRACE_LEAVE(...)  NVTRACE("%s END\n", __FUNCTION__)
+#define NVTRACE_ENTER(...)  NVTRACE("%s START\n", __func__)
+#define NVTRACE_LEAVE(...)  NVTRACE("%s END\n", __func__)
 
 #ifdef CONFIG_FB_NVIDIA_DEBUG
 #define assert(expr) \
 	if (!(expr)) { \
 	printk( "Assertion failed! %s,%s,%s,line=%d\n",\
-	#expr,__FILE__,__FUNCTION__,__LINE__); \
+	#expr,__FILE__,__func__,__LINE__); \
 	BUG(); \
 	}
 #else
@@ -1559,7 +1559,6 @@ static int __devinit nvidiafb_init(void)
 
 module_init(nvidiafb_init);
 
-#ifdef MODULE
 static void __exit nvidiafb_exit(void)
 {
 	pci_unregister_driver(&nvidiafb_driver);
@@ -1615,5 +1614,3 @@ MODULE_PARM_DESC(nomtrr, "Disables MTRR support (0 or 1=disabled) "
 MODULE_AUTHOR("Antonino Daplas");
 MODULE_DESCRIPTION("Framebuffer driver for nVidia graphics chipset");
 MODULE_LICENSE("GPL");
-#endif				/* MODULE */
-
diff --git a/trunk/drivers/video/offb.c b/trunk/drivers/video/offb.c
index 452433d46973..d7b3dcc0dc43 100644
--- a/trunk/drivers/video/offb.c
+++ b/trunk/drivers/video/offb.c
@@ -248,7 +248,7 @@ static void __iomem *offb_map_reg(struct device_node *np, int index,
 static void __init offb_init_fb(const char *name, const char *full_name,
 				int width, int height, int depth,
 				int pitch, unsigned long address,
-				struct device_node *dp)
+				int foreign_endian, struct device_node *dp)
 {
 	unsigned long res_size = pitch * height * (depth + 7) / 8;
 	struct offb_par *par = &default_par;
@@ -397,7 +397,7 @@ static void __init offb_init_fb(const char *name, const char *full_name,
 	info->screen_base = ioremap(address, fix->smem_len);
 	info->par = par;
 	info->pseudo_palette = (void *) (info + 1);
-	info->flags = FBINFO_DEFAULT;
+	info->flags = FBINFO_DEFAULT | foreign_endian;
 
 	fb_alloc_cmap(&info->cmap, 256, 0);
 
@@ -424,6 +424,15 @@ static void __init offb_init_nodriver(struct device_node *dp, int no_real_node)
 	u64 rstart, address = OF_BAD_ADDR;
 	const u32 *pp, *addrp, *up;
 	u64 asize;
+	int foreign_endian = 0;
+
+#ifdef __BIG_ENDIAN
+	if (of_get_property(dp, "little-endian", NULL))
+		foreign_endian = FBINFO_FOREIGN_ENDIAN;
+#else
+	if (of_get_property(dp, "big-endian", NULL))
+		foreign_endian = FBINFO_FOREIGN_ENDIAN;
+#endif
 
 	pp = of_get_property(dp, "linux,bootx-depth", &len);
 	if (pp == NULL)
@@ -509,7 +518,7 @@ static void __init offb_init_nodriver(struct device_node *dp, int no_real_node)
 		offb_init_fb(no_real_node ? "bootx" : dp->name,
 			     no_real_node ? "display" : dp->full_name,
 			     width, height, depth, pitch, address,
-			     no_real_node ? NULL : dp);
+			     foreign_endian, no_real_node ? NULL : dp);
 	}
 }
 
diff --git a/trunk/drivers/video/p9100.c b/trunk/drivers/video/p9100.c
index 58496061142d..c95874fe9076 100644
--- a/trunk/drivers/video/p9100.c
+++ b/trunk/drivers/video/p9100.c
@@ -310,7 +310,7 @@ static int __devinit p9100_probe(struct of_device *op, const struct of_device_id
 
 	dev_set_drvdata(&op->dev, info);
 
-	printk("%s: p9100 at %lx:%lx\n",
+	printk(KERN_INFO "%s: p9100 at %lx:%lx\n",
 	       dp->full_name,
 	       par->which_io, par->physbase);
 
diff --git a/trunk/drivers/video/pm2fb.c b/trunk/drivers/video/pm2fb.c
index 30181b593829..3f1ca2adda3d 100644
--- a/trunk/drivers/video/pm2fb.c
+++ b/trunk/drivers/video/pm2fb.c
@@ -56,7 +56,7 @@
 #undef PM2FB_MASTER_DEBUG
 #ifdef PM2FB_MASTER_DEBUG
 #define DPRINTK(a, b...)	\
-	printk(KERN_DEBUG "pm2fb: %s: " a, __FUNCTION__ , ## b)
+	printk(KERN_DEBUG "pm2fb: %s: " a, __func__ , ## b)
 #else
 #define DPRINTK(a, b...)
 #endif
@@ -67,7 +67,7 @@
  * Driver data
  */
 static int hwcursor = 1;
-static char *mode __devinitdata;
+static char *mode_option __devinitdata;
 
 /*
  * The XFree GLINT driver will (I think to implement hardware cursor
@@ -1680,17 +1680,19 @@ static int __devinit pm2fb_probe(struct pci_dev *pdev,
 		info->pixmap.scan_align = 1;
 	}
 
-	if (!mode)
-		mode = "640x480@60";
+	if (!mode_option)
+		mode_option = "640x480@60";
 
-	err = fb_find_mode(&info->var, info, mode, NULL, 0, NULL, 8);
+	err = fb_find_mode(&info->var, info, mode_option, NULL, 0, NULL, 8);
 	if (!err || err == 4)
 		info->var = pm2fb_var;
 
-	if (fb_alloc_cmap(&info->cmap, 256, 0) < 0)
+	retval = fb_alloc_cmap(&info->cmap, 256, 0);
+	if (retval < 0)
 		goto err_exit_both;
 
-	if (register_framebuffer(info) < 0)
+	retval = register_framebuffer(info);
+	if (retval < 0)
 		goto err_exit_all;
 
 	printk(KERN_INFO "fb%d: %s frame buffer device, memory = %dK.\n",
@@ -1797,7 +1799,7 @@ static int __init pm2fb_setup(char *options)
 		else if (!strncmp(this_opt, "noaccel", 7))
 			noaccel = 1;
 		else
-			mode = this_opt;
+			mode_option = this_opt;
 	}
 	return 0;
 }
@@ -1833,8 +1835,10 @@ static void __exit pm2fb_exit(void)
 #ifdef MODULE
 module_exit(pm2fb_exit);
 
-module_param(mode, charp, 0);
-MODULE_PARM_DESC(mode, "Preferred video mode e.g. '648x480-8@60'");
+module_param(mode_option, charp, 0);
+MODULE_PARM_DESC(mode_option, "Initial video mode e.g. '648x480-8@60'");
+module_param_named(mode, mode_option, charp, 0);
+MODULE_PARM_DESC(mode, "Initial video mode e.g. '648x480-8@60' (deprecated)");
 module_param(lowhsync, bool, 0);
 MODULE_PARM_DESC(lowhsync, "Force horizontal sync low regardless of mode");
 module_param(lowvsync, bool, 0);
diff --git a/trunk/drivers/video/pm3fb.c b/trunk/drivers/video/pm3fb.c
index 5dba8cdd0517..68089d1456c2 100644
--- a/trunk/drivers/video/pm3fb.c
+++ b/trunk/drivers/video/pm3fb.c
@@ -45,7 +45,7 @@
 #undef PM3FB_MASTER_DEBUG
 #ifdef PM3FB_MASTER_DEBUG
 #define DPRINTK(a, b...)	\
-	printk(KERN_DEBUG "pm3fb: %s: " a, __FUNCTION__ , ## b)
+	printk(KERN_DEBUG "pm3fb: %s: " a, __func__ , ## b)
 #else
 #define DPRINTK(a, b...)
 #endif
@@ -1571,6 +1571,8 @@ module_exit(pm3fb_exit);
 #endif
 module_init(pm3fb_init);
 
+module_param(mode_option, charp, 0);
+MODULE_PARM_DESC(mode_option, "Initial video mode e.g. '648x480-8@60'");
 module_param(noaccel, bool, 0);
 MODULE_PARM_DESC(noaccel, "Disable acceleration");
 module_param(hwcursor, int, 0644);
diff --git a/trunk/drivers/video/riva/fbdev.c b/trunk/drivers/video/riva/fbdev.c
index 5c47968e7f21..d94c57ffbdb1 100644
--- a/trunk/drivers/video/riva/fbdev.c
+++ b/trunk/drivers/video/riva/fbdev.c
@@ -56,10 +56,6 @@
 #include "rivafb.h"
 #include "nvreg.h"
 
-#ifndef CONFIG_PCI		/* sanity check */
-#error This driver requires PCI support.
-#endif
-
 /* version number of this driver */
 #define RIVAFB_VERSION "0.9.5b"
 
@@ -74,14 +70,14 @@
 #define NVTRACE          if(0) printk
 #endif
 
-#define NVTRACE_ENTER(...)  NVTRACE("%s START\n", __FUNCTION__)
-#define NVTRACE_LEAVE(...)  NVTRACE("%s END\n", __FUNCTION__)
+#define NVTRACE_ENTER(...)  NVTRACE("%s START\n", __func__)
+#define NVTRACE_LEAVE(...)  NVTRACE("%s END\n", __func__)
 
 #ifdef CONFIG_FB_RIVA_DEBUG
 #define assert(expr) \
 	if(!(expr)) { \
 	printk( "Assertion failed! %s,%s,%s,line=%d\n",\
-	#expr,__FILE__,__FUNCTION__,__LINE__); \
+	#expr,__FILE__,__func__,__LINE__); \
 	BUG(); \
 	}
 #else
@@ -2213,14 +2209,12 @@ static int __devinit rivafb_init(void)
 
 module_init(rivafb_init);
 
-#ifdef MODULE
 static void __exit rivafb_exit(void)
 {
 	pci_unregister_driver(&rivafb_driver);
 }
 
 module_exit(rivafb_exit);
-#endif /* MODULE */
 
 module_param(noaccel, bool, 0);
 MODULE_PARM_DESC(noaccel, "bool: disable acceleration");
diff --git a/trunk/drivers/video/riva/nv_driver.c b/trunk/drivers/video/riva/nv_driver.c
index a11026812d1b..f3694cf17e58 100644
--- a/trunk/drivers/video/riva/nv_driver.c
+++ b/trunk/drivers/video/riva/nv_driver.c
@@ -41,11 +41,6 @@
 #include "rivafb.h"
 #include "nvreg.h"
 
-
-#ifndef CONFIG_PCI		/* sanity check */
-#error This driver requires PCI support.
-#endif
-
 #define PFX "rivafb: "
 
 static inline unsigned char MISCin(struct riva_par *par)
@@ -163,7 +158,7 @@ unsigned long riva_get_memlen(struct riva_par *par)
 	unsigned long memlen = 0;
 	unsigned int chipset = par->Chipset;
 	struct pci_dev* dev;
-	int amt;
+	u32 amt;
 
 	switch (chip->Architecture) {
 	case NV_ARCH_03:
diff --git a/trunk/drivers/video/riva/riva_hw.c b/trunk/drivers/video/riva/riva_hw.c
index 13307703a9f0..78fdbf5178d7 100644
--- a/trunk/drivers/video/riva/riva_hw.c
+++ b/trunk/drivers/video/riva/riva_hw.c
@@ -231,7 +231,7 @@ typedef struct {
   int nvclk_khz;
   char mem_page_miss;
   char mem_latency;
-  int memory_type;
+  u32 memory_type;
   int memory_width;
   char enable_video;
   char gr_during_vid;
@@ -2107,7 +2107,7 @@ static void nv10GetConfig
 )
 {
     struct pci_dev* dev;
-    int amt;
+    u32 amt;
 
 #ifdef __BIG_ENDIAN
     /* turn on big endian register access */
diff --git a/trunk/drivers/video/s3c2410fb.c b/trunk/drivers/video/s3c2410fb.c
index 71fa6edb5c47..13b38cbbe4cf 100644
--- a/trunk/drivers/video/s3c2410fb.c
+++ b/trunk/drivers/video/s3c2410fb.c
@@ -430,9 +430,9 @@ static void s3c2410fb_activate_var(struct fb_info *info)
 	struct fb_var_screeninfo *var = &info->var;
 	int clkdiv = s3c2410fb_calc_pixclk(fbi, var->pixclock) / 2;
 
-	dprintk("%s: var->xres  = %d\n", __FUNCTION__, var->xres);
-	dprintk("%s: var->yres  = %d\n", __FUNCTION__, var->yres);
-	dprintk("%s: var->bpp   = %d\n", __FUNCTION__, var->bits_per_pixel);
+	dprintk("%s: var->xres  = %d\n", __func__, var->xres);
+	dprintk("%s: var->yres  = %d\n", __func__, var->yres);
+	dprintk("%s: var->bpp   = %d\n", __func__, var->bits_per_pixel);
 
 	if (type == S3C2410_LCDCON1_TFT) {
 		s3c2410fb_calculate_tft_lcd_regs(info, &fbi->regs);
diff --git a/trunk/drivers/video/s3fb.c b/trunk/drivers/video/s3fb.c
index 7d53bc23b9c7..2972f112dbed 100644
--- a/trunk/drivers/video/s3fb.c
+++ b/trunk/drivers/video/s3fb.c
@@ -132,10 +132,10 @@ static const struct svga_timing_regs s3_timing_regs     = {
 /* Module parameters */
 
 
-static char *mode = "640x480-8@60";
+static char *mode_option __devinitdata = "640x480-8@60";
 
 #ifdef CONFIG_MTRR
-static int mtrr = 1;
+static int mtrr __devinitdata = 1;
 #endif
 
 static int fasttext = 1;
@@ -145,8 +145,10 @@ MODULE_AUTHOR("(c) 2006-2007 Ondrej Zajicek <santiago@crfreenet.org>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("fbdev driver for S3 Trio/Virge");
 
-module_param(mode, charp, 0444);
-MODULE_PARM_DESC(mode, "Default video mode ('640x480-8@60', etc)");
+module_param(mode_option, charp, 0444);
+MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
+module_param_named(mode, mode_option, charp, 0444);
+MODULE_PARM_DESC(mode, "Default video mode ('640x480-8@60', etc) (deprecated)");
 
 #ifdef CONFIG_MTRR
 module_param(mtrr, int, 0444);
@@ -886,7 +888,7 @@ static int __devinit s3_pci_probe(struct pci_dev *dev, const struct pci_device_i
 	}
 
 	/* Allocate and fill driver data structure */
-	info = framebuffer_alloc(sizeof(struct s3fb_info), NULL);
+	info = framebuffer_alloc(sizeof(struct s3fb_info), &(dev->dev));
 	if (!info) {
 		dev_err(&(dev->dev), "cannot allocate memory\n");
 		return -ENOMEM;
@@ -901,13 +903,13 @@ static int __devinit s3_pci_probe(struct pci_dev *dev, const struct pci_device_i
 	/* Prepare PCI device */
 	rc = pci_enable_device(dev);
 	if (rc < 0) {
-		dev_err(&(dev->dev), "cannot enable PCI device\n");
+		dev_err(info->dev, "cannot enable PCI device\n");
 		goto err_enable_device;
 	}
 
 	rc = pci_request_regions(dev, "s3fb");
 	if (rc < 0) {
-		dev_err(&(dev->dev), "cannot reserve framebuffer region\n");
+		dev_err(info->dev, "cannot reserve framebuffer region\n");
 		goto err_request_regions;
 	}
 
@@ -919,7 +921,7 @@ static int __devinit s3_pci_probe(struct pci_dev *dev, const struct pci_device_i
 	info->screen_base = pci_iomap(dev, 0, 0);
 	if (! info->screen_base) {
 		rc = -ENOMEM;
-		dev_err(&(dev->dev), "iomap for framebuffer failed\n");
+		dev_err(info->dev, "iomap for framebuffer failed\n");
 		goto err_iomap;
 	}
 
@@ -960,22 +962,22 @@ static int __devinit s3_pci_probe(struct pci_dev *dev, const struct pci_device_i
 	info->pseudo_palette = (void*) (par->pseudo_palette);
 
 	/* Prepare startup mode */
-	rc = fb_find_mode(&(info->var), info, mode, NULL, 0, NULL, 8);
+	rc = fb_find_mode(&(info->var), info, mode_option, NULL, 0, NULL, 8);
 	if (! ((rc == 1) || (rc == 2))) {
 		rc = -EINVAL;
-		dev_err(&(dev->dev), "mode %s not found\n", mode);
+		dev_err(info->dev, "mode %s not found\n", mode_option);
 		goto err_find_mode;
 	}
 
 	rc = fb_alloc_cmap(&info->cmap, 256, 0);
 	if (rc < 0) {
-		dev_err(&(dev->dev), "cannot allocate colormap\n");
+		dev_err(info->dev, "cannot allocate colormap\n");
 		goto err_alloc_cmap;
 	}
 
 	rc = register_framebuffer(info);
 	if (rc < 0) {
-		dev_err(&(dev->dev), "cannot register framebuffer\n");
+		dev_err(info->dev, "cannot register framebuffer\n");
 		goto err_reg_fb;
 	}
 
@@ -1051,7 +1053,7 @@ static int s3_pci_suspend(struct pci_dev* dev, pm_message_t state)
 	struct fb_info *info = pci_get_drvdata(dev);
 	struct s3fb_info *par = info->par;
 
-	dev_info(&(dev->dev), "suspend\n");
+	dev_info(info->dev, "suspend\n");
 
 	acquire_console_sem();
 	mutex_lock(&(par->open_lock));
@@ -1083,7 +1085,7 @@ static int s3_pci_resume(struct pci_dev* dev)
 	struct s3fb_info *par = info->par;
 	int err;
 
-	dev_info(&(dev->dev), "resume\n");
+	dev_info(info->dev, "resume\n");
 
 	acquire_console_sem();
 	mutex_lock(&(par->open_lock));
@@ -1100,7 +1102,7 @@ static int s3_pci_resume(struct pci_dev* dev)
 	if (err) {
 		mutex_unlock(&(par->open_lock));
 		release_console_sem();
-		dev_err(&(dev->dev), "error %d enabling device for resume\n", err);
+		dev_err(info->dev, "error %d enabling device for resume\n", err);
 		return err;
 	}
 	pci_set_master(dev);
@@ -1168,7 +1170,7 @@ static int  __init s3fb_setup(char *options)
 		else if (!strncmp(opt, "fasttext:", 9))
 			fasttext = simple_strtoul(opt + 9, NULL, 0);
 		else
-			mode = opt;
+			mode_option = opt;
 	}
 
 	return 0;
diff --git a/trunk/drivers/video/sa1100fb.h b/trunk/drivers/video/sa1100fb.h
index 48066ef3af05..f465b27ed860 100644
--- a/trunk/drivers/video/sa1100fb.h
+++ b/trunk/drivers/video/sa1100fb.h
@@ -132,7 +132,7 @@ struct sa1100fb_info {
  *  Debug macros 
  */
 #if DEBUG
-#  define DPRINTK(fmt, args...)	printk("%s: " fmt, __FUNCTION__ , ## args)
+#  define DPRINTK(fmt, args...)	printk("%s: " fmt, __func__ , ## args)
 #else
 #  define DPRINTK(fmt, args...)
 #endif
diff --git a/trunk/drivers/video/savage/savagefb-i2c.c b/trunk/drivers/video/savage/savagefb-i2c.c
index 35c1ce62b216..783d4adffb93 100644
--- a/trunk/drivers/video/savage/savagefb-i2c.c
+++ b/trunk/drivers/video/savage/savagefb-i2c.c
@@ -140,7 +140,7 @@ static int savage_setup_i2c_bus(struct savagefb_i2c_chan *chan,
 		chan->adapter.id		= I2C_HW_B_SAVAGE;
 		chan->adapter.algo_data		= &chan->algo;
 		chan->adapter.dev.parent	= &chan->par->pcidev->dev;
-		chan->algo.udelay		= 40;
+		chan->algo.udelay		= 10;
 		chan->algo.timeout		= 20;
 		chan->algo.data 		= chan;
 
diff --git a/trunk/drivers/video/sis/sis.h b/trunk/drivers/video/sis/sis.h
index 9b05da6268f7..a14e82211037 100644
--- a/trunk/drivers/video/sis/sis.h
+++ b/trunk/drivers/video/sis/sis.h
@@ -55,7 +55,7 @@
 #undef SISFBDEBUG
 
 #ifdef SISFBDEBUG
-#define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt, __FUNCTION__ , ## args)
+#define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt, __func__ , ## args)
 #define TWDEBUG(x) printk(KERN_INFO x "\n");
 #else
 #define DPRINTK(fmt, args...)
diff --git a/trunk/drivers/video/sstfb.c b/trunk/drivers/video/sstfb.c
index 97784f9c184d..5b11a00f49bc 100644
--- a/trunk/drivers/video/sstfb.c
+++ b/trunk/drivers/video/sstfb.c
@@ -1006,7 +1006,7 @@ static int sst_set_pll_att_ti(struct fb_info *info,
 		break;
 	default:
 		dprintk("%s: wrong clock code '%d'\n",
-		        __FUNCTION__, clock);
+		        __func__, clock);
 		return 0;
 		}
 	udelay(300);
@@ -1048,7 +1048,7 @@ static int sst_set_pll_ics(struct fb_info *info,
 		break;
 	default:
 		dprintk("%s: wrong clock code '%d'\n",
-		        __FUNCTION__, clock);
+		        __func__, clock);
 		return 0;
 		}
 	udelay(300);
@@ -1079,7 +1079,7 @@ static void sst_set_vidmod_att_ti(struct fb_info *info, const int bpp)
 		sst_dac_write(DACREG_RMR, (cr0 & 0x0f) | DACREG_CR0_16BPP);
 		break;
 	default:
-		dprintk("%s: bad depth '%u'\n", __FUNCTION__, bpp);
+		dprintk("%s: bad depth '%u'\n", __func__, bpp);
 		break;
 	}
 }
@@ -1093,7 +1093,7 @@ static void sst_set_vidmod_ics(struct fb_info *info, const int bpp)
 		sst_dac_write(DACREG_ICS_CMD, DACREG_ICS_CMD_16BPP);
 		break;
 	default:
-		dprintk("%s: bad depth '%u'\n", __FUNCTION__, bpp);
+		dprintk("%s: bad depth '%u'\n", __func__, bpp);
 		break;
 	}
 }
@@ -1133,7 +1133,7 @@ static int __devinit sst_detect_dactype(struct fb_info *info, struct sstfb_par *
 	}
 	if (!ret)
 		return 0;
-	f_dprintk("%s found %s\n", __FUNCTION__, dacs[i].name);
+	f_dprintk("%s found %s\n", __func__, dacs[i].name);
 	par->dac_sw = dacs[i];
 	return 1;
 }
diff --git a/trunk/drivers/video/stifb.c b/trunk/drivers/video/stifb.c
index f98be301140c..598d35eff935 100644
--- a/trunk/drivers/video/stifb.c
+++ b/trunk/drivers/video/stifb.c
@@ -164,11 +164,11 @@ static int __initdata stifb_bpp_pref[MAX_STI_ROMS];
 # define  DEBUG_ON()  debug_on=1
 # define WRITE_BYTE(value,fb,reg)	do { if (debug_on) \
 						printk(KERN_DEBUG "%30s: WRITE_BYTE(0x%06x) = 0x%02x (old=0x%02x)\n", \
-							__FUNCTION__, reg, value, READ_BYTE(fb,reg)); 		  \
+							__func__, reg, value, READ_BYTE(fb,reg)); 		  \
 					gsc_writeb((value),(fb)->info.fix.mmio_start + (reg)); } while (0)
 # define WRITE_WORD(value,fb,reg)	do { if (debug_on) \
 						printk(KERN_DEBUG "%30s: WRITE_WORD(0x%06x) = 0x%08x (old=0x%08x)\n", \
-							__FUNCTION__, reg, value, READ_WORD(fb,reg)); 		  \
+							__func__, reg, value, READ_WORD(fb,reg)); 		  \
 					gsc_writel((value),(fb)->info.fix.mmio_start + (reg)); } while (0)
 #endif /* DEBUG_STIFB_REGS */
 
diff --git a/trunk/drivers/video/syscopyarea.c b/trunk/drivers/video/syscopyarea.c
index 37af10ab8f52..a352d5f46bbf 100644
--- a/trunk/drivers/video/syscopyarea.c
+++ b/trunk/drivers/video/syscopyarea.c
@@ -26,15 +26,15 @@
      */
 
 static void
-bitcpy(unsigned long *dst, int dst_idx, const unsigned long *src,
-	int src_idx, int bits, unsigned n)
+bitcpy(struct fb_info *p, unsigned long *dst, int dst_idx,
+		const unsigned long *src, int src_idx, int bits, unsigned n)
 {
 	unsigned long first, last;
 	int const shift = dst_idx-src_idx;
 	int left, right;
 
-	first = FB_SHIFT_HIGH(~0UL, dst_idx);
-	last = ~(FB_SHIFT_HIGH(~0UL, (dst_idx+n) % bits));
+	first = FB_SHIFT_HIGH(p, ~0UL, dst_idx);
+	last = ~(FB_SHIFT_HIGH(p, ~0UL, (dst_idx+n) % bits));
 
 	if (!shift) {
 		/* Same alignment for source and dest */
@@ -167,8 +167,8 @@ bitcpy(unsigned long *dst, int dst_idx, const unsigned long *src,
      */
 
 static void
-bitcpy_rev(unsigned long *dst, int dst_idx, const unsigned long *src,
-	   int src_idx, int bits, unsigned n)
+bitcpy_rev(struct fb_info *p, unsigned long *dst, int dst_idx,
+		const unsigned long *src, int src_idx, int bits, unsigned n)
 {
 	unsigned long first, last;
 	int shift;
@@ -186,8 +186,8 @@ bitcpy_rev(unsigned long *dst, int dst_idx, const unsigned long *src,
 
 	shift = dst_idx-src_idx;
 
-	first = FB_SHIFT_LOW(~0UL, bits - 1 - dst_idx);
-	last = ~(FB_SHIFT_LOW(~0UL, bits - 1 - ((dst_idx-n) % bits)));
+	first = FB_SHIFT_LOW(p, ~0UL, bits - 1 - dst_idx);
+	last = ~(FB_SHIFT_LOW(p, ~0UL, bits - 1 - ((dst_idx-n) % bits)));
 
 	if (!shift) {
 		/* Same alignment for source and dest */
@@ -353,7 +353,7 @@ void sys_copyarea(struct fb_info *p, const struct fb_copyarea *area)
 			dst_idx &= (bytes - 1);
 			src += src_idx >> (ffs(bits) - 1);
 			src_idx &= (bytes - 1);
-			bitcpy_rev(dst, dst_idx, src, src_idx, bits,
+			bitcpy_rev(p, dst, dst_idx, src, src_idx, bits,
 				width*p->var.bits_per_pixel);
 		}
 	} else {
@@ -362,7 +362,7 @@ void sys_copyarea(struct fb_info *p, const struct fb_copyarea *area)
 			dst_idx &= (bytes - 1);
 			src += src_idx >> (ffs(bits) - 1);
 			src_idx &= (bytes - 1);
-			bitcpy(dst, dst_idx, src, src_idx, bits,
+			bitcpy(p, dst, dst_idx, src, src_idx, bits,
 				width*p->var.bits_per_pixel);
 			dst_idx += bits_per_line;
 			src_idx += bits_per_line;
diff --git a/trunk/drivers/video/sysfillrect.c b/trunk/drivers/video/sysfillrect.c
index a261e9e6a675..f94d6b6e29ee 100644
--- a/trunk/drivers/video/sysfillrect.c
+++ b/trunk/drivers/video/sysfillrect.c
@@ -22,16 +22,16 @@
      */
 
 static void
-bitfill_aligned(unsigned long *dst, int dst_idx, unsigned long pat,
-		unsigned n, int bits)
+bitfill_aligned(struct fb_info *p, unsigned long *dst, int dst_idx,
+		unsigned long pat, unsigned n, int bits)
 {
 	unsigned long first, last;
 
 	if (!n)
 		return;
 
-	first = FB_SHIFT_HIGH(~0UL, dst_idx);
-	last = ~(FB_SHIFT_HIGH(~0UL, (dst_idx+n) % bits));
+	first = FB_SHIFT_HIGH(p, ~0UL, dst_idx);
+	last = ~(FB_SHIFT_HIGH(p, ~0UL, (dst_idx+n) % bits));
 
 	if (dst_idx+n <= bits) {
 		/* Single word */
@@ -78,16 +78,16 @@ bitfill_aligned(unsigned long *dst, int dst_idx, unsigned long pat,
      */
 
 static void
-bitfill_unaligned(unsigned long *dst, int dst_idx, unsigned long pat,
-		  int left, int right, unsigned n, int bits)
+bitfill_unaligned(struct fb_info *p, unsigned long *dst, int dst_idx,
+		  unsigned long pat, int left, int right, unsigned n, int bits)
 {
 	unsigned long first, last;
 
 	if (!n)
 		return;
 
-	first = FB_SHIFT_HIGH(~0UL, dst_idx);
-	last = ~(FB_SHIFT_HIGH(~0UL, (dst_idx+n) % bits));
+	first = FB_SHIFT_HIGH(p, ~0UL, dst_idx);
+	last = ~(FB_SHIFT_HIGH(p, ~0UL, (dst_idx+n) % bits));
 
 	if (dst_idx+n <= bits) {
 		/* Single word */
@@ -132,8 +132,8 @@ bitfill_unaligned(unsigned long *dst, int dst_idx, unsigned long pat,
      *  Aligned pattern invert using 32/64-bit memory accesses
      */
 static void
-bitfill_aligned_rev(unsigned long *dst, int dst_idx, unsigned long pat,
-		    unsigned n, int bits)
+bitfill_aligned_rev(struct fb_info *p, unsigned long *dst, int dst_idx,
+		    unsigned long pat, unsigned n, int bits)
 {
 	unsigned long val = pat;
 	unsigned long first, last;
@@ -141,8 +141,8 @@ bitfill_aligned_rev(unsigned long *dst, int dst_idx, unsigned long pat,
 	if (!n)
 		return;
 
-	first = FB_SHIFT_HIGH(~0UL, dst_idx);
-	last = ~(FB_SHIFT_HIGH(~0UL, (dst_idx+n) % bits));
+	first = FB_SHIFT_HIGH(p, ~0UL, dst_idx);
+	last = ~(FB_SHIFT_HIGH(p, ~0UL, (dst_idx+n) % bits));
 
 	if (dst_idx+n <= bits) {
 		/* Single word */
@@ -188,16 +188,17 @@ bitfill_aligned_rev(unsigned long *dst, int dst_idx, unsigned long pat,
      */
 
 static void
-bitfill_unaligned_rev(unsigned long *dst, int dst_idx, unsigned long pat,
-			int left, int right, unsigned n, int bits)
+bitfill_unaligned_rev(struct fb_info *p, unsigned long *dst, int dst_idx,
+		      unsigned long pat, int left, int right, unsigned n,
+		      int bits)
 {
 	unsigned long first, last;
 
 	if (!n)
 		return;
 
-	first = FB_SHIFT_HIGH(~0UL, dst_idx);
-	last = ~(FB_SHIFT_HIGH(~0UL, (dst_idx+n) % bits));
+	first = FB_SHIFT_HIGH(p, ~0UL, dst_idx);
+	last = ~(FB_SHIFT_HIGH(p, ~0UL, (dst_idx+n) % bits));
 
 	if (dst_idx+n <= bits) {
 		/* Single word */
@@ -267,9 +268,9 @@ void sys_fillrect(struct fb_info *p, const struct fb_fillrect *rect)
 	if (p->fbops->fb_sync)
 		p->fbops->fb_sync(p);
 	if (!left) {
-		void (*fill_op32)(unsigned long *dst, int dst_idx,
-		                  unsigned long pat, unsigned n, int bits) =
-			NULL;
+		void (*fill_op32)(struct fb_info *p, unsigned long *dst,
+				  int dst_idx, unsigned long pat, unsigned n,
+				  int bits) = NULL;
 
 		switch (rect->rop) {
 		case ROP_XOR:
@@ -287,16 +288,16 @@ void sys_fillrect(struct fb_info *p, const struct fb_fillrect *rect)
 		while (height--) {
 			dst += dst_idx >> (ffs(bits) - 1);
 			dst_idx &= (bits - 1);
-			fill_op32(dst, dst_idx, pat, width*bpp, bits);
+			fill_op32(p, dst, dst_idx, pat, width*bpp, bits);
 			dst_idx += p->fix.line_length*8;
 		}
 	} else {
 		int right;
 		int r;
 		int rot = (left-dst_idx) % bpp;
-		void (*fill_op)(unsigned long *dst, int dst_idx,
-		                unsigned long pat, int left, int right,
-		                unsigned n, int bits) = NULL;
+		void (*fill_op)(struct fb_info *p, unsigned long *dst,
+				int dst_idx, unsigned long pat, int left,
+				int right, unsigned n, int bits) = NULL;
 
 		/* rotate pattern to correct start position */
 		pat = pat << rot | pat >> (bpp-rot);
@@ -318,7 +319,7 @@ void sys_fillrect(struct fb_info *p, const struct fb_fillrect *rect)
 		while (height--) {
 			dst += dst_idx >> (ffs(bits) - 1);
 			dst_idx &= (bits - 1);
-			fill_op(dst, dst_idx, pat, left, right,
+			fill_op(p, dst, dst_idx, pat, left, right,
 				width*bpp, bits);
 			r = (p->fix.line_length*8) % bpp;
 			pat = pat << (bpp-r) | pat >> r;
diff --git a/trunk/drivers/video/sysimgblt.c b/trunk/drivers/video/sysimgblt.c
index bd7e7e9d155f..186c6f607be2 100644
--- a/trunk/drivers/video/sysimgblt.c
+++ b/trunk/drivers/video/sysimgblt.c
@@ -18,35 +18,31 @@
 #define DEBUG
 
 #ifdef DEBUG
-#define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt,__FUNCTION__,## args)
+#define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt,__func__,## args)
 #else
 #define DPRINTK(fmt, args...)
 #endif
 
-static const u32 cfb_tab8[] = {
-#if defined(__BIG_ENDIAN)
+static const u32 cfb_tab8_be[] = {
     0x00000000,0x000000ff,0x0000ff00,0x0000ffff,
     0x00ff0000,0x00ff00ff,0x00ffff00,0x00ffffff,
     0xff000000,0xff0000ff,0xff00ff00,0xff00ffff,
     0xffff0000,0xffff00ff,0xffffff00,0xffffffff
-#elif defined(__LITTLE_ENDIAN)
+};
+
+static const u32 cfb_tab8_le[] = {
     0x00000000,0xff000000,0x00ff0000,0xffff0000,
     0x0000ff00,0xff00ff00,0x00ffff00,0xffffff00,
     0x000000ff,0xff0000ff,0x00ff00ff,0xffff00ff,
     0x0000ffff,0xff00ffff,0x00ffffff,0xffffffff
-#else
-#error FIXME: No endianness??
-#endif
 };
 
-static const u32 cfb_tab16[] = {
-#if defined(__BIG_ENDIAN)
+static const u32 cfb_tab16_be[] = {
     0x00000000, 0x0000ffff, 0xffff0000, 0xffffffff
-#elif defined(__LITTLE_ENDIAN)
+};
+
+static const u32 cfb_tab16_le[] = {
     0x00000000, 0xffff0000, 0x0000ffff, 0xffffffff
-#else
-#error FIXME: No endianness??
-#endif
 };
 
 static const u32 cfb_tab32[] = {
@@ -72,7 +68,7 @@ static void color_imageblit(const struct fb_image *image, struct fb_info *p,
 		val = 0;
 
 		if (start_index) {
-			u32 start_mask = ~(FB_SHIFT_HIGH(~(u32)0,
+			u32 start_mask = ~(FB_SHIFT_HIGH(p, ~(u32)0,
 							 start_index));
 			val = *dst & start_mask;
 			shift = start_index;
@@ -83,20 +79,20 @@ static void color_imageblit(const struct fb_image *image, struct fb_info *p,
 				color = palette[*src];
 			else
 				color = *src;
-			color <<= FB_LEFT_POS(bpp);
-			val |= FB_SHIFT_HIGH(color, shift);
+			color <<= FB_LEFT_POS(p, bpp);
+			val |= FB_SHIFT_HIGH(p, color, shift);
 			if (shift >= null_bits) {
 				*dst++ = val;
 
 				val = (shift == null_bits) ? 0 :
-					FB_SHIFT_LOW(color, 32 - shift);
+					FB_SHIFT_LOW(p, color, 32 - shift);
 			}
 			shift += bpp;
 			shift &= (32 - 1);
 			src++;
 		}
 		if (shift) {
-			u32 end_mask = FB_SHIFT_HIGH(~(u32)0, shift);
+			u32 end_mask = FB_SHIFT_HIGH(p, ~(u32)0, shift);
 
 			*dst &= end_mask;
 			*dst |= val;
@@ -125,8 +121,8 @@ static void slow_imageblit(const struct fb_image *image, struct fb_info *p,
 	u32 i, j, l;
 
 	dst2 = dst1;
-	fgcolor <<= FB_LEFT_POS(bpp);
-	bgcolor <<= FB_LEFT_POS(bpp);
+	fgcolor <<= FB_LEFT_POS(p, bpp);
+	bgcolor <<= FB_LEFT_POS(p, bpp);
 
 	for (i = image->height; i--; ) {
 		shift = val = 0;
@@ -137,7 +133,8 @@ static void slow_imageblit(const struct fb_image *image, struct fb_info *p,
 
 		/* write leading bits */
 		if (start_index) {
-			u32 start_mask = ~(FB_SHIFT_HIGH(~(u32)0,start_index));
+			u32 start_mask = ~(FB_SHIFT_HIGH(p, ~(u32)0,
+							 start_index));
 			val = *dst & start_mask;
 			shift = start_index;
 		}
@@ -145,13 +142,13 @@ static void slow_imageblit(const struct fb_image *image, struct fb_info *p,
 		while (j--) {
 			l--;
 			color = (*s & (1 << l)) ? fgcolor : bgcolor;
-			val |= FB_SHIFT_HIGH(color, shift);
+			val |= FB_SHIFT_HIGH(p, color, shift);
 
 			/* Did the bitshift spill bits to the next long? */
 			if (shift >= null_bits) {
 				*dst++ = val;
 				val = (shift == null_bits) ? 0 :
-					FB_SHIFT_LOW(color,32 - shift);
+					FB_SHIFT_LOW(p, color, 32 - shift);
 			}
 			shift += bpp;
 			shift &= (32 - 1);
@@ -160,7 +157,7 @@ static void slow_imageblit(const struct fb_image *image, struct fb_info *p,
 
 		/* write trailing bits */
  		if (shift) {
-			u32 end_mask = FB_SHIFT_HIGH(~(u32)0, shift);
+			u32 end_mask = FB_SHIFT_HIGH(p, ~(u32)0, shift);
 
 			*dst &= end_mask;
 			*dst |= val;
@@ -199,10 +196,10 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p,
 
 	switch (bpp) {
 	case 8:
-		tab = cfb_tab8;
+		tab = fb_be_math(p) ? cfb_tab8_be : cfb_tab8_le;
 		break;
 	case 16:
-		tab = cfb_tab16;
+		tab = fb_be_math(p) ? cfb_tab16_be : cfb_tab16_le;
 		break;
 	case 32:
 	default:
diff --git a/trunk/drivers/video/tcx.c b/trunk/drivers/video/tcx.c
index e5a9ddb3c8be..a71774305772 100644
--- a/trunk/drivers/video/tcx.c
+++ b/trunk/drivers/video/tcx.c
@@ -419,7 +419,7 @@ static int __devinit tcx_init_one(struct of_device *op)
 		par->mmap_map[6].size = SBUS_MMAP_EMPTY;
 	}
 
-	par->physbase = 0;
+	par->physbase = op->resource[0].start;
 	par->which_io = op->resource[0].flags & IORESOURCE_BITS;
 
 	for (i = 0; i < TCX_MMAP_ENTRIES; i++) {
@@ -470,10 +470,10 @@ static int __devinit tcx_init_one(struct of_device *op)
 
 	dev_set_drvdata(&op->dev, info);
 
-	printk("%s: TCX at %lx:%lx, %s\n",
+	printk(KERN_INFO "%s: TCX at %lx:%lx, %s\n",
 	       dp->full_name,
 	       par->which_io,
-	       op->resource[0].start,
+	       par->physbase,
 	       par->lowdepth ? "8-bit only" : "24-bit depth");
 
 	return 0;
@@ -527,7 +527,7 @@ static struct of_platform_driver tcx_driver = {
 	.remove		= __devexit_p(tcx_remove),
 };
 
-int __init tcx_init(void)
+static int __init tcx_init(void)
 {
 	if (fb_get_options("tcxfb", NULL))
 		return -ENODEV;
@@ -535,7 +535,7 @@ int __init tcx_init(void)
 	return of_register_driver(&tcx_driver, &of_bus_type);
 }
 
-void __exit tcx_exit(void)
+static void __exit tcx_exit(void)
 {
 	of_unregister_driver(&tcx_driver);
 }
diff --git a/trunk/drivers/video/tdfxfb.c b/trunk/drivers/video/tdfxfb.c
index 71e179ea5f95..ea9f19d25597 100644
--- a/trunk/drivers/video/tdfxfb.c
+++ b/trunk/drivers/video/tdfxfb.c
@@ -70,7 +70,7 @@
 
 #include <video/tdfx.h>
 
-#define DPRINTK(a, b...) pr_debug("fb: %s: " a, __FUNCTION__ , ## b)
+#define DPRINTK(a, b...) pr_debug("fb: %s: " a, __func__ , ## b)
 
 #ifdef CONFIG_MTRR
 #include <asm/mtrr.h>
diff --git a/trunk/drivers/video/tridentfb.c b/trunk/drivers/video/tridentfb.c
index 0a4e07d43d2d..bd54cd0de39a 100644
--- a/trunk/drivers/video/tridentfb.c
+++ b/trunk/drivers/video/tridentfb.c
@@ -58,7 +58,7 @@ static int displaytype;
 /* defaults which are normally overriden by user values */
 
 /* video mode */
-static char *mode = "640x480";
+static char *mode_option __devinitdata = "640x480";
 static int bpp = 8;
 
 static int noaccel;
@@ -73,7 +73,10 @@ static int memsize;
 static int memdiff;
 static int nativex;
 
-module_param(mode, charp, 0);
+module_param(mode_option, charp, 0);
+MODULE_PARM_DESC(mode_option, "Initial video mode e.g. '648x480-8@60'");
+module_param_named(mode, mode_option, charp, 0);
+MODULE_PARM_DESC(mode, "Initial video mode e.g. '648x480-8@60' (deprecated)");
 module_param(bpp, int, 0);
 module_param(center, int, 0);
 module_param(stretch, int, 0);
@@ -1297,7 +1300,8 @@ static int __devinit trident_pci_probe(struct pci_dev * dev,
 #endif
 	fb_info.pseudo_palette = pseudo_pal;
 
-	if (!fb_find_mode(&default_var, &fb_info, mode, NULL, 0, NULL, bpp)) {
+	if (!fb_find_mode(&default_var, &fb_info,
+			  mode_option, NULL, 0, NULL, bpp)) {
 		err = -EINVAL;
 		goto out_unmap2;
 	}
@@ -1385,7 +1389,7 @@ static struct pci_driver tridentfb_pci_driver = {
  *	video=trident:800x600,bpp=16,noaccel
  */
 #ifndef MODULE
-static int tridentfb_setup(char *options)
+static int __init tridentfb_setup(char *options)
 {
 	char *opt;
 	if (!options || !*options)
@@ -1412,7 +1416,7 @@ static int tridentfb_setup(char *options)
 		else if (!strncmp(opt, "nativex=", 8))
 			nativex = simple_strtoul(opt + 8, NULL, 0);
 		else
-			mode = opt;
+			mode_option = opt;
 	}
 	return 0;
 }
diff --git a/trunk/drivers/video/uvesafb.c b/trunk/drivers/video/uvesafb.c
index 93361656316c..cdbb56edb6cb 100644
--- a/trunk/drivers/video/uvesafb.c
+++ b/trunk/drivers/video/uvesafb.c
@@ -181,7 +181,8 @@ static int uvesafb_exec(struct uvesafb_ktask *task)
 	/* If all slots are taken -- bail out. */
 	if (uvfb_tasks[seq]) {
 		mutex_unlock(&uvfb_lock);
-		return -EBUSY;
+		err = -EBUSY;
+		goto out;
 	}
 
 	/* Save a pointer to the kernel part of the task struct. */
@@ -205,7 +206,6 @@ static int uvesafb_exec(struct uvesafb_ktask *task)
 			err = cn_netlink_send(m, 0, gfp_any());
 		}
 	}
-	kfree(m);
 
 	if (!err && !(task->t.flags & TF_EXIT))
 		err = !wait_for_completion_timeout(task->done,
@@ -218,7 +218,8 @@ static int uvesafb_exec(struct uvesafb_ktask *task)
 	seq++;
 	if (seq >= UVESAFB_TASKS_MAX)
 		seq = 0;
-
+out:
+	kfree(m);
 	return err;
 }
 
@@ -885,7 +886,7 @@ static int __devinit uvesafb_vbe_init_mode(struct fb_info *info)
 	}
 
 	/* fb_find_mode() failed */
-	if (i == 0 || i >= 3) {
+	if (i == 0) {
 		info->var.xres = 640;
 		info->var.yres = 480;
 		mode = (struct fb_videomode *)
diff --git a/trunk/drivers/video/vermilion/vermilion.c b/trunk/drivers/video/vermilion/vermilion.c
index 2aa71eb67c2b..c18f1884b550 100644
--- a/trunk/drivers/video/vermilion/vermilion.c
+++ b/trunk/drivers/video/vermilion/vermilion.c
@@ -112,8 +112,9 @@ static int vmlfb_alloc_vram_area(struct vram_area *va, unsigned max_order,
 
 	/*
 	 * It seems like __get_free_pages only ups the usage count
-	 * of the first page. This doesn't work with nopage mapping, so
-	 * up the usage count once more.
+	 * of the first page. This doesn't work with fault mapping, so
+	 * up the usage count once more (XXX: should use split_page or
+	 * compound page).
 	 */
 
 	memset((void *)va->logical, 0x00, va->size);
diff --git a/trunk/drivers/video/vt8623fb.c b/trunk/drivers/video/vt8623fb.c
index 4c3a63308df1..536ab11623f0 100644
--- a/trunk/drivers/video/vt8623fb.c
+++ b/trunk/drivers/video/vt8623fb.c
@@ -100,7 +100,7 @@ static struct svga_timing_regs vt8623_timing_regs     = {
 
 /* Module parameters */
 
-static char *mode = "640x480-8@60";
+static char *mode_option = "640x480-8@60";
 
 #ifdef CONFIG_MTRR
 static int mtrr = 1;
@@ -110,8 +110,10 @@ MODULE_AUTHOR("(c) 2006 Ondrej Zajicek <santiago@crfreenet.org>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("fbdev driver for integrated graphics core in VIA VT8623 [CLE266]");
 
-module_param(mode, charp, 0644);
-MODULE_PARM_DESC(mode, "Default video mode ('640x480-8@60', etc)");
+module_param(mode_option, charp, 0644);
+MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
+module_param_named(mode, mode_option, charp, 0);
+MODULE_PARM_DESC(mode, "Default video mode e.g. '648x480-8@60' (deprecated)");
 
 #ifdef CONFIG_MTRR
 module_param(mtrr, int, 0444);
@@ -434,6 +436,10 @@ static int vt8623fb_set_par(struct fb_info *info)
 	svga_wcrt_multi(vt8623_offset_regs, offset_value);
 	svga_wseq_multi(vt8623_fetch_count_regs, fetch_value);
 
+	/* Clear H/V Skew */
+	svga_wcrt_mask(0x03, 0x00, 0x60);
+	svga_wcrt_mask(0x05, 0x00, 0x60);
+
 	if (info->var.vmode & FB_VMODE_DOUBLE)
 		svga_wcrt_mask(0x09, 0x80, 0x80);
 	else
@@ -655,7 +661,7 @@ static int __devinit vt8623_pci_probe(struct pci_dev *dev, const struct pci_devi
 	}
 
 	/* Allocate and fill driver data structure */
-	info = framebuffer_alloc(sizeof(struct vt8623fb_info), NULL);
+	info = framebuffer_alloc(sizeof(struct vt8623fb_info), &(dev->dev));
 	if (! info) {
 		dev_err(&(dev->dev), "cannot allocate memory\n");
 		return -ENOMEM;
@@ -671,13 +677,13 @@ static int __devinit vt8623_pci_probe(struct pci_dev *dev, const struct pci_devi
 
 	rc = pci_enable_device(dev);
 	if (rc < 0) {
-		dev_err(&(dev->dev), "cannot enable PCI device\n");
+		dev_err(info->dev, "cannot enable PCI device\n");
 		goto err_enable_device;
 	}
 
 	rc = pci_request_regions(dev, "vt8623fb");
 	if (rc < 0) {
-		dev_err(&(dev->dev), "cannot reserve framebuffer region\n");
+		dev_err(info->dev, "cannot reserve framebuffer region\n");
 		goto err_request_regions;
 	}
 
@@ -690,14 +696,14 @@ static int __devinit vt8623_pci_probe(struct pci_dev *dev, const struct pci_devi
 	info->screen_base = pci_iomap(dev, 0, 0);
 	if (! info->screen_base) {
 		rc = -ENOMEM;
-		dev_err(&(dev->dev), "iomap for framebuffer failed\n");
+		dev_err(info->dev, "iomap for framebuffer failed\n");
 		goto err_iomap_1;
 	}
 
 	par->mmio_base = pci_iomap(dev, 1, 0);
 	if (! par->mmio_base) {
 		rc = -ENOMEM;
-		dev_err(&(dev->dev), "iomap for MMIO failed\n");
+		dev_err(info->dev, "iomap for MMIO failed\n");
 		goto err_iomap_2;
 	}
 
@@ -708,7 +714,7 @@ static int __devinit vt8623_pci_probe(struct pci_dev *dev, const struct pci_devi
 	if ((16 <= memsize1) && (memsize1 <= 64) && (memsize1 == memsize2))
 		info->screen_size = memsize1 << 20;
 	else {
-		dev_err(&(dev->dev), "memory size detection failed (%x %x), suppose 16 MB\n", memsize1, memsize2);
+		dev_err(info->dev, "memory size detection failed (%x %x), suppose 16 MB\n", memsize1, memsize2);
 		info->screen_size = 16 << 20;
 	}
 
@@ -722,22 +728,22 @@ static int __devinit vt8623_pci_probe(struct pci_dev *dev, const struct pci_devi
 
 	/* Prepare startup mode */
 
-	rc = fb_find_mode(&(info->var), info, mode, NULL, 0, NULL, 8);
+	rc = fb_find_mode(&(info->var), info, mode_option, NULL, 0, NULL, 8);
 	if (! ((rc == 1) || (rc == 2))) {
 		rc = -EINVAL;
-		dev_err(&(dev->dev), "mode %s not found\n", mode);
+		dev_err(info->dev, "mode %s not found\n", mode_option);
 		goto err_find_mode;
 	}
 
 	rc = fb_alloc_cmap(&info->cmap, 256, 0);
 	if (rc < 0) {
-		dev_err(&(dev->dev), "cannot allocate colormap\n");
+		dev_err(info->dev, "cannot allocate colormap\n");
 		goto err_alloc_cmap;
 	}
 
 	rc = register_framebuffer(info);
 	if (rc < 0) {
-		dev_err(&(dev->dev), "cannot register framebugger\n");
+		dev_err(info->dev, "cannot register framebugger\n");
 		goto err_reg_fb;
 	}
 
@@ -811,7 +817,7 @@ static int vt8623_pci_suspend(struct pci_dev* dev, pm_message_t state)
 	struct fb_info *info = pci_get_drvdata(dev);
 	struct vt8623fb_info *par = info->par;
 
-	dev_info(&(dev->dev), "suspend\n");
+	dev_info(info->dev, "suspend\n");
 
 	acquire_console_sem();
 	mutex_lock(&(par->open_lock));
@@ -842,7 +848,7 @@ static int vt8623_pci_resume(struct pci_dev* dev)
 	struct fb_info *info = pci_get_drvdata(dev);
 	struct vt8623fb_info *par = info->par;
 
-	dev_info(&(dev->dev), "resume\n");
+	dev_info(info->dev, "resume\n");
 
 	acquire_console_sem();
 	mutex_lock(&(par->open_lock));
@@ -913,7 +919,7 @@ static int __init vt8623fb_init(void)
 		return -ENODEV;
 
 	if (option && *option)
-		mode = option;
+		mode_option = option;
 #endif
 
 	pr_debug("vt8623fb: initializing\n");
diff --git a/trunk/drivers/video/w100fb.c b/trunk/drivers/video/w100fb.c
index 003c49a490eb..30469bf906e5 100644
--- a/trunk/drivers/video/w100fb.c
+++ b/trunk/drivers/video/w100fb.c
@@ -765,8 +765,10 @@ int __init w100fb_probe(struct platform_device *pdev)
 	printk(KERN_INFO "fb%d: %s frame buffer device\n", info->node, info->fix.id);
 	return 0;
 out:
-	fb_dealloc_cmap(&info->cmap);
-	kfree(info->pseudo_palette);
+	if (info) {
+		fb_dealloc_cmap(&info->cmap);
+		kfree(info->pseudo_palette);
+	}
 	if (remapped_fbuf != NULL)
 		iounmap(remapped_fbuf);
 	if (remapped_regs != NULL)
diff --git a/trunk/drivers/zorro/proc.c b/trunk/drivers/zorro/proc.c
index 2ce4cebc31d9..099b6fb5b5cb 100644
--- a/trunk/drivers/zorro/proc.c
+++ b/trunk/drivers/zorro/proc.c
@@ -13,6 +13,7 @@
 #include <linux/types.h>
 #include <linux/zorro.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/smp_lock.h>
 #include <asm/uaccess.h>
@@ -76,36 +77,58 @@ proc_bus_zorro_read(struct file *file, char __user *buf, size_t nbytes, loff_t *
 }
 
 static const struct file_operations proc_bus_zorro_operations = {
+	.owner		= THIS_MODULE,
 	.llseek		= proc_bus_zorro_lseek,
 	.read		= proc_bus_zorro_read,
 };
 
-static int
-get_zorro_dev_info(char *buf, char **start, off_t pos, int count)
+static void * zorro_seq_start(struct seq_file *m, loff_t *pos)
 {
-	u_int slot;
-	off_t at = 0;
-	int len, cnt;
-
-	for (slot = cnt = 0; slot < zorro_num_autocon && count > cnt; slot++) {
-		struct zorro_dev *z = &zorro_autocon[slot];
-		len = sprintf(buf, "%02x\t%08x\t%08lx\t%08lx\t%02x\n", slot,
-			      z->id, (unsigned long)zorro_resource_start(z),
-			      (unsigned long)zorro_resource_len(z),
-			      z->rom.er_Type);
-		at += len;
-		if (at >= pos) {
-			if (!*start) {
-				*start = buf + (pos - (at - len));
-				cnt = at - pos;
-			} else
-				cnt += len;
-			buf += len;
-		}
-	}
-	return (count > cnt) ? cnt : count;
+	return (*pos < zorro_num_autocon) ? pos : NULL;
+}
+
+static void * zorro_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return (*pos < zorro_num_autocon) ? pos : NULL;
+}
+
+static void zorro_seq_stop(struct seq_file *m, void *v)
+{
+}
+
+static int zorro_seq_show(struct seq_file *m, void *v)
+{
+	u_int slot = *(loff_t *)v;
+	struct zorro_dev *z = &zorro_autocon[slot];
+
+	seq_printf(m, "%02x\t%08x\t%08lx\t%08lx\t%02x\n", slot, z->id,
+		   (unsigned long)zorro_resource_start(z),
+		   (unsigned long)zorro_resource_len(z),
+		   z->rom.er_Type);
+	return 0;
+}
+
+static const struct seq_operations zorro_devices_seq_ops = {
+	.start = zorro_seq_start,
+	.next  = zorro_seq_next,
+	.stop  = zorro_seq_stop,
+	.show  = zorro_seq_show,
+};
+
+static int zorro_devices_proc_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &zorro_devices_seq_ops);
 }
 
+static const struct file_operations zorro_devices_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= zorro_devices_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
 static struct proc_dir_entry *proc_bus_zorro_dir;
 
 static int __init zorro_proc_attach_device(u_int slot)
@@ -114,11 +137,11 @@ static int __init zorro_proc_attach_device(u_int slot)
 	char name[4];
 
 	sprintf(name, "%02x", slot);
-	entry = create_proc_entry(name, 0, proc_bus_zorro_dir);
+	entry = proc_create_data(name, 0, proc_bus_zorro_dir,
+				 &proc_bus_zorro_operations,
+				 &zorro_autocon[slot]);
 	if (!entry)
 		return -ENOMEM;
-	entry->proc_fops = &proc_bus_zorro_operations;
-	entry->data = &zorro_autocon[slot];
 	entry->size = sizeof(struct zorro_dev);
 	return 0;
 }
@@ -128,9 +151,9 @@ static int __init zorro_proc_init(void)
 	u_int slot;
 
 	if (MACH_IS_AMIGA && AMIGAHW_PRESENT(ZORRO)) {
-		proc_bus_zorro_dir = proc_mkdir("zorro", proc_bus);
-		create_proc_info_entry("devices", 0, proc_bus_zorro_dir,
-				       get_zorro_dev_info);
+		proc_bus_zorro_dir = proc_mkdir("bus/zorro", NULL);
+		proc_create("devices", 0, proc_bus_zorro_dir,
+			    &zorro_devices_proc_fops);
 		for (slot = 0; slot < zorro_num_autocon; slot++)
 			zorro_proc_attach_device(slot);
 	}
diff --git a/trunk/fs/Kconfig.binfmt b/trunk/fs/Kconfig.binfmt
index 853845abcca6..55e8ee1900a5 100644
--- a/trunk/fs/Kconfig.binfmt
+++ b/trunk/fs/Kconfig.binfmt
@@ -41,7 +41,7 @@ config BINFMT_ELF_FDPIC
 	  It is also possible to run FDPIC ELF binaries on MMU linux also.
 
 config BINFMT_FLAT
-	tristate "Kernel support for flat binaries"
+	bool "Kernel support for flat binaries"
 	depends on !MMU
 	help
 	  Support uClinux FLAT format binaries.
diff --git a/trunk/fs/adfs/dir_f.c b/trunk/fs/adfs/dir_f.c
index b9b2b27b68c3..ea7df2146921 100644
--- a/trunk/fs/adfs/dir_f.c
+++ b/trunk/fs/adfs/dir_f.c
@@ -122,9 +122,9 @@ adfs_dir_checkbyte(const struct adfs_dir *dir)
 		ptr.ptr8 = bufoff(bh, i);
 		end.ptr8 = ptr.ptr8 + last - i;
 
-		do
+		do {
 			dircheck = *ptr.ptr8++ ^ ror13(dircheck);
-		while (ptr.ptr8 < end.ptr8);
+		} while (ptr.ptr8 < end.ptr8);
 	}
 
 	/*
diff --git a/trunk/fs/affs/file.c b/trunk/fs/affs/file.c
index 6e0c9399200e..e87ede608f77 100644
--- a/trunk/fs/affs/file.c
+++ b/trunk/fs/affs/file.c
@@ -325,8 +325,7 @@ affs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_resul
 	pr_debug("AFFS: get_block(%u, %lu)\n", (u32)inode->i_ino, (unsigned long)block);
 
 
-	if (block > (sector_t)0x7fffffffUL)
-		BUG();
+	BUG_ON(block > (sector_t)0x7fffffffUL);
 
 	if (block >= AFFS_I(inode)->i_blkcnt) {
 		if (block > AFFS_I(inode)->i_blkcnt || !create)
@@ -493,8 +492,7 @@ affs_do_readpage_ofs(struct file *file, struct page *page, unsigned from, unsign
 	u32 tmp;
 
 	pr_debug("AFFS: read_page(%u, %ld, %d, %d)\n", (u32)inode->i_ino, page->index, from, to);
-	if (from > to || to > PAGE_CACHE_SIZE)
-		BUG();
+	BUG_ON(from > to || to > PAGE_CACHE_SIZE);
 	kmap(page);
 	data = page_address(page);
 	bsize = AFFS_SB(sb)->s_data_blksize;
@@ -507,8 +505,7 @@ affs_do_readpage_ofs(struct file *file, struct page *page, unsigned from, unsign
 		if (IS_ERR(bh))
 			return PTR_ERR(bh);
 		tmp = min(bsize - boff, to - from);
-		if (from + tmp > to || tmp > bsize)
-			BUG();
+		BUG_ON(from + tmp > to || tmp > bsize);
 		memcpy(data + from, AFFS_DATA(bh) + boff, tmp);
 		affs_brelse(bh);
 		bidx++;
@@ -540,8 +537,7 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
 		if (IS_ERR(bh))
 			return PTR_ERR(bh);
 		tmp = min(bsize - boff, newsize - size);
-		if (boff + tmp > bsize || tmp > bsize)
-			BUG();
+		BUG_ON(boff + tmp > bsize || tmp > bsize);
 		memset(AFFS_DATA(bh) + boff, 0, tmp);
 		AFFS_DATA_HEAD(bh)->size = cpu_to_be32(be32_to_cpu(AFFS_DATA_HEAD(bh)->size) + tmp);
 		affs_fix_checksum(sb, bh);
@@ -560,8 +556,7 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
 		if (IS_ERR(bh))
 			goto out;
 		tmp = min(bsize, newsize - size);
-		if (tmp > bsize)
-			BUG();
+		BUG_ON(tmp > bsize);
 		AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
 		AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino);
 		AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx);
@@ -683,8 +678,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 		if (IS_ERR(bh))
 			return PTR_ERR(bh);
 		tmp = min(bsize - boff, to - from);
-		if (boff + tmp > bsize || tmp > bsize)
-			BUG();
+		BUG_ON(boff + tmp > bsize || tmp > bsize);
 		memcpy(AFFS_DATA(bh) + boff, data + from, tmp);
 		AFFS_DATA_HEAD(bh)->size = cpu_to_be32(be32_to_cpu(AFFS_DATA_HEAD(bh)->size) + tmp);
 		affs_fix_checksum(sb, bh);
@@ -732,8 +726,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 		if (IS_ERR(bh))
 			goto out;
 		tmp = min(bsize, to - from);
-		if (tmp > bsize)
-			BUG();
+		BUG_ON(tmp > bsize);
 		memcpy(AFFS_DATA(bh), data + from, tmp);
 		if (buffer_new(bh)) {
 			AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
diff --git a/trunk/fs/affs/super.c b/trunk/fs/affs/super.c
index d2dc047cb479..01d25d532541 100644
--- a/trunk/fs/affs/super.c
+++ b/trunk/fs/affs/super.c
@@ -199,7 +199,6 @@ parse_options(char *options, uid_t *uid, gid_t *gid, int *mode, int *reserved, s
 		case Opt_prefix:
 			/* Free any previous prefix */
 			kfree(*prefix);
-			*prefix = NULL;
 			*prefix = match_strdup(&args[0]);
 			if (!*prefix)
 				return 0;
@@ -233,6 +232,8 @@ parse_options(char *options, uid_t *uid, gid_t *gid, int *mode, int *reserved, s
 			break;
 		case Opt_volume: {
 			char *vol = match_strdup(&args[0]);
+			if (!vol)
+				return 0;
 			strlcpy(volume, vol, 32);
 			kfree(vol);
 			break;
diff --git a/trunk/fs/afs/afs_cm.h b/trunk/fs/afs/afs_cm.h
index 7b4d4fab4c80..255f5dd6040c 100644
--- a/trunk/fs/afs/afs_cm.h
+++ b/trunk/fs/afs/afs_cm.h
@@ -24,7 +24,8 @@ enum AFS_CM_Operations {
 	CBGetXStatsVersion	= 209,	/* get version of extended statistics */
 	CBGetXStats		= 210,	/* get contents of extended statistics data */
 	CBInitCallBackState3	= 213,	/* initialise callback state, version 3 */
-	CBGetCapabilities	= 65538, /* get client capabilities */
+	CBProbeUuid		= 214,	/* check the client hasn't rebooted */
+	CBTellMeAboutYourself	= 65538, /* get client capabilities */
 };
 
 #define AFS_CAP_ERROR_TRANSLATION	0x1
diff --git a/trunk/fs/afs/cell.c b/trunk/fs/afs/cell.c
index 584bb0f9c36a..5e1df14e16b1 100644
--- a/trunk/fs/afs/cell.c
+++ b/trunk/fs/afs/cell.c
@@ -20,7 +20,7 @@
 DECLARE_RWSEM(afs_proc_cells_sem);
 LIST_HEAD(afs_proc_cells);
 
-static struct list_head afs_cells = LIST_HEAD_INIT(afs_cells);
+static LIST_HEAD(afs_cells);
 static DEFINE_RWLOCK(afs_cells_lock);
 static DECLARE_RWSEM(afs_cells_sem); /* add/remove serialisation */
 static DECLARE_WAIT_QUEUE_HEAD(afs_cells_freeable_wq);
diff --git a/trunk/fs/afs/cmservice.c b/trunk/fs/afs/cmservice.c
index 47b71c8947f9..eb765489164f 100644
--- a/trunk/fs/afs/cmservice.c
+++ b/trunk/fs/afs/cmservice.c
@@ -26,8 +26,9 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *,
 						struct sk_buff *, bool);
 static int afs_deliver_cb_probe(struct afs_call *, struct sk_buff *, bool);
 static int afs_deliver_cb_callback(struct afs_call *, struct sk_buff *, bool);
-static int afs_deliver_cb_get_capabilities(struct afs_call *, struct sk_buff *,
-					   bool);
+static int afs_deliver_cb_probe_uuid(struct afs_call *, struct sk_buff *, bool);
+static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *,
+						 struct sk_buff *, bool);
 static void afs_cm_destructor(struct afs_call *);
 
 /*
@@ -71,11 +72,21 @@ static const struct afs_call_type afs_SRXCBProbe = {
 };
 
 /*
- * CB.GetCapabilities operation type
+ * CB.ProbeUuid operation type
  */
-static const struct afs_call_type afs_SRXCBGetCapabilites = {
-	.name		= "CB.GetCapabilities",
-	.deliver	= afs_deliver_cb_get_capabilities,
+static const struct afs_call_type afs_SRXCBProbeUuid = {
+	.name		= "CB.ProbeUuid",
+	.deliver	= afs_deliver_cb_probe_uuid,
+	.abort_to_error	= afs_abort_to_error,
+	.destructor	= afs_cm_destructor,
+};
+
+/*
+ * CB.TellMeAboutYourself operation type
+ */
+static const struct afs_call_type afs_SRXCBTellMeAboutYourself = {
+	.name		= "CB.TellMeAboutYourself",
+	.deliver	= afs_deliver_cb_tell_me_about_yourself,
 	.abort_to_error	= afs_abort_to_error,
 	.destructor	= afs_cm_destructor,
 };
@@ -103,8 +114,8 @@ bool afs_cm_incoming_call(struct afs_call *call)
 	case CBProbe:
 		call->type = &afs_SRXCBProbe;
 		return true;
-	case CBGetCapabilities:
-		call->type = &afs_SRXCBGetCapabilites;
+	case CBTellMeAboutYourself:
+		call->type = &afs_SRXCBTellMeAboutYourself;
 		return true;
 	default:
 		return false;
@@ -392,10 +403,106 @@ static int afs_deliver_cb_probe(struct afs_call *call, struct sk_buff *skb,
 	return 0;
 }
 
+/*
+ * allow the fileserver to quickly find out if the fileserver has been rebooted
+ */
+static void SRXAFSCB_ProbeUuid(struct work_struct *work)
+{
+	struct afs_call *call = container_of(work, struct afs_call, work);
+	struct afs_uuid *r = call->request;
+
+	struct {
+		__be32	match;
+	} reply;
+
+	_enter("");
+
+
+	if (memcmp(r, &afs_uuid, sizeof(afs_uuid)) == 0)
+		reply.match = htonl(0);
+	else
+		reply.match = htonl(1);
+
+	afs_send_simple_reply(call, &reply, sizeof(reply));
+	_leave("");
+}
+
+/*
+ * deliver request data to a CB.ProbeUuid call
+ */
+static int afs_deliver_cb_probe_uuid(struct afs_call *call, struct sk_buff *skb,
+				     bool last)
+{
+	struct afs_uuid *r;
+	unsigned loop;
+	__be32 *b;
+	int ret;
+
+	_enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
+
+	if (skb->len > 0)
+		return -EBADMSG;
+	if (!last)
+		return 0;
+
+	switch (call->unmarshall) {
+	case 0:
+		call->offset = 0;
+		call->buffer = kmalloc(11 * sizeof(__be32), GFP_KERNEL);
+		if (!call->buffer)
+			return -ENOMEM;
+		call->unmarshall++;
+
+	case 1:
+		_debug("extract UUID");
+		ret = afs_extract_data(call, skb, last, call->buffer,
+				       11 * sizeof(__be32));
+		switch (ret) {
+		case 0:		break;
+		case -EAGAIN:	return 0;
+		default:	return ret;
+		}
+
+		_debug("unmarshall UUID");
+		call->request = kmalloc(sizeof(struct afs_uuid), GFP_KERNEL);
+		if (!call->request)
+			return -ENOMEM;
+
+		b = call->buffer;
+		r = call->request;
+		r->time_low			= ntohl(b[0]);
+		r->time_mid			= ntohl(b[1]);
+		r->time_hi_and_version		= ntohl(b[2]);
+		r->clock_seq_hi_and_reserved 	= ntohl(b[3]);
+		r->clock_seq_low		= ntohl(b[4]);
+
+		for (loop = 0; loop < 6; loop++)
+			r->node[loop] = ntohl(b[loop + 5]);
+
+		call->offset = 0;
+		call->unmarshall++;
+
+	case 2:
+		_debug("trailer");
+		if (skb->len != 0)
+			return -EBADMSG;
+		break;
+	}
+
+	if (!last)
+		return 0;
+
+	call->state = AFS_CALL_REPLYING;
+
+	INIT_WORK(&call->work, SRXAFSCB_ProbeUuid);
+	schedule_work(&call->work);
+	return 0;
+}
+
 /*
  * allow the fileserver to ask about the cache manager's capabilities
  */
-static void SRXAFSCB_GetCapabilities(struct work_struct *work)
+static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work)
 {
 	struct afs_interface *ifs;
 	struct afs_call *call = container_of(work, struct afs_call, work);
@@ -456,10 +563,10 @@ static void SRXAFSCB_GetCapabilities(struct work_struct *work)
 }
 
 /*
- * deliver request data to a CB.GetCapabilities call
+ * deliver request data to a CB.TellMeAboutYourself call
  */
-static int afs_deliver_cb_get_capabilities(struct afs_call *call,
-					   struct sk_buff *skb, bool last)
+static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call,
+						 struct sk_buff *skb, bool last)
 {
 	_enter(",{%u},%d", skb->len, last);
 
@@ -471,7 +578,7 @@ static int afs_deliver_cb_get_capabilities(struct afs_call *call,
 	/* no unmarshalling required */
 	call->state = AFS_CALL_REPLYING;
 
-	INIT_WORK(&call->work, SRXAFSCB_GetCapabilities);
+	INIT_WORK(&call->work, SRXAFSCB_TellMeAboutYourself);
 	schedule_work(&call->work);
 	return 0;
 }
diff --git a/trunk/fs/afs/proc.c b/trunk/fs/afs/proc.c
index 846c7615ac9e..9f7d1ae70269 100644
--- a/trunk/fs/afs/proc.c
+++ b/trunk/fs/afs/proc.c
@@ -41,6 +41,7 @@ static const struct file_operations afs_proc_cells_fops = {
 	.write		= afs_proc_cells_write,
 	.llseek		= seq_lseek,
 	.release	= seq_release,
+	.owner		= THIS_MODULE,
 };
 
 static int afs_proc_rootcell_open(struct inode *inode, struct file *file);
@@ -56,7 +57,8 @@ static const struct file_operations afs_proc_rootcell_fops = {
 	.read		= afs_proc_rootcell_read,
 	.write		= afs_proc_rootcell_write,
 	.llseek		= no_llseek,
-	.release	= afs_proc_rootcell_release
+	.release	= afs_proc_rootcell_release,
+	.owner		= THIS_MODULE,
 };
 
 static int afs_proc_cell_volumes_open(struct inode *inode, struct file *file);
@@ -80,6 +82,7 @@ static const struct file_operations afs_proc_cell_volumes_fops = {
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= afs_proc_cell_volumes_release,
+	.owner		= THIS_MODULE,
 };
 
 static int afs_proc_cell_vlservers_open(struct inode *inode,
@@ -104,6 +107,7 @@ static const struct file_operations afs_proc_cell_vlservers_fops = {
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= afs_proc_cell_vlservers_release,
+	.owner		= THIS_MODULE,
 };
 
 static int afs_proc_cell_servers_open(struct inode *inode, struct file *file);
@@ -127,6 +131,7 @@ static const struct file_operations afs_proc_cell_servers_fops = {
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= afs_proc_cell_servers_release,
+	.owner		= THIS_MODULE,
 };
 
 /*
@@ -143,17 +148,13 @@ int afs_proc_init(void)
 		goto error_dir;
 	proc_afs->owner = THIS_MODULE;
 
-	p = create_proc_entry("cells", 0, proc_afs);
+	p = proc_create("cells", 0, proc_afs, &afs_proc_cells_fops);
 	if (!p)
 		goto error_cells;
-	p->proc_fops = &afs_proc_cells_fops;
-	p->owner = THIS_MODULE;
 
-	p = create_proc_entry("rootcell", 0, proc_afs);
+	p = proc_create("rootcell", 0, proc_afs, &afs_proc_rootcell_fops);
 	if (!p)
 		goto error_rootcell;
-	p->proc_fops = &afs_proc_rootcell_fops;
-	p->owner = THIS_MODULE;
 
 	_leave(" = 0");
 	return 0;
@@ -395,26 +396,20 @@ int afs_proc_cell_setup(struct afs_cell *cell)
 	if (!cell->proc_dir)
 		goto error_dir;
 
-	p = create_proc_entry("servers", 0, cell->proc_dir);
+	p = proc_create_data("servers", 0, cell->proc_dir,
+			     &afs_proc_cell_servers_fops, cell);
 	if (!p)
 		goto error_servers;
-	p->proc_fops = &afs_proc_cell_servers_fops;
-	p->owner = THIS_MODULE;
-	p->data = cell;
 
-	p = create_proc_entry("vlservers", 0, cell->proc_dir);
+	p = proc_create_data("vlservers", 0, cell->proc_dir,
+			     &afs_proc_cell_vlservers_fops, cell);
 	if (!p)
 		goto error_vlservers;
-	p->proc_fops = &afs_proc_cell_vlservers_fops;
-	p->owner = THIS_MODULE;
-	p->data = cell;
 
-	p = create_proc_entry("volumes", 0, cell->proc_dir);
+	p = proc_create_data("volumes", 0, cell->proc_dir,
+			     &afs_proc_cell_volumes_fops, cell);
 	if (!p)
 		goto error_volumes;
-	p->proc_fops = &afs_proc_cell_volumes_fops;
-	p->owner = THIS_MODULE;
-	p->data = cell;
 
 	_leave(" = 0");
 	return 0;
diff --git a/trunk/fs/aio.c b/trunk/fs/aio.c
index 228368610dfa..99c2352906a0 100644
--- a/trunk/fs/aio.c
+++ b/trunk/fs/aio.c
@@ -191,6 +191,43 @@ static int aio_setup_ring(struct kioctx *ctx)
 	kunmap_atomic((void *)((unsigned long)__event & PAGE_MASK), km); \
 } while(0)
 
+
+/* __put_ioctx
+ *	Called when the last user of an aio context has gone away,
+ *	and the struct needs to be freed.
+ */
+static void __put_ioctx(struct kioctx *ctx)
+{
+	unsigned nr_events = ctx->max_reqs;
+
+	BUG_ON(ctx->reqs_active);
+
+	cancel_delayed_work(&ctx->wq);
+	cancel_work_sync(&ctx->wq.work);
+	aio_free_ring(ctx);
+	mmdrop(ctx->mm);
+	ctx->mm = NULL;
+	pr_debug("__put_ioctx: freeing %p\n", ctx);
+	kmem_cache_free(kioctx_cachep, ctx);
+
+	if (nr_events) {
+		spin_lock(&aio_nr_lock);
+		BUG_ON(aio_nr - nr_events > aio_nr);
+		aio_nr -= nr_events;
+		spin_unlock(&aio_nr_lock);
+	}
+}
+
+#define get_ioctx(kioctx) do {						\
+	BUG_ON(atomic_read(&(kioctx)->users) <= 0);			\
+	atomic_inc(&(kioctx)->users);					\
+} while (0)
+#define put_ioctx(kioctx) do {						\
+	BUG_ON(atomic_read(&(kioctx)->users) <= 0);			\
+	if (unlikely(atomic_dec_and_test(&(kioctx)->users))) 		\
+		__put_ioctx(kioctx);					\
+} while (0)
+
 /* ioctx_alloc
  *	Allocates and initializes an ioctx.  Returns an ERR_PTR if it failed.
  */
@@ -240,7 +277,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 	if (ctx->max_reqs == 0)
 		goto out_cleanup;
 
-	/* now link into global list.  kludge.  FIXME */
+	/* now link into global list. */
 	write_lock(&mm->ioctx_list_lock);
 	ctx->next = mm->ioctx_list;
 	mm->ioctx_list = ctx;
@@ -361,32 +398,6 @@ void exit_aio(struct mm_struct *mm)
 	}
 }
 
-/* __put_ioctx
- *	Called when the last user of an aio context has gone away,
- *	and the struct needs to be freed.
- */
-void __put_ioctx(struct kioctx *ctx)
-{
-	unsigned nr_events = ctx->max_reqs;
-
-	BUG_ON(ctx->reqs_active);
-
-	cancel_delayed_work(&ctx->wq);
-	cancel_work_sync(&ctx->wq.work);
-	aio_free_ring(ctx);
-	mmdrop(ctx->mm);
-	ctx->mm = NULL;
-	pr_debug("__put_ioctx: freeing %p\n", ctx);
-	kmem_cache_free(kioctx_cachep, ctx);
-
-	if (nr_events) {
-		spin_lock(&aio_nr_lock);
-		BUG_ON(aio_nr - nr_events > aio_nr);
-		aio_nr -= nr_events;
-		spin_unlock(&aio_nr_lock);
-	}
-}
-
 /* aio_get_req
  *	Allocate a slot for an aio request.  Increments the users count
  * of the kioctx so that the kioctx stays around until all requests are
@@ -542,10 +553,7 @@ int aio_put_req(struct kiocb *req)
 	return ret;
 }
 
-/*	Lookup an ioctx id.  ioctx_list is lockless for reads.
- *	FIXME: this is O(n) and is only suitable for development.
- */
-struct kioctx *lookup_ioctx(unsigned long ctx_id)
+static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 {
 	struct kioctx *ioctx;
 	struct mm_struct *mm;
@@ -1166,7 +1174,10 @@ static int read_events(struct kioctx *ctx,
 				break;
 			if (min_nr <= i)
 				break;
-			ret = 0;
+			if (unlikely(ctx->dead)) {
+				ret = -EINVAL;
+				break;
+			}
 			if (to.timed_out)	/* Only check after read evt */
 				break;
 			/* Try to only show up in io wait if there are ops
@@ -1231,6 +1242,13 @@ static void io_destroy(struct kioctx *ioctx)
 
 	aio_cancel_all(ioctx);
 	wait_for_all_aios(ioctx);
+
+	/*
+	 * Wake up any waiters.  The setting of ctx->dead must be seen
+	 * by other CPUs at this point.  Right now, we rely on the
+	 * locking done by the above calls to ensure this consistency.
+	 */
+	wake_up(&ioctx->wait);
 	put_ioctx(ioctx);	/* once for the lookup */
 }
 
@@ -1542,7 +1560,7 @@ static int aio_wake_function(wait_queue_t *wait, unsigned mode,
 	return 1;
 }
 
-int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
+static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			 struct iocb *iocb)
 {
 	struct kiocb *req;
@@ -1583,7 +1601,7 @@ int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		 * event using the eventfd_signal() function.
 		 */
 		req->ki_eventfd = eventfd_fget((int) iocb->aio_resfd);
-		if (unlikely(IS_ERR(req->ki_eventfd))) {
+		if (IS_ERR(req->ki_eventfd)) {
 			ret = PTR_ERR(req->ki_eventfd);
 			goto out_put_req;
 		}
diff --git a/trunk/fs/autofs4/root.c b/trunk/fs/autofs4/root.c
index a54a946a50ae..aa4c5ff8a40d 100644
--- a/trunk/fs/autofs4/root.c
+++ b/trunk/fs/autofs4/root.c
@@ -533,9 +533,9 @@ static struct dentry *autofs4_lookup_unhashed(struct autofs_sb_info *sbi, struct
 			goto next;
 
 		if (d_unhashed(dentry)) {
-			struct autofs_info *ino = autofs4_dentry_ino(dentry);
 			struct inode *inode = dentry->d_inode;
 
+			ino = autofs4_dentry_ino(dentry);
 			list_del_init(&ino->rehash);
 			dget(dentry);
 			/*
diff --git a/trunk/fs/befs/linuxvfs.c b/trunk/fs/befs/linuxvfs.c
index 82123ff3e1dd..e8717de3bab3 100644
--- a/trunk/fs/befs/linuxvfs.c
+++ b/trunk/fs/befs/linuxvfs.c
@@ -489,9 +489,9 @@ static void befs_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
 {
 	befs_inode_info *befs_ino = BEFS_I(dentry->d_inode);
 	if (befs_ino->i_flags & BEFS_LONG_SYMLINK) {
-		char *p = nd_get_link(nd);
-		if (!IS_ERR(p))
-			kfree(p);
+		char *link = nd_get_link(nd);
+		if (!IS_ERR(link))
+			kfree(link);
 	}
 }
 
diff --git a/trunk/fs/binfmt_aout.c b/trunk/fs/binfmt_aout.c
index a1bb2244cac7..ba4cddb92f1d 100644
--- a/trunk/fs/binfmt_aout.c
+++ b/trunk/fs/binfmt_aout.c
@@ -372,21 +372,17 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 			 
 		flush_icache_range(text_addr, text_addr+ex.a_text+ex.a_data);
 	} else {
-		static unsigned long error_time, error_time2;
 		if ((ex.a_text & 0xfff || ex.a_data & 0xfff) &&
-		    (N_MAGIC(ex) != NMAGIC) && (jiffies-error_time2) > 5*HZ)
+		    (N_MAGIC(ex) != NMAGIC) && printk_ratelimit())
 		{
 			printk(KERN_NOTICE "executable not page aligned\n");
-			error_time2 = jiffies;
 		}
 
-		if ((fd_offset & ~PAGE_MASK) != 0 &&
-		    (jiffies-error_time) > 5*HZ)
+		if ((fd_offset & ~PAGE_MASK) != 0 && printk_ratelimit())
 		{
 			printk(KERN_WARNING 
 			       "fd_offset is not page aligned. Please convert program: %s\n",
 			       bprm->file->f_path.dentry->d_name.name);
-			error_time = jiffies;
 		}
 
 		if (!bprm->file->f_op->mmap||((fd_offset & ~PAGE_MASK) != 0)) {
@@ -495,15 +491,13 @@ static int load_aout_library(struct file *file)
 	start_addr =  ex.a_entry & 0xfffff000;
 
 	if ((N_TXTOFF(ex) & ~PAGE_MASK) != 0) {
-		static unsigned long error_time;
 		loff_t pos = N_TXTOFF(ex);
 
-		if ((jiffies-error_time) > 5*HZ)
+		if (printk_ratelimit())
 		{
 			printk(KERN_WARNING 
 			       "N_TXTOFF is not page aligned. Please convert library: %s\n",
 			       file->f_path.dentry->d_name.name);
-			error_time = jiffies;
 		}
 		down_write(&current->mm->mmap_sem);
 		do_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
diff --git a/trunk/fs/binfmt_elf.c b/trunk/fs/binfmt_elf.c
index 9924581df6f6..b25707fee2cc 100644
--- a/trunk/fs/binfmt_elf.c
+++ b/trunk/fs/binfmt_elf.c
@@ -1255,26 +1255,23 @@ static int writenote(struct memelfnote *men, struct file *file,
 static void fill_elf_header(struct elfhdr *elf, int segs,
 			    u16 machine, u32 flags, u8 osabi)
 {
+	memset(elf, 0, sizeof(*elf));
+
 	memcpy(elf->e_ident, ELFMAG, SELFMAG);
 	elf->e_ident[EI_CLASS] = ELF_CLASS;
 	elf->e_ident[EI_DATA] = ELF_DATA;
 	elf->e_ident[EI_VERSION] = EV_CURRENT;
 	elf->e_ident[EI_OSABI] = ELF_OSABI;
-	memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD);
 
 	elf->e_type = ET_CORE;
 	elf->e_machine = machine;
 	elf->e_version = EV_CURRENT;
-	elf->e_entry = 0;
 	elf->e_phoff = sizeof(struct elfhdr);
-	elf->e_shoff = 0;
 	elf->e_flags = flags;
 	elf->e_ehsize = sizeof(struct elfhdr);
 	elf->e_phentsize = sizeof(struct elf_phdr);
 	elf->e_phnum = segs;
-	elf->e_shentsize = 0;
-	elf->e_shnum = 0;
-	elf->e_shstrndx = 0;
+
 	return;
 }
 
@@ -1725,26 +1722,25 @@ static int fill_note_info(struct elfhdr *elf, int phdrs,
 
 	info->thread_status_size = 0;
 	if (signr) {
-		struct elf_thread_status *tmp;
+		struct elf_thread_status *ets;
 		rcu_read_lock();
 		do_each_thread(g, p)
 			if (current->mm == p->mm && current != p) {
-				tmp = kzalloc(sizeof(*tmp), GFP_ATOMIC);
-				if (!tmp) {
+				ets = kzalloc(sizeof(*ets), GFP_ATOMIC);
+				if (!ets) {
 					rcu_read_unlock();
 					return 0;
 				}
-				tmp->thread = p;
-				list_add(&tmp->list, &info->thread_list);
+				ets->thread = p;
+				list_add(&ets->list, &info->thread_list);
 			}
 		while_each_thread(g, p);
 		rcu_read_unlock();
 		list_for_each(t, &info->thread_list) {
-			struct elf_thread_status *tmp;
 			int sz;
 
-			tmp = list_entry(t, struct elf_thread_status, list);
-			sz = elf_dump_thread_status(signr, tmp);
+			ets = list_entry(t, struct elf_thread_status, list);
+			sz = elf_dump_thread_status(signr, ets);
 			info->thread_status_size += sz;
 		}
 	}
@@ -2000,10 +1996,10 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file, un
 
 		for (addr = vma->vm_start; addr < end; addr += PAGE_SIZE) {
 			struct page *page;
-			struct vm_area_struct *vma;
+			struct vm_area_struct *tmp_vma;
 
 			if (get_user_pages(current, current->mm, addr, 1, 0, 1,
-						&page, &vma) <= 0) {
+						&page, &tmp_vma) <= 0) {
 				DUMP_SEEK(PAGE_SIZE);
 			} else {
 				if (page == ZERO_PAGE(0)) {
@@ -2013,7 +2009,7 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file, un
 					}
 				} else {
 					void *kaddr;
-					flush_cache_page(vma, addr,
+					flush_cache_page(tmp_vma, addr,
 							 page_to_pfn(page));
 					kaddr = kmap(page);
 					if ((size += PAGE_SIZE) > limit ||
diff --git a/trunk/fs/binfmt_elf_fdpic.c b/trunk/fs/binfmt_elf_fdpic.c
index 32649f2a1654..ddd35d873391 100644
--- a/trunk/fs/binfmt_elf_fdpic.c
+++ b/trunk/fs/binfmt_elf_fdpic.c
@@ -136,8 +136,8 @@ static int elf_fdpic_fetch_phdrs(struct elf_fdpic_params *params,
 
 	retval = kernel_read(file, params->hdr.e_phoff,
 			     (char *) params->phdrs, size);
-	if (retval < 0)
-		return retval;
+	if (unlikely(retval != size))
+		return retval < 0 ? retval : -ENOEXEC;
 
 	/* determine stack size for this binary */
 	phdr = params->phdrs;
@@ -218,8 +218,11 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
 					     phdr->p_offset,
 					     interpreter_name,
 					     phdr->p_filesz);
-			if (retval < 0)
+			if (unlikely(retval != phdr->p_filesz)) {
+				if (retval >= 0)
+					retval = -ENOEXEC;
 				goto error;
+			}
 
 			retval = -ENOENT;
 			if (interpreter_name[phdr->p_filesz - 1] != '\0')
@@ -245,8 +248,11 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
 
 			retval = kernel_read(interpreter, 0, bprm->buf,
 					     BINPRM_BUF_SIZE);
-			if (retval < 0)
+			if (unlikely(retval != BINPRM_BUF_SIZE)) {
+				if (retval >= 0)
+					retval = -ENOEXEC;
 				goto error;
+			}
 
 			interp_params.hdr = *((struct elfhdr *) bprm->buf);
 			break;
diff --git a/trunk/fs/binfmt_em86.c b/trunk/fs/binfmt_em86.c
index f95ae9789c91..f9c88d0c8ced 100644
--- a/trunk/fs/binfmt_em86.c
+++ b/trunk/fs/binfmt_em86.c
@@ -43,7 +43,7 @@ static int load_em86(struct linux_binprm *bprm,struct pt_regs *regs)
 			return -ENOEXEC;
 	}
 
-	bprm->sh_bang++;	/* Well, the bang-shell is implicit... */
+	bprm->sh_bang = 1;	/* Well, the bang-shell is implicit... */
 	allow_write_access(bprm->file);
 	fput(bprm->file);
 	bprm->file = NULL;
diff --git a/trunk/fs/binfmt_flat.c b/trunk/fs/binfmt_flat.c
index 0498b181dd52..3b40d45a3a16 100644
--- a/trunk/fs/binfmt_flat.c
+++ b/trunk/fs/binfmt_flat.c
@@ -531,7 +531,8 @@ static int load_flat_file(struct linux_binprm * bprm,
 		DBG_FLT("BINFMT_FLAT: ROM mapping of file (we hope)\n");
 
 		down_write(&current->mm->mmap_sem);
-		textpos = do_mmap(bprm->file, 0, text_len, PROT_READ|PROT_EXEC, MAP_PRIVATE, 0);
+		textpos = do_mmap(bprm->file, 0, text_len, PROT_READ|PROT_EXEC,
+				  MAP_PRIVATE|MAP_EXECUTABLE, 0);
 		up_write(&current->mm->mmap_sem);
 		if (!textpos  || textpos >= (unsigned long) -4096) {
 			if (!textpos)
@@ -932,14 +933,8 @@ static int __init init_flat_binfmt(void)
 	return register_binfmt(&flat_format);
 }
 
-static void __exit exit_flat_binfmt(void)
-{
-	unregister_binfmt(&flat_format);
-}
-
 /****************************************************************************/
 
 core_initcall(init_flat_binfmt);
-module_exit(exit_flat_binfmt);
 
 /****************************************************************************/
diff --git a/trunk/fs/binfmt_misc.c b/trunk/fs/binfmt_misc.c
index dbf0ac0523de..7191306367c5 100644
--- a/trunk/fs/binfmt_misc.c
+++ b/trunk/fs/binfmt_misc.c
@@ -115,6 +115,12 @@ static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	if (!enabled)
 		goto _ret;
 
+	retval = -ENOEXEC;
+	if (bprm->misc_bang)
+		goto _ret;
+
+	bprm->misc_bang = 1;
+
 	/* to keep locking time low, we copy the interpreter string */
 	read_lock(&entries_lock);
 	fmt = check_file(bprm);
diff --git a/trunk/fs/binfmt_script.c b/trunk/fs/binfmt_script.c
index ab33939b12a7..9e3963f7ebf1 100644
--- a/trunk/fs/binfmt_script.c
+++ b/trunk/fs/binfmt_script.c
@@ -29,7 +29,7 @@ static int load_script(struct linux_binprm *bprm,struct pt_regs *regs)
 	 * Sorta complicated, but hopefully it will work.  -TYT
 	 */
 
-	bprm->sh_bang++;
+	bprm->sh_bang = 1;
 	allow_write_access(bprm->file);
 	fput(bprm->file);
 	bprm->file = NULL;
diff --git a/trunk/fs/bio.c b/trunk/fs/bio.c
index 6e0b6f66df03..799f86deff24 100644
--- a/trunk/fs/bio.c
+++ b/trunk/fs/bio.c
@@ -937,6 +937,95 @@ struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
 	return ERR_PTR(-EINVAL);
 }
 
+static void bio_copy_kern_endio(struct bio *bio, int err)
+{
+	struct bio_vec *bvec;
+	const int read = bio_data_dir(bio) == READ;
+	char *p = bio->bi_private;
+	int i;
+
+	__bio_for_each_segment(bvec, bio, i, 0) {
+		char *addr = page_address(bvec->bv_page);
+
+		if (read && !err)
+			memcpy(p, addr, bvec->bv_len);
+
+		__free_page(bvec->bv_page);
+		p += bvec->bv_len;
+	}
+
+	bio_put(bio);
+}
+
+/**
+ *	bio_copy_kern	-	copy kernel address into bio
+ *	@q: the struct request_queue for the bio
+ *	@data: pointer to buffer to copy
+ *	@len: length in bytes
+ *	@gfp_mask: allocation flags for bio and page allocation
+ *
+ *	copy the kernel address into a bio suitable for io to a block
+ *	device. Returns an error pointer in case of error.
+ */
+struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
+			  gfp_t gfp_mask, int reading)
+{
+	unsigned long kaddr = (unsigned long)data;
+	unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	unsigned long start = kaddr >> PAGE_SHIFT;
+	const int nr_pages = end - start;
+	struct bio *bio;
+	struct bio_vec *bvec;
+	int i, ret;
+
+	bio = bio_alloc(gfp_mask, nr_pages);
+	if (!bio)
+		return ERR_PTR(-ENOMEM);
+
+	while (len) {
+		struct page *page;
+		unsigned int bytes = PAGE_SIZE;
+
+		if (bytes > len)
+			bytes = len;
+
+		page = alloc_page(q->bounce_gfp | gfp_mask);
+		if (!page) {
+			ret = -ENOMEM;
+			goto cleanup;
+		}
+
+		if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes) {
+			ret = -EINVAL;
+			goto cleanup;
+		}
+
+		len -= bytes;
+	}
+
+	if (!reading) {
+		void *p = data;
+
+		bio_for_each_segment(bvec, bio, i) {
+			char *addr = page_address(bvec->bv_page);
+
+			memcpy(addr, p, bvec->bv_len);
+			p += bvec->bv_len;
+		}
+	}
+
+	bio->bi_private = data;
+	bio->bi_end_io = bio_copy_kern_endio;
+	return bio;
+cleanup:
+	bio_for_each_segment(bvec, bio, i)
+		__free_page(bvec->bv_page);
+
+	bio_put(bio);
+
+	return ERR_PTR(ret);
+}
+
 /*
  * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions
  * for performing direct-IO in BIOs.
@@ -1273,6 +1362,7 @@ EXPORT_SYMBOL(bio_get_nr_vecs);
 EXPORT_SYMBOL(bio_map_user);
 EXPORT_SYMBOL(bio_unmap_user);
 EXPORT_SYMBOL(bio_map_kern);
+EXPORT_SYMBOL(bio_copy_kern);
 EXPORT_SYMBOL(bio_pair_release);
 EXPORT_SYMBOL(bio_split);
 EXPORT_SYMBOL(bio_split_pool);
diff --git a/trunk/fs/buffer.c b/trunk/fs/buffer.c
index 39ff14403d13..189efa4efc6e 100644
--- a/trunk/fs/buffer.c
+++ b/trunk/fs/buffer.c
@@ -360,16 +360,19 @@ void invalidate_bdev(struct block_device *bdev)
  */
 static void free_more_memory(void)
 {
-	struct zone **zones;
-	pg_data_t *pgdat;
+	struct zone *zone;
+	int nid;
 
 	wakeup_pdflush(1024);
 	yield();
 
-	for_each_online_pgdat(pgdat) {
-		zones = pgdat->node_zonelists[gfp_zone(GFP_NOFS)].zones;
-		if (*zones)
-			try_to_free_pages(zones, 0, GFP_NOFS);
+	for_each_online_node(nid) {
+		(void)first_zones_zonelist(node_zonelist(nid, GFP_NOFS),
+						gfp_zone(GFP_NOFS), NULL,
+						&zone);
+		if (zone)
+			try_to_free_pages(node_zonelist(nid, GFP_NOFS), 0,
+						GFP_NOFS);
 	}
 }
 
@@ -2208,8 +2211,8 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size)
 	return err;
 }
 
-int cont_expand_zero(struct file *file, struct address_space *mapping,
-			loff_t pos, loff_t *bytes)
+static int cont_expand_zero(struct file *file, struct address_space *mapping,
+			    loff_t pos, loff_t *bytes)
 {
 	struct inode *inode = mapping->host;
 	unsigned blocksize = 1 << inode->i_blkbits;
@@ -2243,6 +2246,8 @@ int cont_expand_zero(struct file *file, struct address_space *mapping,
 			goto out;
 		BUG_ON(err != len);
 		err = 0;
+
+		balance_dirty_pages_ratelimited(mapping);
 	}
 
 	/* page covers the boundary, find the boundary offset */
@@ -2323,23 +2328,6 @@ int block_commit_write(struct page *page, unsigned from, unsigned to)
 	return 0;
 }
 
-int generic_commit_write(struct file *file, struct page *page,
-		unsigned from, unsigned to)
-{
-	struct inode *inode = page->mapping->host;
-	loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
-	__block_commit_write(inode,page,from,to);
-	/*
-	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hold i_mutex.
-	 */
-	if (pos > inode->i_size) {
-		i_size_write(inode, pos);
-		mark_inode_dirty(inode);
-	}
-	return 0;
-}
-
 /*
  * block_page_mkwrite() is not allowed to change the file size as it gets
  * called from a page fault handler when a page is first dirtied. Hence we must
@@ -3180,8 +3168,7 @@ static void recalc_bh_state(void)
 	
 struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
 {
-	struct buffer_head *ret = kmem_cache_alloc(bh_cachep,
-				set_migrateflags(gfp_flags, __GFP_RECLAIMABLE));
+	struct buffer_head *ret = kmem_cache_alloc(bh_cachep, gfp_flags);
 	if (ret) {
 		INIT_LIST_HEAD(&ret->b_assoc_buffers);
 		get_cpu_var(bh_accounting).nr++;
@@ -3311,7 +3298,6 @@ EXPORT_SYMBOL(end_buffer_write_sync);
 EXPORT_SYMBOL(file_fsync);
 EXPORT_SYMBOL(fsync_bdev);
 EXPORT_SYMBOL(generic_block_bmap);
-EXPORT_SYMBOL(generic_commit_write);
 EXPORT_SYMBOL(generic_cont_expand_simple);
 EXPORT_SYMBOL(init_buffer);
 EXPORT_SYMBOL(invalidate_bdev);
diff --git a/trunk/fs/char_dev.c b/trunk/fs/char_dev.c
index 038674aa88a7..68e510b88457 100644
--- a/trunk/fs/char_dev.c
+++ b/trunk/fs/char_dev.c
@@ -55,7 +55,6 @@ static struct char_device_struct {
 	unsigned int baseminor;
 	int minorct;
 	char name[64];
-	struct file_operations *fops;
 	struct cdev *cdev;		/* will die */
 } *chrdevs[CHRDEV_MAJOR_HASH_SIZE];
 
diff --git a/trunk/fs/cifs/cifs_debug.c b/trunk/fs/cifs/cifs_debug.c
index 0228ed06069e..cc950f69e51e 100644
--- a/trunk/fs/cifs/cifs_debug.c
+++ b/trunk/fs/cifs/cifs_debug.c
@@ -468,7 +468,7 @@ cifs_proc_init(void)
 {
 	struct proc_dir_entry *pde;
 
-	proc_fs_cifs = proc_mkdir("cifs", proc_root_fs);
+	proc_fs_cifs = proc_mkdir("fs/cifs", NULL);
 	if (proc_fs_cifs == NULL)
 		return;
 
@@ -559,7 +559,7 @@ cifs_proc_clean(void)
 	remove_proc_entry("LinuxExtensionsEnabled", proc_fs_cifs);
 	remove_proc_entry("Experimental", proc_fs_cifs);
 	remove_proc_entry("LookupCacheEnabled", proc_fs_cifs);
-	remove_proc_entry("cifs", proc_root_fs);
+	remove_proc_entry("fs/cifs", NULL);
 }
 
 static int
diff --git a/trunk/fs/coda/coda_linux.c b/trunk/fs/coda/coda_linux.c
index 95a54253c047..e1c854890f94 100644
--- a/trunk/fs/coda/coda_linux.c
+++ b/trunk/fs/coda/coda_linux.c
@@ -134,7 +134,7 @@ void coda_iattr_to_vattr(struct iattr *iattr, struct coda_vattr *vattr)
         unsigned int valid;
 
         /* clean out */        
-        vattr->va_mode = (umode_t) -1;
+	vattr->va_mode = -1;
         vattr->va_uid = (vuid_t) -1; 
         vattr->va_gid = (vgid_t) -1;
         vattr->va_size = (off_t) -1;
diff --git a/trunk/fs/coda/dir.c b/trunk/fs/coda/dir.c
index f89ff083079b..3d2580e00a3e 100644
--- a/trunk/fs/coda/dir.c
+++ b/trunk/fs/coda/dir.c
@@ -345,7 +345,7 @@ static int coda_symlink(struct inode *dir_inode, struct dentry *de,
 }
 
 /* destruction routines: unlink, rmdir */
-int coda_unlink(struct inode *dir, struct dentry *de)
+static int coda_unlink(struct inode *dir, struct dentry *de)
 {
         int error;
 	const char *name = de->d_name.name;
@@ -365,7 +365,7 @@ int coda_unlink(struct inode *dir, struct dentry *de)
 	return 0;
 }
 
-int coda_rmdir(struct inode *dir, struct dentry *de)
+static int coda_rmdir(struct inode *dir, struct dentry *de)
 {
 	const char *name = de->d_name.name;
 	int len = de->d_name.len;
@@ -424,7 +424,7 @@ static int coda_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 
 /* file operations for directories */
-int coda_readdir(struct file *coda_file, void *buf, filldir_t filldir)
+static int coda_readdir(struct file *coda_file, void *buf, filldir_t filldir)
 {
 	struct coda_file_info *cfi;
 	struct file *host_file;
diff --git a/trunk/fs/dquot.c b/trunk/fs/dquot.c
index 41b9dbd68b0e..dfba1623cccb 100644
--- a/trunk/fs/dquot.c
+++ b/trunk/fs/dquot.c
@@ -289,7 +289,15 @@ static void wait_on_dquot(struct dquot *dquot)
 	mutex_unlock(&dquot->dq_lock);
 }
 
-#define mark_dquot_dirty(dquot) ((dquot)->dq_sb->dq_op->mark_dirty(dquot))
+static inline int dquot_dirty(struct dquot *dquot)
+{
+	return test_bit(DQ_MOD_B, &dquot->dq_flags);
+}
+
+static inline int mark_dquot_dirty(struct dquot *dquot)
+{
+	return dquot->dq_sb->dq_op->mark_dirty(dquot);
+}
 
 int dquot_mark_dquot_dirty(struct dquot *dquot)
 {
@@ -1441,31 +1449,43 @@ static inline void set_enable_flags(struct quota_info *dqopt, int type)
 	switch (type) {
 		case USRQUOTA:
 			dqopt->flags |= DQUOT_USR_ENABLED;
+			dqopt->flags &= ~DQUOT_USR_SUSPENDED;
 			break;
 		case GRPQUOTA:
 			dqopt->flags |= DQUOT_GRP_ENABLED;
+			dqopt->flags &= ~DQUOT_GRP_SUSPENDED;
 			break;
 	}
 }
 
-static inline void reset_enable_flags(struct quota_info *dqopt, int type)
+static inline void reset_enable_flags(struct quota_info *dqopt, int type,
+				      int remount)
 {
 	switch (type) {
 		case USRQUOTA:
 			dqopt->flags &= ~DQUOT_USR_ENABLED;
+			if (remount)
+				dqopt->flags |= DQUOT_USR_SUSPENDED;
+			else
+				dqopt->flags &= ~DQUOT_USR_SUSPENDED;
 			break;
 		case GRPQUOTA:
 			dqopt->flags &= ~DQUOT_GRP_ENABLED;
+			if (remount)
+				dqopt->flags |= DQUOT_GRP_SUSPENDED;
+			else
+				dqopt->flags &= ~DQUOT_GRP_SUSPENDED;
 			break;
 	}
 }
 
+
 /*
  * Turn quota off on a device. type == -1 ==> quotaoff for all types (umount)
  */
-int vfs_quota_off(struct super_block *sb, int type)
+int vfs_quota_off(struct super_block *sb, int type, int remount)
 {
-	int cnt;
+	int cnt, ret = 0;
 	struct quota_info *dqopt = sb_dqopt(sb);
 	struct inode *toputinode[MAXQUOTAS];
 
@@ -1475,9 +1495,17 @@ int vfs_quota_off(struct super_block *sb, int type)
 		toputinode[cnt] = NULL;
 		if (type != -1 && cnt != type)
 			continue;
+		/* If we keep inodes of quota files after remount and quotaoff
+		 * is called, drop kept inodes. */
+		if (!remount && sb_has_quota_suspended(sb, cnt)) {
+			iput(dqopt->files[cnt]);
+			dqopt->files[cnt] = NULL;
+			reset_enable_flags(dqopt, cnt, 0);
+			continue;
+		}
 		if (!sb_has_quota_enabled(sb, cnt))
 			continue;
-		reset_enable_flags(dqopt, cnt);
+		reset_enable_flags(dqopt, cnt, remount);
 
 		/* Note: these are blocking operations */
 		drop_dquot_ref(sb, cnt);
@@ -1493,7 +1521,8 @@ int vfs_quota_off(struct super_block *sb, int type)
 		put_quota_format(dqopt->info[cnt].dqi_format);
 
 		toputinode[cnt] = dqopt->files[cnt];
-		dqopt->files[cnt] = NULL;
+		if (!remount)
+			dqopt->files[cnt] = NULL;
 		dqopt->info[cnt].dqi_flags = 0;
 		dqopt->info[cnt].dqi_igrace = 0;
 		dqopt->info[cnt].dqi_bgrace = 0;
@@ -1523,12 +1552,19 @@ int vfs_quota_off(struct super_block *sb, int type)
 				mutex_unlock(&toputinode[cnt]->i_mutex);
 				mark_inode_dirty(toputinode[cnt]);
 			}
-			iput(toputinode[cnt]);
 			mutex_unlock(&dqopt->dqonoff_mutex);
+			/* On remount RO, we keep the inode pointer so that we
+			 * can reenable quota on the subsequent remount RW.
+			 * But we have better not keep inode pointer when there
+			 * is pending delete on the quota file... */
+			if (!remount)
+				iput(toputinode[cnt]);
+			else if (!toputinode[cnt]->i_nlink)
+				ret = -EBUSY;
 		}
 	if (sb->s_bdev)
 		invalidate_bdev(sb->s_bdev);
-	return 0;
+	return ret;
 }
 
 /*
@@ -1566,7 +1602,8 @@ static int vfs_quota_on_inode(struct inode *inode, int type, int format_id)
 	invalidate_bdev(sb->s_bdev);
 	mutex_lock(&inode->i_mutex);
 	mutex_lock(&dqopt->dqonoff_mutex);
-	if (sb_has_quota_enabled(sb, type)) {
+	if (sb_has_quota_enabled(sb, type) ||
+			sb_has_quota_suspended(sb, type)) {
 		error = -EBUSY;
 		goto out_lock;
 	}
@@ -1589,6 +1626,7 @@ static int vfs_quota_on_inode(struct inode *inode, int type, int format_id)
 
 	dqopt->ops[type] = fmt->qf_ops;
 	dqopt->info[type].dqi_format = fmt;
+	dqopt->info[type].dqi_fmt_id = format_id;
 	INIT_LIST_HEAD(&dqopt->info[type].dqi_dirty_list);
 	mutex_lock(&dqopt->dqio_mutex);
 	if ((error = dqopt->ops[type]->read_file_info(sb, type)) < 0) {
@@ -1624,12 +1662,41 @@ static int vfs_quota_on_inode(struct inode *inode, int type, int format_id)
 	return error; 
 }
 
+/* Reenable quotas on remount RW */
+static int vfs_quota_on_remount(struct super_block *sb, int type)
+{
+	struct quota_info *dqopt = sb_dqopt(sb);
+	struct inode *inode;
+	int ret;
+
+	mutex_lock(&dqopt->dqonoff_mutex);
+	if (!sb_has_quota_suspended(sb, type)) {
+		mutex_unlock(&dqopt->dqonoff_mutex);
+		return 0;
+	}
+	BUG_ON(sb_has_quota_enabled(sb, type));
+
+	inode = dqopt->files[type];
+	dqopt->files[type] = NULL;
+	reset_enable_flags(dqopt, type, 0);
+	mutex_unlock(&dqopt->dqonoff_mutex);
+
+	ret = vfs_quota_on_inode(inode, type, dqopt->info[type].dqi_fmt_id);
+	iput(inode);
+
+	return ret;
+}
+
 /* Actual function called from quotactl() */
-int vfs_quota_on(struct super_block *sb, int type, int format_id, char *path)
+int vfs_quota_on(struct super_block *sb, int type, int format_id, char *path,
+		 int remount)
 {
 	struct nameidata nd;
 	int error;
 
+	if (remount)
+		return vfs_quota_on_remount(sb, type);
+
 	error = path_lookup(path, LOOKUP_FOLLOW, &nd);
 	if (error < 0)
 		return error;
@@ -1709,10 +1776,19 @@ int vfs_get_dqblk(struct super_block *sb, int type, qid_t id, struct if_dqblk *d
 }
 
 /* Generic routine for setting common part of quota structure */
-static void do_set_dqblk(struct dquot *dquot, struct if_dqblk *di)
+static int do_set_dqblk(struct dquot *dquot, struct if_dqblk *di)
 {
 	struct mem_dqblk *dm = &dquot->dq_dqb;
 	int check_blim = 0, check_ilim = 0;
+	struct mem_dqinfo *dqi = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_type];
+
+	if ((di->dqb_valid & QIF_BLIMITS &&
+	     (di->dqb_bhardlimit > dqi->dqi_maxblimit ||
+	      di->dqb_bsoftlimit > dqi->dqi_maxblimit)) ||
+	    (di->dqb_valid & QIF_ILIMITS &&
+	     (di->dqb_ihardlimit > dqi->dqi_maxilimit ||
+	      di->dqb_isoftlimit > dqi->dqi_maxilimit)))
+		return -ERANGE;
 
 	spin_lock(&dq_data_lock);
 	if (di->dqb_valid & QIF_SPACE) {
@@ -1744,7 +1820,7 @@ static void do_set_dqblk(struct dquot *dquot, struct if_dqblk *di)
 			clear_bit(DQ_BLKS_B, &dquot->dq_flags);
 		}
 		else if (!(di->dqb_valid & QIF_BTIME))	/* Set grace only if user hasn't provided his own... */
-			dm->dqb_btime = get_seconds() + sb_dqopt(dquot->dq_sb)->info[dquot->dq_type].dqi_bgrace;
+			dm->dqb_btime = get_seconds() + dqi->dqi_bgrace;
 	}
 	if (check_ilim) {
 		if (!dm->dqb_isoftlimit || dm->dqb_curinodes < dm->dqb_isoftlimit) {
@@ -1752,7 +1828,7 @@ static void do_set_dqblk(struct dquot *dquot, struct if_dqblk *di)
 			clear_bit(DQ_INODES_B, &dquot->dq_flags);
 		}
 		else if (!(di->dqb_valid & QIF_ITIME))	/* Set grace only if user hasn't provided his own... */
-			dm->dqb_itime = get_seconds() + sb_dqopt(dquot->dq_sb)->info[dquot->dq_type].dqi_igrace;
+			dm->dqb_itime = get_seconds() + dqi->dqi_igrace;
 	}
 	if (dm->dqb_bhardlimit || dm->dqb_bsoftlimit || dm->dqb_ihardlimit || dm->dqb_isoftlimit)
 		clear_bit(DQ_FAKE_B, &dquot->dq_flags);
@@ -1760,21 +1836,24 @@ static void do_set_dqblk(struct dquot *dquot, struct if_dqblk *di)
 		set_bit(DQ_FAKE_B, &dquot->dq_flags);
 	spin_unlock(&dq_data_lock);
 	mark_dquot_dirty(dquot);
+
+	return 0;
 }
 
 int vfs_set_dqblk(struct super_block *sb, int type, qid_t id, struct if_dqblk *di)
 {
 	struct dquot *dquot;
+	int rc;
 
 	mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
 	if (!(dquot = dqget(sb, id, type))) {
 		mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
 		return -ESRCH;
 	}
-	do_set_dqblk(dquot, di);
+	rc = do_set_dqblk(dquot, di);
 	dqput(dquot);
 	mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
-	return 0;
+	return rc;
 }
 
 /* Generic routine for getting common part of quota file information */
diff --git a/trunk/fs/drop_caches.c b/trunk/fs/drop_caches.c
index 59375efcf39d..3e5637fc3779 100644
--- a/trunk/fs/drop_caches.c
+++ b/trunk/fs/drop_caches.c
@@ -14,18 +14,26 @@ int sysctl_drop_caches;
 
 static void drop_pagecache_sb(struct super_block *sb)
 {
-	struct inode *inode;
+	struct inode *inode, *toput_inode = NULL;
 
 	spin_lock(&inode_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 		if (inode->i_state & (I_FREEING|I_WILL_FREE))
 			continue;
+		if (inode->i_mapping->nrpages == 0)
+			continue;
+		__iget(inode);
+		spin_unlock(&inode_lock);
 		__invalidate_mapping_pages(inode->i_mapping, 0, -1, true);
+		iput(toput_inode);
+		toput_inode = inode;
+		spin_lock(&inode_lock);
 	}
 	spin_unlock(&inode_lock);
+	iput(toput_inode);
 }
 
-void drop_pagecache(void)
+static void drop_pagecache(void)
 {
 	struct super_block *sb;
 
@@ -45,7 +53,7 @@ void drop_pagecache(void)
 	spin_unlock(&sb_lock);
 }
 
-void drop_slab(void)
+static void drop_slab(void)
 {
 	int nr_objects;
 
diff --git a/trunk/fs/ecryptfs/Makefile b/trunk/fs/ecryptfs/Makefile
index 768857015516..1e34a7fd4884 100644
--- a/trunk/fs/ecryptfs/Makefile
+++ b/trunk/fs/ecryptfs/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_ECRYPT_FS) += ecryptfs.o
 
-ecryptfs-objs := dentry.o file.o inode.o main.o super.o mmap.o read_write.o crypto.o keystore.o messaging.o netlink.o debug.o
+ecryptfs-objs := dentry.o file.o inode.o main.o super.o mmap.o read_write.o crypto.o keystore.o messaging.o netlink.o miscdev.o debug.o
diff --git a/trunk/fs/ecryptfs/crypto.c b/trunk/fs/ecryptfs/crypto.c
index a066e109ad9c..cd62d75b2cc0 100644
--- a/trunk/fs/ecryptfs/crypto.c
+++ b/trunk/fs/ecryptfs/crypto.c
@@ -119,21 +119,21 @@ static int ecryptfs_calculate_md5(char *dst,
 	if (rc) {
 		printk(KERN_ERR
 		       "%s: Error initializing crypto hash; rc = [%d]\n",
-		       __FUNCTION__, rc);
+		       __func__, rc);
 		goto out;
 	}
 	rc = crypto_hash_update(&desc, &sg, len);
 	if (rc) {
 		printk(KERN_ERR
 		       "%s: Error updating crypto hash; rc = [%d]\n",
-		       __FUNCTION__, rc);
+		       __func__, rc);
 		goto out;
 	}
 	rc = crypto_hash_final(&desc, dst);
 	if (rc) {
 		printk(KERN_ERR
 		       "%s: Error finalizing crypto hash; rc = [%d]\n",
-		       __FUNCTION__, rc);
+		       __func__, rc);
 		goto out;
 	}
 out:
@@ -437,7 +437,7 @@ static int ecryptfs_encrypt_extent(struct page *enc_extent_page,
 	if (rc < 0) {
 		printk(KERN_ERR "%s: Error attempting to encrypt page with "
 		       "page->index = [%ld], extent_offset = [%ld]; "
-		       "rc = [%d]\n", __FUNCTION__, page->index, extent_offset,
+		       "rc = [%d]\n", __func__, page->index, extent_offset,
 		       rc);
 		goto out;
 	}
@@ -487,7 +487,7 @@ int ecryptfs_encrypt_page(struct page *page)
 						       0, PAGE_CACHE_SIZE);
 		if (rc)
 			printk(KERN_ERR "%s: Error attempting to copy "
-			       "page at index [%ld]\n", __FUNCTION__,
+			       "page at index [%ld]\n", __func__,
 			       page->index);
 		goto out;
 	}
@@ -508,7 +508,7 @@ int ecryptfs_encrypt_page(struct page *page)
 					     extent_offset);
 		if (rc) {
 			printk(KERN_ERR "%s: Error encrypting extent; "
-			       "rc = [%d]\n", __FUNCTION__, rc);
+			       "rc = [%d]\n", __func__, rc);
 			goto out;
 		}
 		ecryptfs_lower_offset_for_extent(
@@ -569,7 +569,7 @@ static int ecryptfs_decrypt_extent(struct page *page,
 	if (rc < 0) {
 		printk(KERN_ERR "%s: Error attempting to decrypt to page with "
 		       "page->index = [%ld], extent_offset = [%ld]; "
-		       "rc = [%d]\n", __FUNCTION__, page->index, extent_offset,
+		       "rc = [%d]\n", __func__, page->index, extent_offset,
 		       rc);
 		goto out;
 	}
@@ -622,7 +622,7 @@ int ecryptfs_decrypt_page(struct page *page)
 						      ecryptfs_inode);
 		if (rc)
 			printk(KERN_ERR "%s: Error attempting to copy "
-			       "page at index [%ld]\n", __FUNCTION__,
+			       "page at index [%ld]\n", __func__,
 			       page->index);
 		goto out;
 	}
@@ -656,7 +656,7 @@ int ecryptfs_decrypt_page(struct page *page)
 					     extent_offset);
 		if (rc) {
 			printk(KERN_ERR "%s: Error encrypting extent; "
-			       "rc = [%d]\n", __FUNCTION__, rc);
+			       "rc = [%d]\n", __func__, rc);
 			goto out;
 		}
 	}
@@ -1215,7 +1215,7 @@ int ecryptfs_read_and_validate_header_region(char *data,
 				 ecryptfs_inode);
 	if (rc) {
 		printk(KERN_ERR "%s: Error reading header region; rc = [%d]\n",
-		       __FUNCTION__, rc);
+		       __func__, rc);
 		goto out;
 	}
 	if (!contains_ecryptfs_marker(data + ECRYPTFS_FILE_SIZE_BYTES)) {
@@ -1246,7 +1246,6 @@ ecryptfs_write_header_metadata(char *virt,
 	(*written) = 6;
 }
 
-struct kmem_cache *ecryptfs_header_cache_0;
 struct kmem_cache *ecryptfs_header_cache_1;
 struct kmem_cache *ecryptfs_header_cache_2;
 
@@ -1320,7 +1319,7 @@ ecryptfs_write_metadata_to_contents(struct ecryptfs_crypt_stat *crypt_stat,
 				  0, crypt_stat->num_header_bytes_at_front);
 	if (rc)
 		printk(KERN_ERR "%s: Error attempting to write header "
-		       "information to lower file; rc = [%d]\n", __FUNCTION__,
+		       "information to lower file; rc = [%d]\n", __func__,
 		       rc);
 	return rc;
 }
@@ -1365,14 +1364,14 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry)
 		}
 	} else {
 		printk(KERN_WARNING "%s: Encrypted flag not set\n",
-		       __FUNCTION__);
+		       __func__);
 		rc = -EINVAL;
 		goto out;
 	}
 	/* Released in this function */
 	virt = kzalloc(crypt_stat->num_header_bytes_at_front, GFP_KERNEL);
 	if (!virt) {
-		printk(KERN_ERR "%s: Out of memory\n", __FUNCTION__);
+		printk(KERN_ERR "%s: Out of memory\n", __func__);
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -1380,7 +1379,7 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry)
 					 ecryptfs_dentry);
 	if (unlikely(rc)) {
 		printk(KERN_ERR "%s: Error whilst writing headers; rc = [%d]\n",
-		       __FUNCTION__, rc);
+		       __func__, rc);
 		goto out_free;
 	}
 	if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR)
@@ -1391,7 +1390,7 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry)
 							 ecryptfs_dentry, virt);
 	if (rc) {
 		printk(KERN_ERR "%s: Error writing metadata out to lower file; "
-		       "rc = [%d]\n", __FUNCTION__, rc);
+		       "rc = [%d]\n", __func__, rc);
 		goto out_free;
 	}
 out_free:
@@ -1585,7 +1584,7 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
 	if (!page_virt) {
 		rc = -ENOMEM;
 		printk(KERN_ERR "%s: Unable to allocate page_virt\n",
-		       __FUNCTION__);
+		       __func__);
 		goto out;
 	}
 	rc = ecryptfs_read_lower(page_virt, 0, crypt_stat->extent_size,
diff --git a/trunk/fs/ecryptfs/ecryptfs_kernel.h b/trunk/fs/ecryptfs/ecryptfs_kernel.h
index 5007f788da01..951ee33a022d 100644
--- a/trunk/fs/ecryptfs/ecryptfs_kernel.h
+++ b/trunk/fs/ecryptfs/ecryptfs_kernel.h
@@ -4,7 +4,7 @@
  *
  * Copyright (C) 1997-2003 Erez Zadok
  * Copyright (C) 2001-2003 Stony Brook University
- * Copyright (C) 2004-2007 International Business Machines Corp.
+ * Copyright (C) 2004-2008 International Business Machines Corp.
  *   Author(s): Michael A. Halcrow <mahalcro@us.ibm.com>
  *              Trevor S. Highland <trevor.highland@gmail.com>
  *              Tyler Hicks <tyhicks@ou.edu>
@@ -34,6 +34,7 @@
 #include <linux/namei.h>
 #include <linux/scatterlist.h>
 #include <linux/hash.h>
+#include <linux/nsproxy.h>
 
 /* Version verification for shared data structures w/ userspace */
 #define ECRYPTFS_VERSION_MAJOR 0x00
@@ -49,11 +50,13 @@
 #define ECRYPTFS_VERSIONING_POLICY                0x00000008
 #define ECRYPTFS_VERSIONING_XATTR                 0x00000010
 #define ECRYPTFS_VERSIONING_MULTKEY               0x00000020
+#define ECRYPTFS_VERSIONING_DEVMISC               0x00000040
 #define ECRYPTFS_VERSIONING_MASK (ECRYPTFS_VERSIONING_PASSPHRASE \
 				  | ECRYPTFS_VERSIONING_PLAINTEXT_PASSTHROUGH \
 				  | ECRYPTFS_VERSIONING_PUBKEY \
 				  | ECRYPTFS_VERSIONING_XATTR \
-				  | ECRYPTFS_VERSIONING_MULTKEY)
+				  | ECRYPTFS_VERSIONING_MULTKEY \
+				  | ECRYPTFS_VERSIONING_DEVMISC)
 #define ECRYPTFS_MAX_PASSWORD_LENGTH 64
 #define ECRYPTFS_MAX_PASSPHRASE_BYTES ECRYPTFS_MAX_PASSWORD_LENGTH
 #define ECRYPTFS_SALT_SIZE 8
@@ -73,17 +76,14 @@
 #define ECRYPTFS_DEFAULT_MSG_CTX_ELEMS 32
 #define ECRYPTFS_DEFAULT_SEND_TIMEOUT HZ
 #define ECRYPTFS_MAX_MSG_CTX_TTL (HZ*3)
-#define ECRYPTFS_NLMSG_HELO 100
-#define ECRYPTFS_NLMSG_QUIT 101
-#define ECRYPTFS_NLMSG_REQUEST 102
-#define ECRYPTFS_NLMSG_RESPONSE 103
 #define ECRYPTFS_MAX_PKI_NAME_BYTES 16
 #define ECRYPTFS_DEFAULT_NUM_USERS 4
 #define ECRYPTFS_MAX_NUM_USERS 32768
 #define ECRYPTFS_TRANSPORT_NETLINK 0
 #define ECRYPTFS_TRANSPORT_CONNECTOR 1
 #define ECRYPTFS_TRANSPORT_RELAYFS 2
-#define ECRYPTFS_DEFAULT_TRANSPORT ECRYPTFS_TRANSPORT_NETLINK
+#define ECRYPTFS_TRANSPORT_MISCDEV 3
+#define ECRYPTFS_DEFAULT_TRANSPORT ECRYPTFS_TRANSPORT_MISCDEV
 #define ECRYPTFS_XATTR_NAME "user.ecryptfs"
 
 #define RFC2440_CIPHER_DES3_EDE 0x02
@@ -366,32 +366,63 @@ struct ecryptfs_auth_tok_list_item {
 };
 
 struct ecryptfs_message {
+	/* Can never be greater than ecryptfs_message_buf_len */
+	/* Used to find the parent msg_ctx */
+	/* Inherits from msg_ctx->index */
 	u32 index;
 	u32 data_len;
 	u8 data[];
 };
 
 struct ecryptfs_msg_ctx {
-#define ECRYPTFS_MSG_CTX_STATE_FREE      0x0001
-#define ECRYPTFS_MSG_CTX_STATE_PENDING   0x0002
-#define ECRYPTFS_MSG_CTX_STATE_DONE      0x0003
-	u32 state;
-	unsigned int index;
-	unsigned int counter;
+#define ECRYPTFS_MSG_CTX_STATE_FREE     0x01
+#define ECRYPTFS_MSG_CTX_STATE_PENDING  0x02
+#define ECRYPTFS_MSG_CTX_STATE_DONE     0x03
+#define ECRYPTFS_MSG_CTX_STATE_NO_REPLY 0x04
+	u8 state;
+#define ECRYPTFS_MSG_HELO 100
+#define ECRYPTFS_MSG_QUIT 101
+#define ECRYPTFS_MSG_REQUEST 102
+#define ECRYPTFS_MSG_RESPONSE 103
+	u8 type;
+	u32 index;
+	/* Counter converts to a sequence number. Each message sent
+	 * out for which we expect a response has an associated
+	 * sequence number. The response must have the same sequence
+	 * number as the counter for the msg_stc for the message to be
+	 * valid. */
+	u32 counter;
+	size_t msg_size;
 	struct ecryptfs_message *msg;
 	struct task_struct *task;
 	struct list_head node;
+	struct list_head daemon_out_list;
 	struct mutex mux;
 };
 
 extern unsigned int ecryptfs_transport;
 
-struct ecryptfs_daemon_id {
-	pid_t pid;
-	uid_t uid;
-	struct hlist_node id_chain;
+struct ecryptfs_daemon;
+
+struct ecryptfs_daemon {
+#define ECRYPTFS_DAEMON_IN_READ      0x00000001
+#define ECRYPTFS_DAEMON_IN_POLL      0x00000002
+#define ECRYPTFS_DAEMON_ZOMBIE       0x00000004
+#define ECRYPTFS_DAEMON_MISCDEV_OPEN 0x00000008
+	u32 flags;
+	u32 num_queued_msg_ctx;
+	struct pid *pid;
+	uid_t euid;
+	struct user_namespace *user_ns;
+	struct task_struct *task;
+	struct mutex mux;
+	struct list_head msg_ctx_out_queue;
+	wait_queue_head_t wait;
+	struct hlist_node euid_chain;
 };
 
+extern struct mutex ecryptfs_daemon_hash_mux;
+
 static inline struct ecryptfs_file_info *
 ecryptfs_file_to_private(struct file *file)
 {
@@ -500,7 +531,7 @@ ecryptfs_set_dentry_lower_mnt(struct dentry *dentry, struct vfsmount *lower_mnt)
 }
 
 #define ecryptfs_printk(type, fmt, arg...) \
-        __ecryptfs_printk(type "%s: " fmt, __FUNCTION__, ## arg);
+        __ecryptfs_printk(type "%s: " fmt, __func__, ## arg);
 void __ecryptfs_printk(const char *fmt, ...);
 
 extern const struct file_operations ecryptfs_main_fops;
@@ -581,10 +612,13 @@ int
 ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 		  size_t size, int flags);
 int ecryptfs_read_xattr_region(char *page_virt, struct inode *ecryptfs_inode);
-int ecryptfs_process_helo(unsigned int transport, uid_t uid, pid_t pid);
-int ecryptfs_process_quit(uid_t uid, pid_t pid);
-int ecryptfs_process_response(struct ecryptfs_message *msg, uid_t uid,
-			      pid_t pid, u32 seq);
+int ecryptfs_process_helo(unsigned int transport, uid_t euid,
+			  struct user_namespace *user_ns, struct pid *pid);
+int ecryptfs_process_quit(uid_t euid, struct user_namespace *user_ns,
+			  struct pid *pid);
+int ecryptfs_process_response(struct ecryptfs_message *msg, uid_t euid,
+			      struct user_namespace *user_ns, struct pid *pid,
+			      u32 seq);
 int ecryptfs_send_message(unsigned int transport, char *data, int data_len,
 			  struct ecryptfs_msg_ctx **msg_ctx);
 int ecryptfs_wait_for_response(struct ecryptfs_msg_ctx *msg_ctx,
@@ -593,14 +627,14 @@ int ecryptfs_init_messaging(unsigned int transport);
 void ecryptfs_release_messaging(unsigned int transport);
 
 int ecryptfs_send_netlink(char *data, int data_len,
-			  struct ecryptfs_msg_ctx *msg_ctx, u16 msg_type,
-			  u16 msg_flags, pid_t daemon_pid);
+			  struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type,
+			  u16 msg_flags, struct pid *daemon_pid);
 int ecryptfs_init_netlink(void);
 void ecryptfs_release_netlink(void);
 
 int ecryptfs_send_connector(char *data, int data_len,
-			    struct ecryptfs_msg_ctx *msg_ctx, u16 msg_type,
-			    u16 msg_flags, pid_t daemon_pid);
+			    struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type,
+			    u16 msg_flags, struct pid *daemon_pid);
 int ecryptfs_init_connector(void);
 void ecryptfs_release_connector(void);
 void
@@ -642,5 +676,21 @@ int ecryptfs_read_lower_page_segment(struct page *page_for_ecryptfs,
 				     size_t offset_in_page, size_t size,
 				     struct inode *ecryptfs_inode);
 struct page *ecryptfs_get_locked_page(struct file *file, loff_t index);
+int ecryptfs_exorcise_daemon(struct ecryptfs_daemon *daemon);
+int ecryptfs_find_daemon_by_euid(struct ecryptfs_daemon **daemon, uid_t euid,
+				 struct user_namespace *user_ns);
+int ecryptfs_parse_packet_length(unsigned char *data, size_t *size,
+				 size_t *length_size);
+int ecryptfs_write_packet_length(char *dest, size_t size,
+				 size_t *packet_size_length);
+int ecryptfs_init_ecryptfs_miscdev(void);
+void ecryptfs_destroy_ecryptfs_miscdev(void);
+int ecryptfs_send_miscdev(char *data, size_t data_size,
+			  struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type,
+			  u16 msg_flags, struct ecryptfs_daemon *daemon);
+void ecryptfs_msg_ctx_alloc_to_free(struct ecryptfs_msg_ctx *msg_ctx);
+int
+ecryptfs_spawn_daemon(struct ecryptfs_daemon **daemon, uid_t euid,
+		      struct user_namespace *user_ns, struct pid *pid);
 
 #endif /* #ifndef ECRYPTFS_KERNEL_H */
diff --git a/trunk/fs/ecryptfs/file.c b/trunk/fs/ecryptfs/file.c
index 2b8f5ed4adea..2258b8f654a6 100644
--- a/trunk/fs/ecryptfs/file.c
+++ b/trunk/fs/ecryptfs/file.c
@@ -195,7 +195,9 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 		file, ecryptfs_inode_to_private(inode)->lower_file);
 	if (S_ISDIR(ecryptfs_dentry->d_inode->i_mode)) {
 		ecryptfs_printk(KERN_DEBUG, "This is a directory\n");
+		mutex_lock(&crypt_stat->cs_mutex);
 		crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
+		mutex_unlock(&crypt_stat->cs_mutex);
 		rc = 0;
 		goto out;
 	}
diff --git a/trunk/fs/ecryptfs/inode.c b/trunk/fs/ecryptfs/inode.c
index e23861152101..0a1397335a8e 100644
--- a/trunk/fs/ecryptfs/inode.c
+++ b/trunk/fs/ecryptfs/inode.c
@@ -111,7 +111,7 @@ ecryptfs_do_create(struct inode *directory_inode,
 
 	lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
 	lower_dir_dentry = lock_parent(lower_dentry);
-	if (unlikely(IS_ERR(lower_dir_dentry))) {
+	if (IS_ERR(lower_dir_dentry)) {
 		ecryptfs_printk(KERN_ERR, "Error locking directory of "
 				"dentry\n");
 		rc = PTR_ERR(lower_dir_dentry);
@@ -121,7 +121,7 @@ ecryptfs_do_create(struct inode *directory_inode,
 					     ecryptfs_dentry, mode, nd);
 	if (rc) {
 		printk(KERN_ERR "%s: Failure to create dentry in lower fs; "
-		       "rc = [%d]\n", __FUNCTION__, rc);
+		       "rc = [%d]\n", __func__, rc);
 		goto out_lock;
 	}
 	rc = ecryptfs_interpose(lower_dentry, ecryptfs_dentry,
@@ -908,7 +908,9 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
 	if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
 		ia->ia_valid &= ~ATTR_MODE;
 
+	mutex_lock(&lower_dentry->d_inode->i_mutex);
 	rc = notify_change(lower_dentry, ia);
+	mutex_unlock(&lower_dentry->d_inode->i_mutex);
 out:
 	fsstack_copy_attr_all(inode, lower_inode, NULL);
 	return rc;
diff --git a/trunk/fs/ecryptfs/keystore.c b/trunk/fs/ecryptfs/keystore.c
index 682b1b2482c2..e82b457180be 100644
--- a/trunk/fs/ecryptfs/keystore.c
+++ b/trunk/fs/ecryptfs/keystore.c
@@ -65,7 +65,7 @@ static int process_request_key_err(long err_code)
 }
 
 /**
- * parse_packet_length
+ * ecryptfs_parse_packet_length
  * @data: Pointer to memory containing length at offset
  * @size: This function writes the decoded size to this memory
  *        address; zero on error
@@ -73,8 +73,8 @@ static int process_request_key_err(long err_code)
  *
  * Returns zero on success; non-zero on error
  */
-static int parse_packet_length(unsigned char *data, size_t *size,
-			       size_t *length_size)
+int ecryptfs_parse_packet_length(unsigned char *data, size_t *size,
+				 size_t *length_size)
 {
 	int rc = 0;
 
@@ -105,7 +105,7 @@ static int parse_packet_length(unsigned char *data, size_t *size,
 }
 
 /**
- * write_packet_length
+ * ecryptfs_write_packet_length
  * @dest: The byte array target into which to write the length. Must
  *        have at least 5 bytes allocated.
  * @size: The length to write.
@@ -114,8 +114,8 @@ static int parse_packet_length(unsigned char *data, size_t *size,
  *
  * Returns zero on success; non-zero on error.
  */
-static int write_packet_length(char *dest, size_t size,
-			       size_t *packet_size_length)
+int ecryptfs_write_packet_length(char *dest, size_t size,
+				 size_t *packet_size_length)
 {
 	int rc = 0;
 
@@ -162,8 +162,8 @@ write_tag_64_packet(char *signature, struct ecryptfs_session_key *session_key,
 		goto out;
 	}
 	message[i++] = ECRYPTFS_TAG_64_PACKET_TYPE;
-	rc = write_packet_length(&message[i], ECRYPTFS_SIG_SIZE_HEX,
-				 &packet_size_len);
+	rc = ecryptfs_write_packet_length(&message[i], ECRYPTFS_SIG_SIZE_HEX,
+					  &packet_size_len);
 	if (rc) {
 		ecryptfs_printk(KERN_ERR, "Error generating tag 64 packet "
 				"header; cannot generate packet length\n");
@@ -172,8 +172,9 @@ write_tag_64_packet(char *signature, struct ecryptfs_session_key *session_key,
 	i += packet_size_len;
 	memcpy(&message[i], signature, ECRYPTFS_SIG_SIZE_HEX);
 	i += ECRYPTFS_SIG_SIZE_HEX;
-	rc = write_packet_length(&message[i], session_key->encrypted_key_size,
-				 &packet_size_len);
+	rc = ecryptfs_write_packet_length(&message[i],
+					  session_key->encrypted_key_size,
+					  &packet_size_len);
 	if (rc) {
 		ecryptfs_printk(KERN_ERR, "Error generating tag 64 packet "
 				"header; cannot generate packet length\n");
@@ -225,7 +226,7 @@ parse_tag_65_packet(struct ecryptfs_session_key *session_key, u8 *cipher_code,
 		rc = -EIO;
 		goto out;
 	}
-	rc = parse_packet_length(&data[i], &m_size, &data_len);
+	rc = ecryptfs_parse_packet_length(&data[i], &m_size, &data_len);
 	if (rc) {
 		ecryptfs_printk(KERN_WARNING, "Error parsing packet length; "
 				"rc = [%d]\n", rc);
@@ -304,8 +305,8 @@ write_tag_66_packet(char *signature, u8 cipher_code,
 		goto out;
 	}
 	message[i++] = ECRYPTFS_TAG_66_PACKET_TYPE;
-	rc = write_packet_length(&message[i], ECRYPTFS_SIG_SIZE_HEX,
-				 &packet_size_len);
+	rc = ecryptfs_write_packet_length(&message[i], ECRYPTFS_SIG_SIZE_HEX,
+					  &packet_size_len);
 	if (rc) {
 		ecryptfs_printk(KERN_ERR, "Error generating tag 66 packet "
 				"header; cannot generate packet length\n");
@@ -315,8 +316,8 @@ write_tag_66_packet(char *signature, u8 cipher_code,
 	memcpy(&message[i], signature, ECRYPTFS_SIG_SIZE_HEX);
 	i += ECRYPTFS_SIG_SIZE_HEX;
 	/* The encrypted key includes 1 byte cipher code and 2 byte checksum */
-	rc = write_packet_length(&message[i], crypt_stat->key_size + 3,
-				 &packet_size_len);
+	rc = ecryptfs_write_packet_length(&message[i], crypt_stat->key_size + 3,
+					  &packet_size_len);
 	if (rc) {
 		ecryptfs_printk(KERN_ERR, "Error generating tag 66 packet "
 				"header; cannot generate packet length\n");
@@ -357,20 +358,25 @@ parse_tag_67_packet(struct ecryptfs_key_record *key_rec,
 	/* verify that everything through the encrypted FEK size is present */
 	if (message_len < 4) {
 		rc = -EIO;
+		printk(KERN_ERR "%s: message_len is [%Zd]; minimum acceptable "
+		       "message length is [%d]\n", __func__, message_len, 4);
 		goto out;
 	}
 	if (data[i++] != ECRYPTFS_TAG_67_PACKET_TYPE) {
-		ecryptfs_printk(KERN_ERR, "Type should be ECRYPTFS_TAG_67\n");
 		rc = -EIO;
+		printk(KERN_ERR "%s: Type should be ECRYPTFS_TAG_67\n",
+		       __func__);
 		goto out;
 	}
 	if (data[i++]) {
-		ecryptfs_printk(KERN_ERR, "Status indicator has non zero value"
-				" [%d]\n", data[i-1]);
 		rc = -EIO;
+		printk(KERN_ERR "%s: Status indicator has non zero "
+		       "value [%d]\n", __func__, data[i-1]);
+
 		goto out;
 	}
-	rc = parse_packet_length(&data[i], &key_rec->enc_key_size, &data_len);
+	rc = ecryptfs_parse_packet_length(&data[i], &key_rec->enc_key_size,
+					  &data_len);
 	if (rc) {
 		ecryptfs_printk(KERN_WARNING, "Error parsing packet length; "
 				"rc = [%d]\n", rc);
@@ -378,17 +384,17 @@ parse_tag_67_packet(struct ecryptfs_key_record *key_rec,
 	}
 	i += data_len;
 	if (message_len < (i + key_rec->enc_key_size)) {
-		ecryptfs_printk(KERN_ERR, "message_len [%d]; max len is [%d]\n",
-				message_len, (i + key_rec->enc_key_size));
 		rc = -EIO;
+		printk(KERN_ERR "%s: message_len [%Zd]; max len is [%Zd]\n",
+		       __func__, message_len, (i + key_rec->enc_key_size));
 		goto out;
 	}
 	if (key_rec->enc_key_size > ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES) {
-		ecryptfs_printk(KERN_ERR, "Encrypted key_size [%d] larger than "
-				"the maximum key size [%d]\n",
-				key_rec->enc_key_size,
-				ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES);
 		rc = -EIO;
+		printk(KERN_ERR "%s: Encrypted key_size [%Zd] larger than "
+		       "the maximum key size [%d]\n", __func__,
+		       key_rec->enc_key_size,
+		       ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES);
 		goto out;
 	}
 	memcpy(key_rec->enc_key, &data[i], key_rec->enc_key_size);
@@ -445,7 +451,7 @@ decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 	rc = write_tag_64_packet(auth_tok_sig, &(auth_tok->session_key),
 				 &netlink_message, &netlink_message_length);
 	if (rc) {
-		ecryptfs_printk(KERN_ERR, "Failed to write tag 64 packet");
+		ecryptfs_printk(KERN_ERR, "Failed to write tag 64 packet\n");
 		goto out;
 	}
 	rc = ecryptfs_send_message(ecryptfs_transport, netlink_message,
@@ -570,8 +576,8 @@ parse_tag_1_packet(struct ecryptfs_crypt_stat *crypt_stat,
 		goto out;
 	}
 	(*new_auth_tok) = &auth_tok_list_item->auth_tok;
-	rc = parse_packet_length(&data[(*packet_size)], &body_size,
-				 &length_size);
+	rc = ecryptfs_parse_packet_length(&data[(*packet_size)], &body_size,
+					  &length_size);
 	if (rc) {
 		printk(KERN_WARNING "Error parsing packet length; "
 		       "rc = [%d]\n", rc);
@@ -704,8 +710,8 @@ parse_tag_3_packet(struct ecryptfs_crypt_stat *crypt_stat,
 		goto out;
 	}
 	(*new_auth_tok) = &auth_tok_list_item->auth_tok;
-	rc = parse_packet_length(&data[(*packet_size)], &body_size,
-				 &length_size);
+	rc = ecryptfs_parse_packet_length(&data[(*packet_size)], &body_size,
+					  &length_size);
 	if (rc) {
 		printk(KERN_WARNING "Error parsing packet length; rc = [%d]\n",
 		       rc);
@@ -852,8 +858,8 @@ parse_tag_11_packet(unsigned char *data, unsigned char *contents,
 		rc = -EINVAL;
 		goto out;
 	}
-	rc = parse_packet_length(&data[(*packet_size)], &body_size,
-				 &length_size);
+	rc = ecryptfs_parse_packet_length(&data[(*packet_size)], &body_size,
+					  &length_size);
 	if (rc) {
 		printk(KERN_WARNING "Invalid tag 11 packet format\n");
 		goto out;
@@ -1405,8 +1411,8 @@ write_tag_1_packet(char *dest, size_t *remaining_bytes,
 			auth_tok->token.private_key.key_size;
 	rc = pki_encrypt_session_key(auth_tok, crypt_stat, key_rec);
 	if (rc) {
-		ecryptfs_printk(KERN_ERR, "Failed to encrypt session key "
-				"via a pki");
+		printk(KERN_ERR "Failed to encrypt session key via a key "
+		       "module; rc = [%d]\n", rc);
 		goto out;
 	}
 	if (ecryptfs_verbosity > 0) {
@@ -1430,8 +1436,9 @@ write_tag_1_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	dest[(*packet_size)++] = ECRYPTFS_TAG_1_PACKET_TYPE;
-	rc = write_packet_length(&dest[(*packet_size)], (max_packet_size - 4),
-				 &packet_size_length);
+	rc = ecryptfs_write_packet_length(&dest[(*packet_size)],
+					  (max_packet_size - 4),
+					  &packet_size_length);
 	if (rc) {
 		ecryptfs_printk(KERN_ERR, "Error generating tag 1 packet "
 				"header; cannot generate packet length\n");
@@ -1489,8 +1496,9 @@ write_tag_11_packet(char *dest, size_t *remaining_bytes, char *contents,
 		goto out;
 	}
 	dest[(*packet_length)++] = ECRYPTFS_TAG_11_PACKET_TYPE;
-	rc = write_packet_length(&dest[(*packet_length)],
-				 (max_packet_size - 4), &packet_size_length);
+	rc = ecryptfs_write_packet_length(&dest[(*packet_length)],
+					  (max_packet_size - 4),
+					  &packet_size_length);
 	if (rc) {
 		printk(KERN_ERR "Error generating tag 11 packet header; cannot "
 		       "generate packet length. rc = [%d]\n", rc);
@@ -1682,8 +1690,9 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 	dest[(*packet_size)++] = ECRYPTFS_TAG_3_PACKET_TYPE;
 	/* Chop off the Tag 3 identifier(1) and Tag 3 packet size(3)
 	 * to get the number of octets in the actual Tag 3 packet */
-	rc = write_packet_length(&dest[(*packet_size)], (max_packet_size - 4),
-				 &packet_size_length);
+	rc = ecryptfs_write_packet_length(&dest[(*packet_size)],
+					  (max_packet_size - 4),
+					  &packet_size_length);
 	if (rc) {
 		printk(KERN_ERR "Error generating tag 3 packet header; cannot "
 		       "generate packet length. rc = [%d]\n", rc);
diff --git a/trunk/fs/ecryptfs/main.c b/trunk/fs/ecryptfs/main.c
index d25ac9500a92..d603631601eb 100644
--- a/trunk/fs/ecryptfs/main.c
+++ b/trunk/fs/ecryptfs/main.c
@@ -219,7 +219,7 @@ int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to initialize the "
 		       "persistent file for the dentry with name [%s]; "
-		       "rc = [%d]\n", __FUNCTION__, dentry->d_name.name, rc);
+		       "rc = [%d]\n", __func__, dentry->d_name.name, rc);
 		goto out;
 	}
 out:
diff --git a/trunk/fs/ecryptfs/messaging.c b/trunk/fs/ecryptfs/messaging.c
index 9cc2aec27b0d..1b5c20058acb 100644
--- a/trunk/fs/ecryptfs/messaging.c
+++ b/trunk/fs/ecryptfs/messaging.c
@@ -1,7 +1,7 @@
 /**
  * eCryptfs: Linux filesystem encryption layer
  *
- * Copyright (C) 2004-2006 International Business Machines Corp.
+ * Copyright (C) 2004-2008 International Business Machines Corp.
  *   Author(s): Michael A. Halcrow <mhalcrow@us.ibm.com>
  *		Tyler Hicks <tyhicks@ou.edu>
  *
@@ -20,19 +20,21 @@
  * 02111-1307, USA.
  */
 #include <linux/sched.h>
+#include <linux/user_namespace.h>
+#include <linux/nsproxy.h>
 #include "ecryptfs_kernel.h"
 
 static LIST_HEAD(ecryptfs_msg_ctx_free_list);
 static LIST_HEAD(ecryptfs_msg_ctx_alloc_list);
 static struct mutex ecryptfs_msg_ctx_lists_mux;
 
-static struct hlist_head *ecryptfs_daemon_id_hash;
-static struct mutex ecryptfs_daemon_id_hash_mux;
+static struct hlist_head *ecryptfs_daemon_hash;
+struct mutex ecryptfs_daemon_hash_mux;
 static int ecryptfs_hash_buckets;
 #define ecryptfs_uid_hash(uid) \
         hash_long((unsigned long)uid, ecryptfs_hash_buckets)
 
-static unsigned int ecryptfs_msg_counter;
+static u32 ecryptfs_msg_counter;
 static struct ecryptfs_msg_ctx *ecryptfs_msg_ctx_arr;
 
 /**
@@ -40,9 +42,10 @@ static struct ecryptfs_msg_ctx *ecryptfs_msg_ctx_arr;
  * @msg_ctx: The context that was acquired from the free list
  *
  * Acquires a context element from the free list and locks the mutex
- * on the context.  Returns zero on success; non-zero on error or upon
- * failure to acquire a free context element.  Be sure to lock the
- * list mutex before calling.
+ * on the context.  Sets the msg_ctx task to current.  Returns zero on
+ * success; non-zero on error or upon failure to acquire a free
+ * context element.  Must be called with ecryptfs_msg_ctx_lists_mux
+ * held.
  */
 static int ecryptfs_acquire_free_msg_ctx(struct ecryptfs_msg_ctx **msg_ctx)
 {
@@ -50,11 +53,11 @@ static int ecryptfs_acquire_free_msg_ctx(struct ecryptfs_msg_ctx **msg_ctx)
 	int rc;
 
 	if (list_empty(&ecryptfs_msg_ctx_free_list)) {
-		ecryptfs_printk(KERN_WARNING, "The eCryptfs free "
-				"context list is empty.  It may be helpful to "
-				"specify the ecryptfs_message_buf_len "
-				"parameter to be greater than the current "
-				"value of [%d]\n", ecryptfs_message_buf_len);
+		printk(KERN_WARNING "%s: The eCryptfs free "
+		       "context list is empty.  It may be helpful to "
+		       "specify the ecryptfs_message_buf_len "
+		       "parameter to be greater than the current "
+		       "value of [%d]\n", __func__, ecryptfs_message_buf_len);
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -75,8 +78,7 @@ static int ecryptfs_acquire_free_msg_ctx(struct ecryptfs_msg_ctx **msg_ctx)
  * ecryptfs_msg_ctx_free_to_alloc
  * @msg_ctx: The context to move from the free list to the alloc list
  *
- * Be sure to lock the list mutex and the context mutex before
- * calling.
+ * Must be called with ecryptfs_msg_ctx_lists_mux held.
  */
 static void ecryptfs_msg_ctx_free_to_alloc(struct ecryptfs_msg_ctx *msg_ctx)
 {
@@ -89,36 +91,39 @@ static void ecryptfs_msg_ctx_free_to_alloc(struct ecryptfs_msg_ctx *msg_ctx)
  * ecryptfs_msg_ctx_alloc_to_free
  * @msg_ctx: The context to move from the alloc list to the free list
  *
- * Be sure to lock the list mutex and the context mutex before
- * calling.
+ * Must be called with ecryptfs_msg_ctx_lists_mux held.
  */
-static void ecryptfs_msg_ctx_alloc_to_free(struct ecryptfs_msg_ctx *msg_ctx)
+void ecryptfs_msg_ctx_alloc_to_free(struct ecryptfs_msg_ctx *msg_ctx)
 {
 	list_move(&(msg_ctx->node), &ecryptfs_msg_ctx_free_list);
 	if (msg_ctx->msg)
 		kfree(msg_ctx->msg);
+	msg_ctx->msg = NULL;
 	msg_ctx->state = ECRYPTFS_MSG_CTX_STATE_FREE;
 }
 
 /**
- * ecryptfs_find_daemon_id
- * @uid: The user id which maps to the desired daemon id
- * @id: If return value is zero, points to the desired daemon id
- *      pointer
+ * ecryptfs_find_daemon_by_euid
+ * @euid: The effective user id which maps to the desired daemon id
+ * @user_ns: The namespace in which @euid applies
+ * @daemon: If return value is zero, points to the desired daemon pointer
  *
- * Search the hash list for the given user id.  Returns zero if the
- * user id exists in the list; non-zero otherwise.  The daemon id hash
- * mutex should be held before calling this function.
+ * Must be called with ecryptfs_daemon_hash_mux held.
+ *
+ * Search the hash list for the given user id.
+ *
+ * Returns zero if the user id exists in the list; non-zero otherwise.
  */
-static int ecryptfs_find_daemon_id(uid_t uid, struct ecryptfs_daemon_id **id)
+int ecryptfs_find_daemon_by_euid(struct ecryptfs_daemon **daemon, uid_t euid,
+				 struct user_namespace *user_ns)
 {
 	struct hlist_node *elem;
 	int rc;
 
-	hlist_for_each_entry(*id, elem,
-			     &ecryptfs_daemon_id_hash[ecryptfs_uid_hash(uid)],
-			     id_chain) {
-		if ((*id)->uid == uid) {
+	hlist_for_each_entry(*daemon, elem,
+			     &ecryptfs_daemon_hash[ecryptfs_uid_hash(euid)],
+			     euid_chain) {
+		if ((*daemon)->euid == euid && (*daemon)->user_ns == user_ns) {
 			rc = 0;
 			goto out;
 		}
@@ -128,181 +133,325 @@ static int ecryptfs_find_daemon_id(uid_t uid, struct ecryptfs_daemon_id **id)
 	return rc;
 }
 
-static int ecryptfs_send_raw_message(unsigned int transport, u16 msg_type,
-				     pid_t pid)
+static int
+ecryptfs_send_message_locked(unsigned int transport, char *data, int data_len,
+			     u8 msg_type, struct ecryptfs_msg_ctx **msg_ctx);
+
+/**
+ * ecryptfs_send_raw_message
+ * @transport: Transport type
+ * @msg_type: Message type
+ * @daemon: Daemon struct for recipient of message
+ *
+ * A raw message is one that does not include an ecryptfs_message
+ * struct. It simply has a type.
+ *
+ * Must be called with ecryptfs_daemon_hash_mux held.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int ecryptfs_send_raw_message(unsigned int transport, u8 msg_type,
+				     struct ecryptfs_daemon *daemon)
 {
+	struct ecryptfs_msg_ctx *msg_ctx;
 	int rc;
 
 	switch(transport) {
 	case ECRYPTFS_TRANSPORT_NETLINK:
-		rc = ecryptfs_send_netlink(NULL, 0, NULL, msg_type, 0, pid);
+		rc = ecryptfs_send_netlink(NULL, 0, NULL, msg_type, 0,
+					   daemon->pid);
+		break;
+	case ECRYPTFS_TRANSPORT_MISCDEV:
+		rc = ecryptfs_send_message_locked(transport, NULL, 0, msg_type,
+						  &msg_ctx);
+		if (rc) {
+			printk(KERN_ERR "%s: Error whilst attempting to send "
+			       "message via procfs; rc = [%d]\n", __func__, rc);
+			goto out;
+		}
+		/* Raw messages are logically context-free (e.g., no
+		 * reply is expected), so we set the state of the
+		 * ecryptfs_msg_ctx object to indicate that it should
+		 * be freed as soon as the transport sends out the message. */
+		mutex_lock(&msg_ctx->mux);
+		msg_ctx->state = ECRYPTFS_MSG_CTX_STATE_NO_REPLY;
+		mutex_unlock(&msg_ctx->mux);
 		break;
 	case ECRYPTFS_TRANSPORT_CONNECTOR:
 	case ECRYPTFS_TRANSPORT_RELAYFS:
 	default:
 		rc = -ENOSYS;
 	}
+out:
+	return rc;
+}
+
+/**
+ * ecryptfs_spawn_daemon - Create and initialize a new daemon struct
+ * @daemon: Pointer to set to newly allocated daemon struct
+ * @euid: Effective user id for the daemon
+ * @user_ns: The namespace in which @euid applies
+ * @pid: Process id for the daemon
+ *
+ * Must be called ceremoniously while in possession of
+ * ecryptfs_sacred_daemon_hash_mux
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+int
+ecryptfs_spawn_daemon(struct ecryptfs_daemon **daemon, uid_t euid,
+		      struct user_namespace *user_ns, struct pid *pid)
+{
+	int rc = 0;
+
+	(*daemon) = kzalloc(sizeof(**daemon), GFP_KERNEL);
+	if (!(*daemon)) {
+		rc = -ENOMEM;
+		printk(KERN_ERR "%s: Failed to allocate [%Zd] bytes of "
+		       "GFP_KERNEL memory\n", __func__, sizeof(**daemon));
+		goto out;
+	}
+	(*daemon)->euid = euid;
+	(*daemon)->user_ns = get_user_ns(user_ns);
+	(*daemon)->pid = get_pid(pid);
+	(*daemon)->task = current;
+	mutex_init(&(*daemon)->mux);
+	INIT_LIST_HEAD(&(*daemon)->msg_ctx_out_queue);
+	init_waitqueue_head(&(*daemon)->wait);
+	(*daemon)->num_queued_msg_ctx = 0;
+	hlist_add_head(&(*daemon)->euid_chain,
+		       &ecryptfs_daemon_hash[ecryptfs_uid_hash(euid)]);
+out:
 	return rc;
 }
 
 /**
  * ecryptfs_process_helo
  * @transport: The underlying transport (netlink, etc.)
- * @uid: The user ID owner of the message
+ * @euid: The user ID owner of the message
+ * @user_ns: The namespace in which @euid applies
  * @pid: The process ID for the userspace program that sent the
  *       message
  *
- * Adds the uid and pid values to the daemon id hash.  If a uid
+ * Adds the euid and pid values to the daemon euid hash.  If an euid
  * already has a daemon pid registered, the daemon will be
- * unregistered before the new daemon id is put into the hash list.
- * Returns zero after adding a new daemon id to the hash list;
+ * unregistered before the new daemon is put into the hash list.
+ * Returns zero after adding a new daemon to the hash list;
  * non-zero otherwise.
  */
-int ecryptfs_process_helo(unsigned int transport, uid_t uid, pid_t pid)
+int ecryptfs_process_helo(unsigned int transport, uid_t euid,
+			  struct user_namespace *user_ns, struct pid *pid)
 {
-	struct ecryptfs_daemon_id *new_id;
-	struct ecryptfs_daemon_id *old_id;
+	struct ecryptfs_daemon *new_daemon;
+	struct ecryptfs_daemon *old_daemon;
 	int rc;
 
-	mutex_lock(&ecryptfs_daemon_id_hash_mux);
-	new_id = kmalloc(sizeof(*new_id), GFP_KERNEL);
-	if (!new_id) {
-		rc = -ENOMEM;
-		ecryptfs_printk(KERN_ERR, "Failed to allocate memory; unable "
-				"to register daemon [%d] for user [%d]\n",
-				pid, uid);
-		goto unlock;
-	}
-	if (!ecryptfs_find_daemon_id(uid, &old_id)) {
+	mutex_lock(&ecryptfs_daemon_hash_mux);
+	rc = ecryptfs_find_daemon_by_euid(&old_daemon, euid, user_ns);
+	if (rc != 0) {
 		printk(KERN_WARNING "Received request from user [%d] "
-		       "to register daemon [%d]; unregistering daemon "
-		       "[%d]\n", uid, pid, old_id->pid);
-		hlist_del(&old_id->id_chain);
-		rc = ecryptfs_send_raw_message(transport, ECRYPTFS_NLMSG_QUIT,
-					       old_id->pid);
+		       "to register daemon [0x%p]; unregistering daemon "
+		       "[0x%p]\n", euid, pid, old_daemon->pid);
+		rc = ecryptfs_send_raw_message(transport, ECRYPTFS_MSG_QUIT,
+					       old_daemon);
 		if (rc)
 			printk(KERN_WARNING "Failed to send QUIT "
-			       "message to daemon [%d]; rc = [%d]\n",
-			       old_id->pid, rc);
-		kfree(old_id);
+			       "message to daemon [0x%p]; rc = [%d]\n",
+			       old_daemon->pid, rc);
+		hlist_del(&old_daemon->euid_chain);
+		kfree(old_daemon);
 	}
-	new_id->uid = uid;
-	new_id->pid = pid;
-	hlist_add_head(&new_id->id_chain,
-		       &ecryptfs_daemon_id_hash[ecryptfs_uid_hash(uid)]);
-	rc = 0;
-unlock:
-	mutex_unlock(&ecryptfs_daemon_id_hash_mux);
+	rc = ecryptfs_spawn_daemon(&new_daemon, euid, user_ns, pid);
+	if (rc)
+		printk(KERN_ERR "%s: The gods are displeased with this attempt "
+		       "to create a new daemon object for euid [%d]; pid "
+		       "[0x%p]; rc = [%d]\n", __func__, euid, pid, rc);
+	mutex_unlock(&ecryptfs_daemon_hash_mux);
+	return rc;
+}
+
+/**
+ * ecryptfs_exorcise_daemon - Destroy the daemon struct
+ *
+ * Must be called ceremoniously while in possession of
+ * ecryptfs_daemon_hash_mux and the daemon's own mux.
+ */
+int ecryptfs_exorcise_daemon(struct ecryptfs_daemon *daemon)
+{
+	struct ecryptfs_msg_ctx *msg_ctx, *msg_ctx_tmp;
+	int rc = 0;
+
+	mutex_lock(&daemon->mux);
+	if ((daemon->flags & ECRYPTFS_DAEMON_IN_READ)
+	    || (daemon->flags & ECRYPTFS_DAEMON_IN_POLL)) {
+		rc = -EBUSY;
+		printk(KERN_WARNING "%s: Attempt to destroy daemon with pid "
+		       "[0x%p], but it is in the midst of a read or a poll\n",
+		       __func__, daemon->pid);
+		mutex_unlock(&daemon->mux);
+		goto out;
+	}
+	list_for_each_entry_safe(msg_ctx, msg_ctx_tmp,
+				 &daemon->msg_ctx_out_queue, daemon_out_list) {
+		list_del(&msg_ctx->daemon_out_list);
+		daemon->num_queued_msg_ctx--;
+		printk(KERN_WARNING "%s: Warning: dropping message that is in "
+		       "the out queue of a dying daemon\n", __func__);
+		ecryptfs_msg_ctx_alloc_to_free(msg_ctx);
+	}
+	hlist_del(&daemon->euid_chain);
+	if (daemon->task)
+		wake_up_process(daemon->task);
+	if (daemon->pid)
+		put_pid(daemon->pid);
+	if (daemon->user_ns)
+		put_user_ns(daemon->user_ns);
+	mutex_unlock(&daemon->mux);
+	memset(daemon, 0, sizeof(*daemon));
+	kfree(daemon);
+out:
 	return rc;
 }
 
 /**
  * ecryptfs_process_quit
- * @uid: The user ID owner of the message
+ * @euid: The user ID owner of the message
+ * @user_ns: The namespace in which @euid applies
  * @pid: The process ID for the userspace program that sent the
  *       message
  *
- * Deletes the corresponding daemon id for the given uid and pid, if
+ * Deletes the corresponding daemon for the given euid and pid, if
  * it is the registered that is requesting the deletion. Returns zero
- * after deleting the desired daemon id; non-zero otherwise.
+ * after deleting the desired daemon; non-zero otherwise.
  */
-int ecryptfs_process_quit(uid_t uid, pid_t pid)
+int ecryptfs_process_quit(uid_t euid, struct user_namespace *user_ns,
+			  struct pid *pid)
 {
-	struct ecryptfs_daemon_id *id;
+	struct ecryptfs_daemon *daemon;
 	int rc;
 
-	mutex_lock(&ecryptfs_daemon_id_hash_mux);
-	if (ecryptfs_find_daemon_id(uid, &id)) {
+	mutex_lock(&ecryptfs_daemon_hash_mux);
+	rc = ecryptfs_find_daemon_by_euid(&daemon, euid, user_ns);
+	if (rc || !daemon) {
 		rc = -EINVAL;
-		ecryptfs_printk(KERN_ERR, "Received request from user [%d] to "
-				"unregister unrecognized daemon [%d]\n", uid,
-				pid);
-		goto unlock;
+		printk(KERN_ERR "Received request from user [%d] to "
+		       "unregister unrecognized daemon [0x%p]\n", euid, pid);
+		goto out_unlock;
 	}
-	if (id->pid != pid) {
-		rc = -EINVAL;
-		ecryptfs_printk(KERN_WARNING, "Received request from user [%d] "
-				"with pid [%d] to unregister daemon [%d]\n",
-				uid, pid, id->pid);
-		goto unlock;
-	}
-	hlist_del(&id->id_chain);
-	kfree(id);
-	rc = 0;
-unlock:
-	mutex_unlock(&ecryptfs_daemon_id_hash_mux);
+	rc = ecryptfs_exorcise_daemon(daemon);
+out_unlock:
+	mutex_unlock(&ecryptfs_daemon_hash_mux);
 	return rc;
 }
 
 /**
  * ecryptfs_process_reponse
  * @msg: The ecryptfs message received; the caller should sanity check
- *       msg->data_len
+ *       msg->data_len and free the memory
  * @pid: The process ID of the userspace application that sent the
  *       message
- * @seq: The sequence number of the message
+ * @seq: The sequence number of the message; must match the sequence
+ *       number for the existing message context waiting for this
+ *       response
+ *
+ * Processes a response message after sending an operation request to
+ * userspace. Some other process is awaiting this response. Before
+ * sending out its first communications, the other process allocated a
+ * msg_ctx from the ecryptfs_msg_ctx_arr at a particular index. The
+ * response message contains this index so that we can copy over the
+ * response message into the msg_ctx that the process holds a
+ * reference to. The other process is going to wake up, check to see
+ * that msg_ctx->state == ECRYPTFS_MSG_CTX_STATE_DONE, and then
+ * proceed to read off and process the response message. Returns zero
+ * upon delivery to desired context element; non-zero upon delivery
+ * failure or error.
  *
- * Processes a response message after sending a operation request to
- * userspace. Returns zero upon delivery to desired context element;
- * non-zero upon delivery failure or error.
+ * Returns zero on success; non-zero otherwise
  */
-int ecryptfs_process_response(struct ecryptfs_message *msg, uid_t uid,
-			      pid_t pid, u32 seq)
+int ecryptfs_process_response(struct ecryptfs_message *msg, uid_t euid,
+			      struct user_namespace *user_ns, struct pid *pid,
+			      u32 seq)
 {
-	struct ecryptfs_daemon_id *id;
+	struct ecryptfs_daemon *daemon;
 	struct ecryptfs_msg_ctx *msg_ctx;
-	int msg_size;
+	size_t msg_size;
+	struct nsproxy *nsproxy;
+	struct user_namespace *current_user_ns;
 	int rc;
 
 	if (msg->index >= ecryptfs_message_buf_len) {
 		rc = -EINVAL;
-		ecryptfs_printk(KERN_ERR, "Attempt to reference "
-				"context buffer at index [%d]; maximum "
-				"allowable is [%d]\n", msg->index,
-				(ecryptfs_message_buf_len - 1));
+		printk(KERN_ERR "%s: Attempt to reference "
+		       "context buffer at index [%d]; maximum "
+		       "allowable is [%d]\n", __func__, msg->index,
+		       (ecryptfs_message_buf_len - 1));
 		goto out;
 	}
 	msg_ctx = &ecryptfs_msg_ctx_arr[msg->index];
 	mutex_lock(&msg_ctx->mux);
-	if (ecryptfs_find_daemon_id(msg_ctx->task->euid, &id)) {
+	mutex_lock(&ecryptfs_daemon_hash_mux);
+	rcu_read_lock();
+	nsproxy = task_nsproxy(msg_ctx->task);
+	if (nsproxy == NULL) {
 		rc = -EBADMSG;
-		ecryptfs_printk(KERN_WARNING, "User [%d] received a "
-				"message response from process [%d] but does "
-				"not have a registered daemon\n",
-				msg_ctx->task->euid, pid);
+		printk(KERN_ERR "%s: Receiving process is a zombie. Dropping "
+		       "message.\n", __func__);
+		rcu_read_unlock();
+		mutex_unlock(&ecryptfs_daemon_hash_mux);
 		goto wake_up;
 	}
-	if (msg_ctx->task->euid != uid) {
+	current_user_ns = nsproxy->user_ns;
+	rc = ecryptfs_find_daemon_by_euid(&daemon, msg_ctx->task->euid,
+					  current_user_ns);
+	rcu_read_unlock();
+	mutex_unlock(&ecryptfs_daemon_hash_mux);
+	if (rc) {
+		rc = -EBADMSG;
+		printk(KERN_WARNING "%s: User [%d] received a "
+		       "message response from process [0x%p] but does "
+		       "not have a registered daemon\n", __func__,
+		       msg_ctx->task->euid, pid);
+		goto wake_up;
+	}
+	if (msg_ctx->task->euid != euid) {
 		rc = -EBADMSG;
-		ecryptfs_printk(KERN_WARNING, "Received message from user "
-				"[%d]; expected message from user [%d]\n",
-				uid, msg_ctx->task->euid);
+		printk(KERN_WARNING "%s: Received message from user "
+		       "[%d]; expected message from user [%d]\n", __func__,
+		       euid, msg_ctx->task->euid);
 		goto unlock;
 	}
-	if (id->pid != pid) {
+	if (current_user_ns != user_ns) {
 		rc = -EBADMSG;
-		ecryptfs_printk(KERN_ERR, "User [%d] received a "
-				"message response from an unrecognized "
-				"process [%d]\n", msg_ctx->task->euid, pid);
+		printk(KERN_WARNING "%s: Received message from user_ns "
+		       "[0x%p]; expected message from user_ns [0x%p]\n",
+		       __func__, user_ns, nsproxy->user_ns);
+		goto unlock;
+	}
+	if (daemon->pid != pid) {
+		rc = -EBADMSG;
+		printk(KERN_ERR "%s: User [%d] sent a message response "
+		       "from an unrecognized process [0x%p]\n",
+		       __func__, msg_ctx->task->euid, pid);
 		goto unlock;
 	}
 	if (msg_ctx->state != ECRYPTFS_MSG_CTX_STATE_PENDING) {
 		rc = -EINVAL;
-		ecryptfs_printk(KERN_WARNING, "Desired context element is not "
-				"pending a response\n");
+		printk(KERN_WARNING "%s: Desired context element is not "
+		       "pending a response\n", __func__);
 		goto unlock;
 	} else if (msg_ctx->counter != seq) {
 		rc = -EINVAL;
-		ecryptfs_printk(KERN_WARNING, "Invalid message sequence; "
-				"expected [%d]; received [%d]\n",
-				msg_ctx->counter, seq);
+		printk(KERN_WARNING "%s: Invalid message sequence; "
+		       "expected [%d]; received [%d]\n", __func__,
+		       msg_ctx->counter, seq);
 		goto unlock;
 	}
-	msg_size = sizeof(*msg) + msg->data_len;
+	msg_size = (sizeof(*msg) + msg->data_len);
 	msg_ctx->msg = kmalloc(msg_size, GFP_KERNEL);
 	if (!msg_ctx->msg) {
 		rc = -ENOMEM;
-		ecryptfs_printk(KERN_ERR, "Failed to allocate memory\n");
+		printk(KERN_ERR "%s: Failed to allocate [%Zd] bytes of "
+		       "GFP_KERNEL memory\n", __func__, msg_size);
 		goto unlock;
 	}
 	memcpy(msg_ctx->msg, msg, msg_size);
@@ -317,34 +466,38 @@ int ecryptfs_process_response(struct ecryptfs_message *msg, uid_t uid,
 }
 
 /**
- * ecryptfs_send_message
+ * ecryptfs_send_message_locked
  * @transport: The transport over which to send the message (i.e.,
  *             netlink)
  * @data: The data to send
  * @data_len: The length of data
  * @msg_ctx: The message context allocated for the send
+ *
+ * Must be called with ecryptfs_daemon_hash_mux held.
+ *
+ * Returns zero on success; non-zero otherwise
  */
-int ecryptfs_send_message(unsigned int transport, char *data, int data_len,
-			  struct ecryptfs_msg_ctx **msg_ctx)
+static int
+ecryptfs_send_message_locked(unsigned int transport, char *data, int data_len,
+			     u8 msg_type, struct ecryptfs_msg_ctx **msg_ctx)
 {
-	struct ecryptfs_daemon_id *id;
+	struct ecryptfs_daemon *daemon;
 	int rc;
 
-	mutex_lock(&ecryptfs_daemon_id_hash_mux);
-	if (ecryptfs_find_daemon_id(current->euid, &id)) {
-		mutex_unlock(&ecryptfs_daemon_id_hash_mux);
+	rc = ecryptfs_find_daemon_by_euid(&daemon, current->euid,
+					  current->nsproxy->user_ns);
+	if (rc || !daemon) {
 		rc = -ENOTCONN;
-		ecryptfs_printk(KERN_ERR, "User [%d] does not have a daemon "
-				"registered\n", current->euid);
+		printk(KERN_ERR "%s: User [%d] does not have a daemon "
+		       "registered\n", __func__, current->euid);
 		goto out;
 	}
-	mutex_unlock(&ecryptfs_daemon_id_hash_mux);
 	mutex_lock(&ecryptfs_msg_ctx_lists_mux);
 	rc = ecryptfs_acquire_free_msg_ctx(msg_ctx);
 	if (rc) {
 		mutex_unlock(&ecryptfs_msg_ctx_lists_mux);
-		ecryptfs_printk(KERN_WARNING, "Could not claim a free "
-				"context element\n");
+		printk(KERN_WARNING "%s: Could not claim a free "
+		       "context element\n", __func__);
 		goto out;
 	}
 	ecryptfs_msg_ctx_free_to_alloc(*msg_ctx);
@@ -352,22 +505,49 @@ int ecryptfs_send_message(unsigned int transport, char *data, int data_len,
 	mutex_unlock(&ecryptfs_msg_ctx_lists_mux);
 	switch (transport) {
 	case ECRYPTFS_TRANSPORT_NETLINK:
-		rc = ecryptfs_send_netlink(data, data_len, *msg_ctx,
-					   ECRYPTFS_NLMSG_REQUEST, 0, id->pid);
+		rc = ecryptfs_send_netlink(data, data_len, *msg_ctx, msg_type,
+					   0, daemon->pid);
+		break;
+	case ECRYPTFS_TRANSPORT_MISCDEV:
+		rc = ecryptfs_send_miscdev(data, data_len, *msg_ctx, msg_type,
+					   0, daemon);
 		break;
 	case ECRYPTFS_TRANSPORT_CONNECTOR:
 	case ECRYPTFS_TRANSPORT_RELAYFS:
 	default:
 		rc = -ENOSYS;
 	}
-	if (rc) {
-		printk(KERN_ERR "Error attempting to send message to userspace "
-		       "daemon; rc = [%d]\n", rc);
-	}
+	if (rc)
+		printk(KERN_ERR "%s: Error attempting to send message to "
+		       "userspace daemon; rc = [%d]\n", __func__, rc);
 out:
 	return rc;
 }
 
+/**
+ * ecryptfs_send_message
+ * @transport: The transport over which to send the message (i.e.,
+ *             netlink)
+ * @data: The data to send
+ * @data_len: The length of data
+ * @msg_ctx: The message context allocated for the send
+ *
+ * Grabs ecryptfs_daemon_hash_mux.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+int ecryptfs_send_message(unsigned int transport, char *data, int data_len,
+			  struct ecryptfs_msg_ctx **msg_ctx)
+{
+	int rc;
+
+	mutex_lock(&ecryptfs_daemon_hash_mux);
+	rc = ecryptfs_send_message_locked(transport, data, data_len,
+					  ECRYPTFS_MSG_REQUEST, msg_ctx);
+	mutex_unlock(&ecryptfs_daemon_hash_mux);
+	return rc;
+}
+
 /**
  * ecryptfs_wait_for_response
  * @msg_ctx: The context that was assigned when sending a message
@@ -377,7 +557,7 @@ int ecryptfs_send_message(unsigned int transport, char *data, int data_len,
  * of time exceeds ecryptfs_message_wait_timeout.  If zero is
  * returned, msg will point to a valid message from userspace; a
  * non-zero value is returned upon failure to receive a message or an
- * error occurs.
+ * error occurs. Callee must free @msg on success.
  */
 int ecryptfs_wait_for_response(struct ecryptfs_msg_ctx *msg_ctx,
 			       struct ecryptfs_message **msg)
@@ -413,32 +593,32 @@ int ecryptfs_init_messaging(unsigned int transport)
 
 	if (ecryptfs_number_of_users > ECRYPTFS_MAX_NUM_USERS) {
 		ecryptfs_number_of_users = ECRYPTFS_MAX_NUM_USERS;
-		ecryptfs_printk(KERN_WARNING, "Specified number of users is "
-				"too large, defaulting to [%d] users\n",
-				ecryptfs_number_of_users);
+		printk(KERN_WARNING "%s: Specified number of users is "
+		       "too large, defaulting to [%d] users\n", __func__,
+		       ecryptfs_number_of_users);
 	}
-	mutex_init(&ecryptfs_daemon_id_hash_mux);
-	mutex_lock(&ecryptfs_daemon_id_hash_mux);
+	mutex_init(&ecryptfs_daemon_hash_mux);
+	mutex_lock(&ecryptfs_daemon_hash_mux);
 	ecryptfs_hash_buckets = 1;
 	while (ecryptfs_number_of_users >> ecryptfs_hash_buckets)
 		ecryptfs_hash_buckets++;
-	ecryptfs_daemon_id_hash = kmalloc(sizeof(struct hlist_head)
-					  * ecryptfs_hash_buckets, GFP_KERNEL);
-	if (!ecryptfs_daemon_id_hash) {
+	ecryptfs_daemon_hash = kmalloc((sizeof(struct hlist_head)
+					* ecryptfs_hash_buckets), GFP_KERNEL);
+	if (!ecryptfs_daemon_hash) {
 		rc = -ENOMEM;
-		ecryptfs_printk(KERN_ERR, "Failed to allocate memory\n");
-		mutex_unlock(&ecryptfs_daemon_id_hash_mux);
+		printk(KERN_ERR "%s: Failed to allocate memory\n", __func__);
+		mutex_unlock(&ecryptfs_daemon_hash_mux);
 		goto out;
 	}
 	for (i = 0; i < ecryptfs_hash_buckets; i++)
-		INIT_HLIST_HEAD(&ecryptfs_daemon_id_hash[i]);
-	mutex_unlock(&ecryptfs_daemon_id_hash_mux);
-
+		INIT_HLIST_HEAD(&ecryptfs_daemon_hash[i]);
+	mutex_unlock(&ecryptfs_daemon_hash_mux);
 	ecryptfs_msg_ctx_arr = kmalloc((sizeof(struct ecryptfs_msg_ctx)
-				      * ecryptfs_message_buf_len), GFP_KERNEL);
+					* ecryptfs_message_buf_len),
+				       GFP_KERNEL);
 	if (!ecryptfs_msg_ctx_arr) {
 		rc = -ENOMEM;
-		ecryptfs_printk(KERN_ERR, "Failed to allocate memory\n");
+		printk(KERN_ERR "%s: Failed to allocate memory\n", __func__);
 		goto out;
 	}
 	mutex_init(&ecryptfs_msg_ctx_lists_mux);
@@ -446,6 +626,7 @@ int ecryptfs_init_messaging(unsigned int transport)
 	ecryptfs_msg_counter = 0;
 	for (i = 0; i < ecryptfs_message_buf_len; i++) {
 		INIT_LIST_HEAD(&ecryptfs_msg_ctx_arr[i].node);
+		INIT_LIST_HEAD(&ecryptfs_msg_ctx_arr[i].daemon_out_list);
 		mutex_init(&ecryptfs_msg_ctx_arr[i].mux);
 		mutex_lock(&ecryptfs_msg_ctx_arr[i].mux);
 		ecryptfs_msg_ctx_arr[i].index = i;
@@ -464,6 +645,11 @@ int ecryptfs_init_messaging(unsigned int transport)
 		if (rc)
 			ecryptfs_release_messaging(transport);
 		break;
+	case ECRYPTFS_TRANSPORT_MISCDEV:
+		rc = ecryptfs_init_ecryptfs_miscdev();
+		if (rc)
+			ecryptfs_release_messaging(transport);
+		break;
 	case ECRYPTFS_TRANSPORT_CONNECTOR:
 	case ECRYPTFS_TRANSPORT_RELAYFS:
 	default:
@@ -488,27 +674,37 @@ void ecryptfs_release_messaging(unsigned int transport)
 		kfree(ecryptfs_msg_ctx_arr);
 		mutex_unlock(&ecryptfs_msg_ctx_lists_mux);
 	}
-	if (ecryptfs_daemon_id_hash) {
+	if (ecryptfs_daemon_hash) {
 		struct hlist_node *elem;
-		struct ecryptfs_daemon_id *id;
+		struct ecryptfs_daemon *daemon;
 		int i;
 
-		mutex_lock(&ecryptfs_daemon_id_hash_mux);
+		mutex_lock(&ecryptfs_daemon_hash_mux);
 		for (i = 0; i < ecryptfs_hash_buckets; i++) {
-			hlist_for_each_entry(id, elem,
-					     &ecryptfs_daemon_id_hash[i],
-					     id_chain) {
-				hlist_del(elem);
-				kfree(id);
+			int rc;
+
+			hlist_for_each_entry(daemon, elem,
+					     &ecryptfs_daemon_hash[i],
+					     euid_chain) {
+				rc = ecryptfs_exorcise_daemon(daemon);
+				if (rc)
+					printk(KERN_ERR "%s: Error whilst "
+					       "attempting to destroy daemon; "
+					       "rc = [%d]. Dazed and confused, "
+					       "but trying to continue.\n",
+					       __func__, rc);
 			}
 		}
-		kfree(ecryptfs_daemon_id_hash);
-		mutex_unlock(&ecryptfs_daemon_id_hash_mux);
+		kfree(ecryptfs_daemon_hash);
+		mutex_unlock(&ecryptfs_daemon_hash_mux);
 	}
 	switch(transport) {
 	case ECRYPTFS_TRANSPORT_NETLINK:
 		ecryptfs_release_netlink();
 		break;
+	case ECRYPTFS_TRANSPORT_MISCDEV:
+		ecryptfs_destroy_ecryptfs_miscdev();
+		break;
 	case ECRYPTFS_TRANSPORT_CONNECTOR:
 	case ECRYPTFS_TRANSPORT_RELAYFS:
 	default:
diff --git a/trunk/fs/ecryptfs/miscdev.c b/trunk/fs/ecryptfs/miscdev.c
new file mode 100644
index 000000000000..788995efd1d3
--- /dev/null
+++ b/trunk/fs/ecryptfs/miscdev.c
@@ -0,0 +1,598 @@
+/**
+ * eCryptfs: Linux filesystem encryption layer
+ *
+ * Copyright (C) 2008 International Business Machines Corp.
+ *   Author(s): Michael A. Halcrow <mhalcrow@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
+ * 02111-1307, USA.
+ */
+
+#include <linux/fs.h>
+#include <linux/hash.h>
+#include <linux/random.h>
+#include <linux/miscdevice.h>
+#include <linux/poll.h>
+#include <linux/wait.h>
+#include <linux/module.h>
+#include "ecryptfs_kernel.h"
+
+static atomic_t ecryptfs_num_miscdev_opens;
+
+/**
+ * ecryptfs_miscdev_poll
+ * @file: dev file (ignored)
+ * @pt: dev poll table (ignored)
+ *
+ * Returns the poll mask
+ */
+static unsigned int
+ecryptfs_miscdev_poll(struct file *file, poll_table *pt)
+{
+	struct ecryptfs_daemon *daemon;
+	unsigned int mask = 0;
+	int rc;
+
+	mutex_lock(&ecryptfs_daemon_hash_mux);
+	/* TODO: Just use file->private_data? */
+	rc = ecryptfs_find_daemon_by_euid(&daemon, current->euid,
+					  current->nsproxy->user_ns);
+	BUG_ON(rc || !daemon);
+	mutex_lock(&daemon->mux);
+	mutex_unlock(&ecryptfs_daemon_hash_mux);
+	if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) {
+		printk(KERN_WARNING "%s: Attempt to poll on zombified "
+		       "daemon\n", __func__);
+		goto out_unlock_daemon;
+	}
+	if (daemon->flags & ECRYPTFS_DAEMON_IN_READ)
+		goto out_unlock_daemon;
+	if (daemon->flags & ECRYPTFS_DAEMON_IN_POLL)
+		goto out_unlock_daemon;
+	daemon->flags |= ECRYPTFS_DAEMON_IN_POLL;
+	mutex_unlock(&daemon->mux);
+	poll_wait(file, &daemon->wait, pt);
+	mutex_lock(&daemon->mux);
+	if (!list_empty(&daemon->msg_ctx_out_queue))
+		mask |= POLLIN | POLLRDNORM;
+out_unlock_daemon:
+	daemon->flags &= ~ECRYPTFS_DAEMON_IN_POLL;
+	mutex_unlock(&daemon->mux);
+	return mask;
+}
+
+/**
+ * ecryptfs_miscdev_open
+ * @inode: inode of miscdev handle (ignored)
+ * @file: file for miscdev handle (ignored)
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int
+ecryptfs_miscdev_open(struct inode *inode, struct file *file)
+{
+	struct ecryptfs_daemon *daemon = NULL;
+	int rc;
+
+	mutex_lock(&ecryptfs_daemon_hash_mux);
+	rc = try_module_get(THIS_MODULE);
+	if (rc == 0) {
+		rc = -EIO;
+		printk(KERN_ERR "%s: Error attempting to increment module use "
+		       "count; rc = [%d]\n", __func__, rc);
+		goto out_unlock_daemon_list;
+	}
+	rc = ecryptfs_find_daemon_by_euid(&daemon, current->euid,
+					  current->nsproxy->user_ns);
+	if (rc || !daemon) {
+		rc = ecryptfs_spawn_daemon(&daemon, current->euid,
+					   current->nsproxy->user_ns,
+					   task_pid(current));
+		if (rc) {
+			printk(KERN_ERR "%s: Error attempting to spawn daemon; "
+			       "rc = [%d]\n", __func__, rc);
+			goto out_module_put_unlock_daemon_list;
+		}
+	}
+	mutex_lock(&daemon->mux);
+	if (daemon->pid != task_pid(current)) {
+		rc = -EINVAL;
+		printk(KERN_ERR "%s: pid [0x%p] has registered with euid [%d], "
+		       "but pid [0x%p] has attempted to open the handle "
+		       "instead\n", __func__, daemon->pid, daemon->euid,
+		       task_pid(current));
+		goto out_unlock_daemon;
+	}
+	if (daemon->flags & ECRYPTFS_DAEMON_MISCDEV_OPEN) {
+		rc = -EBUSY;
+		printk(KERN_ERR "%s: Miscellaneous device handle may only be "
+		       "opened once per daemon; pid [0x%p] already has this "
+		       "handle open\n", __func__, daemon->pid);
+		goto out_unlock_daemon;
+	}
+	daemon->flags |= ECRYPTFS_DAEMON_MISCDEV_OPEN;
+	atomic_inc(&ecryptfs_num_miscdev_opens);
+out_unlock_daemon:
+	mutex_unlock(&daemon->mux);
+out_module_put_unlock_daemon_list:
+	if (rc)
+		module_put(THIS_MODULE);
+out_unlock_daemon_list:
+	mutex_unlock(&ecryptfs_daemon_hash_mux);
+	return rc;
+}
+
+/**
+ * ecryptfs_miscdev_release
+ * @inode: inode of fs/ecryptfs/euid handle (ignored)
+ * @file: file for fs/ecryptfs/euid handle (ignored)
+ *
+ * This keeps the daemon registered until the daemon sends another
+ * ioctl to fs/ecryptfs/ctl or until the kernel module unregisters.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int
+ecryptfs_miscdev_release(struct inode *inode, struct file *file)
+{
+	struct ecryptfs_daemon *daemon = NULL;
+	int rc;
+
+	mutex_lock(&ecryptfs_daemon_hash_mux);
+	rc = ecryptfs_find_daemon_by_euid(&daemon, current->euid,
+					  current->nsproxy->user_ns);
+	BUG_ON(rc || !daemon);
+	mutex_lock(&daemon->mux);
+	BUG_ON(daemon->pid != task_pid(current));
+	BUG_ON(!(daemon->flags & ECRYPTFS_DAEMON_MISCDEV_OPEN));
+	daemon->flags &= ~ECRYPTFS_DAEMON_MISCDEV_OPEN;
+	atomic_dec(&ecryptfs_num_miscdev_opens);
+	mutex_unlock(&daemon->mux);
+	rc = ecryptfs_exorcise_daemon(daemon);
+	if (rc) {
+		printk(KERN_CRIT "%s: Fatal error whilst attempting to "
+		       "shut down daemon; rc = [%d]. Please report this "
+		       "bug.\n", __func__, rc);
+		BUG();
+	}
+	module_put(THIS_MODULE);
+	mutex_unlock(&ecryptfs_daemon_hash_mux);
+	return rc;
+}
+
+/**
+ * ecryptfs_send_miscdev
+ * @data: Data to send to daemon; may be NULL
+ * @data_size: Amount of data to send to daemon
+ * @msg_ctx: Message context, which is used to handle the reply. If
+ *           this is NULL, then we do not expect a reply.
+ * @msg_type: Type of message
+ * @msg_flags: Flags for message
+ * @daemon: eCryptfs daemon object
+ *
+ * Add msg_ctx to queue and then, if it exists, notify the blocked
+ * miscdevess about the data being available. Must be called with
+ * ecryptfs_daemon_hash_mux held.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+int ecryptfs_send_miscdev(char *data, size_t data_size,
+			  struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type,
+			  u16 msg_flags, struct ecryptfs_daemon *daemon)
+{
+	int rc = 0;
+
+	mutex_lock(&msg_ctx->mux);
+	if (data) {
+		msg_ctx->msg = kmalloc((sizeof(*msg_ctx->msg) + data_size),
+				       GFP_KERNEL);
+		if (!msg_ctx->msg) {
+			rc = -ENOMEM;
+			printk(KERN_ERR "%s: Out of memory whilst attempting "
+			       "to kmalloc(%Zd, GFP_KERNEL)\n", __func__,
+			       (sizeof(*msg_ctx->msg) + data_size));
+			goto out_unlock;
+		}
+	} else
+		msg_ctx->msg = NULL;
+	msg_ctx->msg->index = msg_ctx->index;
+	msg_ctx->msg->data_len = data_size;
+	msg_ctx->type = msg_type;
+	if (data) {
+		memcpy(msg_ctx->msg->data, data, data_size);
+		msg_ctx->msg_size = (sizeof(*msg_ctx->msg) + data_size);
+	} else
+		msg_ctx->msg_size = 0;
+	mutex_lock(&daemon->mux);
+	list_add_tail(&msg_ctx->daemon_out_list, &daemon->msg_ctx_out_queue);
+	daemon->num_queued_msg_ctx++;
+	wake_up_interruptible(&daemon->wait);
+	mutex_unlock(&daemon->mux);
+out_unlock:
+	mutex_unlock(&msg_ctx->mux);
+	return rc;
+}
+
+/**
+ * ecryptfs_miscdev_read - format and send message from queue
+ * @file: fs/ecryptfs/euid miscdevfs handle (ignored)
+ * @buf: User buffer into which to copy the next message on the daemon queue
+ * @count: Amount of space available in @buf
+ * @ppos: Offset in file (ignored)
+ *
+ * Pulls the most recent message from the daemon queue, formats it for
+ * being sent via a miscdevfs handle, and copies it into @buf
+ *
+ * Returns the number of bytes copied into the user buffer
+ */
+static ssize_t
+ecryptfs_miscdev_read(struct file *file, char __user *buf, size_t count,
+		      loff_t *ppos)
+{
+	struct ecryptfs_daemon *daemon;
+	struct ecryptfs_msg_ctx *msg_ctx;
+	size_t packet_length_size;
+	u32 counter_nbo;
+	char packet_length[3];
+	size_t i;
+	size_t total_length;
+	int rc;
+
+	mutex_lock(&ecryptfs_daemon_hash_mux);
+	/* TODO: Just use file->private_data? */
+	rc = ecryptfs_find_daemon_by_euid(&daemon, current->euid,
+					  current->nsproxy->user_ns);
+	BUG_ON(rc || !daemon);
+	mutex_lock(&daemon->mux);
+	if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) {
+		rc = 0;
+		printk(KERN_WARNING "%s: Attempt to read from zombified "
+		       "daemon\n", __func__);
+		goto out_unlock_daemon;
+	}
+	if (daemon->flags & ECRYPTFS_DAEMON_IN_READ) {
+		rc = 0;
+		goto out_unlock_daemon;
+	}
+	/* This daemon will not go away so long as this flag is set */
+	daemon->flags |= ECRYPTFS_DAEMON_IN_READ;
+	mutex_unlock(&ecryptfs_daemon_hash_mux);
+check_list:
+	if (list_empty(&daemon->msg_ctx_out_queue)) {
+		mutex_unlock(&daemon->mux);
+		rc = wait_event_interruptible(
+			daemon->wait, !list_empty(&daemon->msg_ctx_out_queue));
+		mutex_lock(&daemon->mux);
+		if (rc < 0) {
+			rc = 0;
+			goto out_unlock_daemon;
+		}
+	}
+	if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) {
+		rc = 0;
+		goto out_unlock_daemon;
+	}
+	if (list_empty(&daemon->msg_ctx_out_queue)) {
+		/* Something else jumped in since the
+		 * wait_event_interruptable() and removed the
+		 * message from the queue; try again */
+		goto check_list;
+	}
+	BUG_ON(current->euid != daemon->euid);
+	BUG_ON(current->nsproxy->user_ns != daemon->user_ns);
+	BUG_ON(task_pid(current) != daemon->pid);
+	msg_ctx = list_first_entry(&daemon->msg_ctx_out_queue,
+				   struct ecryptfs_msg_ctx, daemon_out_list);
+	BUG_ON(!msg_ctx);
+	mutex_lock(&msg_ctx->mux);
+	if (msg_ctx->msg) {
+		rc = ecryptfs_write_packet_length(packet_length,
+						  msg_ctx->msg_size,
+						  &packet_length_size);
+		if (rc) {
+			rc = 0;
+			printk(KERN_WARNING "%s: Error writing packet length; "
+			       "rc = [%d]\n", __func__, rc);
+			goto out_unlock_msg_ctx;
+		}
+	} else {
+		packet_length_size = 0;
+		msg_ctx->msg_size = 0;
+	}
+	/* miscdevfs packet format:
+	 *  Octet 0: Type
+	 *  Octets 1-4: network byte order msg_ctx->counter
+	 *  Octets 5-N0: Size of struct ecryptfs_message to follow
+	 *  Octets N0-N1: struct ecryptfs_message (including data)
+	 *
+	 *  Octets 5-N1 not written if the packet type does not
+	 *  include a message */
+	total_length = (1 + 4 + packet_length_size + msg_ctx->msg_size);
+	if (count < total_length) {
+		rc = 0;
+		printk(KERN_WARNING "%s: Only given user buffer of "
+		       "size [%Zd], but we need [%Zd] to read the "
+		       "pending message\n", __func__, count, total_length);
+		goto out_unlock_msg_ctx;
+	}
+	i = 0;
+	buf[i++] = msg_ctx->type;
+	counter_nbo = cpu_to_be32(msg_ctx->counter);
+	memcpy(&buf[i], (char *)&counter_nbo, 4);
+	i += 4;
+	if (msg_ctx->msg) {
+		memcpy(&buf[i], packet_length, packet_length_size);
+		i += packet_length_size;
+		rc = copy_to_user(&buf[i], msg_ctx->msg, msg_ctx->msg_size);
+		if (rc) {
+			printk(KERN_ERR "%s: copy_to_user returned error "
+			       "[%d]\n", __func__, rc);
+			goto out_unlock_msg_ctx;
+		}
+		i += msg_ctx->msg_size;
+	}
+	rc = i;
+	list_del(&msg_ctx->daemon_out_list);
+	kfree(msg_ctx->msg);
+	msg_ctx->msg = NULL;
+	/* We do not expect a reply from the userspace daemon for any
+	 * message type other than ECRYPTFS_MSG_REQUEST */
+	if (msg_ctx->type != ECRYPTFS_MSG_REQUEST)
+		ecryptfs_msg_ctx_alloc_to_free(msg_ctx);
+out_unlock_msg_ctx:
+	mutex_unlock(&msg_ctx->mux);
+out_unlock_daemon:
+	daemon->flags &= ~ECRYPTFS_DAEMON_IN_READ;
+	mutex_unlock(&daemon->mux);
+	return rc;
+}
+
+/**
+ * ecryptfs_miscdev_helo
+ * @euid: effective user id of miscdevess sending helo packet
+ * @user_ns: The namespace in which @euid applies
+ * @pid: miscdevess id of miscdevess sending helo packet
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int ecryptfs_miscdev_helo(uid_t euid, struct user_namespace *user_ns,
+				 struct pid *pid)
+{
+	int rc;
+
+	rc = ecryptfs_process_helo(ECRYPTFS_TRANSPORT_MISCDEV, euid, user_ns,
+				   pid);
+	if (rc)
+		printk(KERN_WARNING "Error processing HELO; rc = [%d]\n", rc);
+	return rc;
+}
+
+/**
+ * ecryptfs_miscdev_quit
+ * @euid: effective user id of miscdevess sending quit packet
+ * @user_ns: The namespace in which @euid applies
+ * @pid: miscdevess id of miscdevess sending quit packet
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int ecryptfs_miscdev_quit(uid_t euid, struct user_namespace *user_ns,
+				 struct pid *pid)
+{
+	int rc;
+
+	rc = ecryptfs_process_quit(euid, user_ns, pid);
+	if (rc)
+		printk(KERN_WARNING
+		       "Error processing QUIT message; rc = [%d]\n", rc);
+	return rc;
+}
+
+/**
+ * ecryptfs_miscdev_response - miscdevess response to message previously sent to daemon
+ * @data: Bytes comprising struct ecryptfs_message
+ * @data_size: sizeof(struct ecryptfs_message) + data len
+ * @euid: Effective user id of miscdevess sending the miscdev response
+ * @user_ns: The namespace in which @euid applies
+ * @pid: Miscdevess id of miscdevess sending the miscdev response
+ * @seq: Sequence number for miscdev response packet
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int ecryptfs_miscdev_response(char *data, size_t data_size,
+				     uid_t euid, struct user_namespace *user_ns,
+				     struct pid *pid, u32 seq)
+{
+	struct ecryptfs_message *msg = (struct ecryptfs_message *)data;
+	int rc;
+
+	if ((sizeof(*msg) + msg->data_len) != data_size) {
+		printk(KERN_WARNING "%s: (sizeof(*msg) + msg->data_len) = "
+		       "[%Zd]; data_size = [%Zd]. Invalid packet.\n", __func__,
+		       (sizeof(*msg) + msg->data_len), data_size);
+		rc = -EINVAL;
+		goto out;
+	}
+	rc = ecryptfs_process_response(msg, euid, user_ns, pid, seq);
+	if (rc)
+		printk(KERN_ERR
+		       "Error processing response message; rc = [%d]\n", rc);
+out:
+	return rc;
+}
+
+/**
+ * ecryptfs_miscdev_write - handle write to daemon miscdev handle
+ * @file: File for misc dev handle (ignored)
+ * @buf: Buffer containing user data
+ * @count: Amount of data in @buf
+ * @ppos: Pointer to offset in file (ignored)
+ *
+ * miscdevfs packet format:
+ *  Octet 0: Type
+ *  Octets 1-4: network byte order msg_ctx->counter (0's for non-response)
+ *  Octets 5-N0: Size of struct ecryptfs_message to follow
+ *  Octets N0-N1: struct ecryptfs_message (including data)
+ *
+ * Returns the number of bytes read from @buf
+ */
+static ssize_t
+ecryptfs_miscdev_write(struct file *file, const char __user *buf,
+		       size_t count, loff_t *ppos)
+{
+	u32 counter_nbo, seq;
+	size_t packet_size, packet_size_length, i;
+	ssize_t sz = 0;
+	char *data;
+	int rc;
+
+	if (count == 0)
+		goto out;
+	data = kmalloc(count, GFP_KERNEL);
+	if (!data) {
+		printk(KERN_ERR "%s: Out of memory whilst attempting to "
+		       "kmalloc([%Zd], GFP_KERNEL)\n", __func__, count);
+		goto out;
+	}
+	rc = copy_from_user(data, buf, count);
+	if (rc) {
+		printk(KERN_ERR "%s: copy_from_user returned error [%d]\n",
+		       __func__, rc);
+		goto out_free;
+	}
+	sz = count;
+	i = 0;
+	switch (data[i++]) {
+	case ECRYPTFS_MSG_RESPONSE:
+		if (count < (1 + 4 + 1 + sizeof(struct ecryptfs_message))) {
+			printk(KERN_WARNING "%s: Minimum acceptable packet "
+			       "size is [%Zd], but amount of data written is "
+			       "only [%Zd]. Discarding response packet.\n",
+			       __func__,
+			       (1 + 4 + 1 + sizeof(struct ecryptfs_message)),
+			       count);
+			goto out_free;
+		}
+		memcpy((char *)&counter_nbo, &data[i], 4);
+		seq = be32_to_cpu(counter_nbo);
+		i += 4;
+		rc = ecryptfs_parse_packet_length(&data[i], &packet_size,
+						  &packet_size_length);
+		if (rc) {
+			printk(KERN_WARNING "%s: Error parsing packet length; "
+			       "rc = [%d]\n", __func__, rc);
+			goto out_free;
+		}
+		i += packet_size_length;
+		if ((1 + 4 + packet_size_length + packet_size) != count) {
+			printk(KERN_WARNING "%s: (1 + packet_size_length([%Zd])"
+			       " + packet_size([%Zd]))([%Zd]) != "
+			       "count([%Zd]). Invalid packet format.\n",
+			       __func__, packet_size_length, packet_size,
+			       (1 + packet_size_length + packet_size), count);
+			goto out_free;
+		}
+		rc = ecryptfs_miscdev_response(&data[i], packet_size,
+					       current->euid,
+					       current->nsproxy->user_ns,
+					       task_pid(current), seq);
+		if (rc)
+			printk(KERN_WARNING "%s: Failed to deliver miscdev "
+			       "response to requesting operation; rc = [%d]\n",
+			       __func__, rc);
+		break;
+	case ECRYPTFS_MSG_HELO:
+		rc = ecryptfs_miscdev_helo(current->euid,
+					   current->nsproxy->user_ns,
+					   task_pid(current));
+		if (rc) {
+			printk(KERN_ERR "%s: Error attempting to process "
+			       "helo from pid [0x%p]; rc = [%d]\n", __func__,
+			       task_pid(current), rc);
+			goto out_free;
+		}
+		break;
+	case ECRYPTFS_MSG_QUIT:
+		rc = ecryptfs_miscdev_quit(current->euid,
+					   current->nsproxy->user_ns,
+					   task_pid(current));
+		if (rc) {
+			printk(KERN_ERR "%s: Error attempting to process "
+			       "quit from pid [0x%p]; rc = [%d]\n", __func__,
+			       task_pid(current), rc);
+			goto out_free;
+		}
+		break;
+	default:
+		ecryptfs_printk(KERN_WARNING, "Dropping miscdev "
+				"message of unrecognized type [%d]\n",
+				data[0]);
+		break;
+	}
+out_free:
+	kfree(data);
+out:
+	return sz;
+}
+
+
+static const struct file_operations ecryptfs_miscdev_fops = {
+	.open    = ecryptfs_miscdev_open,
+	.poll    = ecryptfs_miscdev_poll,
+	.read    = ecryptfs_miscdev_read,
+	.write   = ecryptfs_miscdev_write,
+	.release = ecryptfs_miscdev_release,
+};
+
+static struct miscdevice ecryptfs_miscdev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name  = "ecryptfs",
+	.fops  = &ecryptfs_miscdev_fops
+};
+
+/**
+ * ecryptfs_init_ecryptfs_miscdev
+ *
+ * Messages sent to the userspace daemon from the kernel are placed on
+ * a queue associated with the daemon. The next read against the
+ * miscdev handle by that daemon will return the oldest message placed
+ * on the message queue for the daemon.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+int ecryptfs_init_ecryptfs_miscdev(void)
+{
+	int rc;
+
+	atomic_set(&ecryptfs_num_miscdev_opens, 0);
+	mutex_lock(&ecryptfs_daemon_hash_mux);
+	rc = misc_register(&ecryptfs_miscdev);
+	if (rc)
+		printk(KERN_ERR "%s: Failed to register miscellaneous device "
+		       "for communications with userspace daemons; rc = [%d]\n",
+		       __func__, rc);
+	mutex_unlock(&ecryptfs_daemon_hash_mux);
+	return rc;
+}
+
+/**
+ * ecryptfs_destroy_ecryptfs_miscdev
+ *
+ * All of the daemons must be exorcised prior to calling this
+ * function.
+ */
+void ecryptfs_destroy_ecryptfs_miscdev(void)
+{
+	BUG_ON(atomic_read(&ecryptfs_num_miscdev_opens) != 0);
+	misc_deregister(&ecryptfs_miscdev);
+}
diff --git a/trunk/fs/ecryptfs/mmap.c b/trunk/fs/ecryptfs/mmap.c
index 6df1debdccce..2b6fe1e6e8ba 100644
--- a/trunk/fs/ecryptfs/mmap.c
+++ b/trunk/fs/ecryptfs/mmap.c
@@ -153,7 +153,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
 			flush_dcache_page(page);
 			if (rc) {
 				printk(KERN_ERR "%s: Error reading xattr "
-				       "region; rc = [%d]\n", __FUNCTION__, rc);
+				       "region; rc = [%d]\n", __func__, rc);
 				goto out;
 			}
 		} else {
@@ -169,7 +169,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
 			if (rc) {
 				printk(KERN_ERR "%s: Error attempting to read "
 				       "extent at offset [%lld] in the lower "
-				       "file; rc = [%d]\n", __FUNCTION__,
+				       "file; rc = [%d]\n", __func__,
 				       lower_offset, rc);
 				goto out;
 			}
@@ -212,7 +212,7 @@ static int ecryptfs_readpage(struct file *file, struct page *page)
 				       "the encrypted content from the lower "
 				       "file whilst inserting the metadata "
 				       "from the xattr into the header; rc = "
-				       "[%d]\n", __FUNCTION__, rc);
+				       "[%d]\n", __func__, rc);
 				goto out;
 			}
 
@@ -293,7 +293,7 @@ static int ecryptfs_prepare_write(struct file *file, struct page *page,
 			if (rc) {
 				printk(KERN_ERR "%s: Error attemping to read "
 				       "lower page segment; rc = [%d]\n",
-				       __FUNCTION__, rc);
+				       __func__, rc);
 				ClearPageUptodate(page);
 				goto out;
 			} else
@@ -308,7 +308,7 @@ static int ecryptfs_prepare_write(struct file *file, struct page *page,
 					       "from the lower file whilst "
 					       "inserting the metadata from "
 					       "the xattr into the header; rc "
-					       "= [%d]\n", __FUNCTION__, rc);
+					       "= [%d]\n", __func__, rc);
 					ClearPageUptodate(page);
 					goto out;
 				}
@@ -320,7 +320,7 @@ static int ecryptfs_prepare_write(struct file *file, struct page *page,
 				if (rc) {
 					printk(KERN_ERR "%s: Error reading "
 					       "page; rc = [%d]\n",
-					       __FUNCTION__, rc);
+					       __func__, rc);
 					ClearPageUptodate(page);
 					goto out;
 				}
@@ -331,7 +331,7 @@ static int ecryptfs_prepare_write(struct file *file, struct page *page,
 			if (rc) {
 				printk(KERN_ERR "%s: Error decrypting page "
 				       "at index [%ld]; rc = [%d]\n",
-				       __FUNCTION__, page->index, rc);
+				       __func__, page->index, rc);
 				ClearPageUptodate(page);
 				goto out;
 			}
@@ -348,7 +348,7 @@ static int ecryptfs_prepare_write(struct file *file, struct page *page,
 			if (rc) {
 				printk(KERN_ERR "%s: Error on attempt to "
 				       "truncate to (higher) offset [%lld];"
-				       " rc = [%d]\n", __FUNCTION__,
+				       " rc = [%d]\n", __func__,
 				       prev_page_end_size, rc);
 				goto out;
 			}
@@ -389,7 +389,7 @@ static int ecryptfs_write_inode_size_to_header(struct inode *ecryptfs_inode)
 	kfree(file_size_virt);
 	if (rc)
 		printk(KERN_ERR "%s: Error writing file size to header; "
-		       "rc = [%d]\n", __FUNCTION__, rc);
+		       "rc = [%d]\n", __func__, rc);
 out:
 	return rc;
 }
diff --git a/trunk/fs/ecryptfs/netlink.c b/trunk/fs/ecryptfs/netlink.c
index f638a698dc52..e0abad62b395 100644
--- a/trunk/fs/ecryptfs/netlink.c
+++ b/trunk/fs/ecryptfs/netlink.c
@@ -44,8 +44,8 @@ static struct sock *ecryptfs_nl_sock;
  * upon sending the message; non-zero upon error.
  */
 int ecryptfs_send_netlink(char *data, int data_len,
-			  struct ecryptfs_msg_ctx *msg_ctx, u16 msg_type,
-			  u16 msg_flags, pid_t daemon_pid)
+			  struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type,
+			  u16 msg_flags, struct pid *daemon_pid)
 {
 	struct sk_buff *skb;
 	struct nlmsghdr *nlh;
@@ -60,7 +60,7 @@ int ecryptfs_send_netlink(char *data, int data_len,
 		ecryptfs_printk(KERN_ERR, "Failed to allocate socket buffer\n");
 		goto out;
 	}
-	nlh = NLMSG_PUT(skb, daemon_pid, msg_ctx ? msg_ctx->counter : 0,
+	nlh = NLMSG_PUT(skb, pid_nr(daemon_pid), msg_ctx ? msg_ctx->counter : 0,
 			msg_type, payload_len);
 	nlh->nlmsg_flags = msg_flags;
 	if (msg_ctx && payload_len) {
@@ -69,7 +69,7 @@ int ecryptfs_send_netlink(char *data, int data_len,
 		msg->data_len = data_len;
 		memcpy(msg->data, data, data_len);
 	}
-	rc = netlink_unicast(ecryptfs_nl_sock, skb, daemon_pid, 0);
+	rc = netlink_unicast(ecryptfs_nl_sock, skb, pid_nr(daemon_pid), 0);
 	if (rc < 0) {
 		ecryptfs_printk(KERN_ERR, "Failed to send eCryptfs netlink "
 				"message; rc = [%d]\n", rc);
@@ -99,6 +99,7 @@ static int ecryptfs_process_nl_response(struct sk_buff *skb)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(skb);
 	struct ecryptfs_message *msg = NLMSG_DATA(nlh);
+	struct pid *pid;
 	int rc;
 
 	if (skb->len - NLMSG_HDRLEN - sizeof(*msg) != msg->data_len) {
@@ -107,8 +108,10 @@ static int ecryptfs_process_nl_response(struct sk_buff *skb)
 				"incorrectly specified data length\n");
 		goto out;
 	}
-	rc = ecryptfs_process_response(msg, NETLINK_CREDS(skb)->uid,
-				       NETLINK_CREDS(skb)->pid, nlh->nlmsg_seq);
+	pid = find_get_pid(NETLINK_CREDS(skb)->pid);
+	rc = ecryptfs_process_response(msg, NETLINK_CREDS(skb)->uid, NULL,
+				       pid, nlh->nlmsg_seq);
+	put_pid(pid);
 	if (rc)
 		printk(KERN_ERR
 		       "Error processing response message; rc = [%d]\n", rc);
@@ -126,11 +129,13 @@ static int ecryptfs_process_nl_response(struct sk_buff *skb)
  */
 static int ecryptfs_process_nl_helo(struct sk_buff *skb)
 {
+	struct pid *pid;
 	int rc;
 
+	pid = find_get_pid(NETLINK_CREDS(skb)->pid);
 	rc = ecryptfs_process_helo(ECRYPTFS_TRANSPORT_NETLINK,
-				   NETLINK_CREDS(skb)->uid,
-				   NETLINK_CREDS(skb)->pid);
+				   NETLINK_CREDS(skb)->uid, NULL, pid);
+	put_pid(pid);
 	if (rc)
 		printk(KERN_WARNING "Error processing HELO; rc = [%d]\n", rc);
 	return rc;
@@ -147,10 +152,12 @@ static int ecryptfs_process_nl_helo(struct sk_buff *skb)
  */
 static int ecryptfs_process_nl_quit(struct sk_buff *skb)
 {
+	struct pid *pid;
 	int rc;
 
-	rc = ecryptfs_process_quit(NETLINK_CREDS(skb)->uid,
-				   NETLINK_CREDS(skb)->pid);
+	pid = find_get_pid(NETLINK_CREDS(skb)->pid);
+	rc = ecryptfs_process_quit(NETLINK_CREDS(skb)->uid, NULL, pid);
+	put_pid(pid);
 	if (rc)
 		printk(KERN_WARNING
 		       "Error processing QUIT message; rc = [%d]\n", rc);
@@ -176,20 +183,20 @@ static void ecryptfs_receive_nl_message(struct sk_buff *skb)
 		goto free;
 	}
 	switch (nlh->nlmsg_type) {
-		case ECRYPTFS_NLMSG_RESPONSE:
+		case ECRYPTFS_MSG_RESPONSE:
 			if (ecryptfs_process_nl_response(skb)) {
 				ecryptfs_printk(KERN_WARNING, "Failed to "
 						"deliver netlink response to "
 						"requesting operation\n");
 			}
 			break;
-		case ECRYPTFS_NLMSG_HELO:
+		case ECRYPTFS_MSG_HELO:
 			if (ecryptfs_process_nl_helo(skb)) {
 				ecryptfs_printk(KERN_WARNING, "Failed to "
 						"fulfill HELO request\n");
 			}
 			break;
-		case ECRYPTFS_NLMSG_QUIT:
+		case ECRYPTFS_MSG_QUIT:
 			if (ecryptfs_process_nl_quit(skb)) {
 				ecryptfs_printk(KERN_WARNING, "Failed to "
 						"fulfill QUIT request\n");
diff --git a/trunk/fs/ecryptfs/read_write.c b/trunk/fs/ecryptfs/read_write.c
index 0c4928623bbc..ebf55150be56 100644
--- a/trunk/fs/ecryptfs/read_write.c
+++ b/trunk/fs/ecryptfs/read_write.c
@@ -55,7 +55,7 @@ int ecryptfs_write_lower(struct inode *ecryptfs_inode, char *data,
 	set_fs(fs_save);
 	if (octets_written < 0) {
 		printk(KERN_ERR "%s: octets_written = [%td]; "
-		       "expected [%td]\n", __FUNCTION__, octets_written, size);
+		       "expected [%td]\n", __func__, octets_written, size);
 		rc = -EINVAL;
 	}
 	mutex_unlock(&inode_info->lower_file_mutex);
@@ -153,7 +153,7 @@ int ecryptfs_write(struct file *ecryptfs_file, char *data, loff_t offset,
 			rc = PTR_ERR(ecryptfs_page);
 			printk(KERN_ERR "%s: Error getting page at "
 			       "index [%ld] from eCryptfs inode "
-			       "mapping; rc = [%d]\n", __FUNCTION__,
+			       "mapping; rc = [%d]\n", __func__,
 			       ecryptfs_page_idx, rc);
 			goto out;
 		}
@@ -165,7 +165,7 @@ int ecryptfs_write(struct file *ecryptfs_file, char *data, loff_t offset,
 			if (rc) {
 				printk(KERN_ERR "%s: Error decrypting "
 				       "page; rc = [%d]\n",
-				       __FUNCTION__, rc);
+				       __func__, rc);
 				ClearPageUptodate(ecryptfs_page);
 				page_cache_release(ecryptfs_page);
 				goto out;
@@ -202,7 +202,7 @@ int ecryptfs_write(struct file *ecryptfs_file, char *data, loff_t offset,
 		page_cache_release(ecryptfs_page);
 		if (rc) {
 			printk(KERN_ERR "%s: Error encrypting "
-			       "page; rc = [%d]\n", __FUNCTION__, rc);
+			       "page; rc = [%d]\n", __func__, rc);
 			goto out;
 		}
 		pos += num_bytes;
@@ -254,7 +254,7 @@ int ecryptfs_read_lower(char *data, loff_t offset, size_t size,
 	set_fs(fs_save);
 	if (octets_read < 0) {
 		printk(KERN_ERR "%s: octets_read = [%td]; "
-		       "expected [%td]\n", __FUNCTION__, octets_read, size);
+		       "expected [%td]\n", __func__, octets_read, size);
 		rc = -EINVAL;
 	}
 	mutex_unlock(&inode_info->lower_file_mutex);
@@ -327,7 +327,7 @@ int ecryptfs_read(char *data, loff_t offset, size_t size,
 		printk(KERN_ERR "%s: Attempt to read data past the end of the "
 			"file; offset = [%lld]; size = [%td]; "
 		       "ecryptfs_file_size = [%lld]\n",
-		       __FUNCTION__, offset, size, ecryptfs_file_size);
+		       __func__, offset, size, ecryptfs_file_size);
 		goto out;
 	}
 	pos = offset;
@@ -345,14 +345,14 @@ int ecryptfs_read(char *data, loff_t offset, size_t size,
 			rc = PTR_ERR(ecryptfs_page);
 			printk(KERN_ERR "%s: Error getting page at "
 			       "index [%ld] from eCryptfs inode "
-			       "mapping; rc = [%d]\n", __FUNCTION__,
+			       "mapping; rc = [%d]\n", __func__,
 			       ecryptfs_page_idx, rc);
 			goto out;
 		}
 		rc = ecryptfs_decrypt_page(ecryptfs_page);
 		if (rc) {
 			printk(KERN_ERR "%s: Error decrypting "
-			       "page; rc = [%d]\n", __FUNCTION__, rc);
+			       "page; rc = [%d]\n", __func__, rc);
 			ClearPageUptodate(ecryptfs_page);
 			page_cache_release(ecryptfs_page);
 			goto out;
diff --git a/trunk/fs/eventpoll.c b/trunk/fs/eventpoll.c
index a415f42d32cf..0d237182d721 100644
--- a/trunk/fs/eventpoll.c
+++ b/trunk/fs/eventpoll.c
@@ -257,25 +257,6 @@ static inline int ep_cmp_ffd(struct epoll_filefd *p1,
 	        (p1->file < p2->file ? -1 : p1->fd - p2->fd));
 }
 
-/* Special initialization for the RB tree node to detect linkage */
-static inline void ep_rb_initnode(struct rb_node *n)
-{
-	rb_set_parent(n, n);
-}
-
-/* Removes a node from the RB tree and marks it for a fast is-linked check */
-static inline void ep_rb_erase(struct rb_node *n, struct rb_root *r)
-{
-	rb_erase(n, r);
-	rb_set_parent(n, n);
-}
-
-/* Fast check to verify that the item is linked to the main RB tree */
-static inline int ep_rb_linked(struct rb_node *n)
-{
-	return rb_parent(n) != n;
-}
-
 /* Tells us if the item is currently linked */
 static inline int ep_is_linked(struct list_head *p)
 {
@@ -283,13 +264,13 @@ static inline int ep_is_linked(struct list_head *p)
 }
 
 /* Get the "struct epitem" from a wait queue pointer */
-static inline struct epitem * ep_item_from_wait(wait_queue_t *p)
+static inline struct epitem *ep_item_from_wait(wait_queue_t *p)
 {
 	return container_of(p, struct eppoll_entry, wait)->base;
 }
 
 /* Get the "struct epitem" from an epoll queue wrapper */
-static inline struct epitem * ep_item_from_epqueue(poll_table *p)
+static inline struct epitem *ep_item_from_epqueue(poll_table *p)
 {
 	return container_of(p, struct ep_pqueue, pt)->epi;
 }
@@ -411,8 +392,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi)
 		list_del_init(&epi->fllink);
 	spin_unlock(&file->f_ep_lock);
 
-	if (ep_rb_linked(&epi->rbn))
-		ep_rb_erase(&epi->rbn, &ep->rbr);
+	rb_erase(&epi->rbn, &ep->rbr);
 
 	spin_lock_irqsave(&ep->lock, flags);
 	if (ep_is_linked(&epi->rdllink))
@@ -728,7 +708,6 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 		goto error_return;
 
 	/* Item initialization follow here ... */
-	ep_rb_initnode(&epi->rbn);
 	INIT_LIST_HEAD(&epi->rdllink);
 	INIT_LIST_HEAD(&epi->fllink);
 	INIT_LIST_HEAD(&epi->pwqlist);
diff --git a/trunk/fs/exec.c b/trunk/fs/exec.c
index b152029f18f6..a13883903ee9 100644
--- a/trunk/fs/exec.c
+++ b/trunk/fs/exec.c
@@ -735,6 +735,7 @@ static int exec_mmap(struct mm_struct *mm)
 	tsk->active_mm = mm;
 	activate_mm(active_mm, mm);
 	task_unlock(tsk);
+	mm_update_next_owner(mm);
 	arch_pick_mmap_layout(mm);
 	if (old_mm) {
 		up_read(&old_mm->mmap_sem);
@@ -963,6 +964,8 @@ int flush_old_exec(struct linux_binprm * bprm)
 	if (retval)
 		goto out;
 
+	set_mm_exe_file(bprm->mm, bprm->file);
+
 	/*
 	 * Release all of the old mmap stuff
 	 */
@@ -1268,7 +1271,6 @@ int do_execve(char * filename,
 {
 	struct linux_binprm *bprm;
 	struct file *file;
-	unsigned long env_p;
 	struct files_struct *displaced;
 	int retval;
 
@@ -1321,11 +1323,9 @@ int do_execve(char * filename,
 	if (retval < 0)
 		goto out;
 
-	env_p = bprm->p;
 	retval = copy_strings(bprm->argc, argv, bprm);
 	if (retval < 0)
 		goto out;
-	bprm->argv_len = env_p - bprm->p;
 
 	retval = search_binary_handler(bprm,regs);
 	if (retval >= 0) {
diff --git a/trunk/fs/ext2/balloc.c b/trunk/fs/ext2/balloc.c
index e7b2bafa1dd9..10bb02c3f25c 100644
--- a/trunk/fs/ext2/balloc.c
+++ b/trunk/fs/ext2/balloc.c
@@ -106,7 +106,7 @@ static int ext2_valid_block_bitmap(struct super_block *sb,
 		return 1;
 
 err_out:
-	ext2_error(sb, __FUNCTION__,
+	ext2_error(sb, __func__,
 			"Invalid block bitmap - "
 			"block_group = %d, block = %lu",
 			block_group, bitmap_blk);
@@ -132,7 +132,7 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group)
 	bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
 	bh = sb_getblk(sb, bitmap_blk);
 	if (unlikely(!bh)) {
-		ext2_error(sb, __FUNCTION__,
+		ext2_error(sb, __func__,
 			    "Cannot read block bitmap - "
 			    "block_group = %d, block_bitmap = %u",
 			    block_group, le32_to_cpu(desc->bg_block_bitmap));
@@ -143,17 +143,18 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group)
 
 	if (bh_submit_read(bh) < 0) {
 		brelse(bh);
-		ext2_error(sb, __FUNCTION__,
+		ext2_error(sb, __func__,
 			    "Cannot read block bitmap - "
 			    "block_group = %d, block_bitmap = %u",
 			    block_group, le32_to_cpu(desc->bg_block_bitmap));
 		return NULL;
 	}
-	if (!ext2_valid_block_bitmap(sb, desc, block_group, bh)) {
-		brelse(bh);
-		return NULL;
-	}
 
+	ext2_valid_block_bitmap(sb, desc, block_group, bh);
+	/*
+	 * file system mounted not to panic on error, continue with corrupt
+	 * bitmap
+	 */
 	return bh;
 }
 
@@ -245,11 +246,10 @@ static void __rsv_window_dump(struct rb_root *root, int verbose,
 		prev = rsv;
 	}
 	printk("Window map complete.\n");
-	if (bad)
-		BUG();
+	BUG_ON(bad);
 }
 #define rsv_window_dump(root, verbose) \
-	__rsv_window_dump((root), (verbose), __FUNCTION__)
+	__rsv_window_dump((root), (verbose), __func__)
 #else
 #define rsv_window_dump(root, verbose) do {} while (0)
 #endif
@@ -548,7 +548,7 @@ void ext2_free_blocks (struct inode * inode, unsigned long block,
 	for (i = 0, group_freed = 0; i < count; i++) {
 		if (!ext2_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
 						bit + i, bitmap_bh->b_data)) {
-			ext2_error(sb, __FUNCTION__,
+			ext2_error(sb, __func__,
 				"bit already cleared for block %lu", block + i);
 		} else {
 			group_freed++;
@@ -1381,7 +1381,12 @@ ext2_fsblk_t ext2_new_blocks(struct inode *inode, ext2_fsblk_t goal,
 			    "Allocating block in system zone - "
 			    "blocks from "E2FSBLK", length %lu",
 			    ret_block, num);
-		goto out;
+		/*
+		 * ext2_try_to_allocate marked the blocks we allocated as in
+		 * use.  So we may want to selectively mark some of the blocks
+		 * as free
+		 */
+		goto retry_alloc;
 	}
 
 	performed_allocation = 1;
diff --git a/trunk/fs/ext2/dir.c b/trunk/fs/ext2/dir.c
index 8dededd80fe2..a78c6b4af060 100644
--- a/trunk/fs/ext2/dir.c
+++ b/trunk/fs/ext2/dir.c
@@ -41,8 +41,8 @@ static inline __le16 ext2_rec_len_to_disk(unsigned len)
 {
 	if (len == (1 << 16))
 		return cpu_to_le16(EXT2_MAX_REC_LEN);
-	else if (len > (1 << 16))
-		BUG();
+	else
+		BUG_ON(len > (1 << 16));
 	return cpu_to_le16(len);
 }
 
@@ -295,11 +295,11 @@ ext2_readdir (struct file * filp, void * dirent, filldir_t filldir)
 		struct page *page = ext2_get_page(inode, n);
 
 		if (IS_ERR(page)) {
-			ext2_error(sb, __FUNCTION__,
+			ext2_error(sb, __func__,
 				   "bad page in #%lu",
 				   inode->i_ino);
 			filp->f_pos += PAGE_CACHE_SIZE - offset;
-			return -EIO;
+			return PTR_ERR(page);
 		}
 		kaddr = page_address(page);
 		if (unlikely(need_revalidate)) {
@@ -314,7 +314,7 @@ ext2_readdir (struct file * filp, void * dirent, filldir_t filldir)
 		limit = kaddr + ext2_last_byte(inode, n) - EXT2_DIR_REC_LEN(1);
 		for ( ;(char*)de <= limit; de = ext2_next_entry(de)) {
 			if (de->rec_len == 0) {
-				ext2_error(sb, __FUNCTION__,
+				ext2_error(sb, __func__,
 					"zero-length directory entry");
 				ext2_put_page(page);
 				return -EIO;
@@ -381,7 +381,7 @@ struct ext2_dir_entry_2 * ext2_find_entry (struct inode * dir,
 			kaddr += ext2_last_byte(dir, n) - reclen;
 			while ((char *) de <= kaddr) {
 				if (de->rec_len == 0) {
-					ext2_error(dir->i_sb, __FUNCTION__,
+					ext2_error(dir->i_sb, __func__,
 						"zero-length directory entry");
 					ext2_put_page(page);
 					goto out;
@@ -396,7 +396,7 @@ struct ext2_dir_entry_2 * ext2_find_entry (struct inode * dir,
 			n = 0;
 		/* next page is past the blocks we've got */
 		if (unlikely(n > (dir->i_blocks >> (PAGE_CACHE_SHIFT - 9)))) {
-			ext2_error(dir->i_sb, __FUNCTION__,
+			ext2_error(dir->i_sb, __func__,
 				"dir %lu size %lld exceeds block count %llu",
 				dir->i_ino, dir->i_size,
 				(unsigned long long)dir->i_blocks);
@@ -506,7 +506,7 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
 				goto got_it;
 			}
 			if (de->rec_len == 0) {
-				ext2_error(dir->i_sb, __FUNCTION__,
+				ext2_error(dir->i_sb, __func__,
 					"zero-length directory entry");
 				err = -EIO;
 				goto out_unlock;
@@ -578,7 +578,7 @@ int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page )
 
 	while ((char*)de < (char*)dir) {
 		if (de->rec_len == 0) {
-			ext2_error(inode->i_sb, __FUNCTION__,
+			ext2_error(inode->i_sb, __func__,
 				"zero-length directory entry");
 			err = -EIO;
 			goto out;
@@ -670,7 +670,7 @@ int ext2_empty_dir (struct inode * inode)
 
 		while ((char *)de <= kaddr) {
 			if (de->rec_len == 0) {
-				ext2_error(inode->i_sb, __FUNCTION__,
+				ext2_error(inode->i_sb, __func__,
 					"zero-length directory entry");
 				printk("kaddr=%p, de=%p\n", kaddr, de);
 				goto not_empty;
diff --git a/trunk/fs/ext2/ialloc.c b/trunk/fs/ext2/ialloc.c
index 08f647d8188d..f59741346760 100644
--- a/trunk/fs/ext2/ialloc.c
+++ b/trunk/fs/ext2/ialloc.c
@@ -75,11 +75,9 @@ static void ext2_release_inode(struct super_block *sb, int group, int dir)
 	}
 
 	spin_lock(sb_bgl_lock(EXT2_SB(sb), group));
-	desc->bg_free_inodes_count =
-		cpu_to_le16(le16_to_cpu(desc->bg_free_inodes_count) + 1);
+	le16_add_cpu(&desc->bg_free_inodes_count, 1);
 	if (dir)
-		desc->bg_used_dirs_count =
-			cpu_to_le16(le16_to_cpu(desc->bg_used_dirs_count) - 1);
+		le16_add_cpu(&desc->bg_used_dirs_count, -1);
 	spin_unlock(sb_bgl_lock(EXT2_SB(sb), group));
 	if (dir)
 		percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter);
@@ -539,13 +537,11 @@ struct inode *ext2_new_inode(struct inode *dir, int mode)
 		percpu_counter_inc(&sbi->s_dirs_counter);
 
 	spin_lock(sb_bgl_lock(sbi, group));
-	gdp->bg_free_inodes_count =
-                cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1);
+	le16_add_cpu(&gdp->bg_free_inodes_count, -1);
 	if (S_ISDIR(mode)) {
 		if (sbi->s_debts[group] < 255)
 			sbi->s_debts[group]++;
-		gdp->bg_used_dirs_count =
-			cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
+		le16_add_cpu(&gdp->bg_used_dirs_count, 1);
 	} else {
 		if (sbi->s_debts[group])
 			sbi->s_debts[group]--;
diff --git a/trunk/fs/ext2/inode.c b/trunk/fs/ext2/inode.c
index b8a2990bab83..384fc0d1dd74 100644
--- a/trunk/fs/ext2/inode.c
+++ b/trunk/fs/ext2/inode.c
@@ -254,13 +254,13 @@ static Indirect *ext2_get_branch(struct inode *inode,
  *	Caller must make sure that @ind is valid and will stay that way.
  */
 
-static unsigned long ext2_find_near(struct inode *inode, Indirect *ind)
+static ext2_fsblk_t ext2_find_near(struct inode *inode, Indirect *ind)
 {
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	__le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
 	__le32 *p;
-	unsigned long bg_start;
-	unsigned long colour;
+	ext2_fsblk_t bg_start;
+	ext2_fsblk_t colour;
 
 	/* Try to find previous block */
 	for (p = ind->p - 1; p >= start; p--)
@@ -275,8 +275,7 @@ static unsigned long ext2_find_near(struct inode *inode, Indirect *ind)
 	 * It is going to be refered from inode itself? OK, just put it into
 	 * the same cylinder group then.
 	 */
-	bg_start = (ei->i_block_group * EXT2_BLOCKS_PER_GROUP(inode->i_sb)) +
-		le32_to_cpu(EXT2_SB(inode->i_sb)->s_es->s_first_data_block);
+	bg_start = ext2_group_first_block_no(inode->i_sb, ei->i_block_group);
 	colour = (current->pid % 16) *
 			(EXT2_BLOCKS_PER_GROUP(inode->i_sb) / 16);
 	return bg_start + colour;
@@ -291,8 +290,8 @@ static unsigned long ext2_find_near(struct inode *inode, Indirect *ind)
  *	Returns preferred place for a block (the goal).
  */
 
-static inline int ext2_find_goal(struct inode *inode, long block,
-				 Indirect *partial)
+static inline ext2_fsblk_t ext2_find_goal(struct inode *inode, long block,
+					  Indirect *partial)
 {
 	struct ext2_block_alloc_info *block_i;
 
@@ -796,7 +795,7 @@ const struct address_space_operations ext2_aops = {
 
 const struct address_space_operations ext2_aops_xip = {
 	.bmap			= ext2_bmap,
-	.get_xip_page		= ext2_get_xip_page,
+	.get_xip_mem		= ext2_get_xip_mem,
 };
 
 const struct address_space_operations ext2_nobh_aops = {
diff --git a/trunk/fs/ext2/super.c b/trunk/fs/ext2/super.c
index 088b011bb97e..ef50cbc792db 100644
--- a/trunk/fs/ext2/super.c
+++ b/trunk/fs/ext2/super.c
@@ -51,8 +51,7 @@ void ext2_error (struct super_block * sb, const char * function,
 
 	if (!(sb->s_flags & MS_RDONLY)) {
 		sbi->s_mount_state |= EXT2_ERROR_FS;
-		es->s_state =
-			cpu_to_le16(le16_to_cpu(es->s_state) | EXT2_ERROR_FS);
+		es->s_state |= cpu_to_le16(EXT2_ERROR_FS);
 		ext2_sync_super(sb, es);
 	}
 
@@ -90,7 +89,7 @@ void ext2_update_dynamic_rev(struct super_block *sb)
 	if (le32_to_cpu(es->s_rev_level) > EXT2_GOOD_OLD_REV)
 		return;
 
-	ext2_warning(sb, __FUNCTION__,
+	ext2_warning(sb, __func__,
 		     "updating to rev %d because of new feature flag, "
 		     "running e2fsck is recommended",
 		     EXT2_DYNAMIC_REV);
@@ -604,7 +603,7 @@ static int ext2_setup_super (struct super_block * sb,
 			"running e2fsck is recommended\n");
 	if (!le16_to_cpu(es->s_max_mnt_count))
 		es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT);
-	es->s_mnt_count=cpu_to_le16(le16_to_cpu(es->s_mnt_count) + 1);
+	le16_add_cpu(&es->s_mnt_count, 1);
 	ext2_write_super(sb);
 	if (test_opt (sb, DEBUG))
 		printk ("[EXT II FS %s, %s, bs=%lu, fs=%lu, gc=%lu, "
@@ -622,13 +621,13 @@ static int ext2_check_descriptors(struct super_block *sb)
 {
 	int i;
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
-	unsigned long first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
-	unsigned long last_block;
 
 	ext2_debug ("Checking group descriptors");
 
 	for (i = 0; i < sbi->s_groups_count; i++) {
 		struct ext2_group_desc *gdp = ext2_get_group_desc(sb, i, NULL);
+		ext2_fsblk_t first_block = ext2_group_first_block_no(sb, i);
+		ext2_fsblk_t last_block;
 
 		if (i == sbi->s_groups_count - 1)
 			last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
@@ -664,7 +663,6 @@ static int ext2_check_descriptors(struct super_block *sb)
 				    i, (unsigned long) le32_to_cpu(gdp->bg_inode_table));
 			return 0;
 		}
-		first_block += EXT2_BLOCKS_PER_GROUP(sb);
 	}
 	return 1;
 }
@@ -721,10 +719,9 @@ static unsigned long descriptor_loc(struct super_block *sb,
 				    int nr)
 {
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
-	unsigned long bg, first_data_block, first_meta_bg;
+	unsigned long bg, first_meta_bg;
 	int has_super = 0;
 	
-	first_data_block = le32_to_cpu(sbi->s_es->s_first_data_block);
 	first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);
 
 	if (!EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_META_BG) ||
@@ -733,7 +730,8 @@ static unsigned long descriptor_loc(struct super_block *sb,
 	bg = sbi->s_desc_per_block * nr;
 	if (ext2_bg_has_super(sb, bg))
 		has_super = 1;
-	return (first_data_block + has_super + (bg * sbi->s_blocks_per_group));
+
+	return ext2_group_first_block_no(sb, bg) + has_super;
 }
 
 static int ext2_fill_super(struct super_block *sb, void *data, int silent)
@@ -1062,7 +1060,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount3;
 	}
 	if (EXT2_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL))
-		ext2_warning(sb, __FUNCTION__,
+		ext2_warning(sb, __func__,
 			"mounting ext3 filesystem as ext2");
 	ext2_setup_super (sb, es, sb->s_flags & MS_RDONLY);
 	return 0;
@@ -1126,10 +1124,9 @@ void ext2_write_super (struct super_block * sb)
 	if (!(sb->s_flags & MS_RDONLY)) {
 		es = EXT2_SB(sb)->s_es;
 
-		if (le16_to_cpu(es->s_state) & EXT2_VALID_FS) {
+		if (es->s_state & cpu_to_le16(EXT2_VALID_FS)) {
 			ext2_debug ("setting valid to 0\n");
-			es->s_state = cpu_to_le16(le16_to_cpu(es->s_state) &
-						  ~EXT2_VALID_FS);
+			es->s_state &= cpu_to_le16(~EXT2_VALID_FS);
 			es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb));
 			es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb));
 			es->s_mtime = cpu_to_le32(get_seconds());
@@ -1180,7 +1177,7 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 	if (((sbi->s_mount_opt & EXT2_MOUNT_XIP) !=
 	    (old_mount_opt & EXT2_MOUNT_XIP)) &&
 	    invalidate_inodes(sb))
-		ext2_warning(sb, __FUNCTION__, "busy inodes while remounting "\
+		ext2_warning(sb, __func__, "busy inodes while remounting "\
 			     "xip remain in cache (no functional problem)");
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
 		return 0;
diff --git a/trunk/fs/ext2/xattr.c b/trunk/fs/ext2/xattr.c
index a99d46f3b26e..987a5261cc2e 100644
--- a/trunk/fs/ext2/xattr.c
+++ b/trunk/fs/ext2/xattr.c
@@ -646,8 +646,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 					unlock_buffer(new_bh);
 					goto cleanup;
 				}
-				HDR(new_bh)->h_refcount = cpu_to_le32(1 +
-					le32_to_cpu(HDR(new_bh)->h_refcount));
+				le32_add_cpu(&HDR(new_bh)->h_refcount, 1);
 				ea_bdebug(new_bh, "refcount now=%d",
 					le32_to_cpu(HDR(new_bh)->h_refcount));
 			}
@@ -660,10 +659,8 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			ext2_xattr_cache_insert(new_bh);
 		} else {
 			/* We need to allocate a new block */
-			int goal = le32_to_cpu(EXT2_SB(sb)->s_es->
-						           s_first_data_block) +
-				   EXT2_I(inode)->i_block_group *
-				   EXT2_BLOCKS_PER_GROUP(sb);
+			ext2_fsblk_t goal = ext2_group_first_block_no(sb,
+						EXT2_I(inode)->i_block_group);
 			int block = ext2_new_block(inode, goal, &error);
 			if (error)
 				goto cleanup;
@@ -731,8 +728,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			bforget(old_bh);
 		} else {
 			/* Decrement the refcount only. */
-			HDR(old_bh)->h_refcount = cpu_to_le32(
-				le32_to_cpu(HDR(old_bh)->h_refcount) - 1);
+			le32_add_cpu(&HDR(old_bh)->h_refcount, -1);
 			if (ce)
 				mb_cache_entry_release(ce);
 			DQUOT_FREE_BLOCK(inode, 1);
@@ -789,8 +785,7 @@ ext2_xattr_delete_inode(struct inode *inode)
 		bforget(bh);
 		unlock_buffer(bh);
 	} else {
-		HDR(bh)->h_refcount = cpu_to_le32(
-			le32_to_cpu(HDR(bh)->h_refcount) - 1);
+		le32_add_cpu(&HDR(bh)->h_refcount, -1);
 		if (ce)
 			mb_cache_entry_release(ce);
 		ea_bdebug(bh, "refcount now=%d",
diff --git a/trunk/fs/ext2/xip.c b/trunk/fs/ext2/xip.c
index ca7f00312388..4fb94c20041b 100644
--- a/trunk/fs/ext2/xip.c
+++ b/trunk/fs/ext2/xip.c
@@ -15,24 +15,28 @@
 #include "xip.h"
 
 static inline int
-__inode_direct_access(struct inode *inode, sector_t sector,
-		      unsigned long *data)
+__inode_direct_access(struct inode *inode, sector_t block,
+		      void **kaddr, unsigned long *pfn)
 {
-	BUG_ON(!inode->i_sb->s_bdev->bd_disk->fops->direct_access);
-	return inode->i_sb->s_bdev->bd_disk->fops
-		->direct_access(inode->i_sb->s_bdev,sector,data);
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	struct block_device_operations *ops = bdev->bd_disk->fops;
+	sector_t sector;
+
+	sector = block * (PAGE_SIZE / 512); /* ext2 block to bdev sector */
+
+	BUG_ON(!ops->direct_access);
+	return ops->direct_access(bdev, sector, kaddr, pfn);
 }
 
 static inline int
-__ext2_get_sector(struct inode *inode, sector_t offset, int create,
+__ext2_get_block(struct inode *inode, pgoff_t pgoff, int create,
 		   sector_t *result)
 {
 	struct buffer_head tmp;
 	int rc;
 
 	memset(&tmp, 0, sizeof(struct buffer_head));
-	rc = ext2_get_block(inode, offset/ (PAGE_SIZE/512), &tmp,
-			    create);
+	rc = ext2_get_block(inode, pgoff, &tmp, create);
 	*result = tmp.b_blocknr;
 
 	/* did we get a sparse block (hole in the file)? */
@@ -45,15 +49,15 @@ __ext2_get_sector(struct inode *inode, sector_t offset, int create,
 }
 
 int
-ext2_clear_xip_target(struct inode *inode, int block)
+ext2_clear_xip_target(struct inode *inode, sector_t block)
 {
-	sector_t sector = block * (PAGE_SIZE/512);
-	unsigned long data;
+	void *kaddr;
+	unsigned long pfn;
 	int rc;
 
-	rc = __inode_direct_access(inode, sector, &data);
+	rc = __inode_direct_access(inode, block, &kaddr, &pfn);
 	if (!rc)
-		clear_page((void*)data);
+		clear_page(kaddr);
 	return rc;
 }
 
@@ -64,30 +68,23 @@ void ext2_xip_verify_sb(struct super_block *sb)
 	if ((sbi->s_mount_opt & EXT2_MOUNT_XIP) &&
 	    !sb->s_bdev->bd_disk->fops->direct_access) {
 		sbi->s_mount_opt &= (~EXT2_MOUNT_XIP);
-		ext2_warning(sb, __FUNCTION__,
+		ext2_warning(sb, __func__,
 			     "ignoring xip option - not supported by bdev");
 	}
 }
 
-struct page *
-ext2_get_xip_page(struct address_space *mapping, sector_t offset,
-		   int create)
+int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
+				void **kmem, unsigned long *pfn)
 {
 	int rc;
-	unsigned long data;
-	sector_t sector;
+	sector_t block;
 
 	/* first, retrieve the sector number */
-	rc = __ext2_get_sector(mapping->host, offset, create, &sector);
+	rc = __ext2_get_block(mapping->host, pgoff, create, &block);
 	if (rc)
-		goto error;
+		return rc;
 
 	/* retrieve address of the target data */
-	rc = __inode_direct_access
-		(mapping->host, sector * (PAGE_SIZE/512), &data);
-	if (!rc)
-		return virt_to_page(data);
-
- error:
-	return ERR_PTR(rc);
+	rc = __inode_direct_access(mapping->host, block, kmem, pfn);
+	return rc;
 }
diff --git a/trunk/fs/ext2/xip.h b/trunk/fs/ext2/xip.h
index aa85331d6c56..18b34d2f31b3 100644
--- a/trunk/fs/ext2/xip.h
+++ b/trunk/fs/ext2/xip.h
@@ -7,19 +7,20 @@
 
 #ifdef CONFIG_EXT2_FS_XIP
 extern void ext2_xip_verify_sb (struct super_block *);
-extern int ext2_clear_xip_target (struct inode *, int);
+extern int ext2_clear_xip_target (struct inode *, sector_t);
 
 static inline int ext2_use_xip (struct super_block *sb)
 {
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
 	return (sbi->s_mount_opt & EXT2_MOUNT_XIP);
 }
-struct page* ext2_get_xip_page (struct address_space *, sector_t, int);
-#define mapping_is_xip(map) unlikely(map->a_ops->get_xip_page)
+int ext2_get_xip_mem(struct address_space *, pgoff_t, int,
+				void **, unsigned long *);
+#define mapping_is_xip(map) unlikely(map->a_ops->get_xip_mem)
 #else
 #define mapping_is_xip(map)			0
 #define ext2_xip_verify_sb(sb)			do { } while (0)
 #define ext2_use_xip(sb)			0
 #define ext2_clear_xip_target(inode, chain)	0
-#define ext2_get_xip_page			NULL
+#define ext2_get_xip_mem			NULL
 #endif
diff --git a/trunk/fs/ext3/balloc.c b/trunk/fs/ext3/balloc.c
index da0cb2c0e437..92fd0338a6eb 100644
--- a/trunk/fs/ext3/balloc.c
+++ b/trunk/fs/ext3/balloc.c
@@ -117,7 +117,7 @@ static int ext3_valid_block_bitmap(struct super_block *sb,
 		return 1;
 
 err_out:
-	ext3_error(sb, __FUNCTION__,
+	ext3_error(sb, __func__,
 			"Invalid block bitmap - "
 			"block_group = %d, block = %lu",
 			block_group, bitmap_blk);
@@ -147,7 +147,7 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group)
 	bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
 	bh = sb_getblk(sb, bitmap_blk);
 	if (unlikely(!bh)) {
-		ext3_error(sb, __FUNCTION__,
+		ext3_error(sb, __func__,
 			    "Cannot read block bitmap - "
 			    "block_group = %d, block_bitmap = %u",
 			    block_group, le32_to_cpu(desc->bg_block_bitmap));
@@ -158,16 +158,17 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group)
 
 	if (bh_submit_read(bh) < 0) {
 		brelse(bh);
-		ext3_error(sb, __FUNCTION__,
+		ext3_error(sb, __func__,
 			    "Cannot read block bitmap - "
 			    "block_group = %d, block_bitmap = %u",
 			    block_group, le32_to_cpu(desc->bg_block_bitmap));
 		return NULL;
 	}
-	if (!ext3_valid_block_bitmap(sb, desc, block_group, bh)) {
-		brelse(bh);
-		return NULL;
-	}
+	ext3_valid_block_bitmap(sb, desc, block_group, bh);
+	/*
+	 * file system mounted not to panic on error, continue with corrupt
+	 * bitmap
+	 */
 	return bh;
 }
 /*
@@ -232,11 +233,10 @@ static void __rsv_window_dump(struct rb_root *root, int verbose,
 		prev = rsv;
 	}
 	printk("Window map complete.\n");
-	if (bad)
-		BUG();
+	BUG_ON(bad);
 }
 #define rsv_window_dump(root, verbose) \
-	__rsv_window_dump((root), (verbose), __FUNCTION__)
+	__rsv_window_dump((root), (verbose), __func__)
 #else
 #define rsv_window_dump(root, verbose) do {} while (0)
 #endif
@@ -618,7 +618,7 @@ void ext3_free_blocks_sb(handle_t *handle, struct super_block *sb,
 		if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
 						bit + i, bitmap_bh->b_data)) {
 			jbd_unlock_bh_state(bitmap_bh);
-			ext3_error(sb, __FUNCTION__,
+			ext3_error(sb, __func__,
 				"bit already cleared for block "E3FSBLK,
 				 block + i);
 			jbd_lock_bh_state(bitmap_bh);
@@ -1642,7 +1642,11 @@ ext3_fsblk_t ext3_new_blocks(handle_t *handle, struct inode *inode,
 			    "Allocating block in system zone - "
 			    "blocks from "E3FSBLK", length %lu",
 			     ret_block, num);
-		goto out;
+		/*
+		 * claim_block() marked the blocks we allocated as in use. So we
+		 * may want to selectively mark some of the blocks as free.
+		 */
+		goto retry_alloc;
 	}
 
 	performed_allocation = 1;
@@ -1668,7 +1672,7 @@ ext3_fsblk_t ext3_new_blocks(handle_t *handle, struct inode *inode,
 			if (ext3_test_bit(grp_alloc_blk+i,
 					bh2jh(bitmap_bh)->b_committed_data)) {
 				printk("%s: block was unexpectedly set in "
-					"b_committed_data\n", __FUNCTION__);
+					"b_committed_data\n", __func__);
 			}
 		}
 	}
diff --git a/trunk/fs/ext3/ext3_jbd.c b/trunk/fs/ext3/ext3_jbd.c
index e1f91fd26a93..d401f148d74d 100644
--- a/trunk/fs/ext3/ext3_jbd.c
+++ b/trunk/fs/ext3/ext3_jbd.c
@@ -9,7 +9,7 @@ int __ext3_journal_get_undo_access(const char *where, handle_t *handle,
 {
 	int err = journal_get_undo_access(handle, bh);
 	if (err)
-		ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+		ext3_journal_abort_handle(where, __func__, bh, handle,err);
 	return err;
 }
 
@@ -18,7 +18,7 @@ int __ext3_journal_get_write_access(const char *where, handle_t *handle,
 {
 	int err = journal_get_write_access(handle, bh);
 	if (err)
-		ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+		ext3_journal_abort_handle(where, __func__, bh, handle,err);
 	return err;
 }
 
@@ -27,7 +27,7 @@ int __ext3_journal_forget(const char *where, handle_t *handle,
 {
 	int err = journal_forget(handle, bh);
 	if (err)
-		ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+		ext3_journal_abort_handle(where, __func__, bh, handle,err);
 	return err;
 }
 
@@ -36,7 +36,7 @@ int __ext3_journal_revoke(const char *where, handle_t *handle,
 {
 	int err = journal_revoke(handle, blocknr, bh);
 	if (err)
-		ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+		ext3_journal_abort_handle(where, __func__, bh, handle,err);
 	return err;
 }
 
@@ -45,7 +45,7 @@ int __ext3_journal_get_create_access(const char *where,
 {
 	int err = journal_get_create_access(handle, bh);
 	if (err)
-		ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+		ext3_journal_abort_handle(where, __func__, bh, handle,err);
 	return err;
 }
 
@@ -54,6 +54,6 @@ int __ext3_journal_dirty_metadata(const char *where,
 {
 	int err = journal_dirty_metadata(handle, bh);
 	if (err)
-		ext3_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+		ext3_journal_abort_handle(where, __func__, bh, handle,err);
 	return err;
 }
diff --git a/trunk/fs/ext3/fsync.c b/trunk/fs/ext3/fsync.c
index a588e23841d4..d33634119e17 100644
--- a/trunk/fs/ext3/fsync.c
+++ b/trunk/fs/ext3/fsync.c
@@ -72,6 +72,9 @@ int ext3_sync_file(struct file * file, struct dentry *dentry, int datasync)
 		goto out;
 	}
 
+	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+		goto out;
+
 	/*
 	 * The VFS has written the file data.  If the inode is unaltered
 	 * then we need not start a commit.
diff --git a/trunk/fs/ext3/ialloc.c b/trunk/fs/ext3/ialloc.c
index 96dd5573e49b..77126821b2e9 100644
--- a/trunk/fs/ext3/ialloc.c
+++ b/trunk/fs/ext3/ialloc.c
@@ -644,7 +644,7 @@ struct inode *ext3_orphan_get(struct super_block *sb, unsigned long ino)
 
 	/* Error cases - e2fsck has already cleaned up for us */
 	if (ino > max_ino) {
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "bad orphan ino %lu!  e2fsck was run?", ino);
 		goto error;
 	}
@@ -653,7 +653,7 @@ struct inode *ext3_orphan_get(struct super_block *sb, unsigned long ino)
 	bit = (ino - 1) % EXT3_INODES_PER_GROUP(sb);
 	bitmap_bh = read_inode_bitmap(sb, block_group);
 	if (!bitmap_bh) {
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "inode bitmap error for orphan %lu", ino);
 		goto error;
 	}
@@ -678,7 +678,7 @@ struct inode *ext3_orphan_get(struct super_block *sb, unsigned long ino)
 	err = PTR_ERR(inode);
 	inode = NULL;
 bad_orphan:
-	ext3_warning(sb, __FUNCTION__,
+	ext3_warning(sb, __func__,
 		     "bad orphan inode %lu!  e2fsck was run?", ino);
 	printk(KERN_NOTICE "ext3_test_bit(bit=%d, block=%llu) = %d\n",
 	       bit, (unsigned long long)bitmap_bh->b_blocknr,
diff --git a/trunk/fs/ext3/inode.c b/trunk/fs/ext3/inode.c
index c683609b0e3a..cc47b76091bf 100644
--- a/trunk/fs/ext3/inode.c
+++ b/trunk/fs/ext3/inode.c
@@ -95,7 +95,7 @@ int ext3_forget(handle_t *handle, int is_metadata, struct inode *inode,
 	BUFFER_TRACE(bh, "call ext3_journal_revoke");
 	err = ext3_journal_revoke(handle, blocknr, bh);
 	if (err)
-		ext3_abort(inode->i_sb, __FUNCTION__,
+		ext3_abort(inode->i_sb, __func__,
 			   "error %d when attempting revoke", err);
 	BUFFER_TRACE(bh, "exit");
 	return err;
@@ -1190,7 +1190,7 @@ int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
 {
 	int err = journal_dirty_data(handle, bh);
 	if (err)
-		ext3_journal_abort_handle(__FUNCTION__, __FUNCTION__,
+		ext3_journal_abort_handle(__func__, __func__,
 						bh, handle, err);
 	return err;
 }
@@ -2454,11 +2454,10 @@ void ext3_truncate(struct inode *inode)
 static ext3_fsblk_t ext3_get_inode_block(struct super_block *sb,
 		unsigned long ino, struct ext3_iloc *iloc)
 {
-	unsigned long desc, group_desc, block_group;
+	unsigned long block_group;
 	unsigned long offset;
 	ext3_fsblk_t block;
-	struct buffer_head *bh;
-	struct ext3_group_desc * gdp;
+	struct ext3_group_desc *gdp;
 
 	if (!ext3_valid_inum(sb, ino)) {
 		/*
@@ -2470,27 +2469,15 @@ static ext3_fsblk_t ext3_get_inode_block(struct super_block *sb,
 	}
 
 	block_group = (ino - 1) / EXT3_INODES_PER_GROUP(sb);
-	if (block_group >= EXT3_SB(sb)->s_groups_count) {
-		ext3_error(sb,"ext3_get_inode_block","group >= groups count");
-		return 0;
-	}
-	smp_rmb();
-	group_desc = block_group >> EXT3_DESC_PER_BLOCK_BITS(sb);
-	desc = block_group & (EXT3_DESC_PER_BLOCK(sb) - 1);
-	bh = EXT3_SB(sb)->s_group_desc[group_desc];
-	if (!bh) {
-		ext3_error (sb, "ext3_get_inode_block",
-			    "Descriptor not loaded");
+	gdp = ext3_get_group_desc(sb, block_group, NULL);
+	if (!gdp)
 		return 0;
-	}
-
-	gdp = (struct ext3_group_desc *)bh->b_data;
 	/*
 	 * Figure out the offset within the block group inode table
 	 */
 	offset = ((ino - 1) % EXT3_INODES_PER_GROUP(sb)) *
 		EXT3_INODE_SIZE(sb);
-	block = le32_to_cpu(gdp[desc].bg_inode_table) +
+	block = le32_to_cpu(gdp->bg_inode_table) +
 		(offset >> EXT3_BLOCK_SIZE_BITS(sb));
 
 	iloc->block_group = block_group;
@@ -3214,7 +3201,7 @@ void ext3_dirty_inode(struct inode *inode)
 		current_handle->h_transaction != handle->h_transaction) {
 		/* This task has a transaction open against a different fs */
 		printk(KERN_EMERG "%s: transactions do not match!\n",
-		       __FUNCTION__);
+		       __func__);
 	} else {
 		jbd_debug(5, "marking dirty.  outer handle=%p\n",
 				current_handle);
diff --git a/trunk/fs/ext3/namei.c b/trunk/fs/ext3/namei.c
index dec3e0d88ab1..0b8cf80154f1 100644
--- a/trunk/fs/ext3/namei.c
+++ b/trunk/fs/ext3/namei.c
@@ -57,10 +57,15 @@ static struct buffer_head *ext3_append(handle_t *handle,
 
 	*block = inode->i_size >> inode->i_sb->s_blocksize_bits;
 
-	if ((bh = ext3_bread(handle, inode, *block, 1, err))) {
+	bh = ext3_bread(handle, inode, *block, 1, err);
+	if (bh) {
 		inode->i_size += inode->i_sb->s_blocksize;
 		EXT3_I(inode)->i_disksize = inode->i_size;
-		ext3_journal_get_write_access(handle,bh);
+		*err = ext3_journal_get_write_access(handle, bh);
+		if (*err) {
+			brelse(bh);
+			bh = NULL;
+		}
 	}
 	return bh;
 }
@@ -356,7 +361,7 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 	if (root->info.hash_version != DX_HASH_TEA &&
 	    root->info.hash_version != DX_HASH_HALF_MD4 &&
 	    root->info.hash_version != DX_HASH_LEGACY) {
-		ext3_warning(dir->i_sb, __FUNCTION__,
+		ext3_warning(dir->i_sb, __func__,
 			     "Unrecognised inode hash code %d",
 			     root->info.hash_version);
 		brelse(bh);
@@ -370,7 +375,7 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 	hash = hinfo->hash;
 
 	if (root->info.unused_flags & 1) {
-		ext3_warning(dir->i_sb, __FUNCTION__,
+		ext3_warning(dir->i_sb, __func__,
 			     "Unimplemented inode hash flags: %#06x",
 			     root->info.unused_flags);
 		brelse(bh);
@@ -379,7 +384,7 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 	}
 
 	if ((indirect = root->info.indirect_levels) > 1) {
-		ext3_warning(dir->i_sb, __FUNCTION__,
+		ext3_warning(dir->i_sb, __func__,
 			     "Unimplemented inode hash depth: %#06x",
 			     root->info.indirect_levels);
 		brelse(bh);
@@ -392,7 +397,7 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 
 	if (dx_get_limit(entries) != dx_root_limit(dir,
 						   root->info.info_length)) {
-		ext3_warning(dir->i_sb, __FUNCTION__,
+		ext3_warning(dir->i_sb, __func__,
 			     "dx entry: limit != root limit");
 		brelse(bh);
 		*err = ERR_BAD_DX_DIR;
@@ -404,7 +409,7 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 	{
 		count = dx_get_count(entries);
 		if (!count || count > dx_get_limit(entries)) {
-			ext3_warning(dir->i_sb, __FUNCTION__,
+			ext3_warning(dir->i_sb, __func__,
 				     "dx entry: no count or count > limit");
 			brelse(bh);
 			*err = ERR_BAD_DX_DIR;
@@ -449,7 +454,7 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 			goto fail2;
 		at = entries = ((struct dx_node *) bh->b_data)->entries;
 		if (dx_get_limit(entries) != dx_node_limit (dir)) {
-			ext3_warning(dir->i_sb, __FUNCTION__,
+			ext3_warning(dir->i_sb, __func__,
 				     "dx entry: limit != node limit");
 			brelse(bh);
 			*err = ERR_BAD_DX_DIR;
@@ -465,7 +470,7 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 	}
 fail:
 	if (*err == ERR_BAD_DX_DIR)
-		ext3_warning(dir->i_sb, __FUNCTION__,
+		ext3_warning(dir->i_sb, __func__,
 			     "Corrupt dir inode %ld, running e2fsck is "
 			     "recommended.", dir->i_ino);
 	return NULL;
@@ -913,7 +918,7 @@ static struct buffer_head * ext3_find_entry (struct dentry *dentry,
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
 			/* read error, skip block & hope for the best */
-			ext3_error(sb, __FUNCTION__, "reading directory #%lu "
+			ext3_error(sb, __func__, "reading directory #%lu "
 				   "offset %lu", dir->i_ino, block);
 			brelse(bh);
 			goto next;
@@ -1005,7 +1010,7 @@ static struct buffer_head * ext3_dx_find_entry(struct dentry *dentry,
 		retval = ext3_htree_next_block(dir, hash, frame,
 					       frames, NULL);
 		if (retval < 0) {
-			ext3_warning(sb, __FUNCTION__,
+			ext3_warning(sb, __func__,
 			     "error reading index page in directory #%lu",
 			     dir->i_ino);
 			*err = retval;
@@ -1530,7 +1535,7 @@ static int ext3_dx_add_entry(handle_t *handle, struct dentry *dentry,
 
 		if (levels && (dx_get_count(frames->entries) ==
 			       dx_get_limit(frames->entries))) {
-			ext3_warning(sb, __FUNCTION__,
+			ext3_warning(sb, __func__,
 				     "Directory index full!");
 			err = -ENOSPC;
 			goto cleanup;
@@ -1832,11 +1837,11 @@ static int empty_dir (struct inode * inode)
 	if (inode->i_size < EXT3_DIR_REC_LEN(1) + EXT3_DIR_REC_LEN(2) ||
 	    !(bh = ext3_bread (NULL, inode, 0, 0, &err))) {
 		if (err)
-			ext3_error(inode->i_sb, __FUNCTION__,
+			ext3_error(inode->i_sb, __func__,
 				   "error %d reading directory #%lu offset 0",
 				   err, inode->i_ino);
 		else
-			ext3_warning(inode->i_sb, __FUNCTION__,
+			ext3_warning(inode->i_sb, __func__,
 				     "bad directory (dir #%lu) - no data block",
 				     inode->i_ino);
 		return 1;
@@ -1865,7 +1870,7 @@ static int empty_dir (struct inode * inode)
 				offset >> EXT3_BLOCK_SIZE_BITS(sb), 0, &err);
 			if (!bh) {
 				if (err)
-					ext3_error(sb, __FUNCTION__,
+					ext3_error(sb, __func__,
 						   "error %d reading directory"
 						   " #%lu offset %lu",
 						   err, inode->i_ino, offset);
@@ -2318,6 +2323,8 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
 					      EXT3_FEATURE_INCOMPAT_FILETYPE))
 			new_de->file_type = old_de->file_type;
 		new_dir->i_version++;
+		new_dir->i_ctime = new_dir->i_mtime = CURRENT_TIME_SEC;
+		ext3_mark_inode_dirty(handle, new_dir);
 		BUFFER_TRACE(new_bh, "call ext3_journal_dirty_metadata");
 		ext3_journal_dirty_metadata(handle, new_bh);
 		brelse(new_bh);
diff --git a/trunk/fs/ext3/resize.c b/trunk/fs/ext3/resize.c
index 0e97b6e07cb0..28cfd0b40527 100644
--- a/trunk/fs/ext3/resize.c
+++ b/trunk/fs/ext3/resize.c
@@ -48,60 +48,60 @@ static int verify_group_input(struct super_block *sb,
 		       free_blocks_count, input->reserved_blocks);
 
 	if (group != sbi->s_groups_count)
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "Cannot add at group %u (only %lu groups)",
 			     input->group, sbi->s_groups_count);
 	else if ((start - le32_to_cpu(es->s_first_data_block)) %
 		 EXT3_BLOCKS_PER_GROUP(sb))
-		ext3_warning(sb, __FUNCTION__, "Last group not full");
+		ext3_warning(sb, __func__, "Last group not full");
 	else if (input->reserved_blocks > input->blocks_count / 5)
-		ext3_warning(sb, __FUNCTION__, "Reserved blocks too high (%u)",
+		ext3_warning(sb, __func__, "Reserved blocks too high (%u)",
 			     input->reserved_blocks);
 	else if (free_blocks_count < 0)
-		ext3_warning(sb, __FUNCTION__, "Bad blocks count %u",
+		ext3_warning(sb, __func__, "Bad blocks count %u",
 			     input->blocks_count);
 	else if (!(bh = sb_bread(sb, end - 1)))
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "Cannot read last block ("E3FSBLK")",
 			     end - 1);
 	else if (outside(input->block_bitmap, start, end))
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "Block bitmap not in group (block %u)",
 			     input->block_bitmap);
 	else if (outside(input->inode_bitmap, start, end))
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "Inode bitmap not in group (block %u)",
 			     input->inode_bitmap);
 	else if (outside(input->inode_table, start, end) ||
 	         outside(itend - 1, start, end))
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "Inode table not in group (blocks %u-"E3FSBLK")",
 			     input->inode_table, itend - 1);
 	else if (input->inode_bitmap == input->block_bitmap)
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "Block bitmap same as inode bitmap (%u)",
 			     input->block_bitmap);
 	else if (inside(input->block_bitmap, input->inode_table, itend))
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "Block bitmap (%u) in inode table (%u-"E3FSBLK")",
 			     input->block_bitmap, input->inode_table, itend-1);
 	else if (inside(input->inode_bitmap, input->inode_table, itend))
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "Inode bitmap (%u) in inode table (%u-"E3FSBLK")",
 			     input->inode_bitmap, input->inode_table, itend-1);
 	else if (inside(input->block_bitmap, start, metaend))
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "Block bitmap (%u) in GDT table"
 			     " ("E3FSBLK"-"E3FSBLK")",
 			     input->block_bitmap, start, metaend - 1);
 	else if (inside(input->inode_bitmap, start, metaend))
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "Inode bitmap (%u) in GDT table"
 			     " ("E3FSBLK"-"E3FSBLK")",
 			     input->inode_bitmap, start, metaend - 1);
 	else if (inside(input->inode_table, start, metaend) ||
 	         inside(itend - 1, start, metaend))
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "Inode table (%u-"E3FSBLK") overlaps"
 			     "GDT table ("E3FSBLK"-"E3FSBLK")",
 			     input->inode_table, itend - 1, start, metaend - 1);
@@ -386,7 +386,7 @@ static int verify_reserved_gdb(struct super_block *sb,
 
 	while ((grp = ext3_list_backups(sb, &three, &five, &seven)) < end) {
 		if (le32_to_cpu(*p++) != grp * EXT3_BLOCKS_PER_GROUP(sb) + blk){
-			ext3_warning(sb, __FUNCTION__,
+			ext3_warning(sb, __func__,
 				     "reserved GDT "E3FSBLK
 				     " missing grp %d ("E3FSBLK")",
 				     blk, grp,
@@ -440,7 +440,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	 */
 	if (EXT3_SB(sb)->s_sbh->b_blocknr !=
 	    le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block)) {
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			"won't resize using backup superblock at %llu",
 			(unsigned long long)EXT3_SB(sb)->s_sbh->b_blocknr);
 		return -EPERM;
@@ -464,7 +464,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 
 	data = (__le32 *)dind->b_data;
 	if (le32_to_cpu(data[gdb_num % EXT3_ADDR_PER_BLOCK(sb)]) != gdblock) {
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "new group %u GDT block "E3FSBLK" not reserved",
 			     input->group, gdblock);
 		err = -EINVAL;
@@ -488,7 +488,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 			GFP_NOFS);
 	if (!n_group_desc) {
 		err = -ENOMEM;
-		ext3_warning (sb, __FUNCTION__,
+		ext3_warning (sb, __func__,
 			      "not enough memory for %lu groups", gdb_num + 1);
 		goto exit_inode;
 	}
@@ -586,7 +586,7 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
 	/* Get each reserved primary GDT block and verify it holds backups */
 	for (res = 0; res < reserved_gdb; res++, blk++) {
 		if (le32_to_cpu(*data) != blk) {
-			ext3_warning(sb, __FUNCTION__,
+			ext3_warning(sb, __func__,
 				     "reserved block "E3FSBLK
 				     " not at offset %ld",
 				     blk,
@@ -730,7 +730,7 @@ static void update_backups(struct super_block *sb,
 	 */
 exit_err:
 	if (err) {
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "can't update backup for group %d (err %d), "
 			     "forcing fsck on next reboot", group, err);
 		sbi->s_mount_state &= ~EXT3_VALID_FS;
@@ -770,33 +770,33 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
 
 	if (gdb_off == 0 && !EXT3_HAS_RO_COMPAT_FEATURE(sb,
 					EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "Can't resize non-sparse filesystem further");
 		return -EPERM;
 	}
 
 	if (le32_to_cpu(es->s_blocks_count) + input->blocks_count <
 	    le32_to_cpu(es->s_blocks_count)) {
-		ext3_warning(sb, __FUNCTION__, "blocks_count overflow\n");
+		ext3_warning(sb, __func__, "blocks_count overflow\n");
 		return -EINVAL;
 	}
 
 	if (le32_to_cpu(es->s_inodes_count) + EXT3_INODES_PER_GROUP(sb) <
 	    le32_to_cpu(es->s_inodes_count)) {
-		ext3_warning(sb, __FUNCTION__, "inodes_count overflow\n");
+		ext3_warning(sb, __func__, "inodes_count overflow\n");
 		return -EINVAL;
 	}
 
 	if (reserved_gdb || gdb_off == 0) {
 		if (!EXT3_HAS_COMPAT_FEATURE(sb,
 					     EXT3_FEATURE_COMPAT_RESIZE_INODE)){
-			ext3_warning(sb, __FUNCTION__,
+			ext3_warning(sb, __func__,
 				     "No reserved GDT blocks, can't resize");
 			return -EPERM;
 		}
 		inode = ext3_iget(sb, EXT3_RESIZE_INO);
 		if (IS_ERR(inode)) {
-			ext3_warning(sb, __FUNCTION__,
+			ext3_warning(sb, __func__,
 				     "Error opening resize inode");
 			return PTR_ERR(inode);
 		}
@@ -825,7 +825,7 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
 
 	lock_super(sb);
 	if (input->group != sbi->s_groups_count) {
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "multiple resizers run on filesystem!");
 		err = -EBUSY;
 		goto exit_journal;
@@ -988,13 +988,13 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
 			" too large to resize to %lu blocks safely\n",
 			sb->s_id, n_blocks_count);
 		if (sizeof(sector_t) < 8)
-			ext3_warning(sb, __FUNCTION__,
+			ext3_warning(sb, __func__,
 			"CONFIG_LBD not enabled\n");
 		return -EINVAL;
 	}
 
 	if (n_blocks_count < o_blocks_count) {
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "can't shrink FS - resize aborted");
 		return -EBUSY;
 	}
@@ -1004,7 +1004,7 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
 		EXT3_BLOCKS_PER_GROUP(sb);
 
 	if (last == 0) {
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "need to use ext2online to resize further");
 		return -EPERM;
 	}
@@ -1012,7 +1012,7 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
 	add = EXT3_BLOCKS_PER_GROUP(sb) - last;
 
 	if (o_blocks_count + add < o_blocks_count) {
-		ext3_warning(sb, __FUNCTION__, "blocks_count overflow");
+		ext3_warning(sb, __func__, "blocks_count overflow");
 		return -EINVAL;
 	}
 
@@ -1020,7 +1020,7 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
 		add = n_blocks_count - o_blocks_count;
 
 	if (o_blocks_count + add < n_blocks_count)
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "will only finish group ("E3FSBLK
 			     " blocks, %u new)",
 			     o_blocks_count + add, add);
@@ -1028,7 +1028,7 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
 	/* See if the device is actually as big as what was requested */
 	bh = sb_bread(sb, o_blocks_count + add -1);
 	if (!bh) {
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "can't read last block, resize aborted");
 		return -ENOSPC;
 	}
@@ -1040,22 +1040,23 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es,
 	handle = ext3_journal_start_sb(sb, 3);
 	if (IS_ERR(handle)) {
 		err = PTR_ERR(handle);
-		ext3_warning(sb, __FUNCTION__, "error %d on journal start",err);
+		ext3_warning(sb, __func__, "error %d on journal start",err);
 		goto exit_put;
 	}
 
 	lock_super(sb);
 	if (o_blocks_count != le32_to_cpu(es->s_blocks_count)) {
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "multiple resizers run on filesystem!");
 		unlock_super(sb);
+		ext3_journal_stop(handle);
 		err = -EBUSY;
 		goto exit_put;
 	}
 
 	if ((err = ext3_journal_get_write_access(handle,
 						 EXT3_SB(sb)->s_sbh))) {
-		ext3_warning(sb, __FUNCTION__,
+		ext3_warning(sb, __func__,
 			     "error %d on journal write access", err);
 		unlock_super(sb);
 		ext3_journal_stop(handle);
diff --git a/trunk/fs/ext3/super.c b/trunk/fs/ext3/super.c
index ad5360664082..fe3119a71ada 100644
--- a/trunk/fs/ext3/super.c
+++ b/trunk/fs/ext3/super.c
@@ -84,7 +84,7 @@ handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks)
 	 * take the FS itself readonly cleanly. */
 	journal = EXT3_SB(sb)->s_journal;
 	if (is_journal_aborted(journal)) {
-		ext3_abort(sb, __FUNCTION__,
+		ext3_abort(sb, __func__,
 			   "Detected aborted journal");
 		return ERR_PTR(-EROFS);
 	}
@@ -304,7 +304,7 @@ void ext3_update_dynamic_rev(struct super_block *sb)
 	if (le32_to_cpu(es->s_rev_level) > EXT3_GOOD_OLD_REV)
 		return;
 
-	ext3_warning(sb, __FUNCTION__,
+	ext3_warning(sb, __func__,
 		     "updating to rev %d because of new feature flag, "
 		     "running e2fsck is recommended",
 		     EXT3_DYNAMIC_REV);
@@ -685,7 +685,8 @@ static int ext3_acquire_dquot(struct dquot *dquot);
 static int ext3_release_dquot(struct dquot *dquot);
 static int ext3_mark_dquot_dirty(struct dquot *dquot);
 static int ext3_write_info(struct super_block *sb, int type);
-static int ext3_quota_on(struct super_block *sb, int type, int format_id, char *path);
+static int ext3_quota_on(struct super_block *sb, int type, int format_id,
+				char *path, int remount);
 static int ext3_quota_on_mount(struct super_block *sb, int type);
 static ssize_t ext3_quota_read(struct super_block *sb, int type, char *data,
 			       size_t len, loff_t off);
@@ -1096,6 +1097,9 @@ static int parse_options (char *options, struct super_block *sb,
 		case Opt_quota:
 		case Opt_usrquota:
 		case Opt_grpquota:
+			printk(KERN_ERR
+				"EXT3-fs: quota options not supported.\n");
+			break;
 		case Opt_usrjquota:
 		case Opt_grpjquota:
 		case Opt_offusrjquota:
@@ -1103,7 +1107,7 @@ static int parse_options (char *options, struct super_block *sb,
 		case Opt_jqfmt_vfsold:
 		case Opt_jqfmt_vfsv0:
 			printk(KERN_ERR
-				"EXT3-fs: journalled quota options not "
+				"EXT3-fs: journaled quota options not "
 				"supported.\n");
 			break;
 		case Opt_noquota:
@@ -1218,7 +1222,7 @@ static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es,
                    inconsistencies, to force a fsck at reboot.  But for
                    a plain journaled filesystem we can keep it set as
                    valid forever! :) */
-	es->s_state = cpu_to_le16(le16_to_cpu(es->s_state) & ~EXT3_VALID_FS);
+	es->s_state &= cpu_to_le16(~EXT3_VALID_FS);
 #endif
 	if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
 		es->s_max_mnt_count = cpu_to_le16(EXT3_DFL_MAX_MNT_COUNT);
@@ -1253,14 +1257,14 @@ static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es,
 static int ext3_check_descriptors(struct super_block *sb)
 {
 	struct ext3_sb_info *sbi = EXT3_SB(sb);
-	ext3_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
-	ext3_fsblk_t last_block;
 	int i;
 
 	ext3_debug ("Checking group descriptors");
 
 	for (i = 0; i < sbi->s_groups_count; i++) {
 		struct ext3_group_desc *gdp = ext3_get_group_desc(sb, i, NULL);
+		ext3_fsblk_t first_block = ext3_group_first_block_no(sb, i);
+		ext3_fsblk_t last_block;
 
 		if (i == sbi->s_groups_count - 1)
 			last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
@@ -1299,7 +1303,6 @@ static int ext3_check_descriptors(struct super_block *sb)
 					le32_to_cpu(gdp->bg_inode_table));
 			return 0;
 		}
-		first_block += EXT3_BLOCKS_PER_GROUP(sb);
 	}
 
 	sbi->s_es->s_free_blocks_count=cpu_to_le32(ext3_count_free_blocks(sb));
@@ -1387,7 +1390,7 @@ static void ext3_orphan_cleanup (struct super_block * sb,
 		if (inode->i_nlink) {
 			printk(KERN_DEBUG
 				"%s: truncating inode %lu to %Ld bytes\n",
-				__FUNCTION__, inode->i_ino, inode->i_size);
+				__func__, inode->i_ino, inode->i_size);
 			jbd_debug(2, "truncating inode %lu to %Ld bytes\n",
 				  inode->i_ino, inode->i_size);
 			ext3_truncate(inode);
@@ -1395,7 +1398,7 @@ static void ext3_orphan_cleanup (struct super_block * sb,
 		} else {
 			printk(KERN_DEBUG
 				"%s: deleting unreferenced inode %lu\n",
-				__FUNCTION__, inode->i_ino);
+				__func__, inode->i_ino);
 			jbd_debug(2, "deleting unreferenced inode %lu\n",
 				  inode->i_ino);
 			nr_orphans++;
@@ -1415,7 +1418,7 @@ static void ext3_orphan_cleanup (struct super_block * sb,
 	/* Turn quotas off */
 	for (i = 0; i < MAXQUOTAS; i++) {
 		if (sb_dqopt(sb)->files[i])
-			vfs_quota_off(sb, i);
+			vfs_quota_off(sb, i, 0);
 	}
 #endif
 	sb->s_flags = s_flags; /* Restore MS_RDONLY status */
@@ -2298,9 +2301,9 @@ static void ext3_clear_journal_err(struct super_block * sb,
 		char nbuf[16];
 
 		errstr = ext3_decode_error(sb, j_errno, nbuf);
-		ext3_warning(sb, __FUNCTION__, "Filesystem error recorded "
+		ext3_warning(sb, __func__, "Filesystem error recorded "
 			     "from previous mount: %s", errstr);
-		ext3_warning(sb, __FUNCTION__, "Marking fs in need of "
+		ext3_warning(sb, __func__, "Marking fs in need of "
 			     "filesystem check.");
 
 		EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS;
@@ -2427,7 +2430,7 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data)
 	}
 
 	if (sbi->s_mount_opt & EXT3_MOUNT_ABORT)
-		ext3_abort(sb, __FUNCTION__, "Abort forced by user");
+		ext3_abort(sb, __func__, "Abort forced by user");
 
 	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
 		((sbi->s_mount_opt & EXT3_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
@@ -2639,8 +2642,14 @@ static int ext3_dquot_drop(struct inode *inode)
 
 	/* We may delete quota structure so we need to reserve enough blocks */
 	handle = ext3_journal_start(inode, 2*EXT3_QUOTA_DEL_BLOCKS(inode->i_sb));
-	if (IS_ERR(handle))
+	if (IS_ERR(handle)) {
+		/*
+		 * We call dquot_drop() anyway to at least release references
+		 * to quota structures so that umount does not hang.
+		 */
+		dquot_drop(inode);
 		return PTR_ERR(handle);
+	}
 	ret = dquot_drop(inode);
 	err = ext3_journal_stop(handle);
 	if (!ret)
@@ -2743,17 +2752,17 @@ static int ext3_quota_on_mount(struct super_block *sb, int type)
  * Standard function to be called on quota_on
  */
 static int ext3_quota_on(struct super_block *sb, int type, int format_id,
-			 char *path)
+			 char *path, int remount)
 {
 	int err;
 	struct nameidata nd;
 
 	if (!test_opt(sb, QUOTA))
 		return -EINVAL;
-	/* Not journalling quota? */
-	if (!EXT3_SB(sb)->s_qf_names[USRQUOTA] &&
-	    !EXT3_SB(sb)->s_qf_names[GRPQUOTA])
-		return vfs_quota_on(sb, type, format_id, path);
+	/* Not journalling quota or remount? */
+	if ((!EXT3_SB(sb)->s_qf_names[USRQUOTA] &&
+	    !EXT3_SB(sb)->s_qf_names[GRPQUOTA]) || remount)
+		return vfs_quota_on(sb, type, format_id, path, remount);
 	err = path_lookup(path, LOOKUP_FOLLOW, &nd);
 	if (err)
 		return err;
@@ -2762,13 +2771,13 @@ static int ext3_quota_on(struct super_block *sb, int type, int format_id,
 		path_put(&nd.path);
 		return -EXDEV;
 	}
-	/* Quotafile not of fs root? */
+	/* Quotafile not in fs root? */
 	if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode)
 		printk(KERN_WARNING
 			"EXT3-fs: Quota file not on filesystem root. "
 			"Journalled quota will not work.\n");
 	path_put(&nd.path);
-	return vfs_quota_on(sb, type, format_id, path);
+	return vfs_quota_on(sb, type, format_id, path, remount);
 }
 
 /* Read data from quotafile - avoid pagecache and such because we cannot afford
diff --git a/trunk/fs/ext3/xattr.c b/trunk/fs/ext3/xattr.c
index 42856541e9a5..d4a4f0e9ff69 100644
--- a/trunk/fs/ext3/xattr.c
+++ b/trunk/fs/ext3/xattr.c
@@ -99,6 +99,8 @@ static struct buffer_head *ext3_xattr_cache_find(struct inode *,
 						 struct mb_cache_entry **);
 static void ext3_xattr_rehash(struct ext3_xattr_header *,
 			      struct ext3_xattr_entry *);
+static int ext3_xattr_list(struct inode *inode, char *buffer,
+			   size_t buffer_size);
 
 static struct mb_cache *ext3_xattr_cache;
 
@@ -232,7 +234,7 @@ ext3_xattr_block_get(struct inode *inode, int name_index, const char *name,
 	ea_bdebug(bh, "b_count=%d, refcount=%d",
 		atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
 	if (ext3_xattr_check_block(bh)) {
-bad_block:	ext3_error(inode->i_sb, __FUNCTION__,
+bad_block:	ext3_error(inode->i_sb, __func__,
 			   "inode %lu: bad block "E3FSBLK, inode->i_ino,
 			   EXT3_I(inode)->i_file_acl);
 		error = -EIO;
@@ -374,7 +376,7 @@ ext3_xattr_block_list(struct inode *inode, char *buffer, size_t buffer_size)
 	ea_bdebug(bh, "b_count=%d, refcount=%d",
 		atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
 	if (ext3_xattr_check_block(bh)) {
-		ext3_error(inode->i_sb, __FUNCTION__,
+		ext3_error(inode->i_sb, __func__,
 			   "inode %lu: bad block "E3FSBLK, inode->i_ino,
 			   EXT3_I(inode)->i_file_acl);
 		error = -EIO;
@@ -427,7 +429,7 @@ ext3_xattr_ibody_list(struct inode *inode, char *buffer, size_t buffer_size)
  * Returns a negative error number on failure, or the number of bytes
  * used / required on success.
  */
-int
+static int
 ext3_xattr_list(struct inode *inode, char *buffer, size_t buffer_size)
 {
 	int i_error, b_error;
@@ -649,7 +651,7 @@ ext3_xattr_block_find(struct inode *inode, struct ext3_xattr_info *i,
 			atomic_read(&(bs->bh->b_count)),
 			le32_to_cpu(BHDR(bs->bh)->h_refcount));
 		if (ext3_xattr_check_block(bs->bh)) {
-			ext3_error(sb, __FUNCTION__,
+			ext3_error(sb, __func__,
 				"inode %lu: bad block "E3FSBLK, inode->i_ino,
 				EXT3_I(inode)->i_file_acl);
 			error = -EIO;
@@ -797,10 +799,8 @@ ext3_xattr_block_set(handle_t *handle, struct inode *inode,
 			get_bh(new_bh);
 		} else {
 			/* We need to allocate a new block */
-			ext3_fsblk_t goal = le32_to_cpu(
-					EXT3_SB(sb)->s_es->s_first_data_block) +
-				(ext3_fsblk_t)EXT3_I(inode)->i_block_group *
-				EXT3_BLOCKS_PER_GROUP(sb);
+			ext3_fsblk_t goal = ext3_group_first_block_no(sb,
+						EXT3_I(inode)->i_block_group);
 			ext3_fsblk_t block = ext3_new_block(handle, inode,
 							goal, &error);
 			if (error)
@@ -852,7 +852,7 @@ ext3_xattr_block_set(handle_t *handle, struct inode *inode,
 	goto cleanup;
 
 bad_block:
-	ext3_error(inode->i_sb, __FUNCTION__,
+	ext3_error(inode->i_sb, __func__,
 		   "inode %lu: bad block "E3FSBLK, inode->i_ino,
 		   EXT3_I(inode)->i_file_acl);
 	goto cleanup;
@@ -1081,14 +1081,14 @@ ext3_xattr_delete_inode(handle_t *handle, struct inode *inode)
 		goto cleanup;
 	bh = sb_bread(inode->i_sb, EXT3_I(inode)->i_file_acl);
 	if (!bh) {
-		ext3_error(inode->i_sb, __FUNCTION__,
+		ext3_error(inode->i_sb, __func__,
 			"inode %lu: block "E3FSBLK" read error", inode->i_ino,
 			EXT3_I(inode)->i_file_acl);
 		goto cleanup;
 	}
 	if (BHDR(bh)->h_magic != cpu_to_le32(EXT3_XATTR_MAGIC) ||
 	    BHDR(bh)->h_blocks != cpu_to_le32(1)) {
-		ext3_error(inode->i_sb, __FUNCTION__,
+		ext3_error(inode->i_sb, __func__,
 			"inode %lu: bad block "E3FSBLK, inode->i_ino,
 			EXT3_I(inode)->i_file_acl);
 		goto cleanup;
@@ -1215,7 +1215,7 @@ ext3_xattr_cache_find(struct inode *inode, struct ext3_xattr_header *header,
 		}
 		bh = sb_bread(inode->i_sb, ce->e_block);
 		if (!bh) {
-			ext3_error(inode->i_sb, __FUNCTION__,
+			ext3_error(inode->i_sb, __func__,
 				"inode %lu: block %lu read error",
 				inode->i_ino, (unsigned long) ce->e_block);
 		} else if (le32_to_cpu(BHDR(bh)->h_refcount) >=
diff --git a/trunk/fs/ext3/xattr.h b/trunk/fs/ext3/xattr.h
index 6b1ae1c6182c..148a4dfc82ab 100644
--- a/trunk/fs/ext3/xattr.h
+++ b/trunk/fs/ext3/xattr.h
@@ -67,7 +67,6 @@ extern struct xattr_handler ext3_xattr_security_handler;
 extern ssize_t ext3_listxattr(struct dentry *, char *, size_t);
 
 extern int ext3_xattr_get(struct inode *, int, const char *, void *, size_t);
-extern int ext3_xattr_list(struct inode *, char *, size_t);
 extern int ext3_xattr_set(struct inode *, int, const char *, const void *, size_t, int);
 extern int ext3_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int);
 
@@ -88,12 +87,6 @@ ext3_xattr_get(struct inode *inode, int name_index, const char *name,
 	return -EOPNOTSUPP;
 }
 
-static inline int
-ext3_xattr_list(struct inode *inode, void *buffer, size_t size)
-{
-	return -EOPNOTSUPP;
-}
-
 static inline int
 ext3_xattr_set(struct inode *inode, int name_index, const char *name,
 	       const void *value, size_t size, int flags)
diff --git a/trunk/fs/ext4/mballoc.c b/trunk/fs/ext4/mballoc.c
index ef97f19c2f9d..9d57695de746 100644
--- a/trunk/fs/ext4/mballoc.c
+++ b/trunk/fs/ext4/mballoc.c
@@ -2449,17 +2449,10 @@ static void ext4_mb_history_init(struct super_block *sb)
 	int i;
 
 	if (sbi->s_mb_proc != NULL) {
-		struct proc_dir_entry *p;
-		p = create_proc_entry("mb_history", S_IRUGO, sbi->s_mb_proc);
-		if (p) {
-			p->proc_fops = &ext4_mb_seq_history_fops;
-			p->data = sb;
-		}
-		p = create_proc_entry("mb_groups", S_IRUGO, sbi->s_mb_proc);
-		if (p) {
-			p->proc_fops = &ext4_mb_seq_groups_fops;
-			p->data = sb;
-		}
+		proc_create_data("mb_history", S_IRUGO, sbi->s_mb_proc,
+				 &ext4_mb_seq_history_fops, sb);
+		proc_create_data("mb_groups", S_IRUGO, sbi->s_mb_proc,
+				 &ext4_mb_seq_groups_fops, sb);
 	}
 
 	sbi->s_mb_history_max = 1000;
@@ -2867,7 +2860,6 @@ static void ext4_mb_free_committed_blocks(struct super_block *sb)
 	mb_debug("freed %u blocks in %u structures\n", count, count2);
 }
 
-#define EXT4_ROOT			"ext4"
 #define EXT4_MB_STATS_NAME		"stats"
 #define EXT4_MB_MAX_TO_SCAN_NAME	"max_to_scan"
 #define EXT4_MB_MIN_TO_SCAN_NAME	"min_to_scan"
@@ -3007,9 +2999,9 @@ int __init init_ext4_mballoc(void)
 		return -ENOMEM;
 	}
 #ifdef CONFIG_PROC_FS
-	proc_root_ext4 = proc_mkdir(EXT4_ROOT, proc_root_fs);
+	proc_root_ext4 = proc_mkdir("fs/ext4", NULL);
 	if (proc_root_ext4 == NULL)
-		printk(KERN_ERR "EXT4-fs: Unable to create %s\n", EXT4_ROOT);
+		printk(KERN_ERR "EXT4-fs: Unable to create fs/ext4\n");
 #endif
 	return 0;
 }
@@ -3020,7 +3012,7 @@ void exit_ext4_mballoc(void)
 	kmem_cache_destroy(ext4_pspace_cachep);
 	kmem_cache_destroy(ext4_ac_cachep);
 #ifdef CONFIG_PROC_FS
-	remove_proc_entry(EXT4_ROOT, proc_root_fs);
+	remove_proc_entry("fs/ext4", NULL);
 #endif
 }
 
diff --git a/trunk/fs/ext4/super.c b/trunk/fs/ext4/super.c
index 13383ba18f1d..c81a8e759bad 100644
--- a/trunk/fs/ext4/super.c
+++ b/trunk/fs/ext4/super.c
@@ -813,7 +813,8 @@ static int ext4_acquire_dquot(struct dquot *dquot);
 static int ext4_release_dquot(struct dquot *dquot);
 static int ext4_mark_dquot_dirty(struct dquot *dquot);
 static int ext4_write_info(struct super_block *sb, int type);
-static int ext4_quota_on(struct super_block *sb, int type, int format_id, char *path);
+static int ext4_quota_on(struct super_block *sb, int type, int format_id,
+				char *path, int remount);
 static int ext4_quota_on_mount(struct super_block *sb, int type);
 static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
 			       size_t len, loff_t off);
@@ -1632,7 +1633,7 @@ static void ext4_orphan_cleanup (struct super_block * sb,
 	/* Turn quotas off */
 	for (i = 0; i < MAXQUOTAS; i++) {
 		if (sb_dqopt(sb)->files[i])
-			vfs_quota_off(sb, i);
+			vfs_quota_off(sb, i, 0);
 	}
 #endif
 	sb->s_flags = s_flags; /* Restore MS_RDONLY status */
@@ -3143,7 +3144,7 @@ static int ext4_quota_on_mount(struct super_block *sb, int type)
  * Standard function to be called on quota_on
  */
 static int ext4_quota_on(struct super_block *sb, int type, int format_id,
-			 char *path)
+			 char *path, int remount)
 {
 	int err;
 	struct nameidata nd;
@@ -3151,9 +3152,9 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 	if (!test_opt(sb, QUOTA))
 		return -EINVAL;
 	/* Not journalling quota? */
-	if (!EXT4_SB(sb)->s_qf_names[USRQUOTA] &&
-	    !EXT4_SB(sb)->s_qf_names[GRPQUOTA])
-		return vfs_quota_on(sb, type, format_id, path);
+	if ((!EXT4_SB(sb)->s_qf_names[USRQUOTA] &&
+	    !EXT4_SB(sb)->s_qf_names[GRPQUOTA]) || remount)
+		return vfs_quota_on(sb, type, format_id, path, remount);
 	err = path_lookup(path, LOOKUP_FOLLOW, &nd);
 	if (err)
 		return err;
@@ -3168,7 +3169,7 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 			"EXT4-fs: Quota file not on filesystem root. "
 			"Journalled quota will not work.\n");
 	path_put(&nd.path);
-	return vfs_quota_on(sb, type, format_id, path);
+	return vfs_quota_on(sb, type, format_id, path, remount);
 }
 
 /* Read data from quotafile - avoid pagecache and such because we cannot afford
diff --git a/trunk/fs/fat/dir.c b/trunk/fs/fat/dir.c
index 72cbcd61bd95..486725ee99ae 100644
--- a/trunk/fs/fat/dir.c
+++ b/trunk/fs/fat/dir.c
@@ -124,8 +124,8 @@ static inline int fat_get_entry(struct inode *dir, loff_t *pos,
  * but ignore that right now.
  * Ahem... Stack smashing in ring 0 isn't fun. Fixed.
  */
-static int uni16_to_x8(unsigned char *ascii, wchar_t *uni, int uni_xlate,
-		       struct nls_table *nls)
+static int uni16_to_x8(unsigned char *ascii, wchar_t *uni, int len,
+		       int uni_xlate, struct nls_table *nls)
 {
 	wchar_t *ip, ec;
 	unsigned char *op, nc;
@@ -135,10 +135,11 @@ static int uni16_to_x8(unsigned char *ascii, wchar_t *uni, int uni_xlate,
 	ip = uni;
 	op = ascii;
 
-	while (*ip) {
+	while (*ip && ((len - NLS_MAX_CHARSET_SIZE) > 0)) {
 		ec = *ip++;
 		if ( (charlen = nls->uni2char(ec, op, NLS_MAX_CHARSET_SIZE)) > 0) {
 			op += charlen;
+			len -= charlen;
 		} else {
 			if (uni_xlate == 1) {
 				*op = ':';
@@ -149,16 +150,19 @@ static int uni16_to_x8(unsigned char *ascii, wchar_t *uni, int uni_xlate,
 					ec >>= 4;
 				}
 				op += 5;
+				len -= 5;
 			} else {
 				*op++ = '?';
+				len--;
 			}
 		}
-		/* We have some slack there, so it's OK */
-		if (op>ascii+256) {
-			op = ascii + 256;
-			break;
-		}
 	}
+
+	if (unlikely(*ip)) {
+		printk(KERN_WARNING "FAT: filename was truncated while "
+		       "converting.");
+	}
+
 	*op = 0;
 	return (op - ascii);
 }
@@ -243,7 +247,7 @@ static int fat_parse_long(struct inode *dir, loff_t *pos,
 	unsigned char id, slot, slots, alias_checksum;
 
 	if (!*unicode) {
-		*unicode = (wchar_t *)__get_free_page(GFP_KERNEL);
+		*unicode = __getname();
 		if (!*unicode) {
 			brelse(*bh);
 			return -ENOMEM;
@@ -311,9 +315,11 @@ int fat_search_long(struct inode *inode, const unsigned char *name,
 	struct nls_table *nls_io = sbi->nls_io;
 	struct nls_table *nls_disk = sbi->nls_disk;
 	wchar_t bufuname[14];
-	unsigned char xlate_len, nr_slots;
+	unsigned char nr_slots;
+	int xlate_len;
 	wchar_t *unicode = NULL;
-	unsigned char work[MSDOS_NAME], bufname[260];	/* 256 + 4 */
+	unsigned char work[MSDOS_NAME];
+	unsigned char *bufname = NULL;
 	int uni_xlate = sbi->options.unicode_xlate;
 	int utf8 = sbi->options.utf8;
 	int anycase = (sbi->options.name_check != 's');
@@ -321,6 +327,10 @@ int fat_search_long(struct inode *inode, const unsigned char *name,
 	loff_t cpos = 0;
 	int chl, i, j, last_u, err;
 
+	bufname = __getname();
+	if (!bufname)
+		return -ENOMEM;
+
 	err = -ENOENT;
 	while(1) {
 		if (fat_get_entry(inode, &cpos, &bh, &de) == -1)
@@ -386,8 +396,8 @@ int fat_search_long(struct inode *inode, const unsigned char *name,
 
 		bufuname[last_u] = 0x0000;
 		xlate_len = utf8
-			?utf8_wcstombs(bufname, bufuname, sizeof(bufname))
-			:uni16_to_x8(bufname, bufuname, uni_xlate, nls_io);
+			?utf8_wcstombs(bufname, bufuname, PATH_MAX)
+			:uni16_to_x8(bufname, bufuname, PATH_MAX, uni_xlate, nls_io);
 		if (xlate_len == name_len)
 			if ((!anycase && !memcmp(name, bufname, xlate_len)) ||
 			    (anycase && !nls_strnicmp(nls_io, name, bufname,
@@ -396,8 +406,8 @@ int fat_search_long(struct inode *inode, const unsigned char *name,
 
 		if (nr_slots) {
 			xlate_len = utf8
-				?utf8_wcstombs(bufname, unicode, sizeof(bufname))
-				:uni16_to_x8(bufname, unicode, uni_xlate, nls_io);
+				?utf8_wcstombs(bufname, unicode, PATH_MAX)
+				:uni16_to_x8(bufname, unicode, PATH_MAX, uni_xlate, nls_io);
 			if (xlate_len != name_len)
 				continue;
 			if ((!anycase && !memcmp(name, bufname, xlate_len)) ||
@@ -416,8 +426,10 @@ int fat_search_long(struct inode *inode, const unsigned char *name,
 	sinfo->i_pos = fat_make_i_pos(sb, sinfo->bh, sinfo->de);
 	err = 0;
 EODir:
+	if (bufname)
+		__putname(bufname);
 	if (unicode)
-		free_page((unsigned long)unicode);
+		__putname(unicode);
 
 	return err;
 }
@@ -598,7 +610,7 @@ static int __fat_readdir(struct inode *inode, struct file *filp, void *dirent,
 	if (isvfat) {
 		bufuname[j] = 0x0000;
 		i = utf8 ? utf8_wcstombs(bufname, bufuname, sizeof(bufname))
-			 : uni16_to_x8(bufname, bufuname, uni_xlate, nls_io);
+			 : uni16_to_x8(bufname, bufuname, sizeof(bufname), uni_xlate, nls_io);
 	}
 
 	fill_name = bufname;
@@ -607,10 +619,10 @@ static int __fat_readdir(struct inode *inode, struct file *filp, void *dirent,
 		/* convert the unicode long name. 261 is maximum size
 		 * of unicode buffer. (13 * slots + nul) */
 		void *longname = unicode + 261;
-		int buf_size = PAGE_SIZE - (261 * sizeof(unicode[0]));
+		int buf_size = PATH_MAX - (261 * sizeof(unicode[0]));
 		int long_len = utf8
 			? utf8_wcstombs(longname, unicode, buf_size)
-			: uni16_to_x8(longname, unicode, uni_xlate, nls_io);
+			: uni16_to_x8(longname, unicode, buf_size, uni_xlate, nls_io);
 
 		if (!both) {
 			fill_name = longname;
@@ -640,7 +652,7 @@ static int __fat_readdir(struct inode *inode, struct file *filp, void *dirent,
 FillFailed:
 	brelse(bh);
 	if (unicode)
-		free_page((unsigned long)unicode);
+		__putname(unicode);
 out:
 	unlock_kernel();
 	return ret;
diff --git a/trunk/fs/fat/fatent.c b/trunk/fs/fat/fatent.c
index 5fb366992b73..13ab763cc510 100644
--- a/trunk/fs/fat/fatent.c
+++ b/trunk/fs/fat/fatent.c
@@ -450,7 +450,8 @@ int fat_alloc_clusters(struct inode *inode, int *cluster, int nr_cluster)
 	BUG_ON(nr_cluster > (MAX_BUF_PER_PAGE / 2));	/* fixed limit */
 
 	lock_fat(sbi);
-	if (sbi->free_clusters != -1 && sbi->free_clusters < nr_cluster) {
+	if (sbi->free_clusters != -1 && sbi->free_clus_valid &&
+	    sbi->free_clusters < nr_cluster) {
 		unlock_fat(sbi);
 		return -ENOSPC;
 	}
@@ -504,6 +505,7 @@ int fat_alloc_clusters(struct inode *inode, int *cluster, int nr_cluster)
 
 	/* Couldn't allocate the free entries */
 	sbi->free_clusters = 0;
+	sbi->free_clus_valid = 1;
 	sb->s_dirt = 1;
 	err = -ENOSPC;
 
@@ -583,8 +585,6 @@ int fat_free_clusters(struct inode *inode, int cluster)
 		brelse(bhs[i]);
 	unlock_fat(sbi);
 
-	fat_clusters_flush(sb);
-
 	return err;
 }
 
@@ -615,7 +615,7 @@ int fat_count_free_clusters(struct super_block *sb)
 	int err = 0, free;
 
 	lock_fat(sbi);
-	if (sbi->free_clusters != -1)
+	if (sbi->free_clusters != -1 && sbi->free_clus_valid)
 		goto out;
 
 	reada_blocks = FAT_READA_SIZE >> sb->s_blocksize_bits;
@@ -643,6 +643,7 @@ int fat_count_free_clusters(struct super_block *sb)
 		} while (fat_ent_next(sbi, &fatent));
 	}
 	sbi->free_clusters = free;
+	sbi->free_clus_valid = 1;
 	sb->s_dirt = 1;
 	fatent_brelse(&fatent);
 out:
diff --git a/trunk/fs/fat/file.c b/trunk/fs/fat/file.c
index 2a3bed967041..d604bb132422 100644
--- a/trunk/fs/fat/file.c
+++ b/trunk/fs/fat/file.c
@@ -157,104 +157,6 @@ static int fat_cont_expand(struct inode *inode, loff_t size)
 	return err;
 }
 
-static int check_mode(const struct msdos_sb_info *sbi, mode_t mode)
-{
-	mode_t req = mode & ~S_IFMT;
-
-	/*
-	 * Of the r and x bits, all (subject to umask) must be present. Of the
-	 * w bits, either all (subject to umask) or none must be present.
-	 */
-
-	if (S_ISREG(mode)) {
-		req &= ~sbi->options.fs_fmask;
-
-		if ((req & (S_IRUGO | S_IXUGO)) !=
-		    ((S_IRUGO | S_IXUGO) & ~sbi->options.fs_fmask))
-			return -EPERM;
-
-		if ((req & S_IWUGO) != 0 &&
-		    (req & S_IWUGO) != (S_IWUGO & ~sbi->options.fs_fmask))
-			return -EPERM;
-	} else if (S_ISDIR(mode)) {
-		req &= ~sbi->options.fs_dmask;
-
-		if ((req & (S_IRUGO | S_IXUGO)) !=
-		    ((S_IRUGO | S_IXUGO) & ~sbi->options.fs_dmask))
-			return -EPERM;
-
-		if ((req & S_IWUGO) != 0 &&
-		    (req & S_IWUGO) != (S_IWUGO & ~sbi->options.fs_dmask))
-			return -EPERM;
-	} else {
-		return -EPERM;
-	}
-
-	return 0;
-}
-
-int fat_notify_change(struct dentry *dentry, struct iattr *attr)
-{
-	struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb);
-	struct inode *inode = dentry->d_inode;
-	int mask, error = 0;
-
-	lock_kernel();
-
-	/*
-	 * Expand the file. Since inode_setattr() updates ->i_size
-	 * before calling the ->truncate(), but FAT needs to fill the
-	 * hole before it.
-	 */
-	if (attr->ia_valid & ATTR_SIZE) {
-		if (attr->ia_size > inode->i_size) {
-			error = fat_cont_expand(inode, attr->ia_size);
-			if (error || attr->ia_valid == ATTR_SIZE)
-				goto out;
-			attr->ia_valid &= ~ATTR_SIZE;
-		}
-	}
-
-	error = inode_change_ok(inode, attr);
-	if (error) {
-		if (sbi->options.quiet)
-			error = 0;
-		goto out;
-	}
-	if (((attr->ia_valid & ATTR_UID) &&
-	     (attr->ia_uid != sbi->options.fs_uid)) ||
-	    ((attr->ia_valid & ATTR_GID) &&
-	     (attr->ia_gid != sbi->options.fs_gid)))
-		error = -EPERM;
-
-	if (error) {
-		if (sbi->options.quiet)
-			error = 0;
-		goto out;
-	}
-
-	if (attr->ia_valid & ATTR_MODE) {
-		error = check_mode(sbi, attr->ia_mode);
-		if (error != 0 && !sbi->options.quiet)
-			goto out;
-	}
-
-	error = inode_setattr(inode, attr);
-	if (error)
-		goto out;
-
-	if (S_ISDIR(inode->i_mode))
-		mask = sbi->options.fs_dmask;
-	else
-		mask = sbi->options.fs_fmask;
-	inode->i_mode &= S_IFMT | (S_IRWXUGO & ~mask);
-out:
-	unlock_kernel();
-	return error;
-}
-
-EXPORT_SYMBOL_GPL(fat_notify_change);
-
 /* Free all clusters after the skip'th cluster. */
 static int fat_free(struct inode *inode, int skip)
 {
@@ -355,8 +257,112 @@ int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 }
 EXPORT_SYMBOL_GPL(fat_getattr);
 
+static int fat_check_mode(const struct msdos_sb_info *sbi, struct inode *inode,
+			  mode_t mode)
+{
+	mode_t mask, req = mode & ~S_IFMT;
+
+	if (S_ISREG(mode))
+		mask = sbi->options.fs_fmask;
+	else
+		mask = sbi->options.fs_dmask;
+
+	/*
+	 * Of the r and x bits, all (subject to umask) must be present. Of the
+	 * w bits, either all (subject to umask) or none must be present.
+	 */
+	req &= ~mask;
+	if ((req & (S_IRUGO | S_IXUGO)) != (inode->i_mode & (S_IRUGO|S_IXUGO)))
+		return -EPERM;
+	if ((req & S_IWUGO) && ((req & S_IWUGO) != (S_IWUGO & ~mask)))
+		return -EPERM;
+
+	return 0;
+}
+
+static int fat_allow_set_time(struct msdos_sb_info *sbi, struct inode *inode)
+{
+	mode_t allow_utime = sbi->options.allow_utime;
+
+	if (current->fsuid != inode->i_uid) {
+		if (in_group_p(inode->i_gid))
+			allow_utime >>= 3;
+		if (allow_utime & MAY_WRITE)
+			return 1;
+	}
+
+	/* use a default check */
+	return 0;
+}
+
+int fat_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb);
+	struct inode *inode = dentry->d_inode;
+	int mask, error = 0;
+	unsigned int ia_valid;
+
+	lock_kernel();
+
+	/*
+	 * Expand the file. Since inode_setattr() updates ->i_size
+	 * before calling the ->truncate(), but FAT needs to fill the
+	 * hole before it.
+	 */
+	if (attr->ia_valid & ATTR_SIZE) {
+		if (attr->ia_size > inode->i_size) {
+			error = fat_cont_expand(inode, attr->ia_size);
+			if (error || attr->ia_valid == ATTR_SIZE)
+				goto out;
+			attr->ia_valid &= ~ATTR_SIZE;
+		}
+	}
+
+	/* Check for setting the inode time. */
+	ia_valid = attr->ia_valid;
+	if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET)) {
+		if (fat_allow_set_time(sbi, inode))
+			attr->ia_valid &= ~(ATTR_MTIME_SET | ATTR_ATIME_SET);
+	}
+
+	error = inode_change_ok(inode, attr);
+	attr->ia_valid = ia_valid;
+	if (error) {
+		if (sbi->options.quiet)
+			error = 0;
+		goto out;
+	}
+	if (((attr->ia_valid & ATTR_UID) &&
+	     (attr->ia_uid != sbi->options.fs_uid)) ||
+	    ((attr->ia_valid & ATTR_GID) &&
+	     (attr->ia_gid != sbi->options.fs_gid)) ||
+	    ((attr->ia_valid & ATTR_MODE) &&
+	     fat_check_mode(sbi, inode, attr->ia_mode) < 0))
+		error = -EPERM;
+
+	if (error) {
+		if (sbi->options.quiet)
+			error = 0;
+		goto out;
+	}
+
+	error = inode_setattr(inode, attr);
+	if (error)
+		goto out;
+
+	if (S_ISDIR(inode->i_mode))
+		mask = sbi->options.fs_dmask;
+	else
+		mask = sbi->options.fs_fmask;
+	inode->i_mode &= S_IFMT | (S_IRWXUGO & ~mask);
+out:
+	unlock_kernel();
+	return error;
+}
+EXPORT_SYMBOL_GPL(fat_setattr);
+
 const struct inode_operations fat_file_inode_operations = {
 	.truncate	= fat_truncate,
-	.setattr	= fat_notify_change,
+	.setattr	= fat_setattr,
 	.getattr	= fat_getattr,
 };
diff --git a/trunk/fs/fat/inode.c b/trunk/fs/fat/inode.c
index 53f3cf62b7c1..4e0a3dd9d677 100644
--- a/trunk/fs/fat/inode.c
+++ b/trunk/fs/fat/inode.c
@@ -433,11 +433,8 @@ EXPORT_SYMBOL_GPL(fat_build_inode);
 static void fat_delete_inode(struct inode *inode)
 {
 	truncate_inode_pages(&inode->i_data, 0);
-
-	if (!is_bad_inode(inode)) {
-		inode->i_size = 0;
-		fat_truncate(inode);
-	}
+	inode->i_size = 0;
+	fat_truncate(inode);
 	clear_inode(inode);
 }
 
@@ -445,8 +442,6 @@ static void fat_clear_inode(struct inode *inode)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
 
-	if (is_bad_inode(inode))
-		return;
 	lock_kernel();
 	spin_lock(&sbi->inode_hash_lock);
 	fat_cache_inval_inode(inode);
@@ -542,7 +537,7 @@ static int fat_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb);
 
 	/* If the count of free cluster is still unknown, counts it here. */
-	if (sbi->free_clusters == -1) {
+	if (sbi->free_clusters == -1 || !sbi->free_clus_valid) {
 		int err = fat_count_free_clusters(dentry->d_sb);
 		if (err)
 			return err;
@@ -790,6 +785,8 @@ static int fat_show_options(struct seq_file *m, struct vfsmount *mnt)
 		seq_printf(m, ",gid=%u", opts->fs_gid);
 	seq_printf(m, ",fmask=%04o", opts->fs_fmask);
 	seq_printf(m, ",dmask=%04o", opts->fs_dmask);
+	if (opts->allow_utime)
+		seq_printf(m, ",allow_utime=%04o", opts->allow_utime);
 	if (sbi->nls_disk)
 		seq_printf(m, ",codepage=%s", sbi->nls_disk->charset);
 	if (isvfat) {
@@ -845,9 +842,9 @@ static int fat_show_options(struct seq_file *m, struct vfsmount *mnt)
 
 enum {
 	Opt_check_n, Opt_check_r, Opt_check_s, Opt_uid, Opt_gid,
-	Opt_umask, Opt_dmask, Opt_fmask, Opt_codepage, Opt_usefree, Opt_nocase,
-	Opt_quiet, Opt_showexec, Opt_debug, Opt_immutable,
-	Opt_dots, Opt_nodots,
+	Opt_umask, Opt_dmask, Opt_fmask, Opt_allow_utime, Opt_codepage,
+	Opt_usefree, Opt_nocase, Opt_quiet, Opt_showexec, Opt_debug,
+	Opt_immutable, Opt_dots, Opt_nodots,
 	Opt_charset, Opt_shortname_lower, Opt_shortname_win95,
 	Opt_shortname_winnt, Opt_shortname_mixed, Opt_utf8_no, Opt_utf8_yes,
 	Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes,
@@ -866,6 +863,7 @@ static match_table_t fat_tokens = {
 	{Opt_umask, "umask=%o"},
 	{Opt_dmask, "dmask=%o"},
 	{Opt_fmask, "fmask=%o"},
+	{Opt_allow_utime, "allow_utime=%o"},
 	{Opt_codepage, "codepage=%u"},
 	{Opt_usefree, "usefree"},
 	{Opt_nocase, "nocase"},
@@ -937,6 +935,7 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug,
 	opts->fs_uid = current->uid;
 	opts->fs_gid = current->gid;
 	opts->fs_fmask = opts->fs_dmask = current->fs->umask;
+	opts->allow_utime = -1;
 	opts->codepage = fat_default_codepage;
 	opts->iocharset = fat_default_iocharset;
 	if (is_vfat)
@@ -1024,6 +1023,11 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug,
 				return 0;
 			opts->fs_fmask = option;
 			break;
+		case Opt_allow_utime:
+			if (match_octal(&args[0], &option))
+				return 0;
+			opts->allow_utime = option & (S_IWGRP | S_IWOTH);
+			break;
 		case Opt_codepage:
 			if (match_int(&args[0], &option))
 				return 0;
@@ -1106,6 +1110,9 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug,
 		       " for FAT filesystems, filesystem will be case sensitive!\n");
 	}
 
+	/* If user doesn't specify allow_utime, it's initialized from dmask. */
+	if (opts->allow_utime == (unsigned short)-1)
+		opts->allow_utime = ~opts->fs_dmask & (S_IWGRP | S_IWOTH);
 	if (opts->unicode_xlate)
 		opts->utf8 = 0;
 
@@ -1208,18 +1215,17 @@ int fat_fill_super(struct super_block *sb, void *data, int silent,
 	 */
 
 	media = b->media;
-	if (!FAT_VALID_MEDIA(media)) {
+	if (!fat_valid_media(media)) {
 		if (!silent)
 			printk(KERN_ERR "FAT: invalid media value (0x%02x)\n",
 			       media);
 		brelse(bh);
 		goto out_invalid;
 	}
-	logical_sector_size =
-		le16_to_cpu(get_unaligned((__le16 *)&b->sector_size));
+	logical_sector_size = get_unaligned_le16(&b->sector_size);
 	if (!is_power_of_2(logical_sector_size)
 	    || (logical_sector_size < 512)
-	    || (PAGE_CACHE_SIZE < logical_sector_size)) {
+	    || (logical_sector_size > 4096)) {
 		if (!silent)
 			printk(KERN_ERR "FAT: bogus logical sector size %u\n",
 			       logical_sector_size);
@@ -1267,6 +1273,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent,
 	sbi->fat_length = le16_to_cpu(b->fat_length);
 	sbi->root_cluster = 0;
 	sbi->free_clusters = -1;	/* Don't know yet */
+	sbi->free_clus_valid = 0;
 	sbi->prev_free = FAT_START_ENT;
 
 	if (!sbi->fat_length && b->fat32_length) {
@@ -1302,8 +1309,8 @@ int fat_fill_super(struct super_block *sb, void *data, int silent,
 			       sbi->fsinfo_sector);
 		} else {
 			if (sbi->options.usefree)
-				sbi->free_clusters =
-					le32_to_cpu(fsinfo->free_clusters);
+				sbi->free_clus_valid = 1;
+			sbi->free_clusters = le32_to_cpu(fsinfo->free_clusters);
 			sbi->prev_free = le32_to_cpu(fsinfo->next_cluster);
 		}
 
@@ -1314,8 +1321,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent,
 	sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1;
 
 	sbi->dir_start = sbi->fat_start + sbi->fats * sbi->fat_length;
-	sbi->dir_entries =
-		le16_to_cpu(get_unaligned((__le16 *)&b->dir_entries));
+	sbi->dir_entries = get_unaligned_le16(&b->dir_entries);
 	if (sbi->dir_entries & (sbi->dir_per_block - 1)) {
 		if (!silent)
 			printk(KERN_ERR "FAT: bogus directroy-entries per block"
@@ -1327,7 +1333,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent,
 	rootdir_sectors = sbi->dir_entries
 		* sizeof(struct msdos_dir_entry) / sb->s_blocksize;
 	sbi->data_start = sbi->dir_start + rootdir_sectors;
-	total_sectors = le16_to_cpu(get_unaligned((__le16 *)&b->sectors));
+	total_sectors = get_unaligned_le16(&b->sectors);
 	if (total_sectors == 0)
 		total_sectors = le32_to_cpu(b->total_sect);
 
diff --git a/trunk/fs/freevxfs/vxfs_extern.h b/trunk/fs/freevxfs/vxfs_extern.h
index 2b46064f66b2..50ab5eecb99b 100644
--- a/trunk/fs/freevxfs/vxfs_extern.h
+++ b/trunk/fs/freevxfs/vxfs_extern.h
@@ -50,7 +50,11 @@ extern daddr_t			vxfs_bmap1(struct inode *, long);
 /* vxfs_fshead.c */
 extern int			vxfs_read_fshead(struct super_block *);
 
+/* vxfs_immed.c */
+extern const struct inode_operations vxfs_immed_symlink_iops;
+
 /* vxfs_inode.c */
+extern const struct address_space_operations vxfs_immed_aops;
 extern struct kmem_cache	*vxfs_inode_cachep;
 extern void			vxfs_dumpi(struct vxfs_inode_info *, ino_t);
 extern struct inode *		vxfs_get_fake_inode(struct super_block *,
@@ -69,6 +73,7 @@ extern const struct file_operations	vxfs_dir_operations;
 extern int			vxfs_read_olt(struct super_block *, u_long);
 
 /* vxfs_subr.c */
+extern const struct address_space_operations vxfs_aops;
 extern struct page *		vxfs_get_page(struct address_space *, u_long);
 extern void			vxfs_put_page(struct page *);
 extern struct buffer_head *	vxfs_bread(struct inode *, int);
diff --git a/trunk/fs/freevxfs/vxfs_immed.c b/trunk/fs/freevxfs/vxfs_immed.c
index 8a5959a61ba9..c36aeaf92e41 100644
--- a/trunk/fs/freevxfs/vxfs_immed.c
+++ b/trunk/fs/freevxfs/vxfs_immed.c
@@ -35,6 +35,7 @@
 #include <linux/namei.h>
 
 #include "vxfs.h"
+#include "vxfs_extern.h"
 #include "vxfs_inode.h"
 
 
diff --git a/trunk/fs/freevxfs/vxfs_inode.c b/trunk/fs/freevxfs/vxfs_inode.c
index ad88d2364bc2..9f3f2ceb73f0 100644
--- a/trunk/fs/freevxfs/vxfs_inode.c
+++ b/trunk/fs/freevxfs/vxfs_inode.c
@@ -41,11 +41,6 @@
 #include "vxfs_extern.h"
 
 
-extern const struct address_space_operations vxfs_aops;
-extern const struct address_space_operations vxfs_immed_aops;
-
-extern const struct inode_operations vxfs_immed_symlink_iops;
-
 struct kmem_cache		*vxfs_inode_cachep;
 
 
diff --git a/trunk/fs/fs-writeback.c b/trunk/fs/fs-writeback.c
index 06557679ca41..ae45f77765c0 100644
--- a/trunk/fs/fs-writeback.c
+++ b/trunk/fs/fs-writeback.c
@@ -25,6 +25,45 @@
 #include <linux/buffer_head.h>
 #include "internal.h"
 
+
+/**
+ * writeback_acquire - attempt to get exclusive writeback access to a device
+ * @bdi: the device's backing_dev_info structure
+ *
+ * It is a waste of resources to have more than one pdflush thread blocked on
+ * a single request queue.  Exclusion at the request_queue level is obtained
+ * via a flag in the request_queue's backing_dev_info.state.
+ *
+ * Non-request_queue-backed address_spaces will share default_backing_dev_info,
+ * unless they implement their own.  Which is somewhat inefficient, as this
+ * may prevent concurrent writeback against multiple devices.
+ */
+static int writeback_acquire(struct backing_dev_info *bdi)
+{
+	return !test_and_set_bit(BDI_pdflush, &bdi->state);
+}
+
+/**
+ * writeback_in_progress - determine whether there is writeback in progress
+ * @bdi: the device's backing_dev_info structure.
+ *
+ * Determine whether there is writeback in progress against a backing device.
+ */
+int writeback_in_progress(struct backing_dev_info *bdi)
+{
+	return test_bit(BDI_pdflush, &bdi->state);
+}
+
+/**
+ * writeback_release - relinquish exclusive writeback access against a device.
+ * @bdi: the device's backing_dev_info structure
+ */
+static void writeback_release(struct backing_dev_info *bdi)
+{
+	BUG_ON(!writeback_in_progress(bdi));
+	clear_bit(BDI_pdflush, &bdi->state);
+}
+
 /**
  *	__mark_inode_dirty -	internal function
  *	@inode: inode to mark
@@ -747,43 +786,4 @@ int generic_osync_inode(struct inode *inode, struct address_space *mapping, int
 
 	return err;
 }
-
 EXPORT_SYMBOL(generic_osync_inode);
-
-/**
- * writeback_acquire - attempt to get exclusive writeback access to a device
- * @bdi: the device's backing_dev_info structure
- *
- * It is a waste of resources to have more than one pdflush thread blocked on
- * a single request queue.  Exclusion at the request_queue level is obtained
- * via a flag in the request_queue's backing_dev_info.state.
- *
- * Non-request_queue-backed address_spaces will share default_backing_dev_info,
- * unless they implement their own.  Which is somewhat inefficient, as this
- * may prevent concurrent writeback against multiple devices.
- */
-int writeback_acquire(struct backing_dev_info *bdi)
-{
-	return !test_and_set_bit(BDI_pdflush, &bdi->state);
-}
-
-/**
- * writeback_in_progress - determine whether there is writeback in progress
- * @bdi: the device's backing_dev_info structure.
- *
- * Determine whether there is writeback in progress against a backing device.
- */
-int writeback_in_progress(struct backing_dev_info *bdi)
-{
-	return test_bit(BDI_pdflush, &bdi->state);
-}
-
-/**
- * writeback_release - relinquish exclusive writeback access against a device.
- * @bdi: the device's backing_dev_info structure
- */
-void writeback_release(struct backing_dev_info *bdi)
-{
-	BUG_ON(!writeback_in_progress(bdi));
-	clear_bit(BDI_pdflush, &bdi->state);
-}
diff --git a/trunk/fs/gfs2/ops_address.c b/trunk/fs/gfs2/ops_address.c
index 90a04a6e3789..f55394e57cb2 100644
--- a/trunk/fs/gfs2/ops_address.c
+++ b/trunk/fs/gfs2/ops_address.c
@@ -438,7 +438,7 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
 	int error;
 
 	/*
-	 * Due to the order of unstuffing files and ->nopage(), we can be
+	 * Due to the order of unstuffing files and ->fault(), we can be
 	 * asked for a zero page in the case of a stuffed file being extended,
 	 * so we need to supply one here. It doesn't happen often.
 	 */
diff --git a/trunk/fs/hfs/super.c b/trunk/fs/hfs/super.c
index 32de44ed0021..8cf67974adf6 100644
--- a/trunk/fs/hfs/super.c
+++ b/trunk/fs/hfs/super.c
@@ -297,7 +297,8 @@ static int parse_options(char *options, struct hfs_sb_info *hsb)
 				return 0;
 			}
 			p = match_strdup(&args[0]);
-			hsb->nls_disk = load_nls(p);
+			if (p)
+				hsb->nls_disk = load_nls(p);
 			if (!hsb->nls_disk) {
 				printk(KERN_ERR "hfs: unable to load codepage \"%s\"\n", p);
 				kfree(p);
@@ -311,7 +312,8 @@ static int parse_options(char *options, struct hfs_sb_info *hsb)
 				return 0;
 			}
 			p = match_strdup(&args[0]);
-			hsb->nls_io = load_nls(p);
+			if (p)
+				hsb->nls_io = load_nls(p);
 			if (!hsb->nls_io) {
 				printk(KERN_ERR "hfs: unable to load iocharset \"%s\"\n", p);
 				kfree(p);
diff --git a/trunk/fs/hfsplus/hfsplus_fs.h b/trunk/fs/hfsplus/hfsplus_fs.h
index d72d0a8b25aa..9e59537b43d5 100644
--- a/trunk/fs/hfsplus/hfsplus_fs.h
+++ b/trunk/fs/hfsplus/hfsplus_fs.h
@@ -311,6 +311,10 @@ int hfsplus_delete_cat(u32, struct inode *, struct qstr *);
 int hfsplus_rename_cat(u32, struct inode *, struct qstr *,
 		       struct inode *, struct qstr *);
 
+/* dir.c */
+extern const struct inode_operations hfsplus_dir_inode_operations;
+extern const struct file_operations hfsplus_dir_operations;
+
 /* extents.c */
 int hfsplus_ext_cmp_key(const hfsplus_btree_key *, const hfsplus_btree_key *);
 void hfsplus_ext_write_extent(struct inode *);
diff --git a/trunk/fs/hfsplus/inode.c b/trunk/fs/hfsplus/inode.c
index 37744cf3706a..d53b2af91c25 100644
--- a/trunk/fs/hfsplus/inode.c
+++ b/trunk/fs/hfsplus/inode.c
@@ -278,9 +278,6 @@ static int hfsplus_file_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-extern const struct inode_operations hfsplus_dir_inode_operations;
-extern struct file_operations hfsplus_dir_operations;
-
 static const struct inode_operations hfsplus_file_inode_operations = {
 	.lookup		= hfsplus_file_lookup,
 	.truncate	= hfsplus_file_truncate,
diff --git a/trunk/fs/hfsplus/options.c b/trunk/fs/hfsplus/options.c
index dc64fac00831..9997cbf8beb5 100644
--- a/trunk/fs/hfsplus/options.c
+++ b/trunk/fs/hfsplus/options.c
@@ -132,7 +132,8 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi)
 				return 0;
 			}
 			p = match_strdup(&args[0]);
-			sbi->nls = load_nls(p);
+			if (p)
+				sbi->nls = load_nls(p);
 			if (!sbi->nls) {
 				printk(KERN_ERR "hfs: unable to load nls mapping \"%s\"\n", p);
 				kfree(p);
diff --git a/trunk/fs/hfsplus/wrapper.c b/trunk/fs/hfsplus/wrapper.c
index 72cab78f0509..175d08eacc86 100644
--- a/trunk/fs/hfsplus/wrapper.c
+++ b/trunk/fs/hfsplus/wrapper.c
@@ -47,7 +47,7 @@ static int hfsplus_read_mdb(void *bufptr, struct hfsplus_wd *wd)
 		return 0;
 	wd->ablk_start = be16_to_cpu(*(__be16 *)(bufptr + HFSP_WRAPOFF_ABLKSTART));
 
-	extent = be32_to_cpu(get_unaligned((__be32 *)(bufptr + HFSP_WRAPOFF_EMBEDEXT)));
+	extent = get_unaligned_be32(bufptr + HFSP_WRAPOFF_EMBEDEXT);
 	wd->embed_start = (extent >> 16) & 0xFFFF;
 	wd->embed_count = extent & 0xFFFF;
 
diff --git a/trunk/fs/hugetlbfs/inode.c b/trunk/fs/hugetlbfs/inode.c
index 6846785fe904..9783723e8ffe 100644
--- a/trunk/fs/hugetlbfs/inode.c
+++ b/trunk/fs/hugetlbfs/inode.c
@@ -504,7 +504,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid,
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		INIT_LIST_HEAD(&inode->i_mapping->private_list);
 		info = HUGETLBFS_I(inode);
-		mpol_shared_policy_init(&info->policy, MPOL_DEFAULT, NULL);
+		mpol_shared_policy_init(&info->policy, NULL);
 		switch (mode & S_IFMT) {
 		default:
 			init_special_inode(inode, mode, dev);
diff --git a/trunk/fs/inode.c b/trunk/fs/inode.c
index 27ee1af50d02..bf6478130424 100644
--- a/trunk/fs/inode.c
+++ b/trunk/fs/inode.c
@@ -495,8 +495,7 @@ static struct inode * find_inode(struct super_block * sb, struct hlist_head *hea
 	struct inode * inode = NULL;
 
 repeat:
-	hlist_for_each (node, head) { 
-		inode = hlist_entry(node, struct inode, i_hash);
+	hlist_for_each_entry(inode, node, head, i_hash) {
 		if (inode->i_sb != sb)
 			continue;
 		if (!test(inode, data))
@@ -520,8 +519,7 @@ static struct inode * find_inode_fast(struct super_block * sb, struct hlist_head
 	struct inode * inode = NULL;
 
 repeat:
-	hlist_for_each (node, head) {
-		inode = hlist_entry(node, struct inode, i_hash);
+	hlist_for_each_entry(inode, node, head, i_hash) {
 		if (inode->i_ino != ino)
 			continue;
 		if (inode->i_sb != sb)
diff --git a/trunk/fs/inotify_user.c b/trunk/fs/inotify_user.c
index 7b94a1e3c015..6676c06bb7c1 100644
--- a/trunk/fs/inotify_user.c
+++ b/trunk/fs/inotify_user.c
@@ -598,7 +598,7 @@ asmlinkage long sys_inotify_init(void)
 	}
 
 	ih = inotify_init(&inotify_user_ops);
-	if (unlikely(IS_ERR(ih))) {
+	if (IS_ERR(ih)) {
 		ret = PTR_ERR(ih);
 		goto out_free_dev;
 	}
diff --git a/trunk/fs/ioctl.c b/trunk/fs/ioctl.c
index f32fbde2175e..7db32b3382d3 100644
--- a/trunk/fs/ioctl.c
+++ b/trunk/fs/ioctl.c
@@ -28,8 +28,8 @@
  *
  * Returns 0 on success, -errno on error.
  */
-long vfs_ioctl(struct file *filp, unsigned int cmd,
-	       unsigned long arg)
+static long vfs_ioctl(struct file *filp, unsigned int cmd,
+		      unsigned long arg)
 {
 	int error = -ENOTTY;
 
diff --git a/trunk/fs/isofs/isofs.h b/trunk/fs/isofs/isofs.h
index d1bdf8adb351..ccbf72faf27a 100644
--- a/trunk/fs/isofs/isofs.h
+++ b/trunk/fs/isofs/isofs.h
@@ -78,29 +78,29 @@ static inline int isonum_712(char *p)
 }
 static inline unsigned int isonum_721(char *p)
 {
-	return le16_to_cpu(get_unaligned((__le16 *)p));
+	return get_unaligned_le16(p);
 }
 static inline unsigned int isonum_722(char *p)
 {
-	return be16_to_cpu(get_unaligned((__le16 *)p));
+	return get_unaligned_be16(p);
 }
 static inline unsigned int isonum_723(char *p)
 {
 	/* Ignore bigendian datum due to broken mastering programs */
-	return le16_to_cpu(get_unaligned((__le16 *)p));
+	return get_unaligned_le16(p);
 }
 static inline unsigned int isonum_731(char *p)
 {
-	return le32_to_cpu(get_unaligned((__le32 *)p));
+	return get_unaligned_le32(p);
 }
 static inline unsigned int isonum_732(char *p)
 {
-	return be32_to_cpu(get_unaligned((__le32 *)p));
+	return get_unaligned_be32(p);
 }
 static inline unsigned int isonum_733(char *p)
 {
 	/* Ignore bigendian datum due to broken mastering programs */
-	return le32_to_cpu(get_unaligned((__le32 *)p));
+	return get_unaligned_le32(p);
 }
 extern int iso_date(char *, int);
 
diff --git a/trunk/fs/jbd/commit.c b/trunk/fs/jbd/commit.c
index a38c7186c570..cd931ef1f000 100644
--- a/trunk/fs/jbd/commit.c
+++ b/trunk/fs/jbd/commit.c
@@ -406,22 +406,6 @@ void journal_commit_transaction(journal_t *journal)
 
 	jbd_debug (3, "JBD: commit phase 2\n");
 
-	/*
-	 * First, drop modified flag: all accesses to the buffers
-	 * will be tracked for a new trasaction only -bzzz
-	 */
-	spin_lock(&journal->j_list_lock);
-	if (commit_transaction->t_buffers) {
-		new_jh = jh = commit_transaction->t_buffers->b_tnext;
-		do {
-			J_ASSERT_JH(new_jh, new_jh->b_modified == 1 ||
-					new_jh->b_modified == 0);
-			new_jh->b_modified = 0;
-			new_jh = new_jh->b_tnext;
-		} while (new_jh != jh);
-	}
-	spin_unlock(&journal->j_list_lock);
-
 	/*
 	 * Now start flushing things to disk, in the order they appear
 	 * on the transaction lists.  Data blocks go first.
@@ -488,6 +472,9 @@ void journal_commit_transaction(journal_t *journal)
 	 */
 	commit_transaction->t_state = T_COMMIT;
 
+	J_ASSERT(commit_transaction->t_nr_buffers <=
+		 commit_transaction->t_outstanding_credits);
+
 	descriptor = NULL;
 	bufs = 0;
 	while (commit_transaction->t_buffers) {
diff --git a/trunk/fs/jbd/journal.c b/trunk/fs/jbd/journal.c
index 0e081d5f32e8..b99c3b3654c4 100644
--- a/trunk/fs/jbd/journal.c
+++ b/trunk/fs/jbd/journal.c
@@ -534,7 +534,7 @@ int log_wait_commit(journal_t *journal, tid_t tid)
 	if (!tid_geq(journal->j_commit_request, tid)) {
 		printk(KERN_EMERG
 		       "%s: error: j_commit_request=%d, tid=%d\n",
-		       __FUNCTION__, journal->j_commit_request, tid);
+		       __func__, journal->j_commit_request, tid);
 	}
 	spin_unlock(&journal->j_state_lock);
 #endif
@@ -599,7 +599,7 @@ int journal_bmap(journal_t *journal, unsigned long blocknr,
 
 			printk(KERN_ALERT "%s: journal block not found "
 					"at offset %lu on %s\n",
-				__FUNCTION__,
+				__func__,
 				blocknr,
 				bdevname(journal->j_dev, b));
 			err = -EIO;
@@ -728,7 +728,7 @@ journal_t * journal_init_dev(struct block_device *bdev,
 	journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
 	if (!journal->j_wbuf) {
 		printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
-			__FUNCTION__);
+			__func__);
 		kfree(journal);
 		journal = NULL;
 		goto out;
@@ -782,7 +782,7 @@ journal_t * journal_init_inode (struct inode *inode)
 	journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
 	if (!journal->j_wbuf) {
 		printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
-			__FUNCTION__);
+			__func__);
 		kfree(journal);
 		return NULL;
 	}
@@ -791,7 +791,7 @@ journal_t * journal_init_inode (struct inode *inode)
 	/* If that failed, give up */
 	if (err) {
 		printk(KERN_ERR "%s: Cannnot locate journal superblock\n",
-		       __FUNCTION__);
+		       __func__);
 		kfree(journal);
 		return NULL;
 	}
@@ -877,7 +877,7 @@ int journal_create(journal_t *journal)
 		 */
 		printk(KERN_EMERG
 		       "%s: creation of journal on external device!\n",
-		       __FUNCTION__);
+		       __func__);
 		BUG();
 	}
 
@@ -1657,7 +1657,7 @@ static struct journal_head *journal_alloc_journal_head(void)
 		jbd_debug(1, "out of memory for journal_head\n");
 		if (time_after(jiffies, last_warning + 5*HZ)) {
 			printk(KERN_NOTICE "ENOMEM in %s, retrying.\n",
-			       __FUNCTION__);
+			       __func__);
 			last_warning = jiffies;
 		}
 		while (ret == NULL) {
@@ -1794,13 +1794,13 @@ static void __journal_remove_journal_head(struct buffer_head *bh)
 			if (jh->b_frozen_data) {
 				printk(KERN_WARNING "%s: freeing "
 						"b_frozen_data\n",
-						__FUNCTION__);
+						__func__);
 				jbd_free(jh->b_frozen_data, bh->b_size);
 			}
 			if (jh->b_committed_data) {
 				printk(KERN_WARNING "%s: freeing "
 						"b_committed_data\n",
-						__FUNCTION__);
+						__func__);
 				jbd_free(jh->b_committed_data, bh->b_size);
 			}
 			bh->b_private = NULL;
diff --git a/trunk/fs/jbd/revoke.c b/trunk/fs/jbd/revoke.c
index d5f8eee7c88c..1bb43e987f4b 100644
--- a/trunk/fs/jbd/revoke.c
+++ b/trunk/fs/jbd/revoke.c
@@ -138,7 +138,7 @@ static int insert_revoke_hash(journal_t *journal, unsigned long blocknr,
 oom:
 	if (!journal_oom_retry)
 		return -ENOMEM;
-	jbd_debug(1, "ENOMEM in %s, retrying\n", __FUNCTION__);
+	jbd_debug(1, "ENOMEM in %s, retrying\n", __func__);
 	yield();
 	goto repeat;
 }
diff --git a/trunk/fs/jbd/transaction.c b/trunk/fs/jbd/transaction.c
index 2c9e8f5d13aa..67ff2024c23c 100644
--- a/trunk/fs/jbd/transaction.c
+++ b/trunk/fs/jbd/transaction.c
@@ -608,6 +608,12 @@ do_get_write_access(handle_t *handle, struct journal_head *jh,
 	    jh->b_next_transaction == transaction)
 		goto done;
 
+	/*
+	 * this is the first time this transaction is touching this buffer,
+	 * reset the modified flag
+	 */
+	jh->b_modified = 0;
+
 	/*
 	 * If there is already a copy-out version of this buffer, then we don't
 	 * need to make another one
@@ -681,7 +687,7 @@ do_get_write_access(handle_t *handle, struct journal_head *jh,
 				if (!frozen_buffer) {
 					printk(KERN_EMERG
 					       "%s: OOM for frozen_buffer\n",
-					       __FUNCTION__);
+					       __func__);
 					JBUFFER_TRACE(jh, "oom!");
 					error = -ENOMEM;
 					jbd_lock_bh_state(bh);
@@ -820,9 +826,16 @@ int journal_get_create_access(handle_t *handle, struct buffer_head *bh)
 
 	if (jh->b_transaction == NULL) {
 		jh->b_transaction = transaction;
+
+		/* first access by this transaction */
+		jh->b_modified = 0;
+
 		JBUFFER_TRACE(jh, "file as BJ_Reserved");
 		__journal_file_buffer(jh, transaction, BJ_Reserved);
 	} else if (jh->b_transaction == journal->j_committing_transaction) {
+		/* first access by this transaction */
+		jh->b_modified = 0;
+
 		JBUFFER_TRACE(jh, "set next transaction");
 		jh->b_next_transaction = transaction;
 	}
@@ -891,7 +904,7 @@ int journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
 		committed_data = jbd_alloc(jh2bh(jh)->b_size, GFP_NOFS);
 		if (!committed_data) {
 			printk(KERN_EMERG "%s: No memory for committed data\n",
-				__FUNCTION__);
+				__func__);
 			err = -ENOMEM;
 			goto out;
 		}
@@ -1222,6 +1235,7 @@ int journal_forget (handle_t *handle, struct buffer_head *bh)
 	struct journal_head *jh;
 	int drop_reserve = 0;
 	int err = 0;
+	int was_modified = 0;
 
 	BUFFER_TRACE(bh, "entry");
 
@@ -1240,6 +1254,9 @@ int journal_forget (handle_t *handle, struct buffer_head *bh)
 		goto not_jbd;
 	}
 
+	/* keep track of wether or not this transaction modified us */
+	was_modified = jh->b_modified;
+
 	/*
 	 * The buffer's going from the transaction, we must drop
 	 * all references -bzzz
@@ -1257,7 +1274,12 @@ int journal_forget (handle_t *handle, struct buffer_head *bh)
 
 		JBUFFER_TRACE(jh, "belongs to current transaction: unfile");
 
-		drop_reserve = 1;
+		/*
+		 * we only want to drop a reference if this transaction
+		 * modified the buffer
+		 */
+		if (was_modified)
+			drop_reserve = 1;
 
 		/*
 		 * We are no longer going to journal this buffer.
@@ -1297,7 +1319,13 @@ int journal_forget (handle_t *handle, struct buffer_head *bh)
 		if (jh->b_next_transaction) {
 			J_ASSERT(jh->b_next_transaction == transaction);
 			jh->b_next_transaction = NULL;
-			drop_reserve = 1;
+
+			/*
+			 * only drop a reference if this transaction modified
+			 * the buffer
+			 */
+			if (was_modified)
+				drop_reserve = 1;
 		}
 	}
 
@@ -2069,7 +2097,7 @@ void __journal_refile_buffer(struct journal_head *jh)
 	jh->b_transaction = jh->b_next_transaction;
 	jh->b_next_transaction = NULL;
 	__journal_file_buffer(jh, jh->b_transaction,
-				was_dirty ? BJ_Metadata : BJ_Reserved);
+				jh->b_modified ? BJ_Metadata : BJ_Reserved);
 	J_ASSERT_JH(jh, jh->b_transaction->t_state == T_RUNNING);
 
 	if (was_dirty)
diff --git a/trunk/fs/jbd2/journal.c b/trunk/fs/jbd2/journal.c
index 954cff001df6..eb7eb6c27bcb 100644
--- a/trunk/fs/jbd2/journal.c
+++ b/trunk/fs/jbd2/journal.c
@@ -904,19 +904,10 @@ static void jbd2_stats_proc_init(journal_t *journal)
 	snprintf(name, sizeof(name) - 1, "%s", bdevname(journal->j_dev, name));
 	journal->j_proc_entry = proc_mkdir(name, proc_jbd2_stats);
 	if (journal->j_proc_entry) {
-		struct proc_dir_entry *p;
-		p = create_proc_entry("history", S_IRUGO,
-				journal->j_proc_entry);
-		if (p) {
-			p->proc_fops = &jbd2_seq_history_fops;
-			p->data = journal;
-			p = create_proc_entry("info", S_IRUGO,
-						journal->j_proc_entry);
-			if (p) {
-				p->proc_fops = &jbd2_seq_info_fops;
-				p->data = journal;
-			}
-		}
+		proc_create_data("history", S_IRUGO, journal->j_proc_entry,
+				 &jbd2_seq_history_fops, journal);
+		proc_create_data("info", S_IRUGO, journal->j_proc_entry,
+				 &jbd2_seq_info_fops, journal);
 	}
 }
 
diff --git a/trunk/fs/jfs/jfs_debug.c b/trunk/fs/jfs/jfs_debug.c
index 887f5759e536..bf6ab19b86ee 100644
--- a/trunk/fs/jfs/jfs_debug.c
+++ b/trunk/fs/jfs/jfs_debug.c
@@ -89,7 +89,7 @@ void jfs_proc_init(void)
 {
 	int i;
 
-	if (!(base = proc_mkdir("jfs", proc_root_fs)))
+	if (!(base = proc_mkdir("fs/jfs", NULL)))
 		return;
 	base->owner = THIS_MODULE;
 
@@ -109,7 +109,7 @@ void jfs_proc_clean(void)
 	if (base) {
 		for (i = 0; i < NPROCENT; i++)
 			remove_proc_entry(Entries[i].name, base);
-		remove_proc_entry("jfs", proc_root_fs);
+		remove_proc_entry("fs/jfs", NULL);
 	}
 }
 
diff --git a/trunk/fs/msdos/namei.c b/trunk/fs/msdos/namei.c
index 30f7d0ae2215..2d4358c59f68 100644
--- a/trunk/fs/msdos/namei.c
+++ b/trunk/fs/msdos/namei.c
@@ -653,7 +653,7 @@ static const struct inode_operations msdos_dir_inode_operations = {
 	.mkdir		= msdos_mkdir,
 	.rmdir		= msdos_rmdir,
 	.rename		= msdos_rename,
-	.setattr	= fat_notify_change,
+	.setattr	= fat_setattr,
 	.getattr	= fat_getattr,
 };
 
diff --git a/trunk/fs/namei.c b/trunk/fs/namei.c
index e179f71bfcb0..32fd9655485b 100644
--- a/trunk/fs/namei.c
+++ b/trunk/fs/namei.c
@@ -30,6 +30,7 @@
 #include <linux/capability.h>
 #include <linux/file.h>
 #include <linux/fcntl.h>
+#include <linux/device_cgroup.h>
 #include <asm/namei.h>
 #include <asm/uaccess.h>
 
@@ -281,6 +282,10 @@ int permission(struct inode *inode, int mask, struct nameidata *nd)
 	if (retval)
 		return retval;
 
+	retval = devcgroup_inode_permission(inode, mask);
+	if (retval)
+		return retval;
+
 	return security_inode_permission(inode, mask, nd);
 }
 
@@ -2028,6 +2033,10 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
 	if (!dir->i_op || !dir->i_op->mknod)
 		return -EPERM;
 
+	error = devcgroup_inode_mknod(mode, dev);
+	if (error)
+		return error;
+
 	error = security_inode_mknod(dir, dentry, mode, dev);
 	if (error)
 		return error;
diff --git a/trunk/fs/namespace.c b/trunk/fs/namespace.c
index f48f98110c30..061e5edb4d27 100644
--- a/trunk/fs/namespace.c
+++ b/trunk/fs/namespace.c
@@ -14,7 +14,6 @@
 #include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <linux/quotaops.h>
 #include <linux/acct.h>
 #include <linux/capability.h>
 #include <linux/cpumask.h>
@@ -1084,7 +1083,6 @@ static int do_umount(struct vfsmount *mnt, int flags)
 		down_write(&sb->s_umount);
 		if (!(sb->s_flags & MS_RDONLY)) {
 			lock_kernel();
-			DQUOT_OFF(sb);
 			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
 			unlock_kernel();
 		}
@@ -1178,17 +1176,6 @@ static int mount_is_safe(struct nameidata *nd)
 #endif
 }
 
-static int lives_below_in_same_fs(struct dentry *d, struct dentry *dentry)
-{
-	while (1) {
-		if (d == dentry)
-			return 1;
-		if (d == NULL || d == d->d_parent)
-			return 0;
-		d = d->d_parent;
-	}
-}
-
 struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry,
 					int flag)
 {
@@ -1205,7 +1192,7 @@ struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry,
 
 	p = mnt;
 	list_for_each_entry(r, &mnt->mnt_mounts, mnt_child) {
-		if (!lives_below_in_same_fs(r->mnt_mountpoint, dentry))
+		if (!is_subdir(r->mnt_mountpoint, dentry))
 			continue;
 
 		for (s = r; s; s = next_mnt(s, r)) {
diff --git a/trunk/fs/ncpfs/inode.c b/trunk/fs/ncpfs/inode.c
index fbbb9f7afa1a..2e5ab1204dec 100644
--- a/trunk/fs/ncpfs/inode.c
+++ b/trunk/fs/ncpfs/inode.c
@@ -107,12 +107,6 @@ static const struct super_operations ncp_sops =
 	.show_options	= ncp_show_options,
 };
 
-extern struct dentry_operations ncp_root_dentry_operations;
-#if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS)
-extern const struct address_space_operations ncp_symlink_aops;
-extern int ncp_symlink(struct inode*, struct dentry*, const char*);
-#endif
-
 /*
  * Fill in the ncpfs-specific information in the inode.
  */
diff --git a/trunk/fs/ncpfs/ioctl.c b/trunk/fs/ncpfs/ioctl.c
index ad8f167e54bc..3a97c95e1ca2 100644
--- a/trunk/fs/ncpfs/ioctl.c
+++ b/trunk/fs/ncpfs/ioctl.c
@@ -389,11 +389,11 @@ static int __ncp_ioctl(struct inode *inode, struct file *filp,
 				struct dentry* dentry = inode->i_sb->s_root;
 
 				if (dentry) {
-					struct inode* inode = dentry->d_inode;
+					struct inode* s_inode = dentry->d_inode;
 				
-					if (inode) {
-						sr.volNumber = NCP_FINFO(inode)->volNumber;
-						sr.dirEntNum = NCP_FINFO(inode)->dirEntNum;
+					if (s_inode) {
+						sr.volNumber = NCP_FINFO(s_inode)->volNumber;
+						sr.dirEntNum = NCP_FINFO(s_inode)->dirEntNum;
 						sr.namespace = server->name_space[sr.volNumber];
 					} else
 						DPRINTK("ncpfs: s_root->d_inode==NULL\n");
@@ -439,12 +439,12 @@ static int __ncp_ioctl(struct inode *inode, struct file *filp,
 			dentry = inode->i_sb->s_root;
 			server->root_setuped = 1;
 			if (dentry) {
-				struct inode* inode = dentry->d_inode;
+				struct inode* s_inode = dentry->d_inode;
 				
 				if (inode) {
-					NCP_FINFO(inode)->volNumber = vnum;
-					NCP_FINFO(inode)->dirEntNum = de;
-					NCP_FINFO(inode)->DosDirNum = dosde;
+					NCP_FINFO(s_inode)->volNumber = vnum;
+					NCP_FINFO(s_inode)->dirEntNum = de;
+					NCP_FINFO(s_inode)->DosDirNum = dosde;
 				} else
 					DPRINTK("ncpfs: s_root->d_inode==NULL\n");
 			} else
@@ -519,7 +519,6 @@ static int __ncp_ioctl(struct inode *inode, struct file *filp,
 		}
 		{
 			struct ncp_lock_ioctl	 rqdata;
-			int result;
 
 			if (copy_from_user(&rqdata, argp, sizeof(rqdata)))
 				return -EFAULT;
diff --git a/trunk/fs/ncpfs/ncplib_kernel.c b/trunk/fs/ncpfs/ncplib_kernel.c
index df6d60bdfcd3..97645f112114 100644
--- a/trunk/fs/ncpfs/ncplib_kernel.c
+++ b/trunk/fs/ncpfs/ncplib_kernel.c
@@ -102,48 +102,47 @@ static inline void ncp_init_request_s(struct ncp_server *server, int subfunction
 }
 
 static inline char *
- ncp_reply_data(struct ncp_server *server, int offset)
+ncp_reply_data(struct ncp_server *server, int offset)
 {
 	return &(server->packet[sizeof(struct ncp_reply_header) + offset]);
 }
 
-static inline __u8 BVAL(void* data)
+static inline u8 BVAL(void *data)
 {
-	return get_unaligned((__u8*)data);
+	return *(u8 *)data;
 }
 
-static __u8
- ncp_reply_byte(struct ncp_server *server, int offset)
+static u8 ncp_reply_byte(struct ncp_server *server, int offset)
 {
-	return get_unaligned((__u8 *) ncp_reply_data(server, offset));
+	return *(u8 *)ncp_reply_data(server, offset);
 }
 
-static inline __u16 WVAL_LH(void* data)
+static inline u16 WVAL_LH(void *data)
 {
-	return le16_to_cpu(get_unaligned((__le16*)data));
+	return get_unaligned_le16(data);
 }
 
-static __u16
- ncp_reply_le16(struct ncp_server *server, int offset)
+static u16
+ncp_reply_le16(struct ncp_server *server, int offset)
 {
-	return le16_to_cpu(get_unaligned((__le16 *) ncp_reply_data(server, offset)));
+	return get_unaligned_le16(ncp_reply_data(server, offset));
 }
 
-static __u16
- ncp_reply_be16(struct ncp_server *server, int offset)
+static u16
+ncp_reply_be16(struct ncp_server *server, int offset)
 {
-	return be16_to_cpu(get_unaligned((__be16 *) ncp_reply_data(server, offset)));
+	return get_unaligned_be16(ncp_reply_data(server, offset));
 }
 
-static inline __u32 DVAL_LH(void* data)
+static inline u32 DVAL_LH(void *data)
 {
-	return le32_to_cpu(get_unaligned((__le32*)data));
+	return get_unaligned_le32(data);
 }
 
 static __le32
- ncp_reply_dword(struct ncp_server *server, int offset)
+ncp_reply_dword(struct ncp_server *server, int offset)
 {
-	return get_unaligned((__le32 *) ncp_reply_data(server, offset));
+	return get_unaligned((__le32 *)ncp_reply_data(server, offset));
 }
 
 static inline __u32 ncp_reply_dword_lh(struct ncp_server* server, int offset) {
@@ -1006,8 +1005,8 @@ ncp_read_bounce(struct ncp_server *server, const char *file_id,
 	result = ncp_request2(server, 72, bounce, bufsize);
 	ncp_unlock_server(server);
 	if (!result) {
-		int len = be16_to_cpu(get_unaligned((__be16*)((char*)bounce + 
-			  sizeof(struct ncp_reply_header))));
+		int len = get_unaligned_be16((char *)bounce +
+			  sizeof(struct ncp_reply_header));
 		result = -EIO;
 		if (len <= to_read) {
 			char* source;
diff --git a/trunk/fs/ncpfs/ncpsign_kernel.c b/trunk/fs/ncpfs/ncpsign_kernel.c
index 749a18d33599..7c0b5c21e6cf 100644
--- a/trunk/fs/ncpfs/ncpsign_kernel.c
+++ b/trunk/fs/ncpfs/ncpsign_kernel.c
@@ -55,7 +55,7 @@ static void nwsign(char *r_data1, char *r_data2, char *outdata) {
  unsigned int w0,w1,w2,w3;
  static int rbit[4]={0, 2, 1, 3};
 #ifdef __i386__
- unsigned int *data2=(int *)r_data2;
+ unsigned int *data2=(unsigned int *)r_data2;
 #else
  unsigned int data2[16];
  for (i=0;i<16;i++)
diff --git a/trunk/fs/nfs/client.c b/trunk/fs/nfs/client.c
index f2f3b284e6dd..89ac5bb0401c 100644
--- a/trunk/fs/nfs/client.c
+++ b/trunk/fs/nfs/client.c
@@ -1321,6 +1321,7 @@ static const struct file_operations nfs_server_list_fops = {
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release,
+	.owner		= THIS_MODULE,
 };
 
 static int nfs_volume_list_open(struct inode *inode, struct file *file);
@@ -1341,6 +1342,7 @@ static const struct file_operations nfs_volume_list_fops = {
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release,
+	.owner		= THIS_MODULE,
 };
 
 /*
@@ -1500,33 +1502,29 @@ int __init nfs_fs_proc_init(void)
 {
 	struct proc_dir_entry *p;
 
-	proc_fs_nfs = proc_mkdir("nfsfs", proc_root_fs);
+	proc_fs_nfs = proc_mkdir("fs/nfsfs", NULL);
 	if (!proc_fs_nfs)
 		goto error_0;
 
 	proc_fs_nfs->owner = THIS_MODULE;
 
 	/* a file of servers with which we're dealing */
-	p = create_proc_entry("servers", S_IFREG|S_IRUGO, proc_fs_nfs);
+	p = proc_create("servers", S_IFREG|S_IRUGO,
+			proc_fs_nfs, &nfs_server_list_fops);
 	if (!p)
 		goto error_1;
 
-	p->proc_fops = &nfs_server_list_fops;
-	p->owner = THIS_MODULE;
-
 	/* a file of volumes that we have mounted */
-	p = create_proc_entry("volumes", S_IFREG|S_IRUGO, proc_fs_nfs);
+	p = proc_create("volumes", S_IFREG|S_IRUGO,
+			proc_fs_nfs, &nfs_volume_list_fops);
 	if (!p)
 		goto error_2;
-
-	p->proc_fops = &nfs_volume_list_fops;
-	p->owner = THIS_MODULE;
 	return 0;
 
 error_2:
 	remove_proc_entry("servers", proc_fs_nfs);
 error_1:
-	remove_proc_entry("nfsfs", proc_root_fs);
+	remove_proc_entry("fs/nfsfs", NULL);
 error_0:
 	return -ENOMEM;
 }
@@ -1538,7 +1536,7 @@ void nfs_fs_proc_exit(void)
 {
 	remove_proc_entry("volumes", proc_fs_nfs);
 	remove_proc_entry("servers", proc_fs_nfs);
-	remove_proc_entry("nfsfs", proc_root_fs);
+	remove_proc_entry("fs/nfsfs", NULL);
 }
 
 #endif /* CONFIG_PROC_FS */
diff --git a/trunk/fs/nfsd/nfsctl.c b/trunk/fs/nfsd/nfsctl.c
index 42f3820ee8f5..5ac00c4fee91 100644
--- a/trunk/fs/nfsd/nfsctl.c
+++ b/trunk/fs/nfsd/nfsctl.c
@@ -169,6 +169,7 @@ static const struct file_operations exports_operations = {
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release,
+	.owner		= THIS_MODULE,
 };
 
 /*----------------------------------------------------------------------------*/
@@ -801,10 +802,9 @@ static int create_proc_exports_entry(void)
 	entry = proc_mkdir("fs/nfs", NULL);
 	if (!entry)
 		return -ENOMEM;
-	entry = create_proc_entry("fs/nfs/exports", 0, NULL);
+	entry = proc_create("exports", 0, entry, &exports_operations);
 	if (!entry)
 		return -ENOMEM;
-	entry->proc_fops =  &exports_operations;
 	return 0;
 }
 #else /* CONFIG_PROC_FS */
diff --git a/trunk/fs/ntfs/mft.c b/trunk/fs/ntfs/mft.c
index 2ad5c8b104b9..790defb847e7 100644
--- a/trunk/fs/ntfs/mft.c
+++ b/trunk/fs/ntfs/mft.c
@@ -1191,7 +1191,7 @@ static int ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(ntfs_volume *vol,
 		if (size) {
 			page = ntfs_map_page(mftbmp_mapping,
 					ofs >> PAGE_CACHE_SHIFT);
-			if (unlikely(IS_ERR(page))) {
+			if (IS_ERR(page)) {
 				ntfs_error(vol->sb, "Failed to read mft "
 						"bitmap, aborting.");
 				return PTR_ERR(page);
@@ -2118,7 +2118,7 @@ static int ntfs_mft_record_format(const ntfs_volume *vol, const s64 mft_no)
 	}
 	/* Read, map, and pin the page containing the mft record. */
 	page = ntfs_map_page(mft_vi->i_mapping, index);
-	if (unlikely(IS_ERR(page))) {
+	if (IS_ERR(page)) {
 		ntfs_error(vol->sb, "Failed to map page containing mft record "
 				"to format 0x%llx.", (long long)mft_no);
 		return PTR_ERR(page);
@@ -2519,7 +2519,7 @@ ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
 	ofs = (bit << vol->mft_record_size_bits) & ~PAGE_CACHE_MASK;
 	/* Read, map, and pin the page containing the mft record. */
 	page = ntfs_map_page(vol->mft_ino->i_mapping, index);
-	if (unlikely(IS_ERR(page))) {
+	if (IS_ERR(page)) {
 		ntfs_error(vol->sb, "Failed to map page containing allocated "
 				"mft record 0x%llx.", (long long)bit);
 		err = PTR_ERR(page);
diff --git a/trunk/fs/open.c b/trunk/fs/open.c
index b70e7666bb2c..7af1f05d5978 100644
--- a/trunk/fs/open.c
+++ b/trunk/fs/open.c
@@ -837,7 +837,7 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 	if (f->f_flags & O_DIRECT) {
 		if (!f->f_mapping->a_ops ||
 		    ((!f->f_mapping->a_ops->direct_IO) &&
-		    (!f->f_mapping->a_ops->get_xip_page))) {
+		    (!f->f_mapping->a_ops->get_xip_mem))) {
 			fput(f);
 			f = ERR_PTR(-EINVAL);
 		}
diff --git a/trunk/fs/partitions/msdos.c b/trunk/fs/partitions/msdos.c
index 5567ec0d03a3..796511886f28 100644
--- a/trunk/fs/partitions/msdos.c
+++ b/trunk/fs/partitions/msdos.c
@@ -18,7 +18,7 @@
  *
  *  Re-organised Feb 1998 Russell King
  */
-
+#include <linux/msdos_fs.h>
 
 #include "check.h"
 #include "msdos.h"
@@ -419,6 +419,7 @@ int msdos_partition(struct parsed_partitions *state, struct block_device *bdev)
 	Sector sect;
 	unsigned char *data;
 	struct partition *p;
+	struct fat_boot_sector *fb;
 	int slot;
 
 	data = read_dev_sector(bdev, 0, &sect);
@@ -444,8 +445,21 @@ int msdos_partition(struct parsed_partitions *state, struct block_device *bdev)
 	p = (struct partition *) (data + 0x1be);
 	for (slot = 1; slot <= 4; slot++, p++) {
 		if (p->boot_ind != 0 && p->boot_ind != 0x80) {
-			put_dev_sector(sect);
-			return 0;
+			/*
+			 * Even without a valid boot inidicator value
+			 * its still possible this is valid FAT filesystem
+			 * without a partition table.
+			 */
+			fb = (struct fat_boot_sector *) data;
+			if (slot == 1 && fb->reserved && fb->fats
+				&& fat_valid_media(fb->media)) {
+				printk("\n");
+				put_dev_sector(sect);
+				return 1;
+			} else {
+				put_dev_sector(sect);
+				return 0;
+			}
 		}
 	}
 
diff --git a/trunk/fs/proc/base.c b/trunk/fs/proc/base.c
index c5e412a00b17..fcf02f2deeba 100644
--- a/trunk/fs/proc/base.c
+++ b/trunk/fs/proc/base.c
@@ -195,12 +195,32 @@ static int proc_root_link(struct inode *inode, struct path *path)
 	return result;
 }
 
-#define MAY_PTRACE(task) \
-	(task == current || \
-	(task->parent == current && \
-	(task->ptrace & PT_PTRACED) && \
-	 (task_is_stopped_or_traced(task)) && \
-	 security_ptrace(current,task) == 0))
+/*
+ * Return zero if current may access user memory in @task, -error if not.
+ */
+static int check_mem_permission(struct task_struct *task)
+{
+	/*
+	 * A task can always look at itself, in case it chooses
+	 * to use system calls instead of load instructions.
+	 */
+	if (task == current)
+		return 0;
+
+	/*
+	 * If current is actively ptrace'ing, and would also be
+	 * permitted to freshly attach with ptrace now, permit it.
+	 */
+	if (task->parent == current && (task->ptrace & PT_PTRACED) &&
+	    task_is_stopped_or_traced(task) &&
+	    ptrace_may_attach(task))
+		return 0;
+
+	/*
+	 * Noone else is allowed.
+	 */
+	return -EPERM;
+}
 
 struct mm_struct *mm_for_maps(struct task_struct *task)
 {
@@ -722,7 +742,7 @@ static ssize_t mem_read(struct file * file, char __user * buf,
 	if (!task)
 		goto out_no_task;
 
-	if (!MAY_PTRACE(task) || !ptrace_may_attach(task))
+	if (check_mem_permission(task))
 		goto out;
 
 	ret = -ENOMEM;
@@ -748,7 +768,7 @@ static ssize_t mem_read(struct file * file, char __user * buf,
 
 		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
 		retval = access_process_vm(task, src, page, this_len, 0);
-		if (!retval || !MAY_PTRACE(task) || !ptrace_may_attach(task)) {
+		if (!retval || check_mem_permission(task)) {
 			if (!ret)
 				ret = -EIO;
 			break;
@@ -792,7 +812,7 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
 	if (!task)
 		goto out_no_task;
 
-	if (!MAY_PTRACE(task) || !ptrace_may_attach(task))
+	if (check_mem_permission(task))
 		goto out;
 
 	copied = -ENOMEM;
@@ -1181,6 +1201,81 @@ static const struct file_operations proc_pid_sched_operations = {
 
 #endif
 
+/*
+ * We added or removed a vma mapping the executable. The vmas are only mapped
+ * during exec and are not mapped with the mmap system call.
+ * Callers must hold down_write() on the mm's mmap_sem for these
+ */
+void added_exe_file_vma(struct mm_struct *mm)
+{
+	mm->num_exe_file_vmas++;
+}
+
+void removed_exe_file_vma(struct mm_struct *mm)
+{
+	mm->num_exe_file_vmas--;
+	if ((mm->num_exe_file_vmas == 0) && mm->exe_file){
+		fput(mm->exe_file);
+		mm->exe_file = NULL;
+	}
+
+}
+
+void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
+{
+	if (new_exe_file)
+		get_file(new_exe_file);
+	if (mm->exe_file)
+		fput(mm->exe_file);
+	mm->exe_file = new_exe_file;
+	mm->num_exe_file_vmas = 0;
+}
+
+struct file *get_mm_exe_file(struct mm_struct *mm)
+{
+	struct file *exe_file;
+
+	/* We need mmap_sem to protect against races with removal of
+	 * VM_EXECUTABLE vmas */
+	down_read(&mm->mmap_sem);
+	exe_file = mm->exe_file;
+	if (exe_file)
+		get_file(exe_file);
+	up_read(&mm->mmap_sem);
+	return exe_file;
+}
+
+void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm)
+{
+	/* It's safe to write the exe_file pointer without exe_file_lock because
+	 * this is called during fork when the task is not yet in /proc */
+	newmm->exe_file = get_mm_exe_file(oldmm);
+}
+
+static int proc_exe_link(struct inode *inode, struct path *exe_path)
+{
+	struct task_struct *task;
+	struct mm_struct *mm;
+	struct file *exe_file;
+
+	task = get_proc_task(inode);
+	if (!task)
+		return -ENOENT;
+	mm = get_task_mm(task);
+	put_task_struct(task);
+	if (!mm)
+		return -ENOENT;
+	exe_file = get_mm_exe_file(mm);
+	mmput(mm);
+	if (exe_file) {
+		*exe_path = exe_file->f_path;
+		path_get(&exe_file->f_path);
+		fput(exe_file);
+		return 0;
+	} else
+		return -ENOENT;
+}
+
 static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
 	struct inode *inode = dentry->d_inode;
diff --git a/trunk/fs/proc/generic.c b/trunk/fs/proc/generic.c
index a36ad3c75cf4..9d53b39a9cf8 100644
--- a/trunk/fs/proc/generic.c
+++ b/trunk/fs/proc/generic.c
@@ -69,12 +69,7 @@ proc_file_read(struct file *file, char __user *buf, size_t nbytes,
 		count = min_t(size_t, PROC_BLOCK_SIZE, nbytes);
 
 		start = NULL;
-		if (dp->get_info) {
-			/* Handle old net routines */
-			n = dp->get_info(page, &start, *ppos, count);
-			if (n < count)
-				eof = 1;
-		} else if (dp->read_proc) {
+		if (dp->read_proc) {
 			/*
 			 * How to be a proc read function
 			 * ------------------------------
@@ -277,8 +272,11 @@ static int xlate_proc_name(const char *name,
 	int			len;
 	int 			rtn = 0;
 
+	de = *ret;
+	if (!de)
+		de = &proc_root;
+
 	spin_lock(&proc_subdir_lock);
-	de = &proc_root;
 	while (1) {
 		next = strchr(cp, '/');
 		if (!next)
@@ -385,20 +383,18 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
 
 	lock_kernel();
 	spin_lock(&proc_subdir_lock);
-	if (de) {
-		for (de = de->subdir; de ; de = de->next) {
-			if (de->namelen != dentry->d_name.len)
-				continue;
-			if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
-				unsigned int ino;
+	for (de = de->subdir; de ; de = de->next) {
+		if (de->namelen != dentry->d_name.len)
+			continue;
+		if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
+			unsigned int ino;
 
-				ino = de->low_ino;
-				de_get(de);
-				spin_unlock(&proc_subdir_lock);
-				error = -EINVAL;
-				inode = proc_get_inode(dir->i_sb, ino, de);
-				goto out_unlock;
-			}
+			ino = de->low_ino;
+			de_get(de);
+			spin_unlock(&proc_subdir_lock);
+			error = -EINVAL;
+			inode = proc_get_inode(dir->i_sb, ino, de);
+			goto out_unlock;
 		}
 	}
 	spin_unlock(&proc_subdir_lock);
@@ -410,7 +406,8 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
 		d_add(dentry, inode);
 		return NULL;
 	}
-	de_put(de);
+	if (de)
+		de_put(de);
 	return ERR_PTR(error);
 }
 
@@ -440,10 +437,6 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,
 	lock_kernel();
 
 	ino = inode->i_ino;
-	if (!de) {
-		ret = -EINVAL;
-		goto out;
-	}
 	i = filp->f_pos;
 	switch (i) {
 		case 0:
@@ -582,7 +575,7 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
 	/* make sure name is valid */
 	if (!name || !strlen(name)) goto out;
 
-	if (!(*parent) && xlate_proc_name(name, parent, &fn) != 0)
+	if (xlate_proc_name(name, parent, &fn) != 0)
 		goto out;
 
 	/* At this point there must not be any '/' characters beyond *fn */
@@ -682,9 +675,10 @@ struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode,
 	return ent;
 }
 
-struct proc_dir_entry *proc_create(const char *name, mode_t mode,
-				   struct proc_dir_entry *parent,
-				   const struct file_operations *proc_fops)
+struct proc_dir_entry *proc_create_data(const char *name, mode_t mode,
+					struct proc_dir_entry *parent,
+					const struct file_operations *proc_fops,
+					void *data)
 {
 	struct proc_dir_entry *pde;
 	nlink_t nlink;
@@ -705,6 +699,7 @@ struct proc_dir_entry *proc_create(const char *name, mode_t mode,
 	if (!pde)
 		goto out;
 	pde->proc_fops = proc_fops;
+	pde->data = data;
 	if (proc_register(parent, pde) < 0)
 		goto out_free;
 	return pde;
@@ -734,55 +729,58 @@ void free_proc_entry(struct proc_dir_entry *de)
 void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 {
 	struct proc_dir_entry **p;
-	struct proc_dir_entry *de;
+	struct proc_dir_entry *de = NULL;
 	const char *fn = name;
 	int len;
 
-	if (!parent && xlate_proc_name(name, &parent, &fn) != 0)
-		goto out;
+	if (xlate_proc_name(name, &parent, &fn) != 0)
+		return;
 	len = strlen(fn);
 
 	spin_lock(&proc_subdir_lock);
 	for (p = &parent->subdir; *p; p=&(*p)->next ) {
-		if (!proc_match(len, fn, *p))
-			continue;
-		de = *p;
-		*p = de->next;
-		de->next = NULL;
-
-		spin_lock(&de->pde_unload_lock);
-		/*
-		 * Stop accepting new callers into module. If you're
-		 * dynamically allocating ->proc_fops, save a pointer somewhere.
-		 */
-		de->proc_fops = NULL;
-		/* Wait until all existing callers into module are done. */
-		if (de->pde_users > 0) {
-			DECLARE_COMPLETION_ONSTACK(c);
-
-			if (!de->pde_unload_completion)
-				de->pde_unload_completion = &c;
-
-			spin_unlock(&de->pde_unload_lock);
-			spin_unlock(&proc_subdir_lock);
+		if (proc_match(len, fn, *p)) {
+			de = *p;
+			*p = de->next;
+			de->next = NULL;
+			break;
+		}
+	}
+	spin_unlock(&proc_subdir_lock);
+	if (!de)
+		return;
 
-			wait_for_completion(de->pde_unload_completion);
+	spin_lock(&de->pde_unload_lock);
+	/*
+	 * Stop accepting new callers into module. If you're
+	 * dynamically allocating ->proc_fops, save a pointer somewhere.
+	 */
+	de->proc_fops = NULL;
+	/* Wait until all existing callers into module are done. */
+	if (de->pde_users > 0) {
+		DECLARE_COMPLETION_ONSTACK(c);
+
+		if (!de->pde_unload_completion)
+			de->pde_unload_completion = &c;
 
-			spin_lock(&proc_subdir_lock);
-			goto continue_removing;
-		}
 		spin_unlock(&de->pde_unload_lock);
 
+		wait_for_completion(de->pde_unload_completion);
+
+		goto continue_removing;
+	}
+	spin_unlock(&de->pde_unload_lock);
+
 continue_removing:
-		if (S_ISDIR(de->mode))
-			parent->nlink--;
-		de->nlink = 0;
-		WARN_ON(de->subdir);
-		if (atomic_dec_and_test(&de->count))
-			free_proc_entry(de);
-		break;
+	if (S_ISDIR(de->mode))
+		parent->nlink--;
+	de->nlink = 0;
+	if (de->subdir) {
+		printk(KERN_WARNING "%s: removing non-empty directory "
+			"'%s/%s', leaking at least '%s'\n", __func__,
+			de->parent->name, de->name, de->subdir->name);
+		WARN_ON(1);
 	}
-	spin_unlock(&proc_subdir_lock);
-out:
-	return;
+	if (atomic_dec_and_test(&de->count))
+		free_proc_entry(de);
 }
diff --git a/trunk/fs/proc/inode.c b/trunk/fs/proc/inode.c
index 82b3a1b5a70b..6f4e8dc97da1 100644
--- a/trunk/fs/proc/inode.c
+++ b/trunk/fs/proc/inode.c
@@ -25,8 +25,7 @@
 
 struct proc_dir_entry *de_get(struct proc_dir_entry *de)
 {
-	if (de)
-		atomic_inc(&de->count);
+	atomic_inc(&de->count);
 	return de;
 }
 
@@ -35,18 +34,16 @@ struct proc_dir_entry *de_get(struct proc_dir_entry *de)
  */
 void de_put(struct proc_dir_entry *de)
 {
-	if (de) {	
-		lock_kernel();		
-		if (!atomic_read(&de->count)) {
-			printk("de_put: entry %s already free!\n", de->name);
-			unlock_kernel();
-			return;
-		}
-
-		if (atomic_dec_and_test(&de->count))
-			free_proc_entry(de);
+	lock_kernel();
+	if (!atomic_read(&de->count)) {
+		printk("de_put: entry %s already free!\n", de->name);
 		unlock_kernel();
+		return;
 	}
+
+	if (atomic_dec_and_test(&de->count))
+		free_proc_entry(de);
+	unlock_kernel();
 }
 
 /*
@@ -392,7 +389,7 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
 {
 	struct inode * inode;
 
-	if (de != NULL && !try_module_get(de->owner))
+	if (!try_module_get(de->owner))
 		goto out_mod;
 
 	inode = iget_locked(sb, ino);
@@ -402,30 +399,29 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
 		inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 		PROC_I(inode)->fd = 0;
 		PROC_I(inode)->pde = de;
-		if (de) {
-			if (de->mode) {
-				inode->i_mode = de->mode;
-				inode->i_uid = de->uid;
-				inode->i_gid = de->gid;
-			}
-			if (de->size)
-				inode->i_size = de->size;
-			if (de->nlink)
-				inode->i_nlink = de->nlink;
-			if (de->proc_iops)
-				inode->i_op = de->proc_iops;
-			if (de->proc_fops) {
-				if (S_ISREG(inode->i_mode)) {
+
+		if (de->mode) {
+			inode->i_mode = de->mode;
+			inode->i_uid = de->uid;
+			inode->i_gid = de->gid;
+		}
+		if (de->size)
+			inode->i_size = de->size;
+		if (de->nlink)
+			inode->i_nlink = de->nlink;
+		if (de->proc_iops)
+			inode->i_op = de->proc_iops;
+		if (de->proc_fops) {
+			if (S_ISREG(inode->i_mode)) {
 #ifdef CONFIG_COMPAT
-					if (!de->proc_fops->compat_ioctl)
-						inode->i_fop =
-							&proc_reg_file_ops_no_compat;
-					else
+				if (!de->proc_fops->compat_ioctl)
+					inode->i_fop =
+						&proc_reg_file_ops_no_compat;
+				else
 #endif
-						inode->i_fop = &proc_reg_file_ops;
-				} else {
-					inode->i_fop = de->proc_fops;
-				}
+					inode->i_fop = &proc_reg_file_ops;
+			} else {
+				inode->i_fop = de->proc_fops;
 			}
 		}
 		unlock_new_inode(inode);
@@ -433,8 +429,7 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
 	return inode;
 
 out_ino:
-	if (de != NULL)
-		module_put(de->owner);
+	module_put(de->owner);
 out_mod:
 	return NULL;
 }			
diff --git a/trunk/fs/proc/internal.h b/trunk/fs/proc/internal.h
index bc72f5c8c47d..28cbca805905 100644
--- a/trunk/fs/proc/internal.h
+++ b/trunk/fs/proc/internal.h
@@ -11,6 +11,7 @@
 
 #include <linux/proc_fs.h>
 
+extern struct proc_dir_entry proc_root;
 #ifdef CONFIG_PROC_SYSCTL
 extern int proc_sys_init(void);
 #else
@@ -46,9 +47,6 @@ extern int nommu_vma_show(struct seq_file *, struct vm_area_struct *);
 
 extern int maps_protect;
 
-extern void create_seq_entry(char *name, mode_t mode,
-				const struct file_operations *f);
-extern int proc_exe_link(struct inode *, struct path *);
 extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *task);
 extern int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
diff --git a/trunk/fs/proc/nommu.c b/trunk/fs/proc/nommu.c
index 941e95114b5a..79ecd281d2cb 100644
--- a/trunk/fs/proc/nommu.c
+++ b/trunk/fs/proc/nommu.c
@@ -137,7 +137,7 @@ static const struct file_operations proc_nommu_vma_list_operations = {
 
 static int __init proc_nommu_init(void)
 {
-	create_seq_entry("maps", S_IRUGO, &proc_nommu_vma_list_operations);
+	proc_create("maps", S_IRUGO, NULL, &proc_nommu_vma_list_operations);
 	return 0;
 }
 
diff --git a/trunk/fs/proc/proc_misc.c b/trunk/fs/proc/proc_misc.c
index 2d563979cb02..48bcf20cec2f 100644
--- a/trunk/fs/proc/proc_misc.c
+++ b/trunk/fs/proc/proc_misc.c
@@ -456,6 +456,20 @@ static const struct file_operations proc_slabstats_operations = {
 #endif
 #endif
 
+#ifdef CONFIG_MMU
+static int vmalloc_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &vmalloc_op);
+}
+
+static const struct file_operations proc_vmalloc_operations = {
+	.open		= vmalloc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+#endif
+
 static int show_stat(struct seq_file *p, void *v)
 {
 	int i;
@@ -812,14 +826,6 @@ static struct file_operations proc_kpageflags_operations = {
 
 struct proc_dir_entry *proc_root_kcore;
 
-void create_seq_entry(char *name, mode_t mode, const struct file_operations *f)
-{
-	struct proc_dir_entry *entry;
-	entry = create_proc_entry(name, mode, NULL);
-	if (entry)
-		entry->proc_fops = f;
-}
-
 void __init proc_misc_init(void)
 {
 	static struct {
@@ -848,63 +854,52 @@ void __init proc_misc_init(void)
 
 	/* And now for trickier ones */
 #ifdef CONFIG_PRINTK
-	{
-		struct proc_dir_entry *entry;
-		entry = create_proc_entry("kmsg", S_IRUSR, &proc_root);
-		if (entry)
-			entry->proc_fops = &proc_kmsg_operations;
-	}
+	proc_create("kmsg", S_IRUSR, NULL, &proc_kmsg_operations);
 #endif
-	create_seq_entry("locks", 0, &proc_locks_operations);
-	create_seq_entry("devices", 0, &proc_devinfo_operations);
-	create_seq_entry("cpuinfo", 0, &proc_cpuinfo_operations);
+	proc_create("locks", 0, NULL, &proc_locks_operations);
+	proc_create("devices", 0, NULL, &proc_devinfo_operations);
+	proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations);
 #ifdef CONFIG_BLOCK
-	create_seq_entry("partitions", 0, &proc_partitions_operations);
+	proc_create("partitions", 0, NULL, &proc_partitions_operations);
 #endif
-	create_seq_entry("stat", 0, &proc_stat_operations);
-	create_seq_entry("interrupts", 0, &proc_interrupts_operations);
+	proc_create("stat", 0, NULL, &proc_stat_operations);
+	proc_create("interrupts", 0, NULL, &proc_interrupts_operations);
 #ifdef CONFIG_SLABINFO
-	create_seq_entry("slabinfo",S_IWUSR|S_IRUGO,&proc_slabinfo_operations);
+	proc_create("slabinfo",S_IWUSR|S_IRUGO,NULL,&proc_slabinfo_operations);
 #ifdef CONFIG_DEBUG_SLAB_LEAK
-	create_seq_entry("slab_allocators", 0 ,&proc_slabstats_operations);
+	proc_create("slab_allocators", 0, NULL, &proc_slabstats_operations);
+#endif
 #endif
+#ifdef CONFIG_MMU
+	proc_create("vmallocinfo", S_IRUSR, NULL, &proc_vmalloc_operations);
 #endif
-	create_seq_entry("buddyinfo",S_IRUGO, &fragmentation_file_operations);
-	create_seq_entry("pagetypeinfo", S_IRUGO, &pagetypeinfo_file_ops);
-	create_seq_entry("vmstat",S_IRUGO, &proc_vmstat_file_operations);
-	create_seq_entry("zoneinfo",S_IRUGO, &proc_zoneinfo_file_operations);
+	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
+	proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
+	proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
+	proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
 #ifdef CONFIG_BLOCK
-	create_seq_entry("diskstats", 0, &proc_diskstats_operations);
+	proc_create("diskstats", 0, NULL, &proc_diskstats_operations);
 #endif
 #ifdef CONFIG_MODULES
-	create_seq_entry("modules", 0, &proc_modules_operations);
+	proc_create("modules", 0, NULL, &proc_modules_operations);
 #endif
 #ifdef CONFIG_SCHEDSTATS
-	create_seq_entry("schedstat", 0, &proc_schedstat_operations);
+	proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
 #endif
 #ifdef CONFIG_PROC_KCORE
-	proc_root_kcore = create_proc_entry("kcore", S_IRUSR, NULL);
-	if (proc_root_kcore) {
-		proc_root_kcore->proc_fops = &proc_kcore_operations;
+	proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &proc_kcore_operations);
+	if (proc_root_kcore)
 		proc_root_kcore->size =
 				(size_t)high_memory - PAGE_OFFSET + PAGE_SIZE;
-	}
 #endif
 #ifdef CONFIG_PROC_PAGE_MONITOR
-	create_seq_entry("kpagecount", S_IRUSR, &proc_kpagecount_operations);
-	create_seq_entry("kpageflags", S_IRUSR, &proc_kpageflags_operations);
+	proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);
+	proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations);
 #endif
 #ifdef CONFIG_PROC_VMCORE
-	proc_vmcore = create_proc_entry("vmcore", S_IRUSR, NULL);
-	if (proc_vmcore)
-		proc_vmcore->proc_fops = &proc_vmcore_operations;
+	proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations);
 #endif
 #ifdef CONFIG_MAGIC_SYSRQ
-	{
-		struct proc_dir_entry *entry;
-		entry = create_proc_entry("sysrq-trigger", S_IWUSR, NULL);
-		if (entry)
-			entry->proc_fops = &proc_sysrq_trigger_operations;
-	}
+	proc_create("sysrq-trigger", S_IWUSR, NULL, &proc_sysrq_trigger_operations);
 #endif
 }
diff --git a/trunk/fs/proc/proc_sysctl.c b/trunk/fs/proc/proc_sysctl.c
index 614c34b6d1c2..5acc001d49f6 100644
--- a/trunk/fs/proc/proc_sysctl.c
+++ b/trunk/fs/proc/proc_sysctl.c
@@ -165,8 +165,8 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
 	return err;
 }
 
-static ssize_t proc_sys_read(struct file *filp, char __user *buf,
-				size_t count, loff_t *ppos)
+static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
+		size_t count, loff_t *ppos, int write)
 {
 	struct dentry *dentry = filp->f_dentry;
 	struct ctl_table_header *head;
@@ -190,12 +190,12 @@ static ssize_t proc_sys_read(struct file *filp, char __user *buf,
 	 * and won't be until we finish.
 	 */
 	error = -EPERM;
-	if (sysctl_perm(table, MAY_READ))
+	if (sysctl_perm(head->root, table, write ? MAY_WRITE : MAY_READ))
 		goto out;
 
 	/* careful: calling conventions are nasty here */
 	res = count;
-	error = table->proc_handler(table, 0, filp, buf, &res, ppos);
+	error = table->proc_handler(table, write, filp, buf, &res, ppos);
 	if (!error)
 		error = res;
 out:
@@ -204,44 +204,16 @@ static ssize_t proc_sys_read(struct file *filp, char __user *buf,
 	return error;
 }
 
-static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
+static ssize_t proc_sys_read(struct file *filp, char __user *buf,
 				size_t count, loff_t *ppos)
 {
-	struct dentry *dentry = filp->f_dentry;
-	struct ctl_table_header *head;
-	struct ctl_table *table;
-	ssize_t error;
-	size_t res;
-
-	table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
-	/* Has the sysctl entry disappeared on us? */
-	error = -ENOENT;
-	if (!table)
-		goto out;
-
-	/* Has the sysctl entry been replaced by a directory? */
-	error = -EISDIR;
-	if (!table->proc_handler)
-		goto out;
-
-	/*
-	 * At this point we know that the sysctl was not unregistered
-	 * and won't be until we finish.
-	 */
-	error = -EPERM;
-	if (sysctl_perm(table, MAY_WRITE))
-		goto out;
-
-	/* careful: calling conventions are nasty here */
-	res = count;
-	error = table->proc_handler(table, 1, filp, (char __user *)buf,
-				    &res, ppos);
-	if (!error)
-		error = res;
-out:
-	sysctl_head_finish(head);
+	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0);
+}
 
-	return error;
+static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1);
 }
 
 
@@ -416,7 +388,7 @@ static int proc_sys_permission(struct inode *inode, int mask, struct nameidata *
 		goto out;
 
 	/* Use the permissions on the sysctl table entry */
-	error = sysctl_perm(table, mask);
+	error = sysctl_perm(head->root, table, mask);
 out:
 	sysctl_head_finish(head);
 	return error;
diff --git a/trunk/fs/proc/proc_tty.c b/trunk/fs/proc/proc_tty.c
index 49816e00b51a..ac26ccc25f42 100644
--- a/trunk/fs/proc/proc_tty.c
+++ b/trunk/fs/proc/proc_tty.c
@@ -5,7 +5,7 @@
  */
 
 #include <asm/uaccess.h>
-
+#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/time.h>
@@ -136,39 +136,54 @@ static const struct file_operations proc_tty_drivers_operations = {
 	.release	= seq_release,
 };
 
-/*
- * This is the handler for /proc/tty/ldiscs
- */
-static int tty_ldiscs_read_proc(char *page, char **start, off_t off,
-				int count, int *eof, void *data)
+static void * tty_ldiscs_seq_start(struct seq_file *m, loff_t *pos)
 {
-	int	i;
-	int	len = 0;
-	off_t	begin = 0;
+	return (*pos < NR_LDISCS) ? pos : NULL;
+}
+
+static void * tty_ldiscs_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return (*pos < NR_LDISCS) ? pos : NULL;
+}
+
+static void tty_ldiscs_seq_stop(struct seq_file *m, void *v)
+{
+}
+
+static int tty_ldiscs_seq_show(struct seq_file *m, void *v)
+{
+	int i = *(loff_t *)v;
 	struct tty_ldisc *ld;
 	
-	for (i=0; i < NR_LDISCS; i++) {
-		ld = tty_ldisc_get(i);
-		if (ld == NULL)
-			continue;
-		len += sprintf(page+len, "%-10s %2d\n",
-			       ld->name ? ld->name : "???", i);
-		tty_ldisc_put(i);
-		if (len+begin > off+count)
-			break;
-		if (len+begin < off) {
-			begin += len;
-			len = 0;
-		}
-	}
-	if (i >= NR_LDISCS)
-		*eof = 1;
-	if (off >= len+begin)
+	ld = tty_ldisc_get(i);
+	if (ld == NULL)
 		return 0;
-	*start = page + (off-begin);
-	return ((count < begin+len-off) ? count : begin+len-off);
+	seq_printf(m, "%-10s %2d\n", ld->name ? ld->name : "???", i);
+	tty_ldisc_put(i);
+	return 0;
+}
+
+static const struct seq_operations tty_ldiscs_seq_ops = {
+	.start	= tty_ldiscs_seq_start,
+	.next	= tty_ldiscs_seq_next,
+	.stop	= tty_ldiscs_seq_stop,
+	.show	= tty_ldiscs_seq_show,
+};
+
+static int proc_tty_ldiscs_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &tty_ldiscs_seq_ops);
 }
 
+static const struct file_operations tty_ldiscs_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= proc_tty_ldiscs_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
 /*
  * This function is called by tty_register_driver() to handle
  * registering the driver's /proc handler into /proc/tty/driver/<foo>
@@ -214,7 +229,6 @@ void proc_tty_unregister_driver(struct tty_driver *driver)
  */
 void __init proc_tty_init(void)
 {
-	struct proc_dir_entry *entry;
 	if (!proc_mkdir("tty", NULL))
 		return;
 	proc_tty_ldisc = proc_mkdir("tty/ldisc", NULL);
@@ -224,10 +238,7 @@ void __init proc_tty_init(void)
 	 * password lengths and inter-keystroke timings during password
 	 * entry.
 	 */
-	proc_tty_driver = proc_mkdir_mode("tty/driver", S_IRUSR | S_IXUSR, NULL);
-
-	create_proc_read_entry("tty/ldiscs", 0, NULL, tty_ldiscs_read_proc, NULL);
-	entry = create_proc_entry("tty/drivers", 0, NULL);
-	if (entry)
-		entry->proc_fops = &proc_tty_drivers_operations;
+	proc_tty_driver = proc_mkdir_mode("tty/driver", S_IRUSR|S_IXUSR, NULL);
+	proc_create("tty/ldiscs", 0, NULL, &tty_ldiscs_proc_fops);
+	proc_create("tty/drivers", 0, NULL, &proc_tty_drivers_operations);
 }
diff --git a/trunk/fs/proc/root.c b/trunk/fs/proc/root.c
index ef0fb57fc9ef..95117538a4f6 100644
--- a/trunk/fs/proc/root.c
+++ b/trunk/fs/proc/root.c
@@ -22,8 +22,6 @@
 
 #include "internal.h"
 
-struct proc_dir_entry *proc_bus, *proc_root_fs, *proc_root_driver;
-
 static int proc_test_super(struct super_block *sb, void *data)
 {
 	return sb->s_fs_info == data;
@@ -126,8 +124,8 @@ void __init proc_root_init(void)
 #ifdef CONFIG_SYSVIPC
 	proc_mkdir("sysvipc", NULL);
 #endif
-	proc_root_fs = proc_mkdir("fs", NULL);
-	proc_root_driver = proc_mkdir("driver", NULL);
+	proc_mkdir("fs", NULL);
+	proc_mkdir("driver", NULL);
 	proc_mkdir("fs/nfsd", NULL); /* somewhere for the nfsd filesystem to be mounted */
 #if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
 	/* just give it a mountpoint */
@@ -137,7 +135,7 @@ void __init proc_root_init(void)
 #ifdef CONFIG_PROC_DEVICETREE
 	proc_device_tree_init();
 #endif
-	proc_bus = proc_mkdir("bus", NULL);
+	proc_mkdir("bus", NULL);
 	proc_sys_init();
 }
 
@@ -232,9 +230,5 @@ void pid_ns_release_proc(struct pid_namespace *ns)
 EXPORT_SYMBOL(proc_symlink);
 EXPORT_SYMBOL(proc_mkdir);
 EXPORT_SYMBOL(create_proc_entry);
-EXPORT_SYMBOL(proc_create);
+EXPORT_SYMBOL(proc_create_data);
 EXPORT_SYMBOL(remove_proc_entry);
-EXPORT_SYMBOL(proc_root);
-EXPORT_SYMBOL(proc_root_fs);
-EXPORT_SYMBOL(proc_bus);
-EXPORT_SYMBOL(proc_root_driver);
diff --git a/trunk/fs/proc/task_mmu.c b/trunk/fs/proc/task_mmu.c
index 9dfb5ff24209..e2b8e769f510 100644
--- a/trunk/fs/proc/task_mmu.c
+++ b/trunk/fs/proc/task_mmu.c
@@ -75,40 +75,6 @@ int task_statm(struct mm_struct *mm, int *shared, int *text,
 	return mm->total_vm;
 }
 
-int proc_exe_link(struct inode *inode, struct path *path)
-{
-	struct vm_area_struct * vma;
-	int result = -ENOENT;
-	struct task_struct *task = get_proc_task(inode);
-	struct mm_struct * mm = NULL;
-
-	if (task) {
-		mm = get_task_mm(task);
-		put_task_struct(task);
-	}
-	if (!mm)
-		goto out;
-	down_read(&mm->mmap_sem);
-
-	vma = mm->mmap;
-	while (vma) {
-		if ((vma->vm_flags & VM_EXECUTABLE) && vma->vm_file)
-			break;
-		vma = vma->vm_next;
-	}
-
-	if (vma) {
-		*path = vma->vm_file->f_path;
-		path_get(&vma->vm_file->f_path);
-		result = 0;
-	}
-
-	up_read(&mm->mmap_sem);
-	mmput(mm);
-out:
-	return result;
-}
-
 static void pad_len_spaces(struct seq_file *m, int len)
 {
 	len = 25 + sizeof(void*) * 6 - len;
@@ -338,8 +304,7 @@ const struct file_operations proc_maps_operations = {
 #define PSS_SHIFT 12
 
 #ifdef CONFIG_PROC_PAGE_MONITOR
-struct mem_size_stats
-{
+struct mem_size_stats {
 	struct vm_area_struct *vma;
 	unsigned long resident;
 	unsigned long shared_clean;
@@ -347,6 +312,7 @@ struct mem_size_stats
 	unsigned long private_clean;
 	unsigned long private_dirty;
 	unsigned long referenced;
+	unsigned long swap;
 	u64 pss;
 };
 
@@ -363,6 +329,12 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
 		ptent = *pte;
+
+		if (is_swap_pte(ptent)) {
+			mss->swap += PAGE_SIZE;
+			continue;
+		}
+
 		if (!pte_present(ptent))
 			continue;
 
@@ -421,7 +393,8 @@ static int show_smap(struct seq_file *m, void *v)
 		   "Shared_Dirty:   %8lu kB\n"
 		   "Private_Clean:  %8lu kB\n"
 		   "Private_Dirty:  %8lu kB\n"
-		   "Referenced:     %8lu kB\n",
+		   "Referenced:     %8lu kB\n"
+		   "Swap:           %8lu kB\n",
 		   (vma->vm_end - vma->vm_start) >> 10,
 		   mss.resident >> 10,
 		   (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
@@ -429,7 +402,8 @@ static int show_smap(struct seq_file *m, void *v)
 		   mss.shared_dirty  >> 10,
 		   mss.private_clean >> 10,
 		   mss.private_dirty >> 10,
-		   mss.referenced >> 10);
+		   mss.referenced >> 10,
+		   mss.swap >> 10);
 
 	return ret;
 }
@@ -579,7 +553,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 	return err;
 }
 
-u64 swap_pte_to_pagemap_entry(pte_t pte)
+static u64 swap_pte_to_pagemap_entry(pte_t pte)
 {
 	swp_entry_t e = pte_to_swp_entry(pte);
 	return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
diff --git a/trunk/fs/proc/task_nommu.c b/trunk/fs/proc/task_nommu.c
index 8011528518bd..4b733f108455 100644
--- a/trunk/fs/proc/task_nommu.c
+++ b/trunk/fs/proc/task_nommu.c
@@ -103,40 +103,6 @@ int task_statm(struct mm_struct *mm, int *shared, int *text,
 	return size;
 }
 
-int proc_exe_link(struct inode *inode, struct path *path)
-{
-	struct vm_list_struct *vml;
-	struct vm_area_struct *vma;
-	struct task_struct *task = get_proc_task(inode);
-	struct mm_struct *mm = get_task_mm(task);
-	int result = -ENOENT;
-
-	if (!mm)
-		goto out;
-	down_read(&mm->mmap_sem);
-
-	vml = mm->context.vmlist;
-	vma = NULL;
-	while (vml) {
-		if ((vml->vma->vm_flags & VM_EXECUTABLE) && vml->vma->vm_file) {
-			vma = vml->vma;
-			break;
-		}
-		vml = vml->next;
-	}
-
-	if (vma) {
-		*path = vma->vm_file->f_path;
-		path_get(&vma->vm_file->f_path);
-		result = 0;
-	}
-
-	up_read(&mm->mmap_sem);
-	mmput(mm);
-out:
-	return result;
-}
-
 /*
  * display mapping lines for a particular process's /proc/pid/maps
  */
diff --git a/trunk/fs/quota.c b/trunk/fs/quota.c
index 84f28dd72116..db1cc9f3c7aa 100644
--- a/trunk/fs/quota.c
+++ b/trunk/fs/quota.c
@@ -69,7 +69,6 @@ static int generic_quotactl_valid(struct super_block *sb, int type, int cmd, qid
 	switch (cmd) {
 		case Q_GETFMT:
 		case Q_GETINFO:
-		case Q_QUOTAOFF:
 		case Q_SETINFO:
 		case Q_SETQUOTA:
 		case Q_GETQUOTA:
@@ -229,12 +228,12 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, void
 
 			if (IS_ERR(pathname = getname(addr)))
 				return PTR_ERR(pathname);
-			ret = sb->s_qcop->quota_on(sb, type, id, pathname);
+			ret = sb->s_qcop->quota_on(sb, type, id, pathname, 0);
 			putname(pathname);
 			return ret;
 		}
 		case Q_QUOTAOFF:
-			return sb->s_qcop->quota_off(sb, type);
+			return sb->s_qcop->quota_off(sb, type, 0);
 
 		case Q_GETFMT: {
 			__u32 fmt;
diff --git a/trunk/fs/quota_v1.c b/trunk/fs/quota_v1.c
index f3841f233069..a6cf9269105c 100644
--- a/trunk/fs/quota_v1.c
+++ b/trunk/fs/quota_v1.c
@@ -139,6 +139,9 @@ static int v1_read_file_info(struct super_block *sb, int type)
 		goto out;
 	}
 	ret = 0;
+	/* limits are stored as unsigned 32-bit data */
+	dqopt->info[type].dqi_maxblimit = 0xffffffff;
+	dqopt->info[type].dqi_maxilimit = 0xffffffff;
 	dqopt->info[type].dqi_igrace = dqblk.dqb_itime ? dqblk.dqb_itime : MAX_IQ_TIME;
 	dqopt->info[type].dqi_bgrace = dqblk.dqb_btime ? dqblk.dqb_btime : MAX_DQ_TIME;
 out:
diff --git a/trunk/fs/quota_v2.c b/trunk/fs/quota_v2.c
index c519a583e681..23b647f25d08 100644
--- a/trunk/fs/quota_v2.c
+++ b/trunk/fs/quota_v2.c
@@ -59,6 +59,9 @@ static int v2_read_file_info(struct super_block *sb, int type)
 			sb->s_id);
 		return -1;
 	}
+	/* limits are stored as unsigned 32-bit data */
+	info->dqi_maxblimit = 0xffffffff;
+	info->dqi_maxilimit = 0xffffffff;
 	info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace);
 	info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace);
 	info->dqi_flags = le32_to_cpu(dinfo.dqi_flags);
diff --git a/trunk/fs/ramfs/file-mmu.c b/trunk/fs/ramfs/file-mmu.c
index b41a514b0976..9590b9024300 100644
--- a/trunk/fs/ramfs/file-mmu.c
+++ b/trunk/fs/ramfs/file-mmu.c
@@ -26,6 +26,9 @@
 
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/ramfs.h>
+
+#include "internal.h"
 
 const struct address_space_operations ramfs_aops = {
 	.readpage	= simple_readpage,
diff --git a/trunk/fs/ramfs/internal.h b/trunk/fs/ramfs/internal.h
index af7cc074a476..6b330639b51d 100644
--- a/trunk/fs/ramfs/internal.h
+++ b/trunk/fs/ramfs/internal.h
@@ -11,5 +11,4 @@
 
 
 extern const struct address_space_operations ramfs_aops;
-extern const struct file_operations ramfs_file_operations;
 extern const struct inode_operations ramfs_file_inode_operations;
diff --git a/trunk/fs/reiserfs/bitmap.c b/trunk/fs/reiserfs/bitmap.c
index f491ceb5af02..4646caa60455 100644
--- a/trunk/fs/reiserfs/bitmap.c
+++ b/trunk/fs/reiserfs/bitmap.c
@@ -479,7 +479,7 @@ static void __discard_prealloc(struct reiserfs_transaction_handle *th,
 	if (ei->i_prealloc_count < 0)
 		reiserfs_warning(th->t_super,
 				 "zam-4001:%s: inode has negative prealloc blocks count.",
-				 __FUNCTION__);
+				 __func__);
 #endif
 	while (ei->i_prealloc_count > 0) {
 		reiserfs_free_prealloc_block(th, inode, ei->i_prealloc_block);
@@ -517,7 +517,7 @@ void reiserfs_discard_all_prealloc(struct reiserfs_transaction_handle *th)
 		if (!ei->i_prealloc_count) {
 			reiserfs_warning(th->t_super,
 					 "zam-4001:%s: inode is in prealloc list but has no preallocated blocks.",
-					 __FUNCTION__);
+					 __func__);
 		}
 #endif
 		__discard_prealloc(th, ei);
@@ -632,7 +632,7 @@ int reiserfs_parse_alloc_options(struct super_block *s, char *options)
 		}
 
 		reiserfs_warning(s, "zam-4001: %s : unknown option - %s",
-				 __FUNCTION__, this_char);
+				 __func__, this_char);
 		return 1;
 	}
 
@@ -1254,7 +1254,7 @@ struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb,
 	bh = sb_bread(sb, block);
 	if (bh == NULL)
 		reiserfs_warning(sb, "sh-2029: %s: bitmap block (#%u) "
-		                 "reading failed", __FUNCTION__, block);
+		                 "reading failed", __func__, block);
 	else {
 		if (buffer_locked(bh)) {
 			PROC_INFO_INC(sb, scan_bitmap.wait);
diff --git a/trunk/fs/reiserfs/do_balan.c b/trunk/fs/reiserfs/do_balan.c
index 7ee4208793b6..2f87f5b14630 100644
--- a/trunk/fs/reiserfs/do_balan.c
+++ b/trunk/fs/reiserfs/do_balan.c
@@ -1464,29 +1464,29 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih,	/* item h
 				} else
 					/* item falls wholly into S_new[i] */
 				{
-					int ret_val;
+					int leaf_mi;
 					struct item_head *pasted;
 
 #ifdef CONFIG_REISERFS_CHECK
-					struct item_head *ih =
+					struct item_head *ih_check =
 					    B_N_PITEM_HEAD(tbS0, item_pos);
 
-					if (!is_direntry_le_ih(ih)
-					    && (pos_in_item != ih_item_len(ih)
+					if (!is_direntry_le_ih(ih_check)
+					    && (pos_in_item != ih_item_len(ih_check)
 						|| tb->insert_size[0] <= 0))
 						reiserfs_panic(tb->tb_sb,
 							       "PAP-12235: balance_leaf: pos_in_item must be equal to ih_item_len");
 #endif				/* CONFIG_REISERFS_CHECK */
 
-					ret_val =
+					leaf_mi =
 					    leaf_move_items(LEAF_FROM_S_TO_SNEW,
 							    tb, snum[i],
 							    sbytes[i],
 							    S_new[i]);
 
-					RFALSE(ret_val,
+					RFALSE(leaf_mi,
 					       "PAP-12240: unexpected value returned by leaf_move_items (%d)",
-					       ret_val);
+					       leaf_mi);
 
 					/* paste into item */
 					bi.tb = tb;
diff --git a/trunk/fs/reiserfs/ioctl.c b/trunk/fs/reiserfs/ioctl.c
index 74363a7aacbc..830332021ed4 100644
--- a/trunk/fs/reiserfs/ioctl.c
+++ b/trunk/fs/reiserfs/ioctl.c
@@ -12,8 +12,6 @@
 #include <linux/smp_lock.h>
 #include <linux/compat.h>
 
-static int reiserfs_unpack(struct inode *inode, struct file *filp);
-
 /*
 ** reiserfs_ioctl - handler for ioctl for inode
 ** supported commands:
@@ -159,7 +157,7 @@ int reiserfs_prepare_write(struct file *f, struct page *page,
 ** Function try to convert tail from direct item into indirect.
 ** It set up nopack attribute in the REISERFS_I(inode)->nopack
 */
-static int reiserfs_unpack(struct inode *inode, struct file *filp)
+int reiserfs_unpack(struct inode *inode, struct file *filp)
 {
 	int retval = 0;
 	int index;
diff --git a/trunk/fs/reiserfs/journal.c b/trunk/fs/reiserfs/journal.c
index 060eb3f598e7..da86042b3e03 100644
--- a/trunk/fs/reiserfs/journal.c
+++ b/trunk/fs/reiserfs/journal.c
@@ -1187,7 +1187,7 @@ static int flush_commit_list(struct super_block *s,
 
 	if (retval)
 		reiserfs_abort(s, retval, "Journal write error in %s",
-			       __FUNCTION__);
+			       __func__);
 	put_fs_excl();
 	return retval;
 }
@@ -1534,7 +1534,7 @@ static int flush_journal_list(struct super_block *s,
 			reiserfs_warning(s,
 					 "clm-2082: Unable to flush buffer %llu in %s",
 					 (unsigned long long)saved_bh->
-					 b_blocknr, __FUNCTION__);
+					 b_blocknr, __func__);
 		}
 	      free_cnode:
 		last = cn;
@@ -1586,7 +1586,7 @@ static int flush_journal_list(struct super_block *s,
 	if (err)
 		reiserfs_abort(s, -EIO,
 			       "Write error while pushing transaction to disk in %s",
-			       __FUNCTION__);
+			       __func__);
       flush_older_and_return:
 
 	/* before we can update the journal header block, we _must_ flush all 
@@ -1616,7 +1616,7 @@ static int flush_journal_list(struct super_block *s,
 		if (err)
 			reiserfs_abort(s, -EIO,
 				       "Write error while updating journal header in %s",
-				       __FUNCTION__);
+				       __func__);
 	}
 	remove_all_from_journal_list(s, jl, 0);
 	list_del_init(&jl->j_list);
@@ -4316,5 +4316,5 @@ static void __reiserfs_journal_abort_soft(struct super_block *sb, int errno)
 
 void reiserfs_journal_abort(struct super_block *sb, int errno)
 {
-	return __reiserfs_journal_abort_soft(sb, errno);
+	__reiserfs_journal_abort_soft(sb, errno);
 }
diff --git a/trunk/fs/reiserfs/namei.c b/trunk/fs/reiserfs/namei.c
index 8867533cb727..c1add28dd45e 100644
--- a/trunk/fs/reiserfs/namei.c
+++ b/trunk/fs/reiserfs/namei.c
@@ -301,7 +301,7 @@ static int reiserfs_find_entry(struct inode *dir, const char *name, int namelen,
 					path_to_entry, de);
 		if (retval == IO_ERROR) {
 			reiserfs_warning(dir->i_sb, "zam-7001: io error in %s",
-					 __FUNCTION__);
+					 __func__);
 			return IO_ERROR;
 		}
 
@@ -496,7 +496,7 @@ static int reiserfs_add_entry(struct reiserfs_transaction_handle *th,
 			reiserfs_warning(dir->i_sb,
 					 "zam-7002:%s: \"reiserfs_find_entry\" "
 					 "has returned unexpected value (%d)",
-					 __FUNCTION__, retval);
+					 __func__, retval);
 		}
 
 		return -EEXIST;
@@ -907,7 +907,7 @@ static int reiserfs_rmdir(struct inode *dir, struct dentry *dentry)
 
 	if (inode->i_nlink != 2 && inode->i_nlink != 1)
 		reiserfs_warning(inode->i_sb, "%s: empty directory has nlink "
-				 "!= 2 (%d)", __FUNCTION__, inode->i_nlink);
+				 "!= 2 (%d)", __func__, inode->i_nlink);
 
 	clear_nlink(inode);
 	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC;
@@ -984,7 +984,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry)
 
 	if (!inode->i_nlink) {
 		reiserfs_warning(inode->i_sb, "%s: deleting nonexistent file "
-				 "(%s:%lu), %d", __FUNCTION__,
+				 "(%s:%lu), %d", __func__,
 				 reiserfs_bdevname(inode->i_sb), inode->i_ino,
 				 inode->i_nlink);
 		inode->i_nlink = 1;
diff --git a/trunk/fs/reiserfs/objectid.c b/trunk/fs/reiserfs/objectid.c
index 65feba4deb69..ea0cf8c28a99 100644
--- a/trunk/fs/reiserfs/objectid.c
+++ b/trunk/fs/reiserfs/objectid.c
@@ -61,7 +61,7 @@ __u32 reiserfs_get_unused_objectid(struct reiserfs_transaction_handle *th)
 	/* comment needed -Hans */
 	unused_objectid = le32_to_cpu(map[1]);
 	if (unused_objectid == U32_MAX) {
-		reiserfs_warning(s, "%s: no more object ids", __FUNCTION__);
+		reiserfs_warning(s, "%s: no more object ids", __func__);
 		reiserfs_restore_prepared_buffer(s, SB_BUFFER_WITH_SB(s));
 		return 0;
 	}
@@ -114,7 +114,7 @@ void reiserfs_release_objectid(struct reiserfs_transaction_handle *th,
 		if (objectid_to_release == le32_to_cpu(map[i])) {
 			/* This incrementation unallocates the objectid. */
 			//map[i]++;
-			map[i] = cpu_to_le32(le32_to_cpu(map[i]) + 1);
+			le32_add_cpu(&map[i], 1);
 
 			/* Did we unallocate the last member of an odd sequence, and can shrink oids? */
 			if (map[i] == map[i + 1]) {
@@ -138,8 +138,7 @@ void reiserfs_release_objectid(struct reiserfs_transaction_handle *th,
 			/* size of objectid map is not changed */
 			if (objectid_to_release + 1 == le32_to_cpu(map[i + 1])) {
 				//objectid_map[i+1]--;
-				map[i + 1] =
-				    cpu_to_le32(le32_to_cpu(map[i + 1]) - 1);
+				le32_add_cpu(&map[i + 1], -1);
 				return;
 			}
 
diff --git a/trunk/fs/reiserfs/procfs.c b/trunk/fs/reiserfs/procfs.c
index 8f86c52b30d8..b9dbeeca7049 100644
--- a/trunk/fs/reiserfs/procfs.c
+++ b/trunk/fs/reiserfs/procfs.c
@@ -467,6 +467,7 @@ static const struct file_operations r_file_operations = {
 	.read = seq_read,
 	.llseek = seq_lseek,
 	.release = seq_release,
+	.owner = THIS_MODULE,
 };
 
 static struct proc_dir_entry *proc_info_root = NULL;
@@ -475,12 +476,8 @@ static const char proc_info_root_name[] = "fs/reiserfs";
 static void add_file(struct super_block *sb, char *name,
 		     int (*func) (struct seq_file *, struct super_block *))
 {
-	struct proc_dir_entry *de;
-	de = create_proc_entry(name, 0, REISERFS_SB(sb)->procdir);
-	if (de) {
-		de->data = func;
-		de->proc_fops = &r_file_operations;
-	}
+	proc_create_data(name, 0, REISERFS_SB(sb)->procdir,
+			 &r_file_operations, func);
 }
 
 int reiserfs_proc_info_init(struct super_block *sb)
diff --git a/trunk/fs/reiserfs/stree.c b/trunk/fs/reiserfs/stree.c
index d2db2417b2bd..abbc64dcc8d4 100644
--- a/trunk/fs/reiserfs/stree.c
+++ b/trunk/fs/reiserfs/stree.c
@@ -1419,8 +1419,7 @@ int reiserfs_delete_object(struct reiserfs_transaction_handle *th,
 
 		inode_generation =
 		    &REISERFS_SB(th->t_super)->s_rs->s_inode_generation;
-		*inode_generation =
-		    cpu_to_le32(le32_to_cpu(*inode_generation) + 1);
+		le32_add_cpu(inode_generation, 1);
 	}
 /* USE_INODE_GENERATION_COUNTER */
 #endif
diff --git a/trunk/fs/reiserfs/super.c b/trunk/fs/reiserfs/super.c
index 393cc22c1717..ed424d708e69 100644
--- a/trunk/fs/reiserfs/super.c
+++ b/trunk/fs/reiserfs/super.c
@@ -304,7 +304,7 @@ static int finish_unfinished(struct super_block *s)
 	/* Turn quotas off */
 	for (i = 0; i < MAXQUOTAS; i++) {
 		if (sb_dqopt(s)->files[i])
-			vfs_quota_off_mount(s, i);
+			vfs_quota_off(s, i, 0);
 	}
 	if (ms_active_set)
 		/* Restore the flag back */
@@ -634,7 +634,7 @@ static int reiserfs_acquire_dquot(struct dquot *);
 static int reiserfs_release_dquot(struct dquot *);
 static int reiserfs_mark_dquot_dirty(struct dquot *);
 static int reiserfs_write_info(struct super_block *, int);
-static int reiserfs_quota_on(struct super_block *, int, int, char *);
+static int reiserfs_quota_on(struct super_block *, int, int, char *, int);
 
 static struct dquot_operations reiserfs_quota_operations = {
 	.initialize = reiserfs_dquot_initialize,
@@ -1890,8 +1890,14 @@ static int reiserfs_dquot_drop(struct inode *inode)
 	ret =
 	    journal_begin(&th, inode->i_sb,
 			  2 * REISERFS_QUOTA_DEL_BLOCKS(inode->i_sb));
-	if (ret)
+	if (ret) {
+		/*
+		 * We call dquot_drop() anyway to at least release references
+		 * to quota structures so that umount does not hang.
+		 */
+		dquot_drop(inode);
 		goto out;
+	}
 	ret = dquot_drop(inode);
 	err =
 	    journal_end(&th, inode->i_sb,
@@ -2015,13 +2021,17 @@ static int reiserfs_quota_on_mount(struct super_block *sb, int type)
  * Standard function to be called on quota_on
  */
 static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
-			     char *path)
+			     char *path, int remount)
 {
 	int err;
 	struct nameidata nd;
+	struct inode *inode;
 
 	if (!(REISERFS_SB(sb)->s_mount_opt & (1 << REISERFS_QUOTA)))
 		return -EINVAL;
+	/* No more checks needed? Path and format_id are bogus anyway... */
+	if (remount)
+		return vfs_quota_on(sb, type, format_id, path, 1);
 	err = path_lookup(path, LOOKUP_FOLLOW, &nd);
 	if (err)
 		return err;
@@ -2030,18 +2040,24 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
 		path_put(&nd.path);
 		return -EXDEV;
 	}
+	inode = nd.path.dentry->d_inode;
 	/* We must not pack tails for quota files on reiserfs for quota IO to work */
-	if (!(REISERFS_I(nd.path.dentry->d_inode)->i_flags & i_nopack_mask)) {
-		reiserfs_warning(sb,
-				 "reiserfs: Quota file must have tail packing disabled.");
-		path_put(&nd.path);
-		return -EINVAL;
+	if (!(REISERFS_I(inode)->i_flags & i_nopack_mask)) {
+		err = reiserfs_unpack(inode, NULL);
+		if (err) {
+			reiserfs_warning(sb,
+				"reiserfs: Unpacking tail of quota file failed"
+				" (%d). Cannot turn on quotas.", err);
+			path_put(&nd.path);
+			return -EINVAL;
+		}
+		mark_inode_dirty(inode);
 	}
 	/* Not journalling quota? No more tests needed... */
 	if (!REISERFS_SB(sb)->s_qf_names[USRQUOTA] &&
 	    !REISERFS_SB(sb)->s_qf_names[GRPQUOTA]) {
 		path_put(&nd.path);
-		return vfs_quota_on(sb, type, format_id, path);
+		return vfs_quota_on(sb, type, format_id, path, 0);
 	}
 	/* Quotafile not of fs root? */
 	if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode)
@@ -2049,7 +2065,7 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
 				 "reiserfs: Quota file not on filesystem root. "
 				 "Journalled quota will not work.");
 	path_put(&nd.path);
-	return vfs_quota_on(sb, type, format_id, path);
+	return vfs_quota_on(sb, type, format_id, path, 0);
 }
 
 /* Read data from quotafile - avoid pagecache and such because we cannot afford
diff --git a/trunk/fs/splice.c b/trunk/fs/splice.c
index eeb1a86a7014..633f58ebfb72 100644
--- a/trunk/fs/splice.c
+++ b/trunk/fs/splice.c
@@ -1075,7 +1075,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
 
 	ret = splice_direct_to_actor(in, &sd, direct_splice_actor);
 	if (ret > 0)
-		*ppos += ret;
+		*ppos = sd.pos;
 
 	return ret;
 }
diff --git a/trunk/fs/super.c b/trunk/fs/super.c
index 4798350b2bc9..453877c5697b 100644
--- a/trunk/fs/super.c
+++ b/trunk/fs/super.c
@@ -117,7 +117,7 @@ static inline void destroy_super(struct super_block *s)
  * Drop a superblock's refcount.  Returns non-zero if the superblock was
  * destroyed.  The caller must hold sb_lock.
  */
-int __put_super(struct super_block *sb)
+static int __put_super(struct super_block *sb)
 {
 	int ret = 0;
 
@@ -179,7 +179,7 @@ void deactivate_super(struct super_block *s)
 	if (atomic_dec_and_lock(&s->s_active, &sb_lock)) {
 		s->s_count -= S_BIAS-1;
 		spin_unlock(&sb_lock);
-		DQUOT_OFF(s);
+		DQUOT_OFF(s, 0);
 		down_write(&s->s_umount);
 		fs->kill_sb(s);
 		put_filesystem(fs);
@@ -608,6 +608,7 @@ static void mark_files_ro(struct super_block *sb)
 int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 {
 	int retval;
+	int remount_rw;
 	
 #ifdef CONFIG_BLOCK
 	if (!(flags & MS_RDONLY) && bdev_read_only(sb->s_bdev))
@@ -625,8 +626,11 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 			mark_files_ro(sb);
 		else if (!fs_may_remount_ro(sb))
 			return -EBUSY;
-		DQUOT_OFF(sb);
+		retval = DQUOT_OFF(sb, 1);
+		if (retval < 0 && retval != -ENOSYS)
+			return -EBUSY;
 	}
+	remount_rw = !(flags & MS_RDONLY) && (sb->s_flags & MS_RDONLY);
 
 	if (sb->s_op->remount_fs) {
 		lock_super(sb);
@@ -636,6 +640,8 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 			return retval;
 	}
 	sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (flags & MS_RMT_MASK);
+	if (remount_rw)
+		DQUOT_ON_REMOUNT(sb);
 	return 0;
 }
 
diff --git a/trunk/fs/sync.c b/trunk/fs/sync.c
index 7cd005ea7639..228e17b5e9ee 100644
--- a/trunk/fs/sync.c
+++ b/trunk/fs/sync.c
@@ -64,7 +64,7 @@ int file_fsync(struct file *filp, struct dentry *dentry, int datasync)
 	/* sync the superblock to buffers */
 	sb = inode->i_sb;
 	lock_super(sb);
-	if (sb->s_op->write_super)
+	if (sb->s_dirt && sb->s_op->write_super)
 		sb->s_op->write_super(sb);
 	unlock_super(sb);
 
diff --git a/trunk/fs/sysfs/file.c b/trunk/fs/sysfs/file.c
index ade9a7e6a757..dbdfabbfd609 100644
--- a/trunk/fs/sysfs/file.c
+++ b/trunk/fs/sysfs/file.c
@@ -477,11 +477,10 @@ const struct file_operations sysfs_file_operations = {
 	.poll		= sysfs_poll,
 };
 
-
-int sysfs_add_file(struct sysfs_dirent *dir_sd, const struct attribute *attr,
-		   int type)
+int sysfs_add_file_mode(struct sysfs_dirent *dir_sd,
+			const struct attribute *attr, int type, mode_t amode)
 {
-	umode_t mode = (attr->mode & S_IALLUGO) | S_IFREG;
+	umode_t mode = (amode & S_IALLUGO) | S_IFREG;
 	struct sysfs_addrm_cxt acxt;
 	struct sysfs_dirent *sd;
 	int rc;
@@ -502,6 +501,13 @@ int sysfs_add_file(struct sysfs_dirent *dir_sd, const struct attribute *attr,
 }
 
 
+int sysfs_add_file(struct sysfs_dirent *dir_sd, const struct attribute *attr,
+		   int type)
+{
+	return sysfs_add_file_mode(dir_sd, attr, type, attr->mode);
+}
+
+
 /**
  *	sysfs_create_file - create an attribute file for an object.
  *	@kobj:	object we're creating for. 
diff --git a/trunk/fs/sysfs/group.c b/trunk/fs/sysfs/group.c
index 477904915032..eeba38417b1d 100644
--- a/trunk/fs/sysfs/group.c
+++ b/trunk/fs/sysfs/group.c
@@ -23,35 +23,50 @@ static void remove_files(struct sysfs_dirent *dir_sd, struct kobject *kobj,
 	int i;
 
 	for (i = 0, attr = grp->attrs; *attr; i++, attr++)
-		if (!grp->is_visible ||
-		    grp->is_visible(kobj, *attr, i))
-			sysfs_hash_and_remove(dir_sd, (*attr)->name);
+		sysfs_hash_and_remove(dir_sd, (*attr)->name);
 }
 
 static int create_files(struct sysfs_dirent *dir_sd, struct kobject *kobj,
-			const struct attribute_group *grp)
+			const struct attribute_group *grp, int update)
 {
 	struct attribute *const* attr;
 	int error = 0, i;
 
-	for (i = 0, attr = grp->attrs; *attr && !error; i++, attr++)
-		if (!grp->is_visible ||
-		    grp->is_visible(kobj, *attr, i))
-			error |=
-				sysfs_add_file(dir_sd, *attr, SYSFS_KOBJ_ATTR);
+	for (i = 0, attr = grp->attrs; *attr && !error; i++, attr++) {
+		mode_t mode = 0;
+
+		/* in update mode, we're changing the permissions or
+		 * visibility.  Do this by first removing then
+		 * re-adding (if required) the file */
+		if (update)
+			sysfs_hash_and_remove(dir_sd, (*attr)->name);
+		if (grp->is_visible) {
+			mode = grp->is_visible(kobj, *attr, i);
+			if (!mode)
+				continue;
+		}
+		error = sysfs_add_file_mode(dir_sd, *attr, SYSFS_KOBJ_ATTR,
+					    (*attr)->mode | mode);
+		if (unlikely(error))
+			break;
+	}
 	if (error)
 		remove_files(dir_sd, kobj, grp);
 	return error;
 }
 
 
-int sysfs_create_group(struct kobject * kobj, 
-		       const struct attribute_group * grp)
+static int internal_create_group(struct kobject *kobj, int update,
+				 const struct attribute_group *grp)
 {
 	struct sysfs_dirent *sd;
 	int error;
 
-	BUG_ON(!kobj || !kobj->sd);
+	BUG_ON(!kobj || (!update && !kobj->sd));
+
+	/* Updates may happen before the object has been instantiated */
+	if (unlikely(update && !kobj->sd))
+		return -EINVAL;
 
 	if (grp->name) {
 		error = sysfs_create_subdir(kobj, grp->name, &sd);
@@ -60,7 +75,7 @@ int sysfs_create_group(struct kobject * kobj,
 	} else
 		sd = kobj->sd;
 	sysfs_get(sd);
-	error = create_files(sd, kobj, grp);
+	error = create_files(sd, kobj, grp, update);
 	if (error) {
 		if (grp->name)
 			sysfs_remove_subdir(sd);
@@ -69,6 +84,47 @@ int sysfs_create_group(struct kobject * kobj,
 	return error;
 }
 
+/**
+ * sysfs_create_group - given a directory kobject, create an attribute group
+ * @kobj:	The kobject to create the group on
+ * @grp:	The attribute group to create
+ *
+ * This function creates a group for the first time.  It will explicitly
+ * warn and error if any of the attribute files being created already exist.
+ *
+ * Returns 0 on success or error.
+ */
+int sysfs_create_group(struct kobject *kobj,
+		       const struct attribute_group *grp)
+{
+	return internal_create_group(kobj, 0, grp);
+}
+
+/**
+ * sysfs_update_group - given a directory kobject, create an attribute group
+ * @kobj:	The kobject to create the group on
+ * @grp:	The attribute group to create
+ *
+ * This function updates an attribute group.  Unlike
+ * sysfs_create_group(), it will explicitly not warn or error if any
+ * of the attribute files being created already exist.  Furthermore,
+ * if the visibility of the files has changed through the is_visible()
+ * callback, it will update the permissions and add or remove the
+ * relevant files.
+ *
+ * The primary use for this function is to call it after making a change
+ * that affects group visibility.
+ *
+ * Returns 0 on success or error.
+ */
+int sysfs_update_group(struct kobject *kobj,
+		       const struct attribute_group *grp)
+{
+	return internal_create_group(kobj, 1, grp);
+}
+
+
+
 void sysfs_remove_group(struct kobject * kobj, 
 			const struct attribute_group * grp)
 {
@@ -95,4 +151,5 @@ void sysfs_remove_group(struct kobject * kobj,
 
 
 EXPORT_SYMBOL_GPL(sysfs_create_group);
+EXPORT_SYMBOL_GPL(sysfs_update_group);
 EXPORT_SYMBOL_GPL(sysfs_remove_group);
diff --git a/trunk/fs/sysfs/sysfs.h b/trunk/fs/sysfs/sysfs.h
index ff17f8da9b43..ce4e15f8aaeb 100644
--- a/trunk/fs/sysfs/sysfs.h
+++ b/trunk/fs/sysfs/sysfs.h
@@ -154,6 +154,8 @@ extern const struct file_operations sysfs_file_operations;
 int sysfs_add_file(struct sysfs_dirent *dir_sd,
 		   const struct attribute *attr, int type);
 
+int sysfs_add_file_mode(struct sysfs_dirent *dir_sd,
+			const struct attribute *attr, int type, mode_t amode);
 /*
  * bin.c
  */
diff --git a/trunk/fs/timerfd.c b/trunk/fs/timerfd.c
index 10c80b59ec4b..5400524e9cb1 100644
--- a/trunk/fs/timerfd.c
+++ b/trunk/fs/timerfd.c
@@ -20,6 +20,7 @@
 #include <linux/hrtimer.h>
 #include <linux/anon_inodes.h>
 #include <linux/timerfd.h>
+#include <linux/syscalls.h>
 
 struct timerfd_ctx {
 	struct hrtimer tmr;
diff --git a/trunk/fs/udf/namei.c b/trunk/fs/udf/namei.c
index ba5537d4bc15..2b34c8ca6c83 100644
--- a/trunk/fs/udf/namei.c
+++ b/trunk/fs/udf/namei.c
@@ -890,7 +890,7 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry,
 
 	if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
 		kernel_lb_addr eloc;
-		uint32_t elen;
+		uint32_t bsize;
 
 		block = udf_new_block(inode->i_sb, inode,
 				iinfo->i_location.partitionReferenceNum,
@@ -903,9 +903,9 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry,
 		eloc.logicalBlockNum = block;
 		eloc.partitionReferenceNum =
 				iinfo->i_location.partitionReferenceNum;
-		elen = inode->i_sb->s_blocksize;
-		iinfo->i_lenExtents = elen;
-		udf_add_aext(inode, &epos, eloc, elen, 0);
+		bsize = inode->i_sb->s_blocksize;
+		iinfo->i_lenExtents = bsize;
+		udf_add_aext(inode, &epos, eloc, bsize, 0);
 		brelse(epos.bh);
 
 		block = udf_get_pblock(inode->i_sb, block,
diff --git a/trunk/fs/ufs/balloc.c b/trunk/fs/ufs/balloc.c
index 1e7598fb9787..0d9ada173739 100644
--- a/trunk/fs/ufs/balloc.c
+++ b/trunk/fs/ufs/balloc.c
@@ -277,7 +277,7 @@ static void ufs_change_blocknr(struct inode *inode, sector_t beg,
 			if (!page)/* it was truncated */
 				continue;
 			if (IS_ERR(page)) {/* or EIO */
-				ufs_error(inode->i_sb, __FUNCTION__,
+				ufs_error(inode->i_sb, __func__,
 					  "read of page %llu failed\n",
 					  (unsigned long long)index);
 				continue;
@@ -308,7 +308,7 @@ static void ufs_change_blocknr(struct inode *inode, sector_t beg,
 				ll_rw_block(READ, 1, &bh);
 				wait_on_buffer(bh);
 				if (!buffer_uptodate(bh)) {
-					ufs_error(inode->i_sb, __FUNCTION__,
+					ufs_error(inode->i_sb, __func__,
 						  "read of block failed\n");
 					break;
 				}
diff --git a/trunk/fs/ufs/dir.c b/trunk/fs/ufs/dir.c
index ef563fc8d72c..df0bef18742d 100644
--- a/trunk/fs/ufs/dir.c
+++ b/trunk/fs/ufs/dir.c
@@ -179,7 +179,7 @@ static void ufs_check_page(struct page *page)
 	goto fail;
 Eend:
 	p = (struct ufs_dir_entry *)(kaddr + offs);
-	ufs_error(sb, __FUNCTION__,
+	ufs_error(sb, __func__,
 		   "entry in directory #%lu spans the page boundary"
 		   "offset=%lu",
 		   dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs);
@@ -284,7 +284,7 @@ struct ufs_dir_entry *ufs_find_entry(struct inode *dir, struct dentry *dentry,
 			kaddr += ufs_last_byte(dir, n) - reclen;
 			while ((char *) de <= kaddr) {
 				if (de->d_reclen == 0) {
-					ufs_error(dir->i_sb, __FUNCTION__,
+					ufs_error(dir->i_sb, __func__,
 						  "zero-length directory entry");
 					ufs_put_page(page);
 					goto out;
@@ -356,7 +356,7 @@ int ufs_add_link(struct dentry *dentry, struct inode *inode)
 				goto got_it;
 			}
 			if (de->d_reclen == 0) {
-				ufs_error(dir->i_sb, __FUNCTION__,
+				ufs_error(dir->i_sb, __func__,
 					  "zero-length directory entry");
 				err = -EIO;
 				goto out_unlock;
@@ -456,7 +456,7 @@ ufs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 		struct page *page = ufs_get_page(inode, n);
 
 		if (IS_ERR(page)) {
-			ufs_error(sb, __FUNCTION__,
+			ufs_error(sb, __func__,
 				  "bad page in #%lu",
 				  inode->i_ino);
 			filp->f_pos += PAGE_CACHE_SIZE - offset;
@@ -475,7 +475,7 @@ ufs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 		limit = kaddr + ufs_last_byte(inode, n) - UFS_DIR_REC_LEN(1);
 		for ( ;(char*)de <= limit; de = ufs_next_entry(sb, de)) {
 			if (de->d_reclen == 0) {
-				ufs_error(sb, __FUNCTION__,
+				ufs_error(sb, __func__,
 					"zero-length directory entry");
 				ufs_put_page(page);
 				return -EIO;
@@ -536,7 +536,7 @@ int ufs_delete_entry(struct inode *inode, struct ufs_dir_entry *dir,
 
 	while ((char*)de < (char*)dir) {
 		if (de->d_reclen == 0) {
-			ufs_error(inode->i_sb, __FUNCTION__,
+			ufs_error(inode->i_sb, __func__,
 				  "zero-length directory entry");
 			err = -EIO;
 			goto out;
@@ -633,7 +633,7 @@ int ufs_empty_dir(struct inode * inode)
 
 		while ((char *)de <= kaddr) {
 			if (de->d_reclen == 0) {
-				ufs_error(inode->i_sb, __FUNCTION__,
+				ufs_error(inode->i_sb, __func__,
 					"zero-length directory entry: "
 					"kaddr=%p, de=%p\n", kaddr, de);
 				goto not_empty;
diff --git a/trunk/fs/ufs/inode.c b/trunk/fs/ufs/inode.c
index 5446b888fc8e..39f877898565 100644
--- a/trunk/fs/ufs/inode.c
+++ b/trunk/fs/ufs/inode.c
@@ -929,7 +929,7 @@ void ufs_delete_inode (struct inode * inode)
 	old_i_size = inode->i_size;
 	inode->i_size = 0;
 	if (inode->i_blocks && ufs_truncate(inode, old_i_size))
-		ufs_warning(inode->i_sb, __FUNCTION__, "ufs_truncate failed\n");
+		ufs_warning(inode->i_sb, __func__, "ufs_truncate failed\n");
 	ufs_free_inode (inode);
 	unlock_kernel();
 	return;
diff --git a/trunk/fs/ufs/swab.h b/trunk/fs/ufs/swab.h
index 1683d2bee614..8d974c4fd18b 100644
--- a/trunk/fs/ufs/swab.h
+++ b/trunk/fs/ufs/swab.h
@@ -40,25 +40,7 @@ cpu_to_fs64(struct super_block *sbp, u64 n)
 		return (__force __fs64)cpu_to_be64(n);
 }
 
-static __inline u32
-fs64_add(struct super_block *sbp, u32 *n, int d)
-{
-	if (UFS_SB(sbp)->s_bytesex == BYTESEX_LE)
-		return *n = cpu_to_le64(le64_to_cpu(*n)+d);
-	else
-		return *n = cpu_to_be64(be64_to_cpu(*n)+d);
-}
-
-static __inline u32
-fs64_sub(struct super_block *sbp, u32 *n, int d)
-{
-	if (UFS_SB(sbp)->s_bytesex == BYTESEX_LE)
-		return *n = cpu_to_le64(le64_to_cpu(*n)-d);
-	else
-		return *n = cpu_to_be64(be64_to_cpu(*n)-d);
-}
-
-static __inline u32
+static inline u32
 fs32_to_cpu(struct super_block *sbp, __fs32 n)
 {
 	if (UFS_SB(sbp)->s_bytesex == BYTESEX_LE)
@@ -80,18 +62,18 @@ static inline void
 fs32_add(struct super_block *sbp, __fs32 *n, int d)
 {
 	if (UFS_SB(sbp)->s_bytesex == BYTESEX_LE)
-		*(__le32 *)n = cpu_to_le32(le32_to_cpu(*(__le32 *)n)+d);
+		le32_add_cpu((__le32 *)n, d);
 	else
-		*(__be32 *)n = cpu_to_be32(be32_to_cpu(*(__be32 *)n)+d);
+		be32_add_cpu((__be32 *)n, d);
 }
 
 static inline void
 fs32_sub(struct super_block *sbp, __fs32 *n, int d)
 {
 	if (UFS_SB(sbp)->s_bytesex == BYTESEX_LE)
-		*(__le32 *)n = cpu_to_le32(le32_to_cpu(*(__le32 *)n)-d);
+		le32_add_cpu((__le32 *)n, -d);
 	else
-		*(__be32 *)n = cpu_to_be32(be32_to_cpu(*(__be32 *)n)-d);
+		be32_add_cpu((__be32 *)n, -d);
 }
 
 static inline u16
@@ -116,18 +98,18 @@ static inline void
 fs16_add(struct super_block *sbp, __fs16 *n, int d)
 {
 	if (UFS_SB(sbp)->s_bytesex == BYTESEX_LE)
-		*(__le16 *)n = cpu_to_le16(le16_to_cpu(*(__le16 *)n)+d);
+		le16_add_cpu((__le16 *)n, d);
 	else
-		*(__be16 *)n = cpu_to_be16(be16_to_cpu(*(__be16 *)n)+d);
+		be16_add_cpu((__be16 *)n, d);
 }
 
 static inline void
 fs16_sub(struct super_block *sbp, __fs16 *n, int d)
 {
 	if (UFS_SB(sbp)->s_bytesex == BYTESEX_LE)
-		*(__le16 *)n = cpu_to_le16(le16_to_cpu(*(__le16 *)n)-d);
+		le16_add_cpu((__le16 *)n, -d);
 	else
-		*(__be16 *)n = cpu_to_be16(be16_to_cpu(*(__be16 *)n)-d);
+		be16_add_cpu((__be16 *)n, -d);
 }
 
 #endif /* _UFS_SWAB_H */
diff --git a/trunk/fs/ufs/ufs.h b/trunk/fs/ufs/ufs.h
index fcb9231bb9ed..244a1aaa940e 100644
--- a/trunk/fs/ufs/ufs.h
+++ b/trunk/fs/ufs/ufs.h
@@ -66,7 +66,7 @@ struct ufs_inode_info {
 #ifdef CONFIG_UFS_DEBUG
 #	define UFSD(f, a...)	{					\
 		printk ("UFSD (%s, %d): %s:",				\
-			__FILE__, __LINE__, __FUNCTION__);		\
+			__FILE__, __LINE__, __func__);		\
 		printk (f, ## a);					\
 	}
 #else
diff --git a/trunk/fs/vfat/namei.c b/trunk/fs/vfat/namei.c
index cd450bea9f1a..5b66162d0747 100644
--- a/trunk/fs/vfat/namei.c
+++ b/trunk/fs/vfat/namei.c
@@ -176,15 +176,10 @@ static inline int vfat_is_used_badchars(const wchar_t *s, int len)
 	for (i = 0; i < len; i++)
 		if (vfat_bad_char(s[i]))
 			return -EINVAL;
-	return 0;
-}
 
-static int vfat_valid_longname(const unsigned char *name, unsigned int len)
-{
-	if (name[len - 1] == ' ')
+	if (s[i - 1] == ' ') /* last character cannot be space */
 		return -EINVAL;
-	if (len >= 256)
-		return -ENAMETOOLONG;
+
 	return 0;
 }
 
@@ -477,7 +472,7 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname,
 	if (utf8) {
 		int name_len = strlen(name);
 
-		*outlen = utf8_mbstowcs((wchar_t *)outname, name, PAGE_SIZE);
+		*outlen = utf8_mbstowcs((wchar_t *)outname, name, PATH_MAX);
 
 		/*
 		 * We stripped '.'s before and set len appropriately,
@@ -485,11 +480,14 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname,
 		 */
 		*outlen -= (name_len - len);
 
+		if (*outlen > 255)
+			return -ENAMETOOLONG;
+
 		op = &outname[*outlen * sizeof(wchar_t)];
 	} else {
 		if (nls) {
 			for (i = 0, ip = name, op = outname, *outlen = 0;
-			     i < len && *outlen <= 260;
+			     i < len && *outlen <= 255;
 			     *outlen += 1)
 			{
 				if (escape && (*ip == ':')) {
@@ -525,18 +523,20 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname,
 					op += 2;
 				}
 			}
+			if (i < len)
+				return -ENAMETOOLONG;
 		} else {
 			for (i = 0, ip = name, op = outname, *outlen = 0;
-			     i < len && *outlen <= 260;
+			     i < len && *outlen <= 255;
 			     i++, *outlen += 1)
 			{
 				*op++ = *ip++;
 				*op++ = 0;
 			}
+			if (i < len)
+				return -ENAMETOOLONG;
 		}
 	}
-	if (*outlen > 260)
-		return -ENAMETOOLONG;
 
 	*longlen = *outlen;
 	if (*outlen % 13) {
@@ -565,7 +565,6 @@ static int vfat_build_slots(struct inode *dir, const unsigned char *name,
 	struct fat_mount_options *opts = &sbi->options;
 	struct msdos_dir_slot *ps;
 	struct msdos_dir_entry *de;
-	unsigned long page;
 	unsigned char cksum, lcase;
 	unsigned char msdos_name[MSDOS_NAME];
 	wchar_t *uname;
@@ -574,15 +573,11 @@ static int vfat_build_slots(struct inode *dir, const unsigned char *name,
 	loff_t offset;
 
 	*nr_slots = 0;
-	err = vfat_valid_longname(name, len);
-	if (err)
-		return err;
 
-	page = __get_free_page(GFP_KERNEL);
-	if (!page)
+	uname = __getname();
+	if (!uname)
 		return -ENOMEM;
 
-	uname = (wchar_t *)page;
 	err = xlate_to_uni(name, len, (unsigned char *)uname, &ulen, &usize,
 			   opts->unicode_xlate, opts->utf8, sbi->nls_io);
 	if (err)
@@ -634,7 +629,7 @@ static int vfat_build_slots(struct inode *dir, const unsigned char *name,
 	de->starthi = cpu_to_le16(cluster >> 16);
 	de->size = 0;
 out_free:
-	free_page(page);
+	__putname(uname);
 	return err;
 }
 
@@ -1003,7 +998,7 @@ static const struct inode_operations vfat_dir_inode_operations = {
 	.mkdir		= vfat_mkdir,
 	.rmdir		= vfat_rmdir,
 	.rename		= vfat_rename,
-	.setattr	= fat_notify_change,
+	.setattr	= fat_setattr,
 	.getattr	= fat_getattr,
 };
 
diff --git a/trunk/fs/xattr.c b/trunk/fs/xattr.c
index 89a942f07e1b..4706a8b1f495 100644
--- a/trunk/fs/xattr.c
+++ b/trunk/fs/xattr.c
@@ -67,7 +67,7 @@ xattr_permission(struct inode *inode, const char *name, int mask)
 }
 
 int
-vfs_setxattr(struct dentry *dentry, char *name, void *value,
+vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 		size_t size, int flags)
 {
 	struct inode *inode = dentry->d_inode;
@@ -131,7 +131,7 @@ xattr_getsecurity(struct inode *inode, const char *name, void *value,
 EXPORT_SYMBOL_GPL(xattr_getsecurity);
 
 ssize_t
-vfs_getxattr(struct dentry *dentry, char *name, void *value, size_t size)
+vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size)
 {
 	struct inode *inode = dentry->d_inode;
 	int error;
@@ -187,7 +187,7 @@ vfs_listxattr(struct dentry *d, char *list, size_t size)
 EXPORT_SYMBOL_GPL(vfs_listxattr);
 
 int
-vfs_removexattr(struct dentry *dentry, char *name)
+vfs_removexattr(struct dentry *dentry, const char *name)
 {
 	struct inode *inode = dentry->d_inode;
 	int error;
@@ -218,7 +218,7 @@ EXPORT_SYMBOL_GPL(vfs_removexattr);
  * Extended attribute SET operations
  */
 static long
-setxattr(struct dentry *d, char __user *name, void __user *value,
+setxattr(struct dentry *d, const char __user *name, const void __user *value,
 	 size_t size, int flags)
 {
 	int error;
@@ -252,8 +252,8 @@ setxattr(struct dentry *d, char __user *name, void __user *value,
 }
 
 asmlinkage long
-sys_setxattr(char __user *path, char __user *name, void __user *value,
-	     size_t size, int flags)
+sys_setxattr(const char __user *path, const char __user *name,
+	     const void __user *value, size_t size, int flags)
 {
 	struct nameidata nd;
 	int error;
@@ -271,8 +271,8 @@ sys_setxattr(char __user *path, char __user *name, void __user *value,
 }
 
 asmlinkage long
-sys_lsetxattr(char __user *path, char __user *name, void __user *value,
-	      size_t size, int flags)
+sys_lsetxattr(const char __user *path, const char __user *name,
+	      const void __user *value, size_t size, int flags)
 {
 	struct nameidata nd;
 	int error;
@@ -290,7 +290,7 @@ sys_lsetxattr(char __user *path, char __user *name, void __user *value,
 }
 
 asmlinkage long
-sys_fsetxattr(int fd, char __user *name, void __user *value,
+sys_fsetxattr(int fd, const char __user *name, const void __user *value,
 	      size_t size, int flags)
 {
 	struct file *f;
@@ -315,7 +315,8 @@ sys_fsetxattr(int fd, char __user *name, void __user *value,
  * Extended attribute GET operations
  */
 static ssize_t
-getxattr(struct dentry *d, char __user *name, void __user *value, size_t size)
+getxattr(struct dentry *d, const char __user *name, void __user *value,
+	 size_t size)
 {
 	ssize_t error;
 	void *kvalue = NULL;
@@ -349,8 +350,8 @@ getxattr(struct dentry *d, char __user *name, void __user *value, size_t size)
 }
 
 asmlinkage ssize_t
-sys_getxattr(char __user *path, char __user *name, void __user *value,
-	     size_t size)
+sys_getxattr(const char __user *path, const char __user *name,
+	     void __user *value, size_t size)
 {
 	struct nameidata nd;
 	ssize_t error;
@@ -364,7 +365,7 @@ sys_getxattr(char __user *path, char __user *name, void __user *value,
 }
 
 asmlinkage ssize_t
-sys_lgetxattr(char __user *path, char __user *name, void __user *value,
+sys_lgetxattr(const char __user *path, const char __user *name, void __user *value,
 	      size_t size)
 {
 	struct nameidata nd;
@@ -379,7 +380,7 @@ sys_lgetxattr(char __user *path, char __user *name, void __user *value,
 }
 
 asmlinkage ssize_t
-sys_fgetxattr(int fd, char __user *name, void __user *value, size_t size)
+sys_fgetxattr(int fd, const char __user *name, void __user *value, size_t size)
 {
 	struct file *f;
 	ssize_t error = -EBADF;
@@ -424,7 +425,7 @@ listxattr(struct dentry *d, char __user *list, size_t size)
 }
 
 asmlinkage ssize_t
-sys_listxattr(char __user *path, char __user *list, size_t size)
+sys_listxattr(const char __user *path, char __user *list, size_t size)
 {
 	struct nameidata nd;
 	ssize_t error;
@@ -438,7 +439,7 @@ sys_listxattr(char __user *path, char __user *list, size_t size)
 }
 
 asmlinkage ssize_t
-sys_llistxattr(char __user *path, char __user *list, size_t size)
+sys_llistxattr(const char __user *path, char __user *list, size_t size)
 {
 	struct nameidata nd;
 	ssize_t error;
@@ -470,7 +471,7 @@ sys_flistxattr(int fd, char __user *list, size_t size)
  * Extended attribute REMOVE operations
  */
 static long
-removexattr(struct dentry *d, char __user *name)
+removexattr(struct dentry *d, const char __user *name)
 {
 	int error;
 	char kname[XATTR_NAME_MAX + 1];
@@ -485,7 +486,7 @@ removexattr(struct dentry *d, char __user *name)
 }
 
 asmlinkage long
-sys_removexattr(char __user *path, char __user *name)
+sys_removexattr(const char __user *path, const char __user *name)
 {
 	struct nameidata nd;
 	int error;
@@ -503,7 +504,7 @@ sys_removexattr(char __user *path, char __user *name)
 }
 
 asmlinkage long
-sys_lremovexattr(char __user *path, char __user *name)
+sys_lremovexattr(const char __user *path, const char __user *name)
 {
 	struct nameidata nd;
 	int error;
@@ -521,7 +522,7 @@ sys_lremovexattr(char __user *path, char __user *name)
 }
 
 asmlinkage long
-sys_fremovexattr(int fd, char __user *name)
+sys_fremovexattr(int fd, const char __user *name)
 {
 	struct file *f;
 	struct dentry *dentry;
diff --git a/trunk/include/asm-alpha/bug.h b/trunk/include/asm-alpha/bug.h
index 39a3e2a5017d..695a5ee4b5d3 100644
--- a/trunk/include/asm-alpha/bug.h
+++ b/trunk/include/asm-alpha/bug.h
@@ -1,14 +1,24 @@
 #ifndef _ALPHA_BUG_H
 #define _ALPHA_BUG_H
 
+#include <linux/linkage.h>
+
 #ifdef CONFIG_BUG
 #include <asm/pal.h>
 
 /* ??? Would be nice to use .gprel32 here, but we can't be sure that the
    function loaded the GP, so this could fail in modules.  */
-#define BUG() \
-  __asm__ __volatile__("call_pal %0  # bugchk\n\t"".long %1\n\t.8byte %2" \
-		       : : "i" (PAL_bugchk), "i"(__LINE__), "i"(__FILE__))
+static inline void ATTRIB_NORET __BUG(const char *file, int line)
+{
+	__asm__ __volatile__(
+		"call_pal %0  # bugchk\n\t"
+		".long %1\n\t.8byte %2"
+		       : : "i" (PAL_bugchk), "i"(line), "i"(file));
+	for ( ; ; )
+		;
+}
+
+#define BUG() __BUG(__FILE__, __LINE__)
 
 #define HAVE_ARCH_BUG
 #endif
diff --git a/trunk/include/asm-alpha/byteorder.h b/trunk/include/asm-alpha/byteorder.h
index 7af2b8d25486..58e958fc7f1b 100644
--- a/trunk/include/asm-alpha/byteorder.h
+++ b/trunk/include/asm-alpha/byteorder.h
@@ -7,7 +7,7 @@
 
 #ifdef __GNUC__
 
-static __inline __attribute_const__ __u32 __arch__swab32(__u32 x)
+static inline __attribute_const__ __u32 __arch__swab32(__u32 x)
 {
 	/*
 	 * Unfortunately, we can't use the 6 instruction sequence
diff --git a/trunk/include/asm-alpha/pgtable.h b/trunk/include/asm-alpha/pgtable.h
index 99037b032357..05ce5fba43e3 100644
--- a/trunk/include/asm-alpha/pgtable.h
+++ b/trunk/include/asm-alpha/pgtable.h
@@ -268,6 +268,7 @@ extern inline int pte_write(pte_t pte)		{ return !(pte_val(pte) & _PAGE_FOW); }
 extern inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 extern inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 extern inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+extern inline int pte_special(pte_t pte)	{ return 0; }
 
 extern inline pte_t pte_wrprotect(pte_t pte)	{ pte_val(pte) |= _PAGE_FOW; return pte; }
 extern inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~(__DIRTY_BITS); return pte; }
@@ -275,6 +276,7 @@ extern inline pte_t pte_mkold(pte_t pte)	{ pte_val(pte) &= ~(__ACCESS_BITS); ret
 extern inline pte_t pte_mkwrite(pte_t pte)	{ pte_val(pte) &= ~_PAGE_FOW; return pte; }
 extern inline pte_t pte_mkdirty(pte_t pte)	{ pte_val(pte) |= __DIRTY_BITS; return pte; }
 extern inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= __ACCESS_BITS; return pte; }
+extern inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 #define PAGE_DIR_OFFSET(tsk,address) pgd_offset((tsk),(address))
 
diff --git a/trunk/include/asm-alpha/unaligned.h b/trunk/include/asm-alpha/unaligned.h
index a1d72846f61c..3787c60aed3f 100644
--- a/trunk/include/asm-alpha/unaligned.h
+++ b/trunk/include/asm-alpha/unaligned.h
@@ -1,6 +1,11 @@
-#ifndef __ALPHA_UNALIGNED_H
-#define __ALPHA_UNALIGNED_H
+#ifndef _ASM_ALPHA_UNALIGNED_H
+#define _ASM_ALPHA_UNALIGNED_H
 
-#include <asm-generic/unaligned.h>
+#include <linux/unaligned/le_struct.h>
+#include <linux/unaligned/be_byteshift.h>
+#include <linux/unaligned/generic.h>
 
-#endif
+#define get_unaligned __get_unaligned_le
+#define put_unaligned __put_unaligned_le
+
+#endif /* _ASM_ALPHA_UNALIGNED_H */
diff --git a/trunk/include/asm-arm/arch-sa1100/ide.h b/trunk/include/asm-arm/arch-sa1100/ide.h
index 98b10bcf9f1b..b14cbda01dc3 100644
--- a/trunk/include/asm-arm/arch-sa1100/ide.h
+++ b/trunk/include/asm-arm/arch-sa1100/ide.h
@@ -37,12 +37,12 @@ static inline void ide_init_hwif_ports(hw_regs_t *hw, unsigned long data_port,
 
 	memset(hw, 0, sizeof(*hw));
 
-	for (i = IDE_DATA_OFFSET; i <= IDE_STATUS_OFFSET; i++) {
-		hw->io_ports[i] = reg;
+	for (i = 0; i <= 7; i++) {
+		hw->io_ports_array[i] = reg;
 		reg += regincr;
 	}
 
-	hw->io_ports[IDE_CONTROL_OFFSET] = ctrl_port;
+	hw->io_ports.ctl_addr = ctrl_port;
 
 	if (irq)
 		*irq = 0;
diff --git a/trunk/include/asm-arm/pgtable.h b/trunk/include/asm-arm/pgtable.h
index 5e0182485d8c..5571c13c3f3b 100644
--- a/trunk/include/asm-arm/pgtable.h
+++ b/trunk/include/asm-arm/pgtable.h
@@ -260,6 +260,7 @@ extern struct page *empty_zero_page;
 #define pte_write(pte)		(pte_val(pte) & L_PTE_WRITE)
 #define pte_dirty(pte)		(pte_val(pte) & L_PTE_DIRTY)
 #define pte_young(pte)		(pte_val(pte) & L_PTE_YOUNG)
+#define pte_special(pte)	(0)
 
 /*
  * The following only works if pte_present() is not true.
@@ -280,6 +281,8 @@ PTE_BIT_FUNC(mkdirty,   |= L_PTE_DIRTY);
 PTE_BIT_FUNC(mkold,     &= ~L_PTE_YOUNG);
 PTE_BIT_FUNC(mkyoung,   |= L_PTE_YOUNG);
 
+static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
+
 /*
  * Mark the prot value as uncacheable and unbufferable.
  */
diff --git a/trunk/include/asm-arm/unaligned.h b/trunk/include/asm-arm/unaligned.h
index 5db03cf3b905..44593a894903 100644
--- a/trunk/include/asm-arm/unaligned.h
+++ b/trunk/include/asm-arm/unaligned.h
@@ -1,171 +1,9 @@
-#ifndef __ASM_ARM_UNALIGNED_H
-#define __ASM_ARM_UNALIGNED_H
+#ifndef _ASM_ARM_UNALIGNED_H
+#define _ASM_ARM_UNALIGNED_H
 
-#include <asm/types.h>
-
-extern int __bug_unaligned_x(const void *ptr);
-
-/*
- * What is the most efficient way of loading/storing an unaligned value?
- *
- * That is the subject of this file.  Efficiency here is defined as
- * minimum code size with minimum register usage for the common cases.
- * It is currently not believed that long longs are common, so we
- * trade efficiency for the chars, shorts and longs against the long
- * longs.
- *
- * Current stats with gcc 2.7.2.2 for these functions:
- *
- *	ptrsize	get:	code	regs	put:	code	regs
- *	1		1	1		1	2
- *	2		3	2		3	2
- *	4		7	3		7	3
- *	8		20	6		16	6
- *
- * gcc 2.95.1 seems to code differently:
- *
- *	ptrsize	get:	code	regs	put:	code	regs
- *	1		1	1		1	2
- *	2		3	2		3	2
- *	4		7	4		7	4
- *	8		19	8		15	6
- *
- * which may or may not be more efficient (depending upon whether
- * you can afford the extra registers).  Hopefully the gcc 2.95
- * is inteligent enough to decide if it is better to use the
- * extra register, but evidence so far seems to suggest otherwise.
- *
- * Unfortunately, gcc is not able to optimise the high word
- * out of long long >> 32, or the low word from long long << 32
- */
-
-#define __get_unaligned_2_le(__p)					\
-	(unsigned int)(__p[0] | __p[1] << 8)
-
-#define __get_unaligned_2_be(__p)					\
-	(unsigned int)(__p[0] << 8 | __p[1])
-
-#define __get_unaligned_4_le(__p)					\
-	(unsigned int)(__p[0] | __p[1] << 8 | __p[2] << 16 | __p[3] << 24)
-
-#define __get_unaligned_4_be(__p)					\
-	(unsigned int)(__p[0] << 24 | __p[1] << 16 | __p[2] << 8 | __p[3])
-
-#define __get_unaligned_8_le(__p)					\
-	((unsigned long long)__get_unaligned_4_le((__p+4)) << 32 |	\
-		__get_unaligned_4_le(__p))
-
-#define __get_unaligned_8_be(__p)					\
-	((unsigned long long)__get_unaligned_4_be(__p) << 32 |		\
-		__get_unaligned_4_be((__p+4)))
-
-#define __get_unaligned_le(ptr)						\
-	((__force typeof(*(ptr)))({					\
-		const __u8 *__p = (const __u8 *)(ptr);			\
-		__builtin_choose_expr(sizeof(*(ptr)) == 1, *__p,	\
-		  __builtin_choose_expr(sizeof(*(ptr)) == 2, __get_unaligned_2_le(__p),	\
-		  __builtin_choose_expr(sizeof(*(ptr)) == 4, __get_unaligned_4_le(__p),	\
-		  __builtin_choose_expr(sizeof(*(ptr)) == 8, __get_unaligned_8_le(__p),	\
-		    (void)__bug_unaligned_x(__p)))));			\
-	}))
-
-#define __get_unaligned_be(ptr)						\
-	((__force typeof(*(ptr)))({					\
-		const __u8 *__p = (const __u8 *)(ptr);			\
-		__builtin_choose_expr(sizeof(*(ptr)) == 1, *__p,	\
-		  __builtin_choose_expr(sizeof(*(ptr)) == 2, __get_unaligned_2_be(__p),	\
-		  __builtin_choose_expr(sizeof(*(ptr)) == 4, __get_unaligned_4_be(__p),	\
-		  __builtin_choose_expr(sizeof(*(ptr)) == 8, __get_unaligned_8_be(__p),	\
-		    (void)__bug_unaligned_x(__p)))));			\
-	}))
-
-
-static inline void __put_unaligned_2_le(__u32 __v, register __u8 *__p)
-{
-	*__p++ = __v;
-	*__p++ = __v >> 8;
-}
-
-static inline void __put_unaligned_2_be(__u32 __v, register __u8 *__p)
-{
-	*__p++ = __v >> 8;
-	*__p++ = __v;
-}
-
-static inline void __put_unaligned_4_le(__u32 __v, register __u8 *__p)
-{
-	__put_unaligned_2_le(__v >> 16, __p + 2);
-	__put_unaligned_2_le(__v, __p);
-}
-
-static inline void __put_unaligned_4_be(__u32 __v, register __u8 *__p)
-{
-	__put_unaligned_2_be(__v >> 16, __p);
-	__put_unaligned_2_be(__v, __p + 2);
-}
-
-static inline void __put_unaligned_8_le(const unsigned long long __v, register __u8 *__p)
-{
-	/*
-	 * tradeoff: 8 bytes of stack for all unaligned puts (2
-	 * instructions), or an extra register in the long long
-	 * case - go for the extra register.
-	 */
-	__put_unaligned_4_le(__v >> 32, __p+4);
-	__put_unaligned_4_le(__v, __p);
-}
-
-static inline void __put_unaligned_8_be(const unsigned long long __v, register __u8 *__p)
-{
-	/*
-	 * tradeoff: 8 bytes of stack for all unaligned puts (2
-	 * instructions), or an extra register in the long long
-	 * case - go for the extra register.
-	 */
-	__put_unaligned_4_be(__v >> 32, __p);
-	__put_unaligned_4_be(__v, __p+4);
-}
-
-/*
- * Try to store an unaligned value as efficiently as possible.
- */
-#define __put_unaligned_le(val,ptr)					\
-	({							\
-		(void)sizeof(*(ptr) = (val));			\
-		switch (sizeof(*(ptr))) {			\
-		case 1:						\
-			*(ptr) = (val);				\
-			break;					\
-		case 2: __put_unaligned_2_le((__force u16)(val),(__u8 *)(ptr));	\
-			break;					\
-		case 4:	__put_unaligned_4_le((__force u32)(val),(__u8 *)(ptr));	\
-			break;					\
-		case 8:	__put_unaligned_8_le((__force u64)(val),(__u8 *)(ptr)); \
-			break;					\
-		default: __bug_unaligned_x(ptr);		\
-			break;					\
-		}						\
-		(void) 0;					\
-	})
-
-#define __put_unaligned_be(val,ptr)					\
-	({							\
-		(void)sizeof(*(ptr) = (val));			\
-		switch (sizeof(*(ptr))) {			\
-		case 1:						\
-			*(ptr) = (val);				\
-			break;					\
-		case 2: __put_unaligned_2_be((__force u16)(val),(__u8 *)(ptr));	\
-			break;					\
-		case 4:	__put_unaligned_4_be((__force u32)(val),(__u8 *)(ptr));	\
-			break;					\
-		case 8:	__put_unaligned_8_be((__force u64)(val),(__u8 *)(ptr)); \
-			break;					\
-		default: __bug_unaligned_x(ptr);		\
-			break;					\
-		}						\
-		(void) 0;					\
-	})
+#include <linux/unaligned/le_byteshift.h>
+#include <linux/unaligned/be_byteshift.h>
+#include <linux/unaligned/generic.h>
 
 /*
  * Select endianness
@@ -178,4 +16,4 @@ static inline void __put_unaligned_8_be(const unsigned long long __v, register _
 #define put_unaligned	__put_unaligned_be
 #endif
 
-#endif
+#endif /* _ASM_ARM_UNALIGNED_H */
diff --git a/trunk/include/asm-avr32/pgtable.h b/trunk/include/asm-avr32/pgtable.h
index 3ae7b548fce7..c0e5e29417df 100644
--- a/trunk/include/asm-avr32/pgtable.h
+++ b/trunk/include/asm-avr32/pgtable.h
@@ -212,6 +212,10 @@ static inline int pte_young(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_ACCESSED;
 }
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
 
 /*
  * The following only work if pte_present() is not true.
@@ -252,6 +256,10 @@ static inline pte_t pte_mkyoung(pte_t pte)
 	set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED));
 	return pte;
 }
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return pte;
+}
 
 #define pmd_none(x)	(!pmd_val(x))
 #define pmd_present(x)	(pmd_val(x) & _PAGE_PRESENT)
diff --git a/trunk/include/asm-avr32/unaligned.h b/trunk/include/asm-avr32/unaligned.h
index 36f5fd430543..041877290470 100644
--- a/trunk/include/asm-avr32/unaligned.h
+++ b/trunk/include/asm-avr32/unaligned.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_AVR32_UNALIGNED_H
-#define __ASM_AVR32_UNALIGNED_H
+#ifndef _ASM_AVR32_UNALIGNED_H
+#define _ASM_AVR32_UNALIGNED_H
 
 /*
  * AVR32 can handle some unaligned accesses, depending on the
@@ -11,6 +11,11 @@
  * optimize word loads in general.
  */
 
-#include <asm-generic/unaligned.h>
+#include <linux/unaligned/be_struct.h>
+#include <linux/unaligned/le_byteshift.h>
+#include <linux/unaligned/generic.h>
 
-#endif /* __ASM_AVR32_UNALIGNED_H */
+#define get_unaligned	__get_unaligned_be
+#define put_unaligned	__put_unaligned_be
+
+#endif /* _ASM_AVR32_UNALIGNED_H */
diff --git a/trunk/include/asm-blackfin/unaligned.h b/trunk/include/asm-blackfin/unaligned.h
index 10081dc241ef..fd8a1d634945 100644
--- a/trunk/include/asm-blackfin/unaligned.h
+++ b/trunk/include/asm-blackfin/unaligned.h
@@ -1,6 +1,11 @@
-#ifndef __BFIN_UNALIGNED_H
-#define __BFIN_UNALIGNED_H
+#ifndef _ASM_BLACKFIN_UNALIGNED_H
+#define _ASM_BLACKFIN_UNALIGNED_H
 
-#include <asm-generic/unaligned.h>
+#include <linux/unaligned/le_struct.h>
+#include <linux/unaligned/be_byteshift.h>
+#include <linux/unaligned/generic.h>
 
-#endif				/* __BFIN_UNALIGNED_H */
+#define get_unaligned	__get_unaligned_le
+#define put_unaligned	__put_unaligned_le
+
+#endif /* _ASM_BLACKFIN_UNALIGNED_H */
diff --git a/trunk/include/asm-cris/arch-v10/ide.h b/trunk/include/asm-cris/arch-v10/ide.h
index ea34e0d0a388..5366e6239328 100644
--- a/trunk/include/asm-cris/arch-v10/ide.h
+++ b/trunk/include/asm-cris/arch-v10/ide.h
@@ -59,22 +59,19 @@ static inline void ide_init_hwif_ports(hw_regs_t *hw, unsigned long data_port, u
 	int i;
 
 	/* fill in ports for ATA addresses 0 to 7 */
-
-	for (i = IDE_DATA_OFFSET; i <= IDE_STATUS_OFFSET; i++) {
-		hw->io_ports[i] = data_port |
+	for (i = 0; i <= 7; i++) {
+		hw->io_ports_array[i] = data_port |
 			IO_FIELD(R_ATA_CTRL_DATA, addr, i) |
 			IO_STATE(R_ATA_CTRL_DATA, cs0, active);
 	}
 
 	/* the IDE control register is at ATA address 6, with CS1 active instead of CS0 */
-
-	hw->io_ports[IDE_CONTROL_OFFSET] = data_port |
+	hw->io_ports.ctl_addr = data_port |
 			IO_FIELD(R_ATA_CTRL_DATA, addr, 6) |
 			IO_STATE(R_ATA_CTRL_DATA, cs1, active);
 
 	/* whats this for ? */
-
-	hw->io_ports[IDE_IRQ_OFFSET] = 0;
+	hw->io_ports.irq_addr = 0;
 }
 
 static inline void ide_init_default_hwifs(void)
diff --git a/trunk/include/asm-cris/pgtable.h b/trunk/include/asm-cris/pgtable.h
index a2607575681b..829e7a7d9fb9 100644
--- a/trunk/include/asm-cris/pgtable.h
+++ b/trunk/include/asm-cris/pgtable.h
@@ -115,6 +115,7 @@ static inline int pte_write(pte_t pte)          { return pte_val(pte) & _PAGE_WR
 static inline int pte_dirty(pte_t pte)          { return pte_val(pte) & _PAGE_MODIFIED; }
 static inline int pte_young(pte_t pte)          { return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)           { return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
@@ -162,6 +163,7 @@ static inline pte_t pte_mkyoung(pte_t pte)
         }
         return pte;
 }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 /*
  * Conversion functions: convert a page and protection to a page entry,
@@ -229,7 +231,7 @@ static inline void pmd_set(pmd_t * pmdp, pte_t * ptep)
 #define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
 
 /* to find an entry in a page-table-directory */
-static inline pgd_t * pgd_offset(struct mm_struct * mm, unsigned long address)
+static inline pgd_t * pgd_offset(const struct mm_struct *mm, unsigned long address)
 {
 	return mm->pgd + pgd_index(address);
 }
diff --git a/trunk/include/asm-cris/unaligned.h b/trunk/include/asm-cris/unaligned.h
index 7fbbb399f6f1..7b3f3fec567c 100644
--- a/trunk/include/asm-cris/unaligned.h
+++ b/trunk/include/asm-cris/unaligned.h
@@ -1,16 +1,13 @@
-#ifndef __CRIS_UNALIGNED_H
-#define __CRIS_UNALIGNED_H
+#ifndef _ASM_CRIS_UNALIGNED_H
+#define _ASM_CRIS_UNALIGNED_H
 
 /*
  * CRIS can do unaligned accesses itself. 
- *
- * The strange macros are there to make sure these can't
- * be misused in a way that makes them not work on other
- * architectures where unaligned accesses aren't as simple.
  */
+#include <linux/unaligned/access_ok.h>
+#include <linux/unaligned/generic.h>
 
-#define get_unaligned(ptr) (*(ptr))
+#define get_unaligned	__get_unaligned_le
+#define put_unaligned	__put_unaligned_le
 
-#define put_unaligned(val, ptr) ((void)( *(ptr) = (val) ))
-
-#endif
+#endif /* _ASM_CRIS_UNALIGNED_H */
diff --git a/trunk/include/asm-frv/pgtable.h b/trunk/include/asm-frv/pgtable.h
index 4e219046fe42..83c51aba534b 100644
--- a/trunk/include/asm-frv/pgtable.h
+++ b/trunk/include/asm-frv/pgtable.h
@@ -380,6 +380,7 @@ static inline pmd_t *pmd_offset(pud_t *dir, unsigned long address)
 static inline int pte_dirty(pte_t pte)		{ return (pte).pte & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return (pte).pte & _PAGE_ACCESSED; }
 static inline int pte_write(pte_t pte)		{ return !((pte).pte & _PAGE_WP); }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_mkclean(pte_t pte)	{ (pte).pte &= ~_PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkold(pte_t pte)	{ (pte).pte &= ~_PAGE_ACCESSED; return pte; }
@@ -387,6 +388,7 @@ static inline pte_t pte_wrprotect(pte_t pte)	{ (pte).pte |= _PAGE_WP; return pte
 static inline pte_t pte_mkdirty(pte_t pte)	{ (pte).pte |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)	{ (pte).pte |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)	{ (pte).pte &= ~_PAGE_WP; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
diff --git a/trunk/include/asm-frv/unaligned.h b/trunk/include/asm-frv/unaligned.h
index dc8e9c9bf6bd..64ccc736f2d8 100644
--- a/trunk/include/asm-frv/unaligned.h
+++ b/trunk/include/asm-frv/unaligned.h
@@ -9,194 +9,14 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#ifndef _ASM_UNALIGNED_H
-#define _ASM_UNALIGNED_H
+#ifndef _ASM_FRV_UNALIGNED_H
+#define _ASM_FRV_UNALIGNED_H
 
+#include <linux/unaligned/le_byteshift.h>
+#include <linux/unaligned/be_byteshift.h>
+#include <linux/unaligned/generic.h>
 
-/*
- * Unaligned accesses on uClinux can't be performed in a fault handler - the
- * CPU detects them as imprecise exceptions making this impossible.
- *
- * With the FR451, however, they are precise, and so we used to fix them up in
- * the memory access fault handler.  However, instruction bundling make this
- * impractical.  So, now we fall back to using memcpy.
- */
-#ifdef CONFIG_MMU
-
-/*
- * The asm statement in the macros below is a way to get GCC to copy a
- * value from one variable to another without having any clue it's
- * actually doing so, so that it won't have any idea that the values
- * in the two variables are related.
- */
-
-#define get_unaligned(ptr) ({				\
-	typeof((*(ptr))) __x;				\
-	void *__ptrcopy;				\
-	asm("" : "=r" (__ptrcopy) : "0" (ptr));		\
-	memcpy(&__x, __ptrcopy, sizeof(*(ptr)));	\
-	__x;						\
-})
-
-#define put_unaligned(val, ptr) ({			\
-	typeof((*(ptr))) __x = (val);			\
-	void *__ptrcopy;				\
-	asm("" : "=r" (__ptrcopy) : "0" (ptr));		\
-	memcpy(__ptrcopy, &__x, sizeof(*(ptr)));	\
-})
-
-extern int handle_misalignment(unsigned long esr0, unsigned long ear0, unsigned long epcr0);
-
-#else
-
-#define get_unaligned(ptr)							\
-({										\
-	typeof(*(ptr)) x;							\
-	const char *__p = (const char *) (ptr);					\
-										\
-	switch (sizeof(x)) {							\
-	case 1:									\
-		x = *(ptr);							\
-		break;								\
-	case 2:									\
-	{									\
-		uint8_t a;							\
-		asm("	ldub%I2		%M2,%0		\n"			\
-		    "	ldub%I3.p	%M3,%1		\n"			\
-		    "	slli		%0,#8,%0	\n"			\
-		    "	or		%0,%1,%0	\n"			\
-		    : "=&r"(x), "=&r"(a)					\
-		    : "m"(__p[0]),  "m"(__p[1])					\
-		    );								\
-		break;								\
-	}									\
-										\
-	case 4:									\
-	{									\
-		uint8_t a;							\
-		asm("	ldub%I2		%M2,%0		\n"			\
-		    "	ldub%I3.p	%M3,%1		\n"			\
-		    "	slli		%0,#8,%0	\n"			\
-		    "	or		%0,%1,%0	\n"			\
-		    "	ldub%I4.p	%M4,%1		\n"			\
-		    "	slli		%0,#8,%0	\n"			\
-		    "	or		%0,%1,%0	\n"			\
-		    "	ldub%I5.p	%M5,%1		\n"			\
-		    "	slli		%0,#8,%0	\n"			\
-		    "	or		%0,%1,%0	\n"			\
-		    : "=&r"(x), "=&r"(a)					\
-		    : "m"(__p[0]),  "m"(__p[1]), "m"(__p[2]), "m"(__p[3])	\
-		    );								\
-		break;								\
-	}									\
-										\
-	case 8:									\
-	{									\
-		union { uint64_t x; u32 y[2]; } z;				\
-		uint8_t a;							\
-		asm("	ldub%I3		%M3,%0		\n"			\
-		    "	ldub%I4.p	%M4,%2		\n"			\
-		    "	slli		%0,#8,%0	\n"			\
-		    "	or		%0,%2,%0	\n"			\
-		    "	ldub%I5.p	%M5,%2		\n"			\
-		    "	slli		%0,#8,%0	\n"			\
-		    "	or		%0,%2,%0	\n"			\
-		    "	ldub%I6.p	%M6,%2		\n"			\
-		    "	slli		%0,#8,%0	\n"			\
-		    "	or		%0,%2,%0	\n"			\
-		    "	ldub%I7		%M7,%1		\n"			\
-		    "	ldub%I8.p	%M8,%2		\n"			\
-		    "	slli		%1,#8,%1	\n"			\
-		    "	or		%1,%2,%1	\n"			\
-		    "	ldub%I9.p	%M9,%2		\n"			\
-		    "	slli		%1,#8,%1	\n"			\
-		    "	or		%1,%2,%1	\n"			\
-		    "	ldub%I10.p	%M10,%2		\n"			\
-		    "	slli		%1,#8,%1	\n"			\
-		    "	or		%1,%2,%1	\n"			\
-		    : "=&r"(z.y[0]), "=&r"(z.y[1]), "=&r"(a)			\
-		    : "m"(__p[0]), "m"(__p[1]), "m"(__p[2]), "m"(__p[3]),	\
-		      "m"(__p[4]), "m"(__p[5]), "m"(__p[6]), "m"(__p[7])	\
-		    );								\
-		x = z.x;							\
-		break;								\
-	}									\
-										\
-	default:								\
-		x = 0;								\
-		BUG();								\
-		break;								\
-	}									\
-										\
-	x;									\
-})
-
-#define put_unaligned(val, ptr)								\
-do {											\
-	char *__p = (char *) (ptr);							\
-	int x;										\
-											\
-	switch (sizeof(*ptr)) {								\
-	case 2:										\
-	{										\
-		asm("	stb%I1.p	%0,%M1		\n"				\
-		    "	srli		%0,#8,%0	\n"				\
-		    "	stb%I2		%0,%M2		\n"				\
-		    : "=r"(x), "=m"(__p[1]),  "=m"(__p[0])				\
-		    : "0"(val)								\
-		    );									\
-		break;									\
-	}										\
-											\
-	case 4:										\
-	{										\
-		asm("	stb%I1.p	%0,%M1		\n"				\
-		    "	srli		%0,#8,%0	\n"				\
-		    "	stb%I2.p	%0,%M2		\n"				\
-		    "	srli		%0,#8,%0	\n"				\
-		    "	stb%I3.p	%0,%M3		\n"				\
-		    "	srli		%0,#8,%0	\n"				\
-		    "	stb%I4		%0,%M4		\n"				\
-		    : "=r"(x), "=m"(__p[3]),  "=m"(__p[2]), "=m"(__p[1]), "=m"(__p[0])	\
-		    : "0"(val)								\
-		    );									\
-		break;									\
-	}										\
-											\
-	case 8:										\
-	{										\
-		uint32_t __high, __low;							\
-		__high = (uint64_t)val >> 32;						\
-		__low = val & 0xffffffff;						\
-		asm("	stb%I2.p	%0,%M2		\n"				\
-		    "	srli		%0,#8,%0	\n"				\
-		    "	stb%I3.p	%0,%M3		\n"				\
-		    "	srli		%0,#8,%0	\n"				\
-		    "	stb%I4.p	%0,%M4		\n"				\
-		    "	srli		%0,#8,%0	\n"				\
-		    "	stb%I5.p	%0,%M5		\n"				\
-		    "	srli		%0,#8,%0	\n"				\
-		    "	stb%I6.p	%1,%M6		\n"				\
-		    "	srli		%1,#8,%1	\n"				\
-		    "	stb%I7.p	%1,%M7		\n"				\
-		    "	srli		%1,#8,%1	\n"				\
-		    "	stb%I8.p	%1,%M8		\n"				\
-		    "	srli		%1,#8,%1	\n"				\
-		    "	stb%I9		%1,%M9		\n"				\
-		    : "=&r"(__low), "=&r"(__high), "=m"(__p[7]), "=m"(__p[6]), 		\
-		      "=m"(__p[5]), "=m"(__p[4]), "=m"(__p[3]), "=m"(__p[2]), 		\
-		      "=m"(__p[1]), "=m"(__p[0])					\
-		    : "0"(__low), "1"(__high)						\
-		    );									\
-		break;									\
-	}										\
-											\
-        default:									\
-		*(ptr) = (val);								\
-		break;									\
-	}										\
-} while(0)
-
-#endif
+#define get_unaligned	__get_unaligned_be
+#define put_unaligned	__put_unaligned_be
 
-#endif
+#endif /* _ASM_FRV_UNALIGNED_H */
diff --git a/trunk/include/asm-generic/gpio.h b/trunk/include/asm-generic/gpio.h
index f29a502f4a6c..ecf675a59d21 100644
--- a/trunk/include/asm-generic/gpio.h
+++ b/trunk/include/asm-generic/gpio.h
@@ -16,7 +16,14 @@
 #define ARCH_NR_GPIOS		256
 #endif
 
+static inline int gpio_is_valid(int number)
+{
+	/* only some non-negative numbers are valid */
+	return ((unsigned)number) < ARCH_NR_GPIOS;
+}
+
 struct seq_file;
+struct module;
 
 /**
  * struct gpio_chip - abstract a GPIO controller
@@ -48,6 +55,7 @@ struct seq_file;
  */
 struct gpio_chip {
 	char			*label;
+	struct module		*owner;
 
 	int			(*direction_input)(struct gpio_chip *chip,
 						unsigned offset);
@@ -66,6 +74,7 @@ struct gpio_chip {
 
 extern const char *gpiochip_is_requested(struct gpio_chip *chip,
 			unsigned offset);
+extern int __init __must_check gpiochip_reserve(int start, int ngpio);
 
 /* add/remove chips */
 extern int gpiochip_add(struct gpio_chip *chip);
@@ -97,6 +106,12 @@ extern int __gpio_cansleep(unsigned gpio);
 
 #else
 
+static inline int gpio_is_valid(int number)
+{
+	/* only non-negative numbers are valid */
+	return number >= 0;
+}
+
 /* platforms that don't directly support access to GPIOs through I2C, SPI,
  * or other blocking infrastructure can use these wrappers.
  */
diff --git a/trunk/include/asm-generic/ioctl.h b/trunk/include/asm-generic/ioctl.h
index cd027298beb1..864181385579 100644
--- a/trunk/include/asm-generic/ioctl.h
+++ b/trunk/include/asm-generic/ioctl.h
@@ -21,8 +21,19 @@
  */
 #define _IOC_NRBITS	8
 #define _IOC_TYPEBITS	8
-#define _IOC_SIZEBITS	14
-#define _IOC_DIRBITS	2
+
+/*
+ * Let any architecture override either of the following before
+ * including this file.
+ */
+
+#ifndef _IOC_SIZEBITS
+# define _IOC_SIZEBITS	14
+#endif
+
+#ifndef _IOC_DIRBITS
+# define _IOC_DIRBITS	2
+#endif
 
 #define _IOC_NRMASK	((1 << _IOC_NRBITS)-1)
 #define _IOC_TYPEMASK	((1 << _IOC_TYPEBITS)-1)
@@ -35,11 +46,21 @@
 #define _IOC_DIRSHIFT	(_IOC_SIZESHIFT+_IOC_SIZEBITS)
 
 /*
- * Direction bits.
+ * Direction bits, which any architecture can choose to override
+ * before including this file.
  */
-#define _IOC_NONE	0U
-#define _IOC_WRITE	1U
-#define _IOC_READ	2U
+
+#ifndef _IOC_NONE
+# define _IOC_NONE	0U
+#endif
+
+#ifndef _IOC_WRITE
+# define _IOC_WRITE	1U
+#endif
+
+#ifndef _IOC_READ
+# define _IOC_READ	2U
+#endif
 
 #define _IOC(dir,type,nr,size) \
 	(((dir)  << _IOC_DIRSHIFT) | \
diff --git a/trunk/include/asm-generic/unaligned.h b/trunk/include/asm-generic/unaligned.h
deleted file mode 100644
index 2fe1b2e67f01..000000000000
--- a/trunk/include/asm-generic/unaligned.h
+++ /dev/null
@@ -1,124 +0,0 @@
-#ifndef _ASM_GENERIC_UNALIGNED_H_
-#define _ASM_GENERIC_UNALIGNED_H_
-
-/*
- * For the benefit of those who are trying to port Linux to another
- * architecture, here are some C-language equivalents. 
- *
- * This is based almost entirely upon Richard Henderson's
- * asm-alpha/unaligned.h implementation.  Some comments were
- * taken from David Mosberger's asm-ia64/unaligned.h header.
- */
-
-#include <linux/types.h>
-
-/* 
- * The main single-value unaligned transfer routines.
- */
-#define get_unaligned(ptr) \
-	__get_unaligned((ptr), sizeof(*(ptr)))
-#define put_unaligned(x,ptr) \
-	((void)sizeof(*(ptr)=(x)),\
-	__put_unaligned((__force __u64)(x), (ptr), sizeof(*(ptr))))
-
-/*
- * This function doesn't actually exist.  The idea is that when
- * someone uses the macros below with an unsupported size (datatype),
- * the linker will alert us to the problem via an unresolved reference
- * error.
- */
-extern void bad_unaligned_access_length(void) __attribute__((noreturn));
-
-struct __una_u64 { __u64 x __attribute__((packed)); };
-struct __una_u32 { __u32 x __attribute__((packed)); };
-struct __una_u16 { __u16 x __attribute__((packed)); };
-
-/*
- * Elemental unaligned loads 
- */
-
-static inline __u64 __uldq(const __u64 *addr)
-{
-	const struct __una_u64 *ptr = (const struct __una_u64 *) addr;
-	return ptr->x;
-}
-
-static inline __u32 __uldl(const __u32 *addr)
-{
-	const struct __una_u32 *ptr = (const struct __una_u32 *) addr;
-	return ptr->x;
-}
-
-static inline __u16 __uldw(const __u16 *addr)
-{
-	const struct __una_u16 *ptr = (const struct __una_u16 *) addr;
-	return ptr->x;
-}
-
-/*
- * Elemental unaligned stores 
- */
-
-static inline void __ustq(__u64 val, __u64 *addr)
-{
-	struct __una_u64 *ptr = (struct __una_u64 *) addr;
-	ptr->x = val;
-}
-
-static inline void __ustl(__u32 val, __u32 *addr)
-{
-	struct __una_u32 *ptr = (struct __una_u32 *) addr;
-	ptr->x = val;
-}
-
-static inline void __ustw(__u16 val, __u16 *addr)
-{
-	struct __una_u16 *ptr = (struct __una_u16 *) addr;
-	ptr->x = val;
-}
-
-#define __get_unaligned(ptr, size) ({		\
-	const void *__gu_p = ptr;		\
-	__u64 __val;				\
-	switch (size) {				\
-	case 1:					\
-		__val = *(const __u8 *)__gu_p;	\
-		break;				\
-	case 2:					\
-		__val = __uldw(__gu_p);		\
-		break;				\
-	case 4:					\
-		__val = __uldl(__gu_p);		\
-		break;				\
-	case 8:					\
-		__val = __uldq(__gu_p);		\
-		break;				\
-	default:				\
-		bad_unaligned_access_length();	\
-	};					\
-	(__force __typeof__(*(ptr)))__val;	\
-})
-
-#define __put_unaligned(val, ptr, size)		\
-({						\
-	void *__gu_p = ptr;			\
-	switch (size) {				\
-	case 1:					\
-		*(__u8 *)__gu_p = (__force __u8)val;		\
-	        break;				\
-	case 2:					\
-		__ustw((__force __u16)val, __gu_p);		\
-		break;				\
-	case 4:					\
-		__ustl((__force __u32)val, __gu_p);		\
-		break;				\
-	case 8:					\
-		__ustq(val, __gu_p);		\
-		break;				\
-	default:				\
-	    	bad_unaligned_access_length();	\
-	};					\
-	(void)0;				\
-})
-
-#endif /* _ASM_GENERIC_UNALIGNED_H */
diff --git a/trunk/include/asm-h8300/unaligned.h b/trunk/include/asm-h8300/unaligned.h
index ffb67f472070..b8d06c70c2da 100644
--- a/trunk/include/asm-h8300/unaligned.h
+++ b/trunk/include/asm-h8300/unaligned.h
@@ -1,15 +1,11 @@
-#ifndef __H8300_UNALIGNED_H
-#define __H8300_UNALIGNED_H
+#ifndef _ASM_H8300_UNALIGNED_H
+#define _ASM_H8300_UNALIGNED_H
 
+#include <linux/unaligned/be_memmove.h>
+#include <linux/unaligned/le_byteshift.h>
+#include <linux/unaligned/generic.h>
 
-/* Use memmove here, so gcc does not insert a __builtin_memcpy. */
+#define get_unaligned	__get_unaligned_be
+#define put_unaligned	__put_unaligned_be
 
-#define get_unaligned(ptr) \
-  ({ __typeof__(*(ptr)) __tmp; memmove(&__tmp, (ptr), sizeof(*(ptr))); __tmp; })
-
-#define put_unaligned(val, ptr)				\
-  ({ __typeof__(*(ptr)) __tmp = (val);			\
-     memmove((ptr), &__tmp, sizeof(*(ptr)));		\
-     (void)0; })
-
-#endif
+#endif /* _ASM_H8300_UNALIGNED_H */
diff --git a/trunk/include/asm-ia64/dma-mapping.h b/trunk/include/asm-ia64/dma-mapping.h
index f1735a22d0ea..9f0df9bd46b7 100644
--- a/trunk/include/asm-ia64/dma-mapping.h
+++ b/trunk/include/asm-ia64/dma-mapping.h
@@ -23,10 +23,30 @@ dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
 {
 	dma_free_coherent(dev, size, cpu_addr, dma_handle);
 }
-#define dma_map_single		platform_dma_map_single
-#define dma_map_sg		platform_dma_map_sg
-#define dma_unmap_single	platform_dma_unmap_single
-#define dma_unmap_sg		platform_dma_unmap_sg
+#define dma_map_single_attrs	platform_dma_map_single_attrs
+static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
+					size_t size, int dir)
+{
+	return dma_map_single_attrs(dev, cpu_addr, size, dir, NULL);
+}
+#define dma_map_sg_attrs	platform_dma_map_sg_attrs
+static inline int dma_map_sg(struct device *dev, struct scatterlist *sgl,
+			     int nents, int dir)
+{
+	return dma_map_sg_attrs(dev, sgl, nents, dir, NULL);
+}
+#define dma_unmap_single_attrs	platform_dma_unmap_single_attrs
+static inline void dma_unmap_single(struct device *dev, dma_addr_t cpu_addr,
+				    size_t size, int dir)
+{
+	return dma_unmap_single_attrs(dev, cpu_addr, size, dir, NULL);
+}
+#define dma_unmap_sg_attrs	platform_dma_unmap_sg_attrs
+static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sgl,
+				int nents, int dir)
+{
+	return dma_unmap_sg_attrs(dev, sgl, nents, dir, NULL);
+}
 #define dma_sync_single_for_cpu	platform_dma_sync_single_for_cpu
 #define dma_sync_sg_for_cpu	platform_dma_sync_sg_for_cpu
 #define dma_sync_single_for_device platform_dma_sync_single_for_device
diff --git a/trunk/include/asm-ia64/gcc_intrin.h b/trunk/include/asm-ia64/gcc_intrin.h
index de2ed2cbdd84..2fe292c275fe 100644
--- a/trunk/include/asm-ia64/gcc_intrin.h
+++ b/trunk/include/asm-ia64/gcc_intrin.h
@@ -21,6 +21,10 @@
 
 #define ia64_invala_fr(regnum)	asm volatile ("invala.e f%0" :: "i"(regnum))
 
+#define ia64_flushrs() asm volatile ("flushrs;;":::"memory")
+
+#define ia64_loadrs() asm volatile ("loadrs;;":::"memory")
+
 extern void ia64_bad_param_for_setreg (void);
 extern void ia64_bad_param_for_getreg (void);
 
@@ -517,6 +521,14 @@ do {										\
 #define ia64_ptrd(addr, size)						\
 	asm volatile ("ptr.d %0,%1" :: "r"(addr), "r"(size) : "memory")
 
+#define ia64_ttag(addr)							\
+({									  \
+	__u64 ia64_intri_res;						   \
+	asm volatile ("ttag %0=%1" : "=r"(ia64_intri_res) : "r" (addr));   \
+	ia64_intri_res;							 \
+})
+
+
 /* Values for lfhint in ia64_lfetch and ia64_lfetch_fault */
 
 #define ia64_lfhint_none   0
diff --git a/trunk/include/asm-ia64/hugetlb.h b/trunk/include/asm-ia64/hugetlb.h
new file mode 100644
index 000000000000..f28a9701f1cf
--- /dev/null
+++ b/trunk/include/asm-ia64/hugetlb.h
@@ -0,0 +1,79 @@
+#ifndef _ASM_IA64_HUGETLB_H
+#define _ASM_IA64_HUGETLB_H
+
+#include <asm/page.h>
+
+
+void hugetlb_free_pgd_range(struct mmu_gather **tlb, unsigned long addr,
+			    unsigned long end, unsigned long floor,
+			    unsigned long ceiling);
+
+int prepare_hugepage_range(unsigned long addr, unsigned long len);
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					 unsigned long addr,
+					 unsigned long len)
+{
+	return (REGION_NUMBER(addr) == RGN_HPAGE ||
+		REGION_NUMBER((addr)+(len)-1) == RGN_HPAGE);
+}
+
+static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
+{
+}
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+	set_pte_at(mm, addr, ptep, pte);
+}
+
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep)
+{
+	return ptep_get_and_clear(mm, addr, ptep);
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(mm, addr, ptep);
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+					     unsigned long addr, pte_t *ptep,
+					     pte_t pte, int dirty)
+{
+	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	return *ptep;
+}
+
+static inline int arch_prepare_hugepage(struct page *page)
+{
+	return 0;
+}
+
+static inline void arch_release_hugepage(struct page *page)
+{
+}
+
+#endif /* _ASM_IA64_HUGETLB_H */
diff --git a/trunk/include/asm-ia64/kvm.h b/trunk/include/asm-ia64/kvm.h
index 030d29b4b26b..eb2d3559d089 100644
--- a/trunk/include/asm-ia64/kvm.h
+++ b/trunk/include/asm-ia64/kvm.h
@@ -1,6 +1,205 @@
-#ifndef __LINUX_KVM_IA64_H
-#define __LINUX_KVM_IA64_H
+#ifndef __ASM_IA64_KVM_H
+#define __ASM_IA64_KVM_H
 
-/* ia64 does not support KVM */
+/*
+ * asm-ia64/kvm.h: kvm structure definitions  for ia64
+ *
+ * Copyright (C) 2007 Xiantao Zhang <xiantao.zhang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+
+#include <asm/types.h>
+#include <asm/fpu.h>
+
+#include <linux/ioctl.h>
+
+/* Architectural interrupt line count. */
+#define KVM_NR_INTERRUPTS 256
+
+#define KVM_IOAPIC_NUM_PINS  24
+
+struct kvm_ioapic_state {
+	__u64 base_address;
+	__u32 ioregsel;
+	__u32 id;
+	__u32 irr;
+	__u32 pad;
+	union {
+		__u64 bits;
+		struct {
+			__u8 vector;
+			__u8 delivery_mode:3;
+			__u8 dest_mode:1;
+			__u8 delivery_status:1;
+			__u8 polarity:1;
+			__u8 remote_irr:1;
+			__u8 trig_mode:1;
+			__u8 mask:1;
+			__u8 reserve:7;
+			__u8 reserved[4];
+			__u8 dest_id;
+		} fields;
+	} redirtbl[KVM_IOAPIC_NUM_PINS];
+};
+
+#define KVM_IRQCHIP_PIC_MASTER   0
+#define KVM_IRQCHIP_PIC_SLAVE    1
+#define KVM_IRQCHIP_IOAPIC       2
+
+#define KVM_CONTEXT_SIZE	8*1024
+
+union context {
+	/* 8K size */
+	char	dummy[KVM_CONTEXT_SIZE];
+	struct {
+		unsigned long       psr;
+		unsigned long       pr;
+		unsigned long       caller_unat;
+		unsigned long       pad;
+		unsigned long       gr[32];
+		unsigned long       ar[128];
+		unsigned long       br[8];
+		unsigned long       cr[128];
+		unsigned long       rr[8];
+		unsigned long       ibr[8];
+		unsigned long       dbr[8];
+		unsigned long       pkr[8];
+		struct ia64_fpreg   fr[128];
+	};
+};
+
+struct thash_data {
+	union {
+		struct {
+			unsigned long p    :  1; /* 0 */
+			unsigned long rv1  :  1; /* 1 */
+			unsigned long ma   :  3; /* 2-4 */
+			unsigned long a    :  1; /* 5 */
+			unsigned long d    :  1; /* 6 */
+			unsigned long pl   :  2; /* 7-8 */
+			unsigned long ar   :  3; /* 9-11 */
+			unsigned long ppn  : 38; /* 12-49 */
+			unsigned long rv2  :  2; /* 50-51 */
+			unsigned long ed   :  1; /* 52 */
+			unsigned long ig1  : 11; /* 53-63 */
+		};
+		struct {
+			unsigned long __rv1 : 53;     /* 0-52 */
+			unsigned long contiguous : 1; /*53 */
+			unsigned long tc : 1;         /* 54 TR or TC */
+			unsigned long cl : 1;
+			/* 55 I side or D side cache line */
+			unsigned long len  :  4;      /* 56-59 */
+			unsigned long io  : 1;	/* 60 entry is for io or not */
+			unsigned long nomap : 1;
+			/* 61 entry cann't be inserted into machine TLB.*/
+			unsigned long checked : 1;
+			/* 62 for VTLB/VHPT sanity check */
+			unsigned long invalid : 1;
+			/* 63 invalid entry */
+		};
+		unsigned long page_flags;
+	};                  /* same for VHPT and TLB */
+
+	union {
+		struct {
+			unsigned long rv3  :  2;
+			unsigned long ps   :  6;
+			unsigned long key  : 24;
+			unsigned long rv4  : 32;
+		};
+		unsigned long itir;
+	};
+	union {
+		struct {
+			unsigned long ig2  :  12;
+			unsigned long vpn  :  49;
+			unsigned long vrn  :   3;
+		};
+		unsigned long ifa;
+		unsigned long vadr;
+		struct {
+			unsigned long tag  :  63;
+			unsigned long ti   :  1;
+		};
+		unsigned long etag;
+	};
+	union {
+		struct thash_data *next;
+		unsigned long rid;
+		unsigned long gpaddr;
+	};
+};
+
+#define	NITRS	8
+#define NDTRS	8
+
+struct saved_vpd {
+	unsigned long  vhpi;
+	unsigned long  vgr[16];
+	unsigned long  vbgr[16];
+	unsigned long  vnat;
+	unsigned long  vbnat;
+	unsigned long  vcpuid[5];
+	unsigned long  vpsr;
+	unsigned long  vpr;
+	unsigned long  vcr[128];
+};
+
+struct kvm_regs {
+	char *saved_guest;
+	char *saved_stack;
+	struct saved_vpd vpd;
+	/*Arch-regs*/
+	int mp_state;
+	unsigned long vmm_rr;
+	/* TR and TC.  */
+	struct thash_data itrs[NITRS];
+	struct thash_data dtrs[NDTRS];
+	/* Bit is set if there is a tr/tc for the region.  */
+	unsigned char itr_regions;
+	unsigned char dtr_regions;
+	unsigned char tc_regions;
+
+	char irq_check;
+	unsigned long saved_itc;
+	unsigned long itc_check;
+	unsigned long timer_check;
+	unsigned long timer_pending;
+	unsigned long last_itc;
+
+	unsigned long vrr[8];
+	unsigned long ibr[8];
+	unsigned long dbr[8];
+	unsigned long insvc[4];		/* Interrupt in service.  */
+	unsigned long xtp;
+
+	unsigned long metaphysical_rr0; /* from kvm_arch (so is pinned) */
+	unsigned long metaphysical_rr4;	/* from kvm_arch (so is pinned) */
+	unsigned long metaphysical_saved_rr0; /* from kvm_arch          */
+	unsigned long metaphysical_saved_rr4; /* from kvm_arch          */
+	unsigned long fp_psr;       /*used for lazy float register */
+	unsigned long saved_gp;
+	/*for phycial  emulation */
+};
+
+struct kvm_sregs {
+};
+
+struct kvm_fpu {
+};
 
 #endif
diff --git a/trunk/include/asm-ia64/kvm_host.h b/trunk/include/asm-ia64/kvm_host.h
new file mode 100644
index 000000000000..c082c208c1f3
--- /dev/null
+++ b/trunk/include/asm-ia64/kvm_host.h
@@ -0,0 +1,524 @@
+/*
+ * kvm_host.h: used for kvm module, and hold ia64-specific sections.
+ *
+ * Copyright (C) 2007, Intel Corporation.
+ *
+ * Xiantao Zhang <xiantao.zhang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+
+#ifndef __ASM_KVM_HOST_H
+#define __ASM_KVM_HOST_H
+
+
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/kvm.h>
+#include <linux/kvm_para.h>
+#include <linux/kvm_types.h>
+
+#include <asm/pal.h>
+#include <asm/sal.h>
+
+#define KVM_MAX_VCPUS 4
+#define KVM_MEMORY_SLOTS 32
+/* memory slots that does not exposed to userspace */
+#define KVM_PRIVATE_MEM_SLOTS 4
+
+
+/* define exit reasons from vmm to kvm*/
+#define EXIT_REASON_VM_PANIC		0
+#define EXIT_REASON_MMIO_INSTRUCTION	1
+#define EXIT_REASON_PAL_CALL		2
+#define EXIT_REASON_SAL_CALL		3
+#define EXIT_REASON_SWITCH_RR6		4
+#define EXIT_REASON_VM_DESTROY		5
+#define EXIT_REASON_EXTERNAL_INTERRUPT	6
+#define EXIT_REASON_IPI			7
+#define EXIT_REASON_PTC_G		8
+
+/*Define vmm address space and vm data space.*/
+#define KVM_VMM_SIZE (16UL<<20)
+#define KVM_VMM_SHIFT 24
+#define KVM_VMM_BASE 0xD000000000000000UL
+#define VMM_SIZE (8UL<<20)
+
+/*
+ * Define vm_buffer, used by PAL Services, base address.
+ * Note: vmbuffer is in the VMM-BLOCK, the size must be < 8M
+ */
+#define KVM_VM_BUFFER_BASE (KVM_VMM_BASE + VMM_SIZE)
+#define KVM_VM_BUFFER_SIZE (8UL<<20)
+
+/*Define Virtual machine data layout.*/
+#define KVM_VM_DATA_SHIFT  24
+#define KVM_VM_DATA_SIZE (1UL << KVM_VM_DATA_SHIFT)
+#define KVM_VM_DATA_BASE (KVM_VMM_BASE + KVM_VMM_SIZE)
+
+
+#define KVM_P2M_BASE    KVM_VM_DATA_BASE
+#define KVM_P2M_OFS     0
+#define KVM_P2M_SIZE    (8UL << 20)
+
+#define KVM_VHPT_BASE   (KVM_P2M_BASE + KVM_P2M_SIZE)
+#define KVM_VHPT_OFS    KVM_P2M_SIZE
+#define KVM_VHPT_BLOCK_SIZE   (2UL << 20)
+#define VHPT_SHIFT      18
+#define VHPT_SIZE       (1UL << VHPT_SHIFT)
+#define VHPT_NUM_ENTRIES (1<<(VHPT_SHIFT-5))
+
+#define KVM_VTLB_BASE   (KVM_VHPT_BASE+KVM_VHPT_BLOCK_SIZE)
+#define KVM_VTLB_OFS    (KVM_VHPT_OFS+KVM_VHPT_BLOCK_SIZE)
+#define KVM_VTLB_BLOCK_SIZE   (1UL<<20)
+#define VTLB_SHIFT      17
+#define VTLB_SIZE       (1UL<<VTLB_SHIFT)
+#define VTLB_NUM_ENTRIES (1<<(VTLB_SHIFT-5))
+
+#define KVM_VPD_BASE   (KVM_VTLB_BASE+KVM_VTLB_BLOCK_SIZE)
+#define KVM_VPD_OFS    (KVM_VTLB_OFS+KVM_VTLB_BLOCK_SIZE)
+#define KVM_VPD_BLOCK_SIZE   (2UL<<20)
+#define VPD_SHIFT       16
+#define VPD_SIZE        (1UL<<VPD_SHIFT)
+
+#define KVM_VCPU_BASE   (KVM_VPD_BASE+KVM_VPD_BLOCK_SIZE)
+#define KVM_VCPU_OFS    (KVM_VPD_OFS+KVM_VPD_BLOCK_SIZE)
+#define KVM_VCPU_BLOCK_SIZE   (2UL<<20)
+#define VCPU_SHIFT 18
+#define VCPU_SIZE (1UL<<VCPU_SHIFT)
+#define MAX_VCPU_NUM KVM_VCPU_BLOCK_SIZE/VCPU_SIZE
+
+#define KVM_VM_BASE     (KVM_VCPU_BASE+KVM_VCPU_BLOCK_SIZE)
+#define KVM_VM_OFS      (KVM_VCPU_OFS+KVM_VCPU_BLOCK_SIZE)
+#define KVM_VM_BLOCK_SIZE     (1UL<<19)
+
+#define KVM_MEM_DIRTY_LOG_BASE (KVM_VM_BASE+KVM_VM_BLOCK_SIZE)
+#define KVM_MEM_DIRTY_LOG_OFS  (KVM_VM_OFS+KVM_VM_BLOCK_SIZE)
+#define KVM_MEM_DIRTY_LOG_SIZE (1UL<<19)
+
+/* Get vpd, vhpt, tlb, vcpu, base*/
+#define VPD_ADDR(n) (KVM_VPD_BASE+n*VPD_SIZE)
+#define VHPT_ADDR(n) (KVM_VHPT_BASE+n*VHPT_SIZE)
+#define VTLB_ADDR(n) (KVM_VTLB_BASE+n*VTLB_SIZE)
+#define VCPU_ADDR(n) (KVM_VCPU_BASE+n*VCPU_SIZE)
+
+/*IO section definitions*/
+#define IOREQ_READ      1
+#define IOREQ_WRITE     0
+
+#define STATE_IOREQ_NONE        0
+#define STATE_IOREQ_READY       1
+#define STATE_IOREQ_INPROCESS   2
+#define STATE_IORESP_READY      3
+
+/*Guest Physical address layout.*/
+#define GPFN_MEM        (0UL << 60) /* Guest pfn is normal mem */
+#define GPFN_FRAME_BUFFER   (1UL << 60) /* VGA framebuffer */
+#define GPFN_LOW_MMIO       (2UL << 60) /* Low MMIO range */
+#define GPFN_PIB        (3UL << 60) /* PIB base */
+#define GPFN_IOSAPIC        (4UL << 60) /* IOSAPIC base */
+#define GPFN_LEGACY_IO      (5UL << 60) /* Legacy I/O base */
+#define GPFN_GFW        (6UL << 60) /* Guest Firmware */
+#define GPFN_HIGH_MMIO      (7UL << 60) /* High MMIO range */
+
+#define GPFN_IO_MASK        (7UL << 60) /* Guest pfn is I/O type */
+#define GPFN_INV_MASK       (1UL << 63) /* Guest pfn is invalid */
+#define INVALID_MFN       (~0UL)
+#define MEM_G   (1UL << 30)
+#define MEM_M   (1UL << 20)
+#define MMIO_START       (3 * MEM_G)
+#define MMIO_SIZE        (512 * MEM_M)
+#define VGA_IO_START     0xA0000UL
+#define VGA_IO_SIZE      0x20000
+#define LEGACY_IO_START  (MMIO_START + MMIO_SIZE)
+#define LEGACY_IO_SIZE   (64 * MEM_M)
+#define IO_SAPIC_START   0xfec00000UL
+#define IO_SAPIC_SIZE    0x100000
+#define PIB_START 0xfee00000UL
+#define PIB_SIZE 0x200000
+#define GFW_START        (4 * MEM_G - 16 * MEM_M)
+#define GFW_SIZE         (16 * MEM_M)
+
+/*Deliver mode, defined for ioapic.c*/
+#define dest_Fixed IOSAPIC_FIXED
+#define dest_LowestPrio IOSAPIC_LOWEST_PRIORITY
+
+#define NMI_VECTOR      		2
+#define ExtINT_VECTOR       		0
+#define NULL_VECTOR     		(-1)
+#define IA64_SPURIOUS_INT_VECTOR    	0x0f
+
+#define VCPU_LID(v) (((u64)(v)->vcpu_id) << 24)
+
+/*
+ *Delivery mode
+ */
+#define SAPIC_DELIV_SHIFT      8
+#define SAPIC_FIXED            0x0
+#define SAPIC_LOWEST_PRIORITY  0x1
+#define SAPIC_PMI              0x2
+#define SAPIC_NMI              0x4
+#define SAPIC_INIT             0x5
+#define SAPIC_EXTINT           0x7
+
+/*
+ * vcpu->requests bit members for arch
+ */
+#define KVM_REQ_PTC_G		32
+#define KVM_REQ_RESUME		33
+
+#define KVM_PAGES_PER_HPAGE	1
+
+struct kvm;
+struct kvm_vcpu;
+struct kvm_guest_debug{
+};
+
+struct kvm_mmio_req {
+	uint64_t addr;          /*  physical address		*/
+	uint64_t size;          /*  size in bytes		*/
+	uint64_t data;          /*  data (or paddr of data)     */
+	uint8_t state:4;
+	uint8_t dir:1;          /*  1=read, 0=write             */
+};
+
+/*Pal data struct */
+struct kvm_pal_call{
+	/*In area*/
+	uint64_t gr28;
+	uint64_t gr29;
+	uint64_t gr30;
+	uint64_t gr31;
+	/*Out area*/
+	struct ia64_pal_retval ret;
+};
+
+/* Sal data structure */
+struct kvm_sal_call{
+	/*In area*/
+	uint64_t in0;
+	uint64_t in1;
+	uint64_t in2;
+	uint64_t in3;
+	uint64_t in4;
+	uint64_t in5;
+	uint64_t in6;
+	uint64_t in7;
+	struct sal_ret_values ret;
+};
+
+/*Guest change rr6*/
+struct kvm_switch_rr6 {
+	uint64_t old_rr;
+	uint64_t new_rr;
+};
+
+union ia64_ipi_a{
+	unsigned long val;
+	struct {
+		unsigned long rv  : 3;
+		unsigned long ir  : 1;
+		unsigned long eid : 8;
+		unsigned long id  : 8;
+		unsigned long ib_base : 44;
+	};
+};
+
+union ia64_ipi_d {
+	unsigned long val;
+	struct {
+		unsigned long vector : 8;
+		unsigned long dm  : 3;
+		unsigned long ig  : 53;
+	};
+};
+
+/*ipi check exit data*/
+struct kvm_ipi_data{
+	union ia64_ipi_a addr;
+	union ia64_ipi_d data;
+};
+
+/*global purge data*/
+struct kvm_ptc_g {
+	unsigned long vaddr;
+	unsigned long rr;
+	unsigned long ps;
+	struct kvm_vcpu *vcpu;
+};
+
+/*Exit control data */
+struct exit_ctl_data{
+	uint32_t exit_reason;
+	uint32_t vm_status;
+	union {
+		struct kvm_mmio_req	ioreq;
+		struct kvm_pal_call	pal_data;
+		struct kvm_sal_call	sal_data;
+		struct kvm_switch_rr6	rr_data;
+		struct kvm_ipi_data	ipi_data;
+		struct kvm_ptc_g	ptc_g_data;
+	} u;
+};
+
+union pte_flags {
+	unsigned long val;
+	struct {
+		unsigned long p    :  1; /*0      */
+		unsigned long      :  1; /* 1     */
+		unsigned long ma   :  3; /* 2-4   */
+		unsigned long a    :  1; /* 5     */
+		unsigned long d    :  1; /* 6     */
+		unsigned long pl   :  2; /* 7-8   */
+		unsigned long ar   :  3; /* 9-11  */
+		unsigned long ppn  : 38; /* 12-49 */
+		unsigned long      :  2; /* 50-51 */
+		unsigned long ed   :  1; /* 52    */
+	};
+};
+
+union ia64_pta {
+	unsigned long val;
+	struct {
+		unsigned long ve : 1;
+		unsigned long reserved0 : 1;
+		unsigned long size : 6;
+		unsigned long vf : 1;
+		unsigned long reserved1 : 6;
+		unsigned long base : 49;
+	};
+};
+
+struct thash_cb {
+	/* THASH base information */
+	struct thash_data	*hash; /* hash table pointer */
+	union ia64_pta		pta;
+	int           num;
+};
+
+struct kvm_vcpu_stat {
+};
+
+struct kvm_vcpu_arch {
+	int launched;
+	int last_exit;
+	int last_run_cpu;
+	int vmm_tr_slot;
+	int vm_tr_slot;
+
+#define KVM_MP_STATE_RUNNABLE          0
+#define KVM_MP_STATE_UNINITIALIZED     1
+#define KVM_MP_STATE_INIT_RECEIVED     2
+#define KVM_MP_STATE_HALTED            3
+	int mp_state;
+
+#define MAX_PTC_G_NUM			3
+	int ptc_g_count;
+	struct kvm_ptc_g ptc_g_data[MAX_PTC_G_NUM];
+
+	/*halt timer to wake up sleepy vcpus*/
+	struct hrtimer hlt_timer;
+	long ht_active;
+
+	struct kvm_lapic *apic;    /* kernel irqchip context */
+	struct vpd *vpd;
+
+	/* Exit data for vmm_transition*/
+	struct exit_ctl_data exit_data;
+
+	cpumask_t cache_coherent_map;
+
+	unsigned long vmm_rr;
+	unsigned long host_rr6;
+	unsigned long psbits[8];
+	unsigned long cr_iipa;
+	unsigned long cr_isr;
+	unsigned long vsa_base;
+	unsigned long dirty_log_lock_pa;
+	unsigned long __gp;
+	/* TR and TC.  */
+	struct thash_data itrs[NITRS];
+	struct thash_data dtrs[NDTRS];
+	/* Bit is set if there is a tr/tc for the region.  */
+	unsigned char itr_regions;
+	unsigned char dtr_regions;
+	unsigned char tc_regions;
+	/* purge all */
+	unsigned long ptce_base;
+	unsigned long ptce_count[2];
+	unsigned long ptce_stride[2];
+	/* itc/itm */
+	unsigned long last_itc;
+	long itc_offset;
+	unsigned long itc_check;
+	unsigned long timer_check;
+	unsigned long timer_pending;
+
+	unsigned long vrr[8];
+	unsigned long ibr[8];
+	unsigned long dbr[8];
+	unsigned long insvc[4];		/* Interrupt in service.  */
+	unsigned long xtp;
+
+	unsigned long metaphysical_rr0; /* from kvm_arch (so is pinned) */
+	unsigned long metaphysical_rr4;	/* from kvm_arch (so is pinned) */
+	unsigned long metaphysical_saved_rr0; /* from kvm_arch          */
+	unsigned long metaphysical_saved_rr4; /* from kvm_arch          */
+	unsigned long fp_psr;       /*used for lazy float register */
+	unsigned long saved_gp;
+	/*for phycial  emulation */
+	int mode_flags;
+	struct thash_cb vtlb;
+	struct thash_cb vhpt;
+	char irq_check;
+	char irq_new_pending;
+
+	unsigned long opcode;
+	unsigned long cause;
+	union context host;
+	union context guest;
+};
+
+struct kvm_vm_stat {
+	u64 remote_tlb_flush;
+};
+
+struct kvm_sal_data {
+	unsigned long boot_ip;
+	unsigned long boot_gp;
+};
+
+struct kvm_arch {
+	unsigned long	vm_base;
+	unsigned long	metaphysical_rr0;
+	unsigned long	metaphysical_rr4;
+	unsigned long	vmm_init_rr;
+	unsigned long	vhpt_base;
+	unsigned long	vtlb_base;
+	unsigned long 	vpd_base;
+	spinlock_t dirty_log_lock;
+	struct kvm_ioapic *vioapic;
+	struct kvm_vm_stat stat;
+	struct kvm_sal_data rdv_sal_data;
+};
+
+union cpuid3_t {
+	u64 value;
+	struct {
+		u64 number : 8;
+		u64 revision : 8;
+		u64 model : 8;
+		u64 family : 8;
+		u64 archrev : 8;
+		u64 rv : 24;
+	};
+};
+
+struct kvm_pt_regs {
+	/* The following registers are saved by SAVE_MIN: */
+	unsigned long b6;  /* scratch */
+	unsigned long b7;  /* scratch */
+
+	unsigned long ar_csd; /* used by cmp8xchg16 (scratch) */
+	unsigned long ar_ssd; /* reserved for future use (scratch) */
+
+	unsigned long r8;  /* scratch (return value register 0) */
+	unsigned long r9;  /* scratch (return value register 1) */
+	unsigned long r10; /* scratch (return value register 2) */
+	unsigned long r11; /* scratch (return value register 3) */
+
+	unsigned long cr_ipsr; /* interrupted task's psr */
+	unsigned long cr_iip;  /* interrupted task's instruction pointer */
+	unsigned long cr_ifs;  /* interrupted task's function state */
+
+	unsigned long ar_unat; /* interrupted task's NaT register (preserved) */
+	unsigned long ar_pfs;  /* prev function state  */
+	unsigned long ar_rsc;  /* RSE configuration */
+	/* The following two are valid only if cr_ipsr.cpl > 0: */
+	unsigned long ar_rnat;  /* RSE NaT */
+	unsigned long ar_bspstore; /* RSE bspstore */
+
+	unsigned long pr;  /* 64 predicate registers (1 bit each) */
+	unsigned long b0;  /* return pointer (bp) */
+	unsigned long loadrs;  /* size of dirty partition << 16 */
+
+	unsigned long r1;  /* the gp pointer */
+	unsigned long r12; /* interrupted task's memory stack pointer */
+	unsigned long r13; /* thread pointer */
+
+	unsigned long ar_fpsr;  /* floating point status (preserved) */
+	unsigned long r15;  /* scratch */
+
+	/* The remaining registers are NOT saved for system calls.  */
+	unsigned long r14;  /* scratch */
+	unsigned long r2;  /* scratch */
+	unsigned long r3;  /* scratch */
+	unsigned long r16;  /* scratch */
+	unsigned long r17;  /* scratch */
+	unsigned long r18;  /* scratch */
+	unsigned long r19;  /* scratch */
+	unsigned long r20;  /* scratch */
+	unsigned long r21;  /* scratch */
+	unsigned long r22;  /* scratch */
+	unsigned long r23;  /* scratch */
+	unsigned long r24;  /* scratch */
+	unsigned long r25;  /* scratch */
+	unsigned long r26;  /* scratch */
+	unsigned long r27;  /* scratch */
+	unsigned long r28;  /* scratch */
+	unsigned long r29;  /* scratch */
+	unsigned long r30;  /* scratch */
+	unsigned long r31;  /* scratch */
+	unsigned long ar_ccv;  /* compare/exchange value (scratch) */
+
+	/*
+	 * Floating point registers that the kernel considers scratch:
+	 */
+	struct ia64_fpreg f6;  /* scratch */
+	struct ia64_fpreg f7;  /* scratch */
+	struct ia64_fpreg f8;  /* scratch */
+	struct ia64_fpreg f9;  /* scratch */
+	struct ia64_fpreg f10;  /* scratch */
+	struct ia64_fpreg f11;  /* scratch */
+
+	unsigned long r4;  /* preserved */
+	unsigned long r5;  /* preserved */
+	unsigned long r6;  /* preserved */
+	unsigned long r7;  /* preserved */
+	unsigned long eml_unat;    /* used for emulating instruction */
+	unsigned long pad0;     /* alignment pad */
+};
+
+static inline struct kvm_pt_regs *vcpu_regs(struct kvm_vcpu *v)
+{
+	return (struct kvm_pt_regs *) ((unsigned long) v + IA64_STK_OFFSET) - 1;
+}
+
+typedef int kvm_vmm_entry(void);
+typedef void kvm_tramp_entry(union context *host, union context *guest);
+
+struct kvm_vmm_info{
+	struct module	*module;
+	kvm_vmm_entry 	*vmm_entry;
+	kvm_tramp_entry *tramp_entry;
+	unsigned long 	vmm_ivt;
+};
+
+int kvm_highest_pending_irq(struct kvm_vcpu *vcpu);
+int kvm_emulate_halt(struct kvm_vcpu *vcpu);
+int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);
+void kvm_sal_emul(struct kvm_vcpu *vcpu);
+
+#endif
diff --git a/trunk/include/asm-ia64/kvm_para.h b/trunk/include/asm-ia64/kvm_para.h
new file mode 100644
index 000000000000..9f9796bb3441
--- /dev/null
+++ b/trunk/include/asm-ia64/kvm_para.h
@@ -0,0 +1,29 @@
+#ifndef __IA64_KVM_PARA_H
+#define __IA64_KVM_PARA_H
+
+/*
+ * asm-ia64/kvm_para.h
+ *
+ * Copyright (C) 2007 Xiantao Zhang <xiantao.zhang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+
+static inline unsigned int kvm_arch_para_features(void)
+{
+	return 0;
+}
+
+#endif
diff --git a/trunk/include/asm-ia64/machvec.h b/trunk/include/asm-ia64/machvec.h
index c201a2020aa4..9f020eb825c5 100644
--- a/trunk/include/asm-ia64/machvec.h
+++ b/trunk/include/asm-ia64/machvec.h
@@ -22,6 +22,7 @@ struct pci_bus;
 struct task_struct;
 struct pci_dev;
 struct msi_desc;
+struct dma_attrs;
 
 typedef void ia64_mv_setup_t (char **);
 typedef void ia64_mv_cpu_init_t (void);
@@ -56,6 +57,11 @@ typedef void ia64_mv_dma_sync_sg_for_device (struct device *, struct scatterlist
 typedef int ia64_mv_dma_mapping_error (dma_addr_t dma_addr);
 typedef int ia64_mv_dma_supported (struct device *, u64);
 
+typedef dma_addr_t ia64_mv_dma_map_single_attrs (struct device *, void *, size_t, int, struct dma_attrs *);
+typedef void ia64_mv_dma_unmap_single_attrs (struct device *, dma_addr_t, size_t, int, struct dma_attrs *);
+typedef int ia64_mv_dma_map_sg_attrs (struct device *, struct scatterlist *, int, int, struct dma_attrs *);
+typedef void ia64_mv_dma_unmap_sg_attrs (struct device *, struct scatterlist *, int, int, struct dma_attrs *);
+
 /*
  * WARNING: The legacy I/O space is _architected_.  Platforms are
  * expected to follow this architected model (see Section 10.7 in the
@@ -136,10 +142,10 @@ extern void machvec_tlb_migrate_finish (struct mm_struct *);
 #  define platform_dma_init		ia64_mv.dma_init
 #  define platform_dma_alloc_coherent	ia64_mv.dma_alloc_coherent
 #  define platform_dma_free_coherent	ia64_mv.dma_free_coherent
-#  define platform_dma_map_single	ia64_mv.dma_map_single
-#  define platform_dma_unmap_single	ia64_mv.dma_unmap_single
-#  define platform_dma_map_sg		ia64_mv.dma_map_sg
-#  define platform_dma_unmap_sg		ia64_mv.dma_unmap_sg
+#  define platform_dma_map_single_attrs	ia64_mv.dma_map_single_attrs
+#  define platform_dma_unmap_single_attrs	ia64_mv.dma_unmap_single_attrs
+#  define platform_dma_map_sg_attrs	ia64_mv.dma_map_sg_attrs
+#  define platform_dma_unmap_sg_attrs	ia64_mv.dma_unmap_sg_attrs
 #  define platform_dma_sync_single_for_cpu ia64_mv.dma_sync_single_for_cpu
 #  define platform_dma_sync_sg_for_cpu	ia64_mv.dma_sync_sg_for_cpu
 #  define platform_dma_sync_single_for_device ia64_mv.dma_sync_single_for_device
@@ -190,10 +196,10 @@ struct ia64_machine_vector {
 	ia64_mv_dma_init *dma_init;
 	ia64_mv_dma_alloc_coherent *dma_alloc_coherent;
 	ia64_mv_dma_free_coherent *dma_free_coherent;
-	ia64_mv_dma_map_single *dma_map_single;
-	ia64_mv_dma_unmap_single *dma_unmap_single;
-	ia64_mv_dma_map_sg *dma_map_sg;
-	ia64_mv_dma_unmap_sg *dma_unmap_sg;
+	ia64_mv_dma_map_single_attrs *dma_map_single_attrs;
+	ia64_mv_dma_unmap_single_attrs *dma_unmap_single_attrs;
+	ia64_mv_dma_map_sg_attrs *dma_map_sg_attrs;
+	ia64_mv_dma_unmap_sg_attrs *dma_unmap_sg_attrs;
 	ia64_mv_dma_sync_single_for_cpu *dma_sync_single_for_cpu;
 	ia64_mv_dma_sync_sg_for_cpu *dma_sync_sg_for_cpu;
 	ia64_mv_dma_sync_single_for_device *dma_sync_single_for_device;
@@ -240,10 +246,10 @@ struct ia64_machine_vector {
 	platform_dma_init,			\
 	platform_dma_alloc_coherent,		\
 	platform_dma_free_coherent,		\
-	platform_dma_map_single,		\
-	platform_dma_unmap_single,		\
-	platform_dma_map_sg,			\
-	platform_dma_unmap_sg,			\
+	platform_dma_map_single_attrs,		\
+	platform_dma_unmap_single_attrs,	\
+	platform_dma_map_sg_attrs,		\
+	platform_dma_unmap_sg_attrs,		\
 	platform_dma_sync_single_for_cpu,	\
 	platform_dma_sync_sg_for_cpu,		\
 	platform_dma_sync_single_for_device,	\
@@ -292,9 +298,13 @@ extern ia64_mv_dma_init			swiotlb_init;
 extern ia64_mv_dma_alloc_coherent	swiotlb_alloc_coherent;
 extern ia64_mv_dma_free_coherent	swiotlb_free_coherent;
 extern ia64_mv_dma_map_single		swiotlb_map_single;
+extern ia64_mv_dma_map_single_attrs	swiotlb_map_single_attrs;
 extern ia64_mv_dma_unmap_single		swiotlb_unmap_single;
+extern ia64_mv_dma_unmap_single_attrs	swiotlb_unmap_single_attrs;
 extern ia64_mv_dma_map_sg		swiotlb_map_sg;
+extern ia64_mv_dma_map_sg_attrs		swiotlb_map_sg_attrs;
 extern ia64_mv_dma_unmap_sg		swiotlb_unmap_sg;
+extern ia64_mv_dma_unmap_sg_attrs	swiotlb_unmap_sg_attrs;
 extern ia64_mv_dma_sync_single_for_cpu	swiotlb_sync_single_for_cpu;
 extern ia64_mv_dma_sync_sg_for_cpu	swiotlb_sync_sg_for_cpu;
 extern ia64_mv_dma_sync_single_for_device swiotlb_sync_single_for_device;
@@ -340,17 +350,17 @@ extern ia64_mv_dma_supported		swiotlb_dma_supported;
 #ifndef platform_dma_free_coherent
 # define platform_dma_free_coherent	swiotlb_free_coherent
 #endif
-#ifndef platform_dma_map_single
-# define platform_dma_map_single	swiotlb_map_single
+#ifndef platform_dma_map_single_attrs
+# define platform_dma_map_single_attrs	swiotlb_map_single_attrs
 #endif
-#ifndef platform_dma_unmap_single
-# define platform_dma_unmap_single	swiotlb_unmap_single
+#ifndef platform_dma_unmap_single_attrs
+# define platform_dma_unmap_single_attrs	swiotlb_unmap_single_attrs
 #endif
-#ifndef platform_dma_map_sg
-# define platform_dma_map_sg		swiotlb_map_sg
+#ifndef platform_dma_map_sg_attrs
+# define platform_dma_map_sg_attrs	swiotlb_map_sg_attrs
 #endif
-#ifndef platform_dma_unmap_sg
-# define platform_dma_unmap_sg		swiotlb_unmap_sg
+#ifndef platform_dma_unmap_sg_attrs
+# define platform_dma_unmap_sg_attrs	swiotlb_unmap_sg_attrs
 #endif
 #ifndef platform_dma_sync_single_for_cpu
 # define platform_dma_sync_single_for_cpu	swiotlb_sync_single_for_cpu
diff --git a/trunk/include/asm-ia64/machvec_hpzx1.h b/trunk/include/asm-ia64/machvec_hpzx1.h
index e90daf9ce340..2f57f5144b9f 100644
--- a/trunk/include/asm-ia64/machvec_hpzx1.h
+++ b/trunk/include/asm-ia64/machvec_hpzx1.h
@@ -4,10 +4,10 @@
 extern ia64_mv_setup_t			dig_setup;
 extern ia64_mv_dma_alloc_coherent	sba_alloc_coherent;
 extern ia64_mv_dma_free_coherent	sba_free_coherent;
-extern ia64_mv_dma_map_single		sba_map_single;
-extern ia64_mv_dma_unmap_single		sba_unmap_single;
-extern ia64_mv_dma_map_sg		sba_map_sg;
-extern ia64_mv_dma_unmap_sg		sba_unmap_sg;
+extern ia64_mv_dma_map_single_attrs	sba_map_single_attrs;
+extern ia64_mv_dma_unmap_single_attrs	sba_unmap_single_attrs;
+extern ia64_mv_dma_map_sg_attrs		sba_map_sg_attrs;
+extern ia64_mv_dma_unmap_sg_attrs	sba_unmap_sg_attrs;
 extern ia64_mv_dma_supported		sba_dma_supported;
 extern ia64_mv_dma_mapping_error	sba_dma_mapping_error;
 
@@ -23,10 +23,10 @@ extern ia64_mv_dma_mapping_error	sba_dma_mapping_error;
 #define platform_dma_init			machvec_noop
 #define platform_dma_alloc_coherent		sba_alloc_coherent
 #define platform_dma_free_coherent		sba_free_coherent
-#define platform_dma_map_single			sba_map_single
-#define platform_dma_unmap_single		sba_unmap_single
-#define platform_dma_map_sg			sba_map_sg
-#define platform_dma_unmap_sg			sba_unmap_sg
+#define platform_dma_map_single_attrs		sba_map_single_attrs
+#define platform_dma_unmap_single_attrs		sba_unmap_single_attrs
+#define platform_dma_map_sg_attrs		sba_map_sg_attrs
+#define platform_dma_unmap_sg_attrs		sba_unmap_sg_attrs
 #define platform_dma_sync_single_for_cpu	machvec_dma_sync_single
 #define platform_dma_sync_sg_for_cpu		machvec_dma_sync_sg
 #define platform_dma_sync_single_for_device	machvec_dma_sync_single
diff --git a/trunk/include/asm-ia64/machvec_hpzx1_swiotlb.h b/trunk/include/asm-ia64/machvec_hpzx1_swiotlb.h
index f00a34a148ff..a842cdda827b 100644
--- a/trunk/include/asm-ia64/machvec_hpzx1_swiotlb.h
+++ b/trunk/include/asm-ia64/machvec_hpzx1_swiotlb.h
@@ -4,10 +4,10 @@
 extern ia64_mv_setup_t				dig_setup;
 extern ia64_mv_dma_alloc_coherent		hwsw_alloc_coherent;
 extern ia64_mv_dma_free_coherent		hwsw_free_coherent;
-extern ia64_mv_dma_map_single			hwsw_map_single;
-extern ia64_mv_dma_unmap_single			hwsw_unmap_single;
-extern ia64_mv_dma_map_sg			hwsw_map_sg;
-extern ia64_mv_dma_unmap_sg			hwsw_unmap_sg;
+extern ia64_mv_dma_map_single_attrs		hwsw_map_single_attrs;
+extern ia64_mv_dma_unmap_single_attrs		hwsw_unmap_single_attrs;
+extern ia64_mv_dma_map_sg_attrs			hwsw_map_sg_attrs;
+extern ia64_mv_dma_unmap_sg_attrs		hwsw_unmap_sg_attrs;
 extern ia64_mv_dma_supported			hwsw_dma_supported;
 extern ia64_mv_dma_mapping_error		hwsw_dma_mapping_error;
 extern ia64_mv_dma_sync_single_for_cpu		hwsw_sync_single_for_cpu;
@@ -28,10 +28,10 @@ extern ia64_mv_dma_sync_sg_for_device		hwsw_sync_sg_for_device;
 #define platform_dma_init			machvec_noop
 #define platform_dma_alloc_coherent		hwsw_alloc_coherent
 #define platform_dma_free_coherent		hwsw_free_coherent
-#define platform_dma_map_single			hwsw_map_single
-#define platform_dma_unmap_single		hwsw_unmap_single
-#define platform_dma_map_sg			hwsw_map_sg
-#define platform_dma_unmap_sg			hwsw_unmap_sg
+#define platform_dma_map_single_attrs		hwsw_map_single_attrs
+#define platform_dma_unmap_single_attrs		hwsw_unmap_single_attrs
+#define platform_dma_map_sg_attrs		hwsw_map_sg_attrs
+#define platform_dma_unmap_sg_attrs		hwsw_unmap_sg_attrs
 #define platform_dma_supported			hwsw_dma_supported
 #define platform_dma_mapping_error		hwsw_dma_mapping_error
 #define platform_dma_sync_single_for_cpu	hwsw_sync_single_for_cpu
diff --git a/trunk/include/asm-ia64/machvec_sn2.h b/trunk/include/asm-ia64/machvec_sn2.h
index 61439a7f5b08..781308ea7b88 100644
--- a/trunk/include/asm-ia64/machvec_sn2.h
+++ b/trunk/include/asm-ia64/machvec_sn2.h
@@ -57,10 +57,10 @@ extern ia64_mv_readl_t __sn_readl_relaxed;
 extern ia64_mv_readq_t __sn_readq_relaxed;
 extern ia64_mv_dma_alloc_coherent	sn_dma_alloc_coherent;
 extern ia64_mv_dma_free_coherent	sn_dma_free_coherent;
-extern ia64_mv_dma_map_single		sn_dma_map_single;
-extern ia64_mv_dma_unmap_single		sn_dma_unmap_single;
-extern ia64_mv_dma_map_sg		sn_dma_map_sg;
-extern ia64_mv_dma_unmap_sg		sn_dma_unmap_sg;
+extern ia64_mv_dma_map_single_attrs	sn_dma_map_single_attrs;
+extern ia64_mv_dma_unmap_single_attrs	sn_dma_unmap_single_attrs;
+extern ia64_mv_dma_map_sg_attrs		sn_dma_map_sg_attrs;
+extern ia64_mv_dma_unmap_sg_attrs	sn_dma_unmap_sg_attrs;
 extern ia64_mv_dma_sync_single_for_cpu	sn_dma_sync_single_for_cpu;
 extern ia64_mv_dma_sync_sg_for_cpu	sn_dma_sync_sg_for_cpu;
 extern ia64_mv_dma_sync_single_for_device sn_dma_sync_single_for_device;
@@ -113,10 +113,10 @@ extern ia64_mv_pci_fixup_bus_t		sn_pci_fixup_bus;
 #define platform_dma_init		machvec_noop
 #define platform_dma_alloc_coherent	sn_dma_alloc_coherent
 #define platform_dma_free_coherent	sn_dma_free_coherent
-#define platform_dma_map_single		sn_dma_map_single
-#define platform_dma_unmap_single	sn_dma_unmap_single
-#define platform_dma_map_sg		sn_dma_map_sg
-#define platform_dma_unmap_sg		sn_dma_unmap_sg
+#define platform_dma_map_single_attrs	sn_dma_map_single_attrs
+#define platform_dma_unmap_single_attrs	sn_dma_unmap_single_attrs
+#define platform_dma_map_sg_attrs	sn_dma_map_sg_attrs
+#define platform_dma_unmap_sg_attrs	sn_dma_unmap_sg_attrs
 #define platform_dma_sync_single_for_cpu sn_dma_sync_single_for_cpu
 #define platform_dma_sync_sg_for_cpu	sn_dma_sync_sg_for_cpu
 #define platform_dma_sync_single_for_device sn_dma_sync_single_for_device
diff --git a/trunk/include/asm-ia64/page.h b/trunk/include/asm-ia64/page.h
index 4999a6c63775..36f39321b768 100644
--- a/trunk/include/asm-ia64/page.h
+++ b/trunk/include/asm-ia64/page.h
@@ -54,9 +54,6 @@
 # define HPAGE_MASK		(~(HPAGE_SIZE - 1))
 
 # define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
-# define ARCH_HAS_HUGEPAGE_ONLY_RANGE
-# define ARCH_HAS_PREPARE_HUGEPAGE_RANGE
-# define ARCH_HAS_HUGETLB_FREE_PGD_RANGE
 #endif /* CONFIG_HUGETLB_PAGE */
 
 #ifdef __ASSEMBLY__
@@ -153,9 +150,6 @@ typedef union ia64_va {
 # define htlbpage_to_page(x)	(((unsigned long) REGION_NUMBER(x) << 61)			\
 				 | (REGION_OFFSET(x) >> (HPAGE_SHIFT-PAGE_SHIFT)))
 # define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
-# define is_hugepage_only_range(mm, addr, len)		\
-	 (REGION_NUMBER(addr) == RGN_HPAGE ||	\
-	  REGION_NUMBER((addr)+(len)-1) == RGN_HPAGE)
 extern unsigned int hpage_shift;
 #endif
 
diff --git a/trunk/include/asm-ia64/pgtable.h b/trunk/include/asm-ia64/pgtable.h
index ed70862ea247..7a9bff47564f 100644
--- a/trunk/include/asm-ia64/pgtable.h
+++ b/trunk/include/asm-ia64/pgtable.h
@@ -302,6 +302,8 @@ ia64_phys_addr_valid (unsigned long addr)
 #define pte_dirty(pte)		((pte_val(pte) & _PAGE_D) != 0)
 #define pte_young(pte)		((pte_val(pte) & _PAGE_A) != 0)
 #define pte_file(pte)		((pte_val(pte) & _PAGE_FILE) != 0)
+#define pte_special(pte)	0
+
 /*
  * Note: we convert AR_RWX to AR_RX and AR_RW to AR_R by clearing the 2nd bit in the
  * access rights:
@@ -313,6 +315,7 @@ ia64_phys_addr_valid (unsigned long addr)
 #define pte_mkclean(pte)	(__pte(pte_val(pte) & ~_PAGE_D))
 #define pte_mkdirty(pte)	(__pte(pte_val(pte) | _PAGE_D))
 #define pte_mkhuge(pte)		(__pte(pte_val(pte)))
+#define pte_mkspecial(pte)	(pte)
 
 /*
  * Because ia64's Icache and Dcache is not coherent (on a cpu), we need to
diff --git a/trunk/include/asm-ia64/processor.h b/trunk/include/asm-ia64/processor.h
index 741f7ecb986a..6aff126fc07e 100644
--- a/trunk/include/asm-ia64/processor.h
+++ b/trunk/include/asm-ia64/processor.h
@@ -119,6 +119,69 @@ struct ia64_psr {
 	__u64 reserved4 : 19;
 };
 
+union ia64_isr {
+	__u64  val;
+	struct {
+		__u64 code : 16;
+		__u64 vector : 8;
+		__u64 reserved1 : 8;
+		__u64 x : 1;
+		__u64 w : 1;
+		__u64 r : 1;
+		__u64 na : 1;
+		__u64 sp : 1;
+		__u64 rs : 1;
+		__u64 ir : 1;
+		__u64 ni : 1;
+		__u64 so : 1;
+		__u64 ei : 2;
+		__u64 ed : 1;
+		__u64 reserved2 : 20;
+	};
+};
+
+union ia64_lid {
+	__u64 val;
+	struct {
+		__u64  rv  : 16;
+		__u64  eid : 8;
+		__u64  id  : 8;
+		__u64  ig  : 32;
+	};
+};
+
+union ia64_tpr {
+	__u64 val;
+	struct {
+		__u64 ig0 : 4;
+		__u64 mic : 4;
+		__u64 rsv : 8;
+		__u64 mmi : 1;
+		__u64 ig1 : 47;
+	};
+};
+
+union ia64_itir {
+	__u64 val;
+	struct {
+		__u64 rv3  :  2; /* 0-1 */
+		__u64 ps   :  6; /* 2-7 */
+		__u64 key  : 24; /* 8-31 */
+		__u64 rv4  : 32; /* 32-63 */
+	};
+};
+
+union  ia64_rr {
+	__u64 val;
+	struct {
+		__u64  ve	:  1;  /* enable hw walker */
+		__u64  reserved0:  1;  /* reserved */
+		__u64  ps	:  6;  /* log page size */
+		__u64  rid	: 24;  /* region id */
+		__u64  reserved1: 32;  /* reserved */
+	};
+};
+
 /*
  * CPU type, hardware bug flags, and per-CPU state.  Frequently used
  * state comes earlier:
diff --git a/trunk/include/asm-ia64/system.h b/trunk/include/asm-ia64/system.h
index dff8128fa58e..26e250bfb912 100644
--- a/trunk/include/asm-ia64/system.h
+++ b/trunk/include/asm-ia64/system.h
@@ -146,23 +146,23 @@ do {						\
 
 # define local_irq_save(x)					\
 do {								\
-	unsigned long psr;					\
+	unsigned long __psr;					\
 								\
-	__local_irq_save(psr);					\
-	if (psr & IA64_PSR_I)					\
+	__local_irq_save(__psr);				\
+	if (__psr & IA64_PSR_I)					\
 		__save_ip();					\
-	(x) = psr;						\
+	(x) = __psr;						\
 } while (0)
 
-# define local_irq_disable()	do { unsigned long x; local_irq_save(x); } while (0)
+# define local_irq_disable()	do { unsigned long __x; local_irq_save(__x); } while (0)
 
 # define local_irq_restore(x)					\
 do {								\
-	unsigned long old_psr, psr = (x);			\
+	unsigned long __old_psr, __psr = (x);			\
 								\
-	local_save_flags(old_psr);				\
-	__local_irq_restore(psr);				\
-	if ((old_psr & IA64_PSR_I) && !(psr & IA64_PSR_I))	\
+	local_save_flags(__old_psr);				\
+	__local_irq_restore(__psr);				\
+	if ((__old_psr & IA64_PSR_I) && !(__psr & IA64_PSR_I))	\
 		__save_ip();					\
 } while (0)
 
diff --git a/trunk/include/asm-ia64/unaligned.h b/trunk/include/asm-ia64/unaligned.h
index bb8559888103..7bddc7f58584 100644
--- a/trunk/include/asm-ia64/unaligned.h
+++ b/trunk/include/asm-ia64/unaligned.h
@@ -1,6 +1,11 @@
 #ifndef _ASM_IA64_UNALIGNED_H
 #define _ASM_IA64_UNALIGNED_H
 
-#include <asm-generic/unaligned.h>
+#include <linux/unaligned/le_struct.h>
+#include <linux/unaligned/be_byteshift.h>
+#include <linux/unaligned/generic.h>
+
+#define get_unaligned	__get_unaligned_le
+#define put_unaligned	__put_unaligned_le
 
 #endif /* _ASM_IA64_UNALIGNED_H */
diff --git a/trunk/include/asm-m32r/pgtable.h b/trunk/include/asm-m32r/pgtable.h
index 86505387be08..e6359c566b50 100644
--- a/trunk/include/asm-m32r/pgtable.h
+++ b/trunk/include/asm-m32r/pgtable.h
@@ -214,6 +214,11 @@ static inline int pte_file(pte_t pte)
 	return pte_val(pte) & _PAGE_FILE;
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 static inline pte_t pte_mkclean(pte_t pte)
 {
 	pte_val(pte) &= ~_PAGE_DIRTY;
@@ -250,6 +255,11 @@ static inline pte_t pte_mkwrite(pte_t pte)
 	return pte;
 }
 
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return pte;
+}
+
 static inline  int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
 	return test_and_clear_bit(_PAGE_BIT_ACCESSED, ptep);
diff --git a/trunk/include/asm-m32r/unaligned.h b/trunk/include/asm-m32r/unaligned.h
index fccc180c3913..377eb20d1ec6 100644
--- a/trunk/include/asm-m32r/unaligned.h
+++ b/trunk/include/asm-m32r/unaligned.h
@@ -1,19 +1,18 @@
 #ifndef _ASM_M32R_UNALIGNED_H
 #define _ASM_M32R_UNALIGNED_H
 
-/*
- * For the benefit of those who are trying to port Linux to another
- * architecture, here are some C-language equivalents.
- */
-
-#include <asm/string.h>
-
-#define get_unaligned(ptr) \
-  ({ __typeof__(*(ptr)) __tmp; memmove(&__tmp, (ptr), sizeof(*(ptr))); __tmp; })
-
-#define put_unaligned(val, ptr)				\
-  ({ __typeof__(*(ptr)) __tmp = (val);			\
-     memmove((ptr), &__tmp, sizeof(*(ptr)));		\
-     (void)0; })
+#if defined(__LITTLE_ENDIAN__)
+# include <linux/unaligned/le_memmove.h>
+# include <linux/unaligned/be_byteshift.h>
+# include <linux/unaligned/generic.h>
+# define get_unaligned	__get_unaligned_le
+# define put_unaligned	__put_unaligned_le
+#else
+# include <linux/unaligned/be_memmove.h>
+# include <linux/unaligned/le_byteshift.h>
+# include <linux/unaligned/generic.h>
+# define get_unaligned	__get_unaligned_be
+# define put_unaligned	__put_unaligned_be
+#endif
 
 #endif /* _ASM_M32R_UNALIGNED_H */
diff --git a/trunk/include/asm-m68k/motorola_pgtable.h b/trunk/include/asm-m68k/motorola_pgtable.h
index 13135d4821d8..8e9a8a754dde 100644
--- a/trunk/include/asm-m68k/motorola_pgtable.h
+++ b/trunk/include/asm-m68k/motorola_pgtable.h
@@ -168,6 +168,7 @@ static inline int pte_write(pte_t pte)		{ return !(pte_val(pte) & _PAGE_RONLY);
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_wrprotect(pte_t pte)	{ pte_val(pte) |= _PAGE_RONLY; return pte; }
 static inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~_PAGE_DIRTY; return pte; }
@@ -185,6 +186,7 @@ static inline pte_t pte_mkcache(pte_t pte)
 	pte_val(pte) = (pte_val(pte) & _CACHEMASK040) | m68k_supervisor_cachemode;
 	return pte;
 }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 #define PAGE_DIR_OFFSET(tsk,address) pgd_offset((tsk),(address))
 
diff --git a/trunk/include/asm-m68k/sun3_pgtable.h b/trunk/include/asm-m68k/sun3_pgtable.h
index b766fc261bde..f847ec732d62 100644
--- a/trunk/include/asm-m68k/sun3_pgtable.h
+++ b/trunk/include/asm-m68k/sun3_pgtable.h
@@ -169,6 +169,7 @@ static inline int pte_write(pte_t pte)		{ return pte_val(pte) & SUN3_PAGE_WRITEA
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & SUN3_PAGE_MODIFIED; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & SUN3_PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & SUN3_PAGE_ACCESSED; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_wrprotect(pte_t pte)	{ pte_val(pte) &= ~SUN3_PAGE_WRITEABLE; return pte; }
 static inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~SUN3_PAGE_MODIFIED; return pte; }
@@ -181,6 +182,7 @@ static inline pte_t pte_mknocache(pte_t pte)	{ pte_val(pte) |= SUN3_PAGE_NOCACHE
 //static inline pte_t pte_mkcache(pte_t pte)	{ pte_val(pte) &= SUN3_PAGE_NOCACHE; return pte; }
 // until then, use:
 static inline pte_t pte_mkcache(pte_t pte)	{ return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t kernel_pg_dir[PTRS_PER_PGD];
diff --git a/trunk/include/asm-m68k/unaligned.h b/trunk/include/asm-m68k/unaligned.h
index 804cb3f888fe..77698f2dc33c 100644
--- a/trunk/include/asm-m68k/unaligned.h
+++ b/trunk/include/asm-m68k/unaligned.h
@@ -1,16 +1,13 @@
-#ifndef __M68K_UNALIGNED_H
-#define __M68K_UNALIGNED_H
+#ifndef _ASM_M68K_UNALIGNED_H
+#define _ASM_M68K_UNALIGNED_H
 
 /*
  * The m68k can do unaligned accesses itself.
- *
- * The strange macros are there to make sure these can't
- * be misused in a way that makes them not work on other
- * architectures where unaligned accesses aren't as simple.
  */
+#include <linux/unaligned/access_ok.h>
+#include <linux/unaligned/generic.h>
 
-#define get_unaligned(ptr) (*(ptr))
+#define get_unaligned	__get_unaligned_be
+#define put_unaligned	__put_unaligned_be
 
-#define put_unaligned(val, ptr) ((void)( *(ptr) = (val) ))
-
-#endif
+#endif /* _ASM_M68K_UNALIGNED_H */
diff --git a/trunk/include/asm-m68knommu/unaligned.h b/trunk/include/asm-m68knommu/unaligned.h
index 869e9dd24f54..eb1ea4cb9a59 100644
--- a/trunk/include/asm-m68knommu/unaligned.h
+++ b/trunk/include/asm-m68knommu/unaligned.h
@@ -1,23 +1,25 @@
-#ifndef __M68K_UNALIGNED_H
-#define __M68K_UNALIGNED_H
+#ifndef _ASM_M68KNOMMU_UNALIGNED_H
+#define _ASM_M68KNOMMU_UNALIGNED_H
 
 
 #ifdef CONFIG_COLDFIRE
+#include <linux/unaligned/be_struct.h>
+#include <linux/unaligned/le_byteshift.h>
+#include <linux/unaligned/generic.h>
 
-#include <asm-generic/unaligned.h>
+#define get_unaligned	__get_unaligned_be
+#define put_unaligned	__put_unaligned_be
 
 #else
 /*
  * The m68k can do unaligned accesses itself. 
- *
- * The strange macros are there to make sure these can't
- * be misused in a way that makes them not work on other
- * architectures where unaligned accesses aren't as simple.
  */
+#include <linux/unaligned/access_ok.h>
+#include <linux/unaligned/generic.h>
 
-#define get_unaligned(ptr) (*(ptr))
-#define put_unaligned(val, ptr) ((void)( *(ptr) = (val) ))
+#define get_unaligned	__get_unaligned_be
+#define put_unaligned	__put_unaligned_be
 
 #endif
 
-#endif
+#endif /* _ASM_M68KNOMMU_UNALIGNED_H */
diff --git a/trunk/include/asm-mips/cmp.h b/trunk/include/asm-mips/cmp.h
new file mode 100644
index 000000000000..89a73fb93ae6
--- /dev/null
+++ b/trunk/include/asm-mips/cmp.h
@@ -0,0 +1,18 @@
+#ifndef _ASM_CMP_H
+#define _ASM_CMP_H
+
+/*
+ * Definitions for CMP multitasking on MIPS cores
+ */
+struct task_struct;
+
+extern void cmp_smp_setup(void);
+extern void cmp_smp_finish(void);
+extern void cmp_boot_secondary(int cpu, struct task_struct *t);
+extern void cmp_init_secondary(void);
+extern void cmp_cpus_done(void);
+extern void cmp_prepare_cpus(unsigned int max_cpus);
+
+/* This is platform specific */
+extern void cmp_send_ipi(int cpu, unsigned int action);
+#endif /*  _ASM_CMP_H */
diff --git a/trunk/include/asm-mips/cpu.h b/trunk/include/asm-mips/cpu.h
index bf5bbc78a9f7..1c35cac6f35b 100644
--- a/trunk/include/asm-mips/cpu.h
+++ b/trunk/include/asm-mips/cpu.h
@@ -29,7 +29,7 @@
 #define PRID_COMP_ALCHEMY	0x030000
 #define PRID_COMP_SIBYTE	0x040000
 #define PRID_COMP_SANDCRAFT	0x050000
-#define PRID_COMP_PHILIPS	0x060000
+#define PRID_COMP_NXP   	0x060000
 #define PRID_COMP_TOSHIBA	0x070000
 #define PRID_COMP_LSI		0x080000
 #define PRID_COMP_LEXRA		0x0b0000
@@ -89,6 +89,7 @@
 #define PRID_IMP_34K		0x9500
 #define PRID_IMP_24KE		0x9600
 #define PRID_IMP_74K		0x9700
+#define PRID_IMP_1004K		0x9900
 #define PRID_IMP_LOONGSON1      0x4200
 #define PRID_IMP_LOONGSON2      0x6300
 
@@ -194,9 +195,9 @@ enum cpu_type_enum {
 	/*
 	 * MIPS32 class processors
 	 */
-	CPU_4KC, CPU_4KEC, CPU_4KSC, CPU_24K, CPU_34K, CPU_74K, CPU_AU1000,
-	CPU_AU1100, CPU_AU1200, CPU_AU1210, CPU_AU1250, CPU_AU1500, CPU_AU1550,
-	CPU_PR4450, CPU_BCM3302, CPU_BCM4710,
+	CPU_4KC, CPU_4KEC, CPU_4KSC, CPU_24K, CPU_34K, CPU_1004K, CPU_74K,
+	CPU_AU1000, CPU_AU1100, CPU_AU1200, CPU_AU1210, CPU_AU1250, CPU_AU1500,
+	CPU_AU1550, CPU_PR4450, CPU_BCM3302, CPU_BCM4710,
 
 	/*
 	 * MIPS64 class processors
diff --git a/trunk/include/asm-mips/dec/ioasic.h b/trunk/include/asm-mips/dec/ioasic.h
index 486a5b0a1302..98badd6bf22d 100644
--- a/trunk/include/asm-mips/dec/ioasic.h
+++ b/trunk/include/asm-mips/dec/ioasic.h
@@ -33,4 +33,6 @@ static inline u32 ioasic_read(unsigned int reg)
 
 extern void init_ioasic_irqs(int base);
 
+extern void dec_ioasic_clocksource_init(void);
+
 #endif /* __ASM_DEC_IOASIC_H */
diff --git a/trunk/include/asm-mips/ds1287.h b/trunk/include/asm-mips/ds1287.h
new file mode 100644
index 000000000000..ba1702e86931
--- /dev/null
+++ b/trunk/include/asm-mips/ds1287.h
@@ -0,0 +1,27 @@
+/*
+ *  DS1287 timer functions.
+ *
+ *  Copyright (C) 2008  Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#ifndef __ASM_DS1287_H
+#define __ASM_DS1287_H
+
+extern int ds1287_timer_state(void);
+extern void ds1287_set_base_clock(unsigned int clock);
+extern int ds1287_clockevent_init(int irq);
+
+#endif
diff --git a/trunk/include/asm-mips/gcmpregs.h b/trunk/include/asm-mips/gcmpregs.h
new file mode 100644
index 000000000000..d74a8a4ca861
--- /dev/null
+++ b/trunk/include/asm-mips/gcmpregs.h
@@ -0,0 +1,117 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2000, 07 MIPS Technologies, Inc.
+ *
+ * Multiprocessor Subsystem Register Definitions
+ *
+ */
+#ifndef _ASM_GCMPREGS_H
+#define _ASM_GCMPREGS_H
+
+
+/* Offsets to major blocks within GCMP from GCMP base */
+#define GCMP_GCB_OFS		0x0000 /* Global Control Block */
+#define GCMP_CLCB_OFS		0x2000 /* Core Local Control Block */
+#define GCMP_COCB_OFS		0x4000 /* Core Other Control Block */
+#define GCMP_GDB_OFS		0x8000 /* Global Debug Block */
+
+/* Offsets to individual GCMP registers from GCMP base */
+#define GCMPOFS(block, tag, reg)	(GCMP_##block##_OFS + GCMP_##tag##_##reg##_OFS)
+
+#define GCMPGCBOFS(reg)		GCMPOFS(GCB, GCB, reg)
+#define GCMPCLCBOFS(reg)	GCMPOFS(CLCB, CCB, reg)
+#define GCMPCOCBOFS(reg)	GCMPOFS(COCB, CCB, reg)
+#define GCMPGDBOFS(reg)		GCMPOFS(GDB, GDB, reg)
+
+/* GCMP register access */
+#define GCMPGCB(reg)			REGP(_gcmp_base, GCMPGCBOFS(reg))
+#define GCMPCLCB(reg)			REGP(_gcmp_base, GCMPCLCBOFS(reg))
+#define GCMPCOCB(reg)			REGP(_gcmp_base, GCMPCOCBOFS(reg))
+#define GCMPGDB(reg)			REGP(_gcmp_base, GCMPGDBOFS(reg))
+
+/* Mask generation */
+#define GCMPMSK(block, reg, bits)	(MSK(bits)<<GCMP_##block##_##reg##_SHF)
+#define GCMPGCBMSK(reg, bits)		GCMPMSK(GCB, reg, bits)
+#define GCMPCCBMSK(reg, bits)		GCMPMSK(CCB, reg, bits)
+#define GCMPGDBMSK(reg, bits)		GCMPMSK(GDB, reg, bits)
+
+/* GCB registers */
+#define GCMP_GCB_GC_OFS			0x0000	/* Global Config Register */
+#define  GCMP_GCB_GC_NUMIOCU_SHF	8
+#define  GCMP_GCB_GC_NUMIOCU_MSK	GCMPGCBMSK(GC_NUMIOCU, 4)
+#define  GCMP_GCB_GC_NUMCORES_SHF	0
+#define  GCMP_GCB_GC_NUMCORES_MSK	GCMPGCBMSK(GC_NUMCORES, 8)
+#define GCMP_GCB_GCMPB_OFS		0x0008		/* Global GCMP Base */
+#define  GCMP_GCB_GCMPB_GCMPBASE_SHF	15
+#define  GCMP_GCB_GCMPB_GCMPBASE_MSK	GCMPGCBMSK(GCMPB_GCMPBASE, 17)
+#define  GCMP_GCB_GCMPB_CMDEFTGT_SHF	0
+#define  GCMP_GCB_GCMPB_CMDEFTGT_MSK	GCMPGCBMSK(GCMPB_CMDEFTGT, 2)
+#define  GCMP_GCB_GCMPB_CMDEFTGT_MEM	0
+#define  GCMP_GCB_GCMPB_CMDEFTGT_MEM1	1
+#define  GCMP_GCB_GCMPB_CMDEFTGT_IOCU1 2
+#define  GCMP_GCB_GCMPB_CMDEFTGT_IOCU2 3
+#define GCMP_GCB_CCMC_OFS		0x0010	/* Global CM Control */
+#define GCMP_GCB_GCSRAP_OFS		0x0020	/* Global CSR Access Privilege */
+#define  GCMP_GCB_GCSRAP_CMACCESS_SHF	0
+#define  GCMP_GCB_GCSRAP_CMACCESS_MSK	GCMPGCBMSK(GCSRAP_CMACCESS, 8)
+#define GCMP_GCB_GCMPREV_OFS		0x0030	/* GCMP Revision Register */
+#define GCMP_GCB_GCMEM_OFS		0x0040	/* Global CM Error Mask */
+#define GCMP_GCB_GCMEC_OFS		0x0048	/* Global CM Error Cause */
+#define  GCMP_GCB_GMEC_ERROR_TYPE_SHF	27
+#define  GCMP_GCB_GMEC_ERROR_TYPE_MSK	GCMPGCBMSK(GMEC_ERROR_TYPE, 5)
+#define  GCMP_GCB_GMEC_ERROR_INFO_SHF	0
+#define  GCMP_GCB_GMEC_ERROR_INFO_MSK	GCMPGCBMSK(GMEC_ERROR_INFO, 27)
+#define GCMP_GCB_GCMEA_OFS		0x0050	/* Global CM Error Address */
+#define GCMP_GCB_GCMEO_OFS		0x0058	/* Global CM Error Multiple */
+#define  GCMP_GCB_GMEO_ERROR_2ND_SHF	0
+#define  GCMP_GCB_GMEO_ERROR_2ND_MSK	GCMPGCBMSK(GMEO_ERROR_2ND, 5)
+#define GCMP_GCB_GICBA_OFS		0x0080	/* Global Interrupt Controller Base Address */
+#define  GCMP_GCB_GICBA_BASE_SHF	17
+#define  GCMP_GCB_GICBA_BASE_MSK	GCMPGCBMSK(GICBA_BASE, 15)
+#define  GCMP_GCB_GICBA_EN_SHF		0
+#define  GCMP_GCB_GICBA_EN_MSK		GCMPGCBMSK(GICBA_EN, 1)
+
+/* GCB Regions */
+#define GCMP_GCB_CMxBASE_OFS(n)		(0x0090+16*(n))		/* Global Region[0-3] Base Address */
+#define  GCMP_GCB_CMxBASE_BASE_SHF	16
+#define  GCMP_GCB_CMxBASE_BASE_MSK	GCMPGCBMSK(CMxBASE_BASE, 16)
+#define GCMP_GCB_CMxMASK_OFS(n)		(0x0098+16*(n))		/* Global Region[0-3] Address Mask */
+#define  GCMP_GCB_CMxMASK_MASK_SHF	16
+#define  GCMP_GCB_CMxMASK_MASK_MSK	GCMPGCBMSK(CMxMASK_MASK, 16)
+#define  GCMP_GCB_CMxMASK_CMREGTGT_SHF	0
+#define  GCMP_GCB_CMxMASK_CMREGTGT_MSK	GCMPGCBMSK(CMxMASK_CMREGTGT, 2)
+#define  GCMP_GCB_CMxMASK_CMREGTGT_MEM	 0
+#define  GCMP_GCB_CMxMASK_CMREGTGT_MEM1  1
+#define  GCMP_GCB_CMxMASK_CMREGTGT_IOCU1 2
+#define  GCMP_GCB_CMxMASK_CMREGTGT_IOCU2 3
+
+
+/* Core local/Core other control block registers */
+#define GCMP_CCB_RESETR_OFS		0x0000			/* Reset Release */
+#define  GCMP_CCB_RESETR_INRESET_SHF	0
+#define  GCMP_CCB_RESETR_INRESET_MSK	GCMPCCBMSK(RESETR_INRESET, 16)
+#define GCMP_CCB_COHCTL_OFS		0x0008			/* Coherence Control */
+#define  GCMP_CCB_COHCTL_DOMAIN_SHF	0
+#define  GCMP_CCB_COHCTL_DOMAIN_MSK	GCMPCCBMSK(COHCTL_DOMAIN, 8)
+#define GCMP_CCB_CFG_OFS		0x0010			/* Config */
+#define  GCMP_CCB_CFG_IOCUTYPE_SHF	10
+#define  GCMP_CCB_CFG_IOCUTYPE_MSK	GCMPCCBMSK(CFG_IOCUTYPE, 2)
+#define   GCMP_CCB_CFG_IOCUTYPE_CPU	0
+#define   GCMP_CCB_CFG_IOCUTYPE_NCIOCU	1
+#define   GCMP_CCB_CFG_IOCUTYPE_CIOCU	2
+#define  GCMP_CCB_CFG_NUMVPE_SHF	0
+#define  GCMP_CCB_CFG_NUMVPE_MSK	GCMPCCBMSK(CFG_NUMVPE, 10)
+#define GCMP_CCB_OTHER_OFS		0x0018		/* Other Address */
+#define  GCMP_CCB_OTHER_CORENUM_SHF	16
+#define  GCMP_CCB_OTHER_CORENUM_MSK	GCMPCCBMSK(OTHER_CORENUM, 16)
+#define GCMP_CCB_RESETBASE_OFS		0x0020		/* Reset Exception Base */
+#define  GCMP_CCB_RESETBASE_BEV_SHF	12
+#define  GCMP_CCB_RESETBASE_BEV_MSK	GCMPCCBMSK(RESETBASE_BEV, 20)
+#define GCMP_CCB_ID_OFS			0x0028		/* Identification */
+#define GCMP_CCB_DINTGROUP_OFS		0x0030		/* DINT Group Participate */
+#define GCMP_CCB_DBGGROUP_OFS		0x0100		/* DebugBreak Group */
+
+#endif /* _ASM_GCMPREGS_H */
diff --git a/trunk/include/asm-mips/gic.h b/trunk/include/asm-mips/gic.h
new file mode 100644
index 000000000000..01b2f92dc33d
--- /dev/null
+++ b/trunk/include/asm-mips/gic.h
@@ -0,0 +1,487 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2000, 07 MIPS Technologies, Inc.
+ *
+ * GIC Register Definitions
+ *
+ */
+#ifndef _ASM_GICREGS_H
+#define _ASM_GICREGS_H
+
+#undef	GICISBYTELITTLEENDIAN
+#define GICISWORDLITTLEENDIAN
+
+/* Constants */
+#define GIC_POL_POS			1
+#define GIC_POL_NEG			0
+#define GIC_TRIG_EDGE			1
+#define GIC_TRIG_LEVEL			0
+
+#define GIC_NUM_INTRS			32
+
+#define MSK(n) ((1 << (n)) - 1)
+#define REG32(addr)		(*(volatile unsigned int *) (addr))
+#define REG(base, offs)		REG32((unsigned int)(base) + offs##_##OFS)
+#define REGP(base, phys)	REG32((unsigned int)(base) + (phys))
+
+/* Accessors */
+#define GIC_REG(segment, offset) \
+	REG32(_gic_base + segment##_##SECTION_OFS + offset##_##OFS)
+#define GIC_REG_ADDR(segment, offset) \
+	REG32(_gic_base + segment##_##SECTION_OFS + offset)
+
+#define GIC_ABS_REG(segment, offset) \
+       (_gic_base + segment##_##SECTION_OFS + offset##_##OFS)
+#define GIC_REG_ABS_ADDR(segment, offset) \
+       (_gic_base + segment##_##SECTION_OFS + offset)
+
+#ifdef GICISBYTELITTLEENDIAN
+#define GICREAD(reg, data)	(data) = (reg), (data) = le32_to_cpu(data)
+#define GICWRITE(reg, data)	(reg) = cpu_to_le32(data)
+#define GICBIS(reg, bits)			\
+	({unsigned int data;			\
+		GICREAD(reg, data);		\
+		data |= bits;			\
+		GICWRITE(reg, data);		\
+	})
+
+#else
+#define GICREAD(reg, data)	(data) = (reg)
+#define GICWRITE(reg, data)	(reg) = (data)
+#define GICBIS(reg, bits)	(reg) |= (bits)
+#endif
+
+
+/* GIC Address Space */
+#define SHARED_SECTION_OFS		0x0000
+#define SHARED_SECTION_SIZE		0x8000
+#define VPE_LOCAL_SECTION_OFS		0x8000
+#define VPE_LOCAL_SECTION_SIZE		0x4000
+#define VPE_OTHER_SECTION_OFS		0xc000
+#define VPE_OTHER_SECTION_SIZE		0x4000
+#define USM_VISIBLE_SECTION_OFS		0x10000
+#define USM_VISIBLE_SECTION_SIZE	0x10000
+
+/* Register Map for Shared Section */
+#if defined(CONFIG_CPU_LITTLE_ENDIAN) || defined(GICISWORDLITTLEENDIAN)
+
+#define	GIC_SH_CONFIG_OFS		0x0000
+
+/* Shared Global Counter */
+#define GIC_SH_COUNTER_31_00_OFS	0x0010
+#define GIC_SH_COUNTER_63_32_OFS	0x0014
+
+/* Interrupt Polarity */
+#define GIC_SH_POL_31_0_OFS		0x0100
+#define GIC_SH_POL_63_32_OFS		0x0104
+#define GIC_SH_POL_95_64_OFS		0x0108
+#define GIC_SH_POL_127_96_OFS		0x010c
+#define GIC_SH_POL_159_128_OFS		0x0110
+#define GIC_SH_POL_191_160_OFS		0x0114
+#define GIC_SH_POL_223_192_OFS		0x0118
+#define GIC_SH_POL_255_224_OFS		0x011c
+
+/* Edge/Level Triggering */
+#define GIC_SH_TRIG_31_0_OFS		0x0180
+#define GIC_SH_TRIG_63_32_OFS		0x0184
+#define GIC_SH_TRIG_95_64_OFS		0x0188
+#define GIC_SH_TRIG_127_96_OFS		0x018c
+#define GIC_SH_TRIG_159_128_OFS		0x0190
+#define GIC_SH_TRIG_191_160_OFS		0x0194
+#define GIC_SH_TRIG_223_192_OFS		0x0198
+#define GIC_SH_TRIG_255_224_OFS		0x019c
+
+/* Dual Edge Triggering */
+#define GIC_SH_DUAL_31_0_OFS		0x0200
+#define GIC_SH_DUAL_63_32_OFS		0x0204
+#define GIC_SH_DUAL_95_64_OFS		0x0208
+#define GIC_SH_DUAL_127_96_OFS		0x020c
+#define GIC_SH_DUAL_159_128_OFS		0x0210
+#define GIC_SH_DUAL_191_160_OFS		0x0214
+#define GIC_SH_DUAL_223_192_OFS		0x0218
+#define GIC_SH_DUAL_255_224_OFS		0x021c
+
+/* Set/Clear corresponding bit in Edge Detect Register */
+#define GIC_SH_WEDGE_OFS		0x0280
+
+/* Reset Mask - Disables Interrupt */
+#define GIC_SH_RMASK_31_0_OFS		0x0300
+#define GIC_SH_RMASK_63_32_OFS		0x0304
+#define GIC_SH_RMASK_95_64_OFS		0x0308
+#define GIC_SH_RMASK_127_96_OFS		0x030c
+#define GIC_SH_RMASK_159_128_OFS	0x0310
+#define GIC_SH_RMASK_191_160_OFS	0x0314
+#define GIC_SH_RMASK_223_192_OFS	0x0318
+#define GIC_SH_RMASK_255_224_OFS	0x031c
+
+/* Set Mask (WO) - Enables Interrupt */
+#define GIC_SH_SMASK_31_0_OFS		0x0380
+#define GIC_SH_SMASK_63_32_OFS		0x0384
+#define GIC_SH_SMASK_95_64_OFS		0x0388
+#define GIC_SH_SMASK_127_96_OFS		0x038c
+#define GIC_SH_SMASK_159_128_OFS	0x0390
+#define GIC_SH_SMASK_191_160_OFS	0x0394
+#define GIC_SH_SMASK_223_192_OFS	0x0398
+#define GIC_SH_SMASK_255_224_OFS	0x039c
+
+/* Global Interrupt Mask Register (RO) - Bit Set == Interrupt enabled */
+#define GIC_SH_MASK_31_0_OFS		0x0400
+#define GIC_SH_MASK_63_32_OFS		0x0404
+#define GIC_SH_MASK_95_64_OFS		0x0408
+#define GIC_SH_MASK_127_96_OFS		0x040c
+#define GIC_SH_MASK_159_128_OFS		0x0410
+#define GIC_SH_MASK_191_160_OFS		0x0414
+#define GIC_SH_MASK_223_192_OFS		0x0418
+#define GIC_SH_MASK_255_224_OFS		0x041c
+
+/* Pending Global Interrupts (RO) */
+#define GIC_SH_PEND_31_0_OFS		0x0480
+#define GIC_SH_PEND_63_32_OFS		0x0484
+#define GIC_SH_PEND_95_64_OFS		0x0488
+#define GIC_SH_PEND_127_96_OFS		0x048c
+#define GIC_SH_PEND_159_128_OFS		0x0490
+#define GIC_SH_PEND_191_160_OFS		0x0494
+#define GIC_SH_PEND_223_192_OFS		0x0498
+#define GIC_SH_PEND_255_224_OFS		0x049c
+
+#define GIC_SH_INTR_MAP_TO_PIN_BASE_OFS	0x0500
+
+/* Maps Interrupt X to a Pin */
+#define GIC_SH_MAP_TO_PIN(intr) \
+	(GIC_SH_INTR_MAP_TO_PIN_BASE_OFS + (4 * intr))
+
+#define GIC_SH_INTR_MAP_TO_VPE_BASE_OFS	0x2000
+
+/* Maps Interrupt X to a VPE */
+#define GIC_SH_MAP_TO_VPE_REG_OFF(intr, vpe) \
+	(GIC_SH_INTR_MAP_TO_VPE_BASE_OFS + (32 * (intr)) + (((vpe) / 32) * 4))
+#define GIC_SH_MAP_TO_VPE_REG_BIT(vpe)	(1 << ((vpe) % 32))
+
+/* Polarity : Reset Value is always 0 */
+#define GIC_SH_SET_POLARITY_OFS		0x0100
+#define GIC_SET_POLARITY(intr, pol) \
+	GICBIS(GIC_REG_ADDR(SHARED, GIC_SH_SET_POLARITY_OFS + (((intr) / 32) * 4)), (pol) << ((intr) % 32))
+
+/* Triggering : Reset Value is always 0 */
+#define GIC_SH_SET_TRIGGER_OFS		0x0180
+#define GIC_SET_TRIGGER(intr, trig) \
+	GICBIS(GIC_REG_ADDR(SHARED, GIC_SH_SET_TRIGGER_OFS + (((intr) / 32) * 4)), (trig) << ((intr) % 32))
+
+/* Mask manipulation */
+#define GIC_SH_SMASK_OFS		0x0380
+#define GIC_SET_INTR_MASK(intr, val) \
+	GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_SMASK_OFS + (((intr) / 32) * 4)), ((val) << ((intr) % 32)))
+
+#define GIC_SH_RMASK_OFS		0x0300
+#define GIC_CLR_INTR_MASK(intr, val) \
+	GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_RMASK_OFS + (((intr) / 32) * 4)), ((val) << ((intr) % 32)))
+
+/* Register Map for Local Section */
+#define GIC_VPE_CTL_OFS			0x0000
+#define GIC_VPE_PEND_OFS		0x0004
+#define GIC_VPE_MASK_OFS		0x0008
+#define GIC_VPE_RMASK_OFS		0x000c
+#define GIC_VPE_SMASK_OFS		0x0010
+#define GIC_VPE_WD_MAP_OFS		0x0040
+#define GIC_VPE_COMPARE_MAP_OFS		0x0044
+#define GIC_VPE_TIMER_MAP_OFS		0x0048
+#define GIC_VPE_PERFCTR_MAP_OFS		0x0050
+#define GIC_VPE_SWINT0_MAP_OFS		0x0054
+#define GIC_VPE_SWINT1_MAP_OFS		0x0058
+#define GIC_VPE_OTHER_ADDR_OFS		0x0080
+#define GIC_VPE_WD_CONFIG0_OFS		0x0090
+#define GIC_VPE_WD_COUNT0_OFS		0x0094
+#define GIC_VPE_WD_INITIAL0_OFS		0x0098
+#define GIC_VPE_COMPARE_LO_OFS		0x00a0
+#define GIC_VPE_COMPARE_HI		0x00a4
+
+#define GIC_VPE_EIC_SHADOW_SET_BASE	0x0100
+#define GIC_VPE_EIC_SS(intr) \
+	(GIC_EIC_SHADOW_SET_BASE + (4 * intr))
+
+#define GIC_VPE_EIC_VEC_BASE		0x0800
+#define GIC_VPE_EIC_VEC(intr) \
+	(GIC_VPE_EIC_VEC_BASE + (4 * intr))
+
+#define GIC_VPE_TENABLE_NMI_OFS		0x1000
+#define GIC_VPE_TENABLE_YQ_OFS		0x1004
+#define GIC_VPE_TENABLE_INT_31_0_OFS	0x1080
+#define GIC_VPE_TENABLE_INT_63_32_OFS	0x1084
+
+/* User Mode Visible Section Register Map */
+#define GIC_UMV_SH_COUNTER_31_00_OFS	0x0000
+#define GIC_UMV_SH_COUNTER_63_32_OFS	0x0004
+
+#else /* CONFIG_CPU_BIG_ENDIAN */
+
+#define	GIC_SH_CONFIG_OFS		0x0000
+
+/* Shared Global Counter */
+#define GIC_SH_COUNTER_31_00_OFS	0x0014
+#define GIC_SH_COUNTER_63_32_OFS	0x0010
+
+/* Interrupt Polarity */
+#define GIC_SH_POL_31_0_OFS		0x0104
+#define GIC_SH_POL_63_32_OFS		0x0100
+#define GIC_SH_POL_95_64_OFS		0x010c
+#define GIC_SH_POL_127_96_OFS		0x0108
+#define GIC_SH_POL_159_128_OFS		0x0114
+#define GIC_SH_POL_191_160_OFS		0x0110
+#define GIC_SH_POL_223_192_OFS		0x011c
+#define GIC_SH_POL_255_224_OFS		0x0118
+
+/* Edge/Level Triggering */
+#define GIC_SH_TRIG_31_0_OFS		0x0184
+#define GIC_SH_TRIG_63_32_OFS		0x0180
+#define GIC_SH_TRIG_95_64_OFS		0x018c
+#define GIC_SH_TRIG_127_96_OFS		0x0188
+#define GIC_SH_TRIG_159_128_OFS		0x0194
+#define GIC_SH_TRIG_191_160_OFS		0x0190
+#define GIC_SH_TRIG_223_192_OFS		0x019c
+#define GIC_SH_TRIG_255_224_OFS		0x0198
+
+/* Dual Edge Triggering */
+#define GIC_SH_DUAL_31_0_OFS		0x0204
+#define GIC_SH_DUAL_63_32_OFS		0x0200
+#define GIC_SH_DUAL_95_64_OFS		0x020c
+#define GIC_SH_DUAL_127_96_OFS		0x0208
+#define GIC_SH_DUAL_159_128_OFS		0x0214
+#define GIC_SH_DUAL_191_160_OFS		0x0210
+#define GIC_SH_DUAL_223_192_OFS		0x021c
+#define GIC_SH_DUAL_255_224_OFS		0x0218
+
+/* Set/Clear corresponding bit in Edge Detect Register */
+#define GIC_SH_WEDGE_OFS		0x0280
+
+/* Reset Mask - Disables Interrupt */
+#define GIC_SH_RMASK_31_0_OFS		0x0304
+#define GIC_SH_RMASK_63_32_OFS		0x0300
+#define GIC_SH_RMASK_95_64_OFS		0x030c
+#define GIC_SH_RMASK_127_96_OFS		0x0308
+#define GIC_SH_RMASK_159_128_OFS	0x0314
+#define GIC_SH_RMASK_191_160_OFS	0x0310
+#define GIC_SH_RMASK_223_192_OFS	0x031c
+#define GIC_SH_RMASK_255_224_OFS	0x0318
+
+/* Set Mask (WO) - Enables Interrupt */
+#define GIC_SH_SMASK_31_0_OFS		0x0384
+#define GIC_SH_SMASK_63_32_OFS		0x0380
+#define GIC_SH_SMASK_95_64_OFS		0x038c
+#define GIC_SH_SMASK_127_96_OFS		0x0388
+#define GIC_SH_SMASK_159_128_OFS	0x0394
+#define GIC_SH_SMASK_191_160_OFS	0x0390
+#define GIC_SH_SMASK_223_192_OFS	0x039c
+#define GIC_SH_SMASK_255_224_OFS	0x0398
+
+/* Global Interrupt Mask Register (RO) - Bit Set == Interrupt enabled */
+#define GIC_SH_MASK_31_0_OFS		0x0404
+#define GIC_SH_MASK_63_32_OFS		0x0400
+#define GIC_SH_MASK_95_64_OFS		0x040c
+#define GIC_SH_MASK_127_96_OFS		0x0408
+#define GIC_SH_MASK_159_128_OFS		0x0414
+#define GIC_SH_MASK_191_160_OFS		0x0410
+#define GIC_SH_MASK_223_192_OFS		0x041c
+#define GIC_SH_MASK_255_224_OFS		0x0418
+
+/* Pending Global Interrupts (RO) */
+#define GIC_SH_PEND_31_0_OFS		0x0484
+#define GIC_SH_PEND_63_32_OFS		0x0480
+#define GIC_SH_PEND_95_64_OFS		0x048c
+#define GIC_SH_PEND_127_96_OFS		0x0488
+#define GIC_SH_PEND_159_128_OFS		0x0494
+#define GIC_SH_PEND_191_160_OFS		0x0490
+#define GIC_SH_PEND_223_192_OFS		0x049c
+#define GIC_SH_PEND_255_224_OFS		0x0498
+
+#define GIC_SH_INTR_MAP_TO_PIN_BASE_OFS	0x0500
+
+/* Maps Interrupt X to a Pin */
+#define GIC_SH_MAP_TO_PIN(intr) \
+	(GIC_SH_INTR_MAP_TO_PIN_BASE_OFS + (4 * intr))
+
+#define GIC_SH_INTR_MAP_TO_VPE_BASE_OFS	0x2004
+
+/*
+ * Maps Interrupt X to a VPE.  This is more complex than the LE case, as
+ * odd and even registers need to be transposed.  It does work - trust me!
+ */
+#define GIC_SH_MAP_TO_VPE_REG_OFF(intr, vpe) \
+	(GIC_SH_INTR_MAP_TO_VPE_BASE_OFS + (32 * (intr)) + \
+	(((((vpe) / 32) ^ 1) - 1) * 4))
+#define GIC_SH_MAP_TO_VPE_REG_BIT(vpe)	(1 << ((vpe) % 32))
+
+/* Polarity */
+#define GIC_SH_SET_POLARITY_OFS		0x0100
+#define GIC_SET_POLARITY(intr, pol) \
+	GICBIS(GIC_REG_ADDR(SHARED, GIC_SH_SET_POLARITY_OFS + 4 + (((((intr) / 32) ^ 1) - 1) * 4)), (pol) << ((intr) % 32))
+
+/* Triggering */
+#define GIC_SH_SET_TRIGGER_OFS		0x0180
+#define GIC_SET_TRIGGER(intr, trig) \
+	GICBIS(GIC_REG_ADDR(SHARED, GIC_SH_SET_TRIGGER_OFS + 4 + (((((intr) / 32) ^ 1) - 1) * 4)), (trig) << ((intr) % 32))
+
+/* Mask manipulation */
+#define GIC_SH_SMASK_OFS		0x0380
+#define GIC_SET_INTR_MASK(intr, val) \
+	GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_SMASK_OFS + 4 + (((((intr) / 32) ^ 1) - 1) * 4)), ((val) << ((intr) % 32)))
+
+#define GIC_SH_RMASK_OFS		0x0300
+#define GIC_CLR_INTR_MASK(intr, val) \
+	GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_RMASK_OFS + 4 + (((((intr) / 32) ^ 1) - 1) * 4)), ((val) << ((intr) % 32))
+
+/* Register Map for Local Section */
+#define GIC_VPE_CTL_OFS			0x0000
+#define GIC_VPE_PEND_OFS		0x0004
+#define GIC_VPE_MASK_OFS		0x0008
+#define GIC_VPE_RMASK_OFS		0x000c
+#define GIC_VPE_SMASK_OFS		0x0010
+#define GIC_VPE_WD_MAP_OFS		0x0040
+#define GIC_VPE_COMPARE_MAP_OFS		0x0044
+#define GIC_VPE_TIMER_MAP_OFS		0x0048
+#define GIC_VPE_PERFCTR_MAP_OFS		0x0050
+#define GIC_VPE_SWINT0_MAP_OFS		0x0054
+#define GIC_VPE_SWINT1_MAP_OFS		0x0058
+#define GIC_VPE_OTHER_ADDR_OFS		0x0080
+#define GIC_VPE_WD_CONFIG0_OFS		0x0090
+#define GIC_VPE_WD_COUNT0_OFS		0x0094
+#define GIC_VPE_WD_INITIAL0_OFS		0x0098
+#define GIC_VPE_COMPARE_LO_OFS		0x00a4
+#define GIC_VPE_COMPARE_HI_OFS		0x00a0
+
+#define GIC_VPE_EIC_SHADOW_SET_BASE	0x0100
+#define GIC_VPE_EIC_SS(intr) \
+	(GIC_EIC_SHADOW_SET_BASE + (4 * intr))
+
+#define GIC_VPE_EIC_VEC_BASE		0x0800
+#define GIC_VPE_EIC_VEC(intr) \
+	(GIC_VPE_EIC_VEC_BASE + (4 * intr))
+
+#define GIC_VPE_TENABLE_NMI_OFS		0x1000
+#define GIC_VPE_TENABLE_YQ_OFS		0x1004
+#define GIC_VPE_TENABLE_INT_31_0_OFS	0x1080
+#define GIC_VPE_TENABLE_INT_63_32_OFS	0x1084
+
+/* User Mode Visible Section Register Map */
+#define GIC_UMV_SH_COUNTER_31_00_OFS	0x0004
+#define GIC_UMV_SH_COUNTER_63_32_OFS	0x0000
+
+#endif /* !LE */
+
+/* Masks */
+#define GIC_SH_CONFIG_COUNTSTOP_SHF	28
+#define GIC_SH_CONFIG_COUNTSTOP_MSK	(MSK(1) << GIC_SH_CONFIG_COUNTSTOP_SHF)
+
+#define GIC_SH_CONFIG_COUNTBITS_SHF	24
+#define GIC_SH_CONFIG_COUNTBITS_MSK	(MSK(4) << GIC_SH_CONFIG_COUNTBITS_SHF)
+
+#define GIC_SH_CONFIG_NUMINTRS_SHF	16
+#define GIC_SH_CONFIG_NUMINTRS_MSK	(MSK(8) << GIC_SH_CONFIG_NUMINTRS_SHF)
+
+#define GIC_SH_CONFIG_NUMVPES_SHF	0
+#define GIC_SH_CONFIG_NUMVPES_MSK	(MSK(8) << GIC_SH_CONFIG_NUMVPES_SHF)
+
+#define GIC_SH_WEDGE_SET(intr)		(intr | (0x1 << 31))
+#define GIC_SH_WEDGE_CLR(intr)		(intr & ~(0x1 << 31))
+
+#define GIC_MAP_TO_PIN_SHF		31
+#define GIC_MAP_TO_PIN_MSK		(MSK(1) << GIC_MAP_TO_PIN_SHF)
+#define GIC_MAP_TO_NMI_SHF		30
+#define GIC_MAP_TO_NMI_MSK		(MSK(1) << GIC_MAP_TO_NMI_SHF)
+#define GIC_MAP_TO_YQ_SHF		29
+#define GIC_MAP_TO_YQ_MSK		(MSK(1) << GIC_MAP_TO_YQ_SHF)
+#define GIC_MAP_SHF			0
+#define GIC_MAP_MSK			(MSK(6) << GIC_MAP_SHF)
+
+/* GIC_VPE_CTL Masks */
+#define GIC_VPE_CTL_PERFCNT_RTBL_SHF	2
+#define GIC_VPE_CTL_PERFCNT_RTBL_MSK	(MSK(1) << GIC_VPE_CTL_PERFCNT_RTBL_SHF)
+#define GIC_VPE_CTL_TIMER_RTBL_SHF	1
+#define GIC_VPE_CTL_TIMER_RTBL_MSK	(MSK(1) << GIC_VPE_CTL_TIMER_RTBL_SHF)
+#define GIC_VPE_CTL_EIC_MODE_SHF	0
+#define GIC_VPE_CTL_EIC_MODE_MSK	(MSK(1) << GIC_VPE_CTL_EIC_MODE_SHF)
+
+/* GIC_VPE_PEND Masks */
+#define GIC_VPE_PEND_WD_SHF		0
+#define GIC_VPE_PEND_WD_MSK		(MSK(1) << GIC_VPE_PEND_WD_SHF)
+#define GIC_VPE_PEND_CMP_SHF		1
+#define GIC_VPE_PEND_CMP_MSK		(MSK(1) << GIC_VPE_PEND_CMP_SHF)
+#define GIC_VPE_PEND_TIMER_SHF		2
+#define GIC_VPE_PEND_TIMER_MSK		(MSK(1) << GIC_VPE_PEND_TIMER_SHF)
+#define GIC_VPE_PEND_PERFCOUNT_SHF	3
+#define GIC_VPE_PEND_PERFCOUNT_MSK	(MSK(1) << GIC_VPE_PEND_PERFCOUNT_SHF)
+#define GIC_VPE_PEND_SWINT0_SHF		4
+#define GIC_VPE_PEND_SWINT0_MSK		(MSK(1) << GIC_VPE_PEND_SWINT0_SHF)
+#define GIC_VPE_PEND_SWINT1_SHF		5
+#define GIC_VPE_PEND_SWINT1_MSK		(MSK(1) << GIC_VPE_PEND_SWINT1_SHF)
+
+/* GIC_VPE_RMASK Masks */
+#define GIC_VPE_RMASK_WD_SHF		0
+#define GIC_VPE_RMASK_WD_MSK		(MSK(1) << GIC_VPE_RMASK_WD_SHF)
+#define GIC_VPE_RMASK_CMP_SHF		1
+#define GIC_VPE_RMASK_CMP_MSK		(MSK(1) << GIC_VPE_RMASK_CMP_SHF)
+#define GIC_VPE_RMASK_TIMER_SHF		2
+#define GIC_VPE_RMASK_TIMER_MSK		(MSK(1) << GIC_VPE_RMASK_TIMER_SHF)
+#define GIC_VPE_RMASK_PERFCNT_SHF	3
+#define GIC_VPE_RMASK_PERFCNT_MSK	(MSK(1) << GIC_VPE_RMASK_PERFCNT_SHF)
+#define GIC_VPE_RMASK_SWINT0_SHF	4
+#define GIC_VPE_RMASK_SWINT0_MSK	(MSK(1) << GIC_VPE_RMASK_SWINT0_SHF)
+#define GIC_VPE_RMASK_SWINT1_SHF	5
+#define GIC_VPE_RMASK_SWINT1_MSK	(MSK(1) << GIC_VPE_RMASK_SWINT1_SHF)
+
+/* GIC_VPE_SMASK Masks */
+#define GIC_VPE_SMASK_WD_SHF		0
+#define GIC_VPE_SMASK_WD_MSK		(MSK(1) << GIC_VPE_SMASK_WD_SHF)
+#define GIC_VPE_SMASK_CMP_SHF		1
+#define GIC_VPE_SMASK_CMP_MSK		(MSK(1) << GIC_VPE_SMASK_CMP_SHF)
+#define GIC_VPE_SMASK_TIMER_SHF		2
+#define GIC_VPE_SMASK_TIMER_MSK		(MSK(1) << GIC_VPE_SMASK_TIMER_SHF)
+#define GIC_VPE_SMASK_PERFCNT_SHF	3
+#define GIC_VPE_SMASK_PERFCNT_MSK	(MSK(1) << GIC_VPE_SMASK_PERFCNT_SHF)
+#define GIC_VPE_SMASK_SWINT0_SHF	4
+#define GIC_VPE_SMASK_SWINT0_MSK	(MSK(1) << GIC_VPE_SMASK_SWINT0_SHF)
+#define GIC_VPE_SMASK_SWINT1_SHF	5
+#define GIC_VPE_SMASK_SWINT1_MSK	(MSK(1) << GIC_VPE_SMASK_SWINT1_SHF)
+
+/*
+ * Set the Mapping of Interrupt X to a VPE.
+ */
+#define GIC_SH_MAP_TO_VPE_SMASK(intr, vpe) \
+	GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_MAP_TO_VPE_REG_OFF(intr, vpe)), \
+		 GIC_SH_MAP_TO_VPE_REG_BIT(vpe))
+
+struct gic_pcpu_mask {
+       DECLARE_BITMAP(pcpu_mask, GIC_NUM_INTRS);
+};
+
+struct gic_pending_regs {
+       DECLARE_BITMAP(pending, GIC_NUM_INTRS);
+};
+
+struct gic_intrmask_regs {
+       DECLARE_BITMAP(intrmask, GIC_NUM_INTRS);
+};
+
+/*
+ * Interrupt Meta-data specification. The ipiflag helps
+ * in building ipi_map.
+ */
+struct gic_intr_map {
+	unsigned int intrnum; 	/* Ext Intr Num 	*/
+	unsigned int cpunum;	/* Directed to this CPU */
+	unsigned int pin;	/* Directed to this Pin */
+	unsigned int polarity;	/* Polarity : +/-	*/
+	unsigned int trigtype;	/* Trigger  : Edge/Levl */
+	unsigned int ipiflag;	/* Is used for IPI ?	*/
+};
+
+extern void gic_init(unsigned long gic_base_addr,
+	unsigned long gic_addrspace_size, struct gic_intr_map *intrmap,
+	unsigned int intrmap_size, unsigned int irqbase);
+
+extern unsigned int gic_get_int(void);
+extern void gic_send_ipi(unsigned int intr);
+
+#endif /* _ASM_GICREGS_H */
diff --git a/trunk/include/asm-mips/io.h b/trunk/include/asm-mips/io.h
index e62058b0d28c..f18d2816cbec 100644
--- a/trunk/include/asm-mips/io.h
+++ b/trunk/include/asm-mips/io.h
@@ -273,7 +273,7 @@ static inline void __iomem * __ioremap_mode(phys_t offset, unsigned long size,
  * memory-like regions on I/O busses.
  */
 #define ioremap_cachable(offset, size)					\
-	__ioremap_mode((offset), (size), PAGE_CACHABLE_DEFAULT)
+	__ioremap_mode((offset), (size), _page_cachable_default)
 
 /*
  * These two are MIPS specific ioremap variant.  ioremap_cacheable_cow
diff --git a/trunk/include/asm-mips/jmr3927/jmr3927.h b/trunk/include/asm-mips/jmr3927/jmr3927.h
index 81602c8047eb..a162268f17df 100644
--- a/trunk/include/asm-mips/jmr3927/jmr3927.h
+++ b/trunk/include/asm-mips/jmr3927/jmr3927.h
@@ -99,8 +99,8 @@
 #define jmr3927_led_and_set(n/*0-16*/)	jmr3927_ioc_reg_out((~(n)) & jmr3927_ioc_reg_in(JMR3927_IOC_LED_ADDR), JMR3927_IOC_LED_ADDR)
 
 /* DIPSW4 macro */
-#define jmr3927_dipsw1()	((tx3927_pioptr->din & (1 << 11)) == 0)
-#define jmr3927_dipsw2()	((tx3927_pioptr->din & (1 << 10)) == 0)
+#define jmr3927_dipsw1()	(gpio_get_value(11) == 0)
+#define jmr3927_dipsw2()	(gpio_get_value(10) == 0)
 #define jmr3927_dipsw3()	((jmr3927_ioc_reg_in(JMR3927_IOC_DIPSW_ADDR) & 2) == 0)
 #define jmr3927_dipsw4()	((jmr3927_ioc_reg_in(JMR3927_IOC_DIPSW_ADDR) & 1) == 0)
 
diff --git a/trunk/include/asm-mips/jmr3927/tx3927.h b/trunk/include/asm-mips/jmr3927/tx3927.h
index 338f99882a39..fb580333c102 100644
--- a/trunk/include/asm-mips/jmr3927/tx3927.h
+++ b/trunk/include/asm-mips/jmr3927/tx3927.h
@@ -314,6 +314,6 @@ struct tx3927_ccfg_reg {
 #define tx3927_ccfgptr		((struct tx3927_ccfg_reg *)TX3927_CCFG_REG)
 #define tx3927_tmrptr(ch)	((struct txx927_tmr_reg *)TX3927_TMR_REG(ch))
 #define tx3927_sioptr(ch)	((struct txx927_sio_reg *)TX3927_SIO_REG(ch))
-#define tx3927_pioptr		((struct txx927_pio_reg *)TX3927_PIO_REG)
+#define tx3927_pioptr		((struct txx9_pio_reg __iomem *)TX3927_PIO_REG)
 
 #endif /* __ASM_TX3927_H */
diff --git a/trunk/include/asm-mips/jmr3927/txx927.h b/trunk/include/asm-mips/jmr3927/txx927.h
index 0474fe8dac3f..25dcf2feb095 100644
--- a/trunk/include/asm-mips/jmr3927/txx927.h
+++ b/trunk/include/asm-mips/jmr3927/txx927.h
@@ -22,18 +22,6 @@ struct txx927_sio_reg {
 	volatile unsigned long rfifo;
 };
 
-struct txx927_pio_reg {
-	volatile unsigned long dout;
-	volatile unsigned long din;
-	volatile unsigned long dir;
-	volatile unsigned long od;
-	volatile unsigned long flag[2];
-	volatile unsigned long pol;
-	volatile unsigned long intc;
-	volatile unsigned long maskcpu;
-	volatile unsigned long maskext;
-};
-
 /*
  * SIO
  */
diff --git a/trunk/include/asm-mips/mach-au1x00/au1000.h b/trunk/include/asm-mips/mach-au1x00/au1000.h
index 5bb57bf2b9d7..a05555165d05 100644
--- a/trunk/include/asm-mips/mach-au1x00/au1000.h
+++ b/trunk/include/asm-mips/mach-au1x00/au1000.h
@@ -3,9 +3,8 @@
  * BRIEF MODULE DESCRIPTION
  *	Include file for Alchemy Semiconductor's Au1k CPU.
  *
- * Copyright 2000,2001 MontaVista Software Inc.
- * Author: MontaVista Software, Inc.
- *         	ppopov@mvista.com or source@mvista.com
+ * Copyright 2000-2001, 2006-2008 MontaVista Software Inc.
+ * Author: MontaVista Software, Inc. <source@mvista.com>
  *
  *  This program is free software; you can redistribute  it and/or modify it
  *  under  the terms of  the GNU General  Public License as published by the
@@ -117,13 +116,6 @@ extern struct au1xxx_irqmap au1xxx_irq_map[];
 
 #endif /* !defined (_LANGUAGE_ASSEMBLY) */
 
-#ifdef CONFIG_PM
-/* no CP0 timer irq */
-#define ALLINTS (IE_IRQ0 | IE_IRQ1 | IE_IRQ2 | IE_IRQ3 | IE_IRQ4)
-#else
-#define ALLINTS (IE_IRQ0 | IE_IRQ1 | IE_IRQ2 | IE_IRQ3 | IE_IRQ4 | IE_IRQ5)
-#endif
-
 /*
  * SDRAM Register Offsets
  */
@@ -1693,20 +1685,6 @@ enum soc_au1200_ints {
 #define IOMEM_RESOURCE_START  0x10000000
 #define IOMEM_RESOURCE_END    0xffffffff
 
-  /*
-   * Borrowed from the PPC arch:
-   * The following macro is used to lookup irqs in a standard table
-   * format for those PPC systems that do not already have PCI
-   * interrupts properly routed.
-   */
-  /* FIXME - double check this from asm-ppc/pci-bridge.h */
-#define PCI_IRQ_TABLE_LOOKUP                            \
-  ({ long _ctl_ = -1;                                 \
-      if (idsel >= min_idsel && idsel <= max_idsel && pin <= irqs_per_slot)    \
-	       _ctl_ = pci_irq_table[idsel - min_idsel][pin-1];               \
-		      _ctl_; })
-
-
 #else /* Au1000 and Au1100 and Au1200 */
 
 /* don't allow any legacy ports probing */
diff --git a/trunk/include/asm-mips/mach-db1x00/db1200.h b/trunk/include/asm-mips/mach-db1x00/db1200.h
index d2e28e64932e..eedd048a7261 100644
--- a/trunk/include/asm-mips/mach-db1x00/db1200.h
+++ b/trunk/include/asm-mips/mach-db1x00/db1200.h
@@ -169,15 +169,15 @@ static BCSR * const bcsr = (BCSR *)BCSR_KSEG1_ADDR;
 #define BCSR_INT_SD0INSERT	0x1000
 #define BCSR_INT_SD0EJECT	0x2000
 
-#define AU1XXX_SMC91111_PHYS_ADDR	(0x19000300)
-#define AU1XXX_SMC91111_IRQ			DB1200_ETH_INT
-
-#define AU1XXX_ATA_PHYS_ADDR		(0x18800000)
-#define AU1XXX_ATA_REG_OFFSET		(5)
-#define AU1XXX_ATA_PHYS_LEN		(16 << AU1XXX_ATA_REG_OFFSET)
-#define AU1XXX_ATA_INT			DB1200_IDE_INT
-#define AU1XXX_ATA_DDMA_REQ		DSCR_CMD0_DMA_REQ1;
-#define AU1XXX_ATA_RQSIZE		128
+#define SMC91C111_PHYS_ADDR	0x19000300
+#define SMC91C111_INT		DB1200_ETH_INT
+
+#define IDE_PHYS_ADDR		0x18800000
+#define IDE_REG_SHIFT		5
+#define IDE_PHYS_LEN		(16 << IDE_REG_SHIFT)
+#define IDE_INT 		DB1200_IDE_INT
+#define IDE_DDMA_REQ		DSCR_CMD0_DMA_REQ1
+#define IDE_RQSIZE		128
 
 #define NAND_PHYS_ADDR   0x20000000
 
diff --git a/trunk/include/asm-mips/mach-generic/gpio.h b/trunk/include/asm-mips/mach-generic/gpio.h
index 6eaf5efedf3a..e6b376bd9d06 100644
--- a/trunk/include/asm-mips/mach-generic/gpio.h
+++ b/trunk/include/asm-mips/mach-generic/gpio.h
@@ -1,12 +1,18 @@
 #ifndef __ASM_MACH_GENERIC_GPIO_H
 #define __ASM_MACH_GENERIC_GPIO_H
 
+#ifdef CONFIG_HAVE_GPIO_LIB
+#define gpio_get_value	__gpio_get_value
+#define gpio_set_value	__gpio_set_value
+#define gpio_cansleep	__gpio_cansleep
+#else
 int gpio_request(unsigned gpio, const char *label);
 void gpio_free(unsigned gpio);
 int gpio_direction_input(unsigned gpio);
 int gpio_direction_output(unsigned gpio, int value);
 int gpio_get_value(unsigned gpio);
 void gpio_set_value(unsigned gpio, int value);
+#endif
 int gpio_to_irq(unsigned gpio);
 int irq_to_gpio(unsigned irq);
 
diff --git a/trunk/include/asm-mips/mach-ip27/topology.h b/trunk/include/asm-mips/mach-ip27/topology.h
index 372291f53fb9..7785bec732f2 100644
--- a/trunk/include/asm-mips/mach-ip27/topology.h
+++ b/trunk/include/asm-mips/mach-ip27/topology.h
@@ -54,4 +54,6 @@ extern unsigned char __node_distances[MAX_COMPACT_NODES][MAX_COMPACT_NODES];
 	.nr_balance_failed	= 0,			\
 }
 
+#include <asm-generic/topology.h>
+
 #endif /* _ASM_MACH_TOPOLOGY_H */
diff --git a/trunk/include/asm-mips/mach-pb1x00/pb1200.h b/trunk/include/asm-mips/mach-pb1x00/pb1200.h
index edaa489b58f1..e2c6bcac3b42 100644
--- a/trunk/include/asm-mips/mach-pb1x00/pb1200.h
+++ b/trunk/include/asm-mips/mach-pb1x00/pb1200.h
@@ -182,15 +182,15 @@ static BCSR * const bcsr = (BCSR *)BCSR_KSEG1_ADDR;
 #define SET_VCC_VPP(VCC, VPP, SLOT)\
 	((((VCC)<<2) | ((VPP)<<0)) << ((SLOT)*8))
 
-#define AU1XXX_SMC91111_PHYS_ADDR	(0x0D000300)
-#define AU1XXX_SMC91111_IRQ			PB1200_ETH_INT
-
-#define AU1XXX_ATA_PHYS_ADDR		(0x0C800000)
-#define AU1XXX_ATA_REG_OFFSET		(5)
-#define AU1XXX_ATA_PHYS_LEN		(16 << AU1XXX_ATA_REG_OFFSET)
-#define AU1XXX_ATA_INT			PB1200_IDE_INT
-#define AU1XXX_ATA_DDMA_REQ		DSCR_CMD0_DMA_REQ1;
-#define AU1XXX_ATA_RQSIZE		128
+#define SMC91C111_PHYS_ADDR	0x0D000300
+#define SMC91C111_INT		PB1200_ETH_INT
+
+#define IDE_PHYS_ADDR		0x0C800000
+#define IDE_REG_SHIFT		5
+#define IDE_PHYS_LEN		(16 << IDE_REG_SHIFT)
+#define IDE_INT 		PB1200_IDE_INT
+#define IDE_DDMA_REQ		DSCR_CMD0_DMA_REQ1
+#define IDE_RQSIZE		128
 
 #define NAND_PHYS_ADDR   0x1C000000
 
diff --git a/trunk/include/asm-mips/mips-boards/generic.h b/trunk/include/asm-mips/mips-boards/generic.h
index 1c39d339521e..33407bee4e73 100644
--- a/trunk/include/asm-mips/mips-boards/generic.h
+++ b/trunk/include/asm-mips/mips-boards/generic.h
@@ -68,6 +68,7 @@
 #define MIPS_REVISION_CORID_CORE_FPGA3     9
 #define MIPS_REVISION_CORID_CORE_24K       10
 #define MIPS_REVISION_CORID_CORE_FPGA4     11
+#define MIPS_REVISION_CORID_CORE_FPGA5     12
 
 /**** Artificial corid defines ****/
 /*
diff --git a/trunk/include/asm-mips/mips-boards/launch.h b/trunk/include/asm-mips/mips-boards/launch.h
new file mode 100644
index 000000000000..d8ae7f95a522
--- /dev/null
+++ b/trunk/include/asm-mips/mips-boards/launch.h
@@ -0,0 +1,35 @@
+/*
+ *
+ */
+
+#ifndef _ASSEMBLER_
+
+struct cpulaunch {
+    unsigned long	pc;
+    unsigned long	gp;
+    unsigned long	sp;
+    unsigned long	a0;
+    unsigned long	_pad[3]; /* pad to cache line size to avoid thrashing */
+    unsigned long	flags;
+};
+
+#else
+
+#define LOG2CPULAUNCH	5
+#define	LAUNCH_PC	0
+#define	LAUNCH_GP	4
+#define	LAUNCH_SP	8
+#define	LAUNCH_A0	12
+#define	LAUNCH_FLAGS	28
+
+#endif
+
+#define LAUNCH_FREADY	1
+#define LAUNCH_FGO	2
+#define LAUNCH_FGONE	4
+
+#define CPULAUNCH	0x00000f00
+#define NCPULAUNCH	8
+
+/* Polling period in count cycles for secondary CPU's */
+#define LAUNCHPERIOD	10000
diff --git a/trunk/include/asm-mips/mips-boards/malta.h b/trunk/include/asm-mips/mips-boards/malta.h
index 93bf4e51b8a4..c1891578fa65 100644
--- a/trunk/include/asm-mips/mips-boards/malta.h
+++ b/trunk/include/asm-mips/mips-boards/malta.h
@@ -51,6 +51,29 @@ static inline unsigned long get_msc_port_base(unsigned long reg)
 	return (unsigned long) ioremap(addr, 0x10000);
 }
 
+/*
+ * GCMP Specific definitions
+ */
+#define GCMP_BASE_ADDR			0x1fbf8000
+#define GCMP_ADDRSPACE_SZ		(256 * 1024)
+
+/*
+ * GIC Specific definitions
+ */
+#define GIC_BASE_ADDR			0x1bdc0000
+#define GIC_ADDRSPACE_SZ		(128 * 1024)
+
+/*
+ * MSC01 BIU Specific definitions
+ * FIXME : These should be elsewhere ?
+ */
+#define MSC01_BIU_REG_BASE		0x1bc80000
+#define MSC01_BIU_ADDRSPACE_SZ		(256 * 1024)
+#define MSC01_SC_CFG_OFS		0x0110
+#define MSC01_SC_CFG_GICPRES_MSK	0x00000004
+#define MSC01_SC_CFG_GICPRES_SHF	2
+#define MSC01_SC_CFG_GICENA_SHF		3
+
 /*
  * Malta RTC-device indirect register access.
  */
diff --git a/trunk/include/asm-mips/mips-boards/maltaint.h b/trunk/include/asm-mips/mips-boards/maltaint.h
index 7461318f1cd1..cea872fc6f5c 100644
--- a/trunk/include/asm-mips/mips-boards/maltaint.h
+++ b/trunk/include/asm-mips/mips-boards/maltaint.h
@@ -39,7 +39,9 @@
 #define MIPSCPU_INT_I8259A	MIPSCPU_INT_MB0
 #define MIPSCPU_INT_MB1		3
 #define MIPSCPU_INT_SMI		MIPSCPU_INT_MB1
+#define MIPSCPU_INT_IPI0	MIPSCPU_INT_MB1	/* GIC IPI */
 #define MIPSCPU_INT_MB2		4
+#define MIPSCPU_INT_IPI1	MIPSCPU_INT_MB2	/* GIC IPI */
 #define MIPSCPU_INT_MB3		5
 #define MIPSCPU_INT_COREHI	MIPSCPU_INT_MB3
 #define MIPSCPU_INT_MB4		6
@@ -76,6 +78,31 @@
 #define MSC01E_INT_PERFCTR	10
 #define MSC01E_INT_CPUCTR	11
 
+/* GIC's Nomenclature for Core Interrupt Pins on the Malta */
+#define GIC_CPU_INT0		0 /* Core Interrupt 2 	*/
+#define GIC_CPU_INT1		1 /* .			*/
+#define GIC_CPU_INT2		2 /* .			*/
+#define GIC_CPU_INT3		3 /* .			*/
+#define GIC_CPU_INT4		4 /* .			*/
+#define GIC_CPU_INT5		5 /* Core Interrupt 5   */
+
+#define GIC_EXT_INTR(x)		x
+
+/* Dummy data */
+#define X			0xdead
+
+/* External Interrupts used for IPI */
+#define GIC_IPI_EXT_INTR_RESCHED_VPE0	16
+#define GIC_IPI_EXT_INTR_CALLFNC_VPE0	17
+#define GIC_IPI_EXT_INTR_RESCHED_VPE1	18
+#define GIC_IPI_EXT_INTR_CALLFNC_VPE1	19
+#define GIC_IPI_EXT_INTR_RESCHED_VPE2	20
+#define GIC_IPI_EXT_INTR_CALLFNC_VPE2	21
+#define GIC_IPI_EXT_INTR_RESCHED_VPE3	22
+#define GIC_IPI_EXT_INTR_CALLFNC_VPE3	23
+
+#define MIPS_GIC_IRQ_BASE	(MIPS_CPU_IRQ_BASE + 8)
+
 #ifndef __ASSEMBLY__
 extern void maltaint_init(void);
 #endif
diff --git a/trunk/include/asm-mips/mips-boards/maltasmp.h b/trunk/include/asm-mips/mips-boards/maltasmp.h
new file mode 100644
index 000000000000..8d7e955d506e
--- /dev/null
+++ b/trunk/include/asm-mips/mips-boards/maltasmp.h
@@ -0,0 +1,36 @@
+/*
+ * There are several SMP models supported
+ * SMTC is mutually exclusive to other options (atm)
+ */
+#if defined(CONFIG_MIPS_MT_SMTC)
+#define malta_smtc	1
+#define malta_cmp	0
+#define malta_smvp	0
+#else
+#define malta_smtc	0
+#if defined(CONFIG_MIPS_CMP)
+extern int gcmp_present;
+#define malta_cmp	gcmp_present
+#else
+#define malta_cmp	0
+#endif
+/* FIXME: should become COMFIG_MIPS_MT_SMVP */
+#if defined(CONFIG_MIPS_MT_SMP)
+#define malta_smvp	1
+#else
+#define malta_smvp	0
+#endif
+#endif
+
+#include <asm/mipsregs.h>
+#include <asm/mipsmtregs.h>
+
+/* malta_smtc */
+#include <asm/smtc.h>
+#include <asm/smtc_ipi.h>
+
+/* malta_cmp */
+#include <asm/cmp.h>
+
+/* malta_smvp */
+#include <asm/smvp.h>
diff --git a/trunk/include/asm-mips/mipsmtregs.h b/trunk/include/asm-mips/mipsmtregs.h
index 5a2f8a3a6a1f..c9420aa97e32 100644
--- a/trunk/include/asm-mips/mipsmtregs.h
+++ b/trunk/include/asm-mips/mipsmtregs.h
@@ -197,8 +197,8 @@ static inline void __raw_evpe(void)
 	"	.set	pop						\n");
 }
 
-/* Enable multiMT if previous suggested it should be.
-   EMT_ENABLE to force */
+/* Enable virtual processor execution if previous suggested it should be.
+   EVPE_ENABLE to force */
 
 #define EVPE_ENABLE MVPCONTROL_EVP
 
@@ -238,8 +238,8 @@ static inline void __raw_emt(void)
 	"	.set	reorder");
 }
 
-/* enable multiVPE if previous suggested it should be.
-   EVPE_ENABLE to force */
+/* enable multi-threaded execution if previous suggested it should be.
+   EMT_ENABLE to force */
 
 #define EMT_ENABLE VPECONTROL_TE
 
diff --git a/trunk/include/asm-mips/pgtable-32.h b/trunk/include/asm-mips/pgtable-32.h
index ceefe027c761..4396e9ffd418 100644
--- a/trunk/include/asm-mips/pgtable-32.h
+++ b/trunk/include/asm-mips/pgtable-32.h
@@ -107,7 +107,7 @@ static inline void pmd_clear(pmd_t *pmdp)
 	pmd_val(*pmdp) = ((unsigned long) invalid_pte_table);
 }
 
-#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32_R1)
+#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32)
 #define pte_page(x)		pfn_to_page(pte_pfn(x))
 #define pte_pfn(x)		((unsigned long)((x).pte_high >> 6))
 static inline pte_t
@@ -130,7 +130,7 @@ pfn_pte(unsigned long pfn, pgprot_t prot)
 #define pte_pfn(x)		((unsigned long)((x).pte >> PAGE_SHIFT))
 #define pfn_pte(pfn, prot)	__pte(((unsigned long long)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 #endif
-#endif /* defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32_R1) */
+#endif /* defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32) */
 
 #define __pgd_offset(address)	pgd_index(address)
 #define __pud_offset(address)	(((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
diff --git a/trunk/include/asm-mips/pgtable-bits.h b/trunk/include/asm-mips/pgtable-bits.h
index 7494ba91112a..60e2f9338fcd 100644
--- a/trunk/include/asm-mips/pgtable-bits.h
+++ b/trunk/include/asm-mips/pgtable-bits.h
@@ -32,14 +32,14 @@
  * unpredictable things.  The code (when it is written) to deal with
  * this problem will be in the update_mmu_cache() code for the r4k.
  */
-#if defined(CONFIG_CPU_MIPS32_R1) && defined(CONFIG_64BIT_PHYS_ADDR)
+#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32)
 
 #define _PAGE_PRESENT               (1<<6)  /* implemented in software */
 #define _PAGE_READ                  (1<<7)  /* implemented in software */
 #define _PAGE_WRITE                 (1<<8)  /* implemented in software */
 #define _PAGE_ACCESSED              (1<<9)  /* implemented in software */
 #define _PAGE_MODIFIED              (1<<10) /* implemented in software */
-#define _PAGE_FILE                  (1<<10)  /* set:pagecache unset:swap */
+#define _PAGE_FILE                  (1<<10) /* set:pagecache unset:swap */
 
 #define _PAGE_R4KBUG                (1<<0)  /* workaround for r4k bug  */
 #define _PAGE_GLOBAL                (1<<0)
@@ -47,15 +47,9 @@
 #define _PAGE_SILENT_READ           (1<<1)  /* synonym                 */
 #define _PAGE_DIRTY                 (1<<2)  /* The MIPS dirty bit      */
 #define _PAGE_SILENT_WRITE          (1<<2)
+#define _CACHE_SHIFT                3
 #define _CACHE_MASK                 (7<<3)
 
-/* MIPS32 defines only values 2 and 3. The rest are implementation
- * dependent.
- */
-#define _CACHE_UNCACHED             (2<<3)
-#define _CACHE_CACHABLE_NONCOHERENT (3<<3)
-#define _CACHE_CACHABLE_COW         (3<<3)  /* Au1x                    */
-
 #else
 
 #define _PAGE_PRESENT               (1<<0)  /* implemented in software */
@@ -74,75 +68,72 @@
 #define _PAGE_SILENT_WRITE          (1<<10)
 #define _CACHE_UNCACHED             (1<<11)
 #define _CACHE_MASK                 (1<<11)
-#define _CACHE_CACHABLE_NONCOHERENT 0
 
 #else
+
 #define _PAGE_R4KBUG                (1<<5)  /* workaround for r4k bug  */
 #define _PAGE_GLOBAL                (1<<6)
 #define _PAGE_VALID                 (1<<7)
 #define _PAGE_SILENT_READ           (1<<7)  /* synonym                 */
 #define _PAGE_DIRTY                 (1<<8)  /* The MIPS dirty bit      */
 #define _PAGE_SILENT_WRITE          (1<<8)
+#define _CACHE_SHIFT		    9
 #define _CACHE_MASK                 (7<<9)
 
-#ifdef CONFIG_CPU_SB1
+#endif
+#endif /* defined(CONFIG_64BIT_PHYS_ADDR && defined(CONFIG_CPU_MIPS32) */
+
+
+/*
+ * Cache attributes
+ */
+#if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
+
+#define _CACHE_CACHABLE_NONCOHERENT 0
+
+#elif defined(CONFIG_CPU_SB1)
 
 /* No penalty for being coherent on the SB1, so just
    use it for "noncoherent" spaces, too.  Shouldn't hurt. */
 
-#define _CACHE_UNCACHED             (2<<9)
-#define _CACHE_CACHABLE_COW         (5<<9)
-#define _CACHE_CACHABLE_NONCOHERENT (5<<9)
-#define _CACHE_UNCACHED_ACCELERATED (7<<9)
+#define _CACHE_UNCACHED             (2<<_CACHE_SHIFT)
+#define _CACHE_CACHABLE_COW         (5<<_CACHE_SHIFT)
+#define _CACHE_CACHABLE_NONCOHERENT (5<<_CACHE_SHIFT)
+#define _CACHE_UNCACHED_ACCELERATED (7<<_CACHE_SHIFT)
 
 #elif defined(CONFIG_CPU_RM9000)
 
-#define _CACHE_WT			(0 << 9)
-#define _CACHE_WTWA			(1 << 9)
-#define _CACHE_UC_B			(2 << 9)
-#define _CACHE_WB			(3 << 9)
-#define _CACHE_CWBEA			(4 << 9)
-#define _CACHE_CWB			(5 << 9)
-#define _CACHE_UCNB			(6 << 9)
-#define _CACHE_FPC			(7 << 9)
+#define _CACHE_WT		    (0<<_CACHE_SHIFT)
+#define _CACHE_WTWA		    (1<<_CACHE_SHIFT)
+#define _CACHE_UC_B		    (2<<_CACHE_SHIFT)
+#define _CACHE_WB		    (3<<_CACHE_SHIFT)
+#define _CACHE_CWBEA		    (4<<_CACHE_SHIFT)
+#define _CACHE_CWB		    (5<<_CACHE_SHIFT)
+#define _CACHE_UCNB		    (6<<_CACHE_SHIFT)
+#define _CACHE_FPC		    (7<<_CACHE_SHIFT)
 
-#define _CACHE_UNCACHED			_CACHE_UC_B
-#define _CACHE_CACHABLE_NONCOHERENT	_CACHE_WB
+#define _CACHE_UNCACHED		    _CACHE_UC_B
+#define _CACHE_CACHABLE_NONCOHERENT _CACHE_WB
 
 #else
 
-#define _CACHE_CACHABLE_NO_WA       (0<<9)  /* R4600 only              */
-#define _CACHE_CACHABLE_WA          (1<<9)  /* R4600 only              */
-#define _CACHE_UNCACHED             (2<<9)  /* R4[0246]00              */
-#define _CACHE_CACHABLE_NONCOHERENT (3<<9)  /* R4[0246]00              */
-#define _CACHE_CACHABLE_CE          (4<<9)  /* R4[04]00MC only         */
-#define _CACHE_CACHABLE_COW         (5<<9)  /* R4[04]00MC only         */
-#define _CACHE_CACHABLE_CUW         (6<<9)  /* R4[04]00MC only         */
-#define _CACHE_UNCACHED_ACCELERATED (7<<9)  /* R10000 only             */
+#define _CACHE_CACHABLE_NO_WA	    (0<<_CACHE_SHIFT)  /* R4600 only      */
+#define _CACHE_CACHABLE_WA	    (1<<_CACHE_SHIFT)  /* R4600 only      */
+#define _CACHE_UNCACHED             (2<<_CACHE_SHIFT)  /* R4[0246]00      */
+#define _CACHE_CACHABLE_NONCOHERENT (3<<_CACHE_SHIFT)  /* R4[0246]00      */
+#define _CACHE_CACHABLE_CE          (4<<_CACHE_SHIFT)  /* R4[04]00MC only */
+#define _CACHE_CACHABLE_COW         (5<<_CACHE_SHIFT)  /* R4[04]00MC only */
+#define _CACHE_CACHABLE_COHERENT    (5<<_CACHE_SHIFT)  /* MIPS32R2 CMP    */
+#define _CACHE_CACHABLE_CUW         (6<<_CACHE_SHIFT)  /* R4[04]00MC only */
+#define _CACHE_UNCACHED_ACCELERATED (7<<_CACHE_SHIFT)  /* R10000 only     */
 
 #endif
-#endif
-#endif /* defined(CONFIG_CPU_MIPS32_R1) && defined(CONFIG_64BIT_PHYS_ADDR) */
 
 #define __READABLE	(_PAGE_READ | _PAGE_SILENT_READ | _PAGE_ACCESSED)
 #define __WRITEABLE	(_PAGE_WRITE | _PAGE_SILENT_WRITE | _PAGE_MODIFIED)
 
 #define _PAGE_CHG_MASK  (PAGE_MASK | _PAGE_ACCESSED | _PAGE_MODIFIED | _CACHE_MASK)
 
-#ifdef CONFIG_MIPS_UNCACHED
-#define PAGE_CACHABLE_DEFAULT	_CACHE_UNCACHED
-#elif defined(CONFIG_DMA_NONCOHERENT)
-#define PAGE_CACHABLE_DEFAULT	_CACHE_CACHABLE_NONCOHERENT
-#elif defined(CONFIG_CPU_RM9000)
-#define PAGE_CACHABLE_DEFAULT	_CACHE_CWB
-#else
-#define PAGE_CACHABLE_DEFAULT	_CACHE_CACHABLE_COW
-#endif
-
-#if defined(CONFIG_CPU_MIPS32_R1) && defined(CONFIG_64BIT_PHYS_ADDR)
-#define CONF_CM_DEFAULT		(PAGE_CACHABLE_DEFAULT >> 3)
-#else
-#define CONF_CM_DEFAULT		(PAGE_CACHABLE_DEFAULT >> 9)
-#endif
+#define CONF_CM_DEFAULT		(PAGE_CACHABLE_DEFAULT>>_CACHE_SHIFT)
 
 #endif /* _ASM_PGTABLE_BITS_H */
diff --git a/trunk/include/asm-mips/pgtable.h b/trunk/include/asm-mips/pgtable.h
index 17a7703a2969..2f597eea4448 100644
--- a/trunk/include/asm-mips/pgtable.h
+++ b/trunk/include/asm-mips/pgtable.h
@@ -23,15 +23,15 @@ struct vm_area_struct;
 
 #define PAGE_NONE	__pgprot(_PAGE_PRESENT | _CACHE_CACHABLE_NONCOHERENT)
 #define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
-			PAGE_CACHABLE_DEFAULT)
+				 _page_cachable_default)
 #define PAGE_COPY	__pgprot(_PAGE_PRESENT | _PAGE_READ | \
-			PAGE_CACHABLE_DEFAULT)
+				 _page_cachable_default)
 #define PAGE_READONLY	__pgprot(_PAGE_PRESENT | _PAGE_READ | \
-			PAGE_CACHABLE_DEFAULT)
+				 _page_cachable_default)
 #define PAGE_KERNEL	__pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE | \
-			_PAGE_GLOBAL | PAGE_CACHABLE_DEFAULT)
+				 _PAGE_GLOBAL | _page_cachable_default)
 #define PAGE_USERIO	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
-			PAGE_CACHABLE_DEFAULT)
+				 _page_cachable_default)
 #define PAGE_KERNEL_UNCACHED __pgprot(_PAGE_PRESENT | __READABLE | \
 			__WRITEABLE | _PAGE_GLOBAL | _CACHE_UNCACHED)
 
@@ -40,23 +40,30 @@ struct vm_area_struct;
  * read. Also, write permissions imply read permissions. This is the closest
  * we can get by reasonable means..
  */
-#define __P000	PAGE_NONE
-#define __P001	PAGE_READONLY
-#define __P010	PAGE_COPY
-#define __P011	PAGE_COPY
-#define __P100	PAGE_READONLY
-#define __P101	PAGE_READONLY
-#define __P110	PAGE_COPY
-#define __P111	PAGE_COPY
-
-#define __S000	PAGE_NONE
-#define __S001	PAGE_READONLY
-#define __S010	PAGE_SHARED
-#define __S011	PAGE_SHARED
-#define __S100	PAGE_READONLY
-#define __S101	PAGE_READONLY
-#define __S110	PAGE_SHARED
-#define __S111	PAGE_SHARED
+
+/*
+ * Dummy values to fill the table in mmap.c
+ * The real values will be generated at runtime
+ */
+#define __P000 __pgprot(0)
+#define __P001 __pgprot(0)
+#define __P010 __pgprot(0)
+#define __P011 __pgprot(0)
+#define __P100 __pgprot(0)
+#define __P101 __pgprot(0)
+#define __P110 __pgprot(0)
+#define __P111 __pgprot(0)
+
+#define __S000 __pgprot(0)
+#define __S001 __pgprot(0)
+#define __S010 __pgprot(0)
+#define __S011 __pgprot(0)
+#define __S100 __pgprot(0)
+#define __S101 __pgprot(0)
+#define __S110 __pgprot(0)
+#define __S111 __pgprot(0)
+
+extern unsigned long _page_cachable_default;
 
 /*
  * ZERO_PAGE is a global shared page that is always zero; used
@@ -79,7 +86,7 @@ extern void paging_init(void);
 #define pmd_page(pmd)		(pfn_to_page(pmd_phys(pmd) >> PAGE_SHIFT))
 #define pmd_page_vaddr(pmd)	pmd_val(pmd)
 
-#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32_R1)
+#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32)
 
 #define pte_none(pte)		(!(((pte).pte_low | (pte).pte_high) & ~_PAGE_GLOBAL))
 #define pte_present(pte)	((pte).pte_low & _PAGE_PRESENT)
@@ -182,7 +189,7 @@ extern pgd_t swapper_pg_dir[];
  * The following only work if pte_present() is true.
  * Undefined behaviour if not..
  */
-#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32_R1)
+#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32)
 static inline int pte_write(pte_t pte)	{ return pte.pte_low & _PAGE_WRITE; }
 static inline int pte_dirty(pte_t pte)	{ return pte.pte_low & _PAGE_MODIFIED; }
 static inline int pte_young(pte_t pte)	{ return pte.pte_low & _PAGE_ACCESSED; }
@@ -285,6 +292,8 @@ static inline pte_t pte_mkyoung(pte_t pte)
 	return pte;
 }
 #endif
+static inline int pte_special(pte_t pte)	{ return 0; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 /*
  * Macro to make mark a page protection value as "uncacheable".  Note
@@ -309,7 +318,7 @@ static inline pgprot_t pgprot_noncached(pgprot_t _prot)
  */
 #define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
 
-#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32_R1)
+#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32)
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	pte.pte_low  &= _PAGE_CHG_MASK;
diff --git a/trunk/include/asm-mips/r4k-timer.h b/trunk/include/asm-mips/r4k-timer.h
new file mode 100644
index 000000000000..a37d12b3b61c
--- /dev/null
+++ b/trunk/include/asm-mips/r4k-timer.h
@@ -0,0 +1,30 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2008 by Ralf Baechle (ralf@linux-mips.org)
+ */
+#ifndef __ASM_R4K_TYPES_H
+#define __ASM_R4K_TYPES_H
+
+#include <linux/compiler.h>
+
+#ifdef CONFIG_SYNC_R4K
+
+extern void synchronise_count_master(void);
+extern void synchronise_count_slave(void);
+
+#else
+
+static inline void synchronise_count_master(void)
+{
+}
+
+static inline void synchronise_count_slave(void)
+{
+}
+
+#endif
+
+#endif /* __ASM_R4K_TYPES_H */
diff --git a/trunk/include/asm-mips/smp-ops.h b/trunk/include/asm-mips/smp-ops.h
index b17fdfb5d818..43c207e72a63 100644
--- a/trunk/include/asm-mips/smp-ops.h
+++ b/trunk/include/asm-mips/smp-ops.h
@@ -51,6 +51,7 @@ static inline void register_smp_ops(struct plat_smp_ops *ops)
 #endif /* !CONFIG_SMP */
 
 extern struct plat_smp_ops up_smp_ops;
+extern struct plat_smp_ops cmp_smp_ops;
 extern struct plat_smp_ops vsmp_smp_ops;
 
 #endif /* __ASM_SMP_OPS_H */
diff --git a/trunk/include/asm-mips/smtc.h b/trunk/include/asm-mips/smtc.h
index ff3e8936b493..3639b28f80db 100644
--- a/trunk/include/asm-mips/smtc.h
+++ b/trunk/include/asm-mips/smtc.h
@@ -44,6 +44,7 @@ extern int mipsmt_build_cpu_map(int startslot);
 extern void mipsmt_prepare_cpus(void);
 extern void smtc_smp_finish(void);
 extern void smtc_boot_secondary(int cpu, struct task_struct *t);
+extern void smtc_cpus_done(void);
 
 /*
  * Sharing the TLB between multiple VPEs means that the
diff --git a/trunk/include/asm-mips/smvp.h b/trunk/include/asm-mips/smvp.h
new file mode 100644
index 000000000000..0d0e80a39e8a
--- /dev/null
+++ b/trunk/include/asm-mips/smvp.h
@@ -0,0 +1,19 @@
+#ifndef _ASM_SMVP_H
+#define _ASM_SMVP_H
+
+/*
+ * Definitions for SMVP multitasking on MIPS MT cores
+ */
+struct task_struct;
+
+extern void smvp_smp_setup(void);
+extern void smvp_smp_finish(void);
+extern void smvp_boot_secondary(int cpu, struct task_struct *t);
+extern void smvp_init_secondary(void);
+extern void smvp_smp_finish(void);
+extern void smvp_cpus_done(void);
+extern void smvp_prepare_cpus(unsigned int max_cpus);
+
+/* This is platform specific */
+extern void smvp_send_ipi(int cpu, unsigned int action);
+#endif /*  _ASM_SMVP_H */
diff --git a/trunk/include/asm-mips/traps.h b/trunk/include/asm-mips/traps.h
index d02e019b0127..e5dbde625ec2 100644
--- a/trunk/include/asm-mips/traps.h
+++ b/trunk/include/asm-mips/traps.h
@@ -23,5 +23,7 @@ extern int (*board_be_handler)(struct pt_regs *regs, int is_fixup);
 
 extern void (*board_nmi_handler_setup)(void);
 extern void (*board_ejtag_handler_setup)(void);
+extern void (*board_bind_eic_interrupt)(int irq, int regset);
+extern void (*board_watchpoint_handler)(struct pt_regs *regs);
 
 #endif /* _ASM_TRAPS_H */
diff --git a/trunk/include/asm-mips/tx4938/rbtx4938.h b/trunk/include/asm-mips/tx4938/rbtx4938.h
index b180488dcdc4..dfed7beb533f 100644
--- a/trunk/include/asm-mips/tx4938/rbtx4938.h
+++ b/trunk/include/asm-mips/tx4938/rbtx4938.h
@@ -67,44 +67,26 @@
 #define RBTX4938_INTF_MODEM	(1 << RBTX4938_INTB_MODEM)
 #define RBTX4938_INTF_SWINT	(1 << RBTX4938_INTB_SWINT)
 
-#define rbtx4938_fpga_rev_ptr	\
-	((volatile unsigned char *)RBTX4938_FPGA_REV_ADDR)
-#define rbtx4938_led_ptr	\
-	((volatile unsigned char *)RBTX4938_LED_ADDR)
-#define rbtx4938_dipsw_ptr	\
-	((volatile unsigned char *)RBTX4938_DIPSW_ADDR)
-#define rbtx4938_bdipsw_ptr	\
-	((volatile unsigned char *)RBTX4938_BDIPSW_ADDR)
-#define rbtx4938_imask_ptr	\
-	((volatile unsigned char *)RBTX4938_IMASK_ADDR)
-#define rbtx4938_imask2_ptr	\
-	((volatile unsigned char *)RBTX4938_IMASK2_ADDR)
-#define rbtx4938_intpol_ptr	\
-	((volatile unsigned char *)RBTX4938_INTPOL_ADDR)
-#define rbtx4938_istat_ptr	\
-	((volatile unsigned char *)RBTX4938_ISTAT_ADDR)
-#define rbtx4938_istat2_ptr	\
-	((volatile unsigned char *)RBTX4938_ISTAT2_ADDR)
-#define rbtx4938_imstat_ptr	\
-	((volatile unsigned char *)RBTX4938_IMSTAT_ADDR)
-#define rbtx4938_imstat2_ptr	\
-	((volatile unsigned char *)RBTX4938_IMSTAT2_ADDR)
-#define rbtx4938_softint_ptr	\
-	((volatile unsigned char *)RBTX4938_SOFTINT_ADDR)
-#define rbtx4938_piosel_ptr	\
-	((volatile unsigned char *)RBTX4938_PIOSEL_ADDR)
-#define rbtx4938_spics_ptr	\
-	((volatile unsigned char *)RBTX4938_SPICS_ADDR)
-#define rbtx4938_sfpwr_ptr	\
-	((volatile unsigned char *)RBTX4938_SFPWR_ADDR)
-#define rbtx4938_sfvol_ptr	\
-	((volatile unsigned char *)RBTX4938_SFVOL_ADDR)
-#define rbtx4938_softreset_ptr	\
-	((volatile unsigned char *)RBTX4938_SOFTRESET_ADDR)
-#define rbtx4938_softresetlock_ptr	\
-	((volatile unsigned char *)RBTX4938_SOFTRESETLOCK_ADDR)
-#define rbtx4938_pcireset_ptr	\
-	((volatile unsigned char *)RBTX4938_PCIRESET_ADDR)
+#define rbtx4938_fpga_rev_addr	((__u8 __iomem *)RBTX4938_FPGA_REV_ADDR)
+#define rbtx4938_led_addr	((__u8 __iomem *)RBTX4938_LED_ADDR)
+#define rbtx4938_dipsw_addr	((__u8 __iomem *)RBTX4938_DIPSW_ADDR)
+#define rbtx4938_bdipsw_addr	((__u8 __iomem *)RBTX4938_BDIPSW_ADDR)
+#define rbtx4938_imask_addr	((__u8 __iomem *)RBTX4938_IMASK_ADDR)
+#define rbtx4938_imask2_addr	((__u8 __iomem *)RBTX4938_IMASK2_ADDR)
+#define rbtx4938_intpol_addr	((__u8 __iomem *)RBTX4938_INTPOL_ADDR)
+#define rbtx4938_istat_addr	((__u8 __iomem *)RBTX4938_ISTAT_ADDR)
+#define rbtx4938_istat2_addr	((__u8 __iomem *)RBTX4938_ISTAT2_ADDR)
+#define rbtx4938_imstat_addr	((__u8 __iomem *)RBTX4938_IMSTAT_ADDR)
+#define rbtx4938_imstat2_addr	((__u8 __iomem *)RBTX4938_IMSTAT2_ADDR)
+#define rbtx4938_softint_addr	((__u8 __iomem *)RBTX4938_SOFTINT_ADDR)
+#define rbtx4938_piosel_addr	((__u8 __iomem *)RBTX4938_PIOSEL_ADDR)
+#define rbtx4938_spics_addr	((__u8 __iomem *)RBTX4938_SPICS_ADDR)
+#define rbtx4938_sfpwr_addr	((__u8 __iomem *)RBTX4938_SFPWR_ADDR)
+#define rbtx4938_sfvol_addr	((__u8 __iomem *)RBTX4938_SFVOL_ADDR)
+#define rbtx4938_softreset_addr	((__u8 __iomem *)RBTX4938_SOFTRESET_ADDR)
+#define rbtx4938_softresetlock_addr	\
+				((__u8 __iomem *)RBTX4938_SOFTRESETLOCK_ADDR)
+#define rbtx4938_pcireset_addr	((__u8 __iomem *)RBTX4938_PCIRESET_ADDR)
 
 /*
  * IRQ mappings
diff --git a/trunk/include/asm-mips/tx4938/tx4938.h b/trunk/include/asm-mips/tx4938/tx4938.h
index f7c448b90578..e8807f5c61e9 100644
--- a/trunk/include/asm-mips/tx4938/tx4938.h
+++ b/trunk/include/asm-mips/tx4938/tx4938.h
@@ -13,8 +13,6 @@
 #ifndef __ASM_TX_BOARDS_TX4938_H
 #define __ASM_TX_BOARDS_TX4938_H
 
-#include <asm/tx4938/tx4938_mips.h>
-
 #define tx4938_read_nfmc(addr) (*(volatile unsigned int *)(addr))
 #define tx4938_write_nfmc(b, addr) (*(volatile unsigned int *)(addr)) = (b)
 
@@ -54,28 +52,6 @@
 #define TX4938_ACLC_REG		(TX4938_REG_BASE + 0xf700)
 #define TX4938_SPI_REG		(TX4938_REG_BASE + 0xf800)
 
-#ifndef _LANGUAGE_ASSEMBLY
-#include <asm/byteorder.h>
-
-#define TX4938_MKA(x) ((u32)( ((u32)(TX4938_REG_BASE)) | ((u32)(x)) ))
-
-#define TX4938_RD08( reg      )   (*(vu08*)(reg))
-#define TX4938_WR08( reg, val )  ((*(vu08*)(reg))=(val))
-
-#define TX4938_RD16( reg      )   (*(vu16*)(reg))
-#define TX4938_WR16( reg, val )  ((*(vu16*)(reg))=(val))
-
-#define TX4938_RD32( reg      )   (*(vu32*)(reg))
-#define TX4938_WR32( reg, val )  ((*(vu32*)(reg))=(val))
-
-#define TX4938_RD64( reg      )   (*(vu64*)(reg))
-#define TX4938_WR64( reg, val )  ((*(vu64*)(reg))=(val))
-
-#define TX4938_RD( reg      ) TX4938_RD32( reg )
-#define TX4938_WR( reg, val ) TX4938_WR32( reg, val )
-
-#endif /* !__ASSEMBLY__ */
-
 #ifdef __ASSEMBLY__
 #define _CONST64(c)	c
 #else
@@ -261,18 +237,6 @@ struct tx4938_sio_reg {
 	volatile unsigned long rfifo;
 };
 
-struct tx4938_pio_reg {
-	volatile unsigned long dout;
-	volatile unsigned long din;
-	volatile unsigned long dir;
-	volatile unsigned long od;
-	volatile unsigned long flag[2];
-	volatile unsigned long pol;
-	volatile unsigned long intc;
-	volatile unsigned long maskcpu;
-	volatile unsigned long maskext;
-};
-
 struct tx4938_ndfmc_reg {
 	endian_def_l2(unused0, dtr);
 	endian_def_l2(unused1, mcr);
@@ -642,7 +606,7 @@ struct tx4938_ccfg_reg {
 #define tx4938_pcic1ptr		((struct tx4938_pcic_reg *)TX4938_PCIC1_REG)
 #define tx4938_ccfgptr		((struct tx4938_ccfg_reg *)TX4938_CCFG_REG)
 #define tx4938_sioptr(ch)	((struct tx4938_sio_reg *)TX4938_SIO_REG(ch))
-#define tx4938_pioptr		((struct tx4938_pio_reg *)TX4938_PIO_REG)
+#define tx4938_pioptr		((struct txx9_pio_reg __iomem *)TX4938_PIO_REG)
 #define tx4938_aclcptr		((struct tx4938_aclc_reg *)TX4938_ACLC_REG)
 #define tx4938_spiptr		((struct tx4938_spi_reg *)TX4938_SPI_REG)
 #define tx4938_sramcptr		((struct tx4938_sramc_reg *)TX4938_SRAMC_REG)
diff --git a/trunk/include/asm-mips/tx4938/tx4938_mips.h b/trunk/include/asm-mips/tx4938/tx4938_mips.h
deleted file mode 100644
index f346ff58b947..000000000000
--- a/trunk/include/asm-mips/tx4938/tx4938_mips.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * linux/include/asm-mips/tx4938/tx4938_mips.h
- * Generic bitmask definitions
- *
- * 2003-2005 (c) MontaVista Software, Inc. This file is licensed under the
- * terms of the GNU General Public License version 2. This program is
- * licensed "as is" without any warranty of any kind, whether express
- * or implied.
- *
- * Support for TX4938 in 2.6 - Manish Lachwani (mlachwani@mvista.com)
- */
-
-#ifndef TX4938_TX4938_MIPS_H
-#define TX4938_TX4938_MIPS_H
-#ifndef __ASSEMBLY__
-
-#define reg_rd08(r)    ((u8 )(*((vu8 *)(r))))
-#define reg_rd16(r)    ((u16)(*((vu16*)(r))))
-#define reg_rd32(r)    ((u32)(*((vu32*)(r))))
-#define reg_rd64(r)    ((u64)(*((vu64*)(r))))
-
-#define reg_wr08(r, v)  ((*((vu8 *)(r)))=((u8 )(v)))
-#define reg_wr16(r, v)  ((*((vu16*)(r)))=((u16)(v)))
-#define reg_wr32(r, v)  ((*((vu32*)(r)))=((u32)(v)))
-#define reg_wr64(r, v)  ((*((vu64*)(r)))=((u64)(v)))
-
-typedef volatile __signed char vs8;
-typedef volatile unsigned char vu8;
-
-typedef volatile __signed short vs16;
-typedef volatile unsigned short vu16;
-
-typedef volatile __signed int vs32;
-typedef volatile unsigned int vu32;
-
-typedef s8 s08;
-typedef vs8 vs08;
-
-typedef u8 u08;
-typedef vu8 vu08;
-
-#if (_MIPS_SZLONG == 64)
-
-typedef volatile __signed__ long vs64;
-typedef volatile unsigned long vu64;
-
-#else
-
-typedef volatile __signed__ long long vs64;
-typedef volatile unsigned long long vu64;
-
-#endif
-#endif
-#endif
diff --git a/trunk/include/asm-mips/txx9pio.h b/trunk/include/asm-mips/txx9pio.h
new file mode 100644
index 000000000000..3d6fa9f8d513
--- /dev/null
+++ b/trunk/include/asm-mips/txx9pio.h
@@ -0,0 +1,29 @@
+/*
+ * include/asm-mips/txx9pio.h
+ * TX39/TX49 PIO controller definitions.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __ASM_TXX9PIO_H
+#define __ASM_TXX9PIO_H
+
+#include <linux/types.h>
+
+struct txx9_pio_reg {
+	__u32 dout;
+	__u32 din;
+	__u32 dir;
+	__u32 od;
+	__u32 flag[2];
+	__u32 pol;
+	__u32 intc;
+	__u32 maskcpu;
+	__u32 maskext;
+};
+
+int txx9_gpio_init(unsigned long baseaddr,
+		   unsigned int base, unsigned int num);
+
+#endif /* __ASM_TXX9PIO_H */
diff --git a/trunk/include/asm-mips/unaligned.h b/trunk/include/asm-mips/unaligned.h
index 3249049e93aa..792404948571 100644
--- a/trunk/include/asm-mips/unaligned.h
+++ b/trunk/include/asm-mips/unaligned.h
@@ -5,25 +5,24 @@
  *
  * Copyright (C) 2007 Ralf Baechle (ralf@linux-mips.org)
  */
-#ifndef __ASM_GENERIC_UNALIGNED_H
-#define __ASM_GENERIC_UNALIGNED_H
+#ifndef _ASM_MIPS_UNALIGNED_H
+#define _ASM_MIPS_UNALIGNED_H
 
 #include <linux/compiler.h>
+#if defined(__MIPSEB__)
+# include <linux/unaligned/be_struct.h>
+# include <linux/unaligned/le_byteshift.h>
+# include <linux/unaligned/generic.h>
+# define get_unaligned	__get_unaligned_be
+# define put_unaligned	__put_unaligned_be
+#elif defined(__MIPSEL__)
+# include <linux/unaligned/le_struct.h>
+# include <linux/unaligned/be_byteshift.h>
+# include <linux/unaligned/generic.h>
+# define get_unaligned	__get_unaligned_le
+# define put_unaligned	__put_unaligned_le
+#else
+#  error "MIPS, but neither __MIPSEB__, nor __MIPSEL__???"
+#endif
 
-#define get_unaligned(ptr)					\
-({								\
-	struct __packed {					\
-		typeof(*(ptr)) __v;				\
-	} *__p = (void *) (ptr);				\
-	__p->__v;						\
-})
-
-#define put_unaligned(val, ptr)					\
-do {								\
-	struct __packed {					\
-		typeof(*(ptr)) __v;				\
-	} *__p = (void *) (ptr);				\
-	__p->__v = (val);					\
-} while(0)
-
-#endif /* __ASM_GENERIC_UNALIGNED_H */
+#endif /* _ASM_MIPS_UNALIGNED_H */
diff --git a/trunk/include/asm-mips/vr41xx/siu.h b/trunk/include/asm-mips/vr41xx/siu.h
index 98cdb4096485..da9f6e373409 100644
--- a/trunk/include/asm-mips/vr41xx/siu.h
+++ b/trunk/include/asm-mips/vr41xx/siu.h
@@ -1,7 +1,7 @@
 /*
  *  Include file for NEC VR4100 series Serial Interface Unit.
  *
- *  Copyright (C) 2005  Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
+ *  Copyright (C) 2005-2008  Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
@@ -49,4 +49,10 @@ typedef enum {
 
 extern void vr41xx_select_irda_module(irda_module_t module, irda_speed_t speed);
 
+#ifdef CONFIG_SERIAL_VR41XX_CONSOLE
+extern void vr41xx_siu_early_setup(struct uart_port *port);
+#else
+static inline void vr41xx_siu_early_setup(struct uart_port *port) {}
+#endif
+
 #endif /* __NEC_VR41XX_SIU_H */
diff --git a/trunk/include/asm-mips/vr41xx/vr41xx.h b/trunk/include/asm-mips/vr41xx/vr41xx.h
index 88b492f6ea9c..22be64971cc6 100644
--- a/trunk/include/asm-mips/vr41xx/vr41xx.h
+++ b/trunk/include/asm-mips/vr41xx/vr41xx.h
@@ -7,7 +7,7 @@
  * Copyright (C) 2001, 2002 Paul Mundt
  * Copyright (C) 2002 MontaVista Software, Inc.
  * Copyright (C) 2002 TimeSys Corp.
- * Copyright (C) 2003-2005 Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
+ * Copyright (C) 2003-2008 Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
@@ -143,4 +143,10 @@ extern void vr41xx_disable_csiint(uint16_t mask);
 extern void vr41xx_enable_bcuint(void);
 extern void vr41xx_disable_bcuint(void);
 
+#ifdef CONFIG_SERIAL_VR41XX_CONSOLE
+extern void vr41xx_siu_setup(void);
+#else
+static inline void vr41xx_siu_setup(void) {}
+#endif
+
 #endif /* __NEC_VR41XX_H */
diff --git a/trunk/include/asm-mn10300/pgtable.h b/trunk/include/asm-mn10300/pgtable.h
index 375c4941deda..6dc30fc827c4 100644
--- a/trunk/include/asm-mn10300/pgtable.h
+++ b/trunk/include/asm-mn10300/pgtable.h
@@ -224,6 +224,7 @@ static inline int pte_read(pte_t pte)	{ return pte_val(pte) & __PAGE_PROT_USER;
 static inline int pte_dirty(pte_t pte)	{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)	{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_write(pte_t pte)	{ return pte_val(pte) & __PAGE_PROT_WRITE; }
+static inline int pte_special(pte_t pte){ return 0; }
 
 /*
  * The following only works if pte_present() is not true.
@@ -265,6 +266,8 @@ static inline pte_t pte_mkwrite(pte_t pte)
 	return pte;
 }
 
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
+
 #define pte_ERROR(e) \
 	printk(KERN_ERR "%s:%d: bad pte %08lx.\n", \
 	       __FILE__, __LINE__, pte_val(e))
diff --git a/trunk/include/asm-mn10300/unaligned.h b/trunk/include/asm-mn10300/unaligned.h
index cad3afbd035f..0df671318ae4 100644
--- a/trunk/include/asm-mn10300/unaligned.h
+++ b/trunk/include/asm-mn10300/unaligned.h
@@ -8,129 +8,13 @@
  * as published by the Free Software Foundation; either version
  * 2 of the Licence, or (at your option) any later version.
  */
-#ifndef _ASM_UNALIGNED_H
-#define _ASM_UNALIGNED_H
+#ifndef _ASM_MN10300_UNALIGNED_H
+#define _ASM_MN10300_UNALIGNED_H
 
-#include <asm/types.h>
+#include <linux/unaligned/access_ok.h>
+#include <linux/unaligned/generic.h>
 
-#if 0
-extern int __bug_unaligned_x(void *ptr);
+#define get_unaligned	__get_unaligned_le
+#define put_unaligned	__put_unaligned_le
 
-/*
- * What is the most efficient way of loading/storing an unaligned value?
- *
- * That is the subject of this file.  Efficiency here is defined as
- * minimum code size with minimum register usage for the common cases.
- * It is currently not believed that long longs are common, so we
- * trade efficiency for the chars, shorts and longs against the long
- * longs.
- *
- * Current stats with gcc 2.7.2.2 for these functions:
- *
- *	ptrsize	get:	code	regs	put:	code	regs
- *	1		1	1		1	2
- *	2		3	2		3	2
- *	4		7	3		7	3
- *	8		20	6		16	6
- *
- * gcc 2.95.1 seems to code differently:
- *
- *	ptrsize	get:	code	regs	put:	code	regs
- *	1		1	1		1	2
- *	2		3	2		3	2
- *	4		7	4		7	4
- *	8		19	8		15	6
- *
- * which may or may not be more efficient (depending upon whether
- * you can afford the extra registers).  Hopefully the gcc 2.95
- * is inteligent enough to decide if it is better to use the
- * extra register, but evidence so far seems to suggest otherwise.
- *
- * Unfortunately, gcc is not able to optimise the high word
- * out of long long >> 32, or the low word from long long << 32
- */
-
-#define __get_unaligned_2(__p)					\
-	(__p[0] | __p[1] << 8)
-
-#define __get_unaligned_4(__p)					\
-	(__p[0] | __p[1] << 8 | __p[2] << 16 | __p[3] << 24)
-
-#define get_unaligned(ptr)					\
-({								\
-	unsigned int __v1, __v2;				\
-	__typeof__(*(ptr)) __v;					\
-	__u8 *__p = (__u8 *)(ptr);				\
-								\
-	switch (sizeof(*(ptr))) {				\
-	case 1:	__v = *(ptr);			break;		\
-	case 2: __v = __get_unaligned_2(__p);	break;		\
-	case 4: __v = __get_unaligned_4(__p);	break;		\
-	case 8:							\
-		__v2 = __get_unaligned_4((__p+4));		\
-		__v1 = __get_unaligned_4(__p);			\
-		__v = ((unsigned long long)__v2 << 32 | __v1);	\
-		break;						\
-	default: __v = __bug_unaligned_x(__p);	break;		\
-	}							\
-	__v;							\
-})
-
-
-static inline void __put_unaligned_2(__u32 __v, register __u8 *__p)
-{
-	*__p++ = __v;
-	*__p++ = __v >> 8;
-}
-
-static inline void __put_unaligned_4(__u32 __v, register __u8 *__p)
-{
-	__put_unaligned_2(__v >> 16, __p + 2);
-	__put_unaligned_2(__v, __p);
-}
-
-static inline void __put_unaligned_8(const unsigned long long __v, __u8 *__p)
-{
-	/*
-	 * tradeoff: 8 bytes of stack for all unaligned puts (2
-	 * instructions), or an extra register in the long long
-	 * case - go for the extra register.
-	 */
-	__put_unaligned_4(__v >> 32, __p + 4);
-	__put_unaligned_4(__v, __p);
-}
-
-/*
- * Try to store an unaligned value as efficiently as possible.
- */
-#define put_unaligned(val, ptr)						\
-	({								\
-		switch (sizeof(*(ptr))) {				\
-		case 1:							\
-			*(ptr) = (val);					\
-			break;						\
-		case 2:							\
-			__put_unaligned_2((val), (__u8 *)(ptr));	\
-			break;						\
-		case 4:							\
-			__put_unaligned_4((val), (__u8 *)(ptr));	\
-			break;						\
-		case 8:							\
-			__put_unaligned_8((val), (__u8 *)(ptr));	\
-			break;						\
-		default:						\
-			__bug_unaligned_x(ptr);				\
-			break;						\
-		}							\
-		(void) 0;						\
-	})
-
-
-#else
-
-#define get_unaligned(ptr) (*(ptr))
-#define put_unaligned(val, ptr) ({ *(ptr) = (val); (void) 0; })
-
-#endif
-
-#endif
+#endif /* _ASM_MN10300_UNALIGNED_H */
diff --git a/trunk/include/asm-parisc/pgtable.h b/trunk/include/asm-parisc/pgtable.h
index dc86adbec916..470a4b88124d 100644
--- a/trunk/include/asm-parisc/pgtable.h
+++ b/trunk/include/asm-parisc/pgtable.h
@@ -323,6 +323,7 @@ static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_write(pte_t pte)		{ return pte_val(pte) & _PAGE_WRITE; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~_PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkold(pte_t pte)	{ pte_val(pte) &= ~_PAGE_ACCESSED; return pte; }
@@ -330,6 +331,7 @@ static inline pte_t pte_wrprotect(pte_t pte)	{ pte_val(pte) &= ~_PAGE_WRITE; ret
 static inline pte_t pte_mkdirty(pte_t pte)	{ pte_val(pte) |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)	{ pte_val(pte) |= _PAGE_WRITE; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 /*
  * Conversion functions: convert a page and protection to a page entry,
diff --git a/trunk/include/asm-parisc/unaligned.h b/trunk/include/asm-parisc/unaligned.h
index 53c905838d93..dfc5d3321a54 100644
--- a/trunk/include/asm-parisc/unaligned.h
+++ b/trunk/include/asm-parisc/unaligned.h
@@ -1,7 +1,11 @@
-#ifndef _ASM_PARISC_UNALIGNED_H_
-#define _ASM_PARISC_UNALIGNED_H_
+#ifndef _ASM_PARISC_UNALIGNED_H
+#define _ASM_PARISC_UNALIGNED_H
 
-#include <asm-generic/unaligned.h>
+#include <linux/unaligned/be_struct.h>
+#include <linux/unaligned/le_byteshift.h>
+#include <linux/unaligned/generic.h>
+#define get_unaligned	__get_unaligned_be
+#define put_unaligned	__put_unaligned_be
 
 #ifdef __KERNEL__
 struct pt_regs;
@@ -9,4 +13,4 @@ void handle_unaligned(struct pt_regs *regs);
 int check_unaligned(struct pt_regs *regs);
 #endif
 
-#endif /* _ASM_PARISC_UNALIGNED_H_ */
+#endif /* _ASM_PARISC_UNALIGNED_H */
diff --git a/trunk/include/asm-powerpc/hugetlb.h b/trunk/include/asm-powerpc/hugetlb.h
new file mode 100644
index 000000000000..649c6c3b87b3
--- /dev/null
+++ b/trunk/include/asm-powerpc/hugetlb.h
@@ -0,0 +1,79 @@
+#ifndef _ASM_POWERPC_HUGETLB_H
+#define _ASM_POWERPC_HUGETLB_H
+
+#include <asm/page.h>
+
+
+int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
+			   unsigned long len);
+
+void hugetlb_free_pgd_range(struct mmu_gather **tlb, unsigned long addr,
+			    unsigned long end, unsigned long floor,
+			    unsigned long ceiling);
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t pte);
+
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep);
+
+/*
+ * If the arch doesn't supply something else, assume that hugepage
+ * size aligned regions are ok without further preparation.
+ */
+static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+{
+	if (len & ~HPAGE_MASK)
+		return -EINVAL;
+	if (addr & ~HPAGE_MASK)
+		return -EINVAL;
+	return 0;
+}
+
+static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
+{
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(mm, addr, ptep);
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+					     unsigned long addr, pte_t *ptep,
+					     pte_t pte, int dirty)
+{
+	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	return *ptep;
+}
+
+static inline int arch_prepare_hugepage(struct page *page)
+{
+	return 0;
+}
+
+static inline void arch_release_hugepage(struct page *page)
+{
+}
+
+#endif /* _ASM_POWERPC_HUGETLB_H */
diff --git a/trunk/include/asm-powerpc/irq.h b/trunk/include/asm-powerpc/irq.h
index b5c03127a9b9..5089deb8fec3 100644
--- a/trunk/include/asm-powerpc/irq.h
+++ b/trunk/include/asm-powerpc/irq.h
@@ -619,8 +619,6 @@ struct pt_regs;
 
 #define __ARCH_HAS_DO_SOFTIRQ
 
-extern void __do_softirq(void);
-
 #ifdef CONFIG_IRQSTACKS
 /*
  * Per-cpu stacks for handling hard and soft interrupts.
diff --git a/trunk/include/asm-powerpc/kvm.h b/trunk/include/asm-powerpc/kvm.h
index d1b530fbf8dd..f993e4198d5c 100644
--- a/trunk/include/asm-powerpc/kvm.h
+++ b/trunk/include/asm-powerpc/kvm.h
@@ -1,6 +1,55 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
 #ifndef __LINUX_KVM_POWERPC_H
 #define __LINUX_KVM_POWERPC_H
 
-/* powerpc does not support KVM */
+#include <asm/types.h>
+
+struct kvm_regs {
+	__u64 pc;
+	__u64 cr;
+	__u64 ctr;
+	__u64 lr;
+	__u64 xer;
+	__u64 msr;
+	__u64 srr0;
+	__u64 srr1;
+	__u64 pid;
+
+	__u64 sprg0;
+	__u64 sprg1;
+	__u64 sprg2;
+	__u64 sprg3;
+	__u64 sprg4;
+	__u64 sprg5;
+	__u64 sprg6;
+	__u64 sprg7;
+
+	__u64 gpr[32];
+};
+
+struct kvm_sregs {
+};
+
+struct kvm_fpu {
+	__u64 fpr[32];
+};
 
-#endif
+#endif /* __LINUX_KVM_POWERPC_H */
diff --git a/trunk/include/asm-powerpc/kvm_asm.h b/trunk/include/asm-powerpc/kvm_asm.h
new file mode 100644
index 000000000000..2197764796d9
--- /dev/null
+++ b/trunk/include/asm-powerpc/kvm_asm.h
@@ -0,0 +1,55 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#ifndef __POWERPC_KVM_ASM_H__
+#define __POWERPC_KVM_ASM_H__
+
+/* IVPR must be 64KiB-aligned. */
+#define VCPU_SIZE_ORDER 4
+#define VCPU_SIZE_LOG   (VCPU_SIZE_ORDER + 12)
+#define VCPU_TLB_PGSZ   PPC44x_TLB_64K
+#define VCPU_SIZE_BYTES (1<<VCPU_SIZE_LOG)
+
+#define BOOKE_INTERRUPT_CRITICAL 0
+#define BOOKE_INTERRUPT_MACHINE_CHECK 1
+#define BOOKE_INTERRUPT_DATA_STORAGE 2
+#define BOOKE_INTERRUPT_INST_STORAGE 3
+#define BOOKE_INTERRUPT_EXTERNAL 4
+#define BOOKE_INTERRUPT_ALIGNMENT 5
+#define BOOKE_INTERRUPT_PROGRAM 6
+#define BOOKE_INTERRUPT_FP_UNAVAIL 7
+#define BOOKE_INTERRUPT_SYSCALL 8
+#define BOOKE_INTERRUPT_AP_UNAVAIL 9
+#define BOOKE_INTERRUPT_DECREMENTER 10
+#define BOOKE_INTERRUPT_FIT 11
+#define BOOKE_INTERRUPT_WATCHDOG 12
+#define BOOKE_INTERRUPT_DTLB_MISS 13
+#define BOOKE_INTERRUPT_ITLB_MISS 14
+#define BOOKE_INTERRUPT_DEBUG 15
+#define BOOKE_MAX_INTERRUPT 15
+
+#define RESUME_FLAG_NV          (1<<0)  /* Reload guest nonvolatile state? */
+#define RESUME_FLAG_HOST        (1<<1)  /* Resume host? */
+
+#define RESUME_GUEST            0
+#define RESUME_GUEST_NV         RESUME_FLAG_NV
+#define RESUME_HOST             RESUME_FLAG_HOST
+#define RESUME_HOST_NV          (RESUME_FLAG_HOST|RESUME_FLAG_NV)
+
+#endif /* __POWERPC_KVM_ASM_H__ */
diff --git a/trunk/include/asm-powerpc/kvm_host.h b/trunk/include/asm-powerpc/kvm_host.h
new file mode 100644
index 000000000000..04ffbb8e0a35
--- /dev/null
+++ b/trunk/include/asm-powerpc/kvm_host.h
@@ -0,0 +1,152 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#ifndef __POWERPC_KVM_HOST_H__
+#define __POWERPC_KVM_HOST_H__
+
+#include <linux/mutex.h>
+#include <linux/timer.h>
+#include <linux/types.h>
+#include <linux/kvm_types.h>
+#include <asm/kvm_asm.h>
+
+#define KVM_MAX_VCPUS 1
+#define KVM_MEMORY_SLOTS 32
+/* memory slots that does not exposed to userspace */
+#define KVM_PRIVATE_MEM_SLOTS 4
+
+/* We don't currently support large pages. */
+#define KVM_PAGES_PER_HPAGE (1<<31)
+
+struct kvm;
+struct kvm_run;
+struct kvm_vcpu;
+
+struct kvm_vm_stat {
+	u32 remote_tlb_flush;
+};
+
+struct kvm_vcpu_stat {
+	u32 sum_exits;
+	u32 mmio_exits;
+	u32 dcr_exits;
+	u32 signal_exits;
+	u32 light_exits;
+	/* Account for special types of light exits: */
+	u32 itlb_real_miss_exits;
+	u32 itlb_virt_miss_exits;
+	u32 dtlb_real_miss_exits;
+	u32 dtlb_virt_miss_exits;
+	u32 syscall_exits;
+	u32 isi_exits;
+	u32 dsi_exits;
+	u32 emulated_inst_exits;
+	u32 dec_exits;
+	u32 ext_intr_exits;
+};
+
+struct tlbe {
+	u32 tid; /* Only the low 8 bits are used. */
+	u32 word0;
+	u32 word1;
+	u32 word2;
+};
+
+struct kvm_arch {
+};
+
+struct kvm_vcpu_arch {
+	/* Unmodified copy of the guest's TLB. */
+	struct tlbe guest_tlb[PPC44x_TLB_SIZE];
+	/* TLB that's actually used when the guest is running. */
+	struct tlbe shadow_tlb[PPC44x_TLB_SIZE];
+	/* Pages which are referenced in the shadow TLB. */
+	struct page *shadow_pages[PPC44x_TLB_SIZE];
+	/* Copy of the host's TLB. */
+	struct tlbe host_tlb[PPC44x_TLB_SIZE];
+
+	u32 host_stack;
+	u32 host_pid;
+
+	u64 fpr[32];
+	u32 gpr[32];
+
+	u32 pc;
+	u32 cr;
+	u32 ctr;
+	u32 lr;
+	u32 xer;
+
+	u32 msr;
+	u32 mmucr;
+	u32 sprg0;
+	u32 sprg1;
+	u32 sprg2;
+	u32 sprg3;
+	u32 sprg4;
+	u32 sprg5;
+	u32 sprg6;
+	u32 sprg7;
+	u32 srr0;
+	u32 srr1;
+	u32 csrr0;
+	u32 csrr1;
+	u32 dsrr0;
+	u32 dsrr1;
+	u32 dear;
+	u32 esr;
+	u32 dec;
+	u32 decar;
+	u32 tbl;
+	u32 tbu;
+	u32 tcr;
+	u32 tsr;
+	u32 ivor[16];
+	u32 ivpr;
+	u32 pir;
+	u32 pid;
+	u32 pvr;
+	u32 ccr0;
+	u32 ccr1;
+	u32 dbcr0;
+	u32 dbcr1;
+
+	u32 last_inst;
+	u32 fault_dear;
+	u32 fault_esr;
+	gpa_t paddr_accessed;
+
+	u8 io_gpr; /* GPR used as IO source/target */
+	u8 mmio_is_bigendian;
+	u8 dcr_needed;
+	u8 dcr_is_write;
+
+	u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
+
+	struct timer_list dec_timer;
+	unsigned long pending_exceptions;
+};
+
+struct kvm_guest_debug {
+	int enabled;
+	unsigned long bp[4];
+	int singlestep;
+};
+
+#endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/trunk/include/asm-powerpc/kvm_para.h b/trunk/include/asm-powerpc/kvm_para.h
new file mode 100644
index 000000000000..2d48f6a63d0b
--- /dev/null
+++ b/trunk/include/asm-powerpc/kvm_para.h
@@ -0,0 +1,37 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#ifndef __POWERPC_KVM_PARA_H__
+#define __POWERPC_KVM_PARA_H__
+
+#ifdef __KERNEL__
+
+static inline int kvm_para_available(void)
+{
+	return 0;
+}
+
+static inline unsigned int kvm_arch_para_features(void)
+{
+	return 0;
+}
+
+#endif /* __KERNEL__ */
+
+#endif /* __POWERPC_KVM_PARA_H__ */
diff --git a/trunk/include/asm-powerpc/kvm_ppc.h b/trunk/include/asm-powerpc/kvm_ppc.h
new file mode 100644
index 000000000000..7ac820308a7e
--- /dev/null
+++ b/trunk/include/asm-powerpc/kvm_ppc.h
@@ -0,0 +1,88 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#ifndef __POWERPC_KVM_PPC_H__
+#define __POWERPC_KVM_PPC_H__
+
+/* This file exists just so we can dereference kvm_vcpu, avoiding nested header
+ * dependencies. */
+
+#include <linux/mutex.h>
+#include <linux/timer.h>
+#include <linux/types.h>
+#include <linux/kvm_types.h>
+#include <linux/kvm_host.h>
+
+struct kvm_tlb {
+	struct tlbe guest_tlb[PPC44x_TLB_SIZE];
+	struct tlbe shadow_tlb[PPC44x_TLB_SIZE];
+};
+
+enum emulation_result {
+	EMULATE_DONE,         /* no further processing */
+	EMULATE_DO_MMIO,      /* kvm_run filled with MMIO request */
+	EMULATE_DO_DCR,       /* kvm_run filled with DCR request */
+	EMULATE_FAIL,         /* can't emulate this instruction */
+};
+
+extern const unsigned char exception_priority[];
+extern const unsigned char priority_exception[];
+
+extern int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
+extern char kvmppc_handlers_start[];
+extern unsigned long kvmppc_handler_len;
+
+extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu);
+extern int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                              unsigned int rt, unsigned int bytes,
+                              int is_bigendian);
+extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                               u32 val, unsigned int bytes, int is_bigendian);
+
+extern int kvmppc_emulate_instruction(struct kvm_run *run,
+                                      struct kvm_vcpu *vcpu);
+
+extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gfn_t gfn,
+                           u64 asid, u32 flags);
+extern void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, u64 eaddr, u64 asid);
+extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode);
+
+extern void kvmppc_check_and_deliver_interrupts(struct kvm_vcpu *vcpu);
+
+static inline void kvmppc_queue_exception(struct kvm_vcpu *vcpu, int exception)
+{
+	unsigned int priority = exception_priority[exception];
+	set_bit(priority, &vcpu->arch.pending_exceptions);
+}
+
+static inline void kvmppc_clear_exception(struct kvm_vcpu *vcpu, int exception)
+{
+	unsigned int priority = exception_priority[exception];
+	clear_bit(priority, &vcpu->arch.pending_exceptions);
+}
+
+static inline void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr)
+{
+	if ((new_msr & MSR_PR) != (vcpu->arch.msr & MSR_PR))
+		kvmppc_mmu_priv_switch(vcpu, new_msr & MSR_PR);
+
+	vcpu->arch.msr = new_msr;
+}
+
+#endif /* __POWERPC_KVM_PPC_H__ */
diff --git a/trunk/include/asm-powerpc/mmu-44x.h b/trunk/include/asm-powerpc/mmu-44x.h
index c8b02d97f753..a825524c981a 100644
--- a/trunk/include/asm-powerpc/mmu-44x.h
+++ b/trunk/include/asm-powerpc/mmu-44x.h
@@ -53,6 +53,8 @@
 
 #ifndef __ASSEMBLY__
 
+extern unsigned int tlb_44x_hwater;
+
 typedef struct {
 	unsigned long id;
 	unsigned long vdso_base;
diff --git a/trunk/include/asm-powerpc/page_64.h b/trunk/include/asm-powerpc/page_64.h
index 67834eae5702..25af4fc8daf4 100644
--- a/trunk/include/asm-powerpc/page_64.h
+++ b/trunk/include/asm-powerpc/page_64.h
@@ -128,11 +128,6 @@ extern void slice_init_context(struct mm_struct *mm, unsigned int psize);
 extern void slice_set_user_psize(struct mm_struct *mm, unsigned int psize);
 #define slice_mm_new_context(mm)	((mm)->context.id == 0)
 
-#define ARCH_HAS_HUGEPAGE_ONLY_RANGE
-extern int is_hugepage_only_range(struct mm_struct *m,
-				  unsigned long addr,
-				  unsigned long len);
-
 #endif /* __ASSEMBLY__ */
 #else
 #define slice_init()
@@ -146,8 +141,6 @@ do {						\
 
 #ifdef CONFIG_HUGETLB_PAGE
 
-#define ARCH_HAS_HUGETLB_FREE_PGD_RANGE
-#define ARCH_HAS_SETCLEAR_HUGE_PTE
 #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 
 #endif /* !CONFIG_HUGETLB_PAGE */
diff --git a/trunk/include/asm-powerpc/pgtable-ppc32.h b/trunk/include/asm-powerpc/pgtable-ppc32.h
index daea7692d070..7c97b5a08d08 100644
--- a/trunk/include/asm-powerpc/pgtable-ppc32.h
+++ b/trunk/include/asm-powerpc/pgtable-ppc32.h
@@ -504,6 +504,7 @@ static inline int pte_write(pte_t pte)		{ return pte_val(pte) & _PAGE_RW; }
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline void pte_uncache(pte_t pte)       { pte_val(pte) |= _PAGE_NO_CACHE; }
 static inline void pte_cache(pte_t pte)         { pte_val(pte) &= ~_PAGE_NO_CACHE; }
@@ -521,6 +522,8 @@ static inline pte_t pte_mkdirty(pte_t pte) {
 	pte_val(pte) |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte) {
 	pte_val(pte) |= _PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte) {
+	return pte; }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
diff --git a/trunk/include/asm-powerpc/pgtable-ppc64.h b/trunk/include/asm-powerpc/pgtable-ppc64.h
index dd4c26dc57d2..27f18695f7d6 100644
--- a/trunk/include/asm-powerpc/pgtable-ppc64.h
+++ b/trunk/include/asm-powerpc/pgtable-ppc64.h
@@ -239,6 +239,7 @@ static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_RW;}
 static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY;}
 static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED;}
 static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE;}
+static inline int pte_special(pte_t pte) { return 0; }
 
 static inline void pte_uncache(pte_t pte) { pte_val(pte) |= _PAGE_NO_CACHE; }
 static inline void pte_cache(pte_t pte)   { pte_val(pte) &= ~_PAGE_NO_CACHE; }
@@ -257,6 +258,8 @@ static inline pte_t pte_mkyoung(pte_t pte) {
 	pte_val(pte) |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkhuge(pte_t pte) {
 	return pte; }
+static inline pte_t pte_mkspecial(pte_t pte) {
+	return pte; }
 
 /* Atomic PTE updates */
 static inline unsigned long pte_update(struct mm_struct *mm,
diff --git a/trunk/include/asm-powerpc/processor.h b/trunk/include/asm-powerpc/processor.h
index fd98ca998b4f..cf83f2d7e2a5 100644
--- a/trunk/include/asm-powerpc/processor.h
+++ b/trunk/include/asm-powerpc/processor.h
@@ -138,6 +138,8 @@ typedef struct {
 
 struct thread_struct {
 	unsigned long	ksp;		/* Kernel stack pointer */
+	unsigned long	ksp_limit;	/* if ksp <= ksp_limit stack overflow */
+
 #ifdef CONFIG_PPC64
 	unsigned long	ksp_vsid;
 #endif
@@ -182,11 +184,14 @@ struct thread_struct {
 #define ARCH_MIN_TASKALIGN 16
 
 #define INIT_SP		(sizeof(init_stack) + (unsigned long) &init_stack)
+#define INIT_SP_LIMIT \
+	(_ALIGN_UP(sizeof(init_thread_info), 16) + (unsigned long) &init_stack)
 
 
 #ifdef CONFIG_PPC32
 #define INIT_THREAD { \
 	.ksp = INIT_SP, \
+	.ksp_limit = INIT_SP_LIMIT, \
 	.fs = KERNEL_DS, \
 	.pgdir = swapper_pg_dir, \
 	.fpexc_mode = MSR_FE0 | MSR_FE1, \
@@ -194,6 +199,7 @@ struct thread_struct {
 #else
 #define INIT_THREAD  { \
 	.ksp = INIT_SP, \
+	.ksp_limit = INIT_SP_LIMIT, \
 	.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
 	.fs = KERNEL_DS, \
 	.fpr = {0}, \
diff --git a/trunk/include/asm-ppc/rio.h b/trunk/include/asm-powerpc/rio.h
similarity index 100%
rename from trunk/include/asm-ppc/rio.h
rename to trunk/include/asm-powerpc/rio.h
diff --git a/trunk/include/asm-powerpc/system.h b/trunk/include/asm-powerpc/system.h
index fab1674b31b6..2b6559a6d113 100644
--- a/trunk/include/asm-powerpc/system.h
+++ b/trunk/include/asm-powerpc/system.h
@@ -204,7 +204,7 @@ extern int powersave_nap;	/* set if nap mode can be used in idle loop */
  * Changes the memory location '*ptr' to be val and returns
  * the previous value stored there.
  */
-static __inline__ unsigned long
+static __always_inline unsigned long
 __xchg_u32(volatile void *p, unsigned long val)
 {
 	unsigned long prev;
@@ -229,7 +229,7 @@ __xchg_u32(volatile void *p, unsigned long val)
  * Changes the memory location '*ptr' to be val and returns
  * the previous value stored there.
  */
-static __inline__ unsigned long
+static __always_inline unsigned long
 __xchg_u32_local(volatile void *p, unsigned long val)
 {
 	unsigned long prev;
@@ -247,7 +247,7 @@ __xchg_u32_local(volatile void *p, unsigned long val)
 }
 
 #ifdef CONFIG_PPC64
-static __inline__ unsigned long
+static __always_inline unsigned long
 __xchg_u64(volatile void *p, unsigned long val)
 {
 	unsigned long prev;
@@ -266,7 +266,7 @@ __xchg_u64(volatile void *p, unsigned long val)
 	return prev;
 }
 
-static __inline__ unsigned long
+static __always_inline unsigned long
 __xchg_u64_local(volatile void *p, unsigned long val)
 {
 	unsigned long prev;
@@ -290,7 +290,7 @@ __xchg_u64_local(volatile void *p, unsigned long val)
  */
 extern void __xchg_called_with_bad_pointer(void);
 
-static __inline__ unsigned long
+static __always_inline unsigned long
 __xchg(volatile void *ptr, unsigned long x, unsigned int size)
 {
 	switch (size) {
@@ -305,7 +305,7 @@ __xchg(volatile void *ptr, unsigned long x, unsigned int size)
 	return x;
 }
 
-static __inline__ unsigned long
+static __always_inline unsigned long
 __xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
 {
 	switch (size) {
@@ -338,7 +338,7 @@ __xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
  */
 #define __HAVE_ARCH_CMPXCHG	1
 
-static __inline__ unsigned long
+static __always_inline unsigned long
 __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
 {
 	unsigned int prev;
@@ -361,7 +361,7 @@ __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
 	return prev;
 }
 
-static __inline__ unsigned long
+static __always_inline unsigned long
 __cmpxchg_u32_local(volatile unsigned int *p, unsigned long old,
 			unsigned long new)
 {
@@ -384,7 +384,7 @@ __cmpxchg_u32_local(volatile unsigned int *p, unsigned long old,
 }
 
 #ifdef CONFIG_PPC64
-static __inline__ unsigned long
+static __always_inline unsigned long
 __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new)
 {
 	unsigned long prev;
@@ -406,7 +406,7 @@ __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new)
 	return prev;
 }
 
-static __inline__ unsigned long
+static __always_inline unsigned long
 __cmpxchg_u64_local(volatile unsigned long *p, unsigned long old,
 			unsigned long new)
 {
@@ -432,7 +432,7 @@ __cmpxchg_u64_local(volatile unsigned long *p, unsigned long old,
    if something tries to do an invalid cmpxchg().  */
 extern void __cmpxchg_called_with_bad_pointer(void);
 
-static __inline__ unsigned long
+static __always_inline unsigned long
 __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new,
 	  unsigned int size)
 {
@@ -448,7 +448,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new,
 	return old;
 }
 
-static __inline__ unsigned long
+static __always_inline unsigned long
 __cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new,
 	  unsigned int size)
 {
diff --git a/trunk/include/asm-powerpc/unaligned.h b/trunk/include/asm-powerpc/unaligned.h
index 6c95dfa2652f..5f1b1e3c2137 100644
--- a/trunk/include/asm-powerpc/unaligned.h
+++ b/trunk/include/asm-powerpc/unaligned.h
@@ -5,15 +5,12 @@
 
 /*
  * The PowerPC can do unaligned accesses itself in big endian mode.
- *
- * The strange macros are there to make sure these can't
- * be misused in a way that makes them not work on other
- * architectures where unaligned accesses aren't as simple.
  */
+#include <linux/unaligned/access_ok.h>
+#include <linux/unaligned/generic.h>
 
-#define get_unaligned(ptr) (*(ptr))
-
-#define put_unaligned(val, ptr) ((void)( *(ptr) = (val) ))
+#define get_unaligned	__get_unaligned_be
+#define put_unaligned	__put_unaligned_be
 
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_UNALIGNED_H */
diff --git a/trunk/include/asm-ppc/pgtable.h b/trunk/include/asm-ppc/pgtable.h
index 70435d32129a..55f9d38e3bf8 100644
--- a/trunk/include/asm-ppc/pgtable.h
+++ b/trunk/include/asm-ppc/pgtable.h
@@ -483,6 +483,7 @@ static inline int pte_write(pte_t pte)		{ return pte_val(pte) & _PAGE_RW; }
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
 
 static inline void pte_uncache(pte_t pte)       { pte_val(pte) |= _PAGE_NO_CACHE; }
 static inline void pte_cache(pte_t pte)         { pte_val(pte) &= ~_PAGE_NO_CACHE; }
@@ -500,6 +501,8 @@ static inline pte_t pte_mkdirty(pte_t pte) {
 	pte_val(pte) |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte) {
 	pte_val(pte) |= _PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte) {
+	return pte; }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
diff --git a/trunk/include/asm-s390/Kbuild b/trunk/include/asm-s390/Kbuild
index e92b429d2be1..13c9805349f1 100644
--- a/trunk/include/asm-s390/Kbuild
+++ b/trunk/include/asm-s390/Kbuild
@@ -7,6 +7,7 @@ header-y += tape390.h
 header-y += ucontext.h
 header-y += vtoc.h
 header-y += zcrypt.h
+header-y += kvm.h
 
 unifdef-y += cmb.h
 unifdef-y += debug.h
diff --git a/trunk/include/asm-s390/kvm.h b/trunk/include/asm-s390/kvm.h
index 573f2a351386..d74002f95794 100644
--- a/trunk/include/asm-s390/kvm.h
+++ b/trunk/include/asm-s390/kvm.h
@@ -1,6 +1,45 @@
 #ifndef __LINUX_KVM_S390_H
 #define __LINUX_KVM_S390_H
 
-/* s390 does not support KVM */
+/*
+ * asm-s390/kvm.h - KVM s390 specific structures and definitions
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+#include <asm/types.h>
+
+/* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */
+struct kvm_pic_state {
+	/* no PIC for s390 */
+};
+
+struct kvm_ioapic_state {
+	/* no IOAPIC for s390 */
+};
+
+/* for KVM_GET_REGS and KVM_SET_REGS */
+struct kvm_regs {
+	/* general purpose regs for s390 */
+	__u64 gprs[16];
+};
+
+/* for KVM_GET_SREGS and KVM_SET_SREGS */
+struct kvm_sregs {
+	__u32 acrs[16];
+	__u64 crs[16];
+};
+
+/* for KVM_GET_FPU and KVM_SET_FPU */
+struct kvm_fpu {
+	__u32 fpc;
+	__u64 fprs[16];
+};
 
 #endif
diff --git a/trunk/include/asm-s390/kvm_host.h b/trunk/include/asm-s390/kvm_host.h
new file mode 100644
index 000000000000..f8204a4f2e02
--- /dev/null
+++ b/trunk/include/asm-s390/kvm_host.h
@@ -0,0 +1,234 @@
+/*
+ * asm-s390/kvm_host.h - definition for kernel virtual machines on s390
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ */
+
+
+#ifndef ASM_KVM_HOST_H
+#define ASM_KVM_HOST_H
+#include <linux/kvm_host.h>
+#include <asm/debug.h>
+
+#define KVM_MAX_VCPUS 64
+#define KVM_MEMORY_SLOTS 32
+/* memory slots that does not exposed to userspace */
+#define KVM_PRIVATE_MEM_SLOTS 4
+
+struct kvm_guest_debug {
+};
+
+struct sca_entry {
+	atomic_t scn;
+	__u64	reserved;
+	__u64	sda;
+	__u64	reserved2[2];
+} __attribute__((packed));
+
+
+struct sca_block {
+	__u64	ipte_control;
+	__u64	reserved[5];
+	__u64	mcn;
+	__u64	reserved2;
+	struct sca_entry cpu[64];
+} __attribute__((packed));
+
+#define KVM_PAGES_PER_HPAGE 256
+
+#define CPUSTAT_HOST       0x80000000
+#define CPUSTAT_WAIT       0x10000000
+#define CPUSTAT_ECALL_PEND 0x08000000
+#define CPUSTAT_STOP_INT   0x04000000
+#define CPUSTAT_IO_INT     0x02000000
+#define CPUSTAT_EXT_INT    0x01000000
+#define CPUSTAT_RUNNING    0x00800000
+#define CPUSTAT_RETAINED   0x00400000
+#define CPUSTAT_TIMING_SUB 0x00020000
+#define CPUSTAT_SIE_SUB    0x00010000
+#define CPUSTAT_RRF        0x00008000
+#define CPUSTAT_SLSV       0x00004000
+#define CPUSTAT_SLSR       0x00002000
+#define CPUSTAT_ZARCH      0x00000800
+#define CPUSTAT_MCDS       0x00000100
+#define CPUSTAT_SM         0x00000080
+#define CPUSTAT_G          0x00000008
+#define CPUSTAT_J          0x00000002
+#define CPUSTAT_P          0x00000001
+
+struct sie_block {
+	atomic_t cpuflags;		/* 0x0000 */
+	__u32	prefix;			/* 0x0004 */
+	__u8	reserved8[32];		/* 0x0008 */
+	__u64	cputm;			/* 0x0028 */
+	__u64	ckc;			/* 0x0030 */
+	__u64	epoch;			/* 0x0038 */
+	__u8	reserved40[4];		/* 0x0040 */
+#define LCTL_CR0	0x8000
+	__u16   lctl;			/* 0x0044 */
+	__s16	icpua;			/* 0x0046 */
+	__u32	ictl;			/* 0x0048 */
+	__u32	eca;			/* 0x004c */
+	__u8	icptcode;		/* 0x0050 */
+	__u8	reserved51;		/* 0x0051 */
+	__u16	ihcpu;			/* 0x0052 */
+	__u8	reserved54[2];		/* 0x0054 */
+	__u16	ipa;			/* 0x0056 */
+	__u32	ipb;			/* 0x0058 */
+	__u32	scaoh;			/* 0x005c */
+	__u8	reserved60;		/* 0x0060 */
+	__u8	ecb;			/* 0x0061 */
+	__u8	reserved62[2];		/* 0x0062 */
+	__u32	scaol;			/* 0x0064 */
+	__u8	reserved68[4];		/* 0x0068 */
+	__u32	todpr;			/* 0x006c */
+	__u8	reserved70[16];		/* 0x0070 */
+	__u64	gmsor;			/* 0x0080 */
+	__u64	gmslm;			/* 0x0088 */
+	psw_t	gpsw;			/* 0x0090 */
+	__u64	gg14;			/* 0x00a0 */
+	__u64	gg15;			/* 0x00a8 */
+	__u8	reservedb0[30];		/* 0x00b0 */
+	__u16   iprcc;			/* 0x00ce */
+	__u8	reservedd0[48];		/* 0x00d0 */
+	__u64	gcr[16];		/* 0x0100 */
+	__u64	gbea;			/* 0x0180 */
+	__u8	reserved188[120];	/* 0x0188 */
+} __attribute__((packed));
+
+struct kvm_vcpu_stat {
+	u32 exit_userspace;
+	u32 exit_external_request;
+	u32 exit_external_interrupt;
+	u32 exit_stop_request;
+	u32 exit_validity;
+	u32 exit_instruction;
+	u32 instruction_lctl;
+	u32 instruction_lctg;
+	u32 exit_program_interruption;
+	u32 exit_instr_and_program;
+	u32 deliver_emergency_signal;
+	u32 deliver_service_signal;
+	u32 deliver_virtio_interrupt;
+	u32 deliver_stop_signal;
+	u32 deliver_prefix_signal;
+	u32 deliver_restart_signal;
+	u32 deliver_program_int;
+	u32 exit_wait_state;
+	u32 instruction_stidp;
+	u32 instruction_spx;
+	u32 instruction_stpx;
+	u32 instruction_stap;
+	u32 instruction_storage_key;
+	u32 instruction_stsch;
+	u32 instruction_chsc;
+	u32 instruction_stsi;
+	u32 instruction_stfl;
+	u32 instruction_sigp_sense;
+	u32 instruction_sigp_emergency;
+	u32 instruction_sigp_stop;
+	u32 instruction_sigp_arch;
+	u32 instruction_sigp_prefix;
+	u32 instruction_sigp_restart;
+	u32 diagnose_44;
+};
+
+struct io_info {
+	__u16        subchannel_id;            /* 0x0b8 */
+	__u16        subchannel_nr;            /* 0x0ba */
+	__u32        io_int_parm;              /* 0x0bc */
+	__u32        io_int_word;              /* 0x0c0 */
+};
+
+struct ext_info {
+	__u32 ext_params;
+	__u64 ext_params2;
+};
+
+#define PGM_OPERATION            0x01
+#define PGM_PRIVILEGED_OPERATION 0x02
+#define PGM_EXECUTE              0x03
+#define PGM_PROTECTION           0x04
+#define PGM_ADDRESSING           0x05
+#define PGM_SPECIFICATION        0x06
+#define PGM_DATA                 0x07
+
+struct pgm_info {
+	__u16 code;
+};
+
+struct prefix_info {
+	__u32 address;
+};
+
+struct interrupt_info {
+	struct list_head list;
+	u64	type;
+	union {
+		struct io_info io;
+		struct ext_info ext;
+		struct pgm_info pgm;
+		struct prefix_info prefix;
+	};
+};
+
+/* for local_interrupt.action_flags */
+#define ACTION_STORE_ON_STOP 1
+#define ACTION_STOP_ON_STOP  2
+
+struct local_interrupt {
+	spinlock_t lock;
+	struct list_head list;
+	atomic_t active;
+	struct float_interrupt *float_int;
+	int timer_due; /* event indicator for waitqueue below */
+	wait_queue_head_t wq;
+	atomic_t *cpuflags;
+	unsigned int action_bits;
+};
+
+struct float_interrupt {
+	spinlock_t lock;
+	struct list_head list;
+	atomic_t active;
+	int next_rr_cpu;
+	unsigned long idle_mask [(64 + sizeof(long) - 1) / sizeof(long)];
+	struct local_interrupt *local_int[64];
+};
+
+
+struct kvm_vcpu_arch {
+	struct sie_block *sie_block;
+	unsigned long	  guest_gprs[16];
+	s390_fp_regs      host_fpregs;
+	unsigned int      host_acrs[NUM_ACRS];
+	s390_fp_regs      guest_fpregs;
+	unsigned int      guest_acrs[NUM_ACRS];
+	struct local_interrupt local_int;
+	struct timer_list ckc_timer;
+	union  {
+		cpuid_t	  cpu_id;
+		u64	  stidp_data;
+	};
+};
+
+struct kvm_vm_stat {
+	u32 remote_tlb_flush;
+};
+
+struct kvm_arch{
+	unsigned long guest_origin;
+	unsigned long guest_memsize;
+	struct sca_block *sca;
+	debug_info_t *dbf;
+	struct float_interrupt float_int;
+};
+
+extern int sie64a(struct sie_block *, __u64 *);
+#endif
diff --git a/trunk/include/asm-s390/kvm_para.h b/trunk/include/asm-s390/kvm_para.h
new file mode 100644
index 000000000000..2c503796b619
--- /dev/null
+++ b/trunk/include/asm-s390/kvm_para.h
@@ -0,0 +1,150 @@
+/*
+ * asm-s390/kvm_para.h - definition for paravirtual devices on s390
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#ifndef __S390_KVM_PARA_H
+#define __S390_KVM_PARA_H
+
+/*
+ * Hypercalls for KVM on s390. The calling convention is similar to the
+ * s390 ABI, so we use R2-R6 for parameters 1-5. In addition we use R1
+ * as hypercall number and R7 as parameter 6. The return value is
+ * written to R2. We use the diagnose instruction as hypercall. To avoid
+ * conflicts with existing diagnoses for LPAR and z/VM, we do not use
+ * the instruction encoded number, but specify the number in R1 and
+ * use 0x500 as KVM hypercall
+ *
+ * Copyright IBM Corp. 2007,2008
+ * Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+static inline long kvm_hypercall0(unsigned long nr)
+{
+	register unsigned long __nr asm("1") = nr;
+	register long __rc asm("2");
+
+	asm volatile ("diag 2,4,0x500\n"
+		      : "=d" (__rc) : "d" (__nr): "memory", "cc");
+	return __rc;
+}
+
+static inline long kvm_hypercall1(unsigned long nr, unsigned long p1)
+{
+	register unsigned long __nr asm("1") = nr;
+	register unsigned long __p1 asm("2") = p1;
+	register long __rc asm("2");
+
+	asm volatile ("diag 2,4,0x500\n"
+		      : "=d" (__rc) : "d" (__nr), "0" (__p1) : "memory", "cc");
+	return __rc;
+}
+
+static inline long kvm_hypercall2(unsigned long nr, unsigned long p1,
+			       unsigned long p2)
+{
+	register unsigned long __nr asm("1") = nr;
+	register unsigned long __p1 asm("2") = p1;
+	register unsigned long __p2 asm("3") = p2;
+	register long __rc asm("2");
+
+	asm volatile ("diag 2,4,0x500\n"
+		      : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2)
+		      : "memory", "cc");
+	return __rc;
+}
+
+static inline long kvm_hypercall3(unsigned long nr, unsigned long p1,
+			       unsigned long p2, unsigned long p3)
+{
+	register unsigned long __nr asm("1") = nr;
+	register unsigned long __p1 asm("2") = p1;
+	register unsigned long __p2 asm("3") = p2;
+	register unsigned long __p3 asm("4") = p3;
+	register long __rc asm("2");
+
+	asm volatile ("diag 2,4,0x500\n"
+		      : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2),
+			"d" (__p3) : "memory", "cc");
+	return __rc;
+}
+
+
+static inline long kvm_hypercall4(unsigned long nr, unsigned long p1,
+			       unsigned long p2, unsigned long p3,
+			       unsigned long p4)
+{
+	register unsigned long __nr asm("1") = nr;
+	register unsigned long __p1 asm("2") = p1;
+	register unsigned long __p2 asm("3") = p2;
+	register unsigned long __p3 asm("4") = p3;
+	register unsigned long __p4 asm("5") = p4;
+	register long __rc asm("2");
+
+	asm volatile ("diag 2,4,0x500\n"
+		      : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2),
+			"d" (__p3), "d" (__p4) : "memory", "cc");
+	return __rc;
+}
+
+static inline long kvm_hypercall5(unsigned long nr, unsigned long p1,
+			       unsigned long p2, unsigned long p3,
+			       unsigned long p4, unsigned long p5)
+{
+	register unsigned long __nr asm("1") = nr;
+	register unsigned long __p1 asm("2") = p1;
+	register unsigned long __p2 asm("3") = p2;
+	register unsigned long __p3 asm("4") = p3;
+	register unsigned long __p4 asm("5") = p4;
+	register unsigned long __p5 asm("6") = p5;
+	register long __rc asm("2");
+
+	asm volatile ("diag 2,4,0x500\n"
+		      : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2),
+			"d" (__p3), "d" (__p4), "d" (__p5)  : "memory", "cc");
+	return __rc;
+}
+
+static inline long kvm_hypercall6(unsigned long nr, unsigned long p1,
+			       unsigned long p2, unsigned long p3,
+			       unsigned long p4, unsigned long p5,
+			       unsigned long p6)
+{
+	register unsigned long __nr asm("1") = nr;
+	register unsigned long __p1 asm("2") = p1;
+	register unsigned long __p2 asm("3") = p2;
+	register unsigned long __p3 asm("4") = p3;
+	register unsigned long __p4 asm("5") = p4;
+	register unsigned long __p5 asm("6") = p5;
+	register unsigned long __p6 asm("7") = p6;
+	register long __rc asm("2");
+
+	asm volatile ("diag 2,4,0x500\n"
+		      : "=d" (__rc) : "d" (__nr), "0" (__p1), "d" (__p2),
+			"d" (__p3), "d" (__p4), "d" (__p5), "d" (__p6)
+		      : "memory", "cc");
+	return __rc;
+}
+
+/* kvm on s390 is always paravirtualization enabled */
+static inline int kvm_para_available(void)
+{
+	return 1;
+}
+
+/* No feature bits are currently assigned for kvm on s390 */
+static inline unsigned int kvm_arch_para_features(void)
+{
+	return 0;
+}
+
+#endif /* __S390_KVM_PARA_H */
diff --git a/trunk/include/asm-s390/kvm_virtio.h b/trunk/include/asm-s390/kvm_virtio.h
new file mode 100644
index 000000000000..5c871a990c29
--- /dev/null
+++ b/trunk/include/asm-s390/kvm_virtio.h
@@ -0,0 +1,53 @@
+/*
+ * kvm_virtio.h - definition for virtio for kvm on s390
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#ifndef __KVM_S390_VIRTIO_H
+#define __KVM_S390_VIRTIO_H
+
+#include <linux/types.h>
+
+struct kvm_device_desc {
+	/* The device type: console, network, disk etc.  Type 0 terminates. */
+	__u8 type;
+	/* The number of virtqueues (first in config array) */
+	__u8 num_vq;
+	/*
+	 * The number of bytes of feature bits.  Multiply by 2: one for host
+	 * features and one for guest acknowledgements.
+	 */
+	__u8 feature_len;
+	/* The number of bytes of the config array after virtqueues. */
+	__u8 config_len;
+	/* A status byte, written by the Guest. */
+	__u8 status;
+	__u8 config[0];
+};
+
+/*
+ * This is how we expect the device configuration field for a virtqueue
+ * to be laid out in config space.
+ */
+struct kvm_vqconfig {
+	/* The token returned with an interrupt. Set by the guest */
+	__u64 token;
+	/* The address of the virtio ring */
+	__u64 address;
+	/* The number of entries in the virtio_ring */
+	__u16 num;
+
+};
+
+#define KVM_S390_VIRTIO_NOTIFY		0
+#define KVM_S390_VIRTIO_RESET		1
+#define KVM_S390_VIRTIO_SET_STATUS	2
+
+#endif
diff --git a/trunk/include/asm-s390/lowcore.h b/trunk/include/asm-s390/lowcore.h
index 5de3efb31445..0bc51d52a899 100644
--- a/trunk/include/asm-s390/lowcore.h
+++ b/trunk/include/asm-s390/lowcore.h
@@ -381,27 +381,32 @@ struct _lowcore
         /* whether the kernel died with panic() or not */
         __u32        panic_magic;              /* 0xe00 */
 
-	__u8         pad13[0x1200-0xe04];      /* 0xe04 */
+	__u8         pad13[0x11b8-0xe04];      /* 0xe04 */
+
+	/* 64 bit extparam used for pfault, diag 250 etc  */
+	__u64        ext_params2;               /* 0x11B8 */
+
+	__u8         pad14[0x1200-0x11C0];      /* 0x11C0 */
 
         /* System info area */ 
 
 	__u64        floating_pt_save_area[16]; /* 0x1200 */
 	__u64        gpregs_save_area[16];      /* 0x1280 */
 	__u32        st_status_fixed_logout[4]; /* 0x1300 */
-	__u8         pad14[0x1318-0x1310];      /* 0x1310 */
+	__u8         pad15[0x1318-0x1310];      /* 0x1310 */
 	__u32        prefixreg_save_area;       /* 0x1318 */
 	__u32        fpt_creg_save_area;        /* 0x131c */
-	__u8         pad15[0x1324-0x1320];      /* 0x1320 */
+	__u8         pad16[0x1324-0x1320];      /* 0x1320 */
 	__u32        tod_progreg_save_area;     /* 0x1324 */
 	__u32        cpu_timer_save_area[2];    /* 0x1328 */
 	__u32        clock_comp_save_area[2];   /* 0x1330 */
-	__u8         pad16[0x1340-0x1338];      /* 0x1338 */ 
+	__u8         pad17[0x1340-0x1338];      /* 0x1338 */
 	__u32        access_regs_save_area[16]; /* 0x1340 */ 
 	__u64        cregs_save_area[16];       /* 0x1380 */
 
 	/* align to the top of the prefix area */
 
-	__u8         pad17[0x2000-0x1400];      /* 0x1400 */
+	__u8         pad18[0x2000-0x1400];      /* 0x1400 */
 #endif /* !__s390x__ */
 } __attribute__((packed)); /* End structure*/
 
diff --git a/trunk/include/asm-s390/mmu.h b/trunk/include/asm-s390/mmu.h
index 1698e29c5b20..5dd5e7b3476f 100644
--- a/trunk/include/asm-s390/mmu.h
+++ b/trunk/include/asm-s390/mmu.h
@@ -7,6 +7,7 @@ typedef struct {
 	unsigned long asce_bits;
 	unsigned long asce_limit;
 	int noexec;
+	int pgstes;
 } mm_context_t;
 
 #endif
diff --git a/trunk/include/asm-s390/mmu_context.h b/trunk/include/asm-s390/mmu_context.h
index b5a34c6f91a9..4c2fbf48c9c4 100644
--- a/trunk/include/asm-s390/mmu_context.h
+++ b/trunk/include/asm-s390/mmu_context.h
@@ -20,7 +20,13 @@ static inline int init_new_context(struct task_struct *tsk,
 #ifdef CONFIG_64BIT
 	mm->context.asce_bits |= _ASCE_TYPE_REGION3;
 #endif
-	mm->context.noexec = s390_noexec;
+	if (current->mm->context.pgstes) {
+		mm->context.noexec = 0;
+		mm->context.pgstes = 1;
+	} else {
+		mm->context.noexec = s390_noexec;
+		mm->context.pgstes = 0;
+	}
 	mm->context.asce_limit = STACK_TOP_MAX;
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;
diff --git a/trunk/include/asm-s390/pgtable.h b/trunk/include/asm-s390/pgtable.h
index 65154dc9a9e5..f8347ce9c5a1 100644
--- a/trunk/include/asm-s390/pgtable.h
+++ b/trunk/include/asm-s390/pgtable.h
@@ -30,6 +30,7 @@
  */
 #ifndef __ASSEMBLY__
 #include <linux/mm_types.h>
+#include <asm/bitops.h>
 #include <asm/bug.h>
 #include <asm/processor.h>
 
@@ -219,6 +220,8 @@ extern char empty_zero_page[PAGE_SIZE];
 /* Software bits in the page table entry */
 #define _PAGE_SWT	0x001		/* SW pte type bit t */
 #define _PAGE_SWX	0x002		/* SW pte type bit x */
+#define _PAGE_SPECIAL	0x004		/* SW associated with special page */
+#define __HAVE_ARCH_PTE_SPECIAL
 
 /* Six different types of pages. */
 #define _PAGE_TYPE_EMPTY	0x400
@@ -258,6 +261,13 @@ extern char empty_zero_page[PAGE_SIZE];
  * swap pte is 1011 and 0001, 0011, 0101, 0111 are invalid.
  */
 
+/* Page status table bits for virtualization */
+#define RCP_PCL_BIT	55
+#define RCP_HR_BIT	54
+#define RCP_HC_BIT	53
+#define RCP_GR_BIT	50
+#define RCP_GC_BIT	49
+
 #ifndef __s390x__
 
 /* Bits in the segment table address-space-control-element */
@@ -510,9 +520,56 @@ static inline int pte_file(pte_t pte)
 	return (pte_val(pte) & mask) == _PAGE_TYPE_FILE;
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return (pte_val(pte) & _PAGE_SPECIAL);
+}
+
 #define __HAVE_ARCH_PTE_SAME
 #define pte_same(a,b)  (pte_val(a) == pte_val(b))
 
+static inline void rcp_lock(pte_t *ptep)
+{
+#ifdef CONFIG_PGSTE
+	unsigned long *pgste = (unsigned long *) (ptep + PTRS_PER_PTE);
+	preempt_disable();
+	while (test_and_set_bit(RCP_PCL_BIT, pgste))
+		;
+#endif
+}
+
+static inline void rcp_unlock(pte_t *ptep)
+{
+#ifdef CONFIG_PGSTE
+	unsigned long *pgste = (unsigned long *) (ptep + PTRS_PER_PTE);
+	clear_bit(RCP_PCL_BIT, pgste);
+	preempt_enable();
+#endif
+}
+
+/* forward declaration for SetPageUptodate in page-flags.h*/
+static inline void page_clear_dirty(struct page *page);
+#include <linux/page-flags.h>
+
+static inline void ptep_rcp_copy(pte_t *ptep)
+{
+#ifdef CONFIG_PGSTE
+	struct page *page = virt_to_page(pte_val(*ptep));
+	unsigned int skey;
+	unsigned long *pgste = (unsigned long *) (ptep + PTRS_PER_PTE);
+
+	skey = page_get_storage_key(page_to_phys(page));
+	if (skey & _PAGE_CHANGED)
+		set_bit_simple(RCP_GC_BIT, pgste);
+	if (skey & _PAGE_REFERENCED)
+		set_bit_simple(RCP_GR_BIT, pgste);
+	if (test_and_clear_bit_simple(RCP_HC_BIT, pgste))
+		SetPageDirty(page);
+	if (test_and_clear_bit_simple(RCP_HR_BIT, pgste))
+		SetPageReferenced(page);
+#endif
+}
+
 /*
  * query functions pte_write/pte_dirty/pte_young only work if
  * pte_present() is true. Undefined behaviour if not..
@@ -599,6 +656,8 @@ static inline void pmd_clear(pmd_t *pmd)
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
+	if (mm->context.pgstes)
+		ptep_rcp_copy(ptep);
 	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
 	if (mm->context.noexec)
 		pte_val(ptep[PTRS_PER_PTE]) = _PAGE_TYPE_EMPTY;
@@ -663,10 +722,34 @@ static inline pte_t pte_mkyoung(pte_t pte)
 	return pte;
 }
 
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	pte_val(pte) |= _PAGE_SPECIAL;
+	return pte;
+}
+
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long addr, pte_t *ptep)
 {
+#ifdef CONFIG_PGSTE
+	unsigned long physpage;
+	int young;
+	unsigned long *pgste;
+
+	if (!vma->vm_mm->context.pgstes)
+		return 0;
+	physpage = pte_val(*ptep) & PAGE_MASK;
+	pgste = (unsigned long *) (ptep + PTRS_PER_PTE);
+
+	young = ((page_get_storage_key(physpage) & _PAGE_REFERENCED) != 0);
+	rcp_lock(ptep);
+	if (young)
+		set_bit_simple(RCP_GR_BIT, pgste);
+	young |= test_and_clear_bit_simple(RCP_HR_BIT, pgste);
+	rcp_unlock(ptep);
+	return young;
+#endif
 	return 0;
 }
 
@@ -674,7 +757,13 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 					 unsigned long address, pte_t *ptep)
 {
-	/* No need to flush TLB; bits are in storage key */
+	/* No need to flush TLB
+	 * On s390 reference bits are in storage key and never in TLB
+	 * With virtualization we handle the reference bit, without we
+	 * we can simply return */
+#ifdef CONFIG_PGSTE
+	return ptep_test_and_clear_young(vma, address, ptep);
+#endif
 	return 0;
 }
 
@@ -693,15 +782,25 @@ static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
 			: "=m" (*ptep) : "m" (*ptep),
 			  "a" (pto), "a" (address));
 	}
-	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
 }
 
 static inline void ptep_invalidate(struct mm_struct *mm,
 				   unsigned long address, pte_t *ptep)
 {
+	if (mm->context.pgstes) {
+		rcp_lock(ptep);
+		__ptep_ipte(address, ptep);
+		ptep_rcp_copy(ptep);
+		pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+		rcp_unlock(ptep);
+		return;
+	}
 	__ptep_ipte(address, ptep);
-	if (mm->context.noexec)
+	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+	if (mm->context.noexec) {
 		__ptep_ipte(address, ptep + PTRS_PER_PTE);
+		pte_val(*(ptep + PTRS_PER_PTE)) = _PAGE_TYPE_EMPTY;
+	}
 }
 
 /*
@@ -966,6 +1065,7 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
 
 extern int add_shared_memory(unsigned long start, unsigned long size);
 extern int remove_shared_memory(unsigned long start, unsigned long size);
+extern int s390_enable_sie(void);
 
 /*
  * No page table caches to initialise
diff --git a/trunk/include/asm-s390/setup.h b/trunk/include/asm-s390/setup.h
index a76a6b8fd887..aaf4b518b940 100644
--- a/trunk/include/asm-s390/setup.h
+++ b/trunk/include/asm-s390/setup.h
@@ -62,6 +62,7 @@ extern unsigned long machine_flags;
 #define MACHINE_IS_VM		(machine_flags & 1)
 #define MACHINE_IS_P390		(machine_flags & 4)
 #define MACHINE_HAS_MVPG	(machine_flags & 16)
+#define MACHINE_IS_KVM		(machine_flags & 64)
 #define MACHINE_HAS_IDTE	(machine_flags & 128)
 #define MACHINE_HAS_DIAG9C	(machine_flags & 256)
 
diff --git a/trunk/include/asm-s390/unaligned.h b/trunk/include/asm-s390/unaligned.h
index 8ee86dbedd1f..da9627afe5d8 100644
--- a/trunk/include/asm-s390/unaligned.h
+++ b/trunk/include/asm-s390/unaligned.h
@@ -1,24 +1,13 @@
-/*
- *  include/asm-s390/unaligned.h
- *
- *  S390 version
- *
- *  Derived from "include/asm-i386/unaligned.h"
- */
-
-#ifndef __S390_UNALIGNED_H
-#define __S390_UNALIGNED_H
+#ifndef _ASM_S390_UNALIGNED_H
+#define _ASM_S390_UNALIGNED_H
 
 /*
  * The S390 can do unaligned accesses itself. 
- *
- * The strange macros are there to make sure these can't
- * be misused in a way that makes them not work on other
- * architectures where unaligned accesses aren't as simple.
  */
+#include <linux/unaligned/access_ok.h>
+#include <linux/unaligned/generic.h>
 
-#define get_unaligned(ptr) (*(ptr))
-
-#define put_unaligned(val, ptr) ((void)( *(ptr) = (val) ))
+#define get_unaligned	__get_unaligned_be
+#define put_unaligned	__put_unaligned_be
 
-#endif
+#endif /* _ASM_S390_UNALIGNED_H */
diff --git a/trunk/include/asm-sh/hugetlb.h b/trunk/include/asm-sh/hugetlb.h
new file mode 100644
index 000000000000..02402303d89b
--- /dev/null
+++ b/trunk/include/asm-sh/hugetlb.h
@@ -0,0 +1,91 @@
+#ifndef _ASM_SH_HUGETLB_H
+#define _ASM_SH_HUGETLB_H
+
+#include <asm/page.h>
+
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					 unsigned long addr,
+					 unsigned long len) {
+	return 0;
+}
+
+/*
+ * If the arch doesn't supply something else, assume that hugepage
+ * size aligned regions are ok without further preparation.
+ */
+static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+{
+	if (len & ~HPAGE_MASK)
+		return -EINVAL;
+	if (addr & ~HPAGE_MASK)
+		return -EINVAL;
+	return 0;
+}
+
+static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) {
+}
+
+static inline void hugetlb_free_pgd_range(struct mmu_gather **tlb,
+					  unsigned long addr, unsigned long end,
+					  unsigned long floor,
+					  unsigned long ceiling)
+{
+	free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+	set_pte_at(mm, addr, ptep, pte);
+}
+
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep)
+{
+	return ptep_get_and_clear(mm, addr, ptep);
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(mm, addr, ptep);
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+					     unsigned long addr, pte_t *ptep,
+					     pte_t pte, int dirty)
+{
+	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	return *ptep;
+}
+
+static inline int arch_prepare_hugepage(struct page *page)
+{
+	return 0;
+}
+
+static inline void arch_release_hugepage(struct page *page)
+{
+}
+
+#endif /* _ASM_SH_HUGETLB_H */
diff --git a/trunk/include/asm-sh/pgtable_32.h b/trunk/include/asm-sh/pgtable_32.h
index 3e3557c53c55..cbc731d35c25 100644
--- a/trunk/include/asm-sh/pgtable_32.h
+++ b/trunk/include/asm-sh/pgtable_32.h
@@ -326,6 +326,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 #define pte_dirty(pte)		((pte).pte_low & _PAGE_DIRTY)
 #define pte_young(pte)		((pte).pte_low & _PAGE_ACCESSED)
 #define pte_file(pte)		((pte).pte_low & _PAGE_FILE)
+#define pte_special(pte)	(0)
 
 #ifdef CONFIG_X2TLB
 #define pte_write(pte)		((pte).pte_high & _PAGE_EXT_USER_WRITE)
@@ -356,6 +357,8 @@ PTE_BIT_FUNC(low, mkdirty, |= _PAGE_DIRTY);
 PTE_BIT_FUNC(low, mkold, &= ~_PAGE_ACCESSED);
 PTE_BIT_FUNC(low, mkyoung, |= _PAGE_ACCESSED);
 
+static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
+
 /*
  * Macro and implementation to make a page protection as uncachable.
  */
diff --git a/trunk/include/asm-sh/pgtable_64.h b/trunk/include/asm-sh/pgtable_64.h
index f9dd9d311441..c78990cda557 100644
--- a/trunk/include/asm-sh/pgtable_64.h
+++ b/trunk/include/asm-sh/pgtable_64.h
@@ -254,10 +254,11 @@ extern void __handle_bad_pmd_kernel(pmd_t * pmd);
 /*
  * The following have defined behavior only work if pte_present() is true.
  */
-static inline int pte_dirty(pte_t pte){ return pte_val(pte) & _PAGE_DIRTY; }
-static inline int pte_young(pte_t pte){ return pte_val(pte) & _PAGE_ACCESSED; }
-static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; }
-static inline int pte_write(pte_t pte){ return pte_val(pte) & _PAGE_WRITE; }
+static inline int pte_dirty(pte_t pte)  { return pte_val(pte) & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte)  { return pte_val(pte) & _PAGE_ACCESSED; }
+static inline int pte_file(pte_t pte)   { return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_write(pte_t pte)  { return pte_val(pte) & _PAGE_WRITE; }
+static inline int pte_special(pte_t pte){ return 0; }
 
 static inline pte_t pte_wrprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_WRITE)); return pte; }
 static inline pte_t pte_mkclean(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
@@ -266,6 +267,7 @@ static inline pte_t pte_mkwrite(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) |
 static inline pte_t pte_mkdirty(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
 static inline pte_t pte_mkhuge(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_SZHUGE)); return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 
 /*
diff --git a/trunk/include/asm-sh/unaligned.h b/trunk/include/asm-sh/unaligned.h
index 5250e3063b42..c1641a01d50f 100644
--- a/trunk/include/asm-sh/unaligned.h
+++ b/trunk/include/asm-sh/unaligned.h
@@ -1,7 +1,19 @@
-#ifndef __ASM_SH_UNALIGNED_H
-#define __ASM_SH_UNALIGNED_H
+#ifndef _ASM_SH_UNALIGNED_H
+#define _ASM_SH_UNALIGNED_H
 
 /* SH can't handle unaligned accesses. */
-#include <asm-generic/unaligned.h>
+#ifdef __LITTLE_ENDIAN__
+# include <linux/unaligned/le_struct.h>
+# include <linux/unaligned/be_byteshift.h>
+# include <linux/unaligned/generic.h>
+# define get_unaligned	__get_unaligned_le
+# define put_unaligned	__put_unaligned_le
+#else
+# include <linux/unaligned/be_struct.h>
+# include <linux/unaligned/le_byteshift.h>
+# include <linux/unaligned/generic.h>
+# define get_unaligned	__get_unaligned_be
+# define put_unaligned	__put_unaligned_be
+#endif
 
-#endif /* __ASM_SH_UNALIGNED_H */
+#endif /* _ASM_SH_UNALIGNED_H */
diff --git a/trunk/include/asm-sparc/pgtable.h b/trunk/include/asm-sparc/pgtable.h
index 2cc235b74d94..d84af6d95f5c 100644
--- a/trunk/include/asm-sparc/pgtable.h
+++ b/trunk/include/asm-sparc/pgtable.h
@@ -219,6 +219,11 @@ static inline int pte_file(pte_t pte)
 	return pte_val(pte) & BTFIXUP_HALF(pte_filei);
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 /*
  */
 BTFIXUPDEF_HALF(pte_wrprotecti)
@@ -251,6 +256,8 @@ BTFIXUPDEF_CALL_CONST(pte_t, pte_mkyoung, pte_t)
 #define pte_mkdirty(pte) BTFIXUP_CALL(pte_mkdirty)(pte)
 #define pte_mkyoung(pte) BTFIXUP_CALL(pte_mkyoung)(pte)
 
+#define pte_mkspecial(pte)    (pte)
+
 #define pfn_pte(pfn, prot)		mk_pte(pfn_to_page(pfn), prot)
 
 BTFIXUPDEF_CALL(unsigned long,	 pte_pfn, pte_t)
diff --git a/trunk/include/asm-sparc/processor.h b/trunk/include/asm-sparc/processor.h
index e3006979709b..8898efbbbe07 100644
--- a/trunk/include/asm-sparc/processor.h
+++ b/trunk/include/asm-sparc/processor.h
@@ -1,5 +1,4 @@
-/* $Id: processor.h,v 1.83 2001/10/08 09:32:13 davem Exp $
- * include/asm-sparc/processor.h
+/* include/asm-sparc/processor.h
  *
  * Copyright (C) 1994 David S. Miller (davem@caip.rutgers.edu)
  */
@@ -65,7 +64,6 @@ struct thread_struct {
 	struct fpq	fpqueue[16];
 	unsigned long flags;
 	mm_segment_t current_ds;
-	int new_signal;
 };
 
 #define SPARC_FLAG_KTHREAD      0x1    /* task is a kernel thread */
diff --git a/trunk/include/asm-sparc/unaligned.h b/trunk/include/asm-sparc/unaligned.h
index b6f8eddd30af..11d2d5fb5902 100644
--- a/trunk/include/asm-sparc/unaligned.h
+++ b/trunk/include/asm-sparc/unaligned.h
@@ -1,6 +1,10 @@
-#ifndef _ASM_SPARC_UNALIGNED_H_
-#define _ASM_SPARC_UNALIGNED_H_
+#ifndef _ASM_SPARC_UNALIGNED_H
+#define _ASM_SPARC_UNALIGNED_H
 
-#include <asm-generic/unaligned.h>
+#include <linux/unaligned/be_struct.h>
+#include <linux/unaligned/le_byteshift.h>
+#include <linux/unaligned/generic.h>
+#define get_unaligned	__get_unaligned_be
+#define put_unaligned	__put_unaligned_be
 
 #endif /* _ASM_SPARC_UNALIGNED_H */
diff --git a/trunk/include/asm-sparc64/floppy.h b/trunk/include/asm-sparc64/floppy.h
index c47f58d6c15c..ca19f80a9b7d 100644
--- a/trunk/include/asm-sparc64/floppy.h
+++ b/trunk/include/asm-sparc64/floppy.h
@@ -293,7 +293,6 @@ static int sun_fd_eject(int drive)
 
 #ifdef CONFIG_PCI
 #include <asm/ebus.h>
-#include <asm/isa.h>
 #include <asm/ns87303.h>
 
 static struct ebus_dma_info sun_pci_fd_ebus_dma;
@@ -558,82 +557,6 @@ static int __init ebus_fdthree_p(struct linux_ebus_device *edev)
 }
 #endif
 
-#ifdef CONFIG_PCI
-#undef ISA_FLOPPY_WORKS
-
-#ifdef ISA_FLOPPY_WORKS
-static unsigned long __init isa_floppy_init(void)
-{
-	struct sparc_isa_bridge *isa_br;
-	struct sparc_isa_device *isa_dev = NULL;
-
-	for_each_isa(isa_br) {
-		for_each_isadev(isa_dev, isa_br) {
-			if (!strcmp(isa_dev->prom_node->name, "dma")) {
-				struct sparc_isa_device *child =
-					isa_dev->child;
-
-				while (child) {
-					if (!strcmp(child->prom_node->name,
-						    "floppy")) {
-						isa_dev = child;
-						goto isa_done;
-					}
-					child = child->next;
-				}
-			}
-		}
-	}
-isa_done:
-	if (!isa_dev)
-		return 0;
-
-	/* We could use DMA on devices behind the ISA bridge, but...
-	 *
-	 * There is a slight problem.  Normally on x86 kit the x86 processor
-	 * delays I/O port instructions when the ISA bus "dma in progress"
-	 * signal is active.  Well, sparc64 systems do not monitor this
-	 * signal thus we would need to block all I/O port accesses in software
-	 * when a dma transfer is active for some device.
-	 */
-
-	sun_fdc = (struct sun_flpy_controller *)isa_dev->resource.start;
-	FLOPPY_IRQ = isa_dev->irq;
-
-	sun_fdops.fd_inb = sun_pci_fd_inb;
-	sun_fdops.fd_outb = sun_pci_fd_outb;
-
-	can_use_virtual_dma = use_virtual_dma = 1;
-	sun_fdops.fd_enable_dma = sun_fd_enable_dma;
-	sun_fdops.fd_disable_dma = sun_fd_disable_dma;
-	sun_fdops.fd_set_dma_mode = sun_fd_set_dma_mode;
-	sun_fdops.fd_set_dma_addr = sun_fd_set_dma_addr;
-	sun_fdops.fd_set_dma_count = sun_fd_set_dma_count;
-	sun_fdops.get_dma_residue = sun_get_dma_residue;
-
-	sun_fdops.fd_request_irq = sun_fd_request_irq;
-	sun_fdops.fd_free_irq = sun_fd_free_irq;
-
-	/* Floppy eject is manual.   Actually, could determine this
-	 * via presence of 'manual' property in OBP node.
-	 */
-	sun_fdops.fd_eject = sun_pci_fd_eject;
-
-        fdc_status = (unsigned long) &sun_fdc->status_82077;
-
-	allowed_drive_mask = 0;
-	sun_floppy_types[0] = 0;
-	sun_floppy_types[1] = 4;
-
-	sun_pci_broken_drive = 1;
-	sun_fdops.fd_outb = sun_pci_fd_broken_outb;
-
-	return sun_floppy_types[0];
-}
-#endif /* ISA_FLOPPY_WORKS */
-
-#endif
-
 static unsigned long __init sun_floppy_init(void)
 {
 	char state[128];
@@ -667,13 +590,8 @@ static unsigned long __init sun_floppy_init(void)
 			}
 		}
 	ebus_done:
-		if (!edev) {
-#ifdef ISA_FLOPPY_WORKS
-			return isa_floppy_init();
-#else
+		if (!edev)
 			return 0;
-#endif
-		}
 
 		state_prop = of_get_property(edev->prom_node, "status", NULL);
 		if (state_prop && !strncmp(state_prop, "disabled", 8))
diff --git a/trunk/include/asm-sparc64/hugetlb.h b/trunk/include/asm-sparc64/hugetlb.h
new file mode 100644
index 000000000000..412af58926a0
--- /dev/null
+++ b/trunk/include/asm-sparc64/hugetlb.h
@@ -0,0 +1,84 @@
+#ifndef _ASM_SPARC64_HUGETLB_H
+#define _ASM_SPARC64_HUGETLB_H
+
+#include <asm/page.h>
+
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t pte);
+
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep);
+
+void hugetlb_prefault_arch_hook(struct mm_struct *mm);
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					 unsigned long addr,
+					 unsigned long len) {
+	return 0;
+}
+
+/*
+ * If the arch doesn't supply something else, assume that hugepage
+ * size aligned regions are ok without further preparation.
+ */
+static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+{
+	if (len & ~HPAGE_MASK)
+		return -EINVAL;
+	if (addr & ~HPAGE_MASK)
+		return -EINVAL;
+	return 0;
+}
+
+static inline void hugetlb_free_pgd_range(struct mmu_gather **tlb,
+					  unsigned long addr, unsigned long end,
+					  unsigned long floor,
+					  unsigned long ceiling)
+{
+	free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(mm, addr, ptep);
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+					     unsigned long addr, pte_t *ptep,
+					     pte_t pte, int dirty)
+{
+	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	return *ptep;
+}
+
+static inline int arch_prepare_hugepage(struct page *page)
+{
+	return 0;
+}
+
+static inline void arch_release_hugepage(struct page *page)
+{
+}
+
+#endif /* _ASM_SPARC64_HUGETLB_H */
diff --git a/trunk/include/asm-sparc64/isa.h b/trunk/include/asm-sparc64/isa.h
deleted file mode 100644
index ecd9290f78d4..000000000000
--- a/trunk/include/asm-sparc64/isa.h
+++ /dev/null
@@ -1,47 +0,0 @@
-/* $Id: isa.h,v 1.1 2001/05/11 04:31:55 davem Exp $
- * isa.h: Sparc64 layer for PCI to ISA bridge devices.
- *
- * Copyright (C) 2001 David S. Miller (davem@redhat.com)
- */
-
-#ifndef __SPARC64_ISA_H
-#define __SPARC64_ISA_H
-
-#include <asm/oplib.h>
-#include <asm/prom.h>
-#include <asm/of_device.h>
-
-struct sparc_isa_bridge;
-
-struct sparc_isa_device {
-	struct of_device	ofdev;
-	struct sparc_isa_device	*next;
-	struct sparc_isa_device	*child;
-	struct sparc_isa_bridge	*bus;
-	struct device_node	*prom_node;
-	struct resource		resource;
-	unsigned int		irq;
-};
-#define to_isa_device(d) container_of(d, struct sparc_isa_device, ofdev.dev)
-
-struct sparc_isa_bridge {
-	struct of_device	ofdev;
-	struct sparc_isa_bridge	*next;
-	struct sparc_isa_device	*devices;
-	struct pci_dev		*self;
-	int			index;
-	struct device_node	*prom_node;
-};
-#define to_isa_bridge(d) container_of(d, struct sparc_isa_bridge, ofdev.dev)
-
-extern struct sparc_isa_bridge	*isa_chain;
-
-extern void isa_init(void);
-
-#define for_each_isa(bus)						\
-        for((bus) = isa_chain; (bus); (bus) = (bus)->next)
-
-#define for_each_isadev(dev, bus)					\
-        for((dev) = (bus)->devices; (dev); (dev) = (dev)->next)
-
-#endif /* !(__SPARC64_ISA_H) */
diff --git a/trunk/include/asm-sparc64/page.h b/trunk/include/asm-sparc64/page.h
index e93a482aa24a..618117def0dc 100644
--- a/trunk/include/asm-sparc64/page.h
+++ b/trunk/include/asm-sparc64/page.h
@@ -39,8 +39,6 @@
 #define HPAGE_SIZE		(_AC(1,UL) << HPAGE_SHIFT)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1UL))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
-#define ARCH_HAS_SETCLEAR_HUGE_PTE
-#define ARCH_HAS_HUGETLB_PREFAULT_HOOK
 #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 #endif
 
diff --git a/trunk/include/asm-sparc64/pgtable.h b/trunk/include/asm-sparc64/pgtable.h
index 549e45266b68..0e200e7acec7 100644
--- a/trunk/include/asm-sparc64/pgtable.h
+++ b/trunk/include/asm-sparc64/pgtable.h
@@ -506,6 +506,11 @@ static inline pte_t pte_mkyoung(pte_t pte)
 	return __pte(pte_val(pte) | mask);
 }
 
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return pte;
+}
+
 static inline unsigned long pte_young(pte_t pte)
 {
 	unsigned long mask;
@@ -608,6 +613,11 @@ static inline unsigned long pte_present(pte_t pte)
 	return val;
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 #define pmd_set(pmdp, ptep)	\
 	(pmd_val(*(pmdp)) = (__pa((unsigned long) (ptep)) >> 11UL))
 #define pud_set(pudp, pmdp)	\
diff --git a/trunk/include/asm-sparc64/ptrace.h b/trunk/include/asm-sparc64/ptrace.h
index b4b951d570bb..714b81956f32 100644
--- a/trunk/include/asm-sparc64/ptrace.h
+++ b/trunk/include/asm-sparc64/ptrace.h
@@ -1,4 +1,3 @@
-/* $Id: ptrace.h,v 1.14 2002/02/09 19:49:32 davem Exp $ */
 #ifndef _SPARC64_PTRACE_H
 #define _SPARC64_PTRACE_H
 
@@ -8,10 +7,15 @@
  * stack during a system call and basically all traps.
  */
 
+/* This magic value must have the low 9 bits clear,
+ * as that is where we encode the %tt value, see below.
+ */
 #define PT_REGS_MAGIC 0x57ac6c00
 
 #ifndef __ASSEMBLY__
 
+#include <linux/types.h>
+
 struct pt_regs {
 	unsigned long u_regs[16]; /* globals and ins */
 	unsigned long tstate;
@@ -33,6 +37,23 @@ struct pt_regs {
 	unsigned int magic;
 };
 
+static inline int pt_regs_trap_type(struct pt_regs *regs)
+{
+	return regs->magic & 0x1ff;
+}
+
+static inline int pt_regs_clear_trap_type(struct pt_regs *regs)
+{
+	return regs->magic &= ~0x1ff;
+}
+
+static inline bool pt_regs_is_syscall(struct pt_regs *regs)
+{
+	int tt = pt_regs_trap_type(regs);
+
+	return (tt == 0x110 || tt == 0x111 || tt == 0x16d);
+}
+
 struct pt_regs32 {
 	unsigned int psr;
 	unsigned int pc;
diff --git a/trunk/include/asm-sparc64/thread_info.h b/trunk/include/asm-sparc64/thread_info.h
index 98252cd44dd6..71e42d1a80d9 100644
--- a/trunk/include/asm-sparc64/thread_info.h
+++ b/trunk/include/asm-sparc64/thread_info.h
@@ -1,5 +1,4 @@
-/* $Id: thread_info.h,v 1.1 2002/02/10 00:00:58 davem Exp $
- * thread_info.h: sparc64 low-level thread information
+/* thread_info.h: sparc64 low-level thread information
  *
  * Copyright (C) 2002  David S. Miller (davem@redhat.com)
  */
@@ -223,7 +222,7 @@ register struct thread_info *current_thread_info_reg asm("g6");
 #define TIF_NEED_RESCHED	3	/* rescheduling necessary */
 #define TIF_PERFCTR		4	/* performance counters active */
 #define TIF_UNALIGNED		5	/* allowed to do unaligned accesses */
-#define TIF_NEWSIGNALS		6	/* wants new-style signals */
+/* flag bit 6 is available */
 #define TIF_32BIT		7	/* 32-bit binary */
 /* flag bit 8 is available */
 #define TIF_SECCOMP		9	/* secure computing */
@@ -242,7 +241,6 @@ register struct thread_info *current_thread_info_reg asm("g6");
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
 #define _TIF_PERFCTR		(1<<TIF_PERFCTR)
 #define _TIF_UNALIGNED		(1<<TIF_UNALIGNED)
-#define _TIF_NEWSIGNALS		(1<<TIF_NEWSIGNALS)
 #define _TIF_32BIT		(1<<TIF_32BIT)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
diff --git a/trunk/include/asm-sparc64/unaligned.h b/trunk/include/asm-sparc64/unaligned.h
index 1ed3ba537772..edcebb09441e 100644
--- a/trunk/include/asm-sparc64/unaligned.h
+++ b/trunk/include/asm-sparc64/unaligned.h
@@ -1,6 +1,10 @@
-#ifndef _ASM_SPARC64_UNALIGNED_H_
-#define _ASM_SPARC64_UNALIGNED_H_
+#ifndef _ASM_SPARC64_UNALIGNED_H
+#define _ASM_SPARC64_UNALIGNED_H
 
-#include <asm-generic/unaligned.h>
+#include <linux/unaligned/be_struct.h>
+#include <linux/unaligned/le_byteshift.h>
+#include <linux/unaligned/generic.h>
+#define get_unaligned	__get_unaligned_be
+#define put_unaligned	__put_unaligned_be
 
 #endif /* _ASM_SPARC64_UNALIGNED_H */
diff --git a/trunk/include/asm-um/pgtable.h b/trunk/include/asm-um/pgtable.h
index 4102b443e925..02db81b7b86e 100644
--- a/trunk/include/asm-um/pgtable.h
+++ b/trunk/include/asm-um/pgtable.h
@@ -173,6 +173,11 @@ static inline int pte_newprot(pte_t pte)
 	return(pte_present(pte) && (pte_get_bits(pte, _PAGE_NEWPROT)));
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 /*
  * =================================
  * Flags setting section.
@@ -241,6 +246,11 @@ static inline pte_t pte_mknewpage(pte_t pte)
 	return(pte);
 }
 
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return(pte);
+}
+
 static inline void set_pte(pte_t *pteptr, pte_t pteval)
 {
 	pte_copy(*pteptr, pteval);
diff --git a/trunk/include/asm-um/unaligned.h b/trunk/include/asm-um/unaligned.h
index 1d2497c57274..a47196974e39 100644
--- a/trunk/include/asm-um/unaligned.h
+++ b/trunk/include/asm-um/unaligned.h
@@ -1,6 +1,6 @@
-#ifndef __UM_UNALIGNED_H
-#define __UM_UNALIGNED_H
+#ifndef _ASM_UM_UNALIGNED_H
+#define _ASM_UM_UNALIGNED_H
 
 #include "asm/arch/unaligned.h"
 
-#endif
+#endif /* _ASM_UM_UNALIGNED_H */
diff --git a/trunk/include/asm-v850/unaligned.h b/trunk/include/asm-v850/unaligned.h
index e30b18653a94..53122b28491e 100644
--- a/trunk/include/asm-v850/unaligned.h
+++ b/trunk/include/asm-v850/unaligned.h
@@ -1,6 +1,4 @@
 /*
- * include/asm-v850/unaligned.h -- Unaligned memory access
- *
  *  Copyright (C) 2001  NEC Corporation
  *  Copyright (C) 2001  Miles Bader <miles@gnu.org>
  *
@@ -8,123 +6,17 @@
  * Public License.  See the file COPYING in the main directory of this
  * archive for more details.
  *
- * This file is a copy of the arm version, include/asm-arm/unaligned.h
- *
  * Note that some v850 chips support unaligned access, but it seems too
  * annoying to use.
  */
+#ifndef _ASM_V850_UNALIGNED_H
+#define _ASM_V850_UNALIGNED_H
 
-#ifndef __V850_UNALIGNED_H__
-#define __V850_UNALIGNED_H__
-
-#include <asm/types.h>
-
-extern int __bug_unaligned_x(void *ptr);
-
-/*
- * What is the most efficient way of loading/storing an unaligned value?
- *
- * That is the subject of this file.  Efficiency here is defined as
- * minimum code size with minimum register usage for the common cases.
- * It is currently not believed that long longs are common, so we
- * trade efficiency for the chars, shorts and longs against the long
- * longs.
- *
- * Current stats with gcc 2.7.2.2 for these functions:
- *
- *	ptrsize	get:	code	regs	put:	code	regs
- *	1		1	1		1	2
- *	2		3	2		3	2
- *	4		7	3		7	3
- *	8		20	6		16	6
- *
- * gcc 2.95.1 seems to code differently:
- *
- *	ptrsize	get:	code	regs	put:	code	regs
- *	1		1	1		1	2
- *	2		3	2		3	2
- *	4		7	4		7	4
- *	8		19	8		15	6
- *
- * which may or may not be more efficient (depending upon whether
- * you can afford the extra registers).  Hopefully the gcc 2.95
- * is inteligent enough to decide if it is better to use the
- * extra register, but evidence so far seems to suggest otherwise.
- *
- * Unfortunately, gcc is not able to optimise the high word
- * out of long long >> 32, or the low word from long long << 32
- */
-
-#define __get_unaligned_2(__p)					\
-	(__p[0] | __p[1] << 8)
-
-#define __get_unaligned_4(__p)					\
-	(__p[0] | __p[1] << 8 | __p[2] << 16 | __p[3] << 24)
-
-#define get_unaligned(ptr)					\
-	({							\
-		__typeof__(*(ptr)) __v;				\
-		__u8 *__p = (__u8 *)(ptr);			\
-		switch (sizeof(*(ptr))) {			\
-		case 1:	__v = *(ptr);			break;	\
-		case 2: __v = __get_unaligned_2(__p);	break;	\
-		case 4: __v = __get_unaligned_4(__p);	break;	\
-		case 8: {					\
-				unsigned int __v1, __v2;	\
-				__v2 = __get_unaligned_4((__p+4)); \
-				__v1 = __get_unaligned_4(__p);	\
-				__v = ((unsigned long long)__v2 << 32 | __v1);	\
-			}					\
-			break;					\
-		default: __v = __bug_unaligned_x(__p);	break;	\
-		}						\
-		__v;						\
-	})
-
-
-static inline void __put_unaligned_2(__u32 __v, register __u8 *__p)
-{
-	*__p++ = __v;
-	*__p++ = __v >> 8;
-}
-
-static inline void __put_unaligned_4(__u32 __v, register __u8 *__p)
-{
-	__put_unaligned_2(__v >> 16, __p + 2);
-	__put_unaligned_2(__v, __p);
-}
-
-static inline void __put_unaligned_8(const unsigned long long __v, register __u8 *__p)
-{
-	/*
-	 * tradeoff: 8 bytes of stack for all unaligned puts (2
-	 * instructions), or an extra register in the long long
-	 * case - go for the extra register.
-	 */
-	__put_unaligned_4(__v >> 32, __p+4);
-	__put_unaligned_4(__v, __p);
-}
-
-/*
- * Try to store an unaligned value as efficiently as possible.
- */
-#define put_unaligned(val,ptr)					\
-	({							\
-		switch (sizeof(*(ptr))) {			\
-		case 1:						\
-			*(ptr) = (val);				\
-			break;					\
-		case 2: __put_unaligned_2((val),(__u8 *)(ptr));	\
-			break;					\
-		case 4:	__put_unaligned_4((val),(__u8 *)(ptr));	\
-			break;					\
-		case 8:	__put_unaligned_8((val),(__u8 *)(ptr)); \
-			break;					\
-		default: __bug_unaligned_x(ptr);		\
-			break;					\
-		}						\
-		(void) 0;					\
-	})
+#include <linux/unaligned/be_byteshift.h>
+#include <linux/unaligned/le_byteshift.h>
+#include <linux/unaligned/generic.h>
 
+#define get_unaligned	__get_unaligned_le
+#define put_unaligned	__put_unaligned_le
 
-#endif /* __V850_UNALIGNED_H__ */
+#endif /* _ASM_V850_UNALIGNED_H */
diff --git a/trunk/include/asm-x86/geode.h b/trunk/include/asm-x86/geode.h
index 9870cc1f2f8f..7154dc4de951 100644
--- a/trunk/include/asm-x86/geode.h
+++ b/trunk/include/asm-x86/geode.h
@@ -30,7 +30,13 @@ extern int geode_get_dev_base(unsigned int dev);
 
 /* MSRS */
 
-#define GX_GLCP_SYS_RSTPLL	0x4C000014
+#define MSR_GLIU_P2D_RO0	0x10000029
+
+#define MSR_LX_GLD_MSR_CONFIG	0x48002001
+#define MSR_LX_MSR_PADSEL	0x48002011	/* NOT 0x48000011; the data
+						 * sheet has the wrong value */
+#define MSR_GLCP_SYS_RSTPLL	0x4C000014
+#define MSR_GLCP_DOTPLL		0x4C000015
 
 #define MSR_LBAR_SMB		0x5140000B
 #define MSR_LBAR_GPIO		0x5140000C
@@ -45,8 +51,14 @@ extern int geode_get_dev_base(unsigned int dev);
 #define MSR_PIC_ZSEL_LOW	0x51400022
 #define MSR_PIC_ZSEL_HIGH	0x51400023
 
-#define MFGPT_IRQ_MSR		0x51400028
-#define MFGPT_NR_MSR		0x51400029
+#define MSR_MFGPT_IRQ		0x51400028
+#define MSR_MFGPT_NR		0x51400029
+#define MSR_MFGPT_SETUP		0x5140002B
+
+#define MSR_LX_SPARE_MSR	0x80000011	/* DC-specific */
+
+#define MSR_GX_GLD_MSR_CONFIG	0xC0002001
+#define MSR_GX_MSR_PADSEL	0xC0002011
 
 /* Resource Sizes */
 
@@ -93,6 +105,15 @@ extern int geode_get_dev_base(unsigned int dev);
 #define PM_AWKD			0x50
 #define PM_SSC			0x54
 
+/* VSA2 magic values */
+
+#define VSA_VRC_INDEX		0xAC1C
+#define VSA_VRC_DATA		0xAC1E
+#define VSA_VR_UNLOCK		0xFC53	/* unlock virtual register */
+#define VSA_VR_SIGNATURE	0x0003
+#define VSA_VR_MEM_SIZE		0x0200
+#define VSA_SIG			0x4132	/* signature is ascii 'VSA2' */
+
 /* GPIO */
 
 #define GPIO_OUTPUT_VAL		0x00
@@ -164,6 +185,17 @@ static inline int is_geode(void)
 	return (is_geode_gx() || is_geode_lx());
 }
 
+/*
+ * The VSA has virtual registers that we can query for a signature.
+ */
+static inline int geode_has_vsa2(void)
+{
+	outw(VSA_VR_UNLOCK, VSA_VRC_INDEX);
+	outw(VSA_VR_SIGNATURE, VSA_VRC_INDEX);
+
+	return (inw(VSA_VRC_DATA) == VSA_SIG);
+}
+
 /* MFGPTs */
 
 #define MFGPT_MAX_TIMERS	8
diff --git a/trunk/include/asm-x86/hugetlb.h b/trunk/include/asm-x86/hugetlb.h
new file mode 100644
index 000000000000..14171a4924f6
--- /dev/null
+++ b/trunk/include/asm-x86/hugetlb.h
@@ -0,0 +1,91 @@
+#ifndef _ASM_X86_HUGETLB_H
+#define _ASM_X86_HUGETLB_H
+
+#include <asm/page.h>
+
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					 unsigned long addr,
+					 unsigned long len) {
+	return 0;
+}
+
+/*
+ * If the arch doesn't supply something else, assume that hugepage
+ * size aligned regions are ok without further preparation.
+ */
+static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+{
+	if (len & ~HPAGE_MASK)
+		return -EINVAL;
+	if (addr & ~HPAGE_MASK)
+		return -EINVAL;
+	return 0;
+}
+
+static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) {
+}
+
+static inline void hugetlb_free_pgd_range(struct mmu_gather **tlb,
+					  unsigned long addr, unsigned long end,
+					  unsigned long floor,
+					  unsigned long ceiling)
+{
+	free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+	set_pte_at(mm, addr, ptep, pte);
+}
+
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep)
+{
+	return ptep_get_and_clear(mm, addr, ptep);
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(mm, addr, ptep);
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+					     unsigned long addr, pte_t *ptep,
+					     pte_t pte, int dirty)
+{
+	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	return *ptep;
+}
+
+static inline int arch_prepare_hugepage(struct page *page)
+{
+	return 0;
+}
+
+static inline void arch_release_hugepage(struct page *page)
+{
+}
+
+#endif /* _ASM_X86_HUGETLB_H */
diff --git a/trunk/include/asm-x86/kvm.h b/trunk/include/asm-x86/kvm.h
index 7a71120426a3..80eefef2cc76 100644
--- a/trunk/include/asm-x86/kvm.h
+++ b/trunk/include/asm-x86/kvm.h
@@ -188,4 +188,45 @@ struct kvm_cpuid2 {
 	struct kvm_cpuid_entry2 entries[0];
 };
 
+/* for KVM_GET_PIT and KVM_SET_PIT */
+struct kvm_pit_channel_state {
+	__u32 count; /* can be 65536 */
+	__u16 latched_count;
+	__u8 count_latched;
+	__u8 status_latched;
+	__u8 status;
+	__u8 read_state;
+	__u8 write_state;
+	__u8 write_latch;
+	__u8 rw_mode;
+	__u8 mode;
+	__u8 bcd;
+	__u8 gate;
+	__s64 count_load_time;
+};
+
+struct kvm_pit_state {
+	struct kvm_pit_channel_state channels[3];
+};
+
+#define KVM_TRC_INJ_VIRQ         (KVM_TRC_HANDLER + 0x02)
+#define KVM_TRC_REDELIVER_EVT    (KVM_TRC_HANDLER + 0x03)
+#define KVM_TRC_PEND_INTR        (KVM_TRC_HANDLER + 0x04)
+#define KVM_TRC_IO_READ          (KVM_TRC_HANDLER + 0x05)
+#define KVM_TRC_IO_WRITE         (KVM_TRC_HANDLER + 0x06)
+#define KVM_TRC_CR_READ          (KVM_TRC_HANDLER + 0x07)
+#define KVM_TRC_CR_WRITE         (KVM_TRC_HANDLER + 0x08)
+#define KVM_TRC_DR_READ          (KVM_TRC_HANDLER + 0x09)
+#define KVM_TRC_DR_WRITE         (KVM_TRC_HANDLER + 0x0A)
+#define KVM_TRC_MSR_READ         (KVM_TRC_HANDLER + 0x0B)
+#define KVM_TRC_MSR_WRITE        (KVM_TRC_HANDLER + 0x0C)
+#define KVM_TRC_CPUID            (KVM_TRC_HANDLER + 0x0D)
+#define KVM_TRC_INTR             (KVM_TRC_HANDLER + 0x0E)
+#define KVM_TRC_NMI              (KVM_TRC_HANDLER + 0x0F)
+#define KVM_TRC_VMMCALL          (KVM_TRC_HANDLER + 0x10)
+#define KVM_TRC_HLT              (KVM_TRC_HANDLER + 0x11)
+#define KVM_TRC_CLTS             (KVM_TRC_HANDLER + 0x12)
+#define KVM_TRC_LMSW             (KVM_TRC_HANDLER + 0x13)
+#define KVM_TRC_APIC_ACCESS      (KVM_TRC_HANDLER + 0x14)
+
 #endif
diff --git a/trunk/include/asm-x86/kvm_host.h b/trunk/include/asm-x86/kvm_host.h
index 68ee390b2844..9d963cd6533c 100644
--- a/trunk/include/asm-x86/kvm_host.h
+++ b/trunk/include/asm-x86/kvm_host.h
@@ -20,6 +20,13 @@
 
 #include <asm/desc.h>
 
+#define KVM_MAX_VCPUS 16
+#define KVM_MEMORY_SLOTS 32
+/* memory slots that does not exposed to userspace */
+#define KVM_PRIVATE_MEM_SLOTS 4
+
+#define KVM_PIO_PAGE_OFFSET 1
+
 #define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
 #define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
 #define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS |	\
@@ -39,6 +46,13 @@
 #define INVALID_PAGE (~(hpa_t)0)
 #define UNMAPPED_GVA (~(gpa_t)0)
 
+/* shadow tables are PAE even on non-PAE hosts */
+#define KVM_HPAGE_SHIFT 21
+#define KVM_HPAGE_SIZE (1UL << KVM_HPAGE_SHIFT)
+#define KVM_HPAGE_MASK (~(KVM_HPAGE_SIZE - 1))
+
+#define KVM_PAGES_PER_HPAGE (KVM_HPAGE_SIZE / PAGE_SIZE)
+
 #define DE_VECTOR 0
 #define UD_VECTOR 6
 #define NM_VECTOR 7
@@ -48,6 +62,7 @@
 #define SS_VECTOR 12
 #define GP_VECTOR 13
 #define PF_VECTOR 14
+#define MC_VECTOR 18
 
 #define SELECTOR_TI_MASK (1 << 2)
 #define SELECTOR_RPL_MASK 0x03
@@ -58,7 +73,8 @@
 
 #define KVM_PERMILLE_MMU_PAGES 20
 #define KVM_MIN_ALLOC_MMU_PAGES 64
-#define KVM_NUM_MMU_PAGES 1024
+#define KVM_MMU_HASH_SHIFT 10
+#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
 #define KVM_MIN_FREE_MMU_PAGES 5
 #define KVM_REFILL_PAGES 25
 #define KVM_MAX_CPUID_ENTRIES 40
@@ -106,6 +122,12 @@ enum {
 
 #define KVM_NR_MEM_OBJS 40
 
+struct kvm_guest_debug {
+	int enabled;
+	unsigned long bp[4];
+	int singlestep;
+};
+
 /*
  * We don't want allocation failures within the mmu code, so we preallocate
  * enough memory for a single page fault in a cache.
@@ -140,6 +162,7 @@ union kvm_mmu_page_role {
 		unsigned pad_for_nice_hex_output:6;
 		unsigned metaphysical:1;
 		unsigned access:3;
+		unsigned invalid:1;
 	};
 };
 
@@ -204,11 +227,6 @@ struct kvm_vcpu_arch {
 	u64 shadow_efer;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
-#define VCPU_MP_STATE_RUNNABLE          0
-#define VCPU_MP_STATE_UNINITIALIZED     1
-#define VCPU_MP_STATE_INIT_RECEIVED     2
-#define VCPU_MP_STATE_SIPI_RECEIVED     3
-#define VCPU_MP_STATE_HALTED            4
 	int mp_state;
 	int sipi_vector;
 	u64 ia32_misc_enable_msr;
@@ -226,8 +244,9 @@ struct kvm_vcpu_arch {
 	u64  *last_pte_updated;
 
 	struct {
-		gfn_t gfn;          /* presumed gfn during guest pte update */
-		struct page *page;  /* page corresponding to that gfn */
+		gfn_t gfn;	/* presumed gfn during guest pte update */
+		pfn_t pfn;	/* pfn corresponding to that gfn */
+		int largepage;
 	} update_pte;
 
 	struct i387_fxsave_struct host_fx_image;
@@ -261,6 +280,11 @@ struct kvm_vcpu_arch {
 	/* emulate context */
 
 	struct x86_emulate_ctxt emulate_ctxt;
+
+	gpa_t time;
+	struct kvm_vcpu_time_info hv_clock;
+	unsigned int time_offset;
+	struct page *time_page;
 };
 
 struct kvm_mem_alias {
@@ -283,10 +307,13 @@ struct kvm_arch{
 	struct list_head active_mmu_pages;
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
+	struct kvm_pit *vpit;
 
 	int round_robin_prev_vcpu;
 	unsigned int tss_addr;
 	struct page *apic_access_page;
+
+	gpa_t wall_clock;
 };
 
 struct kvm_vm_stat {
@@ -298,6 +325,7 @@ struct kvm_vm_stat {
 	u32 mmu_recycled;
 	u32 mmu_cache_miss;
 	u32 remote_tlb_flush;
+	u32 lpages;
 };
 
 struct kvm_vcpu_stat {
@@ -320,6 +348,7 @@ struct kvm_vcpu_stat {
 	u32 fpu_reload;
 	u32 insn_emulation;
 	u32 insn_emulation_fail;
+	u32 hypercalls;
 };
 
 struct descriptor_table {
@@ -355,6 +384,7 @@ struct kvm_x86_ops {
 	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
 	void (*get_segment)(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
+	int (*get_cpl)(struct kvm_vcpu *vcpu);
 	void (*set_segment)(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
 	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
@@ -410,6 +440,15 @@ void kvm_mmu_zap_all(struct kvm *kvm);
 unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
 
+int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
+
+int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
+			  const void *val, int bytes);
+int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
+		  gpa_t addr, unsigned long *ret);
+
+extern bool tdp_enabled;
+
 enum emulation_result {
 	EMULATE_DONE,       /* no further processing */
 	EMULATE_DO_MMIO,      /* kvm_run filled with mmio request */
@@ -429,6 +468,7 @@ void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
 unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr);
 void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value,
 		     unsigned long *rflags);
+void kvm_enable_efer_bits(u64);
 int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data);
 int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 
@@ -448,12 +488,14 @@ int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr,
 int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
 		    unsigned long value);
 
-void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
-void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr0);
-void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr0);
-void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr0);
-unsigned long get_cr8(struct kvm_vcpu *vcpu);
-void lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
+int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason);
+
+void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
+void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
+void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
+void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
+unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu);
+void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
 void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
 
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
@@ -491,6 +533,8 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu);
 
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code);
 
+void kvm_enable_tdp(void);
+
 int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
 int complete_pio(struct kvm_vcpu *vcpu);
 
@@ -600,6 +644,7 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
 #define ASM_VMX_VMWRITE_RSP_RDX   ".byte 0x0f, 0x79, 0xd4"
 #define ASM_VMX_VMXOFF            ".byte 0x0f, 0x01, 0xc4"
 #define ASM_VMX_VMXON_RAX         ".byte 0xf3, 0x0f, 0xc7, 0x30"
+#define ASM_VMX_INVVPID		  ".byte 0x66, 0x0f, 0x38, 0x81, 0x08"
 
 #define MSR_IA32_TIME_STAMP_COUNTER		0x010
 
@@ -610,4 +655,30 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
 #define RMODE_TSS_SIZE							\
 	(TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1)
 
+enum {
+	TASK_SWITCH_CALL = 0,
+	TASK_SWITCH_IRET = 1,
+	TASK_SWITCH_JMP = 2,
+	TASK_SWITCH_GATE = 3,
+};
+
+#define KVMTRACE_5D(evt, vcpu, d1, d2, d3, d4, d5, name) \
+	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
+						vcpu, 5, d1, d2, d3, d4, d5)
+#define KVMTRACE_4D(evt, vcpu, d1, d2, d3, d4, name) \
+	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
+						vcpu, 4, d1, d2, d3, d4, 0)
+#define KVMTRACE_3D(evt, vcpu, d1, d2, d3, name) \
+	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
+						vcpu, 3, d1, d2, d3, 0, 0)
+#define KVMTRACE_2D(evt, vcpu, d1, d2, name) \
+	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
+						vcpu, 2, d1, d2, 0, 0, 0)
+#define KVMTRACE_1D(evt, vcpu, d1, name) \
+	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
+						vcpu, 1, d1, 0, 0, 0, 0)
+#define KVMTRACE_0D(evt, vcpu, name) \
+	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
+						vcpu, 0, 0, 0, 0, 0, 0)
+
 #endif
diff --git a/trunk/include/asm-x86/kvm_para.h b/trunk/include/asm-x86/kvm_para.h
index c6f3fd8d8c53..509845942070 100644
--- a/trunk/include/asm-x86/kvm_para.h
+++ b/trunk/include/asm-x86/kvm_para.h
@@ -10,10 +10,65 @@
  * paravirtualization, the appropriate feature bit should be checked.
  */
 #define KVM_CPUID_FEATURES	0x40000001
+#define KVM_FEATURE_CLOCKSOURCE		0
+#define KVM_FEATURE_NOP_IO_DELAY	1
+#define KVM_FEATURE_MMU_OP		2
+
+#define MSR_KVM_WALL_CLOCK  0x11
+#define MSR_KVM_SYSTEM_TIME 0x12
+
+#define KVM_MAX_MMU_OP_BATCH           32
+
+/* Operations for KVM_HC_MMU_OP */
+#define KVM_MMU_OP_WRITE_PTE            1
+#define KVM_MMU_OP_FLUSH_TLB	        2
+#define KVM_MMU_OP_RELEASE_PT	        3
+
+/* Payload for KVM_HC_MMU_OP */
+struct kvm_mmu_op_header {
+	__u32 op;
+	__u32 pad;
+};
+
+struct kvm_mmu_op_write_pte {
+	struct kvm_mmu_op_header header;
+	__u64 pte_phys;
+	__u64 pte_val;
+};
+
+struct kvm_mmu_op_flush_tlb {
+	struct kvm_mmu_op_header header;
+};
+
+struct kvm_mmu_op_release_pt {
+	struct kvm_mmu_op_header header;
+	__u64 pt_phys;
+};
 
 #ifdef __KERNEL__
 #include <asm/processor.h>
 
+/* xen binary-compatible interface. See xen headers for details */
+struct kvm_vcpu_time_info {
+	uint32_t version;
+	uint32_t pad0;
+	uint64_t tsc_timestamp;
+	uint64_t system_time;
+	uint32_t tsc_to_system_mul;
+	int8_t   tsc_shift;
+	int8_t	 pad[3];
+} __attribute__((__packed__)); /* 32 bytes */
+
+struct kvm_wall_clock {
+	uint32_t wc_version;
+	uint32_t wc_sec;
+	uint32_t wc_nsec;
+} __attribute__((__packed__));
+
+
+extern void kvmclock_init(void);
+
+
 /* This instruction is vmcall.  On non-VT architectures, it will generate a
  * trap that we will then rewrite to the appropriate instruction.
  */
diff --git a/trunk/include/asm-x86/olpc.h b/trunk/include/asm-x86/olpc.h
new file mode 100644
index 000000000000..97d47133486f
--- /dev/null
+++ b/trunk/include/asm-x86/olpc.h
@@ -0,0 +1,132 @@
+/* OLPC machine specific definitions */
+
+#ifndef ASM_OLPC_H_
+#define ASM_OLPC_H_
+
+#include <asm/geode.h>
+
+struct olpc_platform_t {
+	int flags;
+	uint32_t boardrev;
+	int ecver;
+};
+
+#define OLPC_F_PRESENT		0x01
+#define OLPC_F_DCON		0x02
+#define OLPC_F_VSA		0x04
+
+#ifdef CONFIG_OLPC
+
+extern struct olpc_platform_t olpc_platform_info;
+
+/*
+ * OLPC board IDs contain the major build number within the mask 0x0ff0,
+ * and the minor build number withing 0x000f.  Pre-builds have a minor
+ * number less than 8, and normal builds start at 8.  For example, 0x0B10
+ * is a PreB1, and 0x0C18 is a C1.
+ */
+
+static inline uint32_t olpc_board(uint8_t id)
+{
+	return (id << 4) | 0x8;
+}
+
+static inline uint32_t olpc_board_pre(uint8_t id)
+{
+	return id << 4;
+}
+
+static inline int machine_is_olpc(void)
+{
+	return (olpc_platform_info.flags & OLPC_F_PRESENT) ? 1 : 0;
+}
+
+/*
+ * The DCON is OLPC's Display Controller.  It has a number of unique
+ * features that we might want to take advantage of..
+ */
+static inline int olpc_has_dcon(void)
+{
+	return (olpc_platform_info.flags & OLPC_F_DCON) ? 1 : 0;
+}
+
+/*
+ * The VSA is software from AMD that typical Geode bioses will include.
+ * It is used to emulate the PCI bus, VGA, etc.  OLPC's Open Firmware does
+ * not include the VSA; instead, PCI is emulated by the kernel.
+ *
+ * The VSA is described further in arch/x86/pci/olpc.c.
+ */
+static inline int olpc_has_vsa(void)
+{
+	return (olpc_platform_info.flags & OLPC_F_VSA) ? 1 : 0;
+}
+
+/*
+ * The "Mass Production" version of OLPC's XO is identified as being model
+ * C2.  During the prototype phase, the following models (in chronological
+ * order) were created: A1, B1, B2, B3, B4, C1.  The A1 through B2 models
+ * were based on Geode GX CPUs, and models after that were based upon
+ * Geode LX CPUs.  There were also some hand-assembled models floating
+ * around, referred to as PreB1, PreB2, etc.
+ */
+static inline int olpc_board_at_least(uint32_t rev)
+{
+	return olpc_platform_info.boardrev >= rev;
+}
+
+#else
+
+static inline int machine_is_olpc(void)
+{
+	return 0;
+}
+
+static inline int olpc_has_dcon(void)
+{
+	return 0;
+}
+
+static inline int olpc_has_vsa(void)
+{
+	return 0;
+}
+
+#endif
+
+/* EC related functions */
+
+extern int olpc_ec_cmd(unsigned char cmd, unsigned char *inbuf, size_t inlen,
+		unsigned char *outbuf, size_t outlen);
+
+extern int olpc_ec_mask_set(uint8_t bits);
+extern int olpc_ec_mask_unset(uint8_t bits);
+
+/* EC commands */
+
+#define EC_FIRMWARE_REV		0x08
+
+/* SCI source values */
+
+#define EC_SCI_SRC_EMPTY	0x00
+#define EC_SCI_SRC_GAME		0x01
+#define EC_SCI_SRC_BATTERY	0x02
+#define EC_SCI_SRC_BATSOC	0x04
+#define EC_SCI_SRC_BATERR	0x08
+#define EC_SCI_SRC_EBOOK	0x10
+#define EC_SCI_SRC_WLAN		0x20
+#define EC_SCI_SRC_ACPWR	0x40
+#define EC_SCI_SRC_ALL		0x7F
+
+/* GPIO assignments */
+
+#define OLPC_GPIO_MIC_AC	geode_gpio(1)
+#define OLPC_GPIO_DCON_IRQ	geode_gpio(7)
+#define OLPC_GPIO_THRM_ALRM	geode_gpio(10)
+#define OLPC_GPIO_SMB_CLK	geode_gpio(14)
+#define OLPC_GPIO_SMB_DATA	geode_gpio(15)
+#define OLPC_GPIO_WORKAUX	geode_gpio(24)
+#define OLPC_GPIO_LID		geode_gpio(26)
+#define OLPC_GPIO_ECSCI		geode_gpio(27)
+
+#endif
diff --git a/trunk/include/asm-x86/pgtable.h b/trunk/include/asm-x86/pgtable.h
index a496d6335d3b..801b31f71452 100644
--- a/trunk/include/asm-x86/pgtable.h
+++ b/trunk/include/asm-x86/pgtable.h
@@ -195,6 +195,11 @@ static inline int pte_exec(pte_t pte)
 	return !(pte_val(pte) & _PAGE_NX);
 }
 
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
 static inline int pmd_large(pmd_t pte)
 {
 	return (pmd_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
@@ -256,6 +261,11 @@ static inline pte_t pte_clrglobal(pte_t pte)
 	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_GLOBAL);
 }
 
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return pte;
+}
+
 extern pteval_t __supported_pte_mask;
 
 static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
diff --git a/trunk/include/asm-x86/processor.h b/trunk/include/asm-x86/processor.h
index 117343b0c271..2e7974ec77ec 100644
--- a/trunk/include/asm-x86/processor.h
+++ b/trunk/include/asm-x86/processor.h
@@ -722,6 +722,7 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
 
 static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 {
+	trace_hardirqs_on();
 	/* "mwait %eax, %ecx;" */
 	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
 		     :: "a" (eax), "c" (ecx));
diff --git a/trunk/include/asm-x86/reboot.h b/trunk/include/asm-x86/reboot.h
index 6b5233b4f84b..e63741f19392 100644
--- a/trunk/include/asm-x86/reboot.h
+++ b/trunk/include/asm-x86/reboot.h
@@ -15,5 +15,7 @@ struct machine_ops {
 extern struct machine_ops machine_ops;
 
 void machine_real_restart(unsigned char *code, int length);
+void native_machine_crash_shutdown(struct pt_regs *regs);
+void native_machine_shutdown(void);
 
 #endif	/* _ASM_REBOOT_H */
diff --git a/trunk/include/asm-x86/time.h b/trunk/include/asm-x86/time.h
index 68779b048a3e..bce72d7a958c 100644
--- a/trunk/include/asm-x86/time.h
+++ b/trunk/include/asm-x86/time.h
@@ -1,7 +1,6 @@
 #ifndef _ASMX86_TIME_H
 #define _ASMX86_TIME_H
 
-extern void (*late_time_init)(void);
 extern void hpet_time_init(void);
 
 #include <asm/mc146818rtc.h>
diff --git a/trunk/include/asm-x86/unaligned.h b/trunk/include/asm-x86/unaligned.h
index d270ffe72759..a7bd416b4763 100644
--- a/trunk/include/asm-x86/unaligned.h
+++ b/trunk/include/asm-x86/unaligned.h
@@ -3,35 +3,12 @@
 
 /*
  * The x86 can do unaligned accesses itself.
- *
- * The strange macros are there to make sure these can't
- * be misused in a way that makes them not work on other
- * architectures where unaligned accesses aren't as simple.
  */
 
-/**
- * get_unaligned - get value from possibly mis-aligned location
- * @ptr: pointer to value
- *
- * This macro should be used for accessing values larger in size than
- * single bytes at locations that are expected to be improperly aligned,
- * e.g. retrieving a u16 value from a location not u16-aligned.
- *
- * Note that unaligned accesses can be very expensive on some architectures.
- */
-#define get_unaligned(ptr) (*(ptr))
+#include <linux/unaligned/access_ok.h>
+#include <linux/unaligned/generic.h>
 
-/**
- * put_unaligned - put value to a possibly mis-aligned location
- * @val: value to place
- * @ptr: pointer to location
- *
- * This macro should be used for placing values larger in size than
- * single bytes at locations that are expected to be improperly aligned,
- * e.g. writing a u16 value to a location not u16-aligned.
- *
- * Note that unaligned accesses can be very expensive on some architectures.
- */
-#define put_unaligned(val, ptr) ((void)(*(ptr) = (val)))
+#define get_unaligned __get_unaligned_le
+#define put_unaligned __put_unaligned_le
 
 #endif /* _ASM_X86_UNALIGNED_H */
diff --git a/trunk/include/asm-xtensa/pgtable.h b/trunk/include/asm-xtensa/pgtable.h
index c8b024a48b4d..8014d96b21f1 100644
--- a/trunk/include/asm-xtensa/pgtable.h
+++ b/trunk/include/asm-xtensa/pgtable.h
@@ -210,6 +210,8 @@ static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_WRITABLE; }
 static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_file(pte_t pte)  { return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte) { return 0; }
+
 static inline pte_t pte_wrprotect(pte_t pte)	
 	{ pte_val(pte) &= ~(_PAGE_WRITABLE | _PAGE_HW_WRITE); return pte; }
 static inline pte_t pte_mkclean(pte_t pte)
@@ -222,6 +224,8 @@ static inline pte_t pte_mkyoung(pte_t pte)
 	{ pte_val(pte) |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)
 	{ pte_val(pte) |= _PAGE_WRITABLE; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)
+	{ return pte; }
 
 /*
  * Conversion functions: convert a page and protection to a page entry,
diff --git a/trunk/include/asm-xtensa/unaligned.h b/trunk/include/asm-xtensa/unaligned.h
index 28220890d0a6..8f3424fc5d18 100644
--- a/trunk/include/asm-xtensa/unaligned.h
+++ b/trunk/include/asm-xtensa/unaligned.h
@@ -1,6 +1,4 @@
 /*
- * include/asm-xtensa/unaligned.h
- *
  * Xtensa doesn't handle unaligned accesses efficiently.
  *
  * This file is subject to the terms and conditions of the GNU General Public
@@ -9,20 +7,23 @@
  *
  * Copyright (C) 2001 - 2005 Tensilica Inc.
  */
+#ifndef _ASM_XTENSA_UNALIGNED_H
+#define _ASM_XTENSA_UNALIGNED_H
 
-#ifndef _XTENSA_UNALIGNED_H
-#define _XTENSA_UNALIGNED_H
-
-#include <linux/string.h>
-
-/* Use memmove here, so gcc does not insert a __builtin_memcpy. */
-
-#define get_unaligned(ptr) \
-  ({ __typeof__(*(ptr)) __tmp; memmove(&__tmp, (ptr), sizeof(*(ptr))); __tmp; })
-
-#define put_unaligned(val, ptr)				\
-  ({ __typeof__(*(ptr)) __tmp = (val);			\
-     memmove((ptr), &__tmp, sizeof(*(ptr)));		\
-     (void)0; })
+#ifdef __XTENSA_EL__
+# include <linux/unaligned/le_memmove.h>
+# include <linux/unaligned/be_byteshift.h>
+# include <linux/unaligned/generic.h>
+# define get_unaligned	__get_unaligned_le
+# define put_unaligned	__put_unaligned_le
+#elif defined(__XTENSA_EB__)
+# include <linux/unaligned/be_memmove.h>
+# include <linux/unaligned/le_byteshift.h>
+# include <linux/unaligned/generic.h>
+# define get_unaligned	__get_unaligned_be
+# define put_unaligned	__put_unaligned_be
+#else
+# error processor byte order undefined!
+#endif
 
-#endif	/* _XTENSA_UNALIGNED_H */
+#endif	/* _ASM_XTENSA_UNALIGNED_H */
diff --git a/trunk/include/linux/Kbuild b/trunk/include/linux/Kbuild
index bda6f04791d4..78fade0a1e35 100644
--- a/trunk/include/linux/Kbuild
+++ b/trunk/include/linux/Kbuild
@@ -20,6 +20,7 @@ header-y += affs_hardblocks.h
 header-y += aio_abi.h
 header-y += arcfb.h
 header-y += atmapi.h
+header-y += atmarp.h
 header-y += atmbr2684.h
 header-y += atmclip.h
 header-y += atm_eni.h
@@ -48,6 +49,7 @@ header-y += coff.h
 header-y += comstats.h
 header-y += const.h
 header-y += cgroupstats.h
+header-y += cramfs_fs.h
 header-y += cycx_cfm.h
 header-y += dlmconstants.h
 header-y += dlm_device.h
@@ -70,10 +72,12 @@ header-y += firewire-constants.h
 header-y += fuse.h
 header-y += genetlink.h
 header-y += gen_stats.h
+header-y += gfs2_ondisk.h
 header-y += gigaset_dev.h
 header-y += hysdn_if.h
 header-y += i2o-dev.h
 header-y += i8k.h
+header-y += if_addrlabel.h
 header-y += if_arcnet.h
 header-y += if_bonding.h
 header-y += if_cablemodem.h
@@ -91,6 +95,7 @@ header-y += if_tunnel.h
 header-y += in6.h
 header-y += in_route.h
 header-y += ioctl.h
+header-y += ip6_tunnel.h
 header-y += ipmi_msgdefs.h
 header-y += ipsec.h
 header-y += ipx.h
@@ -117,7 +122,6 @@ header-y += nfs2.h
 header-y += nfs4_mount.h
 header-y += nfs_mount.h
 header-y += nl80211.h
-header-y += oom.h
 header-y += param.h
 header-y += pci_regs.h
 header-y += pfkeyv2.h
@@ -166,7 +170,6 @@ unifdef-y += adfs_fs.h
 unifdef-y += agpgart.h
 unifdef-y += apm_bios.h
 unifdef-y += atalk.h
-unifdef-y += atmarp.h
 unifdef-y += atmdev.h
 unifdef-y += atm.h
 unifdef-y += atm_tcp.h
@@ -182,7 +185,6 @@ unifdef-y += cm4000_cs.h
 unifdef-y += cn_proc.h
 unifdef-y += coda.h
 unifdef-y += connector.h
-unifdef-y += cramfs_fs.h
 unifdef-y += cuda.h
 unifdef-y += cyclades.h
 unifdef-y += dccp.h
@@ -205,7 +207,6 @@ unifdef-y += futex.h
 unifdef-y += fs.h
 unifdef-y += gameport.h
 unifdef-y += generic_serial.h
-unifdef-y += gfs2_ondisk.h
 unifdef-y += hayesesp.h
 unifdef-y += hdlcdrv.h
 unifdef-y += hdlc.h
@@ -219,7 +220,6 @@ unifdef-y += i2c-dev.h
 unifdef-y += icmp.h
 unifdef-y += icmpv6.h
 unifdef-y += if_addr.h
-unifdef-y += if_addrlabel.h
 unifdef-y += if_arp.h
 unifdef-y += if_bridge.h
 unifdef-y += if_ec.h
@@ -243,7 +243,6 @@ unifdef-y += ipc.h
 unifdef-y += ipmi.h
 unifdef-y += ipv6.h
 unifdef-y += ipv6_route.h
-unifdef-y += ip6_tunnel.h
 unifdef-y += isdn.h
 unifdef-y += isdnif.h
 unifdef-y += isdn_divertif.h
diff --git a/trunk/include/linux/aio.h b/trunk/include/linux/aio.h
index 0d0b7f629bd3..b51ddd28444e 100644
--- a/trunk/include/linux/aio.h
+++ b/trunk/include/linux/aio.h
@@ -209,27 +209,8 @@ extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb);
 extern int aio_put_req(struct kiocb *iocb);
 extern void kick_iocb(struct kiocb *iocb);
 extern int aio_complete(struct kiocb *iocb, long res, long res2);
-extern void __put_ioctx(struct kioctx *ctx);
 struct mm_struct;
 extern void exit_aio(struct mm_struct *mm);
-extern struct kioctx *lookup_ioctx(unsigned long ctx_id);
-extern int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
-			 struct iocb *iocb);
-
-/* semi private, but used by the 32bit emulations: */
-struct kioctx *lookup_ioctx(unsigned long ctx_id);
-int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
-		  struct iocb *iocb);
-
-#define get_ioctx(kioctx) do {						\
-	BUG_ON(atomic_read(&(kioctx)->users) <= 0);			\
-	atomic_inc(&(kioctx)->users);					\
-} while (0)
-#define put_ioctx(kioctx) do {						\
-	BUG_ON(atomic_read(&(kioctx)->users) <= 0);			\
-	if (unlikely(atomic_dec_and_test(&(kioctx)->users))) 		\
-		__put_ioctx(kioctx);					\
-} while (0)
 
 #define io_wait_to_kiocb(wait) container_of(wait, struct kiocb, ki_wait)
 
diff --git a/trunk/include/linux/backing-dev.h b/trunk/include/linux/backing-dev.h
index 48a62baace58..b66fa2bdfd9c 100644
--- a/trunk/include/linux/backing-dev.h
+++ b/trunk/include/linux/backing-dev.h
@@ -156,9 +156,7 @@ static inline unsigned long bdi_stat_error(struct backing_dev_info *bdi)
 extern struct backing_dev_info default_backing_dev_info;
 void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page);
 
-int writeback_acquire(struct backing_dev_info *bdi);
 int writeback_in_progress(struct backing_dev_info *bdi);
-void writeback_release(struct backing_dev_info *bdi);
 
 static inline int bdi_congested(struct backing_dev_info *bdi, int bdi_bits)
 {
diff --git a/trunk/include/linux/binfmts.h b/trunk/include/linux/binfmts.h
index b7fc55ec8d48..b512e48f6d8e 100644
--- a/trunk/include/linux/binfmts.h
+++ b/trunk/include/linux/binfmts.h
@@ -34,7 +34,8 @@ struct linux_binprm{
 #endif
 	struct mm_struct *mm;
 	unsigned long p; /* current top of mem */
-	int sh_bang;
+	unsigned int sh_bang:1,
+		     misc_bang:1;
 	struct file * file;
 	int e_uid, e_gid;
 	kernel_cap_t cap_inheritable, cap_permitted;
@@ -48,7 +49,6 @@ struct linux_binprm{
 	unsigned interp_flags;
 	unsigned interp_data;
 	unsigned long loader, exec;
-	unsigned long argv_len;
 };
 
 #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0
diff --git a/trunk/include/linux/bio.h b/trunk/include/linux/bio.h
index d259690863fb..61c15eaf3fb3 100644
--- a/trunk/include/linux/bio.h
+++ b/trunk/include/linux/bio.h
@@ -324,6 +324,8 @@ extern struct bio *bio_map_user_iov(struct request_queue *,
 extern void bio_unmap_user(struct bio *);
 extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int,
 				gfp_t);
+extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int,
+				 gfp_t, int);
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
 extern struct bio *bio_copy_user(struct request_queue *, unsigned long, unsigned int, int);
diff --git a/trunk/include/linux/bitmap.h b/trunk/include/linux/bitmap.h
index 1dbe074f1c64..43b406def35f 100644
--- a/trunk/include/linux/bitmap.h
+++ b/trunk/include/linux/bitmap.h
@@ -46,6 +46,8 @@
  * bitmap_shift_left(dst, src, n, nbits)	*dst = *src << n
  * bitmap_remap(dst, src, old, new, nbits)	*dst = map(old, new)(src)
  * bitmap_bitremap(oldbit, old, new, nbits)	newbit = map(old, new)(oldbit)
+ * bitmap_onto(dst, orig, relmap, nbits)	*dst = orig relative to relmap
+ * bitmap_fold(dst, orig, sz, nbits)		dst bits = orig bits mod sz
  * bitmap_scnprintf(buf, len, src, nbits)	Print bitmap src to buf
  * bitmap_parse(buf, buflen, dst, nbits)	Parse bitmap dst from kernel buf
  * bitmap_parse_user(ubuf, ulen, dst, nbits)	Parse bitmap dst from user buf
@@ -121,6 +123,10 @@ extern void bitmap_remap(unsigned long *dst, const unsigned long *src,
 		const unsigned long *old, const unsigned long *new, int bits);
 extern int bitmap_bitremap(int oldbit,
 		const unsigned long *old, const unsigned long *new, int bits);
+extern void bitmap_onto(unsigned long *dst, const unsigned long *orig,
+		const unsigned long *relmap, int bits);
+extern void bitmap_fold(unsigned long *dst, const unsigned long *orig,
+		int sz, int bits);
 extern int bitmap_find_free_region(unsigned long *bitmap, int bits, int order);
 extern void bitmap_release_region(unsigned long *bitmap, int pos, int order);
 extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order);
diff --git a/trunk/include/linux/bitops.h b/trunk/include/linux/bitops.h
index 48bde600a2db..024f2b027244 100644
--- a/trunk/include/linux/bitops.h
+++ b/trunk/include/linux/bitops.h
@@ -6,8 +6,8 @@
 #define BIT(nr)			(1UL << (nr))
 #define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
 #define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
-#define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_LONG)
 #define BITS_PER_BYTE		8
+#define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 #endif
 
 /*
@@ -114,8 +114,6 @@ static inline unsigned fls_long(unsigned long l)
 
 #ifdef __KERNEL__
 #ifdef CONFIG_GENERIC_FIND_FIRST_BIT
-extern unsigned long __find_first_bit(const unsigned long *addr,
-		unsigned long size);
 
 /**
  * find_first_bit - find the first set bit in a memory region
@@ -124,28 +122,8 @@ extern unsigned long __find_first_bit(const unsigned long *addr,
  *
  * Returns the bit number of the first set bit.
  */
-static __always_inline unsigned long
-find_first_bit(const unsigned long *addr, unsigned long size)
-{
-	/* Avoid a function call if the bitmap size is a constant */
-	/* and not bigger than BITS_PER_LONG. */
-
-	/* insert a sentinel so that __ffs returns size if there */
-	/* are no set bits in the bitmap */
-	if (__builtin_constant_p(size) && (size < BITS_PER_LONG))
-		return __ffs((*addr) | (1ul << size));
-
-	/* the result of __ffs(0) is undefined, so it needs to be */
-	/* handled separately */
-	if (__builtin_constant_p(size) && (size == BITS_PER_LONG))
-		return ((*addr) == 0) ? BITS_PER_LONG : __ffs(*addr);
-
-	/* size is not constant or too big */
-	return __find_first_bit(addr, size);
-}
-
-extern unsigned long __find_first_zero_bit(const unsigned long *addr,
-		unsigned long size);
+extern unsigned long find_first_bit(const unsigned long *addr,
+				    unsigned long size);
 
 /**
  * find_first_zero_bit - find the first cleared bit in a memory region
@@ -154,31 +132,12 @@ extern unsigned long __find_first_zero_bit(const unsigned long *addr,
  *
  * Returns the bit number of the first cleared bit.
  */
-static __always_inline unsigned long
-find_first_zero_bit(const unsigned long *addr, unsigned long size)
-{
-	/* Avoid a function call if the bitmap size is a constant */
-	/* and not bigger than BITS_PER_LONG. */
-
-	/* insert a sentinel so that __ffs returns size if there */
-	/* are no set bits in the bitmap */
-	if (__builtin_constant_p(size) && (size < BITS_PER_LONG)) {
-		return __ffs(~(*addr) | (1ul << size));
-	}
-
-	/* the result of __ffs(0) is undefined, so it needs to be */
-	/* handled separately */
-	if (__builtin_constant_p(size) && (size == BITS_PER_LONG))
-		return (~(*addr) == 0) ? BITS_PER_LONG : __ffs(~(*addr));
-
-	/* size is not constant or too big */
-	return __find_first_zero_bit(addr, size);
-}
+extern unsigned long find_first_zero_bit(const unsigned long *addr,
+					 unsigned long size);
+
 #endif /* CONFIG_GENERIC_FIND_FIRST_BIT */
 
 #ifdef CONFIG_GENERIC_FIND_NEXT_BIT
-extern unsigned long __find_next_bit(const unsigned long *addr,
-		unsigned long size, unsigned long offset);
 
 /**
  * find_next_bit - find the next set bit in a memory region
@@ -186,36 +145,8 @@ extern unsigned long __find_next_bit(const unsigned long *addr,
  * @offset: The bitnumber to start searching at
  * @size: The bitmap size in bits
  */
-static __always_inline unsigned long
-find_next_bit(const unsigned long *addr, unsigned long size,
-		unsigned long offset)
-{
-	unsigned long value;
-
-	/* Avoid a function call if the bitmap size is a constant */
-	/* and not bigger than BITS_PER_LONG. */
-
-	/* insert a sentinel so that __ffs returns size if there */
-	/* are no set bits in the bitmap */
-	if (__builtin_constant_p(size) && (size < BITS_PER_LONG)) {
-		value = (*addr) & ((~0ul) << offset);
-		value |= (1ul << size);
-		return __ffs(value);
-	}
-
-	/* the result of __ffs(0) is undefined, so it needs to be */
-	/* handled separately */
-	if (__builtin_constant_p(size) && (size == BITS_PER_LONG)) {
-		value = (*addr) & ((~0ul) << offset);
-		return (value == 0) ? BITS_PER_LONG : __ffs(value);
-	}
-
-	/* size is not constant or too big */
-	return __find_next_bit(addr, size, offset);
-}
-
-extern unsigned long __find_next_zero_bit(const unsigned long *addr,
-		unsigned long size, unsigned long offset);
+extern unsigned long find_next_bit(const unsigned long *addr,
+				   unsigned long size, unsigned long offset);
 
 /**
  * find_next_zero_bit - find the next cleared bit in a memory region
@@ -223,33 +154,11 @@ extern unsigned long __find_next_zero_bit(const unsigned long *addr,
  * @offset: The bitnumber to start searching at
  * @size: The bitmap size in bits
  */
-static __always_inline unsigned long
-find_next_zero_bit(const unsigned long *addr, unsigned long size,
-		unsigned long offset)
-{
-	unsigned long value;
-
-	/* Avoid a function call if the bitmap size is a constant */
-	/* and not bigger than BITS_PER_LONG. */
-
-	/* insert a sentinel so that __ffs returns size if there */
-	/* are no set bits in the bitmap */
-	if (__builtin_constant_p(size) && (size < BITS_PER_LONG)) {
-		value = (~(*addr)) & ((~0ul) << offset);
-		value |= (1ul << size);
-		return __ffs(value);
-	}
-
-	/* the result of __ffs(0) is undefined, so it needs to be */
-	/* handled separately */
-	if (__builtin_constant_p(size) && (size == BITS_PER_LONG)) {
-		value = (~(*addr)) & ((~0ul) << offset);
-		return (value == 0) ? BITS_PER_LONG : __ffs(value);
-	}
-
-	/* size is not constant or too big */
-	return __find_next_zero_bit(addr, size, offset);
-}
+
+extern unsigned long find_next_zero_bit(const unsigned long *addr,
+					unsigned long size,
+					unsigned long offset);
+
 #endif /* CONFIG_GENERIC_FIND_NEXT_BIT */
 #endif /* __KERNEL__ */
 #endif
diff --git a/trunk/include/linux/blkdev.h b/trunk/include/linux/blkdev.h
index c5065e3d2ca9..c09696a90d6a 100644
--- a/trunk/include/linux/blkdev.h
+++ b/trunk/include/linux/blkdev.h
@@ -215,8 +215,9 @@ struct request {
 	/*
 	 * when request is used as a packet command carrier
 	 */
-	unsigned int cmd_len;
-	unsigned char cmd[BLK_MAX_CDB];
+	unsigned short cmd_len;
+	unsigned char __cmd[BLK_MAX_CDB];
+	unsigned char *cmd;
 
 	unsigned int data_len;
 	unsigned int extra_len;	/* length of alignment and padding */
@@ -407,6 +408,31 @@ struct request_queue
 #define QUEUE_FLAG_PLUGGED	7	/* queue is plugged */
 #define QUEUE_FLAG_ELVSWITCH	8	/* don't use elevator, just do FIFO */
 #define QUEUE_FLAG_BIDI		9	/* queue supports bidi requests */
+#define QUEUE_FLAG_NOMERGES    10	/* disable merge attempts */
+
+static inline void queue_flag_set_unlocked(unsigned int flag,
+					   struct request_queue *q)
+{
+	__set_bit(flag, &q->queue_flags);
+}
+
+static inline void queue_flag_set(unsigned int flag, struct request_queue *q)
+{
+	WARN_ON_ONCE(!spin_is_locked(q->queue_lock));
+	__set_bit(flag, &q->queue_flags);
+}
+
+static inline void queue_flag_clear_unlocked(unsigned int flag,
+					     struct request_queue *q)
+{
+	__clear_bit(flag, &q->queue_flags);
+}
+
+static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
+{
+	WARN_ON_ONCE(!spin_is_locked(q->queue_lock));
+	__clear_bit(flag, &q->queue_flags);
+}
 
 enum {
 	/*
@@ -451,6 +477,7 @@ enum {
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
+#define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_flushing(q)	((q)->ordseq)
 
 #define blk_fs_request(rq)	((rq)->cmd_type == REQ_TYPE_FS)
@@ -496,17 +523,17 @@ static inline int blk_queue_full(struct request_queue *q, int rw)
 static inline void blk_set_queue_full(struct request_queue *q, int rw)
 {
 	if (rw == READ)
-		set_bit(QUEUE_FLAG_READFULL, &q->queue_flags);
+		queue_flag_set(QUEUE_FLAG_READFULL, q);
 	else
-		set_bit(QUEUE_FLAG_WRITEFULL, &q->queue_flags);
+		queue_flag_set(QUEUE_FLAG_WRITEFULL, q);
 }
 
 static inline void blk_clear_queue_full(struct request_queue *q, int rw)
 {
 	if (rw == READ)
-		clear_bit(QUEUE_FLAG_READFULL, &q->queue_flags);
+		queue_flag_clear(QUEUE_FLAG_READFULL, q);
 	else
-		clear_bit(QUEUE_FLAG_WRITEFULL, &q->queue_flags);
+		queue_flag_clear(QUEUE_FLAG_WRITEFULL, q);
 }
 
 
@@ -583,6 +610,7 @@ extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
 extern void register_disk(struct gendisk *dev);
 extern void generic_make_request(struct bio *bio);
+extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_put_request(struct request *);
 extern void __blk_put_request(struct request_queue *, struct request *);
 extern void blk_end_sync_rq(struct request *rq, int error);
@@ -626,6 +654,7 @@ extern void blk_start_queue(struct request_queue *q);
 extern void blk_stop_queue(struct request_queue *q);
 extern void blk_sync_queue(struct request_queue *q);
 extern void __blk_stop_queue(struct request_queue *q);
+extern void __blk_run_queue(struct request_queue *);
 extern void blk_run_queue(struct request_queue *);
 extern void blk_start_queueing(struct request_queue *);
 extern int blk_rq_map_user(struct request_queue *, struct request *, void __user *, unsigned long);
diff --git a/trunk/include/linux/bootmem.h b/trunk/include/linux/bootmem.h
index 4e4e340592fb..6a5dbdc8a7dc 100644
--- a/trunk/include/linux/bootmem.h
+++ b/trunk/include/linux/bootmem.h
@@ -101,6 +101,8 @@ extern void reserve_bootmem_node(pg_data_t *pgdat,
 extern void free_bootmem_node(pg_data_t *pgdat,
 			      unsigned long addr,
 			      unsigned long size);
+extern void *alloc_bootmem_section(unsigned long size,
+				   unsigned long section_nr);
 
 #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
 #define alloc_bootmem_node(pgdat, x) \
diff --git a/trunk/include/linux/bsg.h b/trunk/include/linux/bsg.h
index e8406c55c6d3..cf0303a60611 100644
--- a/trunk/include/linux/bsg.h
+++ b/trunk/include/linux/bsg.h
@@ -56,19 +56,25 @@ struct sg_io_v4 {
 #if defined(CONFIG_BLK_DEV_BSG)
 struct bsg_class_device {
 	struct device *class_dev;
-	struct device *dev;
+	struct device *parent;
 	int minor;
 	struct request_queue *queue;
+	struct kref ref;
+	void (*release)(struct device *);
 };
 
-extern int bsg_register_queue(struct request_queue *, struct device *, const char *);
+extern int bsg_register_queue(struct request_queue *q,
+			      struct device *parent, const char *name,
+			      void (*release)(struct device *));
 extern void bsg_unregister_queue(struct request_queue *);
 #else
-static inline int bsg_register_queue(struct request_queue * rq, struct device *dev, const char *name)
+static inline int bsg_register_queue(struct request_queue *q,
+				     struct device *parent, const char *name,
+				     void (*release)(struct device *))
 {
 	return 0;
 }
-static inline void bsg_unregister_queue(struct request_queue *rq)
+static inline void bsg_unregister_queue(struct request_queue *q)
 {
 }
 #endif
diff --git a/trunk/include/linux/buffer_head.h b/trunk/include/linux/buffer_head.h
index 932eb02a2753..82aa36c53ea7 100644
--- a/trunk/include/linux/buffer_head.h
+++ b/trunk/include/linux/buffer_head.h
@@ -225,7 +225,6 @@ int block_page_mkwrite(struct vm_area_struct *vma, struct page *page,
 				get_block_t get_block);
 void block_sync_page(struct page *);
 sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *);
-int generic_commit_write(struct file *, struct page *, unsigned, unsigned);
 int block_truncate_page(struct address_space *, loff_t, get_block_t *);
 int file_fsync(struct file *, struct dentry *, int);
 int nobh_write_begin(struct file *, struct address_space *,
diff --git a/trunk/include/linux/cache.h b/trunk/include/linux/cache.h
index 4552504c0228..97e24881c4c6 100644
--- a/trunk/include/linux/cache.h
+++ b/trunk/include/linux/cache.h
@@ -60,4 +60,8 @@
 #endif
 #endif
 
+#ifndef CONFIG_ARCH_HAS_CACHE_LINE_SIZE
+#define cache_line_size()	L1_CACHE_BYTES
+#endif
+
 #endif /* __LINUX_CACHE_H */
diff --git a/trunk/include/linux/capability.h b/trunk/include/linux/capability.h
index 7d50ff6d269f..eaab759b1460 100644
--- a/trunk/include/linux/capability.h
+++ b/trunk/include/linux/capability.h
@@ -155,6 +155,7 @@ typedef struct kernel_cap_struct {
  *   Add any capability from current's capability bounding set
  *       to the current process' inheritable set
  *   Allow taking bits out of capability bounding set
+ *   Allow modification of the securebits for a process
  */
 
 #define CAP_SETPCAP          8
@@ -490,8 +491,6 @@ extern const kernel_cap_t __cap_init_eff_set;
 int capable(int cap);
 int __capable(struct task_struct *t, int cap);
 
-extern long cap_prctl_drop(unsigned long cap);
-
 #endif /* __KERNEL__ */
 
 #endif /* !_LINUX_CAPABILITY_H */
diff --git a/trunk/include/linux/cgroup.h b/trunk/include/linux/cgroup.h
index a6a6035a4e1e..e155aa78d859 100644
--- a/trunk/include/linux/cgroup.h
+++ b/trunk/include/linux/cgroup.h
@@ -88,6 +88,17 @@ static inline void css_put(struct cgroup_subsys_state *css)
 		__css_put(css);
 }
 
+/* bits in struct cgroup flags field */
+enum {
+	/* Control Group is dead */
+	CGRP_REMOVED,
+	/* Control Group has previously had a child cgroup or a task,
+	 * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set) */
+	CGRP_RELEASABLE,
+	/* Control Group requires release notifications to userspace */
+	CGRP_NOTIFY_ON_RELEASE,
+};
+
 struct cgroup {
 	unsigned long flags;		/* "unsigned long" so bitops work */
 
@@ -139,10 +150,10 @@ struct css_set {
 	struct kref ref;
 
 	/*
-	 * List running through all cgroup groups. Protected by
-	 * css_set_lock
+	 * List running through all cgroup groups in the same hash
+	 * slot. Protected by css_set_lock
 	 */
-	struct list_head list;
+	struct hlist_node hlist;
 
 	/*
 	 * List running through all tasks using this cgroup
@@ -163,7 +174,16 @@ struct css_set {
 	 * during subsystem registration (at boot time).
 	 */
 	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
+};
+
+/*
+ * cgroup_map_cb is an abstract callback API for reporting map-valued
+ * control files
+ */
 
+struct cgroup_map_cb {
+	int (*fill)(struct cgroup_map_cb *cb, const char *key, u64 value);
+	void *state;
 };
 
 /* struct cftype:
@@ -190,20 +210,51 @@ struct cftype {
 			 struct file *file,
 			 char __user *buf, size_t nbytes, loff_t *ppos);
 	/*
-	 * read_uint() is a shortcut for the common case of returning a
+	 * read_u64() is a shortcut for the common case of returning a
 	 * single integer. Use it in place of read()
 	 */
-	u64 (*read_uint) (struct cgroup *cgrp, struct cftype *cft);
+	u64 (*read_u64) (struct cgroup *cgrp, struct cftype *cft);
+	/*
+	 * read_s64() is a signed version of read_u64()
+	 */
+	s64 (*read_s64) (struct cgroup *cgrp, struct cftype *cft);
+	/*
+	 * read_map() is used for defining a map of key/value
+	 * pairs. It should call cb->fill(cb, key, value) for each
+	 * entry. The key/value pairs (and their ordering) should not
+	 * change between reboots.
+	 */
+	int (*read_map) (struct cgroup *cont, struct cftype *cft,
+			 struct cgroup_map_cb *cb);
+	/*
+	 * read_seq_string() is used for outputting a simple sequence
+	 * using seqfile.
+	 */
+	int (*read_seq_string) (struct cgroup *cont, struct cftype *cft,
+			 struct seq_file *m);
+
 	ssize_t (*write) (struct cgroup *cgrp, struct cftype *cft,
 			  struct file *file,
 			  const char __user *buf, size_t nbytes, loff_t *ppos);
 
 	/*
-	 * write_uint() is a shortcut for the common case of accepting
+	 * write_u64() is a shortcut for the common case of accepting
 	 * a single integer (as parsed by simple_strtoull) from
 	 * userspace. Use in place of write(); return 0 or error.
 	 */
-	int (*write_uint) (struct cgroup *cgrp, struct cftype *cft, u64 val);
+	int (*write_u64) (struct cgroup *cgrp, struct cftype *cft, u64 val);
+	/*
+	 * write_s64() is a signed version of write_u64()
+	 */
+	int (*write_s64) (struct cgroup *cgrp, struct cftype *cft, s64 val);
+
+	/*
+	 * trigger() callback can be used to get some kick from the
+	 * userspace, when the actual string written is not important
+	 * at all. The private field can be used to determine the
+	 * kick type for multiplexing.
+	 */
+	int (*trigger)(struct cgroup *cgrp, unsigned int event);
 
 	int (*release) (struct inode *inode, struct file *file);
 };
@@ -254,6 +305,12 @@ struct cgroup_subsys {
 			struct cgroup *cgrp);
 	void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cgrp);
 	void (*bind)(struct cgroup_subsys *ss, struct cgroup *root);
+	/*
+	 * This routine is called with the task_lock of mm->owner held
+	 */
+	void (*mm_owner_changed)(struct cgroup_subsys *ss,
+					struct cgroup *old,
+					struct cgroup *new);
 	int subsys_id;
 	int active;
 	int disabled;
@@ -339,4 +396,13 @@ static inline int cgroupstats_build(struct cgroupstats *stats,
 
 #endif /* !CONFIG_CGROUPS */
 
+#ifdef CONFIG_MM_OWNER
+extern void
+cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new);
+#else /* !CONFIG_MM_OWNER */
+static inline void
+cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
+{
+}
+#endif /* CONFIG_MM_OWNER */
 #endif /* _LINUX_CGROUP_H */
diff --git a/trunk/include/linux/cgroup_subsys.h b/trunk/include/linux/cgroup_subsys.h
index 1ddebfc52565..e2877454ec82 100644
--- a/trunk/include/linux/cgroup_subsys.h
+++ b/trunk/include/linux/cgroup_subsys.h
@@ -42,3 +42,9 @@ SUBSYS(mem_cgroup)
 #endif
 
 /* */
+
+#ifdef CONFIG_CGROUP_DEVICE
+SUBSYS(devices)
+#endif
+
+/* */
diff --git a/trunk/include/linux/coda_linux.h b/trunk/include/linux/coda_linux.h
index 1c47a34aa794..31b75311e2ca 100644
--- a/trunk/include/linux/coda_linux.h
+++ b/trunk/include/linux/coda_linux.h
@@ -43,9 +43,6 @@ int coda_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 int coda_setattr(struct dentry *, struct iattr *);
 
 /* this file:  heloers */
-static __inline__ struct CodaFid *coda_i2f(struct inode *);
-static __inline__ char *coda_i2s(struct inode *);
-static __inline__ void coda_flag_inode(struct inode *, int flag);
 char *coda_f2s(struct CodaFid *f);
 int coda_isroot(struct inode *i);
 int coda_iscontrol(const char *name, size_t length);
diff --git a/trunk/include/linux/console_struct.h b/trunk/include/linux/console_struct.h
index d71f7c0f931b..b03f80a078be 100644
--- a/trunk/include/linux/console_struct.h
+++ b/trunk/include/linux/console_struct.h
@@ -53,6 +53,7 @@ struct vc_data {
 	unsigned short	vc_hi_font_mask;	/* [#] Attribute set for upper 256 chars of font or 0 if not supported */
 	struct console_font vc_font;		/* Current VC font set */
 	unsigned short	vc_video_erase_char;	/* Background erase character */
+	unsigned short	vc_scrl_erase_char;	/* Erase character for scroll */
 	/* VT terminal data */
 	unsigned int	vc_state;		/* Escape sequence parser state */
 	unsigned int	vc_npar,vc_par[NPAR];	/* Parameters of current escape sequence */
diff --git a/trunk/include/linux/cpu.h b/trunk/include/linux/cpu.h
index f212fa98283e..7464ba3b4333 100644
--- a/trunk/include/linux/cpu.h
+++ b/trunk/include/linux/cpu.h
@@ -108,7 +108,7 @@ static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex)
 extern void get_online_cpus(void);
 extern void put_online_cpus(void);
 #define hotcpu_notifier(fn, pri) {				\
-	static struct notifier_block fn##_nb =			\
+	static struct notifier_block fn##_nb __cpuinitdata =	\
 		{ .notifier_call = fn, .priority = pri };	\
 	register_cpu_notifier(&fn##_nb);			\
 }
diff --git a/trunk/include/linux/cpufreq.h b/trunk/include/linux/cpufreq.h
index ddd8652fc3f3..e7e91dbfde0f 100644
--- a/trunk/include/linux/cpufreq.h
+++ b/trunk/include/linux/cpufreq.h
@@ -83,7 +83,8 @@ struct cpufreq_real_policy {
 };
 
 struct cpufreq_policy {
-	cpumask_t		cpus;	/* affected CPUs */
+	cpumask_t		cpus;	/* CPUs requiring sw coordination */
+	cpumask_t		related_cpus; /* CPUs with any coordination */
 	unsigned int		shared_type; /* ANY or ALL affected CPUs
 						should set cpufreq */
 	unsigned int		cpu;    /* cpu nr of registered CPU */
@@ -307,6 +308,9 @@ extern struct cpufreq_governor cpufreq_gov_performance;
 #endif
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
 #define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_performance)
+#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE)
+extern struct cpufreq_governor cpufreq_gov_powersave;
+#define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_powersave)
 #elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE)
 extern struct cpufreq_governor cpufreq_gov_userspace;
 #define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_userspace)
diff --git a/trunk/include/linux/cpumask.h b/trunk/include/linux/cpumask.h
index 259c8051155d..9650806fe2ea 100644
--- a/trunk/include/linux/cpumask.h
+++ b/trunk/include/linux/cpumask.h
@@ -14,6 +14,8 @@
  * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c.
  * For details of cpu_remap(), see bitmap_bitremap in lib/bitmap.c
  * For details of cpus_remap(), see bitmap_remap in lib/bitmap.c.
+ * For details of cpus_onto(), see bitmap_onto in lib/bitmap.c.
+ * For details of cpus_fold(), see bitmap_fold in lib/bitmap.c.
  *
  * The available cpumask operations are:
  *
@@ -53,7 +55,9 @@
  * int cpulist_scnprintf(buf, len, mask) Format cpumask as list for printing
  * int cpulist_parse(buf, map)		Parse ascii string as cpulist
  * int cpu_remap(oldbit, old, new)	newbit = map(old, new)(oldbit)
- * int cpus_remap(dst, src, old, new)	*dst = map(old, new)(src)
+ * void cpus_remap(dst, src, old, new)	*dst = map(old, new)(src)
+ * void cpus_onto(dst, orig, relmap)	*dst = orig relative to relmap
+ * void cpus_fold(dst, orig, sz)	dst bits = orig bits mod sz
  *
  * for_each_cpu_mask(cpu, mask)		for-loop cpu over mask
  *
@@ -330,6 +334,22 @@ static inline void __cpus_remap(cpumask_t *dstp, const cpumask_t *srcp,
 	bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits);
 }
 
+#define cpus_onto(dst, orig, relmap) \
+		__cpus_onto(&(dst), &(orig), &(relmap), NR_CPUS)
+static inline void __cpus_onto(cpumask_t *dstp, const cpumask_t *origp,
+		const cpumask_t *relmapp, int nbits)
+{
+	bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits);
+}
+
+#define cpus_fold(dst, orig, sz) \
+		__cpus_fold(&(dst), &(orig), sz, NR_CPUS)
+static inline void __cpus_fold(cpumask_t *dstp, const cpumask_t *origp,
+		int sz, int nbits)
+{
+	bitmap_fold(dstp->bits, origp->bits, sz, nbits);
+}
+
 #if NR_CPUS > 1
 #define for_each_cpu_mask(cpu, mask)		\
 	for ((cpu) = first_cpu(mask);		\
diff --git a/trunk/include/linux/cpuset.h b/trunk/include/linux/cpuset.h
index 726761e24003..038578362b47 100644
--- a/trunk/include/linux/cpuset.h
+++ b/trunk/include/linux/cpuset.h
@@ -26,7 +26,7 @@ extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 #define cpuset_current_mems_allowed (current->mems_allowed)
 void cpuset_init_current_mems_allowed(void);
 void cpuset_update_task_memory_state(void);
-int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl);
+int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask);
 
 extern int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask);
 extern int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask);
@@ -103,7 +103,7 @@ static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
 static inline void cpuset_init_current_mems_allowed(void) {}
 static inline void cpuset_update_task_memory_state(void) {}
 
-static inline int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl)
+static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)
 {
 	return 1;
 }
diff --git a/trunk/include/linux/device_cgroup.h b/trunk/include/linux/device_cgroup.h
new file mode 100644
index 000000000000..0b0d9c39ed67
--- /dev/null
+++ b/trunk/include/linux/device_cgroup.h
@@ -0,0 +1,12 @@
+#include <linux/module.h>
+#include <linux/fs.h>
+
+#ifdef CONFIG_CGROUP_DEVICE
+extern int devcgroup_inode_permission(struct inode *inode, int mask);
+extern int devcgroup_inode_mknod(int mode, dev_t dev);
+#else
+static inline int devcgroup_inode_permission(struct inode *inode, int mask)
+{ return 0; }
+static inline int devcgroup_inode_mknod(int mode, dev_t dev)
+{ return 0; }
+#endif
diff --git a/trunk/include/linux/dma-attrs.h b/trunk/include/linux/dma-attrs.h
new file mode 100644
index 000000000000..1677e2bfa00c
--- /dev/null
+++ b/trunk/include/linux/dma-attrs.h
@@ -0,0 +1,74 @@
+#ifndef _DMA_ATTR_H
+#define _DMA_ATTR_H
+
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/bug.h>
+
+/**
+ * an enum dma_attr represents an attribute associated with a DMA
+ * mapping. The semantics of each attribute should be defined in
+ * Documentation/DMA-attributes.txt.
+ */
+enum dma_attr {
+	DMA_ATTR_WRITE_BARRIER,
+	DMA_ATTR_MAX,
+};
+
+#define __DMA_ATTRS_LONGS BITS_TO_LONGS(DMA_ATTR_MAX)
+
+/**
+ * struct dma_attrs - an opaque container for DMA attributes
+ * @flags - bitmask representing a collection of enum dma_attr
+ */
+struct dma_attrs {
+	unsigned long flags[__DMA_ATTRS_LONGS];
+};
+
+#define DEFINE_DMA_ATTRS(x) 					\
+	struct dma_attrs x = {					\
+		.flags = { [0 ... __DMA_ATTRS_LONGS-1] = 0 },	\
+	}
+
+static inline void init_dma_attrs(struct dma_attrs *attrs)
+{
+	bitmap_zero(attrs->flags, __DMA_ATTRS_LONGS);
+}
+
+#ifdef CONFIG_HAVE_DMA_ATTRS
+/**
+ * dma_set_attr - set a specific attribute
+ * @attr: attribute to set
+ * @attrs: struct dma_attrs (may be NULL)
+ */
+static inline void dma_set_attr(enum dma_attr attr, struct dma_attrs *attrs)
+{
+	if (attrs == NULL)
+		return;
+	BUG_ON(attr >= DMA_ATTR_MAX);
+	__set_bit(attr, attrs->flags);
+}
+
+/**
+ * dma_get_attr - check for a specific attribute
+ * @attr: attribute to set
+ * @attrs: struct dma_attrs (may be NULL)
+ */
+static inline int dma_get_attr(enum dma_attr attr, struct dma_attrs *attrs)
+{
+	if (attrs == NULL)
+		return 0;
+	BUG_ON(attr >= DMA_ATTR_MAX);
+	return test_bit(attr, attrs->flags);
+}
+#else /* !CONFIG_HAVE_DMA_ATTRS */
+static inline void dma_set_attr(enum dma_attr attr, struct dma_attrs *attrs)
+{
+}
+
+static inline int dma_get_attr(enum dma_attr attr, struct dma_attrs *attrs)
+{
+	return 0;
+}
+#endif /* CONFIG_HAVE_DMA_ATTRS */
+#endif /* _DMA_ATTR_H */
diff --git a/trunk/include/linux/dma-mapping.h b/trunk/include/linux/dma-mapping.h
index 332030709623..952e0f857ac9 100644
--- a/trunk/include/linux/dma-mapping.h
+++ b/trunk/include/linux/dma-mapping.h
@@ -146,4 +146,21 @@ static inline void dmam_release_declared_memory(struct device *dev)
 }
 #endif /* ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY */
 
+#ifndef CONFIG_HAVE_DMA_ATTRS
+struct dma_attrs;
+
+#define dma_map_single_attrs(dev, cpu_addr, size, dir, attrs) \
+	dma_map_single(dev, cpu_addr, size, dir)
+
+#define dma_unmap_single_attrs(dev, dma_addr, size, dir, attrs) \
+	dma_unmap_single(dev, dma_addr, size, dir)
+
+#define dma_map_sg_attrs(dev, sgl, nents, dir, attrs) \
+	dma_map_sg(dev, sgl, nents, dir)
+
+#define dma_unmap_sg_attrs(dev, sgl, nents, dir, attrs) \
+	dma_unmap_sg(dev, sgl, nents, dir)
+
+#endif /* CONFIG_HAVE_DMA_ATTRS */
+
 #endif
diff --git a/trunk/include/linux/dmi.h b/trunk/include/linux/dmi.h
index 325acdf5c462..2a063b64133f 100644
--- a/trunk/include/linux/dmi.h
+++ b/trunk/include/linux/dmi.h
@@ -90,6 +90,7 @@ static inline int dmi_check_system(const struct dmi_system_id *list) { return 0;
 static inline const char * dmi_get_system_info(int field) { return NULL; }
 static inline const struct dmi_device * dmi_find_device(int type, const char *name,
 	const struct dmi_device *from) { return NULL; }
+static inline void dmi_scan_machine(void) { return; }
 static inline int dmi_get_year(int year) { return 0; }
 static inline int dmi_name_in_vendors(const char *s) { return 0; }
 #define dmi_available 0
diff --git a/trunk/include/linux/edac.h b/trunk/include/linux/edac.h
index eab451e69a91..7cf92e8a4196 100644
--- a/trunk/include/linux/edac.h
+++ b/trunk/include/linux/edac.h
@@ -3,7 +3,7 @@
  *
  * Author: Dave Jiang <djiang@mvista.com>
  *
- * 2006-2007 (c) MontaVista Software, Inc. This file is licensed under
+ * 2006-2008 (c) MontaVista Software, Inc. This file is licensed under
  * the terms of the GNU General Public License version 2. This program
  * is licensed "as is" without any warranty of any kind, whether express
  * or implied.
@@ -26,4 +26,16 @@ extern atomic_t edac_handlers;
 extern int edac_handler_set(void);
 extern void edac_atomic_assert_error(void);
 
+static inline void opstate_init(void)
+{
+	switch (edac_op_state) {
+	case EDAC_OPSTATE_POLL:
+	case EDAC_OPSTATE_NMI:
+		break;
+	default:
+		edac_op_state = EDAC_OPSTATE_POLL;
+	}
+	return;
+}
+
 #endif
diff --git a/trunk/include/linux/elf.h b/trunk/include/linux/elf.h
index bad1b16ec49a..ff9fbed90123 100644
--- a/trunk/include/linux/elf.h
+++ b/trunk/include/linux/elf.h
@@ -208,7 +208,7 @@ typedef struct elf32_hdr{
 } Elf32_Ehdr;
 
 typedef struct elf64_hdr {
-  unsigned char	e_ident[16];		/* ELF "magic number" */
+  unsigned char	e_ident[EI_NIDENT];	/* ELF "magic number" */
   Elf64_Half e_type;
   Elf64_Half e_machine;
   Elf64_Word e_version;
diff --git a/trunk/include/linux/fb.h b/trunk/include/linux/fb.h
index 58c57a33e5dd..72295b099228 100644
--- a/trunk/include/linux/fb.h
+++ b/trunk/include/linux/fb.h
@@ -791,6 +791,17 @@ struct fb_tile_ops {
  */
 #define FBINFO_MISC_ALWAYS_SETPAR   0x40000
 
+/*
+ * Host and GPU endianness differ.
+ */
+#define FBINFO_FOREIGN_ENDIAN	0x100000
+/*
+ * Big endian math. This is the same flags as above, but with different
+ * meaning, it is set by the fb subsystem depending FOREIGN_ENDIAN flag
+ * and host endianness. Drivers should not use this flag.
+ */
+#define FBINFO_BE_MATH  0x100000
+
 struct fb_info {
 	int node;
 	int flags;
@@ -899,15 +910,11 @@ struct fb_info {
 
 #endif
 
-#if defined (__BIG_ENDIAN)
-#define FB_LEFT_POS(bpp)          (32 - bpp)
-#define FB_SHIFT_HIGH(val, bits)  ((val) >> (bits))
-#define FB_SHIFT_LOW(val, bits)   ((val) << (bits))
-#else
-#define FB_LEFT_POS(bpp)          (0)
-#define FB_SHIFT_HIGH(val, bits)  ((val) << (bits))
-#define FB_SHIFT_LOW(val, bits)   ((val) >> (bits))
-#endif
+#define FB_LEFT_POS(p, bpp)          (fb_be_math(p) ? (32 - (bpp)) : 0)
+#define FB_SHIFT_HIGH(p, val, bits)  (fb_be_math(p) ? (val) >> (bits) : \
+						      (val) << (bits))
+#define FB_SHIFT_LOW(p, val, bits)   (fb_be_math(p) ? (val) << (bits) : \
+						      (val) >> (bits))
 
     /*
      *  `Generic' versions of the frame buffer device operations
@@ -970,6 +977,25 @@ extern void fb_deferred_io_cleanup(struct fb_info *info);
 extern int fb_deferred_io_fsync(struct file *file, struct dentry *dentry,
 				int datasync);
 
+static inline bool fb_be_math(struct fb_info *info)
+{
+#ifdef CONFIG_FB_FOREIGN_ENDIAN
+#if defined(CONFIG_FB_BOTH_ENDIAN)
+	return info->flags & FBINFO_BE_MATH;
+#elif defined(CONFIG_FB_BIG_ENDIAN)
+	return true;
+#elif defined(CONFIG_FB_LITTLE_ENDIAN)
+	return false;
+#endif /* CONFIG_FB_BOTH_ENDIAN */
+#else
+#ifdef __BIG_ENDIAN
+	return true;
+#else
+	return false;
+#endif /* __BIG_ENDIAN */
+#endif /* CONFIG_FB_FOREIGN_ENDIAN */
+}
+
 /* drivers/video/fbsysfs.c */
 extern struct fb_info *framebuffer_alloc(size_t size, struct device *dev);
 extern void framebuffer_release(struct fb_info *info);
diff --git a/trunk/include/linux/fs.h b/trunk/include/linux/fs.h
index d6d7c52055c6..a1ba005d08e7 100644
--- a/trunk/include/linux/fs.h
+++ b/trunk/include/linux/fs.h
@@ -474,8 +474,8 @@ struct address_space_operations {
 	int (*releasepage) (struct page *, gfp_t);
 	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
 			loff_t offset, unsigned long nr_segs);
-	struct page* (*get_xip_page)(struct address_space *, sector_t,
-			int);
+	int (*get_xip_mem)(struct address_space *, pgoff_t, int,
+						void **, unsigned long *);
 	/* migrate the contents of a page to the specified target */
 	int (*migratepage) (struct address_space *,
 			struct page *, struct page *);
@@ -1178,7 +1178,8 @@ struct block_device_operations {
 	int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long);
 	long (*unlocked_ioctl) (struct file *, unsigned, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned, unsigned long);
-	int (*direct_access) (struct block_device *, sector_t, unsigned long *);
+	int (*direct_access) (struct block_device *, sector_t,
+						void **, unsigned long *);
 	int (*media_changed) (struct gendisk *);
 	int (*revalidate_disk) (struct gendisk *);
 	int (*getgeo)(struct block_device *, struct hd_geometry *);
@@ -1520,7 +1521,6 @@ extern int get_sb_pseudo(struct file_system_type *, char *,
 	const struct super_operations *ops, unsigned long,
 	struct vfsmount *mnt);
 extern int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
-int __put_super(struct super_block *sb);
 int __put_super_and_need_restart(struct super_block *sb);
 void unnamed_dev_init(void);
 
@@ -1964,7 +1964,6 @@ extern int vfs_stat_fd(int dfd, char __user *, struct kstat *);
 extern int vfs_lstat_fd(int dfd, char __user *, struct kstat *);
 extern int vfs_fstat(unsigned int, struct kstat *);
 
-extern long vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
 extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 		    unsigned long arg);
 
diff --git a/trunk/include/linux/gfp.h b/trunk/include/linux/gfp.h
index 164be9da3c1b..b414be387180 100644
--- a/trunk/include/linux/gfp.h
+++ b/trunk/include/linux/gfp.h
@@ -40,9 +40,9 @@ struct vm_area_struct;
 #define __GFP_FS	((__force gfp_t)0x80u)	/* Can call down to low-level FS? */
 #define __GFP_COLD	((__force gfp_t)0x100u)	/* Cache-cold page required */
 #define __GFP_NOWARN	((__force gfp_t)0x200u)	/* Suppress page allocation failure warning */
-#define __GFP_REPEAT	((__force gfp_t)0x400u)	/* Retry the allocation.  Might fail */
-#define __GFP_NOFAIL	((__force gfp_t)0x800u)	/* Retry for ever.  Cannot fail */
-#define __GFP_NORETRY	((__force gfp_t)0x1000u)/* Do not retry.  Might fail */
+#define __GFP_REPEAT	((__force gfp_t)0x400u)	/* See above */
+#define __GFP_NOFAIL	((__force gfp_t)0x800u)	/* See above */
+#define __GFP_NORETRY	((__force gfp_t)0x1000u)/* See above */
 #define __GFP_COMP	((__force gfp_t)0x4000u)/* Add compound page metadata */
 #define __GFP_ZERO	((__force gfp_t)0x8000u)/* Return zeroed page on success */
 #define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use emergency reserves */
@@ -119,35 +119,22 @@ static inline int allocflags_to_migratetype(gfp_t gfp_flags)
 
 static inline enum zone_type gfp_zone(gfp_t flags)
 {
-	int base = 0;
-
-#ifdef CONFIG_NUMA
-	if (flags & __GFP_THISNODE)
-		base = MAX_NR_ZONES;
-#endif
-
 #ifdef CONFIG_ZONE_DMA
 	if (flags & __GFP_DMA)
-		return base + ZONE_DMA;
+		return ZONE_DMA;
 #endif
 #ifdef CONFIG_ZONE_DMA32
 	if (flags & __GFP_DMA32)
-		return base + ZONE_DMA32;
+		return ZONE_DMA32;
 #endif
 	if ((flags & (__GFP_HIGHMEM | __GFP_MOVABLE)) ==
 			(__GFP_HIGHMEM | __GFP_MOVABLE))
-		return base + ZONE_MOVABLE;
+		return ZONE_MOVABLE;
 #ifdef CONFIG_HIGHMEM
 	if (flags & __GFP_HIGHMEM)
-		return base + ZONE_HIGHMEM;
+		return ZONE_HIGHMEM;
 #endif
-	return base + ZONE_NORMAL;
-}
-
-static inline gfp_t set_migrateflags(gfp_t gfp, gfp_t migrate_flags)
-{
-	BUG_ON((gfp & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);
-	return (gfp & ~(GFP_MOVABLE_MASK)) | migrate_flags;
+	return ZONE_NORMAL;
 }
 
 /*
@@ -157,13 +144,27 @@ static inline gfp_t set_migrateflags(gfp_t gfp, gfp_t migrate_flags)
  * virtual kernel addresses to the allocated page(s).
  */
 
+static inline int gfp_zonelist(gfp_t flags)
+{
+	if (NUMA_BUILD && unlikely(flags & __GFP_THISNODE))
+		return 1;
+
+	return 0;
+}
+
 /*
  * We get the zone list from the current node and the gfp_mask.
  * This zone list contains a maximum of MAXNODES*MAX_NR_ZONES zones.
+ * There are two zonelists per node, one for all zones with memory and
+ * one containing just zones from the node the zonelist belongs to.
  *
  * For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets
  * optimized to &contig_page_data at compile-time.
  */
+static inline struct zonelist *node_zonelist(int nid, gfp_t flags)
+{
+	return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags);
+}
 
 #ifndef HAVE_ARCH_FREE_PAGE
 static inline void arch_free_page(struct page *page, int order) { }
@@ -174,6 +175,10 @@ static inline void arch_alloc_page(struct page *page, int order) { }
 
 extern struct page *__alloc_pages(gfp_t, unsigned int, struct zonelist *);
 
+extern struct page *
+__alloc_pages_nodemask(gfp_t, unsigned int,
+				struct zonelist *, nodemask_t *nodemask);
+
 static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
 						unsigned int order)
 {
@@ -184,8 +189,7 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
 	if (nid < 0)
 		nid = numa_node_id();
 
-	return __alloc_pages(gfp_mask, order,
-		NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_mask));
+	return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
 }
 
 #ifdef CONFIG_NUMA
diff --git a/trunk/include/linux/hid.h b/trunk/include/linux/hid.h
index d951ec411241..4ce3b7a979ba 100644
--- a/trunk/include/linux/hid.h
+++ b/trunk/include/linux/hid.h
@@ -498,13 +498,13 @@ struct hid_parser {
 
 struct hid_class_descriptor {
 	__u8  bDescriptorType;
-	__u16 wDescriptorLength;
+	__le16 wDescriptorLength;
 } __attribute__ ((packed));
 
 struct hid_descriptor {
 	__u8  bLength;
 	__u8  bDescriptorType;
-	__u16 bcdHID;
+	__le16 bcdHID;
 	__u8  bCountryCode;
 	__u8  bNumDescriptors;
 
diff --git a/trunk/include/linux/hugetlb.h b/trunk/include/linux/hugetlb.h
index addca4cd4f11..a79e80b689d8 100644
--- a/trunk/include/linux/hugetlb.h
+++ b/trunk/include/linux/hugetlb.h
@@ -8,6 +8,7 @@
 #include <linux/mempolicy.h>
 #include <linux/shm.h>
 #include <asm/tlbflush.h>
+#include <asm/hugetlb.h>
 
 struct ctl_table;
 
@@ -51,51 +52,6 @@ int pmd_huge(pmd_t pmd);
 void hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot);
 
-#ifndef ARCH_HAS_HUGEPAGE_ONLY_RANGE
-#define is_hugepage_only_range(mm, addr, len)	0
-#endif
-
-#ifndef ARCH_HAS_HUGETLB_FREE_PGD_RANGE
-#define hugetlb_free_pgd_range	free_pgd_range
-#else
-void hugetlb_free_pgd_range(struct mmu_gather **tlb, unsigned long addr,
-			    unsigned long end, unsigned long floor,
-			    unsigned long ceiling);
-#endif
-
-#ifndef ARCH_HAS_PREPARE_HUGEPAGE_RANGE
-/*
- * If the arch doesn't supply something else, assume that hugepage
- * size aligned regions are ok without further preparation.
- */
-static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
-{
-	if (len & ~HPAGE_MASK)
-		return -EINVAL;
-	if (addr & ~HPAGE_MASK)
-		return -EINVAL;
-	return 0;
-}
-#else
-int prepare_hugepage_range(unsigned long addr, unsigned long len);
-#endif
-
-#ifndef ARCH_HAS_SETCLEAR_HUGE_PTE
-#define set_huge_pte_at(mm, addr, ptep, pte)	set_pte_at(mm, addr, ptep, pte)
-#define huge_ptep_get_and_clear(mm, addr, ptep) ptep_get_and_clear(mm, addr, ptep)
-#else
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-		     pte_t *ptep, pte_t pte);
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
-#endif
-
-#ifndef ARCH_HAS_HUGETLB_PREFAULT_HOOK
-#define hugetlb_prefault_arch_hook(mm)		do { } while (0)
-#else
-void hugetlb_prefault_arch_hook(struct mm_struct *mm);
-#endif
-
 #else /* !CONFIG_HUGETLB_PAGE */
 
 static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
diff --git a/trunk/include/linux/i2o.h b/trunk/include/linux/i2o.h
index e92170dda245..f65e58a1d925 100644
--- a/trunk/include/linux/i2o.h
+++ b/trunk/include/linux/i2o.h
@@ -613,14 +613,9 @@ struct i2o_sys_tbl {
 extern struct list_head i2o_controllers;
 
 /* Message functions */
-static inline struct i2o_message *i2o_msg_get(struct i2o_controller *);
 extern struct i2o_message *i2o_msg_get_wait(struct i2o_controller *, int);
-static inline void i2o_msg_post(struct i2o_controller *, struct i2o_message *);
-static inline int i2o_msg_post_wait(struct i2o_controller *,
-				    struct i2o_message *, unsigned long);
 extern int i2o_msg_post_wait_mem(struct i2o_controller *, struct i2o_message *,
 				 unsigned long, struct i2o_dma *);
-static inline void i2o_flush_reply(struct i2o_controller *, u32);
 
 /* IOP functions */
 extern int i2o_status_get(struct i2o_controller *);
diff --git a/trunk/include/linux/ide.h b/trunk/include/linux/ide.h
index f0af504dfa42..b0135b0c3a04 100644
--- a/trunk/include/linux/ide.h
+++ b/trunk/include/linux/ide.h
@@ -47,13 +47,6 @@ typedef unsigned char	byte;	/* used everywhere */
 #define ERROR_RESET	3	/* Reset controller every 4th retry */
 #define ERROR_RECAL	1	/* Recalibrate every 2nd retry */
 
-/*
- * Tune flags
- */
-#define IDE_TUNE_NOAUTO		2
-#define IDE_TUNE_AUTO		1
-#define IDE_TUNE_DEFAULT	0
-
 /*
  * state flags
  */
@@ -68,23 +61,30 @@ typedef unsigned char	byte;	/* used everywhere */
  */
 #define IDE_NR_PORTS		(10)
 
-#define IDE_DATA_OFFSET		(0)
-#define IDE_ERROR_OFFSET	(1)
-#define IDE_NSECTOR_OFFSET	(2)
-#define IDE_SECTOR_OFFSET	(3)
-#define IDE_LCYL_OFFSET		(4)
-#define IDE_HCYL_OFFSET		(5)
-#define IDE_SELECT_OFFSET	(6)
-#define IDE_STATUS_OFFSET	(7)
-#define IDE_CONTROL_OFFSET	(8)
-#define IDE_IRQ_OFFSET		(9)
-
-#define IDE_FEATURE_OFFSET	IDE_ERROR_OFFSET
-#define IDE_COMMAND_OFFSET	IDE_STATUS_OFFSET
-#define IDE_ALTSTATUS_OFFSET	IDE_CONTROL_OFFSET
-#define IDE_IREASON_OFFSET	IDE_NSECTOR_OFFSET
-#define IDE_BCOUNTL_OFFSET	IDE_LCYL_OFFSET
-#define IDE_BCOUNTH_OFFSET	IDE_HCYL_OFFSET
+struct ide_io_ports {
+	unsigned long	data_addr;
+
+	union {
+		unsigned long error_addr;	/*   read:  error */
+		unsigned long feature_addr;	/*  write: feature */
+	};
+
+	unsigned long	nsect_addr;
+	unsigned long	lbal_addr;
+	unsigned long	lbam_addr;
+	unsigned long	lbah_addr;
+
+	unsigned long	device_addr;
+
+	union {
+		unsigned long status_addr;	/*  read: status  */
+		unsigned long command_addr;	/* write: command */
+	};
+
+	unsigned long	ctl_addr;
+
+	unsigned long	irq_addr;
+};
 
 #define OK_STAT(stat,good,bad)	(((stat)&((good)|(bad)))==(good))
 #define BAD_R_STAT		(BUSY_STAT   | ERR_STAT)
@@ -163,7 +163,11 @@ typedef u8 hwif_chipset_t;
  * Structure to hold all information about the location of this port
  */
 typedef struct hw_regs_s {
-	unsigned long	io_ports[IDE_NR_PORTS];	/* task file registers */
+	union {
+		struct ide_io_ports	io_ports;
+		unsigned long		io_ports_array[IDE_NR_PORTS];
+	};
+
 	int		irq;			/* our irq number */
 	ide_ack_intr_t	*ack_intr;		/* acknowledge interrupt */
 	hwif_chipset_t  chipset;
@@ -179,10 +183,10 @@ static inline void ide_std_init_ports(hw_regs_t *hw,
 {
 	unsigned int i;
 
-	for (i = IDE_DATA_OFFSET; i <= IDE_STATUS_OFFSET; i++)
-		hw->io_ports[i] = io_addr++;
+	for (i = 0; i <= 7; i++)
+		hw->io_ports_array[i] = io_addr++;
 
-	hw->io_ports[IDE_CONTROL_OFFSET] = ctl_addr;
+	hw->io_ports.ctl_addr = ctl_addr;
 }
 
 #include <asm/ide.h>
@@ -328,7 +332,6 @@ typedef struct ide_drive_s {
 	unsigned atapi_overlap	: 1;	/* ATAPI overlap (not supported) */
 	unsigned doorlocking	: 1;	/* for removable only: door lock/unlock works */
 	unsigned nodma		: 1;	/* disallow DMA */
-	unsigned autotune	: 2;	/* 0=default, 1=autotune, 2=noautotune */
 	unsigned remap_0_to_1	: 1;	/* 0=noremap, 1=remap 0->1 (for EZDrive) */
 	unsigned blocked        : 1;	/* 1=powermanagment told us not to do anything, so sleep nicely */
 	unsigned vdma		: 1;	/* 1=doing PIO over DMA 0=doing normal DMA */
@@ -424,6 +427,8 @@ struct ide_dma_ops {
 	void	(*dma_timeout)(struct ide_drive_s *);
 };
 
+struct ide_task_s;
+
 typedef struct hwif_s {
 	struct hwif_s *next;		/* for linked-list in ide_hwgroup_t */
 	struct hwif_s *mate;		/* other hwif from same PCI chip */
@@ -432,8 +437,8 @@ typedef struct hwif_s {
 
 	char name[6];			/* name of interface, eg. "ide0" */
 
-		/* task file registers for pata and sata */
-	unsigned long	io_ports[IDE_NR_PORTS];
+	struct ide_io_ports	io_ports;
+
 	unsigned long	sata_scr[SATA_NR_PORTS];
 
 	ide_drive_t	drives[MAX_DRIVES];	/* drive info */
@@ -464,24 +469,18 @@ typedef struct hwif_s {
 	const struct ide_port_ops	*port_ops;
 	const struct ide_dma_ops	*dma_ops;
 
-	void (*ata_input_data)(ide_drive_t *, void *, u32);
-	void (*ata_output_data)(ide_drive_t *, void *, u32);
+	void (*tf_load)(ide_drive_t *, struct ide_task_s *);
+	void (*tf_read)(ide_drive_t *, struct ide_task_s *);
 
-	void (*atapi_input_bytes)(ide_drive_t *, void *, u32);
-	void (*atapi_output_bytes)(ide_drive_t *, void *, u32);
+	void (*input_data)(ide_drive_t *, struct request *, void *, unsigned);
+	void (*output_data)(ide_drive_t *, struct request *, void *, unsigned);
 
 	void (*ide_dma_clear_irq)(ide_drive_t *drive);
 
 	void (*OUTB)(u8 addr, unsigned long port);
 	void (*OUTBSYNC)(ide_drive_t *drive, u8 addr, unsigned long port);
-	void (*OUTW)(u16 addr, unsigned long port);
-	void (*OUTSW)(unsigned long port, void *addr, u32 count);
-	void (*OUTSL)(unsigned long port, void *addr, u32 count);
 
 	u8  (*INB)(unsigned long port);
-	u16 (*INW)(unsigned long port);
-	void (*INSW)(unsigned long port, void *addr, u32 count);
-	void (*INSL)(unsigned long port, void *addr, u32 count);
 
 	/* dma physical region descriptor table (cpu view) */
 	unsigned int	*dmatable_cpu;
@@ -506,10 +505,7 @@ typedef struct hwif_s {
 
 	unsigned long	dma_base;	/* base addr for dma ports */
 	unsigned long	dma_command;	/* dma command register */
-	unsigned long	dma_vendor1;	/* dma vendor 1 register */
 	unsigned long	dma_status;	/* dma status register */
-	unsigned long	dma_vendor3;	/* dma vendor 3 register */
-	unsigned long	dma_prdtable;	/* actual prd table address */
 
 	unsigned long	config_data;	/* for use by chipset-specific code */
 	unsigned long	select_data;	/* for use by chipset-specific code */
@@ -520,7 +516,6 @@ typedef struct hwif_s {
 	unsigned	present    : 1;	/* this interface exists */
 	unsigned	serialized : 1;	/* serialized all channel operation */
 	unsigned	sharing_irq: 1;	/* 1 = sharing irq with another hwif */
-	unsigned	reset      : 1;	/* reset after probe */
 	unsigned	sg_mapped  : 1;	/* sg_table and sg_nents are ready */
 	unsigned	mmio       : 1; /* host uses MMIO */
 
@@ -545,7 +540,7 @@ typedef ide_startstop_t (ide_handler_t)(ide_drive_t *);
 typedef int (ide_expiry_t)(ide_drive_t *);
 
 /* used by ide-cd, ide-floppy, etc. */
-typedef void (xfer_func_t)(ide_drive_t *, void *, u32);
+typedef void (xfer_func_t)(ide_drive_t *, struct request *rq, void *, unsigned);
 
 typedef struct hwgroup_s {
 		/* irq handler, if active */
@@ -703,10 +698,6 @@ void ide_add_generic_settings(ide_drive_t *);
 read_proc_t proc_ide_read_capacity;
 read_proc_t proc_ide_read_geometry;
 
-#ifdef CONFIG_BLK_DEV_IDEPCI
-void ide_pci_create_host_proc(const char *, get_info_t *);
-#endif
-
 /*
  * Standard exit stuff:
  */
@@ -807,8 +798,14 @@ int generic_ide_ioctl(ide_drive_t *, struct file *, struct block_device *, unsig
 #ifndef _IDE_C
 extern	ide_hwif_t	ide_hwifs[];		/* master data repository */
 #endif
+extern int ide_noacpi;
+extern int ide_acpigtf;
+extern int ide_acpionboot;
 extern int noautodma;
 
+extern int ide_vlb_clk;
+extern int ide_pci_clk;
+
 ide_hwif_t *ide_find_port_slot(const struct ide_port_info *);
 
 static inline ide_hwif_t *ide_find_port(void)
@@ -825,6 +822,10 @@ extern void ide_set_handler (ide_drive_t *drive, ide_handler_t *handler, unsigne
 void ide_execute_command(ide_drive_t *, u8, ide_handler_t *, unsigned int,
 			 ide_expiry_t *);
 
+void ide_execute_pkt_cmd(ide_drive_t *);
+
+void ide_pad_transfer(ide_drive_t *, int, int);
+
 ide_startstop_t __ide_error(ide_drive_t *, struct request *, u8, u8);
 
 ide_startstop_t ide_error (ide_drive_t *drive, const char *msg, byte stat);
@@ -961,8 +962,7 @@ typedef struct ide_task_s {
 	void			*special;	/* valid_t generally */
 } ide_task_t;
 
-void ide_tf_load(ide_drive_t *, ide_task_t *);
-void ide_tf_read(ide_drive_t *, ide_task_t *);
+void ide_tf_dump(const char *, struct ide_taskfile *);
 
 extern void SELECT_DRIVE(ide_drive_t *);
 extern void SELECT_MASK(ide_drive_t *, int);
@@ -1068,8 +1068,8 @@ enum {
 	IDE_HFLAG_NO_DMA		= (1 << 14),
 	/* check if host is PCI IDE device before allowing DMA */
 	IDE_HFLAG_NO_AUTODMA		= (1 << 15),
-	/* don't autotune PIO */
-	IDE_HFLAG_NO_AUTOTUNE		= (1 << 16),
+	/* host uses MMIO */
+	IDE_HFLAG_MMIO			= (1 << 16),
 	/* host is CS5510/CS5520 */
 	IDE_HFLAG_CS5520		= IDE_HFLAG_VDMA,
 	/* no LBA48 */
@@ -1215,13 +1215,15 @@ static inline void ide_acpi_set_state(ide_hwif_t *hwif, int on) {}
 #endif
 
 void ide_remove_port_from_hwgroup(ide_hwif_t *);
-void ide_unregister(unsigned int);
+void ide_unregister(ide_hwif_t *);
 
 void ide_register_region(struct gendisk *);
 void ide_unregister_region(struct gendisk *);
 
 void ide_undecoded_slave(ide_drive_t *);
 
+void ide_port_apply_params(ide_hwif_t *);
+
 int ide_device_add_all(u8 *idx, const struct ide_port_info *);
 int ide_device_add(u8 idx[4], const struct ide_port_info *);
 int ide_legacy_device_add(const struct ide_port_info *, unsigned long);
@@ -1333,51 +1335,27 @@ static inline void ide_set_irq(ide_drive_t *drive, int on)
 {
 	ide_hwif_t *hwif = drive->hwif;
 
-	hwif->OUTB(drive->ctl | (on ? 0 : 2),
-		   hwif->io_ports[IDE_CONTROL_OFFSET]);
+	hwif->OUTB(drive->ctl | (on ? 0 : 2), hwif->io_ports.ctl_addr);
 }
 
 static inline u8 ide_read_status(ide_drive_t *drive)
 {
 	ide_hwif_t *hwif = drive->hwif;
 
-	return hwif->INB(hwif->io_ports[IDE_STATUS_OFFSET]);
+	return hwif->INB(hwif->io_ports.status_addr);
 }
 
 static inline u8 ide_read_altstatus(ide_drive_t *drive)
 {
 	ide_hwif_t *hwif = drive->hwif;
 
-	return hwif->INB(hwif->io_ports[IDE_CONTROL_OFFSET]);
+	return hwif->INB(hwif->io_ports.ctl_addr);
 }
 
 static inline u8 ide_read_error(ide_drive_t *drive)
 {
 	ide_hwif_t *hwif = drive->hwif;
 
-	return hwif->INB(hwif->io_ports[IDE_ERROR_OFFSET]);
+	return hwif->INB(hwif->io_ports.error_addr);
 }
-
-/*
- * Too bad. The drive wants to send us data which we are not ready to accept.
- * Just throw it away.
- */
-static inline void ide_atapi_discard_data(ide_drive_t *drive, unsigned bcount)
-{
-	ide_hwif_t *hwif = drive->hwif;
-
-	/* FIXME: use ->atapi_input_bytes */
-	while (bcount--)
-		(void)hwif->INB(hwif->io_ports[IDE_DATA_OFFSET]);
-}
-
-static inline void ide_atapi_write_zeros(ide_drive_t *drive, unsigned bcount)
-{
-	ide_hwif_t *hwif = drive->hwif;
-
-	/* FIXME: use ->atapi_output_bytes */
-	while (bcount--)
-		hwif->OUTB(0, hwif->io_ports[IDE_DATA_OFFSET]);
-}
-
 #endif /* _IDE_H */
diff --git a/trunk/include/linux/idr.h b/trunk/include/linux/idr.h
index 0edda411959c..9a2d762124de 100644
--- a/trunk/include/linux/idr.h
+++ b/trunk/include/linux/idr.h
@@ -14,6 +14,7 @@
 
 #include <linux/types.h>
 #include <linux/bitops.h>
+#include <linux/init.h>
 
 #if BITS_PER_LONG == 32
 # define IDR_BITS 5
@@ -115,4 +116,6 @@ void ida_remove(struct ida *ida, int id);
 void ida_destroy(struct ida *ida);
 void ida_init(struct ida *ida);
 
+void __init idr_init_cache(void);
+
 #endif /* __IDR_H__ */
diff --git a/trunk/include/linux/init.h b/trunk/include/linux/init.h
index fb58c0493cf2..21d658cdfa27 100644
--- a/trunk/include/linux/init.h
+++ b/trunk/include/linux/init.h
@@ -147,6 +147,8 @@ extern unsigned int reset_devices;
 void setup_arch(char **);
 void prepare_namespace(void);
 
+extern void (*late_time_init)(void);
+
 #endif
   
 #ifndef MODULE
diff --git a/trunk/include/linux/init_task.h b/trunk/include/linux/init_task.h
index 37a6f5bc4a92..bf6b8a61f8db 100644
--- a/trunk/include/linux/init_task.h
+++ b/trunk/include/linux/init_task.h
@@ -9,6 +9,7 @@
 #include <linux/ipc.h>
 #include <linux/pid_namespace.h>
 #include <linux/user_namespace.h>
+#include <linux/securebits.h>
 #include <net/net_namespace.h>
 
 #define INIT_FDTABLE \
@@ -172,7 +173,7 @@ extern struct group_info init_groups;
 	.cap_inheritable = CAP_INIT_INH_SET,				\
 	.cap_permitted	= CAP_FULL_SET,					\
 	.cap_bset 	= CAP_INIT_BSET,				\
-	.keep_capabilities = 0,						\
+	.securebits     = SECUREBITS_DEFAULT,				\
 	.user		= INIT_USER,					\
 	.comm		= "swapper",					\
 	.thread		= INIT_THREAD,					\
diff --git a/trunk/include/linux/interrupt.h b/trunk/include/linux/interrupt.h
index b5fef13148bd..f1fc7470d26c 100644
--- a/trunk/include/linux/interrupt.h
+++ b/trunk/include/linux/interrupt.h
@@ -289,6 +289,7 @@ struct softirq_action
 };
 
 asmlinkage void do_softirq(void);
+asmlinkage void __do_softirq(void);
 extern void open_softirq(int nr, void (*action)(struct softirq_action*), void *data);
 extern void softirq_init(void);
 #define __raise_softirq_irqoff(nr) do { or_softirq_pending(1UL << (nr)); } while (0)
diff --git a/trunk/include/linux/ipc_namespace.h b/trunk/include/linux/ipc_namespace.h
index e4451d1da753..ea6c18a8b0d4 100644
--- a/trunk/include/linux/ipc_namespace.h
+++ b/trunk/include/linux/ipc_namespace.h
@@ -4,6 +4,17 @@
 #include <linux/err.h>
 #include <linux/idr.h>
 #include <linux/rwsem.h>
+#include <linux/notifier.h>
+
+/*
+ * ipc namespace events
+ */
+#define IPCNS_MEMCHANGED   0x00000001   /* Notify lowmem size changed */
+#define IPCNS_CREATED  0x00000002   /* Notify new ipc namespace created */
+#define IPCNS_REMOVED  0x00000003   /* Notify ipc namespace removed */
+
+#define IPCNS_CALLBACK_PRI 0
+
 
 struct ipc_ids {
 	int in_use;
@@ -30,15 +41,24 @@ struct ipc_namespace {
 	size_t		shm_ctlall;
 	int		shm_ctlmni;
 	int		shm_tot;
+
+	struct notifier_block ipcns_nb;
 };
 
 extern struct ipc_namespace init_ipc_ns;
+extern atomic_t nr_ipc_ns;
 
 #ifdef CONFIG_SYSVIPC
 #define INIT_IPC_NS(ns)		.ns		= &init_ipc_ns,
-#else
+
+extern int register_ipcns_notifier(struct ipc_namespace *);
+extern int cond_register_ipcns_notifier(struct ipc_namespace *);
+extern int unregister_ipcns_notifier(struct ipc_namespace *);
+extern int ipcns_notify(unsigned long);
+
+#else /* CONFIG_SYSVIPC */
 #define INIT_IPC_NS(ns)
-#endif
+#endif /* CONFIG_SYSVIPC */
 
 #if defined(CONFIG_SYSVIPC) && defined(CONFIG_IPC_NS)
 extern void free_ipc_ns(struct kref *kref);
diff --git a/trunk/include/linux/ipmi.h b/trunk/include/linux/ipmi.h
index c5bd28b69aec..7ebdb4fb4e54 100644
--- a/trunk/include/linux/ipmi.h
+++ b/trunk/include/linux/ipmi.h
@@ -64,7 +64,7 @@
  * applications and another for userland applications.  The
  * capabilities are basically the same for both interface, although
  * the interfaces are somewhat different.  The stuff in the
- * #ifdef KERNEL below is the in-kernel interface.  The userland
+ * #ifdef __KERNEL__ below is the in-kernel interface.  The userland
  * interface is defined later in the file.  */
 
 
@@ -75,8 +75,7 @@
  * work for sockets.
  */
 #define IPMI_MAX_ADDR_SIZE 32
-struct ipmi_addr
-{
+struct ipmi_addr {
 	 /* Try to take these from the "Channel Medium Type" table
 	    in section 6.5 of the IPMI 1.5 manual. */
 	int   addr_type;
@@ -90,8 +89,7 @@ struct ipmi_addr
  * 0), or IPMC_BMC_CHANNEL if communicating directly with the BMC.
  */
 #define IPMI_SYSTEM_INTERFACE_ADDR_TYPE	0x0c
-struct ipmi_system_interface_addr
-{
+struct ipmi_system_interface_addr {
 	int           addr_type;
 	short         channel;
 	unsigned char lun;
@@ -100,10 +98,9 @@ struct ipmi_system_interface_addr
 /* An IPMB Address. */
 #define IPMI_IPMB_ADDR_TYPE		0x01
 /* Used for broadcast get device id as described in section 17.9 of the
-   IPMI 1.5 manual. */ 
+   IPMI 1.5 manual. */
 #define IPMI_IPMB_BROADCAST_ADDR_TYPE	0x41
-struct ipmi_ipmb_addr
-{
+struct ipmi_ipmb_addr {
 	int           addr_type;
 	short         channel;
 	unsigned char slave_addr;
@@ -128,8 +125,7 @@ struct ipmi_ipmb_addr
  * message is a little weird, but this is required.
  */
 #define IPMI_LAN_ADDR_TYPE		0x04
-struct ipmi_lan_addr
-{
+struct ipmi_lan_addr {
 	int           addr_type;
 	short         channel;
 	unsigned char privilege;
@@ -162,16 +158,14 @@ struct ipmi_lan_addr
  * byte of data in the response (as the spec shows the messages laid
  * out).
  */
-struct ipmi_msg
-{
+struct ipmi_msg {
 	unsigned char  netfn;
 	unsigned char  cmd;
 	unsigned short data_len;
 	unsigned char  __user *data;
 };
 
-struct kernel_ipmi_msg
-{
+struct kernel_ipmi_msg {
 	unsigned char  netfn;
 	unsigned char  cmd;
 	unsigned short data_len;
@@ -239,12 +233,11 @@ typedef struct ipmi_user *ipmi_user_t;
  * used after the message is delivered, so the upper layer may use the
  * link to build a linked list, if it likes.
  */
-struct ipmi_recv_msg
-{
+struct ipmi_recv_msg {
 	struct list_head link;
 
 	/* The type of message as defined in the "Receive Types"
-           defines above. */
+	   defines above. */
 	int              recv_type;
 
 	ipmi_user_t      user;
@@ -271,9 +264,8 @@ struct ipmi_recv_msg
 /* Allocate and free the receive message. */
 void ipmi_free_recv_msg(struct ipmi_recv_msg *msg);
 
-struct ipmi_user_hndl
-{
-        /* Routine type to call when a message needs to be routed to
+struct ipmi_user_hndl {
+	/* Routine type to call when a message needs to be routed to
 	   the upper layer.  This will be called with some locks held,
 	   the only IPMI routines that can be called are ipmi_request
 	   and the alloc/free operations.  The handler_data is the
@@ -368,9 +360,8 @@ int ipmi_request_supply_msgs(ipmi_user_t          user,
  * Poll the IPMI interface for the user.  This causes the IPMI code to
  * do an immediate check for information from the driver and handle
  * anything that is immediately pending.  This will not block in any
- * way.  This is useful if you need to implement polling from the user
- * for things like modifying the watchdog timeout when a panic occurs
- * or disabling the watchdog timer on a reboot.
+ * way.  This is useful if you need to spin waiting for something to
+ * happen in the IPMI driver.
  */
 void ipmi_poll_interface(ipmi_user_t user);
 
@@ -421,12 +412,6 @@ int ipmi_unregister_for_cmd(ipmi_user_t   user,
 int ipmi_get_maintenance_mode(ipmi_user_t user);
 int ipmi_set_maintenance_mode(ipmi_user_t user, int mode);
 
-/*
- * Allow run-to-completion mode to be set for the interface of
- * a specific user.
- */
-void ipmi_user_set_run_to_completion(ipmi_user_t user, int val);
-
 /*
  * When the user is created, it will not receive IPMI events by
  * default.  The user must set this to TRUE to get incoming events.
@@ -440,8 +425,7 @@ int ipmi_set_gets_events(ipmi_user_t user, int val);
  * every existing interface when a new watcher is registered with
  * ipmi_smi_watcher_register().
  */
-struct ipmi_smi_watcher
-{
+struct ipmi_smi_watcher {
 	struct list_head link;
 
 	/* You must set the owner to the current module, if you are in
@@ -512,8 +496,7 @@ int ipmi_validate_addr(struct ipmi_addr *addr, int len);
 
 
 /* Messages sent to the interface are this format. */
-struct ipmi_req
-{
+struct ipmi_req {
 	unsigned char __user *addr; /* Address to send the message to. */
 	unsigned int  addr_len;
 
@@ -538,12 +521,11 @@ struct ipmi_req
 
 /* Messages sent to the interface with timing parameters are this
    format. */
-struct ipmi_req_settime
-{
+struct ipmi_req_settime {
 	struct ipmi_req req;
 
 	/* See ipmi_request_settime() above for details on these
-           values. */
+	   values. */
 	int          retries;
 	unsigned int retry_time_ms;
 };
@@ -560,8 +542,7 @@ struct ipmi_req_settime
 					     struct ipmi_req_settime)
 
 /* Messages received from the interface are this format. */
-struct ipmi_recv
-{
+struct ipmi_recv {
 	int     recv_type; /* Is this a command, response or an
 			      asyncronous event. */
 
@@ -607,13 +588,12 @@ struct ipmi_recv
 					      struct ipmi_recv)
 
 /* Register to get commands from other entities on this interface. */
-struct ipmi_cmdspec
-{
+struct ipmi_cmdspec {
 	unsigned char netfn;
 	unsigned char cmd;
 };
 
-/* 
+/*
  * Register to receive a specific command.  error values:
  *   - EFAULT - an address supplied was invalid.
  *   - EBUSY - The netfn/cmd supplied was already in use.
@@ -636,8 +616,7 @@ struct ipmi_cmdspec
  * else.  The chans field is a bitmask, (1 << channel) for each channel.
  * It may be IPMI_CHAN_ALL for all channels.
  */
-struct ipmi_cmdspec_chans
-{
+struct ipmi_cmdspec_chans {
 	unsigned int netfn;
 	unsigned int cmd;
 	unsigned int chans;
@@ -659,7 +638,7 @@ struct ipmi_cmdspec_chans
 #define IPMICTL_UNREGISTER_FOR_CMD_CHANS _IOR(IPMI_IOC_MAGIC, 29,	\
 					     struct ipmi_cmdspec_chans)
 
-/* 
+/*
  * Set whether this interface receives events.  Note that the first
  * user registered for events will get all pending events for the
  * interface.  error values:
@@ -675,15 +654,18 @@ struct ipmi_cmdspec_chans
  * things it takes to determine your address (if not the BMC) and set
  * it for everyone else.  You should probably leave the LUN alone.
  */
-struct ipmi_channel_lun_address_set
-{
+struct ipmi_channel_lun_address_set {
 	unsigned short channel;
 	unsigned char  value;
 };
-#define IPMICTL_SET_MY_CHANNEL_ADDRESS_CMD _IOR(IPMI_IOC_MAGIC, 24, struct ipmi_channel_lun_address_set)
-#define IPMICTL_GET_MY_CHANNEL_ADDRESS_CMD _IOR(IPMI_IOC_MAGIC, 25, struct ipmi_channel_lun_address_set)
-#define IPMICTL_SET_MY_CHANNEL_LUN_CMD	   _IOR(IPMI_IOC_MAGIC, 26, struct ipmi_channel_lun_address_set)
-#define IPMICTL_GET_MY_CHANNEL_LUN_CMD	   _IOR(IPMI_IOC_MAGIC, 27, struct ipmi_channel_lun_address_set)
+#define IPMICTL_SET_MY_CHANNEL_ADDRESS_CMD \
+	_IOR(IPMI_IOC_MAGIC, 24, struct ipmi_channel_lun_address_set)
+#define IPMICTL_GET_MY_CHANNEL_ADDRESS_CMD \
+	_IOR(IPMI_IOC_MAGIC, 25, struct ipmi_channel_lun_address_set)
+#define IPMICTL_SET_MY_CHANNEL_LUN_CMD \
+	_IOR(IPMI_IOC_MAGIC, 26, struct ipmi_channel_lun_address_set)
+#define IPMICTL_GET_MY_CHANNEL_LUN_CMD \
+	_IOR(IPMI_IOC_MAGIC, 27, struct ipmi_channel_lun_address_set)
 /* Legacy interfaces, these only set IPMB 0. */
 #define IPMICTL_SET_MY_ADDRESS_CMD	_IOR(IPMI_IOC_MAGIC, 17, unsigned int)
 #define IPMICTL_GET_MY_ADDRESS_CMD	_IOR(IPMI_IOC_MAGIC, 18, unsigned int)
@@ -694,8 +676,7 @@ struct ipmi_channel_lun_address_set
  * Get/set the default timing values for an interface.  You shouldn't
  * generally mess with these.
  */
-struct ipmi_timing_parms
-{
+struct ipmi_timing_parms {
 	int          retries;
 	unsigned int retry_time_ms;
 };
diff --git a/trunk/include/linux/ipmi_smi.h b/trunk/include/linux/ipmi_smi.h
index 6e8cec503380..62b73668b602 100644
--- a/trunk/include/linux/ipmi_smi.h
+++ b/trunk/include/linux/ipmi_smi.h
@@ -60,8 +60,7 @@ typedef struct ipmi_smi *ipmi_smi_t;
  * asynchronous data and messages and request them from the
  * interface.
  */
-struct ipmi_smi_msg
-{
+struct ipmi_smi_msg {
 	struct list_head link;
 
 	long    msgid;
@@ -74,12 +73,11 @@ struct ipmi_smi_msg
 	unsigned char rsp[IPMI_MAX_MSG_LENGTH];
 
 	/* Will be called when the system is done with the message
-           (presumably to free it). */
+	   (presumably to free it). */
 	void (*done)(struct ipmi_smi_msg *msg);
 };
 
-struct ipmi_smi_handlers
-{
+struct ipmi_smi_handlers {
 	struct module *owner;
 
 	/* The low-level interface cannot start sending messages to
@@ -231,7 +229,7 @@ static inline void ipmi_free_smi_msg(struct ipmi_smi_msg *msg)
    directory for this interface.  Note that the entry will
    automatically be dstroyed when the interface is destroyed. */
 int ipmi_smi_add_proc_entry(ipmi_smi_t smi, char *name,
-			    read_proc_t *read_proc, write_proc_t *write_proc,
+			    read_proc_t *read_proc,
 			    void *data, struct module *owner);
 
 #endif /* __LINUX_IPMI_SMI_H */
diff --git a/trunk/include/linux/kbuild.h b/trunk/include/linux/kbuild.h
new file mode 100644
index 000000000000..22a72198c14b
--- /dev/null
+++ b/trunk/include/linux/kbuild.h
@@ -0,0 +1,15 @@
+#ifndef __LINUX_KBUILD_H
+#define __LINUX_KBUILD_H
+
+#define DEFINE(sym, val) \
+        asm volatile("\n->" #sym " %0 " #val : : "i" (val))
+
+#define BLANK() asm volatile("\n->" : : )
+
+#define OFFSET(sym, str, mem) \
+	DEFINE(sym, offsetof(struct str, mem))
+
+#define COMMENT(x) \
+	asm volatile("\n->#" x)
+
+#endif
diff --git a/trunk/include/linux/kernel.h b/trunk/include/linux/kernel.h
index cd6d02cf854d..53839ba265ec 100644
--- a/trunk/include/linux/kernel.h
+++ b/trunk/include/linux/kernel.h
@@ -20,6 +20,9 @@
 extern const char linux_banner[];
 extern const char linux_proc_banner[];
 
+#define USHORT_MAX	((u16)(~0U))
+#define SHORT_MAX	((s16)(USHORT_MAX>>1))
+#define SHORT_MIN	(-SHORT_MAX - 1)
 #define INT_MAX		((int)(~0U>>1))
 #define INT_MIN		(-INT_MAX - 1)
 #define UINT_MAX	(~0U)
@@ -188,6 +191,7 @@ extern int log_buf_copy(char *dest, int idx, int len);
 extern int printk_ratelimit_jiffies;
 extern int printk_ratelimit_burst;
 extern int printk_ratelimit(void);
+extern int __ratelimit(int ratelimit_jiffies, int ratelimit_burst);
 extern int __printk_ratelimit(int ratelimit_jiffies, int ratelimit_burst);
 extern bool printk_timed_ratelimit(unsigned long *caller_jiffies,
 				   unsigned int interval_msec);
@@ -255,6 +259,7 @@ extern enum system_states {
 #define TAINT_USER			(1<<6)
 #define TAINT_DIE			(1<<7)
 #define TAINT_OVERRIDDEN_ACPI_TABLE	(1<<8)
+#define TAINT_WARN			(1<<9)
 
 extern void dump_stack(void) __cold;
 
diff --git a/trunk/include/linux/key.h b/trunk/include/linux/key.h
index a70b8a8f2005..c45c962d1cc5 100644
--- a/trunk/include/linux/key.h
+++ b/trunk/include/linux/key.h
@@ -19,6 +19,7 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <linux/rcupdate.h>
+#include <linux/sysctl.h>
 #include <asm/atomic.h>
 
 #ifdef __KERNEL__
@@ -67,6 +68,8 @@ struct key;
 #define KEY_OTH_SETATTR	0x00000020
 #define KEY_OTH_ALL	0x0000003f
 
+#define KEY_PERM_UNDEF	0xffffffff
+
 struct seq_file;
 struct user_struct;
 struct signal_struct;
@@ -208,16 +211,19 @@ extern struct key *request_key(struct key_type *type,
 
 extern struct key *request_key_with_auxdata(struct key_type *type,
 					    const char *description,
-					    const char *callout_info,
+					    const void *callout_info,
+					    size_t callout_len,
 					    void *aux);
 
 extern struct key *request_key_async(struct key_type *type,
 				     const char *description,
-				     const char *callout_info);
+				     const void *callout_info,
+				     size_t callout_len);
 
 extern struct key *request_key_async_with_auxdata(struct key_type *type,
 						  const char *description,
-						  const char *callout_info,
+						  const void *callout_info,
+						  size_t callout_len,
 						  void *aux);
 
 extern int wait_for_key_construction(struct key *key, bool intr);
@@ -229,6 +235,7 @@ extern key_ref_t key_create_or_update(key_ref_t keyring,
 				      const char *description,
 				      const void *payload,
 				      size_t plen,
+				      key_perm_t perm,
 				      unsigned long flags);
 
 extern int key_update(key_ref_t key,
@@ -257,14 +264,18 @@ extern int keyring_add_key(struct key *keyring,
 
 extern struct key *key_lookup(key_serial_t id);
 
-#define key_serial(key) ((key) ? (key)->serial : 0)
+static inline key_serial_t key_serial(struct key *key)
+{
+	return key ? key->serial : 0;
+}
+
+#ifdef CONFIG_SYSCTL
+extern ctl_table key_sysctls[];
+#endif
 
 /*
  * the userspace interface
  */
-extern struct key root_user_keyring, root_session_keyring;
-extern int alloc_uid_keyring(struct user_struct *user,
-			     struct task_struct *ctx);
 extern void switch_uid_keyring(struct user_struct *new_user);
 extern int copy_keys(unsigned long clone_flags, struct task_struct *tsk);
 extern int copy_thread_group_keys(struct task_struct *tsk);
@@ -293,7 +304,6 @@ extern void key_init(void);
 #define make_key_ref(k, p)			({ NULL; })
 #define key_ref_to_ptr(k)		({ NULL; })
 #define is_key_possessed(k)		0
-#define alloc_uid_keyring(u,c)		0
 #define switch_uid_keyring(u)		do { } while(0)
 #define __install_session_keyring(t, k)	({ NULL; })
 #define copy_keys(f,t)			0
@@ -306,10 +316,6 @@ extern void key_init(void);
 #define key_fsgid_changed(t)		do { } while(0)
 #define key_init()			do { } while(0)
 
-/* Initial keyrings */
-extern struct key root_user_keyring;
-extern struct key root_session_keyring;
-
 #endif /* CONFIG_KEYS */
 #endif /* __KERNEL__ */
 #endif /* _LINUX_KEY_H */
diff --git a/trunk/include/linux/keyctl.h b/trunk/include/linux/keyctl.h
index 3365945640c9..656ee6b77a4a 100644
--- a/trunk/include/linux/keyctl.h
+++ b/trunk/include/linux/keyctl.h
@@ -49,5 +49,6 @@
 #define KEYCTL_SET_REQKEY_KEYRING	14	/* set default request-key keyring */
 #define KEYCTL_SET_TIMEOUT		15	/* set key timeout */
 #define KEYCTL_ASSUME_AUTHORITY		16	/* assume request_key() authorisation */
+#define KEYCTL_GET_SECURITY		17	/* get key security label */
 
 #endif /*  _LINUX_KEYCTL_H */
diff --git a/trunk/include/linux/kprobes.h b/trunk/include/linux/kprobes.h
index 0f28486f6360..1036631ff4fa 100644
--- a/trunk/include/linux/kprobes.h
+++ b/trunk/include/linux/kprobes.h
@@ -173,6 +173,13 @@ struct kretprobe_blackpoint {
 	const char *name;
 	void *addr;
 };
+
+struct kprobe_blackpoint {
+	const char *name;
+	unsigned long start_addr;
+	unsigned long range;
+};
+
 extern struct kretprobe_blackpoint kretprobe_blacklist[];
 
 static inline void kretprobe_assert(struct kretprobe_instance *ri,
@@ -227,15 +234,21 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void)
 
 int register_kprobe(struct kprobe *p);
 void unregister_kprobe(struct kprobe *p);
+int register_kprobes(struct kprobe **kps, int num);
+void unregister_kprobes(struct kprobe **kps, int num);
 int setjmp_pre_handler(struct kprobe *, struct pt_regs *);
 int longjmp_break_handler(struct kprobe *, struct pt_regs *);
 int register_jprobe(struct jprobe *p);
 void unregister_jprobe(struct jprobe *p);
+int register_jprobes(struct jprobe **jps, int num);
+void unregister_jprobes(struct jprobe **jps, int num);
 void jprobe_return(void);
 unsigned long arch_deref_entry_point(void *);
 
 int register_kretprobe(struct kretprobe *rp);
 void unregister_kretprobe(struct kretprobe *rp);
+int register_kretprobes(struct kretprobe **rps, int num);
+void unregister_kretprobes(struct kretprobe **rps, int num);
 
 void kprobe_flush_task(struct task_struct *tk);
 void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);
@@ -254,16 +267,30 @@ static inline int register_kprobe(struct kprobe *p)
 {
 	return -ENOSYS;
 }
+static inline int register_kprobes(struct kprobe **kps, int num)
+{
+	return -ENOSYS;
+}
 static inline void unregister_kprobe(struct kprobe *p)
 {
 }
+static inline void unregister_kprobes(struct kprobe **kps, int num)
+{
+}
 static inline int register_jprobe(struct jprobe *p)
 {
 	return -ENOSYS;
 }
+static inline int register_jprobes(struct jprobe **jps, int num)
+{
+	return -ENOSYS;
+}
 static inline void unregister_jprobe(struct jprobe *p)
 {
 }
+static inline void unregister_jprobes(struct jprobe **jps, int num)
+{
+}
 static inline void jprobe_return(void)
 {
 }
@@ -271,9 +298,16 @@ static inline int register_kretprobe(struct kretprobe *rp)
 {
 	return -ENOSYS;
 }
+static inline int register_kretprobes(struct kretprobe **rps, int num)
+{
+	return -ENOSYS;
+}
 static inline void unregister_kretprobe(struct kretprobe *rp)
 {
 }
+static inline void unregister_kretprobes(struct kretprobe **rps, int num)
+{
+}
 static inline void kprobe_flush_task(struct task_struct *tk)
 {
 }
diff --git a/trunk/include/linux/kvm.h b/trunk/include/linux/kvm.h
index c1ec04fd000d..a281afeddfbb 100644
--- a/trunk/include/linux/kvm.h
+++ b/trunk/include/linux/kvm.h
@@ -8,11 +8,18 @@
  */
 
 #include <asm/types.h>
+#include <linux/compiler.h>
 #include <linux/ioctl.h>
 #include <asm/kvm.h>
 
 #define KVM_API_VERSION 12
 
+/* for KVM_TRACE_ENABLE */
+struct kvm_user_trace_setup {
+	__u32 buf_size; /* sub_buffer size of each per-cpu */
+	__u32 buf_nr; /* the number of sub_buffers of each per-cpu */
+};
+
 /* for KVM_CREATE_MEMORY_REGION */
 struct kvm_memory_region {
 	__u32 slot;
@@ -73,6 +80,9 @@ struct kvm_irqchip {
 #define KVM_EXIT_INTR             10
 #define KVM_EXIT_SET_TPR          11
 #define KVM_EXIT_TPR_ACCESS       12
+#define KVM_EXIT_S390_SIEIC       13
+#define KVM_EXIT_S390_RESET       14
+#define KVM_EXIT_DCR              15
 
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
@@ -137,6 +147,27 @@ struct kvm_run {
 			__u32 is_write;
 			__u32 pad;
 		} tpr_access;
+		/* KVM_EXIT_S390_SIEIC */
+		struct {
+			__u8 icptcode;
+			__u64 mask; /* psw upper half */
+			__u64 addr; /* psw lower half */
+			__u16 ipa;
+			__u32 ipb;
+		} s390_sieic;
+		/* KVM_EXIT_S390_RESET */
+#define KVM_S390_RESET_POR       1
+#define KVM_S390_RESET_CLEAR     2
+#define KVM_S390_RESET_SUBSYSTEM 4
+#define KVM_S390_RESET_CPU_INIT  8
+#define KVM_S390_RESET_IPL       16
+		__u64 s390_reset_flags;
+		/* KVM_EXIT_DCR */
+		struct {
+			__u32 dcrn;
+			__u32 data;
+			__u8  is_write;
+		} dcr;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -204,6 +235,74 @@ struct kvm_vapic_addr {
 	__u64 vapic_addr;
 };
 
+/* for KVM_SET_MPSTATE */
+
+#define KVM_MP_STATE_RUNNABLE          0
+#define KVM_MP_STATE_UNINITIALIZED     1
+#define KVM_MP_STATE_INIT_RECEIVED     2
+#define KVM_MP_STATE_HALTED            3
+#define KVM_MP_STATE_SIPI_RECEIVED     4
+
+struct kvm_mp_state {
+	__u32 mp_state;
+};
+
+struct kvm_s390_psw {
+	__u64 mask;
+	__u64 addr;
+};
+
+/* valid values for type in kvm_s390_interrupt */
+#define KVM_S390_SIGP_STOP		0xfffe0000u
+#define KVM_S390_PROGRAM_INT		0xfffe0001u
+#define KVM_S390_SIGP_SET_PREFIX	0xfffe0002u
+#define KVM_S390_RESTART		0xfffe0003u
+#define KVM_S390_INT_VIRTIO		0xffff2603u
+#define KVM_S390_INT_SERVICE		0xffff2401u
+#define KVM_S390_INT_EMERGENCY		0xffff1201u
+
+struct kvm_s390_interrupt {
+	__u32 type;
+	__u32 parm;
+	__u64 parm64;
+};
+
+#define KVM_TRC_SHIFT           16
+/*
+ * kvm trace categories
+ */
+#define KVM_TRC_ENTRYEXIT       (1 << KVM_TRC_SHIFT)
+#define KVM_TRC_HANDLER         (1 << (KVM_TRC_SHIFT + 1)) /* only 12 bits */
+
+/*
+ * kvm trace action
+ */
+#define KVM_TRC_VMENTRY         (KVM_TRC_ENTRYEXIT + 0x01)
+#define KVM_TRC_VMEXIT          (KVM_TRC_ENTRYEXIT + 0x02)
+#define KVM_TRC_PAGE_FAULT      (KVM_TRC_HANDLER + 0x01)
+
+#define KVM_TRC_HEAD_SIZE       12
+#define KVM_TRC_CYCLE_SIZE      8
+#define KVM_TRC_EXTRA_MAX       7
+
+/* This structure represents a single trace buffer record. */
+struct kvm_trace_rec {
+	__u32 event:28;
+	__u32 extra_u32:3;
+	__u32 cycle_in:1;
+	__u32 pid;
+	__u32 vcpu_id;
+	union {
+		struct {
+			__u32 cycle_lo, cycle_hi;
+			__u32 extra_u32[KVM_TRC_EXTRA_MAX];
+		} cycle;
+		struct {
+			__u32 extra_u32[KVM_TRC_EXTRA_MAX];
+		} nocycle;
+	} u;
+};
+
 #define KVMIO 0xAE
 
 /*
@@ -212,6 +311,8 @@ struct kvm_vapic_addr {
 #define KVM_GET_API_VERSION       _IO(KVMIO,   0x00)
 #define KVM_CREATE_VM             _IO(KVMIO,   0x01) /* returns a VM fd */
 #define KVM_GET_MSR_INDEX_LIST    _IOWR(KVMIO, 0x02, struct kvm_msr_list)
+
+#define KVM_S390_ENABLE_SIE       _IO(KVMIO,   0x06)
 /*
  * Check if a kvm extension is available.  Argument is extension number,
  * return is 1 (yes) or 0 (no, sorry).
@@ -222,7 +323,12 @@ struct kvm_vapic_addr {
  */
 #define KVM_GET_VCPU_MMAP_SIZE    _IO(KVMIO,   0x04) /* in bytes */
 #define KVM_GET_SUPPORTED_CPUID   _IOWR(KVMIO, 0x05, struct kvm_cpuid2)
-
+/*
+ * ioctls for kvm trace
+ */
+#define KVM_TRACE_ENABLE          _IOW(KVMIO, 0x06, struct kvm_user_trace_setup)
+#define KVM_TRACE_PAUSE           _IO(KVMIO,  0x07)
+#define KVM_TRACE_DISABLE         _IO(KVMIO,  0x08)
 /*
  * Extension capability list.
  */
@@ -233,6 +339,13 @@ struct kvm_vapic_addr {
 #define KVM_CAP_SET_TSS_ADDR 4
 #define KVM_CAP_VAPIC 6
 #define KVM_CAP_EXT_CPUID 7
+#define KVM_CAP_CLOCKSOURCE 8
+#define KVM_CAP_NR_VCPUS 9       /* returns max vcpus per vm */
+#define KVM_CAP_NR_MEMSLOTS 10   /* returns max memory slots per vm */
+#define KVM_CAP_PIT 11
+#define KVM_CAP_NOP_IO_DELAY 12
+#define KVM_CAP_PV_MMU 13
+#define KVM_CAP_MP_STATE 14
 
 /*
  * ioctls for VM fds
@@ -255,6 +368,9 @@ struct kvm_vapic_addr {
 #define KVM_IRQ_LINE		  _IOW(KVMIO, 0x61, struct kvm_irq_level)
 #define KVM_GET_IRQCHIP		  _IOWR(KVMIO, 0x62, struct kvm_irqchip)
 #define KVM_SET_IRQCHIP		  _IOR(KVMIO,  0x63, struct kvm_irqchip)
+#define KVM_CREATE_PIT		  _IO(KVMIO,  0x64)
+#define KVM_GET_PIT		  _IOWR(KVMIO, 0x65, struct kvm_pit_state)
+#define KVM_SET_PIT		  _IOR(KVMIO,  0x66, struct kvm_pit_state)
 
 /*
  * ioctls for vcpu fds
@@ -281,5 +397,17 @@ struct kvm_vapic_addr {
 #define KVM_TPR_ACCESS_REPORTING  _IOWR(KVMIO,  0x92, struct kvm_tpr_access_ctl)
 /* Available with KVM_CAP_VAPIC */
 #define KVM_SET_VAPIC_ADDR        _IOW(KVMIO,  0x93, struct kvm_vapic_addr)
+/* valid for virtual machine (for floating interrupt)_and_ vcpu */
+#define KVM_S390_INTERRUPT        _IOW(KVMIO,  0x94, struct kvm_s390_interrupt)
+/* store status for s390 */
+#define KVM_S390_STORE_STATUS_NOADDR    (-1ul)
+#define KVM_S390_STORE_STATUS_PREFIXED  (-2ul)
+#define KVM_S390_STORE_STATUS	  _IOW(KVMIO,  0x95, unsigned long)
+/* initial ipl psw for s390 */
+#define KVM_S390_SET_INITIAL_PSW  _IOW(KVMIO,  0x96, struct kvm_s390_psw)
+/* initial reset for s390 */
+#define KVM_S390_INITIAL_RESET    _IO(KVMIO,  0x97)
+#define KVM_GET_MP_STATE          _IOR(KVMIO,  0x98, struct kvm_mp_state)
+#define KVM_SET_MP_STATE          _IOW(KVMIO,  0x99, struct kvm_mp_state)
 
 #endif
diff --git a/trunk/include/linux/kvm_host.h b/trunk/include/linux/kvm_host.h
index 928b0d59e9ba..398978972b7a 100644
--- a/trunk/include/linux/kvm_host.h
+++ b/trunk/include/linux/kvm_host.h
@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/preempt.h>
+#include <linux/marker.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -24,29 +25,18 @@
 
 #include <asm/kvm_host.h>
 
-#define KVM_MAX_VCPUS 4
-#define KVM_MEMORY_SLOTS 8
-/* memory slots that does not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 4
-
-#define KVM_PIO_PAGE_OFFSET 1
-
 /*
  * vcpu->requests bit members
  */
 #define KVM_REQ_TLB_FLUSH          0
 #define KVM_REQ_MIGRATE_TIMER      1
 #define KVM_REQ_REPORT_TPR_ACCESS  2
+#define KVM_REQ_MMU_RELOAD         3
+#define KVM_REQ_TRIPLE_FAULT       4
 
 struct kvm_vcpu;
 extern struct kmem_cache *kvm_vcpu_cache;
 
-struct kvm_guest_debug {
-	int enabled;
-	unsigned long bp[4];
-	int singlestep;
-};
-
 /*
  * It would be nice to use something smarter than a linear search, TBD...
  * Thankfully we dont expect many devices to register (famous last words :),
@@ -67,7 +57,9 @@ void kvm_io_bus_register_dev(struct kvm_io_bus *bus,
 
 struct kvm_vcpu {
 	struct kvm *kvm;
+#ifdef CONFIG_PREEMPT_NOTIFIERS
 	struct preempt_notifier preempt_notifier;
+#endif
 	int vcpu_id;
 	struct mutex mutex;
 	int   cpu;
@@ -100,6 +92,10 @@ struct kvm_memory_slot {
 	unsigned long flags;
 	unsigned long *rmap;
 	unsigned long *dirty_bitmap;
+	struct {
+		unsigned long rmap_pde;
+		int write_count;
+	} *lpage_info;
 	unsigned long userspace_addr;
 	int user_alloc;
 };
@@ -114,11 +110,11 @@ struct kvm {
 					KVM_PRIVATE_MEM_SLOTS];
 	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
 	struct list_head vm_list;
-	struct file *filp;
 	struct kvm_io_bus mmio_bus;
 	struct kvm_io_bus pio_bus;
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
+	atomic_t users_count;
 };
 
 /* The guest did something we don't support. */
@@ -145,14 +141,19 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 		  struct module *module);
 void kvm_exit(void);
 
+void kvm_get_kvm(struct kvm *kvm);
+void kvm_put_kvm(struct kvm *kvm);
+
 #define HPA_MSB ((sizeof(hpa_t) * 8) - 1)
 #define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB)
 static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; }
 struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva);
 
 extern struct page *bad_page;
+extern pfn_t bad_pfn;
 
 int is_error_page(struct page *page);
+int is_error_pfn(pfn_t pfn);
 int kvm_is_error_hva(unsigned long addr);
 int kvm_set_memory_region(struct kvm *kvm,
 			  struct kvm_userspace_memory_region *mem,
@@ -166,8 +167,19 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 				int user_alloc);
 gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn);
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
+unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
 void kvm_release_page_clean(struct page *page);
 void kvm_release_page_dirty(struct page *page);
+void kvm_set_page_dirty(struct page *page);
+void kvm_set_page_accessed(struct page *page);
+
+pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn);
+void kvm_release_pfn_dirty(pfn_t);
+void kvm_release_pfn_clean(pfn_t pfn);
+void kvm_set_pfn_dirty(pfn_t pfn);
+void kvm_set_pfn_accessed(pfn_t pfn);
+void kvm_get_pfn(pfn_t pfn);
+
 int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 			int len);
 int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data,
@@ -188,6 +200,7 @@ void kvm_resched(struct kvm_vcpu *vcpu);
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_flush_remote_tlbs(struct kvm *kvm);
+void kvm_reload_remote_mmus(struct kvm *kvm);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -223,6 +236,10 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs);
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs);
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state);
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state);
 int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
 				    struct kvm_debug_guest *dbg);
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);
@@ -255,6 +272,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm);
 
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *v);
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
 
 static inline void kvm_guest_enter(void)
@@ -296,5 +314,18 @@ struct kvm_stats_debugfs_item {
 	struct dentry *dentry;
 };
 extern struct kvm_stats_debugfs_item debugfs_entries[];
+extern struct dentry *kvm_debugfs_dir;
+
+#ifdef CONFIG_KVM_TRACE
+int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg);
+void kvm_trace_cleanup(void);
+#else
+static inline
+int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg)
+{
+	return -EINVAL;
+}
+#define kvm_trace_cleanup() ((void)0)
+#endif
 
 #endif
diff --git a/trunk/include/linux/kvm_para.h b/trunk/include/linux/kvm_para.h
index 5497aac0d2f8..3ddce03766ca 100644
--- a/trunk/include/linux/kvm_para.h
+++ b/trunk/include/linux/kvm_para.h
@@ -11,8 +11,11 @@
 
 /* Return values for hypercalls */
 #define KVM_ENOSYS		1000
+#define KVM_EFAULT		EFAULT
+#define KVM_E2BIG		E2BIG
 
-#define KVM_HC_VAPIC_POLL_IRQ            1
+#define KVM_HC_VAPIC_POLL_IRQ		1
+#define KVM_HC_MMU_OP			2
 
 /*
  * hypercalls use architecture specific
@@ -20,6 +23,12 @@
 #include <asm/kvm_para.h>
 
 #ifdef __KERNEL__
+#ifdef CONFIG_KVM_GUEST
+void __init kvm_guest_init(void);
+#else
+#define kvm_guest_init() do { } while (0)
+#endif
+
 static inline int kvm_para_has_feature(unsigned int feature)
 {
 	if (kvm_arch_para_features() & (1UL << feature))
diff --git a/trunk/include/linux/kvm_types.h b/trunk/include/linux/kvm_types.h
index 1c4e46decb22..9b6f395c9625 100644
--- a/trunk/include/linux/kvm_types.h
+++ b/trunk/include/linux/kvm_types.h
@@ -38,6 +38,8 @@ typedef unsigned long  hva_t;
 typedef u64            hpa_t;
 typedef unsigned long  hfn_t;
 
+typedef hfn_t pfn_t;
+
 struct kvm_pio_request {
 	unsigned long count;
 	int cur_count;
diff --git a/trunk/include/linux/list.h b/trunk/include/linux/list.h
index dac16f99c701..7627508f1b74 100644
--- a/trunk/include/linux/list.h
+++ b/trunk/include/linux/list.h
@@ -319,7 +319,16 @@ static inline int list_empty_careful(const struct list_head *head)
 	return (next == head) && (next == head->prev);
 }
 
-static inline void __list_splice(struct list_head *list,
+/**
+ * list_is_singular - tests whether a list has just one entry.
+ * @head: the list to test.
+ */
+static inline int list_is_singular(const struct list_head *head)
+{
+	return !list_empty(head) && (head->next == head->prev);
+}
+
+static inline void __list_splice(const struct list_head *list,
 				 struct list_head *head)
 {
 	struct list_head *first = list->next;
@@ -338,7 +347,8 @@ static inline void __list_splice(struct list_head *list,
  * @list: the new list to add.
  * @head: the place to add it in the first list.
  */
-static inline void list_splice(struct list_head *list, struct list_head *head)
+static inline void list_splice(const struct list_head *list,
+				struct list_head *head)
 {
 	if (!list_empty(list))
 		__list_splice(list, head);
diff --git a/trunk/include/linux/lmb.h b/trunk/include/linux/lmb.h
index 271153d27fba..c46c89505dac 100644
--- a/trunk/include/linux/lmb.h
+++ b/trunk/include/linux/lmb.h
@@ -40,7 +40,8 @@ extern struct lmb lmb;
 
 extern void __init lmb_init(void);
 extern void __init lmb_analyze(void);
-extern long __init lmb_add(u64 base, u64 size);
+extern long lmb_add(u64 base, u64 size);
+extern long lmb_remove(u64 base, u64 size);
 extern long __init lmb_reserve(u64 base, u64 size);
 extern u64 __init lmb_alloc_nid(u64 size, u64 align, int nid,
 				u64 (*nid_range)(u64, u64, int *));
@@ -53,6 +54,7 @@ extern u64 __init lmb_phys_mem_size(void);
 extern u64 __init lmb_end_of_DRAM(void);
 extern void __init lmb_enforce_memory_limit(u64 memory_limit);
 extern int __init lmb_is_reserved(u64 addr);
+extern int lmb_find(struct lmb_property *res);
 
 extern void lmb_dump_all(void);
 
diff --git a/trunk/include/linux/mca-legacy.h b/trunk/include/linux/mca-legacy.h
index f2bb770e530a..7a3aea845902 100644
--- a/trunk/include/linux/mca-legacy.h
+++ b/trunk/include/linux/mca-legacy.h
@@ -34,7 +34,6 @@
 extern int mca_find_adapter(int id, int start);
 extern int mca_find_unused_adapter(int id, int start);
 
-extern int mca_is_adapter_used(int slot);
 extern int mca_mark_as_used(int slot);
 extern void mca_mark_as_unused(int slot);
 
diff --git a/trunk/include/linux/memcontrol.h b/trunk/include/linux/memcontrol.h
index 8b1c4295848b..e6608776bc96 100644
--- a/trunk/include/linux/memcontrol.h
+++ b/trunk/include/linux/memcontrol.h
@@ -27,9 +27,6 @@ struct mm_struct;
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 
-extern void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p);
-extern void mm_free_cgroup(struct mm_struct *mm);
-
 #define page_reset_bad_cgroup(page)	((page)->page_cgroup = 0)
 
 extern struct page_cgroup *page_get_page_cgroup(struct page *page);
@@ -48,8 +45,10 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);
 
+extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
+
 #define mm_match_cgroup(mm, cgroup)	\
-	((cgroup) == rcu_dereference((mm)->mem_cgroup))
+	((cgroup) == mem_cgroup_from_task((mm)->owner))
 
 extern int mem_cgroup_prepare_migration(struct page *page);
 extern void mem_cgroup_end_migration(struct page *page);
@@ -73,15 +72,6 @@ extern long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
 				struct zone *zone, int priority);
 
 #else /* CONFIG_CGROUP_MEM_RES_CTLR */
-static inline void mm_init_cgroup(struct mm_struct *mm,
-					struct task_struct *p)
-{
-}
-
-static inline void mm_free_cgroup(struct mm_struct *mm)
-{
-}
-
 static inline void page_reset_bad_cgroup(struct page *page)
 {
 }
diff --git a/trunk/include/linux/memory.h b/trunk/include/linux/memory.h
index f80e0e331cb7..2f5f8a5ef2a0 100644
--- a/trunk/include/linux/memory.h
+++ b/trunk/include/linux/memory.h
@@ -53,6 +53,13 @@ struct memory_notify {
 struct notifier_block;
 struct mem_section;
 
+/*
+ * Priorities for the hotplug memory callback routines (stored in decreasing
+ * order in the callback chain)
+ */
+#define SLAB_CALLBACK_PRI       1
+#define IPC_CALLBACK_PRI        10
+
 #ifndef CONFIG_MEMORY_HOTPLUG_SPARSE
 static inline int memory_dev_init(void)
 {
diff --git a/trunk/include/linux/memory_hotplug.h b/trunk/include/linux/memory_hotplug.h
index 8fee7a45736b..73e358612eaf 100644
--- a/trunk/include/linux/memory_hotplug.h
+++ b/trunk/include/linux/memory_hotplug.h
@@ -8,8 +8,18 @@
 struct page;
 struct zone;
 struct pglist_data;
+struct mem_section;
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+
+/*
+ * Magic number for free bootmem.
+ * The normal smallest mapcount is -1. Here is smaller value than it.
+ */
+#define SECTION_INFO		0xfffffffe
+#define MIX_INFO		0xfffffffd
+#define NODE_INFO		0xfffffffc
+
 /*
  * pgdat resizing functions
  */
@@ -64,9 +74,11 @@ extern int offline_pages(unsigned long, unsigned long, unsigned long);
 /* reasonably generic interface to expand the physical pages in a zone  */
 extern int __add_pages(struct zone *zone, unsigned long start_pfn,
 	unsigned long nr_pages);
+extern int __remove_pages(struct zone *zone, unsigned long start_pfn,
+	unsigned long nr_pages);
 
 /*
- * Walk thorugh all memory which is registered as resource.
+ * Walk through all memory which is registered as resource.
  * arg is (start_pfn, nr_pages, private_arg_pointer)
  */
 extern int walk_memory_resource(unsigned long start_pfn,
@@ -142,6 +154,18 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
 #endif /* CONFIG_NUMA */
 #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
+{
+}
+static inline void put_page_bootmem(struct page *page)
+{
+}
+#else
+extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
+extern void put_page_bootmem(struct page *page);
+#endif
+
 #else /* ! CONFIG_MEMORY_HOTPLUG */
 /*
  * Stub functions for when hotplug is off
@@ -169,6 +193,10 @@ static inline int mhp_notimplemented(const char *func)
 	return -ENOSYS;
 }
 
+static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
+{
+}
+
 #endif /* ! CONFIG_MEMORY_HOTPLUG */
 
 extern int add_memory(int nid, u64 start, u64 size);
@@ -176,5 +204,8 @@ extern int arch_add_memory(int nid, u64 start, u64 size);
 extern int remove_memory(u64 start, u64 size);
 extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 								int nr_pages);
+extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms);
+extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
+					  unsigned long pnum);
 
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/trunk/include/linux/mempolicy.h b/trunk/include/linux/mempolicy.h
index 59c4865bc85f..3a39570b81b8 100644
--- a/trunk/include/linux/mempolicy.h
+++ b/trunk/include/linux/mempolicy.h
@@ -8,15 +8,32 @@
  * Copyright 2003,2004 Andi Kleen SuSE Labs
  */
 
+/*
+ * Both the MPOL_* mempolicy mode and the MPOL_F_* optional mode flags are
+ * passed by the user to either set_mempolicy() or mbind() in an 'int' actual.
+ * The MPOL_MODE_FLAGS macro determines the legal set of optional mode flags.
+ */
+
 /* Policies */
-#define MPOL_DEFAULT	0
-#define MPOL_PREFERRED	1
-#define MPOL_BIND	2
-#define MPOL_INTERLEAVE	3
+enum {
+	MPOL_DEFAULT,
+	MPOL_PREFERRED,
+	MPOL_BIND,
+	MPOL_INTERLEAVE,
+	MPOL_MAX,	/* always last member of enum */
+};
 
-#define MPOL_MAX MPOL_INTERLEAVE
+/* Flags for set_mempolicy */
+#define MPOL_F_STATIC_NODES	(1 << 15)
+#define MPOL_F_RELATIVE_NODES	(1 << 14)
 
-/* Flags for get_mem_policy */
+/*
+ * MPOL_MODE_FLAGS is the union of all possible optional mode flags passed to
+ * either set_mempolicy() or mbind().
+ */
+#define MPOL_MODE_FLAGS	(MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES)
+
+/* Flags for get_mempolicy */
 #define MPOL_F_NODE	(1<<0)	/* return next IL mode instead of node mask */
 #define MPOL_F_ADDR	(1<<1)	/* look up vma using address */
 #define MPOL_F_MEMS_ALLOWED (1<<2) /* return allowed memories */
@@ -27,6 +44,14 @@
 #define MPOL_MF_MOVE_ALL (1<<2)	/* Move every page to conform to mapping */
 #define MPOL_MF_INTERNAL (1<<3)	/* Internal flags start here */
 
+/*
+ * Internal flags that share the struct mempolicy flags word with
+ * "mode flags".  These flags are allocated from bit 0 up, as they
+ * are never OR'ed into the mode in mempolicy API arguments.
+ */
+#define MPOL_F_SHARED  (1 << 0)	/* identify shared policies */
+#define MPOL_F_LOCAL   (1 << 1)	/* preferred local allocation */
+
 #ifdef __KERNEL__
 
 #include <linux/mmzone.h>
@@ -35,7 +60,6 @@
 #include <linux/spinlock.h>
 #include <linux/nodemask.h>
 
-struct vm_area_struct;
 struct mm_struct;
 
 #ifdef CONFIG_NUMA
@@ -54,22 +78,27 @@ struct mm_struct;
  * mmap_sem.
  *
  * Freeing policy:
- * When policy is MPOL_BIND v.zonelist is kmalloc'ed and must be kfree'd.
- * All other policies don't have any external state. mpol_free() handles this.
+ * Mempolicy objects are reference counted.  A mempolicy will be freed when
+ * mpol_put() decrements the reference count to zero.
  *
- * Copying policy objects:
- * For MPOL_BIND the zonelist must be always duplicated. mpol_clone() does this.
+ * Duplicating policy objects:
+ * mpol_dup() allocates a new mempolicy and copies the specified mempolicy
+ * to the new storage.  The reference count of the new object is initialized
+ * to 1, representing the caller of mpol_dup().
  */
 struct mempolicy {
 	atomic_t refcnt;
-	short policy; 	/* See MPOL_* above */
+	unsigned short mode; 	/* See MPOL_* above */
+	unsigned short flags;	/* See set_mempolicy() MPOL_F_* above */
 	union {
-		struct zonelist  *zonelist;	/* bind */
 		short 		 preferred_node; /* preferred */
-		nodemask_t	 nodes;		/* interleave */
+		nodemask_t	 nodes;		/* interleave/bind */
 		/* undefined for default */
 	} v;
-	nodemask_t cpuset_mems_allowed;	/* mempolicy relative to these nodes */
+	union {
+		nodemask_t cpuset_mems_allowed;	/* relative to these nodes */
+		nodemask_t user_nodemask;	/* nodemask passed by user */
+	} w;
 };
 
 /*
@@ -77,18 +106,43 @@ struct mempolicy {
  * The default fast path of a NULL MPOL_DEFAULT policy is always inlined.
  */
 
-extern void __mpol_free(struct mempolicy *pol);
-static inline void mpol_free(struct mempolicy *pol)
+extern void __mpol_put(struct mempolicy *pol);
+static inline void mpol_put(struct mempolicy *pol)
 {
 	if (pol)
-		__mpol_free(pol);
+		__mpol_put(pol);
 }
 
-extern struct mempolicy *__mpol_copy(struct mempolicy *pol);
-static inline struct mempolicy *mpol_copy(struct mempolicy *pol)
+/*
+ * Does mempolicy pol need explicit unref after use?
+ * Currently only needed for shared policies.
+ */
+static inline int mpol_needs_cond_ref(struct mempolicy *pol)
+{
+	return (pol && (pol->flags & MPOL_F_SHARED));
+}
+
+static inline void mpol_cond_put(struct mempolicy *pol)
+{
+	if (mpol_needs_cond_ref(pol))
+		__mpol_put(pol);
+}
+
+extern struct mempolicy *__mpol_cond_copy(struct mempolicy *tompol,
+					  struct mempolicy *frompol);
+static inline struct mempolicy *mpol_cond_copy(struct mempolicy *tompol,
+						struct mempolicy *frompol)
+{
+	if (!frompol)
+		return frompol;
+	return __mpol_cond_copy(tompol, frompol);
+}
+
+extern struct mempolicy *__mpol_dup(struct mempolicy *pol);
+static inline struct mempolicy *mpol_dup(struct mempolicy *pol)
 {
 	if (pol)
-		pol = __mpol_copy(pol);
+		pol = __mpol_dup(pol);
 	return pol;
 }
 
@@ -108,11 +162,6 @@ static inline int mpol_equal(struct mempolicy *a, struct mempolicy *b)
 		return 1;
 	return __mpol_equal(a, b);
 }
-#define vma_mpol_equal(a,b) mpol_equal(vma_policy(a), vma_policy(b))
-
-/* Could later add inheritance of the process policy here. */
-
-#define mpol_set_vma_default(vma) ((vma)->vm_policy = NULL)
 
 /*
  * Tree of shared policies for a shared memory region.
@@ -133,8 +182,7 @@ struct shared_policy {
 	spinlock_t lock;
 };
 
-void mpol_shared_policy_init(struct shared_policy *info, int policy,
-				nodemask_t *nodes);
+void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol);
 int mpol_set_shared_policy(struct shared_policy *info,
 				struct vm_area_struct *vma,
 				struct mempolicy *new);
@@ -149,9 +197,9 @@ extern void mpol_rebind_task(struct task_struct *tsk,
 extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);
 extern void mpol_fix_fork_child_flag(struct task_struct *p);
 
-extern struct mempolicy default_policy;
 extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
-		unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol);
+				unsigned long addr, gfp_t gfp_flags,
+				struct mempolicy **mpol, nodemask_t **nodemask);
 extern unsigned slab_node(struct mempolicy *policy);
 
 extern enum zone_type policy_zone;
@@ -165,6 +213,13 @@ static inline void check_highest_zone(enum zone_type k)
 int do_migrate_pages(struct mm_struct *mm,
 	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags);
 
+
+#ifdef CONFIG_TMPFS
+extern int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context);
+
+extern int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol,
+			int no_context);
+#endif
 #else
 
 struct mempolicy {};
@@ -173,19 +228,26 @@ static inline int mpol_equal(struct mempolicy *a, struct mempolicy *b)
 {
 	return 1;
 }
-#define vma_mpol_equal(a,b) 1
 
-#define mpol_set_vma_default(vma) do {} while(0)
+static inline void mpol_put(struct mempolicy *p)
+{
+}
+
+static inline void mpol_cond_put(struct mempolicy *pol)
+{
+}
 
-static inline void mpol_free(struct mempolicy *p)
+static inline struct mempolicy *mpol_cond_copy(struct mempolicy *to,
+						struct mempolicy *from)
 {
+	return from;
 }
 
 static inline void mpol_get(struct mempolicy *pol)
 {
 }
 
-static inline struct mempolicy *mpol_copy(struct mempolicy *old)
+static inline struct mempolicy *mpol_dup(struct mempolicy *old)
 {
 	return NULL;
 }
@@ -199,8 +261,8 @@ static inline int mpol_set_shared_policy(struct shared_policy *info,
 	return -EINVAL;
 }
 
-static inline void mpol_shared_policy_init(struct shared_policy *info,
-					int policy, nodemask_t *nodes)
+static inline void mpol_shared_policy_init(struct shared_policy *sp,
+						struct mempolicy *mpol)
 {
 }
 
@@ -239,9 +301,12 @@ static inline void mpol_fix_fork_child_flag(struct task_struct *p)
 }
 
 static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
- 		unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol)
+				unsigned long addr, gfp_t gfp_flags,
+				struct mempolicy **mpol, nodemask_t **nodemask)
 {
-	return NODE_DATA(0)->node_zonelists + gfp_zone(gfp_flags);
+	*mpol = NULL;
+	*nodemask = NULL;
+	return node_zonelist(0, gfp_flags);
 }
 
 static inline int do_migrate_pages(struct mm_struct *mm,
@@ -254,6 +319,21 @@ static inline int do_migrate_pages(struct mm_struct *mm,
 static inline void check_highest_zone(int k)
 {
 }
+
+#ifdef CONFIG_TMPFS
+static inline int mpol_parse_str(char *str, struct mempolicy **mpol,
+				int no_context)
+{
+	return 1;	/* error */
+}
+
+static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol,
+				int no_context)
+{
+	return 0;
+}
+#endif
+
 #endif /* CONFIG_NUMA */
 #endif /* __KERNEL__ */
 
diff --git a/trunk/include/linux/mlx4/device.h b/trunk/include/linux/mlx4/device.h
index ff7df1a2222f..9fa1a8002ce2 100644
--- a/trunk/include/linux/mlx4/device.h
+++ b/trunk/include/linux/mlx4/device.h
@@ -208,6 +208,38 @@ struct mlx4_mtt {
 	int			page_shift;
 };
 
+enum {
+	MLX4_DB_PER_PAGE = PAGE_SIZE / 4
+};
+
+struct mlx4_db_pgdir {
+	struct list_head	list;
+	DECLARE_BITMAP(order0, MLX4_DB_PER_PAGE);
+	DECLARE_BITMAP(order1, MLX4_DB_PER_PAGE / 2);
+	unsigned long	       *bits[2];
+	__be32		       *db_page;
+	dma_addr_t		db_dma;
+};
+
+struct mlx4_ib_user_db_page;
+
+struct mlx4_db {
+	__be32			*db;
+	union {
+		struct mlx4_db_pgdir		*pgdir;
+		struct mlx4_ib_user_db_page	*user_page;
+	}			u;
+	dma_addr_t		dma;
+	int			index;
+	int			order;
+};
+
+struct mlx4_hwq_resources {
+	struct mlx4_db		db;
+	struct mlx4_mtt		mtt;
+	struct mlx4_buf		buf;
+};
+
 struct mlx4_mr {
 	struct mlx4_mtt		mtt;
 	u64			iova;
@@ -341,6 +373,14 @@ int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 		       struct mlx4_buf *buf);
 
+int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order);
+void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db);
+
+int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
+		       int size, int max_direct);
+void mlx4_free_hwq_res(struct mlx4_dev *mdev, struct mlx4_hwq_resources *wqres,
+		       int size);
+
 int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 		  struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq);
 void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq);
diff --git a/trunk/include/linux/mlx4/qp.h b/trunk/include/linux/mlx4/qp.h
index a5e43febee4f..7f128b266faa 100644
--- a/trunk/include/linux/mlx4/qp.h
+++ b/trunk/include/linux/mlx4/qp.h
@@ -296,6 +296,10 @@ int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 int mlx4_qp_query(struct mlx4_dev *dev, struct mlx4_qp *qp,
 		  struct mlx4_qp_context *context);
 
+int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+		     struct mlx4_qp_context *context,
+		     struct mlx4_qp *qp, enum mlx4_qp_state *qp_state);
+
 static inline struct mlx4_qp *__mlx4_qp_lookup(struct mlx4_dev *dev, u32 qpn)
 {
 	return radix_tree_lookup(&dev->qp_table_tree, qpn & (dev->caps.num_qps - 1));
diff --git a/trunk/include/linux/mm.h b/trunk/include/linux/mm.h
index 286d31521605..c31a9cd2a30e 100644
--- a/trunk/include/linux/mm.h
+++ b/trunk/include/linux/mm.h
@@ -107,6 +107,7 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_ALWAYSDUMP	0x04000000	/* Always include in core dumps */
 
 #define VM_CAN_NONLINEAR 0x08000000	/* Has ->fault & does nonlinear pages */
+#define VM_MIXEDMAP	0x10000000	/* Can contain "struct page" and pure PFN pages */
 
 #ifndef VM_STACK_DEFAULT_FLAGS		/* arch can override this */
 #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
@@ -164,8 +165,6 @@ struct vm_operations_struct {
 	void (*open)(struct vm_area_struct * area);
 	void (*close)(struct vm_area_struct * area);
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
-	struct page *(*nopage)(struct vm_area_struct *area,
-			unsigned long address, int *type);
 	unsigned long (*nopfn)(struct vm_area_struct *area,
 			unsigned long address);
 
@@ -173,7 +172,25 @@ struct vm_operations_struct {
 	 * writable, if an error is returned it will cause a SIGBUS */
 	int (*page_mkwrite)(struct vm_area_struct *vma, struct page *page);
 #ifdef CONFIG_NUMA
+	/*
+	 * set_policy() op must add a reference to any non-NULL @new mempolicy
+	 * to hold the policy upon return.  Caller should pass NULL @new to
+	 * remove a policy and fall back to surrounding context--i.e. do not
+	 * install a MPOL_DEFAULT policy, nor the task or system default
+	 * mempolicy.
+	 */
 	int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new);
+
+	/*
+	 * get_policy() op must add reference [mpol_get()] to any policy at
+	 * (vma,addr) marked as MPOL_SHARED.  The shared policy infrastructure
+	 * in mm/mempolicy.c will do this automatically.
+	 * get_policy() must NOT add a ref if the policy at (vma,addr) is not
+	 * marked as MPOL_SHARED. vma policies are protected by the mmap_sem.
+	 * If no [shared/vma] mempolicy exists at the addr, get_policy() op
+	 * must return NULL--i.e., do not "fallback" to task or system default
+	 * policy.
+	 */
 	struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
 					unsigned long addr);
 	int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from,
@@ -397,11 +414,11 @@ static inline void set_compound_order(struct page *page, unsigned long order)
  * we have run out of space and have to fall back to an
  * alternate (slower) way of determining the node.
  *
- *        No sparsemem: |       NODE     | ZONE | ... | FLAGS |
- * with space for node: | SECTION | NODE | ZONE | ... | FLAGS |
- *   no space for node: | SECTION |     ZONE    | ... | FLAGS |
+ * No sparsemem or sparsemem vmemmap: |       NODE     | ZONE | ... | FLAGS |
+ * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS |
+ * classic sparse no space for node:  | SECTION |     ZONE    | ... | FLAGS |
  */
-#ifdef CONFIG_SPARSEMEM
+#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
 #define SECTIONS_WIDTH		SECTIONS_SHIFT
 #else
 #define SECTIONS_WIDTH		0
@@ -409,9 +426,12 @@ static inline void set_compound_order(struct page *page, unsigned long order)
 
 #define ZONES_WIDTH		ZONES_SHIFT
 
-#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= FLAGS_RESERVED
+#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
 #define NODES_WIDTH		NODES_SHIFT
 #else
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+#error "Vmemmap: No space for nodes field in page flags"
+#endif
 #define NODES_WIDTH		0
 #endif
 
@@ -454,8 +474,8 @@ static inline void set_compound_order(struct page *page, unsigned long order)
 
 #define ZONEID_PGSHIFT		(ZONEID_PGOFF * (ZONEID_SHIFT != 0))
 
-#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > FLAGS_RESERVED
-#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > FLAGS_RESERVED
+#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
+#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
 #endif
 
 #define ZONES_MASK		((1UL << ZONES_WIDTH) - 1)
@@ -504,10 +524,12 @@ static inline struct zone *page_zone(struct page *page)
 	return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
 }
 
+#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
 static inline unsigned long page_to_section(struct page *page)
 {
 	return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
 }
+#endif
 
 static inline void set_page_zone(struct page *page, enum zone_type zone)
 {
@@ -602,9 +624,12 @@ static inline struct address_space *page_mapping(struct page *page)
 	struct address_space *mapping = page->mapping;
 
 	VM_BUG_ON(PageSlab(page));
+#ifdef CONFIG_SWAP
 	if (unlikely(PageSwapCache(page)))
 		mapping = &swapper_space;
-	else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
+	else
+#endif
+	if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
 		mapping = NULL;
 	return mapping;
 }
@@ -648,12 +673,6 @@ static inline int page_mapped(struct page *page)
 	return atomic_read(&(page)->_mapcount) >= 0;
 }
 
-/*
- * Error return values for the *_nopage functions
- */
-#define NOPAGE_SIGBUS	(NULL)
-#define NOPAGE_OOM	((struct page *) (-1))
-
 /*
  * Error return values for the *_nopfn functions
  */
@@ -720,7 +739,9 @@ struct zap_details {
 	unsigned long truncate_count;		/* Compare vm_truncate_count */
 };
 
-struct page *vm_normal_page(struct vm_area_struct *, unsigned long, pte_t);
+struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+		pte_t pte);
+
 unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
 		unsigned long size, struct zap_details *);
 unsigned long unmap_vmas(struct mmu_gather **tlb,
@@ -1045,6 +1066,19 @@ extern void unlink_file_vma(struct vm_area_struct *);
 extern struct vm_area_struct *copy_vma(struct vm_area_struct **,
 	unsigned long addr, unsigned long len, pgoff_t pgoff);
 extern void exit_mmap(struct mm_struct *);
+
+#ifdef CONFIG_PROC_FS
+/* From fs/proc/base.c. callers must _not_ hold the mm's exe_file_lock */
+extern void added_exe_file_vma(struct mm_struct *mm);
+extern void removed_exe_file_vma(struct mm_struct *mm);
+#else
+static inline void added_exe_file_vma(struct mm_struct *mm)
+{}
+
+static inline void removed_exe_file_vma(struct mm_struct *mm)
+{}
+#endif /* CONFIG_PROC_FS */
+
 extern int may_expand_vm(struct mm_struct *mm, unsigned long npages);
 extern int install_special_mapping(struct mm_struct *mm,
 				   unsigned long addr, unsigned long len,
@@ -1149,6 +1183,8 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
 int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
 int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
+int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long pfn);
 
 struct page *follow_page(struct vm_area_struct *, unsigned long address,
 			unsigned int foll_flags);
@@ -1207,8 +1243,6 @@ int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *,
 					void __user *, size_t *, loff_t *);
 unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
 			unsigned long lru_pages);
-void drop_pagecache(void);
-void drop_slab(void);
 
 #ifndef CONFIG_MMU
 #define randomize_va_space 0
diff --git a/trunk/include/linux/mm_types.h b/trunk/include/linux/mm_types.h
index af190ceab971..eb7c16cc9559 100644
--- a/trunk/include/linux/mm_types.h
+++ b/trunk/include/linux/mm_types.h
@@ -42,7 +42,10 @@ struct page {
 					 * to show when page is mapped
 					 * & limit reverse map searches.
 					 */
-		unsigned int inuse;	/* SLUB: Nr of objects */
+		struct {		/* SLUB */
+			u16 inuse;
+			u16 objects;
+		};
 	};
 	union {
 	    struct {
@@ -172,6 +175,7 @@ struct mm_struct {
 	atomic_t mm_users;			/* How many users with user space? */
 	atomic_t mm_count;			/* How many references to "struct mm_struct" (users count as 1) */
 	int map_count;				/* number of VMAs */
+	int core_waiters;
 	struct rw_semaphore mmap_sem;
 	spinlock_t page_table_lock;		/* Protects page tables and some counters */
 
@@ -216,14 +220,20 @@ struct mm_struct {
 	unsigned long flags; /* Must use atomic bitops to access the bits */
 
 	/* coredumping support */
-	int core_waiters;
 	struct completion *core_startup_done, core_done;
 
 	/* aio bits */
-	rwlock_t		ioctx_list_lock;
+	rwlock_t		ioctx_list_lock;	/* aio lock */
 	struct kioctx		*ioctx_list;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-	struct mem_cgroup *mem_cgroup;
+#ifdef CONFIG_MM_OWNER
+	struct task_struct *owner;	/* The thread group leader that */
+					/* owns the mm_struct.		*/
+#endif
+
+#ifdef CONFIG_PROC_FS
+	/* store ref to file /proc/<pid>/exe symlink points to */
+	struct file *exe_file;
+	unsigned long num_exe_file_vmas;
 #endif
 };
 
diff --git a/trunk/include/linux/mmzone.h b/trunk/include/linux/mmzone.h
index 9f274a687c7e..aad98003176f 100644
--- a/trunk/include/linux/mmzone.h
+++ b/trunk/include/linux/mmzone.h
@@ -3,6 +3,7 @@
 
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
+#ifndef __GENERATING_BOUNDS_H
 
 #include <linux/spinlock.h>
 #include <linux/list.h>
@@ -15,6 +16,7 @@
 #include <linux/seqlock.h>
 #include <linux/nodemask.h>
 #include <linux/pageblock-flags.h>
+#include <linux/bounds.h>
 #include <asm/atomic.h>
 #include <asm/page.h>
 
@@ -129,6 +131,8 @@ struct per_cpu_pageset {
 #define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)])
 #endif
 
+#endif /* !__GENERATING_BOUNDS.H */
+
 enum zone_type {
 #ifdef CONFIG_ZONE_DMA
 	/*
@@ -177,9 +181,11 @@ enum zone_type {
 	ZONE_HIGHMEM,
 #endif
 	ZONE_MOVABLE,
-	MAX_NR_ZONES
+	__MAX_NR_ZONES
 };
 
+#ifndef __GENERATING_BOUNDS_H
+
 /*
  * When a memory allocation must conform to specific limitations (such
  * as being suitable for DMA) the caller will pass in hints to the
@@ -188,28 +194,15 @@ enum zone_type {
  * match the requested limits. See gfp_zone() in include/linux/gfp.h
  */
 
-/*
- * Count the active zones.  Note that the use of defined(X) outside
- * #if and family is not necessarily defined so ensure we cannot use
- * it later.  Use __ZONE_COUNT to work out how many shift bits we need.
- */
-#define __ZONE_COUNT (			\
-	  defined(CONFIG_ZONE_DMA)	\
-	+ defined(CONFIG_ZONE_DMA32)	\
-	+ 1				\
-	+ defined(CONFIG_HIGHMEM)	\
-	+ 1				\
-)
-#if __ZONE_COUNT < 2
+#if MAX_NR_ZONES < 2
 #define ZONES_SHIFT 0
-#elif __ZONE_COUNT <= 2
+#elif MAX_NR_ZONES <= 2
 #define ZONES_SHIFT 1
-#elif __ZONE_COUNT <= 4
+#elif MAX_NR_ZONES <= 4
 #define ZONES_SHIFT 2
 #else
 #error ZONES_SHIFT -- too many zones configured adjust calculation
 #endif
-#undef __ZONE_COUNT
 
 struct zone {
 	/* Fields commonly accessed by the page allocator */
@@ -393,10 +386,10 @@ static inline int zone_is_oom_locked(const struct zone *zone)
  * The NUMA zonelists are doubled becausse we need zonelists that restrict the
  * allocations to a single node for GFP_THISNODE.
  *
- * [0 .. MAX_NR_ZONES -1] 		: Zonelists with fallback
- * [MAZ_NR_ZONES ... MAZ_ZONELISTS -1]  : No fallback (GFP_THISNODE)
+ * [0]	: Zonelist with fallback
+ * [1]	: No fallback (GFP_THISNODE)
  */
-#define MAX_ZONELISTS (2 * MAX_NR_ZONES)
+#define MAX_ZONELISTS 2
 
 
 /*
@@ -464,10 +457,19 @@ struct zonelist_cache {
 	unsigned long last_full_zap;		/* when last zap'd (jiffies) */
 };
 #else
-#define MAX_ZONELISTS MAX_NR_ZONES
+#define MAX_ZONELISTS 1
 struct zonelist_cache;
 #endif
 
+/*
+ * This struct contains information about a zone in a zonelist. It is stored
+ * here to avoid dereferences into large structures and lookups of tables
+ */
+struct zoneref {
+	struct zone *zone;	/* Pointer to actual zone */
+	int zone_idx;		/* zone_idx(zoneref->zone) */
+};
+
 /*
  * One allocation request operates on a zonelist. A zonelist
  * is a list of zones, the first one is the 'goal' of the
@@ -476,34 +478,23 @@ struct zonelist_cache;
  *
  * If zlcache_ptr is not NULL, then it is just the address of zlcache,
  * as explained above.  If zlcache_ptr is NULL, there is no zlcache.
+ * *
+ * To speed the reading of the zonelist, the zonerefs contain the zone index
+ * of the entry being read. Helper functions to access information given
+ * a struct zoneref are
+ *
+ * zonelist_zone()	- Return the struct zone * for an entry in _zonerefs
+ * zonelist_zone_idx()	- Return the index of the zone for an entry
+ * zonelist_node_idx()	- Return the index of the node for an entry
  */
-
 struct zonelist {
 	struct zonelist_cache *zlcache_ptr;		     // NULL or &zlcache
-	struct zone *zones[MAX_ZONES_PER_ZONELIST + 1];      // NULL delimited
+	struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1];
 #ifdef CONFIG_NUMA
 	struct zonelist_cache zlcache;			     // optional ...
 #endif
 };
 
-#ifdef CONFIG_NUMA
-/*
- * Only custom zonelists like MPOL_BIND need to be filtered as part of
- * policies. As described in the comment for struct zonelist_cache, these
- * zonelists will not have a zlcache so zlcache_ptr will not be set. Use
- * that to determine if the zonelists needs to be filtered or not.
- */
-static inline int alloc_should_filter_zonelist(struct zonelist *zonelist)
-{
-	return !zonelist->zlcache_ptr;
-}
-#else
-static inline int alloc_should_filter_zonelist(struct zonelist *zonelist)
-{
-	return 0;
-}
-#endif /* CONFIG_NUMA */
-
 #ifdef CONFIG_ARCH_POPULATES_NODE_MAP
 struct node_active_region {
 	unsigned long start_pfn;
@@ -637,9 +628,10 @@ static inline int is_normal_idx(enum zone_type idx)
 static inline int is_highmem(struct zone *zone)
 {
 #ifdef CONFIG_HIGHMEM
-	int zone_idx = zone - zone->zone_pgdat->node_zones;
-	return zone_idx == ZONE_HIGHMEM ||
-		(zone_idx == ZONE_MOVABLE && zone_movable_is_highmem());
+	int zone_off = (char *)zone - (char *)zone->zone_pgdat->node_zones;
+	return zone_off == ZONE_HIGHMEM * sizeof(*zone) ||
+	       (zone_off == ZONE_MOVABLE * sizeof(*zone) &&
+		zone_movable_is_highmem());
 #else
 	return 0;
 #endif
@@ -730,32 +722,103 @@ extern struct zone *next_zone(struct zone *zone);
 	     zone;					\
 	     zone = next_zone(zone))
 
-#ifdef CONFIG_SPARSEMEM
-#include <asm/sparsemem.h>
-#endif
+static inline struct zone *zonelist_zone(struct zoneref *zoneref)
+{
+	return zoneref->zone;
+}
 
-#if BITS_PER_LONG == 32
-/*
- * with 32 bit page->flags field, we reserve 9 bits for node/zone info.
- * there are 4 zones (3 bits) and this leaves 9-3=6 bits for nodes.
+static inline int zonelist_zone_idx(struct zoneref *zoneref)
+{
+	return zoneref->zone_idx;
+}
+
+static inline int zonelist_node_idx(struct zoneref *zoneref)
+{
+#ifdef CONFIG_NUMA
+	/* zone_to_nid not available in this context */
+	return zoneref->zone->node;
+#else
+	return 0;
+#endif /* CONFIG_NUMA */
+}
+
+/**
+ * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point
+ * @z - The cursor used as a starting point for the search
+ * @highest_zoneidx - The zone index of the highest zone to return
+ * @nodes - An optional nodemask to filter the zonelist with
+ * @zone - The first suitable zone found is returned via this parameter
+ *
+ * This function returns the next zone at or below a given zone index that is
+ * within the allowed nodemask using a cursor as the starting point for the
+ * search. The zoneref returned is a cursor that is used as the next starting
+ * point for future calls to next_zones_zonelist().
  */
-#define FLAGS_RESERVED		9
+struct zoneref *next_zones_zonelist(struct zoneref *z,
+					enum zone_type highest_zoneidx,
+					nodemask_t *nodes,
+					struct zone **zone);
 
-#elif BITS_PER_LONG == 64
-/*
- * with 64 bit flags field, there's plenty of room.
+/**
+ * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist
+ * @zonelist - The zonelist to search for a suitable zone
+ * @highest_zoneidx - The zone index of the highest zone to return
+ * @nodes - An optional nodemask to filter the zonelist with
+ * @zone - The first suitable zone found is returned via this parameter
+ *
+ * This function returns the first zone at or below a given zone index that is
+ * within the allowed nodemask. The zoneref returned is a cursor that can be
+ * used to iterate the zonelist with next_zones_zonelist. The cursor should
+ * not be used by the caller as it does not match the value of the zone
+ * returned.
  */
-#define FLAGS_RESERVED		32
+static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
+					enum zone_type highest_zoneidx,
+					nodemask_t *nodes,
+					struct zone **zone)
+{
+	return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes,
+								zone);
+}
 
-#else
+/**
+ * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask
+ * @zone - The current zone in the iterator
+ * @z - The current pointer within zonelist->zones being iterated
+ * @zlist - The zonelist being iterated
+ * @highidx - The zone index of the highest zone to return
+ * @nodemask - Nodemask allowed by the allocator
+ *
+ * This iterator iterates though all zones at or below a given zone index and
+ * within a given nodemask
+ */
+#define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
+	for (z = first_zones_zonelist(zlist, highidx, nodemask, &zone);	\
+		zone;							\
+		z = next_zones_zonelist(z, highidx, nodemask, &zone))	\
 
-#error BITS_PER_LONG not defined
+/**
+ * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index
+ * @zone - The current zone in the iterator
+ * @z - The current pointer within zonelist->zones being iterated
+ * @zlist - The zonelist being iterated
+ * @highidx - The zone index of the highest zone to return
+ *
+ * This iterator iterates though all zones at or below a given zone index.
+ */
+#define for_each_zone_zonelist(zone, z, zlist, highidx) \
+	for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL)
 
+#ifdef CONFIG_SPARSEMEM
+#include <asm/sparsemem.h>
 #endif
 
 #if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \
 	!defined(CONFIG_ARCH_POPULATES_NODE_MAP)
-#define early_pfn_to_nid(nid)  (0UL)
+static inline unsigned long early_pfn_to_nid(unsigned long pfn)
+{
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_FLATMEM
@@ -833,6 +896,7 @@ static inline struct mem_section *__nr_to_section(unsigned long nr)
 	return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
 }
 extern int __section_nr(struct mem_section* ms);
+extern unsigned long usemap_size(void);
 
 /*
  * We use the lower bits of the mem_map pointer to store
@@ -938,6 +1002,7 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long);
 #define pfn_valid_within(pfn) (1)
 #endif
 
+#endif /* !__GENERATING_BOUNDS.H */
 #endif /* !__ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MMZONE_H */
diff --git a/trunk/include/linux/msdos_fs.h b/trunk/include/linux/msdos_fs.h
index f950921523f5..b03b27457413 100644
--- a/trunk/include/linux/msdos_fs.h
+++ b/trunk/include/linux/msdos_fs.h
@@ -58,7 +58,11 @@
 #define MSDOS_DOTDOT	"..         "	/* "..", padded to MSDOS_NAME chars */
 
 /* media of boot sector */
-#define FAT_VALID_MEDIA(x)	((0xF8 <= (x) && (x) <= 0xFF) || (x) == 0xF0)
+static inline int fat_valid_media(u8 media)
+{
+	return 0xf8 <= media || media == 0xf0;
+}
+
 #define FAT_FIRST_ENT(s, x)	((MSDOS_SB(s)->fat_bits == 32 ? 0x0FFFFF00 : \
 	MSDOS_SB(s)->fat_bits == 16 ? 0xFF00 : 0xF00) | (x))
 
@@ -195,6 +199,7 @@ struct fat_mount_options {
 	char *iocharset;          /* Charset used for filename input/display */
 	unsigned short shortname; /* flags for shortname display/create rule */
 	unsigned char name_check; /* r = relaxed, n = normal, s = strict */
+	unsigned short allow_utime;/* permission for setting the [am]time */
 	unsigned quiet:1,         /* set = fake successful chmods and chowns */
 		 showexec:1,      /* set = only set x bit for com/exe/bat */
 		 sys_immutable:1, /* set = system files are immutable */
@@ -232,6 +237,7 @@ struct msdos_sb_info {
 	struct mutex fat_lock;
 	unsigned int prev_free;      /* previously allocated cluster number */
 	unsigned int free_clusters;  /* -1 if undefined */
+	unsigned int free_clus_valid; /* is free_clusters valid? */
 	struct fat_mount_options options;
 	struct nls_table *nls_disk;  /* Codepage used on disk */
 	struct nls_table *nls_io;    /* Charset used for input and display */
@@ -401,7 +407,7 @@ extern int fat_generic_ioctl(struct inode *inode, struct file *filp,
 			     unsigned int cmd, unsigned long arg);
 extern const struct file_operations fat_file_operations;
 extern const struct inode_operations fat_file_inode_operations;
-extern int fat_notify_change(struct dentry * dentry, struct iattr * attr);
+extern int fat_setattr(struct dentry * dentry, struct iattr * attr);
 extern void fat_truncate(struct inode *inode);
 extern int fat_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		       struct kstat *stat);
diff --git a/trunk/include/linux/msg.h b/trunk/include/linux/msg.h
index 10a3d5a1abff..6f3b8e79a991 100644
--- a/trunk/include/linux/msg.h
+++ b/trunk/include/linux/msg.h
@@ -49,16 +49,26 @@ struct msginfo {
 	unsigned short  msgseg; 
 };
 
+/*
+ * Scaling factor to compute msgmni:
+ * the memory dedicated to msg queues (msgmni * msgmnb) should occupy
+ * at most 1/MSG_MEM_SCALE of the lowmem (see the formula in ipc/msg.c):
+ * up to 8MB       : msgmni = 16 (MSGMNI)
+ * 4 GB            : msgmni = 8K
+ * more than 16 GB : msgmni = 32K (IPCMNI)
+ */
+#define MSG_MEM_SCALE 32
+
 #define MSGMNI    16   /* <= IPCMNI */     /* max # of msg queue identifiers */
 #define MSGMAX  8192   /* <= INT_MAX */   /* max size of message (bytes) */
 #define MSGMNB 16384   /* <= INT_MAX */   /* default max size of a message queue */
 
 /* unused */
-#define MSGPOOL (MSGMNI*MSGMNB/1024)  /* size in kilobytes of message pool */
+#define MSGPOOL (MSGMNI * MSGMNB) /* size in bytes of message pool */
 #define MSGTQL  MSGMNB            /* number of system message headers */
 #define MSGMAP  MSGMNB            /* number of entries in message map */
 #define MSGSSZ  16                /* message segment size */
-#define __MSGSEG ((MSGPOOL*1024)/ MSGSSZ) /* max no. of segments */
+#define __MSGSEG (MSGPOOL / MSGSSZ) /* max no. of segments */
 #define MSGSEG (__MSGSEG <= 0xffff ? __MSGSEG : 0xffff)
 
 #ifdef __KERNEL__
diff --git a/trunk/include/linux/nbd.h b/trunk/include/linux/nbd.h
index 986572081e19..155719dab813 100644
--- a/trunk/include/linux/nbd.h
+++ b/trunk/include/linux/nbd.h
@@ -56,9 +56,11 @@ struct nbd_device {
 	int magic;
 
 	spinlock_t queue_lock;
-	struct list_head queue_head;/* Requests are added here...	*/
+	struct list_head queue_head;	/* Requests waiting result */
 	struct request *active_req;
 	wait_queue_head_t active_wq;
+	struct list_head waiting_queue;	/* Requests to be sent */
+	wait_queue_head_t waiting_wq;
 
 	struct mutex tx_lock;
 	struct gendisk *disk;
@@ -86,11 +88,7 @@ struct nbd_request {
 	char handle[8];
 	__be64 from;
 	__be32 len;
-}
-#ifdef __GNUC__
-	__attribute__ ((packed))
-#endif
-;
+} __attribute__ ((packed));
 
 /*
  * This is the reply packet that nbd-server sends back to the client after
diff --git a/trunk/include/linux/ncp_fs.h b/trunk/include/linux/ncp_fs.h
index 88766e43e121..9f2d76347f19 100644
--- a/trunk/include/linux/ncp_fs.h
+++ b/trunk/include/linux/ncp_fs.h
@@ -204,6 +204,7 @@ void ncp_update_inode2(struct inode *, struct ncp_entry_info *);
 /* linux/fs/ncpfs/dir.c */
 extern const struct inode_operations ncp_dir_inode_operations;
 extern const struct file_operations ncp_dir_operations;
+extern struct dentry_operations ncp_root_dentry_operations;
 int ncp_conn_logged_in(struct super_block *);
 int ncp_date_dos2unix(__le16 time, __le16 date);
 void ncp_date_unix2dos(int unix_date, __le16 * time, __le16 * date);
@@ -223,6 +224,12 @@ int ncp_disconnect(struct ncp_server *server);
 void ncp_lock_server(struct ncp_server *server);
 void ncp_unlock_server(struct ncp_server *server);
 
+/* linux/fs/ncpfs/symlink.c */
+#if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS)
+extern const struct address_space_operations ncp_symlink_aops;
+int ncp_symlink(struct inode*, struct dentry*, const char*);
+#endif
+
 /* linux/fs/ncpfs/file.c */
 extern const struct inode_operations ncp_file_inode_operations;
 extern const struct file_operations ncp_file_operations;
diff --git a/trunk/include/linux/nodemask.h b/trunk/include/linux/nodemask.h
index 905e18f4b412..848025cd7087 100644
--- a/trunk/include/linux/nodemask.h
+++ b/trunk/include/linux/nodemask.h
@@ -14,6 +14,8 @@
  * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c.
  * For details of node_remap(), see bitmap_bitremap in lib/bitmap.c.
  * For details of nodes_remap(), see bitmap_remap in lib/bitmap.c.
+ * For details of nodes_onto(), see bitmap_onto in lib/bitmap.c.
+ * For details of nodes_fold(), see bitmap_fold in lib/bitmap.c.
  *
  * The available nodemask operations are:
  *
@@ -55,7 +57,9 @@
  * int nodelist_scnprintf(buf, len, mask) Format nodemask as list for printing
  * int nodelist_parse(buf, map)		Parse ascii string as nodelist
  * int node_remap(oldbit, old, new)	newbit = map(old, new)(oldbit)
- * int nodes_remap(dst, src, old, new)	*dst = map(old, new)(dst)
+ * void nodes_remap(dst, src, old, new)	*dst = map(old, new)(src)
+ * void nodes_onto(dst, orig, relmap)	*dst = orig relative to relmap
+ * void nodes_fold(dst, orig, sz)	dst bits = orig bits mod sz
  *
  * for_each_node_mask(node, mask)	for-loop node over mask
  *
@@ -326,6 +330,22 @@ static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp,
 	bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits);
 }
 
+#define nodes_onto(dst, orig, relmap) \
+		__nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES)
+static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp,
+		const nodemask_t *relmapp, int nbits)
+{
+	bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits);
+}
+
+#define nodes_fold(dst, orig, sz) \
+		__nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES)
+static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp,
+		int sz, int nbits)
+{
+	bitmap_fold(dstp->bits, origp->bits, sz, nbits);
+}
+
 #if MAX_NUMNODES > 1
 #define for_each_node_mask(node, mask)			\
 	for ((node) = first_node(mask);			\
diff --git a/trunk/include/linux/notifier.h b/trunk/include/linux/notifier.h
index f4df40038f0c..0ff6224d172a 100644
--- a/trunk/include/linux/notifier.h
+++ b/trunk/include/linux/notifier.h
@@ -121,6 +121,10 @@ extern int raw_notifier_chain_register(struct raw_notifier_head *nh,
 extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh,
 		struct notifier_block *nb);
 
+extern int blocking_notifier_chain_cond_register(
+		struct blocking_notifier_head *nh,
+		struct notifier_block *nb);
+
 extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh,
 		struct notifier_block *nb);
 extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh,
@@ -247,6 +251,7 @@ extern struct blocking_notifier_head reboot_notifier_list;
 #define VT_DEALLOCATE		0x0002 /* Console will be deallocated */
 #define VT_WRITE		0x0003 /* A char got output */
 #define VT_UPDATE		0x0004 /* A bigger update occurred */
+#define VT_PREWRITE		0x0005 /* A char is about to be written to the console */
 
 #endif /* __KERNEL__ */
 #endif /* _LINUX_NOTIFIER_H */
diff --git a/trunk/include/linux/oom.h b/trunk/include/linux/oom.h
index 3852436b652a..a7979baf1e39 100644
--- a/trunk/include/linux/oom.h
+++ b/trunk/include/linux/oom.h
@@ -23,8 +23,8 @@ enum oom_constraint {
 	CONSTRAINT_MEMORY_POLICY,
 };
 
-extern int try_set_zone_oom(struct zonelist *zonelist);
-extern void clear_zonelist_oom(struct zonelist *zonelist);
+extern int try_set_zone_oom(struct zonelist *zonelist, gfp_t gfp_flags);
+extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
 
 extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order);
 extern int register_oom_notifier(struct notifier_block *nb);
diff --git a/trunk/include/linux/page-flags.h b/trunk/include/linux/page-flags.h
index b5b30f1c1e59..590cff32415d 100644
--- a/trunk/include/linux/page-flags.h
+++ b/trunk/include/linux/page-flags.h
@@ -6,7 +6,10 @@
 #define PAGE_FLAGS_H
 
 #include <linux/types.h>
+#ifndef __GENERATING_BOUNDS_H
 #include <linux/mm_types.h>
+#include <linux/bounds.h>
+#endif /* !__GENERATING_BOUNDS_H */
 
 /*
  * Various page->flags bits:
@@ -59,77 +62,138 @@
  * extends from the high bits downwards.
  *
  *  | FIELD | ... | FLAGS |
- *  N-1     ^             0
- *          (N-FLAGS_RESERVED)
+ *  N-1           ^       0
+ *               (NR_PAGEFLAGS)
  *
- * The fields area is reserved for fields mapping zone, node and SPARSEMEM
- * section.  The boundry between these two areas is defined by
- * FLAGS_RESERVED which defines the width of the fields section
- * (see linux/mmzone.h).  New flags must _not_ overlap with this area.
+ * The fields area is reserved for fields mapping zone, node (for NUMA) and
+ * SPARSEMEM section (for variants of SPARSEMEM that require section ids like
+ * SPARSEMEM_EXTREME with !SPARSEMEM_VMEMMAP).
  */
-#define PG_locked	 	 0	/* Page is locked. Don't touch. */
-#define PG_error		 1
-#define PG_referenced		 2
-#define PG_uptodate		 3
+enum pageflags {
+	PG_locked,		/* Page is locked. Don't touch. */
+	PG_error,
+	PG_referenced,
+	PG_uptodate,
+	PG_dirty,
+	PG_lru,
+	PG_active,
+	PG_slab,
+	PG_owner_priv_1,	/* Owner use. If pagecache, fs may use*/
+	PG_arch_1,
+	PG_reserved,
+	PG_private,		/* If pagecache, has fs-private data */
+	PG_writeback,		/* Page is under writeback */
+#ifdef CONFIG_PAGEFLAGS_EXTENDED
+	PG_head,		/* A head page */
+	PG_tail,		/* A tail page */
+#else
+	PG_compound,		/* A compound page */
+#endif
+	PG_swapcache,		/* Swap page: swp_entry_t in private */
+	PG_mappedtodisk,	/* Has blocks allocated on-disk */
+	PG_reclaim,		/* To be reclaimed asap */
+	PG_buddy,		/* Page is free, on buddy lists */
+#ifdef CONFIG_IA64_UNCACHED_ALLOCATOR
+	PG_uncached,		/* Page has been mapped as uncached */
+#endif
+	__NR_PAGEFLAGS
+};
+
+#ifndef __GENERATING_BOUNDS_H
+
+/*
+ * Macros to create function definitions for page flags
+ */
+#define TESTPAGEFLAG(uname, lname)					\
+static inline int Page##uname(struct page *page) 			\
+			{ return test_bit(PG_##lname, &page->flags); }
 
-#define PG_dirty	 	 4
-#define PG_lru			 5
-#define PG_active		 6
-#define PG_slab			 7	/* slab debug (Suparna wants this) */
+#define SETPAGEFLAG(uname, lname)					\
+static inline void SetPage##uname(struct page *page)			\
+			{ set_bit(PG_##lname, &page->flags); }
 
-#define PG_owner_priv_1		 8	/* Owner use. If pagecache, fs may use*/
-#define PG_arch_1		 9
-#define PG_reserved		10
-#define PG_private		11	/* If pagecache, has fs-private data */
+#define CLEARPAGEFLAG(uname, lname)					\
+static inline void ClearPage##uname(struct page *page)			\
+			{ clear_bit(PG_##lname, &page->flags); }
 
-#define PG_writeback		12	/* Page is under writeback */
-#define PG_compound		14	/* Part of a compound page */
-#define PG_swapcache		15	/* Swap page: swp_entry_t in private */
+#define __SETPAGEFLAG(uname, lname)					\
+static inline void __SetPage##uname(struct page *page)			\
+			{ __set_bit(PG_##lname, &page->flags); }
 
-#define PG_mappedtodisk		16	/* Has blocks allocated on-disk */
-#define PG_reclaim		17	/* To be reclaimed asap */
-#define PG_buddy		19	/* Page is free, on buddy lists */
+#define __CLEARPAGEFLAG(uname, lname)					\
+static inline void __ClearPage##uname(struct page *page)		\
+			{ __clear_bit(PG_##lname, &page->flags); }
+
+#define TESTSETFLAG(uname, lname)					\
+static inline int TestSetPage##uname(struct page *page)			\
+		{ return test_and_set_bit(PG_##lname, &page->flags); }
+
+#define TESTCLEARFLAG(uname, lname)					\
+static inline int TestClearPage##uname(struct page *page)		\
+		{ return test_and_clear_bit(PG_##lname, &page->flags); }
 
-/* PG_readahead is only used for file reads; PG_reclaim is only for writes */
-#define PG_readahead		PG_reclaim /* Reminder to do async read-ahead */
 
-/* PG_owner_priv_1 users should have descriptive aliases */
-#define PG_checked		PG_owner_priv_1 /* Used by some filesystems */
-#define PG_pinned		PG_owner_priv_1	/* Xen pinned pagetable */
+#define PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname)		\
+	SETPAGEFLAG(uname, lname) CLEARPAGEFLAG(uname, lname)
+
+#define __PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname)		\
+	__SETPAGEFLAG(uname, lname)  __CLEARPAGEFLAG(uname, lname)
+
+#define PAGEFLAG_FALSE(uname) 						\
+static inline int Page##uname(struct page *page) 			\
+			{ return 0; }
+
+#define TESTSCFLAG(uname, lname)					\
+	TESTSETFLAG(uname, lname) TESTCLEARFLAG(uname, lname)
+
+struct page;	/* forward declaration */
+
+PAGEFLAG(Locked, locked) TESTSCFLAG(Locked, locked)
+PAGEFLAG(Error, error)
+PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
+PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
+PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru)
+PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active)
+__PAGEFLAG(Slab, slab)
+PAGEFLAG(Checked, owner_priv_1)		/* Used by some filesystems */
+PAGEFLAG(Pinned, owner_priv_1) TESTSCFLAG(Pinned, owner_priv_1) /* Xen */
+PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
+PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private)
+	__SETPAGEFLAG(Private, private)
 
-#if (BITS_PER_LONG > 32)
 /*
- * 64-bit-only flags build down from bit 31
- *
- * 32 bit  -------------------------------| FIELDS |       FLAGS         |
- * 64 bit  |           FIELDS             | ??????         FLAGS         |
- *         63                            32                              0
+ * Only test-and-set exist for PG_writeback.  The unconditional operators are
+ * risky: they bypass page accounting.
  */
-#define PG_uncached		31	/* Page has been mapped as uncached */
-#endif
+TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback)
+__PAGEFLAG(Buddy, buddy)
+PAGEFLAG(MappedToDisk, mappedtodisk)
 
+/* PG_readahead is only used for file reads; PG_reclaim is only for writes */
+PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim)
+PAGEFLAG(Readahead, reclaim)		/* Reminder to do async read-ahead */
+
+#ifdef CONFIG_HIGHMEM
 /*
- * Manipulation of page state flags
+ * Must use a macro here due to header dependency issues. page_zone() is not
+ * available at this point.
  */
-#define PageLocked(page)		\
-		test_bit(PG_locked, &(page)->flags)
-#define SetPageLocked(page)		\
-		set_bit(PG_locked, &(page)->flags)
-#define TestSetPageLocked(page)		\
-		test_and_set_bit(PG_locked, &(page)->flags)
-#define ClearPageLocked(page)		\
-		clear_bit(PG_locked, &(page)->flags)
-#define TestClearPageLocked(page)	\
-		test_and_clear_bit(PG_locked, &(page)->flags)
-
-#define PageError(page)		test_bit(PG_error, &(page)->flags)
-#define SetPageError(page)	set_bit(PG_error, &(page)->flags)
-#define ClearPageError(page)	clear_bit(PG_error, &(page)->flags)
-
-#define PageReferenced(page)	test_bit(PG_referenced, &(page)->flags)
-#define SetPageReferenced(page)	set_bit(PG_referenced, &(page)->flags)
-#define ClearPageReferenced(page)	clear_bit(PG_referenced, &(page)->flags)
-#define TestClearPageReferenced(page) test_and_clear_bit(PG_referenced, &(page)->flags)
+#define PageHighMem(__p) is_highmem(page_zone(__p))
+#else
+PAGEFLAG_FALSE(HighMem)
+#endif
+
+#ifdef CONFIG_SWAP
+PAGEFLAG(SwapCache, swapcache)
+#else
+PAGEFLAG_FALSE(SwapCache)
+#endif
+
+#ifdef CONFIG_IA64_UNCACHED_ALLOCATOR
+PAGEFLAG(Uncached, uncached)
+#else
+PAGEFLAG_FALSE(Uncached)
+#endif
 
 static inline int PageUptodate(struct page *page)
 {
@@ -177,97 +241,59 @@ static inline void SetPageUptodate(struct page *page)
 #endif
 }
 
-#define ClearPageUptodate(page)	clear_bit(PG_uptodate, &(page)->flags)
-
-#define PageDirty(page)		test_bit(PG_dirty, &(page)->flags)
-#define SetPageDirty(page)	set_bit(PG_dirty, &(page)->flags)
-#define TestSetPageDirty(page)	test_and_set_bit(PG_dirty, &(page)->flags)
-#define ClearPageDirty(page)	clear_bit(PG_dirty, &(page)->flags)
-#define __ClearPageDirty(page)	__clear_bit(PG_dirty, &(page)->flags)
-#define TestClearPageDirty(page) test_and_clear_bit(PG_dirty, &(page)->flags)
-
-#define PageLRU(page)		test_bit(PG_lru, &(page)->flags)
-#define SetPageLRU(page)	set_bit(PG_lru, &(page)->flags)
-#define ClearPageLRU(page)	clear_bit(PG_lru, &(page)->flags)
-#define __ClearPageLRU(page)	__clear_bit(PG_lru, &(page)->flags)
-
-#define PageActive(page)	test_bit(PG_active, &(page)->flags)
-#define SetPageActive(page)	set_bit(PG_active, &(page)->flags)
-#define ClearPageActive(page)	clear_bit(PG_active, &(page)->flags)
-#define __ClearPageActive(page)	__clear_bit(PG_active, &(page)->flags)
-
-#define PageSlab(page)		test_bit(PG_slab, &(page)->flags)
-#define __SetPageSlab(page)	__set_bit(PG_slab, &(page)->flags)
-#define __ClearPageSlab(page)	__clear_bit(PG_slab, &(page)->flags)
-
-#ifdef CONFIG_HIGHMEM
-#define PageHighMem(page)	is_highmem(page_zone(page))
-#else
-#define PageHighMem(page)	0 /* needed to optimize away at compile time */
-#endif
+CLEARPAGEFLAG(Uptodate, uptodate)
 
-#define PageChecked(page)	test_bit(PG_checked, &(page)->flags)
-#define SetPageChecked(page)	set_bit(PG_checked, &(page)->flags)
-#define ClearPageChecked(page)	clear_bit(PG_checked, &(page)->flags)
-
-#define PagePinned(page)	test_bit(PG_pinned, &(page)->flags)
-#define SetPagePinned(page)	set_bit(PG_pinned, &(page)->flags)
-#define ClearPagePinned(page)	clear_bit(PG_pinned, &(page)->flags)
+extern void cancel_dirty_page(struct page *page, unsigned int account_size);
 
-#define PageReserved(page)	test_bit(PG_reserved, &(page)->flags)
-#define SetPageReserved(page)	set_bit(PG_reserved, &(page)->flags)
-#define ClearPageReserved(page)	clear_bit(PG_reserved, &(page)->flags)
-#define __ClearPageReserved(page)	__clear_bit(PG_reserved, &(page)->flags)
+int test_clear_page_writeback(struct page *page);
+int test_set_page_writeback(struct page *page);
 
-#define SetPagePrivate(page)	set_bit(PG_private, &(page)->flags)
-#define ClearPagePrivate(page)	clear_bit(PG_private, &(page)->flags)
-#define PagePrivate(page)	test_bit(PG_private, &(page)->flags)
-#define __SetPagePrivate(page)  __set_bit(PG_private, &(page)->flags)
-#define __ClearPagePrivate(page) __clear_bit(PG_private, &(page)->flags)
+static inline void set_page_writeback(struct page *page)
+{
+	test_set_page_writeback(page);
+}
 
+#ifdef CONFIG_PAGEFLAGS_EXTENDED
 /*
- * Only test-and-set exist for PG_writeback.  The unconditional operators are
- * risky: they bypass page accounting.
+ * System with lots of page flags available. This allows separate
+ * flags for PageHead() and PageTail() checks of compound pages so that bit
+ * tests can be used in performance sensitive paths. PageCompound is
+ * generally not used in hot code paths.
  */
-#define PageWriteback(page)	test_bit(PG_writeback, &(page)->flags)
-#define TestSetPageWriteback(page) test_and_set_bit(PG_writeback,	\
-							&(page)->flags)
-#define TestClearPageWriteback(page) test_and_clear_bit(PG_writeback,	\
-							&(page)->flags)
+__PAGEFLAG(Head, head)
+__PAGEFLAG(Tail, tail)
 
-#define PageBuddy(page)		test_bit(PG_buddy, &(page)->flags)
-#define __SetPageBuddy(page)	__set_bit(PG_buddy, &(page)->flags)
-#define __ClearPageBuddy(page)	__clear_bit(PG_buddy, &(page)->flags)
-
-#define PageMappedToDisk(page)	test_bit(PG_mappedtodisk, &(page)->flags)
-#define SetPageMappedToDisk(page) set_bit(PG_mappedtodisk, &(page)->flags)
-#define ClearPageMappedToDisk(page) clear_bit(PG_mappedtodisk, &(page)->flags)
-
-#define PageReadahead(page)	test_bit(PG_readahead, &(page)->flags)
-#define SetPageReadahead(page)	set_bit(PG_readahead, &(page)->flags)
-#define ClearPageReadahead(page) clear_bit(PG_readahead, &(page)->flags)
-
-#define PageReclaim(page)	test_bit(PG_reclaim, &(page)->flags)
-#define SetPageReclaim(page)	set_bit(PG_reclaim, &(page)->flags)
-#define ClearPageReclaim(page)	clear_bit(PG_reclaim, &(page)->flags)
-#define TestClearPageReclaim(page) test_and_clear_bit(PG_reclaim, &(page)->flags)
+static inline int PageCompound(struct page *page)
+{
+	return page->flags & ((1L << PG_head) | (1L << PG_tail));
 
-#define PageCompound(page)	test_bit(PG_compound, &(page)->flags)
-#define __SetPageCompound(page)	__set_bit(PG_compound, &(page)->flags)
-#define __ClearPageCompound(page) __clear_bit(PG_compound, &(page)->flags)
+}
+#else
+/*
+ * Reduce page flag use as much as possible by overlapping
+ * compound page flags with the flags used for page cache pages. Possible
+ * because PageCompound is always set for compound pages and not for
+ * pages on the LRU and/or pagecache.
+ */
+TESTPAGEFLAG(Compound, compound)
+__PAGEFLAG(Head, compound)
 
 /*
  * PG_reclaim is used in combination with PG_compound to mark the
- * head and tail of a compound page
+ * head and tail of a compound page. This saves one page flag
+ * but makes it impossible to use compound pages for the page cache.
+ * The PG_reclaim bit would have to be used for reclaim or readahead
+ * if compound pages enter the page cache.
  *
  * PG_compound & PG_reclaim	=> Tail page
  * PG_compound & ~PG_reclaim	=> Head page
  */
-
 #define PG_head_tail_mask ((1L << PG_compound) | (1L << PG_reclaim))
 
-#define PageTail(page)	(((page)->flags & PG_head_tail_mask)	\
-				== PG_head_tail_mask)
+static inline int PageTail(struct page *page)
+{
+	return ((page->flags & PG_head_tail_mask) == PG_head_tail_mask);
+}
 
 static inline void __SetPageTail(struct page *page)
 {
@@ -279,33 +305,6 @@ static inline void __ClearPageTail(struct page *page)
 	page->flags &= ~PG_head_tail_mask;
 }
 
-#define PageHead(page)	(((page)->flags & PG_head_tail_mask)	\
-				== (1L << PG_compound))
-#define __SetPageHead(page)	__SetPageCompound(page)
-#define __ClearPageHead(page)	__ClearPageCompound(page)
-
-#ifdef CONFIG_SWAP
-#define PageSwapCache(page)	test_bit(PG_swapcache, &(page)->flags)
-#define SetPageSwapCache(page)	set_bit(PG_swapcache, &(page)->flags)
-#define ClearPageSwapCache(page) clear_bit(PG_swapcache, &(page)->flags)
-#else
-#define PageSwapCache(page)	0
-#endif
-
-#define PageUncached(page)	test_bit(PG_uncached, &(page)->flags)
-#define SetPageUncached(page)	set_bit(PG_uncached, &(page)->flags)
-#define ClearPageUncached(page)	clear_bit(PG_uncached, &(page)->flags)
-
-struct page;	/* forward declaration */
-
-extern void cancel_dirty_page(struct page *page, unsigned int account_size);
-
-int test_clear_page_writeback(struct page *page);
-int test_set_page_writeback(struct page *page);
-
-static inline void set_page_writeback(struct page *page)
-{
-	test_set_page_writeback(page);
-}
-
+#endif /* !PAGEFLAGS_EXTENDED */
+#endif /* !__GENERATING_BOUNDS_H */
 #endif	/* PAGE_FLAGS_H */
diff --git a/trunk/include/linux/percpu.h b/trunk/include/linux/percpu.h
index 1ac969724bb2..d746a2abb322 100644
--- a/trunk/include/linux/percpu.h
+++ b/trunk/include/linux/percpu.h
@@ -4,7 +4,6 @@
 #include <linux/preempt.h>
 #include <linux/slab.h> /* For kmalloc() */
 #include <linux/smp.h>
-#include <linux/string.h> /* For memset() */
 #include <linux/cpumask.h>
 
 #include <asm/percpu.h>
diff --git a/trunk/include/linux/personality.h b/trunk/include/linux/personality.h
index 012cd558189b..a84e9ff9b27e 100644
--- a/trunk/include/linux/personality.h
+++ b/trunk/include/linux/personality.h
@@ -105,10 +105,6 @@ struct exec_domain {
  */
 #define personality(pers)	(pers & PER_MASK)
 
-/*
- * Personality of the currently running process.
- */
-#define get_personality		(current->personality)
 
 /*
  * Change personality of the currently running process.
diff --git a/trunk/include/linux/phantom.h b/trunk/include/linux/phantom.h
index 96f4048a6cc3..02268c54c250 100644
--- a/trunk/include/linux/phantom.h
+++ b/trunk/include/linux/phantom.h
@@ -27,14 +27,17 @@ struct phm_regs {
 
 #define PH_IOC_MAGIC		'p'
 #define PHN_GET_REG		_IOWR(PH_IOC_MAGIC, 0, struct phm_reg *)
-#define PHN_SET_REG		_IOW (PH_IOC_MAGIC, 1, struct phm_reg *)
+#define PHN_SET_REG		_IOW(PH_IOC_MAGIC, 1, struct phm_reg *)
 #define PHN_GET_REGS		_IOWR(PH_IOC_MAGIC, 2, struct phm_regs *)
-#define PHN_SET_REGS		_IOW (PH_IOC_MAGIC, 3, struct phm_regs *)
+#define PHN_SET_REGS		_IOW(PH_IOC_MAGIC, 3, struct phm_regs *)
 /* this ioctl tells the driver, that the caller is not OpenHaptics and might
  * use improved registers update (no more phantom switchoffs when using
  * libphantom) */
-#define PHN_NOT_OH		_IO  (PH_IOC_MAGIC, 4)
-#define PH_IOC_MAXNR		4
+#define PHN_NOT_OH		_IO(PH_IOC_MAGIC, 4)
+#define PHN_GETREG		_IOWR(PH_IOC_MAGIC, 5, struct phm_reg)
+#define PHN_SETREG		_IOW(PH_IOC_MAGIC, 6, struct phm_reg)
+#define PHN_GETREGS		_IOWR(PH_IOC_MAGIC, 7, struct phm_regs)
+#define PHN_SETREGS		_IOW(PH_IOC_MAGIC, 8, struct phm_regs)
 
 #define PHN_CONTROL		0x6     /* control byte in iaddr space */
 #define PHN_CTL_AMP		0x1     /*   switch after torques change */
diff --git a/trunk/include/linux/prctl.h b/trunk/include/linux/prctl.h
index 5c80b1939636..5ad79198d6f9 100644
--- a/trunk/include/linux/prctl.h
+++ b/trunk/include/linux/prctl.h
@@ -16,7 +16,8 @@
 # define PR_UNALIGN_NOPRINT	1	/* silently fix up unaligned user accesses */
 # define PR_UNALIGN_SIGBUS	2	/* generate SIGBUS on unaligned user access */
 
-/* Get/set whether or not to drop capabilities on setuid() away from uid 0 */
+/* Get/set whether or not to drop capabilities on setuid() away from
+ * uid 0 (as per security/commoncap.c) */
 #define PR_GET_KEEPCAPS   7
 #define PR_SET_KEEPCAPS   8
 
@@ -63,7 +64,7 @@
 #define PR_GET_SECCOMP	21
 #define PR_SET_SECCOMP	22
 
-/* Get/set the capability bounding set */
+/* Get/set the capability bounding set (as per security/commoncap.c) */
 #define PR_CAPBSET_READ 23
 #define PR_CAPBSET_DROP 24
 
@@ -73,4 +74,8 @@
 # define PR_TSC_ENABLE		1	/* allow the use of the timestamp counter */
 # define PR_TSC_SIGSEGV		2	/* throw a SIGSEGV instead of reading the TSC */
 
+/* Get/set securebits (as per security/commoncap.c) */
+#define PR_GET_SECUREBITS 27
+#define PR_SET_SECUREBITS 28
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/trunk/include/linux/proc_fs.h b/trunk/include/linux/proc_fs.h
index 9b6c935f69cf..9883bc942262 100644
--- a/trunk/include/linux/proc_fs.h
+++ b/trunk/include/linux/proc_fs.h
@@ -9,7 +9,6 @@
 
 struct net;
 struct completion;
-
 /*
  * The proc filesystem constants/structures
  */
@@ -41,7 +40,7 @@ enum {
  * /proc file has a parent, but "subdir" is NULL for all
  * non-directory entries).
  *
- * "get_info" is called at "read", while "owner" is used to protect module
+ * "owner" is used to protect module
  * from unloading while proc_dir_entry is in use
  */
 
@@ -49,7 +48,6 @@ typedef	int (read_proc_t)(char *page, char **start, off_t off,
 			  int count, int *eof, void *data);
 typedef	int (write_proc_t)(struct file *file, const char __user *buffer,
 			   unsigned long count, void *data);
-typedef int (get_info_t)(char *, char **, off_t, int);
 
 struct proc_dir_entry {
 	unsigned int low_ino;
@@ -70,7 +68,6 @@ struct proc_dir_entry {
 	 * somewhere.
 	 */
 	const struct file_operations *proc_fops;
-	get_info_t *get_info;
 	struct module *owner;
 	struct proc_dir_entry *next, *parent, *subdir;
 	void *data;
@@ -97,10 +94,6 @@ struct vmcore {
 
 #ifdef CONFIG_PROC_FS
 
-extern struct proc_dir_entry proc_root;
-extern struct proc_dir_entry *proc_root_fs;
-extern struct proc_dir_entry *proc_bus;
-extern struct proc_dir_entry *proc_root_driver;
 extern struct proc_dir_entry *proc_root_kcore;
 
 extern spinlock_t proc_subdir_lock;
@@ -123,9 +116,10 @@ void de_put(struct proc_dir_entry *de);
 
 extern struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode,
 						struct proc_dir_entry *parent);
-struct proc_dir_entry *proc_create(const char *name, mode_t mode,
+struct proc_dir_entry *proc_create_data(const char *name, mode_t mode,
 				struct proc_dir_entry *parent,
-				const struct file_operations *proc_fops);
+				const struct file_operations *proc_fops,
+				void *data);
 extern void remove_proc_entry(const char *name, struct proc_dir_entry *parent);
 
 extern struct vfsmount *proc_mnt;
@@ -180,6 +174,12 @@ extern struct proc_dir_entry *proc_mkdir(const char *,struct proc_dir_entry *);
 extern struct proc_dir_entry *proc_mkdir_mode(const char *name, mode_t mode,
 			struct proc_dir_entry *parent);
 
+static inline struct proc_dir_entry *proc_create(const char *name, mode_t mode,
+	struct proc_dir_entry *parent, const struct file_operations *proc_fops)
+{
+	return proc_create_data(name, mode, parent, proc_fops, NULL);
+}
+
 static inline struct proc_dir_entry *create_proc_read_entry(const char *name,
 	mode_t mode, struct proc_dir_entry *base, 
 	read_proc_t *read_proc, void * data)
@@ -192,24 +192,19 @@ static inline struct proc_dir_entry *create_proc_read_entry(const char *name,
 	return res;
 }
  
-static inline struct proc_dir_entry *create_proc_info_entry(const char *name,
-	mode_t mode, struct proc_dir_entry *base, get_info_t *get_info)
-{
-	struct proc_dir_entry *res=create_proc_entry(name,mode,base);
-	if (res) res->get_info=get_info;
-	return res;
-}
-
 extern struct proc_dir_entry *proc_net_fops_create(struct net *net,
 	const char *name, mode_t mode, const struct file_operations *fops);
 extern void proc_net_remove(struct net *net, const char *name);
 extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name,
 	struct proc_dir_entry *parent);
 
-#else
+/* While the {get|set|dup}_mm_exe_file functions are for mm_structs, they are
+ * only needed to implement /proc/<pid>|self/exe so we define them here. */
+extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
+extern struct file *get_mm_exe_file(struct mm_struct *mm);
+extern void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm);
 
-#define proc_root_driver NULL
-#define proc_bus NULL
+#else
 
 #define proc_net_fops_create(net, name, mode, fops)  ({ (void)(mode), NULL; })
 static inline void proc_net_remove(struct net *net, const char *name) {}
@@ -226,6 +221,12 @@ static inline struct proc_dir_entry *proc_create(const char *name,
 {
 	return NULL;
 }
+static inline struct proc_dir_entry *proc_create_data(const char *name,
+	mode_t mode, struct proc_dir_entry *parent,
+	const struct file_operations *proc_fops, void *data)
+{
+	return NULL;
+}
 #define remove_proc_entry(name, parent) do {} while (0)
 
 static inline struct proc_dir_entry *proc_symlink(const char *name,
@@ -236,16 +237,11 @@ static inline struct proc_dir_entry *proc_mkdir(const char *name,
 static inline struct proc_dir_entry *create_proc_read_entry(const char *name,
 	mode_t mode, struct proc_dir_entry *base, 
 	read_proc_t *read_proc, void * data) { return NULL; }
-static inline struct proc_dir_entry *create_proc_info_entry(const char *name,
-	mode_t mode, struct proc_dir_entry *base, get_info_t *get_info)
-	{ return NULL; }
 
 struct tty_driver;
 static inline void proc_tty_register_driver(struct tty_driver *driver) {};
 static inline void proc_tty_unregister_driver(struct tty_driver *driver) {};
 
-extern struct proc_dir_entry proc_root;
-
 static inline int pid_ns_prepare_proc(struct pid_namespace *ns)
 {
 	return 0;
@@ -255,6 +251,19 @@ static inline void pid_ns_release_proc(struct pid_namespace *ns)
 {
 }
 
+static inline void set_mm_exe_file(struct mm_struct *mm,
+				   struct file *new_exe_file)
+{}
+
+static inline struct file *get_mm_exe_file(struct mm_struct *mm)
+{
+	return NULL;
+}
+
+static inline void dup_mm_exe_file(struct mm_struct *oldmm,
+	       			   struct mm_struct *newmm)
+{}
+
 #endif /* CONFIG_PROC_FS */
 
 #if !defined(CONFIG_PROC_KCORE)
diff --git a/trunk/include/linux/quota.h b/trunk/include/linux/quota.h
index eb560d031acd..52e49dce6584 100644
--- a/trunk/include/linux/quota.h
+++ b/trunk/include/linux/quota.h
@@ -202,10 +202,14 @@ struct quota_format_type;
 
 struct mem_dqinfo {
 	struct quota_format_type *dqi_format;
+	int dqi_fmt_id;		/* Id of the dqi_format - used when turning
+				 * quotas on after remount RW */
 	struct list_head dqi_dirty_list;	/* List of dirty dquots */
 	unsigned long dqi_flags;
 	unsigned int dqi_bgrace;
 	unsigned int dqi_igrace;
+	qsize_t dqi_maxblimit;
+	qsize_t dqi_maxilimit;
 	union {
 		struct v1_mem_dqinfo v1_i;
 		struct v2_mem_dqinfo v2_i;
@@ -296,8 +300,8 @@ struct dquot_operations {
 
 /* Operations handling requests from userspace */
 struct quotactl_ops {
-	int (*quota_on)(struct super_block *, int, int, char *);
-	int (*quota_off)(struct super_block *, int);
+	int (*quota_on)(struct super_block *, int, int, char *, int);
+	int (*quota_off)(struct super_block *, int, int);
 	int (*quota_sync)(struct super_block *, int);
 	int (*get_info)(struct super_block *, int, struct if_dqinfo *);
 	int (*set_info)(struct super_block *, int, struct if_dqinfo *);
@@ -318,6 +322,10 @@ struct quota_format_type {
 
 #define DQUOT_USR_ENABLED	0x01		/* User diskquotas enabled */
 #define DQUOT_GRP_ENABLED	0x02		/* Group diskquotas enabled */
+#define DQUOT_USR_SUSPENDED	0x04		/* User diskquotas are off, but
+						 * we have necessary info in
+						 * memory to turn them on */
+#define DQUOT_GRP_SUSPENDED	0x08		/* The same for group quotas */
 
 struct quota_info {
 	unsigned int flags;			/* Flags for diskquotas on this device */
@@ -329,17 +337,16 @@ struct quota_info {
 	struct quota_format_ops *ops[MAXQUOTAS];	/* Operations for each type */
 };
 
-/* Inline would be better but we need to dereference super_block which is not defined yet */
-int mark_dquot_dirty(struct dquot *dquot);
-
-#define dquot_dirty(dquot) test_bit(DQ_MOD_B, &(dquot)->dq_flags)
-
 #define sb_has_quota_enabled(sb, type) ((type)==USRQUOTA ? \
 	(sb_dqopt(sb)->flags & DQUOT_USR_ENABLED) : (sb_dqopt(sb)->flags & DQUOT_GRP_ENABLED))
 
 #define sb_any_quota_enabled(sb) (sb_has_quota_enabled(sb, USRQUOTA) | \
 				  sb_has_quota_enabled(sb, GRPQUOTA))
 
+#define sb_has_quota_suspended(sb, type) \
+	((type) == USRQUOTA ? (sb_dqopt(sb)->flags & DQUOT_USR_SUSPENDED) : \
+			      (sb_dqopt(sb)->flags & DQUOT_GRP_SUSPENDED))
+
 int register_quota_format(struct quota_format_type *fmt);
 void unregister_quota_format(struct quota_format_type *fmt);
 
diff --git a/trunk/include/linux/quotaops.h b/trunk/include/linux/quotaops.h
index 5110201a4159..f86702053853 100644
--- a/trunk/include/linux/quotaops.h
+++ b/trunk/include/linux/quotaops.h
@@ -37,11 +37,11 @@ extern int dquot_release(struct dquot *dquot);
 extern int dquot_commit_info(struct super_block *sb, int type);
 extern int dquot_mark_dquot_dirty(struct dquot *dquot);
 
-extern int vfs_quota_on(struct super_block *sb, int type, int format_id, char *path);
+extern int vfs_quota_on(struct super_block *sb, int type, int format_id,
+		char *path, int remount);
 extern int vfs_quota_on_mount(struct super_block *sb, char *qf_name,
 		int format_id, int type);
-extern int vfs_quota_off(struct super_block *sb, int type);
-#define vfs_quota_off_mount(sb, type) vfs_quota_off(sb, type)
+extern int vfs_quota_off(struct super_block *sb, int type, int remount);
 extern int vfs_quota_sync(struct super_block *sb, int type);
 extern int vfs_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii);
 extern int vfs_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii);
@@ -59,7 +59,7 @@ extern struct quotactl_ops vfs_quotactl_ops;
 
 /* It is better to call this function outside of any transaction as it might
  * need a lot of space in journal for dquot structure allocation. */
-static __inline__ void DQUOT_INIT(struct inode *inode)
+static inline void DQUOT_INIT(struct inode *inode)
 {
 	BUG_ON(!inode->i_sb);
 	if (sb_any_quota_enabled(inode->i_sb) && !IS_NOQUOTA(inode))
@@ -67,7 +67,7 @@ static __inline__ void DQUOT_INIT(struct inode *inode)
 }
 
 /* The same as with DQUOT_INIT */
-static __inline__ void DQUOT_DROP(struct inode *inode)
+static inline void DQUOT_DROP(struct inode *inode)
 {
 	/* Here we can get arbitrary inode from clear_inode() so we have
 	 * to be careful. OTOH we don't need locking as quota operations
@@ -90,7 +90,7 @@ static __inline__ void DQUOT_DROP(struct inode *inode)
 
 /* The following allocation/freeing/transfer functions *must* be called inside
  * a transaction (deadlocks possible otherwise) */
-static __inline__ int DQUOT_PREALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr)
+static inline int DQUOT_PREALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr)
 {
 	if (sb_any_quota_enabled(inode->i_sb)) {
 		/* Used space is updated in alloc_space() */
@@ -102,7 +102,7 @@ static __inline__ int DQUOT_PREALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t
 	return 0;
 }
 
-static __inline__ int DQUOT_PREALLOC_SPACE(struct inode *inode, qsize_t nr)
+static inline int DQUOT_PREALLOC_SPACE(struct inode *inode, qsize_t nr)
 {
 	int ret;
         if (!(ret =  DQUOT_PREALLOC_SPACE_NODIRTY(inode, nr)))
@@ -110,7 +110,7 @@ static __inline__ int DQUOT_PREALLOC_SPACE(struct inode *inode, qsize_t nr)
 	return ret;
 }
 
-static __inline__ int DQUOT_ALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr)
+static inline int DQUOT_ALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr)
 {
 	if (sb_any_quota_enabled(inode->i_sb)) {
 		/* Used space is updated in alloc_space() */
@@ -122,7 +122,7 @@ static __inline__ int DQUOT_ALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr)
 	return 0;
 }
 
-static __inline__ int DQUOT_ALLOC_SPACE(struct inode *inode, qsize_t nr)
+static inline int DQUOT_ALLOC_SPACE(struct inode *inode, qsize_t nr)
 {
 	int ret;
 	if (!(ret = DQUOT_ALLOC_SPACE_NODIRTY(inode, nr)))
@@ -130,7 +130,7 @@ static __inline__ int DQUOT_ALLOC_SPACE(struct inode *inode, qsize_t nr)
 	return ret;
 }
 
-static __inline__ int DQUOT_ALLOC_INODE(struct inode *inode)
+static inline int DQUOT_ALLOC_INODE(struct inode *inode)
 {
 	if (sb_any_quota_enabled(inode->i_sb)) {
 		DQUOT_INIT(inode);
@@ -140,7 +140,7 @@ static __inline__ int DQUOT_ALLOC_INODE(struct inode *inode)
 	return 0;
 }
 
-static __inline__ void DQUOT_FREE_SPACE_NODIRTY(struct inode *inode, qsize_t nr)
+static inline void DQUOT_FREE_SPACE_NODIRTY(struct inode *inode, qsize_t nr)
 {
 	if (sb_any_quota_enabled(inode->i_sb))
 		inode->i_sb->dq_op->free_space(inode, nr);
@@ -148,19 +148,19 @@ static __inline__ void DQUOT_FREE_SPACE_NODIRTY(struct inode *inode, qsize_t nr)
 		inode_sub_bytes(inode, nr);
 }
 
-static __inline__ void DQUOT_FREE_SPACE(struct inode *inode, qsize_t nr)
+static inline void DQUOT_FREE_SPACE(struct inode *inode, qsize_t nr)
 {
 	DQUOT_FREE_SPACE_NODIRTY(inode, nr);
 	mark_inode_dirty(inode);
 }
 
-static __inline__ void DQUOT_FREE_INODE(struct inode *inode)
+static inline void DQUOT_FREE_INODE(struct inode *inode)
 {
 	if (sb_any_quota_enabled(inode->i_sb))
 		inode->i_sb->dq_op->free_inode(inode, 1);
 }
 
-static __inline__ int DQUOT_TRANSFER(struct inode *inode, struct iattr *iattr)
+static inline int DQUOT_TRANSFER(struct inode *inode, struct iattr *iattr)
 {
 	if (sb_any_quota_enabled(inode->i_sb) && !IS_NOQUOTA(inode)) {
 		DQUOT_INIT(inode);
@@ -171,14 +171,32 @@ static __inline__ int DQUOT_TRANSFER(struct inode *inode, struct iattr *iattr)
 }
 
 /* The following two functions cannot be called inside a transaction */
-#define DQUOT_SYNC(sb)	sync_dquots(sb, -1)
+static inline void DQUOT_SYNC(struct super_block *sb)
+{
+	sync_dquots(sb, -1);
+}
 
-static __inline__ int DQUOT_OFF(struct super_block *sb)
+static inline int DQUOT_OFF(struct super_block *sb, int remount)
 {
 	int ret = -ENOSYS;
 
-	if (sb_any_quota_enabled(sb) && sb->s_qcop && sb->s_qcop->quota_off)
-		ret = sb->s_qcop->quota_off(sb, -1);
+	if (sb->s_qcop && sb->s_qcop->quota_off)
+		ret = sb->s_qcop->quota_off(sb, -1, remount);
+	return ret;
+}
+
+static inline int DQUOT_ON_REMOUNT(struct super_block *sb)
+{
+	int cnt;
+	int ret = 0, err;
+
+	if (!sb->s_qcop || !sb->s_qcop->quota_on)
+		return -ENOSYS;
+	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
+		err = sb->s_qcop->quota_on(sb, cnt, 0, NULL, 1);
+		if (err < 0 && !ret)
+			ret = err;
+	}
 	return ret;
 }
 
@@ -189,13 +207,43 @@ static __inline__ int DQUOT_OFF(struct super_block *sb)
  */
 #define sb_dquot_ops				(NULL)
 #define sb_quotactl_ops				(NULL)
-#define DQUOT_INIT(inode)			do { } while(0)
-#define DQUOT_DROP(inode)			do { } while(0)
-#define DQUOT_ALLOC_INODE(inode)		(0)
-#define DQUOT_FREE_INODE(inode)			do { } while(0)
-#define DQUOT_SYNC(sb)				do { } while(0)
-#define DQUOT_OFF(sb)				do { } while(0)
-#define DQUOT_TRANSFER(inode, iattr)		(0)
+
+static inline void DQUOT_INIT(struct inode *inode)
+{
+}
+
+static inline void DQUOT_DROP(struct inode *inode)
+{
+}
+
+static inline int DQUOT_ALLOC_INODE(struct inode *inode)
+{
+	return 0;
+}
+
+static inline void DQUOT_FREE_INODE(struct inode *inode)
+{
+}
+
+static inline void DQUOT_SYNC(struct super_block *sb)
+{
+}
+
+static inline int DQUOT_OFF(struct super_block *sb, int remount)
+{
+	return 0;
+}
+
+static inline int DQUOT_ON_REMOUNT(struct super_block *sb)
+{
+	return 0;
+}
+
+static inline int DQUOT_TRANSFER(struct inode *inode, struct iattr *iattr)
+{
+	return 0;
+}
+
 static inline int DQUOT_PREALLOC_SPACE_NODIRTY(struct inode *inode, qsize_t nr)
 {
 	inode_add_bytes(inode, nr);
@@ -235,11 +283,38 @@ static inline void DQUOT_FREE_SPACE(struct inode *inode, qsize_t nr)
 
 #endif /* CONFIG_QUOTA */
 
-#define DQUOT_PREALLOC_BLOCK_NODIRTY(inode, nr)	DQUOT_PREALLOC_SPACE_NODIRTY(inode, ((qsize_t)(nr)) << (inode)->i_sb->s_blocksize_bits)
-#define DQUOT_PREALLOC_BLOCK(inode, nr)	DQUOT_PREALLOC_SPACE(inode, ((qsize_t)(nr)) << (inode)->i_sb->s_blocksize_bits)
-#define DQUOT_ALLOC_BLOCK_NODIRTY(inode, nr) DQUOT_ALLOC_SPACE_NODIRTY(inode, ((qsize_t)(nr)) << (inode)->i_sb->s_blocksize_bits)
-#define DQUOT_ALLOC_BLOCK(inode, nr) DQUOT_ALLOC_SPACE(inode, ((qsize_t)(nr)) << (inode)->i_sb->s_blocksize_bits)
-#define DQUOT_FREE_BLOCK_NODIRTY(inode, nr) DQUOT_FREE_SPACE_NODIRTY(inode, ((qsize_t)(nr)) << (inode)->i_sb->s_blocksize_bits)
-#define DQUOT_FREE_BLOCK(inode, nr) DQUOT_FREE_SPACE(inode, ((qsize_t)(nr)) << (inode)->i_sb->s_blocksize_bits)
+static inline int DQUOT_PREALLOC_BLOCK_NODIRTY(struct inode *inode, qsize_t nr)
+{
+	return DQUOT_PREALLOC_SPACE_NODIRTY(inode,
+			nr << inode->i_sb->s_blocksize_bits);
+}
+
+static inline int DQUOT_PREALLOC_BLOCK(struct inode *inode, qsize_t nr)
+{
+	return DQUOT_PREALLOC_SPACE(inode,
+			nr << inode->i_sb->s_blocksize_bits);
+}
+
+static inline int DQUOT_ALLOC_BLOCK_NODIRTY(struct inode *inode, qsize_t nr)
+{
+	return DQUOT_ALLOC_SPACE_NODIRTY(inode,
+			nr << inode->i_sb->s_blocksize_bits);
+}
+
+static inline int DQUOT_ALLOC_BLOCK(struct inode *inode, qsize_t nr)
+{
+	return DQUOT_ALLOC_SPACE(inode,
+			nr << inode->i_sb->s_blocksize_bits);
+}
+
+static inline void DQUOT_FREE_BLOCK_NODIRTY(struct inode *inode, qsize_t nr)
+{
+	DQUOT_FREE_SPACE_NODIRTY(inode, nr << inode->i_sb->s_blocksize_bits);
+}
+
+static inline void DQUOT_FREE_BLOCK(struct inode *inode, qsize_t nr)
+{
+	DQUOT_FREE_SPACE(inode, nr << inode->i_sb->s_blocksize_bits);
+}
 
 #endif /* _LINUX_QUOTAOPS_ */
diff --git a/trunk/include/linux/raid/raid5.h b/trunk/include/linux/raid/raid5.h
index 93678f57ccbe..f0827d31ae6f 100644
--- a/trunk/include/linux/raid/raid5.h
+++ b/trunk/include/linux/raid/raid5.h
@@ -252,6 +252,8 @@ struct r6_state {
 #define	STRIPE_EXPANDING	9
 #define	STRIPE_EXPAND_SOURCE	10
 #define	STRIPE_EXPAND_READY	11
+#define	STRIPE_IO_STARTED	12 /* do not count towards 'bypass_count' */
+#define	STRIPE_FULL_WRITE	13 /* all blocks are set to be overwritten */
 /*
  * Operations flags (in issue order)
  */
@@ -316,12 +318,17 @@ struct raid5_private_data {
 	int			previous_raid_disks;
 
 	struct list_head	handle_list; /* stripes needing handling */
+	struct list_head	hold_list; /* preread ready stripes */
 	struct list_head	delayed_list; /* stripes that have plugged requests */
 	struct list_head	bitmap_list; /* stripes delaying awaiting bitmap update */
 	struct bio		*retry_read_aligned; /* currently retrying aligned bios   */
 	struct bio		*retry_read_aligned_list; /* aligned bios retry list  */
 	atomic_t		preread_active_stripes; /* stripes with scheduled io */
 	atomic_t		active_aligned_reads;
+	atomic_t		pending_full_writes; /* full write backlog */
+	int			bypass_count; /* bypassed prereads */
+	int			bypass_threshold; /* preread nice */
+	struct list_head	*last_hold; /* detect hold_list promotions */
 
 	atomic_t		reshape_stripes; /* stripes with pending writes for reshape */
 	/* unfortunately we need two cache names as we temporarily have
diff --git a/trunk/include/linux/reiserfs_fs.h b/trunk/include/linux/reiserfs_fs.h
index 8e7eff2cd0ab..4aacaeecb56f 100644
--- a/trunk/include/linux/reiserfs_fs.h
+++ b/trunk/include/linux/reiserfs_fs.h
@@ -2176,6 +2176,7 @@ int reiserfs_ioctl(struct inode *inode, struct file *filp,
 		   unsigned int cmd, unsigned long arg);
 long reiserfs_compat_ioctl(struct file *filp,
 		   unsigned int cmd, unsigned long arg);
+int reiserfs_unpack(struct inode *inode, struct file *filp);
 
 /* ioctl's command */
 #define REISERFS_IOC_UNPACK		_IOW(0xCD,1,long)
diff --git a/trunk/include/linux/res_counter.h b/trunk/include/linux/res_counter.h
index 61363ce896d5..6d9e1fca098c 100644
--- a/trunk/include/linux/res_counter.h
+++ b/trunk/include/linux/res_counter.h
@@ -9,6 +9,8 @@
  *
  * Author: Pavel Emelianov <xemul@openvz.org>
  *
+ * See Documentation/controllers/resource_counter.txt for more
+ * info about what this counter is.
  */
 
 #include <linux/cgroup.h>
@@ -24,6 +26,10 @@ struct res_counter {
 	 * the current resource consumption level
 	 */
 	unsigned long long usage;
+	/*
+	 * the maximal value of the usage from the counter creation
+	 */
+	unsigned long long max_usage;
 	/*
 	 * the limit that usage cannot exceed
 	 */
@@ -39,8 +45,9 @@ struct res_counter {
 	spinlock_t lock;
 };
 
-/*
+/**
  * Helpers to interact with userspace
+ * res_counter_read_u64() - returns the value of the specified member.
  * res_counter_read/_write - put/get the specified fields from the
  * res_counter struct to/from the user
  *
@@ -51,6 +58,8 @@ struct res_counter {
  * @pos:     and the offset.
  */
 
+u64 res_counter_read_u64(struct res_counter *counter, int member);
+
 ssize_t res_counter_read(struct res_counter *counter, int member,
 		const char __user *buf, size_t nbytes, loff_t *pos,
 		int (*read_strategy)(unsigned long long val, char *s));
@@ -64,6 +73,7 @@ ssize_t res_counter_write(struct res_counter *counter, int member,
 
 enum {
 	RES_USAGE,
+	RES_MAX_USAGE,
 	RES_LIMIT,
 	RES_FAILCNT,
 };
@@ -124,4 +134,21 @@ static inline bool res_counter_check_under_limit(struct res_counter *cnt)
 	return ret;
 }
 
+static inline void res_counter_reset_max(struct res_counter *cnt)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cnt->lock, flags);
+	cnt->max_usage = cnt->usage;
+	spin_unlock_irqrestore(&cnt->lock, flags);
+}
+
+static inline void res_counter_reset_failcnt(struct res_counter *cnt)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cnt->lock, flags);
+	cnt->failcnt = 0;
+	spin_unlock_irqrestore(&cnt->lock, flags);
+}
 #endif
diff --git a/trunk/include/linux/resource.h b/trunk/include/linux/resource.h
index ae13db714742..aaa423a6f3d9 100644
--- a/trunk/include/linux/resource.h
+++ b/trunk/include/linux/resource.h
@@ -19,6 +19,7 @@ struct task_struct;
 #define	RUSAGE_SELF	0
 #define	RUSAGE_CHILDREN	(-1)
 #define RUSAGE_BOTH	(-2)		/* sys_wait4() uses this */
+#define	RUSAGE_THREAD	1		/* only the calling thread */
 
 struct	rusage {
 	struct timeval ru_utime;	/* user time used */
diff --git a/trunk/include/linux/rio.h b/trunk/include/linux/rio.h
index 68e3f6853fa6..cfb66bbc0f27 100644
--- a/trunk/include/linux/rio.h
+++ b/trunk/include/linux/rio.h
@@ -23,7 +23,6 @@
 #include <linux/device.h>
 #include <linux/rio_regs.h>
 
-#define RIO_ANY_DESTID		0xff
 #define RIO_NO_HOPCOUNT		-1
 #define RIO_INVALID_DESTID	0xffff
 
@@ -39,11 +38,8 @@
 					   entry is invalid (no route
 					   exists for the device ID) */
 
-#ifdef CONFIG_RAPIDIO_8_BIT_TRANSPORT
-#define RIO_MAX_ROUTE_ENTRIES	(1 << 8)
-#else
-#define RIO_MAX_ROUTE_ENTRIES	(1 << 16)
-#endif
+#define RIO_MAX_ROUTE_ENTRIES(size)	(size ? (1 << 16) : (1 << 8))
+#define RIO_ANY_DESTID(size)		(size ? 0xffff : 0xff)
 
 #define RIO_MAX_MBOX		4
 #define RIO_MAX_MSG_SIZE	0x1000
@@ -149,6 +145,11 @@ struct rio_dbell {
 	void *dev_id;
 };
 
+enum rio_phy_type {
+	RIO_PHY_PARALLEL,
+	RIO_PHY_SERIAL,
+};
+
 /**
  * struct rio_mport - RIO master port info
  * @dbells: List of doorbell events
@@ -163,6 +164,7 @@ struct rio_dbell {
  * @id: Port ID, unique among all ports
  * @index: Port index, unique among all port interfaces of the same type
  * @name: Port name string
+ * @priv: Master port private data
  */
 struct rio_mport {
 	struct list_head dbells;	/* list of doorbell events */
@@ -177,7 +179,13 @@ struct rio_mport {
 	unsigned char id;	/* port ID, unique among all ports */
 	unsigned char index;	/* port index, unique among all port
 				   interfaces of the same type */
+	unsigned int sys_size;	/* RapidIO common transport system size.
+				 * 0 - Small size. 256 devices.
+				 * 1 - Large size, 65536 devices.
+				 */
+	enum rio_phy_type phy_type;	/* RapidIO phy type */
 	unsigned char name[40];
+	void *priv;		/* Master port private data */
 };
 
 /**
@@ -211,7 +219,7 @@ struct rio_switch {
 	u16 switchid;
 	u16 hopcount;
 	u16 destid;
-	u8 route_table[RIO_MAX_ROUTE_ENTRIES];
+	u8 *route_table;
 	int (*add_entry) (struct rio_mport * mport, u16 destid, u8 hopcount,
 			  u16 table, u16 route_destid, u8 route_port);
 	int (*get_entry) (struct rio_mport * mport, u16 destid, u8 hopcount,
@@ -229,13 +237,15 @@ struct rio_switch {
  * @dsend: Callback to send a doorbell message.
  */
 struct rio_ops {
-	int (*lcread) (int index, u32 offset, int len, u32 * data);
-	int (*lcwrite) (int index, u32 offset, int len, u32 data);
-	int (*cread) (int index, u16 destid, u8 hopcount, u32 offset, int len,
-		      u32 * data);
-	int (*cwrite) (int index, u16 destid, u8 hopcount, u32 offset, int len,
-		       u32 data);
-	int (*dsend) (int index, u16 destid, u16 data);
+	int (*lcread) (struct rio_mport *mport, int index, u32 offset, int len,
+			u32 *data);
+	int (*lcwrite) (struct rio_mport *mport, int index, u32 offset, int len,
+			u32 data);
+	int (*cread) (struct rio_mport *mport, int index, u16 destid,
+			u8 hopcount, u32 offset, int len, u32 *data);
+	int (*cwrite) (struct rio_mport *mport, int index, u16 destid,
+			u8 hopcount, u32 offset, int len, u32 data);
+	int (*dsend) (struct rio_mport *mport, int index, u16 destid, u16 data);
 };
 
 #define RIO_RESOURCE_MEM	0x00000100
diff --git a/trunk/include/linux/sched.h b/trunk/include/linux/sched.h
index d0bd97044abd..1d02babdb2c7 100644
--- a/trunk/include/linux/sched.h
+++ b/trunk/include/linux/sched.h
@@ -68,7 +68,6 @@ struct sched_param {
 #include <linux/smp.h>
 #include <linux/sem.h>
 #include <linux/signal.h>
-#include <linux/securebits.h>
 #include <linux/fs_struct.h>
 #include <linux/compiler.h>
 #include <linux/completion.h>
@@ -1133,7 +1132,7 @@ struct task_struct {
 	gid_t gid,egid,sgid,fsgid;
 	struct group_info *group_info;
 	kernel_cap_t   cap_effective, cap_inheritable, cap_permitted, cap_bset;
-	unsigned keep_capabilities:1;
+	unsigned securebits;
 	struct user_struct *user;
 #ifdef CONFIG_KEYS
 	struct key *request_key_auth;	/* assumed request_key authority */
@@ -1798,6 +1797,8 @@ extern void mmput(struct mm_struct *);
 extern struct mm_struct *get_task_mm(struct task_struct *task);
 /* Remove the current tasks stale references to the old mm_struct */
 extern void mm_release(struct task_struct *, struct mm_struct *);
+/* Allocate a new mm structure and copy contents from tsk->mm */
+extern struct mm_struct *dup_mm(struct task_struct *tsk);
 
 extern int  copy_thread(int, unsigned long, unsigned long, unsigned long, struct task_struct *, struct pt_regs *);
 extern void flush_thread(void);
@@ -2147,6 +2148,19 @@ static inline void migration_init(void)
 #define TASK_SIZE_OF(tsk)	TASK_SIZE
 #endif
 
+#ifdef CONFIG_MM_OWNER
+extern void mm_update_next_owner(struct mm_struct *mm);
+extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
+#else
+static inline void mm_update_next_owner(struct mm_struct *mm)
+{
+}
+
+static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
+{
+}
+#endif /* CONFIG_MM_OWNER */
+
 #endif /* __KERNEL__ */
 
 #endif
diff --git a/trunk/include/linux/securebits.h b/trunk/include/linux/securebits.h
index 5b0617840fa4..c1f19dbceb05 100644
--- a/trunk/include/linux/securebits.h
+++ b/trunk/include/linux/securebits.h
@@ -3,28 +3,39 @@
 
 #define SECUREBITS_DEFAULT 0x00000000
 
-extern unsigned securebits;
-
 /* When set UID 0 has no special privileges. When unset, we support
    inheritance of root-permissions and suid-root executable under
    compatibility mode. We raise the effective and inheritable bitmasks
    *of the executable file* if the effective uid of the new process is
    0. If the real uid is 0, we raise the inheritable bitmask of the
    executable file. */
-#define SECURE_NOROOT            0
+#define SECURE_NOROOT			0
+#define SECURE_NOROOT_LOCKED		1  /* make bit-0 immutable */
 
 /* When set, setuid to/from uid 0 does not trigger capability-"fixes"
    to be compatible with old programs relying on set*uid to loose
    privileges. When unset, setuid doesn't change privileges. */
-#define SECURE_NO_SETUID_FIXUP   2
+#define SECURE_NO_SETUID_FIXUP		2
+#define SECURE_NO_SETUID_FIXUP_LOCKED	3  /* make bit-2 immutable */
+
+/* When set, a process can retain its capabilities even after
+   transitioning to a non-root user (the set-uid fixup suppressed by
+   bit 2). Bit-4 is cleared when a process calls exec(); setting both
+   bit 4 and 5 will create a barrier through exec that no exec()'d
+   child can use this feature again. */
+#define SECURE_KEEP_CAPS		4
+#define SECURE_KEEP_CAPS_LOCKED		5  /* make bit-4 immutable */
 
 /* Each securesetting is implemented using two bits. One bit specify
    whether the setting is on or off. The other bit specify whether the
    setting is fixed or not. A setting which is fixed cannot be changed
    from user-level. */
+#define issecure_mask(X)	(1 << (X))
+#define issecure(X)		(issecure_mask(X) & current->securebits)
 
-#define issecure(X) ( (1 << (X+1)) & SECUREBITS_DEFAULT ? 	\
-		      (1 << (X)) & SECUREBITS_DEFAULT :		\
-		      (1 << (X)) & securebits )
+#define SECURE_ALL_BITS		(issecure_mask(SECURE_NOROOT) | \
+				 issecure_mask(SECURE_NO_SETUID_FIXUP) | \
+				 issecure_mask(SECURE_KEEP_CAPS))
+#define SECURE_ALL_LOCKS	(SECURE_ALL_BITS << 1)
 
 #endif /* !_LINUX_SECUREBITS_H */
diff --git a/trunk/include/linux/security.h b/trunk/include/linux/security.h
index 53a34539382a..adb09d893ae0 100644
--- a/trunk/include/linux/security.h
+++ b/trunk/include/linux/security.h
@@ -34,8 +34,6 @@
 #include <linux/xfrm.h>
 #include <net/flow.h>
 
-extern unsigned securebits;
-
 /* Maximum number of letters for an LSM name string */
 #define SECURITY_NAME_MAX	10
 
@@ -46,25 +44,28 @@ struct audit_krule;
  * These functions are in security/capability.c and are used
  * as the default capabilities functions
  */
-extern int cap_capable (struct task_struct *tsk, int cap);
-extern int cap_settime (struct timespec *ts, struct timezone *tz);
-extern int cap_ptrace (struct task_struct *parent, struct task_struct *child);
-extern int cap_capget (struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted);
-extern int cap_capset_check (struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted);
-extern void cap_capset_set (struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted);
-extern int cap_bprm_set_security (struct linux_binprm *bprm);
-extern void cap_bprm_apply_creds (struct linux_binprm *bprm, int unsafe);
+extern int cap_capable(struct task_struct *tsk, int cap);
+extern int cap_settime(struct timespec *ts, struct timezone *tz);
+extern int cap_ptrace(struct task_struct *parent, struct task_struct *child);
+extern int cap_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted);
+extern int cap_capset_check(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted);
+extern void cap_capset_set(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted);
+extern int cap_bprm_set_security(struct linux_binprm *bprm);
+extern void cap_bprm_apply_creds(struct linux_binprm *bprm, int unsafe);
 extern int cap_bprm_secureexec(struct linux_binprm *bprm);
-extern int cap_inode_setxattr(struct dentry *dentry, char *name, void *value, size_t size, int flags);
-extern int cap_inode_removexattr(struct dentry *dentry, char *name);
+extern int cap_inode_setxattr(struct dentry *dentry, const char *name,
+			      const void *value, size_t size, int flags);
+extern int cap_inode_removexattr(struct dentry *dentry, const char *name);
 extern int cap_inode_need_killpriv(struct dentry *dentry);
 extern int cap_inode_killpriv(struct dentry *dentry);
-extern int cap_task_post_setuid (uid_t old_ruid, uid_t old_euid, uid_t old_suid, int flags);
-extern void cap_task_reparent_to_init (struct task_struct *p);
-extern int cap_task_setscheduler (struct task_struct *p, int policy, struct sched_param *lp);
-extern int cap_task_setioprio (struct task_struct *p, int ioprio);
-extern int cap_task_setnice (struct task_struct *p, int nice);
-extern int cap_syslog (int type);
+extern int cap_task_post_setuid(uid_t old_ruid, uid_t old_euid, uid_t old_suid, int flags);
+extern void cap_task_reparent_to_init(struct task_struct *p);
+extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
+			  unsigned long arg4, unsigned long arg5, long *rc_p);
+extern int cap_task_setscheduler(struct task_struct *p, int policy, struct sched_param *lp);
+extern int cap_task_setioprio(struct task_struct *p, int ioprio);
+extern int cap_task_setnice(struct task_struct *p, int nice);
+extern int cap_syslog(int type);
 extern int cap_vm_enough_memory(struct mm_struct *mm, long pages);
 
 struct msghdr;
@@ -128,7 +129,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
 {
 	int i;
 	if (opts->mnt_opts)
-		for(i = 0; i < opts->num_mnt_opts; i++)
+		for (i = 0; i < opts->num_mnt_opts; i++)
 			kfree(opts->mnt_opts[i]);
 	kfree(opts->mnt_opts);
 	opts->mnt_opts = NULL;
@@ -190,21 +191,21 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	@bprm contains the linux_binprm structure.
  *	Return 0 if the hook is successful and permission is granted.
  * @bprm_check_security:
- * 	This hook mediates the point when a search for a binary handler	will
- * 	begin.  It allows a check the @bprm->security value which is set in
- * 	the preceding set_security call.  The primary difference from
- * 	set_security is that the argv list and envp list are reliably
- * 	available in @bprm.  This hook may be called multiple times
- * 	during a single execve; and in each pass set_security is called
- * 	first.
- * 	@bprm contains the linux_binprm structure.
+ *	This hook mediates the point when a search for a binary handler	will
+ *	begin.  It allows a check the @bprm->security value which is set in
+ *	the preceding set_security call.  The primary difference from
+ *	set_security is that the argv list and envp list are reliably
+ *	available in @bprm.  This hook may be called multiple times
+ *	during a single execve; and in each pass set_security is called
+ *	first.
+ *	@bprm contains the linux_binprm structure.
  *	Return 0 if the hook is successful and permission is granted.
  * @bprm_secureexec:
- *      Return a boolean value (0 or 1) indicating whether a "secure exec" 
- *      is required.  The flag is passed in the auxiliary table
- *      on the initial stack to the ELF interpreter to indicate whether libc 
- *      should enable secure mode.
- *      @bprm contains the linux_binprm structure.
+ *	Return a boolean value (0 or 1) indicating whether a "secure exec"
+ *	is required.  The flag is passed in the auxiliary table
+ *	on the initial stack to the ELF interpreter to indicate whether libc
+ *	should enable secure mode.
+ *	@bprm contains the linux_binprm structure.
  *
  * Security hooks for filesystem operations.
  *
@@ -221,7 +222,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	Check permission before obtaining filesystem statistics for the @mnt
  *	mountpoint.
  *	@dentry is a handle on the superblock for the filesystem.
- *	Return 0 if permission is granted.  
+ *	Return 0 if permission is granted.
  * @sb_mount:
  *	Check permission before an object specified by @dev_name is mounted on
  *	the mount point named by @nd.  For an ordinary mount, @dev_name
@@ -282,12 +283,12 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  * @sb_pivotroot:
  *	Check permission before pivoting the root filesystem.
  *	@old_path contains the path for the new location of the current root (put_old).
- *      @new_path contains the path for the new root (new_root).
+ *	@new_path contains the path for the new root (new_root).
  *	Return 0 if permission is granted.
  * @sb_post_pivotroot:
  *	Update module state after a successful pivot.
  *	@old_path contains the path for the old root.
- *      @new_path contains the path for the new root.
+ *	@new_path contains the path for the new root.
  * @sb_get_mnt_opts:
  *	Get the security relevant mount options used for a superblock
  *	@sb the superblock to get security mount options from
@@ -316,9 +317,9 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  * @inode_free_security:
  *	@inode contains the inode structure.
  *	Deallocate the inode security structure and set @inode->i_security to
- *	NULL. 
+ *	NULL.
  * @inode_init_security:
- * 	Obtain the security attribute name suffix and value to set on a newly
+ *	Obtain the security attribute name suffix and value to set on a newly
  *	created inode and set up the incore security field for the new inode.
  *	This hook is called by the fs code as part of the inode creation
  *	transaction and provides for atomic labeling of the inode, unlike
@@ -349,7 +350,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	@new_dentry contains the dentry structure for the new link.
  *	Return 0 if permission is granted.
  * @inode_unlink:
- *	Check the permission to remove a hard link to a file. 
+ *	Check the permission to remove a hard link to a file.
  *	@dir contains the inode structure of parent directory of the file.
  *	@dentry contains the dentry structure for file to be unlinked.
  *	Return 0 if permission is granted.
@@ -361,7 +362,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	Return 0 if permission is granted.
  * @inode_mkdir:
  *	Check permissions to create a new directory in the existing directory
- *	associated with inode strcture @dir. 
+ *	associated with inode strcture @dir.
  *	@dir containst the inode structure of parent of the directory to be created.
  *	@dentry contains the dentry structure of new directory.
  *	@mode contains the mode of new directory.
@@ -406,7 +407,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	called when the actual read/write operations are performed.
  *	@inode contains the inode structure to check.
  *	@mask contains the permission mask.
- *     @nd contains the nameidata (may be NULL).
+ *	@nd contains the nameidata (may be NULL).
  *	Return 0 if permission is granted.
  * @inode_setattr:
  *	Check permission before setting file attributes.  Note that the kernel
@@ -428,24 +429,24 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	can use this hook to release any persistent label associated with the
  *	inode.
  * @inode_setxattr:
- * 	Check permission before setting the extended attributes
- * 	@value identified by @name for @dentry.
- * 	Return 0 if permission is granted.
+ *	Check permission before setting the extended attributes
+ *	@value identified by @name for @dentry.
+ *	Return 0 if permission is granted.
  * @inode_post_setxattr:
- * 	Update inode security field after successful setxattr operation.
- * 	@value identified by @name for @dentry.
+ *	Update inode security field after successful setxattr operation.
+ *	@value identified by @name for @dentry.
  * @inode_getxattr:
- * 	Check permission before obtaining the extended attributes
- * 	identified by @name for @dentry.
- * 	Return 0 if permission is granted.
+ *	Check permission before obtaining the extended attributes
+ *	identified by @name for @dentry.
+ *	Return 0 if permission is granted.
  * @inode_listxattr:
- * 	Check permission before obtaining the list of extended attribute 
- * 	names for @dentry.
- * 	Return 0 if permission is granted.
+ *	Check permission before obtaining the list of extended attribute
+ *	names for @dentry.
+ *	Return 0 if permission is granted.
  * @inode_removexattr:
- * 	Check permission before removing the extended attribute
- * 	identified by @name for @dentry.
- * 	Return 0 if permission is granted.
+ *	Check permission before removing the extended attribute
+ *	identified by @name for @dentry.
+ *	Return 0 if permission is granted.
  * @inode_getsecurity:
  *	Retrieve a copy of the extended attribute representation of the
  *	security label associated with @name for @inode via @buffer.  Note that
@@ -457,7 +458,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	Set the security label associated with @name for @inode from the
  *	extended attribute value @value.  @size indicates the size of the
  *	@value in bytes.  @flags may be XATTR_CREATE, XATTR_REPLACE, or 0.
- *	Note that @name is the remainder of the attribute name after the 
+ *	Note that @name is the remainder of the attribute name after the
  *	security. prefix has been removed.
  *	Return 0 on success.
  * @inode_listsecurity:
@@ -564,7 +565,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	struct file, so the file structure (and associated security information)
  *	can always be obtained:
  *		container_of(fown, struct file, f_owner)
- * 	@tsk contains the structure of task receiving signal.
+ *	@tsk contains the structure of task receiving signal.
  *	@fown contains the file owner information.
  *	@sig is the signal that will be sent.  When 0, kernel sends SIGIO.
  *	Return 0 if permission is granted.
@@ -720,14 +721,16 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	@arg3 contains a argument.
  *	@arg4 contains a argument.
  *	@arg5 contains a argument.
- *	Return 0 if permission is granted.
+ *      @rc_p contains a pointer to communicate back the forced return code
+ *	Return 0 if permission is granted, and non-zero if the security module
+ *      has taken responsibility (setting *rc_p) for the prctl call.
  * @task_reparent_to_init:
- * 	Set the security attributes in @p->security for a kernel thread that
- * 	is being reparented to the init task.
+ *	Set the security attributes in @p->security for a kernel thread that
+ *	is being reparented to the init task.
  *	@p contains the task_struct for the kernel thread.
  * @task_to_inode:
- * 	Set the security attributes for an inode based on an associated task's
- * 	security attributes, e.g. for /proc/pid inodes.
+ *	Set the security attributes for an inode based on an associated task's
+ *	security attributes, e.g. for /proc/pid inodes.
  *	@p contains the task_struct for the task.
  *	@inode contains the inode structure for the inode.
  *
@@ -737,7 +740,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	Save security information for a netlink message so that permission
  *	checking can be performed when the message is processed.  The security
  *	information can be saved using the eff_cap field of the
- *      netlink_skb_parms structure.  Also may be used to provide fine
+ *	netlink_skb_parms structure.  Also may be used to provide fine
  *	grained control over message transmission.
  *	@sk associated sock of task sending the message.,
  *	@skb contains the sk_buff structure for the netlink message.
@@ -805,14 +808,14 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	@sock contains the socket structure.
  *	@address contains the address to bind to.
  *	@addrlen contains the length of address.
- *	Return 0 if permission is granted.  
+ *	Return 0 if permission is granted.
  * @socket_connect:
  *	Check permission before socket protocol layer connect operation
  *	attempts to connect socket @sock to a remote address, @address.
  *	@sock contains the socket structure.
  *	@address contains the address of remote endpoint.
  *	@addrlen contains the length of address.
- *	Return 0 if permission is granted.  
+ *	Return 0 if permission is granted.
  * @socket_listen:
  *	Check permission before socket protocol layer listen operation.
  *	@sock contains the socket structure.
@@ -842,7 +845,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	@msg contains the message structure.
  *	@size contains the size of message structure.
  *	@flags contains the operational flags.
- *	Return 0 if permission is granted.  
+ *	Return 0 if permission is granted.
  * @socket_getsockname:
  *	Check permission before the local address (name) of the socket object
  *	@sock is retrieved.
@@ -866,7 +869,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	@sock contains the socket structure.
  *	@level contains the protocol level to set options for.
  *	@optname contains the name of the option to set.
- *	Return 0 if permission is granted.  
+ *	Return 0 if permission is granted.
  * @socket_shutdown:
  *	Checks permission before all or part of a connection on the socket
  *	@sock is shut down.
@@ -893,19 +896,19 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	Return 0 if all is well, otherwise, typical getsockopt return
  *	values.
  * @socket_getpeersec_dgram:
- * 	This hook allows the security module to provide peer socket security
- * 	state for udp sockets on a per-packet basis to userspace via
- * 	getsockopt SO_GETPEERSEC.  The application must first have indicated
- * 	the IP_PASSSEC option via getsockopt.  It can then retrieve the
- * 	security state returned by this hook for a packet via the SCM_SECURITY
- * 	ancillary message type.
- * 	@skb is the skbuff for the packet being queried
- * 	@secdata is a pointer to a buffer in which to copy the security data
- * 	@seclen is the maximum length for @secdata
- * 	Return 0 on success, error on failure.
+ *	This hook allows the security module to provide peer socket security
+ *	state for udp sockets on a per-packet basis to userspace via
+ *	getsockopt SO_GETPEERSEC.  The application must first have indicated
+ *	the IP_PASSSEC option via getsockopt.  It can then retrieve the
+ *	security state returned by this hook for a packet via the SCM_SECURITY
+ *	ancillary message type.
+ *	@skb is the skbuff for the packet being queried
+ *	@secdata is a pointer to a buffer in which to copy the security data
+ *	@seclen is the maximum length for @secdata
+ *	Return 0 on success, error on failure.
  * @sk_alloc_security:
- *      Allocate and attach a security structure to the sk->sk_security field,
- *      which is used to copy security attributes between local stream sockets.
+ *	Allocate and attach a security structure to the sk->sk_security field,
+ *	which is used to copy security attributes between local stream sockets.
  * @sk_free_security:
  *	Deallocate security structure.
  * @sk_clone_security:
@@ -920,7 +923,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  * @inet_csk_clone:
  *	Sets the new child socket's sid to the openreq sid.
  * @inet_conn_established:
- *     Sets the connection's peersid to the secmark on skb.
+ *	Sets the connection's peersid to the secmark on skb.
  * @req_classify_flow:
  *	Sets the flow's sid to the openreq sid.
  *
@@ -999,13 +1002,24 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	No return value.
  * @key_permission:
  *	See whether a specific operational right is granted to a process on a
- *      key.
+ *	key.
  *	@key_ref refers to the key (key pointer + possession attribute bit).
  *	@context points to the process to provide the context against which to
- *       evaluate the security data on the key.
+ *	evaluate the security data on the key.
  *	@perm describes the combination of permissions required of this key.
  *	Return 1 if permission granted, 0 if permission denied and -ve it the
- *      normal permissions model should be effected.
+ *	normal permissions model should be effected.
+ * @key_getsecurity:
+ *	Get a textual representation of the security context attached to a key
+ *	for the purposes of honouring KEYCTL_GETSECURITY.  This function
+ *	allocates the storage for the NUL-terminated string and the caller
+ *	should free it.
+ *	@key points to the key to be queried.
+ *	@_buffer points to a pointer that should be set to point to the
+ *	 resulting string (if no label or an error occurs).
+ *	Return the length of the string (including terminating NUL) or -ve if
+ *      an error.
+ *	May also return 0 (and a NULL buffer pointer) if there is no label.
  *
  * Security hooks affecting all System V IPC operations.
  *
@@ -1056,7 +1070,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	The @msq may be NULL, e.g. for IPC_INFO or MSG_INFO.
  *	@msq contains the message queue to act upon.  May be NULL.
  *	@cmd contains the operation to be performed.
- *	Return 0 if permission is granted.  
+ *	Return 0 if permission is granted.
  * @msg_queue_msgsnd:
  *	Check permission before a message, @msg, is enqueued on the message
  *	queue, @msq.
@@ -1066,8 +1080,8 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	Return 0 if permission is granted.
  * @msg_queue_msgrcv:
  *	Check permission before a message, @msg, is removed from the message
- *	queue, @msq.  The @target task structure contains a pointer to the 
- *	process that will be receiving the message (not equal to the current 
+ *	queue, @msq.  The @target task structure contains a pointer to the
+ *	process that will be receiving the message (not equal to the current
  *	process when inline receives are being performed).
  *	@msq contains the message queue to retrieve message from.
  *	@msg contains the message destination.
@@ -1132,15 +1146,15 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	Return 0 if permission is granted.
  * @sem_semctl:
  *	Check permission when a semaphore operation specified by @cmd is to be
- *	performed on the semaphore @sma.  The @sma may be NULL, e.g. for 
+ *	performed on the semaphore @sma.  The @sma may be NULL, e.g. for
  *	IPC_INFO or SEM_INFO.
  *	@sma contains the semaphore structure.  May be NULL.
  *	@cmd contains the operation to be performed.
  *	Return 0 if permission is granted.
  * @sem_semop
  *	Check permissions before performing operations on members of the
- *	semaphore set @sma.  If the @alter flag is nonzero, the semaphore set 
- *      may be modified.
+ *	semaphore set @sma.  If the @alter flag is nonzero, the semaphore set
+ *	may be modified.
  *	@sma contains the semaphore structure.
  *	@sops contains the operations to perform.
  *	@nsops contains the number of operations to perform.
@@ -1211,7 +1225,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  * @syslog:
  *	Check permission before accessing the kernel message ring or changing
  *	logging to the console.
- *	See the syslog(2) manual page for an explanation of the @type values.  
+ *	See the syslog(2) manual page for an explanation of the @type values.
  *	@type contains the type of action.
  *	Return 0 if permission is granted.
  * @settime:
@@ -1223,22 +1237,22 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  * @vm_enough_memory:
  *	Check permissions for allocating a new virtual mapping.
  *	@mm contains the mm struct it is being added to.
- *      @pages contains the number of pages.
+ *	@pages contains the number of pages.
  *	Return 0 if permission is granted.
  *
  * @register_security:
- * 	allow module stacking.
- * 	@name contains the name of the security module being stacked.
- * 	@ops contains a pointer to the struct security_operations of the module to stack.
- * 
+ *	allow module stacking.
+ *	@name contains the name of the security module being stacked.
+ *	@ops contains a pointer to the struct security_operations of the module to stack.
+ *
  * @secid_to_secctx:
  *	Convert secid to security context.
  *	@secid contains the security ID.
  *	@secdata contains the pointer that stores the converted security context.
  * @secctx_to_secid:
- *      Convert security context to secid.
- *      @secid contains the pointer to the generated security ID.
- *      @secdata contains the security context.
+ *	Convert security context to secid.
+ *	@secid contains the pointer to the generated security ID.
+ *	@secdata contains the security context.
  *
  * @release_secctx:
  *	Release the security context.
@@ -1281,49 +1295,49 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
 struct security_operations {
 	char name[SECURITY_NAME_MAX + 1];
 
-	int (*ptrace) (struct task_struct * parent, struct task_struct * child);
-	int (*capget) (struct task_struct * target,
-		       kernel_cap_t * effective,
-		       kernel_cap_t * inheritable, kernel_cap_t * permitted);
-	int (*capset_check) (struct task_struct * target,
-			     kernel_cap_t * effective,
-			     kernel_cap_t * inheritable,
-			     kernel_cap_t * permitted);
-	void (*capset_set) (struct task_struct * target,
-			    kernel_cap_t * effective,
-			    kernel_cap_t * inheritable,
-			    kernel_cap_t * permitted);
-	int (*capable) (struct task_struct * tsk, int cap);
-	int (*acct) (struct file * file);
-	int (*sysctl) (struct ctl_table * table, int op);
-	int (*quotactl) (int cmds, int type, int id, struct super_block * sb);
-	int (*quota_on) (struct dentry * dentry);
+	int (*ptrace) (struct task_struct *parent, struct task_struct *child);
+	int (*capget) (struct task_struct *target,
+		       kernel_cap_t *effective,
+		       kernel_cap_t *inheritable, kernel_cap_t *permitted);
+	int (*capset_check) (struct task_struct *target,
+			     kernel_cap_t *effective,
+			     kernel_cap_t *inheritable,
+			     kernel_cap_t *permitted);
+	void (*capset_set) (struct task_struct *target,
+			    kernel_cap_t *effective,
+			    kernel_cap_t *inheritable,
+			    kernel_cap_t *permitted);
+	int (*capable) (struct task_struct *tsk, int cap);
+	int (*acct) (struct file *file);
+	int (*sysctl) (struct ctl_table *table, int op);
+	int (*quotactl) (int cmds, int type, int id, struct super_block *sb);
+	int (*quota_on) (struct dentry *dentry);
 	int (*syslog) (int type);
 	int (*settime) (struct timespec *ts, struct timezone *tz);
 	int (*vm_enough_memory) (struct mm_struct *mm, long pages);
 
-	int (*bprm_alloc_security) (struct linux_binprm * bprm);
-	void (*bprm_free_security) (struct linux_binprm * bprm);
-	void (*bprm_apply_creds) (struct linux_binprm * bprm, int unsafe);
-	void (*bprm_post_apply_creds) (struct linux_binprm * bprm);
-	int (*bprm_set_security) (struct linux_binprm * bprm);
-	int (*bprm_check_security) (struct linux_binprm * bprm);
-	int (*bprm_secureexec) (struct linux_binprm * bprm);
-
-	int (*sb_alloc_security) (struct super_block * sb);
-	void (*sb_free_security) (struct super_block * sb);
-	int (*sb_copy_data)(char *orig, char *copy);
+	int (*bprm_alloc_security) (struct linux_binprm *bprm);
+	void (*bprm_free_security) (struct linux_binprm *bprm);
+	void (*bprm_apply_creds) (struct linux_binprm *bprm, int unsafe);
+	void (*bprm_post_apply_creds) (struct linux_binprm *bprm);
+	int (*bprm_set_security) (struct linux_binprm *bprm);
+	int (*bprm_check_security) (struct linux_binprm *bprm);
+	int (*bprm_secureexec) (struct linux_binprm *bprm);
+
+	int (*sb_alloc_security) (struct super_block *sb);
+	void (*sb_free_security) (struct super_block *sb);
+	int (*sb_copy_data) (char *orig, char *copy);
 	int (*sb_kern_mount) (struct super_block *sb, void *data);
 	int (*sb_statfs) (struct dentry *dentry);
 	int (*sb_mount) (char *dev_name, struct path *path,
 			 char *type, unsigned long flags, void *data);
-	int (*sb_check_sb) (struct vfsmount * mnt, struct path *path);
-	int (*sb_umount) (struct vfsmount * mnt, int flags);
-	void (*sb_umount_close) (struct vfsmount * mnt);
-	void (*sb_umount_busy) (struct vfsmount * mnt);
-	void (*sb_post_remount) (struct vfsmount * mnt,
+	int (*sb_check_sb) (struct vfsmount *mnt, struct path *path);
+	int (*sb_umount) (struct vfsmount *mnt, int flags);
+	void (*sb_umount_close) (struct vfsmount *mnt);
+	void (*sb_umount_busy) (struct vfsmount *mnt);
+	void (*sb_post_remount) (struct vfsmount *mnt,
 				 unsigned long flags, void *data);
-	void (*sb_post_addmount) (struct vfsmount * mnt,
+	void (*sb_post_addmount) (struct vfsmount *mnt,
 				  struct path *mountpoint);
 	int (*sb_pivotroot) (struct path *old_path,
 			     struct path *new_path);
@@ -1337,177 +1351,177 @@ struct security_operations {
 				   struct super_block *newsb);
 	int (*sb_parse_opts_str) (char *options, struct security_mnt_opts *opts);
 
-	int (*inode_alloc_security) (struct inode *inode);	
+	int (*inode_alloc_security) (struct inode *inode);
 	void (*inode_free_security) (struct inode *inode);
 	int (*inode_init_security) (struct inode *inode, struct inode *dir,
 				    char **name, void **value, size_t *len);
 	int (*inode_create) (struct inode *dir,
-	                     struct dentry *dentry, int mode);
+			     struct dentry *dentry, int mode);
 	int (*inode_link) (struct dentry *old_dentry,
-	                   struct inode *dir, struct dentry *new_dentry);
+			   struct inode *dir, struct dentry *new_dentry);
 	int (*inode_unlink) (struct inode *dir, struct dentry *dentry);
 	int (*inode_symlink) (struct inode *dir,
-	                      struct dentry *dentry, const char *old_name);
+			      struct dentry *dentry, const char *old_name);
 	int (*inode_mkdir) (struct inode *dir, struct dentry *dentry, int mode);
 	int (*inode_rmdir) (struct inode *dir, struct dentry *dentry);
 	int (*inode_mknod) (struct inode *dir, struct dentry *dentry,
-	                    int mode, dev_t dev);
+			    int mode, dev_t dev);
 	int (*inode_rename) (struct inode *old_dir, struct dentry *old_dentry,
-	                     struct inode *new_dir, struct dentry *new_dentry);
+			     struct inode *new_dir, struct dentry *new_dentry);
 	int (*inode_readlink) (struct dentry *dentry);
 	int (*inode_follow_link) (struct dentry *dentry, struct nameidata *nd);
 	int (*inode_permission) (struct inode *inode, int mask, struct nameidata *nd);
 	int (*inode_setattr)	(struct dentry *dentry, struct iattr *attr);
 	int (*inode_getattr) (struct vfsmount *mnt, struct dentry *dentry);
-        void (*inode_delete) (struct inode *inode);
-	int (*inode_setxattr) (struct dentry *dentry, char *name, void *value,
-			       size_t size, int flags);
-	void (*inode_post_setxattr) (struct dentry *dentry, char *name, void *value,
-				     size_t size, int flags);
-	int (*inode_getxattr) (struct dentry *dentry, char *name);
+	void (*inode_delete) (struct inode *inode);
+	int (*inode_setxattr) (struct dentry *dentry, const char *name,
+			       const void *value, size_t size, int flags);
+	void (*inode_post_setxattr) (struct dentry *dentry, const char *name,
+				     const void *value, size_t size, int flags);
+	int (*inode_getxattr) (struct dentry *dentry, const char *name);
 	int (*inode_listxattr) (struct dentry *dentry);
-	int (*inode_removexattr) (struct dentry *dentry, char *name);
+	int (*inode_removexattr) (struct dentry *dentry, const char *name);
 	int (*inode_need_killpriv) (struct dentry *dentry);
 	int (*inode_killpriv) (struct dentry *dentry);
-	int (*inode_getsecurity)(const struct inode *inode, const char *name, void **buffer, bool alloc);
-  	int (*inode_setsecurity)(struct inode *inode, const char *name, const void *value, size_t size, int flags);
-  	int (*inode_listsecurity)(struct inode *inode, char *buffer, size_t buffer_size);
-	void (*inode_getsecid)(const struct inode *inode, u32 *secid);
-
-	int (*file_permission) (struct file * file, int mask);
-	int (*file_alloc_security) (struct file * file);
-	void (*file_free_security) (struct file * file);
-	int (*file_ioctl) (struct file * file, unsigned int cmd,
+	int (*inode_getsecurity) (const struct inode *inode, const char *name, void **buffer, bool alloc);
+	int (*inode_setsecurity) (struct inode *inode, const char *name, const void *value, size_t size, int flags);
+	int (*inode_listsecurity) (struct inode *inode, char *buffer, size_t buffer_size);
+	void (*inode_getsecid) (const struct inode *inode, u32 *secid);
+
+	int (*file_permission) (struct file *file, int mask);
+	int (*file_alloc_security) (struct file *file);
+	void (*file_free_security) (struct file *file);
+	int (*file_ioctl) (struct file *file, unsigned int cmd,
 			   unsigned long arg);
-	int (*file_mmap) (struct file * file,
+	int (*file_mmap) (struct file *file,
 			  unsigned long reqprot, unsigned long prot,
 			  unsigned long flags, unsigned long addr,
 			  unsigned long addr_only);
-	int (*file_mprotect) (struct vm_area_struct * vma,
+	int (*file_mprotect) (struct vm_area_struct *vma,
 			      unsigned long reqprot,
 			      unsigned long prot);
-	int (*file_lock) (struct file * file, unsigned int cmd);
-	int (*file_fcntl) (struct file * file, unsigned int cmd,
+	int (*file_lock) (struct file *file, unsigned int cmd);
+	int (*file_fcntl) (struct file *file, unsigned int cmd,
 			   unsigned long arg);
-	int (*file_set_fowner) (struct file * file);
-	int (*file_send_sigiotask) (struct task_struct * tsk,
-				    struct fown_struct * fown, int sig);
-	int (*file_receive) (struct file * file);
-	int (*dentry_open)  (struct file *file);
+	int (*file_set_fowner) (struct file *file);
+	int (*file_send_sigiotask) (struct task_struct *tsk,
+				    struct fown_struct *fown, int sig);
+	int (*file_receive) (struct file *file);
+	int (*dentry_open) (struct file *file);
 
 	int (*task_create) (unsigned long clone_flags);
-	int (*task_alloc_security) (struct task_struct * p);
-	void (*task_free_security) (struct task_struct * p);
+	int (*task_alloc_security) (struct task_struct *p);
+	void (*task_free_security) (struct task_struct *p);
 	int (*task_setuid) (uid_t id0, uid_t id1, uid_t id2, int flags);
 	int (*task_post_setuid) (uid_t old_ruid /* or fsuid */ ,
 				 uid_t old_euid, uid_t old_suid, int flags);
 	int (*task_setgid) (gid_t id0, gid_t id1, gid_t id2, int flags);
-	int (*task_setpgid) (struct task_struct * p, pid_t pgid);
-	int (*task_getpgid) (struct task_struct * p);
-	int (*task_getsid) (struct task_struct * p);
-	void (*task_getsecid) (struct task_struct * p, u32 * secid);
+	int (*task_setpgid) (struct task_struct *p, pid_t pgid);
+	int (*task_getpgid) (struct task_struct *p);
+	int (*task_getsid) (struct task_struct *p);
+	void (*task_getsecid) (struct task_struct *p, u32 *secid);
 	int (*task_setgroups) (struct group_info *group_info);
-	int (*task_setnice) (struct task_struct * p, int nice);
-	int (*task_setioprio) (struct task_struct * p, int ioprio);
-	int (*task_getioprio) (struct task_struct * p);
-	int (*task_setrlimit) (unsigned int resource, struct rlimit * new_rlim);
-	int (*task_setscheduler) (struct task_struct * p, int policy,
-				  struct sched_param * lp);
-	int (*task_getscheduler) (struct task_struct * p);
-	int (*task_movememory) (struct task_struct * p);
-	int (*task_kill) (struct task_struct * p,
-			  struct siginfo * info, int sig, u32 secid);
-	int (*task_wait) (struct task_struct * p);
+	int (*task_setnice) (struct task_struct *p, int nice);
+	int (*task_setioprio) (struct task_struct *p, int ioprio);
+	int (*task_getioprio) (struct task_struct *p);
+	int (*task_setrlimit) (unsigned int resource, struct rlimit *new_rlim);
+	int (*task_setscheduler) (struct task_struct *p, int policy,
+				  struct sched_param *lp);
+	int (*task_getscheduler) (struct task_struct *p);
+	int (*task_movememory) (struct task_struct *p);
+	int (*task_kill) (struct task_struct *p,
+			  struct siginfo *info, int sig, u32 secid);
+	int (*task_wait) (struct task_struct *p);
 	int (*task_prctl) (int option, unsigned long arg2,
 			   unsigned long arg3, unsigned long arg4,
-			   unsigned long arg5);
-	void (*task_reparent_to_init) (struct task_struct * p);
-	void (*task_to_inode)(struct task_struct *p, struct inode *inode);
+			   unsigned long arg5, long *rc_p);
+	void (*task_reparent_to_init) (struct task_struct *p);
+	void (*task_to_inode) (struct task_struct *p, struct inode *inode);
 
-	int (*ipc_permission) (struct kern_ipc_perm * ipcp, short flag);
+	int (*ipc_permission) (struct kern_ipc_perm *ipcp, short flag);
 	void (*ipc_getsecid) (struct kern_ipc_perm *ipcp, u32 *secid);
 
-	int (*msg_msg_alloc_security) (struct msg_msg * msg);
-	void (*msg_msg_free_security) (struct msg_msg * msg);
-
-	int (*msg_queue_alloc_security) (struct msg_queue * msq);
-	void (*msg_queue_free_security) (struct msg_queue * msq);
-	int (*msg_queue_associate) (struct msg_queue * msq, int msqflg);
-	int (*msg_queue_msgctl) (struct msg_queue * msq, int cmd);
-	int (*msg_queue_msgsnd) (struct msg_queue * msq,
-				 struct msg_msg * msg, int msqflg);
-	int (*msg_queue_msgrcv) (struct msg_queue * msq,
-				 struct msg_msg * msg,
-				 struct task_struct * target,
+	int (*msg_msg_alloc_security) (struct msg_msg *msg);
+	void (*msg_msg_free_security) (struct msg_msg *msg);
+
+	int (*msg_queue_alloc_security) (struct msg_queue *msq);
+	void (*msg_queue_free_security) (struct msg_queue *msq);
+	int (*msg_queue_associate) (struct msg_queue *msq, int msqflg);
+	int (*msg_queue_msgctl) (struct msg_queue *msq, int cmd);
+	int (*msg_queue_msgsnd) (struct msg_queue *msq,
+				 struct msg_msg *msg, int msqflg);
+	int (*msg_queue_msgrcv) (struct msg_queue *msq,
+				 struct msg_msg *msg,
+				 struct task_struct *target,
 				 long type, int mode);
 
-	int (*shm_alloc_security) (struct shmid_kernel * shp);
-	void (*shm_free_security) (struct shmid_kernel * shp);
-	int (*shm_associate) (struct shmid_kernel * shp, int shmflg);
-	int (*shm_shmctl) (struct shmid_kernel * shp, int cmd);
-	int (*shm_shmat) (struct shmid_kernel * shp, 
+	int (*shm_alloc_security) (struct shmid_kernel *shp);
+	void (*shm_free_security) (struct shmid_kernel *shp);
+	int (*shm_associate) (struct shmid_kernel *shp, int shmflg);
+	int (*shm_shmctl) (struct shmid_kernel *shp, int cmd);
+	int (*shm_shmat) (struct shmid_kernel *shp,
 			  char __user *shmaddr, int shmflg);
 
-	int (*sem_alloc_security) (struct sem_array * sma);
-	void (*sem_free_security) (struct sem_array * sma);
-	int (*sem_associate) (struct sem_array * sma, int semflg);
-	int (*sem_semctl) (struct sem_array * sma, int cmd);
-	int (*sem_semop) (struct sem_array * sma, 
-			  struct sembuf * sops, unsigned nsops, int alter);
+	int (*sem_alloc_security) (struct sem_array *sma);
+	void (*sem_free_security) (struct sem_array *sma);
+	int (*sem_associate) (struct sem_array *sma, int semflg);
+	int (*sem_semctl) (struct sem_array *sma, int cmd);
+	int (*sem_semop) (struct sem_array *sma,
+			  struct sembuf *sops, unsigned nsops, int alter);
 
-	int (*netlink_send) (struct sock * sk, struct sk_buff * skb);
-	int (*netlink_recv) (struct sk_buff * skb, int cap);
+	int (*netlink_send) (struct sock *sk, struct sk_buff *skb);
+	int (*netlink_recv) (struct sk_buff *skb, int cap);
 
 	/* allow module stacking */
 	int (*register_security) (const char *name,
-	                          struct security_operations *ops);
+				  struct security_operations *ops);
 
 	void (*d_instantiate) (struct dentry *dentry, struct inode *inode);
 
- 	int (*getprocattr)(struct task_struct *p, char *name, char **value);
- 	int (*setprocattr)(struct task_struct *p, char *name, void *value, size_t size);
-	int (*secid_to_secctx)(u32 secid, char **secdata, u32 *seclen);
-	int (*secctx_to_secid)(char *secdata, u32 seclen, u32 *secid);
-	void (*release_secctx)(char *secdata, u32 seclen);
+	int (*getprocattr) (struct task_struct *p, char *name, char **value);
+	int (*setprocattr) (struct task_struct *p, char *name, void *value, size_t size);
+	int (*secid_to_secctx) (u32 secid, char **secdata, u32 *seclen);
+	int (*secctx_to_secid) (char *secdata, u32 seclen, u32 *secid);
+	void (*release_secctx) (char *secdata, u32 seclen);
 
 #ifdef CONFIG_SECURITY_NETWORK
-	int (*unix_stream_connect) (struct socket * sock,
-				    struct socket * other, struct sock * newsk);
-	int (*unix_may_send) (struct socket * sock, struct socket * other);
+	int (*unix_stream_connect) (struct socket *sock,
+				    struct socket *other, struct sock *newsk);
+	int (*unix_may_send) (struct socket *sock, struct socket *other);
 
 	int (*socket_create) (int family, int type, int protocol, int kern);
-	int (*socket_post_create) (struct socket * sock, int family,
+	int (*socket_post_create) (struct socket *sock, int family,
 				   int type, int protocol, int kern);
-	int (*socket_bind) (struct socket * sock,
-			    struct sockaddr * address, int addrlen);
-	int (*socket_connect) (struct socket * sock,
-			       struct sockaddr * address, int addrlen);
-	int (*socket_listen) (struct socket * sock, int backlog);
-	int (*socket_accept) (struct socket * sock, struct socket * newsock);
-	void (*socket_post_accept) (struct socket * sock,
-				    struct socket * newsock);
-	int (*socket_sendmsg) (struct socket * sock,
-			       struct msghdr * msg, int size);
-	int (*socket_recvmsg) (struct socket * sock,
-			       struct msghdr * msg, int size, int flags);
-	int (*socket_getsockname) (struct socket * sock);
-	int (*socket_getpeername) (struct socket * sock);
-	int (*socket_getsockopt) (struct socket * sock, int level, int optname);
-	int (*socket_setsockopt) (struct socket * sock, int level, int optname);
-	int (*socket_shutdown) (struct socket * sock, int how);
-	int (*socket_sock_rcv_skb) (struct sock * sk, struct sk_buff * skb);
+	int (*socket_bind) (struct socket *sock,
+			    struct sockaddr *address, int addrlen);
+	int (*socket_connect) (struct socket *sock,
+			       struct sockaddr *address, int addrlen);
+	int (*socket_listen) (struct socket *sock, int backlog);
+	int (*socket_accept) (struct socket *sock, struct socket *newsock);
+	void (*socket_post_accept) (struct socket *sock,
+				    struct socket *newsock);
+	int (*socket_sendmsg) (struct socket *sock,
+			       struct msghdr *msg, int size);
+	int (*socket_recvmsg) (struct socket *sock,
+			       struct msghdr *msg, int size, int flags);
+	int (*socket_getsockname) (struct socket *sock);
+	int (*socket_getpeername) (struct socket *sock);
+	int (*socket_getsockopt) (struct socket *sock, int level, int optname);
+	int (*socket_setsockopt) (struct socket *sock, int level, int optname);
+	int (*socket_shutdown) (struct socket *sock, int how);
+	int (*socket_sock_rcv_skb) (struct sock *sk, struct sk_buff *skb);
 	int (*socket_getpeersec_stream) (struct socket *sock, char __user *optval, int __user *optlen, unsigned len);
 	int (*socket_getpeersec_dgram) (struct socket *sock, struct sk_buff *skb, u32 *secid);
 	int (*sk_alloc_security) (struct sock *sk, int family, gfp_t priority);
 	void (*sk_free_security) (struct sock *sk);
 	void (*sk_clone_security) (const struct sock *sk, struct sock *newsk);
 	void (*sk_getsecid) (struct sock *sk, u32 *secid);
-	void (*sock_graft)(struct sock* sk, struct socket *parent);
-	int (*inet_conn_request)(struct sock *sk, struct sk_buff *skb,
-					struct request_sock *req);
-	void (*inet_csk_clone)(struct sock *newsk, const struct request_sock *req);
-	void (*inet_conn_established)(struct sock *sk, struct sk_buff *skb);
-	void (*req_classify_flow)(const struct request_sock *req, struct flowi *fl);
+	void (*sock_graft) (struct sock *sk, struct socket *parent);
+	int (*inet_conn_request) (struct sock *sk, struct sk_buff *skb,
+				  struct request_sock *req);
+	void (*inet_csk_clone) (struct sock *newsk, const struct request_sock *req);
+	void (*inet_conn_established) (struct sock *sk, struct sk_buff *skb);
+	void (*req_classify_flow) (const struct request_sock *req, struct flowi *fl);
 #endif	/* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
@@ -1521,57 +1535,57 @@ struct security_operations {
 		u32 secid);
 	void (*xfrm_state_free_security) (struct xfrm_state *x);
 	int (*xfrm_state_delete_security) (struct xfrm_state *x);
-	int (*xfrm_policy_lookup)(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir);
-	int (*xfrm_state_pol_flow_match)(struct xfrm_state *x,
-			struct xfrm_policy *xp, struct flowi *fl);
-	int (*xfrm_decode_session)(struct sk_buff *skb, u32 *secid, int ckall);
+	int (*xfrm_policy_lookup) (struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir);
+	int (*xfrm_state_pol_flow_match) (struct xfrm_state *x,
+					  struct xfrm_policy *xp,
+					  struct flowi *fl);
+	int (*xfrm_decode_session) (struct sk_buff *skb, u32 *secid, int ckall);
 #endif	/* CONFIG_SECURITY_NETWORK_XFRM */
 
 	/* key management security hooks */
 #ifdef CONFIG_KEYS
-	int (*key_alloc)(struct key *key, struct task_struct *tsk, unsigned long flags);
-	void (*key_free)(struct key *key);
-	int (*key_permission)(key_ref_t key_ref,
-			      struct task_struct *context,
-			      key_perm_t perm);
-
+	int (*key_alloc) (struct key *key, struct task_struct *tsk, unsigned long flags);
+	void (*key_free) (struct key *key);
+	int (*key_permission) (key_ref_t key_ref,
+			       struct task_struct *context,
+			       key_perm_t perm);
+	int (*key_getsecurity)(struct key *key, char **_buffer);
 #endif	/* CONFIG_KEYS */
 
 #ifdef CONFIG_AUDIT
-	int (*audit_rule_init)(u32 field, u32 op, char *rulestr, void **lsmrule);
-	int (*audit_rule_known)(struct audit_krule *krule);
-	int (*audit_rule_match)(u32 secid, u32 field, u32 op, void *lsmrule,
-				struct audit_context *actx);
-	void (*audit_rule_free)(void *lsmrule);
+	int (*audit_rule_init) (u32 field, u32 op, char *rulestr, void **lsmrule);
+	int (*audit_rule_known) (struct audit_krule *krule);
+	int (*audit_rule_match) (u32 secid, u32 field, u32 op, void *lsmrule,
+				 struct audit_context *actx);
+	void (*audit_rule_free) (void *lsmrule);
 #endif /* CONFIG_AUDIT */
 };
 
 /* prototypes */
-extern int security_init	(void);
+extern int security_init(void);
 extern int security_module_enable(struct security_operations *ops);
-extern int register_security	(struct security_operations *ops);
-extern int mod_reg_security	(const char *name, struct security_operations *ops);
+extern int register_security(struct security_operations *ops);
+extern int mod_reg_security(const char *name, struct security_operations *ops);
 extern struct dentry *securityfs_create_file(const char *name, mode_t mode,
 					     struct dentry *parent, void *data,
 					     const struct file_operations *fops);
 extern struct dentry *securityfs_create_dir(const char *name, struct dentry *parent);
 extern void securityfs_remove(struct dentry *dentry);
 
-
 /* Security operations */
 int security_ptrace(struct task_struct *parent, struct task_struct *child);
 int security_capget(struct task_struct *target,
-		     kernel_cap_t *effective,
-		     kernel_cap_t *inheritable,
-		     kernel_cap_t *permitted);
+		    kernel_cap_t *effective,
+		    kernel_cap_t *inheritable,
+		    kernel_cap_t *permitted);
 int security_capset_check(struct task_struct *target,
-			   kernel_cap_t *effective,
-			   kernel_cap_t *inheritable,
-			   kernel_cap_t *permitted);
-void security_capset_set(struct task_struct *target,
 			  kernel_cap_t *effective,
 			  kernel_cap_t *inheritable,
 			  kernel_cap_t *permitted);
+void security_capset_set(struct task_struct *target,
+			 kernel_cap_t *effective,
+			 kernel_cap_t *inheritable,
+			 kernel_cap_t *permitted);
 int security_capable(struct task_struct *tsk, int cap);
 int security_acct(struct file *file);
 int security_sysctl(struct ctl_table *table, int op);
@@ -1594,7 +1608,7 @@ int security_sb_copy_data(char *orig, char *copy);
 int security_sb_kern_mount(struct super_block *sb, void *data);
 int security_sb_statfs(struct dentry *dentry);
 int security_sb_mount(char *dev_name, struct path *path,
-                       char *type, unsigned long flags, void *data);
+		      char *type, unsigned long flags, void *data);
 int security_sb_check_sb(struct vfsmount *mnt, struct path *path);
 int security_sb_umount(struct vfsmount *mnt, int flags);
 void security_sb_umount_close(struct vfsmount *mnt);
@@ -1619,25 +1633,25 @@ int security_inode_link(struct dentry *old_dentry, struct inode *dir,
 			 struct dentry *new_dentry);
 int security_inode_unlink(struct inode *dir, struct dentry *dentry);
 int security_inode_symlink(struct inode *dir, struct dentry *dentry,
-			    const char *old_name);
+			   const char *old_name);
 int security_inode_mkdir(struct inode *dir, struct dentry *dentry, int mode);
 int security_inode_rmdir(struct inode *dir, struct dentry *dentry);
 int security_inode_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev);
 int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry,
-			   struct inode *new_dir, struct dentry *new_dentry);
+			  struct inode *new_dir, struct dentry *new_dentry);
 int security_inode_readlink(struct dentry *dentry);
 int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd);
 int security_inode_permission(struct inode *inode, int mask, struct nameidata *nd);
 int security_inode_setattr(struct dentry *dentry, struct iattr *attr);
 int security_inode_getattr(struct vfsmount *mnt, struct dentry *dentry);
 void security_inode_delete(struct inode *inode);
-int security_inode_setxattr(struct dentry *dentry, char *name,
-			     void *value, size_t size, int flags);
-void security_inode_post_setxattr(struct dentry *dentry, char *name,
-				   void *value, size_t size, int flags);
-int security_inode_getxattr(struct dentry *dentry, char *name);
+int security_inode_setxattr(struct dentry *dentry, const char *name,
+			    const void *value, size_t size, int flags);
+void security_inode_post_setxattr(struct dentry *dentry, const char *name,
+				  const void *value, size_t size, int flags);
+int security_inode_getxattr(struct dentry *dentry, const char *name);
 int security_inode_listxattr(struct dentry *dentry);
-int security_inode_removexattr(struct dentry *dentry, char *name);
+int security_inode_removexattr(struct dentry *dentry, const char *name);
 int security_inode_need_killpriv(struct dentry *dentry);
 int security_inode_killpriv(struct dentry *dentry);
 int security_inode_getsecurity(const struct inode *inode, const char *name, void **buffer, bool alloc);
@@ -1652,12 +1666,12 @@ int security_file_mmap(struct file *file, unsigned long reqprot,
 			unsigned long prot, unsigned long flags,
 			unsigned long addr, unsigned long addr_only);
 int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
-			    unsigned long prot);
+			   unsigned long prot);
 int security_file_lock(struct file *file, unsigned int cmd);
 int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg);
 int security_file_set_fowner(struct file *file);
 int security_file_send_sigiotask(struct task_struct *tsk,
-				  struct fown_struct *fown, int sig);
+				 struct fown_struct *fown, int sig);
 int security_file_receive(struct file *file);
 int security_dentry_open(struct file *file);
 int security_task_create(unsigned long clone_flags);
@@ -1665,7 +1679,7 @@ int security_task_alloc(struct task_struct *p);
 void security_task_free(struct task_struct *p);
 int security_task_setuid(uid_t id0, uid_t id1, uid_t id2, int flags);
 int security_task_post_setuid(uid_t old_ruid, uid_t old_euid,
-			       uid_t old_suid, int flags);
+			      uid_t old_suid, int flags);
 int security_task_setgid(gid_t id0, gid_t id1, gid_t id2, int flags);
 int security_task_setpgid(struct task_struct *p, pid_t pgid);
 int security_task_getpgid(struct task_struct *p);
@@ -1684,7 +1698,7 @@ int security_task_kill(struct task_struct *p, struct siginfo *info,
 			int sig, u32 secid);
 int security_task_wait(struct task_struct *p);
 int security_task_prctl(int option, unsigned long arg2, unsigned long arg3,
-			 unsigned long arg4, unsigned long arg5);
+			 unsigned long arg4, unsigned long arg5, long *rc_p);
 void security_task_reparent_to_init(struct task_struct *p);
 void security_task_to_inode(struct task_struct *p, struct inode *inode);
 int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag);
@@ -1696,9 +1710,9 @@ void security_msg_queue_free(struct msg_queue *msq);
 int security_msg_queue_associate(struct msg_queue *msq, int msqflg);
 int security_msg_queue_msgctl(struct msg_queue *msq, int cmd);
 int security_msg_queue_msgsnd(struct msg_queue *msq,
-			       struct msg_msg *msg, int msqflg);
+			      struct msg_msg *msg, int msqflg);
 int security_msg_queue_msgrcv(struct msg_queue *msq, struct msg_msg *msg,
-			       struct task_struct *target, long type, int mode);
+			      struct task_struct *target, long type, int mode);
 int security_shm_alloc(struct shmid_kernel *shp);
 void security_shm_free(struct shmid_kernel *shp);
 int security_shm_associate(struct shmid_kernel *shp, int shmflg);
@@ -1710,7 +1724,7 @@ int security_sem_associate(struct sem_array *sma, int semflg);
 int security_sem_semctl(struct sem_array *sma, int cmd);
 int security_sem_semop(struct sem_array *sma, struct sembuf *sops,
 			unsigned nsops, int alter);
-void security_d_instantiate (struct dentry *dentry, struct inode *inode);
+void security_d_instantiate(struct dentry *dentry, struct inode *inode);
 int security_getprocattr(struct task_struct *p, char *name, char **value);
 int security_setprocattr(struct task_struct *p, char *name, void *value, size_t size);
 int security_netlink_send(struct sock *sk, struct sk_buff *skb);
@@ -1741,33 +1755,33 @@ static inline int security_init(void)
 	return 0;
 }
 
-static inline int security_ptrace (struct task_struct *parent, struct task_struct * child)
+static inline int security_ptrace(struct task_struct *parent, struct task_struct *child)
 {
-	return cap_ptrace (parent, child);
+	return cap_ptrace(parent, child);
 }
 
-static inline int security_capget (struct task_struct *target,
+static inline int security_capget(struct task_struct *target,
 				   kernel_cap_t *effective,
 				   kernel_cap_t *inheritable,
 				   kernel_cap_t *permitted)
 {
-	return cap_capget (target, effective, inheritable, permitted);
+	return cap_capget(target, effective, inheritable, permitted);
 }
 
-static inline int security_capset_check (struct task_struct *target,
+static inline int security_capset_check(struct task_struct *target,
 					 kernel_cap_t *effective,
 					 kernel_cap_t *inheritable,
 					 kernel_cap_t *permitted)
 {
-	return cap_capset_check (target, effective, inheritable, permitted);
+	return cap_capset_check(target, effective, inheritable, permitted);
 }
 
-static inline void security_capset_set (struct task_struct *target,
+static inline void security_capset_set(struct task_struct *target,
 					kernel_cap_t *effective,
 					kernel_cap_t *inheritable,
 					kernel_cap_t *permitted)
 {
-	cap_capset_set (target, effective, inheritable, permitted);
+	cap_capset_set(target, effective, inheritable, permitted);
 }
 
 static inline int security_capable(struct task_struct *tsk, int cap)
@@ -1775,7 +1789,7 @@ static inline int security_capable(struct task_struct *tsk, int cap)
 	return cap_capable(tsk, cap);
 }
 
-static inline int security_acct (struct file *file)
+static inline int security_acct(struct file *file)
 {
 	return 0;
 }
@@ -1785,13 +1799,13 @@ static inline int security_sysctl(struct ctl_table *table, int op)
 	return 0;
 }
 
-static inline int security_quotactl (int cmds, int type, int id,
-				     struct super_block * sb)
+static inline int security_quotactl(int cmds, int type, int id,
+				     struct super_block *sb)
 {
 	return 0;
 }
 
-static inline int security_quota_on (struct dentry * dentry)
+static inline int security_quota_on(struct dentry *dentry)
 {
 	return 0;
 }
@@ -1816,102 +1830,102 @@ static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages)
 	return cap_vm_enough_memory(mm, pages);
 }
 
-static inline int security_bprm_alloc (struct linux_binprm *bprm)
+static inline int security_bprm_alloc(struct linux_binprm *bprm)
 {
 	return 0;
 }
 
-static inline void security_bprm_free (struct linux_binprm *bprm)
+static inline void security_bprm_free(struct linux_binprm *bprm)
 { }
 
-static inline void security_bprm_apply_creds (struct linux_binprm *bprm, int unsafe)
-{ 
-	cap_bprm_apply_creds (bprm, unsafe);
+static inline void security_bprm_apply_creds(struct linux_binprm *bprm, int unsafe)
+{
+	cap_bprm_apply_creds(bprm, unsafe);
 }
 
-static inline void security_bprm_post_apply_creds (struct linux_binprm *bprm)
+static inline void security_bprm_post_apply_creds(struct linux_binprm *bprm)
 {
 	return;
 }
 
-static inline int security_bprm_set (struct linux_binprm *bprm)
+static inline int security_bprm_set(struct linux_binprm *bprm)
 {
-	return cap_bprm_set_security (bprm);
+	return cap_bprm_set_security(bprm);
 }
 
-static inline int security_bprm_check (struct linux_binprm *bprm)
+static inline int security_bprm_check(struct linux_binprm *bprm)
 {
 	return 0;
 }
 
-static inline int security_bprm_secureexec (struct linux_binprm *bprm)
+static inline int security_bprm_secureexec(struct linux_binprm *bprm)
 {
 	return cap_bprm_secureexec(bprm);
 }
 
-static inline int security_sb_alloc (struct super_block *sb)
+static inline int security_sb_alloc(struct super_block *sb)
 {
 	return 0;
 }
 
-static inline void security_sb_free (struct super_block *sb)
+static inline void security_sb_free(struct super_block *sb)
 { }
 
-static inline int security_sb_copy_data (char *orig, char *copy)
+static inline int security_sb_copy_data(char *orig, char *copy)
 {
 	return 0;
 }
 
-static inline int security_sb_kern_mount (struct super_block *sb, void *data)
+static inline int security_sb_kern_mount(struct super_block *sb, void *data)
 {
 	return 0;
 }
 
-static inline int security_sb_statfs (struct dentry *dentry)
+static inline int security_sb_statfs(struct dentry *dentry)
 {
 	return 0;
 }
 
-static inline int security_sb_mount (char *dev_name, struct path *path,
+static inline int security_sb_mount(char *dev_name, struct path *path,
 				    char *type, unsigned long flags,
 				    void *data)
 {
 	return 0;
 }
 
-static inline int security_sb_check_sb (struct vfsmount *mnt,
-					struct path *path)
+static inline int security_sb_check_sb(struct vfsmount *mnt,
+				       struct path *path)
 {
 	return 0;
 }
 
-static inline int security_sb_umount (struct vfsmount *mnt, int flags)
+static inline int security_sb_umount(struct vfsmount *mnt, int flags)
 {
 	return 0;
 }
 
-static inline void security_sb_umount_close (struct vfsmount *mnt)
+static inline void security_sb_umount_close(struct vfsmount *mnt)
 { }
 
-static inline void security_sb_umount_busy (struct vfsmount *mnt)
+static inline void security_sb_umount_busy(struct vfsmount *mnt)
 { }
 
-static inline void security_sb_post_remount (struct vfsmount *mnt,
+static inline void security_sb_post_remount(struct vfsmount *mnt,
 					     unsigned long flags, void *data)
 { }
 
-static inline void security_sb_post_addmount (struct vfsmount *mnt,
-					      struct path *mountpoint)
+static inline void security_sb_post_addmount(struct vfsmount *mnt,
+					     struct path *mountpoint)
 { }
 
-static inline int security_sb_pivotroot (struct path *old_path,
-					 struct path *new_path)
+static inline int security_sb_pivotroot(struct path *old_path,
+					struct path *new_path)
 {
 	return 0;
 }
 
-static inline void security_sb_post_pivotroot (struct path *old_path,
-					       struct path *new_path)
+static inline void security_sb_post_pivotroot(struct path *old_path,
+					      struct path *new_path)
 { }
 static inline int security_sb_get_mnt_opts(const struct super_block *sb,
 					   struct security_mnt_opts *opts)
@@ -1935,15 +1949,15 @@ static inline int security_sb_parse_opts_str(char *options, struct security_mnt_
 	return 0;
 }
 
-static inline int security_inode_alloc (struct inode *inode)
+static inline int security_inode_alloc(struct inode *inode)
 {
 	return 0;
 }
 
-static inline void security_inode_free (struct inode *inode)
+static inline void security_inode_free(struct inode *inode)
 { }
 
-static inline int security_inode_init_security (struct inode *inode,
+static inline int security_inode_init_security(struct inode *inode,
 						struct inode *dir,
 						char **name,
 						void **value,
@@ -1951,55 +1965,55 @@ static inline int security_inode_init_security (struct inode *inode,
 {
 	return -EOPNOTSUPP;
 }
-	
-static inline int security_inode_create (struct inode *dir,
+
+static inline int security_inode_create(struct inode *dir,
 					 struct dentry *dentry,
 					 int mode)
 {
 	return 0;
 }
 
-static inline int security_inode_link (struct dentry *old_dentry,
+static inline int security_inode_link(struct dentry *old_dentry,
 				       struct inode *dir,
 				       struct dentry *new_dentry)
 {
 	return 0;
 }
 
-static inline int security_inode_unlink (struct inode *dir,
+static inline int security_inode_unlink(struct inode *dir,
 					 struct dentry *dentry)
 {
 	return 0;
 }
 
-static inline int security_inode_symlink (struct inode *dir,
+static inline int security_inode_symlink(struct inode *dir,
 					  struct dentry *dentry,
 					  const char *old_name)
 {
 	return 0;
 }
 
-static inline int security_inode_mkdir (struct inode *dir,
+static inline int security_inode_mkdir(struct inode *dir,
 					struct dentry *dentry,
 					int mode)
 {
 	return 0;
 }
 
-static inline int security_inode_rmdir (struct inode *dir,
+static inline int security_inode_rmdir(struct inode *dir,
 					struct dentry *dentry)
 {
 	return 0;
 }
 
-static inline int security_inode_mknod (struct inode *dir,
+static inline int security_inode_mknod(struct inode *dir,
 					struct dentry *dentry,
 					int mode, dev_t dev)
 {
 	return 0;
 }
 
-static inline int security_inode_rename (struct inode *old_dir,
+static inline int security_inode_rename(struct inode *old_dir,
 					 struct dentry *old_dentry,
 					 struct inode *new_dir,
 					 struct dentry *new_dentry)
@@ -2007,59 +2021,61 @@ static inline int security_inode_rename (struct inode *old_dir,
 	return 0;
 }
 
-static inline int security_inode_readlink (struct dentry *dentry)
+static inline int security_inode_readlink(struct dentry *dentry)
 {
 	return 0;
 }
 
-static inline int security_inode_follow_link (struct dentry *dentry,
+static inline int security_inode_follow_link(struct dentry *dentry,
 					      struct nameidata *nd)
 {
 	return 0;
 }
 
-static inline int security_inode_permission (struct inode *inode, int mask,
+static inline int security_inode_permission(struct inode *inode, int mask,
 					     struct nameidata *nd)
 {
 	return 0;
 }
 
-static inline int security_inode_setattr (struct dentry *dentry,
+static inline int security_inode_setattr(struct dentry *dentry,
 					  struct iattr *attr)
 {
 	return 0;
 }
 
-static inline int security_inode_getattr (struct vfsmount *mnt,
+static inline int security_inode_getattr(struct vfsmount *mnt,
 					  struct dentry *dentry)
 {
 	return 0;
 }
 
-static inline void security_inode_delete (struct inode *inode)
+static inline void security_inode_delete(struct inode *inode)
 { }
 
-static inline int security_inode_setxattr (struct dentry *dentry, char *name,
-					   void *value, size_t size, int flags)
+static inline int security_inode_setxattr(struct dentry *dentry,
+		const char *name, const void *value, size_t size, int flags)
 {
 	return cap_inode_setxattr(dentry, name, value, size, flags);
 }
 
-static inline void security_inode_post_setxattr (struct dentry *dentry, char *name,
-						 void *value, size_t size, int flags)
+static inline void security_inode_post_setxattr(struct dentry *dentry,
+		const char *name, const void *value, size_t size, int flags)
 { }
 
-static inline int security_inode_getxattr (struct dentry *dentry, char *name)
+static inline int security_inode_getxattr(struct dentry *dentry,
+			const char *name)
 {
 	return 0;
 }
 
-static inline int security_inode_listxattr (struct dentry *dentry)
+static inline int security_inode_listxattr(struct dentry *dentry)
 {
 	return 0;
 }
 
-static inline int security_inode_removexattr (struct dentry *dentry, char *name)
+static inline int security_inode_removexattr(struct dentry *dentry,
+			const char *name)
 {
 	return cap_inode_removexattr(dentry, name);
 }
@@ -2094,198 +2110,198 @@ static inline void security_inode_getsecid(const struct inode *inode, u32 *secid
 	*secid = 0;
 }
 
-static inline int security_file_permission (struct file *file, int mask)
+static inline int security_file_permission(struct file *file, int mask)
 {
 	return 0;
 }
 
-static inline int security_file_alloc (struct file *file)
+static inline int security_file_alloc(struct file *file)
 {
 	return 0;
 }
 
-static inline void security_file_free (struct file *file)
+static inline void security_file_free(struct file *file)
 { }
 
-static inline int security_file_ioctl (struct file *file, unsigned int cmd,
-				       unsigned long arg)
+static inline int security_file_ioctl(struct file *file, unsigned int cmd,
+				      unsigned long arg)
 {
 	return 0;
 }
 
-static inline int security_file_mmap (struct file *file, unsigned long reqprot,
-				      unsigned long prot,
-				      unsigned long flags,
-				      unsigned long addr,
-				      unsigned long addr_only)
+static inline int security_file_mmap(struct file *file, unsigned long reqprot,
+				     unsigned long prot,
+				     unsigned long flags,
+				     unsigned long addr,
+				     unsigned long addr_only)
 {
 	return 0;
 }
 
-static inline int security_file_mprotect (struct vm_area_struct *vma,
-					  unsigned long reqprot,
-					  unsigned long prot)
+static inline int security_file_mprotect(struct vm_area_struct *vma,
+					 unsigned long reqprot,
+					 unsigned long prot)
 {
 	return 0;
 }
 
-static inline int security_file_lock (struct file *file, unsigned int cmd)
+static inline int security_file_lock(struct file *file, unsigned int cmd)
 {
 	return 0;
 }
 
-static inline int security_file_fcntl (struct file *file, unsigned int cmd,
-				       unsigned long arg)
+static inline int security_file_fcntl(struct file *file, unsigned int cmd,
+				      unsigned long arg)
 {
 	return 0;
 }
 
-static inline int security_file_set_fowner (struct file *file)
+static inline int security_file_set_fowner(struct file *file)
 {
 	return 0;
 }
 
-static inline int security_file_send_sigiotask (struct task_struct *tsk,
-						struct fown_struct *fown,
-						int sig)
+static inline int security_file_send_sigiotask(struct task_struct *tsk,
+					       struct fown_struct *fown,
+					       int sig)
 {
 	return 0;
 }
 
-static inline int security_file_receive (struct file *file)
+static inline int security_file_receive(struct file *file)
 {
 	return 0;
 }
 
-static inline int security_dentry_open (struct file *file)
+static inline int security_dentry_open(struct file *file)
 {
 	return 0;
 }
 
-static inline int security_task_create (unsigned long clone_flags)
+static inline int security_task_create(unsigned long clone_flags)
 {
 	return 0;
 }
 
-static inline int security_task_alloc (struct task_struct *p)
+static inline int security_task_alloc(struct task_struct *p)
 {
 	return 0;
 }
 
-static inline void security_task_free (struct task_struct *p)
+static inline void security_task_free(struct task_struct *p)
 { }
 
-static inline int security_task_setuid (uid_t id0, uid_t id1, uid_t id2,
-					int flags)
+static inline int security_task_setuid(uid_t id0, uid_t id1, uid_t id2,
+				       int flags)
 {
 	return 0;
 }
 
-static inline int security_task_post_setuid (uid_t old_ruid, uid_t old_euid,
-					     uid_t old_suid, int flags)
+static inline int security_task_post_setuid(uid_t old_ruid, uid_t old_euid,
+					    uid_t old_suid, int flags)
 {
-	return cap_task_post_setuid (old_ruid, old_euid, old_suid, flags);
+	return cap_task_post_setuid(old_ruid, old_euid, old_suid, flags);
 }
 
-static inline int security_task_setgid (gid_t id0, gid_t id1, gid_t id2,
-					int flags)
+static inline int security_task_setgid(gid_t id0, gid_t id1, gid_t id2,
+				       int flags)
 {
 	return 0;
 }
 
-static inline int security_task_setpgid (struct task_struct *p, pid_t pgid)
+static inline int security_task_setpgid(struct task_struct *p, pid_t pgid)
 {
 	return 0;
 }
 
-static inline int security_task_getpgid (struct task_struct *p)
+static inline int security_task_getpgid(struct task_struct *p)
 {
 	return 0;
 }
 
-static inline int security_task_getsid (struct task_struct *p)
+static inline int security_task_getsid(struct task_struct *p)
 {
 	return 0;
 }
 
-static inline void security_task_getsecid (struct task_struct *p, u32 *secid)
+static inline void security_task_getsecid(struct task_struct *p, u32 *secid)
 {
 	*secid = 0;
 }
 
-static inline int security_task_setgroups (struct group_info *group_info)
+static inline int security_task_setgroups(struct group_info *group_info)
 {
 	return 0;
 }
 
-static inline int security_task_setnice (struct task_struct *p, int nice)
+static inline int security_task_setnice(struct task_struct *p, int nice)
 {
 	return cap_task_setnice(p, nice);
 }
 
-static inline int security_task_setioprio (struct task_struct *p, int ioprio)
+static inline int security_task_setioprio(struct task_struct *p, int ioprio)
 {
 	return cap_task_setioprio(p, ioprio);
 }
 
-static inline int security_task_getioprio (struct task_struct *p)
+static inline int security_task_getioprio(struct task_struct *p)
 {
 	return 0;
 }
 
-static inline int security_task_setrlimit (unsigned int resource,
-					   struct rlimit *new_rlim)
+static inline int security_task_setrlimit(unsigned int resource,
+					  struct rlimit *new_rlim)
 {
 	return 0;
 }
 
-static inline int security_task_setscheduler (struct task_struct *p,
-					      int policy,
-					      struct sched_param *lp)
+static inline int security_task_setscheduler(struct task_struct *p,
+					     int policy,
+					     struct sched_param *lp)
 {
 	return cap_task_setscheduler(p, policy, lp);
 }
 
-static inline int security_task_getscheduler (struct task_struct *p)
+static inline int security_task_getscheduler(struct task_struct *p)
 {
 	return 0;
 }
 
-static inline int security_task_movememory (struct task_struct *p)
+static inline int security_task_movememory(struct task_struct *p)
 {
 	return 0;
 }
 
-static inline int security_task_kill (struct task_struct *p,
-				      struct siginfo *info, int sig,
-				      u32 secid)
+static inline int security_task_kill(struct task_struct *p,
+				     struct siginfo *info, int sig,
+				     u32 secid)
 {
 	return 0;
 }
 
-static inline int security_task_wait (struct task_struct *p)
+static inline int security_task_wait(struct task_struct *p)
 {
 	return 0;
 }
 
-static inline int security_task_prctl (int option, unsigned long arg2,
-				       unsigned long arg3,
-				       unsigned long arg4,
-				       unsigned long arg5)
+static inline int security_task_prctl(int option, unsigned long arg2,
+				      unsigned long arg3,
+				      unsigned long arg4,
+				      unsigned long arg5, long *rc_p)
 {
-	return 0;
+	return cap_task_prctl(option, arg2, arg3, arg3, arg5, rc_p);
 }
 
-static inline void security_task_reparent_to_init (struct task_struct *p)
+static inline void security_task_reparent_to_init(struct task_struct *p)
 {
-	cap_task_reparent_to_init (p);
+	cap_task_reparent_to_init(p);
 }
 
 static inline void security_task_to_inode(struct task_struct *p, struct inode *inode)
 { }
 
-static inline int security_ipc_permission (struct kern_ipc_perm *ipcp,
-					   short flag)
+static inline int security_ipc_permission(struct kern_ipc_perm *ipcp,
+					  short flag)
 {
 	return 0;
 }
@@ -2295,98 +2311,98 @@ static inline void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid)
 	*secid = 0;
 }
 
-static inline int security_msg_msg_alloc (struct msg_msg * msg)
+static inline int security_msg_msg_alloc(struct msg_msg *msg)
 {
 	return 0;
 }
 
-static inline void security_msg_msg_free (struct msg_msg * msg)
+static inline void security_msg_msg_free(struct msg_msg *msg)
 { }
 
-static inline int security_msg_queue_alloc (struct msg_queue *msq)
+static inline int security_msg_queue_alloc(struct msg_queue *msq)
 {
 	return 0;
 }
 
-static inline void security_msg_queue_free (struct msg_queue *msq)
+static inline void security_msg_queue_free(struct msg_queue *msq)
 { }
 
-static inline int security_msg_queue_associate (struct msg_queue * msq, 
-						int msqflg)
+static inline int security_msg_queue_associate(struct msg_queue *msq,
+					       int msqflg)
 {
 	return 0;
 }
 
-static inline int security_msg_queue_msgctl (struct msg_queue * msq, int cmd)
+static inline int security_msg_queue_msgctl(struct msg_queue *msq, int cmd)
 {
 	return 0;
 }
 
-static inline int security_msg_queue_msgsnd (struct msg_queue * msq,
-					     struct msg_msg * msg, int msqflg)
+static inline int security_msg_queue_msgsnd(struct msg_queue *msq,
+					    struct msg_msg *msg, int msqflg)
 {
 	return 0;
 }
 
-static inline int security_msg_queue_msgrcv (struct msg_queue * msq,
-					     struct msg_msg * msg,
-					     struct task_struct * target,
-					     long type, int mode)
+static inline int security_msg_queue_msgrcv(struct msg_queue *msq,
+					    struct msg_msg *msg,
+					    struct task_struct *target,
+					    long type, int mode)
 {
 	return 0;
 }
 
-static inline int security_shm_alloc (struct shmid_kernel *shp)
+static inline int security_shm_alloc(struct shmid_kernel *shp)
 {
 	return 0;
 }
 
-static inline void security_shm_free (struct shmid_kernel *shp)
+static inline void security_shm_free(struct shmid_kernel *shp)
 { }
 
-static inline int security_shm_associate (struct shmid_kernel * shp, 
-					  int shmflg)
+static inline int security_shm_associate(struct shmid_kernel *shp,
+					 int shmflg)
 {
 	return 0;
 }
 
-static inline int security_shm_shmctl (struct shmid_kernel * shp, int cmd)
+static inline int security_shm_shmctl(struct shmid_kernel *shp, int cmd)
 {
 	return 0;
 }
 
-static inline int security_shm_shmat (struct shmid_kernel * shp, 
-				      char __user *shmaddr, int shmflg)
+static inline int security_shm_shmat(struct shmid_kernel *shp,
+				     char __user *shmaddr, int shmflg)
 {
 	return 0;
 }
 
-static inline int security_sem_alloc (struct sem_array *sma)
+static inline int security_sem_alloc(struct sem_array *sma)
 {
 	return 0;
 }
 
-static inline void security_sem_free (struct sem_array *sma)
+static inline void security_sem_free(struct sem_array *sma)
 { }
 
-static inline int security_sem_associate (struct sem_array * sma, int semflg)
+static inline int security_sem_associate(struct sem_array *sma, int semflg)
 {
 	return 0;
 }
 
-static inline int security_sem_semctl (struct sem_array * sma, int cmd)
+static inline int security_sem_semctl(struct sem_array *sma, int cmd)
 {
 	return 0;
 }
 
-static inline int security_sem_semop (struct sem_array * sma, 
-				      struct sembuf * sops, unsigned nsops, 
-				      int alter)
+static inline int security_sem_semop(struct sem_array *sma,
+				     struct sembuf *sops, unsigned nsops,
+				     int alter)
 {
 	return 0;
 }
 
-static inline void security_d_instantiate (struct dentry *dentry, struct inode *inode)
+static inline void security_d_instantiate(struct dentry *dentry, struct inode *inode)
 { }
 
 static inline int security_getprocattr(struct task_struct *p, char *name, char **value)
@@ -2399,14 +2415,14 @@ static inline int security_setprocattr(struct task_struct *p, char *name, void *
 	return -EINVAL;
 }
 
-static inline int security_netlink_send (struct sock *sk, struct sk_buff *skb)
+static inline int security_netlink_send(struct sock *sk, struct sk_buff *skb)
 {
-	return cap_netlink_send (sk, skb);
+	return cap_netlink_send(sk, skb);
 }
 
-static inline int security_netlink_recv (struct sk_buff *skb, int cap)
+static inline int security_netlink_recv(struct sk_buff *skb, int cap)
 {
-	return cap_netlink_recv (skb, cap);
+	return cap_netlink_recv(skb, cap);
 }
 
 static inline struct dentry *securityfs_create_dir(const char *name,
@@ -2484,26 +2500,26 @@ void security_inet_conn_established(struct sock *sk,
 			struct sk_buff *skb);
 
 #else	/* CONFIG_SECURITY_NETWORK */
-static inline int security_unix_stream_connect(struct socket * sock,
-					       struct socket * other,
-					       struct sock * newsk)
+static inline int security_unix_stream_connect(struct socket *sock,
+					       struct socket *other,
+					       struct sock *newsk)
 {
 	return 0;
 }
 
-static inline int security_unix_may_send(struct socket * sock, 
-					 struct socket * other)
+static inline int security_unix_may_send(struct socket *sock,
+					 struct socket *other)
 {
 	return 0;
 }
 
-static inline int security_socket_create (int family, int type,
-					  int protocol, int kern)
+static inline int security_socket_create(int family, int type,
+					 int protocol, int kern)
 {
 	return 0;
 }
 
-static inline int security_socket_post_create(struct socket * sock,
+static inline int security_socket_post_create(struct socket *sock,
 					      int family,
 					      int type,
 					      int protocol, int kern)
@@ -2511,77 +2527,77 @@ static inline int security_socket_post_create(struct socket * sock,
 	return 0;
 }
 
-static inline int security_socket_bind(struct socket * sock, 
-				       struct sockaddr * address, 
+static inline int security_socket_bind(struct socket *sock,
+				       struct sockaddr *address,
 				       int addrlen)
 {
 	return 0;
 }
 
-static inline int security_socket_connect(struct socket * sock, 
-					  struct sockaddr * address, 
+static inline int security_socket_connect(struct socket *sock,
+					  struct sockaddr *address,
 					  int addrlen)
 {
 	return 0;
 }
 
-static inline int security_socket_listen(struct socket * sock, int backlog)
+static inline int security_socket_listen(struct socket *sock, int backlog)
 {
 	return 0;
 }
 
-static inline int security_socket_accept(struct socket * sock, 
-					 struct socket * newsock)
+static inline int security_socket_accept(struct socket *sock,
+					 struct socket *newsock)
 {
 	return 0;
 }
 
-static inline void security_socket_post_accept(struct socket * sock, 
-					       struct socket * newsock)
+static inline void security_socket_post_accept(struct socket *sock,
+					       struct socket *newsock)
 {
 }
 
-static inline int security_socket_sendmsg(struct socket * sock, 
-					  struct msghdr * msg, int size)
+static inline int security_socket_sendmsg(struct socket *sock,
+					  struct msghdr *msg, int size)
 {
 	return 0;
 }
 
-static inline int security_socket_recvmsg(struct socket * sock, 
-					  struct msghdr * msg, int size, 
+static inline int security_socket_recvmsg(struct socket *sock,
+					  struct msghdr *msg, int size,
 					  int flags)
 {
 	return 0;
 }
 
-static inline int security_socket_getsockname(struct socket * sock)
+static inline int security_socket_getsockname(struct socket *sock)
 {
 	return 0;
 }
 
-static inline int security_socket_getpeername(struct socket * sock)
+static inline int security_socket_getpeername(struct socket *sock)
 {
 	return 0;
 }
 
-static inline int security_socket_getsockopt(struct socket * sock, 
+static inline int security_socket_getsockopt(struct socket *sock,
 					     int level, int optname)
 {
 	return 0;
 }
 
-static inline int security_socket_setsockopt(struct socket * sock, 
+static inline int security_socket_setsockopt(struct socket *sock,
 					     int level, int optname)
 {
 	return 0;
 }
 
-static inline int security_socket_shutdown(struct socket * sock, int how)
+static inline int security_socket_shutdown(struct socket *sock, int how)
 {
 	return 0;
 }
-static inline int security_sock_rcv_skb (struct sock * sk, 
-					 struct sk_buff * skb)
+static inline int security_sock_rcv_skb(struct sock *sk,
+					struct sk_buff *skb)
 {
 	return 0;
 }
@@ -2618,7 +2634,7 @@ static inline void security_req_classify_flow(const struct request_sock *req, st
 {
 }
 
-static inline void security_sock_graft(struct sock* sk, struct socket *parent)
+static inline void security_sock_graft(struct sock *sk, struct socket *parent)
 {
 }
 
@@ -2727,6 +2743,7 @@ int security_key_alloc(struct key *key, struct task_struct *tsk, unsigned long f
 void security_key_free(struct key *key);
 int security_key_permission(key_ref_t key_ref,
 			    struct task_struct *context, key_perm_t perm);
+int security_key_getsecurity(struct key *key, char **_buffer);
 
 #else
 
@@ -2748,6 +2765,12 @@ static inline int security_key_permission(key_ref_t key_ref,
 	return 0;
 }
 
+static inline int security_key_getsecurity(struct key *key, char **_buffer)
+{
+	*_buffer = NULL;
+	return 0;
+}
+
 #endif
 #endif /* CONFIG_KEYS */
 
diff --git a/trunk/include/linux/serial_8250.h b/trunk/include/linux/serial_8250.h
index 00b65c0a82ca..3d37c94abbc8 100644
--- a/trunk/include/linux/serial_8250.h
+++ b/trunk/include/linux/serial_8250.h
@@ -46,6 +46,7 @@ enum {
 	PLAT8250_DEV_HUB6,
 	PLAT8250_DEV_MCA,
 	PLAT8250_DEV_AU1X00,
+	PLAT8250_DEV_SM501,
 };
 
 /*
diff --git a/trunk/include/linux/shmem_fs.h b/trunk/include/linux/shmem_fs.h
index 8d5fb36ea047..f2d12d5a21b8 100644
--- a/trunk/include/linux/shmem_fs.h
+++ b/trunk/include/linux/shmem_fs.h
@@ -34,8 +34,7 @@ struct shmem_sb_info {
 	uid_t uid;		    /* Mount uid for root directory */
 	gid_t gid;		    /* Mount gid for root directory */
 	mode_t mode;		    /* Mount mode for root directory */
-	int policy;		    /* Default NUMA memory alloc policy */
-	nodemask_t policy_nodes;    /* nodemask for preferred and bind */
+	struct mempolicy *mpol;     /* default memory policy for mappings */
 };
 
 static inline struct shmem_inode_info *SHMEM_I(struct inode *inode)
diff --git a/trunk/include/linux/slub_def.h b/trunk/include/linux/slub_def.h
index 79d59c937fac..71e43a12ebbb 100644
--- a/trunk/include/linux/slub_def.h
+++ b/trunk/include/linux/slub_def.h
@@ -29,6 +29,7 @@ enum stat_item {
 	DEACTIVATE_TO_HEAD,	/* Cpu slab was moved to the head of partials */
 	DEACTIVATE_TO_TAIL,	/* Cpu slab was moved to the tail of partials */
 	DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */
+	ORDER_FALLBACK,		/* Number of times fallback was necessary */
 	NR_SLUB_STAT_ITEMS };
 
 struct kmem_cache_cpu {
@@ -48,10 +49,20 @@ struct kmem_cache_node {
 	struct list_head partial;
 #ifdef CONFIG_SLUB_DEBUG
 	atomic_long_t nr_slabs;
+	atomic_long_t total_objects;
 	struct list_head full;
 #endif
 };
 
+/*
+ * Word size structure that can be atomically updated or read and that
+ * contains both the order and the number of objects that a slab of the
+ * given order would contain.
+ */
+struct kmem_cache_order_objects {
+	unsigned long x;
+};
+
 /*
  * Slab cache management.
  */
@@ -61,7 +72,7 @@ struct kmem_cache {
 	int size;		/* The size of an object including meta data */
 	int objsize;		/* The size of an object without meta data */
 	int offset;		/* Free pointer offset. */
-	int order;		/* Current preferred allocation order */
+	struct kmem_cache_order_objects oo;
 
 	/*
 	 * Avoid an extra cache line for UP, SMP and for the node local to
@@ -70,7 +81,8 @@ struct kmem_cache {
 	struct kmem_cache_node local_node;
 
 	/* Allocation and freeing of slabs */
-	int objects;		/* Number of objects in slab */
+	struct kmem_cache_order_objects max;
+	struct kmem_cache_order_objects min;
 	gfp_t allocflags;	/* gfp flags to use on each alloc */
 	int refcount;		/* Refcount for slab cache destroy */
 	void (*ctor)(struct kmem_cache *, void *);
diff --git a/trunk/include/linux/smb.h b/trunk/include/linux/smb.h
index f098dff93f6b..caa43b2370cb 100644
--- a/trunk/include/linux/smb.h
+++ b/trunk/include/linux/smb.h
@@ -11,6 +11,7 @@
 
 #include <linux/types.h>
 #include <linux/magic.h>
+#include <linux/time.h>
 
 enum smb_protocol { 
 	SMB_PROTOCOL_NONE, 
diff --git a/trunk/include/linux/suspend.h b/trunk/include/linux/suspend.h
index 1d7d4c5797ee..a6977423baf7 100644
--- a/trunk/include/linux/suspend.h
+++ b/trunk/include/linux/suspend.h
@@ -12,11 +12,22 @@
 #include <asm/errno.h>
 
 #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE)
+extern void pm_set_vt_switch(int);
 extern int pm_prepare_console(void);
 extern void pm_restore_console(void);
 #else
-static inline int pm_prepare_console(void) { return 0; }
-static inline void pm_restore_console(void) {}
+static inline void pm_set_vt_switch(int do_switch)
+{
+}
+
+static inline int pm_prepare_console(void)
+{
+	return 0;
+}
+
+static inline void pm_restore_console(void)
+{
+}
 #endif
 
 typedef int __bitwise suspend_state_t;
diff --git a/trunk/include/linux/swap.h b/trunk/include/linux/swap.h
index 878459ae0454..0b3377650c85 100644
--- a/trunk/include/linux/swap.h
+++ b/trunk/include/linux/swap.h
@@ -177,11 +177,11 @@ extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
 extern int lru_add_drain_all(void);
-extern int rotate_reclaimable_page(struct page *page);
+extern void rotate_reclaimable_page(struct page *page);
 extern void swap_setup(void);
 
 /* linux/mm/vmscan.c */
-extern unsigned long try_to_free_pages(struct zone **zones, int order,
+extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask);
 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
 							gfp_t gfp_mask);
diff --git a/trunk/include/linux/synclink.h b/trunk/include/linux/synclink.h
index 5562fbf72095..45f6bc82d317 100644
--- a/trunk/include/linux/synclink.h
+++ b/trunk/include/linux/synclink.h
@@ -13,10 +13,6 @@
 #define _SYNCLINK_H_
 #define SYNCLINK_H_VERSION 3.6
 
-#define BOOLEAN int
-#define TRUE 1
-#define FALSE 0
-
 #define BIT0	0x0001
 #define BIT1	0x0002
 #define BIT2	0x0004
diff --git a/trunk/include/linux/syscalls.h b/trunk/include/linux/syscalls.h
index 8df6d1382ac8..0522f368f9d7 100644
--- a/trunk/include/linux/syscalls.h
+++ b/trunk/include/linux/syscalls.h
@@ -240,26 +240,28 @@ asmlinkage long sys_truncate64(const char __user *path, loff_t length);
 asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length);
 #endif
 
-asmlinkage long sys_setxattr(char __user *path, char __user *name,
-				void __user *value, size_t size, int flags);
-asmlinkage long sys_lsetxattr(char __user *path, char __user *name,
-				void __user *value, size_t size, int flags);
-asmlinkage long sys_fsetxattr(int fd, char __user *name, void __user *value,
-				size_t size, int flags);
-asmlinkage ssize_t sys_getxattr(char __user *path, char __user *name,
+asmlinkage long sys_setxattr(const char __user *path, const char __user *name,
+			     const void __user *value, size_t size, int flags);
+asmlinkage long sys_lsetxattr(const char __user *path, const char __user *name,
+			      const void __user *value, size_t size, int flags);
+asmlinkage long sys_fsetxattr(int fd, const char __user *name,
+			      const void __user *value, size_t size, int flags);
+asmlinkage ssize_t sys_getxattr(const char __user *path, const char __user *name,
 				void __user *value, size_t size);
-asmlinkage ssize_t sys_lgetxattr(char __user *path, char __user *name,
+asmlinkage ssize_t sys_lgetxattr(const char __user *path, const char __user *name,
 				void __user *value, size_t size);
-asmlinkage ssize_t sys_fgetxattr(int fd, char __user *name,
+asmlinkage ssize_t sys_fgetxattr(int fd, const char __user *name,
 				void __user *value, size_t size);
-asmlinkage ssize_t sys_listxattr(char __user *path, char __user *list,
+asmlinkage ssize_t sys_listxattr(const char __user *path, char __user *list,
 				size_t size);
-asmlinkage ssize_t sys_llistxattr(char __user *path, char __user *list,
+asmlinkage ssize_t sys_llistxattr(const char __user *path, char __user *list,
 				size_t size);
 asmlinkage ssize_t sys_flistxattr(int fd, char __user *list, size_t size);
-asmlinkage long sys_removexattr(char __user *path, char __user *name);
-asmlinkage long sys_lremovexattr(char __user *path, char __user *name);
-asmlinkage long sys_fremovexattr(int fd, char __user *name);
+asmlinkage long sys_removexattr(const char __user *path,
+				const char __user *name);
+asmlinkage long sys_lremovexattr(const char __user *path,
+				 const char __user *name);
+asmlinkage long sys_fremovexattr(int fd, const char __user *name);
 
 asmlinkage unsigned long sys_brk(unsigned long brk);
 asmlinkage long sys_mprotect(unsigned long start, size_t len,
diff --git a/trunk/include/linux/sysctl.h b/trunk/include/linux/sysctl.h
index 571f01d20a86..24141b4d1a11 100644
--- a/trunk/include/linux/sysctl.h
+++ b/trunk/include/linux/sysctl.h
@@ -945,11 +945,14 @@ enum
 /* For the /proc/sys support */
 struct ctl_table;
 struct nsproxy;
+struct ctl_table_root;
+
 extern struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev);
 extern struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces,
 						struct ctl_table_header *prev);
 extern void sysctl_head_finish(struct ctl_table_header *prev);
-extern int sysctl_perm(struct ctl_table *table, int op);
+extern int sysctl_perm(struct ctl_table_root *root,
+		struct ctl_table *table, int op);
 
 typedef struct ctl_table ctl_table;
 
@@ -981,11 +984,6 @@ extern int do_sysctl (int __user *name, int nlen,
 		      void __user *oldval, size_t __user *oldlenp,
 		      void __user *newval, size_t newlen);
 
-extern int do_sysctl_strategy (struct ctl_table *table,
-			       int __user *name, int nlen,
-			       void __user *oldval, size_t __user *oldlenp,
-			       void __user *newval, size_t newlen);
-
 extern ctl_handler sysctl_data;
 extern ctl_handler sysctl_string;
 extern ctl_handler sysctl_intvec;
@@ -1054,6 +1052,8 @@ struct ctl_table_root {
 	struct list_head header_list;
 	struct list_head *(*lookup)(struct ctl_table_root *root,
 					   struct nsproxy *namespaces);
+	int (*permissions)(struct ctl_table_root *root,
+			struct nsproxy *namespaces, struct ctl_table *table);
 };
 
 /* struct ctl_table_header is used to maintain dynamic lists of
@@ -1085,8 +1085,6 @@ struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
 void unregister_sysctl_table(struct ctl_table_header * table);
 int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table);
 
-#else /* __KERNEL__ */
-
 #endif /* __KERNEL__ */
 
 #endif /* _LINUX_SYSCTL_H */
diff --git a/trunk/include/linux/sysfs.h b/trunk/include/linux/sysfs.h
index 03378e3515b3..add3c5a40827 100644
--- a/trunk/include/linux/sysfs.h
+++ b/trunk/include/linux/sysfs.h
@@ -32,7 +32,7 @@ struct attribute {
 
 struct attribute_group {
 	const char		*name;
-	int			(*is_visible)(struct kobject *,
+	mode_t			(*is_visible)(struct kobject *,
 					      struct attribute *, int);
 	struct attribute	**attrs;
 };
@@ -105,6 +105,8 @@ void sysfs_remove_link(struct kobject *kobj, const char *name);
 
 int __must_check sysfs_create_group(struct kobject *kobj,
 				    const struct attribute_group *grp);
+int sysfs_update_group(struct kobject *kobj,
+		       const struct attribute_group *grp);
 void sysfs_remove_group(struct kobject *kobj,
 			const struct attribute_group *grp);
 int sysfs_add_file_to_group(struct kobject *kobj,
diff --git a/trunk/include/linux/sysv_fs.h b/trunk/include/linux/sysv_fs.h
index e0248631e461..96411306eec6 100644
--- a/trunk/include/linux/sysv_fs.h
+++ b/trunk/include/linux/sysv_fs.h
@@ -1,11 +1,7 @@
 #ifndef _LINUX_SYSV_FS_H
 #define _LINUX_SYSV_FS_H
 
-#if defined(__GNUC__)
-# define __packed2__	__attribute__((packed, aligned(2)))
-#else
->> I want to scream! <<
-#endif
+#define __packed2__	__attribute__((packed, aligned(2)))
 
 
 #ifndef __KERNEL__
diff --git a/trunk/include/linux/unaligned/access_ok.h b/trunk/include/linux/unaligned/access_ok.h
new file mode 100644
index 000000000000..99c1b4d20b0f
--- /dev/null
+++ b/trunk/include/linux/unaligned/access_ok.h
@@ -0,0 +1,67 @@
+#ifndef _LINUX_UNALIGNED_ACCESS_OK_H
+#define _LINUX_UNALIGNED_ACCESS_OK_H
+
+#include <linux/kernel.h>
+#include <asm/byteorder.h>
+
+static inline u16 get_unaligned_le16(const void *p)
+{
+	return le16_to_cpup((__le16 *)p);
+}
+
+static inline u32 get_unaligned_le32(const void *p)
+{
+	return le32_to_cpup((__le32 *)p);
+}
+
+static inline u64 get_unaligned_le64(const void *p)
+{
+	return le64_to_cpup((__le64 *)p);
+}
+
+static inline u16 get_unaligned_be16(const void *p)
+{
+	return be16_to_cpup((__be16 *)p);
+}
+
+static inline u32 get_unaligned_be32(const void *p)
+{
+	return be32_to_cpup((__be32 *)p);
+}
+
+static inline u64 get_unaligned_be64(const void *p)
+{
+	return be64_to_cpup((__be64 *)p);
+}
+
+static inline void put_unaligned_le16(u16 val, void *p)
+{
+	*((__le16 *)p) = cpu_to_le16(val);
+}
+
+static inline void put_unaligned_le32(u32 val, void *p)
+{
+	*((__le32 *)p) = cpu_to_le32(val);
+}
+
+static inline void put_unaligned_le64(u64 val, void *p)
+{
+	*((__le64 *)p) = cpu_to_le64(val);
+}
+
+static inline void put_unaligned_be16(u16 val, void *p)
+{
+	*((__be16 *)p) = cpu_to_be16(val);
+}
+
+static inline void put_unaligned_be32(u32 val, void *p)
+{
+	*((__be32 *)p) = cpu_to_be32(val);
+}
+
+static inline void put_unaligned_be64(u64 val, void *p)
+{
+	*((__be64 *)p) = cpu_to_be64(val);
+}
+
+#endif /* _LINUX_UNALIGNED_ACCESS_OK_H */
diff --git a/trunk/include/linux/unaligned/be_byteshift.h b/trunk/include/linux/unaligned/be_byteshift.h
new file mode 100644
index 000000000000..46dd12c5709e
--- /dev/null
+++ b/trunk/include/linux/unaligned/be_byteshift.h
@@ -0,0 +1,70 @@
+#ifndef _LINUX_UNALIGNED_BE_BYTESHIFT_H
+#define _LINUX_UNALIGNED_BE_BYTESHIFT_H
+
+#include <linux/kernel.h>
+
+static inline u16 __get_unaligned_be16(const u8 *p)
+{
+	return p[0] << 8 | p[1];
+}
+
+static inline u32 __get_unaligned_be32(const u8 *p)
+{
+	return p[0] << 24 | p[1] << 16 | p[2] << 8 | p[3];
+}
+
+static inline u64 __get_unaligned_be64(const u8 *p)
+{
+	return (u64)__get_unaligned_be32(p) << 32 |
+	       __get_unaligned_be32(p + 4);
+}
+
+static inline void __put_unaligned_be16(u16 val, u8 *p)
+{
+	*p++ = val >> 8;
+	*p++ = val;
+}
+
+static inline void __put_unaligned_be32(u32 val, u8 *p)
+{
+	__put_unaligned_be16(val >> 16, p);
+	__put_unaligned_be16(val, p + 2);
+}
+
+static inline void __put_unaligned_be64(u64 val, u8 *p)
+{
+	__put_unaligned_be32(val >> 32, p);
+	__put_unaligned_be32(val, p + 4);
+}
+
+static inline u16 get_unaligned_be16(const void *p)
+{
+	return __get_unaligned_be16((const u8 *)p);
+}
+
+static inline u32 get_unaligned_be32(const void *p)
+{
+	return __get_unaligned_be32((const u8 *)p);
+}
+
+static inline u64 get_unaligned_be64(const void *p)
+{
+	return __get_unaligned_be64((const u8 *)p);
+}
+
+static inline void put_unaligned_be16(u16 val, void *p)
+{
+	__put_unaligned_be16(val, p);
+}
+
+static inline void put_unaligned_be32(u32 val, void *p)
+{
+	__put_unaligned_be32(val, p);
+}
+
+static inline void put_unaligned_be64(u64 val, void *p)
+{
+	__put_unaligned_be64(val, p);
+}
+
+#endif /* _LINUX_UNALIGNED_BE_BYTESHIFT_H */
diff --git a/trunk/include/linux/unaligned/be_memmove.h b/trunk/include/linux/unaligned/be_memmove.h
new file mode 100644
index 000000000000..c2a76c5c9ed0
--- /dev/null
+++ b/trunk/include/linux/unaligned/be_memmove.h
@@ -0,0 +1,36 @@
+#ifndef _LINUX_UNALIGNED_BE_MEMMOVE_H
+#define _LINUX_UNALIGNED_BE_MEMMOVE_H
+
+#include <linux/unaligned/memmove.h>
+
+static inline u16 get_unaligned_be16(const void *p)
+{
+	return __get_unaligned_memmove16((const u8 *)p);
+}
+
+static inline u32 get_unaligned_be32(const void *p)
+{
+	return __get_unaligned_memmove32((const u8 *)p);
+}
+
+static inline u64 get_unaligned_be64(const void *p)
+{
+	return __get_unaligned_memmove64((const u8 *)p);
+}
+
+static inline void put_unaligned_be16(u16 val, void *p)
+{
+	__put_unaligned_memmove16(val, p);
+}
+
+static inline void put_unaligned_be32(u32 val, void *p)
+{
+	__put_unaligned_memmove32(val, p);
+}
+
+static inline void put_unaligned_be64(u64 val, void *p)
+{
+	__put_unaligned_memmove64(val, p);
+}
+
+#endif /* _LINUX_UNALIGNED_LE_MEMMOVE_H */
diff --git a/trunk/include/linux/unaligned/be_struct.h b/trunk/include/linux/unaligned/be_struct.h
new file mode 100644
index 000000000000..132415836c50
--- /dev/null
+++ b/trunk/include/linux/unaligned/be_struct.h
@@ -0,0 +1,36 @@
+#ifndef _LINUX_UNALIGNED_BE_STRUCT_H
+#define _LINUX_UNALIGNED_BE_STRUCT_H
+
+#include <linux/unaligned/packed_struct.h>
+
+static inline u16 get_unaligned_be16(const void *p)
+{
+	return __get_unaligned_cpu16((const u8 *)p);
+}
+
+static inline u32 get_unaligned_be32(const void *p)
+{
+	return __get_unaligned_cpu32((const u8 *)p);
+}
+
+static inline u64 get_unaligned_be64(const void *p)
+{
+	return __get_unaligned_cpu64((const u8 *)p);
+}
+
+static inline void put_unaligned_be16(u16 val, void *p)
+{
+	__put_unaligned_cpu16(val, p);
+}
+
+static inline void put_unaligned_be32(u32 val, void *p)
+{
+	__put_unaligned_cpu32(val, p);
+}
+
+static inline void put_unaligned_be64(u64 val, void *p)
+{
+	__put_unaligned_cpu64(val, p);
+}
+
+#endif /* _LINUX_UNALIGNED_BE_STRUCT_H */
diff --git a/trunk/include/linux/unaligned/generic.h b/trunk/include/linux/unaligned/generic.h
new file mode 100644
index 000000000000..02d97ff3df70
--- /dev/null
+++ b/trunk/include/linux/unaligned/generic.h
@@ -0,0 +1,68 @@
+#ifndef _LINUX_UNALIGNED_GENERIC_H
+#define _LINUX_UNALIGNED_GENERIC_H
+
+/*
+ * Cause a link-time error if we try an unaligned access other than
+ * 1,2,4 or 8 bytes long
+ */
+extern void __bad_unaligned_access_size(void);
+
+#define __get_unaligned_le(ptr) ((__force typeof(*(ptr)))({			\
+	__builtin_choose_expr(sizeof(*(ptr)) == 1, *(ptr),			\
+	__builtin_choose_expr(sizeof(*(ptr)) == 2, get_unaligned_le16((ptr)),	\
+	__builtin_choose_expr(sizeof(*(ptr)) == 4, get_unaligned_le32((ptr)),	\
+	__builtin_choose_expr(sizeof(*(ptr)) == 8, get_unaligned_le64((ptr)),	\
+	__bad_unaligned_access_size()))));					\
+	}))
+
+#define __get_unaligned_be(ptr) ((__force typeof(*(ptr)))({			\
+	__builtin_choose_expr(sizeof(*(ptr)) == 1, *(ptr),			\
+	__builtin_choose_expr(sizeof(*(ptr)) == 2, get_unaligned_be16((ptr)),	\
+	__builtin_choose_expr(sizeof(*(ptr)) == 4, get_unaligned_be32((ptr)),	\
+	__builtin_choose_expr(sizeof(*(ptr)) == 8, get_unaligned_be64((ptr)),	\
+	__bad_unaligned_access_size()))));					\
+	}))
+
+#define __put_unaligned_le(val, ptr) ({					\
+	void *__gu_p = (ptr);						\
+	switch (sizeof(*(ptr))) {					\
+	case 1:								\
+		*(u8 *)__gu_p = (__force u8)(val);			\
+		break;							\
+	case 2:								\
+		put_unaligned_le16((__force u16)(val), __gu_p);		\
+		break;							\
+	case 4:								\
+		put_unaligned_le32((__force u32)(val), __gu_p);		\
+		break;							\
+	case 8:								\
+		put_unaligned_le64((__force u64)(val), __gu_p);		\
+		break;							\
+	default:							\
+		__bad_unaligned_access_size();				\
+		break;							\
+	}								\
+	(void)0; })
+
+#define __put_unaligned_be(val, ptr) ({					\
+	void *__gu_p = (ptr);						\
+	switch (sizeof(*(ptr))) {					\
+	case 1:								\
+		*(u8 *)__gu_p = (__force u8)(val);			\
+		break;							\
+	case 2:								\
+		put_unaligned_be16((__force u16)(val), __gu_p);		\
+		break;							\
+	case 4:								\
+		put_unaligned_be32((__force u32)(val), __gu_p);		\
+		break;							\
+	case 8:								\
+		put_unaligned_be64((__force u64)(val), __gu_p);		\
+		break;							\
+	default:							\
+		__bad_unaligned_access_size();				\
+		break;							\
+	}								\
+	(void)0; })
+
+#endif /* _LINUX_UNALIGNED_GENERIC_H */
diff --git a/trunk/include/linux/unaligned/le_byteshift.h b/trunk/include/linux/unaligned/le_byteshift.h
new file mode 100644
index 000000000000..59777e951baf
--- /dev/null
+++ b/trunk/include/linux/unaligned/le_byteshift.h
@@ -0,0 +1,70 @@
+#ifndef _LINUX_UNALIGNED_LE_BYTESHIFT_H
+#define _LINUX_UNALIGNED_LE_BYTESHIFT_H
+
+#include <linux/kernel.h>
+
+static inline u16 __get_unaligned_le16(const u8 *p)
+{
+	return p[0] | p[1] << 8;
+}
+
+static inline u32 __get_unaligned_le32(const u8 *p)
+{
+	return p[0] | p[1] << 8 | p[2] << 16 | p[3] << 24;
+}
+
+static inline u64 __get_unaligned_le64(const u8 *p)
+{
+	return (u64)__get_unaligned_le32(p + 4) << 32 |
+	       __get_unaligned_le32(p);
+}
+
+static inline void __put_unaligned_le16(u16 val, u8 *p)
+{
+	*p++ = val;
+	*p++ = val >> 8;
+}
+
+static inline void __put_unaligned_le32(u32 val, u8 *p)
+{
+	__put_unaligned_le16(val >> 16, p + 2);
+	__put_unaligned_le16(val, p);
+}
+
+static inline void __put_unaligned_le64(u64 val, u8 *p)
+{
+	__put_unaligned_le32(val >> 32, p + 4);
+	__put_unaligned_le32(val, p);
+}
+
+static inline u16 get_unaligned_le16(const void *p)
+{
+	return __get_unaligned_le16((const u8 *)p);
+}
+
+static inline u32 get_unaligned_le32(const void *p)
+{
+	return __get_unaligned_le32((const u8 *)p);
+}
+
+static inline u64 get_unaligned_le64(const void *p)
+{
+	return __get_unaligned_le64((const u8 *)p);
+}
+
+static inline void put_unaligned_le16(u16 val, void *p)
+{
+	__put_unaligned_le16(val, p);
+}
+
+static inline void put_unaligned_le32(u32 val, void *p)
+{
+	__put_unaligned_le32(val, p);
+}
+
+static inline void put_unaligned_le64(u64 val, void *p)
+{
+	__put_unaligned_le64(val, p);
+}
+
+#endif /* _LINUX_UNALIGNED_LE_BYTESHIFT_H */
diff --git a/trunk/include/linux/unaligned/le_memmove.h b/trunk/include/linux/unaligned/le_memmove.h
new file mode 100644
index 000000000000..269849bee4ec
--- /dev/null
+++ b/trunk/include/linux/unaligned/le_memmove.h
@@ -0,0 +1,36 @@
+#ifndef _LINUX_UNALIGNED_LE_MEMMOVE_H
+#define _LINUX_UNALIGNED_LE_MEMMOVE_H
+
+#include <linux/unaligned/memmove.h>
+
+static inline u16 get_unaligned_le16(const void *p)
+{
+	return __get_unaligned_memmove16((const u8 *)p);
+}
+
+static inline u32 get_unaligned_le32(const void *p)
+{
+	return __get_unaligned_memmove32((const u8 *)p);
+}
+
+static inline u64 get_unaligned_le64(const void *p)
+{
+	return __get_unaligned_memmove64((const u8 *)p);
+}
+
+static inline void put_unaligned_le16(u16 val, void *p)
+{
+	__put_unaligned_memmove16(val, p);
+}
+
+static inline void put_unaligned_le32(u32 val, void *p)
+{
+	__put_unaligned_memmove32(val, p);
+}
+
+static inline void put_unaligned_le64(u64 val, void *p)
+{
+	__put_unaligned_memmove64(val, p);
+}
+
+#endif /* _LINUX_UNALIGNED_LE_MEMMOVE_H */
diff --git a/trunk/include/linux/unaligned/le_struct.h b/trunk/include/linux/unaligned/le_struct.h
new file mode 100644
index 000000000000..088c4572faa8
--- /dev/null
+++ b/trunk/include/linux/unaligned/le_struct.h
@@ -0,0 +1,36 @@
+#ifndef _LINUX_UNALIGNED_LE_STRUCT_H
+#define _LINUX_UNALIGNED_LE_STRUCT_H
+
+#include <linux/unaligned/packed_struct.h>
+
+static inline u16 get_unaligned_le16(const void *p)
+{
+	return __get_unaligned_cpu16((const u8 *)p);
+}
+
+static inline u32 get_unaligned_le32(const void *p)
+{
+	return __get_unaligned_cpu32((const u8 *)p);
+}
+
+static inline u64 get_unaligned_le64(const void *p)
+{
+	return __get_unaligned_cpu64((const u8 *)p);
+}
+
+static inline void put_unaligned_le16(u16 val, void *p)
+{
+	__put_unaligned_cpu16(val, p);
+}
+
+static inline void put_unaligned_le32(u32 val, void *p)
+{
+	__put_unaligned_cpu32(val, p);
+}
+
+static inline void put_unaligned_le64(u64 val, void *p)
+{
+	__put_unaligned_cpu64(val, p);
+}
+
+#endif /* _LINUX_UNALIGNED_LE_STRUCT_H */
diff --git a/trunk/include/linux/unaligned/memmove.h b/trunk/include/linux/unaligned/memmove.h
new file mode 100644
index 000000000000..eeb5a779a4fd
--- /dev/null
+++ b/trunk/include/linux/unaligned/memmove.h
@@ -0,0 +1,45 @@
+#ifndef _LINUX_UNALIGNED_MEMMOVE_H
+#define _LINUX_UNALIGNED_MEMMOVE_H
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+
+/* Use memmove here, so gcc does not insert a __builtin_memcpy. */
+
+static inline u16 __get_unaligned_memmove16(const void *p)
+{
+	u16 tmp;
+	memmove(&tmp, p, 2);
+	return tmp;
+}
+
+static inline u32 __get_unaligned_memmove32(const void *p)
+{
+	u32 tmp;
+	memmove(&tmp, p, 4);
+	return tmp;
+}
+
+static inline u64 __get_unaligned_memmove64(const void *p)
+{
+	u64 tmp;
+	memmove(&tmp, p, 8);
+	return tmp;
+}
+
+static inline void __put_unaligned_memmove16(u16 val, void *p)
+{
+	memmove(p, &val, 2);
+}
+
+static inline void __put_unaligned_memmove32(u32 val, void *p)
+{
+	memmove(p, &val, 4);
+}
+
+static inline void __put_unaligned_memmove64(u64 val, void *p)
+{
+	memmove(p, &val, 8);
+}
+
+#endif /* _LINUX_UNALIGNED_MEMMOVE_H */
diff --git a/trunk/include/linux/unaligned/packed_struct.h b/trunk/include/linux/unaligned/packed_struct.h
new file mode 100644
index 000000000000..2498bb9fe002
--- /dev/null
+++ b/trunk/include/linux/unaligned/packed_struct.h
@@ -0,0 +1,46 @@
+#ifndef _LINUX_UNALIGNED_PACKED_STRUCT_H
+#define _LINUX_UNALIGNED_PACKED_STRUCT_H
+
+#include <linux/kernel.h>
+
+struct __una_u16 { u16 x __attribute__((packed)); };
+struct __una_u32 { u32 x __attribute__((packed)); };
+struct __una_u64 { u64 x __attribute__((packed)); };
+
+static inline u16 __get_unaligned_cpu16(const void *p)
+{
+	const struct __una_u16 *ptr = (const struct __una_u16 *)p;
+	return ptr->x;
+}
+
+static inline u32 __get_unaligned_cpu32(const void *p)
+{
+	const struct __una_u32 *ptr = (const struct __una_u32 *)p;
+	return ptr->x;
+}
+
+static inline u64 __get_unaligned_cpu64(const void *p)
+{
+	const struct __una_u64 *ptr = (const struct __una_u64 *)p;
+	return ptr->x;
+}
+
+static inline void __put_unaligned_cpu16(u16 val, void *p)
+{
+	struct __una_u16 *ptr = (struct __una_u16 *)p;
+	ptr->x = val;
+}
+
+static inline void __put_unaligned_cpu32(u32 val, void *p)
+{
+	struct __una_u32 *ptr = (struct __una_u32 *)p;
+	ptr->x = val;
+}
+
+static inline void __put_unaligned_cpu64(u64 val, void *p)
+{
+	struct __una_u64 *ptr = (struct __una_u64 *)p;
+	ptr->x = val;
+}
+
+#endif /* _LINUX_UNALIGNED_PACKED_STRUCT_H */
diff --git a/trunk/include/linux/vmalloc.h b/trunk/include/linux/vmalloc.h
index ce8e7da05807..364789aae9f3 100644
--- a/trunk/include/linux/vmalloc.h
+++ b/trunk/include/linux/vmalloc.h
@@ -31,6 +31,7 @@ struct vm_struct {
 	struct page		**pages;
 	unsigned int		nr_pages;
 	unsigned long		phys_addr;
+	void			*caller;
 };
 
 /*
@@ -66,6 +67,8 @@ static inline size_t get_vm_area_size(const struct vm_struct *area)
 }
 
 extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags);
+extern struct vm_struct *get_vm_area_caller(unsigned long size,
+					unsigned long flags, void *caller);
 extern struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
 					unsigned long start, unsigned long end);
 extern struct vm_struct *get_vm_area_node(unsigned long size,
@@ -87,4 +90,6 @@ extern void free_vm_area(struct vm_struct *area);
 extern rwlock_t vmlist_lock;
 extern struct vm_struct *vmlist;
 
+extern const struct seq_operations vmalloc_op;
+
 #endif /* _LINUX_VMALLOC_H */
diff --git a/trunk/include/linux/vmstat.h b/trunk/include/linux/vmstat.h
index 9f1b4b46151e..e83b69346d23 100644
--- a/trunk/include/linux/vmstat.h
+++ b/trunk/include/linux/vmstat.h
@@ -25,6 +25,7 @@
 #define HIGHMEM_ZONE(xx)
 #endif
 
+
 #define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL HIGHMEM_ZONE(xx) , xx##_MOVABLE
 
 enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
@@ -37,6 +38,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGSCAN_DIRECT),
 		PGINODESTEAL, SLABS_SCANNED, KSWAPD_STEAL, KSWAPD_INODESTEAL,
 		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
+#ifdef CONFIG_HUGETLB_PAGE
+		HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL,
+#endif
 		NR_VM_EVENT_ITEMS
 };
 
@@ -174,7 +178,7 @@ static inline unsigned long node_page_state(int node,
 		zone_page_state(&zones[ZONE_MOVABLE], item);
 }
 
-extern void zone_statistics(struct zonelist *, struct zone *);
+extern void zone_statistics(struct zone *, struct zone *);
 
 #else
 
diff --git a/trunk/include/linux/xattr.h b/trunk/include/linux/xattr.h
index df6b95d2218e..d131e352cfe1 100644
--- a/trunk/include/linux/xattr.h
+++ b/trunk/include/linux/xattr.h
@@ -47,10 +47,10 @@ struct xattr_handler {
 };
 
 ssize_t xattr_getsecurity(struct inode *, const char *, void *, size_t);
-ssize_t vfs_getxattr(struct dentry *, char *, void *, size_t);
+ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t);
 ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size);
-int vfs_setxattr(struct dentry *, char *, void *, size_t, int);
-int vfs_removexattr(struct dentry *, char *);
+int vfs_setxattr(struct dentry *, const char *, const void *, size_t, int);
+int vfs_removexattr(struct dentry *, const char *);
 
 ssize_t generic_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size);
 ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size);
diff --git a/trunk/include/net/compat.h b/trunk/include/net/compat.h
index 406db242f73a..05fa5d0254ab 100644
--- a/trunk/include/net/compat.h
+++ b/trunk/include/net/compat.h
@@ -40,4 +40,7 @@ extern int put_cmsg_compat(struct msghdr*, int, int, int, void *);
 
 extern int cmsghdr_from_user_compat_to_kern(struct msghdr *, struct sock *, unsigned char *, int);
 
+extern int compat_mc_setsockopt(struct sock *, int, int, char __user *, int,
+	int (*)(struct sock *, int, int, char __user *, int));
+
 #endif /* NET_COMPAT_H */
diff --git a/trunk/include/rdma/ib_umem.h b/trunk/include/rdma/ib_umem.h
index 22298423cf0b..9ee0d2e51b16 100644
--- a/trunk/include/rdma/ib_umem.h
+++ b/trunk/include/rdma/ib_umem.h
@@ -62,7 +62,7 @@ struct ib_umem_chunk {
 #ifdef CONFIG_INFINIBAND_USER_MEM
 
 struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
-			    size_t size, int access);
+			    size_t size, int access, int dmasync);
 void ib_umem_release(struct ib_umem *umem);
 int ib_umem_page_count(struct ib_umem *umem);
 
@@ -72,7 +72,7 @@ int ib_umem_page_count(struct ib_umem *umem);
 
 static inline struct ib_umem *ib_umem_get(struct ib_ucontext *context,
 					  unsigned long addr, size_t size,
-					  int access) {
+					  int access, int dmasync) {
 	return ERR_PTR(-EINVAL);
 }
 static inline void ib_umem_release(struct ib_umem *umem) { }
diff --git a/trunk/include/rdma/ib_verbs.h b/trunk/include/rdma/ib_verbs.h
index 2dcbecce3f61..911a661b7278 100644
--- a/trunk/include/rdma/ib_verbs.h
+++ b/trunk/include/rdma/ib_verbs.h
@@ -1542,6 +1542,24 @@ static inline void ib_dma_unmap_single(struct ib_device *dev,
 		dma_unmap_single(dev->dma_device, addr, size, direction);
 }
 
+static inline u64 ib_dma_map_single_attrs(struct ib_device *dev,
+					  void *cpu_addr, size_t size,
+					  enum dma_data_direction direction,
+					  struct dma_attrs *attrs)
+{
+	return dma_map_single_attrs(dev->dma_device, cpu_addr, size,
+				    direction, attrs);
+}
+
+static inline void ib_dma_unmap_single_attrs(struct ib_device *dev,
+					     u64 addr, size_t size,
+					     enum dma_data_direction direction,
+					     struct dma_attrs *attrs)
+{
+	return dma_unmap_single_attrs(dev->dma_device, addr, size,
+				      direction, attrs);
+}
+
 /**
  * ib_dma_map_page - Map a physical page to DMA address
  * @dev: The device for which the dma_addr is to be created
@@ -1611,6 +1629,21 @@ static inline void ib_dma_unmap_sg(struct ib_device *dev,
 		dma_unmap_sg(dev->dma_device, sg, nents, direction);
 }
 
+static inline int ib_dma_map_sg_attrs(struct ib_device *dev,
+				      struct scatterlist *sg, int nents,
+				      enum dma_data_direction direction,
+				      struct dma_attrs *attrs)
+{
+	return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, attrs);
+}
+
+static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev,
+					 struct scatterlist *sg, int nents,
+					 enum dma_data_direction direction,
+					 struct dma_attrs *attrs)
+{
+	dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, attrs);
+}
 /**
  * ib_sg_dma_address - Return the DMA address from a scatter/gather entry
  * @dev: The device for which the DMA addresses were created
diff --git a/trunk/include/scsi/scsi_device.h b/trunk/include/scsi/scsi_device.h
index b8b19e2f57bb..f6a9fe0ef09c 100644
--- a/trunk/include/scsi/scsi_device.h
+++ b/trunk/include/scsi/scsi_device.h
@@ -181,7 +181,8 @@ struct scsi_device {
 	sdev_printk(prefix, (scmd)->device, fmt, ##a)
 
 enum scsi_target_state {
-	STARGET_RUNNING = 1,
+	STARGET_CREATED = 1,
+	STARGET_RUNNING,
 	STARGET_DEL,
 };
 
diff --git a/trunk/include/video/atmel_lcdc.h b/trunk/include/video/atmel_lcdc.h
index 336c20db87f8..ed64862c4e18 100644
--- a/trunk/include/video/atmel_lcdc.h
+++ b/trunk/include/video/atmel_lcdc.h
@@ -22,6 +22,15 @@
 #ifndef __ATMEL_LCDC_H__
 #define __ATMEL_LCDC_H__
 
+
+/* Way LCD wires are connected to the chip:
+ * Some Atmel chips use BGR color mode (instead of standard RGB)
+ * A swapped wiring onboard can bring to RGB mode.
+ */
+#define ATMEL_LCDC_WIRING_BGR	0
+#define ATMEL_LCDC_WIRING_RGB	1
+
+
  /* LCD Controller info data structure, stored in device platform_data */
 struct atmel_lcdfb_info {
 	spinlock_t		lock;
@@ -39,8 +48,10 @@ struct atmel_lcdfb_info {
 	u8			bl_power;
 #endif
 	bool			lcdcon_is_backlight;
+	u8			saved_lcdcon;
 
 	u8			default_bpp;
+	u8			lcd_wiring_mode;
 	unsigned int		default_lcdcon2;
 	unsigned int		default_dmacon;
 	void (*atmel_lcdfb_power_control)(int on);
diff --git a/trunk/include/video/hecubafb.h b/trunk/include/video/hecubafb.h
new file mode 100644
index 000000000000..7b9952339762
--- /dev/null
+++ b/trunk/include/video/hecubafb.h
@@ -0,0 +1,51 @@
+/*
+ * hecubafb.h - definitions for the hecuba framebuffer driver
+ *
+ * Copyright (C) 2008 by Jaya Kumar
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file COPYING in the main directory of this archive for
+ * more details.
+ *
+ */
+
+#ifndef _LINUX_HECUBAFB_H_
+#define _LINUX_HECUBAFB_H_
+
+/* Apollo controller specific defines */
+#define APOLLO_START_NEW_IMG	0xA0
+#define APOLLO_STOP_IMG_DATA	0xA1
+#define APOLLO_DISPLAY_IMG	0xA2
+#define APOLLO_ERASE_DISPLAY	0xA3
+#define APOLLO_INIT_DISPLAY	0xA4
+
+/* Hecuba interface specific defines */
+#define HCB_WUP_BIT	0x01
+#define HCB_DS_BIT 	0x02
+#define HCB_RW_BIT 	0x04
+#define HCB_CD_BIT 	0x08
+#define HCB_ACK_BIT 	0x80
+
+/* struct used by hecuba. board specific stuff comes from *board */
+struct hecubafb_par {
+	struct fb_info *info;
+	struct hecuba_board *board;
+	void (*send_command)(struct hecubafb_par *, unsigned char);
+	void (*send_data)(struct hecubafb_par *, unsigned char);
+};
+
+/* board specific routines
+board drivers can implement wait_for_ack with interrupts if desired. if
+wait_for_ack is called with clear=0, then go to sleep and return when ack
+goes hi or if wait_for_ack with clear=1, then return when ack goes lo */
+struct hecuba_board {
+	struct module *owner;
+	void (*remove)(struct hecubafb_par *);
+	void (*set_ctl)(struct hecubafb_par *, unsigned char, unsigned char);
+	void (*set_data)(struct hecubafb_par *, unsigned char);
+	void (*wait_for_ack)(struct hecubafb_par *, int);
+	int (*init)(struct hecubafb_par *);
+};
+
+
+#endif
diff --git a/trunk/include/video/metronomefb.h b/trunk/include/video/metronomefb.h
new file mode 100644
index 000000000000..dab04b4fad7f
--- /dev/null
+++ b/trunk/include/video/metronomefb.h
@@ -0,0 +1,62 @@
+/*
+ * metronomefb.h - definitions for the metronome framebuffer driver
+ *
+ * Copyright (C) 2008 by Jaya Kumar
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file COPYING in the main directory of this archive for
+ * more details.
+ *
+ */
+
+#ifndef _LINUX_METRONOMEFB_H_
+#define _LINUX_METRONOMEFB_H_
+
+/* address and control descriptors used by metronome controller */
+struct metromem_desc {
+	u32 mFDADR0;
+	u32 mFSADR0;
+	u32 mFIDR0;
+	u32 mLDCMD0;
+};
+
+/* command structure used by metronome controller */
+struct metromem_cmd {
+	u16 opcode;
+	u16 args[((64-2)/2)];
+	u16 csum;
+};
+
+/* struct used by metronome. board specific stuff comes from *board */
+struct metronomefb_par {
+	unsigned char *metromem;
+	struct metromem_desc *metromem_desc;
+	struct metromem_cmd *metromem_cmd;
+	unsigned char *metromem_wfm;
+	unsigned char *metromem_img;
+	u16 *metromem_img_csum;
+	u16 *csum_table;
+	int metromemsize;
+	dma_addr_t metromem_dma;
+	dma_addr_t metromem_desc_dma;
+	struct fb_info *info;
+	struct metronome_board *board;
+	wait_queue_head_t waitq;
+	u8 frame_count;
+};
+
+/* board specific routines */
+struct metronome_board {
+	struct module *owner;
+	void (*free_irq)(struct fb_info *);
+	void (*init_gpio_regs)(struct metronomefb_par *);
+	void (*init_lcdc_regs)(struct metronomefb_par *);
+	void (*post_dma_setup)(struct metronomefb_par *);
+	void (*set_rst)(struct metronomefb_par *, int);
+	void (*set_stdby)(struct metronomefb_par *, int);
+	int (*met_wait_event)(struct metronomefb_par *);
+	int (*met_wait_event_intr)(struct metronomefb_par *);
+	int (*setup_irq)(struct fb_info *);
+};
+
+#endif
diff --git a/trunk/init/Kconfig b/trunk/init/Kconfig
index ba3a389fab94..3e7b257fc05f 100644
--- a/trunk/init/Kconfig
+++ b/trunk/init/Kconfig
@@ -259,17 +259,14 @@ config IKCONFIG_PROC
 config LOG_BUF_SHIFT
 	int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
 	range 12 21
-	default 17 if S390 || LOCKDEP
-	default 16 if X86_NUMAQ || IA64
-	default 15 if SMP
-	default 14
+	default 17
 	help
 	  Select kernel log buffer size as a power of 2.
-	  Defaults and Examples:
-	  	     17 => 128 KB for S/390
-		     16 => 64 KB for x86 NUMAQ or IA-64
-	             15 => 32 KB for SMP
-	             14 => 16 KB for uniprocessor
+	  Examples:
+	  	     17 => 128 KB
+		     16 => 64 KB
+	             15 => 32 KB
+	             14 => 16 KB
 		     13 =>  8 KB
 		     12 =>  4 KB
 
@@ -284,6 +281,7 @@ config CGROUPS
 config CGROUP_DEBUG
 	bool "Example debug cgroup subsystem"
 	depends on CGROUPS
+	default n
 	help
 	  This option enables a simple cgroup subsystem that
 	  exports useful debugging information about the cgroups
@@ -300,6 +298,13 @@ config CGROUP_NS
           for instance virtual servers and checkpoint/restart
           jobs.
 
+config CGROUP_DEVICE
+	bool "Device controller for cgroups"
+	depends on CGROUPS && EXPERIMENTAL
+	help
+	  Provides a cgroup implementing whitelists for devices which
+	  a process in the cgroup can mknod or open.
+
 config CPUSETS
 	bool "Cpuset support"
 	depends on SMP && CGROUPS
@@ -373,9 +378,13 @@ config RESOURCE_COUNTERS
           infrastructure that works with cgroups
 	depends on CGROUPS
 
+config MM_OWNER
+	bool
+
 config CGROUP_MEM_RES_CTLR
 	bool "Memory Resource Controller for Control Groups"
 	depends on CGROUPS && RESOURCE_COUNTERS
+	select MM_OWNER
 	help
 	  Provides a memory resource controller that manages both page cache and
 	  RSS memory.
@@ -388,6 +397,9 @@ config CGROUP_MEM_RES_CTLR
 	  Only enable when you're ok with these trade offs and really
 	  sure you need the memory resource controller.
 
+	  This config option also selects MM_OWNER config option, which
+	  could in turn add some fork/exit overhead.
+
 config SYSFS_DEPRECATED
 	bool
 
@@ -496,16 +508,12 @@ source "usr/Kconfig"
 endif
 
 config CC_OPTIMIZE_FOR_SIZE
-	bool "Optimize for size (Look out for broken compilers!)"
+	bool "Optimize for size"
 	default y
-	depends on ARM || H8300 || SUPERH || EXPERIMENTAL
 	help
 	  Enabling this option will pass "-Os" instead of "-O2" to gcc
 	  resulting in a smaller kernel.
 
-	  WARNING: some versions of gcc may generate incorrect code with this
-	  option.  If problems are observed, a gcc upgrade may be needed.
-
 	  If unsure, say N.
 
 config SYSCTL
@@ -521,7 +529,7 @@ menuconfig EMBEDDED
 
 config UID16
 	bool "Enable 16-bit UID system calls" if EMBEDDED
-	depends on ARM || BLACKFIN || CRIS || FRV || H8300 || X86_32 || M68K || (S390 && !64BIT) || SUPERH || SPARC32 || (SPARC64 && SPARC32_COMPAT) || UML || (X86_64 && IA32_EMULATION)
+	depends on ARM || BLACKFIN || CRIS || FRV || H8300 || X86_32 || M68K || (S390 && !64BIT) || SUPERH || SPARC32 || (SPARC64 && COMPAT) || UML || (X86_64 && IA32_EMULATION)
 	default y
 	help
 	  This enables the legacy 16-bit UID syscall wrappers.
@@ -542,6 +550,17 @@ config SYSCTL_SYSCALL
 
 	  If unsure say Y here.
 
+config SYSCTL_SYSCALL_CHECK
+	bool "Sysctl checks" if EMBEDDED
+	depends on SYSCTL_SYSCALL
+	default y
+	---help---
+	  sys_sysctl uses binary paths that have been found challenging
+	  to properly maintain and use. This enables checks that help
+	  you to keep things correct.
+
+	  If unsure say Y here.
+
 config KALLSYMS
 	 bool "Load all symbols for debugging/ksymoops" if EMBEDDED
 	 default y
diff --git a/trunk/init/do_mounts_md.c b/trunk/init/do_mounts_md.c
index 753dc54a6649..7473b0c59d4d 100644
--- a/trunk/init/do_mounts_md.c
+++ b/trunk/init/do_mounts_md.c
@@ -133,7 +133,7 @@ static void __init md_setup_drive(void)
 		else
 			dev = MKDEV(MD_MAJOR, minor);
 		create_dev(name, dev);
-		for (i = 0; i < MD_SB_DISKS && devname != 0; i++) {
+		for (i = 0; i < MD_SB_DISKS && devname != NULL; i++) {
 			char *p;
 			char comp_name[64];
 			u32 rdev;
diff --git a/trunk/init/do_mounts_rd.c b/trunk/init/do_mounts_rd.c
index 3ac5904d1b12..46dfd64ae8fb 100644
--- a/trunk/init/do_mounts_rd.c
+++ b/trunk/init/do_mounts_rd.c
@@ -212,7 +212,7 @@ int __init rd_load_image(char *from)
 	}
 
 	buf = kmalloc(BLOCK_SIZE, GFP_KERNEL);
-	if (buf == 0) {
+	if (!buf) {
 		printk(KERN_ERR "RAMDISK: could not allocate buffer\n");
 		goto done;
 	}
diff --git a/trunk/init/initramfs.c b/trunk/init/initramfs.c
index d53fee8d8604..8eeeccb328c9 100644
--- a/trunk/init/initramfs.c
+++ b/trunk/init/initramfs.c
@@ -57,7 +57,7 @@ static char __init *find_link(int major, int minor, int ino,
 			continue;
 		return (*p)->name;
 	}
-	q = (struct hash *)malloc(sizeof(struct hash));
+	q = kmalloc(sizeof(struct hash), GFP_KERNEL);
 	if (!q)
 		panic("can't allocate link hash entry");
 	q->major = major;
@@ -77,7 +77,7 @@ static void __init free_hash(void)
 		while (*p) {
 			q = *p;
 			*p = q->next;
-			free(q);
+			kfree(q);
 		}
 	}
 }
@@ -445,10 +445,10 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only)
 {
 	int written;
 	dry_run = check_only;
-	header_buf = malloc(110);
-	symlink_buf = malloc(PATH_MAX + N_ALIGN(PATH_MAX) + 1);
-	name_buf = malloc(N_ALIGN(PATH_MAX));
-	window = malloc(WSIZE);
+	header_buf = kmalloc(110, GFP_KERNEL);
+	symlink_buf = kmalloc(PATH_MAX + N_ALIGN(PATH_MAX) + 1, GFP_KERNEL);
+	name_buf = kmalloc(N_ALIGN(PATH_MAX), GFP_KERNEL);
+	window = kmalloc(WSIZE, GFP_KERNEL);
 	if (!window || !header_buf || !symlink_buf || !name_buf)
 		panic("can't allocate buffers");
 	state = Start;
@@ -484,10 +484,10 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only)
 		buf += inptr;
 		len -= inptr;
 	}
-	free(window);
-	free(name_buf);
-	free(symlink_buf);
-	free(header_buf);
+	kfree(window);
+	kfree(name_buf);
+	kfree(symlink_buf);
+	kfree(header_buf);
 	return message;
 }
 
diff --git a/trunk/init/main.c b/trunk/init/main.c
index 1687b0167c4a..624266b524d4 100644
--- a/trunk/init/main.c
+++ b/trunk/init/main.c
@@ -58,6 +58,7 @@
 #include <linux/kthread.h>
 #include <linux/sched.h>
 #include <linux/signal.h>
+#include <linux/idr.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -559,6 +560,7 @@ asmlinkage void __init start_kernel(void)
 	printk(KERN_NOTICE);
 	printk(linux_banner);
 	setup_arch(&command_line);
+	mm_init_owner(&init_mm, &init_task);
 	setup_command_line(command_line);
 	unwind_setup();
 	setup_per_cpu_areas();
@@ -636,6 +638,7 @@ asmlinkage void __init start_kernel(void)
 	enable_debug_pagealloc();
 	cpu_hotplug_init();
 	kmem_cache_init();
+	idr_init_cache();
 	setup_per_cpu_pageset();
 	numa_policy_init();
 	if (late_time_init)
@@ -700,10 +703,8 @@ static void __init do_initcalls(void)
 		int result;
 
 		if (initcall_debug) {
-			printk("Calling initcall 0x%p", *call);
-			print_fn_descriptor_symbol(": %s()",
+			print_fn_descriptor_symbol("calling  %s()\n",
 					(unsigned long) *call);
-			printk("\n");
 			t0 = ktime_get();
 		}
 
@@ -713,15 +714,10 @@ static void __init do_initcalls(void)
 			t1 = ktime_get();
 			delta = ktime_sub(t1, t0);
 
-			printk("initcall 0x%p", *call);
-			print_fn_descriptor_symbol(": %s()",
+			print_fn_descriptor_symbol("initcall %s()",
 					(unsigned long) *call);
-			printk(" returned %d.\n", result);
-
-			printk("initcall 0x%p ran for %Ld msecs: ",
-				*call, (unsigned long long)delta.tv64 >> 20);
-			print_fn_descriptor_symbol("%s()\n",
-				(unsigned long) *call);
+			printk(" returned %d after %Ld msecs\n", result,
+				(unsigned long long) delta.tv64 >> 20);
 		}
 
 		if (result && result != -ENODEV && initcall_debug) {
@@ -737,10 +733,9 @@ static void __init do_initcalls(void)
 			local_irq_enable();
 		}
 		if (msg) {
-			printk(KERN_WARNING "initcall at 0x%p", *call);
-			print_fn_descriptor_symbol(": %s()",
+			print_fn_descriptor_symbol(KERN_WARNING "initcall %s()",
 					(unsigned long) *call);
-			printk(": returned with %s\n", msg);
+			printk(" returned with %s\n", msg);
 		}
 	}
 
diff --git a/trunk/ipc/Makefile b/trunk/ipc/Makefile
index 5fc5e33ea047..65c384395801 100644
--- a/trunk/ipc/Makefile
+++ b/trunk/ipc/Makefile
@@ -3,7 +3,7 @@
 #
 
 obj-$(CONFIG_SYSVIPC_COMPAT) += compat.o
-obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o
+obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o ipcns_notifier.o
 obj-$(CONFIG_SYSVIPC_SYSCTL) += ipc_sysctl.o
 obj_mq-$(CONFIG_COMPAT) += compat_mq.o
 obj-$(CONFIG_POSIX_MQUEUE) += mqueue.o msgutil.o $(obj_mq-y)
diff --git a/trunk/ipc/ipc_sysctl.c b/trunk/ipc/ipc_sysctl.c
index 7f4235bed51b..d3497465cc0a 100644
--- a/trunk/ipc/ipc_sysctl.c
+++ b/trunk/ipc/ipc_sysctl.c
@@ -15,6 +15,8 @@
 #include <linux/sysctl.h>
 #include <linux/uaccess.h>
 #include <linux/ipc_namespace.h>
+#include <linux/msg.h>
+#include "util.h"
 
 static void *get_ipc(ctl_table *table)
 {
@@ -24,6 +26,27 @@ static void *get_ipc(ctl_table *table)
 	return which;
 }
 
+/*
+ * Routine that is called when a tunable has successfully been changed by
+ * hand and it has a callback routine registered on the ipc namespace notifier
+ * chain: we don't want such tunables to be recomputed anymore upon memory
+ * add/remove or ipc namespace creation/removal.
+ * They can come back to a recomputable state by being set to a <0 value.
+ */
+static void tunable_set_callback(int val)
+{
+	if (val >= 0)
+		unregister_ipcns_notifier(current->nsproxy->ipc_ns);
+	else {
+		/*
+		 * Re-enable automatic recomputing only if not already
+		 * enabled.
+		 */
+		recompute_msgmni(current->nsproxy->ipc_ns);
+		cond_register_ipcns_notifier(current->nsproxy->ipc_ns);
+	}
+}
+
 #ifdef CONFIG_PROC_FS
 static int proc_ipc_dointvec(ctl_table *table, int write, struct file *filp,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -35,6 +58,24 @@ static int proc_ipc_dointvec(ctl_table *table, int write, struct file *filp,
 	return proc_dointvec(&ipc_table, write, filp, buffer, lenp, ppos);
 }
 
+static int proc_ipc_callback_dointvec(ctl_table *table, int write,
+	struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table ipc_table;
+	size_t lenp_bef = *lenp;
+	int rc;
+
+	memcpy(&ipc_table, table, sizeof(ipc_table));
+	ipc_table.data = get_ipc(table);
+
+	rc = proc_dointvec(&ipc_table, write, filp, buffer, lenp, ppos);
+
+	if (write && !rc && lenp_bef == *lenp)
+		tunable_set_callback(*((int *)(ipc_table.data)));
+
+	return rc;
+}
+
 static int proc_ipc_doulongvec_minmax(ctl_table *table, int write,
 	struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -49,6 +90,7 @@ static int proc_ipc_doulongvec_minmax(ctl_table *table, int write,
 #else
 #define proc_ipc_doulongvec_minmax NULL
 #define proc_ipc_dointvec	   NULL
+#define proc_ipc_callback_dointvec NULL
 #endif
 
 #ifdef CONFIG_SYSCTL_SYSCALL
@@ -90,8 +132,30 @@ static int sysctl_ipc_data(ctl_table *table, int __user *name, int nlen,
 	}
 	return 1;
 }
+
+static int sysctl_ipc_registered_data(ctl_table *table, int __user *name,
+		int nlen, void __user *oldval, size_t __user *oldlenp,
+		void __user *newval, size_t newlen)
+{
+	int rc;
+
+	rc = sysctl_ipc_data(table, name, nlen, oldval, oldlenp, newval,
+		newlen);
+
+	if (newval && newlen && rc > 0) {
+		/*
+		 * Tunable has successfully been changed from userland
+		 */
+		int *data = get_ipc(table);
+
+		tunable_set_callback(*data);
+	}
+
+	return rc;
+}
 #else
 #define sysctl_ipc_data NULL
+#define sysctl_ipc_registered_data NULL
 #endif
 
 static struct ctl_table ipc_kern_table[] = {
@@ -137,8 +201,8 @@ static struct ctl_table ipc_kern_table[] = {
 		.data		= &init_ipc_ns.msg_ctlmni,
 		.maxlen		= sizeof (init_ipc_ns.msg_ctlmni),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_dointvec,
-		.strategy	= sysctl_ipc_data,
+		.proc_handler	= proc_ipc_callback_dointvec,
+		.strategy	= sysctl_ipc_registered_data,
 	},
 	{
 		.ctl_name	= KERN_MSGMNB,
diff --git a/trunk/ipc/ipcns_notifier.c b/trunk/ipc/ipcns_notifier.c
new file mode 100644
index 000000000000..70ff09183f7b
--- /dev/null
+++ b/trunk/ipc/ipcns_notifier.c
@@ -0,0 +1,82 @@
+/*
+ * linux/ipc/ipcns_notifier.c
+ * Copyright (C) 2007 BULL SA. Nadia Derbey
+ *
+ * Notification mechanism for ipc namespaces:
+ * The callback routine registered in the memory chain invokes the ipcns
+ * notifier chain with the IPCNS_MEMCHANGED event.
+ * Each callback routine registered in the ipcns namespace recomputes msgmni
+ * for the owning namespace.
+ */
+
+#include <linux/msg.h>
+#include <linux/rcupdate.h>
+#include <linux/notifier.h>
+#include <linux/nsproxy.h>
+#include <linux/ipc_namespace.h>
+
+#include "util.h"
+
+
+
+static BLOCKING_NOTIFIER_HEAD(ipcns_chain);
+
+
+static int ipcns_callback(struct notifier_block *self,
+				unsigned long action, void *arg)
+{
+	struct ipc_namespace *ns;
+
+	switch (action) {
+	case IPCNS_MEMCHANGED:   /* amount of lowmem has changed */
+	case IPCNS_CREATED:
+	case IPCNS_REMOVED:
+		/*
+		 * It's time to recompute msgmni
+		 */
+		ns = container_of(self, struct ipc_namespace, ipcns_nb);
+		/*
+		 * No need to get a reference on the ns: the 1st job of
+		 * free_ipc_ns() is to unregister the callback routine.
+		 * blocking_notifier_chain_unregister takes the wr lock to do
+		 * it.
+		 * When this callback routine is called the rd lock is held by
+		 * blocking_notifier_call_chain.
+		 * So the ipc ns cannot be freed while we are here.
+		 */
+		recompute_msgmni(ns);
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+int register_ipcns_notifier(struct ipc_namespace *ns)
+{
+	memset(&ns->ipcns_nb, 0, sizeof(ns->ipcns_nb));
+	ns->ipcns_nb.notifier_call = ipcns_callback;
+	ns->ipcns_nb.priority = IPCNS_CALLBACK_PRI;
+	return blocking_notifier_chain_register(&ipcns_chain, &ns->ipcns_nb);
+}
+
+int cond_register_ipcns_notifier(struct ipc_namespace *ns)
+{
+	memset(&ns->ipcns_nb, 0, sizeof(ns->ipcns_nb));
+	ns->ipcns_nb.notifier_call = ipcns_callback;
+	ns->ipcns_nb.priority = IPCNS_CALLBACK_PRI;
+	return blocking_notifier_chain_cond_register(&ipcns_chain,
+							&ns->ipcns_nb);
+}
+
+int unregister_ipcns_notifier(struct ipc_namespace *ns)
+{
+	return blocking_notifier_chain_unregister(&ipcns_chain,
+						&ns->ipcns_nb);
+}
+
+int ipcns_notify(unsigned long val)
+{
+	return blocking_notifier_call_chain(&ipcns_chain, val, NULL);
+}
diff --git a/trunk/ipc/msg.c b/trunk/ipc/msg.c
index 46585a05473e..32494e8cc7a5 100644
--- a/trunk/ipc/msg.c
+++ b/trunk/ipc/msg.c
@@ -27,6 +27,7 @@
 #include <linux/msg.h>
 #include <linux/spinlock.h>
 #include <linux/init.h>
+#include <linux/mm.h>
 #include <linux/proc_fs.h>
 #include <linux/list.h>
 #include <linux/security.h>
@@ -70,7 +71,6 @@ struct msg_sender {
 #define msg_ids(ns)	((ns)->ids[IPC_MSG_IDS])
 
 #define msg_unlock(msq)		ipc_unlock(&(msq)->q_perm)
-#define msg_buildid(id, seq)	ipc_buildid(id, seq)
 
 static void freeque(struct ipc_namespace *, struct kern_ipc_perm *);
 static int newque(struct ipc_namespace *, struct ipc_params *);
@@ -78,11 +78,49 @@ static int newque(struct ipc_namespace *, struct ipc_params *);
 static int sysvipc_msg_proc_show(struct seq_file *s, void *it);
 #endif
 
+/*
+ * Scale msgmni with the available lowmem size: the memory dedicated to msg
+ * queues should occupy at most 1/MSG_MEM_SCALE of lowmem.
+ * Also take into account the number of nsproxies created so far.
+ * This should be done staying within the (MSGMNI , IPCMNI/nr_ipc_ns) range.
+ */
+void recompute_msgmni(struct ipc_namespace *ns)
+{
+	struct sysinfo i;
+	unsigned long allowed;
+	int nb_ns;
+
+	si_meminfo(&i);
+	allowed = (((i.totalram - i.totalhigh) / MSG_MEM_SCALE) * i.mem_unit)
+		/ MSGMNB;
+	nb_ns = atomic_read(&nr_ipc_ns);
+	allowed /= nb_ns;
+
+	if (allowed < MSGMNI) {
+		ns->msg_ctlmni = MSGMNI;
+		goto out_callback;
+	}
+
+	if (allowed > IPCMNI / nb_ns) {
+		ns->msg_ctlmni = IPCMNI / nb_ns;
+		goto out_callback;
+	}
+
+	ns->msg_ctlmni = allowed;
+
+out_callback:
+
+	printk(KERN_INFO "msgmni has been set to %d for ipc namespace %p\n",
+		ns->msg_ctlmni, ns);
+}
+
 void msg_init_ns(struct ipc_namespace *ns)
 {
 	ns->msg_ctlmax = MSGMAX;
 	ns->msg_ctlmnb = MSGMNB;
-	ns->msg_ctlmni = MSGMNI;
+
+	recompute_msgmni(ns);
+
 	atomic_set(&ns->msg_bytes, 0);
 	atomic_set(&ns->msg_hdrs, 0);
 	ipc_init_ids(&ns->ids[IPC_MSG_IDS]);
@@ -103,21 +141,6 @@ void __init msg_init(void)
 				IPC_MSG_IDS, sysvipc_msg_proc_show);
 }
 
-/*
- * This routine is called in the paths where the rw_mutex is held to protect
- * access to the idr tree.
- */
-static inline struct msg_queue *msg_lock_check_down(struct ipc_namespace *ns,
-						int id)
-{
-	struct kern_ipc_perm *ipcp = ipc_lock_check_down(&msg_ids(ns), id);
-
-	if (IS_ERR(ipcp))
-		return (struct msg_queue *)ipcp;
-
-	return container_of(ipcp, struct msg_queue, q_perm);
-}
-
 /*
  * msg_lock_(check_) routines are called in the paths where the rw_mutex
  * is not held.
@@ -186,7 +209,6 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
 		return id;
 	}
 
-	msq->q_perm.id = msg_buildid(id, msq->q_perm.seq);
 	msq->q_stime = msq->q_rtime = 0;
 	msq->q_ctime = get_seconds();
 	msq->q_cbytes = msq->q_qnum = 0;
@@ -324,19 +346,19 @@ copy_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version)
 		out.msg_rtime		= in->msg_rtime;
 		out.msg_ctime		= in->msg_ctime;
 
-		if (in->msg_cbytes > USHRT_MAX)
-			out.msg_cbytes	= USHRT_MAX;
+		if (in->msg_cbytes > USHORT_MAX)
+			out.msg_cbytes	= USHORT_MAX;
 		else
 			out.msg_cbytes	= in->msg_cbytes;
 		out.msg_lcbytes		= in->msg_cbytes;
 
-		if (in->msg_qnum > USHRT_MAX)
-			out.msg_qnum	= USHRT_MAX;
+		if (in->msg_qnum > USHORT_MAX)
+			out.msg_qnum	= USHORT_MAX;
 		else
 			out.msg_qnum	= in->msg_qnum;
 
-		if (in->msg_qbytes > USHRT_MAX)
-			out.msg_qbytes	= USHRT_MAX;
+		if (in->msg_qbytes > USHORT_MAX)
+			out.msg_qbytes	= USHORT_MAX;
 		else
 			out.msg_qbytes	= in->msg_qbytes;
 		out.msg_lqbytes		= in->msg_qbytes;
@@ -351,31 +373,14 @@ copy_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version)
 	}
 }
 
-struct msq_setbuf {
-	unsigned long	qbytes;
-	uid_t		uid;
-	gid_t		gid;
-	mode_t		mode;
-};
-
 static inline unsigned long
-copy_msqid_from_user(struct msq_setbuf *out, void __user *buf, int version)
+copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version)
 {
 	switch(version) {
 	case IPC_64:
-	{
-		struct msqid64_ds tbuf;
-
-		if (copy_from_user(&tbuf, buf, sizeof(tbuf)))
+		if (copy_from_user(out, buf, sizeof(*out)))
 			return -EFAULT;
-
-		out->qbytes		= tbuf.msg_qbytes;
-		out->uid		= tbuf.msg_perm.uid;
-		out->gid		= tbuf.msg_perm.gid;
-		out->mode		= tbuf.msg_perm.mode;
-
 		return 0;
-	}
 	case IPC_OLD:
 	{
 		struct msqid_ds tbuf_old;
@@ -383,14 +388,14 @@ copy_msqid_from_user(struct msq_setbuf *out, void __user *buf, int version)
 		if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old)))
 			return -EFAULT;
 
-		out->uid		= tbuf_old.msg_perm.uid;
-		out->gid		= tbuf_old.msg_perm.gid;
-		out->mode		= tbuf_old.msg_perm.mode;
+		out->msg_perm.uid      	= tbuf_old.msg_perm.uid;
+		out->msg_perm.gid      	= tbuf_old.msg_perm.gid;
+		out->msg_perm.mode     	= tbuf_old.msg_perm.mode;
 
 		if (tbuf_old.msg_qbytes == 0)
-			out->qbytes	= tbuf_old.msg_lqbytes;
+			out->msg_qbytes	= tbuf_old.msg_lqbytes;
 		else
-			out->qbytes	= tbuf_old.msg_qbytes;
+			out->msg_qbytes	= tbuf_old.msg_qbytes;
 
 		return 0;
 	}
@@ -399,10 +404,71 @@ copy_msqid_from_user(struct msq_setbuf *out, void __user *buf, int version)
 	}
 }
 
-asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf)
+/*
+ * This function handles some msgctl commands which require the rw_mutex
+ * to be held in write mode.
+ * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ */
+static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
+		       struct msqid_ds __user *buf, int version)
 {
 	struct kern_ipc_perm *ipcp;
-	struct msq_setbuf uninitialized_var(setbuf);
+	struct msqid64_ds msqid64;
+	struct msg_queue *msq;
+	int err;
+
+	if (cmd == IPC_SET) {
+		if (copy_msqid_from_user(&msqid64, buf, version))
+			return -EFAULT;
+	}
+
+	ipcp = ipcctl_pre_down(&msg_ids(ns), msqid, cmd,
+			       &msqid64.msg_perm, msqid64.msg_qbytes);
+	if (IS_ERR(ipcp))
+		return PTR_ERR(ipcp);
+
+	msq = container_of(ipcp, struct msg_queue, q_perm);
+
+	err = security_msg_queue_msgctl(msq, cmd);
+	if (err)
+		goto out_unlock;
+
+	switch (cmd) {
+	case IPC_RMID:
+		freeque(ns, ipcp);
+		goto out_up;
+	case IPC_SET:
+		if (msqid64.msg_qbytes > ns->msg_ctlmnb &&
+		    !capable(CAP_SYS_RESOURCE)) {
+			err = -EPERM;
+			goto out_unlock;
+		}
+
+		msq->q_qbytes = msqid64.msg_qbytes;
+
+		ipc_update_perm(&msqid64.msg_perm, ipcp);
+		msq->q_ctime = get_seconds();
+		/* sleeping receivers might be excluded by
+		 * stricter permissions.
+		 */
+		expunge_all(msq, -EAGAIN);
+		/* sleeping senders might be able to send
+		 * due to a larger queue size.
+		 */
+		ss_wakeup(&msq->q_senders, 0);
+		break;
+	default:
+		err = -EINVAL;
+	}
+out_unlock:
+	msg_unlock(msq);
+out_up:
+	up_write(&msg_ids(ns).rw_mutex);
+	return err;
+}
+
+asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf)
+{
 	struct msg_queue *msq;
 	int err, version;
 	struct ipc_namespace *ns;
@@ -498,82 +564,13 @@ asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf)
 		return success_return;
 	}
 	case IPC_SET:
-		if (!buf)
-			return -EFAULT;
-		if (copy_msqid_from_user(&setbuf, buf, version))
-			return -EFAULT;
-		break;
 	case IPC_RMID:
-		break;
+		err = msgctl_down(ns, msqid, cmd, buf, version);
+		return err;
 	default:
 		return  -EINVAL;
 	}
 
-	down_write(&msg_ids(ns).rw_mutex);
-	msq = msg_lock_check_down(ns, msqid);
-	if (IS_ERR(msq)) {
-		err = PTR_ERR(msq);
-		goto out_up;
-	}
-
-	ipcp = &msq->q_perm;
-
-	err = audit_ipc_obj(ipcp);
-	if (err)
-		goto out_unlock_up;
-	if (cmd == IPC_SET) {
-		err = audit_ipc_set_perm(setbuf.qbytes, setbuf.uid, setbuf.gid,
-					 setbuf.mode);
-		if (err)
-			goto out_unlock_up;
-	}
-
-	err = -EPERM;
-	if (current->euid != ipcp->cuid &&
-	    current->euid != ipcp->uid && !capable(CAP_SYS_ADMIN))
-		/* We _could_ check for CAP_CHOWN above, but we don't */
-		goto out_unlock_up;
-
-	err = security_msg_queue_msgctl(msq, cmd);
-	if (err)
-		goto out_unlock_up;
-
-	switch (cmd) {
-	case IPC_SET:
-	{
-		err = -EPERM;
-		if (setbuf.qbytes > ns->msg_ctlmnb && !capable(CAP_SYS_RESOURCE))
-			goto out_unlock_up;
-
-		msq->q_qbytes = setbuf.qbytes;
-
-		ipcp->uid = setbuf.uid;
-		ipcp->gid = setbuf.gid;
-		ipcp->mode = (ipcp->mode & ~S_IRWXUGO) |
-			     (S_IRWXUGO & setbuf.mode);
-		msq->q_ctime = get_seconds();
-		/* sleeping receivers might be excluded by
-		 * stricter permissions.
-		 */
-		expunge_all(msq, -EAGAIN);
-		/* sleeping senders might be able to send
-		 * due to a larger queue size.
-		 */
-		ss_wakeup(&msq->q_senders, 0);
-		msg_unlock(msq);
-		break;
-	}
-	case IPC_RMID:
-		freeque(ns, &msq->q_perm);
-		break;
-	}
-	err = 0;
-out_up:
-	up_write(&msg_ids(ns).rw_mutex);
-	return err;
-out_unlock_up:
-	msg_unlock(msq);
-	goto out_up;
 out_unlock:
 	msg_unlock(msq);
 	return err;
diff --git a/trunk/ipc/namespace.c b/trunk/ipc/namespace.c
index 1b967655eb35..9171d948751e 100644
--- a/trunk/ipc/namespace.c
+++ b/trunk/ipc/namespace.c
@@ -20,10 +20,20 @@ static struct ipc_namespace *clone_ipc_ns(struct ipc_namespace *old_ns)
 	if (ns == NULL)
 		return ERR_PTR(-ENOMEM);
 
+	atomic_inc(&nr_ipc_ns);
+
 	sem_init_ns(ns);
 	msg_init_ns(ns);
 	shm_init_ns(ns);
 
+	/*
+	 * msgmni has already been computed for the new ipc ns.
+	 * Thus, do the ipcns creation notification before registering that
+	 * new ipcns in the chain.
+	 */
+	ipcns_notify(IPCNS_CREATED);
+	register_ipcns_notifier(ns);
+
 	kref_init(&ns->kref);
 	return ns;
 }
@@ -79,8 +89,24 @@ void free_ipc_ns(struct kref *kref)
 	struct ipc_namespace *ns;
 
 	ns = container_of(kref, struct ipc_namespace, kref);
+	/*
+	 * Unregistering the hotplug notifier at the beginning guarantees
+	 * that the ipc namespace won't be freed while we are inside the
+	 * callback routine. Since the blocking_notifier_chain_XXX routines
+	 * hold a rw lock on the notifier list, unregister_ipcns_notifier()
+	 * won't take the rw lock before blocking_notifier_call_chain() has
+	 * released the rd lock.
+	 */
+	unregister_ipcns_notifier(ns);
 	sem_exit_ns(ns);
 	msg_exit_ns(ns);
 	shm_exit_ns(ns);
 	kfree(ns);
+	atomic_dec(&nr_ipc_ns);
+
+	/*
+	 * Do the ipcns removal notification after decrementing nr_ipc_ns in
+	 * order to have a correct value when recomputing msgmni.
+	 */
+	ipcns_notify(IPCNS_REMOVED);
 }
diff --git a/trunk/ipc/sem.c b/trunk/ipc/sem.c
index 0b45a4d383c6..e9418df5ff3e 100644
--- a/trunk/ipc/sem.c
+++ b/trunk/ipc/sem.c
@@ -91,7 +91,6 @@
 
 #define sem_unlock(sma)		ipc_unlock(&(sma)->sem_perm)
 #define sem_checkid(sma, semid)	ipc_checkid(&sma->sem_perm, semid)
-#define sem_buildid(id, seq)	ipc_buildid(id, seq)
 
 static int newary(struct ipc_namespace *, struct ipc_params *);
 static void freeary(struct ipc_namespace *, struct kern_ipc_perm *);
@@ -141,21 +140,6 @@ void __init sem_init (void)
 				IPC_SEM_IDS, sysvipc_sem_proc_show);
 }
 
-/*
- * This routine is called in the paths where the rw_mutex is held to protect
- * access to the idr tree.
- */
-static inline struct sem_array *sem_lock_check_down(struct ipc_namespace *ns,
-						int id)
-{
-	struct kern_ipc_perm *ipcp = ipc_lock_check_down(&sem_ids(ns), id);
-
-	if (IS_ERR(ipcp))
-		return (struct sem_array *)ipcp;
-
-	return container_of(ipcp, struct sem_array, sem_perm);
-}
-
 /*
  * sem_lock_(check_) routines are called in the paths where the rw_mutex
  * is not held.
@@ -181,6 +165,25 @@ static inline struct sem_array *sem_lock_check(struct ipc_namespace *ns,
 	return container_of(ipcp, struct sem_array, sem_perm);
 }
 
+static inline void sem_lock_and_putref(struct sem_array *sma)
+{
+	ipc_lock_by_ptr(&sma->sem_perm);
+	ipc_rcu_putref(sma);
+}
+
+static inline void sem_getref_and_unlock(struct sem_array *sma)
+{
+	ipc_rcu_getref(sma);
+	ipc_unlock(&(sma)->sem_perm);
+}
+
+static inline void sem_putref(struct sem_array *sma)
+{
+	ipc_lock_by_ptr(&sma->sem_perm);
+	ipc_rcu_putref(sma);
+	ipc_unlock(&(sma)->sem_perm);
+}
+
 static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
 {
 	ipc_rmid(&sem_ids(ns), &s->sem_perm);
@@ -268,7 +271,6 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 	}
 	ns->used_sems += nsems;
 
-	sma->sem_perm.id = sem_buildid(id, sma->sem_perm.seq);
 	sma->sem_base = (struct sem *) &sma[1];
 	/* sma->sem_pending = NULL; */
 	sma->sem_pending_last = &sma->sem_pending;
@@ -700,19 +702,15 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		int i;
 
 		if(nsems > SEMMSL_FAST) {
-			ipc_rcu_getref(sma);
-			sem_unlock(sma);			
+			sem_getref_and_unlock(sma);
 
 			sem_io = ipc_alloc(sizeof(ushort)*nsems);
 			if(sem_io == NULL) {
-				ipc_lock_by_ptr(&sma->sem_perm);
-				ipc_rcu_putref(sma);
-				sem_unlock(sma);
+				sem_putref(sma);
 				return -ENOMEM;
 			}
 
-			ipc_lock_by_ptr(&sma->sem_perm);
-			ipc_rcu_putref(sma);
+			sem_lock_and_putref(sma);
 			if (sma->sem_perm.deleted) {
 				sem_unlock(sma);
 				err = -EIDRM;
@@ -733,38 +731,30 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		int i;
 		struct sem_undo *un;
 
-		ipc_rcu_getref(sma);
-		sem_unlock(sma);
+		sem_getref_and_unlock(sma);
 
 		if(nsems > SEMMSL_FAST) {
 			sem_io = ipc_alloc(sizeof(ushort)*nsems);
 			if(sem_io == NULL) {
-				ipc_lock_by_ptr(&sma->sem_perm);
-				ipc_rcu_putref(sma);
-				sem_unlock(sma);
+				sem_putref(sma);
 				return -ENOMEM;
 			}
 		}
 
 		if (copy_from_user (sem_io, arg.array, nsems*sizeof(ushort))) {
-			ipc_lock_by_ptr(&sma->sem_perm);
-			ipc_rcu_putref(sma);
-			sem_unlock(sma);
+			sem_putref(sma);
 			err = -EFAULT;
 			goto out_free;
 		}
 
 		for (i = 0; i < nsems; i++) {
 			if (sem_io[i] > SEMVMX) {
-				ipc_lock_by_ptr(&sma->sem_perm);
-				ipc_rcu_putref(sma);
-				sem_unlock(sma);
+				sem_putref(sma);
 				err = -ERANGE;
 				goto out_free;
 			}
 		}
-		ipc_lock_by_ptr(&sma->sem_perm);
-		ipc_rcu_putref(sma);
+		sem_lock_and_putref(sma);
 		if (sma->sem_perm.deleted) {
 			sem_unlock(sma);
 			err = -EIDRM;
@@ -830,28 +820,14 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 	return err;
 }
 
-struct sem_setbuf {
-	uid_t	uid;
-	gid_t	gid;
-	mode_t	mode;
-};
-
-static inline unsigned long copy_semid_from_user(struct sem_setbuf *out, void __user *buf, int version)
+static inline unsigned long
+copy_semid_from_user(struct semid64_ds *out, void __user *buf, int version)
 {
 	switch(version) {
 	case IPC_64:
-	    {
-		struct semid64_ds tbuf;
-
-		if(copy_from_user(&tbuf, buf, sizeof(tbuf)))
+		if (copy_from_user(out, buf, sizeof(*out)))
 			return -EFAULT;
-
-		out->uid	= tbuf.sem_perm.uid;
-		out->gid	= tbuf.sem_perm.gid;
-		out->mode	= tbuf.sem_perm.mode;
-
 		return 0;
-	    }
 	case IPC_OLD:
 	    {
 		struct semid_ds tbuf_old;
@@ -859,9 +835,9 @@ static inline unsigned long copy_semid_from_user(struct sem_setbuf *out, void __
 		if(copy_from_user(&tbuf_old, buf, sizeof(tbuf_old)))
 			return -EFAULT;
 
-		out->uid	= tbuf_old.sem_perm.uid;
-		out->gid	= tbuf_old.sem_perm.gid;
-		out->mode	= tbuf_old.sem_perm.mode;
+		out->sem_perm.uid	= tbuf_old.sem_perm.uid;
+		out->sem_perm.gid	= tbuf_old.sem_perm.gid;
+		out->sem_perm.mode	= tbuf_old.sem_perm.mode;
 
 		return 0;
 	    }
@@ -870,38 +846,29 @@ static inline unsigned long copy_semid_from_user(struct sem_setbuf *out, void __
 	}
 }
 
-static int semctl_down(struct ipc_namespace *ns, int semid, int semnum,
-		int cmd, int version, union semun arg)
+/*
+ * This function handles some semctl commands which require the rw_mutex
+ * to be held in write mode.
+ * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ */
+static int semctl_down(struct ipc_namespace *ns, int semid,
+		       int cmd, int version, union semun arg)
 {
 	struct sem_array *sma;
 	int err;
-	struct sem_setbuf uninitialized_var(setbuf);
+	struct semid64_ds semid64;
 	struct kern_ipc_perm *ipcp;
 
 	if(cmd == IPC_SET) {
-		if(copy_semid_from_user (&setbuf, arg.buf, version))
+		if (copy_semid_from_user(&semid64, arg.buf, version))
 			return -EFAULT;
 	}
-	sma = sem_lock_check_down(ns, semid);
-	if (IS_ERR(sma))
-		return PTR_ERR(sma);
 
-	ipcp = &sma->sem_perm;
-
-	err = audit_ipc_obj(ipcp);
-	if (err)
-		goto out_unlock;
+	ipcp = ipcctl_pre_down(&sem_ids(ns), semid, cmd, &semid64.sem_perm, 0);
+	if (IS_ERR(ipcp))
+		return PTR_ERR(ipcp);
 
-	if (cmd == IPC_SET) {
-		err = audit_ipc_set_perm(0, setbuf.uid, setbuf.gid, setbuf.mode);
-		if (err)
-			goto out_unlock;
-	}
-	if (current->euid != ipcp->cuid && 
-	    current->euid != ipcp->uid && !capable(CAP_SYS_ADMIN)) {
-	    	err=-EPERM;
-		goto out_unlock;
-	}
+	sma = container_of(ipcp, struct sem_array, sem_perm);
 
 	err = security_sem_semctl(sma, cmd);
 	if (err)
@@ -910,26 +877,19 @@ static int semctl_down(struct ipc_namespace *ns, int semid, int semnum,
 	switch(cmd){
 	case IPC_RMID:
 		freeary(ns, ipcp);
-		err = 0;
-		break;
+		goto out_up;
 	case IPC_SET:
-		ipcp->uid = setbuf.uid;
-		ipcp->gid = setbuf.gid;
-		ipcp->mode = (ipcp->mode & ~S_IRWXUGO)
-				| (setbuf.mode & S_IRWXUGO);
+		ipc_update_perm(&semid64.sem_perm, ipcp);
 		sma->sem_ctime = get_seconds();
-		sem_unlock(sma);
-		err = 0;
 		break;
 	default:
-		sem_unlock(sma);
 		err = -EINVAL;
-		break;
 	}
-	return err;
 
 out_unlock:
 	sem_unlock(sma);
+out_up:
+	up_write(&sem_ids(ns).rw_mutex);
 	return err;
 }
 
@@ -963,9 +923,7 @@ asmlinkage long sys_semctl (int semid, int semnum, int cmd, union semun arg)
 		return err;
 	case IPC_RMID:
 	case IPC_SET:
-		down_write(&sem_ids(ns).rw_mutex);
-		err = semctl_down(ns,semid,semnum,cmd,version,arg);
-		up_write(&sem_ids(ns).rw_mutex);
+		err = semctl_down(ns, semid, cmd, version, arg);
 		return err;
 	default:
 		return -EINVAL;
@@ -1044,14 +1002,11 @@ static struct sem_undo *find_undo(struct ipc_namespace *ns, int semid)
 		return ERR_PTR(PTR_ERR(sma));
 
 	nsems = sma->sem_nsems;
-	ipc_rcu_getref(sma);
-	sem_unlock(sma);
+	sem_getref_and_unlock(sma);
 
 	new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL);
 	if (!new) {
-		ipc_lock_by_ptr(&sma->sem_perm);
-		ipc_rcu_putref(sma);
-		sem_unlock(sma);
+		sem_putref(sma);
 		return ERR_PTR(-ENOMEM);
 	}
 	new->semadj = (short *) &new[1];
@@ -1062,13 +1017,10 @@ static struct sem_undo *find_undo(struct ipc_namespace *ns, int semid)
 	if (un) {
 		spin_unlock(&ulp->lock);
 		kfree(new);
-		ipc_lock_by_ptr(&sma->sem_perm);
-		ipc_rcu_putref(sma);
-		sem_unlock(sma);
+		sem_putref(sma);
 		goto out;
 	}
-	ipc_lock_by_ptr(&sma->sem_perm);
-	ipc_rcu_putref(sma);
+	sem_lock_and_putref(sma);
 	if (sma->sem_perm.deleted) {
 		sem_unlock(sma);
 		spin_unlock(&ulp->lock);
@@ -1298,6 +1250,7 @@ void exit_sem(struct task_struct *tsk)
 	undo_list = tsk->sysvsem.undo_list;
 	if (!undo_list)
 		return;
+	tsk->sysvsem.undo_list = NULL;
 
 	if (!atomic_dec_and_test(&undo_list->refcnt))
 		return;
diff --git a/trunk/ipc/shm.c b/trunk/ipc/shm.c
index cc63fae02f06..554429ade079 100644
--- a/trunk/ipc/shm.c
+++ b/trunk/ipc/shm.c
@@ -60,7 +60,6 @@ static struct vm_operations_struct shm_vm_ops;
 
 #define shm_unlock(shp)			\
 	ipc_unlock(&(shp)->shm_perm)
-#define shm_buildid(id, seq)	ipc_buildid(id, seq)
 
 static int newseg(struct ipc_namespace *, struct ipc_params *);
 static void shm_open(struct vm_area_struct *vma);
@@ -127,18 +126,6 @@ static inline struct shmid_kernel *shm_lock_down(struct ipc_namespace *ns,
 	return container_of(ipcp, struct shmid_kernel, shm_perm);
 }
 
-static inline struct shmid_kernel *shm_lock_check_down(
-						struct ipc_namespace *ns,
-						int id)
-{
-	struct kern_ipc_perm *ipcp = ipc_lock_check_down(&shm_ids(ns), id);
-
-	if (IS_ERR(ipcp))
-		return (struct shmid_kernel *)ipcp;
-
-	return container_of(ipcp, struct shmid_kernel, shm_perm);
-}
-
 /*
  * shm_lock_(check_) routines are called in the paths where the rw_mutex
  * is not held.
@@ -169,12 +156,6 @@ static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
 	ipc_rmid(&shm_ids(ns), &s->shm_perm);
 }
 
-static inline int shm_addid(struct ipc_namespace *ns, struct shmid_kernel *shp)
-{
-	return ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
-}
-
-
 
 /* This is called by fork, once for every shm attach. */
 static void shm_open(struct vm_area_struct *vma)
@@ -271,11 +252,9 @@ static struct mempolicy *shm_get_policy(struct vm_area_struct *vma,
 
 	if (sfd->vm_ops->get_policy)
 		pol = sfd->vm_ops->get_policy(vma, addr);
-	else if (vma->vm_policy) {
+	else if (vma->vm_policy)
 		pol = vma->vm_policy;
-		mpol_get(pol);	/* get_vma_policy() expects this */
-	} else
-		pol = current->mempolicy;
+
 	return pol;
 }
 #endif
@@ -418,7 +397,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	if (IS_ERR(file))
 		goto no_file;
 
-	id = shm_addid(ns, shp);
+	id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
 	if (id < 0) {
 		error = id;
 		goto no_id;
@@ -430,7 +409,6 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	shp->shm_ctim = get_seconds();
 	shp->shm_segsz = size;
 	shp->shm_nattch = 0;
-	shp->shm_perm.id = shm_buildid(id, shp->shm_perm.seq);
 	shp->shm_file = file;
 	/*
 	 * shmid gets reported as "inode#" in /proc/pid/maps.
@@ -521,28 +499,14 @@ static inline unsigned long copy_shmid_to_user(void __user *buf, struct shmid64_
 	}
 }
 
-struct shm_setbuf {
-	uid_t	uid;
-	gid_t	gid;
-	mode_t	mode;
-};	
-
-static inline unsigned long copy_shmid_from_user(struct shm_setbuf *out, void __user *buf, int version)
+static inline unsigned long
+copy_shmid_from_user(struct shmid64_ds *out, void __user *buf, int version)
 {
 	switch(version) {
 	case IPC_64:
-	    {
-		struct shmid64_ds tbuf;
-
-		if (copy_from_user(&tbuf, buf, sizeof(tbuf)))
+		if (copy_from_user(out, buf, sizeof(*out)))
 			return -EFAULT;
-
-		out->uid	= tbuf.shm_perm.uid;
-		out->gid	= tbuf.shm_perm.gid;
-		out->mode	= tbuf.shm_perm.mode;
-
 		return 0;
-	    }
 	case IPC_OLD:
 	    {
 		struct shmid_ds tbuf_old;
@@ -550,9 +514,9 @@ static inline unsigned long copy_shmid_from_user(struct shm_setbuf *out, void __
 		if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old)))
 			return -EFAULT;
 
-		out->uid	= tbuf_old.shm_perm.uid;
-		out->gid	= tbuf_old.shm_perm.gid;
-		out->mode	= tbuf_old.shm_perm.mode;
+		out->shm_perm.uid	= tbuf_old.shm_perm.uid;
+		out->shm_perm.gid	= tbuf_old.shm_perm.gid;
+		out->shm_perm.mode	= tbuf_old.shm_perm.mode;
 
 		return 0;
 	    }
@@ -626,9 +590,53 @@ static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
 	}
 }
 
-asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf)
+/*
+ * This function handles some shmctl commands which require the rw_mutex
+ * to be held in write mode.
+ * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ */
+static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
+		       struct shmid_ds __user *buf, int version)
+{
+	struct kern_ipc_perm *ipcp;
+	struct shmid64_ds shmid64;
+	struct shmid_kernel *shp;
+	int err;
+
+	if (cmd == IPC_SET) {
+		if (copy_shmid_from_user(&shmid64, buf, version))
+			return -EFAULT;
+	}
+
+	ipcp = ipcctl_pre_down(&shm_ids(ns), shmid, cmd, &shmid64.shm_perm, 0);
+	if (IS_ERR(ipcp))
+		return PTR_ERR(ipcp);
+
+	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+
+	err = security_shm_shmctl(shp, cmd);
+	if (err)
+		goto out_unlock;
+	switch (cmd) {
+	case IPC_RMID:
+		do_shm_rmid(ns, ipcp);
+		goto out_up;
+	case IPC_SET:
+		ipc_update_perm(&shmid64.shm_perm, ipcp);
+		shp->shm_ctim = get_seconds();
+		break;
+	default:
+		err = -EINVAL;
+	}
+out_unlock:
+	shm_unlock(shp);
+out_up:
+	up_write(&shm_ids(ns).rw_mutex);
+	return err;
+}
+
+asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf)
 {
-	struct shm_setbuf setbuf;
 	struct shmid_kernel *shp;
 	int err, version;
 	struct ipc_namespace *ns;
@@ -785,97 +793,13 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf)
 		goto out;
 	}
 	case IPC_RMID:
-	{
-		/*
-		 *	We cannot simply remove the file. The SVID states
-		 *	that the block remains until the last person
-		 *	detaches from it, then is deleted. A shmat() on
-		 *	an RMID segment is legal in older Linux and if 
-		 *	we change it apps break...
-		 *
-		 *	Instead we set a destroyed flag, and then blow
-		 *	the name away when the usage hits zero.
-		 */
-		down_write(&shm_ids(ns).rw_mutex);
-		shp = shm_lock_check_down(ns, shmid);
-		if (IS_ERR(shp)) {
-			err = PTR_ERR(shp);
-			goto out_up;
-		}
-
-		err = audit_ipc_obj(&(shp->shm_perm));
-		if (err)
-			goto out_unlock_up;
-
-		if (current->euid != shp->shm_perm.uid &&
-		    current->euid != shp->shm_perm.cuid && 
-		    !capable(CAP_SYS_ADMIN)) {
-			err=-EPERM;
-			goto out_unlock_up;
-		}
-
-		err = security_shm_shmctl(shp, cmd);
-		if (err)
-			goto out_unlock_up;
-
-		do_shm_rmid(ns, &shp->shm_perm);
-		up_write(&shm_ids(ns).rw_mutex);
-		goto out;
-	}
-
 	case IPC_SET:
-	{
-		if (!buf) {
-			err = -EFAULT;
-			goto out;
-		}
-
-		if (copy_shmid_from_user (&setbuf, buf, version)) {
-			err = -EFAULT;
-			goto out;
-		}
-		down_write(&shm_ids(ns).rw_mutex);
-		shp = shm_lock_check_down(ns, shmid);
-		if (IS_ERR(shp)) {
-			err = PTR_ERR(shp);
-			goto out_up;
-		}
-		err = audit_ipc_obj(&(shp->shm_perm));
-		if (err)
-			goto out_unlock_up;
-		err = audit_ipc_set_perm(0, setbuf.uid, setbuf.gid, setbuf.mode);
-		if (err)
-			goto out_unlock_up;
-		err=-EPERM;
-		if (current->euid != shp->shm_perm.uid &&
-		    current->euid != shp->shm_perm.cuid && 
-		    !capable(CAP_SYS_ADMIN)) {
-			goto out_unlock_up;
-		}
-
-		err = security_shm_shmctl(shp, cmd);
-		if (err)
-			goto out_unlock_up;
-		
-		shp->shm_perm.uid = setbuf.uid;
-		shp->shm_perm.gid = setbuf.gid;
-		shp->shm_perm.mode = (shp->shm_perm.mode & ~S_IRWXUGO)
-			| (setbuf.mode & S_IRWXUGO);
-		shp->shm_ctim = get_seconds();
-		break;
-	}
-
+		err = shmctl_down(ns, shmid, cmd, buf, version);
+		return err;
 	default:
-		err = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
-	err = 0;
-out_unlock_up:
-	shm_unlock(shp);
-out_up:
-	up_write(&shm_ids(ns).rw_mutex);
-	goto out;
 out_unlock:
 	shm_unlock(shp);
 out:
diff --git a/trunk/ipc/util.c b/trunk/ipc/util.c
index fd1b50da9db8..3339177b336c 100644
--- a/trunk/ipc/util.c
+++ b/trunk/ipc/util.c
@@ -33,6 +33,7 @@
 #include <linux/audit.h>
 #include <linux/nsproxy.h>
 #include <linux/rwsem.h>
+#include <linux/memory.h>
 #include <linux/ipc_namespace.h>
 
 #include <asm/unistd.h>
@@ -52,11 +53,57 @@ struct ipc_namespace init_ipc_ns = {
 	},
 };
 
+atomic_t nr_ipc_ns = ATOMIC_INIT(1);
+
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+
+static void ipc_memory_notifier(struct work_struct *work)
+{
+	ipcns_notify(IPCNS_MEMCHANGED);
+}
+
+static DECLARE_WORK(ipc_memory_wq, ipc_memory_notifier);
+
+
+static int ipc_memory_callback(struct notifier_block *self,
+				unsigned long action, void *arg)
+{
+	switch (action) {
+	case MEM_ONLINE:    /* memory successfully brought online */
+	case MEM_OFFLINE:   /* or offline: it's time to recompute msgmni */
+		/*
+		 * This is done by invoking the ipcns notifier chain with the
+		 * IPC_MEMCHANGED event.
+		 * In order not to keep the lock on the hotplug memory chain
+		 * for too long, queue a work item that will, when waken up,
+		 * activate the ipcns notification chain.
+		 * No need to keep several ipc work items on the queue.
+		 */
+		if (!work_pending(&ipc_memory_wq))
+			schedule_work(&ipc_memory_wq);
+		break;
+	case MEM_GOING_ONLINE:
+	case MEM_GOING_OFFLINE:
+	case MEM_CANCEL_ONLINE:
+	case MEM_CANCEL_OFFLINE:
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
 /**
  *	ipc_init	-	initialise IPC subsystem
  *
  *	The various system5 IPC resources (semaphores, messages and shared
  *	memory) are initialised
+ *	A callback routine is registered into the memory hotplug notifier
+ *	chain: since msgmni scales to lowmem this callback routine will be
+ *	called upon successful memory add / remove to recompute msmgni.
  */
  
 static int __init ipc_init(void)
@@ -64,6 +111,8 @@ static int __init ipc_init(void)
 	sem_init();
 	msg_init();
 	shm_init();
+	hotplug_memory_notifier(ipc_memory_callback, IPC_CALLBACK_PRI);
+	register_ipcns_notifier(&init_ipc_ns);
 	return 0;
 }
 __initcall(ipc_init);
@@ -84,8 +133,8 @@ void ipc_init_ids(struct ipc_ids *ids)
 	ids->seq = 0;
 	{
 		int seq_limit = INT_MAX/SEQ_MULTIPLIER;
-		if(seq_limit > USHRT_MAX)
-			ids->seq_max = USHRT_MAX;
+		if (seq_limit > USHORT_MAX)
+			ids->seq_max = USHORT_MAX;
 		 else
 		 	ids->seq_max = seq_limit;
 	}
@@ -116,13 +165,12 @@ void __init ipc_init_proc_interface(const char *path, const char *header,
 	iface->ids	= ids;
 	iface->show	= show;
 
-	pde = create_proc_entry(path,
-				S_IRUGO,        /* world readable */
-				NULL            /* parent dir */);
-	if (pde) {
-		pde->data = iface;
-		pde->proc_fops = &sysvipc_proc_fops;
-	} else {
+	pde = proc_create_data(path,
+			       S_IRUGO,        /* world readable */
+			       NULL,           /* parent dir */
+			       &sysvipc_proc_fops,
+			       iface);
+	if (!pde) {
 		kfree(iface);
 	}
 }
@@ -231,6 +279,7 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
 	if(ids->seq > ids->seq_max)
 		ids->seq = 0;
 
+	new->id = ipc_buildid(id, new->seq);
 	spin_lock_init(&new->lock);
 	new->deleted = 0;
 	rcu_read_lock();
@@ -761,6 +810,70 @@ int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids,
 		return ipcget_public(ns, ids, ops, params);
 }
 
+/**
+ * ipc_update_perm - update the permissions of an IPC.
+ * @in:  the permission given as input.
+ * @out: the permission of the ipc to set.
+ */
+void ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
+{
+	out->uid = in->uid;
+	out->gid = in->gid;
+	out->mode = (out->mode & ~S_IRWXUGO)
+		| (in->mode & S_IRWXUGO);
+}
+
+/**
+ * ipcctl_pre_down - retrieve an ipc and check permissions for some IPC_XXX cmd
+ * @ids:  the table of ids where to look for the ipc
+ * @id:   the id of the ipc to retrieve
+ * @cmd:  the cmd to check
+ * @perm: the permission to set
+ * @extra_perm: one extra permission parameter used by msq
+ *
+ * This function does some common audit and permissions check for some IPC_XXX
+ * cmd and is called from semctl_down, shmctl_down and msgctl_down.
+ * It must be called without any lock held and
+ *  - retrieves the ipc with the given id in the given table.
+ *  - performs some audit and permission check, depending on the given cmd
+ *  - returns the ipc with both ipc and rw_mutex locks held in case of success
+ *    or an err-code without any lock held otherwise.
+ */
+struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd,
+				      struct ipc64_perm *perm, int extra_perm)
+{
+	struct kern_ipc_perm *ipcp;
+	int err;
+
+	down_write(&ids->rw_mutex);
+	ipcp = ipc_lock_check_down(ids, id);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		goto out_up;
+	}
+
+	err = audit_ipc_obj(ipcp);
+	if (err)
+		goto out_unlock;
+
+	if (cmd == IPC_SET) {
+		err = audit_ipc_set_perm(extra_perm, perm->uid,
+					 perm->gid, perm->mode);
+		if (err)
+			goto out_unlock;
+	}
+	if (current->euid == ipcp->cuid ||
+	    current->euid == ipcp->uid || capable(CAP_SYS_ADMIN))
+		return ipcp;
+
+	err = -EPERM;
+out_unlock:
+	ipc_unlock(ipcp);
+out_up:
+	up_write(&ids->rw_mutex);
+	return ERR_PTR(err);
+}
+
 #ifdef __ARCH_WANT_IPC_PARSE_VERSION
 
 
diff --git a/trunk/ipc/util.h b/trunk/ipc/util.h
index f37d160c98fe..cdb966aebe07 100644
--- a/trunk/ipc/util.h
+++ b/trunk/ipc/util.h
@@ -12,7 +12,6 @@
 
 #include <linux/err.h>
 
-#define USHRT_MAX 0xffff
 #define SEQ_MULTIPLIER	(IPCMNI)
 
 void sem_init (void);
@@ -112,6 +111,9 @@ struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int);
 
 void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out);
 void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out);
+void ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out);
+struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd,
+				      struct ipc64_perm *perm, int extra_perm);
 
 #if defined(__ia64__) || defined(__x86_64__) || defined(__hppa__) || defined(__XTENSA__)
   /* On IA-64, we always use the "64-bit version" of the IPC structures.  */ 
@@ -124,6 +126,8 @@ extern void free_msg(struct msg_msg *msg);
 extern struct msg_msg *load_msg(const void __user *src, int len);
 extern int store_msg(void __user *dest, struct msg_msg *msg, int len);
 
+extern void recompute_msgmni(struct ipc_namespace *);
+
 static inline int ipc_buildid(int id, int seq)
 {
 	return SEQ_MULTIPLIER * seq + id;
diff --git a/trunk/kernel/Makefile b/trunk/kernel/Makefile
index 6c5f081132a4..188c43223f52 100644
--- a/trunk/kernel/Makefile
+++ b/trunk/kernel/Makefile
@@ -11,7 +11,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o
 
-obj-$(CONFIG_SYSCTL) += sysctl_check.o
+obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
 obj-y += time/
 obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
diff --git a/trunk/kernel/auditfilter.c b/trunk/kernel/auditfilter.c
index 28fef6bf8534..13430176b3c9 100644
--- a/trunk/kernel/auditfilter.c
+++ b/trunk/kernel/auditfilter.c
@@ -272,7 +272,7 @@ static int audit_to_watch(struct audit_krule *krule, char *path, int len,
 		return -EINVAL;
 
 	watch = audit_init_watch(path);
-	if (unlikely(IS_ERR(watch)))
+	if (IS_ERR(watch))
 		return PTR_ERR(watch);
 
 	audit_get_watch(watch);
@@ -848,7 +848,7 @@ static struct audit_watch *audit_dupe_watch(struct audit_watch *old)
 		return ERR_PTR(-ENOMEM);
 
 	new = audit_init_watch(path);
-	if (unlikely(IS_ERR(new))) {
+	if (IS_ERR(new)) {
 		kfree(path);
 		goto out;
 	}
@@ -989,7 +989,7 @@ static void audit_update_watch(struct audit_parent *parent,
 			audit_set_auditable(current->audit_context);
 
 		nwatch = audit_dupe_watch(owatch);
-		if (unlikely(IS_ERR(nwatch))) {
+		if (IS_ERR(nwatch)) {
 			mutex_unlock(&audit_filter_mutex);
 			audit_panic("error updating watch, skipping");
 			return;
@@ -1004,7 +1004,7 @@ static void audit_update_watch(struct audit_parent *parent,
 			list_del_rcu(&oentry->list);
 
 			nentry = audit_dupe_rule(&oentry->rule, nwatch);
-			if (unlikely(IS_ERR(nentry)))
+			if (IS_ERR(nentry))
 				audit_panic("error updating watch, removing");
 			else {
 				int h = audit_hash_ino((u32)ino);
@@ -1785,7 +1785,7 @@ int audit_update_lsm_rules(void)
 			watch = entry->rule.watch;
 			tree = entry->rule.tree;
 			nentry = audit_dupe_rule(&entry->rule, watch);
-			if (unlikely(IS_ERR(nentry))) {
+			if (IS_ERR(nentry)) {
 				/* save the first error encountered for the
 				 * return value */
 				if (!err)
diff --git a/trunk/kernel/bounds.c b/trunk/kernel/bounds.c
new file mode 100644
index 000000000000..3c5301381837
--- /dev/null
+++ b/trunk/kernel/bounds.c
@@ -0,0 +1,19 @@
+/*
+ * Generate definitions needed by the preprocessor.
+ * This code generates raw asm output which is post-processed
+ * to extract and format the required data.
+ */
+
+#define __GENERATING_BOUNDS_H
+/* Include headers that define the enum constants of interest */
+#include <linux/page-flags.h>
+#include <linux/mmzone.h>
+#include <linux/kbuild.h>
+
+void foo(void)
+{
+	/* The enum constants to put into include/linux/bounds.h */
+	DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
+	DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES);
+	/* End of constants */
+}
diff --git a/trunk/kernel/cgroup.c b/trunk/kernel/cgroup.c
index 6d8de051382b..b9d467d83fc1 100644
--- a/trunk/kernel/cgroup.c
+++ b/trunk/kernel/cgroup.c
@@ -44,6 +44,7 @@
 #include <linux/kmod.h>
 #include <linux/delayacct.h>
 #include <linux/cgroupstats.h>
+#include <linux/hash.h>
 
 #include <asm/atomic.h>
 
@@ -118,17 +119,7 @@ static int root_count;
  * be called.
  */
 static int need_forkexit_callback;
-
-/* bits in struct cgroup flags field */
-enum {
-	/* Control Group is dead */
-	CGRP_REMOVED,
-	/* Control Group has previously had a child cgroup or a task,
-	 * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set) */
-	CGRP_RELEASABLE,
-	/* Control Group requires release notifications to userspace */
-	CGRP_NOTIFY_ON_RELEASE,
-};
+static int need_mm_owner_callback __read_mostly;
 
 /* convenient tests for these bits */
 inline int cgroup_is_removed(const struct cgroup *cgrp)
@@ -204,6 +195,27 @@ static struct cg_cgroup_link init_css_set_link;
 static DEFINE_RWLOCK(css_set_lock);
 static int css_set_count;
 
+/* hash table for cgroup groups. This improves the performance to
+ * find an existing css_set */
+#define CSS_SET_HASH_BITS	7
+#define CSS_SET_TABLE_SIZE	(1 << CSS_SET_HASH_BITS)
+static struct hlist_head css_set_table[CSS_SET_TABLE_SIZE];
+
+static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
+{
+	int i;
+	int index;
+	unsigned long tmp = 0UL;
+
+	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++)
+		tmp += (unsigned long)css[i];
+	tmp = (tmp >> 16) ^ tmp;
+
+	index = hash_long(tmp, CSS_SET_HASH_BITS);
+
+	return &css_set_table[index];
+}
+
 /* We don't maintain the lists running through each css_set to its
  * task until after the first call to cgroup_iter_start(). This
  * reduces the fork()/exit() overhead for people who have cgroups
@@ -230,7 +242,7 @@ static int use_task_css_set_links;
 static void unlink_css_set(struct css_set *cg)
 {
 	write_lock(&css_set_lock);
-	list_del(&cg->list);
+	hlist_del(&cg->hlist);
 	css_set_count--;
 	while (!list_empty(&cg->cg_links)) {
 		struct cg_cgroup_link *link;
@@ -295,9 +307,7 @@ static inline void put_css_set_taskexit(struct css_set *cg)
 /*
  * find_existing_css_set() is a helper for
  * find_css_set(), and checks to see whether an existing
- * css_set is suitable. This currently walks a linked-list for
- * simplicity; a later patch will use a hash table for better
- * performance
+ * css_set is suitable.
  *
  * oldcg: the cgroup group that we're using before the cgroup
  * transition
@@ -314,7 +324,9 @@ static struct css_set *find_existing_css_set(
 {
 	int i;
 	struct cgroupfs_root *root = cgrp->root;
-	struct list_head *l = &init_css_set.list;
+	struct hlist_head *hhead;
+	struct hlist_node *node;
+	struct css_set *cg;
 
 	/* Built the set of subsystem state objects that we want to
 	 * see in the new css_set */
@@ -331,18 +343,13 @@ static struct css_set *find_existing_css_set(
 		}
 	}
 
-	/* Look through existing cgroup groups to find one to reuse */
-	do {
-		struct css_set *cg =
-			list_entry(l, struct css_set, list);
-
+	hhead = css_set_hash(template);
+	hlist_for_each_entry(cg, node, hhead, hlist) {
 		if (!memcmp(template, cg->subsys, sizeof(cg->subsys))) {
 			/* All subsystems matched */
 			return cg;
 		}
-		/* Try the next cgroup group */
-		l = l->next;
-	} while (l != &init_css_set.list);
+	}
 
 	/* No existing cgroup group matched */
 	return NULL;
@@ -404,6 +411,8 @@ static struct css_set *find_css_set(
 	struct list_head tmp_cg_links;
 	struct cg_cgroup_link *link;
 
+	struct hlist_head *hhead;
+
 	/* First see if we already have a cgroup group that matches
 	 * the desired set */
 	write_lock(&css_set_lock);
@@ -428,6 +437,7 @@ static struct css_set *find_css_set(
 	kref_init(&res->ref);
 	INIT_LIST_HEAD(&res->cg_links);
 	INIT_LIST_HEAD(&res->tasks);
+	INIT_HLIST_NODE(&res->hlist);
 
 	/* Copy the set of subsystem state objects generated in
 	 * find_existing_css_set() */
@@ -467,9 +477,12 @@ static struct css_set *find_css_set(
 
 	BUG_ON(!list_empty(&tmp_cg_links));
 
-	/* Link this cgroup group into the list */
-	list_add(&res->list, &init_css_set.list);
 	css_set_count++;
+
+	/* Add this cgroup group to the hash table */
+	hhead = css_set_hash(res->subsys);
+	hlist_add_head(&res->hlist, hhead);
+
 	write_unlock(&css_set_lock);
 
 	return res;
@@ -948,7 +961,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 	int ret = 0;
 	struct super_block *sb;
 	struct cgroupfs_root *root;
-	struct list_head tmp_cg_links, *l;
+	struct list_head tmp_cg_links;
 	INIT_LIST_HEAD(&tmp_cg_links);
 
 	/* First find the desired set of subsystems */
@@ -990,6 +1003,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 		/* New superblock */
 		struct cgroup *cgrp = &root->top_cgroup;
 		struct inode *inode;
+		int i;
 
 		BUG_ON(sb->s_root != NULL);
 
@@ -1034,22 +1048,25 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 		/* Link the top cgroup in this hierarchy into all
 		 * the css_set objects */
 		write_lock(&css_set_lock);
-		l = &init_css_set.list;
-		do {
+		for (i = 0; i < CSS_SET_TABLE_SIZE; i++) {
+			struct hlist_head *hhead = &css_set_table[i];
+			struct hlist_node *node;
 			struct css_set *cg;
-			struct cg_cgroup_link *link;
-			cg = list_entry(l, struct css_set, list);
-			BUG_ON(list_empty(&tmp_cg_links));
-			link = list_entry(tmp_cg_links.next,
-					  struct cg_cgroup_link,
-					  cgrp_link_list);
-			list_del(&link->cgrp_link_list);
-			link->cg = cg;
-			list_add(&link->cgrp_link_list,
-				 &root->top_cgroup.css_sets);
-			list_add(&link->cg_link_list, &cg->cg_links);
-			l = l->next;
-		} while (l != &init_css_set.list);
+
+			hlist_for_each_entry(cg, node, hhead, hlist) {
+				struct cg_cgroup_link *link;
+
+				BUG_ON(list_empty(&tmp_cg_links));
+				link = list_entry(tmp_cg_links.next,
+						  struct cg_cgroup_link,
+						  cgrp_link_list);
+				list_del(&link->cgrp_link_list);
+				link->cg = cg;
+				list_add(&link->cgrp_link_list,
+					 &root->top_cgroup.css_sets);
+				list_add(&link->cg_link_list, &cg->cg_links);
+			}
+		}
 		write_unlock(&css_set_lock);
 
 		free_cg_links(&tmp_cg_links);
@@ -1307,18 +1324,16 @@ enum cgroup_filetype {
 	FILE_DIR,
 	FILE_TASKLIST,
 	FILE_NOTIFY_ON_RELEASE,
-	FILE_RELEASABLE,
 	FILE_RELEASE_AGENT,
 };
 
-static ssize_t cgroup_write_uint(struct cgroup *cgrp, struct cftype *cft,
-				 struct file *file,
-				 const char __user *userbuf,
-				 size_t nbytes, loff_t *unused_ppos)
+static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft,
+				struct file *file,
+				const char __user *userbuf,
+				size_t nbytes, loff_t *unused_ppos)
 {
 	char buffer[64];
 	int retval = 0;
-	u64 val;
 	char *end;
 
 	if (!nbytes)
@@ -1329,16 +1344,18 @@ static ssize_t cgroup_write_uint(struct cgroup *cgrp, struct cftype *cft,
 		return -EFAULT;
 
 	buffer[nbytes] = 0;     /* nul-terminate */
-
-	/* strip newline if necessary */
-	if (nbytes && (buffer[nbytes-1] == '\n'))
-		buffer[nbytes-1] = 0;
-	val = simple_strtoull(buffer, &end, 0);
-	if (*end)
-		return -EINVAL;
-
-	/* Pass to subsystem */
-	retval = cft->write_uint(cgrp, cft, val);
+	strstrip(buffer);
+	if (cft->write_u64) {
+		u64 val = simple_strtoull(buffer, &end, 0);
+		if (*end)
+			return -EINVAL;
+		retval = cft->write_u64(cgrp, cft, val);
+	} else {
+		s64 val = simple_strtoll(buffer, &end, 0);
+		if (*end)
+			return -EINVAL;
+		retval = cft->write_s64(cgrp, cft, val);
+	}
 	if (!retval)
 		retval = nbytes;
 	return retval;
@@ -1419,23 +1436,39 @@ static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
 		return -ENODEV;
 	if (cft->write)
 		return cft->write(cgrp, cft, file, buf, nbytes, ppos);
-	if (cft->write_uint)
-		return cgroup_write_uint(cgrp, cft, file, buf, nbytes, ppos);
+	if (cft->write_u64 || cft->write_s64)
+		return cgroup_write_X64(cgrp, cft, file, buf, nbytes, ppos);
+	if (cft->trigger) {
+		int ret = cft->trigger(cgrp, (unsigned int)cft->private);
+		return ret ? ret : nbytes;
+	}
 	return -EINVAL;
 }
 
-static ssize_t cgroup_read_uint(struct cgroup *cgrp, struct cftype *cft,
-				   struct file *file,
-				   char __user *buf, size_t nbytes,
-				   loff_t *ppos)
+static ssize_t cgroup_read_u64(struct cgroup *cgrp, struct cftype *cft,
+			       struct file *file,
+			       char __user *buf, size_t nbytes,
+			       loff_t *ppos)
 {
 	char tmp[64];
-	u64 val = cft->read_uint(cgrp, cft);
+	u64 val = cft->read_u64(cgrp, cft);
 	int len = sprintf(tmp, "%llu\n", (unsigned long long) val);
 
 	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
 }
 
+static ssize_t cgroup_read_s64(struct cgroup *cgrp, struct cftype *cft,
+			       struct file *file,
+			       char __user *buf, size_t nbytes,
+			       loff_t *ppos)
+{
+	char tmp[64];
+	s64 val = cft->read_s64(cgrp, cft);
+	int len = sprintf(tmp, "%lld\n", (long long) val);
+
+	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
+}
+
 static ssize_t cgroup_common_file_read(struct cgroup *cgrp,
 					  struct cftype *cft,
 					  struct file *file,
@@ -1490,11 +1523,56 @@ static ssize_t cgroup_file_read(struct file *file, char __user *buf,
 
 	if (cft->read)
 		return cft->read(cgrp, cft, file, buf, nbytes, ppos);
-	if (cft->read_uint)
-		return cgroup_read_uint(cgrp, cft, file, buf, nbytes, ppos);
+	if (cft->read_u64)
+		return cgroup_read_u64(cgrp, cft, file, buf, nbytes, ppos);
+	if (cft->read_s64)
+		return cgroup_read_s64(cgrp, cft, file, buf, nbytes, ppos);
 	return -EINVAL;
 }
 
+/*
+ * seqfile ops/methods for returning structured data. Currently just
+ * supports string->u64 maps, but can be extended in future.
+ */
+
+struct cgroup_seqfile_state {
+	struct cftype *cft;
+	struct cgroup *cgroup;
+};
+
+static int cgroup_map_add(struct cgroup_map_cb *cb, const char *key, u64 value)
+{
+	struct seq_file *sf = cb->state;
+	return seq_printf(sf, "%s %llu\n", key, (unsigned long long)value);
+}
+
+static int cgroup_seqfile_show(struct seq_file *m, void *arg)
+{
+	struct cgroup_seqfile_state *state = m->private;
+	struct cftype *cft = state->cft;
+	if (cft->read_map) {
+		struct cgroup_map_cb cb = {
+			.fill = cgroup_map_add,
+			.state = m,
+		};
+		return cft->read_map(state->cgroup, cft, &cb);
+	}
+	return cft->read_seq_string(state->cgroup, cft, m);
+}
+
+int cgroup_seqfile_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	kfree(seq->private);
+	return single_release(inode, file);
+}
+
+static struct file_operations cgroup_seqfile_operations = {
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = cgroup_seqfile_release,
+};
+
 static int cgroup_file_open(struct inode *inode, struct file *file)
 {
 	int err;
@@ -1507,7 +1585,18 @@ static int cgroup_file_open(struct inode *inode, struct file *file)
 	cft = __d_cft(file->f_dentry);
 	if (!cft)
 		return -ENODEV;
-	if (cft->open)
+	if (cft->read_map || cft->read_seq_string) {
+		struct cgroup_seqfile_state *state =
+			kzalloc(sizeof(*state), GFP_USER);
+		if (!state)
+			return -ENOMEM;
+		state->cft = cft;
+		state->cgroup = __d_cgrp(file->f_dentry->d_parent);
+		file->f_op = &cgroup_seqfile_operations;
+		err = single_open(file, cgroup_seqfile_show, state);
+		if (err < 0)
+			kfree(state);
+	} else if (cft->open)
 		err = cft->open(inode, file);
 	else
 		err = 0;
@@ -1715,7 +1804,7 @@ static void cgroup_advance_iter(struct cgroup *cgrp,
  * The tasklist_lock is not held here, as do_each_thread() and
  * while_each_thread() are protected by RCU.
  */
-void cgroup_enable_task_cg_lists(void)
+static void cgroup_enable_task_cg_lists(void)
 {
 	struct task_struct *p, *g;
 	write_lock(&css_set_lock);
@@ -1913,14 +2002,14 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
 
 	if (heap->size) {
 		for (i = 0; i < heap->size; i++) {
-			struct task_struct *p = heap->ptrs[i];
+			struct task_struct *q = heap->ptrs[i];
 			if (i == 0) {
-				latest_time = p->start_time;
-				latest_task = p;
+				latest_time = q->start_time;
+				latest_task = q;
 			}
 			/* Process the task per the caller's callback */
-			scan->process_task(p, scan);
-			put_task_struct(p);
+			scan->process_task(q, scan);
+			put_task_struct(q);
 		}
 		/*
 		 * If we had to process any tasks at all, scan again
@@ -2138,11 +2227,6 @@ static u64 cgroup_read_notify_on_release(struct cgroup *cgrp,
 	return notify_on_release(cgrp);
 }
 
-static u64 cgroup_read_releasable(struct cgroup *cgrp, struct cftype *cft)
-{
-	return test_bit(CGRP_RELEASABLE, &cgrp->flags);
-}
-
 /*
  * for the common functions, 'private' gives the type of file
  */
@@ -2158,16 +2242,10 @@ static struct cftype files[] = {
 
 	{
 		.name = "notify_on_release",
-		.read_uint = cgroup_read_notify_on_release,
+		.read_u64 = cgroup_read_notify_on_release,
 		.write = cgroup_common_file_write,
 		.private = FILE_NOTIFY_ON_RELEASE,
 	},
-
-	{
-		.name = "releasable",
-		.read_uint = cgroup_read_releasable,
-		.private = FILE_RELEASABLE,
-	}
 };
 
 static struct cftype cft_release_agent = {
@@ -2401,10 +2479,9 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	return 0;
 }
 
-static void cgroup_init_subsys(struct cgroup_subsys *ss)
+static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 {
 	struct cgroup_subsys_state *css;
-	struct list_head *l;
 
 	printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);
 
@@ -2415,34 +2492,19 @@ static void cgroup_init_subsys(struct cgroup_subsys *ss)
 	BUG_ON(IS_ERR(css));
 	init_cgroup_css(css, ss, dummytop);
 
-	/* Update all cgroup groups to contain a subsys
+	/* Update the init_css_set to contain a subsys
 	 * pointer to this state - since the subsystem is
-	 * newly registered, all tasks and hence all cgroup
-	 * groups are in the subsystem's top cgroup. */
-	write_lock(&css_set_lock);
-	l = &init_css_set.list;
-	do {
-		struct css_set *cg =
-			list_entry(l, struct css_set, list);
-		cg->subsys[ss->subsys_id] = dummytop->subsys[ss->subsys_id];
-		l = l->next;
-	} while (l != &init_css_set.list);
-	write_unlock(&css_set_lock);
-
- 	/* If this subsystem requested that it be notified with fork
- 	 * events, we should send it one now for every process in the
- 	 * system */
-	if (ss->fork) {
-		struct task_struct *g, *p;
-
-		read_lock(&tasklist_lock);
-		do_each_thread(g, p) {
-			ss->fork(ss, p);
-		} while_each_thread(g, p);
-		read_unlock(&tasklist_lock);
-	}
+	 * newly registered, all tasks and hence the
+	 * init_css_set is in the subsystem's top cgroup. */
+	init_css_set.subsys[ss->subsys_id] = dummytop->subsys[ss->subsys_id];
 
 	need_forkexit_callback |= ss->fork || ss->exit;
+	need_mm_owner_callback |= !!ss->mm_owner_changed;
+
+	/* At system boot, before all subsystems have been
+	 * registered, no tasks have been forked, so we don't
+	 * need to invoke fork callbacks here. */
+	BUG_ON(!list_empty(&init_task.tasks));
 
 	ss->active = 1;
 }
@@ -2458,9 +2520,9 @@ int __init cgroup_init_early(void)
 	int i;
 	kref_init(&init_css_set.ref);
 	kref_get(&init_css_set.ref);
-	INIT_LIST_HEAD(&init_css_set.list);
 	INIT_LIST_HEAD(&init_css_set.cg_links);
 	INIT_LIST_HEAD(&init_css_set.tasks);
+	INIT_HLIST_NODE(&init_css_set.hlist);
 	css_set_count = 1;
 	init_cgroup_root(&rootnode);
 	list_add(&rootnode.root_list, &roots);
@@ -2473,6 +2535,9 @@ int __init cgroup_init_early(void)
 	list_add(&init_css_set_link.cg_link_list,
 		 &init_css_set.cg_links);
 
+	for (i = 0; i < CSS_SET_TABLE_SIZE; i++)
+		INIT_HLIST_HEAD(&css_set_table[i]);
+
 	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 		struct cgroup_subsys *ss = subsys[i];
 
@@ -2502,7 +2567,7 @@ int __init cgroup_init(void)
 {
 	int err;
 	int i;
-	struct proc_dir_entry *entry;
+	struct hlist_head *hhead;
 
 	err = bdi_init(&cgroup_backing_dev_info);
 	if (err)
@@ -2514,13 +2579,15 @@ int __init cgroup_init(void)
 			cgroup_init_subsys(ss);
 	}
 
+	/* Add init_css_set to the hash table */
+	hhead = css_set_hash(init_css_set.subsys);
+	hlist_add_head(&init_css_set.hlist, hhead);
+
 	err = register_filesystem(&cgroup_fs_type);
 	if (err < 0)
 		goto out;
 
-	entry = create_proc_entry("cgroups", 0, NULL);
-	if (entry)
-		entry->proc_fops = &proc_cgroupstats_operations;
+	proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations);
 
 out:
 	if (err)
@@ -2683,6 +2750,34 @@ void cgroup_fork_callbacks(struct task_struct *child)
 	}
 }
 
+#ifdef CONFIG_MM_OWNER
+/**
+ * cgroup_mm_owner_callbacks - run callbacks when the mm->owner changes
+ * @p: the new owner
+ *
+ * Called on every change to mm->owner. mm_init_owner() does not
+ * invoke this routine, since it assigns the mm->owner the first time
+ * and does not change it.
+ */
+void cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
+{
+	struct cgroup *oldcgrp, *newcgrp;
+
+	if (need_mm_owner_callback) {
+		int i;
+		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+			oldcgrp = task_cgroup(old, ss->subsys_id);
+			newcgrp = task_cgroup(new, ss->subsys_id);
+			if (oldcgrp == newcgrp)
+				continue;
+			if (ss->mm_owner_changed)
+				ss->mm_owner_changed(ss, oldcgrp, newcgrp);
+		}
+	}
+}
+#endif /* CONFIG_MM_OWNER */
+
 /**
  * cgroup_post_fork - called on a new task after adding it to the task list
  * @child: the task in question
diff --git a/trunk/kernel/cgroup_debug.c b/trunk/kernel/cgroup_debug.c
index 37301e877cb0..c3dc3aba4c02 100644
--- a/trunk/kernel/cgroup_debug.c
+++ b/trunk/kernel/cgroup_debug.c
@@ -1,5 +1,5 @@
 /*
- * kernel/ccontainer_debug.c - Example cgroup subsystem that
+ * kernel/cgroup_debug.c - Example cgroup subsystem that
  * exposes debug info
  *
  * Copyright (C) Google Inc, 2007
@@ -62,25 +62,35 @@ static u64 current_css_set_refcount_read(struct cgroup *cont,
 	return count;
 }
 
+static u64 releasable_read(struct cgroup *cgrp, struct cftype *cft)
+{
+	return test_bit(CGRP_RELEASABLE, &cgrp->flags);
+}
+
 static struct cftype files[] =  {
 	{
 		.name = "cgroup_refcount",
-		.read_uint = cgroup_refcount_read,
+		.read_u64 = cgroup_refcount_read,
 	},
 	{
 		.name = "taskcount",
-		.read_uint = taskcount_read,
+		.read_u64 = taskcount_read,
 	},
 
 	{
 		.name = "current_css_set",
-		.read_uint = current_css_set_read,
+		.read_u64 = current_css_set_read,
 	},
 
 	{
 		.name = "current_css_set_refcount",
-		.read_uint = current_css_set_refcount_read,
+		.read_u64 = current_css_set_refcount_read,
 	},
+
+	{
+		.name = "releasable",
+		.read_u64 = releasable_read,
+	}
 };
 
 static int debug_populate(struct cgroup_subsys *ss, struct cgroup *cont)
diff --git a/trunk/kernel/configs.c b/trunk/kernel/configs.c
index e84d3f9c6c7b..4c345210ed8c 100644
--- a/trunk/kernel/configs.c
+++ b/trunk/kernel/configs.c
@@ -79,12 +79,11 @@ static int __init ikconfig_init(void)
 	struct proc_dir_entry *entry;
 
 	/* create the current config file */
-	entry = create_proc_entry("config.gz", S_IFREG | S_IRUGO,
-				  &proc_root);
+	entry = proc_create("config.gz", S_IFREG | S_IRUGO, NULL,
+			    &ikconfig_file_ops);
 	if (!entry)
 		return -ENOMEM;
 
-	entry->proc_fops = &ikconfig_file_ops;
 	entry->size = kernel_config_data_size;
 
 	return 0;
@@ -95,7 +94,7 @@ static int __init ikconfig_init(void)
 
 static void __exit ikconfig_cleanup(void)
 {
-	remove_proc_entry("config.gz", &proc_root);
+	remove_proc_entry("config.gz", NULL);
 }
 
 module_init(ikconfig_init);
diff --git a/trunk/kernel/cpu.c b/trunk/kernel/cpu.c
index 2011ad8d2697..a98f6ab16ecd 100644
--- a/trunk/kernel/cpu.c
+++ b/trunk/kernel/cpu.c
@@ -33,17 +33,13 @@ static struct {
 	 * an ongoing cpu hotplug operation.
 	 */
 	int refcount;
-	wait_queue_head_t writer_queue;
 } cpu_hotplug;
 
-#define writer_exists() (cpu_hotplug.active_writer != NULL)
-
 void __init cpu_hotplug_init(void)
 {
 	cpu_hotplug.active_writer = NULL;
 	mutex_init(&cpu_hotplug.lock);
 	cpu_hotplug.refcount = 0;
-	init_waitqueue_head(&cpu_hotplug.writer_queue);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -65,11 +61,8 @@ void put_online_cpus(void)
 	if (cpu_hotplug.active_writer == current)
 		return;
 	mutex_lock(&cpu_hotplug.lock);
-	cpu_hotplug.refcount--;
-
-	if (unlikely(writer_exists()) && !cpu_hotplug.refcount)
-		wake_up(&cpu_hotplug.writer_queue);
-
+	if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
+		wake_up_process(cpu_hotplug.active_writer);
 	mutex_unlock(&cpu_hotplug.lock);
 
 }
@@ -98,8 +91,8 @@ void cpu_maps_update_done(void)
  * Note that during a cpu-hotplug operation, the new readers, if any,
  * will be blocked by the cpu_hotplug.lock
  *
- * Since cpu_maps_update_begin is always called after invoking
- * cpu_maps_update_begin, we can be sure that only one writer is active.
+ * Since cpu_hotplug_begin() is always called after invoking
+ * cpu_maps_update_begin(), we can be sure that only one writer is active.
  *
  * Note that theoretically, there is a possibility of a livelock:
  * - Refcount goes to zero, last reader wakes up the sleeping
@@ -115,19 +108,16 @@ void cpu_maps_update_done(void)
  */
 static void cpu_hotplug_begin(void)
 {
-	DECLARE_WAITQUEUE(wait, current);
-
-	mutex_lock(&cpu_hotplug.lock);
-
 	cpu_hotplug.active_writer = current;
-	add_wait_queue_exclusive(&cpu_hotplug.writer_queue, &wait);
-	while (cpu_hotplug.refcount) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
+
+	for (;;) {
+		mutex_lock(&cpu_hotplug.lock);
+		if (likely(!cpu_hotplug.refcount))
+			break;
+		__set_current_state(TASK_UNINTERRUPTIBLE);
 		mutex_unlock(&cpu_hotplug.lock);
 		schedule();
-		mutex_lock(&cpu_hotplug.lock);
 	}
-	remove_wait_queue_locked(&cpu_hotplug.writer_queue, &wait);
 }
 
 static void cpu_hotplug_done(void)
@@ -136,7 +126,7 @@ static void cpu_hotplug_done(void)
 	mutex_unlock(&cpu_hotplug.lock);
 }
 /* Need to know about CPUs going up/down? */
-int __cpuinit register_cpu_notifier(struct notifier_block *nb)
+int __ref register_cpu_notifier(struct notifier_block *nb)
 {
 	int ret;
 	cpu_maps_update_begin();
@@ -149,7 +139,7 @@ int __cpuinit register_cpu_notifier(struct notifier_block *nb)
 
 EXPORT_SYMBOL(register_cpu_notifier);
 
-void unregister_cpu_notifier(struct notifier_block *nb)
+void __ref unregister_cpu_notifier(struct notifier_block *nb)
 {
 	cpu_maps_update_begin();
 	raw_notifier_chain_unregister(&cpu_chain, nb);
@@ -180,7 +170,7 @@ struct take_cpu_down_param {
 };
 
 /* Take this CPU down. */
-static int take_cpu_down(void *_param)
+static int __ref take_cpu_down(void *_param)
 {
 	struct take_cpu_down_param *param = _param;
 	int err;
@@ -199,7 +189,7 @@ static int take_cpu_down(void *_param)
 }
 
 /* Requires cpu_add_remove_lock to be held */
-static int _cpu_down(unsigned int cpu, int tasks_frozen)
+static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 {
 	int err, nr_calls = 0;
 	struct task_struct *p;
@@ -274,7 +264,7 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
 	return err;
 }
 
-int cpu_down(unsigned int cpu)
+int __ref cpu_down(unsigned int cpu)
 {
 	int err = 0;
 
diff --git a/trunk/kernel/cpuset.c b/trunk/kernel/cpuset.c
index 8b35fbd8292f..8da627d33804 100644
--- a/trunk/kernel/cpuset.c
+++ b/trunk/kernel/cpuset.c
@@ -127,6 +127,7 @@ struct cpuset_hotplug_scanner {
 typedef enum {
 	CS_CPU_EXCLUSIVE,
 	CS_MEM_EXCLUSIVE,
+	CS_MEM_HARDWALL,
 	CS_MEMORY_MIGRATE,
 	CS_SCHED_LOAD_BALANCE,
 	CS_SPREAD_PAGE,
@@ -144,6 +145,11 @@ static inline int is_mem_exclusive(const struct cpuset *cs)
 	return test_bit(CS_MEM_EXCLUSIVE, &cs->flags);
 }
 
+static inline int is_mem_hardwall(const struct cpuset *cs)
+{
+	return test_bit(CS_MEM_HARDWALL, &cs->flags);
+}
+
 static inline int is_sched_load_balance(const struct cpuset *cs)
 {
 	return test_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
@@ -735,7 +741,8 @@ static inline int started_after(void *p1, void *p2)
  * Return nonzero if this tasks's cpus_allowed mask should be changed (in other
  * words, if its mask is not equal to its cpuset's mask).
  */
-int cpuset_test_cpumask(struct task_struct *tsk, struct cgroup_scanner *scan)
+static int cpuset_test_cpumask(struct task_struct *tsk,
+			       struct cgroup_scanner *scan)
 {
 	return !cpus_equal(tsk->cpus_allowed,
 			(cgroup_cs(scan->cg))->cpus_allowed);
@@ -752,7 +759,8 @@ int cpuset_test_cpumask(struct task_struct *tsk, struct cgroup_scanner *scan)
  * We don't need to re-check for the cgroup/cpuset membership, since we're
  * holding cgroup_lock() at this point.
  */
-void cpuset_change_cpumask(struct task_struct *tsk, struct cgroup_scanner *scan)
+static void cpuset_change_cpumask(struct task_struct *tsk,
+				  struct cgroup_scanner *scan)
 {
 	set_cpus_allowed_ptr(tsk, &((cgroup_cs(scan->cg))->cpus_allowed));
 }
@@ -941,7 +949,7 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 	cs->mems_generation = cpuset_mems_generation++;
 	mutex_unlock(&callback_mutex);
 
-	cpuset_being_rebound = cs;		/* causes mpol_copy() rebind */
+	cpuset_being_rebound = cs;		/* causes mpol_dup() rebind */
 
 	fudge = 10;				/* spare mmarray[] slots */
 	fudge += cpus_weight(cs->cpus_allowed);	/* imagine one fork-bomb/cpu */
@@ -992,7 +1000,7 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 	 * rebind the vma mempolicies of each mm in mmarray[] to their
 	 * new cpuset, and release that mm.  The mpol_rebind_mm()
 	 * call takes mmap_sem, which we couldn't take while holding
-	 * tasklist_lock.  Forks can happen again now - the mpol_copy()
+	 * tasklist_lock.  Forks can happen again now - the mpol_dup()
 	 * cpuset_being_rebound check will catch such forks, and rebind
 	 * their vma mempolicies too.  Because we still hold the global
 	 * cgroup_mutex, we know that no other rebind effort will
@@ -1023,19 +1031,6 @@ int current_cpuset_is_being_rebound(void)
 	return task_cs(current) == cpuset_being_rebound;
 }
 
-/*
- * Call with cgroup_mutex held.
- */
-
-static int update_memory_pressure_enabled(struct cpuset *cs, char *buf)
-{
-	if (simple_strtoul(buf, NULL, 10) != 0)
-		cpuset_memory_pressure_enabled = 1;
-	else
-		cpuset_memory_pressure_enabled = 0;
-	return 0;
-}
-
 static int update_relax_domain_level(struct cpuset *cs, char *buf)
 {
 	int val = simple_strtol(buf, NULL, 10);
@@ -1053,25 +1048,20 @@ static int update_relax_domain_level(struct cpuset *cs, char *buf)
 
 /*
  * update_flag - read a 0 or a 1 in a file and update associated flag
- * bit:	the bit to update (CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE,
- *				CS_SCHED_LOAD_BALANCE,
- *				CS_NOTIFY_ON_RELEASE, CS_MEMORY_MIGRATE,
- *				CS_SPREAD_PAGE, CS_SPREAD_SLAB)
- * cs:	the cpuset to update
- * buf:	the buffer where we read the 0 or 1
+ * bit:		the bit to update (see cpuset_flagbits_t)
+ * cs:		the cpuset to update
+ * turning_on: 	whether the flag is being set or cleared
  *
  * Call with cgroup_mutex held.
  */
 
-static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf)
+static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
+		       int turning_on)
 {
-	int turning_on;
 	struct cpuset trialcs;
 	int err;
 	int cpus_nonempty, balance_flag_changed;
 
-	turning_on = (simple_strtoul(buf, NULL, 10) != 0);
-
 	trialcs = *cs;
 	if (turning_on)
 		set_bit(bit, &trialcs.flags);
@@ -1241,6 +1231,7 @@ typedef enum {
 	FILE_MEMLIST,
 	FILE_CPU_EXCLUSIVE,
 	FILE_MEM_EXCLUSIVE,
+	FILE_MEM_HARDWALL,
 	FILE_SCHED_LOAD_BALANCE,
 	FILE_SCHED_RELAX_DOMAIN_LEVEL,
 	FILE_MEMORY_PRESSURE_ENABLED,
@@ -1265,7 +1256,8 @@ static ssize_t cpuset_common_file_write(struct cgroup *cont,
 		return -E2BIG;
 
 	/* +1 for nul-terminator */
-	if ((buffer = kmalloc(nbytes + 1, GFP_KERNEL)) == 0)
+	buffer = kmalloc(nbytes + 1, GFP_KERNEL);
+	if (!buffer)
 		return -ENOMEM;
 
 	if (copy_from_user(buffer, userbuf, nbytes)) {
@@ -1288,46 +1280,71 @@ static ssize_t cpuset_common_file_write(struct cgroup *cont,
 	case FILE_MEMLIST:
 		retval = update_nodemask(cs, buffer);
 		break;
+	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+		retval = update_relax_domain_level(cs, buffer);
+		break;
+	default:
+		retval = -EINVAL;
+		goto out2;
+	}
+
+	if (retval == 0)
+		retval = nbytes;
+out2:
+	cgroup_unlock();
+out1:
+	kfree(buffer);
+	return retval;
+}
+
+static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
+{
+	int retval = 0;
+	struct cpuset *cs = cgroup_cs(cgrp);
+	cpuset_filetype_t type = cft->private;
+
+	cgroup_lock();
+
+	if (cgroup_is_removed(cgrp)) {
+		cgroup_unlock();
+		return -ENODEV;
+	}
+
+	switch (type) {
 	case FILE_CPU_EXCLUSIVE:
-		retval = update_flag(CS_CPU_EXCLUSIVE, cs, buffer);
+		retval = update_flag(CS_CPU_EXCLUSIVE, cs, val);
 		break;
 	case FILE_MEM_EXCLUSIVE:
-		retval = update_flag(CS_MEM_EXCLUSIVE, cs, buffer);
+		retval = update_flag(CS_MEM_EXCLUSIVE, cs, val);
 		break;
-	case FILE_SCHED_LOAD_BALANCE:
-		retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, buffer);
+	case FILE_MEM_HARDWALL:
+		retval = update_flag(CS_MEM_HARDWALL, cs, val);
 		break;
-	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
-		retval = update_relax_domain_level(cs, buffer);
+	case FILE_SCHED_LOAD_BALANCE:
+		retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, val);
 		break;
 	case FILE_MEMORY_MIGRATE:
-		retval = update_flag(CS_MEMORY_MIGRATE, cs, buffer);
+		retval = update_flag(CS_MEMORY_MIGRATE, cs, val);
 		break;
 	case FILE_MEMORY_PRESSURE_ENABLED:
-		retval = update_memory_pressure_enabled(cs, buffer);
+		cpuset_memory_pressure_enabled = !!val;
 		break;
 	case FILE_MEMORY_PRESSURE:
 		retval = -EACCES;
 		break;
 	case FILE_SPREAD_PAGE:
-		retval = update_flag(CS_SPREAD_PAGE, cs, buffer);
+		retval = update_flag(CS_SPREAD_PAGE, cs, val);
 		cs->mems_generation = cpuset_mems_generation++;
 		break;
 	case FILE_SPREAD_SLAB:
-		retval = update_flag(CS_SPREAD_SLAB, cs, buffer);
+		retval = update_flag(CS_SPREAD_SLAB, cs, val);
 		cs->mems_generation = cpuset_mems_generation++;
 		break;
 	default:
 		retval = -EINVAL;
-		goto out2;
+		break;
 	}
-
-	if (retval == 0)
-		retval = nbytes;
-out2:
 	cgroup_unlock();
-out1:
-	kfree(buffer);
 	return retval;
 }
 
@@ -1389,33 +1406,9 @@ static ssize_t cpuset_common_file_read(struct cgroup *cont,
 	case FILE_MEMLIST:
 		s += cpuset_sprintf_memlist(s, cs);
 		break;
-	case FILE_CPU_EXCLUSIVE:
-		*s++ = is_cpu_exclusive(cs) ? '1' : '0';
-		break;
-	case FILE_MEM_EXCLUSIVE:
-		*s++ = is_mem_exclusive(cs) ? '1' : '0';
-		break;
-	case FILE_SCHED_LOAD_BALANCE:
-		*s++ = is_sched_load_balance(cs) ? '1' : '0';
-		break;
 	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
 		s += sprintf(s, "%d", cs->relax_domain_level);
 		break;
-	case FILE_MEMORY_MIGRATE:
-		*s++ = is_memory_migrate(cs) ? '1' : '0';
-		break;
-	case FILE_MEMORY_PRESSURE_ENABLED:
-		*s++ = cpuset_memory_pressure_enabled ? '1' : '0';
-		break;
-	case FILE_MEMORY_PRESSURE:
-		s += sprintf(s, "%d", fmeter_getrate(&cs->fmeter));
-		break;
-	case FILE_SPREAD_PAGE:
-		*s++ = is_spread_page(cs) ? '1' : '0';
-		break;
-	case FILE_SPREAD_SLAB:
-		*s++ = is_spread_slab(cs) ? '1' : '0';
-		break;
 	default:
 		retval = -EINVAL;
 		goto out;
@@ -1428,121 +1421,137 @@ static ssize_t cpuset_common_file_read(struct cgroup *cont,
 	return retval;
 }
 
-
-
+static u64 cpuset_read_u64(struct cgroup *cont, struct cftype *cft)
+{
+	struct cpuset *cs = cgroup_cs(cont);
+	cpuset_filetype_t type = cft->private;
+	switch (type) {
+	case FILE_CPU_EXCLUSIVE:
+		return is_cpu_exclusive(cs);
+	case FILE_MEM_EXCLUSIVE:
+		return is_mem_exclusive(cs);
+	case FILE_MEM_HARDWALL:
+		return is_mem_hardwall(cs);
+	case FILE_SCHED_LOAD_BALANCE:
+		return is_sched_load_balance(cs);
+	case FILE_MEMORY_MIGRATE:
+		return is_memory_migrate(cs);
+	case FILE_MEMORY_PRESSURE_ENABLED:
+		return cpuset_memory_pressure_enabled;
+	case FILE_MEMORY_PRESSURE:
+		return fmeter_getrate(&cs->fmeter);
+	case FILE_SPREAD_PAGE:
+		return is_spread_page(cs);
+	case FILE_SPREAD_SLAB:
+		return is_spread_slab(cs);
+	default:
+		BUG();
+	}
+}
 
 
 /*
  * for the common functions, 'private' gives the type of file
  */
 
-static struct cftype cft_cpus = {
-	.name = "cpus",
-	.read = cpuset_common_file_read,
-	.write = cpuset_common_file_write,
-	.private = FILE_CPULIST,
-};
-
-static struct cftype cft_mems = {
-	.name = "mems",
-	.read = cpuset_common_file_read,
-	.write = cpuset_common_file_write,
-	.private = FILE_MEMLIST,
-};
-
-static struct cftype cft_cpu_exclusive = {
-	.name = "cpu_exclusive",
-	.read = cpuset_common_file_read,
-	.write = cpuset_common_file_write,
-	.private = FILE_CPU_EXCLUSIVE,
-};
-
-static struct cftype cft_mem_exclusive = {
-	.name = "mem_exclusive",
-	.read = cpuset_common_file_read,
-	.write = cpuset_common_file_write,
-	.private = FILE_MEM_EXCLUSIVE,
-};
-
-static struct cftype cft_sched_load_balance = {
-	.name = "sched_load_balance",
-	.read = cpuset_common_file_read,
-	.write = cpuset_common_file_write,
-	.private = FILE_SCHED_LOAD_BALANCE,
-};
-
-static struct cftype cft_sched_relax_domain_level = {
-	.name = "sched_relax_domain_level",
-	.read = cpuset_common_file_read,
-	.write = cpuset_common_file_write,
-	.private = FILE_SCHED_RELAX_DOMAIN_LEVEL,
-};
-
-static struct cftype cft_memory_migrate = {
-	.name = "memory_migrate",
-	.read = cpuset_common_file_read,
-	.write = cpuset_common_file_write,
-	.private = FILE_MEMORY_MIGRATE,
+static struct cftype files[] = {
+	{
+		.name = "cpus",
+		.read = cpuset_common_file_read,
+		.write = cpuset_common_file_write,
+		.private = FILE_CPULIST,
+	},
+
+	{
+		.name = "mems",
+		.read = cpuset_common_file_read,
+		.write = cpuset_common_file_write,
+		.private = FILE_MEMLIST,
+	},
+
+	{
+		.name = "cpu_exclusive",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_CPU_EXCLUSIVE,
+	},
+
+	{
+		.name = "mem_exclusive",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_MEM_EXCLUSIVE,
+	},
+
+	{
+		.name = "mem_hardwall",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_MEM_HARDWALL,
+	},
+
+	{
+		.name = "sched_load_balance",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_SCHED_LOAD_BALANCE,
+	},
+
+	{
+		.name = "sched_relax_domain_level",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_SCHED_RELAX_DOMAIN_LEVEL,
+	},
+
+	{
+		.name = "memory_migrate",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_MEMORY_MIGRATE,
+	},
+
+	{
+		.name = "memory_pressure",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_MEMORY_PRESSURE,
+	},
+
+	{
+		.name = "memory_spread_page",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_SPREAD_PAGE,
+	},
+
+	{
+		.name = "memory_spread_slab",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_SPREAD_SLAB,
+	},
 };
 
 static struct cftype cft_memory_pressure_enabled = {
 	.name = "memory_pressure_enabled",
-	.read = cpuset_common_file_read,
-	.write = cpuset_common_file_write,
+	.read_u64 = cpuset_read_u64,
+	.write_u64 = cpuset_write_u64,
 	.private = FILE_MEMORY_PRESSURE_ENABLED,
 };
 
-static struct cftype cft_memory_pressure = {
-	.name = "memory_pressure",
-	.read = cpuset_common_file_read,
-	.write = cpuset_common_file_write,
-	.private = FILE_MEMORY_PRESSURE,
-};
-
-static struct cftype cft_spread_page = {
-	.name = "memory_spread_page",
-	.read = cpuset_common_file_read,
-	.write = cpuset_common_file_write,
-	.private = FILE_SPREAD_PAGE,
-};
-
-static struct cftype cft_spread_slab = {
-	.name = "memory_spread_slab",
-	.read = cpuset_common_file_read,
-	.write = cpuset_common_file_write,
-	.private = FILE_SPREAD_SLAB,
-};
-
 static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont)
 {
 	int err;
 
-	if ((err = cgroup_add_file(cont, ss, &cft_cpus)) < 0)
-		return err;
-	if ((err = cgroup_add_file(cont, ss, &cft_mems)) < 0)
-		return err;
-	if ((err = cgroup_add_file(cont, ss, &cft_cpu_exclusive)) < 0)
-		return err;
-	if ((err = cgroup_add_file(cont, ss, &cft_mem_exclusive)) < 0)
-		return err;
-	if ((err = cgroup_add_file(cont, ss, &cft_memory_migrate)) < 0)
-		return err;
-	if ((err = cgroup_add_file(cont, ss, &cft_sched_load_balance)) < 0)
-		return err;
-	if ((err = cgroup_add_file(cont, ss,
-					&cft_sched_relax_domain_level)) < 0)
-		return err;
-	if ((err = cgroup_add_file(cont, ss, &cft_memory_pressure)) < 0)
-		return err;
-	if ((err = cgroup_add_file(cont, ss, &cft_spread_page)) < 0)
-		return err;
-	if ((err = cgroup_add_file(cont, ss, &cft_spread_slab)) < 0)
+	err = cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
+	if (err)
 		return err;
 	/* memory_pressure_enabled is in root cpuset only */
-	if (err == 0 && !cont->parent)
+	if (!cont->parent)
 		err = cgroup_add_file(cont, ss,
-					 &cft_memory_pressure_enabled);
-	return 0;
+				      &cft_memory_pressure_enabled);
+	return err;
 }
 
 /*
@@ -1642,7 +1651,7 @@ static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
 	cpuset_update_task_memory_state();
 
 	if (is_sched_load_balance(cs))
-		update_flag(CS_SCHED_LOAD_BALANCE, cs, "0");
+		update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
 
 	number_of_cpusets--;
 	kfree(cs);
@@ -1707,7 +1716,8 @@ int __init cpuset_init(void)
  * Called by cgroup_scan_tasks() for each task in a cgroup.
  * Return nonzero to stop the walk through the tasks.
  */
-void cpuset_do_move_task(struct task_struct *tsk, struct cgroup_scanner *scan)
+static void cpuset_do_move_task(struct task_struct *tsk,
+				struct cgroup_scanner *scan)
 {
 	struct cpuset_hotplug_scanner *chsp;
 
@@ -1958,33 +1968,25 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
 }
 
 /**
- * cpuset_zonelist_valid_mems_allowed - check zonelist vs. curremt mems_allowed
- * @zl: the zonelist to be checked
+ * cpuset_nodemask_valid_mems_allowed - check nodemask vs. curremt mems_allowed
+ * @nodemask: the nodemask to be checked
  *
- * Are any of the nodes on zonelist zl allowed in current->mems_allowed?
+ * Are any of the nodes in the nodemask allowed in current->mems_allowed?
  */
-int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl)
+int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)
 {
-	int i;
-
-	for (i = 0; zl->zones[i]; i++) {
-		int nid = zone_to_nid(zl->zones[i]);
-
-		if (node_isset(nid, current->mems_allowed))
-			return 1;
-	}
-	return 0;
+	return nodes_intersects(*nodemask, current->mems_allowed);
 }
 
 /*
- * nearest_exclusive_ancestor() - Returns the nearest mem_exclusive
- * ancestor to the specified cpuset.  Call holding callback_mutex.
- * If no ancestor is mem_exclusive (an unusual configuration), then
- * returns the root cpuset.
+ * nearest_hardwall_ancestor() - Returns the nearest mem_exclusive or
+ * mem_hardwall ancestor to the specified cpuset.  Call holding
+ * callback_mutex.  If no ancestor is mem_exclusive or mem_hardwall
+ * (an unusual configuration), then returns the root cpuset.
  */
-static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs)
+static const struct cpuset *nearest_hardwall_ancestor(const struct cpuset *cs)
 {
-	while (!is_mem_exclusive(cs) && cs->parent)
+	while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && cs->parent)
 		cs = cs->parent;
 	return cs;
 }
@@ -1998,7 +2000,7 @@ static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs)
  * __GFP_THISNODE is set, yes, we can always allocate.  If zone
  * z's node is in our tasks mems_allowed, yes.  If it's not a
  * __GFP_HARDWALL request and this zone's nodes is in the nearest
- * mem_exclusive cpuset ancestor to this tasks cpuset, yes.
+ * hardwalled cpuset ancestor to this tasks cpuset, yes.
  * If the task has been OOM killed and has access to memory reserves
  * as specified by the TIF_MEMDIE flag, yes.
  * Otherwise, no.
@@ -2021,7 +2023,7 @@ static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs)
  * and do not allow allocations outside the current tasks cpuset
  * unless the task has been OOM killed as is marked TIF_MEMDIE.
  * GFP_KERNEL allocations are not so marked, so can escape to the
- * nearest enclosing mem_exclusive ancestor cpuset.
+ * nearest enclosing hardwalled ancestor cpuset.
  *
  * Scanning up parent cpusets requires callback_mutex.  The
  * __alloc_pages() routine only calls here with __GFP_HARDWALL bit
@@ -2044,7 +2046,7 @@ static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs)
  *	in_interrupt - any node ok (current task context irrelevant)
  *	GFP_ATOMIC   - any node ok
  *	TIF_MEMDIE   - any node ok
- *	GFP_KERNEL   - any node in enclosing mem_exclusive cpuset ok
+ *	GFP_KERNEL   - any node in enclosing hardwalled cpuset ok
  *	GFP_USER     - only nodes in current tasks mems allowed ok.
  *
  * Rule:
@@ -2081,7 +2083,7 @@ int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
 	mutex_lock(&callback_mutex);
 
 	task_lock(current);
-	cs = nearest_exclusive_ancestor(task_cs(current));
+	cs = nearest_hardwall_ancestor(task_cs(current));
 	task_unlock(current);
 
 	allowed = node_isset(node, cs->mems_allowed);
diff --git a/trunk/kernel/dma.c b/trunk/kernel/dma.c
index 6a82bb716dac..d2c60a822790 100644
--- a/trunk/kernel/dma.c
+++ b/trunk/kernel/dma.c
@@ -149,12 +149,7 @@ static const struct file_operations proc_dma_operations = {
 
 static int __init proc_dma_init(void)
 {
-	struct proc_dir_entry *e;
-
-	e = create_proc_entry("dma", 0, NULL);
-	if (e)
-		e->proc_fops = &proc_dma_operations;
-
+	proc_create("dma", 0, NULL, &proc_dma_operations);
 	return 0;
 }
 
diff --git a/trunk/kernel/exit.c b/trunk/kernel/exit.c
index 97f609f574b1..ae0f2c4e452b 100644
--- a/trunk/kernel/exit.c
+++ b/trunk/kernel/exit.c
@@ -557,6 +557,88 @@ void exit_fs(struct task_struct *tsk)
 
 EXPORT_SYMBOL_GPL(exit_fs);
 
+#ifdef CONFIG_MM_OWNER
+/*
+ * Task p is exiting and it owned mm, lets find a new owner for it
+ */
+static inline int
+mm_need_new_owner(struct mm_struct *mm, struct task_struct *p)
+{
+	/*
+	 * If there are other users of the mm and the owner (us) is exiting
+	 * we need to find a new owner to take on the responsibility.
+	 */
+	if (!mm)
+		return 0;
+	if (atomic_read(&mm->mm_users) <= 1)
+		return 0;
+	if (mm->owner != p)
+		return 0;
+	return 1;
+}
+
+void mm_update_next_owner(struct mm_struct *mm)
+{
+	struct task_struct *c, *g, *p = current;
+
+retry:
+	if (!mm_need_new_owner(mm, p))
+		return;
+
+	read_lock(&tasklist_lock);
+	/*
+	 * Search in the children
+	 */
+	list_for_each_entry(c, &p->children, sibling) {
+		if (c->mm == mm)
+			goto assign_new_owner;
+	}
+
+	/*
+	 * Search in the siblings
+	 */
+	list_for_each_entry(c, &p->parent->children, sibling) {
+		if (c->mm == mm)
+			goto assign_new_owner;
+	}
+
+	/*
+	 * Search through everything else. We should not get
+	 * here often
+	 */
+	do_each_thread(g, c) {
+		if (c->mm == mm)
+			goto assign_new_owner;
+	} while_each_thread(g, c);
+
+	read_unlock(&tasklist_lock);
+	return;
+
+assign_new_owner:
+	BUG_ON(c == p);
+	get_task_struct(c);
+	/*
+	 * The task_lock protects c->mm from changing.
+	 * We always want mm->owner->mm == mm
+	 */
+	task_lock(c);
+	/*
+	 * Delay read_unlock() till we have the task_lock()
+	 * to ensure that c does not slip away underneath us
+	 */
+	read_unlock(&tasklist_lock);
+	if (c->mm != mm) {
+		task_unlock(c);
+		put_task_struct(c);
+		goto retry;
+	}
+	cgroup_mm_owner_callbacks(mm->owner, c);
+	mm->owner = c;
+	task_unlock(c);
+	put_task_struct(c);
+}
+#endif /* CONFIG_MM_OWNER */
+
 /*
  * Turn us into a lazy TLB process if we
  * aren't already..
@@ -596,6 +678,7 @@ static void exit_mm(struct task_struct * tsk)
 	/* We don't want this task to be frozen prematurely */
 	clear_freeze_flag(tsk);
 	task_unlock(tsk);
+	mm_update_next_owner(mm);
 	mmput(mm);
 }
 
@@ -967,7 +1050,7 @@ NORET_TYPE void do_exit(long code)
 	proc_exit_connector(tsk);
 	exit_notify(tsk, group_dead);
 #ifdef CONFIG_NUMA
-	mpol_free(tsk->mempolicy);
+	mpol_put(tsk->mempolicy);
 	tsk->mempolicy = NULL;
 #endif
 #ifdef CONFIG_FUTEX
diff --git a/trunk/kernel/fork.c b/trunk/kernel/fork.c
index cb46befdd3a0..068ffe007529 100644
--- a/trunk/kernel/fork.c
+++ b/trunk/kernel/fork.c
@@ -279,7 +279,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		if (!tmp)
 			goto fail_nomem;
 		*tmp = *mpnt;
-		pol = mpol_copy(vma_policy(mpnt));
+		pol = mpol_dup(vma_policy(mpnt));
 		retval = PTR_ERR(pol);
 		if (IS_ERR(pol))
 			goto fail_nomem_policy;
@@ -381,14 +381,13 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 	mm->ioctx_list = NULL;
 	mm->free_area_cache = TASK_UNMAPPED_BASE;
 	mm->cached_hole_size = ~0UL;
-	mm_init_cgroup(mm, p);
+	mm_init_owner(mm, p);
 
 	if (likely(!mm_alloc_pgd(mm))) {
 		mm->def_flags = 0;
 		return mm;
 	}
 
-	mm_free_cgroup(mm);
 	free_mm(mm);
 	return NULL;
 }
@@ -432,13 +431,13 @@ void mmput(struct mm_struct *mm)
 	if (atomic_dec_and_test(&mm->mm_users)) {
 		exit_aio(mm);
 		exit_mmap(mm);
+		set_mm_exe_file(mm, NULL);
 		if (!list_empty(&mm->mmlist)) {
 			spin_lock(&mmlist_lock);
 			list_del(&mm->mmlist);
 			spin_unlock(&mmlist_lock);
 		}
 		put_swap_token(mm);
-		mm_free_cgroup(mm);
 		mmdrop(mm);
 	}
 }
@@ -521,7 +520,7 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
  * Allocate a new mm structure and copy contents from the
  * mm structure of the passed in task structure.
  */
-static struct mm_struct *dup_mm(struct task_struct *tsk)
+struct mm_struct *dup_mm(struct task_struct *tsk)
 {
 	struct mm_struct *mm, *oldmm = current->mm;
 	int err;
@@ -545,6 +544,8 @@ static struct mm_struct *dup_mm(struct task_struct *tsk)
 	if (init_new_context(tsk, mm))
 		goto fail_nocontext;
 
+	dup_mm_exe_file(oldmm, mm);
+
 	err = dup_mmap(mm, oldmm);
 	if (err)
 		goto free_pt;
@@ -982,6 +983,13 @@ static void rt_mutex_init_task(struct task_struct *p)
 #endif
 }
 
+#ifdef CONFIG_MM_OWNER
+void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
+{
+	mm->owner = p;
+}
+#endif /* CONFIG_MM_OWNER */
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -1116,7 +1124,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->audit_context = NULL;
 	cgroup_fork(p);
 #ifdef CONFIG_NUMA
- 	p->mempolicy = mpol_copy(p->mempolicy);
+	p->mempolicy = mpol_dup(p->mempolicy);
  	if (IS_ERR(p->mempolicy)) {
  		retval = PTR_ERR(p->mempolicy);
  		p->mempolicy = NULL;
@@ -1374,7 +1382,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	security_task_free(p);
 bad_fork_cleanup_policy:
 #ifdef CONFIG_NUMA
-	mpol_free(p->mempolicy);
+	mpol_put(p->mempolicy);
 bad_fork_cleanup_cgroup:
 #endif
 	cgroup_exit(p, cgroup_callbacks_done);
@@ -1663,18 +1671,6 @@ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp
 	return 0;
 }
 
-/*
- * Unsharing of semundo for tasks created with CLONE_SYSVSEM is not
- * supported yet
- */
-static int unshare_semundo(unsigned long unshare_flags, struct sem_undo_list **new_ulistp)
-{
-	if (unshare_flags & CLONE_SYSVSEM)
-		return -EINVAL;
-
-	return 0;
-}
-
 /*
  * unshare allows a process to 'unshare' part of the process
  * context which was originally shared using clone.  copy_*
@@ -1690,8 +1686,8 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
 	struct sighand_struct *new_sigh = NULL;
 	struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL;
 	struct files_struct *fd, *new_fd = NULL;
-	struct sem_undo_list *new_ulist = NULL;
 	struct nsproxy *new_nsproxy = NULL;
+	int do_sysvsem = 0;
 
 	check_unshare_flags(&unshare_flags);
 
@@ -1703,6 +1699,13 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
 				CLONE_NEWNET))
 		goto bad_unshare_out;
 
+	/*
+	 * CLONE_NEWIPC must also detach from the undolist: after switching
+	 * to a new ipc namespace, the semaphore arrays from the old
+	 * namespace are unreachable.
+	 */
+	if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM))
+		do_sysvsem = 1;
 	if ((err = unshare_thread(unshare_flags)))
 		goto bad_unshare_out;
 	if ((err = unshare_fs(unshare_flags, &new_fs)))
@@ -1713,13 +1716,17 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
 		goto bad_unshare_cleanup_sigh;
 	if ((err = unshare_fd(unshare_flags, &new_fd)))
 		goto bad_unshare_cleanup_vm;
-	if ((err = unshare_semundo(unshare_flags, &new_ulist)))
-		goto bad_unshare_cleanup_fd;
 	if ((err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy,
 			new_fs)))
-		goto bad_unshare_cleanup_semundo;
+		goto bad_unshare_cleanup_fd;
 
-	if (new_fs ||  new_mm || new_fd || new_ulist || new_nsproxy) {
+	if (new_fs ||  new_mm || new_fd || do_sysvsem || new_nsproxy) {
+		if (do_sysvsem) {
+			/*
+			 * CLONE_SYSVSEM is equivalent to sys_exit().
+			 */
+			exit_sem(current);
+		}
 
 		if (new_nsproxy) {
 			switch_task_namespaces(current, new_nsproxy);
@@ -1755,7 +1762,6 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
 	if (new_nsproxy)
 		put_nsproxy(new_nsproxy);
 
-bad_unshare_cleanup_semundo:
 bad_unshare_cleanup_fd:
 	if (new_fd)
 		put_files_struct(new_fd);
diff --git a/trunk/kernel/hrtimer.c b/trunk/kernel/hrtimer.c
index f78777abe769..dea4c9124ac8 100644
--- a/trunk/kernel/hrtimer.c
+++ b/trunk/kernel/hrtimer.c
@@ -590,7 +590,6 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
 			list_add_tail(&timer->cb_entry,
 				      &base->cpu_base->cb_pending);
 			timer->state = HRTIMER_STATE_PENDING;
-			raise_softirq(HRTIMER_SOFTIRQ);
 			return 1;
 		default:
 			BUG();
@@ -633,6 +632,11 @@ static int hrtimer_switch_to_hres(void)
 	return 1;
 }
 
+static inline void hrtimer_raise_softirq(void)
+{
+	raise_softirq(HRTIMER_SOFTIRQ);
+}
+
 #else
 
 static inline int hrtimer_hres_active(void) { return 0; }
@@ -651,6 +655,7 @@ static inline int hrtimer_reprogram(struct hrtimer *timer,
 {
 	return 0;
 }
+static inline void hrtimer_raise_softirq(void) { }
 
 #endif /* CONFIG_HIGH_RES_TIMERS */
 
@@ -850,7 +855,7 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 {
 	struct hrtimer_clock_base *base, *new_base;
 	unsigned long flags;
-	int ret;
+	int ret, raise;
 
 	base = lock_hrtimer_base(timer, &flags);
 
@@ -884,8 +889,18 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 	enqueue_hrtimer(timer, new_base,
 			new_base->cpu_base == &__get_cpu_var(hrtimer_bases));
 
+	/*
+	 * The timer may be expired and moved to the cb_pending
+	 * list. We can not raise the softirq with base lock held due
+	 * to a possible deadlock with runqueue lock.
+	 */
+	raise = timer->state == HRTIMER_STATE_PENDING;
+
 	unlock_hrtimer_base(timer, &flags);
 
+	if (raise)
+		hrtimer_raise_softirq();
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(hrtimer_start);
@@ -1080,8 +1095,19 @@ static void run_hrtimer_pending(struct hrtimer_cpu_base *cpu_base)
 			 * If the timer was rearmed on another CPU, reprogram
 			 * the event device.
 			 */
-			if (timer->base->first == &timer->node)
-				hrtimer_reprogram(timer, timer->base);
+			struct hrtimer_clock_base *base = timer->base;
+
+			if (base->first == &timer->node &&
+			    hrtimer_reprogram(timer, base)) {
+				/*
+				 * Timer is expired. Thus move it from tree to
+				 * pending list again.
+				 */
+				__remove_hrtimer(timer, base,
+						 HRTIMER_STATE_PENDING, 0);
+				list_add_tail(&timer->cb_entry,
+					      &base->cpu_base->cb_pending);
+			}
 		}
 	}
 	spin_unlock_irq(&cpu_base->lock);
diff --git a/trunk/kernel/irq/devres.c b/trunk/kernel/irq/devres.c
index 6d9204f3a370..38a25b8d8bff 100644
--- a/trunk/kernel/irq/devres.c
+++ b/trunk/kernel/irq/devres.c
@@ -1,6 +1,7 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/device.h>
+#include <linux/gfp.h>
 
 /*
  * Device resource management aware IRQ request/free implementation.
diff --git a/trunk/kernel/irq/manage.c b/trunk/kernel/irq/manage.c
index 438a01464287..46e4ad1723f0 100644
--- a/trunk/kernel/irq/manage.c
+++ b/trunk/kernel/irq/manage.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/interrupt.h>
+#include <linux/slab.h>
 
 #include "internals.h"
 
diff --git a/trunk/kernel/kallsyms.c b/trunk/kernel/kallsyms.c
index f091d13def00..6fc0040f3e3a 100644
--- a/trunk/kernel/kallsyms.c
+++ b/trunk/kernel/kallsyms.c
@@ -472,11 +472,7 @@ static const struct file_operations kallsyms_operations = {
 
 static int __init kallsyms_init(void)
 {
-	struct proc_dir_entry *entry;
-
-	entry = create_proc_entry("kallsyms", 0444, NULL);
-	if (entry)
-		entry->proc_fops = &kallsyms_operations;
+	proc_create("kallsyms", 0444, NULL, &kallsyms_operations);
 	return 0;
 }
 __initcall(kallsyms_init);
diff --git a/trunk/kernel/kexec.c b/trunk/kernel/kexec.c
index 6782dce93d01..cb85c79989b4 100644
--- a/trunk/kernel/kexec.c
+++ b/trunk/kernel/kexec.c
@@ -1405,6 +1405,9 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
 	VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
 	VMCOREINFO_NUMBER(NR_FREE_PAGES);
+	VMCOREINFO_NUMBER(PG_lru);
+	VMCOREINFO_NUMBER(PG_private);
+	VMCOREINFO_NUMBER(PG_swapcache);
 
 	arch_crash_save_vmcoreinfo();
 
diff --git a/trunk/kernel/kprobes.c b/trunk/kernel/kprobes.c
index fcfb580c3afc..1e0250cb9486 100644
--- a/trunk/kernel/kprobes.c
+++ b/trunk/kernel/kprobes.c
@@ -72,6 +72,18 @@ DEFINE_MUTEX(kprobe_mutex);		/* Protects kprobe_table */
 DEFINE_SPINLOCK(kretprobe_lock);	/* Protects kretprobe_inst_table */
 static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
 
+/*
+ * Normally, functions that we'd want to prohibit kprobes in, are marked
+ * __kprobes. But, there are cases where such functions already belong to
+ * a different section (__sched for preempt_schedule)
+ *
+ * For such cases, we now have a blacklist
+ */
+struct kprobe_blackpoint kprobe_blacklist[] = {
+	{"preempt_schedule",},
+	{NULL}    /* Terminator */
+};
+
 #ifdef __ARCH_WANT_KPROBES_INSN_SLOT
 /*
  * kprobe->ainsn.insn points to the copy of the instruction to be
@@ -417,6 +429,21 @@ static inline void free_rp_inst(struct kretprobe *rp)
 	}
 }
 
+static void __kprobes cleanup_rp_inst(struct kretprobe *rp)
+{
+	unsigned long flags;
+	struct kretprobe_instance *ri;
+	struct hlist_node *pos, *next;
+	/* No race here */
+	spin_lock_irqsave(&kretprobe_lock, flags);
+	hlist_for_each_entry_safe(ri, pos, next, &rp->used_instances, uflist) {
+		ri->rp = NULL;
+		hlist_del(&ri->uflist);
+	}
+	spin_unlock_irqrestore(&kretprobe_lock, flags);
+	free_rp_inst(rp);
+}
+
 /*
  * Keep all fields in the kprobe consistent
  */
@@ -492,9 +519,22 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
 
 static int __kprobes in_kprobes_functions(unsigned long addr)
 {
+	struct kprobe_blackpoint *kb;
+
 	if (addr >= (unsigned long)__kprobes_text_start &&
 	    addr < (unsigned long)__kprobes_text_end)
 		return -EINVAL;
+	/*
+	 * If there exists a kprobe_blacklist, verify and
+	 * fail any probe registration in the prohibited area
+	 */
+	for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
+		if (kb->start_addr) {
+			if (addr >= kb->start_addr &&
+			    addr < (kb->start_addr + kb->range))
+				return -EINVAL;
+		}
+	}
 	return 0;
 }
 
@@ -555,6 +595,7 @@ static int __kprobes __register_kprobe(struct kprobe *p,
 	}
 
 	p->nmissed = 0;
+	INIT_LIST_HEAD(&p->list);
 	mutex_lock(&kprobe_mutex);
 	old_p = get_kprobe(p->addr);
 	if (old_p) {
@@ -581,35 +622,28 @@ static int __kprobes __register_kprobe(struct kprobe *p,
 	return ret;
 }
 
-int __kprobes register_kprobe(struct kprobe *p)
-{
-	return __register_kprobe(p, (unsigned long)__builtin_return_address(0));
-}
-
-void __kprobes unregister_kprobe(struct kprobe *p)
+/*
+ * Unregister a kprobe without a scheduler synchronization.
+ */
+static int __kprobes __unregister_kprobe_top(struct kprobe *p)
 {
-	struct module *mod;
 	struct kprobe *old_p, *list_p;
-	int cleanup_p;
 
-	mutex_lock(&kprobe_mutex);
 	old_p = get_kprobe(p->addr);
-	if (unlikely(!old_p)) {
-		mutex_unlock(&kprobe_mutex);
-		return;
-	}
+	if (unlikely(!old_p))
+		return -EINVAL;
+
 	if (p != old_p) {
 		list_for_each_entry_rcu(list_p, &old_p->list, list)
 			if (list_p == p)
 			/* kprobe p is a valid probe */
 				goto valid_p;
-		mutex_unlock(&kprobe_mutex);
-		return;
+		return -EINVAL;
 	}
 valid_p:
 	if (old_p == p ||
 	    (old_p->pre_handler == aggr_pre_handler &&
-	     p->list.next == &old_p->list && p->list.prev == &old_p->list)) {
+	     list_is_singular(&old_p->list))) {
 		/*
 		 * Only probe on the hash list. Disarm only if kprobes are
 		 * enabled - otherwise, the breakpoint would already have
@@ -618,43 +652,97 @@ void __kprobes unregister_kprobe(struct kprobe *p)
 		if (kprobe_enabled)
 			arch_disarm_kprobe(p);
 		hlist_del_rcu(&old_p->hlist);
-		cleanup_p = 1;
 	} else {
+		if (p->break_handler)
+			old_p->break_handler = NULL;
+		if (p->post_handler) {
+			list_for_each_entry_rcu(list_p, &old_p->list, list) {
+				if ((list_p != p) && (list_p->post_handler))
+					goto noclean;
+			}
+			old_p->post_handler = NULL;
+		}
+noclean:
 		list_del_rcu(&p->list);
-		cleanup_p = 0;
 	}
+	return 0;
+}
 
-	mutex_unlock(&kprobe_mutex);
+static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
+{
+	struct module *mod;
+	struct kprobe *old_p;
 
-	synchronize_sched();
 	if (p->mod_refcounted) {
 		mod = module_text_address((unsigned long)p->addr);
 		if (mod)
 			module_put(mod);
 	}
 
-	if (cleanup_p) {
-		if (p != old_p) {
-			list_del_rcu(&p->list);
+	if (list_empty(&p->list) || list_is_singular(&p->list)) {
+		if (!list_empty(&p->list)) {
+			/* "p" is the last child of an aggr_kprobe */
+			old_p = list_entry(p->list.next, struct kprobe, list);
+			list_del(&p->list);
 			kfree(old_p);
 		}
 		arch_remove_kprobe(p);
-	} else {
-		mutex_lock(&kprobe_mutex);
-		if (p->break_handler)
-			old_p->break_handler = NULL;
-		if (p->post_handler){
-			list_for_each_entry_rcu(list_p, &old_p->list, list){
-				if (list_p->post_handler){
-					cleanup_p = 2;
-					break;
-				}
-			}
-			if (cleanup_p == 0)
-				old_p->post_handler = NULL;
+	}
+}
+
+static int __register_kprobes(struct kprobe **kps, int num,
+	unsigned long called_from)
+{
+	int i, ret = 0;
+
+	if (num <= 0)
+		return -EINVAL;
+	for (i = 0; i < num; i++) {
+		ret = __register_kprobe(kps[i], called_from);
+		if (ret < 0 && i > 0) {
+			unregister_kprobes(kps, i);
+			break;
 		}
-		mutex_unlock(&kprobe_mutex);
 	}
+	return ret;
+}
+
+/*
+ * Registration and unregistration functions for kprobe.
+ */
+int __kprobes register_kprobe(struct kprobe *p)
+{
+	return __register_kprobes(&p, 1,
+				  (unsigned long)__builtin_return_address(0));
+}
+
+void __kprobes unregister_kprobe(struct kprobe *p)
+{
+	unregister_kprobes(&p, 1);
+}
+
+int __kprobes register_kprobes(struct kprobe **kps, int num)
+{
+	return __register_kprobes(kps, num,
+				  (unsigned long)__builtin_return_address(0));
+}
+
+void __kprobes unregister_kprobes(struct kprobe **kps, int num)
+{
+	int i;
+
+	if (num <= 0)
+		return;
+	mutex_lock(&kprobe_mutex);
+	for (i = 0; i < num; i++)
+		if (__unregister_kprobe_top(kps[i]) < 0)
+			kps[i]->addr = NULL;
+	mutex_unlock(&kprobe_mutex);
+
+	synchronize_sched();
+	for (i = 0; i < num; i++)
+		if (kps[i]->addr)
+			__unregister_kprobe_bottom(kps[i]);
 }
 
 static struct notifier_block kprobe_exceptions_nb = {
@@ -667,24 +755,69 @@ unsigned long __weak arch_deref_entry_point(void *entry)
 	return (unsigned long)entry;
 }
 
-int __kprobes register_jprobe(struct jprobe *jp)
+static int __register_jprobes(struct jprobe **jps, int num,
+	unsigned long called_from)
 {
-	unsigned long addr = arch_deref_entry_point(jp->entry);
+	struct jprobe *jp;
+	int ret = 0, i;
 
-	if (!kernel_text_address(addr))
+	if (num <= 0)
 		return -EINVAL;
+	for (i = 0; i < num; i++) {
+		unsigned long addr;
+		jp = jps[i];
+		addr = arch_deref_entry_point(jp->entry);
+
+		if (!kernel_text_address(addr))
+			ret = -EINVAL;
+		else {
+			/* Todo: Verify probepoint is a function entry point */
+			jp->kp.pre_handler = setjmp_pre_handler;
+			jp->kp.break_handler = longjmp_break_handler;
+			ret = __register_kprobe(&jp->kp, called_from);
+		}
+		if (ret < 0 && i > 0) {
+			unregister_jprobes(jps, i);
+			break;
+		}
+	}
+	return ret;
+}
 
-	/* Todo: Verify probepoint is a function entry point */
-	jp->kp.pre_handler = setjmp_pre_handler;
-	jp->kp.break_handler = longjmp_break_handler;
-
-	return __register_kprobe(&jp->kp,
+int __kprobes register_jprobe(struct jprobe *jp)
+{
+	return __register_jprobes(&jp, 1,
 		(unsigned long)__builtin_return_address(0));
 }
 
 void __kprobes unregister_jprobe(struct jprobe *jp)
 {
-	unregister_kprobe(&jp->kp);
+	unregister_jprobes(&jp, 1);
+}
+
+int __kprobes register_jprobes(struct jprobe **jps, int num)
+{
+	return __register_jprobes(jps, num,
+		(unsigned long)__builtin_return_address(0));
+}
+
+void __kprobes unregister_jprobes(struct jprobe **jps, int num)
+{
+	int i;
+
+	if (num <= 0)
+		return;
+	mutex_lock(&kprobe_mutex);
+	for (i = 0; i < num; i++)
+		if (__unregister_kprobe_top(&jps[i]->kp) < 0)
+			jps[i]->kp.addr = NULL;
+	mutex_unlock(&kprobe_mutex);
+
+	synchronize_sched();
+	for (i = 0; i < num; i++) {
+		if (jps[i]->kp.addr)
+			__unregister_kprobe_bottom(&jps[i]->kp);
+	}
 }
 
 #ifdef CONFIG_KRETPROBES
@@ -725,7 +858,8 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p,
 	return 0;
 }
 
-int __kprobes register_kretprobe(struct kretprobe *rp)
+static int __kprobes __register_kretprobe(struct kretprobe *rp,
+					  unsigned long called_from)
 {
 	int ret = 0;
 	struct kretprobe_instance *inst;
@@ -771,46 +905,101 @@ int __kprobes register_kretprobe(struct kretprobe *rp)
 
 	rp->nmissed = 0;
 	/* Establish function entry probe point */
-	if ((ret = __register_kprobe(&rp->kp,
-		(unsigned long)__builtin_return_address(0))) != 0)
+	ret = __register_kprobe(&rp->kp, called_from);
+	if (ret != 0)
 		free_rp_inst(rp);
 	return ret;
 }
 
+static int __register_kretprobes(struct kretprobe **rps, int num,
+	unsigned long called_from)
+{
+	int ret = 0, i;
+
+	if (num <= 0)
+		return -EINVAL;
+	for (i = 0; i < num; i++) {
+		ret = __register_kretprobe(rps[i], called_from);
+		if (ret < 0 && i > 0) {
+			unregister_kretprobes(rps, i);
+			break;
+		}
+	}
+	return ret;
+}
+
+int __kprobes register_kretprobe(struct kretprobe *rp)
+{
+	return __register_kretprobes(&rp, 1,
+			(unsigned long)__builtin_return_address(0));
+}
+
+void __kprobes unregister_kretprobe(struct kretprobe *rp)
+{
+	unregister_kretprobes(&rp, 1);
+}
+
+int __kprobes register_kretprobes(struct kretprobe **rps, int num)
+{
+	return __register_kretprobes(rps, num,
+			(unsigned long)__builtin_return_address(0));
+}
+
+void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
+{
+	int i;
+
+	if (num <= 0)
+		return;
+	mutex_lock(&kprobe_mutex);
+	for (i = 0; i < num; i++)
+		if (__unregister_kprobe_top(&rps[i]->kp) < 0)
+			rps[i]->kp.addr = NULL;
+	mutex_unlock(&kprobe_mutex);
+
+	synchronize_sched();
+	for (i = 0; i < num; i++) {
+		if (rps[i]->kp.addr) {
+			__unregister_kprobe_bottom(&rps[i]->kp);
+			cleanup_rp_inst(rps[i]);
+		}
+	}
+}
+
 #else /* CONFIG_KRETPROBES */
 int __kprobes register_kretprobe(struct kretprobe *rp)
 {
 	return -ENOSYS;
 }
 
-static int __kprobes pre_handler_kretprobe(struct kprobe *p,
-					   struct pt_regs *regs)
+int __kprobes register_kretprobes(struct kretprobe **rps, int num)
 {
-	return 0;
+	return -ENOSYS;
 }
-#endif /* CONFIG_KRETPROBES */
-
 void __kprobes unregister_kretprobe(struct kretprobe *rp)
 {
-	unsigned long flags;
-	struct kretprobe_instance *ri;
-	struct hlist_node *pos, *next;
+}
 
-	unregister_kprobe(&rp->kp);
+void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
+{
+}
 
-	/* No race here */
-	spin_lock_irqsave(&kretprobe_lock, flags);
-	hlist_for_each_entry_safe(ri, pos, next, &rp->used_instances, uflist) {
-		ri->rp = NULL;
-		hlist_del(&ri->uflist);
-	}
-	spin_unlock_irqrestore(&kretprobe_lock, flags);
-	free_rp_inst(rp);
+static int __kprobes pre_handler_kretprobe(struct kprobe *p,
+					   struct pt_regs *regs)
+{
+	return 0;
 }
 
+#endif /* CONFIG_KRETPROBES */
+
 static int __init init_kprobes(void)
 {
 	int i, err = 0;
+	unsigned long offset = 0, size = 0;
+	char *modname, namebuf[128];
+	const char *symbol_name;
+	void *addr;
+	struct kprobe_blackpoint *kb;
 
 	/* FIXME allocate the probe table, currently defined statically */
 	/* initialize all list heads */
@@ -819,6 +1008,28 @@ static int __init init_kprobes(void)
 		INIT_HLIST_HEAD(&kretprobe_inst_table[i]);
 	}
 
+	/*
+	 * Lookup and populate the kprobe_blacklist.
+	 *
+	 * Unlike the kretprobe blacklist, we'll need to determine
+	 * the range of addresses that belong to the said functions,
+	 * since a kprobe need not necessarily be at the beginning
+	 * of a function.
+	 */
+	for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
+		kprobe_lookup_name(kb->name, addr);
+		if (!addr)
+			continue;
+
+		kb->start_addr = (unsigned long)addr;
+		symbol_name = kallsyms_lookup(kb->start_addr,
+				&size, &offset, &modname, namebuf);
+		if (!symbol_name)
+			kb->range = 0;
+		else
+			kb->range = size;
+	}
+
 	if (kretprobe_blacklist_size) {
 		/* lookup the function address from its name */
 		for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
@@ -1066,8 +1277,12 @@ module_init(init_kprobes);
 
 EXPORT_SYMBOL_GPL(register_kprobe);
 EXPORT_SYMBOL_GPL(unregister_kprobe);
+EXPORT_SYMBOL_GPL(register_kprobes);
+EXPORT_SYMBOL_GPL(unregister_kprobes);
 EXPORT_SYMBOL_GPL(register_jprobe);
 EXPORT_SYMBOL_GPL(unregister_jprobe);
+EXPORT_SYMBOL_GPL(register_jprobes);
+EXPORT_SYMBOL_GPL(unregister_jprobes);
 #ifdef CONFIG_KPROBES
 EXPORT_SYMBOL_GPL(jprobe_return);
 #endif
@@ -1075,4 +1290,6 @@ EXPORT_SYMBOL_GPL(jprobe_return);
 #ifdef CONFIG_KPROBES
 EXPORT_SYMBOL_GPL(register_kretprobe);
 EXPORT_SYMBOL_GPL(unregister_kretprobe);
+EXPORT_SYMBOL_GPL(register_kretprobes);
+EXPORT_SYMBOL_GPL(unregister_kretprobes);
 #endif
diff --git a/trunk/kernel/kthread.c b/trunk/kernel/kthread.c
index 92cf6930ab51..ac72eea48339 100644
--- a/trunk/kernel/kthread.c
+++ b/trunk/kernel/kthread.c
@@ -144,9 +144,9 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
 
 	spin_lock(&kthread_create_lock);
 	list_add_tail(&create.list, &kthread_create_list);
-	wake_up_process(kthreadd_task);
 	spin_unlock(&kthread_create_lock);
 
+	wake_up_process(kthreadd_task);
 	wait_for_completion(&create.done);
 
 	if (!IS_ERR(create.result)) {
diff --git a/trunk/kernel/latencytop.c b/trunk/kernel/latencytop.c
index 7c74dab0d21b..5e7b45c56923 100644
--- a/trunk/kernel/latencytop.c
+++ b/trunk/kernel/latencytop.c
@@ -233,14 +233,7 @@ static struct file_operations lstats_fops = {
 
 static int __init init_lstats_procfs(void)
 {
-	struct proc_dir_entry *pe;
-
-	pe = create_proc_entry("latency_stats", 0644, NULL);
-	if (!pe)
-		return -ENOMEM;
-
-	pe->proc_fops = &lstats_fops;
-
+	proc_create("latency_stats", 0644, NULL, &lstats_fops);
 	return 0;
 }
 __initcall(init_lstats_procfs);
diff --git a/trunk/kernel/lockdep_proc.c b/trunk/kernel/lockdep_proc.c
index 8a135bd163c2..dc5d29648d85 100644
--- a/trunk/kernel/lockdep_proc.c
+++ b/trunk/kernel/lockdep_proc.c
@@ -660,20 +660,12 @@ static const struct file_operations proc_lock_stat_operations = {
 
 static int __init lockdep_proc_init(void)
 {
-	struct proc_dir_entry *entry;
-
-	entry = create_proc_entry("lockdep", S_IRUSR, NULL);
-	if (entry)
-		entry->proc_fops = &proc_lockdep_operations;
-
-	entry = create_proc_entry("lockdep_stats", S_IRUSR, NULL);
-	if (entry)
-		entry->proc_fops = &proc_lockdep_stats_operations;
+	proc_create("lockdep", S_IRUSR, NULL, &proc_lockdep_operations);
+	proc_create("lockdep_stats", S_IRUSR, NULL,
+		    &proc_lockdep_stats_operations);
 
 #ifdef CONFIG_LOCK_STAT
-	entry = create_proc_entry("lock_stat", S_IRUSR, NULL);
-	if (entry)
-		entry->proc_fops = &proc_lock_stat_operations;
+	proc_create("lock_stat", S_IRUSR, NULL, &proc_lock_stat_operations);
 #endif
 
 	return 0;
diff --git a/trunk/kernel/marker.c b/trunk/kernel/marker.c
index 005b95954593..139260e5460c 100644
--- a/trunk/kernel/marker.c
+++ b/trunk/kernel/marker.c
@@ -23,6 +23,7 @@
 #include <linux/rcupdate.h>
 #include <linux/marker.h>
 #include <linux/err.h>
+#include <linux/slab.h>
 
 extern struct marker __start___markers[];
 extern struct marker __stop___markers[];
diff --git a/trunk/kernel/notifier.c b/trunk/kernel/notifier.c
index 643360d1bb14..823be11584ef 100644
--- a/trunk/kernel/notifier.c
+++ b/trunk/kernel/notifier.c
@@ -31,6 +31,21 @@ static int notifier_chain_register(struct notifier_block **nl,
 	return 0;
 }
 
+static int notifier_chain_cond_register(struct notifier_block **nl,
+		struct notifier_block *n)
+{
+	while ((*nl) != NULL) {
+		if ((*nl) == n)
+			return 0;
+		if (n->priority > (*nl)->priority)
+			break;
+		nl = &((*nl)->next);
+	}
+	n->next = *nl;
+	rcu_assign_pointer(*nl, n);
+	return 0;
+}
+
 static int notifier_chain_unregister(struct notifier_block **nl,
 		struct notifier_block *n)
 {
@@ -204,6 +219,29 @@ int blocking_notifier_chain_register(struct blocking_notifier_head *nh,
 }
 EXPORT_SYMBOL_GPL(blocking_notifier_chain_register);
 
+/**
+ *	blocking_notifier_chain_cond_register - Cond add notifier to a blocking notifier chain
+ *	@nh: Pointer to head of the blocking notifier chain
+ *	@n: New entry in notifier chain
+ *
+ *	Adds a notifier to a blocking notifier chain, only if not already
+ *	present in the chain.
+ *	Must be called in process context.
+ *
+ *	Currently always returns zero.
+ */
+int blocking_notifier_chain_cond_register(struct blocking_notifier_head *nh,
+		struct notifier_block *n)
+{
+	int ret;
+
+	down_write(&nh->rwsem);
+	ret = notifier_chain_cond_register(&nh->head, n);
+	up_write(&nh->rwsem);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blocking_notifier_chain_cond_register);
+
 /**
  *	blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain
  *	@nh: Pointer to head of the blocking notifier chain
diff --git a/trunk/kernel/ns_cgroup.c b/trunk/kernel/ns_cgroup.c
index aead4d69f62b..48d7ed6fc3a4 100644
--- a/trunk/kernel/ns_cgroup.c
+++ b/trunk/kernel/ns_cgroup.c
@@ -7,6 +7,8 @@
 #include <linux/module.h>
 #include <linux/cgroup.h>
 #include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/nsproxy.h>
 
 struct ns_cgroup {
 	struct cgroup_subsys_state css;
diff --git a/trunk/kernel/nsproxy.c b/trunk/kernel/nsproxy.c
index f5d332cf8c63..adc785146a1c 100644
--- a/trunk/kernel/nsproxy.c
+++ b/trunk/kernel/nsproxy.c
@@ -139,6 +139,18 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 		goto out;
 	}
 
+	/*
+	 * CLONE_NEWIPC must detach from the undolist: after switching
+	 * to a new ipc namespace, the semaphore arrays from the old
+	 * namespace are unreachable.  In clone parlance, CLONE_SYSVSEM
+	 * means share undolist with parent, so we must forbid using
+	 * it along with CLONE_NEWIPC.
+	 */
+	if ((flags & CLONE_NEWIPC) && (flags & CLONE_SYSVSEM)) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	new_ns = create_new_namespaces(flags, tsk, tsk->fs);
 	if (IS_ERR(new_ns)) {
 		err = PTR_ERR(new_ns);
diff --git a/trunk/kernel/panic.c b/trunk/kernel/panic.c
index 24af9f8bac99..425567f45b9f 100644
--- a/trunk/kernel/panic.c
+++ b/trunk/kernel/panic.c
@@ -153,6 +153,8 @@ EXPORT_SYMBOL(panic);
  *  'M' - System experienced a machine check exception.
  *  'B' - System has hit bad_page.
  *  'U' - Userspace-defined naughtiness.
+ *  'A' - ACPI table overridden.
+ *  'W' - Taint on warning.
  *
  *	The string is overwritten by the next call to print_taint().
  */
@@ -161,7 +163,7 @@ const char *print_tainted(void)
 {
 	static char buf[20];
 	if (tainted) {
-		snprintf(buf, sizeof(buf), "Tainted: %c%c%c%c%c%c%c%c%c",
+		snprintf(buf, sizeof(buf), "Tainted: %c%c%c%c%c%c%c%c%c%c",
 			tainted & TAINT_PROPRIETARY_MODULE ? 'P' : 'G',
 			tainted & TAINT_FORCED_MODULE ? 'F' : ' ',
 			tainted & TAINT_UNSAFE_SMP ? 'S' : ' ',
@@ -170,7 +172,8 @@ const char *print_tainted(void)
 			tainted & TAINT_BAD_PAGE ? 'B' : ' ',
 			tainted & TAINT_USER ? 'U' : ' ',
 			tainted & TAINT_DIE ? 'D' : ' ',
-			tainted & TAINT_OVERRIDDEN_ACPI_TABLE ? 'A' : ' ');
+			tainted & TAINT_OVERRIDDEN_ACPI_TABLE ? 'A' : ' ',
+			tainted & TAINT_WARN ? 'W' : ' ');
 	}
 	else
 		snprintf(buf, sizeof(buf), "Not tainted");
@@ -312,6 +315,7 @@ void warn_on_slowpath(const char *file, int line)
 	print_modules();
 	dump_stack();
 	print_oops_end_marker();
+	add_taint(TAINT_WARN);
 }
 EXPORT_SYMBOL(warn_on_slowpath);
 #endif
diff --git a/trunk/kernel/pid_namespace.c b/trunk/kernel/pid_namespace.c
index 6d792b66d854..5ca37fa50beb 100644
--- a/trunk/kernel/pid_namespace.c
+++ b/trunk/kernel/pid_namespace.c
@@ -92,7 +92,7 @@ static struct pid_namespace *create_pid_namespace(int level)
 	atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
 
 	for (i = 1; i < PIDMAP_ENTRIES; i++) {
-		ns->pidmap[i].page = 0;
+		ns->pidmap[i].page = NULL;
 		atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
 	}
 
diff --git a/trunk/kernel/power/console.c b/trunk/kernel/power/console.c
index 89bcf4973ee5..b8628be2a465 100644
--- a/trunk/kernel/power/console.c
+++ b/trunk/kernel/power/console.c
@@ -7,17 +7,39 @@
 #include <linux/vt_kern.h>
 #include <linux/kbd_kern.h>
 #include <linux/console.h>
+#include <linux/module.h>
 #include "power.h"
 
 #if defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE)
 #define SUSPEND_CONSOLE	(MAX_NR_CONSOLES-1)
 
 static int orig_fgconsole, orig_kmsg;
+static int disable_vt_switch;
+
+/*
+ * Normally during a suspend, we allocate a new console and switch to it.
+ * When we resume, we switch back to the original console.  This switch
+ * can be slow, so on systems where the framebuffer can handle restoration
+ * of video registers anyways, there's little point in doing the console
+ * switch.  This function allows you to disable it by passing it '0'.
+ */
+void pm_set_vt_switch(int do_switch)
+{
+	acquire_console_sem();
+	disable_vt_switch = !do_switch;
+	release_console_sem();
+}
+EXPORT_SYMBOL(pm_set_vt_switch);
 
 int pm_prepare_console(void)
 {
 	acquire_console_sem();
 
+	if (disable_vt_switch) {
+		release_console_sem();
+		return 0;
+	}
+
 	orig_fgconsole = fg_console;
 
 	if (vc_allocate(SUSPEND_CONSOLE)) {
@@ -50,9 +72,12 @@ int pm_prepare_console(void)
 void pm_restore_console(void)
 {
 	acquire_console_sem();
+	if (disable_vt_switch) {
+		release_console_sem();
+		return;
+	}
 	set_console(orig_fgconsole);
 	release_console_sem();
 	kmsg_redirect = orig_kmsg;
-	return;
 }
 #endif
diff --git a/trunk/kernel/printk.c b/trunk/kernel/printk.c
index bdd4ea8c3f2b..d3f9c0f788bf 100644
--- a/trunk/kernel/printk.c
+++ b/trunk/kernel/printk.c
@@ -1287,31 +1287,7 @@ void tty_write_message(struct tty_struct *tty, char *msg)
  */
 int __printk_ratelimit(int ratelimit_jiffies, int ratelimit_burst)
 {
-	static DEFINE_SPINLOCK(ratelimit_lock);
-	static unsigned toks = 10 * 5 * HZ;
-	static unsigned long last_msg;
-	static int missed;
-	unsigned long flags;
-	unsigned long now = jiffies;
-
-	spin_lock_irqsave(&ratelimit_lock, flags);
-	toks += now - last_msg;
-	last_msg = now;
-	if (toks > (ratelimit_burst * ratelimit_jiffies))
-		toks = ratelimit_burst * ratelimit_jiffies;
-	if (toks >= ratelimit_jiffies) {
-		int lost = missed;
-
-		missed = 0;
-		toks -= ratelimit_jiffies;
-		spin_unlock_irqrestore(&ratelimit_lock, flags);
-		if (lost)
-			printk(KERN_WARNING "printk: %d messages suppressed.\n", lost);
-		return 1;
-	}
-	missed++;
-	spin_unlock_irqrestore(&ratelimit_lock, flags);
-	return 0;
+	return __ratelimit(ratelimit_jiffies, ratelimit_burst);
 }
 EXPORT_SYMBOL(__printk_ratelimit);
 
diff --git a/trunk/kernel/profile.c b/trunk/kernel/profile.c
index 606d7387265c..ae7ead82cbc9 100644
--- a/trunk/kernel/profile.c
+++ b/trunk/kernel/profile.c
@@ -587,10 +587,10 @@ static int __init create_proc_profile(void)
 		return 0;
 	if (create_hash_tables())
 		return -1;
-	entry = create_proc_entry("profile", S_IWUSR | S_IRUGO, NULL);
+	entry = proc_create("profile", S_IWUSR | S_IRUGO,
+			    NULL, &proc_profile_operations);
 	if (!entry)
 		return 0;
-	entry->proc_fops = &proc_profile_operations;
 	entry->size = (1+prof_len) * sizeof(atomic_t);
 	hotcpu_notifier(profile_cpu_callback, 0);
 	return 0;
diff --git a/trunk/kernel/ptrace.c b/trunk/kernel/ptrace.c
index 67e392ed5496..dac4b4e57293 100644
--- a/trunk/kernel/ptrace.c
+++ b/trunk/kernel/ptrace.c
@@ -612,7 +612,7 @@ int generic_ptrace_pokedata(struct task_struct *tsk, long addr, long data)
 	return (copied == sizeof(data)) ? 0 : -EIO;
 }
 
-#ifdef CONFIG_COMPAT
+#if defined CONFIG_COMPAT && defined __ARCH_WANT_COMPAT_SYS_PTRACE
 #include <linux/compat.h>
 
 int compat_ptrace_request(struct task_struct *child, compat_long_t request,
@@ -667,7 +667,6 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
 	return ret;
 }
 
-#ifdef __ARCH_WANT_COMPAT_SYS_PTRACE
 asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 				  compat_long_t addr, compat_long_t data)
 {
@@ -710,6 +709,4 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 	unlock_kernel();
 	return ret;
 }
-#endif /* __ARCH_WANT_COMPAT_SYS_PTRACE */
-
-#endif	/* CONFIG_COMPAT */
+#endif	/* CONFIG_COMPAT && __ARCH_WANT_COMPAT_SYS_PTRACE */
diff --git a/trunk/kernel/rcutorture.c b/trunk/kernel/rcutorture.c
index 47894f919d4e..33acc424667e 100644
--- a/trunk/kernel/rcutorture.c
+++ b/trunk/kernel/rcutorture.c
@@ -45,6 +45,7 @@
 #include <linux/byteorder/swabb.h>
 #include <linux/stat.h>
 #include <linux/srcu.h>
+#include <linux/slab.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and "
diff --git a/trunk/kernel/relay.c b/trunk/kernel/relay.c
index d6204a485818..7de644cdec43 100644
--- a/trunk/kernel/relay.c
+++ b/trunk/kernel/relay.c
@@ -65,6 +65,35 @@ static struct vm_operations_struct relay_file_mmap_ops = {
 	.close = relay_file_mmap_close,
 };
 
+/*
+ * allocate an array of pointers of struct page
+ */
+static struct page **relay_alloc_page_array(unsigned int n_pages)
+{
+	struct page **array;
+	size_t pa_size = n_pages * sizeof(struct page *);
+
+	if (pa_size > PAGE_SIZE) {
+		array = vmalloc(pa_size);
+		if (array)
+			memset(array, 0, pa_size);
+	} else {
+		array = kzalloc(pa_size, GFP_KERNEL);
+	}
+	return array;
+}
+
+/*
+ * free an array of pointers of struct page
+ */
+static void relay_free_page_array(struct page **array)
+{
+	if (is_vmalloc_addr(array))
+		vfree(array);
+	else
+		kfree(array);
+}
+
 /**
  *	relay_mmap_buf: - mmap channel buffer to process address space
  *	@buf: relay channel buffer
@@ -109,7 +138,7 @@ static void *relay_alloc_buf(struct rchan_buf *buf, size_t *size)
 	*size = PAGE_ALIGN(*size);
 	n_pages = *size >> PAGE_SHIFT;
 
-	buf->page_array = kcalloc(n_pages, sizeof(struct page *), GFP_KERNEL);
+	buf->page_array = relay_alloc_page_array(n_pages);
 	if (!buf->page_array)
 		return NULL;
 
@@ -130,7 +159,7 @@ static void *relay_alloc_buf(struct rchan_buf *buf, size_t *size)
 depopulate:
 	for (j = 0; j < i; j++)
 		__free_page(buf->page_array[j]);
-	kfree(buf->page_array);
+	relay_free_page_array(buf->page_array);
 	return NULL;
 }
 
@@ -189,7 +218,7 @@ static void relay_destroy_buf(struct rchan_buf *buf)
 		vunmap(buf->start);
 		for (i = 0; i < buf->page_count; i++)
 			__free_page(buf->page_array[i]);
-		kfree(buf->page_array);
+		relay_free_page_array(buf->page_array);
 	}
 	chan->buf[buf->cpu] = NULL;
 	kfree(buf->padding);
@@ -1162,7 +1191,7 @@ static ssize_t relay_file_splice_read(struct file *in,
 	ret = 0;
 	spliced = 0;
 
-	while (len) {
+	while (len && !spliced) {
 		ret = subbuf_splice_actor(in, ppos, pipe, len, flags, &nonpad_ret);
 		if (ret < 0)
 			break;
diff --git a/trunk/kernel/res_counter.c b/trunk/kernel/res_counter.c
index efbfc0fc232f..d3c61b4ebef2 100644
--- a/trunk/kernel/res_counter.c
+++ b/trunk/kernel/res_counter.c
@@ -10,6 +10,7 @@
 #include <linux/types.h>
 #include <linux/parser.h>
 #include <linux/fs.h>
+#include <linux/slab.h>
 #include <linux/res_counter.h>
 #include <linux/uaccess.h>
 
@@ -27,6 +28,8 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
 	}
 
 	counter->usage += val;
+	if (counter->usage > counter->max_usage)
+		counter->max_usage = counter->usage;
 	return 0;
 }
 
@@ -65,6 +68,8 @@ res_counter_member(struct res_counter *counter, int member)
 	switch (member) {
 	case RES_USAGE:
 		return &counter->usage;
+	case RES_MAX_USAGE:
+		return &counter->max_usage;
 	case RES_LIMIT:
 		return &counter->limit;
 	case RES_FAILCNT:
@@ -92,6 +97,11 @@ ssize_t res_counter_read(struct res_counter *counter, int member,
 			pos, buf, s - buf);
 }
 
+u64 res_counter_read_u64(struct res_counter *counter, int member)
+{
+	return *res_counter_member(counter, member);
+}
+
 ssize_t res_counter_write(struct res_counter *counter, int member,
 		const char __user *userbuf, size_t nbytes, loff_t *pos,
 		int (*write_strategy)(char *st_buf, unsigned long long *val))
diff --git a/trunk/kernel/resource.c b/trunk/kernel/resource.c
index cee12cc47cab..74af2d7cb5a1 100644
--- a/trunk/kernel/resource.c
+++ b/trunk/kernel/resource.c
@@ -131,14 +131,8 @@ static const struct file_operations proc_iomem_operations = {
 
 static int __init ioresources_init(void)
 {
-	struct proc_dir_entry *entry;
-
-	entry = create_proc_entry("ioports", 0, NULL);
-	if (entry)
-		entry->proc_fops = &proc_ioports_operations;
-	entry = create_proc_entry("iomem", 0, NULL);
-	if (entry)
-		entry->proc_fops = &proc_iomem_operations;
+	proc_create("ioports", 0, NULL, &proc_ioports_operations);
+	proc_create("iomem", 0, NULL, &proc_iomem_operations);
 	return 0;
 }
 __initcall(ioresources_init);
diff --git a/trunk/kernel/sched.c b/trunk/kernel/sched.c
index 740fb409e5bb..e2f7f5acc807 100644
--- a/trunk/kernel/sched.c
+++ b/trunk/kernel/sched.c
@@ -9057,13 +9057,13 @@ cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static int cpu_shares_write_uint(struct cgroup *cgrp, struct cftype *cftype,
+static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype,
 				u64 shareval)
 {
 	return sched_group_set_shares(cgroup_tg(cgrp), shareval);
 }
 
-static u64 cpu_shares_read_uint(struct cgroup *cgrp, struct cftype *cft)
+static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft)
 {
 	struct task_group *tg = cgroup_tg(cgrp);
 
@@ -9073,48 +9073,14 @@ static u64 cpu_shares_read_uint(struct cgroup *cgrp, struct cftype *cft)
 
 #ifdef CONFIG_RT_GROUP_SCHED
 static ssize_t cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft,
-				struct file *file,
-				const char __user *userbuf,
-				size_t nbytes, loff_t *unused_ppos)
+				s64 val)
 {
-	char buffer[64];
-	int retval = 0;
-	s64 val;
-	char *end;
-
-	if (!nbytes)
-		return -EINVAL;
-	if (nbytes >= sizeof(buffer))
-		return -E2BIG;
-	if (copy_from_user(buffer, userbuf, nbytes))
-		return -EFAULT;
-
-	buffer[nbytes] = 0;     /* nul-terminate */
-
-	/* strip newline if necessary */
-	if (nbytes && (buffer[nbytes-1] == '\n'))
-		buffer[nbytes-1] = 0;
-	val = simple_strtoll(buffer, &end, 0);
-	if (*end)
-		return -EINVAL;
-
-	/* Pass to subsystem */
-	retval = sched_group_set_rt_runtime(cgroup_tg(cgrp), val);
-	if (!retval)
-		retval = nbytes;
-	return retval;
+	return sched_group_set_rt_runtime(cgroup_tg(cgrp), val);
 }
 
-static ssize_t cpu_rt_runtime_read(struct cgroup *cgrp, struct cftype *cft,
-				   struct file *file,
-				   char __user *buf, size_t nbytes,
-				   loff_t *ppos)
+static s64 cpu_rt_runtime_read(struct cgroup *cgrp, struct cftype *cft)
 {
-	char tmp[64];
-	long val = sched_group_rt_runtime(cgroup_tg(cgrp));
-	int len = sprintf(tmp, "%ld\n", val);
-
-	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
+	return sched_group_rt_runtime(cgroup_tg(cgrp));
 }
 
 static int cpu_rt_period_write_uint(struct cgroup *cgrp, struct cftype *cftype,
@@ -9133,20 +9099,20 @@ static struct cftype cpu_files[] = {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	{
 		.name = "shares",
-		.read_uint = cpu_shares_read_uint,
-		.write_uint = cpu_shares_write_uint,
+		.read_u64 = cpu_shares_read_u64,
+		.write_u64 = cpu_shares_write_u64,
 	},
 #endif
 #ifdef CONFIG_RT_GROUP_SCHED
 	{
 		.name = "rt_runtime_us",
-		.read = cpu_rt_runtime_read,
-		.write = cpu_rt_runtime_write,
+		.read_s64 = cpu_rt_runtime_read,
+		.write_s64 = cpu_rt_runtime_write,
 	},
 	{
 		.name = "rt_period_us",
-		.read_uint = cpu_rt_period_read_uint,
-		.write_uint = cpu_rt_period_write_uint,
+		.read_u64 = cpu_rt_period_read_uint,
+		.write_u64 = cpu_rt_period_write_uint,
 	},
 #endif
 };
@@ -9277,8 +9243,8 @@ static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
 static struct cftype files[] = {
 	{
 		.name = "usage",
-		.read_uint = cpuusage_read,
-		.write_uint = cpuusage_write,
+		.read_u64 = cpuusage_read,
+		.write_u64 = cpuusage_write,
 	},
 };
 
diff --git a/trunk/kernel/sched_debug.c b/trunk/kernel/sched_debug.c
index f3f4af4b8b0f..8a9498e7c831 100644
--- a/trunk/kernel/sched_debug.c
+++ b/trunk/kernel/sched_debug.c
@@ -277,12 +277,9 @@ static int __init init_sched_debug_procfs(void)
 {
 	struct proc_dir_entry *pe;
 
-	pe = create_proc_entry("sched_debug", 0644, NULL);
+	pe = proc_create("sched_debug", 0644, NULL, &sched_debug_fops);
 	if (!pe)
 		return -ENOMEM;
-
-	pe->proc_fops = &sched_debug_fops;
-
 	return 0;
 }
 
diff --git a/trunk/kernel/sys.c b/trunk/kernel/sys.c
index 6a0cc71ee88d..e423d0d9e6ff 100644
--- a/trunk/kernel/sys.c
+++ b/trunk/kernel/sys.c
@@ -1545,6 +1545,19 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
  *
  */
 
+static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r,
+				     cputime_t *utimep, cputime_t *stimep)
+{
+	*utimep = cputime_add(*utimep, t->utime);
+	*stimep = cputime_add(*stimep, t->stime);
+	r->ru_nvcsw += t->nvcsw;
+	r->ru_nivcsw += t->nivcsw;
+	r->ru_minflt += t->min_flt;
+	r->ru_majflt += t->maj_flt;
+	r->ru_inblock += task_io_get_inblock(t);
+	r->ru_oublock += task_io_get_oublock(t);
+}
+
 static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 {
 	struct task_struct *t;
@@ -1554,6 +1567,11 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 	memset((char *) r, 0, sizeof *r);
 	utime = stime = cputime_zero;
 
+	if (who == RUSAGE_THREAD) {
+		accumulate_thread_rusage(p, r, &utime, &stime);
+		goto out;
+	}
+
 	rcu_read_lock();
 	if (!lock_task_sighand(p, &flags)) {
 		rcu_read_unlock();
@@ -1586,14 +1604,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 			r->ru_oublock += p->signal->oublock;
 			t = p;
 			do {
-				utime = cputime_add(utime, t->utime);
-				stime = cputime_add(stime, t->stime);
-				r->ru_nvcsw += t->nvcsw;
-				r->ru_nivcsw += t->nivcsw;
-				r->ru_minflt += t->min_flt;
-				r->ru_majflt += t->maj_flt;
-				r->ru_inblock += task_io_get_inblock(t);
-				r->ru_oublock += task_io_get_oublock(t);
+				accumulate_thread_rusage(t, r, &utime, &stime);
 				t = next_thread(t);
 			} while (t != p);
 			break;
@@ -1605,6 +1616,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 	unlock_task_sighand(p, &flags);
 	rcu_read_unlock();
 
+out:
 	cputime_to_timeval(utime, &r->ru_utime);
 	cputime_to_timeval(stime, &r->ru_stime);
 }
@@ -1618,7 +1630,8 @@ int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
 
 asmlinkage long sys_getrusage(int who, struct rusage __user *ru)
 {
-	if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN)
+	if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN &&
+	    who != RUSAGE_THREAD)
 		return -EINVAL;
 	return getrusage(current, who, ru);
 }
@@ -1632,10 +1645,9 @@ asmlinkage long sys_umask(int mask)
 asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
 			  unsigned long arg4, unsigned long arg5)
 {
-	long error;
+	long uninitialized_var(error);
 
-	error = security_task_prctl(option, arg2, arg3, arg4, arg5);
-	if (error)
+	if (security_task_prctl(option, arg2, arg3, arg4, arg5, &error))
 		return error;
 
 	switch (option) {
@@ -1688,17 +1700,6 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
 				error = -EINVAL;
 			break;
 
-		case PR_GET_KEEPCAPS:
-			if (current->keep_capabilities)
-				error = 1;
-			break;
-		case PR_SET_KEEPCAPS:
-			if (arg2 != 0 && arg2 != 1) {
-				error = -EINVAL;
-				break;
-			}
-			current->keep_capabilities = arg2;
-			break;
 		case PR_SET_NAME: {
 			struct task_struct *me = current;
 			unsigned char ncomm[sizeof(me->comm)];
@@ -1732,17 +1733,6 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
 		case PR_SET_SECCOMP:
 			error = prctl_set_seccomp(arg2);
 			break;
-
-		case PR_CAPBSET_READ:
-			if (!cap_valid(arg2))
-				return -EINVAL;
-			return !!cap_raised(current->cap_bset, arg2);
-		case PR_CAPBSET_DROP:
-#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
-			return cap_prctl_drop(arg2);
-#else
-			return -EINVAL;
-#endif
 		case PR_GET_TSC:
 			error = GET_TSC_CTL(arg2);
 			break;
diff --git a/trunk/kernel/sysctl.c b/trunk/kernel/sysctl.c
index fd3364827ccf..d7ffdc59816a 100644
--- a/trunk/kernel/sysctl.c
+++ b/trunk/kernel/sysctl.c
@@ -38,6 +38,7 @@
 #include <linux/writeback.h>
 #include <linux/hugetlb.h>
 #include <linux/initrd.h>
+#include <linux/key.h>
 #include <linux/times.h>
 #include <linux/limits.h>
 #include <linux/dcache.h>
@@ -144,12 +145,6 @@ extern int no_unaligned_warning;
 extern int max_lock_depth;
 #endif
 
-#ifdef CONFIG_SYSCTL_SYSCALL
-static int parse_table(int __user *, int, void __user *, size_t __user *,
-		void __user *, size_t, struct ctl_table *);
-#endif
-
-
 #ifdef CONFIG_PROC_SYSCTL
 static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
 		  void __user *buffer, size_t *lenp, loff_t *ppos);
@@ -809,6 +804,14 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &proc_dostring,
 		.strategy	= &sysctl_string,
 	},
+#ifdef CONFIG_KEYS
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "keys",
+		.mode		= 0555,
+		.child		= key_sysctls,
+	},
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
@@ -1430,6 +1433,76 @@ void register_sysctl_root(struct ctl_table_root *root)
 }
 
 #ifdef CONFIG_SYSCTL_SYSCALL
+/* Perform the actual read/write of a sysctl table entry. */
+static int do_sysctl_strategy(struct ctl_table_root *root,
+			struct ctl_table *table,
+			int __user *name, int nlen,
+			void __user *oldval, size_t __user *oldlenp,
+			void __user *newval, size_t newlen)
+{
+	int op = 0, rc;
+
+	if (oldval)
+		op |= 004;
+	if (newval)
+		op |= 002;
+	if (sysctl_perm(root, table, op))
+		return -EPERM;
+
+	if (table->strategy) {
+		rc = table->strategy(table, name, nlen, oldval, oldlenp,
+				     newval, newlen);
+		if (rc < 0)
+			return rc;
+		if (rc > 0)
+			return 0;
+	}
+
+	/* If there is no strategy routine, or if the strategy returns
+	 * zero, proceed with automatic r/w */
+	if (table->data && table->maxlen) {
+		rc = sysctl_data(table, name, nlen, oldval, oldlenp,
+				 newval, newlen);
+		if (rc < 0)
+			return rc;
+	}
+	return 0;
+}
+
+static int parse_table(int __user *name, int nlen,
+		       void __user *oldval, size_t __user *oldlenp,
+		       void __user *newval, size_t newlen,
+		       struct ctl_table_root *root,
+		       struct ctl_table *table)
+{
+	int n;
+repeat:
+	if (!nlen)
+		return -ENOTDIR;
+	if (get_user(n, name))
+		return -EFAULT;
+	for ( ; table->ctl_name || table->procname; table++) {
+		if (!table->ctl_name)
+			continue;
+		if (n == table->ctl_name) {
+			int error;
+			if (table->child) {
+				if (sysctl_perm(root, table, 001))
+					return -EPERM;
+				name++;
+				nlen--;
+				table = table->child;
+				goto repeat;
+			}
+			error = do_sysctl_strategy(root, table, name, nlen,
+						   oldval, oldlenp,
+						   newval, newlen);
+			return error;
+		}
+	}
+	return -ENOTDIR;
+}
+
 int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp,
 	       void __user *newval, size_t newlen)
 {
@@ -1447,7 +1520,8 @@ int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *ol
 	for (head = sysctl_head_next(NULL); head;
 			head = sysctl_head_next(head)) {
 		error = parse_table(name, nlen, oldval, oldlenp, 
-					newval, newlen, head->ctl_table);
+					newval, newlen,
+					head->root, head->ctl_table);
 		if (error != -ENOTDIR) {
 			sysctl_head_finish(head);
 			break;
@@ -1493,84 +1567,22 @@ static int test_perm(int mode, int op)
 	return -EACCES;
 }
 
-int sysctl_perm(struct ctl_table *table, int op)
+int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
 {
 	int error;
+	int mode;
+
 	error = security_sysctl(table, op);
 	if (error)
 		return error;
-	return test_perm(table->mode, op);
-}
-
-#ifdef CONFIG_SYSCTL_SYSCALL
-static int parse_table(int __user *name, int nlen,
-		       void __user *oldval, size_t __user *oldlenp,
-		       void __user *newval, size_t newlen,
-		       struct ctl_table *table)
-{
-	int n;
-repeat:
-	if (!nlen)
-		return -ENOTDIR;
-	if (get_user(n, name))
-		return -EFAULT;
-	for ( ; table->ctl_name || table->procname; table++) {
-		if (!table->ctl_name)
-			continue;
-		if (n == table->ctl_name) {
-			int error;
-			if (table->child) {
-				if (sysctl_perm(table, 001))
-					return -EPERM;
-				name++;
-				nlen--;
-				table = table->child;
-				goto repeat;
-			}
-			error = do_sysctl_strategy(table, name, nlen,
-						   oldval, oldlenp,
-						   newval, newlen);
-			return error;
-		}
-	}
-	return -ENOTDIR;
-}
 
-/* Perform the actual read/write of a sysctl table entry. */
-int do_sysctl_strategy (struct ctl_table *table,
-			int __user *name, int nlen,
-			void __user *oldval, size_t __user *oldlenp,
-			void __user *newval, size_t newlen)
-{
-	int op = 0, rc;
-
-	if (oldval)
-		op |= 004;
-	if (newval) 
-		op |= 002;
-	if (sysctl_perm(table, op))
-		return -EPERM;
+	if (root->permissions)
+		mode = root->permissions(root, current->nsproxy, table);
+	else
+		mode = table->mode;
 
-	if (table->strategy) {
-		rc = table->strategy(table, name, nlen, oldval, oldlenp,
-				     newval, newlen);
-		if (rc < 0)
-			return rc;
-		if (rc > 0)
-			return 0;
-	}
-
-	/* If there is no strategy routine, or if the strategy returns
-	 * zero, proceed with automatic r/w */
-	if (table->data && table->maxlen) {
-		rc = sysctl_data(table, name, nlen, oldval, oldlenp,
-				 newval, newlen);
-		if (rc < 0)
-			return rc;
-	}
-	return 0;
+	return test_perm(mode, op);
 }
-#endif /* CONFIG_SYSCTL_SYSCALL */
 
 static void sysctl_set_parent(struct ctl_table *parent, struct ctl_table *table)
 {
@@ -1583,9 +1595,13 @@ static void sysctl_set_parent(struct ctl_table *parent, struct ctl_table *table)
 
 static __init int sysctl_init(void)
 {
-	int err;
 	sysctl_set_parent(NULL, root_table);
-	err = sysctl_check_table(current->nsproxy, root_table);
+#ifdef CONFIG_SYSCTL_SYSCALL_CHECK
+	{
+		int err;
+		err = sysctl_check_table(current->nsproxy, root_table);
+	}
+#endif
 	return 0;
 }
 
@@ -1712,10 +1728,12 @@ struct ctl_table_header *__register_sysctl_paths(
 	header->unregistering = NULL;
 	header->root = root;
 	sysctl_set_parent(NULL, header->ctl_table);
+#ifdef CONFIG_SYSCTL_SYSCALL_CHECK
 	if (sysctl_check_table(namespaces, header->ctl_table)) {
 		kfree(header);
 		return NULL;
 	}
+#endif
 	spin_lock(&sysctl_lock);
 	header_list = lookup_header_list(root, namespaces);
 	list_add_tail(&header->ctl_entry, header_list);
diff --git a/trunk/kernel/time.c b/trunk/kernel/time.c
index 35d373a98782..86729042e4cd 100644
--- a/trunk/kernel/time.c
+++ b/trunk/kernel/time.c
@@ -35,6 +35,7 @@
 #include <linux/syscalls.h>
 #include <linux/security.h>
 #include <linux/fs.h>
+#include <linux/slab.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
diff --git a/trunk/kernel/time/timer_list.c b/trunk/kernel/time/timer_list.c
index 67fe8fc21fb1..a40e20fd0001 100644
--- a/trunk/kernel/time/timer_list.c
+++ b/trunk/kernel/time/timer_list.c
@@ -278,12 +278,9 @@ static int __init init_timer_list_procfs(void)
 {
 	struct proc_dir_entry *pe;
 
-	pe = create_proc_entry("timer_list", 0644, NULL);
+	pe = proc_create("timer_list", 0644, NULL, &timer_list_fops);
 	if (!pe)
 		return -ENOMEM;
-
-	pe->proc_fops = &timer_list_fops;
-
 	return 0;
 }
 __initcall(init_timer_list_procfs);
diff --git a/trunk/kernel/time/timer_stats.c b/trunk/kernel/time/timer_stats.c
index 417da8c5bc72..c994530d166d 100644
--- a/trunk/kernel/time/timer_stats.c
+++ b/trunk/kernel/time/timer_stats.c
@@ -415,12 +415,9 @@ static int __init init_tstats_procfs(void)
 {
 	struct proc_dir_entry *pe;
 
-	pe = create_proc_entry("timer_stats", 0644, NULL);
+	pe = proc_create("timer_stats", 0644, NULL, &tstats_fops);
 	if (!pe)
 		return -ENOMEM;
-
-	pe->proc_fops = &tstats_fops;
-
 	return 0;
 }
 __initcall(init_tstats_procfs);
diff --git a/trunk/kernel/user.c b/trunk/kernel/user.c
index debce602bfdd..aefbbfa3159f 100644
--- a/trunk/kernel/user.c
+++ b/trunk/kernel/user.c
@@ -53,10 +53,6 @@ struct user_struct root_user = {
 	.files		= ATOMIC_INIT(0),
 	.sigpending	= ATOMIC_INIT(0),
 	.locked_shm     = 0,
-#ifdef CONFIG_KEYS
-	.uid_keyring	= &root_user_keyring,
-	.session_keyring = &root_session_keyring,
-#endif
 #ifdef CONFIG_USER_SCHED
 	.tg		= &init_task_group,
 #endif
@@ -420,12 +416,12 @@ struct user_struct * alloc_uid(struct user_namespace *ns, uid_t uid)
 		new->mq_bytes = 0;
 #endif
 		new->locked_shm = 0;
-
-		if (alloc_uid_keyring(new, current) < 0)
-			goto out_free_user;
+#ifdef CONFIG_KEYS
+		new->uid_keyring = new->session_keyring = NULL;
+#endif
 
 		if (sched_create_user(new) < 0)
-			goto out_put_keys;
+			goto out_free_user;
 
 		if (uids_user_create(new))
 			goto out_destoy_sched;
@@ -459,9 +455,6 @@ struct user_struct * alloc_uid(struct user_namespace *ns, uid_t uid)
 
 out_destoy_sched:
 	sched_destroy_user(new);
-out_put_keys:
-	key_put(new->uid_keyring);
-	key_put(new->session_keyring);
 out_free_user:
 	kmem_cache_free(uid_cachep, new);
 out_unlock:
diff --git a/trunk/kernel/user_namespace.c b/trunk/kernel/user_namespace.c
index 4c9006275df7..a9ab0596de44 100644
--- a/trunk/kernel/user_namespace.c
+++ b/trunk/kernel/user_namespace.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/version.h>
 #include <linux/nsproxy.h>
+#include <linux/slab.h>
 #include <linux/user_namespace.h>
 
 /*
@@ -73,3 +74,4 @@ void free_user_ns(struct kref *kref)
 	release_uids(ns);
 	kfree(ns);
 }
+EXPORT_SYMBOL(free_user_ns);
diff --git a/trunk/kernel/utsname.c b/trunk/kernel/utsname.c
index 816d7b24fa03..64d398f12444 100644
--- a/trunk/kernel/utsname.c
+++ b/trunk/kernel/utsname.c
@@ -14,6 +14,7 @@
 #include <linux/utsname.h>
 #include <linux/version.h>
 #include <linux/err.h>
+#include <linux/slab.h>
 
 /*
  * Clone a new ns copying an original utsname, setting refcount to 1
diff --git a/trunk/kernel/workqueue.c b/trunk/kernel/workqueue.c
index 00ff4d08e370..7db251a959c5 100644
--- a/trunk/kernel/workqueue.c
+++ b/trunk/kernel/workqueue.c
@@ -158,8 +158,8 @@ static void __queue_work(struct cpu_workqueue_struct *cwq,
  *
  * Returns 0 if @work was already on a queue, non-zero otherwise.
  *
- * We queue the work to the CPU it was submitted, but there is no
- * guarantee that it will be processed by that CPU.
+ * We queue the work to the CPU on which it was submitted, but if the CPU dies
+ * it can be processed by another CPU.
  */
 int queue_work(struct workqueue_struct *wq, struct work_struct *work)
 {
@@ -772,7 +772,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
 }
 EXPORT_SYMBOL_GPL(__create_workqueue_key);
 
-static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
+static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
 {
 	/*
 	 * Our caller is either destroy_workqueue() or CPU_DEAD,
@@ -808,19 +808,16 @@ static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
 void destroy_workqueue(struct workqueue_struct *wq)
 {
 	const cpumask_t *cpu_map = wq_cpu_map(wq);
-	struct cpu_workqueue_struct *cwq;
 	int cpu;
 
 	get_online_cpus();
 	spin_lock(&workqueue_lock);
 	list_del(&wq->list);
 	spin_unlock(&workqueue_lock);
-	put_online_cpus();
 
-	for_each_cpu_mask(cpu, *cpu_map) {
-		cwq = per_cpu_ptr(wq->cpu_wq, cpu);
-		cleanup_workqueue_thread(cwq, cpu);
-	}
+	for_each_cpu_mask(cpu, *cpu_map)
+		cleanup_workqueue_thread(per_cpu_ptr(wq->cpu_wq, cpu));
+	put_online_cpus();
 
 	free_percpu(wq->cpu_wq);
 	kfree(wq);
@@ -838,7 +835,6 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 	action &= ~CPU_TASKS_FROZEN;
 
 	switch (action) {
-
 	case CPU_UP_PREPARE:
 		cpu_set(cpu, cpu_populated_map);
 	}
@@ -861,11 +857,17 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 		case CPU_UP_CANCELED:
 			start_workqueue_thread(cwq, -1);
 		case CPU_DEAD:
-			cleanup_workqueue_thread(cwq, cpu);
+			cleanup_workqueue_thread(cwq);
 			break;
 		}
 	}
 
+	switch (action) {
+	case CPU_UP_CANCELED:
+	case CPU_DEAD:
+		cpu_clear(cpu, cpu_populated_map);
+	}
+
 	return NOTIFY_OK;
 }
 
diff --git a/trunk/lib/Makefile b/trunk/lib/Makefile
index 2d7001b7f5a4..0ae4eb047aac 100644
--- a/trunk/lib/Makefile
+++ b/trunk/lib/Makefile
@@ -6,7 +6,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o dump_stack.o \
 	 idr.o int_sqrt.o extable.o prio_tree.o \
 	 sha1.o irq_regs.o reciprocal_div.o argv_split.o \
-	 proportions.o prio_heap.o
+	 proportions.o prio_heap.o ratelimit.o
 
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
diff --git a/trunk/lib/bitmap.c b/trunk/lib/bitmap.c
index a6939e18d7bb..c4cb48f77f0c 100644
--- a/trunk/lib/bitmap.c
+++ b/trunk/lib/bitmap.c
@@ -714,6 +714,164 @@ int bitmap_bitremap(int oldbit, const unsigned long *old,
 }
 EXPORT_SYMBOL(bitmap_bitremap);
 
+/**
+ * bitmap_onto - translate one bitmap relative to another
+ *	@dst: resulting translated bitmap
+ * 	@orig: original untranslated bitmap
+ * 	@relmap: bitmap relative to which translated
+ *	@bits: number of bits in each of these bitmaps
+ *
+ * Set the n-th bit of @dst iff there exists some m such that the
+ * n-th bit of @relmap is set, the m-th bit of @orig is set, and
+ * the n-th bit of @relmap is also the m-th _set_ bit of @relmap.
+ * (If you understood the previous sentence the first time your
+ * read it, you're overqualified for your current job.)
+ *
+ * In other words, @orig is mapped onto (surjectively) @dst,
+ * using the the map { <n, m> | the n-th bit of @relmap is the
+ * m-th set bit of @relmap }.
+ *
+ * Any set bits in @orig above bit number W, where W is the
+ * weight of (number of set bits in) @relmap are mapped nowhere.
+ * In particular, if for all bits m set in @orig, m >= W, then
+ * @dst will end up empty.  In situations where the possibility
+ * of such an empty result is not desired, one way to avoid it is
+ * to use the bitmap_fold() operator, below, to first fold the
+ * @orig bitmap over itself so that all its set bits x are in the
+ * range 0 <= x < W.  The bitmap_fold() operator does this by
+ * setting the bit (m % W) in @dst, for each bit (m) set in @orig.
+ *
+ * Example [1] for bitmap_onto():
+ *  Let's say @relmap has bits 30-39 set, and @orig has bits
+ *  1, 3, 5, 7, 9 and 11 set.  Then on return from this routine,
+ *  @dst will have bits 31, 33, 35, 37 and 39 set.
+ *
+ *  When bit 0 is set in @orig, it means turn on the bit in
+ *  @dst corresponding to whatever is the first bit (if any)
+ *  that is turned on in @relmap.  Since bit 0 was off in the
+ *  above example, we leave off that bit (bit 30) in @dst.
+ *
+ *  When bit 1 is set in @orig (as in the above example), it
+ *  means turn on the bit in @dst corresponding to whatever
+ *  is the second bit that is turned on in @relmap.  The second
+ *  bit in @relmap that was turned on in the above example was
+ *  bit 31, so we turned on bit 31 in @dst.
+ *
+ *  Similarly, we turned on bits 33, 35, 37 and 39 in @dst,
+ *  because they were the 4th, 6th, 8th and 10th set bits
+ *  set in @relmap, and the 4th, 6th, 8th and 10th bits of
+ *  @orig (i.e. bits 3, 5, 7 and 9) were also set.
+ *
+ *  When bit 11 is set in @orig, it means turn on the bit in
+ *  @dst corresponding to whatever is the twelth bit that is
+ *  turned on in @relmap.  In the above example, there were
+ *  only ten bits turned on in @relmap (30..39), so that bit
+ *  11 was set in @orig had no affect on @dst.
+ *
+ * Example [2] for bitmap_fold() + bitmap_onto():
+ *  Let's say @relmap has these ten bits set:
+ *		40 41 42 43 45 48 53 61 74 95
+ *  (for the curious, that's 40 plus the first ten terms of the
+ *  Fibonacci sequence.)
+ *
+ *  Further lets say we use the following code, invoking
+ *  bitmap_fold() then bitmap_onto, as suggested above to
+ *  avoid the possitility of an empty @dst result:
+ *
+ *	unsigned long *tmp;	// a temporary bitmap's bits
+ *
+ *	bitmap_fold(tmp, orig, bitmap_weight(relmap, bits), bits);
+ *	bitmap_onto(dst, tmp, relmap, bits);
+ *
+ *  Then this table shows what various values of @dst would be, for
+ *  various @orig's.  I list the zero-based positions of each set bit.
+ *  The tmp column shows the intermediate result, as computed by
+ *  using bitmap_fold() to fold the @orig bitmap modulo ten
+ *  (the weight of @relmap).
+ *
+ *      @orig           tmp            @dst
+ *      0                0             40
+ *      1                1             41
+ *      9                9             95
+ *      10               0             40 (*)
+ *      1 3 5 7          1 3 5 7       41 43 48 61
+ *      0 1 2 3 4        0 1 2 3 4     40 41 42 43 45
+ *      0 9 18 27        0 9 8 7       40 61 74 95
+ *      0 10 20 30       0             40
+ *      0 11 22 33       0 1 2 3       40 41 42 43
+ *      0 12 24 36       0 2 4 6       40 42 45 53
+ *      78 102 211       1 2 8         41 42 74 (*)
+ *
+ * (*) For these marked lines, if we hadn't first done bitmap_fold()
+ *     into tmp, then the @dst result would have been empty.
+ *
+ * If either of @orig or @relmap is empty (no set bits), then @dst
+ * will be returned empty.
+ *
+ * If (as explained above) the only set bits in @orig are in positions
+ * m where m >= W, (where W is the weight of @relmap) then @dst will
+ * once again be returned empty.
+ *
+ * All bits in @dst not set by the above rule are cleared.
+ */
+void bitmap_onto(unsigned long *dst, const unsigned long *orig,
+			const unsigned long *relmap, int bits)
+{
+	int n, m;       	/* same meaning as in above comment */
+
+	if (dst == orig)	/* following doesn't handle inplace mappings */
+		return;
+	bitmap_zero(dst, bits);
+
+	/*
+	 * The following code is a more efficient, but less
+	 * obvious, equivalent to the loop:
+	 *	for (m = 0; m < bitmap_weight(relmap, bits); m++) {
+	 *		n = bitmap_ord_to_pos(orig, m, bits);
+	 *		if (test_bit(m, orig))
+	 *			set_bit(n, dst);
+	 *	}
+	 */
+
+	m = 0;
+	for (n = find_first_bit(relmap, bits);
+	     n < bits;
+	     n = find_next_bit(relmap, bits, n + 1)) {
+		/* m == bitmap_pos_to_ord(relmap, n, bits) */
+		if (test_bit(m, orig))
+			set_bit(n, dst);
+		m++;
+	}
+}
+EXPORT_SYMBOL(bitmap_onto);
+
+/**
+ * bitmap_fold - fold larger bitmap into smaller, modulo specified size
+ *	@dst: resulting smaller bitmap
+ *	@orig: original larger bitmap
+ *	@sz: specified size
+ *	@bits: number of bits in each of these bitmaps
+ *
+ * For each bit oldbit in @orig, set bit oldbit mod @sz in @dst.
+ * Clear all other bits in @dst.  See further the comment and
+ * Example [2] for bitmap_onto() for why and how to use this.
+ */
+void bitmap_fold(unsigned long *dst, const unsigned long *orig,
+			int sz, int bits)
+{
+	int oldbit;
+
+	if (dst == orig)	/* following doesn't handle inplace mappings */
+		return;
+	bitmap_zero(dst, bits);
+
+	for (oldbit = find_first_bit(orig, bits);
+	     oldbit < bits;
+	     oldbit = find_next_bit(orig, bits, oldbit + 1))
+		set_bit(oldbit % sz, dst);
+}
+EXPORT_SYMBOL(bitmap_fold);
+
 /*
  * Common code for bitmap_*_region() routines.
  *	bitmap: array of unsigned longs corresponding to the bitmap
diff --git a/trunk/lib/find_next_bit.c b/trunk/lib/find_next_bit.c
index d3f5784807b4..24c59ded47a0 100644
--- a/trunk/lib/find_next_bit.c
+++ b/trunk/lib/find_next_bit.c
@@ -20,8 +20,8 @@
 /*
  * Find the next set bit in a memory region.
  */
-unsigned long __find_next_bit(const unsigned long *addr,
-		unsigned long size, unsigned long offset)
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+			    unsigned long offset)
 {
 	const unsigned long *p = addr + BITOP_WORD(offset);
 	unsigned long result = offset & ~(BITS_PER_LONG-1);
@@ -58,14 +58,14 @@ unsigned long __find_next_bit(const unsigned long *addr,
 found_middle:
 	return result + __ffs(tmp);
 }
-EXPORT_SYMBOL(__find_next_bit);
+EXPORT_SYMBOL(find_next_bit);
 
 /*
  * This implementation of find_{first,next}_zero_bit was stolen from
  * Linus' asm-alpha/bitops.h.
  */
-unsigned long __find_next_zero_bit(const unsigned long *addr,
-		unsigned long size, unsigned long offset)
+unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
+				 unsigned long offset)
 {
 	const unsigned long *p = addr + BITOP_WORD(offset);
 	unsigned long result = offset & ~(BITS_PER_LONG-1);
@@ -102,15 +102,14 @@ unsigned long __find_next_zero_bit(const unsigned long *addr,
 found_middle:
 	return result + ffz(tmp);
 }
-EXPORT_SYMBOL(__find_next_zero_bit);
+EXPORT_SYMBOL(find_next_zero_bit);
 #endif /* CONFIG_GENERIC_FIND_NEXT_BIT */
 
 #ifdef CONFIG_GENERIC_FIND_FIRST_BIT
 /*
  * Find the first set bit in a memory region.
  */
-unsigned long __find_first_bit(const unsigned long *addr,
-		unsigned long size)
+unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
 {
 	const unsigned long *p = addr;
 	unsigned long result = 0;
@@ -131,13 +130,12 @@ unsigned long __find_first_bit(const unsigned long *addr,
 found:
 	return result + __ffs(tmp);
 }
-EXPORT_SYMBOL(__find_first_bit);
+EXPORT_SYMBOL(find_first_bit);
 
 /*
  * Find the first cleared bit in a memory region.
  */
-unsigned long __find_first_zero_bit(const unsigned long *addr,
-		unsigned long size)
+unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
 {
 	const unsigned long *p = addr;
 	unsigned long result = 0;
@@ -158,7 +156,7 @@ unsigned long __find_first_zero_bit(const unsigned long *addr,
 found:
 	return result + ffz(tmp);
 }
-EXPORT_SYMBOL(__find_first_zero_bit);
+EXPORT_SYMBOL(find_first_zero_bit);
 #endif /* CONFIG_GENERIC_FIND_FIRST_BIT */
 
 #ifdef __BIG_ENDIAN
diff --git a/trunk/lib/idr.c b/trunk/lib/idr.c
index afbb0b1023d4..8368c81fcb7d 100644
--- a/trunk/lib/idr.c
+++ b/trunk/lib/idr.c
@@ -585,12 +585,11 @@ static void idr_cache_ctor(struct kmem_cache *idr_layer_cache, void *idr_layer)
 	memset(idr_layer, 0, sizeof(struct idr_layer));
 }
 
-static  int init_id_cache(void)
+void __init idr_init_cache(void)
 {
-	if (!idr_layer_cache)
-		idr_layer_cache = kmem_cache_create("idr_layer_cache",
-			sizeof(struct idr_layer), 0, 0, idr_cache_ctor);
-	return 0;
+	idr_layer_cache = kmem_cache_create("idr_layer_cache",
+				sizeof(struct idr_layer), 0, SLAB_PANIC,
+				idr_cache_ctor);
 }
 
 /**
@@ -602,7 +601,6 @@ static  int init_id_cache(void)
  */
 void idr_init(struct idr *idp)
 {
-	init_id_cache();
 	memset(idp, 0, sizeof(struct idr));
 	spin_lock_init(&idp->lock);
 }
diff --git a/trunk/lib/inflate.c b/trunk/lib/inflate.c
index 845f91d3ac12..9762294be062 100644
--- a/trunk/lib/inflate.c
+++ b/trunk/lib/inflate.c
@@ -811,6 +811,9 @@ DEBG("<dyn");
   ll = malloc(sizeof(*ll) * (286+30));  /* literal/length and distance code lengths */
 #endif
 
+  if (ll == NULL)
+    return 1;
+
   /* make local bit buffer */
   b = bb;
   k = bk;
diff --git a/trunk/lib/iomap.c b/trunk/lib/iomap.c
index dd6ca48fe6b0..37a3ea4cac9f 100644
--- a/trunk/lib/iomap.c
+++ b/trunk/lib/iomap.c
@@ -257,7 +257,7 @@ EXPORT_SYMBOL(ioport_unmap);
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
 	resource_size_t start = pci_resource_start(dev, bar);
-	unsigned long len = pci_resource_len(dev, bar);
+	resource_size_t len = pci_resource_len(dev, bar);
 	unsigned long flags = pci_resource_flags(dev, bar);
 
 	if (!len || !start)
diff --git a/trunk/lib/lmb.c b/trunk/lib/lmb.c
index 207147ab25e4..83287d3869a3 100644
--- a/trunk/lib/lmb.c
+++ b/trunk/lib/lmb.c
@@ -46,14 +46,13 @@ void lmb_dump_all(void)
 #endif /* DEBUG */
 }
 
-static unsigned long __init lmb_addrs_overlap(u64 base1, u64 size1,
-		u64 base2, u64 size2)
+static unsigned long lmb_addrs_overlap(u64 base1, u64 size1, u64 base2,
+					u64 size2)
 {
 	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
 }
 
-static long __init lmb_addrs_adjacent(u64 base1, u64 size1,
-		u64 base2, u64 size2)
+static long lmb_addrs_adjacent(u64 base1, u64 size1, u64 base2, u64 size2)
 {
 	if (base2 == base1 + size1)
 		return 1;
@@ -63,7 +62,7 @@ static long __init lmb_addrs_adjacent(u64 base1, u64 size1,
 	return 0;
 }
 
-static long __init lmb_regions_adjacent(struct lmb_region *rgn,
+static long lmb_regions_adjacent(struct lmb_region *rgn,
 		unsigned long r1, unsigned long r2)
 {
 	u64 base1 = rgn->region[r1].base;
@@ -74,7 +73,7 @@ static long __init lmb_regions_adjacent(struct lmb_region *rgn,
 	return lmb_addrs_adjacent(base1, size1, base2, size2);
 }
 
-static void __init lmb_remove_region(struct lmb_region *rgn, unsigned long r)
+static void lmb_remove_region(struct lmb_region *rgn, unsigned long r)
 {
 	unsigned long i;
 
@@ -86,7 +85,7 @@ static void __init lmb_remove_region(struct lmb_region *rgn, unsigned long r)
 }
 
 /* Assumption: base addr of region 1 < base addr of region 2 */
-static void __init lmb_coalesce_regions(struct lmb_region *rgn,
+static void lmb_coalesce_regions(struct lmb_region *rgn,
 		unsigned long r1, unsigned long r2)
 {
 	rgn->region[r1].size += rgn->region[r2].size;
@@ -118,7 +117,7 @@ void __init lmb_analyze(void)
 		lmb.memory.size += lmb.memory.region[i].size;
 }
 
-static long __init lmb_add_region(struct lmb_region *rgn, u64 base, u64 size)
+static long lmb_add_region(struct lmb_region *rgn, u64 base, u64 size)
 {
 	unsigned long coalesced = 0;
 	long adjacent, i;
@@ -182,7 +181,7 @@ static long __init lmb_add_region(struct lmb_region *rgn, u64 base, u64 size)
 	return 0;
 }
 
-long __init lmb_add(u64 base, u64 size)
+long lmb_add(u64 base, u64 size)
 {
 	struct lmb_region *_rgn = &lmb.memory;
 
@@ -194,6 +193,55 @@ long __init lmb_add(u64 base, u64 size)
 
 }
 
+long lmb_remove(u64 base, u64 size)
+{
+	struct lmb_region *rgn = &(lmb.memory);
+	u64 rgnbegin, rgnend;
+	u64 end = base + size;
+	int i;
+
+	rgnbegin = rgnend = 0; /* supress gcc warnings */
+
+	/* Find the region where (base, size) belongs to */
+	for (i=0; i < rgn->cnt; i++) {
+		rgnbegin = rgn->region[i].base;
+		rgnend = rgnbegin + rgn->region[i].size;
+
+		if ((rgnbegin <= base) && (end <= rgnend))
+			break;
+	}
+
+	/* Didn't find the region */
+	if (i == rgn->cnt)
+		return -1;
+
+	/* Check to see if we are removing entire region */
+	if ((rgnbegin == base) && (rgnend == end)) {
+		lmb_remove_region(rgn, i);
+		return 0;
+	}
+
+	/* Check to see if region is matching at the front */
+	if (rgnbegin == base) {
+		rgn->region[i].base = end;
+		rgn->region[i].size -= size;
+		return 0;
+	}
+
+	/* Check to see if the region is matching at the end */
+	if (rgnend == end) {
+		rgn->region[i].size -= size;
+		return 0;
+	}
+
+	/*
+	 * We need to split the entry -  adjust the current one to the
+	 * beginging of the hole and add the region after hole.
+	 */
+	rgn->region[i].size = base - rgn->region[i].base;
+	return lmb_add_region(rgn, end, rgnend - end);
+}
+
 long __init lmb_reserve(u64 base, u64 size)
 {
 	struct lmb_region *_rgn = &lmb.reserved;
@@ -426,3 +474,36 @@ int __init lmb_is_reserved(u64 addr)
 	}
 	return 0;
 }
+
+/*
+ * Given a <base, len>, find which memory regions belong to this range.
+ * Adjust the request and return a contiguous chunk.
+ */
+int lmb_find(struct lmb_property *res)
+{
+	int i;
+	u64 rstart, rend;
+
+	rstart = res->base;
+	rend = rstart + res->size - 1;
+
+	for (i = 0; i < lmb.memory.cnt; i++) {
+		u64 start = lmb.memory.region[i].base;
+		u64 end = start + lmb.memory.region[i].size - 1;
+
+		if (start > rend)
+			return -1;
+
+		if ((end >= rstart) && (start < rend)) {
+			/* adjust the request */
+			if (rstart < start)
+				rstart = start;
+			if (rend > end)
+				rend = end;
+			res->base = rstart;
+			res->size = rend - rstart + 1;
+			return 0;
+		}
+	}
+	return -1;
+}
diff --git a/trunk/lib/radix-tree.c b/trunk/lib/radix-tree.c
index 65f0e758ec38..bd521716ab1a 100644
--- a/trunk/lib/radix-tree.c
+++ b/trunk/lib/radix-tree.c
@@ -114,8 +114,7 @@ radix_tree_node_alloc(struct radix_tree_root *root)
 		}
 	}
 	if (ret == NULL)
-		ret = kmem_cache_alloc(radix_tree_node_cachep,
-				set_migrateflags(gfp_mask, __GFP_RECLAIMABLE));
+		ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
 
 	BUG_ON(radix_tree_is_indirect_ptr(ret));
 	return ret;
@@ -150,8 +149,7 @@ int radix_tree_preload(gfp_t gfp_mask)
 	rtp = &__get_cpu_var(radix_tree_preloads);
 	while (rtp->nr < ARRAY_SIZE(rtp->nodes)) {
 		preempt_enable();
-		node = kmem_cache_alloc(radix_tree_node_cachep,
-				set_migrateflags(gfp_mask, __GFP_RECLAIMABLE));
+		node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
 		if (node == NULL)
 			goto out;
 		preempt_disable();
@@ -1098,7 +1096,8 @@ void __init radix_tree_init(void)
 {
 	radix_tree_node_cachep = kmem_cache_create("radix_tree_node",
 			sizeof(struct radix_tree_node), 0,
-			SLAB_PANIC, radix_tree_node_ctor);
+			SLAB_PANIC | SLAB_RECLAIM_ACCOUNT,
+			radix_tree_node_ctor);
 	radix_tree_init_maxindex();
 	hotcpu_notifier(radix_tree_callback, 0);
 }
diff --git a/trunk/lib/ratelimit.c b/trunk/lib/ratelimit.c
new file mode 100644
index 000000000000..485e3040dcd4
--- /dev/null
+++ b/trunk/lib/ratelimit.c
@@ -0,0 +1,51 @@
+/*
+ * ratelimit.c - Do something with rate limit.
+ *
+ * Isolated from kernel/printk.c by Dave Young <hidave.darkstar@gmail.com>
+ *
+ * This file is released under the GPLv2.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+
+/*
+ * __ratelimit - rate limiting
+ * @ratelimit_jiffies: minimum time in jiffies between two callbacks
+ * @ratelimit_burst: number of callbacks we do before ratelimiting
+ *
+ * This enforces a rate limit: not more than @ratelimit_burst callbacks
+ * in every ratelimit_jiffies
+ */
+int __ratelimit(int ratelimit_jiffies, int ratelimit_burst)
+{
+	static DEFINE_SPINLOCK(ratelimit_lock);
+	static unsigned toks = 10 * 5 * HZ;
+	static unsigned long last_msg;
+	static int missed;
+	unsigned long flags;
+	unsigned long now = jiffies;
+
+	spin_lock_irqsave(&ratelimit_lock, flags);
+	toks += now - last_msg;
+	last_msg = now;
+	if (toks > (ratelimit_burst * ratelimit_jiffies))
+		toks = ratelimit_burst * ratelimit_jiffies;
+	if (toks >= ratelimit_jiffies) {
+		int lost = missed;
+
+		missed = 0;
+		toks -= ratelimit_jiffies;
+		spin_unlock_irqrestore(&ratelimit_lock, flags);
+		if (lost)
+			printk(KERN_WARNING "%s: %d messages suppressed\n",
+				__func__, lost);
+		return 1;
+	}
+	missed++;
+	spin_unlock_irqrestore(&ratelimit_lock, flags);
+	return 0;
+}
+EXPORT_SYMBOL(__ratelimit);
diff --git a/trunk/lib/swiotlb.c b/trunk/lib/swiotlb.c
index 025922807e6e..d568894df8cc 100644
--- a/trunk/lib/swiotlb.c
+++ b/trunk/lib/swiotlb.c
@@ -31,6 +31,7 @@
 
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/iommu-helper.h>
 
 #define OFFSET(val,align) ((unsigned long)	\
 	                   ( (val) & ( (align) - 1)))
@@ -282,15 +283,6 @@ address_needs_mapping(struct device *hwdev, dma_addr_t addr)
 	return (addr & ~mask) != 0;
 }
 
-static inline unsigned int is_span_boundary(unsigned int index,
-					    unsigned int nslots,
-					    unsigned long offset_slots,
-					    unsigned long max_slots)
-{
-	unsigned long offset = (offset_slots + index) & (max_slots - 1);
-	return offset + nslots > max_slots;
-}
-
 /*
  * Allocates bounce buffer and returns its kernel virtual address.
  */
@@ -331,56 +323,53 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir)
 	 * request and allocate a buffer from that IO TLB pool.
 	 */
 	spin_lock_irqsave(&io_tlb_lock, flags);
-	{
-		index = ALIGN(io_tlb_index, stride);
-		if (index >= io_tlb_nslabs)
-			index = 0;
-		wrap = index;
-
-		do {
-			while (is_span_boundary(index, nslots, offset_slots,
-						max_slots)) {
-				index += stride;
-				if (index >= io_tlb_nslabs)
-					index = 0;
-				if (index == wrap)
-					goto not_found;
-			}
-
-			/*
-			 * If we find a slot that indicates we have 'nslots'
-			 * number of contiguous buffers, we allocate the
-			 * buffers from that slot and mark the entries as '0'
-			 * indicating unavailable.
-			 */
-			if (io_tlb_list[index] >= nslots) {
-				int count = 0;
-
-				for (i = index; i < (int) (index + nslots); i++)
-					io_tlb_list[i] = 0;
-				for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
-					io_tlb_list[i] = ++count;
-				dma_addr = io_tlb_start + (index << IO_TLB_SHIFT);
-
-				/*
-				 * Update the indices to avoid searching in
-				 * the next round.
-				 */
-				io_tlb_index = ((index + nslots) < io_tlb_nslabs
-						? (index + nslots) : 0);
-
-				goto found;
-			}
+	index = ALIGN(io_tlb_index, stride);
+	if (index >= io_tlb_nslabs)
+		index = 0;
+	wrap = index;
+
+	do {
+		while (iommu_is_span_boundary(index, nslots, offset_slots,
+					      max_slots)) {
 			index += stride;
 			if (index >= io_tlb_nslabs)
 				index = 0;
-		} while (index != wrap);
+			if (index == wrap)
+				goto not_found;
+		}
 
-  not_found:
-		spin_unlock_irqrestore(&io_tlb_lock, flags);
-		return NULL;
-	}
-  found:
+		/*
+		 * If we find a slot that indicates we have 'nslots' number of
+		 * contiguous buffers, we allocate the buffers from that slot
+		 * and mark the entries as '0' indicating unavailable.
+		 */
+		if (io_tlb_list[index] >= nslots) {
+			int count = 0;
+
+			for (i = index; i < (int) (index + nslots); i++)
+				io_tlb_list[i] = 0;
+			for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--)
+				io_tlb_list[i] = ++count;
+			dma_addr = io_tlb_start + (index << IO_TLB_SHIFT);
+
+			/*
+			 * Update the indices to avoid searching in the next
+			 * round.
+			 */
+			io_tlb_index = ((index + nslots) < io_tlb_nslabs
+					? (index + nslots) : 0);
+
+			goto found;
+		}
+		index += stride;
+		if (index >= io_tlb_nslabs)
+			index = 0;
+	} while (index != wrap);
+
+not_found:
+	spin_unlock_irqrestore(&io_tlb_lock, flags);
+	return NULL;
+found:
 	spin_unlock_irqrestore(&io_tlb_lock, flags);
 
 	/*
@@ -566,7 +555,8 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
  * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed.
  */
 dma_addr_t
-swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
+swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size,
+			 int dir, struct dma_attrs *attrs)
 {
 	dma_addr_t dev_addr = virt_to_bus(ptr);
 	void *map;
@@ -599,6 +589,13 @@ swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
 
 	return dev_addr;
 }
+EXPORT_SYMBOL(swiotlb_map_single_attrs);
+
+dma_addr_t
+swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
+{
+	return swiotlb_map_single_attrs(hwdev, ptr, size, dir, NULL);
+}
 
 /*
  * Unmap a single streaming mode DMA translation.  The dma_addr and size must
@@ -609,8 +606,8 @@ swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
  * whatever the device wrote there.
  */
 void
-swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size,
-		     int dir)
+swiotlb_unmap_single_attrs(struct device *hwdev, dma_addr_t dev_addr,
+			   size_t size, int dir, struct dma_attrs *attrs)
 {
 	char *dma_addr = bus_to_virt(dev_addr);
 
@@ -620,7 +617,14 @@ swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size,
 	else if (dir == DMA_FROM_DEVICE)
 		dma_mark_clean(dma_addr, size);
 }
+EXPORT_SYMBOL(swiotlb_unmap_single_attrs);
 
+void
+swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size,
+		     int dir)
+{
+	return swiotlb_unmap_single_attrs(hwdev, dev_addr, size, dir, NULL);
+}
 /*
  * Make physical memory consistent for a single streaming mode DMA translation
  * after a transfer.
@@ -691,6 +695,8 @@ swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr,
 				  SYNC_FOR_DEVICE);
 }
 
+void swiotlb_unmap_sg_attrs(struct device *, struct scatterlist *, int, int,
+			    struct dma_attrs *);
 /*
  * Map a set of buffers described by scatterlist in streaming mode for DMA.
  * This is the scatter-gather version of the above swiotlb_map_single
@@ -708,8 +714,8 @@ swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr,
  * same here.
  */
 int
-swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
-	       int dir)
+swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
+		     int dir, struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
 	void *addr;
@@ -727,7 +733,8 @@ swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
 				/* Don't panic here, we expect map_sg users
 				   to do proper error handling. */
 				swiotlb_full(hwdev, sg->length, dir, 0);
-				swiotlb_unmap_sg(hwdev, sgl, i, dir);
+				swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
+						       attrs);
 				sgl[0].dma_length = 0;
 				return 0;
 			}
@@ -738,14 +745,22 @@ swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
 	}
 	return nelems;
 }
+EXPORT_SYMBOL(swiotlb_map_sg_attrs);
+
+int
+swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
+	       int dir)
+{
+	return swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, NULL);
+}
 
 /*
  * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
  * concerning calls here are the same as for swiotlb_unmap_single() above.
  */
 void
-swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
-		 int dir)
+swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+		       int nelems, int dir, struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
 	int i;
@@ -760,6 +775,14 @@ swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
 			dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length);
 	}
 }
+EXPORT_SYMBOL(swiotlb_unmap_sg_attrs);
+
+void
+swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
+		 int dir)
+{
+	return swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, NULL);
+}
 
 /*
  * Make physical memory consistent for a set of streaming mode DMA translations
diff --git a/trunk/mm/Kconfig b/trunk/mm/Kconfig
index 0016ebd4dcba..3aa819d628c1 100644
--- a/trunk/mm/Kconfig
+++ b/trunk/mm/Kconfig
@@ -143,6 +143,18 @@ config MEMORY_HOTREMOVE
 	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
 	depends on MIGRATION
 
+#
+# If we have space for more page flags then we can enable additional
+# optimizations and functionality.
+#
+# Regular Sparsemem takes page flag bits for the sectionid if it does not
+# use a virtual memmap. Disable extended page flags for 32 bit platforms
+# that require the use of a sectionid in the page flags.
+#
+config PAGEFLAGS_EXTENDED
+	def_bool y
+	depends on 64BIT || SPARSEMEM_VMEMMAP || !NUMA || !SPARSEMEM
+
 # Heavily threaded applications may benefit from splitting the mm-wide
 # page_table_lock, so that faults on different parts of the user address
 # space can be handled with less contention: split it at this NR_CPUS.
diff --git a/trunk/mm/bootmem.c b/trunk/mm/bootmem.c
index b6791646143e..e8fb927392b9 100644
--- a/trunk/mm/bootmem.c
+++ b/trunk/mm/bootmem.c
@@ -461,6 +461,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 
 unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
 {
+	register_page_bootmem_info_node(pgdat);
 	return free_all_bootmem_core(pgdat);
 }
 
@@ -544,6 +545,37 @@ void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 	return __alloc_bootmem(size, align, goal);
 }
 
+#ifdef CONFIG_SPARSEMEM
+void * __init alloc_bootmem_section(unsigned long size,
+				    unsigned long section_nr)
+{
+	void *ptr;
+	unsigned long limit, goal, start_nr, end_nr, pfn;
+	struct pglist_data *pgdat;
+
+	pfn = section_nr_to_pfn(section_nr);
+	goal = PFN_PHYS(pfn);
+	limit = PFN_PHYS(section_nr_to_pfn(section_nr + 1)) - 1;
+	pgdat = NODE_DATA(early_pfn_to_nid(pfn));
+	ptr = __alloc_bootmem_core(pgdat->bdata, size, SMP_CACHE_BYTES, goal,
+				   limit);
+
+	if (!ptr)
+		return NULL;
+
+	start_nr = pfn_to_section_nr(PFN_DOWN(__pa(ptr)));
+	end_nr = pfn_to_section_nr(PFN_DOWN(__pa(ptr) + size));
+	if (start_nr != section_nr || end_nr != section_nr) {
+		printk(KERN_WARNING "alloc_bootmem failed on section %ld.\n",
+		       section_nr);
+		free_bootmem_core(pgdat->bdata, __pa(ptr), size);
+		ptr = NULL;
+	}
+
+	return ptr;
+}
+#endif
+
 #ifndef ARCH_LOW_ADDRESS_LIMIT
 #define ARCH_LOW_ADDRESS_LIMIT	0xffffffffUL
 #endif
diff --git a/trunk/mm/dmapool.c b/trunk/mm/dmapool.c
index 34aaac451a96..b1f0885dda22 100644
--- a/trunk/mm/dmapool.c
+++ b/trunk/mm/dmapool.c
@@ -37,6 +37,10 @@
 #include <linux/types.h>
 #include <linux/wait.h>
 
+#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB_DEBUG_ON)
+#define DMAPOOL_DEBUG 1
+#endif
+
 struct dma_pool {		/* the pool */
 	struct list_head page_list;
 	spinlock_t lock;
@@ -216,7 +220,7 @@ static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags)
 	page->vaddr = dma_alloc_coherent(pool->dev, pool->allocation,
 					 &page->dma, mem_flags);
 	if (page->vaddr) {
-#ifdef	CONFIG_DEBUG_SLAB
+#ifdef	DMAPOOL_DEBUG
 		memset(page->vaddr, POOL_POISON_FREED, pool->allocation);
 #endif
 		pool_initialise_page(pool, page);
@@ -239,7 +243,7 @@ static void pool_free_page(struct dma_pool *pool, struct dma_page *page)
 {
 	dma_addr_t dma = page->dma;
 
-#ifdef	CONFIG_DEBUG_SLAB
+#ifdef	DMAPOOL_DEBUG
 	memset(page->vaddr, POOL_POISON_FREED, pool->allocation);
 #endif
 	dma_free_coherent(pool->dev, pool->allocation, page->vaddr, dma);
@@ -336,7 +340,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 	page->offset = *(int *)(page->vaddr + offset);
 	retval = offset + page->vaddr;
 	*handle = offset + page->dma;
-#ifdef	CONFIG_DEBUG_SLAB
+#ifdef	DMAPOOL_DEBUG
 	memset(retval, POOL_POISON_ALLOCATED, pool->size);
 #endif
  done:
@@ -391,7 +395,7 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma)
 	}
 
 	offset = vaddr - page->vaddr;
-#ifdef	CONFIG_DEBUG_SLAB
+#ifdef	DMAPOOL_DEBUG
 	if ((dma - page->dma) != offset) {
 		if (pool->dev)
 			dev_err(pool->dev,
diff --git a/trunk/mm/fadvise.c b/trunk/mm/fadvise.c
index 3c0f1e99f5e4..343cfdfebd9e 100644
--- a/trunk/mm/fadvise.c
+++ b/trunk/mm/fadvise.c
@@ -49,7 +49,7 @@ asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 		goto out;
 	}
 
-	if (mapping->a_ops->get_xip_page) {
+	if (mapping->a_ops->get_xip_mem) {
 		switch (advice) {
 		case POSIX_FADV_NORMAL:
 		case POSIX_FADV_RANDOM:
diff --git a/trunk/mm/filemap.c b/trunk/mm/filemap.c
index 07e9d9258b48..239d36163bbe 100644
--- a/trunk/mm/filemap.c
+++ b/trunk/mm/filemap.c
@@ -576,10 +576,12 @@ EXPORT_SYMBOL(unlock_page);
  */
 void end_page_writeback(struct page *page)
 {
-	if (!TestClearPageReclaim(page) || rotate_reclaimable_page(page)) {
-		if (!test_clear_page_writeback(page))
-			BUG();
-	}
+	if (TestClearPageReclaim(page))
+		rotate_reclaimable_page(page);
+
+	if (!test_clear_page_writeback(page))
+		BUG();
+
 	smp_mb__after_clear_bit();
 	wake_up_page(page, PG_writeback);
 }
diff --git a/trunk/mm/filemap_xip.c b/trunk/mm/filemap_xip.c
index 5e598c42afd7..3e744abcce9d 100644
--- a/trunk/mm/filemap_xip.c
+++ b/trunk/mm/filemap_xip.c
@@ -15,6 +15,7 @@
 #include <linux/rmap.h>
 #include <linux/sched.h>
 #include <asm/tlbflush.h>
+#include <asm/io.h>
 
 /*
  * We do use our own empty page to avoid interference with other users
@@ -42,37 +43,41 @@ static struct page *xip_sparse_page(void)
 
 /*
  * This is a file read routine for execute in place files, and uses
- * the mapping->a_ops->get_xip_page() function for the actual low-level
+ * the mapping->a_ops->get_xip_mem() function for the actual low-level
  * stuff.
  *
  * Note the struct file* is not used at all.  It may be NULL.
  */
-static void
+static ssize_t
 do_xip_mapping_read(struct address_space *mapping,
 		    struct file_ra_state *_ra,
 		    struct file *filp,
-		    loff_t *ppos,
-		    read_descriptor_t *desc,
-		    read_actor_t actor)
+		    char __user *buf,
+		    size_t len,
+		    loff_t *ppos)
 {
 	struct inode *inode = mapping->host;
 	pgoff_t index, end_index;
 	unsigned long offset;
-	loff_t isize;
+	loff_t isize, pos;
+	size_t copied = 0, error = 0;
 
-	BUG_ON(!mapping->a_ops->get_xip_page);
+	BUG_ON(!mapping->a_ops->get_xip_mem);
 
-	index = *ppos >> PAGE_CACHE_SHIFT;
-	offset = *ppos & ~PAGE_CACHE_MASK;
+	pos = *ppos;
+	index = pos >> PAGE_CACHE_SHIFT;
+	offset = pos & ~PAGE_CACHE_MASK;
 
 	isize = i_size_read(inode);
 	if (!isize)
 		goto out;
 
 	end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
-	for (;;) {
-		struct page *page;
-		unsigned long nr, ret;
+	do {
+		unsigned long nr, left;
+		void *xip_mem;
+		unsigned long xip_pfn;
+		int zero = 0;
 
 		/* nr is the maximum number of bytes to copy from this page */
 		nr = PAGE_CACHE_SIZE;
@@ -85,19 +90,17 @@ do_xip_mapping_read(struct address_space *mapping,
 			}
 		}
 		nr = nr - offset;
+		if (nr > len)
+			nr = len;
 
-		page = mapping->a_ops->get_xip_page(mapping,
-			index*(PAGE_SIZE/512), 0);
-		if (!page)
-			goto no_xip_page;
-		if (unlikely(IS_ERR(page))) {
-			if (PTR_ERR(page) == -ENODATA) {
+		error = mapping->a_ops->get_xip_mem(mapping, index, 0,
+							&xip_mem, &xip_pfn);
+		if (unlikely(error)) {
+			if (error == -ENODATA) {
 				/* sparse */
-				page = ZERO_PAGE(0);
-			} else {
-				desc->error = PTR_ERR(page);
+				zero = 1;
+			} else
 				goto out;
-			}
 		}
 
 		/* If users can be writing to this page using arbitrary
@@ -105,10 +108,10 @@ do_xip_mapping_read(struct address_space *mapping,
 		 * before reading the page on the kernel side.
 		 */
 		if (mapping_writably_mapped(mapping))
-			flush_dcache_page(page);
+			/* address based flush */ ;
 
 		/*
-		 * Ok, we have the page, so now we can copy it to user space...
+		 * Ok, we have the mem, so now we can copy it to user space...
 		 *
 		 * The actor routine returns how many bytes were actually used..
 		 * NOTE! This may not be the same as how much of a user buffer
@@ -116,47 +119,38 @@ do_xip_mapping_read(struct address_space *mapping,
 		 * "pos" here (the actor routine has to update the user buffer
 		 * pointers and the remaining count).
 		 */
-		ret = actor(desc, page, offset, nr);
-		offset += ret;
-		index += offset >> PAGE_CACHE_SHIFT;
-		offset &= ~PAGE_CACHE_MASK;
+		if (!zero)
+			left = __copy_to_user(buf+copied, xip_mem+offset, nr);
+		else
+			left = __clear_user(buf + copied, nr);
 
-		if (ret == nr && desc->count)
-			continue;
-		goto out;
+		if (left) {
+			error = -EFAULT;
+			goto out;
+		}
 
-no_xip_page:
-		/* Did not get the page. Report it */
-		desc->error = -EIO;
-		goto out;
-	}
+		copied += (nr - left);
+		offset += (nr - left);
+		index += offset >> PAGE_CACHE_SHIFT;
+		offset &= ~PAGE_CACHE_MASK;
+	} while (copied < len);
 
 out:
-	*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
+	*ppos = pos + copied;
 	if (filp)
 		file_accessed(filp);
+
+	return (copied ? copied : error);
 }
 
 ssize_t
 xip_file_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
 {
-	read_descriptor_t desc;
-
 	if (!access_ok(VERIFY_WRITE, buf, len))
 		return -EFAULT;
 
-	desc.written = 0;
-	desc.arg.buf = buf;
-	desc.count = len;
-	desc.error = 0;
-
-	do_xip_mapping_read(filp->f_mapping, &filp->f_ra, filp,
-			    ppos, &desc, file_read_actor);
-
-	if (desc.written)
-		return desc.written;
-	else
-		return desc.error;
+	return do_xip_mapping_read(filp->f_mapping, &filp->f_ra, filp,
+			    buf, len, ppos);
 }
 EXPORT_SYMBOL_GPL(xip_file_read);
 
@@ -211,13 +205,16 @@ __xip_unmap (struct address_space * mapping,
  *
  * This function is derived from filemap_fault, but used for execute in place
  */
-static int xip_file_fault(struct vm_area_struct *area, struct vm_fault *vmf)
+static int xip_file_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	struct file *file = area->vm_file;
+	struct file *file = vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
-	struct page *page;
 	pgoff_t size;
+	void *xip_mem;
+	unsigned long xip_pfn;
+	struct page *page;
+	int error;
 
 	/* XXX: are VM_FAULT_ codes OK? */
 
@@ -225,35 +222,44 @@ static int xip_file_fault(struct vm_area_struct *area, struct vm_fault *vmf)
 	if (vmf->pgoff >= size)
 		return VM_FAULT_SIGBUS;
 
-	page = mapping->a_ops->get_xip_page(mapping,
-					vmf->pgoff*(PAGE_SIZE/512), 0);
-	if (!IS_ERR(page))
-		goto out;
-	if (PTR_ERR(page) != -ENODATA)
+	error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 0,
+						&xip_mem, &xip_pfn);
+	if (likely(!error))
+		goto found;
+	if (error != -ENODATA)
 		return VM_FAULT_OOM;
 
 	/* sparse block */
-	if ((area->vm_flags & (VM_WRITE | VM_MAYWRITE)) &&
-	    (area->vm_flags & (VM_SHARED| VM_MAYSHARE)) &&
+	if ((vma->vm_flags & (VM_WRITE | VM_MAYWRITE)) &&
+	    (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) &&
 	    (!(mapping->host->i_sb->s_flags & MS_RDONLY))) {
+		int err;
+
 		/* maybe shared writable, allocate new block */
-		page = mapping->a_ops->get_xip_page(mapping,
-					vmf->pgoff*(PAGE_SIZE/512), 1);
-		if (IS_ERR(page))
+		error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 1,
+							&xip_mem, &xip_pfn);
+		if (error)
 			return VM_FAULT_SIGBUS;
-		/* unmap page at pgoff from all other vmas */
+		/* unmap sparse mappings at pgoff from all other vmas */
 		__xip_unmap(mapping, vmf->pgoff);
+
+found:
+		err = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address,
+							xip_pfn);
+		if (err == -ENOMEM)
+			return VM_FAULT_OOM;
+		BUG_ON(err);
+		return VM_FAULT_NOPAGE;
 	} else {
 		/* not shared and writable, use xip_sparse_page() */
 		page = xip_sparse_page();
 		if (!page)
 			return VM_FAULT_OOM;
-	}
 
-out:
-	page_cache_get(page);
-	vmf->page = page;
-	return 0;
+		page_cache_get(page);
+		vmf->page = page;
+		return 0;
+	}
 }
 
 static struct vm_operations_struct xip_file_vm_ops = {
@@ -262,11 +268,11 @@ static struct vm_operations_struct xip_file_vm_ops = {
 
 int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
 {
-	BUG_ON(!file->f_mapping->a_ops->get_xip_page);
+	BUG_ON(!file->f_mapping->a_ops->get_xip_mem);
 
 	file_accessed(file);
 	vma->vm_ops = &xip_file_vm_ops;
-	vma->vm_flags |= VM_CAN_NONLINEAR;
+	vma->vm_flags |= VM_CAN_NONLINEAR | VM_MIXEDMAP;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xip_file_mmap);
@@ -279,17 +285,17 @@ __xip_file_write(struct file *filp, const char __user *buf,
 	const struct address_space_operations *a_ops = mapping->a_ops;
 	struct inode 	*inode = mapping->host;
 	long		status = 0;
-	struct page	*page;
 	size_t		bytes;
 	ssize_t		written = 0;
 
-	BUG_ON(!mapping->a_ops->get_xip_page);
+	BUG_ON(!mapping->a_ops->get_xip_mem);
 
 	do {
 		unsigned long index;
 		unsigned long offset;
 		size_t copied;
-		char *kaddr;
+		void *xip_mem;
+		unsigned long xip_pfn;
 
 		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
 		index = pos >> PAGE_CACHE_SHIFT;
@@ -297,28 +303,22 @@ __xip_file_write(struct file *filp, const char __user *buf,
 		if (bytes > count)
 			bytes = count;
 
-		page = a_ops->get_xip_page(mapping,
-					   index*(PAGE_SIZE/512), 0);
-		if (IS_ERR(page) && (PTR_ERR(page) == -ENODATA)) {
+		status = a_ops->get_xip_mem(mapping, index, 0,
+						&xip_mem, &xip_pfn);
+		if (status == -ENODATA) {
 			/* we allocate a new page unmap it */
-			page = a_ops->get_xip_page(mapping,
-						   index*(PAGE_SIZE/512), 1);
-			if (!IS_ERR(page))
+			status = a_ops->get_xip_mem(mapping, index, 1,
+							&xip_mem, &xip_pfn);
+			if (!status)
 				/* unmap page at pgoff from all other vmas */
 				__xip_unmap(mapping, index);
 		}
 
-		if (IS_ERR(page)) {
-			status = PTR_ERR(page);
+		if (status)
 			break;
-		}
 
-		fault_in_pages_readable(buf, bytes);
-		kaddr = kmap_atomic(page, KM_USER0);
 		copied = bytes -
-			__copy_from_user_inatomic_nocache(kaddr + offset, buf, bytes);
-		kunmap_atomic(kaddr, KM_USER0);
-		flush_dcache_page(page);
+			__copy_from_user_nocache(xip_mem + offset, buf, bytes);
 
 		if (likely(copied > 0)) {
 			status = copied;
@@ -398,7 +398,7 @@ EXPORT_SYMBOL_GPL(xip_file_write);
 
 /*
  * truncate a page used for execute in place
- * functionality is analog to block_truncate_page but does use get_xip_page
+ * functionality is analog to block_truncate_page but does use get_xip_mem
  * to get the page instead of page cache
  */
 int
@@ -408,9 +408,11 @@ xip_truncate_page(struct address_space *mapping, loff_t from)
 	unsigned offset = from & (PAGE_CACHE_SIZE-1);
 	unsigned blocksize;
 	unsigned length;
-	struct page *page;
+	void *xip_mem;
+	unsigned long xip_pfn;
+	int err;
 
-	BUG_ON(!mapping->a_ops->get_xip_page);
+	BUG_ON(!mapping->a_ops->get_xip_mem);
 
 	blocksize = 1 << mapping->host->i_blkbits;
 	length = offset & (blocksize - 1);
@@ -421,18 +423,16 @@ xip_truncate_page(struct address_space *mapping, loff_t from)
 
 	length = blocksize - length;
 
-	page = mapping->a_ops->get_xip_page(mapping,
-					    index*(PAGE_SIZE/512), 0);
-	if (!page)
-		return -ENOMEM;
-	if (unlikely(IS_ERR(page))) {
-		if (PTR_ERR(page) == -ENODATA)
+	err = mapping->a_ops->get_xip_mem(mapping, index, 0,
+						&xip_mem, &xip_pfn);
+	if (unlikely(err)) {
+		if (err == -ENODATA)
 			/* Hole? No need to truncate */
 			return 0;
 		else
-			return PTR_ERR(page);
+			return err;
 	}
-	zero_user(page, offset, length);
+	memset(xip_mem + offset, 0, length);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xip_truncate_page);
diff --git a/trunk/mm/hugetlb.c b/trunk/mm/hugetlb.c
index 51c9e2c01640..bbf953eeb58b 100644
--- a/trunk/mm/hugetlb.c
+++ b/trunk/mm/hugetlb.c
@@ -95,13 +95,16 @@ static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma,
 	int nid;
 	struct page *page = NULL;
 	struct mempolicy *mpol;
+	nodemask_t *nodemask;
 	struct zonelist *zonelist = huge_zonelist(vma, address,
-					htlb_alloc_mask, &mpol);
-	struct zone **z;
-
-	for (z = zonelist->zones; *z; z++) {
-		nid = zone_to_nid(*z);
-		if (cpuset_zone_allowed_softwall(*z, htlb_alloc_mask) &&
+					htlb_alloc_mask, &mpol, &nodemask);
+	struct zone *zone;
+	struct zoneref *z;
+
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+						MAX_NR_ZONES - 1, nodemask) {
+		nid = zone_to_nid(zone);
+		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) &&
 		    !list_empty(&hugepage_freelists[nid])) {
 			page = list_entry(hugepage_freelists[nid].next,
 					  struct page, lru);
@@ -113,7 +116,7 @@ static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma,
 			break;
 		}
 	}
-	mpol_free(mpol);	/* unref if mpol !NULL */
+	mpol_cond_put(mpol);
 	return page;
 }
 
@@ -129,6 +132,7 @@ static void update_and_free_page(struct page *page)
 	}
 	set_compound_page_dtor(page, NULL);
 	set_page_refcounted(page);
+	arch_release_hugepage(page);
 	__free_pages(page, HUGETLB_PAGE_ORDER);
 }
 
@@ -195,9 +199,14 @@ static struct page *alloc_fresh_huge_page_node(int nid)
 	struct page *page;
 
 	page = alloc_pages_node(nid,
-		htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|__GFP_NOWARN,
+		htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
+						__GFP_REPEAT|__GFP_NOWARN,
 		HUGETLB_PAGE_ORDER);
 	if (page) {
+		if (arch_prepare_hugepage(page)) {
+			__free_pages(page, HUGETLB_PAGE_ORDER);
+			return NULL;
+		}
 		set_compound_page_dtor(page, free_huge_page);
 		spin_lock(&hugetlb_lock);
 		nr_huge_pages++;
@@ -239,6 +248,11 @@ static int alloc_fresh_huge_page(void)
 		hugetlb_next_nid = next_nid;
 	} while (!page && hugetlb_next_nid != start_nid);
 
+	if (ret)
+		count_vm_event(HTLB_BUDDY_PGALLOC);
+	else
+		count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
+
 	return ret;
 }
 
@@ -281,7 +295,8 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
 	}
 	spin_unlock(&hugetlb_lock);
 
-	page = alloc_pages(htlb_alloc_mask|__GFP_COMP|__GFP_NOWARN,
+	page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
+					__GFP_REPEAT|__GFP_NOWARN,
 					HUGETLB_PAGE_ORDER);
 
 	spin_lock(&hugetlb_lock);
@@ -299,9 +314,11 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
 		 */
 		nr_huge_pages_node[nid]++;
 		surplus_huge_pages_node[nid]++;
+		__count_vm_event(HTLB_BUDDY_PGALLOC);
 	} else {
 		nr_huge_pages--;
 		surplus_huge_pages--;
+		__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
 	}
 	spin_unlock(&hugetlb_lock);
 
@@ -369,11 +386,19 @@ static int gather_surplus_pages(int delta)
 	resv_huge_pages += delta;
 	ret = 0;
 free:
+	/* Free the needed pages to the hugetlb pool */
 	list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
+		if ((--needed) < 0)
+			break;
 		list_del(&page->lru);
-		if ((--needed) >= 0)
-			enqueue_huge_page(page);
-		else {
+		enqueue_huge_page(page);
+	}
+
+	/* Free unnecessary surplus pages to the buddy allocator */
+	if (!list_empty(&surplus_list)) {
+		spin_unlock(&hugetlb_lock);
+		list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
+			list_del(&page->lru);
 			/*
 			 * The page has a reference count of zero already, so
 			 * call free_huge_page directly instead of using
@@ -381,10 +406,9 @@ static int gather_surplus_pages(int delta)
 			 * unlocked which is safe because free_huge_page takes
 			 * hugetlb_lock before deciding how to free the page.
 			 */
-			spin_unlock(&hugetlb_lock);
 			free_huge_page(page);
-			spin_lock(&hugetlb_lock);
 		}
+		spin_lock(&hugetlb_lock);
 	}
 
 	return ret;
@@ -718,7 +742,7 @@ static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
 		entry =
 		    pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
 	} else {
-		entry = pte_wrprotect(mk_pte(page, vma->vm_page_prot));
+		entry = huge_pte_wrprotect(mk_pte(page, vma->vm_page_prot));
 	}
 	entry = pte_mkyoung(entry);
 	entry = pte_mkhuge(entry);
@@ -731,8 +755,8 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
 {
 	pte_t entry;
 
-	entry = pte_mkwrite(pte_mkdirty(*ptep));
-	if (ptep_set_access_flags(vma, address, ptep, entry, 1)) {
+	entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep)));
+	if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) {
 		update_mmu_cache(vma, address, entry);
 	}
 }
@@ -762,10 +786,10 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 
 		spin_lock(&dst->page_table_lock);
 		spin_lock(&src->page_table_lock);
-		if (!pte_none(*src_pte)) {
+		if (!huge_pte_none(huge_ptep_get(src_pte))) {
 			if (cow)
-				ptep_set_wrprotect(src, addr, src_pte);
-			entry = *src_pte;
+				huge_ptep_set_wrprotect(src, addr, src_pte);
+			entry = huge_ptep_get(src_pte);
 			ptepage = pte_page(entry);
 			get_page(ptepage);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
@@ -809,7 +833,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 			continue;
 
 		pte = huge_ptep_get_and_clear(mm, address, ptep);
-		if (pte_none(pte))
+		if (huge_pte_none(pte))
 			continue;
 
 		page = pte_page(pte);
@@ -873,8 +897,9 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 	spin_lock(&mm->page_table_lock);
 
 	ptep = huge_pte_offset(mm, address & HPAGE_MASK);
-	if (likely(pte_same(*ptep, pte))) {
+	if (likely(pte_same(huge_ptep_get(ptep), pte))) {
 		/* Break COW */
+		huge_ptep_clear_flush(vma, address, ptep);
 		set_huge_pte_at(mm, address, ptep,
 				make_huge_pte(vma, new_page, 1));
 		/* Make the old page be freed below */
@@ -942,7 +967,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto backout;
 
 	ret = 0;
-	if (!pte_none(*ptep))
+	if (!huge_pte_none(huge_ptep_get(ptep)))
 		goto backout;
 
 	new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
@@ -984,8 +1009,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * the same page in the page cache.
 	 */
 	mutex_lock(&hugetlb_instantiation_mutex);
-	entry = *ptep;
-	if (pte_none(entry)) {
+	entry = huge_ptep_get(ptep);
+	if (huge_pte_none(entry)) {
 		ret = hugetlb_no_page(mm, vma, address, ptep, write_access);
 		mutex_unlock(&hugetlb_instantiation_mutex);
 		return ret;
@@ -995,7 +1020,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	spin_lock(&mm->page_table_lock);
 	/* Check for a racing update before calling hugetlb_cow */
-	if (likely(pte_same(entry, *ptep)))
+	if (likely(pte_same(entry, huge_ptep_get(ptep))))
 		if (write_access && !pte_write(entry))
 			ret = hugetlb_cow(mm, vma, address, ptep, entry);
 	spin_unlock(&mm->page_table_lock);
@@ -1025,7 +1050,8 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		pte = huge_pte_offset(mm, vaddr & HPAGE_MASK);
 
-		if (!pte || pte_none(*pte) || (write && !pte_write(*pte))) {
+		if (!pte || huge_pte_none(huge_ptep_get(pte)) ||
+		    (write && !pte_write(huge_ptep_get(pte)))) {
 			int ret;
 
 			spin_unlock(&mm->page_table_lock);
@@ -1041,7 +1067,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		}
 
 		pfn_offset = (vaddr & ~HPAGE_MASK) >> PAGE_SHIFT;
-		page = pte_page(*pte);
+		page = pte_page(huge_ptep_get(pte));
 same_page:
 		if (pages) {
 			get_page(page);
@@ -1090,7 +1116,7 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 			continue;
 		if (huge_pmd_unshare(mm, &address, ptep))
 			continue;
-		if (!pte_none(*ptep)) {
+		if (!huge_pte_none(huge_ptep_get(ptep))) {
 			pte = huge_ptep_get_and_clear(mm, address, ptep);
 			pte = pte_mkhuge(pte_modify(pte, newprot));
 			set_huge_pte_at(mm, address, ptep, pte);
diff --git a/trunk/mm/internal.h b/trunk/mm/internal.h
index 789727309f4d..0034e947e4bc 100644
--- a/trunk/mm/internal.h
+++ b/trunk/mm/internal.h
@@ -34,8 +34,7 @@ static inline void __put_page(struct page *page)
 	atomic_dec(&page->_count);
 }
 
-extern void __init __free_pages_bootmem(struct page *page,
-						unsigned int order);
+extern void __free_pages_bootmem(struct page *page, unsigned int order);
 
 /*
  * function for dealing with page's order in buddy system.
diff --git a/trunk/mm/madvise.c b/trunk/mm/madvise.c
index 93ee375b38e7..23a0ec3e0ea0 100644
--- a/trunk/mm/madvise.c
+++ b/trunk/mm/madvise.c
@@ -112,7 +112,7 @@ static long madvise_willneed(struct vm_area_struct * vma,
 	if (!file)
 		return -EBADF;
 
-	if (file->f_mapping->a_ops->get_xip_page) {
+	if (file->f_mapping->a_ops->get_xip_mem) {
 		/* no bad return value, but ignore advice */
 		return 0;
 	}
diff --git a/trunk/mm/memcontrol.c b/trunk/mm/memcontrol.c
index 2e0bfc93484b..33add96cd5fb 100644
--- a/trunk/mm/memcontrol.c
+++ b/trunk/mm/memcontrol.c
@@ -26,15 +26,18 @@
 #include <linux/backing-dev.h>
 #include <linux/bit_spinlock.h>
 #include <linux/rcupdate.h>
+#include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/spinlock.h>
 #include <linux/fs.h>
 #include <linux/seq_file.h>
+#include <linux/vmalloc.h>
 
 #include <asm/uaccess.h>
 
 struct cgroup_subsys mem_cgroup_subsys;
 static const int MEM_CGROUP_RECLAIM_RETRIES = 5;
+static struct kmem_cache *page_cgroup_cache;
 
 /*
  * Statistics for memory cgroup.
@@ -236,26 +239,12 @@ static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
 				css);
 }
 
-static struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
+struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 {
 	return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
 				struct mem_cgroup, css);
 }
 
-void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p)
-{
-	struct mem_cgroup *mem;
-
-	mem = mem_cgroup_from_task(p);
-	css_get(&mem->css);
-	mm->mem_cgroup = mem;
-}
-
-void mm_free_cgroup(struct mm_struct *mm)
-{
-	css_put(&mm->mem_cgroup->css);
-}
-
 static inline int page_cgroup_locked(struct page *page)
 {
 	return bit_spin_is_locked(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
@@ -287,10 +276,10 @@ static void unlock_page_cgroup(struct page *page)
 	bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
 }
 
-static void __mem_cgroup_remove_list(struct page_cgroup *pc)
+static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
+			struct page_cgroup *pc)
 {
 	int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
-	struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
 
 	if (from)
 		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) -= 1;
@@ -301,10 +290,10 @@ static void __mem_cgroup_remove_list(struct page_cgroup *pc)
 	list_del_init(&pc->lru);
 }
 
-static void __mem_cgroup_add_list(struct page_cgroup *pc)
+static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
+				struct page_cgroup *pc)
 {
 	int to = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
-	struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
 
 	if (!to) {
 		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;
@@ -476,6 +465,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 	int zid = zone_idx(z);
 	struct mem_cgroup_per_zone *mz;
 
+	BUG_ON(!mem_cont);
 	mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
 	if (active)
 		src = &mz->active_list;
@@ -560,7 +550,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 	}
 	unlock_page_cgroup(page);
 
-	pc = kzalloc(sizeof(struct page_cgroup), gfp_mask);
+	pc = kmem_cache_zalloc(page_cgroup_cache, gfp_mask);
 	if (pc == NULL)
 		goto err;
 
@@ -574,7 +564,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 		mm = &init_mm;
 
 	rcu_read_lock();
-	mem = rcu_dereference(mm->mem_cgroup);
+	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
 	/*
 	 * For every charge from the cgroup, increment reference count
 	 */
@@ -602,7 +592,6 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 			mem_cgroup_out_of_memory(mem, gfp_mask);
 			goto out;
 		}
-		congestion_wait(WRITE, HZ/10);
 	}
 
 	pc->ref_cnt = 1;
@@ -610,7 +599,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 	pc->page = page;
 	pc->flags = PAGE_CGROUP_FLAG_ACTIVE;
 	if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE)
-		pc->flags |= PAGE_CGROUP_FLAG_CACHE;
+		pc->flags = PAGE_CGROUP_FLAG_CACHE;
 
 	lock_page_cgroup(page);
 	if (page_get_page_cgroup(page)) {
@@ -622,14 +611,14 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 		 */
 		res_counter_uncharge(&mem->res, PAGE_SIZE);
 		css_put(&mem->css);
-		kfree(pc);
+		kmem_cache_free(page_cgroup_cache, pc);
 		goto retry;
 	}
 	page_assign_page_cgroup(page, pc);
 
 	mz = page_cgroup_zoneinfo(pc);
 	spin_lock_irqsave(&mz->lru_lock, flags);
-	__mem_cgroup_add_list(pc);
+	__mem_cgroup_add_list(mz, pc);
 	spin_unlock_irqrestore(&mz->lru_lock, flags);
 
 	unlock_page_cgroup(page);
@@ -637,7 +626,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 	return 0;
 out:
 	css_put(&mem->css);
-	kfree(pc);
+	kmem_cache_free(page_cgroup_cache, pc);
 err:
 	return -ENOMEM;
 }
@@ -685,7 +674,7 @@ void mem_cgroup_uncharge_page(struct page *page)
 	if (--(pc->ref_cnt) == 0) {
 		mz = page_cgroup_zoneinfo(pc);
 		spin_lock_irqsave(&mz->lru_lock, flags);
-		__mem_cgroup_remove_list(pc);
+		__mem_cgroup_remove_list(mz, pc);
 		spin_unlock_irqrestore(&mz->lru_lock, flags);
 
 		page_assign_page_cgroup(page, NULL);
@@ -695,7 +684,7 @@ void mem_cgroup_uncharge_page(struct page *page)
 		res_counter_uncharge(&mem->res, PAGE_SIZE);
 		css_put(&mem->css);
 
-		kfree(pc);
+		kmem_cache_free(page_cgroup_cache, pc);
 		return;
 	}
 
@@ -747,7 +736,7 @@ void mem_cgroup_page_migration(struct page *page, struct page *newpage)
 
 	mz = page_cgroup_zoneinfo(pc);
 	spin_lock_irqsave(&mz->lru_lock, flags);
-	__mem_cgroup_remove_list(pc);
+	__mem_cgroup_remove_list(mz, pc);
 	spin_unlock_irqrestore(&mz->lru_lock, flags);
 
 	page_assign_page_cgroup(page, NULL);
@@ -759,7 +748,7 @@ void mem_cgroup_page_migration(struct page *page, struct page *newpage)
 
 	mz = page_cgroup_zoneinfo(pc);
 	spin_lock_irqsave(&mz->lru_lock, flags);
-	__mem_cgroup_add_list(pc);
+	__mem_cgroup_add_list(mz, pc);
 	spin_unlock_irqrestore(&mz->lru_lock, flags);
 
 	unlock_page_cgroup(newpage);
@@ -853,13 +842,10 @@ static int mem_cgroup_write_strategy(char *buf, unsigned long long *tmp)
 	return 0;
 }
 
-static ssize_t mem_cgroup_read(struct cgroup *cont,
-			struct cftype *cft, struct file *file,
-			char __user *userbuf, size_t nbytes, loff_t *ppos)
+static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
 {
-	return res_counter_read(&mem_cgroup_from_cont(cont)->res,
-				cft->private, userbuf, nbytes, ppos,
-				NULL);
+	return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res,
+				    cft->private);
 }
 
 static ssize_t mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
@@ -871,27 +857,25 @@ static ssize_t mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
 				mem_cgroup_write_strategy);
 }
 
-static ssize_t mem_force_empty_write(struct cgroup *cont,
-				struct cftype *cft, struct file *file,
-				const char __user *userbuf,
-				size_t nbytes, loff_t *ppos)
+static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
 {
-	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
-	int ret = mem_cgroup_force_empty(mem);
-	if (!ret)
-		ret = nbytes;
-	return ret;
+	struct mem_cgroup *mem;
+
+	mem = mem_cgroup_from_cont(cont);
+	switch (event) {
+	case RES_MAX_USAGE:
+		res_counter_reset_max(&mem->res);
+		break;
+	case RES_FAILCNT:
+		res_counter_reset_failcnt(&mem->res);
+		break;
+	}
+	return 0;
 }
 
-/*
- * Note: This should be removed if cgroup supports write-only file.
- */
-static ssize_t mem_force_empty_read(struct cgroup *cont,
-				struct cftype *cft,
-				struct file *file, char __user *userbuf,
-				size_t nbytes, loff_t *ppos)
+static int mem_force_empty_write(struct cgroup *cont, unsigned int event)
 {
-	return -EINVAL;
+	return mem_cgroup_force_empty(mem_cgroup_from_cont(cont));
 }
 
 static const struct mem_cgroup_stat_desc {
@@ -902,9 +886,9 @@ static const struct mem_cgroup_stat_desc {
 	[MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
 };
 
-static int mem_control_stat_show(struct seq_file *m, void *arg)
+static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
+				 struct cgroup_map_cb *cb)
 {
-	struct cgroup *cont = m->private;
 	struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);
 	struct mem_cgroup_stat *stat = &mem_cont->stat;
 	int i;
@@ -914,8 +898,7 @@ static int mem_control_stat_show(struct seq_file *m, void *arg)
 
 		val = mem_cgroup_read_stat(stat, i);
 		val *= mem_cgroup_stat_desc[i].unit;
-		seq_printf(m, "%s %lld\n", mem_cgroup_stat_desc[i].msg,
-				(long long)val);
+		cb->fill(cb, mem_cgroup_stat_desc[i].msg, val);
 	}
 	/* showing # of active pages */
 	{
@@ -925,52 +908,43 @@ static int mem_control_stat_show(struct seq_file *m, void *arg)
 						MEM_CGROUP_ZSTAT_INACTIVE);
 		active = mem_cgroup_get_all_zonestat(mem_cont,
 						MEM_CGROUP_ZSTAT_ACTIVE);
-		seq_printf(m, "active %ld\n", (active) * PAGE_SIZE);
-		seq_printf(m, "inactive %ld\n", (inactive) * PAGE_SIZE);
+		cb->fill(cb, "active", (active) * PAGE_SIZE);
+		cb->fill(cb, "inactive", (inactive) * PAGE_SIZE);
 	}
 	return 0;
 }
 
-static const struct file_operations mem_control_stat_file_operations = {
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
-static int mem_control_stat_open(struct inode *unused, struct file *file)
-{
-	/* XXX __d_cont */
-	struct cgroup *cont = file->f_dentry->d_parent->d_fsdata;
-
-	file->f_op = &mem_control_stat_file_operations;
-	return single_open(file, mem_control_stat_show, cont);
-}
-
 static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "usage_in_bytes",
 		.private = RES_USAGE,
-		.read = mem_cgroup_read,
+		.read_u64 = mem_cgroup_read,
+	},
+	{
+		.name = "max_usage_in_bytes",
+		.private = RES_MAX_USAGE,
+		.trigger = mem_cgroup_reset,
+		.read_u64 = mem_cgroup_read,
 	},
 	{
 		.name = "limit_in_bytes",
 		.private = RES_LIMIT,
 		.write = mem_cgroup_write,
-		.read = mem_cgroup_read,
+		.read_u64 = mem_cgroup_read,
 	},
 	{
 		.name = "failcnt",
 		.private = RES_FAILCNT,
-		.read = mem_cgroup_read,
+		.trigger = mem_cgroup_reset,
+		.read_u64 = mem_cgroup_read,
 	},
 	{
 		.name = "force_empty",
-		.write = mem_force_empty_write,
-		.read = mem_force_empty_read,
+		.trigger = mem_force_empty_write,
 	},
 	{
 		.name = "stat",
-		.open = mem_control_stat_open,
+		.read_map = mem_control_stat_show,
 	},
 };
 
@@ -1010,6 +984,29 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
 	kfree(mem->info.nodeinfo[node]);
 }
 
+static struct mem_cgroup *mem_cgroup_alloc(void)
+{
+	struct mem_cgroup *mem;
+
+	if (sizeof(*mem) < PAGE_SIZE)
+		mem = kmalloc(sizeof(*mem), GFP_KERNEL);
+	else
+		mem = vmalloc(sizeof(*mem));
+
+	if (mem)
+		memset(mem, 0, sizeof(*mem));
+	return mem;
+}
+
+static void mem_cgroup_free(struct mem_cgroup *mem)
+{
+	if (sizeof(*mem) < PAGE_SIZE)
+		kfree(mem);
+	else
+		vfree(mem);
+}
+
+
 static struct cgroup_subsys_state *
 mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 {
@@ -1018,17 +1015,15 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 
 	if (unlikely((cont->parent) == NULL)) {
 		mem = &init_mem_cgroup;
-		init_mm.mem_cgroup = mem;
-	} else
-		mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL);
-
-	if (mem == NULL)
-		return ERR_PTR(-ENOMEM);
+		page_cgroup_cache = KMEM_CACHE(page_cgroup, SLAB_PANIC);
+	} else {
+		mem = mem_cgroup_alloc();
+		if (!mem)
+			return ERR_PTR(-ENOMEM);
+	}
 
 	res_counter_init(&mem->res);
 
-	memset(&mem->info, 0, sizeof(mem->info));
-
 	for_each_node_state(node, N_POSSIBLE)
 		if (alloc_mem_cgroup_per_zone_info(mem, node))
 			goto free_out;
@@ -1038,7 +1033,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	for_each_node_state(node, N_POSSIBLE)
 		free_mem_cgroup_per_zone_info(mem, node);
 	if (cont->parent != NULL)
-		kfree(mem);
+		mem_cgroup_free(mem);
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -1058,7 +1053,7 @@ static void mem_cgroup_destroy(struct cgroup_subsys *ss,
 	for_each_node_state(node, N_POSSIBLE)
 		free_mem_cgroup_per_zone_info(mem, node);
 
-	kfree(mem_cgroup_from_cont(cont));
+	mem_cgroup_free(mem_cgroup_from_cont(cont));
 }
 
 static int mem_cgroup_populate(struct cgroup_subsys *ss,
@@ -1098,10 +1093,6 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
 	if (!thread_group_leader(p))
 		goto out;
 
-	css_get(&mem->css);
-	rcu_assign_pointer(mm->mem_cgroup, mem);
-	css_put(&old_mem->css);
-
 out:
 	mmput(mm);
 }
diff --git a/trunk/mm/memory.c b/trunk/mm/memory.c
index 0d14d1e58a5f..bbab1e37055e 100644
--- a/trunk/mm/memory.c
+++ b/trunk/mm/memory.c
@@ -371,57 +371,93 @@ static inline int is_cow_mapping(unsigned int flags)
 }
 
 /*
- * This function gets the "struct page" associated with a pte.
+ * vm_normal_page -- This function gets the "struct page" associated with a pte.
  *
- * NOTE! Some mappings do not have "struct pages". A raw PFN mapping
- * will have each page table entry just pointing to a raw page frame
- * number, and as far as the VM layer is concerned, those do not have
- * pages associated with them - even if the PFN might point to memory
- * that otherwise is perfectly fine and has a "struct page".
+ * "Special" mappings do not wish to be associated with a "struct page" (either
+ * it doesn't exist, or it exists but they don't want to touch it). In this
+ * case, NULL is returned here. "Normal" mappings do have a struct page.
  *
- * The way we recognize those mappings is through the rules set up
- * by "remap_pfn_range()": the vma will have the VM_PFNMAP bit set,
- * and the vm_pgoff will point to the first PFN mapped: thus every
- * page that is a raw mapping will always honor the rule
+ * There are 2 broad cases. Firstly, an architecture may define a pte_special()
+ * pte bit, in which case this function is trivial. Secondly, an architecture
+ * may not have a spare pte bit, which requires a more complicated scheme,
+ * described below.
+ *
+ * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a
+ * special mapping (even if there are underlying and valid "struct pages").
+ * COWed pages of a VM_PFNMAP are always normal.
+ *
+ * The way we recognize COWed pages within VM_PFNMAP mappings is through the
+ * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit
+ * set, and the vm_pgoff will point to the first PFN mapped: thus every special
+ * mapping will always honor the rule
  *
  *	pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT)
  *
- * and if that isn't true, the page has been COW'ed (in which case it
- * _does_ have a "struct page" associated with it even if it is in a
- * VM_PFNMAP range).
+ * And for normal mappings this is false.
+ *
+ * This restricts such mappings to be a linear translation from virtual address
+ * to pfn. To get around this restriction, we allow arbitrary mappings so long
+ * as the vma is not a COW mapping; in that case, we know that all ptes are
+ * special (because none can have been COWed).
+ *
+ *
+ * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP.
+ *
+ * VM_MIXEDMAP mappings can likewise contain memory with or without "struct
+ * page" backing, however the difference is that _all_ pages with a struct
+ * page (that is, those where pfn_valid is true) are refcounted and considered
+ * normal pages by the VM. The disadvantage is that pages are refcounted
+ * (which can be slower and simply not an option for some PFNMAP users). The
+ * advantage is that we don't have to follow the strict linearity rule of
+ * PFNMAP mappings in order to support COWable mappings.
+ *
  */
-struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
+#ifdef __HAVE_ARCH_PTE_SPECIAL
+# define HAVE_PTE_SPECIAL 1
+#else
+# define HAVE_PTE_SPECIAL 0
+#endif
+struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+				pte_t pte)
 {
-	unsigned long pfn = pte_pfn(pte);
+	unsigned long pfn;
 
-	if (unlikely(vma->vm_flags & VM_PFNMAP)) {
-		unsigned long off = (addr - vma->vm_start) >> PAGE_SHIFT;
-		if (pfn == vma->vm_pgoff + off)
-			return NULL;
-		if (!is_cow_mapping(vma->vm_flags))
-			return NULL;
+	if (HAVE_PTE_SPECIAL) {
+		if (likely(!pte_special(pte))) {
+			VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+			return pte_page(pte);
+		}
+		VM_BUG_ON(!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)));
+		return NULL;
 	}
 
-#ifdef CONFIG_DEBUG_VM
-	/*
-	 * Add some anal sanity checks for now. Eventually,
-	 * we should just do "return pfn_to_page(pfn)", but
-	 * in the meantime we check that we get a valid pfn,
-	 * and that the resulting page looks ok.
-	 */
-	if (unlikely(!pfn_valid(pfn))) {
-		print_bad_pte(vma, pte, addr);
-		return NULL;
+	/* !HAVE_PTE_SPECIAL case follows: */
+
+	pfn = pte_pfn(pte);
+
+	if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
+		if (vma->vm_flags & VM_MIXEDMAP) {
+			if (!pfn_valid(pfn))
+				return NULL;
+			goto out;
+		} else {
+			unsigned long off;
+			off = (addr - vma->vm_start) >> PAGE_SHIFT;
+			if (pfn == vma->vm_pgoff + off)
+				return NULL;
+			if (!is_cow_mapping(vma->vm_flags))
+				return NULL;
+		}
 	}
-#endif
+
+	VM_BUG_ON(!pfn_valid(pfn));
 
 	/*
-	 * NOTE! We still have PageReserved() pages in the page 
-	 * tables. 
+	 * NOTE! We still have PageReserved() pages in the page tables.
 	 *
-	 * The PAGE_ZERO() pages and various VDSO mappings can
-	 * cause them to exist.
+	 * eg. VDSO mappings can cause them to exist.
 	 */
+out:
 	return pfn_to_page(pfn);
 }
 
@@ -1057,8 +1093,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		if (pages)
 			foll_flags |= FOLL_GET;
 		if (!write && !(vma->vm_flags & VM_LOCKED) &&
-		    (!vma->vm_ops || (!vma->vm_ops->nopage &&
-					!vma->vm_ops->fault)))
+		    (!vma->vm_ops || !vma->vm_ops->fault))
 			foll_flags |= FOLL_ANON;
 
 		do {
@@ -1141,8 +1176,10 @@ pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
  * old drivers should use this, and they needed to mark their
  * pages reserved for the old functions anyway.
  */
-static int insert_page(struct mm_struct *mm, unsigned long addr, struct page *page, pgprot_t prot)
+static int insert_page(struct vm_area_struct *vma, unsigned long addr,
+			struct page *page, pgprot_t prot)
 {
+	struct mm_struct *mm = vma->vm_mm;
 	int retval;
 	pte_t *pte;
 	spinlock_t *ptl;
@@ -1202,40 +1239,26 @@ static int insert_page(struct mm_struct *mm, unsigned long addr, struct page *pa
  *
  * The page does not need to be reserved.
  */
-int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page)
+int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
+			struct page *page)
 {
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return -EFAULT;
 	if (!page_count(page))
 		return -EINVAL;
 	vma->vm_flags |= VM_INSERTPAGE;
-	return insert_page(vma->vm_mm, addr, page, vma->vm_page_prot);
+	return insert_page(vma, addr, page, vma->vm_page_prot);
 }
 EXPORT_SYMBOL(vm_insert_page);
 
-/**
- * vm_insert_pfn - insert single pfn into user vma
- * @vma: user vma to map to
- * @addr: target user address of this page
- * @pfn: source kernel pfn
- *
- * Similar to vm_inert_page, this allows drivers to insert individual pages
- * they've allocated into a user vma. Same comments apply.
- *
- * This function should only be called from a vm_ops->fault handler, and
- * in that case the handler should return NULL.
- */
-int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
-		unsigned long pfn)
+static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long pfn, pgprot_t prot)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	int retval;
 	pte_t *pte, entry;
 	spinlock_t *ptl;
 
-	BUG_ON(!(vma->vm_flags & VM_PFNMAP));
-	BUG_ON(is_cow_mapping(vma->vm_flags));
-
 	retval = -ENOMEM;
 	pte = get_locked_pte(mm, addr, &ptl);
 	if (!pte)
@@ -1245,19 +1268,74 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 		goto out_unlock;
 
 	/* Ok, finally just insert the thing.. */
-	entry = pfn_pte(pfn, vma->vm_page_prot);
+	entry = pte_mkspecial(pfn_pte(pfn, prot));
 	set_pte_at(mm, addr, pte, entry);
-	update_mmu_cache(vma, addr, entry);
+	update_mmu_cache(vma, addr, entry); /* XXX: why not for insert_page? */
 
 	retval = 0;
 out_unlock:
 	pte_unmap_unlock(pte, ptl);
-
 out:
 	return retval;
 }
+
+/**
+ * vm_insert_pfn - insert single pfn into user vma
+ * @vma: user vma to map to
+ * @addr: target user address of this page
+ * @pfn: source kernel pfn
+ *
+ * Similar to vm_inert_page, this allows drivers to insert individual pages
+ * they've allocated into a user vma. Same comments apply.
+ *
+ * This function should only be called from a vm_ops->fault handler, and
+ * in that case the handler should return NULL.
+ */
+int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long pfn)
+{
+	/*
+	 * Technically, architectures with pte_special can avoid all these
+	 * restrictions (same for remap_pfn_range).  However we would like
+	 * consistency in testing and feature parity among all, so we should
+	 * try to keep these invariants in place for everybody.
+	 */
+	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
+	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
+						(VM_PFNMAP|VM_MIXEDMAP));
+	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
+	BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));
+
+	if (addr < vma->vm_start || addr >= vma->vm_end)
+		return -EFAULT;
+	return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+}
 EXPORT_SYMBOL(vm_insert_pfn);
 
+int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long pfn)
+{
+	BUG_ON(!(vma->vm_flags & VM_MIXEDMAP));
+
+	if (addr < vma->vm_start || addr >= vma->vm_end)
+		return -EFAULT;
+
+	/*
+	 * If we don't have pte special, then we have to use the pfn_valid()
+	 * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*
+	 * refcount the page if pfn_valid is true (hence insert_page rather
+	 * than insert_pfn).
+	 */
+	if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) {
+		struct page *page;
+
+		page = pfn_to_page(pfn);
+		return insert_page(vma, addr, page, vma->vm_page_prot);
+	}
+	return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_insert_mixed);
+
 /*
  * maps a range of physical memory into the requested pages. the old
  * mappings are removed. any references to nonexistent pages results
@@ -1276,7 +1354,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 	arch_enter_lazy_mmu_mode();
 	do {
 		BUG_ON(!pte_none(*pte));
-		set_pte_at(mm, addr, pte, pfn_pte(pfn, prot));
+		set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
@@ -2199,20 +2277,9 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	BUG_ON(vma->vm_flags & VM_PFNMAP);
 
-	if (likely(vma->vm_ops->fault)) {
-		ret = vma->vm_ops->fault(vma, &vmf);
-		if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
-			return ret;
-	} else {
-		/* Legacy ->nopage path */
-		ret = 0;
-		vmf.page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret);
-		/* no page was available -- either SIGBUS or OOM */
-		if (unlikely(vmf.page == NOPAGE_SIGBUS))
-			return VM_FAULT_SIGBUS;
-		else if (unlikely(vmf.page == NOPAGE_OOM))
-			return VM_FAULT_OOM;
-	}
+	ret = vma->vm_ops->fault(vma, &vmf);
+	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
+		return ret;
 
 	/*
 	 * For consistency in subsequent calls, make the faulted page always
@@ -2377,10 +2444,13 @@ static noinline int do_no_pfn(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long pfn;
 
 	pte_unmap(page_table);
-	BUG_ON(!(vma->vm_flags & VM_PFNMAP));
-	BUG_ON(is_cow_mapping(vma->vm_flags));
+	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
+	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
 
 	pfn = vma->vm_ops->nopfn(vma, address & PAGE_MASK);
+
+	BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));
+
 	if (unlikely(pfn == NOPFN_OOM))
 		return VM_FAULT_OOM;
 	else if (unlikely(pfn == NOPFN_SIGBUS))
@@ -2458,7 +2528,7 @@ static inline int handle_pte_fault(struct mm_struct *mm,
 	if (!pte_present(entry)) {
 		if (pte_none(entry)) {
 			if (vma->vm_ops) {
-				if (vma->vm_ops->fault || vma->vm_ops->nopage)
+				if (likely(vma->vm_ops->fault))
 					return do_linear_fault(mm, vma, address,
 						pte, pmd, write_access, entry);
 				if (unlikely(vma->vm_ops->nopfn))
diff --git a/trunk/mm/memory_hotplug.c b/trunk/mm/memory_hotplug.c
index 0fb330271271..b17dca7249f8 100644
--- a/trunk/mm/memory_hotplug.c
+++ b/trunk/mm/memory_hotplug.c
@@ -29,6 +29,8 @@
 
 #include <asm/tlbflush.h>
 
+#include "internal.h"
+
 /* add this memory to iomem resource */
 static struct resource *register_memory_resource(u64 start, u64 size)
 {
@@ -58,8 +60,105 @@ static void release_memory_resource(struct resource *res)
 	return;
 }
 
-
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
+static void get_page_bootmem(unsigned long info,  struct page *page, int magic)
+{
+	atomic_set(&page->_mapcount, magic);
+	SetPagePrivate(page);
+	set_page_private(page, info);
+	atomic_inc(&page->_count);
+}
+
+void put_page_bootmem(struct page *page)
+{
+	int magic;
+
+	magic = atomic_read(&page->_mapcount);
+	BUG_ON(magic >= -1);
+
+	if (atomic_dec_return(&page->_count) == 1) {
+		ClearPagePrivate(page);
+		set_page_private(page, 0);
+		reset_page_mapcount(page);
+		__free_pages_bootmem(page, 0);
+	}
+
+}
+
+void register_page_bootmem_info_section(unsigned long start_pfn)
+{
+	unsigned long *usemap, mapsize, section_nr, i;
+	struct mem_section *ms;
+	struct page *page, *memmap;
+
+	if (!pfn_valid(start_pfn))
+		return;
+
+	section_nr = pfn_to_section_nr(start_pfn);
+	ms = __nr_to_section(section_nr);
+
+	/* Get section's memmap address */
+	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
+
+	/*
+	 * Get page for the memmap's phys address
+	 * XXX: need more consideration for sparse_vmemmap...
+	 */
+	page = virt_to_page(memmap);
+	mapsize = sizeof(struct page) * PAGES_PER_SECTION;
+	mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT;
+
+	/* remember memmap's page */
+	for (i = 0; i < mapsize; i++, page++)
+		get_page_bootmem(section_nr, page, SECTION_INFO);
+
+	usemap = __nr_to_section(section_nr)->pageblock_flags;
+	page = virt_to_page(usemap);
+
+	mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
+
+	for (i = 0; i < mapsize; i++, page++)
+		get_page_bootmem(section_nr, page, MIX_INFO);
+
+}
+
+void register_page_bootmem_info_node(struct pglist_data *pgdat)
+{
+	unsigned long i, pfn, end_pfn, nr_pages;
+	int node = pgdat->node_id;
+	struct page *page;
+	struct zone *zone;
+
+	nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
+	page = virt_to_page(pgdat);
+
+	for (i = 0; i < nr_pages; i++, page++)
+		get_page_bootmem(node, page, NODE_INFO);
+
+	zone = &pgdat->node_zones[0];
+	for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) {
+		if (zone->wait_table) {
+			nr_pages = zone->wait_table_hash_nr_entries
+				* sizeof(wait_queue_head_t);
+			nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT;
+			page = virt_to_page(zone->wait_table);
+
+			for (i = 0; i < nr_pages; i++, page++)
+				get_page_bootmem(node, page, NODE_INFO);
+		}
+	}
+
+	pfn = pgdat->node_start_pfn;
+	end_pfn = pfn + pgdat->node_spanned_pages;
+
+	/* register_section info */
+	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION)
+		register_page_bootmem_info_section(pfn);
+
+}
+#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
+
 static int __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
@@ -101,6 +200,36 @@ static int __add_section(struct zone *zone, unsigned long phys_start_pfn)
 	return register_new_memory(__pfn_to_section(phys_start_pfn));
 }
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static int __remove_section(struct zone *zone, struct mem_section *ms)
+{
+	/*
+	 * XXX: Freeing memmap with vmemmap is not implement yet.
+	 *      This should be removed later.
+	 */
+	return -EBUSY;
+}
+#else
+static int __remove_section(struct zone *zone, struct mem_section *ms)
+{
+	unsigned long flags;
+	struct pglist_data *pgdat = zone->zone_pgdat;
+	int ret = -EINVAL;
+
+	if (!valid_section(ms))
+		return ret;
+
+	ret = unregister_memory_section(ms);
+	if (ret)
+		return ret;
+
+	pgdat_resize_lock(pgdat, &flags);
+	sparse_remove_one_section(zone, ms);
+	pgdat_resize_unlock(pgdat, &flags);
+	return 0;
+}
+#endif
+
 /*
  * Reasonably generic function for adding memory.  It is
  * expected that archs that support memory hotplug will
@@ -134,6 +263,42 @@ int __add_pages(struct zone *zone, unsigned long phys_start_pfn,
 }
 EXPORT_SYMBOL_GPL(__add_pages);
 
+/**
+ * __remove_pages() - remove sections of pages from a zone
+ * @zone: zone from which pages need to be removed
+ * @phys_start_pfn: starting pageframe (must be aligned to start of a section)
+ * @nr_pages: number of pages to remove (must be multiple of section size)
+ *
+ * Generic helper function to remove section mappings and sysfs entries
+ * for the section of the memory we are removing. Caller needs to make
+ * sure that pages are marked reserved and zones are adjust properly by
+ * calling offline_pages().
+ */
+int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
+		 unsigned long nr_pages)
+{
+	unsigned long i, ret = 0;
+	int sections_to_remove;
+
+	/*
+	 * We can only remove entire sections
+	 */
+	BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
+	BUG_ON(nr_pages % PAGES_PER_SECTION);
+
+	release_mem_region(phys_start_pfn << PAGE_SHIFT, nr_pages * PAGE_SIZE);
+
+	sections_to_remove = nr_pages / PAGES_PER_SECTION;
+	for (i = 0; i < sections_to_remove; i++) {
+		unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
+		ret = __remove_section(zone, __pfn_to_section(pfn));
+		if (ret)
+			break;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__remove_pages);
+
 static void grow_zone_span(struct zone *zone,
 		unsigned long start_pfn, unsigned long end_pfn)
 {
@@ -164,6 +329,25 @@ static void grow_pgdat_span(struct pglist_data *pgdat,
 					pgdat->node_start_pfn;
 }
 
+void online_page(struct page *page)
+{
+	totalram_pages++;
+	num_physpages++;
+
+#ifdef CONFIG_HIGHMEM
+	if (PageHighMem(page))
+		totalhigh_pages++;
+#endif
+
+#ifdef CONFIG_FLATMEM
+	max_mapnr = max(page_to_pfn(page), max_mapnr);
+#endif
+
+	ClearPageReserved(page);
+	init_page_count(page);
+	__free_page(page);
+}
+
 static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 			void *arg)
 {
diff --git a/trunk/mm/mempolicy.c b/trunk/mm/mempolicy.c
index 3c3601121509..a37a5034f63d 100644
--- a/trunk/mm/mempolicy.c
+++ b/trunk/mm/mempolicy.c
@@ -63,7 +63,6 @@
    grows down?
    make bind policy root only? It can trigger oom much faster and the
    kernel is not always grateful with that.
-   could replace all the switch()es with a mempolicy_ops structure.
 */
 
 #include <linux/mempolicy.h>
@@ -89,6 +88,7 @@
 #include <linux/rmap.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
+#include <linux/ctype.h>
 
 #include <asm/tlbflush.h>
 #include <asm/uaccess.h>
@@ -105,142 +105,264 @@ static struct kmem_cache *sn_cache;
    policied. */
 enum zone_type policy_zone = 0;
 
+/*
+ * run-time system-wide default policy => local allocation
+ */
 struct mempolicy default_policy = {
 	.refcnt = ATOMIC_INIT(1), /* never free it */
-	.policy = MPOL_DEFAULT,
+	.mode = MPOL_PREFERRED,
+	.flags = MPOL_F_LOCAL,
 };
 
-static void mpol_rebind_policy(struct mempolicy *pol,
-                               const nodemask_t *newmask);
+static const struct mempolicy_operations {
+	int (*create)(struct mempolicy *pol, const nodemask_t *nodes);
+	void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes);
+} mpol_ops[MPOL_MAX];
 
-/* Do sanity checking on a policy */
-static int mpol_check_policy(int mode, nodemask_t *nodes)
+/* Check that the nodemask contains at least one populated zone */
+static int is_valid_nodemask(const nodemask_t *nodemask)
 {
-	int was_empty, is_empty;
+	int nd, k;
 
-	if (!nodes)
-		return 0;
+	/* Check that there is something useful in this mask */
+	k = policy_zone;
 
-	/*
-	 * "Contextualize" the in-coming nodemast for cpusets:
-	 * Remember whether in-coming nodemask was empty,  If not,
-	 * restrict the nodes to the allowed nodes in the cpuset.
-	 * This is guaranteed to be a subset of nodes with memory.
-	 */
-	cpuset_update_task_memory_state();
-	is_empty = was_empty = nodes_empty(*nodes);
-	if (!was_empty) {
-		nodes_and(*nodes, *nodes, cpuset_current_mems_allowed);
-		is_empty = nodes_empty(*nodes);	/* after "contextualization" */
-	}
+	for_each_node_mask(nd, *nodemask) {
+		struct zone *z;
 
-	switch (mode) {
-	case MPOL_DEFAULT:
-		/*
-		 * require caller to specify an empty nodemask
-		 * before "contextualization"
-		 */
-		if (!was_empty)
-			return -EINVAL;
-		break;
-	case MPOL_BIND:
-	case MPOL_INTERLEAVE:
-		/*
-		 * require at least 1 valid node after "contextualization"
-		 */
-		if (is_empty)
-			return -EINVAL;
-		break;
-	case MPOL_PREFERRED:
-		/*
-		 * Did caller specify invalid nodes?
-		 * Don't silently accept this as "local allocation".
-		 */
-		if (!was_empty && is_empty)
-			return -EINVAL;
-		break;
+		for (k = 0; k <= policy_zone; k++) {
+			z = &NODE_DATA(nd)->node_zones[k];
+			if (z->present_pages > 0)
+				return 1;
+		}
 	}
+
 	return 0;
 }
 
-/* Generate a custom zonelist for the BIND policy. */
-static struct zonelist *bind_zonelist(nodemask_t *nodes)
+static inline int mpol_store_user_nodemask(const struct mempolicy *pol)
 {
-	struct zonelist *zl;
-	int num, max, nd;
-	enum zone_type k;
+	return pol->flags & (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES);
+}
 
-	max = 1 + MAX_NR_ZONES * nodes_weight(*nodes);
-	max++;			/* space for zlcache_ptr (see mmzone.h) */
-	zl = kmalloc(sizeof(struct zone *) * max, GFP_KERNEL);
-	if (!zl)
-		return ERR_PTR(-ENOMEM);
-	zl->zlcache_ptr = NULL;
-	num = 0;
-	/* First put in the highest zones from all nodes, then all the next 
-	   lower zones etc. Avoid empty zones because the memory allocator
-	   doesn't like them. If you implement node hot removal you
-	   have to fix that. */
-	k = MAX_NR_ZONES - 1;
-	while (1) {
-		for_each_node_mask(nd, *nodes) { 
-			struct zone *z = &NODE_DATA(nd)->node_zones[k];
-			if (z->present_pages > 0) 
-				zl->zones[num++] = z;
-		}
-		if (k == 0)
-			break;
-		k--;
-	}
-	if (num == 0) {
-		kfree(zl);
-		return ERR_PTR(-EINVAL);
-	}
-	zl->zones[num] = NULL;
-	return zl;
+static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig,
+				   const nodemask_t *rel)
+{
+	nodemask_t tmp;
+	nodes_fold(tmp, *orig, nodes_weight(*rel));
+	nodes_onto(*ret, tmp, *rel);
+}
+
+static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes)
+{
+	if (nodes_empty(*nodes))
+		return -EINVAL;
+	pol->v.nodes = *nodes;
+	return 0;
+}
+
+static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
+{
+	if (!nodes)
+		pol->flags |= MPOL_F_LOCAL;	/* local allocation */
+	else if (nodes_empty(*nodes))
+		return -EINVAL;			/*  no allowed nodes */
+	else
+		pol->v.preferred_node = first_node(*nodes);
+	return 0;
+}
+
+static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
+{
+	if (!is_valid_nodemask(nodes))
+		return -EINVAL;
+	pol->v.nodes = *nodes;
+	return 0;
 }
 
 /* Create a new policy */
-static struct mempolicy *mpol_new(int mode, nodemask_t *nodes)
+static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
+				  nodemask_t *nodes)
 {
 	struct mempolicy *policy;
+	nodemask_t cpuset_context_nmask;
+	int ret;
 
-	pr_debug("setting mode %d nodes[0] %lx\n",
-		 mode, nodes ? nodes_addr(*nodes)[0] : -1);
+	pr_debug("setting mode %d flags %d nodes[0] %lx\n",
+		 mode, flags, nodes ? nodes_addr(*nodes)[0] : -1);
 
-	if (mode == MPOL_DEFAULT)
-		return NULL;
+	if (mode == MPOL_DEFAULT) {
+		if (nodes && !nodes_empty(*nodes))
+			return ERR_PTR(-EINVAL);
+		return NULL;	/* simply delete any existing policy */
+	}
+	VM_BUG_ON(!nodes);
+
+	/*
+	 * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or
+	 * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation).
+	 * All other modes require a valid pointer to a non-empty nodemask.
+	 */
+	if (mode == MPOL_PREFERRED) {
+		if (nodes_empty(*nodes)) {
+			if (((flags & MPOL_F_STATIC_NODES) ||
+			     (flags & MPOL_F_RELATIVE_NODES)))
+				return ERR_PTR(-EINVAL);
+			nodes = NULL;	/* flag local alloc */
+		}
+	} else if (nodes_empty(*nodes))
+		return ERR_PTR(-EINVAL);
 	policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
 	if (!policy)
 		return ERR_PTR(-ENOMEM);
 	atomic_set(&policy->refcnt, 1);
-	switch (mode) {
-	case MPOL_INTERLEAVE:
-		policy->v.nodes = *nodes;
-		if (nodes_weight(policy->v.nodes) == 0) {
-			kmem_cache_free(policy_cache, policy);
-			return ERR_PTR(-EINVAL);
-		}
-		break;
-	case MPOL_PREFERRED:
-		policy->v.preferred_node = first_node(*nodes);
-		if (policy->v.preferred_node >= MAX_NUMNODES)
-			policy->v.preferred_node = -1;
-		break;
-	case MPOL_BIND:
-		policy->v.zonelist = bind_zonelist(nodes);
-		if (IS_ERR(policy->v.zonelist)) {
-			void *error_code = policy->v.zonelist;
-			kmem_cache_free(policy_cache, policy);
-			return error_code;
-		}
-		break;
+	policy->mode = mode;
+	policy->flags = flags;
+
+	if (nodes) {
+		/*
+		 * cpuset related setup doesn't apply to local allocation
+		 */
+		cpuset_update_task_memory_state();
+		if (flags & MPOL_F_RELATIVE_NODES)
+			mpol_relative_nodemask(&cpuset_context_nmask, nodes,
+					       &cpuset_current_mems_allowed);
+		else
+			nodes_and(cpuset_context_nmask, *nodes,
+				  cpuset_current_mems_allowed);
+		if (mpol_store_user_nodemask(policy))
+			policy->w.user_nodemask = *nodes;
+		else
+			policy->w.cpuset_mems_allowed =
+						cpuset_mems_allowed(current);
+	}
+
+	ret = mpol_ops[mode].create(policy,
+				nodes ? &cpuset_context_nmask : NULL);
+	if (ret < 0) {
+		kmem_cache_free(policy_cache, policy);
+		return ERR_PTR(ret);
 	}
-	policy->policy = mode;
-	policy->cpuset_mems_allowed = cpuset_mems_allowed(current);
 	return policy;
 }
 
+/* Slow path of a mpol destructor. */
+void __mpol_put(struct mempolicy *p)
+{
+	if (!atomic_dec_and_test(&p->refcnt))
+		return;
+	kmem_cache_free(policy_cache, p);
+}
+
+static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes)
+{
+}
+
+static void mpol_rebind_nodemask(struct mempolicy *pol,
+				 const nodemask_t *nodes)
+{
+	nodemask_t tmp;
+
+	if (pol->flags & MPOL_F_STATIC_NODES)
+		nodes_and(tmp, pol->w.user_nodemask, *nodes);
+	else if (pol->flags & MPOL_F_RELATIVE_NODES)
+		mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
+	else {
+		nodes_remap(tmp, pol->v.nodes, pol->w.cpuset_mems_allowed,
+			    *nodes);
+		pol->w.cpuset_mems_allowed = *nodes;
+	}
+
+	pol->v.nodes = tmp;
+	if (!node_isset(current->il_next, tmp)) {
+		current->il_next = next_node(current->il_next, tmp);
+		if (current->il_next >= MAX_NUMNODES)
+			current->il_next = first_node(tmp);
+		if (current->il_next >= MAX_NUMNODES)
+			current->il_next = numa_node_id();
+	}
+}
+
+static void mpol_rebind_preferred(struct mempolicy *pol,
+				  const nodemask_t *nodes)
+{
+	nodemask_t tmp;
+
+	if (pol->flags & MPOL_F_STATIC_NODES) {
+		int node = first_node(pol->w.user_nodemask);
+
+		if (node_isset(node, *nodes)) {
+			pol->v.preferred_node = node;
+			pol->flags &= ~MPOL_F_LOCAL;
+		} else
+			pol->flags |= MPOL_F_LOCAL;
+	} else if (pol->flags & MPOL_F_RELATIVE_NODES) {
+		mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
+		pol->v.preferred_node = first_node(tmp);
+	} else if (!(pol->flags & MPOL_F_LOCAL)) {
+		pol->v.preferred_node = node_remap(pol->v.preferred_node,
+						   pol->w.cpuset_mems_allowed,
+						   *nodes);
+		pol->w.cpuset_mems_allowed = *nodes;
+	}
+}
+
+/* Migrate a policy to a different set of nodes */
+static void mpol_rebind_policy(struct mempolicy *pol,
+			       const nodemask_t *newmask)
+{
+	if (!pol)
+		return;
+	if (!mpol_store_user_nodemask(pol) &&
+	    nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
+		return;
+	mpol_ops[pol->mode].rebind(pol, newmask);
+}
+
+/*
+ * Wrapper for mpol_rebind_policy() that just requires task
+ * pointer, and updates task mempolicy.
+ */
+
+void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new)
+{
+	mpol_rebind_policy(tsk->mempolicy, new);
+}
+
+/*
+ * Rebind each vma in mm to new nodemask.
+ *
+ * Call holding a reference to mm.  Takes mm->mmap_sem during call.
+ */
+
+void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
+{
+	struct vm_area_struct *vma;
+
+	down_write(&mm->mmap_sem);
+	for (vma = mm->mmap; vma; vma = vma->vm_next)
+		mpol_rebind_policy(vma->vm_policy, new);
+	up_write(&mm->mmap_sem);
+}
+
+static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
+	[MPOL_DEFAULT] = {
+		.rebind = mpol_rebind_default,
+	},
+	[MPOL_INTERLEAVE] = {
+		.create = mpol_new_interleave,
+		.rebind = mpol_rebind_nodemask,
+	},
+	[MPOL_PREFERRED] = {
+		.create = mpol_new_preferred,
+		.rebind = mpol_rebind_preferred,
+	},
+	[MPOL_BIND] = {
+		.create = mpol_new_bind,
+		.rebind = mpol_rebind_nodemask,
+	},
+};
+
 static void gather_stats(struct page *, void *, int pte_dirty);
 static void migrate_page_add(struct page *page, struct list_head *pagelist,
 				unsigned long flags);
@@ -421,7 +543,7 @@ static int policy_vma(struct vm_area_struct *vma, struct mempolicy *new)
 	if (!err) {
 		mpol_get(new);
 		vma->vm_policy = new;
-		mpol_free(old);
+		mpol_put(old);
 	}
 	return err;
 }
@@ -479,46 +601,55 @@ static void mpol_set_task_struct_flag(void)
 }
 
 /* Set the process memory policy */
-static long do_set_mempolicy(int mode, nodemask_t *nodes)
+static long do_set_mempolicy(unsigned short mode, unsigned short flags,
+			     nodemask_t *nodes)
 {
 	struct mempolicy *new;
+	struct mm_struct *mm = current->mm;
 
-	if (mpol_check_policy(mode, nodes))
-		return -EINVAL;
-	new = mpol_new(mode, nodes);
+	new = mpol_new(mode, flags, nodes);
 	if (IS_ERR(new))
 		return PTR_ERR(new);
-	mpol_free(current->mempolicy);
+
+	/*
+	 * prevent changing our mempolicy while show_numa_maps()
+	 * is using it.
+	 * Note:  do_set_mempolicy() can be called at init time
+	 * with no 'mm'.
+	 */
+	if (mm)
+		down_write(&mm->mmap_sem);
+	mpol_put(current->mempolicy);
 	current->mempolicy = new;
 	mpol_set_task_struct_flag();
-	if (new && new->policy == MPOL_INTERLEAVE)
+	if (new && new->mode == MPOL_INTERLEAVE &&
+	    nodes_weight(new->v.nodes))
 		current->il_next = first_node(new->v.nodes);
+	if (mm)
+		up_write(&mm->mmap_sem);
+
 	return 0;
 }
 
-/* Fill a zone bitmap for a policy */
-static void get_zonemask(struct mempolicy *p, nodemask_t *nodes)
+/*
+ * Return nodemask for policy for get_mempolicy() query
+ */
+static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes)
 {
-	int i;
-
 	nodes_clear(*nodes);
-	switch (p->policy) {
+	if (p == &default_policy)
+		return;
+
+	switch (p->mode) {
 	case MPOL_BIND:
-		for (i = 0; p->v.zonelist->zones[i]; i++)
-			node_set(zone_to_nid(p->v.zonelist->zones[i]),
-				*nodes);
-		break;
-	case MPOL_DEFAULT:
-		break;
+		/* Fall through */
 	case MPOL_INTERLEAVE:
 		*nodes = p->v.nodes;
 		break;
 	case MPOL_PREFERRED:
-		/* or use current node instead of memory_map? */
-		if (p->v.preferred_node < 0)
-			*nodes = node_states[N_HIGH_MEMORY];
-		else
+		if (!(p->flags & MPOL_F_LOCAL))
 			node_set(p->v.preferred_node, *nodes);
+		/* else return empty node mask for local allocation */
 		break;
 	default:
 		BUG();
@@ -561,6 +692,11 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 	}
 
 	if (flags & MPOL_F_ADDR) {
+		/*
+		 * Do NOT fall back to task policy if the
+		 * vma/shared policy at addr is NULL.  We
+		 * want to return MPOL_DEFAULT in this case.
+		 */
 		down_read(&mm->mmap_sem);
 		vma = find_vma_intersection(mm, addr, addr+1);
 		if (!vma) {
@@ -575,7 +711,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 		return -EINVAL;
 
 	if (!pol)
-		pol = &default_policy;
+		pol = &default_policy;	/* indicates default behavior */
 
 	if (flags & MPOL_F_NODE) {
 		if (flags & MPOL_F_ADDR) {
@@ -584,14 +720,17 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 				goto out;
 			*policy = err;
 		} else if (pol == current->mempolicy &&
-				pol->policy == MPOL_INTERLEAVE) {
+				pol->mode == MPOL_INTERLEAVE) {
 			*policy = current->il_next;
 		} else {
 			err = -EINVAL;
 			goto out;
 		}
-	} else
-		*policy = pol->policy;
+	} else {
+		*policy = pol == &default_policy ? MPOL_DEFAULT :
+						pol->mode;
+		*policy |= pol->flags;
+	}
 
 	if (vma) {
 		up_read(&current->mm->mmap_sem);
@@ -600,9 +739,10 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 
 	err = 0;
 	if (nmask)
-		get_zonemask(pol, nmask);
+		get_policy_nodemask(pol, nmask);
 
  out:
+	mpol_cond_put(pol);
 	if (vma)
 		up_read(&current->mm->mmap_sem);
 	return err;
@@ -664,7 +804,7 @@ int do_migrate_pages(struct mm_struct *mm,
 	int err = 0;
 	nodemask_t tmp;
 
-  	down_read(&mm->mmap_sem);
+	down_read(&mm->mmap_sem);
 
 	err = migrate_vmas(mm, from_nodes, to_nodes, flags);
 	if (err)
@@ -781,8 +921,8 @@ static struct page *new_vma_page(struct page *page, unsigned long private, int *
 #endif
 
 static long do_mbind(unsigned long start, unsigned long len,
-		     unsigned long mode, nodemask_t *nmask,
-		     unsigned long flags)
+		     unsigned short mode, unsigned short mode_flags,
+		     nodemask_t *nmask, unsigned long flags)
 {
 	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
@@ -791,9 +931,8 @@ static long do_mbind(unsigned long start, unsigned long len,
 	int err;
 	LIST_HEAD(pagelist);
 
-	if ((flags & ~(unsigned long)(MPOL_MF_STRICT |
-				      MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
-	    || mode > MPOL_MAX)
+	if (flags & ~(unsigned long)(MPOL_MF_STRICT |
+				     MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
 		return -EINVAL;
 	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
 		return -EPERM;
@@ -812,10 +951,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 	if (end == start)
 		return 0;
 
-	if (mpol_check_policy(mode, nmask))
-		return -EINVAL;
-
-	new = mpol_new(mode, nmask);
+	new = mpol_new(mode, mode_flags, nmask);
 	if (IS_ERR(new))
 		return PTR_ERR(new);
 
@@ -826,8 +962,9 @@ static long do_mbind(unsigned long start, unsigned long len,
 	if (!new)
 		flags |= MPOL_MF_DISCONTIG_OK;
 
-	pr_debug("mbind %lx-%lx mode:%ld nodes:%lx\n",start,start+len,
-		 mode, nmask ? nodes_addr(*nmask)[0] : -1);
+	pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n",
+		 start, start + len, mode, mode_flags,
+		 nmask ? nodes_addr(*nmask)[0] : -1);
 
 	down_write(&mm->mmap_sem);
 	vma = check_range(mm, start, end, nmask,
@@ -848,7 +985,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 	}
 
 	up_write(&mm->mmap_sem);
-	mpol_free(new);
+	mpol_put(new);
 	return err;
 }
 
@@ -926,11 +1063,19 @@ asmlinkage long sys_mbind(unsigned long start, unsigned long len,
 {
 	nodemask_t nodes;
 	int err;
+	unsigned short mode_flags;
 
+	mode_flags = mode & MPOL_MODE_FLAGS;
+	mode &= ~MPOL_MODE_FLAGS;
+	if (mode >= MPOL_MAX)
+		return -EINVAL;
+	if ((mode_flags & MPOL_F_STATIC_NODES) &&
+	    (mode_flags & MPOL_F_RELATIVE_NODES))
+		return -EINVAL;
 	err = get_nodes(&nodes, nmask, maxnode);
 	if (err)
 		return err;
-	return do_mbind(start, len, mode, &nodes, flags);
+	return do_mbind(start, len, mode, mode_flags, &nodes, flags);
 }
 
 /* Set the process memory policy */
@@ -939,13 +1084,18 @@ asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask,
 {
 	int err;
 	nodemask_t nodes;
+	unsigned short flags;
 
-	if (mode < 0 || mode > MPOL_MAX)
+	flags = mode & MPOL_MODE_FLAGS;
+	mode &= ~MPOL_MODE_FLAGS;
+	if ((unsigned int)mode >= MPOL_MAX)
+		return -EINVAL;
+	if ((flags & MPOL_F_STATIC_NODES) && (flags & MPOL_F_RELATIVE_NODES))
 		return -EINVAL;
 	err = get_nodes(&nodes, nmask, maxnode);
 	if (err)
 		return err;
-	return do_set_mempolicy(mode, &nodes);
+	return do_set_mempolicy(mode, flags, &nodes);
 }
 
 asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
@@ -1131,59 +1281,75 @@ asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
  *
  * Returns effective policy for a VMA at specified address.
  * Falls back to @task or system default policy, as necessary.
- * Returned policy has extra reference count if shared, vma,
- * or some other task's policy [show_numa_maps() can pass
- * @task != current].  It is the caller's responsibility to
- * free the reference in these cases.
+ * Current or other task's task mempolicy and non-shared vma policies
+ * are protected by the task's mmap_sem, which must be held for read by
+ * the caller.
+ * Shared policies [those marked as MPOL_F_SHARED] require an extra reference
+ * count--added by the get_policy() vm_op, as appropriate--to protect against
+ * freeing by another task.  It is the caller's responsibility to free the
+ * extra reference for shared policies.
  */
-static struct mempolicy * get_vma_policy(struct task_struct *task,
+static struct mempolicy *get_vma_policy(struct task_struct *task,
 		struct vm_area_struct *vma, unsigned long addr)
 {
 	struct mempolicy *pol = task->mempolicy;
-	int shared_pol = 0;
 
 	if (vma) {
 		if (vma->vm_ops && vma->vm_ops->get_policy) {
-			pol = vma->vm_ops->get_policy(vma, addr);
-			shared_pol = 1;	/* if pol non-NULL, add ref below */
-		} else if (vma->vm_policy &&
-				vma->vm_policy->policy != MPOL_DEFAULT)
+			struct mempolicy *vpol = vma->vm_ops->get_policy(vma,
+									addr);
+			if (vpol)
+				pol = vpol;
+		} else if (vma->vm_policy)
 			pol = vma->vm_policy;
 	}
 	if (!pol)
 		pol = &default_policy;
-	else if (!shared_pol && pol != current->mempolicy)
-		mpol_get(pol);	/* vma or other task's policy */
 	return pol;
 }
 
-/* Return a zonelist representing a mempolicy */
-static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
+/*
+ * Return a nodemask representing a mempolicy for filtering nodes for
+ * page allocation
+ */
+static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
 {
-	int nd;
+	/* Lower zones don't get a nodemask applied for MPOL_BIND */
+	if (unlikely(policy->mode == MPOL_BIND) &&
+			gfp_zone(gfp) >= policy_zone &&
+			cpuset_nodemask_valid_mems_allowed(&policy->v.nodes))
+		return &policy->v.nodes;
 
-	switch (policy->policy) {
+	return NULL;
+}
+
+/* Return a zonelist indicated by gfp for node representing a mempolicy */
+static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy)
+{
+	int nd = numa_node_id();
+
+	switch (policy->mode) {
 	case MPOL_PREFERRED:
-		nd = policy->v.preferred_node;
-		if (nd < 0)
-			nd = numa_node_id();
+		if (!(policy->flags & MPOL_F_LOCAL))
+			nd = policy->v.preferred_node;
 		break;
 	case MPOL_BIND:
-		/* Lower zones don't get a policy applied */
-		/* Careful: current->mems_allowed might have moved */
-		if (gfp_zone(gfp) >= policy_zone)
-			if (cpuset_zonelist_valid_mems_allowed(policy->v.zonelist))
-				return policy->v.zonelist;
-		/*FALL THROUGH*/
+		/*
+		 * Normally, MPOL_BIND allocations are node-local within the
+		 * allowed nodemask.  However, if __GFP_THISNODE is set and the
+		 * current node is part of the mask, we use the zonelist for
+		 * the first node in the mask instead.
+		 */
+		if (unlikely(gfp & __GFP_THISNODE) &&
+				unlikely(!node_isset(nd, policy->v.nodes)))
+			nd = first_node(policy->v.nodes);
+		break;
 	case MPOL_INTERLEAVE: /* should not happen */
-	case MPOL_DEFAULT:
-		nd = numa_node_id();
 		break;
 	default:
-		nd = 0;
 		BUG();
 	}
-	return NODE_DATA(nd)->node_zonelists + gfp_zone(gfp);
+	return node_zonelist(nd, gfp);
 }
 
 /* Do dynamic interleaving for a process */
@@ -1196,36 +1362,51 @@ static unsigned interleave_nodes(struct mempolicy *policy)
 	next = next_node(nid, policy->v.nodes);
 	if (next >= MAX_NUMNODES)
 		next = first_node(policy->v.nodes);
-	me->il_next = next;
+	if (next < MAX_NUMNODES)
+		me->il_next = next;
 	return nid;
 }
 
 /*
  * Depending on the memory policy provide a node from which to allocate the
  * next slab entry.
+ * @policy must be protected by freeing by the caller.  If @policy is
+ * the current task's mempolicy, this protection is implicit, as only the
+ * task can change it's policy.  The system default policy requires no
+ * such protection.
  */
 unsigned slab_node(struct mempolicy *policy)
 {
-	int pol = policy ? policy->policy : MPOL_DEFAULT;
+	if (!policy || policy->flags & MPOL_F_LOCAL)
+		return numa_node_id();
+
+	switch (policy->mode) {
+	case MPOL_PREFERRED:
+		/*
+		 * handled MPOL_F_LOCAL above
+		 */
+		return policy->v.preferred_node;
 
-	switch (pol) {
 	case MPOL_INTERLEAVE:
 		return interleave_nodes(policy);
 
-	case MPOL_BIND:
+	case MPOL_BIND: {
 		/*
 		 * Follow bind policy behavior and start allocation at the
 		 * first node.
 		 */
-		return zone_to_nid(policy->v.zonelist->zones[0]);
-
-	case MPOL_PREFERRED:
-		if (policy->v.preferred_node >= 0)
-			return policy->v.preferred_node;
-		/* Fall through */
+		struct zonelist *zonelist;
+		struct zone *zone;
+		enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL);
+		zonelist = &NODE_DATA(numa_node_id())->node_zonelists[0];
+		(void)first_zones_zonelist(zonelist, highest_zoneidx,
+							&policy->v.nodes,
+							&zone);
+		return zone->node;
+	}
 
 	default:
-		return numa_node_id();
+		BUG();
 	}
 }
 
@@ -1234,10 +1415,13 @@ static unsigned offset_il_node(struct mempolicy *pol,
 		struct vm_area_struct *vma, unsigned long off)
 {
 	unsigned nnodes = nodes_weight(pol->v.nodes);
-	unsigned target = (unsigned)off % nnodes;
+	unsigned target;
 	int c;
 	int nid = -1;
 
+	if (!nnodes)
+		return numa_node_id();
+	target = (unsigned int)off % nnodes;
 	c = 0;
 	do {
 		nid = next_node(nid, pol->v.nodes);
@@ -1274,40 +1458,30 @@ static inline unsigned interleave_nid(struct mempolicy *pol,
  * @vma = virtual memory area whose policy is sought
  * @addr = address in @vma for shared policy lookup and interleave policy
  * @gfp_flags = for requested zone
- * @mpol = pointer to mempolicy pointer for reference counted 'BIND policy
+ * @mpol = pointer to mempolicy pointer for reference counted mempolicy
+ * @nodemask = pointer to nodemask pointer for MPOL_BIND nodemask
  *
- * Returns a zonelist suitable for a huge page allocation.
- * If the effective policy is 'BIND, returns pointer to policy's zonelist.
- * If it is also a policy for which get_vma_policy() returns an extra
- * reference, we must hold that reference until after allocation.
- * In that case, return policy via @mpol so hugetlb allocation can drop
- * the reference.  For non-'BIND referenced policies, we can/do drop the
- * reference here, so the caller doesn't need to know about the special case
- * for default and current task policy.
+ * Returns a zonelist suitable for a huge page allocation and a pointer
+ * to the struct mempolicy for conditional unref after allocation.
+ * If the effective policy is 'BIND, returns a pointer to the mempolicy's
+ * @nodemask for filtering the zonelist.
  */
 struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
-				gfp_t gfp_flags, struct mempolicy **mpol)
+				gfp_t gfp_flags, struct mempolicy **mpol,
+				nodemask_t **nodemask)
 {
-	struct mempolicy *pol = get_vma_policy(current, vma, addr);
 	struct zonelist *zl;
 
-	*mpol = NULL;		/* probably no unref needed */
-	if (pol->policy == MPOL_INTERLEAVE) {
-		unsigned nid;
-
-		nid = interleave_nid(pol, vma, addr, HPAGE_SHIFT);
-		if (unlikely(pol != &default_policy &&
-				pol != current->mempolicy))
-			__mpol_free(pol);	/* finished with pol */
-		return NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_flags);
-	}
+	*mpol = get_vma_policy(current, vma, addr);
+	*nodemask = NULL;	/* assume !MPOL_BIND */
 
-	zl = zonelist_policy(GFP_HIGHUSER, pol);
-	if (unlikely(pol != &default_policy && pol != current->mempolicy)) {
-		if (pol->policy != MPOL_BIND)
-			__mpol_free(pol);	/* finished with pol */
-		else
-			*mpol = pol;	/* unref needed after allocation */
+	if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) {
+		zl = node_zonelist(interleave_nid(*mpol, vma, addr,
+						HPAGE_SHIFT), gfp_flags);
+	} else {
+		zl = policy_zonelist(gfp_flags, *mpol);
+		if ((*mpol)->mode == MPOL_BIND)
+			*nodemask = &(*mpol)->v.nodes;
 	}
 	return zl;
 }
@@ -1321,9 +1495,9 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
 	struct zonelist *zl;
 	struct page *page;
 
-	zl = NODE_DATA(nid)->node_zonelists + gfp_zone(gfp);
+	zl = node_zonelist(nid, gfp);
 	page = __alloc_pages(gfp, order, zl);
-	if (page && page_zone(page) == zl->zones[0])
+	if (page && page_zone(page) == zonelist_zone(&zl->_zonerefs[0]))
 		inc_zone_page_state(page, NUMA_INTERLEAVE_HIT);
 	return page;
 }
@@ -1358,28 +1532,27 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
 
 	cpuset_update_task_memory_state();
 
-	if (unlikely(pol->policy == MPOL_INTERLEAVE)) {
+	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
 		unsigned nid;
 
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
-		if (unlikely(pol != &default_policy &&
-				pol != current->mempolicy))
-			__mpol_free(pol);	/* finished with pol */
+		mpol_cond_put(pol);
 		return alloc_page_interleave(gfp, 0, nid);
 	}
-	zl = zonelist_policy(gfp, pol);
-	if (pol != &default_policy && pol != current->mempolicy) {
+	zl = policy_zonelist(gfp, pol);
+	if (unlikely(mpol_needs_cond_ref(pol))) {
 		/*
-		 * slow path: ref counted policy -- shared or vma
+		 * slow path: ref counted shared policy
 		 */
-		struct page *page =  __alloc_pages(gfp, 0, zl);
-		__mpol_free(pol);
+		struct page *page =  __alloc_pages_nodemask(gfp, 0,
+						zl, policy_nodemask(gfp, pol));
+		__mpol_put(pol);
 		return page;
 	}
 	/*
 	 * fast path:  default or task policy
 	 */
-	return __alloc_pages(gfp, 0, zl);
+	return __alloc_pages_nodemask(gfp, 0, zl, policy_nodemask(gfp, pol));
 }
 
 /**
@@ -1409,22 +1582,28 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 		cpuset_update_task_memory_state();
 	if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
 		pol = &default_policy;
-	if (pol->policy == MPOL_INTERLEAVE)
+
+	/*
+	 * No reference counting needed for current->mempolicy
+	 * nor system default_policy
+	 */
+	if (pol->mode == MPOL_INTERLEAVE)
 		return alloc_page_interleave(gfp, order, interleave_nodes(pol));
-	return __alloc_pages(gfp, order, zonelist_policy(gfp, pol));
+	return __alloc_pages_nodemask(gfp, order,
+			policy_zonelist(gfp, pol), policy_nodemask(gfp, pol));
 }
 EXPORT_SYMBOL(alloc_pages_current);
 
 /*
- * If mpol_copy() sees current->cpuset == cpuset_being_rebound, then it
+ * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it
  * rebinds the mempolicy its copying by calling mpol_rebind_policy()
  * with the mems_allowed returned by cpuset_mems_allowed().  This
  * keeps mempolicies cpuset relative after its cpuset moves.  See
  * further kernel/cpuset.c update_nodemask().
  */
 
-/* Slow path of a mempolicy copy */
-struct mempolicy *__mpol_copy(struct mempolicy *old)
+/* Slow path of a mempolicy duplicate */
+struct mempolicy *__mpol_dup(struct mempolicy *old)
 {
 	struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
 
@@ -1436,55 +1615,64 @@ struct mempolicy *__mpol_copy(struct mempolicy *old)
 	}
 	*new = *old;
 	atomic_set(&new->refcnt, 1);
-	if (new->policy == MPOL_BIND) {
-		int sz = ksize(old->v.zonelist);
-		new->v.zonelist = kmemdup(old->v.zonelist, sz, GFP_KERNEL);
-		if (!new->v.zonelist) {
-			kmem_cache_free(policy_cache, new);
-			return ERR_PTR(-ENOMEM);
-		}
-	}
 	return new;
 }
 
+/*
+ * If *frompol needs [has] an extra ref, copy *frompol to *tompol ,
+ * eliminate the * MPOL_F_* flags that require conditional ref and
+ * [NOTE!!!] drop the extra ref.  Not safe to reference *frompol directly
+ * after return.  Use the returned value.
+ *
+ * Allows use of a mempolicy for, e.g., multiple allocations with a single
+ * policy lookup, even if the policy needs/has extra ref on lookup.
+ * shmem_readahead needs this.
+ */
+struct mempolicy *__mpol_cond_copy(struct mempolicy *tompol,
+						struct mempolicy *frompol)
+{
+	if (!mpol_needs_cond_ref(frompol))
+		return frompol;
+
+	*tompol = *frompol;
+	tompol->flags &= ~MPOL_F_SHARED;	/* copy doesn't need unref */
+	__mpol_put(frompol);
+	return tompol;
+}
+
+static int mpol_match_intent(const struct mempolicy *a,
+			     const struct mempolicy *b)
+{
+	if (a->flags != b->flags)
+		return 0;
+	if (!mpol_store_user_nodemask(a))
+		return 1;
+	return nodes_equal(a->w.user_nodemask, b->w.user_nodemask);
+}
+
 /* Slow path of a mempolicy comparison */
 int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
 {
 	if (!a || !b)
 		return 0;
-	if (a->policy != b->policy)
+	if (a->mode != b->mode)
 		return 0;
-	switch (a->policy) {
-	case MPOL_DEFAULT:
-		return 1;
+	if (a->mode != MPOL_DEFAULT && !mpol_match_intent(a, b))
+		return 0;
+	switch (a->mode) {
+	case MPOL_BIND:
+		/* Fall through */
 	case MPOL_INTERLEAVE:
 		return nodes_equal(a->v.nodes, b->v.nodes);
 	case MPOL_PREFERRED:
-		return a->v.preferred_node == b->v.preferred_node;
-	case MPOL_BIND: {
-		int i;
-		for (i = 0; a->v.zonelist->zones[i]; i++)
-			if (a->v.zonelist->zones[i] != b->v.zonelist->zones[i])
-				return 0;
-		return b->v.zonelist->zones[i] == NULL;
-	}
+		return a->v.preferred_node == b->v.preferred_node &&
+			a->flags == b->flags;
 	default:
 		BUG();
 		return 0;
 	}
 }
 
-/* Slow path of a mpol destructor. */
-void __mpol_free(struct mempolicy *p)
-{
-	if (!atomic_dec_and_test(&p->refcnt))
-		return;
-	if (p->policy == MPOL_BIND)
-		kfree(p->v.zonelist);
-	p->policy = MPOL_DEFAULT;
-	kmem_cache_free(policy_cache, p);
-}
-
 /*
  * Shared memory backing store policy support.
  *
@@ -1547,7 +1735,7 @@ static void sp_insert(struct shared_policy *sp, struct sp_node *new)
 	rb_link_node(&new->nd, parent, p);
 	rb_insert_color(&new->nd, &sp->root);
 	pr_debug("inserting %lx-%lx: %d\n", new->start, new->end,
-		 new->policy ? new->policy->policy : 0);
+		 new->policy ? new->policy->mode : 0);
 }
 
 /* Find shared policy intersecting idx */
@@ -1573,7 +1761,7 @@ static void sp_delete(struct shared_policy *sp, struct sp_node *n)
 {
 	pr_debug("deleting %lx-l%lx\n", n->start, n->end);
 	rb_erase(&n->nd, &sp->root);
-	mpol_free(n->policy);
+	mpol_put(n->policy);
 	kmem_cache_free(sn_cache, n);
 }
 
@@ -1587,6 +1775,7 @@ static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
 	n->start = start;
 	n->end = end;
 	mpol_get(pol);
+	pol->flags |= MPOL_F_SHARED;	/* for unref */
 	n->policy = pol;
 	return n;
 }
@@ -1633,33 +1822,41 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
 		sp_insert(sp, new);
 	spin_unlock(&sp->lock);
 	if (new2) {
-		mpol_free(new2->policy);
+		mpol_put(new2->policy);
 		kmem_cache_free(sn_cache, new2);
 	}
 	return 0;
 }
 
-void mpol_shared_policy_init(struct shared_policy *info, int policy,
-				nodemask_t *policy_nodes)
-{
-	info->root = RB_ROOT;
-	spin_lock_init(&info->lock);
-
-	if (policy != MPOL_DEFAULT) {
-		struct mempolicy *newpol;
-
-		/* Falls back to MPOL_DEFAULT on any error */
-		newpol = mpol_new(policy, policy_nodes);
-		if (!IS_ERR(newpol)) {
-			/* Create pseudo-vma that contains just the policy */
-			struct vm_area_struct pvma;
-
-			memset(&pvma, 0, sizeof(struct vm_area_struct));
-			/* Policy covers entire file */
-			pvma.vm_end = TASK_SIZE;
-			mpol_set_shared_policy(info, &pvma, newpol);
-			mpol_free(newpol);
-		}
+/**
+ * mpol_shared_policy_init - initialize shared policy for inode
+ * @sp: pointer to inode shared policy
+ * @mpol:  struct mempolicy to install
+ *
+ * Install non-NULL @mpol in inode's shared policy rb-tree.
+ * On entry, the current task has a reference on a non-NULL @mpol.
+ * This must be released on exit.
+ */
+void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
+{
+	sp->root = RB_ROOT;		/* empty tree == default mempolicy */
+	spin_lock_init(&sp->lock);
+
+	if (mpol) {
+		struct vm_area_struct pvma;
+		struct mempolicy *new;
+
+		/* contextualize the tmpfs mount point mempolicy */
+		new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask);
+		mpol_put(mpol);	/* drop our ref on sb mpol */
+		if (IS_ERR(new))
+			return;		/* no valid nodemask intersection */
+
+		/* Create pseudo-vma that contains just the policy */
+		memset(&pvma, 0, sizeof(struct vm_area_struct));
+		pvma.vm_end = TASK_SIZE;	/* policy covers entire file */
+		mpol_set_shared_policy(sp, &pvma, new); /* adds ref */
+		mpol_put(new);			/* drop initial ref */
 	}
 }
 
@@ -1670,9 +1867,10 @@ int mpol_set_shared_policy(struct shared_policy *info,
 	struct sp_node *new = NULL;
 	unsigned long sz = vma_pages(vma);
 
-	pr_debug("set_shared_policy %lx sz %lu %d %lx\n",
+	pr_debug("set_shared_policy %lx sz %lu %d %d %lx\n",
 		 vma->vm_pgoff,
-		 sz, npol? npol->policy : -1,
+		 sz, npol ? npol->mode : -1,
+		 npol ? npol->flags : -1,
 		 npol ? nodes_addr(npol->v.nodes)[0] : -1);
 
 	if (npol) {
@@ -1700,7 +1898,7 @@ void mpol_free_shared_policy(struct shared_policy *p)
 		n = rb_entry(next, struct sp_node, nd);
 		next = rb_next(&n->nd);
 		rb_erase(&n->nd, &p->root);
-		mpol_free(n->policy);
+		mpol_put(n->policy);
 		kmem_cache_free(sn_cache, n);
 	}
 	spin_unlock(&p->lock);
@@ -1745,120 +1943,177 @@ void __init numa_policy_init(void)
 	if (unlikely(nodes_empty(interleave_nodes)))
 		node_set(prefer, interleave_nodes);
 
-	if (do_set_mempolicy(MPOL_INTERLEAVE, &interleave_nodes))
+	if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes))
 		printk("numa_policy_init: interleaving failed\n");
 }
 
 /* Reset policy of current process to default */
 void numa_default_policy(void)
 {
-	do_set_mempolicy(MPOL_DEFAULT, NULL);
+	do_set_mempolicy(MPOL_DEFAULT, 0, NULL);
 }
 
-/* Migrate a policy to a different set of nodes */
-static void mpol_rebind_policy(struct mempolicy *pol,
-			       const nodemask_t *newmask)
-{
-	nodemask_t *mpolmask;
-	nodemask_t tmp;
+/*
+ * Parse and format mempolicy from/to strings
+ */
 
-	if (!pol)
-		return;
-	mpolmask = &pol->cpuset_mems_allowed;
-	if (nodes_equal(*mpolmask, *newmask))
-		return;
+/*
+ * "local" is pseudo-policy:  MPOL_PREFERRED with MPOL_F_LOCAL flag
+ * Used only for mpol_parse_str() and mpol_to_str()
+ */
+#define MPOL_LOCAL (MPOL_INTERLEAVE + 1)
+static const char * const policy_types[] =
+	{ "default", "prefer", "bind", "interleave", "local" };
 
-	switch (pol->policy) {
-	case MPOL_DEFAULT:
-		break;
-	case MPOL_INTERLEAVE:
-		nodes_remap(tmp, pol->v.nodes, *mpolmask, *newmask);
-		pol->v.nodes = tmp;
-		*mpolmask = *newmask;
-		current->il_next = node_remap(current->il_next,
-						*mpolmask, *newmask);
-		break;
-	case MPOL_PREFERRED:
-		pol->v.preferred_node = node_remap(pol->v.preferred_node,
-						*mpolmask, *newmask);
-		*mpolmask = *newmask;
-		break;
-	case MPOL_BIND: {
-		nodemask_t nodes;
-		struct zone **z;
-		struct zonelist *zonelist;
 
+#ifdef CONFIG_TMPFS
+/**
+ * mpol_parse_str - parse string to mempolicy
+ * @str:  string containing mempolicy to parse
+ * @mpol:  pointer to struct mempolicy pointer, returned on success.
+ * @no_context:  flag whether to "contextualize" the mempolicy
+ *
+ * Format of input:
+ *	<mode>[=<flags>][:<nodelist>]
+ *
+ * if @no_context is true, save the input nodemask in w.user_nodemask in
+ * the returned mempolicy.  This will be used to "clone" the mempolicy in
+ * a specific context [cpuset] at a later time.  Used to parse tmpfs mpol
+ * mount option.  Note that if 'static' or 'relative' mode flags were
+ * specified, the input nodemask will already have been saved.  Saving
+ * it again is redundant, but safe.
+ *
+ * On success, returns 0, else 1
+ */
+int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
+{
+	struct mempolicy *new = NULL;
+	unsigned short uninitialized_var(mode);
+	unsigned short uninitialized_var(mode_flags);
+	nodemask_t nodes;
+	char *nodelist = strchr(str, ':');
+	char *flags = strchr(str, '=');
+	int i;
+	int err = 1;
+
+	if (nodelist) {
+		/* NUL-terminate mode or flags string */
+		*nodelist++ = '\0';
+		if (nodelist_parse(nodelist, nodes))
+			goto out;
+		if (!nodes_subset(nodes, node_states[N_HIGH_MEMORY]))
+			goto out;
+	} else
 		nodes_clear(nodes);
-		for (z = pol->v.zonelist->zones; *z; z++)
-			node_set(zone_to_nid(*z), nodes);
-		nodes_remap(tmp, nodes, *mpolmask, *newmask);
-		nodes = tmp;
 
-		zonelist = bind_zonelist(&nodes);
+	if (flags)
+		*flags++ = '\0';	/* terminate mode string */
 
-		/* If no mem, then zonelist is NULL and we keep old zonelist.
-		 * If that old zonelist has no remaining mems_allowed nodes,
-		 * then zonelist_policy() will "FALL THROUGH" to MPOL_DEFAULT.
-		 */
+	for (i = 0; i <= MPOL_LOCAL; i++) {
+		if (!strcmp(str, policy_types[i])) {
+			mode = i;
+			break;
+		}
+	}
+	if (i > MPOL_LOCAL)
+		goto out;
 
-		if (!IS_ERR(zonelist)) {
-			/* Good - got mem - substitute new zonelist */
-			kfree(pol->v.zonelist);
-			pol->v.zonelist = zonelist;
+	switch (mode) {
+	case MPOL_PREFERRED:
+		/*
+		 * Insist on a nodelist of one node only
+		 */
+		if (nodelist) {
+			char *rest = nodelist;
+			while (isdigit(*rest))
+				rest++;
+			if (!*rest)
+				err = 0;
 		}
-		*mpolmask = *newmask;
 		break;
-	}
-	default:
-		BUG();
+	case MPOL_INTERLEAVE:
+		/*
+		 * Default to online nodes with memory if no nodelist
+		 */
+		if (!nodelist)
+			nodes = node_states[N_HIGH_MEMORY];
+		err = 0;
+		break;
+	case MPOL_LOCAL:
+		/*
+		 * Don't allow a nodelist;  mpol_new() checks flags
+		 */
+		if (nodelist)
+			goto out;
+		mode = MPOL_PREFERRED;
 		break;
-	}
-}
-
-/*
- * Wrapper for mpol_rebind_policy() that just requires task
- * pointer, and updates task mempolicy.
- */
 
-void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new)
-{
-	mpol_rebind_policy(tsk->mempolicy, new);
-}
+	/*
+	 * case MPOL_BIND:    mpol_new() enforces non-empty nodemask.
+	 * case MPOL_DEFAULT: mpol_new() enforces empty nodemask, ignores flags.
+	 */
+	}
 
-/*
- * Rebind each vma in mm to new nodemask.
- *
- * Call holding a reference to mm.  Takes mm->mmap_sem during call.
- */
+	mode_flags = 0;
+	if (flags) {
+		/*
+		 * Currently, we only support two mutually exclusive
+		 * mode flags.
+		 */
+		if (!strcmp(flags, "static"))
+			mode_flags |= MPOL_F_STATIC_NODES;
+		else if (!strcmp(flags, "relative"))
+			mode_flags |= MPOL_F_RELATIVE_NODES;
+		else
+			err = 1;
+	}
 
-void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
-{
-	struct vm_area_struct *vma;
+	new = mpol_new(mode, mode_flags, &nodes);
+	if (IS_ERR(new))
+		err = 1;
+	else if (no_context)
+		new->w.user_nodemask = nodes;	/* save for contextualization */
 
-	down_write(&mm->mmap_sem);
-	for (vma = mm->mmap; vma; vma = vma->vm_next)
-		mpol_rebind_policy(vma->vm_policy, new);
-	up_write(&mm->mmap_sem);
+out:
+	/* Restore string for error message */
+	if (nodelist)
+		*--nodelist = ':';
+	if (flags)
+		*--flags = '=';
+	if (!err)
+		*mpol = new;
+	return err;
 }
+#endif /* CONFIG_TMPFS */
 
-/*
- * Display pages allocated per node and memory policy via /proc.
- */
-
-static const char * const policy_types[] =
-	{ "default", "prefer", "bind", "interleave" };
-
-/*
+/**
+ * mpol_to_str - format a mempolicy structure for printing
+ * @buffer:  to contain formatted mempolicy string
+ * @maxlen:  length of @buffer
+ * @pol:  pointer to mempolicy to be formatted
+ * @no_context:  "context free" mempolicy - use nodemask in w.user_nodemask
+ *
  * Convert a mempolicy into a string.
  * Returns the number of characters in buffer (if positive)
  * or an error (negative)
  */
-static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
+int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
 {
 	char *p = buffer;
 	int l;
 	nodemask_t nodes;
-	int mode = pol ? pol->policy : MPOL_DEFAULT;
+	unsigned short mode;
+	unsigned short flags = pol ? pol->flags : 0;
+
+	/*
+	 * Sanity check:  room for longest mode, flag and some nodes
+	 */
+	VM_BUG_ON(maxlen < strlen("interleave") + strlen("relative") + 16);
+
+	if (!pol || pol == &default_policy)
+		mode = MPOL_DEFAULT;
+	else
+		mode = pol->mode;
 
 	switch (mode) {
 	case MPOL_DEFAULT:
@@ -1867,33 +2122,50 @@ static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 
 	case MPOL_PREFERRED:
 		nodes_clear(nodes);
-		node_set(pol->v.preferred_node, nodes);
+		if (flags & MPOL_F_LOCAL)
+			mode = MPOL_LOCAL;	/* pseudo-policy */
+		else
+			node_set(pol->v.preferred_node, nodes);
 		break;
 
 	case MPOL_BIND:
-		get_zonemask(pol, &nodes);
-		break;
-
+		/* Fall through */
 	case MPOL_INTERLEAVE:
-		nodes = pol->v.nodes;
+		if (no_context)
+			nodes = pol->w.user_nodemask;
+		else
+			nodes = pol->v.nodes;
 		break;
 
 	default:
 		BUG();
-		return -EFAULT;
 	}
 
 	l = strlen(policy_types[mode]);
- 	if (buffer + maxlen < p + l + 1)
- 		return -ENOSPC;
+	if (buffer + maxlen < p + l + 1)
+		return -ENOSPC;
 
 	strcpy(p, policy_types[mode]);
 	p += l;
 
-	if (!nodes_empty(nodes)) {
+	if (flags & MPOL_MODE_FLAGS) {
 		if (buffer + maxlen < p + 2)
 			return -ENOSPC;
 		*p++ = '=';
+
+		/*
+		 * Currently, the only defined flags are mutually exclusive
+		 */
+		if (flags & MPOL_F_STATIC_NODES)
+			p += snprintf(p, buffer + maxlen - p, "static");
+		else if (flags & MPOL_F_RELATIVE_NODES)
+			p += snprintf(p, buffer + maxlen - p, "relative");
+	}
+
+	if (!nodes_empty(nodes)) {
+		if (buffer + maxlen < p + 2)
+			return -ENOSPC;
+		*p++ = ':';
 	 	p += nodelist_scnprintf(p, buffer + maxlen - p, nodes);
 	}
 	return p - buffer;
@@ -1971,6 +2243,9 @@ static inline void check_huge_range(struct vm_area_struct *vma,
 }
 #endif
 
+/*
+ * Display pages allocated per node and memory policy via /proc.
+ */
 int show_numa_map(struct seq_file *m, void *v)
 {
 	struct proc_maps_private *priv = m->private;
@@ -1990,12 +2265,8 @@ int show_numa_map(struct seq_file *m, void *v)
 		return 0;
 
 	pol = get_vma_policy(priv->task, vma, vma->vm_start);
-	mpol_to_str(buffer, sizeof(buffer), pol);
-	/*
-	 * unref shared or other task's mempolicy
-	 */
-	if (pol != &default_policy && pol != current->mempolicy)
-		__mpol_free(pol);
+	mpol_to_str(buffer, sizeof(buffer), pol, 0);
+	mpol_cond_put(pol);
 
 	seq_printf(m, "%08lx %s", vma->vm_start, buffer);
 
diff --git a/trunk/mm/mincore.c b/trunk/mm/mincore.c
index 5efe0ded69b1..5178800bc129 100644
--- a/trunk/mm/mincore.c
+++ b/trunk/mm/mincore.c
@@ -33,7 +33,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 	 * When tmpfs swaps out a page from a file, any process mapping that
 	 * file will not get a swp_entry_t in its pte, but rather it is like
 	 * any other file mapping (ie. marked !present and faulted in with
-	 * tmpfs's .nopage). So swapped out tmpfs mappings are tested here.
+	 * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
 	 *
 	 * However when tmpfs moves the page from pagecache and into swapcache,
 	 * it is still in core, but the find_get_page below won't find it.
diff --git a/trunk/mm/mmap.c b/trunk/mm/mmap.c
index a32d28ce31cd..fac66337da2a 100644
--- a/trunk/mm/mmap.c
+++ b/trunk/mm/mmap.c
@@ -230,9 +230,12 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
 	might_sleep();
 	if (vma->vm_ops && vma->vm_ops->close)
 		vma->vm_ops->close(vma);
-	if (vma->vm_file)
+	if (vma->vm_file) {
 		fput(vma->vm_file);
-	mpol_free(vma_policy(vma));
+		if (vma->vm_flags & VM_EXECUTABLE)
+			removed_exe_file_vma(vma->vm_mm);
+	}
+	mpol_put(vma_policy(vma));
 	kmem_cache_free(vm_area_cachep, vma);
 	return next;
 }
@@ -623,10 +626,13 @@ again:			remove_next = 1 + (end > next->vm_end);
 		spin_unlock(&mapping->i_mmap_lock);
 
 	if (remove_next) {
-		if (file)
+		if (file) {
 			fput(file);
+			if (next->vm_flags & VM_EXECUTABLE)
+				removed_exe_file_vma(mm);
+		}
 		mm->map_count--;
-		mpol_free(vma_policy(next));
+		mpol_put(vma_policy(next));
 		kmem_cache_free(vm_area_cachep, next);
 		/*
 		 * In mprotect's case 6 (see comments on vma_merge),
@@ -1068,7 +1074,6 @@ int vma_wants_writenotify(struct vm_area_struct *vma)
 		mapping_cap_account_dirty(vma->vm_file->f_mapping);
 }
 
-
 unsigned long mmap_region(struct file *file, unsigned long addr,
 			  unsigned long len, unsigned long flags,
 			  unsigned int vm_flags, unsigned long pgoff,
@@ -1155,6 +1160,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		error = file->f_op->mmap(file, vma);
 		if (error)
 			goto unmap_and_free_vma;
+		if (vm_flags & VM_EXECUTABLE)
+			added_exe_file_vma(mm);
 	} else if (vm_flags & VM_SHARED) {
 		error = shmem_zero_setup(vma);
 		if (error)
@@ -1181,22 +1188,22 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	if (vma_wants_writenotify(vma))
 		vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED);
 
-	if (!file || !vma_merge(mm, prev, addr, vma->vm_end,
+	if (file && vma_merge(mm, prev, addr, vma->vm_end,
 			vma->vm_flags, NULL, file, pgoff, vma_policy(vma))) {
-		file = vma->vm_file;
-		vma_link(mm, vma, prev, rb_link, rb_parent);
-		if (correct_wcount)
-			atomic_inc(&inode->i_writecount);
-	} else {
-		if (file) {
-			if (correct_wcount)
-				atomic_inc(&inode->i_writecount);
-			fput(file);
-		}
-		mpol_free(vma_policy(vma));
+		mpol_put(vma_policy(vma));
 		kmem_cache_free(vm_area_cachep, vma);
+		fput(file);
+		if (vm_flags & VM_EXECUTABLE)
+			removed_exe_file_vma(mm);
+	} else {
+		vma_link(mm, vma, prev, rb_link, rb_parent);
+		file = vma->vm_file;
 	}
-out:	
+
+	/* Once vma denies write, undo our temporary denial count */
+	if (correct_wcount)
+		atomic_inc(&inode->i_writecount);
+out:
 	mm->total_vm += len >> PAGE_SHIFT;
 	vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
 	if (vm_flags & VM_LOCKED) {
@@ -1813,15 +1820,18 @@ int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 		new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT);
 	}
 
-	pol = mpol_copy(vma_policy(vma));
+	pol = mpol_dup(vma_policy(vma));
 	if (IS_ERR(pol)) {
 		kmem_cache_free(vm_area_cachep, new);
 		return PTR_ERR(pol);
 	}
 	vma_set_policy(new, pol);
 
-	if (new->vm_file)
+	if (new->vm_file) {
 		get_file(new->vm_file);
+		if (vma->vm_flags & VM_EXECUTABLE)
+			added_exe_file_vma(mm);
+	}
 
 	if (new->vm_ops && new->vm_ops->open)
 		new->vm_ops->open(new);
@@ -2129,7 +2139,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 		new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 		if (new_vma) {
 			*new_vma = *vma;
-			pol = mpol_copy(vma_policy(vma));
+			pol = mpol_dup(vma_policy(vma));
 			if (IS_ERR(pol)) {
 				kmem_cache_free(vm_area_cachep, new_vma);
 				return NULL;
@@ -2138,8 +2148,11 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 			new_vma->vm_start = addr;
 			new_vma->vm_end = addr + len;
 			new_vma->vm_pgoff = pgoff;
-			if (new_vma->vm_file)
+			if (new_vma->vm_file) {
 				get_file(new_vma->vm_file);
+				if (vma->vm_flags & VM_EXECUTABLE)
+					added_exe_file_vma(mm);
+			}
 			if (new_vma->vm_ops && new_vma->vm_ops->open)
 				new_vma->vm_ops->open(new_vma);
 			vma_link(mm, new_vma, prev, rb_link, rb_parent);
diff --git a/trunk/mm/mmzone.c b/trunk/mm/mmzone.c
index eb5838634f18..486ed595ee6f 100644
--- a/trunk/mm/mmzone.c
+++ b/trunk/mm/mmzone.c
@@ -42,3 +42,33 @@ struct zone *next_zone(struct zone *zone)
 	return zone;
 }
 
+static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes)
+{
+#ifdef CONFIG_NUMA
+	return node_isset(zonelist_node_idx(zref), *nodes);
+#else
+	return 1;
+#endif /* CONFIG_NUMA */
+}
+
+/* Returns the next zone at or below highest_zoneidx in a zonelist */
+struct zoneref *next_zones_zonelist(struct zoneref *z,
+					enum zone_type highest_zoneidx,
+					nodemask_t *nodes,
+					struct zone **zone)
+{
+	/*
+	 * Find the next suitable zone to use for the allocation.
+	 * Only filter based on nodemask if it's set
+	 */
+	if (likely(nodes == NULL))
+		while (zonelist_zone_idx(z) > highest_zoneidx)
+			z++;
+	else
+		while (zonelist_zone_idx(z) > highest_zoneidx ||
+				(z->zone && !zref_in_nodemask(z, nodes)))
+			z++;
+
+	*zone = zonelist_zone(z++);
+	return z;
+}
diff --git a/trunk/mm/nommu.c b/trunk/mm/nommu.c
index 5d8ae086f74e..ef8c62cec697 100644
--- a/trunk/mm/nommu.c
+++ b/trunk/mm/nommu.c
@@ -105,7 +105,11 @@ unsigned int kobjsize(const void *objp)
 {
 	struct page *page;
 
-	if (!objp || !((page = virt_to_page(objp))))
+	/*
+	 * If the object we have should not have ksize performed on it,
+	 * return size of 0
+	 */
+	if (!objp || (unsigned long)objp >= memory_end || !((page = virt_to_page(objp))))
 		return 0;
 
 	if (PageSlab(page))
@@ -962,8 +966,13 @@ unsigned long do_mmap_pgoff(struct file *file,
 
 	INIT_LIST_HEAD(&vma->anon_vma_node);
 	atomic_set(&vma->vm_usage, 1);
-	if (file)
+	if (file) {
 		get_file(file);
+		if (vm_flags & VM_EXECUTABLE) {
+			added_exe_file_vma(current->mm);
+			vma->vm_mm = current->mm;
+		}
+	}
 	vma->vm_file	= file;
 	vma->vm_flags	= vm_flags;
 	vma->vm_start	= addr;
@@ -1018,8 +1027,11 @@ unsigned long do_mmap_pgoff(struct file *file,
 	up_write(&nommu_vma_sem);
 	kfree(vml);
 	if (vma) {
-		if (vma->vm_file)
+		if (vma->vm_file) {
 			fput(vma->vm_file);
+			if (vma->vm_flags & VM_EXECUTABLE)
+				removed_exe_file_vma(vma->vm_mm);
+		}
 		kfree(vma);
 	}
 	return ret;
@@ -1049,7 +1061,7 @@ EXPORT_SYMBOL(do_mmap_pgoff);
 /*
  * handle mapping disposal for uClinux
  */
-static void put_vma(struct vm_area_struct *vma)
+static void put_vma(struct mm_struct *mm, struct vm_area_struct *vma)
 {
 	if (vma) {
 		down_write(&nommu_vma_sem);
@@ -1071,8 +1083,11 @@ static void put_vma(struct vm_area_struct *vma)
 			realalloc -= kobjsize(vma);
 			askedalloc -= sizeof(*vma);
 
-			if (vma->vm_file)
+			if (vma->vm_file) {
 				fput(vma->vm_file);
+				if (vma->vm_flags & VM_EXECUTABLE)
+					removed_exe_file_vma(mm);
+			}
 			kfree(vma);
 		}
 
@@ -1109,7 +1124,7 @@ int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len)
  found:
 	vml = *parent;
 
-	put_vma(vml->vma);
+	put_vma(mm, vml->vma);
 
 	*parent = vml->next;
 	realalloc -= kobjsize(vml);
@@ -1154,7 +1169,7 @@ void exit_mmap(struct mm_struct * mm)
 
 		while ((tmp = mm->context.vmlist)) {
 			mm->context.vmlist = tmp->next;
-			put_vma(tmp->vma);
+			put_vma(mm, tmp->vma);
 
 			realalloc -= kobjsize(tmp);
 			askedalloc -= sizeof(*tmp);
diff --git a/trunk/mm/oom_kill.c b/trunk/mm/oom_kill.c
index beb592fe9389..8a5467ee6265 100644
--- a/trunk/mm/oom_kill.c
+++ b/trunk/mm/oom_kill.c
@@ -53,8 +53,7 @@ static DEFINE_SPINLOCK(zone_scan_mutex);
  *    of least surprise ... (be careful when you change it)
  */
 
-unsigned long badness(struct task_struct *p, unsigned long uptime,
-			struct mem_cgroup *mem)
+unsigned long badness(struct task_struct *p, unsigned long uptime)
 {
 	unsigned long points, cpu_time, run_time, s;
 	struct mm_struct *mm;
@@ -175,12 +174,14 @@ static inline enum oom_constraint constrained_alloc(struct zonelist *zonelist,
 						    gfp_t gfp_mask)
 {
 #ifdef CONFIG_NUMA
-	struct zone **z;
+	struct zone *zone;
+	struct zoneref *z;
+	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	nodemask_t nodes = node_states[N_HIGH_MEMORY];
 
-	for (z = zonelist->zones; *z; z++)
-		if (cpuset_zone_allowed_softwall(*z, gfp_mask))
-			node_clear(zone_to_nid(*z), nodes);
+	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
+		if (cpuset_zone_allowed_softwall(zone, gfp_mask))
+			node_clear(zone_to_nid(zone), nodes);
 		else
 			return CONSTRAINT_CPUSET;
 
@@ -254,7 +255,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints,
 		if (p->oomkilladj == OOM_DISABLE)
 			continue;
 
-		points = badness(p, uptime.tv_sec, mem);
+		points = badness(p, uptime.tv_sec);
 		if (points > *ppoints || !chosen) {
 			chosen = p;
 			*ppoints = points;
@@ -460,29 +461,29 @@ EXPORT_SYMBOL_GPL(unregister_oom_notifier);
  * if a parallel OOM killing is already taking place that includes a zone in
  * the zonelist.  Otherwise, locks all zones in the zonelist and returns 1.
  */
-int try_set_zone_oom(struct zonelist *zonelist)
+int try_set_zone_oom(struct zonelist *zonelist, gfp_t gfp_mask)
 {
-	struct zone **z;
+	struct zoneref *z;
+	struct zone *zone;
 	int ret = 1;
 
-	z = zonelist->zones;
-
 	spin_lock(&zone_scan_mutex);
-	do {
-		if (zone_is_oom_locked(*z)) {
+	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
+		if (zone_is_oom_locked(zone)) {
 			ret = 0;
 			goto out;
 		}
-	} while (*(++z) != NULL);
+	}
+
+	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
+		/*
+		 * Lock each zone in the zonelist under zone_scan_mutex so a
+		 * parallel invocation of try_set_zone_oom() doesn't succeed
+		 * when it shouldn't.
+		 */
+		zone_set_flag(zone, ZONE_OOM_LOCKED);
+	}
 
-	/*
-	 * Lock each zone in the zonelist under zone_scan_mutex so a parallel
-	 * invocation of try_set_zone_oom() doesn't succeed when it shouldn't.
-	 */
-	z = zonelist->zones;
-	do {
-		zone_set_flag(*z, ZONE_OOM_LOCKED);
-	} while (*(++z) != NULL);
 out:
 	spin_unlock(&zone_scan_mutex);
 	return ret;
@@ -493,16 +494,15 @@ int try_set_zone_oom(struct zonelist *zonelist)
  * allocation attempts with zonelists containing them may now recall the OOM
  * killer, if necessary.
  */
-void clear_zonelist_oom(struct zonelist *zonelist)
+void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask)
 {
-	struct zone **z;
-
-	z = zonelist->zones;
+	struct zoneref *z;
+	struct zone *zone;
 
 	spin_lock(&zone_scan_mutex);
-	do {
-		zone_clear_flag(*z, ZONE_OOM_LOCKED);
-	} while (*(++z) != NULL);
+	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
+		zone_clear_flag(zone, ZONE_OOM_LOCKED);
+	}
 	spin_unlock(&zone_scan_mutex);
 }
 
diff --git a/trunk/mm/page_alloc.c b/trunk/mm/page_alloc.c
index 32e796af12a1..0a502e99ee22 100644
--- a/trunk/mm/page_alloc.c
+++ b/trunk/mm/page_alloc.c
@@ -546,7 +546,7 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 /*
  * permit the bootmem allocator to evade page validation on high-order frees
  */
-void __init __free_pages_bootmem(struct page *page, unsigned int order)
+void __free_pages_bootmem(struct page *page, unsigned int order)
 {
 	if (order == 0) {
 		__ClearPageReserved(page);
@@ -632,7 +632,7 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
 	if (PageReserved(page))
 		return 1;
 
-	page->flags &= ~(1 << PG_uptodate | 1 << PG_error | 1 << PG_readahead |
+	page->flags &= ~(1 << PG_uptodate | 1 << PG_error | 1 << PG_reclaim |
 			1 << PG_referenced | 1 << PG_arch_1 |
 			1 << PG_owner_priv_1 | 1 << PG_mappedtodisk);
 	set_page_private(page, 0);
@@ -1050,7 +1050,7 @@ void split_page(struct page *page, unsigned int order)
  * we cheat by calling it from here, in the order > 0 path.  Saves a branch
  * or two.
  */
-static struct page *buffered_rmqueue(struct zonelist *zonelist,
+static struct page *buffered_rmqueue(struct zone *preferred_zone,
 			struct zone *zone, int order, gfp_t gfp_flags)
 {
 	unsigned long flags;
@@ -1102,7 +1102,7 @@ static struct page *buffered_rmqueue(struct zonelist *zonelist,
 	}
 
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
-	zone_statistics(zonelist, zone);
+	zone_statistics(preferred_zone, zone);
 	local_irq_restore(flags);
 	put_cpu();
 
@@ -1284,7 +1284,7 @@ static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
 	if (!zlc)
 		return NULL;
 
-       if (time_after(jiffies, zlc->last_full_zap + HZ)) {
+	if (time_after(jiffies, zlc->last_full_zap + HZ)) {
 		bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
 		zlc->last_full_zap = jiffies;
 	}
@@ -1317,7 +1317,7 @@ static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
  * We are low on memory in the second scan, and should leave no stone
  * unturned looking for a free page.
  */
-static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z,
+static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
 						nodemask_t *allowednodes)
 {
 	struct zonelist_cache *zlc;	/* cached zonelist speedup info */
@@ -1328,7 +1328,7 @@ static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z,
 	if (!zlc)
 		return 1;
 
-	i = z - zonelist->zones;
+	i = z - zonelist->_zonerefs;
 	n = zlc->z_to_n[i];
 
 	/* This zone is worth trying if it is allowed but not full */
@@ -1340,7 +1340,7 @@ static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z,
  * zlc->fullzones, so that subsequent attempts to allocate a page
  * from that zone don't waste time re-examining it.
  */
-static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
+static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
 {
 	struct zonelist_cache *zlc;	/* cached zonelist speedup info */
 	int i;				/* index of *z in zonelist zones */
@@ -1349,7 +1349,7 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
 	if (!zlc)
 		return;
 
-	i = z - zonelist->zones;
+	i = z - zonelist->_zonerefs;
 
 	set_bit(i, zlc->fullzones);
 }
@@ -1361,13 +1361,13 @@ static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
 	return NULL;
 }
 
-static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z,
+static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
 				nodemask_t *allowednodes)
 {
 	return 1;
 }
 
-static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
+static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
 {
 }
 #endif	/* CONFIG_NUMA */
@@ -1377,42 +1377,31 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
  * a page.
  */
 static struct page *
-get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
-		struct zonelist *zonelist, int alloc_flags)
+get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
+		struct zonelist *zonelist, int high_zoneidx, int alloc_flags)
 {
-	struct zone **z;
+	struct zoneref *z;
 	struct page *page = NULL;
-	int classzone_idx = zone_idx(zonelist->zones[0]);
-	struct zone *zone;
+	int classzone_idx;
+	struct zone *zone, *preferred_zone;
 	nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
 	int zlc_active = 0;		/* set if using zonelist_cache */
 	int did_zlc_setup = 0;		/* just call zlc_setup() one time */
-	enum zone_type highest_zoneidx = -1; /* Gets set for policy zonelists */
+
+	(void)first_zones_zonelist(zonelist, high_zoneidx, nodemask,
+							&preferred_zone);
+	classzone_idx = zone_idx(preferred_zone);
 
 zonelist_scan:
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
 	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 	 */
-	z = zonelist->zones;
-
-	do {
-		/*
-		 * In NUMA, this could be a policy zonelist which contains
-		 * zones that may not be allowed by the current gfp_mask.
-		 * Check the zone is allowed by the current flags
-		 */
-		if (unlikely(alloc_should_filter_zonelist(zonelist))) {
-			if (highest_zoneidx == -1)
-				highest_zoneidx = gfp_zone(gfp_mask);
-			if (zone_idx(*z) > highest_zoneidx)
-				continue;
-		}
-
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+						high_zoneidx, nodemask) {
 		if (NUMA_BUILD && zlc_active &&
 			!zlc_zone_worth_trying(zonelist, z, allowednodes))
 				continue;
-		zone = *z;
 		if ((alloc_flags & ALLOC_CPUSET) &&
 			!cpuset_zone_allowed_softwall(zone, gfp_mask))
 				goto try_next_zone;
@@ -1433,7 +1422,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
 			}
 		}
 
-		page = buffered_rmqueue(zonelist, zone, order, gfp_mask);
+		page = buffered_rmqueue(preferred_zone, zone, order, gfp_mask);
 		if (page)
 			break;
 this_zone_full:
@@ -1446,7 +1435,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
 			zlc_active = 1;
 			did_zlc_setup = 1;
 		}
-	} while (*(++z) != NULL);
+	}
 
 	if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
 		/* Disable zlc cache for second zonelist scan */
@@ -1459,18 +1448,21 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
 /*
  * This is the 'heart' of the zoned buddy allocator.
  */
-struct page *
-__alloc_pages(gfp_t gfp_mask, unsigned int order,
-		struct zonelist *zonelist)
+static struct page *
+__alloc_pages_internal(gfp_t gfp_mask, unsigned int order,
+			struct zonelist *zonelist, nodemask_t *nodemask)
 {
 	const gfp_t wait = gfp_mask & __GFP_WAIT;
-	struct zone **z;
+	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
+	struct zoneref *z;
+	struct zone *zone;
 	struct page *page;
 	struct reclaim_state reclaim_state;
 	struct task_struct *p = current;
 	int do_retry;
 	int alloc_flags;
-	int did_some_progress;
+	unsigned long did_some_progress;
+	unsigned long pages_reclaimed = 0;
 
 	might_sleep_if(wait);
 
@@ -1478,9 +1470,9 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		return NULL;
 
 restart:
-	z = zonelist->zones;  /* the list of zones suitable for gfp_mask */
+	z = zonelist->_zonerefs;  /* the list of zones suitable for gfp_mask */
 
-	if (unlikely(*z == NULL)) {
+	if (unlikely(!z->zone)) {
 		/*
 		 * Happens if we have an empty zonelist as a result of
 		 * GFP_THISNODE being used on a memoryless node
@@ -1488,8 +1480,8 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		return NULL;
 	}
 
-	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
-				zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
+	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
+			zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET);
 	if (page)
 		goto got_pg;
 
@@ -1504,8 +1496,8 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 	if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
 		goto nopage;
 
-	for (z = zonelist->zones; *z; z++)
-		wakeup_kswapd(*z, order);
+	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
+		wakeup_kswapd(zone, order);
 
 	/*
 	 * OK, we're below the kswapd watermark and have kicked background
@@ -1533,7 +1525,8 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 	 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
 	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 	 */
-	page = get_page_from_freelist(gfp_mask, order, zonelist, alloc_flags);
+	page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
+						high_zoneidx, alloc_flags);
 	if (page)
 		goto got_pg;
 
@@ -1545,8 +1538,8 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
 nofail_alloc:
 			/* go through the zonelist yet again, ignoring mins */
-			page = get_page_from_freelist(gfp_mask, order,
-				zonelist, ALLOC_NO_WATERMARKS);
+			page = get_page_from_freelist(gfp_mask, nodemask, order,
+				zonelist, high_zoneidx, ALLOC_NO_WATERMARKS);
 			if (page)
 				goto got_pg;
 			if (gfp_mask & __GFP_NOFAIL) {
@@ -1569,7 +1562,7 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
-	did_some_progress = try_to_free_pages(zonelist->zones, order, gfp_mask);
+	did_some_progress = try_to_free_pages(zonelist, order, gfp_mask);
 
 	p->reclaim_state = NULL;
 	p->flags &= ~PF_MEMALLOC;
@@ -1580,12 +1573,12 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		drain_all_pages();
 
 	if (likely(did_some_progress)) {
-		page = get_page_from_freelist(gfp_mask, order,
-						zonelist, alloc_flags);
+		page = get_page_from_freelist(gfp_mask, nodemask, order,
+					zonelist, high_zoneidx, alloc_flags);
 		if (page)
 			goto got_pg;
 	} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
-		if (!try_set_zone_oom(zonelist)) {
+		if (!try_set_zone_oom(zonelist, gfp_mask)) {
 			schedule_timeout_uninterruptible(1);
 			goto restart;
 		}
@@ -1596,21 +1589,22 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 		 * a parallel oom killing, we must fail if we're still
 		 * under heavy pressure.
 		 */
-		page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
-				zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
+		page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
+			order, zonelist, high_zoneidx,
+			ALLOC_WMARK_HIGH|ALLOC_CPUSET);
 		if (page) {
-			clear_zonelist_oom(zonelist);
+			clear_zonelist_oom(zonelist, gfp_mask);
 			goto got_pg;
 		}
 
 		/* The OOM killer will not help higher order allocs so fail */
 		if (order > PAGE_ALLOC_COSTLY_ORDER) {
-			clear_zonelist_oom(zonelist);
+			clear_zonelist_oom(zonelist, gfp_mask);
 			goto nopage;
 		}
 
 		out_of_memory(zonelist, gfp_mask, order);
-		clear_zonelist_oom(zonelist);
+		clear_zonelist_oom(zonelist, gfp_mask);
 		goto restart;
 	}
 
@@ -1618,14 +1612,26 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 	 * Don't let big-order allocations loop unless the caller explicitly
 	 * requests that.  Wait for some write requests to complete then retry.
 	 *
-	 * In this implementation, __GFP_REPEAT means __GFP_NOFAIL for order
-	 * <= 3, but that may not be true in other implementations.
+	 * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
+	 * means __GFP_NOFAIL, but that may not be true in other
+	 * implementations.
+	 *
+	 * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
+	 * specified, then we retry until we no longer reclaim any pages
+	 * (above), or we've reclaimed an order of pages at least as
+	 * large as the allocation's order. In both cases, if the
+	 * allocation still fails, we stop retrying.
 	 */
+	pages_reclaimed += did_some_progress;
 	do_retry = 0;
 	if (!(gfp_mask & __GFP_NORETRY)) {
-		if ((order <= PAGE_ALLOC_COSTLY_ORDER) ||
-						(gfp_mask & __GFP_REPEAT))
+		if (order <= PAGE_ALLOC_COSTLY_ORDER) {
 			do_retry = 1;
+		} else {
+			if (gfp_mask & __GFP_REPEAT &&
+				pages_reclaimed < (1 << order))
+					do_retry = 1;
+		}
 		if (gfp_mask & __GFP_NOFAIL)
 			do_retry = 1;
 	}
@@ -1646,6 +1652,20 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 	return page;
 }
 
+struct page *
+__alloc_pages(gfp_t gfp_mask, unsigned int order,
+		struct zonelist *zonelist)
+{
+	return __alloc_pages_internal(gfp_mask, order, zonelist, NULL);
+}
+
+struct page *
+__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
+		struct zonelist *zonelist, nodemask_t *nodemask)
+{
+	return __alloc_pages_internal(gfp_mask, order, zonelist, nodemask);
+}
+
 EXPORT_SYMBOL(__alloc_pages);
 
 /*
@@ -1712,15 +1732,15 @@ EXPORT_SYMBOL(free_pages);
 
 static unsigned int nr_free_zone_pages(int offset)
 {
+	struct zoneref *z;
+	struct zone *zone;
+
 	/* Just pick one node, since fallback list is circular */
-	pg_data_t *pgdat = NODE_DATA(numa_node_id());
 	unsigned int sum = 0;
 
-	struct zonelist *zonelist = pgdat->node_zonelists + offset;
-	struct zone **zonep = zonelist->zones;
-	struct zone *zone;
+	struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);
 
-	for (zone = *zonep++; zone; zone = *zonep++) {
+	for_each_zone_zonelist(zone, z, zonelist, offset) {
 		unsigned long size = zone->present_pages;
 		unsigned long high = zone->pages_high;
 		if (size > high)
@@ -1889,6 +1909,12 @@ void show_free_areas(void)
 	show_swap_cache_info();
 }
 
+static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
+{
+	zoneref->zone = zone;
+	zoneref->zone_idx = zone_idx(zone);
+}
+
 /*
  * Builds allocation fallback zone lists.
  *
@@ -1906,7 +1932,8 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
 		zone_type--;
 		zone = pgdat->node_zones + zone_type;
 		if (populated_zone(zone)) {
-			zonelist->zones[nr_zones++] = zone;
+			zoneref_set_zone(zone,
+				&zonelist->_zonerefs[nr_zones++]);
 			check_highest_zone(zone_type);
 		}
 
@@ -2078,17 +2105,16 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
  */
 static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
 {
-	enum zone_type i;
 	int j;
 	struct zonelist *zonelist;
 
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		zonelist = pgdat->node_zonelists + i;
-		for (j = 0; zonelist->zones[j] != NULL; j++)
-			;
- 		j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
-		zonelist->zones[j] = NULL;
-	}
+	zonelist = &pgdat->node_zonelists[0];
+	for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++)
+		;
+	j = build_zonelists_node(NODE_DATA(node), zonelist, j,
+							MAX_NR_ZONES - 1);
+	zonelist->_zonerefs[j].zone = NULL;
+	zonelist->_zonerefs[j].zone_idx = 0;
 }
 
 /*
@@ -2096,15 +2122,13 @@ static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
  */
 static void build_thisnode_zonelists(pg_data_t *pgdat)
 {
-	enum zone_type i;
 	int j;
 	struct zonelist *zonelist;
 
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		zonelist = pgdat->node_zonelists + MAX_NR_ZONES + i;
-		j = build_zonelists_node(pgdat, zonelist, 0, i);
-		zonelist->zones[j] = NULL;
-	}
+	zonelist = &pgdat->node_zonelists[1];
+	j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);
+	zonelist->_zonerefs[j].zone = NULL;
+	zonelist->_zonerefs[j].zone_idx = 0;
 }
 
 /*
@@ -2117,27 +2141,26 @@ static int node_order[MAX_NUMNODES];
 
 static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
 {
-	enum zone_type i;
 	int pos, j, node;
 	int zone_type;		/* needs to be signed */
 	struct zone *z;
 	struct zonelist *zonelist;
 
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		zonelist = pgdat->node_zonelists + i;
-		pos = 0;
-		for (zone_type = i; zone_type >= 0; zone_type--) {
-			for (j = 0; j < nr_nodes; j++) {
-				node = node_order[j];
-				z = &NODE_DATA(node)->node_zones[zone_type];
-				if (populated_zone(z)) {
-					zonelist->zones[pos++] = z;
-					check_highest_zone(zone_type);
-				}
+	zonelist = &pgdat->node_zonelists[0];
+	pos = 0;
+	for (zone_type = MAX_NR_ZONES - 1; zone_type >= 0; zone_type--) {
+		for (j = 0; j < nr_nodes; j++) {
+			node = node_order[j];
+			z = &NODE_DATA(node)->node_zones[zone_type];
+			if (populated_zone(z)) {
+				zoneref_set_zone(z,
+					&zonelist->_zonerefs[pos++]);
+				check_highest_zone(zone_type);
 			}
 		}
-		zonelist->zones[pos] = NULL;
 	}
+	zonelist->_zonerefs[pos].zone = NULL;
+	zonelist->_zonerefs[pos].zone_idx = 0;
 }
 
 static int default_zonelist_order(void)
@@ -2214,7 +2237,8 @@ static void build_zonelists(pg_data_t *pgdat)
 	/* initialize zonelists */
 	for (i = 0; i < MAX_ZONELISTS; i++) {
 		zonelist = pgdat->node_zonelists + i;
-		zonelist->zones[0] = NULL;
+		zonelist->_zonerefs[0].zone = NULL;
+		zonelist->_zonerefs[0].zone_idx = 0;
 	}
 
 	/* NUMA-aware ordering of nodes */
@@ -2264,19 +2288,15 @@ static void build_zonelists(pg_data_t *pgdat)
 /* Construct the zonelist performance cache - see further mmzone.h */
 static void build_zonelist_cache(pg_data_t *pgdat)
 {
-	int i;
-
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		struct zonelist *zonelist;
-		struct zonelist_cache *zlc;
-		struct zone **z;
+	struct zonelist *zonelist;
+	struct zonelist_cache *zlc;
+	struct zoneref *z;
 
-		zonelist = pgdat->node_zonelists + i;
-		zonelist->zlcache_ptr = zlc = &zonelist->zlcache;
-		bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
-		for (z = zonelist->zones; *z; z++)
-			zlc->z_to_n[z - zonelist->zones] = zone_to_nid(*z);
-	}
+	zonelist = &pgdat->node_zonelists[0];
+	zonelist->zlcache_ptr = zlc = &zonelist->zlcache;
+	bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
+	for (z = zonelist->_zonerefs; z->zone; z++)
+		zlc->z_to_n[z - zonelist->_zonerefs] = zonelist_node_idx(z);
 }
 
 
@@ -2290,45 +2310,44 @@ static void set_zonelist_order(void)
 static void build_zonelists(pg_data_t *pgdat)
 {
 	int node, local_node;
-	enum zone_type i,j;
+	enum zone_type j;
+	struct zonelist *zonelist;
 
 	local_node = pgdat->node_id;
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		struct zonelist *zonelist;
 
-		zonelist = pgdat->node_zonelists + i;
+	zonelist = &pgdat->node_zonelists[0];
+	j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);
 
- 		j = build_zonelists_node(pgdat, zonelist, 0, i);
- 		/*
- 		 * Now we build the zonelist so that it contains the zones
- 		 * of all the other nodes.
- 		 * We don't want to pressure a particular node, so when
- 		 * building the zones for node N, we make sure that the
- 		 * zones coming right after the local ones are those from
- 		 * node N+1 (modulo N)
- 		 */
-		for (node = local_node + 1; node < MAX_NUMNODES; node++) {
-			if (!node_online(node))
-				continue;
-			j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
-		}
-		for (node = 0; node < local_node; node++) {
-			if (!node_online(node))
-				continue;
-			j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
-		}
-
-		zonelist->zones[j] = NULL;
+	/*
+	 * Now we build the zonelist so that it contains the zones
+	 * of all the other nodes.
+	 * We don't want to pressure a particular node, so when
+	 * building the zones for node N, we make sure that the
+	 * zones coming right after the local ones are those from
+	 * node N+1 (modulo N)
+	 */
+	for (node = local_node + 1; node < MAX_NUMNODES; node++) {
+		if (!node_online(node))
+			continue;
+		j = build_zonelists_node(NODE_DATA(node), zonelist, j,
+							MAX_NR_ZONES - 1);
 	}
+	for (node = 0; node < local_node; node++) {
+		if (!node_online(node))
+			continue;
+		j = build_zonelists_node(NODE_DATA(node), zonelist, j,
+							MAX_NR_ZONES - 1);
+	}
+
+	zonelist->_zonerefs[j].zone = NULL;
+	zonelist->_zonerefs[j].zone_idx = 0;
 }
 
 /* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */
 static void build_zonelist_cache(pg_data_t *pgdat)
 {
-	int i;
-
-	for (i = 0; i < MAX_NR_ZONES; i++)
-		pgdat->node_zonelists[i].zlcache_ptr = NULL;
+	pgdat->node_zonelists[0].zlcache_ptr = NULL;
+	pgdat->node_zonelists[1].zlcache_ptr = NULL;
 }
 
 #endif	/* CONFIG_NUMA */
@@ -2518,7 +2537,9 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 	struct page *page;
 	unsigned long end_pfn = start_pfn + size;
 	unsigned long pfn;
+	struct zone *z;
 
+	z = &NODE_DATA(nid)->node_zones[zone];
 	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
 		/*
 		 * There can be holes in boot-time mem_map[]s
@@ -2536,7 +2557,6 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		init_page_count(page);
 		reset_page_mapcount(page);
 		SetPageReserved(page);
-
 		/*
 		 * Mark the block movable so that blocks are reserved for
 		 * movable at startup. This will force kernel allocations
@@ -2545,8 +2565,15 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		 * kernel allocations are made. Later some blocks near
 		 * the start are marked MIGRATE_RESERVE by
 		 * setup_zone_migrate_reserve()
+		 *
+		 * bitmap is created for zone's valid pfn range. but memmap
+		 * can be created for invalid pages (for alignment)
+		 * check here not to call set_pageblock_migratetype() against
+		 * pfn out of zone.
 		 */
-		if ((pfn & (pageblock_nr_pages-1)))
+		if ((z->zone_start_pfn <= pfn)
+		    && (pfn < z->zone_start_pfn + z->spanned_pages)
+		    && !(pfn & (pageblock_nr_pages - 1)))
 			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
 
 		INIT_LIST_HEAD(&page->lru);
@@ -4339,9 +4366,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 		else if (hashdist)
 			table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
 		else {
-			unsigned long order;
-			for (order = 0; ((1UL << order) << PAGE_SHIFT) < size; order++)
-				;
+			unsigned long order = get_order(size);
 			table = (void*) __get_free_pages(GFP_ATOMIC, order);
 			/*
 			 * If bucketsize is not a power-of-two, we may free
@@ -4460,6 +4485,8 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags,
 	pfn = page_to_pfn(page);
 	bitmap = get_pageblock_bitmap(zone, pfn);
 	bitidx = pfn_to_bitidx(zone, pfn);
+	VM_BUG_ON(pfn < zone->zone_start_pfn);
+	VM_BUG_ON(pfn >= zone->zone_start_pfn + zone->spanned_pages);
 
 	for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
 		if (flags & value)
diff --git a/trunk/mm/pagewalk.c b/trunk/mm/pagewalk.c
index 1cf1417ef8b7..0afd2387e507 100644
--- a/trunk/mm/pagewalk.c
+++ b/trunk/mm/pagewalk.c
@@ -9,11 +9,15 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	int err = 0;
 
 	pte = pte_offset_map(pmd, addr);
-	do {
+	for (;;) {
 		err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, private);
 		if (err)
 		       break;
-	} while (pte++, addr += PAGE_SIZE, addr != end);
+		addr += PAGE_SIZE;
+		if (addr == end)
+			break;
+		pte++;
+	}
 
 	pte_unmap(pte);
 	return err;
diff --git a/trunk/mm/rmap.c b/trunk/mm/rmap.c
index 997f06907b6d..bf0a5b7cfb8e 100644
--- a/trunk/mm/rmap.c
+++ b/trunk/mm/rmap.c
@@ -413,9 +413,6 @@ int page_referenced(struct page *page, int is_locked,
 {
 	int referenced = 0;
 
-	if (page_test_and_clear_young(page))
-		referenced++;
-
 	if (TestClearPageReferenced(page))
 		referenced++;
 
@@ -433,6 +430,10 @@ int page_referenced(struct page *page, int is_locked,
 			unlock_page(page);
 		}
 	}
+
+	if (page_test_and_clear_young(page))
+		referenced++;
+
 	return referenced;
 }
 
@@ -661,7 +662,6 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma)
 			printk (KERN_EMERG "  page->mapping = %p\n", page->mapping);
 			print_symbol (KERN_EMERG "  vma->vm_ops = %s\n", (unsigned long)vma->vm_ops);
 			if (vma->vm_ops) {
-				print_symbol (KERN_EMERG "  vma->vm_ops->nopage = %s\n", (unsigned long)vma->vm_ops->nopage);
 				print_symbol (KERN_EMERG "  vma->vm_ops->fault = %s\n", (unsigned long)vma->vm_ops->fault);
 			}
 			if (vma->vm_file && vma->vm_file->f_op)
diff --git a/trunk/mm/shmem.c b/trunk/mm/shmem.c
index f514dd392cd9..e6d9298aa22a 100644
--- a/trunk/mm/shmem.c
+++ b/trunk/mm/shmem.c
@@ -1079,104 +1079,47 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 
 #ifdef CONFIG_NUMA
 #ifdef CONFIG_TMPFS
-static int shmem_parse_mpol(char *value, int *policy, nodemask_t *policy_nodes)
+static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)
 {
-	char *nodelist = strchr(value, ':');
-	int err = 1;
+	char buffer[64];
 
-	if (nodelist) {
-		/* NUL-terminate policy string */
-		*nodelist++ = '\0';
-		if (nodelist_parse(nodelist, *policy_nodes))
-			goto out;
-		if (!nodes_subset(*policy_nodes, node_states[N_HIGH_MEMORY]))
-			goto out;
-	}
-	if (!strcmp(value, "default")) {
-		*policy = MPOL_DEFAULT;
-		/* Don't allow a nodelist */
-		if (!nodelist)
-			err = 0;
-	} else if (!strcmp(value, "prefer")) {
-		*policy = MPOL_PREFERRED;
-		/* Insist on a nodelist of one node only */
-		if (nodelist) {
-			char *rest = nodelist;
-			while (isdigit(*rest))
-				rest++;
-			if (!*rest)
-				err = 0;
-		}
-	} else if (!strcmp(value, "bind")) {
-		*policy = MPOL_BIND;
-		/* Insist on a nodelist */
-		if (nodelist)
-			err = 0;
-	} else if (!strcmp(value, "interleave")) {
-		*policy = MPOL_INTERLEAVE;
-		/*
-		 * Default to online nodes with memory if no nodelist
-		 */
-		if (!nodelist)
-			*policy_nodes = node_states[N_HIGH_MEMORY];
-		err = 0;
-	}
-out:
-	/* Restore string for error message */
-	if (nodelist)
-		*--nodelist = ':';
-	return err;
-}
-
-static void shmem_show_mpol(struct seq_file *seq, int policy,
-			    const nodemask_t policy_nodes)
-{
-	char *policy_string;
+	if (!mpol || mpol->mode == MPOL_DEFAULT)
+		return;		/* show nothing */
 
-	switch (policy) {
-	case MPOL_PREFERRED:
-		policy_string = "prefer";
-		break;
-	case MPOL_BIND:
-		policy_string = "bind";
-		break;
-	case MPOL_INTERLEAVE:
-		policy_string = "interleave";
-		break;
-	default:
-		/* MPOL_DEFAULT */
-		return;
-	}
+	mpol_to_str(buffer, sizeof(buffer), mpol, 1);
 
-	seq_printf(seq, ",mpol=%s", policy_string);
-
-	if (policy != MPOL_INTERLEAVE ||
-	    !nodes_equal(policy_nodes, node_states[N_HIGH_MEMORY])) {
-		char buffer[64];
-		int len;
+	seq_printf(seq, ",mpol=%s", buffer);
+}
 
-		len = nodelist_scnprintf(buffer, sizeof(buffer), policy_nodes);
-		if (len < sizeof(buffer))
-			seq_printf(seq, ":%s", buffer);
-		else
-			seq_printf(seq, ":?");
+static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
+{
+	struct mempolicy *mpol = NULL;
+	if (sbinfo->mpol) {
+		spin_lock(&sbinfo->stat_lock);	/* prevent replace/use races */
+		mpol = sbinfo->mpol;
+		mpol_get(mpol);
+		spin_unlock(&sbinfo->stat_lock);
 	}
+	return mpol;
 }
 #endif /* CONFIG_TMPFS */
 
 static struct page *shmem_swapin(swp_entry_t entry, gfp_t gfp,
 			struct shmem_inode_info *info, unsigned long idx)
 {
+	struct mempolicy mpol, *spol;
 	struct vm_area_struct pvma;
 	struct page *page;
 
+	spol = mpol_cond_copy(&mpol,
+				mpol_shared_policy_lookup(&info->policy, idx));
+
 	/* Create a pseudo vma that just contains the policy */
 	pvma.vm_start = 0;
 	pvma.vm_pgoff = idx;
 	pvma.vm_ops = NULL;
-	pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
+	pvma.vm_policy = spol;
 	page = swapin_readahead(entry, gfp, &pvma, 0);
-	mpol_free(pvma.vm_policy);
 	return page;
 }
 
@@ -1184,27 +1127,21 @@ static struct page *shmem_alloc_page(gfp_t gfp,
 			struct shmem_inode_info *info, unsigned long idx)
 {
 	struct vm_area_struct pvma;
-	struct page *page;
 
 	/* Create a pseudo vma that just contains the policy */
 	pvma.vm_start = 0;
 	pvma.vm_pgoff = idx;
 	pvma.vm_ops = NULL;
 	pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
-	page = alloc_page_vma(gfp, &pvma, 0);
-	mpol_free(pvma.vm_policy);
-	return page;
+
+	/*
+	 * alloc_page_vma() will drop the shared policy reference
+	 */
+	return alloc_page_vma(gfp, &pvma, 0);
 }
 #else /* !CONFIG_NUMA */
 #ifdef CONFIG_TMPFS
-static inline int shmem_parse_mpol(char *value, int *policy,
-						nodemask_t *policy_nodes)
-{
-	return 1;
-}
-
-static inline void shmem_show_mpol(struct seq_file *seq, int policy,
-			    const nodemask_t policy_nodes)
+static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *p)
 {
 }
 #endif /* CONFIG_TMPFS */
@@ -1222,6 +1159,13 @@ static inline struct page *shmem_alloc_page(gfp_t gfp,
 }
 #endif /* CONFIG_NUMA */
 
+#if !defined(CONFIG_NUMA) || !defined(CONFIG_TMPFS)
+static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
+{
+	return NULL;
+}
+#endif
+
 /*
  * shmem_getpage - either get the page from swap or allocate a new one
  *
@@ -1576,8 +1520,8 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev)
 		case S_IFREG:
 			inode->i_op = &shmem_inode_operations;
 			inode->i_fop = &shmem_file_operations;
-			mpol_shared_policy_init(&info->policy, sbinfo->policy,
-							&sbinfo->policy_nodes);
+			mpol_shared_policy_init(&info->policy,
+						 shmem_get_sbmpol(sbinfo));
 			break;
 		case S_IFDIR:
 			inc_nlink(inode);
@@ -1591,8 +1535,7 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev)
 			 * Must not load anything in the rbtree,
 			 * mpol_free_shared_policy will not be called.
 			 */
-			mpol_shared_policy_init(&info->policy, MPOL_DEFAULT,
-						NULL);
+			mpol_shared_policy_init(&info->policy, NULL);
 			break;
 		}
 	} else
@@ -2207,8 +2150,7 @@ static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo,
 			if (*rest)
 				goto bad_val;
 		} else if (!strcmp(this_char,"mpol")) {
-			if (shmem_parse_mpol(value, &sbinfo->policy,
-					     &sbinfo->policy_nodes))
+			if (mpol_parse_str(value, &sbinfo->mpol, 1))
 				goto bad_val;
 		} else {
 			printk(KERN_ERR "tmpfs: Bad mount option %s\n",
@@ -2259,8 +2201,9 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data)
 	sbinfo->free_blocks = config.max_blocks - blocks;
 	sbinfo->max_inodes  = config.max_inodes;
 	sbinfo->free_inodes = config.max_inodes - inodes;
-	sbinfo->policy      = config.policy;
-	sbinfo->policy_nodes = config.policy_nodes;
+
+	mpol_put(sbinfo->mpol);
+	sbinfo->mpol        = config.mpol;	/* transfers initial ref */
 out:
 	spin_unlock(&sbinfo->stat_lock);
 	return error;
@@ -2281,7 +2224,7 @@ static int shmem_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_printf(seq, ",uid=%u", sbinfo->uid);
 	if (sbinfo->gid != 0)
 		seq_printf(seq, ",gid=%u", sbinfo->gid);
-	shmem_show_mpol(seq, sbinfo->policy, sbinfo->policy_nodes);
+	shmem_show_mpol(seq, sbinfo->mpol);
 	return 0;
 }
 #endif /* CONFIG_TMPFS */
@@ -2311,8 +2254,7 @@ static int shmem_fill_super(struct super_block *sb,
 	sbinfo->mode = S_IRWXUGO | S_ISVTX;
 	sbinfo->uid = current->fsuid;
 	sbinfo->gid = current->fsgid;
-	sbinfo->policy = MPOL_DEFAULT;
-	sbinfo->policy_nodes = node_states[N_HIGH_MEMORY];
+	sbinfo->mpol = NULL;
 	sb->s_fs_info = sbinfo;
 
 #ifdef CONFIG_TMPFS
diff --git a/trunk/mm/slab.c b/trunk/mm/slab.c
index 03927cb5ec9e..39d20f8a0791 100644
--- a/trunk/mm/slab.c
+++ b/trunk/mm/slab.c
@@ -139,10 +139,6 @@
 #define	BYTES_PER_WORD		sizeof(void *)
 #define	REDZONE_ALIGN		max(BYTES_PER_WORD, __alignof__(unsigned long long))
 
-#ifndef cache_line_size
-#define cache_line_size()	L1_CACHE_BYTES
-#endif
-
 #ifndef ARCH_KMALLOC_MINALIGN
 /*
  * Enforce a minimum alignment for the kmalloc caches.
@@ -3242,15 +3238,16 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 {
 	struct zonelist *zonelist;
 	gfp_t local_flags;
-	struct zone **z;
+	struct zoneref *z;
+	struct zone *zone;
+	enum zone_type high_zoneidx = gfp_zone(flags);
 	void *obj = NULL;
 	int nid;
 
 	if (flags & __GFP_THISNODE)
 		return NULL;
 
-	zonelist = &NODE_DATA(slab_node(current->mempolicy))
-			->node_zonelists[gfp_zone(flags)];
+	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
 	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
 
 retry:
@@ -3258,10 +3255,10 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 	 * Look through allowed nodes for objects available
 	 * from existing per node queues.
 	 */
-	for (z = zonelist->zones; *z && !obj; z++) {
-		nid = zone_to_nid(*z);
+	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
+		nid = zone_to_nid(zone);
 
-		if (cpuset_zone_allowed_hardwall(*z, flags) &&
+		if (cpuset_zone_allowed_hardwall(zone, flags) &&
 			cache->nodelists[nid] &&
 			cache->nodelists[nid]->free_objects)
 				obj = ____cache_alloc_node(cache,
diff --git a/trunk/mm/slob.c b/trunk/mm/slob.c
index e2c3c0ec5463..6038cbadf796 100644
--- a/trunk/mm/slob.c
+++ b/trunk/mm/slob.c
@@ -533,7 +533,8 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 {
 	struct kmem_cache *c;
 
-	c = slob_alloc(sizeof(struct kmem_cache), flags, 0, -1);
+	c = slob_alloc(sizeof(struct kmem_cache),
+		flags, ARCH_KMALLOC_MINALIGN, -1);
 
 	if (c) {
 		c->name = name;
diff --git a/trunk/mm/slub.c b/trunk/mm/slub.c
index 39592b5ce68a..b145e798bf3d 100644
--- a/trunk/mm/slub.c
+++ b/trunk/mm/slub.c
@@ -149,25 +149,6 @@ static inline void ClearSlabDebug(struct page *page)
 /* Enable to test recovery from slab corruption on boot */
 #undef SLUB_RESILIENCY_TEST
 
-#if PAGE_SHIFT <= 12
-
-/*
- * Small page size. Make sure that we do not fragment memory
- */
-#define DEFAULT_MAX_ORDER 1
-#define DEFAULT_MIN_OBJECTS 4
-
-#else
-
-/*
- * Large page machines are customarily able to handle larger
- * page orders.
- */
-#define DEFAULT_MAX_ORDER 2
-#define DEFAULT_MIN_OBJECTS 8
-
-#endif
-
 /*
  * Mininum number of partial slabs. These will be left on the partial
  * lists even if they are empty. kmem_cache_shrink may reclaim them.
@@ -204,13 +185,6 @@ static inline void ClearSlabDebug(struct page *page)
 /* Internal SLUB flags */
 #define __OBJECT_POISON		0x80000000 /* Poison object */
 #define __SYSFS_ADD_DEFERRED	0x40000000 /* Not yet visible via sysfs */
-#define __KMALLOC_CACHE		0x20000000 /* objects freed using kfree */
-#define __PAGE_ALLOC_FALLBACK	0x10000000 /* Allow fallback to page alloc */
-
-/* Not all arches define cache_line_size */
-#ifndef cache_line_size
-#define cache_line_size()	L1_CACHE_BYTES
-#endif
 
 static int kmem_size = sizeof(struct kmem_cache);
 
@@ -301,7 +275,7 @@ static inline int check_valid_pointer(struct kmem_cache *s,
 		return 1;
 
 	base = page_address(page);
-	if (object < base || object >= base + s->objects * s->size ||
+	if (object < base || object >= base + page->objects * s->size ||
 		(object - base) % s->size) {
 		return 0;
 	}
@@ -327,8 +301,8 @@ static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
 }
 
 /* Loop over all objects in a slab */
-#define for_each_object(__p, __s, __addr) \
-	for (__p = (__addr); __p < (__addr) + (__s)->objects * (__s)->size;\
+#define for_each_object(__p, __s, __addr, __objects) \
+	for (__p = (__addr); __p < (__addr) + (__objects) * (__s)->size;\
 			__p += (__s)->size)
 
 /* Scan freelist */
@@ -341,6 +315,26 @@ static inline int slab_index(void *p, struct kmem_cache *s, void *addr)
 	return (p - addr) / s->size;
 }
 
+static inline struct kmem_cache_order_objects oo_make(int order,
+						unsigned long size)
+{
+	struct kmem_cache_order_objects x = {
+		(order << 16) + (PAGE_SIZE << order) / size
+	};
+
+	return x;
+}
+
+static inline int oo_order(struct kmem_cache_order_objects x)
+{
+	return x.x >> 16;
+}
+
+static inline int oo_objects(struct kmem_cache_order_objects x)
+{
+	return x.x & ((1 << 16) - 1);
+}
+
 #ifdef CONFIG_SLUB_DEBUG
 /*
  * Debug settings:
@@ -451,8 +445,8 @@ static void print_tracking(struct kmem_cache *s, void *object)
 
 static void print_page_info(struct page *page)
 {
-	printk(KERN_ERR "INFO: Slab 0x%p used=%u fp=0x%p flags=0x%04lx\n",
-		page, page->inuse, page->freelist, page->flags);
+	printk(KERN_ERR "INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n",
+		page, page->objects, page->inuse, page->freelist, page->flags);
 
 }
 
@@ -652,6 +646,7 @@ static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p)
 				p + off, POISON_INUSE, s->size - off);
 }
 
+/* Check the pad bytes at the end of a slab page */
 static int slab_pad_check(struct kmem_cache *s, struct page *page)
 {
 	u8 *start;
@@ -664,20 +659,20 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page)
 		return 1;
 
 	start = page_address(page);
-	end = start + (PAGE_SIZE << s->order);
-	length = s->objects * s->size;
-	remainder = end - (start + length);
+	length = (PAGE_SIZE << compound_order(page));
+	end = start + length;
+	remainder = length % s->size;
 	if (!remainder)
 		return 1;
 
-	fault = check_bytes(start + length, POISON_INUSE, remainder);
+	fault = check_bytes(end - remainder, POISON_INUSE, remainder);
 	if (!fault)
 		return 1;
 	while (end > fault && end[-1] == POISON_INUSE)
 		end--;
 
 	slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1);
-	print_section("Padding", start, length);
+	print_section("Padding", end - remainder, remainder);
 
 	restore_bytes(s, "slab padding", POISON_INUSE, start, end);
 	return 0;
@@ -739,15 +734,24 @@ static int check_object(struct kmem_cache *s, struct page *page,
 
 static int check_slab(struct kmem_cache *s, struct page *page)
 {
+	int maxobj;
+
 	VM_BUG_ON(!irqs_disabled());
 
 	if (!PageSlab(page)) {
 		slab_err(s, page, "Not a valid slab page");
 		return 0;
 	}
-	if (page->inuse > s->objects) {
+
+	maxobj = (PAGE_SIZE << compound_order(page)) / s->size;
+	if (page->objects > maxobj) {
+		slab_err(s, page, "objects %u > max %u",
+			s->name, page->objects, maxobj);
+		return 0;
+	}
+	if (page->inuse > page->objects) {
 		slab_err(s, page, "inuse %u > max %u",
-			s->name, page->inuse, s->objects);
+			s->name, page->inuse, page->objects);
 		return 0;
 	}
 	/* Slab_pad_check fixes things up after itself */
@@ -764,8 +768,9 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
 	int nr = 0;
 	void *fp = page->freelist;
 	void *object = NULL;
+	unsigned long max_objects;
 
-	while (fp && nr <= s->objects) {
+	while (fp && nr <= page->objects) {
 		if (fp == search)
 			return 1;
 		if (!check_valid_pointer(s, page, fp)) {
@@ -777,7 +782,7 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
 			} else {
 				slab_err(s, page, "Freepointer corrupt");
 				page->freelist = NULL;
-				page->inuse = s->objects;
+				page->inuse = page->objects;
 				slab_fix(s, "Freelist cleared");
 				return 0;
 			}
@@ -788,10 +793,20 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
 		nr++;
 	}
 
-	if (page->inuse != s->objects - nr) {
+	max_objects = (PAGE_SIZE << compound_order(page)) / s->size;
+	if (max_objects > 65535)
+		max_objects = 65535;
+
+	if (page->objects != max_objects) {
+		slab_err(s, page, "Wrong number of objects. Found %d but "
+			"should be %d", page->objects, max_objects);
+		page->objects = max_objects;
+		slab_fix(s, "Number of objects adjusted.");
+	}
+	if (page->inuse != page->objects - nr) {
 		slab_err(s, page, "Wrong object count. Counter is %d but "
-			"counted were %d", page->inuse, s->objects - nr);
-		page->inuse = s->objects - nr;
+			"counted were %d", page->inuse, page->objects - nr);
+		page->inuse = page->objects - nr;
 		slab_fix(s, "Object count adjusted.");
 	}
 	return search == NULL;
@@ -845,7 +860,7 @@ static inline unsigned long slabs_node(struct kmem_cache *s, int node)
 	return atomic_long_read(&n->nr_slabs);
 }
 
-static inline void inc_slabs_node(struct kmem_cache *s, int node)
+static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects)
 {
 	struct kmem_cache_node *n = get_node(s, node);
 
@@ -855,14 +870,17 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node)
 	 * dilemma by deferring the increment of the count during
 	 * bootstrap (see early_kmem_cache_node_alloc).
 	 */
-	if (!NUMA_BUILD || n)
+	if (!NUMA_BUILD || n) {
 		atomic_long_inc(&n->nr_slabs);
+		atomic_long_add(objects, &n->total_objects);
+	}
 }
-static inline void dec_slabs_node(struct kmem_cache *s, int node)
+static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects)
 {
 	struct kmem_cache_node *n = get_node(s, node);
 
 	atomic_long_dec(&n->nr_slabs);
+	atomic_long_sub(objects, &n->total_objects);
 }
 
 /* Object debug checks for alloc/free paths */
@@ -910,7 +928,7 @@ static int alloc_debug_processing(struct kmem_cache *s, struct page *page,
 		 * as used avoids touching the remaining objects.
 		 */
 		slab_fix(s, "Marking all objects used");
-		page->inuse = s->objects;
+		page->inuse = page->objects;
 		page->freelist = NULL;
 	}
 	return 0;
@@ -1060,31 +1078,52 @@ static inline unsigned long kmem_cache_flags(unsigned long objsize,
 
 static inline unsigned long slabs_node(struct kmem_cache *s, int node)
 							{ return 0; }
-static inline void inc_slabs_node(struct kmem_cache *s, int node) {}
-static inline void dec_slabs_node(struct kmem_cache *s, int node) {}
+static inline void inc_slabs_node(struct kmem_cache *s, int node,
+							int objects) {}
+static inline void dec_slabs_node(struct kmem_cache *s, int node,
+							int objects) {}
 #endif
+
 /*
  * Slab allocation and freeing
  */
+static inline struct page *alloc_slab_page(gfp_t flags, int node,
+					struct kmem_cache_order_objects oo)
+{
+	int order = oo_order(oo);
+
+	if (node == -1)
+		return alloc_pages(flags, order);
+	else
+		return alloc_pages_node(node, flags, order);
+}
+
 static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 {
 	struct page *page;
-	int pages = 1 << s->order;
+	struct kmem_cache_order_objects oo = s->oo;
 
 	flags |= s->allocflags;
 
-	if (node == -1)
-		page = alloc_pages(flags, s->order);
-	else
-		page = alloc_pages_node(node, flags, s->order);
-
-	if (!page)
-		return NULL;
+	page = alloc_slab_page(flags | __GFP_NOWARN | __GFP_NORETRY, node,
+									oo);
+	if (unlikely(!page)) {
+		oo = s->min;
+		/*
+		 * Allocation may have failed due to fragmentation.
+		 * Try a lower order alloc if possible
+		 */
+		page = alloc_slab_page(flags, node, oo);
+		if (!page)
+			return NULL;
 
+		stat(get_cpu_slab(s, raw_smp_processor_id()), ORDER_FALLBACK);
+	}
+	page->objects = oo_objects(oo);
 	mod_zone_page_state(page_zone(page),
 		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
 		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
-		pages);
+		1 << oo_order(oo));
 
 	return page;
 }
@@ -1111,7 +1150,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	if (!page)
 		goto out;
 
-	inc_slabs_node(s, page_to_nid(page));
+	inc_slabs_node(s, page_to_nid(page), page->objects);
 	page->slab = s;
 	page->flags |= 1 << PG_slab;
 	if (s->flags & (SLAB_DEBUG_FREE | SLAB_RED_ZONE | SLAB_POISON |
@@ -1121,10 +1160,10 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	start = page_address(page);
 
 	if (unlikely(s->flags & SLAB_POISON))
-		memset(start, POISON_INUSE, PAGE_SIZE << s->order);
+		memset(start, POISON_INUSE, PAGE_SIZE << compound_order(page));
 
 	last = start;
-	for_each_object(p, s, start) {
+	for_each_object(p, s, start, page->objects) {
 		setup_object(s, page, last);
 		set_freepointer(s, last, p);
 		last = p;
@@ -1140,13 +1179,15 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 
 static void __free_slab(struct kmem_cache *s, struct page *page)
 {
-	int pages = 1 << s->order;
+	int order = compound_order(page);
+	int pages = 1 << order;
 
 	if (unlikely(SlabDebug(page))) {
 		void *p;
 
 		slab_pad_check(s, page);
-		for_each_object(p, s, page_address(page))
+		for_each_object(p, s, page_address(page),
+						page->objects)
 			check_object(s, page, p, 0);
 		ClearSlabDebug(page);
 	}
@@ -1158,7 +1199,7 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 
 	__ClearPageSlab(page);
 	reset_page_mapcount(page);
-	__free_pages(page, s->order);
+	__free_pages(page, order);
 }
 
 static void rcu_free_slab(struct rcu_head *h)
@@ -1184,7 +1225,7 @@ static void free_slab(struct kmem_cache *s, struct page *page)
 
 static void discard_slab(struct kmem_cache *s, struct page *page)
 {
-	dec_slabs_node(s, page_to_nid(page));
+	dec_slabs_node(s, page_to_nid(page), page->objects);
 	free_slab(s, page);
 }
 
@@ -1284,7 +1325,9 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 {
 #ifdef CONFIG_NUMA
 	struct zonelist *zonelist;
-	struct zone **z;
+	struct zoneref *z;
+	struct zone *zone;
+	enum zone_type high_zoneidx = gfp_zone(flags);
 	struct page *page;
 
 	/*
@@ -1309,14 +1352,13 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 			get_cycles() % 1024 > s->remote_node_defrag_ratio)
 		return NULL;
 
-	zonelist = &NODE_DATA(
-		slab_node(current->mempolicy))->node_zonelists[gfp_zone(flags)];
-	for (z = zonelist->zones; *z; z++) {
+	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 		struct kmem_cache_node *n;
 
-		n = get_node(s, zone_to_nid(*z));
+		n = get_node(s, zone_to_nid(zone));
 
-		if (n && cpuset_zone_allowed_hardwall(*z, flags) &&
+		if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
 				n->nr_partial > MIN_PARTIAL) {
 			page = get_partial_node(n);
 			if (page)
@@ -1519,7 +1561,7 @@ static void *__slab_alloc(struct kmem_cache *s,
 		goto debug;
 
 	c->freelist = object[c->offset];
-	c->page->inuse = s->objects;
+	c->page->inuse = c->page->objects;
 	c->page->freelist = NULL;
 	c->node = page_to_nid(c->page);
 unlock_out:
@@ -1556,27 +1598,6 @@ static void *__slab_alloc(struct kmem_cache *s,
 		c->page = new;
 		goto load_freelist;
 	}
-
-	/*
-	 * No memory available.
-	 *
-	 * If the slab uses higher order allocs but the object is
-	 * smaller than a page size then we can fallback in emergencies
-	 * to the page allocator via kmalloc_large. The page allocator may
-	 * have failed to obtain a higher order page and we can try to
-	 * allocate a single page if the object fits into a single page.
-	 * That is only possible if certain conditions are met that are being
-	 * checked when a slab is created.
-	 */
-	if (!(gfpflags & __GFP_NORETRY) &&
-				(s->flags & __PAGE_ALLOC_FALLBACK)) {
-		if (gfpflags & __GFP_WAIT)
-			local_irq_enable();
-		object = kmalloc_large(s->objsize, gfpflags);
-		if (gfpflags & __GFP_WAIT)
-			local_irq_disable();
-		return object;
-	}
 	return NULL;
 debug:
 	if (!alloc_debug_processing(s, c->page, object, addr))
@@ -1777,8 +1798,8 @@ static struct page *get_object_page(const void *x)
  * take the list_lock.
  */
 static int slub_min_order;
-static int slub_max_order = DEFAULT_MAX_ORDER;
-static int slub_min_objects = DEFAULT_MIN_OBJECTS;
+static int slub_max_order = PAGE_ALLOC_COSTLY_ORDER;
+static int slub_min_objects;
 
 /*
  * Merge control. If this is set then no merging of slab caches will occur.
@@ -1793,7 +1814,7 @@ static int slub_nomerge;
  * system components. Generally order 0 allocations should be preferred since
  * order 0 does not cause fragmentation in the page allocator. Larger objects
  * be problematic to put into order 0 slabs because there may be too much
- * unused space left. We go to a higher order if more than 1/8th of the slab
+ * unused space left. We go to a higher order if more than 1/16th of the slab
  * would be wasted.
  *
  * In order to reach satisfactory performance we must ensure that a minimum
@@ -1818,6 +1839,9 @@ static inline int slab_order(int size, int min_objects,
 	int rem;
 	int min_order = slub_min_order;
 
+	if ((PAGE_SIZE << min_order) / size > 65535)
+		return get_order(size * 65535) - 1;
+
 	for (order = max(min_order,
 				fls(min_objects * size - 1) - PAGE_SHIFT);
 			order <= max_order; order++) {
@@ -1852,8 +1876,10 @@ static inline int calculate_order(int size)
 	 * we reduce the minimum objects required in a slab.
 	 */
 	min_objects = slub_min_objects;
+	if (!min_objects)
+		min_objects = 4 * (fls(nr_cpu_ids) + 1);
 	while (min_objects > 1) {
-		fraction = 8;
+		fraction = 16;
 		while (fraction >= 4) {
 			order = slab_order(size, min_objects,
 						slub_max_order, fraction);
@@ -2095,7 +2121,7 @@ static struct kmem_cache_node *early_kmem_cache_node_alloc(gfp_t gfpflags,
 	init_tracking(kmalloc_caches, n);
 #endif
 	init_kmem_cache_node(n);
-	inc_slabs_node(kmalloc_caches, node);
+	inc_slabs_node(kmalloc_caches, node, page->objects);
 
 	/*
 	 * lockdep requires consistent irq usage for each lock
@@ -2171,11 +2197,12 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
  * calculate_sizes() determines the order and the distribution of data within
  * a slab object.
  */
-static int calculate_sizes(struct kmem_cache *s)
+static int calculate_sizes(struct kmem_cache *s, int forced_order)
 {
 	unsigned long flags = s->flags;
 	unsigned long size = s->objsize;
 	unsigned long align = s->align;
+	int order;
 
 	/*
 	 * Round up object size to the next word boundary. We can only
@@ -2259,26 +2286,16 @@ static int calculate_sizes(struct kmem_cache *s)
 	 */
 	size = ALIGN(size, align);
 	s->size = size;
+	if (forced_order >= 0)
+		order = forced_order;
+	else
+		order = calculate_order(size);
 
-	if ((flags & __KMALLOC_CACHE) &&
-			PAGE_SIZE / size < slub_min_objects) {
-		/*
-		 * Kmalloc cache that would not have enough objects in
-		 * an order 0 page. Kmalloc slabs can fallback to
-		 * page allocator order 0 allocs so take a reasonably large
-		 * order that will allows us a good number of objects.
-		 */
-		s->order = max(slub_max_order, PAGE_ALLOC_COSTLY_ORDER);
-		s->flags |= __PAGE_ALLOC_FALLBACK;
-		s->allocflags |= __GFP_NOWARN;
-	} else
-		s->order = calculate_order(size);
-
-	if (s->order < 0)
+	if (order < 0)
 		return 0;
 
 	s->allocflags = 0;
-	if (s->order)
+	if (order)
 		s->allocflags |= __GFP_COMP;
 
 	if (s->flags & SLAB_CACHE_DMA)
@@ -2290,9 +2307,12 @@ static int calculate_sizes(struct kmem_cache *s)
 	/*
 	 * Determine the number of objects per slab
 	 */
-	s->objects = (PAGE_SIZE << s->order) / size;
+	s->oo = oo_make(order, size);
+	s->min = oo_make(get_order(size), size);
+	if (oo_objects(s->oo) > oo_objects(s->max))
+		s->max = s->oo;
 
-	return !!s->objects;
+	return !!oo_objects(s->oo);
 
 }
 
@@ -2308,7 +2328,7 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
 	s->align = align;
 	s->flags = kmem_cache_flags(size, flags, name, ctor);
 
-	if (!calculate_sizes(s))
+	if (!calculate_sizes(s, -1))
 		goto error;
 
 	s->refcount = 1;
@@ -2325,7 +2345,7 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
 	if (flags & SLAB_PANIC)
 		panic("Cannot create slab %s size=%lu realsize=%u "
 			"order=%u offset=%u flags=%lx\n",
-			s->name, (unsigned long)size, s->size, s->order,
+			s->name, (unsigned long)size, s->size, oo_order(s->oo),
 			s->offset, flags);
 	return 0;
 }
@@ -2371,26 +2391,52 @@ const char *kmem_cache_name(struct kmem_cache *s)
 }
 EXPORT_SYMBOL(kmem_cache_name);
 
+static void list_slab_objects(struct kmem_cache *s, struct page *page,
+							const char *text)
+{
+#ifdef CONFIG_SLUB_DEBUG
+	void *addr = page_address(page);
+	void *p;
+	DECLARE_BITMAP(map, page->objects);
+
+	bitmap_zero(map, page->objects);
+	slab_err(s, page, "%s", text);
+	slab_lock(page);
+	for_each_free_object(p, s, page->freelist)
+		set_bit(slab_index(p, s, addr), map);
+
+	for_each_object(p, s, addr, page->objects) {
+
+		if (!test_bit(slab_index(p, s, addr), map)) {
+			printk(KERN_ERR "INFO: Object 0x%p @offset=%tu\n",
+							p, p - addr);
+			print_tracking(s, p);
+		}
+	}
+	slab_unlock(page);
+#endif
+}
+
 /*
- * Attempt to free all slabs on a node. Return the number of slabs we
- * were unable to free.
+ * Attempt to free all partial slabs on a node.
  */
-static int free_list(struct kmem_cache *s, struct kmem_cache_node *n,
-			struct list_head *list)
+static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 {
-	int slabs_inuse = 0;
 	unsigned long flags;
 	struct page *page, *h;
 
 	spin_lock_irqsave(&n->list_lock, flags);
-	list_for_each_entry_safe(page, h, list, lru)
+	list_for_each_entry_safe(page, h, &n->partial, lru) {
 		if (!page->inuse) {
 			list_del(&page->lru);
 			discard_slab(s, page);
-		} else
-			slabs_inuse++;
+			n->nr_partial--;
+		} else {
+			list_slab_objects(s, page,
+				"Objects remaining on kmem_cache_close()");
+		}
+	}
 	spin_unlock_irqrestore(&n->list_lock, flags);
-	return slabs_inuse;
 }
 
 /*
@@ -2407,8 +2453,8 @@ static inline int kmem_cache_close(struct kmem_cache *s)
 	for_each_node_state(node, N_NORMAL_MEMORY) {
 		struct kmem_cache_node *n = get_node(s, node);
 
-		n->nr_partial -= free_list(s, n, &n->partial);
-		if (slabs_node(s, node))
+		free_partial(s, n);
+		if (n->nr_partial || slabs_node(s, node))
 			return 1;
 	}
 	free_kmem_cache_nodes(s);
@@ -2426,8 +2472,11 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (!s->refcount) {
 		list_del(&s->list);
 		up_write(&slub_lock);
-		if (kmem_cache_close(s))
-			WARN_ON(1);
+		if (kmem_cache_close(s)) {
+			printk(KERN_ERR "SLUB %s: %s called for cache that "
+				"still has objects.\n", s->name, __func__);
+			dump_stack();
+		}
 		sysfs_slab_remove(s);
 	} else
 		up_write(&slub_lock);
@@ -2486,7 +2535,7 @@ static struct kmem_cache *create_kmalloc_cache(struct kmem_cache *s,
 
 	down_write(&slub_lock);
 	if (!kmem_cache_open(s, gfp_flags, name, size, ARCH_KMALLOC_MINALIGN,
-			flags | __KMALLOC_CACHE, NULL))
+								flags, NULL))
 		goto panic;
 
 	list_add(&s->list, &slab_caches);
@@ -2734,8 +2783,9 @@ int kmem_cache_shrink(struct kmem_cache *s)
 	struct kmem_cache_node *n;
 	struct page *page;
 	struct page *t;
+	int objects = oo_objects(s->max);
 	struct list_head *slabs_by_inuse =
-		kmalloc(sizeof(struct list_head) * s->objects, GFP_KERNEL);
+		kmalloc(sizeof(struct list_head) * objects, GFP_KERNEL);
 	unsigned long flags;
 
 	if (!slabs_by_inuse)
@@ -2748,7 +2798,7 @@ int kmem_cache_shrink(struct kmem_cache *s)
 		if (!n->nr_partial)
 			continue;
 
-		for (i = 0; i < s->objects; i++)
+		for (i = 0; i < objects; i++)
 			INIT_LIST_HEAD(slabs_by_inuse + i);
 
 		spin_lock_irqsave(&n->list_lock, flags);
@@ -2780,7 +2830,7 @@ int kmem_cache_shrink(struct kmem_cache *s)
 		 * Rebuild the partial list with the slabs filled up most
 		 * first and the least used slabs at the end.
 		 */
-		for (i = s->objects - 1; i >= 0; i--)
+		for (i = objects - 1; i >= 0; i--)
 			list_splice(slabs_by_inuse + i, n->partial.prev);
 
 		spin_unlock_irqrestore(&n->list_lock, flags);
@@ -2928,7 +2978,7 @@ void __init kmem_cache_init(void)
 	kmalloc_caches[0].refcount = -1;
 	caches++;
 
-	hotplug_memory_notifier(slab_memory_callback, 1);
+	hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
 #endif
 
 	/* Able to allocate the per node structures */
@@ -3001,9 +3051,6 @@ static int slab_unmergeable(struct kmem_cache *s)
 	if (slub_nomerge || (s->flags & SLUB_NEVER_MERGE))
 		return 1;
 
-	if ((s->flags & __PAGE_ALLOC_FALLBACK))
-		return 1;
-
 	if (s->ctor)
 		return 1;
 
@@ -3196,7 +3243,8 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 }
 
 #if (defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)) || defined(CONFIG_SLABINFO)
-static unsigned long count_partial(struct kmem_cache_node *n)
+static unsigned long count_partial(struct kmem_cache_node *n,
+					int (*get_count)(struct page *))
 {
 	unsigned long flags;
 	unsigned long x = 0;
@@ -3204,10 +3252,25 @@ static unsigned long count_partial(struct kmem_cache_node *n)
 
 	spin_lock_irqsave(&n->list_lock, flags);
 	list_for_each_entry(page, &n->partial, lru)
-		x += page->inuse;
+		x += get_count(page);
 	spin_unlock_irqrestore(&n->list_lock, flags);
 	return x;
 }
+
+static int count_inuse(struct page *page)
+{
+	return page->inuse;
+}
+
+static int count_total(struct page *page)
+{
+	return page->objects;
+}
+
+static int count_free(struct page *page)
+{
+	return page->objects - page->inuse;
+}
 #endif
 
 #if defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)
@@ -3222,7 +3285,7 @@ static int validate_slab(struct kmem_cache *s, struct page *page,
 		return 0;
 
 	/* Now we know that a valid freelist exists */
-	bitmap_zero(map, s->objects);
+	bitmap_zero(map, page->objects);
 
 	for_each_free_object(p, s, page->freelist) {
 		set_bit(slab_index(p, s, addr), map);
@@ -3230,7 +3293,7 @@ static int validate_slab(struct kmem_cache *s, struct page *page,
 			return 0;
 	}
 
-	for_each_object(p, s, addr)
+	for_each_object(p, s, addr, page->objects)
 		if (!test_bit(slab_index(p, s, addr), map))
 			if (!check_object(s, page, p, 1))
 				return 0;
@@ -3296,7 +3359,7 @@ static long validate_slab_cache(struct kmem_cache *s)
 {
 	int node;
 	unsigned long count = 0;
-	unsigned long *map = kmalloc(BITS_TO_LONGS(s->objects) *
+	unsigned long *map = kmalloc(BITS_TO_LONGS(oo_objects(s->max)) *
 				sizeof(unsigned long), GFP_KERNEL);
 
 	if (!map)
@@ -3499,14 +3562,14 @@ static void process_slab(struct loc_track *t, struct kmem_cache *s,
 		struct page *page, enum track_item alloc)
 {
 	void *addr = page_address(page);
-	DECLARE_BITMAP(map, s->objects);
+	DECLARE_BITMAP(map, page->objects);
 	void *p;
 
-	bitmap_zero(map, s->objects);
+	bitmap_zero(map, page->objects);
 	for_each_free_object(p, s, page->freelist)
 		set_bit(slab_index(p, s, addr), map);
 
-	for_each_object(p, s, addr)
+	for_each_object(p, s, addr, page->objects)
 		if (!test_bit(slab_index(p, s, addr), map))
 			add_location(t, s, get_track(s, p, alloc));
 }
@@ -3596,22 +3659,23 @@ static int list_locations(struct kmem_cache *s, char *buf,
 }
 
 enum slab_stat_type {
-	SL_FULL,
-	SL_PARTIAL,
-	SL_CPU,
-	SL_OBJECTS
+	SL_ALL,			/* All slabs */
+	SL_PARTIAL,		/* Only partially allocated slabs */
+	SL_CPU,			/* Only slabs used for cpu caches */
+	SL_OBJECTS,		/* Determine allocated objects not slabs */
+	SL_TOTAL		/* Determine object capacity not slabs */
 };
 
-#define SO_FULL		(1 << SL_FULL)
+#define SO_ALL		(1 << SL_ALL)
 #define SO_PARTIAL	(1 << SL_PARTIAL)
 #define SO_CPU		(1 << SL_CPU)
 #define SO_OBJECTS	(1 << SL_OBJECTS)
+#define SO_TOTAL	(1 << SL_TOTAL)
 
 static ssize_t show_slab_objects(struct kmem_cache *s,
 			    char *buf, unsigned long flags)
 {
 	unsigned long total = 0;
-	int cpu;
 	int node;
 	int x;
 	unsigned long *nodes;
@@ -3622,56 +3686,60 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 		return -ENOMEM;
 	per_cpu = nodes + nr_node_ids;
 
-	for_each_possible_cpu(cpu) {
-		struct page *page;
-		struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
+	if (flags & SO_CPU) {
+		int cpu;
 
-		if (!c)
-			continue;
+		for_each_possible_cpu(cpu) {
+			struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
 
-		page = c->page;
-		node = c->node;
-		if (node < 0)
-			continue;
-		if (page) {
-			if (flags & SO_CPU) {
-				if (flags & SO_OBJECTS)
-					x = page->inuse;
+			if (!c || c->node < 0)
+				continue;
+
+			if (c->page) {
+					if (flags & SO_TOTAL)
+						x = c->page->objects;
+				else if (flags & SO_OBJECTS)
+					x = c->page->inuse;
 				else
 					x = 1;
+
 				total += x;
-				nodes[node] += x;
+				nodes[c->node] += x;
 			}
-			per_cpu[node]++;
+			per_cpu[c->node]++;
 		}
 	}
 
-	for_each_node_state(node, N_NORMAL_MEMORY) {
-		struct kmem_cache_node *n = get_node(s, node);
+	if (flags & SO_ALL) {
+		for_each_node_state(node, N_NORMAL_MEMORY) {
+			struct kmem_cache_node *n = get_node(s, node);
+
+		if (flags & SO_TOTAL)
+			x = atomic_long_read(&n->total_objects);
+		else if (flags & SO_OBJECTS)
+			x = atomic_long_read(&n->total_objects) -
+				count_partial(n, count_free);
 
-		if (flags & SO_PARTIAL) {
-			if (flags & SO_OBJECTS)
-				x = count_partial(n);
 			else
-				x = n->nr_partial;
+				x = atomic_long_read(&n->nr_slabs);
 			total += x;
 			nodes[node] += x;
 		}
 
-		if (flags & SO_FULL) {
-			int full_slabs = atomic_long_read(&n->nr_slabs)
-					- per_cpu[node]
-					- n->nr_partial;
+	} else if (flags & SO_PARTIAL) {
+		for_each_node_state(node, N_NORMAL_MEMORY) {
+			struct kmem_cache_node *n = get_node(s, node);
 
-			if (flags & SO_OBJECTS)
-				x = full_slabs * s->objects;
+			if (flags & SO_TOTAL)
+				x = count_partial(n, count_total);
+			else if (flags & SO_OBJECTS)
+				x = count_partial(n, count_inuse);
 			else
-				x = full_slabs;
+				x = n->nr_partial;
 			total += x;
 			nodes[node] += x;
 		}
 	}
-
 	x = sprintf(buf, "%lu", total);
 #ifdef CONFIG_NUMA
 	for_each_node_state(node, N_NORMAL_MEMORY)
@@ -3686,14 +3754,6 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 static int any_slab_objects(struct kmem_cache *s)
 {
 	int node;
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
-
-		if (c && c->page)
-			return 1;
-	}
 
 	for_each_online_node(node) {
 		struct kmem_cache_node *n = get_node(s, node);
@@ -3701,7 +3761,7 @@ static int any_slab_objects(struct kmem_cache *s)
 		if (!n)
 			continue;
 
-		if (n->nr_partial || atomic_long_read(&n->nr_slabs))
+		if (atomic_read(&n->total_objects))
 			return 1;
 	}
 	return 0;
@@ -3743,15 +3803,27 @@ SLAB_ATTR_RO(object_size);
 
 static ssize_t objs_per_slab_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", s->objects);
+	return sprintf(buf, "%d\n", oo_objects(s->oo));
 }
 SLAB_ATTR_RO(objs_per_slab);
 
+static ssize_t order_store(struct kmem_cache *s,
+				const char *buf, size_t length)
+{
+	int order = simple_strtoul(buf, NULL, 10);
+
+	if (order > slub_max_order || order < slub_min_order)
+		return -EINVAL;
+
+	calculate_sizes(s, order);
+	return length;
+}
+
 static ssize_t order_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", s->order);
+	return sprintf(buf, "%d\n", oo_order(s->oo));
 }
-SLAB_ATTR_RO(order);
+SLAB_ATTR(order);
 
 static ssize_t ctor_show(struct kmem_cache *s, char *buf)
 {
@@ -3772,7 +3844,7 @@ SLAB_ATTR_RO(aliases);
 
 static ssize_t slabs_show(struct kmem_cache *s, char *buf)
 {
-	return show_slab_objects(s, buf, SO_FULL|SO_PARTIAL|SO_CPU);
+	return show_slab_objects(s, buf, SO_ALL);
 }
 SLAB_ATTR_RO(slabs);
 
@@ -3790,10 +3862,22 @@ SLAB_ATTR_RO(cpu_slabs);
 
 static ssize_t objects_show(struct kmem_cache *s, char *buf)
 {
-	return show_slab_objects(s, buf, SO_FULL|SO_PARTIAL|SO_CPU|SO_OBJECTS);
+	return show_slab_objects(s, buf, SO_ALL|SO_OBJECTS);
 }
 SLAB_ATTR_RO(objects);
 
+static ssize_t objects_partial_show(struct kmem_cache *s, char *buf)
+{
+	return show_slab_objects(s, buf, SO_PARTIAL|SO_OBJECTS);
+}
+SLAB_ATTR_RO(objects_partial);
+
+static ssize_t total_objects_show(struct kmem_cache *s, char *buf)
+{
+	return show_slab_objects(s, buf, SO_ALL|SO_TOTAL);
+}
+SLAB_ATTR_RO(total_objects);
+
 static ssize_t sanity_checks_show(struct kmem_cache *s, char *buf)
 {
 	return sprintf(buf, "%d\n", !!(s->flags & SLAB_DEBUG_FREE));
@@ -3873,7 +3957,7 @@ static ssize_t red_zone_store(struct kmem_cache *s,
 	s->flags &= ~SLAB_RED_ZONE;
 	if (buf[0] == '1')
 		s->flags |= SLAB_RED_ZONE;
-	calculate_sizes(s);
+	calculate_sizes(s, -1);
 	return length;
 }
 SLAB_ATTR(red_zone);
@@ -3892,7 +3976,7 @@ static ssize_t poison_store(struct kmem_cache *s,
 	s->flags &= ~SLAB_POISON;
 	if (buf[0] == '1')
 		s->flags |= SLAB_POISON;
-	calculate_sizes(s);
+	calculate_sizes(s, -1);
 	return length;
 }
 SLAB_ATTR(poison);
@@ -3911,7 +3995,7 @@ static ssize_t store_user_store(struct kmem_cache *s,
 	s->flags &= ~SLAB_STORE_USER;
 	if (buf[0] == '1')
 		s->flags |= SLAB_STORE_USER;
-	calculate_sizes(s);
+	calculate_sizes(s, -1);
 	return length;
 }
 SLAB_ATTR(store_user);
@@ -4042,7 +4126,7 @@ STAT_ATTR(DEACTIVATE_EMPTY, deactivate_empty);
 STAT_ATTR(DEACTIVATE_TO_HEAD, deactivate_to_head);
 STAT_ATTR(DEACTIVATE_TO_TAIL, deactivate_to_tail);
 STAT_ATTR(DEACTIVATE_REMOTE_FREES, deactivate_remote_frees);
-
+STAT_ATTR(ORDER_FALLBACK, order_fallback);
 #endif
 
 static struct attribute *slab_attrs[] = {
@@ -4051,6 +4135,8 @@ static struct attribute *slab_attrs[] = {
 	&objs_per_slab_attr.attr,
 	&order_attr.attr,
 	&objects_attr.attr,
+	&objects_partial_attr.attr,
+	&total_objects_attr.attr,
 	&slabs_attr.attr,
 	&partial_attr.attr,
 	&cpu_slabs_attr.attr,
@@ -4093,6 +4179,7 @@ static struct attribute *slab_attrs[] = {
 	&deactivate_to_head_attr.attr,
 	&deactivate_to_tail_attr.attr,
 	&deactivate_remote_frees_attr.attr,
+	&order_fallback_attr.attr,
 #endif
 	NULL
 };
@@ -4379,7 +4466,8 @@ static int s_show(struct seq_file *m, void *p)
 	unsigned long nr_partials = 0;
 	unsigned long nr_slabs = 0;
 	unsigned long nr_inuse = 0;
-	unsigned long nr_objs;
+	unsigned long nr_objs = 0;
+	unsigned long nr_free = 0;
 	struct kmem_cache *s;
 	int node;
 
@@ -4393,14 +4481,15 @@ static int s_show(struct seq_file *m, void *p)
 
 		nr_partials += n->nr_partial;
 		nr_slabs += atomic_long_read(&n->nr_slabs);
-		nr_inuse += count_partial(n);
+		nr_objs += atomic_long_read(&n->total_objects);
+		nr_free += count_partial(n, count_free);
 	}
 
-	nr_objs = nr_slabs * s->objects;
-	nr_inuse += (nr_slabs - nr_partials) * s->objects;
+	nr_inuse = nr_objs - nr_free;
 
 	seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d", s->name, nr_inuse,
-		   nr_objs, s->size, s->objects, (1 << s->order));
+		   nr_objs, s->size, oo_objects(s->oo),
+		   (1 << oo_order(s->oo)));
 	seq_printf(m, " : tunables %4u %4u %4u", 0, 0, 0);
 	seq_printf(m, " : slabdata %6lu %6lu %6lu", nr_slabs, nr_slabs,
 		   0UL);
diff --git a/trunk/mm/sparse.c b/trunk/mm/sparse.c
index 7e9191381f86..dff71f173ae9 100644
--- a/trunk/mm/sparse.c
+++ b/trunk/mm/sparse.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
+#include "internal.h"
 #include <asm/dma.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
@@ -208,12 +209,12 @@ static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long p
 }
 
 /*
- * We need this if we ever free the mem_maps.  While not implemented yet,
- * this function is included for parity with its sibling.
+ * Decode mem_map from the coded memmap
  */
-static __attribute((unused))
 struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum)
 {
+	/* mask off the extra low bits of information */
+	coded_mem_map &= SECTION_MAP_MASK;
 	return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
 }
 
@@ -232,7 +233,7 @@ static int __meminit sparse_init_one_section(struct mem_section *ms,
 	return 1;
 }
 
-static unsigned long usemap_size(void)
+unsigned long usemap_size(void)
 {
 	unsigned long size_bytes;
 	size_bytes = roundup(SECTION_BLOCKFLAGS_BITS, 8) / 8;
@@ -249,11 +250,22 @@ static unsigned long *__kmalloc_section_usemap(void)
 
 static unsigned long *__init sparse_early_usemap_alloc(unsigned long pnum)
 {
-	unsigned long *usemap;
+	unsigned long *usemap, section_nr;
 	struct mem_section *ms = __nr_to_section(pnum);
 	int nid = sparse_early_nid(ms);
+	struct pglist_data *pgdat = NODE_DATA(nid);
 
-	usemap = alloc_bootmem_node(NODE_DATA(nid), usemap_size());
+	/*
+	 * Usemap's page can't be freed until freeing other sections
+	 * which use it. And, Pgdat has same feature.
+	 * If section A has pgdat and section B has usemap for other
+	 * sections (includes section A), both sections can't be removed,
+	 * because there is the dependency each other.
+	 * To solve above issue, this collects all usemap on the same section
+	 * which has pgdat.
+	 */
+	section_nr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
+	usemap = alloc_bootmem_section(usemap_size(), section_nr);
 	if (usemap)
 		return usemap;
 
@@ -273,8 +285,8 @@ struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid)
 	if (map)
 		return map;
 
-	map = alloc_bootmem_node(NODE_DATA(nid),
-			sizeof(struct page) * PAGES_PER_SECTION);
+	map = alloc_bootmem_pages_node(NODE_DATA(nid),
+		       PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION));
 	return map;
 }
 #endif /* !CONFIG_SPARSEMEM_VMEMMAP */
@@ -365,6 +377,9 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
 {
 	return; /* XXX: Not implemented yet */
 }
+static void free_map_bootmem(struct page *page, unsigned long nr_pages)
+{
+}
 #else
 static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
 {
@@ -402,8 +417,69 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
 		free_pages((unsigned long)memmap,
 			   get_order(sizeof(struct page) * nr_pages));
 }
+
+static void free_map_bootmem(struct page *page, unsigned long nr_pages)
+{
+	unsigned long maps_section_nr, removing_section_nr, i;
+	int magic;
+
+	for (i = 0; i < nr_pages; i++, page++) {
+		magic = atomic_read(&page->_mapcount);
+
+		BUG_ON(magic == NODE_INFO);
+
+		maps_section_nr = pfn_to_section_nr(page_to_pfn(page));
+		removing_section_nr = page->private;
+
+		/*
+		 * When this function is called, the removing section is
+		 * logical offlined state. This means all pages are isolated
+		 * from page allocator. If removing section's memmap is placed
+		 * on the same section, it must not be freed.
+		 * If it is freed, page allocator may allocate it which will
+		 * be removed physically soon.
+		 */
+		if (maps_section_nr != removing_section_nr)
+			put_page_bootmem(page);
+	}
+}
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
+static void free_section_usemap(struct page *memmap, unsigned long *usemap)
+{
+	struct page *usemap_page;
+	unsigned long nr_pages;
+
+	if (!usemap)
+		return;
+
+	usemap_page = virt_to_page(usemap);
+	/*
+	 * Check to see if allocation came from hot-plug-add
+	 */
+	if (PageSlab(usemap_page)) {
+		kfree(usemap);
+		if (memmap)
+			__kfree_section_memmap(memmap, PAGES_PER_SECTION);
+		return;
+	}
+
+	/*
+	 * The usemap came from bootmem. This is packed with other usemaps
+	 * on the section which has pgdat at boot time. Just keep it as is now.
+	 */
+
+	if (memmap) {
+		struct page *memmap_page;
+		memmap_page = virt_to_page(memmap);
+
+		nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
+			>> PAGE_SHIFT;
+
+		free_map_bootmem(memmap_page, nr_pages);
+	}
+}
+
 /*
  * returns the number of sections whose mem_maps were properly
  * set.  If this is <=0, then that means that the passed-in
@@ -456,4 +532,20 @@ int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 	}
 	return ret;
 }
+
+void sparse_remove_one_section(struct zone *zone, struct mem_section *ms)
+{
+	struct page *memmap = NULL;
+	unsigned long *usemap = NULL;
+
+	if (ms->section_mem_map) {
+		usemap = ms->pageblock_flags;
+		memmap = sparse_decode_mem_map(ms->section_mem_map,
+						__section_nr(ms));
+		ms->section_mem_map = 0;
+		ms->pageblock_flags = NULL;
+	}
+
+	free_section_usemap(memmap, usemap);
+}
 #endif
diff --git a/trunk/mm/swap.c b/trunk/mm/swap.c
index aa1139ccf3a7..91e194445a5e 100644
--- a/trunk/mm/swap.c
+++ b/trunk/mm/swap.c
@@ -132,34 +132,21 @@ static void pagevec_move_tail(struct pagevec *pvec)
  * Writeback is about to end against a page which has been marked for immediate
  * reclaim.  If it still appears to be reclaimable, move it to the tail of the
  * inactive list.
- *
- * Returns zero if it cleared PG_writeback.
  */
-int rotate_reclaimable_page(struct page *page)
+void  rotate_reclaimable_page(struct page *page)
 {
-	struct pagevec *pvec;
-	unsigned long flags;
-
-	if (PageLocked(page))
-		return 1;
-	if (PageDirty(page))
-		return 1;
-	if (PageActive(page))
-		return 1;
-	if (!PageLRU(page))
-		return 1;
-
-	page_cache_get(page);
-	local_irq_save(flags);
-	pvec = &__get_cpu_var(lru_rotate_pvecs);
-	if (!pagevec_add(pvec, page))
-		pagevec_move_tail(pvec);
-	local_irq_restore(flags);
-
-	if (!test_clear_page_writeback(page))
-		BUG();
+	if (!PageLocked(page) && !PageDirty(page) && !PageActive(page) &&
+	    PageLRU(page)) {
+		struct pagevec *pvec;
+		unsigned long flags;
 
-	return 0;
+		page_cache_get(page);
+		local_irq_save(flags);
+		pvec = &__get_cpu_var(lru_rotate_pvecs);
+		if (!pagevec_add(pvec, page))
+			pagevec_move_tail(pvec);
+		local_irq_restore(flags);
+	}
 }
 
 /*
diff --git a/trunk/mm/swapfile.c b/trunk/mm/swapfile.c
index 2da149cfc9ac..bd1bb5920306 100644
--- a/trunk/mm/swapfile.c
+++ b/trunk/mm/swapfile.c
@@ -1426,11 +1426,7 @@ static const struct file_operations proc_swaps_operations = {
 
 static int __init procswaps_init(void)
 {
-	struct proc_dir_entry *entry;
-
-	entry = create_proc_entry("swaps", 0, NULL);
-	if (entry)
-		entry->proc_fops = &proc_swaps_operations;
+	proc_create("swaps", 0, NULL, &proc_swaps_operations);
 	return 0;
 }
 __initcall(procswaps_init);
@@ -1582,6 +1578,14 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
 		error = -EINVAL;
 		goto bad_swap;
 	case 2:
+		/* swap partition endianess hack... */
+		if (swab32(swap_header->info.version) == 1) {
+			swab32s(&swap_header->info.version);
+			swab32s(&swap_header->info.last_page);
+			swab32s(&swap_header->info.nr_badpages);
+			for (i = 0; i < swap_header->info.nr_badpages; i++)
+				swab32s(&swap_header->info.badpages[i]);
+		}
 		/* Check the swap header's sub-version and the size of
                    the swap file and bad block lists */
 		if (swap_header->info.version != 1) {
diff --git a/trunk/mm/truncate.c b/trunk/mm/truncate.c
index 7d20ce41ecf5..b8961cb63414 100644
--- a/trunk/mm/truncate.c
+++ b/trunk/mm/truncate.c
@@ -391,6 +391,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 	pgoff_t next;
 	int i;
 	int ret = 0;
+	int ret2 = 0;
 	int did_range_unmap = 0;
 	int wrapped = 0;
 
@@ -438,9 +439,13 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 				}
 			}
 			BUG_ON(page_mapped(page));
-			ret = do_launder_page(mapping, page);
-			if (ret == 0 && !invalidate_complete_page2(mapping, page))
-				ret = -EIO;
+			ret2 = do_launder_page(mapping, page);
+			if (ret2 == 0) {
+				if (!invalidate_complete_page2(mapping, page))
+					ret2 = -EIO;
+			}
+			if (ret2 < 0)
+				ret = ret2;
 			unlock_page(page);
 		}
 		pagevec_release(&pvec);
diff --git a/trunk/mm/vmalloc.c b/trunk/mm/vmalloc.c
index ecf91f8034bf..e33e0ae69ad1 100644
--- a/trunk/mm/vmalloc.c
+++ b/trunk/mm/vmalloc.c
@@ -14,8 +14,9 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
-
+#include <linux/seq_file.h>
 #include <linux/vmalloc.h>
+#include <linux/kallsyms.h>
 
 #include <asm/uaccess.h>
 #include <asm/tlbflush.h>
@@ -25,7 +26,7 @@ DEFINE_RWLOCK(vmlist_lock);
 struct vm_struct *vmlist;
 
 static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
-			    int node);
+			    int node, void *caller);
 
 static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end)
 {
@@ -204,9 +205,9 @@ unsigned long vmalloc_to_pfn(const void *vmalloc_addr)
 }
 EXPORT_SYMBOL(vmalloc_to_pfn);
 
-static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags,
-					    unsigned long start, unsigned long end,
-					    int node, gfp_t gfp_mask)
+static struct vm_struct *
+__get_vm_area_node(unsigned long size, unsigned long flags, unsigned long start,
+		unsigned long end, int node, gfp_t gfp_mask, void *caller)
 {
 	struct vm_struct **p, *tmp, *area;
 	unsigned long align = 1;
@@ -269,6 +270,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long fl
 	area->pages = NULL;
 	area->nr_pages = 0;
 	area->phys_addr = 0;
+	area->caller = caller;
 	write_unlock(&vmlist_lock);
 
 	return area;
@@ -284,7 +286,8 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long fl
 struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
 				unsigned long start, unsigned long end)
 {
-	return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL);
+	return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL,
+						__builtin_return_address(0));
 }
 EXPORT_SYMBOL_GPL(__get_vm_area);
 
@@ -299,14 +302,22 @@ EXPORT_SYMBOL_GPL(__get_vm_area);
  */
 struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
 {
-	return __get_vm_area(size, flags, VMALLOC_START, VMALLOC_END);
+	return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END,
+				-1, GFP_KERNEL, __builtin_return_address(0));
+}
+
+struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
+				void *caller)
+{
+	return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END,
+						-1, GFP_KERNEL, caller);
 }
 
 struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags,
 				   int node, gfp_t gfp_mask)
 {
 	return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node,
-				  gfp_mask);
+				  gfp_mask, __builtin_return_address(0));
 }
 
 /* Caller must hold vmlist_lock */
@@ -455,9 +466,11 @@ void *vmap(struct page **pages, unsigned int count,
 	if (count > num_physpages)
 		return NULL;
 
-	area = get_vm_area((count << PAGE_SHIFT), flags);
+	area = get_vm_area_caller((count << PAGE_SHIFT), flags,
+					__builtin_return_address(0));
 	if (!area)
 		return NULL;
+
 	if (map_vm_area(area, prot, &pages)) {
 		vunmap(area->addr);
 		return NULL;
@@ -468,7 +481,7 @@ void *vmap(struct page **pages, unsigned int count,
 EXPORT_SYMBOL(vmap);
 
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
-				 pgprot_t prot, int node)
+				 pgprot_t prot, int node, void *caller)
 {
 	struct page **pages;
 	unsigned int nr_pages, array_size, i;
@@ -480,7 +493,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	/* Please note that the recursion is strictly bounded. */
 	if (array_size > PAGE_SIZE) {
 		pages = __vmalloc_node(array_size, gfp_mask | __GFP_ZERO,
-					PAGE_KERNEL, node);
+				PAGE_KERNEL, node, caller);
 		area->flags |= VM_VPAGES;
 	} else {
 		pages = kmalloc_node(array_size,
@@ -488,6 +501,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 				node);
 	}
 	area->pages = pages;
+	area->caller = caller;
 	if (!area->pages) {
 		remove_vm_area(area->addr);
 		kfree(area);
@@ -521,7 +535,8 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 
 void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
 {
-	return __vmalloc_area_node(area, gfp_mask, prot, -1);
+	return __vmalloc_area_node(area, gfp_mask, prot, -1,
+					__builtin_return_address(0));
 }
 
 /**
@@ -536,7 +551,7 @@ void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
  *	kernel virtual space, using a pagetable protection of @prot.
  */
 static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
-			    int node)
+						int node, void *caller)
 {
 	struct vm_struct *area;
 
@@ -544,16 +559,19 @@ static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
 	if (!size || (size >> PAGE_SHIFT) > num_physpages)
 		return NULL;
 
-	area = get_vm_area_node(size, VM_ALLOC, node, gfp_mask);
+	area = __get_vm_area_node(size, VM_ALLOC, VMALLOC_START, VMALLOC_END,
+						node, gfp_mask, caller);
+
 	if (!area)
 		return NULL;
 
-	return __vmalloc_area_node(area, gfp_mask, prot, node);
+	return __vmalloc_area_node(area, gfp_mask, prot, node, caller);
 }
 
 void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
 {
-	return __vmalloc_node(size, gfp_mask, prot, -1);
+	return __vmalloc_node(size, gfp_mask, prot, -1,
+				__builtin_return_address(0));
 }
 EXPORT_SYMBOL(__vmalloc);
 
@@ -568,7 +586,8 @@ EXPORT_SYMBOL(__vmalloc);
  */
 void *vmalloc(unsigned long size)
 {
-	return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL);
+	return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
+					-1, __builtin_return_address(0));
 }
 EXPORT_SYMBOL(vmalloc);
 
@@ -608,7 +627,8 @@ EXPORT_SYMBOL(vmalloc_user);
  */
 void *vmalloc_node(unsigned long size, int node)
 {
-	return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, node);
+	return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
+					node, __builtin_return_address(0));
 }
 EXPORT_SYMBOL(vmalloc_node);
 
@@ -843,7 +863,8 @@ struct vm_struct *alloc_vm_area(size_t size)
 {
 	struct vm_struct *area;
 
-	area = get_vm_area(size, VM_IOREMAP);
+	area = get_vm_area_caller(size, VM_IOREMAP,
+				__builtin_return_address(0));
 	if (area == NULL)
 		return NULL;
 
@@ -873,3 +894,85 @@ void free_vm_area(struct vm_struct *area)
 	kfree(area);
 }
 EXPORT_SYMBOL_GPL(free_vm_area);
+
+
+#ifdef CONFIG_PROC_FS
+static void *s_start(struct seq_file *m, loff_t *pos)
+{
+	loff_t n = *pos;
+	struct vm_struct *v;
+
+	read_lock(&vmlist_lock);
+	v = vmlist;
+	while (n > 0 && v) {
+		n--;
+		v = v->next;
+	}
+	if (!n)
+		return v;
+
+	return NULL;
+
+}
+
+static void *s_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	struct vm_struct *v = p;
+
+	++*pos;
+	return v->next;
+}
+
+static void s_stop(struct seq_file *m, void *p)
+{
+	read_unlock(&vmlist_lock);
+}
+
+static int s_show(struct seq_file *m, void *p)
+{
+	struct vm_struct *v = p;
+
+	seq_printf(m, "0x%p-0x%p %7ld",
+		v->addr, v->addr + v->size, v->size);
+
+	if (v->caller) {
+		char buff[2 * KSYM_NAME_LEN];
+
+		seq_putc(m, ' ');
+		sprint_symbol(buff, (unsigned long)v->caller);
+		seq_puts(m, buff);
+	}
+
+	if (v->nr_pages)
+		seq_printf(m, " pages=%d", v->nr_pages);
+
+	if (v->phys_addr)
+		seq_printf(m, " phys=%lx", v->phys_addr);
+
+	if (v->flags & VM_IOREMAP)
+		seq_printf(m, " ioremap");
+
+	if (v->flags & VM_ALLOC)
+		seq_printf(m, " vmalloc");
+
+	if (v->flags & VM_MAP)
+		seq_printf(m, " vmap");
+
+	if (v->flags & VM_USERMAP)
+		seq_printf(m, " user");
+
+	if (v->flags & VM_VPAGES)
+		seq_printf(m, " vpages");
+
+	seq_putc(m, '\n');
+	return 0;
+}
+
+const struct seq_operations vmalloc_op = {
+	.start = s_start,
+	.next = s_next,
+	.stop = s_stop,
+	.show = s_show,
+};
+#endif
+
diff --git a/trunk/mm/vmscan.c b/trunk/mm/vmscan.c
index f80a5b7c057f..12e8627c9747 100644
--- a/trunk/mm/vmscan.c
+++ b/trunk/mm/vmscan.c
@@ -1246,17 +1246,16 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static unsigned long shrink_zones(int priority, struct zone **zones,
+static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
 					struct scan_control *sc)
 {
+	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
 	unsigned long nr_reclaimed = 0;
-	int i;
-
+	struct zoneref *z;
+	struct zone *zone;
 
 	sc->all_unreclaimable = 1;
-	for (i = 0; zones[i] != NULL; i++) {
-		struct zone *zone = zones[i];
-
+	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 		if (!populated_zone(zone))
 			continue;
 		/*
@@ -1300,9 +1299,12 @@ static unsigned long shrink_zones(int priority, struct zone **zones,
  * hope that some of these pages can be written.  But if the allocating task
  * holds filesystem locks which prevent writeout this might not work, and the
  * allocation attempt will fail.
+ *
+ * returns:	0, if no pages reclaimed
+ * 		else, the number of pages reclaimed
  */
-static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask,
-					  struct scan_control *sc)
+static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
+					struct scan_control *sc)
 {
 	int priority;
 	int ret = 0;
@@ -1310,7 +1312,9 @@ static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask,
 	unsigned long nr_reclaimed = 0;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	unsigned long lru_pages = 0;
-	int i;
+	struct zoneref *z;
+	struct zone *zone;
+	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
 
 	if (scan_global_lru(sc))
 		count_vm_event(ALLOCSTALL);
@@ -1318,8 +1322,7 @@ static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask,
 	 * mem_cgroup will not do shrink_slab.
 	 */
 	if (scan_global_lru(sc)) {
-		for (i = 0; zones[i] != NULL; i++) {
-			struct zone *zone = zones[i];
+		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 				continue;
@@ -1333,13 +1336,13 @@ static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask,
 		sc->nr_scanned = 0;
 		if (!priority)
 			disable_swap_token();
-		nr_reclaimed += shrink_zones(priority, zones, sc);
+		nr_reclaimed += shrink_zones(priority, zonelist, sc);
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
 		 */
 		if (scan_global_lru(sc)) {
-			shrink_slab(sc->nr_scanned, gfp_mask, lru_pages);
+			shrink_slab(sc->nr_scanned, sc->gfp_mask, lru_pages);
 			if (reclaim_state) {
 				nr_reclaimed += reclaim_state->reclaimed_slab;
 				reclaim_state->reclaimed_slab = 0;
@@ -1347,7 +1350,7 @@ static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask,
 		}
 		total_scanned += sc->nr_scanned;
 		if (nr_reclaimed >= sc->swap_cluster_max) {
-			ret = 1;
+			ret = nr_reclaimed;
 			goto out;
 		}
 
@@ -1370,7 +1373,7 @@ static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask,
 	}
 	/* top priority shrink_caches still had more to do? don't OOM, then */
 	if (!sc->all_unreclaimable && scan_global_lru(sc))
-		ret = 1;
+		ret = nr_reclaimed;
 out:
 	/*
 	 * Now that we've scanned all the zones at this priority level, note
@@ -1383,8 +1386,7 @@ static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask,
 		priority = 0;
 
 	if (scan_global_lru(sc)) {
-		for (i = 0; zones[i] != NULL; i++) {
-			struct zone *zone = zones[i];
+		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 				continue;
@@ -1397,7 +1399,8 @@ static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask,
 	return ret;
 }
 
-unsigned long try_to_free_pages(struct zone **zones, int order, gfp_t gfp_mask)
+unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
+								gfp_t gfp_mask)
 {
 	struct scan_control sc = {
 		.gfp_mask = gfp_mask,
@@ -1410,7 +1413,7 @@ unsigned long try_to_free_pages(struct zone **zones, int order, gfp_t gfp_mask)
 		.isolate_pages = isolate_pages_global,
 	};
 
-	return do_try_to_free_pages(zones, gfp_mask, &sc);
+	return do_try_to_free_pages(zonelist, &sc);
 }
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
@@ -1419,7 +1422,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 						gfp_t gfp_mask)
 {
 	struct scan_control sc = {
-		.gfp_mask = gfp_mask,
 		.may_writepage = !laptop_mode,
 		.may_swap = 1,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
@@ -1428,13 +1430,12 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 		.mem_cgroup = mem_cont,
 		.isolate_pages = mem_cgroup_isolate_pages,
 	};
-	struct zone **zones;
-	int target_zone = gfp_zone(GFP_HIGHUSER_MOVABLE);
+	struct zonelist *zonelist;
 
-	zones = NODE_DATA(numa_node_id())->node_zonelists[target_zone].zones;
-	if (do_try_to_free_pages(zones, sc.gfp_mask, &sc))
-		return 1;
-	return 0;
+	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
+			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
+	zonelist = NODE_DATA(numa_node_id())->node_zonelists;
+	return do_try_to_free_pages(zonelist, &sc);
 }
 #endif
 
diff --git a/trunk/mm/vmstat.c b/trunk/mm/vmstat.c
index 7c7286e9506d..ec6035eda933 100644
--- a/trunk/mm/vmstat.c
+++ b/trunk/mm/vmstat.c
@@ -322,6 +322,7 @@ void refresh_cpu_vm_stats(int cpu)
 				p->expire = 3;
 #endif
 			}
+		cond_resched();
 #ifdef CONFIG_NUMA
 		/*
 		 * Deal with draining the remote pageset of this
@@ -364,13 +365,13 @@ void refresh_cpu_vm_stats(int cpu)
  *
  * Must be called with interrupts disabled.
  */
-void zone_statistics(struct zonelist *zonelist, struct zone *z)
+void zone_statistics(struct zone *preferred_zone, struct zone *z)
 {
-	if (z->zone_pgdat == zonelist->zones[0]->zone_pgdat) {
+	if (z->zone_pgdat == preferred_zone->zone_pgdat) {
 		__inc_zone_state(z, NUMA_HIT);
 	} else {
 		__inc_zone_state(z, NUMA_MISS);
-		__inc_zone_state(zonelist->zones[0], NUMA_FOREIGN);
+		__inc_zone_state(preferred_zone, NUMA_FOREIGN);
 	}
 	if (z->node == numa_node_id())
 		__inc_zone_state(z, NUMA_LOCAL);
@@ -645,6 +646,10 @@ static const char * const vmstat_text[] = {
 	"allocstall",
 
 	"pgrotated",
+#ifdef CONFIG_HUGETLB_PAGE
+	"htlb_buddy_alloc_success",
+	"htlb_buddy_alloc_fail",
+#endif
 #endif
 };
 
diff --git a/trunk/net/can/raw.c b/trunk/net/can/raw.c
index 201cbfc6b9ec..69877b8e7e9c 100644
--- a/trunk/net/can/raw.c
+++ b/trunk/net/can/raw.c
@@ -435,15 +435,13 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 			if (!filter)
 				return -ENOMEM;
 
-			err = copy_from_user(filter, optval, optlen);
-			if (err) {
+			if (copy_from_user(filter, optval, optlen)) {
 				kfree(filter);
-				return err;
+				return -EFAULT;
 			}
 		} else if (count == 1) {
-			err = copy_from_user(&sfilter, optval, optlen);
-			if (err)
-				return err;
+			if (copy_from_user(&sfilter, optval, optlen))
+				return -EFAULT;
 		}
 
 		lock_sock(sk);
@@ -493,9 +491,8 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		if (optlen != sizeof(err_mask))
 			return -EINVAL;
 
-		err = copy_from_user(&err_mask, optval, optlen);
-		if (err)
-			return err;
+		if (copy_from_user(&err_mask, optval, optlen))
+			return -EFAULT;
 
 		err_mask &= CAN_ERR_MASK;
 
@@ -531,7 +528,8 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		if (optlen != sizeof(ro->loopback))
 			return -EINVAL;
 
-		err = copy_from_user(&ro->loopback, optval, optlen);
+		if (copy_from_user(&ro->loopback, optval, optlen))
+			return -EFAULT;
 
 		break;
 
@@ -539,7 +537,8 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
 		if (optlen != sizeof(ro->recv_own_msgs))
 			return -EINVAL;
 
-		err = copy_from_user(&ro->recv_own_msgs, optval, optlen);
+		if (copy_from_user(&ro->recv_own_msgs, optval, optlen))
+			return -EFAULT;
 
 		break;
 
diff --git a/trunk/net/compat.c b/trunk/net/compat.c
index 80013fb69a61..01bf95d0832e 100644
--- a/trunk/net/compat.c
+++ b/trunk/net/compat.c
@@ -24,6 +24,8 @@
 
 #include <net/scm.h>
 #include <net/sock.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
 #include <asm/uaccess.h>
 #include <net/compat.h>
 
@@ -521,6 +523,121 @@ asmlinkage long compat_sys_getsockopt(int fd, int level, int optname,
 	}
 	return err;
 }
+
+struct compat_group_req {
+	__u32				 gr_interface;
+	struct __kernel_sockaddr_storage gr_group
+		__attribute__ ((aligned(4)));
+} __attribute__ ((packed));
+
+struct compat_group_source_req {
+	__u32				 gsr_interface;
+	struct __kernel_sockaddr_storage gsr_group
+		__attribute__ ((aligned(4)));
+	struct __kernel_sockaddr_storage gsr_source
+		__attribute__ ((aligned(4)));
+} __attribute__ ((packed));
+
+struct compat_group_filter {
+	__u32				 gf_interface;
+	struct __kernel_sockaddr_storage gf_group
+		__attribute__ ((aligned(4)));
+	__u32				 gf_fmode;
+	__u32				 gf_numsrc;
+	struct __kernel_sockaddr_storage gf_slist[1]
+		__attribute__ ((aligned(4)));
+} __attribute__ ((packed));
+
+
+int compat_mc_setsockopt(struct sock *sock, int level, int optname,
+	char __user *optval, int optlen,
+	int (*setsockopt)(struct sock *,int,int,char __user *,int))
+{
+	char __user	*koptval = optval;
+	int		koptlen = optlen;
+
+	switch (optname) {
+	case MCAST_JOIN_GROUP:
+	case MCAST_LEAVE_GROUP:
+	{
+		struct compat_group_req __user *gr32 = (void *)optval;
+		struct group_req __user *kgr =
+			compat_alloc_user_space(sizeof(struct group_req));
+		u32 interface;
+
+		if (!access_ok(VERIFY_READ, gr32, sizeof(*gr32)) ||
+		    !access_ok(VERIFY_WRITE, kgr, sizeof(struct group_req)) ||
+		    __get_user(interface, &gr32->gr_interface) ||
+		    __put_user(interface, &kgr->gr_interface) ||
+		    copy_in_user(&kgr->gr_group, &gr32->gr_group,
+				sizeof(kgr->gr_group)))
+			return -EFAULT;
+		koptval = (char __user *)kgr;
+		koptlen = sizeof(struct group_req);
+		break;
+	}
+	case MCAST_JOIN_SOURCE_GROUP:
+	case MCAST_LEAVE_SOURCE_GROUP:
+	case MCAST_BLOCK_SOURCE:
+	case MCAST_UNBLOCK_SOURCE:
+	{
+		struct compat_group_source_req __user *gsr32 = (void *)optval;
+		struct group_source_req *kgsr = compat_alloc_user_space(
+			sizeof(struct group_source_req));
+		u32 interface;
+
+		if (!access_ok(VERIFY_READ, gsr32, sizeof(*gsr32)) ||
+		    !access_ok(VERIFY_WRITE, kgsr,
+			sizeof(struct group_source_req)) ||
+		    __get_user(interface, &gsr32->gsr_interface) ||
+		    __put_user(interface, &kgsr->gsr_interface) ||
+		    copy_in_user(&kgsr->gsr_group, &gsr32->gsr_group,
+				sizeof(kgsr->gsr_group)) ||
+		    copy_in_user(&kgsr->gsr_source, &gsr32->gsr_source,
+				sizeof(kgsr->gsr_source)))
+			return -EFAULT;
+		koptval = (char __user *)kgsr;
+		koptlen = sizeof(struct group_source_req);
+		break;
+	}
+	case MCAST_MSFILTER:
+	{
+		struct compat_group_filter __user *gf32 = (void *)optval;
+		struct group_filter *kgf;
+		u32 interface, fmode, numsrc;
+
+		if (!access_ok(VERIFY_READ, gf32, sizeof(*gf32)) ||
+		    __get_user(interface, &gf32->gf_interface) ||
+		    __get_user(fmode, &gf32->gf_fmode) ||
+		    __get_user(numsrc, &gf32->gf_numsrc))
+			return -EFAULT;
+		koptlen = optlen + sizeof(struct group_filter) -
+				sizeof(struct compat_group_filter);
+		if (koptlen < GROUP_FILTER_SIZE(numsrc))
+			return -EINVAL;
+		kgf = compat_alloc_user_space(koptlen);
+		if (!access_ok(VERIFY_WRITE, kgf, koptlen) ||
+		    __put_user(interface, &kgf->gf_interface) ||
+		    __put_user(fmode, &kgf->gf_fmode) ||
+		    __put_user(numsrc, &kgf->gf_numsrc) ||
+		    copy_in_user(&kgf->gf_group, &gf32->gf_group,
+				sizeof(kgf->gf_group)) ||
+		    (numsrc && copy_in_user(&kgf->gf_slist, &gf32->gf_slist,
+				numsrc * sizeof(kgf->gf_slist[0]))))
+			return -EFAULT;
+		koptval = (char __user *)kgf;
+		break;
+	}
+
+	default:
+		break;
+	}
+	return setsockopt(sock, level, optname, koptval, koptlen);
+}
+
+EXPORT_SYMBOL(compat_mc_setsockopt);
+
+
 /* Argument list sizes for compat_sys_socketcall */
 #define AL(x) ((x) * sizeof(u32))
 static unsigned char nas[18]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3),
diff --git a/trunk/net/core/dev.c b/trunk/net/core/dev.c
index e1df1ab3e04a..ed49da592051 100644
--- a/trunk/net/core/dev.c
+++ b/trunk/net/core/dev.c
@@ -1524,7 +1524,7 @@ static int dev_gso_segment(struct sk_buff *skb)
 	if (!segs)
 		return 0;
 
-	if (unlikely(IS_ERR(segs)))
+	if (IS_ERR(segs))
 		return PTR_ERR(segs);
 
 	skb->next = segs;
diff --git a/trunk/net/ipv4/af_inet.c b/trunk/net/ipv4/af_inet.c
index f2b5270efdaa..24eca23c2db3 100644
--- a/trunk/net/ipv4/af_inet.c
+++ b/trunk/net/ipv4/af_inet.c
@@ -1234,7 +1234,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features)
 		segs = ops->gso_segment(skb, features);
 	rcu_read_unlock();
 
-	if (!segs || unlikely(IS_ERR(segs)))
+	if (!segs || IS_ERR(segs))
 		goto out;
 
 	skb = segs;
diff --git a/trunk/net/ipv4/ip_sockglue.c b/trunk/net/ipv4/ip_sockglue.c
index d8adfd4972e2..4d8d95404f45 100644
--- a/trunk/net/ipv4/ip_sockglue.c
+++ b/trunk/net/ipv4/ip_sockglue.c
@@ -36,6 +36,7 @@
 #include <linux/mroute.h>
 #include <net/route.h>
 #include <net/xfrm.h>
+#include <net/compat.h>
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 #include <net/transp_v6.h>
 #endif
@@ -923,6 +924,10 @@ int compat_ip_setsockopt(struct sock *sk, int level, int optname,
 	if (level != SOL_IP)
 		return -ENOPROTOOPT;
 
+	if (optname >= MCAST_JOIN_GROUP && optname <= MCAST_MSFILTER)
+		return compat_mc_setsockopt(sk, level, optname, optval, optlen,
+			ip_setsockopt);
+
 	err = do_ip_setsockopt(sk, level, optname, optval, optlen);
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
diff --git a/trunk/net/ipv4/tcp_input.c b/trunk/net/ipv4/tcp_input.c
index ac9b8482f702..0298f80681f2 100644
--- a/trunk/net/ipv4/tcp_input.c
+++ b/trunk/net/ipv4/tcp_input.c
@@ -4925,8 +4925,7 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 	tcp_data_snd_check(sk);
 	tcp_ack_snd_check(sk);
 
-	if (tcp_defer_accept_check(sk))
-		return -1;
+	tcp_defer_accept_check(sk);
 	return 0;
 
 csum_error:
diff --git a/trunk/net/ipv6/Kconfig b/trunk/net/ipv6/Kconfig
index b2c9becc02e8..42814a2ec9d7 100644
--- a/trunk/net/ipv6/Kconfig
+++ b/trunk/net/ipv6/Kconfig
@@ -167,7 +167,7 @@ config IPV6_SIT
 	  Tunneling means encapsulating data of one protocol type within
 	  another protocol and sending it over a channel that understands the
 	  encapsulating protocol. This driver implements encapsulation of IPv6
-	  into IPv4 packets. This is useful if you want to connect to IPv6
+	  into IPv4 packets. This is useful if you want to connect two IPv6
 	  networks over an IPv4-only path.
 
 	  Saying M here will produce a module called sit.ko. If unsure, say Y.
diff --git a/trunk/net/ipv6/ip6mr.c b/trunk/net/ipv6/ip6mr.c
index c8c6e33d1163..2de3c464fe75 100644
--- a/trunk/net/ipv6/ip6mr.c
+++ b/trunk/net/ipv6/ip6mr.c
@@ -358,7 +358,7 @@ static int pim6_rcv(struct sk_buff *skb)
 	if (pim->type != ((PIM_VERSION << 4) | PIM_REGISTER) ||
 	    (pim->flags & PIM_NULL_REGISTER) ||
 	    (ip_compute_csum((void *)pim, sizeof(*pim)) != 0 &&
-	     (u16)csum_fold(skb_checksum(skb, 0, skb->len, 0))))
+	     csum_fold(skb_checksum(skb, 0, skb->len, 0))))
 		goto drop;
 
 	/* check if the inner packet is destined to mcast group */
diff --git a/trunk/net/ipv6/ipv6_sockglue.c b/trunk/net/ipv6/ipv6_sockglue.c
index 06de9d0e1f6b..db6fdc1498aa 100644
--- a/trunk/net/ipv6/ipv6_sockglue.c
+++ b/trunk/net/ipv6/ipv6_sockglue.c
@@ -52,6 +52,7 @@
 #include <net/udp.h>
 #include <net/udplite.h>
 #include <net/xfrm.h>
+#include <net/compat.h>
 
 #include <asm/uaccess.h>
 
@@ -779,6 +780,10 @@ int compat_ipv6_setsockopt(struct sock *sk, int level, int optname,
 	if (level != SOL_IPV6)
 		return -ENOPROTOOPT;
 
+	if (optname >= MCAST_JOIN_GROUP && optname <= MCAST_MSFILTER)
+		return compat_mc_setsockopt(sk, level, optname, optval, optlen,
+			ipv6_setsockopt);
+
 	err = do_ipv6_setsockopt(sk, level, optname, optval, optlen);
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
diff --git a/trunk/net/irda/irnet/irnet_irda.c b/trunk/net/irda/irnet/irnet_irda.c
index a4f1439ffdd8..75497e55927d 100644
--- a/trunk/net/irda/irnet/irnet_irda.c
+++ b/trunk/net/irda/irnet/irnet_irda.c
@@ -9,6 +9,7 @@
  */
 
 #include "irnet_irda.h"		/* Private header */
+#include <linux/seq_file.h>
 
 /*
  * PPP disconnect work: we need to make sure we're in
@@ -1717,34 +1718,23 @@ irnet_expiry_indication(discinfo_t *	expiry,
  */
 
 #ifdef CONFIG_PROC_FS
-/*------------------------------------------------------------------*/
-/*
- * Function irnet_proc_read (buf, start, offset, len, unused)
- *
- *    Give some info to the /proc file system
- */
 static int
-irnet_proc_read(char *	buf,
-		char **	start,
-		off_t	offset,
-		int	len)
+irnet_proc_show(struct seq_file *m, void *v)
 {
   irnet_socket *	self;
   char *		state;
   int			i = 0;
 
-  len = 0;
-
   /* Get the IrNET server information... */
-  len += sprintf(buf+len, "IrNET server - ");
-  len += sprintf(buf+len, "IrDA state: %s, ",
+  seq_printf(m, "IrNET server - ");
+  seq_printf(m, "IrDA state: %s, ",
 		 (irnet_server.running ? "running" : "dead"));
-  len += sprintf(buf+len, "stsap_sel: %02x, ", irnet_server.s.stsap_sel);
-  len += sprintf(buf+len, "dtsap_sel: %02x\n", irnet_server.s.dtsap_sel);
+  seq_printf(m, "stsap_sel: %02x, ", irnet_server.s.stsap_sel);
+  seq_printf(m, "dtsap_sel: %02x\n", irnet_server.s.dtsap_sel);
 
   /* Do we need to continue ? */
   if(!irnet_server.running)
-    return len;
+    return 0;
 
   /* Protect access to the instance list */
   spin_lock_bh(&irnet_server.spinlock);
@@ -1754,23 +1744,23 @@ irnet_proc_read(char *	buf,
   while(self != NULL)
     {
       /* Start printing info about the socket. */
-      len += sprintf(buf+len, "\nIrNET socket %d - ", i++);
+      seq_printf(m, "\nIrNET socket %d - ", i++);
 
       /* First, get the requested configuration */
-      len += sprintf(buf+len, "Requested IrDA name: \"%s\", ", self->rname);
-      len += sprintf(buf+len, "daddr: %08x, ", self->rdaddr);
-      len += sprintf(buf+len, "saddr: %08x\n", self->rsaddr);
+      seq_printf(m, "Requested IrDA name: \"%s\", ", self->rname);
+      seq_printf(m, "daddr: %08x, ", self->rdaddr);
+      seq_printf(m, "saddr: %08x\n", self->rsaddr);
 
       /* Second, get all the PPP info */
-      len += sprintf(buf+len, "	PPP state: %s",
+      seq_printf(m, "	PPP state: %s",
 		 (self->ppp_open ? "registered" : "unregistered"));
       if(self->ppp_open)
 	{
-	  len += sprintf(buf+len, ", unit: ppp%d",
+	  seq_printf(m, ", unit: ppp%d",
 			 ppp_unit_number(&self->chan));
-	  len += sprintf(buf+len, ", channel: %d",
+	  seq_printf(m, ", channel: %d",
 			 ppp_channel_index(&self->chan));
-	  len += sprintf(buf+len, ", mru: %d",
+	  seq_printf(m, ", mru: %d",
 			 self->mru);
 	  /* Maybe add self->flags ? Later... */
 	}
@@ -1789,10 +1779,10 @@ irnet_proc_read(char *	buf,
 	      state = "weird";
 	    else
 	      state = "idle";
-      len += sprintf(buf+len, "\n	IrDA state: %s, ", state);
-      len += sprintf(buf+len, "daddr: %08x, ", self->daddr);
-      len += sprintf(buf+len, "stsap_sel: %02x, ", self->stsap_sel);
-      len += sprintf(buf+len, "dtsap_sel: %02x\n", self->dtsap_sel);
+      seq_printf(m, "\n	IrDA state: %s, ", state);
+      seq_printf(m, "daddr: %08x, ", self->daddr);
+      seq_printf(m, "stsap_sel: %02x, ", self->stsap_sel);
+      seq_printf(m, "dtsap_sel: %02x\n", self->dtsap_sel);
 
       /* Next socket, please... */
       self = (irnet_socket *) hashbin_get_next(irnet_server.list);
@@ -1801,8 +1791,21 @@ irnet_proc_read(char *	buf,
   /* Spin lock end */
   spin_unlock_bh(&irnet_server.spinlock);
 
-  return len;
+  return 0;
 }
+
+static int irnet_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, irnet_proc_show, NULL);
+}
+
+static const struct file_operations irnet_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= irnet_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
 #endif /* PROC_FS */
 
 
@@ -1841,7 +1844,7 @@ irda_irnet_init(void)
 
 #ifdef CONFIG_PROC_FS
   /* Add a /proc file for irnet infos */
-  create_proc_info_entry("irnet", 0, proc_irda, irnet_proc_read);
+  proc_create("irnet", 0, proc_irda, &irnet_proc_fops);
 #endif /* CONFIG_PROC_FS */
 
   /* Setup the IrNET server */
diff --git a/trunk/net/irda/irnet/irnet_irda.h b/trunk/net/irda/irnet/irnet_irda.h
index 0ba92d0d5204..3e408952a3f1 100644
--- a/trunk/net/irda/irnet/irnet_irda.h
+++ b/trunk/net/irda/irnet/irnet_irda.h
@@ -159,14 +159,6 @@ static void
 				DISCOVERY_MODE,
 				void *);
 #endif
-/* -------------------------- PROC ENTRY -------------------------- */
-#ifdef CONFIG_PROC_FS
-static int
-	irnet_proc_read(char *,
-			char **,
-			off_t,
-			int);
-#endif /* CONFIG_PROC_FS */
 
 /**************************** VARIABLES ****************************/
 
diff --git a/trunk/net/mac80211/Kconfig b/trunk/net/mac80211/Kconfig
index 520a5180a4f6..a24b459dd45a 100644
--- a/trunk/net/mac80211/Kconfig
+++ b/trunk/net/mac80211/Kconfig
@@ -73,7 +73,9 @@ config MAC80211_MESH
 
 config MAC80211_LEDS
 	bool "Enable LED triggers"
-	depends on MAC80211 && LEDS_TRIGGERS
+	depends on MAC80211
+	select NEW_LEDS
+	select LEDS_TRIGGERS
 	---help---
 	  This option enables a few LED triggers for different
 	  packet receive/transmit events.
diff --git a/trunk/net/mac80211/mesh.h b/trunk/net/mac80211/mesh.h
index 742003d3a841..9ee3affab346 100644
--- a/trunk/net/mac80211/mesh.h
+++ b/trunk/net/mac80211/mesh.h
@@ -13,6 +13,7 @@
 
 #include <linux/types.h>
 #include <linux/jhash.h>
+#include <asm/unaligned.h>
 #include "ieee80211_i.h"
 
 
diff --git a/trunk/net/mac80211/mesh_hwmp.c b/trunk/net/mac80211/mesh_hwmp.c
index 02de8f1522a3..3df809222d1c 100644
--- a/trunk/net/mac80211/mesh_hwmp.c
+++ b/trunk/net/mac80211/mesh_hwmp.c
@@ -7,7 +7,6 @@
  * published by the Free Software Foundation.
  */
 
-#include <asm/unaligned.h>
 #include "mesh.h"
 
 #define TEST_FRAME_LEN	8192
diff --git a/trunk/net/netfilter/nf_queue.c b/trunk/net/netfilter/nf_queue.c
index bbd26893c0c4..582ec3efc8a5 100644
--- a/trunk/net/netfilter/nf_queue.c
+++ b/trunk/net/netfilter/nf_queue.c
@@ -214,7 +214,7 @@ int nf_queue(struct sk_buff *skb,
 
 	segs = skb_gso_segment(skb, 0);
 	kfree_skb(skb);
-	if (unlikely(IS_ERR(segs)))
+	if (IS_ERR(segs))
 		return 1;
 
 	do {
diff --git a/trunk/net/sunrpc/xprt.c b/trunk/net/sunrpc/xprt.c
index 75d748eee0eb..e1770f7ba0b3 100644
--- a/trunk/net/sunrpc/xprt.c
+++ b/trunk/net/sunrpc/xprt.c
@@ -445,7 +445,7 @@ EXPORT_SYMBOL_GPL(xprt_wake_pending_tasks);
 /**
  * xprt_wait_for_buffer_space - wait for transport output buffer to clear
  * @task: task to be put to sleep
- *
+ * @action: function pointer to be executed after wait
  */
 void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action)
 {
diff --git a/trunk/net/tipc/msg.h b/trunk/net/tipc/msg.h
index 6ad070d87702..ad487e8abcc2 100644
--- a/trunk/net/tipc/msg.h
+++ b/trunk/net/tipc/msg.h
@@ -70,10 +70,9 @@ static inline void msg_set_bits(struct tipc_msg *m, u32 w,
 				u32 pos, u32 mask, u32 val)
 {
 	val = (val & mask) << pos;
-	val = htonl(val);
-	mask = htonl(mask << pos);
-	m->hdr[w] &= ~mask;
-	m->hdr[w] |= val;
+	mask = mask << pos;
+	m->hdr[w] &= ~htonl(mask);
+	m->hdr[w] |= htonl(val);
 }
 
 /*
diff --git a/trunk/net/xfrm/xfrm_algo.c b/trunk/net/xfrm/xfrm_algo.c
index 8aa6440d689f..ac765dd9c7f5 100644
--- a/trunk/net/xfrm/xfrm_algo.c
+++ b/trunk/net/xfrm/xfrm_algo.c
@@ -129,8 +129,7 @@ static struct xfrm_algo_desc aead_list[] = {
 
 static struct xfrm_algo_desc aalg_list[] = {
 {
-	.name = "hmac(digest_null)",
-	.compat = "digest_null",
+	.name = "digest_null",
 
 	.uinfo = {
 		.auth = {
diff --git a/trunk/net/xfrm/xfrm_output.c b/trunk/net/xfrm/xfrm_output.c
index 2519129c6d21..09cd9c0c2d80 100644
--- a/trunk/net/xfrm/xfrm_output.c
+++ b/trunk/net/xfrm/xfrm_output.c
@@ -150,7 +150,7 @@ static int xfrm_output_gso(struct sk_buff *skb)
 
 	segs = skb_gso_segment(skb, 0);
 	kfree_skb(skb);
-	if (unlikely(IS_ERR(segs)))
+	if (IS_ERR(segs))
 		return PTR_ERR(segs);
 
 	do {
diff --git a/trunk/net/xfrm/xfrm_state.c b/trunk/net/xfrm/xfrm_state.c
index 5dcc10b93c86..fac27ce770d5 100644
--- a/trunk/net/xfrm/xfrm_state.c
+++ b/trunk/net/xfrm/xfrm_state.c
@@ -2112,7 +2112,7 @@ static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family,
 		iph6 = ipv6_hdr(skb);
 		audit_log_format(audit_buf,
 				 " src=" NIP6_FMT " dst=" NIP6_FMT
-				 " flowlbl=0x%x%x%x",
+				 " flowlbl=0x%x%02x%02x",
 				 NIP6(iph6->saddr),
 				 NIP6(iph6->daddr),
 				 iph6->flow_lbl[0] & 0x0f,
diff --git a/trunk/samples/markers/marker-example.c b/trunk/samples/markers/marker-example.c
index 05e438f8b4e2..e90dc5d04392 100644
--- a/trunk/samples/markers/marker-example.c
+++ b/trunk/samples/markers/marker-example.c
@@ -33,10 +33,8 @@ static struct file_operations mark_ops = {
 static int example_init(void)
 {
 	printk(KERN_ALERT "example init\n");
-	pentry_example = create_proc_entry("marker-example", 0444, NULL);
-	if (pentry_example)
-		pentry_example->proc_fops = &mark_ops;
-	else
+	pentry_example = proc_create("marker-example", 0444, NULL, &mark_ops);
+	if (!pentry_example)
 		return -EPERM;
 	return 0;
 }
diff --git a/trunk/scripts/Lindent b/trunk/scripts/Lindent
index 9468ec7971db..9c4b3e2b7098 100755
--- a/trunk/scripts/Lindent
+++ b/trunk/scripts/Lindent
@@ -1,2 +1,18 @@
 #!/bin/sh
-indent -npro -kr -i8 -ts8 -sob -l80 -ss -ncs -cp1 "$@"
+PARAM="-npro -kr -i8 -ts8 -sob -l80 -ss -ncs -cp1"
+RES=`indent --version`
+V1=`echo $RES | cut -d' ' -f3 | cut -d'.' -f1`
+V2=`echo $RES | cut -d' ' -f3 | cut -d'.' -f2`
+V3=`echo $RES | cut -d' ' -f3 | cut -d'.' -f3`
+if [ $V1 -gt 2 ]; then
+  PARAM="$PARAM -il0"
+elif [ $V1 -eq 2 ]; then
+  if [ $V2 -gt 2 ]; then
+    PARAM="$PARAM -il0";
+  elif [ $V2 -eq 2 ]; then
+    if [ $V3 -ge 10 ]; then
+      PARAM="$PARAM -il0"
+    fi
+  fi
+fi
+indent $PARAM "$@"
diff --git a/trunk/scripts/checkpatch.pl b/trunk/scripts/checkpatch.pl
index 64ec4b8a51b5..b6bbbcdc557e 100755
--- a/trunk/scripts/checkpatch.pl
+++ b/trunk/scripts/checkpatch.pl
@@ -9,7 +9,7 @@
 my $P = $0;
 $P =~ s@.*/@@g;
 
-my $V = '0.16';
+my $V = '0.18';
 
 use Getopt::Long qw(:config no_auto_abbrev);
 
@@ -131,6 +131,17 @@
 our $Type;
 our $Declare;
 
+our $UTF8	= qr {
+	[\x09\x0A\x0D\x20-\x7E]              # ASCII
+	| [\xC2-\xDF][\x80-\xBF]             # non-overlong 2-byte
+	|  \xE0[\xA0-\xBF][\x80-\xBF]        # excluding overlongs
+	| [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}  # straight 3-byte
+	|  \xED[\x80-\x9F][\x80-\xBF]        # excluding surrogates
+	|  \xF0[\x90-\xBF][\x80-\xBF]{2}     # planes 1-3
+	| [\xF1-\xF3][\x80-\xBF]{3}          # planes 4-15
+	|  \xF4[\x80-\x8F][\x80-\xBF]{2}     # plane 16
+}x;
+
 our @typeList = (
 	qr{void},
 	qr{char},
@@ -692,7 +703,7 @@ sub annotate_values {
 	while (length($cur)) {
 		@av_paren_type = ('E') if ($#av_paren_type < 0);
 		print " <" . join('', @av_paren_type) .
-					"> <$type> " if ($dbg_values > 1);
+				"> <$type> <$av_pending>" if ($dbg_values > 1);
 		if ($cur =~ /^(\s+)/o) {
 			print "WS($1)\n" if ($dbg_values > 1);
 			if ($1 =~ /\n/ && $av_preprocessor) {
@@ -705,9 +716,18 @@ sub annotate_values {
 			$type = 'T';
 
 		} elsif ($cur =~ /^(#\s*define\s*$Ident)(\(?)/o) {
-			print "DEFINE($1)\n" if ($dbg_values > 1);
+			print "DEFINE($1,$2)\n" if ($dbg_values > 1);
 			$av_preprocessor = 1;
-			$av_pending = 'N';
+			push(@av_paren_type, $type);
+			if ($2 ne '') {
+				$av_pending = 'N';
+			}
+			$type = 'E';
+
+		} elsif ($cur =~ /^(#\s*undef\s*$Ident)/o) {
+			print "UNDEF($1)\n" if ($dbg_values > 1);
+			$av_preprocessor = 1;
+			push(@av_paren_type, $type);
 
 		} elsif ($cur =~ /^(#\s*(?:ifdef|ifndef|if))/o) {
 			print "PRE_START($1)\n" if ($dbg_values > 1);
@@ -715,7 +735,7 @@ sub annotate_values {
 
 			push(@av_paren_type, $type);
 			push(@av_paren_type, $type);
-			$type = 'N';
+			$type = 'E';
 
 		} elsif ($cur =~ /^(#\s*(?:else|elif))/o) {
 			print "PRE_RESTART($1)\n" if ($dbg_values > 1);
@@ -723,7 +743,7 @@ sub annotate_values {
 
 			push(@av_paren_type, $av_paren_type[$#av_paren_type]);
 
-			$type = 'N';
+			$type = 'E';
 
 		} elsif ($cur =~ /^(#\s*(?:endif))/o) {
 			print "PRE_END($1)\n" if ($dbg_values > 1);
@@ -734,11 +754,16 @@ sub annotate_values {
 			# one does, and continue as if the #endif was not here.
 			pop(@av_paren_type);
 			push(@av_paren_type, $type);
-			$type = 'N';
+			$type = 'E';
 
 		} elsif ($cur =~ /^(\\\n)/o) {
 			print "PRECONT($1)\n" if ($dbg_values > 1);
 
+		} elsif ($cur =~ /^(__attribute__)\s*\(?/o) {
+			print "ATTR($1)\n" if ($dbg_values > 1);
+			$av_pending = $type;
+			$type = 'N';
+
 		} elsif ($cur =~ /^(sizeof)\s*(\()?/o) {
 			print "SIZEOF($1)\n" if ($dbg_values > 1);
 			if (defined $2) {
@@ -930,7 +955,7 @@ sub process {
 			# edge is a close comment then we must be in a comment
 			# at context start.
 			my $edge;
-			for (my $ln = $linenr; $ln < ($linenr + $realcnt); $ln++) {
+			for (my $ln = $linenr + 1; $ln < ($linenr + $realcnt); $ln++) {
 				next if ($line =~ /^-/);
 				($edge) = ($rawlines[$ln - 1] =~ m@(/\*|\*/)@);
 				last if (defined $edge);
@@ -951,9 +976,9 @@ sub process {
 			##print "COMMENT:$in_comment edge<$edge> $rawline\n";
 			sanitise_line_reset($in_comment);
 
-		} elsif ($realcnt) {
+		} elsif ($realcnt && $rawline =~ /^(?:\+| |$)/) {
 			# Standardise the strings and chars within the input to
-			# simplify matching.
+			# simplify matching -- only bother with positive lines.
 			$line = sanitise_line($rawline);
 		}
 		push(@lines, $line);
@@ -1066,17 +1091,14 @@ sub process {
 
 # UTF-8 regex found at http://www.w3.org/International/questions/qa-forms-utf-8.en.php
 		if (($realfile =~ /^$/ || $line =~ /^\+/) &&
-		     !($rawline =~ m/^(
-				[\x09\x0A\x0D\x20-\x7E]              # ASCII
-				| [\xC2-\xDF][\x80-\xBF]             # non-overlong 2-byte
-				|  \xE0[\xA0-\xBF][\x80-\xBF]        # excluding overlongs
-				| [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}  # straight 3-byte
-				|  \xED[\x80-\x9F][\x80-\xBF]        # excluding surrogates
-				|  \xF0[\x90-\xBF][\x80-\xBF]{2}     # planes 1-3
-				| [\xF1-\xF3][\x80-\xBF]{3}          # planes 4-15
-				|  \xF4[\x80-\x8F][\x80-\xBF]{2}     # plane 16
-				)*$/x )) {
-			ERROR("Invalid UTF-8, patch and commit message should be encoded in UTF-8\n" . $herecurr);
+		    $rawline !~ m/^$UTF8*$/) {
+			my ($utf8_prefix) = ($rawline =~ /^($UTF8*)/);
+
+			my $blank = copy_spacing($rawline);
+			my $ptr = substr($blank, 0, length($utf8_prefix)) . "^";
+			my $hereptr = "$hereline$ptr\n";
+
+			ERROR("Invalid UTF-8, patch and commit message should be encoded in UTF-8\n" . $hereptr);
 		}
 
 #ignore lines being removed
@@ -1112,7 +1134,7 @@ sub process {
 		if ($rawline =~ /^\+\s* \t\s*\S/ ||
 		    $rawline =~ /^\+\s*        \s*/) {
 			my $herevet = "$here\n" . cat_vet($rawline) . "\n";
-			ERROR("use tabs not spaces\n" . $herevet);
+			ERROR("code indent should use tabs where possible\n" . $herevet);
 		}
 
 # check for RCS/CVS revision markers
@@ -1121,35 +1143,40 @@ sub process {
 		}
 
 # Check for potential 'bare' types
-		if ($realcnt) {
-			my ($s, $c) = ctx_statement_block($linenr, $realcnt, 0);
-			$s =~ s/\n./ /g;
-			$s =~ s/{.*$//;
+		my ($stat, $cond);
+		if ($realcnt && $line =~ /.\s*\S/) {
+			($stat, $cond) = ctx_statement_block($linenr,
+								$realcnt, 0);
+			$stat =~ s/\n./\n /g;
+			$cond =~ s/\n./\n /g;
+
+			my $s = $stat;
+			$s =~ s/{.*$//s;
 
 			# Ignore goto labels.
-			if ($s =~ /$Ident:\*$/) {
+			if ($s =~ /$Ident:\*$/s) {
 
 			# Ignore functions being called
-			} elsif ($s =~ /^.\s*$Ident\s*\(/) {
+			} elsif ($s =~ /^.\s*$Ident\s*\(/s) {
 
 			# definitions in global scope can only start with types
-			} elsif ($s =~ /^.(?:$Storage\s+)?(?:$Inline\s+)?(?:const\s+)?($Ident)\b/) {
+			} elsif ($s =~ /^.(?:$Storage\s+)?(?:$Inline\s+)?(?:const\s+)?($Ident)\b/s) {
 				possible($1, $s);
 
 			# declarations always start with types
-			} elsif ($prev_values eq 'E' && $s =~ /^.\s*(?:$Storage\s+)?(?:const\s+)?($Ident)\b(:?\s+$Sparse)?\s*\**\s*$Ident\s*(?:;|=|,)/) {
+			} elsif ($prev_values eq 'E' && $s =~ /^.\s*(?:$Storage\s+)?(?:const\s+)?($Ident)\b(:?\s+$Sparse)?\s*\**\s*$Ident\s*(?:;|=|,)/s) {
 				possible($1, $s);
 			}
 
 			# any (foo ... *) is a pointer cast, and foo is a type
-			while ($s =~ /\(($Ident)(?:\s+$Sparse)*\s*\*+\s*\)/g) {
+			while ($s =~ /\(($Ident)(?:\s+$Sparse)*\s*\*+\s*\)/sg) {
 				possible($1, $s);
 			}
 
 			# Check for any sort of function declaration.
 			# int foo(something bar, other baz);
 			# void (*store_gdt)(x86_descr_ptr *);
-			if ($prev_values eq 'E' && $s =~ /^(.(?:typedef\s*)?(?:(?:$Storage|$Inline)\s*)*\s*$Type\s*(?:\b$Ident|\(\*\s*$Ident\))\s*)\(/) {
+			if ($prev_values eq 'E' && $s =~ /^(.(?:typedef\s*)?(?:(?:$Storage|$Inline)\s*)*\s*$Type\s*(?:\b$Ident|\(\*\s*$Ident\))\s*)\(/s) {
 				my ($name_len) = length($1);
 
 				my $ctx = $s;
@@ -1282,18 +1309,19 @@ sub process {
 			   ($prevline !~ /^ }/) &&
 			   ($prevline !~ /^.DECLARE_$Ident\(\Q$name\E\)/) &&
 			   ($prevline !~ /^.LIST_HEAD\(\Q$name\E\)/) &&
+			   ($prevline !~ /^.$Type\s*\(\s*\*\s*\Q$name\E\s*\)\s*\(/) &&
 			   ($prevline !~ /\b\Q$name\E(?:\s+$Attribute)?\s*(?:;|=|\[)/)) {
 				WARN("EXPORT_SYMBOL(foo); should immediately follow its function/variable\n" . $herecurr);
 			}
 		}
 
 # check for external initialisers.
-		if ($line =~ /^.$Type\s*$Ident\s*=\s*(0|NULL);/) {
+		if ($line =~ /^.$Type\s*$Ident\s*=\s*(0|NULL|false)\s*;/) {
 			ERROR("do not initialise externals to 0 or NULL\n" .
 				$herecurr);
 		}
 # check for static initialisers.
-		if ($line =~ /\s*static\s.*=\s*(0|NULL);/) {
+		if ($line =~ /\s*static\s.*=\s*(0|NULL|false)\s*;/) {
 			ERROR("do not initialise statics to 0 or NULL\n" .
 				$herecurr);
 		}
@@ -1512,7 +1540,10 @@ sub process {
 					if ($ctx !~ /[WEBC]x./ && $ca !~ /(?:\)|!|~|\*|-|\&|\||\+\+|\-\-|\{)$/) {
 						ERROR("space required before that '$op' $at\n" . $hereptr);
 					}
-					if ($ctx =~ /.xW/) {
+					if ($op  eq '*' && $cc =~/\s*const\b/) {
+						# A unary '*' may be const
+
+					} elsif ($ctx =~ /.xW/) {
 						ERROR("space prohibited after that '$op' $at\n" . $hereptr);
 					}
 
@@ -1617,7 +1648,7 @@ sub process {
 
 # Check for illegal assignment in if conditional.
 		if ($line =~ /\bif\s*\(/) {
-			my ($s, $c) = ctx_statement_block($linenr, $realcnt, 0);
+			my ($s, $c) = ($stat, $cond);
 
 			if ($c =~ /\bif\s*\(.*[^<>!=]=[^=].*/) {
 				ERROR("do not use assignment in if condition\n" . $herecurr);
@@ -1695,7 +1726,7 @@ sub process {
 #warn if <asm/foo.h> is #included and <linux/foo.h> is available (uses RAW line)
 		if ($tree && $rawline =~ m{^.\#\s*include\s*\<asm\/(.*)\.h\>}) {
 			my $checkfile = "$root/include/linux/$1.h";
-			if (-f $checkfile && $1 ne 'irq.h') {
+			if (-f $checkfile && $1 ne 'irq') {
 				WARN("Use #include <linux/$1.h> instead of <asm/$1.h>\n" .
 					$herecurr);
 			}
@@ -1910,7 +1941,8 @@ sub process {
 		}
 
 # check for spinlock_t definitions without a comment.
-		if ($line =~ /^.\s*(struct\s+mutex|spinlock_t)\s+\S+;/) {
+		if ($line =~ /^.\s*(struct\s+mutex|spinlock_t)\s+\S+;/ ||
+		    $line =~ /^.\s*(DEFINE_MUTEX)\s*\(/) {
 			my $which = $1;
 			if (!ctx_has_comment($first_line, $linenr)) {
 				CHK("$1 definition without comment\n" . $herecurr);
@@ -1940,7 +1972,26 @@ sub process {
 		}
 
 # check for new externs in .c files.
-		if ($line =~ /^.\s*extern\s/ && ($realfile =~ /\.c$/)) {
+		if ($realfile =~ /\.c$/ && defined $stat &&
+		    $stat =~ /^.\s*(?:extern\s+)?$Type\s+$Ident(\s*)\(/s)
+		{
+			my $paren_space = $1;
+
+			my $s = $stat;
+			if (defined $cond) {
+				substr($s, 0, length($cond), '');
+			}
+			if ($s =~ /^\s*;/) {
+				WARN("externs should be avoided in .c files\n" .  $herecurr);
+			}
+
+			if ($paren_space =~ /\n/) {
+				WARN("arguments for function declarations should follow identifier\n" . $herecurr);
+			}
+
+		} elsif ($realfile =~ /\.c$/ && defined $stat &&
+		    $stat =~ /^.\s*extern\s+/)
+		{
 			WARN("externs should be avoided in .c files\n" .  $herecurr);
 		}
 
@@ -1964,11 +2015,11 @@ sub process {
 		}
 
 # check for semaphores used as mutexes
-		if ($line =~ /\b(DECLARE_MUTEX|init_MUTEX)\s*\(/) {
+		if ($line =~ /^.\s*(DECLARE_MUTEX|init_MUTEX)\s*\(/) {
 			WARN("mutexes are preferred for single holder semaphores\n" . $herecurr);
 		}
 # check for semaphores used as mutexes
-		if ($line =~ /\binit_MUTEX_LOCKED\s*\(/) {
+		if ($line =~ /^.\s*init_MUTEX_LOCKED\s*\(/) {
 			WARN("consider using a completion\n" . $herecurr);
 		}
 # recommend strict_strto* over simple_strto*
@@ -1979,11 +2030,24 @@ sub process {
 # use of NR_CPUS is usually wrong
 # ignore definitions of NR_CPUS and usage to define arrays as likely right
 		if ($line =~ /\bNR_CPUS\b/ &&
-		    $line !~ /^.#\s*define\s+NR_CPUS\s+/ &&
-		    $line !~ /^.\s*$Declare\s.*\[[^\]]*NR_CPUS[^\]]*\]/)
+		    $line !~ /^.#\s*if\b.*\bNR_CPUS\b/ &&
+		    $line !~ /^.#\s*define\b.*\bNR_CPUS\b/ &&
+		    $line !~ /^.\s*$Declare\s.*\[[^\]]*NR_CPUS[^\]]*\]/ &&
+		    $line !~ /\[[^\]]*\.\.\.[^\]]*NR_CPUS[^\]]*\]/ &&
+		    $line !~ /\[[^\]]*NR_CPUS[^\]]*\.\.\.[^\]]*\]/)
 		{
 			WARN("usage of NR_CPUS is often wrong - consider using cpu_possible(), num_possible_cpus(), for_each_possible_cpu(), etc\n" . $herecurr);
 		}
+
+# check for %L{u,d,i} in strings
+		my $string;
+		while ($line =~ /(?:^|")([X\t]*)(?:"|$)/g) {
+			$string = substr($rawline, $-[1], $+[1] - $-[1]);
+			if ($string =~ /(?<!%)%L[udi]/) {
+				WARN("\%Ld/%Lu are not-standard C, use %lld/%llu\n" . $herecurr);
+				last;
+			}
+		}
 	}
 
 	# If we have no input at all, then there is nothing to report on
diff --git a/trunk/scripts/gen_initramfs_list.sh b/trunk/scripts/gen_initramfs_list.sh
index 684fb9cdc055..5f3415f28736 100644
--- a/trunk/scripts/gen_initramfs_list.sh
+++ b/trunk/scripts/gen_initramfs_list.sh
@@ -135,7 +135,7 @@ parse() {
 			str="${ftype} ${name} ${str} ${dev} ${maj} ${min}"
 			;;
 		"slink")
-			local target=`field 11 $(LC_ALL=C ls -l "${location}")`
+			local target=`readlink "${location}"`
 			str="${ftype} ${name} ${target} ${str}"
 			;;
 		*)
diff --git a/trunk/scripts/kconfig/lex.zconf.c_shipped b/trunk/scripts/kconfig/lex.zconf.c_shipped
index bed0f4e2d2f7..6a61cee4a32c 100644
--- a/trunk/scripts/kconfig/lex.zconf.c_shipped
+++ b/trunk/scripts/kconfig/lex.zconf.c_shipped
@@ -5,25 +5,6 @@
 
 /* A lexical scanner generated by flex */
 
-#define yy_create_buffer zconf_create_buffer
-#define yy_delete_buffer zconf_delete_buffer
-#define yy_flex_debug zconf_flex_debug
-#define yy_init_buffer zconf_init_buffer
-#define yy_flush_buffer zconf_flush_buffer
-#define yy_load_buffer_state zconf_load_buffer_state
-#define yy_switch_to_buffer zconf_switch_to_buffer
-#define yyin zconfin
-#define yyleng zconfleng
-#define yylex zconflex
-#define yylineno zconflineno
-#define yyout zconfout
-#define yyrestart zconfrestart
-#define yytext zconftext
-#define yywrap zconfwrap
-#define yyalloc zconfalloc
-#define yyrealloc zconfrealloc
-#define yyfree zconffree
-
 #define FLEX_SCANNER
 #define YY_FLEX_MAJOR_VERSION 2
 #define YY_FLEX_MINOR_VERSION 5
@@ -354,7 +335,7 @@ void zconffree (void *  );
 
 /* Begin user sect3 */
 
-#define zconfwrap(n) 1
+#define zconfwrap() 1
 #define YY_SKIP_YYWRAP
 
 typedef unsigned char YY_CHAR;
@@ -1535,7 +1516,7 @@ static int yy_get_next_buffer (void)
 
 		/* Read in more data. */
 		YY_INPUT( (&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[number_to_move]),
-			(yy_n_chars), num_to_read );
+			(yy_n_chars), (size_t) num_to_read );
 
 		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
 		}
@@ -2007,7 +1988,7 @@ YY_BUFFER_STATE zconf_scan_buffer  (char * base, yy_size_t  size )
 
 /** Setup the input buffer state to scan a string. The next call to zconflex() will
  * scan from a @e copy of @a str.
- * @param str a NUL-terminated string to scan
+ * @param yystr a NUL-terminated string to scan
  * 
  * @return the newly allocated buffer state object.
  * @note If you want to scan bytes that may contain NUL values, then use
diff --git a/trunk/scripts/kconfig/lkc_proto.h b/trunk/scripts/kconfig/lkc_proto.h
index 4d09f6ddefe3..8e69461313d1 100644
--- a/trunk/scripts/kconfig/lkc_proto.h
+++ b/trunk/scripts/kconfig/lkc_proto.h
@@ -21,7 +21,7 @@ P(menu_get_help,const char *,(struct menu *menu));
 /* symbol.c */
 P(symbol_hash,struct symbol *,[SYMBOL_HASHSIZE]);
 
-P(sym_lookup,struct symbol *,(const char *name, int isconst));
+P(sym_lookup,struct symbol *,(const char *name, int flags));
 P(sym_find,struct symbol *,(const char *name));
 P(sym_re_search,struct symbol **,(const char *pattern));
 P(sym_type_name,const char *,(enum symbol_type type));
diff --git a/trunk/scripts/kconfig/lxdialog/inputbox.c b/trunk/scripts/kconfig/lxdialog/inputbox.c
index 4946bd02b46d..616c60138183 100644
--- a/trunk/scripts/kconfig/lxdialog/inputbox.c
+++ b/trunk/scripts/kconfig/lxdialog/inputbox.c
@@ -89,7 +89,7 @@ int dialog_inputbox(const char *title, const char *prompt, int height, int width
 	box_y = y + 2;
 	box_x = (width - box_width) / 2;
 	draw_box(dialog, y + 1, box_x - 1, 3, box_width + 2,
-		 dlg.border.atr, dlg.dialog.atr);
+		 dlg.dialog.atr, dlg.border.atr);
 
 	print_buttons(dialog, height, width, 0);
 
diff --git a/trunk/scripts/kconfig/menu.c b/trunk/scripts/kconfig/menu.c
index 606ceb9e746e..07ff8d105c9d 100644
--- a/trunk/scripts/kconfig/menu.c
+++ b/trunk/scripts/kconfig/menu.c
@@ -235,18 +235,22 @@ void menu_finalize(struct menu *parent)
 	sym = parent->sym;
 	if (parent->list) {
 		if (sym && sym_is_choice(sym)) {
-			/* find the first choice value and find out choice type */
-			for (menu = parent->list; menu; menu = menu->next) {
-				if (menu->sym) {
-					current_entry = parent;
-					if (sym->type == S_UNKNOWN)
+			if (sym->type == S_UNKNOWN) {
+				/* find the first choice value to find out choice type */
+				current_entry = parent;
+				for (menu = parent->list; menu; menu = menu->next) {
+					if (menu->sym && menu->sym->type != S_UNKNOWN) {
 						menu_set_type(menu->sym->type);
-					current_entry = menu;
-					if (menu->sym->type == S_UNKNOWN)
-						menu_set_type(sym->type);
-					break;
+						break;
+					}
 				}
 			}
+			/* set the type of the remaining choice values */
+			for (menu = parent->list; menu; menu = menu->next) {
+				current_entry = menu;
+				if (menu->sym && menu->sym->type == S_UNKNOWN)
+					menu_set_type(sym->type);
+			}
 			parentdep = expr_alloc_symbol(sym);
 		} else if (parent->prompt)
 			parentdep = parent->prompt->visible.expr;
@@ -313,50 +317,36 @@ void menu_finalize(struct menu *parent)
 		}
 	}
 	for (menu = parent->list; menu; menu = menu->next) {
-		if (sym && sym_is_choice(sym) && menu->sym) {
+		if (sym && sym_is_choice(sym) &&
+		    menu->sym && !sym_is_choice_value(menu->sym)) {
+			current_entry = menu;
 			menu->sym->flags |= SYMBOL_CHOICEVAL;
 			if (!menu->prompt)
 				menu_warn(menu, "choice value must have a prompt");
 			for (prop = menu->sym->prop; prop; prop = prop->next) {
-				if (prop->type == P_PROMPT && prop->menu != menu) {
-					prop_warn(prop, "choice values "
-					    "currently only support a "
-					    "single prompt");
-				}
 				if (prop->type == P_DEFAULT)
 					prop_warn(prop, "defaults for choice "
-					    "values not supported");
+						  "values not supported");
+				if (prop->menu == menu)
+					continue;
+				if (prop->type == P_PROMPT &&
+				    prop->menu->parent->sym != sym)
+					prop_warn(prop, "choice value used outside its choice group");
 			}
-			current_entry = menu;
-			if (menu->sym->type == S_UNKNOWN)
-				menu_set_type(sym->type);
 			/* Non-tristate choice values of tristate choices must
 			 * depend on the choice being set to Y. The choice
 			 * values' dependencies were propagated to their
 			 * properties above, so the change here must be re-
-			 * propagated. */
+			 * propagated.
+			 */
 			if (sym->type == S_TRISTATE && menu->sym->type != S_TRISTATE) {
 				basedep = expr_alloc_comp(E_EQUAL, sym, &symbol_yes);
-				basedep = expr_alloc_and(basedep, menu->dep);
-				basedep = expr_eliminate_dups(basedep);
-				menu->dep = basedep;
+				menu->dep = expr_alloc_and(basedep, menu->dep);
 				for (prop = menu->sym->prop; prop; prop = prop->next) {
 					if (prop->menu != menu)
 						continue;
-					dep = expr_alloc_and(expr_copy(basedep),
-							     prop->visible.expr);
-					dep = expr_eliminate_dups(dep);
-					dep = expr_trans_bool(dep);
-					prop->visible.expr = dep;
-					if (prop->type == P_SELECT) {
-						struct symbol *es = prop_get_symbol(prop);
-						dep2 = expr_alloc_symbol(menu->sym);
-						dep = expr_alloc_and(dep2,
-								     expr_copy(dep));
-						dep = expr_alloc_or(es->rev_dep.expr, dep);
-						dep = expr_eliminate_dups(dep);
-						es->rev_dep.expr = dep;
-					}
+					prop->visible.expr = expr_alloc_and(expr_copy(basedep),
+									    prop->visible.expr);
 				}
 			}
 			menu_add_symbol(P_CHOICE, sym, NULL);
diff --git a/trunk/scripts/kconfig/symbol.c b/trunk/scripts/kconfig/symbol.c
index 4a03191ad176..18f3e5c33634 100644
--- a/trunk/scripts/kconfig/symbol.c
+++ b/trunk/scripts/kconfig/symbol.c
@@ -40,7 +40,7 @@ void sym_add_default(struct symbol *sym, const char *def)
 {
 	struct property *prop = prop_alloc(P_DEFAULT, sym);
 
-	prop->expr = expr_alloc_symbol(sym_lookup(def, 1));
+	prop->expr = expr_alloc_symbol(sym_lookup(def, SYMBOL_CONST));
 }
 
 void sym_init(void)
@@ -350,9 +350,6 @@ void sym_calc_value(struct symbol *sym)
 		;
 	}
 
-	if (sym->flags & SYMBOL_AUTO)
-		sym->flags &= ~SYMBOL_WRITE;
-
 	sym->curr = newval;
 	if (sym_is_choice(sym) && newval.tri == yes)
 		sym->curr.val = sym_calc_choice(sym);
@@ -377,6 +374,9 @@ void sym_calc_value(struct symbol *sym)
 				sym_set_changed(choice_sym);
 		}
 	}
+
+	if (sym->flags & SYMBOL_AUTO)
+		sym->flags &= ~SYMBOL_WRITE;
 }
 
 void sym_clear_all_valid(void)
@@ -651,7 +651,7 @@ bool sym_is_changable(struct symbol *sym)
 	return sym->visible > sym->rev_dep.tri;
 }
 
-struct symbol *sym_lookup(const char *name, int isconst)
+struct symbol *sym_lookup(const char *name, int flags)
 {
 	struct symbol *symbol;
 	const char *ptr;
@@ -671,11 +671,10 @@ struct symbol *sym_lookup(const char *name, int isconst)
 		hash &= 0xff;
 
 		for (symbol = symbol_hash[hash]; symbol; symbol = symbol->next) {
-			if (!strcmp(symbol->name, name)) {
-				if ((isconst && symbol->flags & SYMBOL_CONST) ||
-				    (!isconst && !(symbol->flags & SYMBOL_CONST)))
-					return symbol;
-			}
+			if (!strcmp(symbol->name, name) &&
+			    (flags ? symbol->flags & flags
+				   : !(symbol->flags & (SYMBOL_CONST|SYMBOL_CHOICE))))
+				return symbol;
 		}
 		new_name = strdup(name);
 	} else {
@@ -687,8 +686,7 @@ struct symbol *sym_lookup(const char *name, int isconst)
 	memset(symbol, 0, sizeof(*symbol));
 	symbol->name = new_name;
 	symbol->type = S_UNKNOWN;
-	if (isconst)
-		symbol->flags |= SYMBOL_CONST;
+	symbol->flags |= flags;
 
 	symbol->next = symbol_hash[hash];
 	symbol_hash[hash] = symbol;
@@ -762,8 +760,6 @@ struct symbol **sym_re_search(const char *pattern)
 }
 
 
-struct symbol *sym_check_deps(struct symbol *sym);
-
 static struct symbol *sym_check_expr_deps(struct expr *e)
 {
 	struct symbol *sym;
@@ -795,40 +791,100 @@ static struct symbol *sym_check_expr_deps(struct expr *e)
 }
 
 /* return NULL when dependencies are OK */
-struct symbol *sym_check_deps(struct symbol *sym)
+static struct symbol *sym_check_sym_deps(struct symbol *sym)
 {
 	struct symbol *sym2;
 	struct property *prop;
 
-	if (sym->flags & SYMBOL_CHECK) {
-		fprintf(stderr, "%s:%d:error: found recursive dependency: %s",
-		        sym->prop->file->name, sym->prop->lineno, sym->name);
-		return sym;
-	}
-	if (sym->flags & SYMBOL_CHECKED)
-		return NULL;
-
-	sym->flags |= (SYMBOL_CHECK | SYMBOL_CHECKED);
 	sym2 = sym_check_expr_deps(sym->rev_dep.expr);
 	if (sym2)
-		goto out;
+		return sym2;
 
 	for (prop = sym->prop; prop; prop = prop->next) {
 		if (prop->type == P_CHOICE || prop->type == P_SELECT)
 			continue;
 		sym2 = sym_check_expr_deps(prop->visible.expr);
 		if (sym2)
-			goto out;
+			break;
 		if (prop->type != P_DEFAULT || sym_is_choice(sym))
 			continue;
 		sym2 = sym_check_expr_deps(prop->expr);
 		if (sym2)
-			goto out;
+			break;
 	}
-out:
+
+	return sym2;
+}
+
+static struct symbol *sym_check_choice_deps(struct symbol *choice)
+{
+	struct symbol *sym, *sym2;
+	struct property *prop;
+	struct expr *e;
+
+	prop = sym_get_choice_prop(choice);
+	expr_list_for_each_sym(prop->expr, e, sym)
+		sym->flags |= (SYMBOL_CHECK | SYMBOL_CHECKED);
+
+	choice->flags |= (SYMBOL_CHECK | SYMBOL_CHECKED);
+	sym2 = sym_check_sym_deps(choice);
+	choice->flags &= ~SYMBOL_CHECK;
 	if (sym2)
-		fprintf(stderr, " -> %s%s", sym->name, sym2 == sym? "\n": "");
-	sym->flags &= ~SYMBOL_CHECK;
+		goto out;
+
+	expr_list_for_each_sym(prop->expr, e, sym) {
+		sym2 = sym_check_sym_deps(sym);
+		if (sym2) {
+			fprintf(stderr, " -> %s", sym->name);
+			break;
+		}
+	}
+out:
+	expr_list_for_each_sym(prop->expr, e, sym)
+		sym->flags &= ~SYMBOL_CHECK;
+
+	if (sym2 && sym_is_choice_value(sym2) &&
+	    prop_get_symbol(sym_get_choice_prop(sym2)) == choice)
+		sym2 = choice;
+
+	return sym2;
+}
+
+struct symbol *sym_check_deps(struct symbol *sym)
+{
+	struct symbol *sym2;
+	struct property *prop;
+
+	if (sym->flags & SYMBOL_CHECK) {
+		fprintf(stderr, "%s:%d:error: found recursive dependency: %s",
+		        sym->prop->file->name, sym->prop->lineno,
+			sym->name ? sym->name : "<choice>");
+		return sym;
+	}
+	if (sym->flags & SYMBOL_CHECKED)
+		return NULL;
+
+	if (sym_is_choice_value(sym)) {
+		/* for choice groups start the check with main choice symbol */
+		prop = sym_get_choice_prop(sym);
+		sym2 = sym_check_deps(prop_get_symbol(prop));
+	} else if (sym_is_choice(sym)) {
+		sym2 = sym_check_choice_deps(sym);
+	} else {
+		sym->flags |= (SYMBOL_CHECK | SYMBOL_CHECKED);
+		sym2 = sym_check_sym_deps(sym);
+		sym->flags &= ~SYMBOL_CHECK;
+	}
+
+	if (sym2) {
+		fprintf(stderr, " -> %s", sym->name ? sym->name : "<choice>");
+		if (sym2 == sym) {
+			fprintf(stderr, "\n");
+			zconfnerrs++;
+			sym2 = NULL;
+		}
+	}
+
 	return sym2;
 }
 
@@ -904,7 +960,7 @@ void prop_add_env(const char *env)
 	}
 
 	prop = prop_alloc(P_ENV, sym);
-	prop->expr = expr_alloc_symbol(sym_lookup(env, 1));
+	prop->expr = expr_alloc_symbol(sym_lookup(env, SYMBOL_CONST));
 
 	sym_env_list = expr_alloc_one(E_LIST, sym_env_list);
 	sym_env_list->right.sym = sym;
diff --git a/trunk/scripts/kconfig/zconf.tab.c_shipped b/trunk/scripts/kconfig/zconf.tab.c_shipped
index d22d92496f25..95df833b5a9d 100644
--- a/trunk/scripts/kconfig/zconf.tab.c_shipped
+++ b/trunk/scripts/kconfig/zconf.tab.c_shipped
@@ -446,16 +446,16 @@ union yyalloc
 /* YYFINAL -- State number of the termination state.  */
 #define YYFINAL  3
 /* YYLAST -- Last index in YYTABLE.  */
-#define YYLAST   258
+#define YYLAST   259
 
 /* YYNTOKENS -- Number of terminals.  */
 #define YYNTOKENS  35
 /* YYNNTS -- Number of nonterminals.  */
-#define YYNNTS  45
+#define YYNNTS  46
 /* YYNRULES -- Number of rules.  */
-#define YYNRULES  108
+#define YYNRULES  110
 /* YYNRULES -- Number of states.  */
-#define YYNSTATES  178
+#define YYNSTATES  180
 
 /* YYTRANSLATE(YYLEX) -- Bison symbol number corresponding to YYLEX.  */
 #define YYUNDEFTOK  2
@@ -507,13 +507,14 @@ static const yytype_uint16 yyprhs[] =
       28,    33,    37,    39,    41,    43,    45,    47,    49,    51,
       53,    55,    57,    59,    61,    63,    67,    70,    74,    77,
       81,    84,    85,    88,    91,    94,    97,   100,   103,   107,
-     112,   117,   122,   128,   132,   133,   137,   138,   141,   144,
-     147,   149,   153,   154,   157,   160,   163,   166,   169,   174,
-     178,   181,   186,   187,   190,   194,   196,   200,   201,   204,
-     207,   210,   214,   217,   219,   223,   224,   227,   230,   233,
-     237,   241,   244,   247,   250,   251,   254,   257,   260,   265,
-     266,   269,   271,   273,   276,   279,   282,   284,   287,   288,
-     291,   293,   297,   301,   305,   308,   312,   316,   318
+     112,   117,   122,   128,   132,   133,   137,   138,   141,   145,
+     148,   150,   154,   155,   158,   161,   164,   167,   170,   175,
+     179,   182,   187,   188,   191,   195,   197,   201,   202,   205,
+     208,   211,   215,   218,   220,   224,   225,   228,   231,   234,
+     238,   242,   245,   248,   251,   252,   255,   258,   261,   266,
+     267,   270,   272,   274,   277,   280,   283,   285,   288,   289,
+     292,   294,   298,   302,   306,   309,   313,   317,   319,   321,
+     322
 };
 
 /* YYRHS -- A `-1'-separated list of the rules' RHS.  */
@@ -533,24 +534,25 @@ static const yytype_int8 yyrhs[] =
       30,    -1,    20,    78,    77,    30,    -1,    21,    25,    77,
       30,    -1,    22,    79,    79,    77,    30,    -1,    23,    48,
       30,    -1,    -1,    48,    25,    49,    -1,    -1,    33,    74,
-      -1,     7,    30,    -1,    50,    54,    -1,    75,    -1,    51,
-      56,    52,    -1,    -1,    54,    55,    -1,    54,    72,    -1,
-      54,    70,    -1,    54,    30,    -1,    54,    40,    -1,    18,
-      74,    77,    30,    -1,    19,    73,    30,    -1,    17,    30,
-      -1,    20,    25,    77,    30,    -1,    -1,    56,    39,    -1,
-      14,    78,    76,    -1,    75,    -1,    57,    60,    58,    -1,
-      -1,    60,    39,    -1,    60,    64,    -1,    60,    53,    -1,
-       4,    74,    30,    -1,    61,    71,    -1,    75,    -1,    62,
-      65,    63,    -1,    -1,    65,    39,    -1,    65,    64,    -1,
-      65,    53,    -1,     6,    74,    30,    -1,     9,    74,    30,
-      -1,    67,    71,    -1,    12,    30,    -1,    69,    13,    -1,
-      -1,    71,    72,    -1,    71,    30,    -1,    71,    40,    -1,
-      16,    24,    78,    30,    -1,    -1,    74,    77,    -1,    25,
-      -1,    26,    -1,     5,    30,    -1,     8,    30,    -1,    15,
-      30,    -1,    30,    -1,    76,    30,    -1,    -1,    14,    78,
-      -1,    79,    -1,    79,    33,    79,    -1,    79,    27,    79,
-      -1,    29,    78,    28,    -1,    34,    78,    -1,    78,    31,
-      78,    -1,    78,    32,    78,    -1,    25,    -1,    26,    -1
+      -1,     7,    80,    30,    -1,    50,    54,    -1,    75,    -1,
+      51,    56,    52,    -1,    -1,    54,    55,    -1,    54,    72,
+      -1,    54,    70,    -1,    54,    30,    -1,    54,    40,    -1,
+      18,    74,    77,    30,    -1,    19,    73,    30,    -1,    17,
+      30,    -1,    20,    25,    77,    30,    -1,    -1,    56,    39,
+      -1,    14,    78,    76,    -1,    75,    -1,    57,    60,    58,
+      -1,    -1,    60,    39,    -1,    60,    64,    -1,    60,    53,
+      -1,     4,    74,    30,    -1,    61,    71,    -1,    75,    -1,
+      62,    65,    63,    -1,    -1,    65,    39,    -1,    65,    64,
+      -1,    65,    53,    -1,     6,    74,    30,    -1,     9,    74,
+      30,    -1,    67,    71,    -1,    12,    30,    -1,    69,    13,
+      -1,    -1,    71,    72,    -1,    71,    30,    -1,    71,    40,
+      -1,    16,    24,    78,    30,    -1,    -1,    74,    77,    -1,
+      25,    -1,    26,    -1,     5,    30,    -1,     8,    30,    -1,
+      15,    30,    -1,    30,    -1,    76,    30,    -1,    -1,    14,
+      78,    -1,    79,    -1,    79,    33,    79,    -1,    79,    27,
+      79,    -1,    29,    78,    28,    -1,    34,    78,    -1,    78,
+      31,    78,    -1,    78,    32,    78,    -1,    25,    -1,    26,
+      -1,    -1,    25,    -1
 };
 
 /* YYRLINE[YYN] -- source line where rule number YYN was defined.  */
@@ -566,7 +568,8 @@ static const yytype_uint16 yyrline[] =
      339,   344,   351,   356,   364,   367,   369,   370,   371,   374,
      382,   389,   396,   402,   409,   411,   412,   413,   416,   424,
      426,   431,   432,   435,   436,   437,   441,   442,   445,   446,
-     449,   450,   451,   452,   453,   454,   455,   458,   459
+     449,   450,   451,   452,   453,   454,   455,   458,   459,   462,
+     463
 };
 #endif
 
@@ -590,7 +593,8 @@ static const char *const yytname[] =
   "if_entry", "if_end", "if_stmt", "if_block", "menu", "menu_entry",
   "menu_end", "menu_stmt", "menu_block", "source_stmt", "comment",
   "comment_stmt", "help_start", "help", "depends_list", "depends",
-  "prompt_stmt_opt", "prompt", "end", "nl", "if_expr", "expr", "symbol", 0
+  "prompt_stmt_opt", "prompt", "end", "nl", "if_expr", "expr", "symbol",
+  "word_opt", 0
 };
 #endif
 
@@ -619,7 +623,8 @@ static const yytype_uint8 yyr1[] =
       60,    61,    62,    63,    64,    65,    65,    65,    65,    66,
       67,    68,    69,    70,    71,    71,    71,    71,    72,    73,
       73,    74,    74,    75,    75,    75,    76,    76,    77,    77,
-      78,    78,    78,    78,    78,    78,    78,    79,    79
+      78,    78,    78,    78,    78,    78,    78,    79,    79,    80,
+      80
 };
 
 /* YYR2[YYN] -- Number of symbols composing right hand side of rule YYN.  */
@@ -629,13 +634,14 @@ static const yytype_uint8 yyr2[] =
        4,     3,     1,     1,     1,     1,     1,     1,     1,     1,
        1,     1,     1,     1,     1,     3,     2,     3,     2,     3,
        2,     0,     2,     2,     2,     2,     2,     2,     3,     4,
-       4,     4,     5,     3,     0,     3,     0,     2,     2,     2,
+       4,     4,     5,     3,     0,     3,     0,     2,     3,     2,
        1,     3,     0,     2,     2,     2,     2,     2,     4,     3,
        2,     4,     0,     2,     3,     1,     3,     0,     2,     2,
        2,     3,     2,     1,     3,     0,     2,     2,     2,     3,
        3,     2,     2,     2,     0,     2,     2,     2,     4,     0,
        2,     1,     1,     2,     2,     2,     1,     2,     0,     2,
-       1,     3,     3,     3,     2,     3,     3,     1,     1
+       1,     3,     3,     3,     2,     3,     3,     1,     1,     0,
+       1
 };
 
 /* YYDEFACT[STATE-NAME] -- Default rule to reduce with in state
@@ -643,69 +649,69 @@ static const yytype_uint8 yyr2[] =
    means the default is an error.  */
 static const yytype_uint8 yydefact[] =
 {
-       3,     0,     0,     1,     0,     0,     0,     0,     0,     0,
+       3,     0,     0,     1,     0,     0,     0,     0,     0,   109,
        0,     0,     0,     0,     0,     0,    12,    16,    13,    14,
       18,    15,    17,     0,    19,     0,     4,    31,    22,    31,
       23,    52,    62,     5,    67,    20,    84,    75,     6,    24,
       84,    21,     8,    11,    91,    92,     0,     0,    93,     0,
-      48,    94,     0,     0,     0,   107,   108,     0,     0,     0,
-     100,    95,     0,     0,     0,     0,     0,     0,     0,     0,
-       0,     0,    96,     7,    71,    79,    80,    27,    29,     0,
-     104,     0,     0,    64,     0,     0,     9,    10,     0,     0,
-       0,     0,    89,     0,     0,     0,    44,     0,    37,    36,
-      32,    33,     0,    35,    34,     0,     0,    89,     0,    56,
-      57,    53,    55,    54,    63,    51,    50,    68,    70,    66,
-      69,    65,    86,    87,    85,    76,    78,    74,    77,    73,
-      97,   103,   105,   106,   102,   101,    26,    82,     0,    98,
-       0,    98,    98,    98,     0,     0,     0,    83,    60,    98,
-       0,    98,     0,     0,     0,    38,    90,     0,     0,    98,
-      46,    43,    25,     0,    59,     0,    88,    99,    39,    40,
-      41,     0,     0,    45,    58,    61,    42,    47
+     110,     0,    94,     0,     0,     0,   107,   108,     0,     0,
+       0,   100,    95,     0,     0,     0,     0,     0,     0,     0,
+       0,     0,     0,    96,     7,    71,    79,    48,    80,    27,
+      29,     0,   104,     0,     0,    64,     0,     0,     9,    10,
+       0,     0,     0,     0,    89,     0,     0,     0,    44,     0,
+      37,    36,    32,    33,     0,    35,    34,     0,     0,    89,
+       0,    56,    57,    53,    55,    54,    63,    51,    50,    68,
+      70,    66,    69,    65,    86,    87,    85,    76,    78,    74,
+      77,    73,    97,   103,   105,   106,   102,   101,    26,    82,
+       0,    98,     0,    98,    98,    98,     0,     0,     0,    83,
+      60,    98,     0,    98,     0,     0,     0,    38,    90,     0,
+       0,    98,    46,    43,    25,     0,    59,     0,    88,    99,
+      39,    40,    41,     0,     0,    45,    58,    61,    42,    47
 };
 
 /* YYDEFGOTO[NTERM-NUM].  */
 static const yytype_int16 yydefgoto[] =
 {
-      -1,     1,     2,    25,    26,    99,    27,    28,    29,    30,
-      64,   100,   101,   145,   173,    31,    32,   115,    33,    66,
-     111,    67,    34,   119,    35,    68,    36,    37,   127,    38,
-      70,    39,    40,    41,   102,   103,    69,   104,   140,   141,
-      42,    73,   154,    59,    60
+      -1,     1,     2,    25,    26,   101,    27,    28,    29,    30,
+      65,   102,   103,   147,   175,    31,    32,   117,    33,    67,
+     113,    68,    34,   121,    35,    69,    36,    37,   129,    38,
+      71,    39,    40,    41,   104,   105,    70,   106,   142,   143,
+      42,    74,   156,    60,    61,    51
 };
 
 /* YYPACT[STATE-NUM] -- Index in YYTABLE of the portion describing
    STATE-NUM.  */
-#define YYPACT_NINF -78
+#define YYPACT_NINF -80
 static const yytype_int16 yypact[] =
 {
-     -78,    33,   130,   -78,   -28,    73,    73,     7,    73,    36,
-      41,    73,    26,    52,    -4,    58,   -78,   -78,   -78,   -78,
-     -78,   -78,   -78,    90,   -78,    94,   -78,   -78,   -78,   -78,
-     -78,   -78,   -78,   -78,   -78,   -78,   -78,   -78,   -78,   -78,
-     -78,   -78,   -78,   -78,   -78,   -78,    74,    85,   -78,    96,
-     -78,   -78,   131,   134,   147,   -78,   -78,    -4,    -4,   193,
-     -10,   -78,   162,   164,    38,   102,    64,   148,     5,   192,
-       5,   165,   -78,   174,   -78,   -78,   -78,   -78,   -78,    65,
-     -78,    -4,    -4,   174,   103,   103,   -78,   -78,   175,   185,
-     197,    73,    73,    -4,   194,   103,   -78,   231,   -78,   -78,
-     -78,   -78,   220,   -78,   -78,   204,    73,    73,   210,   -78,
-     -78,   -78,   -78,   -78,   -78,   -78,   -78,   -78,   -78,   -78,
-     -78,   -78,   -78,   -78,   -78,   -78,   -78,   -78,   -78,   -78,
-     -78,   -78,   205,   -78,   -78,   -78,   -78,   -78,    -4,   222,
-     208,   222,   195,   222,   103,     2,   209,   -78,   -78,   222,
-     211,   222,   199,    -4,   212,   -78,   -78,   213,   214,   222,
-     207,   -78,   -78,   215,   -78,   216,   -78,   111,   -78,   -78,
-     -78,   217,    73,   -78,   -78,   -78,   -78,   -78
+     -80,     2,   132,   -80,   -13,    -1,    -1,    -2,    -1,     9,
+      33,    -1,    27,    40,    -3,    38,   -80,   -80,   -80,   -80,
+     -80,   -80,   -80,    71,   -80,    77,   -80,   -80,   -80,   -80,
+     -80,   -80,   -80,   -80,   -80,   -80,   -80,   -80,   -80,   -80,
+     -80,   -80,   -80,   -80,   -80,   -80,    57,    61,   -80,    63,
+     -80,    76,   -80,    87,   101,   133,   -80,   -80,    -3,    -3,
+     195,    -6,   -80,   136,   149,    39,   104,    65,   150,     5,
+     194,     5,   167,   -80,   176,   -80,   -80,   -80,   -80,   -80,
+     -80,    68,   -80,    -3,    -3,   176,    72,    72,   -80,   -80,
+     177,   187,    78,    -1,    -1,    -3,   196,    72,   -80,   222,
+     -80,   -80,   -80,   -80,   221,   -80,   -80,   205,    -1,    -1,
+     211,   -80,   -80,   -80,   -80,   -80,   -80,   -80,   -80,   -80,
+     -80,   -80,   -80,   -80,   -80,   -80,   -80,   -80,   -80,   -80,
+     -80,   -80,   -80,   -80,   206,   -80,   -80,   -80,   -80,   -80,
+      -3,   223,   209,   223,   197,   223,    72,     7,   210,   -80,
+     -80,   223,   212,   223,   201,    -3,   213,   -80,   -80,   214,
+     215,   223,   208,   -80,   -80,   216,   -80,   217,   -80,   113,
+     -80,   -80,   -80,   218,    -1,   -80,   -80,   -80,   -80,   -80
 };
 
 /* YYPGOTO[NTERM-NUM].  */
 static const yytype_int16 yypgoto[] =
 {
-     -78,   -78,   -78,   -78,   121,   -35,   -78,   -78,   -78,   -78,
-     219,   -78,   -78,   -78,   -78,   -78,   -78,   -78,   -44,   -78,
-     -78,   -78,   -78,   -78,   -78,   -78,   -78,   -78,   -78,    -6,
-     -78,   -78,   -78,   -78,   -78,   183,   218,    21,   143,    -5,
-     146,   196,    69,   -53,   -77
+     -80,   -80,   -80,   -80,   122,   -34,   -80,   -80,   -80,   -80,
+     220,   -80,   -80,   -80,   -80,   -80,   -80,   -80,    59,   -80,
+     -80,   -80,   -80,   -80,   -80,   -80,   -80,   -80,   -80,   125,
+     -80,   -80,   -80,   -80,   -80,   183,   219,    22,   142,    -5,
+     147,   192,    69,   -54,   -79,   -80
 };
 
 /* YYTABLE[YYPACT[STATE-NUM]].  What to do in state STATE-NUM.  If
@@ -715,62 +721,62 @@ static const yytype_int16 yypgoto[] =
 #define YYTABLE_NINF -82
 static const yytype_int16 yytable[] =
 {
-      46,    47,    43,    49,    79,    80,    52,   134,   135,     6,
-       7,     8,     9,    10,    11,    12,    13,    84,   144,    14,
-      15,    55,    56,    85,   118,    57,   126,   160,   132,   133,
-      58,   110,   161,     3,   123,    24,   123,    48,   -28,    88,
-     142,   -28,   -28,   -28,   -28,   -28,   -28,   -28,   -28,   -28,
-      89,    53,   -28,   -28,    90,   -28,    91,    92,    93,    94,
-      95,    96,   120,    97,   128,    88,    50,   159,    98,   -49,
-     -49,    51,   -49,   -49,   -49,   -49,    89,    54,   -49,   -49,
-      90,   105,   106,   107,   108,   152,   139,   113,    61,    97,
-     124,    62,   124,   131,   109,    63,    81,    82,    44,    45,
-     167,   149,   -30,    88,    72,   -30,   -30,   -30,   -30,   -30,
-     -30,   -30,   -30,   -30,    89,    74,   -30,   -30,    90,   -30,
-      91,    92,    93,    94,    95,    96,    75,    97,    55,    56,
-      -2,     4,    98,     5,     6,     7,     8,     9,    10,    11,
-      12,    13,    81,    82,    14,    15,    16,    17,    18,    19,
-      20,    21,    22,     7,     8,    23,    10,    11,    12,    13,
-      24,    76,    14,    15,    77,   -81,    88,   177,   -81,   -81,
-     -81,   -81,   -81,   -81,   -81,   -81,   -81,    78,    24,   -81,
-     -81,    90,   -81,   -81,   -81,   -81,   -81,   -81,   114,   117,
-      97,   125,    86,    88,    87,   122,   -72,   -72,   -72,   -72,
-     -72,   -72,   -72,   -72,   130,   136,   -72,   -72,    90,   153,
-     156,   157,   158,   116,   121,   137,   129,    97,   163,   143,
-     165,   138,   122,    72,    81,    82,    81,    82,   171,   166,
-      81,    82,   146,   147,   148,   151,   153,    82,   155,   162,
-     172,   164,   168,   169,   170,   174,   175,   176,    65,   112,
-     150,     0,     0,     0,     0,    83,     0,     0,    71
+      46,    47,     3,    49,    81,    82,    53,   136,   137,     6,
+       7,     8,     9,    10,    11,    12,    13,    43,   146,    14,
+      15,    86,    56,    57,    44,    45,    58,    87,    48,   134,
+     135,    59,   162,   112,    50,    24,   125,   163,   125,   -28,
+      90,   144,   -28,   -28,   -28,   -28,   -28,   -28,   -28,   -28,
+     -28,    91,    54,   -28,   -28,    92,   -28,    93,    94,    95,
+      96,    97,    98,    52,    99,    55,    90,   161,    62,   100,
+     -49,   -49,    63,   -49,   -49,   -49,   -49,    91,    64,   -49,
+     -49,    92,   107,   108,   109,   110,   154,    73,   141,   115,
+      99,    75,   126,    76,   126,   111,   133,    56,    57,    83,
+      84,   169,   140,   151,   -30,    90,    77,   -30,   -30,   -30,
+     -30,   -30,   -30,   -30,   -30,   -30,    91,    78,   -30,   -30,
+      92,   -30,    93,    94,    95,    96,    97,    98,   120,    99,
+     128,    79,    -2,     4,   100,     5,     6,     7,     8,     9,
+      10,    11,    12,    13,    83,    84,    14,    15,    16,    17,
+      18,    19,    20,    21,    22,     7,     8,    23,    10,    11,
+      12,    13,    24,    80,    14,    15,    88,   -81,    90,   179,
+     -81,   -81,   -81,   -81,   -81,   -81,   -81,   -81,   -81,    89,
+      24,   -81,   -81,    92,   -81,   -81,   -81,   -81,   -81,   -81,
+     116,   119,    99,   127,   122,    90,   130,   124,   -72,   -72,
+     -72,   -72,   -72,   -72,   -72,   -72,   132,   138,   -72,   -72,
+      92,   155,   158,   159,   160,   118,   123,   139,   131,    99,
+     165,   145,   167,   148,   124,    73,    83,    84,    83,    84,
+     173,   168,    83,    84,   149,   150,   153,   155,    84,   157,
+     164,   174,   166,   170,   171,   172,   176,   177,   178,    66,
+     114,   152,    85,     0,     0,     0,     0,     0,     0,    72
 };
 
 static const yytype_int16 yycheck[] =
 {
-       5,     6,    30,     8,    57,    58,    11,    84,    85,     4,
-       5,     6,     7,     8,     9,    10,    11,    27,    95,    14,
-      15,    25,    26,    33,    68,    29,    70,    25,    81,    82,
-      34,    66,    30,     0,    69,    30,    71,    30,     0,     1,
-      93,     3,     4,     5,     6,     7,     8,     9,    10,    11,
-      12,    25,    14,    15,    16,    17,    18,    19,    20,    21,
-      22,    23,    68,    25,    70,     1,    30,   144,    30,     5,
-       6,    30,     8,     9,    10,    11,    12,    25,    14,    15,
-      16,    17,    18,    19,    20,   138,    91,    66,    30,    25,
-      69,     1,    71,    28,    30,     1,    31,    32,    25,    26,
-     153,   106,     0,     1,    30,     3,     4,     5,     6,     7,
-       8,     9,    10,    11,    12,    30,    14,    15,    16,    17,
-      18,    19,    20,    21,    22,    23,    30,    25,    25,    26,
-       0,     1,    30,     3,     4,     5,     6,     7,     8,     9,
-      10,    11,    31,    32,    14,    15,    16,    17,    18,    19,
-      20,    21,    22,     5,     6,    25,     8,     9,    10,    11,
-      30,    30,    14,    15,    30,     0,     1,   172,     3,     4,
-       5,     6,     7,     8,     9,    10,    11,    30,    30,    14,
-      15,    16,    17,    18,    19,    20,    21,    22,    67,    68,
-      25,    70,    30,     1,    30,    30,     4,     5,     6,     7,
-       8,     9,    10,    11,    30,    30,    14,    15,    16,    14,
-     141,   142,   143,    67,    68,    30,    70,    25,   149,    25,
-     151,    24,    30,    30,    31,    32,    31,    32,   159,    30,
-      31,    32,     1,    13,    30,    25,    14,    32,    30,    30,
-      33,    30,    30,    30,    30,    30,    30,    30,    29,    66,
-     107,    -1,    -1,    -1,    -1,    59,    -1,    -1,    40
+       5,     6,     0,     8,    58,    59,    11,    86,    87,     4,
+       5,     6,     7,     8,     9,    10,    11,    30,    97,    14,
+      15,    27,    25,    26,    25,    26,    29,    33,    30,    83,
+      84,    34,    25,    67,    25,    30,    70,    30,    72,     0,
+       1,    95,     3,     4,     5,     6,     7,     8,     9,    10,
+      11,    12,    25,    14,    15,    16,    17,    18,    19,    20,
+      21,    22,    23,    30,    25,    25,     1,   146,    30,    30,
+       5,     6,     1,     8,     9,    10,    11,    12,     1,    14,
+      15,    16,    17,    18,    19,    20,   140,    30,    93,    67,
+      25,    30,    70,    30,    72,    30,    28,    25,    26,    31,
+      32,   155,    24,   108,     0,     1,    30,     3,     4,     5,
+       6,     7,     8,     9,    10,    11,    12,    30,    14,    15,
+      16,    17,    18,    19,    20,    21,    22,    23,    69,    25,
+      71,    30,     0,     1,    30,     3,     4,     5,     6,     7,
+       8,     9,    10,    11,    31,    32,    14,    15,    16,    17,
+      18,    19,    20,    21,    22,     5,     6,    25,     8,     9,
+      10,    11,    30,    30,    14,    15,    30,     0,     1,   174,
+       3,     4,     5,     6,     7,     8,     9,    10,    11,    30,
+      30,    14,    15,    16,    17,    18,    19,    20,    21,    22,
+      68,    69,    25,    71,    69,     1,    71,    30,     4,     5,
+       6,     7,     8,     9,    10,    11,    30,    30,    14,    15,
+      16,    14,   143,   144,   145,    68,    69,    30,    71,    25,
+     151,    25,   153,     1,    30,    30,    31,    32,    31,    32,
+     161,    30,    31,    32,    13,    30,    25,    14,    32,    30,
+      30,    33,    30,    30,    30,    30,    30,    30,    30,    29,
+      67,   109,    60,    -1,    -1,    -1,    -1,    -1,    -1,    40
 };
 
 /* YYSTOS[STATE-NUM] -- The (internal number of the) accessing
@@ -782,19 +788,19 @@ static const yytype_uint8 yystos[] =
       20,    21,    22,    25,    30,    38,    39,    41,    42,    43,
       44,    50,    51,    53,    57,    59,    61,    62,    64,    66,
       67,    68,    75,    30,    25,    26,    74,    74,    30,    74,
-      30,    30,    74,    25,    25,    25,    26,    29,    34,    78,
-      79,    30,     1,     1,    45,    45,    54,    56,    60,    71,
-      65,    71,    30,    76,    30,    30,    30,    30,    30,    78,
-      78,    31,    32,    76,    27,    33,    30,    30,     1,    12,
-      16,    18,    19,    20,    21,    22,    23,    25,    30,    40,
-      46,    47,    69,    70,    72,    17,    18,    19,    20,    30,
-      40,    55,    70,    72,    39,    52,    75,    39,    53,    58,
-      64,    75,    30,    40,    72,    39,    53,    63,    64,    75,
-      30,    28,    78,    78,    79,    79,    30,    30,    24,    74,
-      73,    74,    78,    25,    79,    48,     1,    13,    30,    74,
-      73,    25,    78,    14,    77,    30,    77,    77,    77,    79,
-      25,    30,    30,    77,    30,    77,    30,    78,    30,    30,
-      30,    77,    33,    49,    30,    30,    30,    74
+      25,    80,    30,    74,    25,    25,    25,    26,    29,    34,
+      78,    79,    30,     1,     1,    45,    45,    54,    56,    60,
+      71,    65,    71,    30,    76,    30,    30,    30,    30,    30,
+      30,    78,    78,    31,    32,    76,    27,    33,    30,    30,
+       1,    12,    16,    18,    19,    20,    21,    22,    23,    25,
+      30,    40,    46,    47,    69,    70,    72,    17,    18,    19,
+      20,    30,    40,    55,    70,    72,    39,    52,    75,    39,
+      53,    58,    64,    75,    30,    40,    72,    39,    53,    63,
+      64,    75,    30,    28,    78,    78,    79,    79,    30,    30,
+      24,    74,    73,    74,    78,    25,    79,    48,     1,    13,
+      30,    74,    73,    25,    78,    14,    77,    30,    77,    77,
+      77,    79,    25,    30,    30,    77,    30,    77,    30,    78,
+      30,    30,    30,    77,    33,    49,    30,    30,    30,    74
 };
 
 #define yyerrok		(yyerrstatus = 0)
@@ -1781,8 +1787,8 @@ yyreduce:
   case 48:
 
     {
-	struct symbol *sym = sym_lookup(NULL, 0);
-	sym->flags |= SYMBOL_CHOICE;
+	struct symbol *sym = sym_lookup((yyvsp[(2) - (3)].string), SYMBOL_CHOICE);
+	sym->flags |= SYMBOL_AUTO;
 	menu_add_entry(sym);
 	menu_add_expr(P_CHOICE, NULL, NULL);
 	printd(DEBUG_PARSE, "%s:%d:choice\n", zconf_curname(), zconf_lineno());
@@ -2014,7 +2020,12 @@ yyreduce:
 
   case 108:
 
-    { (yyval.symbol) = sym_lookup((yyvsp[(1) - (1)].string), 1); free((yyvsp[(1) - (1)].string)); ;}
+    { (yyval.symbol) = sym_lookup((yyvsp[(1) - (1)].string), SYMBOL_CONST); free((yyvsp[(1) - (1)].string)); ;}
+    break;
+
+  case 109:
+
+    { (yyval.string) = NULL; ;}
     break;
 
 
diff --git a/trunk/scripts/kconfig/zconf.y b/trunk/scripts/kconfig/zconf.y
index d9b96ba8e38c..9710b82466f2 100644
--- a/trunk/scripts/kconfig/zconf.y
+++ b/trunk/scripts/kconfig/zconf.y
@@ -91,7 +91,7 @@ static struct menu *current_menu, *current_entry;
 %type <id> end
 %type <id> option_name
 %type <menu> if_entry menu_entry choice_entry
-%type <string> symbol_option_arg
+%type <string> symbol_option_arg word_opt
 
 %destructor {
 	fprintf(stderr, "%s:%d: missing end statement for this entry\n",
@@ -239,10 +239,10 @@ symbol_option_arg:
 
 /* choice entry */
 
-choice: T_CHOICE T_EOL
+choice: T_CHOICE word_opt T_EOL
 {
-	struct symbol *sym = sym_lookup(NULL, 0);
-	sym->flags |= SYMBOL_CHOICE;
+	struct symbol *sym = sym_lookup($2, SYMBOL_CHOICE);
+	sym->flags |= SYMBOL_AUTO;
 	menu_add_entry(sym);
 	menu_add_expr(P_CHOICE, NULL, NULL);
 	printd(DEBUG_PARSE, "%s:%d:choice\n", zconf_curname(), zconf_lineno());
@@ -456,9 +456,12 @@ expr:	  symbol				{ $$ = expr_alloc_symbol($1); }
 ;
 
 symbol:	  T_WORD	{ $$ = sym_lookup($1, 0); free($1); }
-	| T_WORD_QUOTE	{ $$ = sym_lookup($1, 1); free($1); }
+	| T_WORD_QUOTE	{ $$ = sym_lookup($1, SYMBOL_CONST); free($1); }
 ;
 
+word_opt: /* empty */			{ $$ = NULL; }
+	| T_WORD
+
 %%
 
 void conf_parse(const char *name)
diff --git a/trunk/scripts/kernel-doc b/trunk/scripts/kernel-doc
index 263d04ab2d94..83cee18a02e9 100755
--- a/trunk/scripts/kernel-doc
+++ b/trunk/scripts/kernel-doc
@@ -5,7 +5,7 @@ use strict;
 ## Copyright (c) 1998 Michael Zucchi, All Rights Reserved        ##
 ## Copyright (C) 2000, 1  Tim Waugh <twaugh@redhat.com>          ##
 ## Copyright (C) 2001  Simon Huggins                             ##
-## Copyright (C) 2005-2007  Randy Dunlap                         ##
+## Copyright (C) 2005-2008  Randy Dunlap                         ##
 ## 								 ##
 ## #define enhancements by Armin Kuster <akuster@mvista.com>	 ##
 ## Copyright (c) 2000 MontaVista Software, Inc.			 ##
@@ -366,6 +366,7 @@ foreach my $pattern (keys %highlights) {
 # dumps section contents to arrays/hashes intended for that purpose.
 #
 sub dump_section {
+    my $file = shift;
     my $name = shift;
     my $contents = join "\n", @_;
 
@@ -379,6 +380,10 @@ sub dump_section {
 	$parameterdescs{$name} = $contents;
     } else {
 #	print STDERR "other section '$name' = '$contents'\n";
+	if (defined($sections{$name}) && ($sections{$name} ne "")) {
+		print STDERR "Error(${file}:$.): duplicate section name '$name'\n";
+		++$errors;
+	}
 	$sections{$name} = $contents;
 	push @sectionlist, $name;
     }
@@ -388,6 +393,7 @@ sub dump_section {
 # dump DOC: section after checking that it should go out
 #
 sub dump_doc_section {
+    my $file = shift;
     my $name = shift;
     my $contents = join "\n", @_;
 
@@ -399,7 +405,7 @@ sub dump_doc_section {
 	( $function_only == 1 && defined($function_table{$name})) ||
 	( $function_only == 2 && !defined($function_table{$name})))
     {
-	dump_section $name, $contents;
+	dump_section($file, $name, $contents);
 	output_blockhead({'sectionlist' => \@sectionlist,
 			  'sections' => \%sections,
 			  'module' => $modulename,
@@ -1923,7 +1929,7 @@ sub process_file($) {
 			print STDERR "Warning(${file}:$.): contents before sections\n";
 			++$warnings;
 		    }
-		    dump_section($section, xml_escape($contents));
+		    dump_section($file, $section, xml_escape($contents));
 		    $section = $section_default;
 		}
 
@@ -1940,10 +1946,15 @@ sub process_file($) {
 	    } elsif (/$doc_end/) {
 
 		if ($contents ne "") {
-		    dump_section($section, xml_escape($contents));
+		    dump_section($file, $section, xml_escape($contents));
 		    $section = $section_default;
 		    $contents = "";
 		}
+		# look for doc_com + <text> + doc_end:
+		if ($_ =~ m'\s*\*\s*[a-zA-Z_0-9:\.]+\*/') {
+		    print STDERR "Warning(${file}:$.): suspicious ending line: $_";
+		    ++$warnings;
+		}
 
 		$prototype = "";
 		$state = 3;
@@ -1954,7 +1965,7 @@ sub process_file($) {
 		# @parameter line to signify start of description
 		if ($1 eq "" &&
 			($section =~ m/^@/ || $section eq $section_context)) {
-		    dump_section($section, xml_escape($contents));
+		    dump_section($file, $section, xml_escape($contents));
 		    $section = $section_default;
 		    $contents = "";
 		} else {
@@ -1974,7 +1985,7 @@ sub process_file($) {
 	} elsif ($state == 4) {
 		# Documentation block
 		if (/$doc_block/) {
-			dump_doc_section($section, xml_escape($contents));
+			dump_doc_section($file, $section, xml_escape($contents));
 			$contents = "";
 			$function = "";
 			%constants = ();
@@ -1992,7 +2003,7 @@ sub process_file($) {
 		}
 		elsif (/$doc_end/)
 		{
-			dump_doc_section($section, xml_escape($contents));
+			dump_doc_section($file, $section, xml_escape($contents));
 			$contents = "";
 			$function = "";
 			%constants = ();
diff --git a/trunk/security/Makefile b/trunk/security/Makefile
index 9e8b02525014..7ef1107a7287 100644
--- a/trunk/security/Makefile
+++ b/trunk/security/Makefile
@@ -18,3 +18,4 @@ obj-$(CONFIG_SECURITY_SELINUX)		+= selinux/built-in.o
 obj-$(CONFIG_SECURITY_SMACK)		+= commoncap.o smack/built-in.o
 obj-$(CONFIG_SECURITY_CAPABILITIES)	+= commoncap.o capability.o
 obj-$(CONFIG_SECURITY_ROOTPLUG)		+= commoncap.o root_plug.o
+obj-$(CONFIG_CGROUP_DEVICE)		+= device_cgroup.o
diff --git a/trunk/security/capability.c b/trunk/security/capability.c
index 2c6e06d18fab..38ac54e3aed1 100644
--- a/trunk/security/capability.c
+++ b/trunk/security/capability.c
@@ -44,6 +44,7 @@ static struct security_operations capability_ops = {
 	.task_setioprio =		cap_task_setioprio,
 	.task_setnice =			cap_task_setnice,
 	.task_post_setuid =		cap_task_post_setuid,
+	.task_prctl =                   cap_task_prctl,
 	.task_reparent_to_init =	cap_task_reparent_to_init,
 
 	.syslog =                       cap_syslog,
diff --git a/trunk/security/commoncap.c b/trunk/security/commoncap.c
index 852905789caf..5edabc7542ae 100644
--- a/trunk/security/commoncap.c
+++ b/trunk/security/commoncap.c
@@ -24,11 +24,8 @@
 #include <linux/hugetlb.h>
 #include <linux/mount.h>
 #include <linux/sched.h>
-
-/* Global security state */
-
-unsigned securebits = SECUREBITS_DEFAULT; /* systemwide security settings */
-EXPORT_SYMBOL(securebits);
+#include <linux/prctl.h>
+#include <linux/securebits.h>
 
 int cap_netlink_send(struct sock *sk, struct sk_buff *skb)
 {
@@ -368,7 +365,7 @@ void cap_bprm_apply_creds (struct linux_binprm *bprm, int unsafe)
 
 	/* AUD: Audit candidate if current->cap_effective is set */
 
-	current->keep_capabilities = 0;
+	current->securebits &= ~issecure_mask(SECURE_KEEP_CAPS);
 }
 
 int cap_bprm_secureexec (struct linux_binprm *bprm)
@@ -386,8 +383,8 @@ int cap_bprm_secureexec (struct linux_binprm *bprm)
 		current->egid != current->gid);
 }
 
-int cap_inode_setxattr(struct dentry *dentry, char *name, void *value,
-		       size_t size, int flags)
+int cap_inode_setxattr(struct dentry *dentry, const char *name,
+		       const void *value, size_t size, int flags)
 {
 	if (!strcmp(name, XATTR_NAME_CAPS)) {
 		if (!capable(CAP_SETFCAP))
@@ -400,7 +397,7 @@ int cap_inode_setxattr(struct dentry *dentry, char *name, void *value,
 	return 0;
 }
 
-int cap_inode_removexattr(struct dentry *dentry, char *name)
+int cap_inode_removexattr(struct dentry *dentry, const char *name)
 {
 	if (!strcmp(name, XATTR_NAME_CAPS)) {
 		if (!capable(CAP_SETFCAP))
@@ -448,7 +445,7 @@ static inline void cap_emulate_setxuid (int old_ruid, int old_euid,
 {
 	if ((old_ruid == 0 || old_euid == 0 || old_suid == 0) &&
 	    (current->uid != 0 && current->euid != 0 && current->suid != 0) &&
-	    !current->keep_capabilities) {
+	    !issecure(SECURE_KEEP_CAPS)) {
 		cap_clear (current->cap_permitted);
 		cap_clear (current->cap_effective);
 	}
@@ -547,7 +544,7 @@ int cap_task_setnice (struct task_struct *p, int nice)
  * this task could get inconsistent info.  There can be no
  * racing writer bc a task can only change its own caps.
  */
-long cap_prctl_drop(unsigned long cap)
+static long cap_prctl_drop(unsigned long cap)
 {
 	if (!capable(CAP_SETPCAP))
 		return -EPERM;
@@ -556,6 +553,7 @@ long cap_prctl_drop(unsigned long cap)
 	cap_lower(current->cap_bset, cap);
 	return 0;
 }
+
 #else
 int cap_task_setscheduler (struct task_struct *p, int policy,
 			   struct sched_param *lp)
@@ -572,12 +570,99 @@ int cap_task_setnice (struct task_struct *p, int nice)
 }
 #endif
 
+int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
+		   unsigned long arg4, unsigned long arg5, long *rc_p)
+{
+	long error = 0;
+
+	switch (option) {
+	case PR_CAPBSET_READ:
+		if (!cap_valid(arg2))
+			error = -EINVAL;
+		else
+			error = !!cap_raised(current->cap_bset, arg2);
+		break;
+#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
+	case PR_CAPBSET_DROP:
+		error = cap_prctl_drop(arg2);
+		break;
+
+	/*
+	 * The next four prctl's remain to assist with transitioning a
+	 * system from legacy UID=0 based privilege (when filesystem
+	 * capabilities are not in use) to a system using filesystem
+	 * capabilities only - as the POSIX.1e draft intended.
+	 *
+	 * Note:
+	 *
+	 *  PR_SET_SECUREBITS =
+	 *      issecure_mask(SECURE_KEEP_CAPS_LOCKED)
+	 *    | issecure_mask(SECURE_NOROOT)
+	 *    | issecure_mask(SECURE_NOROOT_LOCKED)
+	 *    | issecure_mask(SECURE_NO_SETUID_FIXUP)
+	 *    | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED)
+	 *
+	 * will ensure that the current process and all of its
+	 * children will be locked into a pure
+	 * capability-based-privilege environment.
+	 */
+	case PR_SET_SECUREBITS:
+		if ((((current->securebits & SECURE_ALL_LOCKS) >> 1)
+		     & (current->securebits ^ arg2))                  /*[1]*/
+		    || ((current->securebits & SECURE_ALL_LOCKS
+			 & ~arg2))                                    /*[2]*/
+		    || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/
+		    || (cap_capable(current, CAP_SETPCAP) != 0)) {    /*[4]*/
+			/*
+			 * [1] no changing of bits that are locked
+			 * [2] no unlocking of locks
+			 * [3] no setting of unsupported bits
+			 * [4] doing anything requires privilege (go read about
+			 *     the "sendmail capabilities bug")
+			 */
+			error = -EPERM;  /* cannot change a locked bit */
+		} else {
+			current->securebits = arg2;
+		}
+		break;
+	case PR_GET_SECUREBITS:
+		error = current->securebits;
+		break;
+
+#endif /* def CONFIG_SECURITY_FILE_CAPABILITIES */
+
+	case PR_GET_KEEPCAPS:
+		if (issecure(SECURE_KEEP_CAPS))
+			error = 1;
+		break;
+	case PR_SET_KEEPCAPS:
+		if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */
+			error = -EINVAL;
+		else if (issecure(SECURE_KEEP_CAPS_LOCKED))
+			error = -EPERM;
+		else if (arg2)
+			current->securebits |= issecure_mask(SECURE_KEEP_CAPS);
+		else
+			current->securebits &=
+				~issecure_mask(SECURE_KEEP_CAPS);
+		break;
+
+	default:
+		/* No functionality available - continue with default */
+		return 0;
+	}
+
+	/* Functionality provided */
+	*rc_p = error;
+	return 1;
+}
+
 void cap_task_reparent_to_init (struct task_struct *p)
 {
 	cap_set_init_eff(p->cap_effective);
 	cap_clear(p->cap_inheritable);
 	cap_set_full(p->cap_permitted);
-	p->keep_capabilities = 0;
+	p->securebits = SECUREBITS_DEFAULT;
 	return;
 }
 
diff --git a/trunk/security/device_cgroup.c b/trunk/security/device_cgroup.c
new file mode 100644
index 000000000000..4ea583689eec
--- /dev/null
+++ b/trunk/security/device_cgroup.c
@@ -0,0 +1,575 @@
+/*
+ * dev_cgroup.c - device cgroup subsystem
+ *
+ * Copyright 2007 IBM Corp
+ */
+
+#include <linux/device_cgroup.h>
+#include <linux/cgroup.h>
+#include <linux/ctype.h>
+#include <linux/list.h>
+#include <linux/uaccess.h>
+#include <linux/seq_file.h>
+
+#define ACC_MKNOD 1
+#define ACC_READ  2
+#define ACC_WRITE 4
+#define ACC_MASK (ACC_MKNOD | ACC_READ | ACC_WRITE)
+
+#define DEV_BLOCK 1
+#define DEV_CHAR  2
+#define DEV_ALL   4  /* this represents all devices */
+
+/*
+ * whitelist locking rules:
+ * cgroup_lock() cannot be taken under dev_cgroup->lock.
+ * dev_cgroup->lock can be taken with or without cgroup_lock().
+ *
+ * modifications always require cgroup_lock
+ * modifications to a list which is visible require the
+ *   dev_cgroup->lock *and* cgroup_lock()
+ * walking the list requires dev_cgroup->lock or cgroup_lock().
+ *
+ * reasoning: dev_whitelist_copy() needs to kmalloc, so needs
+ *   a mutex, which the cgroup_lock() is.  Since modifying
+ *   a visible list requires both locks, either lock can be
+ *   taken for walking the list.
+ */
+
+struct dev_whitelist_item {
+	u32 major, minor;
+	short type;
+	short access;
+	struct list_head list;
+};
+
+struct dev_cgroup {
+	struct cgroup_subsys_state css;
+	struct list_head whitelist;
+	spinlock_t lock;
+};
+
+static inline struct dev_cgroup *cgroup_to_devcgroup(struct cgroup *cgroup)
+{
+	return container_of(cgroup_subsys_state(cgroup, devices_subsys_id),
+			    struct dev_cgroup, css);
+}
+
+struct cgroup_subsys devices_subsys;
+
+static int devcgroup_can_attach(struct cgroup_subsys *ss,
+		struct cgroup *new_cgroup, struct task_struct *task)
+{
+	if (current != task && !capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+	return 0;
+}
+
+/*
+ * called under cgroup_lock()
+ */
+static int dev_whitelist_copy(struct list_head *dest, struct list_head *orig)
+{
+	struct dev_whitelist_item *wh, *tmp, *new;
+
+	list_for_each_entry(wh, orig, list) {
+		new = kmalloc(sizeof(*wh), GFP_KERNEL);
+		if (!new)
+			goto free_and_exit;
+		new->major = wh->major;
+		new->minor = wh->minor;
+		new->type = wh->type;
+		new->access = wh->access;
+		list_add_tail(&new->list, dest);
+	}
+
+	return 0;
+
+free_and_exit:
+	list_for_each_entry_safe(wh, tmp, dest, list) {
+		list_del(&wh->list);
+		kfree(wh);
+	}
+	return -ENOMEM;
+}
+
+/* Stupid prototype - don't bother combining existing entries */
+/*
+ * called under cgroup_lock()
+ * since the list is visible to other tasks, we need the spinlock also
+ */
+static int dev_whitelist_add(struct dev_cgroup *dev_cgroup,
+			struct dev_whitelist_item *wh)
+{
+	struct dev_whitelist_item *whcopy;
+
+	whcopy = kmalloc(sizeof(*whcopy), GFP_KERNEL);
+	if (!whcopy)
+		return -ENOMEM;
+
+	memcpy(whcopy, wh, sizeof(*whcopy));
+	spin_lock(&dev_cgroup->lock);
+	list_add_tail(&whcopy->list, &dev_cgroup->whitelist);
+	spin_unlock(&dev_cgroup->lock);
+	return 0;
+}
+
+/*
+ * called under cgroup_lock()
+ * since the list is visible to other tasks, we need the spinlock also
+ */
+static void dev_whitelist_rm(struct dev_cgroup *dev_cgroup,
+			struct dev_whitelist_item *wh)
+{
+	struct dev_whitelist_item *walk, *tmp;
+
+	spin_lock(&dev_cgroup->lock);
+	list_for_each_entry_safe(walk, tmp, &dev_cgroup->whitelist, list) {
+		if (walk->type == DEV_ALL)
+			goto remove;
+		if (walk->type != wh->type)
+			continue;
+		if (walk->major != ~0 && walk->major != wh->major)
+			continue;
+		if (walk->minor != ~0 && walk->minor != wh->minor)
+			continue;
+
+remove:
+		walk->access &= ~wh->access;
+		if (!walk->access) {
+			list_del(&walk->list);
+			kfree(walk);
+		}
+	}
+	spin_unlock(&dev_cgroup->lock);
+}
+
+/*
+ * called from kernel/cgroup.c with cgroup_lock() held.
+ */
+static struct cgroup_subsys_state *devcgroup_create(struct cgroup_subsys *ss,
+						struct cgroup *cgroup)
+{
+	struct dev_cgroup *dev_cgroup, *parent_dev_cgroup;
+	struct cgroup *parent_cgroup;
+	int ret;
+
+	dev_cgroup = kzalloc(sizeof(*dev_cgroup), GFP_KERNEL);
+	if (!dev_cgroup)
+		return ERR_PTR(-ENOMEM);
+	INIT_LIST_HEAD(&dev_cgroup->whitelist);
+	parent_cgroup = cgroup->parent;
+
+	if (parent_cgroup == NULL) {
+		struct dev_whitelist_item *wh;
+		wh = kmalloc(sizeof(*wh), GFP_KERNEL);
+		if (!wh) {
+			kfree(dev_cgroup);
+			return ERR_PTR(-ENOMEM);
+		}
+		wh->minor = wh->major = ~0;
+		wh->type = DEV_ALL;
+		wh->access = ACC_MKNOD | ACC_READ | ACC_WRITE;
+		list_add(&wh->list, &dev_cgroup->whitelist);
+	} else {
+		parent_dev_cgroup = cgroup_to_devcgroup(parent_cgroup);
+		ret = dev_whitelist_copy(&dev_cgroup->whitelist,
+				&parent_dev_cgroup->whitelist);
+		if (ret) {
+			kfree(dev_cgroup);
+			return ERR_PTR(ret);
+		}
+	}
+
+	spin_lock_init(&dev_cgroup->lock);
+	return &dev_cgroup->css;
+}
+
+static void devcgroup_destroy(struct cgroup_subsys *ss,
+			struct cgroup *cgroup)
+{
+	struct dev_cgroup *dev_cgroup;
+	struct dev_whitelist_item *wh, *tmp;
+
+	dev_cgroup = cgroup_to_devcgroup(cgroup);
+	list_for_each_entry_safe(wh, tmp, &dev_cgroup->whitelist, list) {
+		list_del(&wh->list);
+		kfree(wh);
+	}
+	kfree(dev_cgroup);
+}
+
+#define DEVCG_ALLOW 1
+#define DEVCG_DENY 2
+#define DEVCG_LIST 3
+
+#define MAJMINLEN 10
+#define ACCLEN 4
+
+static void set_access(char *acc, short access)
+{
+	int idx = 0;
+	memset(acc, 0, ACCLEN);
+	if (access & ACC_READ)
+		acc[idx++] = 'r';
+	if (access & ACC_WRITE)
+		acc[idx++] = 'w';
+	if (access & ACC_MKNOD)
+		acc[idx++] = 'm';
+}
+
+static char type_to_char(short type)
+{
+	if (type == DEV_ALL)
+		return 'a';
+	if (type == DEV_CHAR)
+		return 'c';
+	if (type == DEV_BLOCK)
+		return 'b';
+	return 'X';
+}
+
+static void set_majmin(char *str, unsigned m)
+{
+	memset(str, 0, MAJMINLEN);
+	if (m == ~0)
+		sprintf(str, "*");
+	else
+		snprintf(str, MAJMINLEN, "%d", m);
+}
+
+static int devcgroup_seq_read(struct cgroup *cgroup, struct cftype *cft,
+				struct seq_file *m)
+{
+	struct dev_cgroup *devcgroup = cgroup_to_devcgroup(cgroup);
+	struct dev_whitelist_item *wh;
+	char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN];
+
+	spin_lock(&devcgroup->lock);
+	list_for_each_entry(wh, &devcgroup->whitelist, list) {
+		set_access(acc, wh->access);
+		set_majmin(maj, wh->major);
+		set_majmin(min, wh->minor);
+		seq_printf(m, "%c %s:%s %s\n", type_to_char(wh->type),
+			   maj, min, acc);
+	}
+	spin_unlock(&devcgroup->lock);
+
+	return 0;
+}
+
+/*
+ * may_access_whitelist:
+ * does the access granted to dev_cgroup c contain the access
+ * requested in whitelist item refwh.
+ * return 1 if yes, 0 if no.
+ * call with c->lock held
+ */
+static int may_access_whitelist(struct dev_cgroup *c,
+				       struct dev_whitelist_item *refwh)
+{
+	struct dev_whitelist_item *whitem;
+
+	list_for_each_entry(whitem, &c->whitelist, list) {
+		if (whitem->type & DEV_ALL)
+			return 1;
+		if ((refwh->type & DEV_BLOCK) && !(whitem->type & DEV_BLOCK))
+			continue;
+		if ((refwh->type & DEV_CHAR) && !(whitem->type & DEV_CHAR))
+			continue;
+		if (whitem->major != ~0 && whitem->major != refwh->major)
+			continue;
+		if (whitem->minor != ~0 && whitem->minor != refwh->minor)
+			continue;
+		if (refwh->access & (~(whitem->access | ACC_MASK)))
+			continue;
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * parent_has_perm:
+ * when adding a new allow rule to a device whitelist, the rule
+ * must be allowed in the parent device
+ */
+static int parent_has_perm(struct cgroup *childcg,
+				  struct dev_whitelist_item *wh)
+{
+	struct cgroup *pcg = childcg->parent;
+	struct dev_cgroup *parent;
+	int ret;
+
+	if (!pcg)
+		return 1;
+	parent = cgroup_to_devcgroup(pcg);
+	spin_lock(&parent->lock);
+	ret = may_access_whitelist(parent, wh);
+	spin_unlock(&parent->lock);
+	return ret;
+}
+
+/*
+ * Modify the whitelist using allow/deny rules.
+ * CAP_SYS_ADMIN is needed for this.  It's at least separate from CAP_MKNOD
+ * so we can give a container CAP_MKNOD to let it create devices but not
+ * modify the whitelist.
+ * It seems likely we'll want to add a CAP_CONTAINER capability to allow
+ * us to also grant CAP_SYS_ADMIN to containers without giving away the
+ * device whitelist controls, but for now we'll stick with CAP_SYS_ADMIN
+ *
+ * Taking rules away is always allowed (given CAP_SYS_ADMIN).  Granting
+ * new access is only allowed if you're in the top-level cgroup, or your
+ * parent cgroup has the access you're asking for.
+ */
+static ssize_t devcgroup_access_write(struct cgroup *cgroup, struct cftype *cft,
+				struct file *file, const char __user *userbuf,
+				size_t nbytes, loff_t *ppos)
+{
+	struct cgroup *cur_cgroup;
+	struct dev_cgroup *devcgroup, *cur_devcgroup;
+	int filetype = cft->private;
+	char *buffer, *b;
+	int retval = 0, count;
+	struct dev_whitelist_item wh;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	devcgroup = cgroup_to_devcgroup(cgroup);
+	cur_cgroup = task_cgroup(current, devices_subsys.subsys_id);
+	cur_devcgroup = cgroup_to_devcgroup(cur_cgroup);
+
+	buffer = kmalloc(nbytes+1, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	if (copy_from_user(buffer, userbuf, nbytes)) {
+		retval = -EFAULT;
+		goto out1;
+	}
+	buffer[nbytes] = 0;	/* nul-terminate */
+
+	cgroup_lock();
+	if (cgroup_is_removed(cgroup)) {
+		retval = -ENODEV;
+		goto out2;
+	}
+
+	memset(&wh, 0, sizeof(wh));
+	b = buffer;
+
+	switch (*b) {
+	case 'a':
+		wh.type = DEV_ALL;
+		wh.access = ACC_MASK;
+		goto handle;
+	case 'b':
+		wh.type = DEV_BLOCK;
+		break;
+	case 'c':
+		wh.type = DEV_CHAR;
+		break;
+	default:
+		retval = -EINVAL;
+		goto out2;
+	}
+	b++;
+	if (!isspace(*b)) {
+		retval = -EINVAL;
+		goto out2;
+	}
+	b++;
+	if (*b == '*') {
+		wh.major = ~0;
+		b++;
+	} else if (isdigit(*b)) {
+		wh.major = 0;
+		while (isdigit(*b)) {
+			wh.major = wh.major*10+(*b-'0');
+			b++;
+		}
+	} else {
+		retval = -EINVAL;
+		goto out2;
+	}
+	if (*b != ':') {
+		retval = -EINVAL;
+		goto out2;
+	}
+	b++;
+
+	/* read minor */
+	if (*b == '*') {
+		wh.minor = ~0;
+		b++;
+	} else if (isdigit(*b)) {
+		wh.minor = 0;
+		while (isdigit(*b)) {
+			wh.minor = wh.minor*10+(*b-'0');
+			b++;
+		}
+	} else {
+		retval = -EINVAL;
+		goto out2;
+	}
+	if (!isspace(*b)) {
+		retval = -EINVAL;
+		goto out2;
+	}
+	for (b++, count = 0; count < 3; count++, b++) {
+		switch (*b) {
+		case 'r':
+			wh.access |= ACC_READ;
+			break;
+		case 'w':
+			wh.access |= ACC_WRITE;
+			break;
+		case 'm':
+			wh.access |= ACC_MKNOD;
+			break;
+		case '\n':
+		case '\0':
+			count = 3;
+			break;
+		default:
+			retval = -EINVAL;
+			goto out2;
+		}
+	}
+
+handle:
+	retval = 0;
+	switch (filetype) {
+	case DEVCG_ALLOW:
+		if (!parent_has_perm(cgroup, &wh))
+			retval = -EPERM;
+		else
+			retval = dev_whitelist_add(devcgroup, &wh);
+		break;
+	case DEVCG_DENY:
+		dev_whitelist_rm(devcgroup, &wh);
+		break;
+	default:
+		retval = -EINVAL;
+		goto out2;
+	}
+
+	if (retval == 0)
+		retval = nbytes;
+
+out2:
+	cgroup_unlock();
+out1:
+	kfree(buffer);
+	return retval;
+}
+
+static struct cftype dev_cgroup_files[] = {
+	{
+		.name = "allow",
+		.write  = devcgroup_access_write,
+		.private = DEVCG_ALLOW,
+	},
+	{
+		.name = "deny",
+		.write = devcgroup_access_write,
+		.private = DEVCG_DENY,
+	},
+	{
+		.name = "list",
+		.read_seq_string = devcgroup_seq_read,
+		.private = DEVCG_LIST,
+	},
+};
+
+static int devcgroup_populate(struct cgroup_subsys *ss,
+				struct cgroup *cgroup)
+{
+	return cgroup_add_files(cgroup, ss, dev_cgroup_files,
+					ARRAY_SIZE(dev_cgroup_files));
+}
+
+struct cgroup_subsys devices_subsys = {
+	.name = "devices",
+	.can_attach = devcgroup_can_attach,
+	.create = devcgroup_create,
+	.destroy  = devcgroup_destroy,
+	.populate = devcgroup_populate,
+	.subsys_id = devices_subsys_id,
+};
+
+int devcgroup_inode_permission(struct inode *inode, int mask)
+{
+	struct cgroup *cgroup;
+	struct dev_cgroup *dev_cgroup;
+	struct dev_whitelist_item *wh;
+
+	dev_t device = inode->i_rdev;
+	if (!device)
+		return 0;
+	if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode))
+		return 0;
+	cgroup = task_cgroup(current, devices_subsys.subsys_id);
+	dev_cgroup = cgroup_to_devcgroup(cgroup);
+	if (!dev_cgroup)
+		return 0;
+
+	spin_lock(&dev_cgroup->lock);
+	list_for_each_entry(wh, &dev_cgroup->whitelist, list) {
+		if (wh->type & DEV_ALL)
+			goto acc_check;
+		if ((wh->type & DEV_BLOCK) && !S_ISBLK(inode->i_mode))
+			continue;
+		if ((wh->type & DEV_CHAR) && !S_ISCHR(inode->i_mode))
+			continue;
+		if (wh->major != ~0 && wh->major != imajor(inode))
+			continue;
+		if (wh->minor != ~0 && wh->minor != iminor(inode))
+			continue;
+acc_check:
+		if ((mask & MAY_WRITE) && !(wh->access & ACC_WRITE))
+			continue;
+		if ((mask & MAY_READ) && !(wh->access & ACC_READ))
+			continue;
+		spin_unlock(&dev_cgroup->lock);
+		return 0;
+	}
+	spin_unlock(&dev_cgroup->lock);
+
+	return -EPERM;
+}
+
+int devcgroup_inode_mknod(int mode, dev_t dev)
+{
+	struct cgroup *cgroup;
+	struct dev_cgroup *dev_cgroup;
+	struct dev_whitelist_item *wh;
+
+	cgroup = task_cgroup(current, devices_subsys.subsys_id);
+	dev_cgroup = cgroup_to_devcgroup(cgroup);
+	if (!dev_cgroup)
+		return 0;
+
+	spin_lock(&dev_cgroup->lock);
+	list_for_each_entry(wh, &dev_cgroup->whitelist, list) {
+		if (wh->type & DEV_ALL)
+			goto acc_check;
+		if ((wh->type & DEV_BLOCK) && !S_ISBLK(mode))
+			continue;
+		if ((wh->type & DEV_CHAR) && !S_ISCHR(mode))
+			continue;
+		if (wh->major != ~0 && wh->major != MAJOR(dev))
+			continue;
+		if (wh->minor != ~0 && wh->minor != MINOR(dev))
+			continue;
+acc_check:
+		if (!(wh->access & ACC_MKNOD))
+			continue;
+		spin_unlock(&dev_cgroup->lock);
+		return 0;
+	}
+	spin_unlock(&dev_cgroup->lock);
+	return -EPERM;
+}
diff --git a/trunk/security/dummy.c b/trunk/security/dummy.c
index b0232bbf427b..48cf30226e16 100644
--- a/trunk/security/dummy.c
+++ b/trunk/security/dummy.c
@@ -365,8 +365,8 @@ static void dummy_inode_delete (struct inode *ino)
 	return;
 }
 
-static int dummy_inode_setxattr (struct dentry *dentry, char *name, void *value,
-				size_t size, int flags)
+static int dummy_inode_setxattr (struct dentry *dentry, const char *name,
+				 const void *value, size_t size, int flags)
 {
 	if (!strncmp(name, XATTR_SECURITY_PREFIX,
 		     sizeof(XATTR_SECURITY_PREFIX) - 1) &&
@@ -375,12 +375,13 @@ static int dummy_inode_setxattr (struct dentry *dentry, char *name, void *value,
 	return 0;
 }
 
-static void dummy_inode_post_setxattr (struct dentry *dentry, char *name, void *value,
-				       size_t size, int flags)
+static void dummy_inode_post_setxattr (struct dentry *dentry, const char *name,
+				       const void *value, size_t size,
+				       int flags)
 {
 }
 
-static int dummy_inode_getxattr (struct dentry *dentry, char *name)
+static int dummy_inode_getxattr (struct dentry *dentry, const char *name)
 {
 	return 0;
 }
@@ -390,7 +391,7 @@ static int dummy_inode_listxattr (struct dentry *dentry)
 	return 0;
 }
 
-static int dummy_inode_removexattr (struct dentry *dentry, char *name)
+static int dummy_inode_removexattr (struct dentry *dentry, const char *name)
 {
 	if (!strncmp(name, XATTR_SECURITY_PREFIX,
 		     sizeof(XATTR_SECURITY_PREFIX) - 1) &&
@@ -604,7 +605,7 @@ static int dummy_task_kill (struct task_struct *p, struct siginfo *info,
 }
 
 static int dummy_task_prctl (int option, unsigned long arg2, unsigned long arg3,
-			     unsigned long arg4, unsigned long arg5)
+			     unsigned long arg4, unsigned long arg5, long *rc_p)
 {
 	return 0;
 }
@@ -993,6 +994,13 @@ static inline int dummy_key_permission(key_ref_t key_ref,
 {
 	return 0;
 }
+
+static int dummy_key_getsecurity(struct key *key, char **_buffer)
+{
+	*_buffer = NULL;
+	return 0;
+}
+
 #endif /* CONFIG_KEYS */
 
 #ifdef CONFIG_AUDIT
@@ -1209,6 +1217,7 @@ void security_fixup_ops (struct security_operations *ops)
 	set_to_dummy_if_null(ops, key_alloc);
 	set_to_dummy_if_null(ops, key_free);
 	set_to_dummy_if_null(ops, key_permission);
+	set_to_dummy_if_null(ops, key_getsecurity);
 #endif	/* CONFIG_KEYS */
 #ifdef CONFIG_AUDIT
 	set_to_dummy_if_null(ops, audit_rule_init);
diff --git a/trunk/security/keys/Makefile b/trunk/security/keys/Makefile
index 5145adfb6a05..747a464943af 100644
--- a/trunk/security/keys/Makefile
+++ b/trunk/security/keys/Makefile
@@ -14,3 +14,4 @@ obj-y := \
 
 obj-$(CONFIG_KEYS_COMPAT) += compat.o
 obj-$(CONFIG_PROC_FS) += proc.o
+obj-$(CONFIG_SYSCTL) += sysctl.o
diff --git a/trunk/security/keys/compat.c b/trunk/security/keys/compat.c
index e10ec995f275..c766c68a63bc 100644
--- a/trunk/security/keys/compat.c
+++ b/trunk/security/keys/compat.c
@@ -79,6 +79,9 @@ asmlinkage long compat_sys_keyctl(u32 option,
 	case KEYCTL_ASSUME_AUTHORITY:
 		return keyctl_assume_authority(arg2);
 
+	case KEYCTL_GET_SECURITY:
+		return keyctl_get_security(arg2, compat_ptr(arg3), arg4);
+
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/trunk/security/keys/internal.h b/trunk/security/keys/internal.h
index 7d894ef70370..8c05587f5018 100644
--- a/trunk/security/keys/internal.h
+++ b/trunk/security/keys/internal.h
@@ -57,10 +57,6 @@ struct key_user {
 	int			qnbytes;	/* number of bytes allocated to this user */
 };
 
-#define KEYQUOTA_MAX_KEYS	100
-#define KEYQUOTA_MAX_BYTES	10000
-#define KEYQUOTA_LINK_BYTES	4		/* a link in a keyring is worth 4 bytes */
-
 extern struct rb_root	key_user_tree;
 extern spinlock_t	key_user_lock;
 extern struct key_user	root_key_user;
@@ -68,6 +64,16 @@ extern struct key_user	root_key_user;
 extern struct key_user *key_user_lookup(uid_t uid);
 extern void key_user_put(struct key_user *user);
 
+/*
+ * key quota limits
+ * - root has its own separate limits to everyone else
+ */
+extern unsigned key_quota_root_maxkeys;
+extern unsigned key_quota_root_maxbytes;
+extern unsigned key_quota_maxkeys;
+extern unsigned key_quota_maxbytes;
+
+#define KEYQUOTA_LINK_BYTES	4		/* a link in a keyring is worth 4 bytes */
 
 
 extern struct rb_root key_serial_tree;
@@ -77,8 +83,6 @@ extern struct mutex key_construction_mutex;
 extern wait_queue_head_t request_key_conswq;
 
 
-extern void keyring_publish_name(struct key *keyring);
-
 extern int __key_link(struct key *keyring, struct key *key);
 
 extern key_ref_t __keyring_search_one(key_ref_t keyring_ref,
@@ -102,14 +106,15 @@ extern key_ref_t search_process_keyrings(struct key_type *type,
 					 key_match_func_t match,
 					 struct task_struct *tsk);
 
-extern struct key *find_keyring_by_name(const char *name, key_serial_t bound);
+extern struct key *find_keyring_by_name(const char *name, bool skip_perm_check);
 
 extern int install_thread_keyring(struct task_struct *tsk);
 extern int install_process_keyring(struct task_struct *tsk);
 
 extern struct key *request_key_and_link(struct key_type *type,
 					const char *description,
-					const char *callout_info,
+					const void *callout_info,
+					size_t callout_len,
 					void *aux,
 					struct key *dest_keyring,
 					unsigned long flags);
@@ -120,13 +125,15 @@ extern struct key *request_key_and_link(struct key_type *type,
 struct request_key_auth {
 	struct key		*target_key;
 	struct task_struct	*context;
-	char			*callout_info;
+	void			*callout_info;
+	size_t			callout_len;
 	pid_t			pid;
 };
 
 extern struct key_type key_type_request_key_auth;
 extern struct key *request_key_auth_new(struct key *target,
-					const char *callout_info);
+					const void *callout_info,
+					size_t callout_len);
 
 extern struct key *key_get_instantiation_authkey(key_serial_t target_id);
 
@@ -152,7 +159,8 @@ extern long keyctl_negate_key(key_serial_t, unsigned, key_serial_t);
 extern long keyctl_set_reqkey_keyring(int);
 extern long keyctl_set_timeout(key_serial_t, unsigned);
 extern long keyctl_assume_authority(key_serial_t);
-
+extern long keyctl_get_security(key_serial_t keyid, char __user *buffer,
+				size_t buflen);
 
 /*
  * debugging key validation
diff --git a/trunk/security/keys/key.c b/trunk/security/keys/key.c
index 654d23baf352..14948cf83ef6 100644
--- a/trunk/security/keys/key.c
+++ b/trunk/security/keys/key.c
@@ -1,6 +1,6 @@
 /* Basic authentication token and access key management
  *
- * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2004-2008 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * This program is free software; you can redistribute it and/or
@@ -27,6 +27,11 @@ DEFINE_SPINLOCK(key_serial_lock);
 struct rb_root	key_user_tree; /* tree of quota records indexed by UID */
 DEFINE_SPINLOCK(key_user_lock);
 
+unsigned int key_quota_root_maxkeys = 200;	/* root's key count quota */
+unsigned int key_quota_root_maxbytes = 20000;	/* root's key space quota */
+unsigned int key_quota_maxkeys = 200;		/* general key count quota */
+unsigned int key_quota_maxbytes = 20000;	/* general key space quota */
+
 static LIST_HEAD(key_types_list);
 static DECLARE_RWSEM(key_types_sem);
 
@@ -137,36 +142,6 @@ void key_user_put(struct key_user *user)
 
 } /* end key_user_put() */
 
-/*****************************************************************************/
-/*
- * insert a key with a fixed serial number
- */
-static void __init __key_insert_serial(struct key *key)
-{
-	struct rb_node *parent, **p;
-	struct key *xkey;
-
-	parent = NULL;
-	p = &key_serial_tree.rb_node;
-
-	while (*p) {
-		parent = *p;
-		xkey = rb_entry(parent, struct key, serial_node);
-
-		if (key->serial < xkey->serial)
-			p = &(*p)->rb_left;
-		else if (key->serial > xkey->serial)
-			p = &(*p)->rb_right;
-		else
-			BUG();
-	}
-
-	/* we've found a suitable hole - arrange for this key to occupy it */
-	rb_link_node(&key->serial_node, parent, p);
-	rb_insert_color(&key->serial_node, &key_serial_tree);
-
-} /* end __key_insert_serial() */
-
 /*****************************************************************************/
 /*
  * assign a key the next unique serial number
@@ -266,11 +241,16 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 	/* check that the user's quota permits allocation of another key and
 	 * its description */
 	if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) {
+		unsigned maxkeys = (uid == 0) ?
+			key_quota_root_maxkeys : key_quota_maxkeys;
+		unsigned maxbytes = (uid == 0) ?
+			key_quota_root_maxbytes : key_quota_maxbytes;
+
 		spin_lock(&user->lock);
 		if (!(flags & KEY_ALLOC_QUOTA_OVERRUN)) {
-			if (user->qnkeys + 1 >= KEYQUOTA_MAX_KEYS ||
-			    user->qnbytes + quotalen >= KEYQUOTA_MAX_BYTES
-			    )
+			if (user->qnkeys + 1 >= maxkeys ||
+			    user->qnbytes + quotalen >= maxbytes ||
+			    user->qnbytes + quotalen < user->qnbytes)
 				goto no_quota;
 		}
 
@@ -375,11 +355,14 @@ int key_payload_reserve(struct key *key, size_t datalen)
 
 	/* contemplate the quota adjustment */
 	if (delta != 0 && test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) {
+		unsigned maxbytes = (key->user->uid == 0) ?
+			key_quota_root_maxbytes : key_quota_maxbytes;
+
 		spin_lock(&key->user->lock);
 
 		if (delta > 0 &&
-		    key->user->qnbytes + delta > KEYQUOTA_MAX_BYTES
-		    ) {
+		    (key->user->qnbytes + delta >= maxbytes ||
+		     key->user->qnbytes + delta < key->user->qnbytes)) {
 			ret = -EDQUOT;
 		}
 		else {
@@ -757,11 +740,11 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 			       const char *description,
 			       const void *payload,
 			       size_t plen,
+			       key_perm_t perm,
 			       unsigned long flags)
 {
 	struct key_type *ktype;
 	struct key *keyring, *key = NULL;
-	key_perm_t perm;
 	key_ref_t key_ref;
 	int ret;
 
@@ -806,15 +789,17 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 			goto found_matching_key;
 	}
 
-	/* decide on the permissions we want */
-	perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR;
-	perm |= KEY_USR_VIEW | KEY_USR_SEARCH | KEY_USR_LINK | KEY_USR_SETATTR;
+	/* if the client doesn't provide, decide on the permissions we want */
+	if (perm == KEY_PERM_UNDEF) {
+		perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR;
+		perm |= KEY_USR_VIEW | KEY_USR_SEARCH | KEY_USR_LINK | KEY_USR_SETATTR;
 
-	if (ktype->read)
-		perm |= KEY_POS_READ | KEY_USR_READ;
+		if (ktype->read)
+			perm |= KEY_POS_READ | KEY_USR_READ;
 
-	if (ktype == &key_type_keyring || ktype->update)
-		perm |= KEY_USR_WRITE;
+		if (ktype == &key_type_keyring || ktype->update)
+			perm |= KEY_USR_WRITE;
+	}
 
 	/* allocate a new key */
 	key = key_alloc(ktype, description, current->fsuid, current->fsgid,
@@ -1018,17 +1003,4 @@ void __init key_init(void)
 	rb_insert_color(&root_key_user.node,
 			&key_user_tree);
 
-	/* record root's user standard keyrings */
-	key_check(&root_user_keyring);
-	key_check(&root_session_keyring);
-
-	__key_insert_serial(&root_user_keyring);
-	__key_insert_serial(&root_session_keyring);
-
-	keyring_publish_name(&root_user_keyring);
-	keyring_publish_name(&root_session_keyring);
-
-	/* link the two root keyrings together */
-	key_link(&root_session_keyring, &root_user_keyring);
-
 } /* end key_init() */
diff --git a/trunk/security/keys/keyctl.c b/trunk/security/keys/keyctl.c
index d9ca15c109cc..acc9c89e40a8 100644
--- a/trunk/security/keys/keyctl.c
+++ b/trunk/security/keys/keyctl.c
@@ -19,6 +19,8 @@
 #include <linux/capability.h>
 #include <linux/string.h>
 #include <linux/err.h>
+#include <linux/vmalloc.h>
+#include <linux/security.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
@@ -62,9 +64,10 @@ asmlinkage long sys_add_key(const char __user *_type,
 	char type[32], *description;
 	void *payload;
 	long ret;
+	bool vm;
 
 	ret = -EINVAL;
-	if (plen > 32767)
+	if (plen > 1024 * 1024 - 1)
 		goto error;
 
 	/* draw all the data into kernel space */
@@ -81,11 +84,18 @@ asmlinkage long sys_add_key(const char __user *_type,
 	/* pull the payload in if one was supplied */
 	payload = NULL;
 
+	vm = false;
 	if (_payload) {
 		ret = -ENOMEM;
 		payload = kmalloc(plen, GFP_KERNEL);
-		if (!payload)
-			goto error2;
+		if (!payload) {
+			if (plen <= PAGE_SIZE)
+				goto error2;
+			vm = true;
+			payload = vmalloc(plen);
+			if (!payload)
+				goto error2;
+		}
 
 		ret = -EFAULT;
 		if (copy_from_user(payload, _payload, plen) != 0)
@@ -102,7 +112,8 @@ asmlinkage long sys_add_key(const char __user *_type,
 	/* create or update the requested key and add it to the target
 	 * keyring */
 	key_ref = key_create_or_update(keyring_ref, type, description,
-				       payload, plen, KEY_ALLOC_IN_QUOTA);
+				       payload, plen, KEY_PERM_UNDEF,
+				       KEY_ALLOC_IN_QUOTA);
 	if (!IS_ERR(key_ref)) {
 		ret = key_ref_to_ptr(key_ref)->serial;
 		key_ref_put(key_ref);
@@ -113,7 +124,10 @@ asmlinkage long sys_add_key(const char __user *_type,
 
 	key_ref_put(keyring_ref);
  error3:
-	kfree(payload);
+	if (!vm)
+		kfree(payload);
+	else
+		vfree(payload);
  error2:
 	kfree(description);
  error:
@@ -140,6 +154,7 @@ asmlinkage long sys_request_key(const char __user *_type,
 	struct key_type *ktype;
 	struct key *key;
 	key_ref_t dest_ref;
+	size_t callout_len;
 	char type[32], *description, *callout_info;
 	long ret;
 
@@ -157,12 +172,14 @@ asmlinkage long sys_request_key(const char __user *_type,
 
 	/* pull the callout info into kernel space */
 	callout_info = NULL;
+	callout_len = 0;
 	if (_callout_info) {
 		callout_info = strndup_user(_callout_info, PAGE_SIZE);
 		if (IS_ERR(callout_info)) {
 			ret = PTR_ERR(callout_info);
 			goto error2;
 		}
+		callout_len = strlen(callout_info);
 	}
 
 	/* get the destination keyring if specified */
@@ -183,8 +200,8 @@ asmlinkage long sys_request_key(const char __user *_type,
 	}
 
 	/* do the search */
-	key = request_key_and_link(ktype, description, callout_info, NULL,
-				   key_ref_to_ptr(dest_ref),
+	key = request_key_and_link(ktype, description, callout_info,
+				   callout_len, NULL, key_ref_to_ptr(dest_ref),
 				   KEY_ALLOC_IN_QUOTA);
 	if (IS_ERR(key)) {
 		ret = PTR_ERR(key);
@@ -714,10 +731,16 @@ long keyctl_chown_key(key_serial_t id, uid_t uid, gid_t gid)
 
 		/* transfer the quota burden to the new user */
 		if (test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) {
+			unsigned maxkeys = (uid == 0) ?
+				key_quota_root_maxkeys : key_quota_maxkeys;
+			unsigned maxbytes = (uid == 0) ?
+				key_quota_root_maxbytes : key_quota_maxbytes;
+
 			spin_lock(&newowner->lock);
-			if (newowner->qnkeys + 1 >= KEYQUOTA_MAX_KEYS ||
-			    newowner->qnbytes + key->quotalen >=
-			    KEYQUOTA_MAX_BYTES)
+			if (newowner->qnkeys + 1 >= maxkeys ||
+			    newowner->qnbytes + key->quotalen >= maxbytes ||
+			    newowner->qnbytes + key->quotalen <
+			    newowner->qnbytes)
 				goto quota_overrun;
 
 			newowner->qnkeys++;
@@ -821,9 +844,10 @@ long keyctl_instantiate_key(key_serial_t id,
 	key_ref_t keyring_ref;
 	void *payload;
 	long ret;
+	bool vm = false;
 
 	ret = -EINVAL;
-	if (plen > 32767)
+	if (plen > 1024 * 1024 - 1)
 		goto error;
 
 	/* the appropriate instantiation authorisation key must have been
@@ -843,8 +867,14 @@ long keyctl_instantiate_key(key_serial_t id,
 	if (_payload) {
 		ret = -ENOMEM;
 		payload = kmalloc(plen, GFP_KERNEL);
-		if (!payload)
-			goto error;
+		if (!payload) {
+			if (plen <= PAGE_SIZE)
+				goto error;
+			vm = true;
+			payload = vmalloc(plen);
+			if (!payload)
+				goto error;
+		}
 
 		ret = -EFAULT;
 		if (copy_from_user(payload, _payload, plen) != 0)
@@ -877,7 +907,10 @@ long keyctl_instantiate_key(key_serial_t id,
 	}
 
 error2:
-	kfree(payload);
+	if (!vm)
+		kfree(payload);
+	else
+		vfree(payload);
 error:
 	return ret;
 
@@ -1055,6 +1088,66 @@ long keyctl_assume_authority(key_serial_t id)
 
 } /* end keyctl_assume_authority() */
 
+/*
+ * get the security label of a key
+ * - the key must grant us view permission
+ * - if there's a buffer, we place up to buflen bytes of data into it
+ * - unless there's an error, we return the amount of information available,
+ *   irrespective of how much we may have copied (including the terminal NUL)
+ * - implements keyctl(KEYCTL_GET_SECURITY)
+ */
+long keyctl_get_security(key_serial_t keyid,
+			 char __user *buffer,
+			 size_t buflen)
+{
+	struct key *key, *instkey;
+	key_ref_t key_ref;
+	char *context;
+	long ret;
+
+	key_ref = lookup_user_key(NULL, keyid, 0, 1, KEY_VIEW);
+	if (IS_ERR(key_ref)) {
+		if (PTR_ERR(key_ref) != -EACCES)
+			return PTR_ERR(key_ref);
+
+		/* viewing a key under construction is also permitted if we
+		 * have the authorisation token handy */
+		instkey = key_get_instantiation_authkey(keyid);
+		if (IS_ERR(instkey))
+			return PTR_ERR(key_ref);
+		key_put(instkey);
+
+		key_ref = lookup_user_key(NULL, keyid, 0, 1, 0);
+		if (IS_ERR(key_ref))
+			return PTR_ERR(key_ref);
+	}
+
+	key = key_ref_to_ptr(key_ref);
+	ret = security_key_getsecurity(key, &context);
+	if (ret == 0) {
+		/* if no information was returned, give userspace an empty
+		 * string */
+		ret = 1;
+		if (buffer && buflen > 0 &&
+		    copy_to_user(buffer, "", 1) != 0)
+			ret = -EFAULT;
+	} else if (ret > 0) {
+		/* return as much data as there's room for */
+		if (buffer && buflen > 0) {
+			if (buflen > ret)
+				buflen = ret;
+
+			if (copy_to_user(buffer, context, buflen) != 0)
+				ret = -EFAULT;
+		}
+
+		kfree(context);
+	}
+
+	key_ref_put(key_ref);
+	return ret;
+}
+
 /*****************************************************************************/
 /*
  * the key control system call
@@ -1135,6 +1228,11 @@ asmlinkage long sys_keyctl(int option, unsigned long arg2, unsigned long arg3,
 	case KEYCTL_ASSUME_AUTHORITY:
 		return keyctl_assume_authority((key_serial_t) arg2);
 
+	case KEYCTL_GET_SECURITY:
+		return keyctl_get_security((key_serial_t) arg2,
+					   (char *) arg3,
+					   (size_t) arg4);
+
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/trunk/security/keys/keyring.c b/trunk/security/keys/keyring.c
index 88292e3dee96..a9ab8affc092 100644
--- a/trunk/security/keys/keyring.c
+++ b/trunk/security/keys/keyring.c
@@ -1,6 +1,6 @@
-/* keyring.c: keyring handling
+/* Keyring handling
  *
- * Copyright (C) 2004-5 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2004-2005, 2008 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * This program is free software; you can redistribute it and/or
@@ -79,7 +79,7 @@ static DECLARE_RWSEM(keyring_serialise_link_sem);
  * publish the name of a keyring so that it can be found by name (if it has
  * one)
  */
-void keyring_publish_name(struct key *keyring)
+static void keyring_publish_name(struct key *keyring)
 {
 	int bucket;
 
@@ -292,7 +292,7 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 
 	struct keyring_list *keylist;
 	struct timespec now;
-	unsigned long possessed;
+	unsigned long possessed, kflags;
 	struct key *keyring, *key;
 	key_ref_t key_ref;
 	long err;
@@ -319,6 +319,32 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 	err = -EAGAIN;
 	sp = 0;
 
+	/* firstly we should check to see if this top-level keyring is what we
+	 * are looking for */
+	key_ref = ERR_PTR(-EAGAIN);
+	kflags = keyring->flags;
+	if (keyring->type == type && match(keyring, description)) {
+		key = keyring;
+
+		/* check it isn't negative and hasn't expired or been
+		 * revoked */
+		if (kflags & (1 << KEY_FLAG_REVOKED))
+			goto error_2;
+		if (key->expiry && now.tv_sec >= key->expiry)
+			goto error_2;
+		key_ref = ERR_PTR(-ENOKEY);
+		if (kflags & (1 << KEY_FLAG_NEGATIVE))
+			goto error_2;
+		goto found;
+	}
+
+	/* otherwise, the top keyring must not be revoked, expired, or
+	 * negatively instantiated if we are to search it */
+	key_ref = ERR_PTR(-EAGAIN);
+	if (kflags & ((1 << KEY_FLAG_REVOKED) | (1 << KEY_FLAG_NEGATIVE)) ||
+	    (keyring->expiry && now.tv_sec >= keyring->expiry))
+		goto error_2;
+
 	/* start processing a new keyring */
 descend:
 	if (test_bit(KEY_FLAG_REVOKED, &keyring->flags))
@@ -331,13 +357,14 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 	/* iterate through the keys in this keyring first */
 	for (kix = 0; kix < keylist->nkeys; kix++) {
 		key = keylist->keys[kix];
+		kflags = key->flags;
 
 		/* ignore keys not of this type */
 		if (key->type != type)
 			continue;
 
 		/* skip revoked keys and expired keys */
-		if (test_bit(KEY_FLAG_REVOKED, &key->flags))
+		if (kflags & (1 << KEY_FLAG_REVOKED))
 			continue;
 
 		if (key->expiry && now.tv_sec >= key->expiry)
@@ -352,8 +379,8 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 					context, KEY_SEARCH) < 0)
 			continue;
 
-		/* we set a different error code if we find a negative key */
-		if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) {
+		/* we set a different error code if we pass a negative key */
+		if (kflags & (1 << KEY_FLAG_NEGATIVE)) {
 			err = -ENOKEY;
 			continue;
 		}
@@ -489,10 +516,9 @@ key_ref_t __keyring_search_one(key_ref_t keyring_ref,
 /*
  * find a keyring with the specified name
  * - all named keyrings are searched
- * - only find keyrings with search permission for the process
- * - only find keyrings with a serial number greater than the one specified
+ * - normally only finds keyrings with search permission for the current process
  */
-struct key *find_keyring_by_name(const char *name, key_serial_t bound)
+struct key *find_keyring_by_name(const char *name, bool skip_perm_check)
 {
 	struct key *keyring;
 	int bucket;
@@ -518,15 +544,11 @@ struct key *find_keyring_by_name(const char *name, key_serial_t bound)
 			if (strcmp(keyring->description, name) != 0)
 				continue;
 
-			if (key_permission(make_key_ref(keyring, 0),
+			if (!skip_perm_check &&
+			    key_permission(make_key_ref(keyring, 0),
 					   KEY_SEARCH) < 0)
 				continue;
 
-			/* found a potential candidate, but we still need to
-			 * check the serial number */
-			if (keyring->serial <= bound)
-				continue;
-
 			/* we've got a match */
 			atomic_inc(&keyring->usage);
 			read_unlock(&keyring_name_lock);
diff --git a/trunk/security/keys/proc.c b/trunk/security/keys/proc.c
index 694126003ed3..f619170da760 100644
--- a/trunk/security/keys/proc.c
+++ b/trunk/security/keys/proc.c
@@ -70,19 +70,15 @@ static int __init key_proc_init(void)
 	struct proc_dir_entry *p;
 
 #ifdef CONFIG_KEYS_DEBUG_PROC_KEYS
-	p = create_proc_entry("keys", 0, NULL);
+	p = proc_create("keys", 0, NULL, &proc_keys_fops);
 	if (!p)
 		panic("Cannot create /proc/keys\n");
-
-	p->proc_fops = &proc_keys_fops;
 #endif
 
-	p = create_proc_entry("key-users", 0, NULL);
+	p = proc_create("key-users", 0, NULL, &proc_key_users_fops);
 	if (!p)
 		panic("Cannot create /proc/key-users\n");
 
-	p->proc_fops = &proc_key_users_fops;
-
 	return 0;
 
 } /* end key_proc_init() */
@@ -246,6 +242,10 @@ static int proc_key_users_show(struct seq_file *m, void *v)
 {
 	struct rb_node *_p = v;
 	struct key_user *user = rb_entry(_p, struct key_user, node);
+	unsigned maxkeys = (user->uid == 0) ?
+		key_quota_root_maxkeys : key_quota_maxkeys;
+	unsigned maxbytes = (user->uid == 0) ?
+		key_quota_root_maxbytes : key_quota_maxbytes;
 
 	seq_printf(m, "%5u: %5d %d/%d %d/%d %d/%d\n",
 		   user->uid,
@@ -253,10 +253,9 @@ static int proc_key_users_show(struct seq_file *m, void *v)
 		   atomic_read(&user->nkeys),
 		   atomic_read(&user->nikeys),
 		   user->qnkeys,
-		   KEYQUOTA_MAX_KEYS,
+		   maxkeys,
 		   user->qnbytes,
-		   KEYQUOTA_MAX_BYTES
-		   );
+		   maxbytes);
 
 	return 0;
 
diff --git a/trunk/security/keys/process_keys.c b/trunk/security/keys/process_keys.c
index c886a2bb792a..5be6d018759a 100644
--- a/trunk/security/keys/process_keys.c
+++ b/trunk/security/keys/process_keys.c
@@ -1,6 +1,6 @@
-/* process_keys.c: management of a process's keyrings
+/* Management of a process's keyrings
  *
- * Copyright (C) 2004-5 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2004-2005, 2008 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * This program is free software; you can redistribute it and/or
@@ -23,6 +23,9 @@
 /* session keyring create vs join semaphore */
 static DEFINE_MUTEX(key_session_mutex);
 
+/* user keyring creation semaphore */
+static DEFINE_MUTEX(key_user_keyring_mutex);
+
 /* the root user's tracking struct */
 struct key_user root_key_user = {
 	.usage		= ATOMIC_INIT(3),
@@ -33,78 +36,84 @@ struct key_user root_key_user = {
 	.uid		= 0,
 };
 
-/* the root user's UID keyring */
-struct key root_user_keyring = {
-	.usage		= ATOMIC_INIT(1),
-	.serial		= 2,
-	.type		= &key_type_keyring,
-	.user		= &root_key_user,
-	.sem		= __RWSEM_INITIALIZER(root_user_keyring.sem),
-	.perm		= (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_ALL,
-	.flags		= 1 << KEY_FLAG_INSTANTIATED,
-	.description	= "_uid.0",
-#ifdef KEY_DEBUGGING
-	.magic		= KEY_DEBUG_MAGIC,
-#endif
-};
-
-/* the root user's default session keyring */
-struct key root_session_keyring = {
-	.usage		= ATOMIC_INIT(1),
-	.serial		= 1,
-	.type		= &key_type_keyring,
-	.user		= &root_key_user,
-	.sem		= __RWSEM_INITIALIZER(root_session_keyring.sem),
-	.perm		= (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_ALL,
-	.flags		= 1 << KEY_FLAG_INSTANTIATED,
-	.description	= "_uid_ses.0",
-#ifdef KEY_DEBUGGING
-	.magic		= KEY_DEBUG_MAGIC,
-#endif
-};
-
 /*****************************************************************************/
 /*
- * allocate the keyrings to be associated with a UID
+ * install user and user session keyrings for a particular UID
  */
-int alloc_uid_keyring(struct user_struct *user,
-		      struct task_struct *ctx)
+static int install_user_keyrings(struct task_struct *tsk)
 {
+	struct user_struct *user = tsk->user;
 	struct key *uid_keyring, *session_keyring;
 	char buf[20];
 	int ret;
 
-	/* concoct a default session keyring */
-	sprintf(buf, "_uid_ses.%u", user->uid);
+	kenter("%p{%u}", user, user->uid);
 
-	session_keyring = keyring_alloc(buf, user->uid, (gid_t) -1, ctx,
-					KEY_ALLOC_IN_QUOTA, NULL);
-	if (IS_ERR(session_keyring)) {
-		ret = PTR_ERR(session_keyring);
-		goto error;
+	if (user->uid_keyring) {
+		kleave(" = 0 [exist]");
+		return 0;
 	}
 
-	/* and a UID specific keyring, pointed to by the default session
-	 * keyring */
-	sprintf(buf, "_uid.%u", user->uid);
+	mutex_lock(&key_user_keyring_mutex);
+	ret = 0;
 
-	uid_keyring = keyring_alloc(buf, user->uid, (gid_t) -1, ctx,
-				    KEY_ALLOC_IN_QUOTA, session_keyring);
-	if (IS_ERR(uid_keyring)) {
-		key_put(session_keyring);
-		ret = PTR_ERR(uid_keyring);
-		goto error;
+	if (!user->uid_keyring) {
+		/* get the UID-specific keyring
+		 * - there may be one in existence already as it may have been
+		 *   pinned by a session, but the user_struct pointing to it
+		 *   may have been destroyed by setuid */
+		sprintf(buf, "_uid.%u", user->uid);
+
+		uid_keyring = find_keyring_by_name(buf, true);
+		if (IS_ERR(uid_keyring)) {
+			uid_keyring = keyring_alloc(buf, user->uid, (gid_t) -1,
+						    tsk, KEY_ALLOC_IN_QUOTA,
+						    NULL);
+			if (IS_ERR(uid_keyring)) {
+				ret = PTR_ERR(uid_keyring);
+				goto error;
+			}
+		}
+
+		/* get a default session keyring (which might also exist
+		 * already) */
+		sprintf(buf, "_uid_ses.%u", user->uid);
+
+		session_keyring = find_keyring_by_name(buf, true);
+		if (IS_ERR(session_keyring)) {
+			session_keyring =
+				keyring_alloc(buf, user->uid, (gid_t) -1,
+					      tsk, KEY_ALLOC_IN_QUOTA, NULL);
+			if (IS_ERR(session_keyring)) {
+				ret = PTR_ERR(session_keyring);
+				goto error_release;
+			}
+
+			/* we install a link from the user session keyring to
+			 * the user keyring */
+			ret = key_link(session_keyring, uid_keyring);
+			if (ret < 0)
+				goto error_release_both;
+		}
+
+		/* install the keyrings */
+		user->uid_keyring = uid_keyring;
+		user->session_keyring = session_keyring;
 	}
 
-	/* install the keyrings */
-	user->uid_keyring = uid_keyring;
-	user->session_keyring = session_keyring;
-	ret = 0;
+	mutex_unlock(&key_user_keyring_mutex);
+	kleave(" = 0");
+	return 0;
 
+error_release_both:
+	key_put(session_keyring);
+error_release:
+	key_put(uid_keyring);
 error:
+	mutex_unlock(&key_user_keyring_mutex);
+	kleave(" = %d", ret);
 	return ret;
-
-} /* end alloc_uid_keyring() */
+}
 
 /*****************************************************************************/
 /*
@@ -481,7 +490,7 @@ key_ref_t search_process_keyrings(struct key_type *type,
 		}
 	}
 	/* or search the user-session keyring */
-	else {
+	else if (context->user->session_keyring) {
 		key_ref = keyring_search_aux(
 			make_key_ref(context->user->session_keyring, 1),
 			context, type, description, match);
@@ -614,6 +623,9 @@ key_ref_t lookup_user_key(struct task_struct *context, key_serial_t id,
 		if (!context->signal->session_keyring) {
 			/* always install a session keyring upon access if one
 			 * doesn't exist yet */
+			ret = install_user_keyrings(context);
+			if (ret < 0)
+				goto error;
 			ret = install_session_keyring(
 				context, context->user->session_keyring);
 			if (ret < 0)
@@ -628,12 +640,24 @@ key_ref_t lookup_user_key(struct task_struct *context, key_serial_t id,
 		break;
 
 	case KEY_SPEC_USER_KEYRING:
+		if (!context->user->uid_keyring) {
+			ret = install_user_keyrings(context);
+			if (ret < 0)
+				goto error;
+		}
+
 		key = context->user->uid_keyring;
 		atomic_inc(&key->usage);
 		key_ref = make_key_ref(key, 1);
 		break;
 
 	case KEY_SPEC_USER_SESSION_KEYRING:
+		if (!context->user->session_keyring) {
+			ret = install_user_keyrings(context);
+			if (ret < 0)
+				goto error;
+		}
+
 		key = context->user->session_keyring;
 		atomic_inc(&key->usage);
 		key_ref = make_key_ref(key, 1);
@@ -744,7 +768,7 @@ long join_session_keyring(const char *name)
 	mutex_lock(&key_session_mutex);
 
 	/* look for an existing keyring of this name */
-	keyring = find_keyring_by_name(name, 0);
+	keyring = find_keyring_by_name(name, false);
 	if (PTR_ERR(keyring) == -ENOKEY) {
 		/* not found - try and create a new one */
 		keyring = keyring_alloc(name, tsk->uid, tsk->gid, tsk,
diff --git a/trunk/security/keys/request_key.c b/trunk/security/keys/request_key.c
index 5ecc5057fb54..ba32ca6469bd 100644
--- a/trunk/security/keys/request_key.c
+++ b/trunk/security/keys/request_key.c
@@ -16,6 +16,7 @@
 #include <linux/kmod.h>
 #include <linux/err.h>
 #include <linux/keyctl.h>
+#include <linux/slab.h>
 #include "internal.h"
 
 /*
@@ -161,21 +162,22 @@ static int call_sbin_request_key(struct key_construction *cons,
  * call out to userspace for key construction
  * - we ignore program failure and go on key status instead
  */
-static int construct_key(struct key *key, const char *callout_info, void *aux)
+static int construct_key(struct key *key, const void *callout_info,
+			 size_t callout_len, void *aux)
 {
 	struct key_construction *cons;
 	request_key_actor_t actor;
 	struct key *authkey;
 	int ret;
 
-	kenter("%d,%s,%p", key->serial, callout_info, aux);
+	kenter("%d,%p,%zu,%p", key->serial, callout_info, callout_len, aux);
 
 	cons = kmalloc(sizeof(*cons), GFP_KERNEL);
 	if (!cons)
 		return -ENOMEM;
 
 	/* allocate an authorisation key */
-	authkey = request_key_auth_new(key, callout_info);
+	authkey = request_key_auth_new(key, callout_info, callout_len);
 	if (IS_ERR(authkey)) {
 		kfree(cons);
 		ret = PTR_ERR(authkey);
@@ -331,6 +333,7 @@ static int construct_alloc_key(struct key_type *type,
 static struct key *construct_key_and_link(struct key_type *type,
 					  const char *description,
 					  const char *callout_info,
+					  size_t callout_len,
 					  void *aux,
 					  struct key *dest_keyring,
 					  unsigned long flags)
@@ -348,7 +351,7 @@ static struct key *construct_key_and_link(struct key_type *type,
 	key_user_put(user);
 
 	if (ret == 0) {
-		ret = construct_key(key, callout_info, aux);
+		ret = construct_key(key, callout_info, callout_len, aux);
 		if (ret < 0)
 			goto construction_failed;
 	}
@@ -370,7 +373,8 @@ static struct key *construct_key_and_link(struct key_type *type,
  */
 struct key *request_key_and_link(struct key_type *type,
 				 const char *description,
-				 const char *callout_info,
+				 const void *callout_info,
+				 size_t callout_len,
 				 void *aux,
 				 struct key *dest_keyring,
 				 unsigned long flags)
@@ -378,8 +382,8 @@ struct key *request_key_and_link(struct key_type *type,
 	struct key *key;
 	key_ref_t key_ref;
 
-	kenter("%s,%s,%s,%p,%p,%lx",
-	       type->name, description, callout_info, aux,
+	kenter("%s,%s,%p,%zu,%p,%p,%lx",
+	       type->name, description, callout_info, callout_len, aux,
 	       dest_keyring, flags);
 
 	/* search all the process keyrings for a key */
@@ -398,7 +402,8 @@ struct key *request_key_and_link(struct key_type *type,
 			goto error;
 
 		key = construct_key_and_link(type, description, callout_info,
-					     aux, dest_keyring, flags);
+					     callout_len, aux, dest_keyring,
+					     flags);
 	}
 
 error:
@@ -434,10 +439,13 @@ struct key *request_key(struct key_type *type,
 			const char *callout_info)
 {
 	struct key *key;
+	size_t callout_len = 0;
 	int ret;
 
-	key = request_key_and_link(type, description, callout_info, NULL,
-				   NULL, KEY_ALLOC_IN_QUOTA);
+	if (callout_info)
+		callout_len = strlen(callout_info);
+	key = request_key_and_link(type, description, callout_info, callout_len,
+				   NULL, NULL, KEY_ALLOC_IN_QUOTA);
 	if (!IS_ERR(key)) {
 		ret = wait_for_key_construction(key, false);
 		if (ret < 0) {
@@ -458,14 +466,15 @@ EXPORT_SYMBOL(request_key);
  */
 struct key *request_key_with_auxdata(struct key_type *type,
 				     const char *description,
-				     const char *callout_info,
+				     const void *callout_info,
+				     size_t callout_len,
 				     void *aux)
 {
 	struct key *key;
 	int ret;
 
-	key = request_key_and_link(type, description, callout_info, aux,
-				   NULL, KEY_ALLOC_IN_QUOTA);
+	key = request_key_and_link(type, description, callout_info, callout_len,
+				   aux, NULL, KEY_ALLOC_IN_QUOTA);
 	if (!IS_ERR(key)) {
 		ret = wait_for_key_construction(key, false);
 		if (ret < 0) {
@@ -485,10 +494,12 @@ EXPORT_SYMBOL(request_key_with_auxdata);
  */
 struct key *request_key_async(struct key_type *type,
 			      const char *description,
-			      const char *callout_info)
+			      const void *callout_info,
+			      size_t callout_len)
 {
-	return request_key_and_link(type, description, callout_info, NULL,
-				    NULL, KEY_ALLOC_IN_QUOTA);
+	return request_key_and_link(type, description, callout_info,
+				    callout_len, NULL, NULL,
+				    KEY_ALLOC_IN_QUOTA);
 }
 EXPORT_SYMBOL(request_key_async);
 
@@ -500,10 +511,11 @@ EXPORT_SYMBOL(request_key_async);
  */
 struct key *request_key_async_with_auxdata(struct key_type *type,
 					   const char *description,
-					   const char *callout_info,
+					   const void *callout_info,
+					   size_t callout_len,
 					   void *aux)
 {
-	return request_key_and_link(type, description, callout_info, aux,
-				    NULL, KEY_ALLOC_IN_QUOTA);
+	return request_key_and_link(type, description, callout_info,
+				    callout_len, aux, NULL, KEY_ALLOC_IN_QUOTA);
 }
 EXPORT_SYMBOL(request_key_async_with_auxdata);
diff --git a/trunk/security/keys/request_key_auth.c b/trunk/security/keys/request_key_auth.c
index e42b5252486f..bd237b0a6331 100644
--- a/trunk/security/keys/request_key_auth.c
+++ b/trunk/security/keys/request_key_auth.c
@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/err.h>
 #include <linux/seq_file.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
@@ -61,7 +62,7 @@ static void request_key_auth_describe(const struct key *key,
 
 	seq_puts(m, "key:");
 	seq_puts(m, key->description);
-	seq_printf(m, " pid:%d ci:%zu", rka->pid, strlen(rka->callout_info));
+	seq_printf(m, " pid:%d ci:%zu", rka->pid, rka->callout_len);
 
 } /* end request_key_auth_describe() */
 
@@ -77,7 +78,7 @@ static long request_key_auth_read(const struct key *key,
 	size_t datalen;
 	long ret;
 
-	datalen = strlen(rka->callout_info);
+	datalen = rka->callout_len;
 	ret = datalen;
 
 	/* we can return the data as is */
@@ -137,7 +138,8 @@ static void request_key_auth_destroy(struct key *key)
  * create an authorisation token for /sbin/request-key or whoever to gain
  * access to the caller's security data
  */
-struct key *request_key_auth_new(struct key *target, const char *callout_info)
+struct key *request_key_auth_new(struct key *target, const void *callout_info,
+				 size_t callout_len)
 {
 	struct request_key_auth *rka, *irka;
 	struct key *authkey = NULL;
@@ -152,7 +154,7 @@ struct key *request_key_auth_new(struct key *target, const char *callout_info)
 		kleave(" = -ENOMEM");
 		return ERR_PTR(-ENOMEM);
 	}
-	rka->callout_info = kmalloc(strlen(callout_info) + 1, GFP_KERNEL);
+	rka->callout_info = kmalloc(callout_len, GFP_KERNEL);
 	if (!rka->callout_info) {
 		kleave(" = -ENOMEM");
 		kfree(rka);
@@ -186,7 +188,8 @@ struct key *request_key_auth_new(struct key *target, const char *callout_info)
 	}
 
 	rka->target_key = key_get(target);
-	strcpy(rka->callout_info, callout_info);
+	memcpy(rka->callout_info, callout_info, callout_len);
+	rka->callout_len = callout_len;
 
 	/* allocate the auth key */
 	sprintf(desc, "%x", target->serial);
diff --git a/trunk/security/keys/sysctl.c b/trunk/security/keys/sysctl.c
new file mode 100644
index 000000000000..b611d493c2d8
--- /dev/null
+++ b/trunk/security/keys/sysctl.c
@@ -0,0 +1,50 @@
+/* Key management controls
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/key.h>
+#include <linux/sysctl.h>
+#include "internal.h"
+
+ctl_table key_sysctls[] = {
+	{
+		.ctl_name = CTL_UNNUMBERED,
+		.procname = "maxkeys",
+		.data = &key_quota_maxkeys,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = &proc_dointvec,
+	},
+	{
+		.ctl_name = CTL_UNNUMBERED,
+		.procname = "maxbytes",
+		.data = &key_quota_maxbytes,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = &proc_dointvec,
+	},
+	{
+		.ctl_name = CTL_UNNUMBERED,
+		.procname = "root_maxkeys",
+		.data = &key_quota_root_maxkeys,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = &proc_dointvec,
+	},
+	{
+		.ctl_name = CTL_UNNUMBERED,
+		.procname = "root_maxbytes",
+		.data = &key_quota_root_maxbytes,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = &proc_dointvec,
+	},
+	{ .ctl_name = 0 }
+};
diff --git a/trunk/security/root_plug.c b/trunk/security/root_plug.c
index 6112d1404c81..a41cf42a4fa0 100644
--- a/trunk/security/root_plug.c
+++ b/trunk/security/root_plug.c
@@ -86,6 +86,7 @@ static struct security_operations rootplug_security_ops = {
 
 	.task_post_setuid =		cap_task_post_setuid,
 	.task_reparent_to_init =	cap_task_reparent_to_init,
+	.task_prctl =			cap_task_prctl,
 
 	.bprm_check_security =		rootplug_bprm_check_security,
 };
diff --git a/trunk/security/security.c b/trunk/security/security.c
index 8a285c7b9962..8e64a29dc55d 100644
--- a/trunk/security/security.c
+++ b/trunk/security/security.c
@@ -491,23 +491,23 @@ void security_inode_delete(struct inode *inode)
 	security_ops->inode_delete(inode);
 }
 
-int security_inode_setxattr(struct dentry *dentry, char *name,
-			     void *value, size_t size, int flags)
+int security_inode_setxattr(struct dentry *dentry, const char *name,
+			    const void *value, size_t size, int flags)
 {
 	if (unlikely(IS_PRIVATE(dentry->d_inode)))
 		return 0;
 	return security_ops->inode_setxattr(dentry, name, value, size, flags);
 }
 
-void security_inode_post_setxattr(struct dentry *dentry, char *name,
-				   void *value, size_t size, int flags)
+void security_inode_post_setxattr(struct dentry *dentry, const char *name,
+				  const void *value, size_t size, int flags)
 {
 	if (unlikely(IS_PRIVATE(dentry->d_inode)))
 		return;
 	security_ops->inode_post_setxattr(dentry, name, value, size, flags);
 }
 
-int security_inode_getxattr(struct dentry *dentry, char *name)
+int security_inode_getxattr(struct dentry *dentry, const char *name)
 {
 	if (unlikely(IS_PRIVATE(dentry->d_inode)))
 		return 0;
@@ -521,7 +521,7 @@ int security_inode_listxattr(struct dentry *dentry)
 	return security_ops->inode_listxattr(dentry);
 }
 
-int security_inode_removexattr(struct dentry *dentry, char *name)
+int security_inode_removexattr(struct dentry *dentry, const char *name)
 {
 	if (unlikely(IS_PRIVATE(dentry->d_inode)))
 		return 0;
@@ -733,9 +733,9 @@ int security_task_wait(struct task_struct *p)
 }
 
 int security_task_prctl(int option, unsigned long arg2, unsigned long arg3,
-			 unsigned long arg4, unsigned long arg5)
+			 unsigned long arg4, unsigned long arg5, long *rc_p)
 {
-	return security_ops->task_prctl(option, arg2, arg3, arg4, arg5);
+	return security_ops->task_prctl(option, arg2, arg3, arg4, arg5, rc_p);
 }
 
 void security_task_reparent_to_init(struct task_struct *p)
@@ -1156,6 +1156,11 @@ int security_key_permission(key_ref_t key_ref,
 	return security_ops->key_permission(key_ref, context, perm);
 }
 
+int security_key_getsecurity(struct key *key, char **_buffer)
+{
+	return security_ops->key_getsecurity(key, _buffer);
+}
+
 #endif	/* CONFIG_KEYS */
 
 #ifdef CONFIG_AUDIT
diff --git a/trunk/security/selinux/hooks.c b/trunk/security/selinux/hooks.c
index 308e2cf17d75..4e4de98941ae 100644
--- a/trunk/security/selinux/hooks.c
+++ b/trunk/security/selinux/hooks.c
@@ -2619,7 +2619,7 @@ static int selinux_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
 	return dentry_has_perm(current, mnt, dentry, FILE__GETATTR);
 }
 
-static int selinux_inode_setotherxattr(struct dentry *dentry, char *name)
+static int selinux_inode_setotherxattr(struct dentry *dentry, const char *name)
 {
 	if (!strncmp(name, XATTR_SECURITY_PREFIX,
 		     sizeof XATTR_SECURITY_PREFIX - 1)) {
@@ -2638,7 +2638,8 @@ static int selinux_inode_setotherxattr(struct dentry *dentry, char *name)
 	return dentry_has_perm(current, NULL, dentry, FILE__SETATTR);
 }
 
-static int selinux_inode_setxattr(struct dentry *dentry, char *name, void *value, size_t size, int flags)
+static int selinux_inode_setxattr(struct dentry *dentry, const char *name,
+				  const void *value, size_t size, int flags)
 {
 	struct task_security_struct *tsec = current->security;
 	struct inode *inode = dentry->d_inode;
@@ -2687,8 +2688,9 @@ static int selinux_inode_setxattr(struct dentry *dentry, char *name, void *value
 			    &ad);
 }
 
-static void selinux_inode_post_setxattr(struct dentry *dentry, char *name,
-					void *value, size_t size, int flags)
+static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name,
+                                        const void *value, size_t size,
+					int flags)
 {
 	struct inode *inode = dentry->d_inode;
 	struct inode_security_struct *isec = inode->i_security;
@@ -2711,7 +2713,7 @@ static void selinux_inode_post_setxattr(struct dentry *dentry, char *name,
 	return;
 }
 
-static int selinux_inode_getxattr(struct dentry *dentry, char *name)
+static int selinux_inode_getxattr(struct dentry *dentry, const char *name)
 {
 	return dentry_has_perm(current, NULL, dentry, FILE__GETATTR);
 }
@@ -2721,7 +2723,7 @@ static int selinux_inode_listxattr(struct dentry *dentry)
 	return dentry_has_perm(current, NULL, dentry, FILE__GETATTR);
 }
 
-static int selinux_inode_removexattr(struct dentry *dentry, char *name)
+static int selinux_inode_removexattr(struct dentry *dentry, const char *name)
 {
 	if (strcmp(name, XATTR_NAME_SELINUX))
 		return selinux_inode_setotherxattr(dentry, name);
@@ -3303,12 +3305,13 @@ static int selinux_task_prctl(int option,
 			      unsigned long arg2,
 			      unsigned long arg3,
 			      unsigned long arg4,
-			      unsigned long arg5)
+			      unsigned long arg5,
+			      long *rc_p)
 {
 	/* The current prctl operations do not appear to require
 	   any SELinux controls since they merely observe or modify
 	   the state of the current process. */
-	return 0;
+	return secondary_ops->task_prctl(option, arg2, arg3, arg4, arg5, rc_p);
 }
 
 static int selinux_task_wait(struct task_struct *p)
@@ -5297,6 +5300,20 @@ static int selinux_key_permission(key_ref_t key_ref,
 			    SECCLASS_KEY, perm, NULL);
 }
 
+static int selinux_key_getsecurity(struct key *key, char **_buffer)
+{
+	struct key_security_struct *ksec = key->security;
+	char *context = NULL;
+	unsigned len;
+	int rc;
+
+	rc = security_sid_to_context(ksec->sid, &context, &len);
+	if (!rc)
+		rc = len;
+	*_buffer = context;
+	return rc;
+}
+
 #endif
 
 static struct security_operations selinux_ops = {
@@ -5485,6 +5502,7 @@ static struct security_operations selinux_ops = {
 	.key_alloc =			selinux_key_alloc,
 	.key_free =			selinux_key_free,
 	.key_permission =		selinux_key_permission,
+	.key_getsecurity =		selinux_key_getsecurity,
 #endif
 
 #ifdef CONFIG_AUDIT
@@ -5533,14 +5551,6 @@ static __init int selinux_init(void)
 	else
 		printk(KERN_DEBUG "SELinux:  Starting in permissive mode\n");
 
-#ifdef CONFIG_KEYS
-	/* Add security information to initial keyrings */
-	selinux_key_alloc(&root_user_keyring, current,
-			  KEY_ALLOC_NOT_IN_QUOTA);
-	selinux_key_alloc(&root_session_keyring, current,
-			  KEY_ALLOC_NOT_IN_QUOTA);
-#endif
-
 	return 0;
 }
 
diff --git a/trunk/security/selinux/include/avc_ss.h b/trunk/security/selinux/include/avc_ss.h
index ff869e8b6f4a..c0d314d9f8e1 100644
--- a/trunk/security/selinux/include/avc_ss.h
+++ b/trunk/security/selinux/include/avc_ss.h
@@ -10,22 +10,19 @@
 
 int avc_ss_reset(u32 seqno);
 
-struct av_perm_to_string
-{
+struct av_perm_to_string {
 	u16 tclass;
 	u32 value;
 	const char *name;
 };
 
-struct av_inherit
-{
+struct av_inherit {
 	u16 tclass;
 	const char **common_pts;
 	u32 common_base;
 };
 
-struct selinux_class_perm
-{
+struct selinux_class_perm {
 	const struct av_perm_to_string *av_perm_to_string;
 	u32 av_pts_len;
 	const char **class_to_string;
diff --git a/trunk/security/selinux/include/netlabel.h b/trunk/security/selinux/include/netlabel.h
index 9a9e7cd9a379..487a7d81fe20 100644
--- a/trunk/security/selinux/include/netlabel.h
+++ b/trunk/security/selinux/include/netlabel.h
@@ -64,7 +64,7 @@ static inline void selinux_netlbl_cache_invalidate(void)
 }
 
 static inline void selinux_netlbl_sk_security_reset(
-	                                       struct sk_security_struct *ssec,
+					       struct sk_security_struct *ssec,
 					       int family)
 {
 	return;
diff --git a/trunk/security/selinux/include/objsec.h b/trunk/security/selinux/include/objsec.h
index 300b61bad7b3..032c2357dad1 100644
--- a/trunk/security/selinux/include/objsec.h
+++ b/trunk/security/selinux/include/objsec.h
@@ -4,16 +4,16 @@
  *  This file contains the SELinux security data structures for kernel objects.
  *
  *  Author(s):  Stephen Smalley, <sds@epoch.ncsc.mil>
- *              Chris Vance, <cvance@nai.com>
- *              Wayne Salamon, <wsalamon@nai.com>
- *              James Morris <jmorris@redhat.com>
+ *		Chris Vance, <cvance@nai.com>
+ *		Wayne Salamon, <wsalamon@nai.com>
+ *		James Morris <jmorris@redhat.com>
  *
  *  Copyright (C) 2001,2002 Networks Associates Technology, Inc.
  *  Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com>
  *
  *	This program is free software; you can redistribute it and/or modify
  *	it under the terms of the GNU General Public License version 2,
- *      as published by the Free Software Foundation.
+ *	as published by the Free Software Foundation.
  */
 #ifndef _SELINUX_OBJSEC_H_
 #define _SELINUX_OBJSEC_H_
@@ -28,58 +28,58 @@
 #include "avc.h"
 
 struct task_security_struct {
-	u32 osid;            /* SID prior to last execve */
-	u32 sid;             /* current SID */
-	u32 exec_sid;        /* exec SID */
-	u32 create_sid;      /* fscreate SID */
-	u32 keycreate_sid;   /* keycreate SID */
-	u32 sockcreate_sid;  /* fscreate SID */
+	u32 osid;		/* SID prior to last execve */
+	u32 sid;		/* current SID */
+	u32 exec_sid;		/* exec SID */
+	u32 create_sid;		/* fscreate SID */
+	u32 keycreate_sid;	/* keycreate SID */
+	u32 sockcreate_sid;	/* fscreate SID */
 };
 
 struct inode_security_struct {
-        struct inode *inode;           /* back pointer to inode object */
-	struct list_head list;         /* list of inode_security_struct */
-	u32 task_sid;        /* SID of creating task */
-	u32 sid;             /* SID of this object */
-	u16 sclass;       /* security class of this object */
-	unsigned char initialized;     /* initialization flag */
+	struct inode *inode;	/* back pointer to inode object */
+	struct list_head list;	/* list of inode_security_struct */
+	u32 task_sid;		/* SID of creating task */
+	u32 sid;		/* SID of this object */
+	u16 sclass;		/* security class of this object */
+	unsigned char initialized;	/* initialization flag */
 	struct mutex lock;
-	unsigned char inherit;         /* inherit SID from parent entry */
+	unsigned char inherit;	/* inherit SID from parent entry */
 };
 
 struct file_security_struct {
-	u32 sid;              /* SID of open file description */
-	u32 fown_sid;         /* SID of file owner (for SIGIO) */
-	u32 isid;             /* SID of inode at the time of file open */
-	u32 pseqno;           /* Policy seqno at the time of file open */
+	u32 sid;		/* SID of open file description */
+	u32 fown_sid;		/* SID of file owner (for SIGIO) */
+	u32 isid;		/* SID of inode at the time of file open */
+	u32 pseqno;		/* Policy seqno at the time of file open */
 };
 
 struct superblock_security_struct {
-	struct super_block *sb;         /* back pointer to sb object */
-	struct list_head list;          /* list of superblock_security_struct */
+	struct super_block *sb;		/* back pointer to sb object */
+	struct list_head list;		/* list of superblock_security_struct */
 	u32 sid;			/* SID of file system superblock */
 	u32 def_sid;			/* default SID for labeling */
 	u32 mntpoint_sid;		/* SECURITY_FS_USE_MNTPOINT context for files */
-	unsigned int behavior;          /* labeling behavior */
-	unsigned char initialized;      /* initialization flag */
+	unsigned int behavior;		/* labeling behavior */
+	unsigned char initialized;	/* initialization flag */
 	unsigned char flags;		/* which mount options were specified */
-	unsigned char proc;             /* proc fs */
+	unsigned char proc;		/* proc fs */
 	struct mutex lock;
 	struct list_head isec_head;
 	spinlock_t isec_lock;
 };
 
 struct msg_security_struct {
-	u32 sid;              /* SID of message */
+	u32 sid;	/* SID of message */
 };
 
 struct ipc_security_struct {
 	u16 sclass;	/* security class of this object */
-	u32 sid;              /* SID of IPC resource */
+	u32 sid;	/* SID of IPC resource */
 };
 
 struct bprm_security_struct {
-	u32 sid;                       /* SID for transformed process */
+	u32 sid;		/* SID for transformed process */
 	unsigned char set;
 
 	/*
@@ -123,7 +123,7 @@ struct sk_security_struct {
 };
 
 struct key_security_struct {
-	u32 sid;         /* SID of key */
+	u32 sid;	/* SID of key */
 };
 
 extern unsigned int selinux_checkreqprot;
diff --git a/trunk/security/selinux/include/security.h b/trunk/security/selinux/include/security.h
index 1904c462a605..cdb14add27d2 100644
--- a/trunk/security/selinux/include/security.h
+++ b/trunk/security/selinux/include/security.h
@@ -62,7 +62,7 @@ enum {
 extern int selinux_policycap_netpeer;
 extern int selinux_policycap_openperm;
 
-int security_load_policy(void * data, size_t len);
+int security_load_policy(void *data, size_t len);
 
 int security_policycap_supported(unsigned int req_cap);
 
@@ -93,7 +93,7 @@ int security_change_sid(u32 ssid, u32 tsid,
 int security_sid_to_context(u32 sid, char **scontext,
 	u32 *scontext_len);
 
-int security_context_to_sid(char *scontext, u32 scontext_len,
+int security_context_to_sid(const char *scontext, u32 scontext_len,
 	u32 *out_sid);
 
 int security_context_to_sid_default(char *scontext, u32 scontext_len,
@@ -110,7 +110,7 @@ int security_node_sid(u16 domain, void *addr, u32 addrlen,
 	u32 *out_sid);
 
 int security_validate_transition(u32 oldsid, u32 newsid, u32 tasksid,
-                                 u16 tclass);
+				 u16 tclass);
 
 int security_sid_mls_copy(u32 sid, u32 mls_sid, u32 *new_sid);
 
diff --git a/trunk/security/selinux/netnode.c b/trunk/security/selinux/netnode.c
index 2edc4c5e0c61..b6ccd09379f1 100644
--- a/trunk/security/selinux/netnode.c
+++ b/trunk/security/selinux/netnode.c
@@ -40,11 +40,17 @@
 #include <net/ipv6.h>
 #include <asm/bug.h>
 
+#include "netnode.h"
 #include "objsec.h"
 
 #define SEL_NETNODE_HASH_SIZE       256
 #define SEL_NETNODE_HASH_BKT_LIMIT   16
 
+struct sel_netnode_bkt {
+	unsigned int size;
+	struct list_head list;
+};
+
 struct sel_netnode {
 	struct netnode_security_struct nsec;
 
@@ -60,7 +66,7 @@ struct sel_netnode {
 
 static LIST_HEAD(sel_netnode_list);
 static DEFINE_SPINLOCK(sel_netnode_lock);
-static struct list_head sel_netnode_hash[SEL_NETNODE_HASH_SIZE];
+static struct sel_netnode_bkt sel_netnode_hash[SEL_NETNODE_HASH_SIZE];
 
 /**
  * sel_netnode_free - Frees a node entry
@@ -87,7 +93,7 @@ static void sel_netnode_free(struct rcu_head *p)
  * the bucket number for the given IP address.
  *
  */
-static u32 sel_netnode_hashfn_ipv4(__be32 addr)
+static unsigned int sel_netnode_hashfn_ipv4(__be32 addr)
 {
 	/* at some point we should determine if the mismatch in byte order
 	 * affects the hash function dramatically */
@@ -103,7 +109,7 @@ static u32 sel_netnode_hashfn_ipv4(__be32 addr)
  * the bucket number for the given IP address.
  *
  */
-static u32 sel_netnode_hashfn_ipv6(const struct in6_addr *addr)
+static unsigned int sel_netnode_hashfn_ipv6(const struct in6_addr *addr)
 {
 	/* just hash the least significant 32 bits to keep things fast (they
 	 * are the most likely to be different anyway), we can revisit this
@@ -123,7 +129,7 @@ static u32 sel_netnode_hashfn_ipv6(const struct in6_addr *addr)
  */
 static struct sel_netnode *sel_netnode_find(const void *addr, u16 family)
 {
-	u32 idx;
+	unsigned int idx;
 	struct sel_netnode *node;
 
 	switch (family) {
@@ -137,7 +143,7 @@ static struct sel_netnode *sel_netnode_find(const void *addr, u16 family)
 		BUG();
 	}
 
-	list_for_each_entry_rcu(node, &sel_netnode_hash[idx], list)
+	list_for_each_entry_rcu(node, &sel_netnode_hash[idx].list, list)
 		if (node->nsec.family == family)
 			switch (family) {
 			case PF_INET:
@@ -159,15 +165,12 @@ static struct sel_netnode *sel_netnode_find(const void *addr, u16 family)
  * @node: the new node record
  *
  * Description:
- * Add a new node record to the network address hash table.  Returns zero on
- * success, negative values on failure.
+ * Add a new node record to the network address hash table.
  *
  */
-static int sel_netnode_insert(struct sel_netnode *node)
+static void sel_netnode_insert(struct sel_netnode *node)
 {
-	u32 idx;
-	u32 count = 0;
-	struct sel_netnode *iter;
+	unsigned int idx;
 
 	switch (node->nsec.family) {
 	case PF_INET:
@@ -179,32 +182,21 @@ static int sel_netnode_insert(struct sel_netnode *node)
 	default:
 		BUG();
 	}
-	list_add_rcu(&node->list, &sel_netnode_hash[idx]);
+
+	INIT_RCU_HEAD(&node->rcu);
 
 	/* we need to impose a limit on the growth of the hash table so check
 	 * this bucket to make sure it is within the specified bounds */
-	list_for_each_entry(iter, &sel_netnode_hash[idx], list)
-		if (++count > SEL_NETNODE_HASH_BKT_LIMIT) {
-			list_del_rcu(&iter->list);
-			call_rcu(&iter->rcu, sel_netnode_free);
-			break;
-		}
-
-	return 0;
-}
-
-/**
- * sel_netnode_destroy - Remove a node record from the table
- * @node: the existing node record
- *
- * Description:
- * Remove an existing node record from the network address table.
- *
- */
-static void sel_netnode_destroy(struct sel_netnode *node)
-{
-	list_del_rcu(&node->list);
-	call_rcu(&node->rcu, sel_netnode_free);
+	list_add_rcu(&node->list, &sel_netnode_hash[idx].list);
+	if (sel_netnode_hash[idx].size == SEL_NETNODE_HASH_BKT_LIMIT) {
+		struct sel_netnode *tail;
+		tail = list_entry(
+			rcu_dereference(sel_netnode_hash[idx].list.prev),
+			struct sel_netnode, list);
+		list_del_rcu(&tail->list);
+		call_rcu(&tail->rcu, sel_netnode_free);
+	} else
+		sel_netnode_hash[idx].size++;
 }
 
 /**
@@ -222,7 +214,7 @@ static void sel_netnode_destroy(struct sel_netnode *node)
  */
 static int sel_netnode_sid_slow(void *addr, u16 family, u32 *sid)
 {
-	int ret;
+	int ret = -ENOMEM;
 	struct sel_netnode *node;
 	struct sel_netnode *new = NULL;
 
@@ -230,25 +222,21 @@ static int sel_netnode_sid_slow(void *addr, u16 family, u32 *sid)
 	node = sel_netnode_find(addr, family);
 	if (node != NULL) {
 		*sid = node->nsec.sid;
-		ret = 0;
-		goto out;
+		spin_unlock_bh(&sel_netnode_lock);
+		return 0;
 	}
 	new = kzalloc(sizeof(*new), GFP_ATOMIC);
-	if (new == NULL) {
-		ret = -ENOMEM;
+	if (new == NULL)
 		goto out;
-	}
 	switch (family) {
 	case PF_INET:
 		ret = security_node_sid(PF_INET,
-					addr, sizeof(struct in_addr),
-					&new->nsec.sid);
+					addr, sizeof(struct in_addr), sid);
 		new->nsec.addr.ipv4 = *(__be32 *)addr;
 		break;
 	case PF_INET6:
 		ret = security_node_sid(PF_INET6,
-					addr, sizeof(struct in6_addr),
-					&new->nsec.sid);
+					addr, sizeof(struct in6_addr), sid);
 		ipv6_addr_copy(&new->nsec.addr.ipv6, addr);
 		break;
 	default:
@@ -256,11 +244,10 @@ static int sel_netnode_sid_slow(void *addr, u16 family, u32 *sid)
 	}
 	if (ret != 0)
 		goto out;
+
 	new->nsec.family = family;
-	ret = sel_netnode_insert(new);
-	if (ret != 0)
-		goto out;
-	*sid = new->nsec.sid;
+	new->nsec.sid = *sid;
+	sel_netnode_insert(new);
 
 out:
 	spin_unlock_bh(&sel_netnode_lock);
@@ -312,13 +299,18 @@ int sel_netnode_sid(void *addr, u16 family, u32 *sid)
  */
 static void sel_netnode_flush(void)
 {
-	u32 idx;
-	struct sel_netnode *node;
+	unsigned int idx;
+	struct sel_netnode *node, *node_tmp;
 
 	spin_lock_bh(&sel_netnode_lock);
-	for (idx = 0; idx < SEL_NETNODE_HASH_SIZE; idx++)
-		list_for_each_entry(node, &sel_netnode_hash[idx], list)
-			sel_netnode_destroy(node);
+	for (idx = 0; idx < SEL_NETNODE_HASH_SIZE; idx++) {
+		list_for_each_entry_safe(node, node_tmp,
+					 &sel_netnode_hash[idx].list, list) {
+				list_del_rcu(&node->list);
+				call_rcu(&node->rcu, sel_netnode_free);
+		}
+		sel_netnode_hash[idx].size = 0;
+	}
 	spin_unlock_bh(&sel_netnode_lock);
 }
 
@@ -340,8 +332,10 @@ static __init int sel_netnode_init(void)
 	if (!selinux_enabled)
 		return 0;
 
-	for (iter = 0; iter < SEL_NETNODE_HASH_SIZE; iter++)
-		INIT_LIST_HEAD(&sel_netnode_hash[iter]);
+	for (iter = 0; iter < SEL_NETNODE_HASH_SIZE; iter++) {
+		INIT_LIST_HEAD(&sel_netnode_hash[iter].list);
+		sel_netnode_hash[iter].size = 0;
+	}
 
 	ret = avc_add_callback(sel_netnode_avc_callback, AVC_CALLBACK_RESET,
 			       SECSID_NULL, SECSID_NULL, SECCLASS_NULL, 0);
diff --git a/trunk/security/selinux/netport.c b/trunk/security/selinux/netport.c
index 68ede3c498ab..90b4cff7c350 100644
--- a/trunk/security/selinux/netport.c
+++ b/trunk/security/selinux/netport.c
@@ -114,8 +114,7 @@ static struct sel_netport *sel_netport_find(u8 protocol, u16 pnum)
 
 	idx = sel_netport_hashfn(pnum);
 	list_for_each_entry_rcu(port, &sel_netport_hash[idx].list, list)
-		if (port->psec.port == pnum &&
-		    port->psec.protocol == protocol)
+		if (port->psec.port == pnum && port->psec.protocol == protocol)
 			return port;
 
 	return NULL;
@@ -126,11 +125,10 @@ static struct sel_netport *sel_netport_find(u8 protocol, u16 pnum)
  * @port: the new port record
  *
  * Description:
- * Add a new port record to the network address hash table.  Returns zero on
- * success, negative values on failure.
+ * Add a new port record to the network address hash table.
  *
  */
-static int sel_netport_insert(struct sel_netport *port)
+static void sel_netport_insert(struct sel_netport *port)
 {
 	unsigned int idx;
 
@@ -140,13 +138,13 @@ static int sel_netport_insert(struct sel_netport *port)
 	list_add_rcu(&port->list, &sel_netport_hash[idx].list);
 	if (sel_netport_hash[idx].size == SEL_NETPORT_HASH_BKT_LIMIT) {
 		struct sel_netport *tail;
-		tail = list_entry(port->list.prev, struct sel_netport, list);
-		list_del_rcu(port->list.prev);
+		tail = list_entry(
+			rcu_dereference(sel_netport_hash[idx].list.prev),
+			struct sel_netport, list);
+		list_del_rcu(&tail->list);
 		call_rcu(&tail->rcu, sel_netport_free);
 	} else
 		sel_netport_hash[idx].size++;
-
-	return 0;
 }
 
 /**
@@ -163,7 +161,7 @@ static int sel_netport_insert(struct sel_netport *port)
  */
 static int sel_netport_sid_slow(u8 protocol, u16 pnum, u32 *sid)
 {
-	int ret;
+	int ret = -ENOMEM;
 	struct sel_netport *port;
 	struct sel_netport *new = NULL;
 
@@ -171,23 +169,20 @@ static int sel_netport_sid_slow(u8 protocol, u16 pnum, u32 *sid)
 	port = sel_netport_find(protocol, pnum);
 	if (port != NULL) {
 		*sid = port->psec.sid;
-		ret = 0;
-		goto out;
+		spin_unlock_bh(&sel_netport_lock);
+		return 0;
 	}
 	new = kzalloc(sizeof(*new), GFP_ATOMIC);
-	if (new == NULL) {
-		ret = -ENOMEM;
+	if (new == NULL)
 		goto out;
-	}
-	ret = security_port_sid(protocol, pnum, &new->psec.sid);
+	ret = security_port_sid(protocol, pnum, sid);
 	if (ret != 0)
 		goto out;
+
 	new->psec.port = pnum;
 	new->psec.protocol = protocol;
-	ret = sel_netport_insert(new);
-	if (ret != 0)
-		goto out;
-	*sid = new->psec.sid;
+	new->psec.sid = *sid;
+	sel_netport_insert(new);
 
 out:
 	spin_unlock_bh(&sel_netport_lock);
@@ -239,11 +234,12 @@ int sel_netport_sid(u8 protocol, u16 pnum, u32 *sid)
 static void sel_netport_flush(void)
 {
 	unsigned int idx;
-	struct sel_netport *port;
+	struct sel_netport *port, *port_tmp;
 
 	spin_lock_bh(&sel_netport_lock);
 	for (idx = 0; idx < SEL_NETPORT_HASH_SIZE; idx++) {
-		list_for_each_entry(port, &sel_netport_hash[idx].list, list) {
+		list_for_each_entry_safe(port, port_tmp,
+					 &sel_netport_hash[idx].list, list) {
 			list_del_rcu(&port->list);
 			call_rcu(&port->rcu, sel_netport_free);
 		}
diff --git a/trunk/security/selinux/ss/conditional.h b/trunk/security/selinux/ss/conditional.h
index f3a1fc6e5d66..65b9f8366e9c 100644
--- a/trunk/security/selinux/ss/conditional.h
+++ b/trunk/security/selinux/ss/conditional.h
@@ -59,10 +59,10 @@ struct cond_node {
 	struct cond_node *next;
 };
 
-int cond_policydb_init(struct policydb* p);
-void cond_policydb_destroy(struct policydb* p);
+int cond_policydb_init(struct policydb *p);
+void cond_policydb_destroy(struct policydb *p);
 
-int cond_init_bool_indexes(struct policydb* p);
+int cond_init_bool_indexes(struct policydb *p);
 int cond_destroy_bool(void *key, void *datum, void *p);
 
 int cond_index_bool(void *key, void *datum, void *datap);
diff --git a/trunk/security/selinux/ss/context.h b/trunk/security/selinux/ss/context.h
index 2eee0dab524d..b9a6f7fc62fc 100644
--- a/trunk/security/selinux/ss/context.h
+++ b/trunk/security/selinux/ss/context.h
@@ -84,9 +84,9 @@ static inline int mls_context_cmp(struct context *c1, struct context *c2)
 		return 1;
 
 	return ((c1->range.level[0].sens == c2->range.level[0].sens) &&
-		ebitmap_cmp(&c1->range.level[0].cat,&c2->range.level[0].cat) &&
+		ebitmap_cmp(&c1->range.level[0].cat, &c2->range.level[0].cat) &&
 		(c1->range.level[1].sens == c2->range.level[1].sens) &&
-		ebitmap_cmp(&c1->range.level[1].cat,&c2->range.level[1].cat));
+		ebitmap_cmp(&c1->range.level[1].cat, &c2->range.level[1].cat));
 }
 
 static inline void mls_context_destroy(struct context *c)
diff --git a/trunk/security/selinux/ss/hashtab.h b/trunk/security/selinux/ss/hashtab.h
index 7e2ff3e3c6d2..953872cd84ab 100644
--- a/trunk/security/selinux/ss/hashtab.h
+++ b/trunk/security/selinux/ss/hashtab.h
@@ -40,8 +40,8 @@ struct hashtab_info {
  * the new hash table otherwise.
  */
 struct hashtab *hashtab_create(u32 (*hash_value)(struct hashtab *h, const void *key),
-                               int (*keycmp)(struct hashtab *h, const void *key1, const void *key2),
-                               u32 size);
+			       int (*keycmp)(struct hashtab *h, const void *key1, const void *key2),
+			       u32 size);
 
 /*
  * Inserts the specified (key, datum) pair into the specified hash table.
@@ -49,7 +49,7 @@ struct hashtab *hashtab_create(u32 (*hash_value)(struct hashtab *h, const void *
  * Returns -ENOMEM on memory allocation error,
  * -EEXIST if there is already an entry with the same key,
  * -EINVAL for general errors or
- * 0 otherwise.
+  0 otherwise.
  */
 int hashtab_insert(struct hashtab *h, void *k, void *d);
 
diff --git a/trunk/security/selinux/ss/mls.h b/trunk/security/selinux/ss/mls.h
index ab53663d9f5f..0fdf6257ef64 100644
--- a/trunk/security/selinux/ss/mls.h
+++ b/trunk/security/selinux/ss/mls.h
@@ -13,7 +13,7 @@
 /*
  * Updated: Hewlett-Packard <paul.moore@hp.com>
  *
- *      Added support to import/export the MLS label from NetLabel
+ *	Added support to import/export the MLS label from NetLabel
  *
  * (c) Copyright Hewlett-Packard Development Company, L.P., 2006
  */
@@ -31,7 +31,7 @@ int mls_range_isvalid(struct policydb *p, struct mls_range *r);
 int mls_level_isvalid(struct policydb *p, struct mls_level *l);
 
 int mls_context_to_sid(char oldc,
-	               char **scontext,
+		       char **scontext,
 		       struct context *context,
 		       struct sidtab *s,
 		       u32 def_sid);
@@ -49,7 +49,7 @@ int mls_compute_sid(struct context *scontext,
 		    struct context *newcontext);
 
 int mls_setup_user_range(struct context *fromcon, struct user_datum *user,
-                         struct context *usercon);
+			 struct context *usercon);
 
 #ifdef CONFIG_NETLABEL
 void mls_export_netlbl_lvl(struct context *context,
diff --git a/trunk/security/selinux/ss/mls_types.h b/trunk/security/selinux/ss/mls_types.h
index 0c692d58d489..b6e943a21061 100644
--- a/trunk/security/selinux/ss/mls_types.h
+++ b/trunk/security/selinux/ss/mls_types.h
@@ -31,7 +31,7 @@ static inline int mls_level_eq(struct mls_level *l1, struct mls_level *l2)
 		return 1;
 
 	return ((l1->sens == l2->sens) &&
-	        ebitmap_cmp(&l1->cat, &l2->cat));
+		ebitmap_cmp(&l1->cat, &l2->cat));
 }
 
 static inline int mls_level_dom(struct mls_level *l1, struct mls_level *l2)
@@ -40,7 +40,7 @@ static inline int mls_level_dom(struct mls_level *l1, struct mls_level *l2)
 		return 1;
 
 	return ((l1->sens >= l2->sens) &&
-	        ebitmap_contains(&l1->cat, &l2->cat));
+		ebitmap_contains(&l1->cat, &l2->cat));
 }
 
 #define mls_level_incomp(l1, l2) \
diff --git a/trunk/security/selinux/ss/policydb.h b/trunk/security/selinux/ss/policydb.h
index ba593a3da877..4253370fda6a 100644
--- a/trunk/security/selinux/ss/policydb.h
+++ b/trunk/security/selinux/ss/policydb.h
@@ -12,12 +12,12 @@
  *
  * Updated: Frank Mayer <mayerf@tresys.com> and Karl MacMillan <kmacmillan@tresys.com>
  *
- * 	Added conditional policy language extensions
+ *	Added conditional policy language extensions
  *
  * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc.
  * Copyright (C) 2003 - 2004 Tresys Technology, LLC
  *	This program is free software; you can redistribute it and/or modify
- *  	it under the terms of the GNU General Public License as published by
+ *	it under the terms of the GNU General Public License as published by
  *	the Free Software Foundation, version 2.
  */
 
@@ -221,7 +221,7 @@ struct policydb {
 	/* type enforcement conditional access vectors and transitions */
 	struct avtab te_cond_avtab;
 	/* linked list indexing te_cond_avtab by conditional */
-	struct cond_node* cond_list;
+	struct cond_node *cond_list;
 
 	/* role allows */
 	struct role_allow *role_allow;
@@ -230,10 +230,10 @@ struct policydb {
 	   TCP or UDP port numbers, network interfaces and nodes */
 	struct ocontext *ocontexts[OCON_NUM];
 
-        /* security contexts for files in filesystems that cannot support
+	/* security contexts for files in filesystems that cannot support
 	   a persistent label mapping or use another
 	   fixed labeling behavior. */
-  	struct genfs *genfs;
+	struct genfs *genfs;
 
 	/* range transitions */
 	struct range_trans *range_tr;
diff --git a/trunk/security/selinux/ss/services.c b/trunk/security/selinux/ss/services.c
index 2daaddbb301d..25cac5a2aa8e 100644
--- a/trunk/security/selinux/ss/services.c
+++ b/trunk/security/selinux/ss/services.c
@@ -708,7 +708,7 @@ int security_sid_to_context(u32 sid, char **scontext, u32 *scontext_len)
 
 }
 
-static int security_context_to_sid_core(char *scontext, u32 scontext_len,
+static int security_context_to_sid_core(const char *scontext, u32 scontext_len,
 					u32 *sid, u32 def_sid, gfp_t gfp_flags)
 {
 	char *scontext2;
@@ -835,7 +835,7 @@ static int security_context_to_sid_core(char *scontext, u32 scontext_len,
  * Returns -%EINVAL if the context is invalid, -%ENOMEM if insufficient
  * memory is available, or 0 on success.
  */
-int security_context_to_sid(char *scontext, u32 scontext_len, u32 *sid)
+int security_context_to_sid(const char *scontext, u32 scontext_len, u32 *sid)
 {
 	return security_context_to_sid_core(scontext, scontext_len,
 					    sid, SECSID_NULL, GFP_KERNEL);
diff --git a/trunk/security/smack/smack_lsm.c b/trunk/security/smack/smack_lsm.c
index 4215971434e6..5d2ec5650e61 100644
--- a/trunk/security/smack/smack_lsm.c
+++ b/trunk/security/smack/smack_lsm.c
@@ -574,8 +574,8 @@ static int smack_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
  *
  * Returns 0 if access is permitted, an error code otherwise
  */
-static int smack_inode_setxattr(struct dentry *dentry, char *name,
-				void *value, size_t size, int flags)
+static int smack_inode_setxattr(struct dentry *dentry, const char *name,
+				const void *value, size_t size, int flags)
 {
 	int rc = 0;
 
@@ -604,8 +604,8 @@ static int smack_inode_setxattr(struct dentry *dentry, char *name,
  * Set the pointer in the inode blob to the entry found
  * in the master label list.
  */
-static void smack_inode_post_setxattr(struct dentry *dentry, char *name,
-				      void *value, size_t size, int flags)
+static void smack_inode_post_setxattr(struct dentry *dentry, const char *name,
+				      const void *value, size_t size, int flags)
 {
 	struct inode_smack *isp;
 	char *nsp;
@@ -641,7 +641,7 @@ static void smack_inode_post_setxattr(struct dentry *dentry, char *name,
  *
  * Returns 0 if access is permitted, an error code otherwise
  */
-static int smack_inode_getxattr(struct dentry *dentry, char *name)
+static int smack_inode_getxattr(struct dentry *dentry, const char *name)
 {
 	return smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ);
 }
@@ -655,7 +655,7 @@ static int smack_inode_getxattr(struct dentry *dentry, char *name)
  *
  * Returns 0 if access is permitted, an error code otherwise
  */
-static int smack_inode_removexattr(struct dentry *dentry, char *name)
+static int smack_inode_removexattr(struct dentry *dentry, const char *name)
 {
 	int rc = 0;
 
@@ -1242,7 +1242,7 @@ static void smack_set_catset(char *catset, struct netlbl_lsm_secattr *sap)
 	int rc;
 	int byte;
 
-	if (catset == 0)
+	if (!catset)
 		return;
 
 	sap->flags |= NETLBL_SECATTR_MLS_CAT;
@@ -2495,6 +2495,7 @@ struct security_operations smack_ops = {
 	.task_wait = 			smack_task_wait,
 	.task_reparent_to_init =	cap_task_reparent_to_init,
 	.task_to_inode = 		smack_task_to_inode,
+	.task_prctl =			cap_task_prctl,
 
 	.ipc_permission = 		smack_ipc_permission,
 
diff --git a/trunk/security/smack/smackfs.c b/trunk/security/smack/smackfs.c
index 6ba283783b70..a5da5a8cfe9b 100644
--- a/trunk/security/smack/smackfs.c
+++ b/trunk/security/smack/smackfs.c
@@ -317,7 +317,7 @@ static const struct file_operations smk_load_ops = {
 /**
  * smk_cipso_doi - initialize the CIPSO domain
  */
-void smk_cipso_doi(void)
+static void smk_cipso_doi(void)
 {
 	int rc;
 	struct cipso_v4_doi *doip;
@@ -350,7 +350,7 @@ void smk_cipso_doi(void)
 /**
  * smk_unlbl_ambient - initialize the unlabeled domain
  */
-void smk_unlbl_ambient(char *oldambient)
+static void smk_unlbl_ambient(char *oldambient)
 {
 	int rc;
 	struct netlbl_audit audit_info;
diff --git a/trunk/sound/core/info.c b/trunk/sound/core/info.c
index 9977ec2eace3..cb5ead3e202d 100644
--- a/trunk/sound/core/info.c
+++ b/trunk/sound/core/info.c
@@ -544,7 +544,7 @@ int __init snd_info_init(void)
 {
 	struct proc_dir_entry *p;
 
-	p = snd_create_proc_entry("asound", S_IFDIR | S_IRUGO | S_IXUGO, &proc_root);
+	p = snd_create_proc_entry("asound", S_IFDIR | S_IRUGO | S_IXUGO, NULL);
 	if (p == NULL)
 		return -ENOMEM;
 	snd_proc_root = p;
@@ -594,7 +594,7 @@ int __exit snd_info_done(void)
 #ifdef CONFIG_SND_OSSEMUL
 		snd_info_free_entry(snd_oss_root);
 #endif
-		snd_remove_proc_entry(&proc_root, snd_proc_root);
+		snd_remove_proc_entry(NULL, snd_proc_root);
 	}
 	return 0;
 }
diff --git a/trunk/sound/core/memalloc.c b/trunk/sound/core/memalloc.c
index 920e5780c228..23b7bc02728b 100644
--- a/trunk/sound/core/memalloc.c
+++ b/trunk/sound/core/memalloc.c
@@ -629,9 +629,8 @@ static const struct file_operations snd_mem_proc_fops = {
 static int __init snd_mem_init(void)
 {
 #ifdef CONFIG_PROC_FS
-	snd_mem_proc = create_proc_entry(SND_MEM_PROC_FILE, 0644, NULL);
-	if (snd_mem_proc)
-		snd_mem_proc->proc_fops = &snd_mem_proc_fops;
+	snd_mem_proc = proc_create(SND_MEM_PROC_FILE, 0644, NULL,
+				   &snd_mem_proc_fops);
 #endif
 	return 0;
 }
diff --git a/trunk/sound/sh/aica.c b/trunk/sound/sh/aica.c
index d49417bf78c6..9ca113326143 100644
--- a/trunk/sound/sh/aica.c
+++ b/trunk/sound/sh/aica.c
@@ -663,7 +663,7 @@ static int __init aica_init(void)
 		return err;
 	pd = platform_device_register_simple(SND_AICA_DRIVER, -1,
 					     aica_memory_space, 2);
-	if (unlikely(IS_ERR(pd))) {
+	if (IS_ERR(pd)) {
 		platform_driver_unregister(&snd_aica_driver);
 		return PTR_ERR(pd);
 	}
diff --git a/trunk/virt/kvm/kvm_main.c b/trunk/virt/kvm/kvm_main.c
index b2e12893e3f4..c82cf15730a1 100644
--- a/trunk/virt/kvm/kvm_main.c
+++ b/trunk/virt/kvm/kvm_main.c
@@ -40,6 +40,7 @@
 #include <linux/kvm_para.h>
 #include <linux/pagemap.h>
 #include <linux/mman.h>
+#include <linux/swap.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -59,7 +60,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_cache);
 
 static __read_mostly struct preempt_ops kvm_preempt_ops;
 
-static struct dentry *debugfs_dir;
+struct dentry *kvm_debugfs_dir;
 
 static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 			   unsigned long arg);
@@ -119,6 +120,29 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 	smp_call_function_mask(cpus, ack_flush, NULL, 1);
 }
 
+void kvm_reload_remote_mmus(struct kvm *kvm)
+{
+	int i, cpu;
+	cpumask_t cpus;
+	struct kvm_vcpu *vcpu;
+
+	cpus_clear(cpus);
+	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+		vcpu = kvm->vcpus[i];
+		if (!vcpu)
+			continue;
+		if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
+			continue;
+		cpu = vcpu->cpu;
+		if (cpu != -1 && cpu != raw_smp_processor_id())
+			cpu_set(cpu, cpus);
+	}
+	if (cpus_empty(cpus))
+		return;
+	smp_call_function_mask(cpus, ack_flush, NULL, 1);
+}
+
+
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 {
 	struct page *page;
@@ -170,6 +194,7 @@ static struct kvm *kvm_create_vm(void)
 	mutex_init(&kvm->lock);
 	kvm_io_bus_init(&kvm->mmio_bus);
 	init_rwsem(&kvm->slots_lock);
+	atomic_set(&kvm->users_count, 1);
 	spin_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
 	spin_unlock(&kvm_lock);
@@ -189,9 +214,13 @@ static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
 	if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
 		vfree(free->dirty_bitmap);
 
+	if (!dont || free->lpage_info != dont->lpage_info)
+		vfree(free->lpage_info);
+
 	free->npages = 0;
 	free->dirty_bitmap = NULL;
 	free->rmap = NULL;
+	free->lpage_info = NULL;
 }
 
 void kvm_free_physmem(struct kvm *kvm)
@@ -215,11 +244,25 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	mmdrop(mm);
 }
 
+void kvm_get_kvm(struct kvm *kvm)
+{
+	atomic_inc(&kvm->users_count);
+}
+EXPORT_SYMBOL_GPL(kvm_get_kvm);
+
+void kvm_put_kvm(struct kvm *kvm)
+{
+	if (atomic_dec_and_test(&kvm->users_count))
+		kvm_destroy_vm(kvm);
+}
+EXPORT_SYMBOL_GPL(kvm_put_kvm);
+
+
 static int kvm_vm_release(struct inode *inode, struct file *filp)
 {
 	struct kvm *kvm = filp->private_data;
 
-	kvm_destroy_vm(kvm);
+	kvm_put_kvm(kvm);
 	return 0;
 }
 
@@ -301,6 +344,25 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		new.user_alloc = user_alloc;
 		new.userspace_addr = mem->userspace_addr;
 	}
+	if (npages && !new.lpage_info) {
+		int largepages = npages / KVM_PAGES_PER_HPAGE;
+		if (npages % KVM_PAGES_PER_HPAGE)
+			largepages++;
+		if (base_gfn % KVM_PAGES_PER_HPAGE)
+			largepages++;
+
+		new.lpage_info = vmalloc(largepages * sizeof(*new.lpage_info));
+
+		if (!new.lpage_info)
+			goto out_free;
+
+		memset(new.lpage_info, 0, largepages * sizeof(*new.lpage_info));
+
+		if (base_gfn % KVM_PAGES_PER_HPAGE)
+			new.lpage_info[0].write_count = 1;
+		if ((base_gfn+npages) % KVM_PAGES_PER_HPAGE)
+			new.lpage_info[largepages-1].write_count = 1;
+	}
 
 	/* Allocate page dirty bitmap if needed */
 	if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) {
@@ -397,6 +459,12 @@ int is_error_page(struct page *page)
 }
 EXPORT_SYMBOL_GPL(is_error_page);
 
+int is_error_pfn(pfn_t pfn)
+{
+	return pfn == bad_pfn;
+}
+EXPORT_SYMBOL_GPL(is_error_pfn);
+
 static inline unsigned long bad_hva(void)
 {
 	return PAGE_OFFSET;
@@ -444,7 +512,7 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
 
-static unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
+unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_memory_slot *slot;
 
@@ -458,7 +526,7 @@ static unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 /*
  * Requires current->mm->mmap_sem to be held
  */
-struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
+pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
 {
 	struct page *page[1];
 	unsigned long addr;
@@ -469,7 +537,7 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 	addr = gfn_to_hva(kvm, gfn);
 	if (kvm_is_error_hva(addr)) {
 		get_page(bad_page);
-		return bad_page;
+		return page_to_pfn(bad_page);
 	}
 
 	npages = get_user_pages(current, current->mm, addr, 1, 1, 1, page,
@@ -477,27 +545,71 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 
 	if (npages != 1) {
 		get_page(bad_page);
-		return bad_page;
+		return page_to_pfn(bad_page);
 	}
 
-	return page[0];
+	return page_to_pfn(page[0]);
+}
+
+EXPORT_SYMBOL_GPL(gfn_to_pfn);
+
+struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
+{
+	return pfn_to_page(gfn_to_pfn(kvm, gfn));
 }
 
 EXPORT_SYMBOL_GPL(gfn_to_page);
 
 void kvm_release_page_clean(struct page *page)
 {
-	put_page(page);
+	kvm_release_pfn_clean(page_to_pfn(page));
 }
 EXPORT_SYMBOL_GPL(kvm_release_page_clean);
 
+void kvm_release_pfn_clean(pfn_t pfn)
+{
+	put_page(pfn_to_page(pfn));
+}
+EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
+
 void kvm_release_page_dirty(struct page *page)
 {
+	kvm_release_pfn_dirty(page_to_pfn(page));
+}
+EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
+
+void kvm_release_pfn_dirty(pfn_t pfn)
+{
+	kvm_set_pfn_dirty(pfn);
+	kvm_release_pfn_clean(pfn);
+}
+EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
+
+void kvm_set_page_dirty(struct page *page)
+{
+	kvm_set_pfn_dirty(page_to_pfn(page));
+}
+EXPORT_SYMBOL_GPL(kvm_set_page_dirty);
+
+void kvm_set_pfn_dirty(pfn_t pfn)
+{
+	struct page *page = pfn_to_page(pfn);
 	if (!PageReserved(page))
 		SetPageDirty(page);
-	put_page(page);
 }
-EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
+EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
+
+void kvm_set_pfn_accessed(pfn_t pfn)
+{
+	mark_page_accessed(pfn_to_page(pfn));
+}
+EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
+
+void kvm_get_pfn(pfn_t pfn)
+{
+	get_page(pfn_to_page(pfn));
+}
+EXPORT_SYMBOL_GPL(kvm_get_pfn);
 
 static int next_segment(unsigned long len, int offset)
 {
@@ -554,7 +666,9 @@ int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data,
 	addr = gfn_to_hva(kvm, gfn);
 	if (kvm_is_error_hva(addr))
 		return -EFAULT;
+	pagefault_disable();
 	r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len);
+	pagefault_enable();
 	if (r)
 		return -EFAULT;
 	return 0;
@@ -651,6 +765,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	 * We will block until either an interrupt or a signal wakes us up
 	 */
 	while (!kvm_cpu_has_interrupt(vcpu)
+	       && !kvm_cpu_has_pending_timer(vcpu)
 	       && !signal_pending(current)
 	       && !kvm_arch_vcpu_runnable(vcpu)) {
 		set_current_state(TASK_INTERRUPTIBLE);
@@ -678,8 +793,10 @@ static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	if (vmf->pgoff == 0)
 		page = virt_to_page(vcpu->run);
+#ifdef CONFIG_X86
 	else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET)
 		page = virt_to_page(vcpu->arch.pio_data);
+#endif
 	else
 		return VM_FAULT_SIGBUS;
 	get_page(page);
@@ -701,11 +818,11 @@ static int kvm_vcpu_release(struct inode *inode, struct file *filp)
 {
 	struct kvm_vcpu *vcpu = filp->private_data;
 
-	fput(vcpu->kvm->filp);
+	kvm_put_kvm(vcpu->kvm);
 	return 0;
 }
 
-static struct file_operations kvm_vcpu_fops = {
+static const struct file_operations kvm_vcpu_fops = {
 	.release        = kvm_vcpu_release,
 	.unlocked_ioctl = kvm_vcpu_ioctl,
 	.compat_ioctl   = kvm_vcpu_ioctl,
@@ -723,9 +840,10 @@ static int create_vcpu_fd(struct kvm_vcpu *vcpu)
 
 	r = anon_inode_getfd(&fd, &inode, &file,
 			     "kvm-vcpu", &kvm_vcpu_fops, vcpu);
-	if (r)
+	if (r) {
+		kvm_put_kvm(vcpu->kvm);
 		return r;
-	atomic_inc(&vcpu->kvm->filp->f_count);
+	}
 	return fd;
 }
 
@@ -760,6 +878,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n)
 	mutex_unlock(&kvm->lock);
 
 	/* Now it's all set up, let userspace reach it */
+	kvm_get_kvm(kvm);
 	r = create_vcpu_fd(vcpu);
 	if (r < 0)
 		goto unlink;
@@ -802,28 +921,39 @@ static long kvm_vcpu_ioctl(struct file *filp,
 		r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run);
 		break;
 	case KVM_GET_REGS: {
-		struct kvm_regs kvm_regs;
+		struct kvm_regs *kvm_regs;
 
-		memset(&kvm_regs, 0, sizeof kvm_regs);
-		r = kvm_arch_vcpu_ioctl_get_regs(vcpu, &kvm_regs);
-		if (r)
+		r = -ENOMEM;
+		kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL);
+		if (!kvm_regs)
 			goto out;
+		r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs);
+		if (r)
+			goto out_free1;
 		r = -EFAULT;
-		if (copy_to_user(argp, &kvm_regs, sizeof kvm_regs))
-			goto out;
+		if (copy_to_user(argp, kvm_regs, sizeof(struct kvm_regs)))
+			goto out_free1;
 		r = 0;
+out_free1:
+		kfree(kvm_regs);
 		break;
 	}
 	case KVM_SET_REGS: {
-		struct kvm_regs kvm_regs;
+		struct kvm_regs *kvm_regs;
 
-		r = -EFAULT;
-		if (copy_from_user(&kvm_regs, argp, sizeof kvm_regs))
+		r = -ENOMEM;
+		kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL);
+		if (!kvm_regs)
 			goto out;
-		r = kvm_arch_vcpu_ioctl_set_regs(vcpu, &kvm_regs);
+		r = -EFAULT;
+		if (copy_from_user(kvm_regs, argp, sizeof(struct kvm_regs)))
+			goto out_free2;
+		r = kvm_arch_vcpu_ioctl_set_regs(vcpu, kvm_regs);
 		if (r)
-			goto out;
+			goto out_free2;
 		r = 0;
+out_free2:
+		kfree(kvm_regs);
 		break;
 	}
 	case KVM_GET_SREGS: {
@@ -851,6 +981,30 @@ static long kvm_vcpu_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
+	case KVM_GET_MP_STATE: {
+		struct kvm_mp_state mp_state;
+
+		r = kvm_arch_vcpu_ioctl_get_mpstate(vcpu, &mp_state);
+		if (r)
+			goto out;
+		r = -EFAULT;
+		if (copy_to_user(argp, &mp_state, sizeof mp_state))
+			goto out;
+		r = 0;
+		break;
+	}
+	case KVM_SET_MP_STATE: {
+		struct kvm_mp_state mp_state;
+
+		r = -EFAULT;
+		if (copy_from_user(&mp_state, argp, sizeof mp_state))
+			goto out;
+		r = kvm_arch_vcpu_ioctl_set_mpstate(vcpu, &mp_state);
+		if (r)
+			goto out;
+		r = 0;
+		break;
+	}
 	case KVM_TRANSLATE: {
 		struct kvm_translation tr;
 
@@ -1005,7 +1159,7 @@ static int kvm_vm_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
-static struct file_operations kvm_vm_fops = {
+static const struct file_operations kvm_vm_fops = {
 	.release        = kvm_vm_release,
 	.unlocked_ioctl = kvm_vm_ioctl,
 	.compat_ioctl   = kvm_vm_ioctl,
@@ -1024,12 +1178,10 @@ static int kvm_dev_ioctl_create_vm(void)
 		return PTR_ERR(kvm);
 	r = anon_inode_getfd(&fd, &inode, &file, "kvm-vm", &kvm_vm_fops, kvm);
 	if (r) {
-		kvm_destroy_vm(kvm);
+		kvm_put_kvm(kvm);
 		return r;
 	}
 
-	kvm->filp = file;
-
 	return fd;
 }
 
@@ -1059,7 +1211,15 @@ static long kvm_dev_ioctl(struct file *filp,
 		r = -EINVAL;
 		if (arg)
 			goto out;
-		r = 2 * PAGE_SIZE;
+		r = PAGE_SIZE;     /* struct kvm_run */
+#ifdef CONFIG_X86
+		r += PAGE_SIZE;    /* pio data page */
+#endif
+		break;
+	case KVM_TRACE_ENABLE:
+	case KVM_TRACE_PAUSE:
+	case KVM_TRACE_DISABLE:
+		r = kvm_trace_ioctl(ioctl, arg);
 		break;
 	default:
 		return kvm_arch_dev_ioctl(filp, ioctl, arg);
@@ -1232,9 +1392,9 @@ static void kvm_init_debug(void)
 {
 	struct kvm_stats_debugfs_item *p;
 
-	debugfs_dir = debugfs_create_dir("kvm", NULL);
+	kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
 	for (p = debugfs_entries; p->name; ++p)
-		p->dentry = debugfs_create_file(p->name, 0444, debugfs_dir,
+		p->dentry = debugfs_create_file(p->name, 0444, kvm_debugfs_dir,
 						(void *)(long)p->offset,
 						stat_fops[p->kind]);
 }
@@ -1245,7 +1405,7 @@ static void kvm_exit_debug(void)
 
 	for (p = debugfs_entries; p->name; ++p)
 		debugfs_remove(p->dentry);
-	debugfs_remove(debugfs_dir);
+	debugfs_remove(kvm_debugfs_dir);
 }
 
 static int kvm_suspend(struct sys_device *dev, pm_message_t state)
@@ -1272,6 +1432,7 @@ static struct sys_device kvm_sysdev = {
 };
 
 struct page *bad_page;
+pfn_t bad_pfn;
 
 static inline
 struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
@@ -1313,6 +1474,8 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 		goto out;
 	}
 
+	bad_pfn = page_to_pfn(bad_page);
+
 	r = kvm_arch_hardware_setup();
 	if (r < 0)
 		goto out_free_0;
@@ -1386,6 +1549,7 @@ EXPORT_SYMBOL_GPL(kvm_init);
 
 void kvm_exit(void)
 {
+	kvm_trace_cleanup();
 	misc_deregister(&kvm_dev);
 	kmem_cache_destroy(kvm_vcpu_cache);
 	sysdev_unregister(&kvm_sysdev);
diff --git a/trunk/virt/kvm/kvm_trace.c b/trunk/virt/kvm/kvm_trace.c
new file mode 100644
index 000000000000..0e495470788d
--- /dev/null
+++ b/trunk/virt/kvm/kvm_trace.c
@@ -0,0 +1,276 @@
+/*
+ * kvm trace
+ *
+ * It is designed to allow debugging traces of kvm to be generated
+ * on UP / SMP machines.  Each trace entry can be timestamped so that
+ * it's possible to reconstruct a chronological record of trace events.
+ * The implementation refers to blktrace kernel support.
+ *
+ * Copyright (c) 2008 Intel Corporation
+ * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
+ *
+ * Authors: Feng(Eric) Liu, eric.e.liu@intel.com
+ *
+ * Date:    Feb 2008
+ */
+
+#include <linux/module.h>
+#include <linux/relay.h>
+#include <linux/debugfs.h>
+
+#include <linux/kvm_host.h>
+
+#define KVM_TRACE_STATE_RUNNING 	(1 << 0)
+#define KVM_TRACE_STATE_PAUSE 		(1 << 1)
+#define KVM_TRACE_STATE_CLEARUP 	(1 << 2)
+
+struct kvm_trace {
+	int trace_state;
+	struct rchan *rchan;
+	struct dentry *lost_file;
+	atomic_t lost_records;
+};
+static struct kvm_trace *kvm_trace;
+
+struct kvm_trace_probe {
+	const char *name;
+	const char *format;
+	u32 cycle_in;
+	marker_probe_func *probe_func;
+};
+
+static inline int calc_rec_size(int cycle, int extra)
+{
+	int rec_size = KVM_TRC_HEAD_SIZE;
+
+	rec_size += extra;
+	return cycle ? rec_size += KVM_TRC_CYCLE_SIZE : rec_size;
+}
+
+static void kvm_add_trace(void *probe_private, void *call_data,
+			  const char *format, va_list *args)
+{
+	struct kvm_trace_probe *p = probe_private;
+	struct kvm_trace *kt = kvm_trace;
+	struct kvm_trace_rec rec;
+	struct kvm_vcpu *vcpu;
+	int    i, extra, size;
+
+	if (unlikely(kt->trace_state != KVM_TRACE_STATE_RUNNING))
+		return;
+
+	rec.event	= va_arg(*args, u32);
+	vcpu		= va_arg(*args, struct kvm_vcpu *);
+	rec.pid		= current->tgid;
+	rec.vcpu_id	= vcpu->vcpu_id;
+
+	extra   	= va_arg(*args, u32);
+	WARN_ON(!(extra <= KVM_TRC_EXTRA_MAX));
+	extra 		= min_t(u32, extra, KVM_TRC_EXTRA_MAX);
+	rec.extra_u32   = extra;
+
+	rec.cycle_in 	= p->cycle_in;
+
+	if (rec.cycle_in) {
+		u64 cycle = 0;
+
+		cycle = get_cycles();
+		rec.u.cycle.cycle_lo = (u32)cycle;
+		rec.u.cycle.cycle_hi = (u32)(cycle >> 32);
+
+		for (i = 0; i < rec.extra_u32; i++)
+			rec.u.cycle.extra_u32[i] = va_arg(*args, u32);
+	} else {
+		for (i = 0; i < rec.extra_u32; i++)
+			rec.u.nocycle.extra_u32[i] = va_arg(*args, u32);
+	}
+
+	size = calc_rec_size(rec.cycle_in, rec.extra_u32 * sizeof(u32));
+	relay_write(kt->rchan, &rec, size);
+}
+
+static struct kvm_trace_probe kvm_trace_probes[] = {
+	{ "kvm_trace_entryexit", "%u %p %u %u %u %u %u %u", 1, kvm_add_trace },
+	{ "kvm_trace_handler", "%u %p %u %u %u %u %u %u", 0, kvm_add_trace },
+};
+
+static int lost_records_get(void *data, u64 *val)
+{
+	struct kvm_trace *kt = data;
+
+	*val = atomic_read(&kt->lost_records);
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(kvm_trace_lost_ops, lost_records_get, NULL, "%llu\n");
+
+/*
+ *  The relay channel is used in "no-overwrite" mode, it keeps trace of how
+ *  many times we encountered a full subbuffer, to tell user space app the
+ *  lost records there were.
+ */
+static int kvm_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
+				     void *prev_subbuf, size_t prev_padding)
+{
+	struct kvm_trace *kt;
+
+	if (!relay_buf_full(buf))
+		return 1;
+
+	kt = buf->chan->private_data;
+	atomic_inc(&kt->lost_records);
+
+	return 0;
+}
+
+static struct dentry *kvm_create_buf_file_callack(const char *filename,
+						 struct dentry *parent,
+						 int mode,
+						 struct rchan_buf *buf,
+						 int *is_global)
+{
+	return debugfs_create_file(filename, mode, parent, buf,
+				   &relay_file_operations);
+}
+
+static int kvm_remove_buf_file_callback(struct dentry *dentry)
+{
+	debugfs_remove(dentry);
+	return 0;
+}
+
+static struct rchan_callbacks kvm_relay_callbacks = {
+	.subbuf_start 		= kvm_subbuf_start_callback,
+	.create_buf_file 	= kvm_create_buf_file_callack,
+	.remove_buf_file 	= kvm_remove_buf_file_callback,
+};
+
+static int do_kvm_trace_enable(struct kvm_user_trace_setup *kuts)
+{
+	struct kvm_trace *kt;
+	int i, r = -ENOMEM;
+
+	if (!kuts->buf_size || !kuts->buf_nr)
+		return -EINVAL;
+
+	kt = kzalloc(sizeof(*kt), GFP_KERNEL);
+	if (!kt)
+		goto err;
+
+	r = -EIO;
+	atomic_set(&kt->lost_records, 0);
+	kt->lost_file = debugfs_create_file("lost_records", 0444, kvm_debugfs_dir,
+					    kt, &kvm_trace_lost_ops);
+	if (!kt->lost_file)
+		goto err;
+
+	kt->rchan = relay_open("trace", kvm_debugfs_dir, kuts->buf_size,
+				kuts->buf_nr, &kvm_relay_callbacks, kt);
+	if (!kt->rchan)
+		goto err;
+
+	kvm_trace = kt;
+
+	for (i = 0; i < ARRAY_SIZE(kvm_trace_probes); i++) {
+		struct kvm_trace_probe *p = &kvm_trace_probes[i];
+
+		r = marker_probe_register(p->name, p->format, p->probe_func, p);
+		if (r)
+			printk(KERN_INFO "Unable to register probe %s\n",
+			       p->name);
+	}
+
+	kvm_trace->trace_state = KVM_TRACE_STATE_RUNNING;
+
+	return 0;
+err:
+	if (kt) {
+		if (kt->lost_file)
+			debugfs_remove(kt->lost_file);
+		if (kt->rchan)
+			relay_close(kt->rchan);
+		kfree(kt);
+	}
+	return r;
+}
+
+static int kvm_trace_enable(char __user *arg)
+{
+	struct kvm_user_trace_setup kuts;
+	int ret;
+
+	ret = copy_from_user(&kuts, arg, sizeof(kuts));
+	if (ret)
+		return -EFAULT;
+
+	ret = do_kvm_trace_enable(&kuts);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int kvm_trace_pause(void)
+{
+	struct kvm_trace *kt = kvm_trace;
+	int r = -EINVAL;
+
+	if (kt == NULL)
+		return r;
+
+	if (kt->trace_state == KVM_TRACE_STATE_RUNNING) {
+		kt->trace_state = KVM_TRACE_STATE_PAUSE;
+		relay_flush(kt->rchan);
+		r = 0;
+	}
+
+	return r;
+}
+
+void kvm_trace_cleanup(void)
+{
+	struct kvm_trace *kt = kvm_trace;
+	int i;
+
+	if (kt == NULL)
+		return;
+
+	if (kt->trace_state == KVM_TRACE_STATE_RUNNING ||
+	    kt->trace_state == KVM_TRACE_STATE_PAUSE) {
+
+		kt->trace_state = KVM_TRACE_STATE_CLEARUP;
+
+		for (i = 0; i < ARRAY_SIZE(kvm_trace_probes); i++) {
+			struct kvm_trace_probe *p = &kvm_trace_probes[i];
+			marker_probe_unregister(p->name, p->probe_func, p);
+		}
+
+		relay_close(kt->rchan);
+		debugfs_remove(kt->lost_file);
+		kfree(kt);
+	}
+}
+
+int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	long r = -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	switch (ioctl) {
+	case KVM_TRACE_ENABLE:
+		r = kvm_trace_enable(argp);
+		break;
+	case KVM_TRACE_PAUSE:
+		r = kvm_trace_pause();
+		break;
+	case KVM_TRACE_DISABLE:
+		r = 0;
+		kvm_trace_cleanup();
+		break;
+	}
+
+	return r;
+}