Merge branch 'x86-core-for-linus' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/tip/linux-2.6-tip

* 'x86-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (246 commits)
  x86: traps.c replace #if CONFIG_X86_32 with #ifdef CONFIG_X86_32
  x86: PAT: fix address types in track_pfn_vma_new()
  x86: prioritize the FPU traps for the error code
  x86: PAT: pfnmap documentation update changes
  x86: PAT: move track untrack pfnmap stubs to asm-generic
  x86: PAT: remove follow_pfnmap_pte in favor of follow_phys
  x86: PAT: modify follow_phys to return phys_addr prot and return value
  x86: PAT: clarify is_linear_pfn_mapping() interface
  x86: ia32_signal: remove unnecessary declaration
  x86: common.c boot_cpu_stack and boot_exception_stacks should be static
  x86: fix intel x86_64 llc_shared_map/cpu_llc_id anomolies
  x86: fix warning in arch/x86/kernel/microcode_amd.c
  x86: ia32.h: remove unused struct sigfram32 and rt_sigframe32
  x86: asm-offset_64: use rt_sigframe_ia32
  x86: sigframe.h: include headers for dependency
  x86: traps.c declare functions before they get used
  x86: PAT: update documentation to cover pgprot and remap_pfn related changes - v3
  x86: PAT: add pgprot_writecombine() interface for drivers - v3
  x86: PAT: change pgprot_noncached to uc_minus instead of strong uc - v3
  x86: PAT: implement track/untrack of pfnmap regions for x86 - v3
  ...

Documentation/feature-removal-schedule.txt

@@ -244,18 +244,6 @@ Who:	Michael Buesch <mb@bu3sch.de>
 
 ---------------------------
 
-What:	init_mm export
-When:	2.6.26
-Why:	Not used in-tree. The current out-of-tree users used it to
-	work around problems in the CPA code which should be resolved
-	by now. One usecase was described to provide verification code
-	of the CPA operation. That's a good idea in general, but such
-	code / infrastructure should be in the kernel and not in some
-	out-of-tree driver.
-Who:	Thomas Gleixner <tglx@linutronix.de>
-
-----------------------------
-
 What:	usedac i386 kernel parameter
 When:	2.6.27
 Why:	replaced by allowdac and no dac combination

Documentation/filesystems/proc.txt

@@ -1339,10 +1339,13 @@ nmi_watchdog
 
 Enables/Disables the NMI watchdog on x86 systems.  When the value is non-zero
 the NMI watchdog is enabled and will continuously test all online cpus to
-determine whether or not they are still functioning properly.
+determine whether or not they are still functioning properly. Currently,
+passing "nmi_watchdog=" parameter at boot time is required for this function
+to work.
 
-Because the NMI watchdog shares registers with oprofile, by disabling the NMI
-watchdog, oprofile may have more registers to utilize.
+If LAPIC NMI watchdog method is in use (nmi_watchdog=2 kernel parameter), the
+NMI watchdog shares registers with oprofile. By disabling the NMI watchdog,
+oprofile may have more registers to utilize.
 
 msgmni
 ------

Documentation/kernel-parameters.txt

@@ -1396,7 +1396,20 @@ and is between 256 and 4096 characters. It is defined in the file
 			when a NMI is triggered.
 			Format: [state][,regs][,debounce][,die]
 
-	nmi_watchdog=	[KNL,BUGS=X86-32] Debugging features for SMP kernels
+	nmi_watchdog=	[KNL,BUGS=X86-32,X86-64] Debugging features for SMP kernels
+			Format: [panic,][num]
+			Valid num: 0,1,2
+			0 - turn nmi_watchdog off
+			1 - use the IO-APIC timer for the NMI watchdog
+			2 - use the local APIC for the NMI watchdog using
+			a performance counter. Note: This will use one performance
+			counter and the local APIC's performance vector.
+			When panic is specified panic when an NMI watchdog timeout occurs.
+			This is useful when you use a panic=... timeout and need the box
+			quickly up again.
+			Instead of 1 and 2 it is possible to use the following
+			symbolic names: lapic and ioapic
+			Example: nmi_watchdog=2 or nmi_watchdog=panic,lapic
 
 	no387		[BUGS=X86-32] Tells the kernel to use the 387 maths
 			emulation library even if a 387 maths coprocessor
@@ -1633,6 +1646,17 @@ and is between 256 and 4096 characters. It is defined in the file
 		nomsi		[MSI] If the PCI_MSI kernel config parameter is
 				enabled, this kernel boot option can be used to
 				disable the use of MSI interrupts system-wide.
+		noioapicquirk	[APIC] Disable all boot interrupt quirks.
+				Safety option to keep boot IRQs enabled. This
+				should never be necessary.
+		ioapicreroute	[APIC] Enable rerouting of boot IRQs to the
+				primary IO-APIC for bridges that cannot disable
+				boot IRQs. This fixes a source of spurious IRQs
+				when the system masks IRQs.
+		noioapicreroute	[APIC] Disable workaround that uses the
+				boot IRQ equivalent of an IRQ that connects to
+				a chipset where boot IRQs cannot be disabled.
+				The opposite of ioapicreroute.
 		biosirq		[X86-32] Use PCI BIOS calls to get the interrupt
 				routing table. These calls are known to be buggy
 				on several machines and they hang the machine
@@ -2262,6 +2286,13 @@ and is between 256 and 4096 characters. It is defined in the file
 			Format:
 			<io>,<irq>,<dma>,<dma2>,<sb_io>,<sb_irq>,<sb_dma>,<mpu_io>,<mpu_irq>
 
+	tsc=		Disable clocksource-must-verify flag for TSC.
+			Format: <string>
+			[x86] reliable: mark tsc clocksource as reliable, this
+			disables clocksource verification at runtime.
+			Used to enable high-resolution timer mode on older
+			hardware, and in virtualized environment.
+
 	turbografx.map[2|3]=	[HW,JOY]
 			TurboGraFX parallel port interface
 			Format:

Documentation/nmi_watchdog.txt

@@ -69,6 +69,11 @@ to the overall system performance.
 On x86 nmi_watchdog is disabled by default so you have to enable it with
 a boot time parameter.
 
+It's possible to disable the NMI watchdog in run-time by writing "0" to
+/proc/sys/kernel/nmi_watchdog. Writing "1" to the same file will re-enable
+the NMI watchdog. Notice that you still need to use "nmi_watchdog=" parameter
+at boot time.
+
 NOTE: In kernels prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
 on x86 SMP boxes.
 

Documentation/x86/boot.txt

@@ -349,7 +349,7 @@ Protocol:	2.00+
 	3  SYSLINUX
 	4  EtherBoot
 	5  ELILO
-	7  GRuB
+	7  GRUB
 	8  U-BOOT
 	9  Xen
 	A  Gujin
@@ -537,8 +537,8 @@ Type:		read
 Offset/size:	0x248/4
 Protocol:	2.08+
 
-  If non-zero then this field contains the offset from the end of the
-  real-mode code to the payload.
+  If non-zero then this field contains the offset from the beginning
+  of the protected-mode code to the payload.
 
   The payload may be compressed. The format of both the compressed and
   uncompressed data should be determined using the standard magic

Documentation/x86/pat.txt

@@ -80,6 +80,30 @@ pci proc               |    --    |    --      |       WC         |
                        |          |            |                  |
 -------------------------------------------------------------------
 
+Advanced APIs for drivers
+-------------------------
+A. Exporting pages to users with remap_pfn_range, io_remap_pfn_range,
+vm_insert_pfn
+
+Drivers wanting to export some pages to userspace do it by using mmap
+interface and a combination of
+1) pgprot_noncached()
+2) io_remap_pfn_range() or remap_pfn_range() or vm_insert_pfn()
+
+With PAT support, a new API pgprot_writecombine is being added. So, drivers can
+continue to use the above sequence, with either pgprot_noncached() or
+pgprot_writecombine() in step 1, followed by step 2.
+
+In addition, step 2 internally tracks the region as UC or WC in memtype
+list in order to ensure no conflicting mapping.
+
+Note that this set of APIs only works with IO (non RAM) regions. If driver
+wants to export a RAM region, it has to do set_memory_uc() or set_memory_wc()
+as step 0 above and also track the usage of those pages and use set_memory_wb()
+before the page is freed to free pool.
+
+
+
 Notes:
 
 -- in the above table mean "Not suggested usage for the API". Some of the --'s

Documentation/x86/x86_64/boot-options.txt

@@ -79,17 +79,6 @@ Timing
   Report when timer interrupts are lost because some code turned off
   interrupts for too long.
 
-  nmi_watchdog=NUMBER[,panic]
-  NUMBER can be:
-  0 don't use an NMI watchdog
-  1 use the IO-APIC timer for the NMI watchdog
-  2 use the local APIC for the NMI watchdog using a performance counter. Note
-  This will use one performance counter and the local APIC's performance
-  vector.
-  When panic is specified panic when an NMI watchdog timeout occurs.
-  This is useful when you use a panic=... timeout and need the box
-  quickly up again.
-
   nohpet
   Don't use the HPET timer.
 

Documentation/x86/x86_64/mm.txt

@@ -6,7 +6,7 @@ Virtual memory map with 4 level page tables:
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
 hole caused by [48:63] sign extension
 ffff800000000000 - ffff80ffffffffff (=40 bits) guard hole
-ffff810000000000 - ffffc0ffffffffff (=46 bits) direct mapping of all phys. memory
+ffff880000000000 - ffffc0ffffffffff (=57 TB) direct mapping of all phys. memory
 ffffc10000000000 - ffffc1ffffffffff (=40 bits) hole
 ffffc20000000000 - ffffe1ffffffffff (=45 bits) vmalloc/ioremap space
 ffffe20000000000 - ffffe2ffffffffff (=40 bits) virtual memory map (1TB)

arch/x86/Kconfig

@@ -19,6 +19,8 @@ config X86_64
 config X86
 	def_bool y
 	select HAVE_AOUT if X86_32
+	select HAVE_READQ
+	select HAVE_WRITEQ
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_IDE
 	select HAVE_OPROFILE
@@ -87,6 +89,10 @@ config GENERIC_IOMAP
 config GENERIC_BUG
 	def_bool y
 	depends on BUG
+	select GENERIC_BUG_RELATIVE_POINTERS if X86_64
+
+config GENERIC_BUG_RELATIVE_POINTERS
+	bool
 
 config GENERIC_HWEIGHT
 	def_bool y
@@ -242,21 +248,13 @@ config X86_FIND_SMP_CONFIG
 	def_bool y
 	depends on X86_MPPARSE || X86_VOYAGER
 
-if ACPI
 config X86_MPPARSE
-	def_bool y
-	bool "Enable MPS table"
+	bool "Enable MPS table" if ACPI
+	default y
 	depends on X86_LOCAL_APIC
 	help
 	  For old smp systems that do not have proper acpi support. Newer systems
 	  (esp with 64bit cpus) with acpi support, MADT and DSDT will override it
-endif
-
-if !ACPI
-config X86_MPPARSE
-	def_bool y
-	depends on X86_LOCAL_APIC
-endif
 
 choice
 	prompt "Subarchitecture Type"
@@ -465,10 +463,6 @@ config X86_CYCLONE_TIMER
 	def_bool y
 	depends on X86_GENERICARCH
 
-config ES7000_CLUSTERED_APIC
-	def_bool y
-	depends on SMP && X86_ES7000 && MPENTIUMIII
-
 source "arch/x86/Kconfig.cpu"
 
 config HPET_TIMER
@@ -569,7 +563,7 @@ config AMD_IOMMU
 
 # need this always selected by IOMMU for the VIA workaround
 config SWIOTLB
-	bool
+	def_bool y if X86_64
 	help
 	  Support for software bounce buffers used on x86-64 systems
 	  which don't have a hardware IOMMU (e.g. the current generation
@@ -660,6 +654,30 @@ config X86_VISWS_APIC
 	def_bool y
 	depends on X86_32 && X86_VISWS
 
+config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
+	bool "Reroute for broken boot IRQs"
+	default n
+	depends on X86_IO_APIC
+	help
+	  This option enables a workaround that fixes a source of
+	  spurious interrupts. This is recommended when threaded
+	  interrupt handling is used on systems where the generation of
+	  superfluous "boot interrupts" cannot be disabled.
+
+	  Some chipsets generate a legacy INTx "boot IRQ" when the IRQ
+	  entry in the chipset's IO-APIC is masked (as, e.g. the RT
+	  kernel does during interrupt handling). On chipsets where this
+	  boot IRQ generation cannot be disabled, this workaround keeps
+	  the original IRQ line masked so that only the equivalent "boot
+	  IRQ" is delivered to the CPUs. The workaround also tells the
+	  kernel to set up the IRQ handler on the boot IRQ line. In this
+	  way only one interrupt is delivered to the kernel. Otherwise
+	  the spurious second interrupt may cause the kernel to bring
+	  down (vital) interrupt lines.
+
+	  Only affects "broken" chipsets. Interrupt sharing may be
+	  increased on these systems.
+
 config X86_MCE
 	bool "Machine Check Exception"
 	depends on !X86_VOYAGER
@@ -956,24 +974,37 @@ config X86_PAE
 config ARCH_PHYS_ADDR_T_64BIT
        def_bool X86_64 || X86_PAE
 
+config DIRECT_GBPAGES
+	bool "Enable 1GB pages for kernel pagetables" if EMBEDDED
+	default y
+	depends on X86_64
+	help
+	  Allow the kernel linear mapping to use 1GB pages on CPUs that
+	  support it. This can improve the kernel's performance a tiny bit by
+	  reducing TLB pressure. If in doubt, say "Y".
+
 # Common NUMA Features
 config NUMA
-	bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)"
+	bool "Numa Memory Allocation and Scheduler Support"
 	depends on SMP
 	depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && EXPERIMENTAL)
 	default n if X86_PC
 	default y if (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP)
 	help
 	  Enable NUMA (Non Uniform Memory Access) support.
+
 	  The kernel will try to allocate memory used by a CPU on the
 	  local memory controller of the CPU and add some more
 	  NUMA awareness to the kernel.
 
-	  For 32-bit this is currently highly experimental and should be only
-	  used for kernel development. It might also cause boot failures.
-	  For 64-bit this is recommended on all multiprocessor Opteron systems.
-	  If the system is EM64T, you should say N unless your system is
-	  EM64T NUMA.
+	  For 64-bit this is recommended if the system is Intel Core i7
+	  (or later), AMD Opteron, or EM64T NUMA.
+
+	  For 32-bit this is only needed on (rare) 32-bit-only platforms
+	  that support NUMA topologies, such as NUMAQ / Summit, or if you
+	  boot a 32-bit kernel on a 64-bit NUMA platform.
+
+	  Otherwise, you should say N.
 
 comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
 	depends on X86_32 && X86_SUMMIT && (!HIGHMEM64G || !ACPI)
@@ -1493,6 +1524,10 @@ config ARCH_ENABLE_MEMORY_HOTPLUG
 	def_bool y
 	depends on X86_64 || (X86_32 && HIGHMEM)
 
+config ARCH_ENABLE_MEMORY_HOTREMOVE
+	def_bool y
+	depends on MEMORY_HOTPLUG
+
 config HAVE_ARCH_EARLY_PFN_TO_NID
 	def_bool X86_64
 	depends on NUMA
@@ -1632,13 +1667,6 @@ config APM_ALLOW_INTS
 	  many of the newer IBM Thinkpads.  If you experience hangs when you
 	  suspend, try setting this to Y.  Otherwise, say N.
 
-config APM_REAL_MODE_POWER_OFF
-	bool "Use real mode APM BIOS call to power off"
-	help
-	  Use real mode APM BIOS calls to switch off the computer. This is
-	  a work-around for a number of buggy BIOSes. Switch this option on if
-	  your computer crashes instead of powering off properly.
-
 endif # APM
 
 source "arch/x86/kernel/cpu/cpufreq/Kconfig"

arch/x86/Kconfig.debug

@@ -114,18 +114,6 @@ config DEBUG_RODATA
 	  data. This is recommended so that we can catch kernel bugs sooner.
 	  If in doubt, say "Y".
 
-config DIRECT_GBPAGES
-	bool "Enable gbpages-mapped kernel pagetables"
-	depends on DEBUG_KERNEL && EXPERIMENTAL && X86_64
-	help
-	  Enable gigabyte pages support (if the CPU supports it). This can
-	  improve the kernel's performance a tiny bit by reducing TLB
-	  pressure.
-
-	  This is experimental code.
-
-	  If in doubt, say "N".
-
 config DEBUG_RODATA_TEST
 	bool "Testcase for the DEBUG_RODATA feature"
 	depends on DEBUG_RODATA
@@ -307,10 +295,10 @@ config OPTIMIZE_INLINING
 	  developers have marked 'inline'. Doing so takes away freedom from gcc to
 	  do what it thinks is best, which is desirable for the gcc 3.x series of
 	  compilers. The gcc 4.x series have a rewritten inlining algorithm and
-	  disabling this option will generate a smaller kernel there. Hopefully
-	  this algorithm is so good that allowing gcc4 to make the decision can
-	  become the default in the future, until then this option is there to
-	  test gcc for this.
+	  enabling this option will generate a smaller kernel there. Hopefully
+	  this algorithm is so good that allowing gcc 4.x and above to make the
+	  decision will become the default in the future. Until then this option
+	  is there to test gcc for this.
 
 	  If unsure, say N.
 

arch/x86/boot/video-vga.c

@@ -34,7 +34,7 @@ static struct mode_info cga_modes[] = {
 	{ VIDEO_80x25,  80, 25, 0 },
 };
 
-__videocard video_vga;
+static __videocard video_vga;
 
 /* Set basic 80x25 mode */
 static u8 vga_set_basic_mode(void)
@@ -259,7 +259,7 @@ static int vga_probe(void)
 	return mode_count[adapter];
 }
 
-__videocard video_vga = {
+static __videocard video_vga = {
 	.card_name	= "VGA",
 	.probe		= vga_probe,
 	.set_mode	= vga_set_mode,