diff --git a/[refs] b/[refs] index ad5b25298c51..ff02ee1168d7 100644 --- a/[refs] +++ b/[refs] @@ -1,2 +1,2 @@ --- -refs/heads/master: c9059598ea8981d02356eead3188bf7fa4d717b8 +refs/heads/master: 4da646b7b52552f3b43eae27ffa5aa2c200f6db6 diff --git a/trunk/Documentation/ABI/testing/sysfs-block b/trunk/Documentation/ABI/testing/sysfs-block index cbbd3e069945..44f52a4f5903 100644 --- a/trunk/Documentation/ABI/testing/sysfs-block +++ b/trunk/Documentation/ABI/testing/sysfs-block @@ -60,62 +60,3 @@ Description: Indicates whether the block layer should automatically generate checksums for write requests bound for devices that support receiving integrity metadata. - -What: /sys/block//alignment_offset -Date: April 2009 -Contact: Martin K. Petersen -Description: - Storage devices may report a physical block size that is - bigger than the logical block size (for instance a drive - with 4KB physical sectors exposing 512-byte logical - blocks to the operating system). This parameter - indicates how many bytes the beginning of the device is - offset from the disk's natural alignment. - -What: /sys/block///alignment_offset -Date: April 2009 -Contact: Martin K. Petersen -Description: - Storage devices may report a physical block size that is - bigger than the logical block size (for instance a drive - with 4KB physical sectors exposing 512-byte logical - blocks to the operating system). This parameter - indicates how many bytes the beginning of the partition - is offset from the disk's natural alignment. - -What: /sys/block//queue/logical_block_size -Date: May 2009 -Contact: Martin K. Petersen -Description: - This is the smallest unit the storage device can - address. It is typically 512 bytes. - -What: /sys/block//queue/physical_block_size -Date: May 2009 -Contact: Martin K. Petersen -Description: - This is the smallest unit the storage device can write - without resorting to read-modify-write operation. It is - usually the same as the logical block size but may be - bigger. One example is SATA drives with 4KB sectors - that expose a 512-byte logical block size to the - operating system. - -What: /sys/block//queue/minimum_io_size -Date: April 2009 -Contact: Martin K. Petersen -Description: - Storage devices may report a preferred minimum I/O size, - which is the smallest request the device can perform - without incurring a read-modify-write penalty. For disk - drives this is often the physical block size. For RAID - arrays it is often the stripe chunk size. - -What: /sys/block//queue/optimal_io_size -Date: April 2009 -Contact: Martin K. Petersen -Description: - Storage devices may report an optimal I/O size, which is - the device's preferred unit of receiving I/O. This is - rarely reported for disk drives. For RAID devices it is - usually the stripe width or the internal block size. diff --git a/trunk/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss b/trunk/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss deleted file mode 100644 index 0a92a7c93a62..000000000000 --- a/trunk/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss +++ /dev/null @@ -1,33 +0,0 @@ -Where: /sys/bus/pci/devices//ccissX/cXdY/model -Date: March 2009 -Kernel Version: 2.6.30 -Contact: iss_storagedev@hp.com -Description: Displays the SCSI INQUIRY page 0 model for logical drive - Y of controller X. - -Where: /sys/bus/pci/devices//ccissX/cXdY/rev -Date: March 2009 -Kernel Version: 2.6.30 -Contact: iss_storagedev@hp.com -Description: Displays the SCSI INQUIRY page 0 revision for logical - drive Y of controller X. - -Where: /sys/bus/pci/devices//ccissX/cXdY/unique_id -Date: March 2009 -Kernel Version: 2.6.30 -Contact: iss_storagedev@hp.com -Description: Displays the SCSI INQUIRY page 83 serial number for logical - drive Y of controller X. - -Where: /sys/bus/pci/devices//ccissX/cXdY/vendor -Date: March 2009 -Kernel Version: 2.6.30 -Contact: iss_storagedev@hp.com -Description: Displays the SCSI INQUIRY page 0 vendor for logical drive - Y of controller X. - -Where: /sys/bus/pci/devices//ccissX/cXdY/block:cciss!cXdY -Date: March 2009 -Kernel Version: 2.6.30 -Contact: iss_storagedev@hp.com -Description: A symbolic link to /sys/block/cciss!cXdY diff --git a/trunk/Documentation/ABI/testing/sysfs-devices-cache_disable b/trunk/Documentation/ABI/testing/sysfs-devices-cache_disable deleted file mode 100644 index 175bb4f70512..000000000000 --- a/trunk/Documentation/ABI/testing/sysfs-devices-cache_disable +++ /dev/null @@ -1,18 +0,0 @@ -What: /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X -Date: August 2008 -KernelVersion: 2.6.27 -Contact: mark.langsdorf@amd.com -Description: These files exist in every cpu's cache index directories. - There are currently 2 cache_disable_# files in each - directory. Reading from these files on a supported - processor will return that cache disable index value - for that processor and node. Writing to one of these - files will cause the specificed cache index to be disabled. - - Currently, only AMD Family 10h Processors support cache index - disable, and only for their L3 caches. See the BIOS and - Kernel Developer's Guide at - http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/31116-Public-GH-BKDG_3.20_2-4-09.pdf - for formatting information and other details on the - cache index disable. -Users: joachim.deguara@amd.com diff --git a/trunk/Documentation/DMA-API.txt b/trunk/Documentation/DMA-API.txt index 25fb8bcf32a2..d9aa43d78bcc 100644 --- a/trunk/Documentation/DMA-API.txt +++ b/trunk/Documentation/DMA-API.txt @@ -704,24 +704,12 @@ this directory the following files can currently be found: The current number of free dma_debug_entries in the allocator. - dma-api/driver-filter - You can write a name of a driver into this file - to limit the debug output to requests from that - particular driver. Write an empty string to - that file to disable the filter and see - all errors again. - If you have this code compiled into your kernel it will be enabled by default. If you want to boot without the bookkeeping anyway you can provide 'dma_debug=off' as a boot parameter. This will disable DMA-API debugging. Notice that you can not enable it again at runtime. You have to reboot to do so. -If you want to see debug messages only for a special device driver you can -specify the dma_debug_driver= parameter. This will enable the -driver filter at boot time. The debug code will only print errors for that -driver afterwards. This filter can be disabled or changed later using debugfs. - When the code disables itself at runtime this is most likely because it ran out of dma_debug_entries. These entries are preallocated at boot. The number of preallocated entries is defined per architecture. If it is too low for you diff --git a/trunk/Documentation/DocBook/Makefile b/trunk/Documentation/DocBook/Makefile index 9632444f6c62..b1eb661e6302 100644 --- a/trunk/Documentation/DocBook/Makefile +++ b/trunk/Documentation/DocBook/Makefile @@ -13,8 +13,7 @@ DOCBOOKS := z8530book.xml mcabook.xml device-drivers.xml \ gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \ genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \ mac80211.xml debugobjects.xml sh.xml regulator.xml \ - alsa-driver-api.xml writing-an-alsa-driver.xml \ - tracepoint.xml + alsa-driver-api.xml writing-an-alsa-driver.xml ### # The build process is as follows (targets): diff --git a/trunk/Documentation/DocBook/tracepoint.tmpl b/trunk/Documentation/DocBook/tracepoint.tmpl deleted file mode 100644 index b0756d0fd579..000000000000 --- a/trunk/Documentation/DocBook/tracepoint.tmpl +++ /dev/null @@ -1,89 +0,0 @@ - - - - - - The Linux Kernel Tracepoint API - - - - Jason - Baron - -
- jbaron@redhat.com -
- - - - - - - This documentation 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 - - - - For more details see the file COPYING in the source - distribution of Linux. - - - - - - - Introduction - - Tracepoints are static probe points that are located in strategic points - throughout the kernel. 'Probes' register/unregister with tracepoints - via a callback mechanism. The 'probes' are strictly typed functions that - are passed a unique set of parameters defined by each tracepoint. - - - - From this simple callback mechanism, 'probes' can be used to profile, debug, - and understand kernel behavior. There are a number of tools that provide a - framework for using 'probes'. These tools include Systemtap, ftrace, and - LTTng. - - - - Tracepoints are defined in a number of header files via various macros. Thus, - the purpose of this document is to provide a clear accounting of the available - tracepoints. The intention is to understand not only what tracepoints are - available but also to understand where future tracepoints might be added. - - - - The API presented has functions of the form: - trace_tracepointname(function parameters). These are the - tracepoints callbacks that are found throughout the code. Registering and - unregistering probes with these callback sites is covered in the - Documentation/trace/* directory. - - - - - IRQ -!Iinclude/trace/events/irq.h - - - diff --git a/trunk/Documentation/RCU/trace.txt b/trunk/Documentation/RCU/trace.txt index 02cced183b2d..068848240a8b 100644 --- a/trunk/Documentation/RCU/trace.txt +++ b/trunk/Documentation/RCU/trace.txt @@ -192,24 +192,23 @@ rcu/rcuhier (which displays the struct rcu_node hierarchy). The output of "cat rcu/rcudata" looks as follows: rcu: -rcu: - 0 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=10951/1 dn=0 df=1101 of=0 ri=36 ql=0 b=10 - 1 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=16117/1 dn=0 df=1015 of=0 ri=0 ql=0 b=10 - 2 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1445/1 dn=0 df=1839 of=0 ri=0 ql=0 b=10 - 3 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=6681/1 dn=0 df=1545 of=0 ri=0 ql=0 b=10 - 4 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1003/1 dn=0 df=1992 of=0 ri=0 ql=0 b=10 - 5 c=17829 g=17830 pq=1 pqc=17829 qp=1 dt=3887/1 dn=0 df=3331 of=0 ri=4 ql=2 b=10 - 6 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=859/1 dn=0 df=3224 of=0 ri=0 ql=0 b=10 - 7 c=17829 g=17830 pq=0 pqc=17829 qp=1 dt=3761/1 dn=0 df=1818 of=0 ri=0 ql=2 b=10 + 0 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=1 rp=3c2a dt=23301/73 dn=2 df=1882 of=0 ri=2126 ql=2 b=10 + 1 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=3 rp=39a6 dt=78073/1 dn=2 df=1402 of=0 ri=1875 ql=46 b=10 + 2 c=4010 g=4010 pq=1 pqc=4010 qp=0 rpfq=-5 rp=1d12 dt=16646/0 dn=2 df=3140 of=0 ri=2080 ql=0 b=10 + 3 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=2b50 dt=21159/1 dn=2 df=2230 of=0 ri=1923 ql=72 b=10 + 4 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1644 dt=5783/1 dn=2 df=3348 of=0 ri=2805 ql=7 b=10 + 5 c=4012 g=4013 pq=0 pqc=4011 qp=1 rpfq=3 rp=1aac dt=5879/1 dn=2 df=3140 of=0 ri=2066 ql=10 b=10 + 6 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=ed8 dt=5847/1 dn=2 df=3797 of=0 ri=1266 ql=10 b=10 + 7 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1fa2 dt=6199/1 dn=2 df=2795 of=0 ri=2162 ql=28 b=10 rcu_bh: - 0 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=10951/1 dn=0 df=0 of=0 ri=0 ql=0 b=10 - 1 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=16117/1 dn=0 df=13 of=0 ri=0 ql=0 b=10 - 2 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1445/1 dn=0 df=15 of=0 ri=0 ql=0 b=10 - 3 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=6681/1 dn=0 df=9 of=0 ri=0 ql=0 b=10 - 4 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1003/1 dn=0 df=15 of=0 ri=0 ql=0 b=10 - 5 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3887/1 dn=0 df=15 of=0 ri=0 ql=0 b=10 - 6 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=859/1 dn=0 df=15 of=0 ri=0 ql=0 b=10 - 7 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3761/1 dn=0 df=15 of=0 ri=0 ql=0 b=10 + 0 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-145 rp=21d6 dt=23301/73 dn=2 df=0 of=0 ri=0 ql=0 b=10 + 1 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-170 rp=20ce dt=78073/1 dn=2 df=26 of=0 ri=5 ql=0 b=10 + 2 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-83 rp=fbd dt=16646/0 dn=2 df=28 of=0 ri=4 ql=0 b=10 + 3 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-105 rp=178c dt=21159/1 dn=2 df=28 of=0 ri=2 ql=0 b=10 + 4 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-30 rp=b54 dt=5783/1 dn=2 df=32 of=0 ri=0 ql=0 b=10 + 5 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-29 rp=df5 dt=5879/1 dn=2 df=30 of=0 ri=3 ql=0 b=10 + 6 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-28 rp=788 dt=5847/1 dn=2 df=32 of=0 ri=0 ql=0 b=10 + 7 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-53 rp=1098 dt=6199/1 dn=2 df=30 of=0 ri=3 ql=0 b=10 The first section lists the rcu_data structures for rcu, the second for rcu_bh. Each section has one line per CPU, or eight for this 8-CPU system. @@ -254,6 +253,12 @@ o "pqc" indicates which grace period the last-observed quiescent o "qp" indicates that RCU still expects a quiescent state from this CPU. +o "rpfq" is the number of rcu_pending() calls on this CPU required + to induce this CPU to invoke force_quiescent_state(). + +o "rp" is low-order four hex digits of the count of how many times + rcu_pending() has been invoked on this CPU. + o "dt" is the current value of the dyntick counter that is incremented when entering or leaving dynticks idle state, either by the scheduler or by irq. The number after the "/" is the interrupt @@ -300,9 +305,6 @@ o "b" is the batch limit for this CPU. If more than this number of RCU callbacks is ready to invoke, then the remainder will be deferred. -There is also an rcu/rcudata.csv file with the same information in -comma-separated-variable spreadsheet format. - The output of "cat rcu/rcugp" looks as follows: @@ -409,63 +411,3 @@ o Each element of the form "1/1 0:127 ^0" represents one struct For example, the first entry at the lowest level shows "^0", indicating that it corresponds to bit zero in the first entry at the middle level. - - -The output of "cat rcu/rcu_pending" looks as follows: - -rcu: - 0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741 - 1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792 - 2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629 - 3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723 - 4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110 - 5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456 - 6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834 - 7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888 -rcu_bh: - 0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314 - 1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180 - 2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936 - 3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863 - 4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671 - 5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235 - 6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921 - 7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542 - -As always, this is once again split into "rcu" and "rcu_bh" portions. -The fields are as follows: - -o "np" is the number of times that __rcu_pending() has been invoked - for the corresponding flavor of RCU. - -o "qsp" is the number of times that the RCU was waiting for a - quiescent state from this CPU. - -o "cbr" is the number of times that this CPU had RCU callbacks - that had passed through a grace period, and were thus ready - to be invoked. - -o "cng" is the number of times that this CPU needed another - grace period while RCU was idle. - -o "gpc" is the number of times that an old grace period had - completed, but this CPU was not yet aware of it. - -o "gps" is the number of times that a new grace period had started, - but this CPU was not yet aware of it. - -o "nf" is the number of times that this CPU suspected that the - current grace period had run for too long, and thus needed to - be forced. - - Please note that "forcing" consists of sending resched IPIs - to holdout CPUs. If that CPU really still is in an old RCU - read-side critical section, then we really do have to wait for it. - The assumption behing "forcing" is that the CPU is not still in - an old RCU read-side critical section, but has not yet responded - for some other reason. - -o "nn" is the number of times that this CPU needed nothing. Alert - readers will note that the rcu "nn" number for a given CPU very - closely matches the rcu_bh "np" number for that same CPU. This - is due to short-circuit evaluation in rcu_pending(). diff --git a/trunk/Documentation/Smack.txt b/trunk/Documentation/Smack.txt index 34614b4c708e..629c92e99783 100644 --- a/trunk/Documentation/Smack.txt +++ b/trunk/Documentation/Smack.txt @@ -184,9 +184,8 @@ length. Single character labels using special characters, that being anything other than a letter or digit, are reserved for use by the Smack development team. Smack labels are unstructured, case sensitive, and the only operation ever performed on them is comparison for equality. Smack labels cannot -contain unprintable characters, the "/" (slash), the "\" (backslash), the "'" -(quote) and '"' (double-quote) characters. -Smack labels cannot begin with a '-', which is reserved for special options. +contain unprintable characters or the "/" (slash) character. Smack labels +cannot begin with a '-', which is reserved for special options. There are some predefined labels: @@ -524,18 +523,3 @@ Smack supports some mount options: These mount options apply to all file system types. -Smack auditing - -If you want Smack auditing of security events, you need to set CONFIG_AUDIT -in your kernel configuration. -By default, all denied events will be audited. You can change this behavior by -writing a single character to the /smack/logging file : -0 : no logging -1 : log denied (default) -2 : log accepted -3 : log denied & accepted - -Events are logged as 'key=value' pairs, for each event you at least will get -the subjet, the object, the rights requested, the action, the kernel function -that triggered the event, plus other pairs depending on the type of event -audited. diff --git a/trunk/Documentation/block/biodoc.txt b/trunk/Documentation/block/biodoc.txt index 8d2158a1c6aa..6fab97ea7e6b 100644 --- a/trunk/Documentation/block/biodoc.txt +++ b/trunk/Documentation/block/biodoc.txt @@ -186,7 +186,7 @@ a virtual address mapping (unlike the earlier scheme of virtual address do not have a corresponding kernel virtual address space mapping) and low-memory pages. -Note: Please refer to Documentation/DMA-mapping.txt for a discussion +Note: Please refer to Documentation/PCI/PCI-DMA-mapping.txt for a discussion on PCI high mem DMA aspects and mapping of scatter gather lists, and support for 64 bit PCI. diff --git a/trunk/Documentation/filesystems/gfs2-glocks.txt b/trunk/Documentation/filesystems/gfs2-glocks.txt index 0494f78d87e4..4dae9a3840bf 100644 --- a/trunk/Documentation/filesystems/gfs2-glocks.txt +++ b/trunk/Documentation/filesystems/gfs2-glocks.txt @@ -60,7 +60,7 @@ go_lock | Called for the first local holder of a lock go_unlock | Called on the final local unlock of a lock go_dump | Called to print content of object for debugfs file, or on | error to dump glock to the log. -go_type | The type of the glock, LM_TYPE_..... +go_type; | The type of the glock, LM_TYPE_..... go_min_hold_time | The minimum hold time The minimum hold time for each lock is the time after a remote lock diff --git a/trunk/Documentation/filesystems/gfs2.txt b/trunk/Documentation/filesystems/gfs2.txt index 5e3ab8f3beff..593004b6bbab 100644 --- a/trunk/Documentation/filesystems/gfs2.txt +++ b/trunk/Documentation/filesystems/gfs2.txt @@ -11,15 +11,18 @@ their I/O so file system consistency is maintained. One of the nifty features of GFS is perfect consistency -- changes made to the file system on one machine show up immediately on all other machines in the cluster. -GFS uses interchangable inter-node locking mechanisms, the currently -supported mechanisms are: +GFS uses interchangable inter-node locking mechanisms. Different lock +modules can plug into GFS and each file system selects the appropriate +lock module at mount time. Lock modules include: lock_nolock -- allows gfs to be used as a local file system lock_dlm -- uses a distributed lock manager (dlm) for inter-node locking The dlm is found at linux/fs/dlm/ -Lock_dlm depends on user space cluster management systems found +In addition to interfacing with an external locking manager, a gfs lock +module is responsible for interacting with external cluster management +systems. Lock_dlm depends on user space cluster management systems found at the URL above. To use gfs as a local file system, no external clustering systems are @@ -28,19 +31,13 @@ needed, simply: $ mkfs -t gfs2 -p lock_nolock -j 1 /dev/block_device $ mount -t gfs2 /dev/block_device /dir -If you are using Fedora, you need to install the gfs2-utils package -and, for lock_dlm, you will also need to install the cman package -and write a cluster.conf as per the documentation. - -GFS2 is not on-disk compatible with previous versions of GFS, but it -is pretty close. +GFS2 is not on-disk compatible with previous versions of GFS. The following man pages can be found at the URL above: - fsck.gfs2 to repair a filesystem + gfs2_fsck to repair a filesystem gfs2_grow to expand a filesystem online gfs2_jadd to add journals to a filesystem online gfs2_tool to manipulate, examine and tune a filesystem gfs2_quota to examine and change quota values in a filesystem - gfs2_convert to convert a gfs filesystem to gfs2 in-place mount.gfs2 to help mount(8) mount a filesystem mkfs.gfs2 to make a filesystem diff --git a/trunk/Documentation/futex-requeue-pi.txt b/trunk/Documentation/futex-requeue-pi.txt deleted file mode 100644 index 9dc1ff4fd536..000000000000 --- a/trunk/Documentation/futex-requeue-pi.txt +++ /dev/null @@ -1,131 +0,0 @@ -Futex Requeue PI ----------------- - -Requeueing of tasks from a non-PI futex to a PI futex requires -special handling in order to ensure the underlying rt_mutex is never -left without an owner if it has waiters; doing so would break the PI -boosting logic [see rt-mutex-desgin.txt] For the purposes of -brevity, this action will be referred to as "requeue_pi" throughout -this document. Priority inheritance is abbreviated throughout as -"PI". - -Motivation ----------- - -Without requeue_pi, the glibc implementation of -pthread_cond_broadcast() must resort to waking all the tasks waiting -on a pthread_condvar and letting them try to sort out which task -gets to run first in classic thundering-herd formation. An ideal -implementation would wake the highest-priority waiter, and leave the -rest to the natural wakeup inherent in unlocking the mutex -associated with the condvar. - -Consider the simplified glibc calls: - -/* caller must lock mutex */ -pthread_cond_wait(cond, mutex) -{ - lock(cond->__data.__lock); - unlock(mutex); - do { - unlock(cond->__data.__lock); - futex_wait(cond->__data.__futex); - lock(cond->__data.__lock); - } while(...) - unlock(cond->__data.__lock); - lock(mutex); -} - -pthread_cond_broadcast(cond) -{ - lock(cond->__data.__lock); - unlock(cond->__data.__lock); - futex_requeue(cond->data.__futex, cond->mutex); -} - -Once pthread_cond_broadcast() requeues the tasks, the cond->mutex -has waiters. Note that pthread_cond_wait() attempts to lock the -mutex only after it has returned to user space. This will leave the -underlying rt_mutex with waiters, and no owner, breaking the -previously mentioned PI-boosting algorithms. - -In order to support PI-aware pthread_condvar's, the kernel needs to -be able to requeue tasks to PI futexes. This support implies that -upon a successful futex_wait system call, the caller would return to -user space already holding the PI futex. The glibc implementation -would be modified as follows: - - -/* caller must lock mutex */ -pthread_cond_wait_pi(cond, mutex) -{ - lock(cond->__data.__lock); - unlock(mutex); - do { - unlock(cond->__data.__lock); - futex_wait_requeue_pi(cond->__data.__futex); - lock(cond->__data.__lock); - } while(...) - unlock(cond->__data.__lock); - /* the kernel acquired the the mutex for us */ -} - -pthread_cond_broadcast_pi(cond) -{ - lock(cond->__data.__lock); - unlock(cond->__data.__lock); - futex_requeue_pi(cond->data.__futex, cond->mutex); -} - -The actual glibc implementation will likely test for PI and make the -necessary changes inside the existing calls rather than creating new -calls for the PI cases. Similar changes are needed for -pthread_cond_timedwait() and pthread_cond_signal(). - -Implementation --------------- - -In order to ensure the rt_mutex has an owner if it has waiters, it -is necessary for both the requeue code, as well as the waiting code, -to be able to acquire the rt_mutex before returning to user space. -The requeue code cannot simply wake the waiter and leave it to -acquire the rt_mutex as it would open a race window between the -requeue call returning to user space and the waiter waking and -starting to run. This is especially true in the uncontended case. - -The solution involves two new rt_mutex helper routines, -rt_mutex_start_proxy_lock() and rt_mutex_finish_proxy_lock(), which -allow the requeue code to acquire an uncontended rt_mutex on behalf -of the waiter and to enqueue the waiter on a contended rt_mutex. -Two new system calls provide the kernel<->user interface to -requeue_pi: FUTEX_WAIT_REQUEUE_PI and FUTEX_REQUEUE_CMP_PI. - -FUTEX_WAIT_REQUEUE_PI is called by the waiter (pthread_cond_wait() -and pthread_cond_timedwait()) to block on the initial futex and wait -to be requeued to a PI-aware futex. The implementation is the -result of a high-speed collision between futex_wait() and -futex_lock_pi(), with some extra logic to check for the additional -wake-up scenarios. - -FUTEX_REQUEUE_CMP_PI is called by the waker -(pthread_cond_broadcast() and pthread_cond_signal()) to requeue and -possibly wake the waiting tasks. Internally, this system call is -still handled by futex_requeue (by passing requeue_pi=1). Before -requeueing, futex_requeue() attempts to acquire the requeue target -PI futex on behalf of the top waiter. If it can, this waiter is -woken. futex_requeue() then proceeds to requeue the remaining -nr_wake+nr_requeue tasks to the PI futex, calling -rt_mutex_start_proxy_lock() prior to each requeue to prepare the -task as a waiter on the underlying rt_mutex. It is possible that -the lock can be acquired at this stage as well, if so, the next -waiter is woken to finish the acquisition of the lock. - -FUTEX_REQUEUE_PI accepts nr_wake and nr_requeue as arguments, but -their sum is all that really matters. futex_requeue() will wake or -requeue up to nr_wake + nr_requeue tasks. It will wake only as many -tasks as it can acquire the lock for, which in the majority of cases -should be 0 as good programming practice dictates that the caller of -either pthread_cond_broadcast() or pthread_cond_signal() acquire the -mutex prior to making the call. FUTEX_REQUEUE_PI requires that -nr_wake=1. nr_requeue should be INT_MAX for broadcast and 0 for -signal. diff --git a/trunk/Documentation/kernel-parameters.txt b/trunk/Documentation/kernel-parameters.txt index 72d3bf08d79b..fd5cac013037 100644 --- a/trunk/Documentation/kernel-parameters.txt +++ b/trunk/Documentation/kernel-parameters.txt @@ -56,6 +56,7 @@ parameter is applicable: ISAPNP ISA PnP code is enabled. ISDN Appropriate ISDN support is enabled. JOY Appropriate joystick support is enabled. + KMEMTRACE kmemtrace is enabled. LIBATA Libata driver is enabled LP Printer support is enabled. LOOP Loopback device support is enabled. @@ -328,6 +329,11 @@ and is between 256 and 4096 characters. It is defined in the file flushed before they will be reused, which is a lot of faster + amd_iommu_size= [HW,X86-64] + Define the size of the aperture for the AMD IOMMU + driver. Possible values are: + '32M', '64M' (default), '128M', '256M', '512M', '1G' + amijoy.map= [HW,JOY] Amiga joystick support Map of devices attached to JOY0DAT and JOY1DAT Format: , @@ -640,13 +646,6 @@ and is between 256 and 4096 characters. It is defined in the file DMA-API debugging code disables itself because the architectural default is too low. - dma_debug_driver= - With this option the DMA-API debugging driver - filter feature can be enabled at boot time. Just - pass the driver to filter for as the parameter. - The filter can be disabled or changed to another - driver later using sysfs. - dscc4.setup= [NET] dtc3181e= [HW,SCSI] @@ -753,25 +752,12 @@ and is between 256 and 4096 characters. It is defined in the file ia64_pal_cache_flush instead of SAL_CACHE_FLUSH. ftrace=[tracer] - [FTRACE] will set and start the specified tracer + [ftrace] will set and start the specified tracer as early as possible in order to facilitate early boot debugging. ftrace_dump_on_oops - [FTRACE] will dump the trace buffers on oops. - - ftrace_filter=[function-list] - [FTRACE] Limit the functions traced by the function - tracer at boot up. function-list is a comma separated - list of functions. This list can be changed at run - time by the set_ftrace_filter file in the debugfs - tracing directory. - - ftrace_notrace=[function-list] - [FTRACE] Do not trace the functions specified in - function-list. This list can be changed at run time - by the set_ftrace_notrace file in the debugfs - tracing directory. + [ftrace] will dump the trace buffers on oops. gamecon.map[2|3]= [HW,JOY] Multisystem joystick and NES/SNES/PSX pad @@ -928,12 +914,6 @@ and is between 256 and 4096 characters. It is defined in the file Formt: { "sha1" | "md5" } default: "sha1" - ima_tcb [IMA] - Load a policy which meets the needs of the Trusted - Computing Base. This means IMA will measure all - programs exec'd, files mmap'd for exec, and all files - opened for read by uid=0. - in2000= [HW,SCSI] See header of drivers/scsi/in2000.c. @@ -1074,6 +1054,15 @@ and is between 256 and 4096 characters. It is defined in the file use the HighMem zone if it exists, and the Normal zone if it does not. + kmemtrace.enable= [KNL,KMEMTRACE] Format: { yes | no } + Controls whether kmemtrace is enabled + at boot-time. + + kmemtrace.subbufs=n [KNL,KMEMTRACE] Overrides the number of + subbufs kmemtrace's relay channel has. Set this + higher than default (KMEMTRACE_N_SUBBUFS in code) if + you experience buffer overruns. + kgdboc= [HW] kgdb over consoles. Requires a tty driver that supports console polling. (only serial suported for now) @@ -1586,9 +1575,6 @@ and is between 256 and 4096 characters. It is defined in the file noinitrd [RAM] Tells the kernel not to load any configured initial RAM disk. - nointremap [X86-64, Intel-IOMMU] Do not enable interrupt - remapping. - nointroute [IA-64] nojitter [IA64] Disables jitter checking for ITC timers. @@ -1674,14 +1660,6 @@ and is between 256 and 4096 characters. It is defined in the file oprofile.timer= [HW] Use timer interrupt instead of performance counters - oprofile.cpu_type= Force an oprofile cpu type - This might be useful if you have an older oprofile - userland or if you want common events. - Format: { archperfmon } - archperfmon: [X86] Force use of architectural - perfmon on Intel CPUs instead of the - CPU specific event set. - osst= [HW,SCSI] SCSI Tape Driver Format: , See also Documentation/scsi/st.txt. diff --git a/trunk/Documentation/memory-barriers.txt b/trunk/Documentation/memory-barriers.txt index 7f5809eddee6..f5b7127f54ac 100644 --- a/trunk/Documentation/memory-barriers.txt +++ b/trunk/Documentation/memory-barriers.txt @@ -31,7 +31,6 @@ Contents: - Locking functions. - Interrupt disabling functions. - - Sleep and wake-up functions. - Miscellaneous functions. (*) Inter-CPU locking barrier effects. @@ -1218,132 +1217,6 @@ barriers are required in such a situation, they must be provided from some other means. -SLEEP AND WAKE-UP FUNCTIONS ---------------------------- - -Sleeping and waking on an event flagged in global data can be viewed as an -interaction between two pieces of data: the task state of the task waiting for -the event and the global data used to indicate the event. To make sure that -these appear to happen in the right order, the primitives to begin the process -of going to sleep, and the primitives to initiate a wake up imply certain -barriers. - -Firstly, the sleeper normally follows something like this sequence of events: - - for (;;) { - set_current_state(TASK_UNINTERRUPTIBLE); - if (event_indicated) - break; - schedule(); - } - -A general memory barrier is interpolated automatically by set_current_state() -after it has altered the task state: - - CPU 1 - =============================== - set_current_state(); - set_mb(); - STORE current->state - - LOAD event_indicated - -set_current_state() may be wrapped by: - - prepare_to_wait(); - prepare_to_wait_exclusive(); - -which therefore also imply a general memory barrier after setting the state. -The whole sequence above is available in various canned forms, all of which -interpolate the memory barrier in the right place: - - wait_event(); - wait_event_interruptible(); - wait_event_interruptible_exclusive(); - wait_event_interruptible_timeout(); - wait_event_killable(); - wait_event_timeout(); - wait_on_bit(); - wait_on_bit_lock(); - - -Secondly, code that performs a wake up normally follows something like this: - - event_indicated = 1; - wake_up(&event_wait_queue); - -or: - - event_indicated = 1; - wake_up_process(event_daemon); - -A write memory barrier is implied by wake_up() and co. if and only if they wake -something up. The barrier occurs before the task state is cleared, and so sits -between the STORE to indicate the event and the STORE to set TASK_RUNNING: - - CPU 1 CPU 2 - =============================== =============================== - set_current_state(); STORE event_indicated - set_mb(); wake_up(); - STORE current->state - STORE current->state - LOAD event_indicated - -The available waker functions include: - - complete(); - wake_up(); - wake_up_all(); - wake_up_bit(); - wake_up_interruptible(); - wake_up_interruptible_all(); - wake_up_interruptible_nr(); - wake_up_interruptible_poll(); - wake_up_interruptible_sync(); - wake_up_interruptible_sync_poll(); - wake_up_locked(); - wake_up_locked_poll(); - wake_up_nr(); - wake_up_poll(); - wake_up_process(); - - -[!] Note that the memory barriers implied by the sleeper and the waker do _not_ -order multiple stores before the wake-up with respect to loads of those stored -values after the sleeper has called set_current_state(). For instance, if the -sleeper does: - - set_current_state(TASK_INTERRUPTIBLE); - if (event_indicated) - break; - __set_current_state(TASK_RUNNING); - do_something(my_data); - -and the waker does: - - my_data = value; - event_indicated = 1; - wake_up(&event_wait_queue); - -there's no guarantee that the change to event_indicated will be perceived by -the sleeper as coming after the change to my_data. In such a circumstance, the -code on both sides must interpolate its own memory barriers between the -separate data accesses. Thus the above sleeper ought to do: - - set_current_state(TASK_INTERRUPTIBLE); - if (event_indicated) { - smp_rmb(); - do_something(my_data); - } - -and the waker should do: - - my_data = value; - smp_wmb(); - event_indicated = 1; - wake_up(&event_wait_queue); - - MISCELLANEOUS FUNCTIONS ----------------------- @@ -1493,7 +1366,7 @@ WHERE ARE MEMORY BARRIERS NEEDED? Under normal operation, memory operation reordering is generally not going to be a problem as a single-threaded linear piece of code will still appear to -work correctly, even if it's in an SMP kernel. There are, however, four +work correctly, even if it's in an SMP kernel. There are, however, three circumstances in which reordering definitely _could_ be a problem: (*) Interprocessor interaction. diff --git a/trunk/Documentation/scheduler/sched-rt-group.txt b/trunk/Documentation/scheduler/sched-rt-group.txt index 1df7f9cdab05..5ba4d3fc625a 100644 --- a/trunk/Documentation/scheduler/sched-rt-group.txt +++ b/trunk/Documentation/scheduler/sched-rt-group.txt @@ -4,7 +4,6 @@ CONTENTS ======== -0. WARNING 1. Overview 1.1 The problem 1.2 The solution @@ -15,23 +14,6 @@ CONTENTS 3. Future plans -0. WARNING -========== - - Fiddling with these settings can result in an unstable system, the knobs are - root only and assumes root knows what he is doing. - -Most notable: - - * very small values in sched_rt_period_us can result in an unstable - system when the period is smaller than either the available hrtimer - resolution, or the time it takes to handle the budget refresh itself. - - * very small values in sched_rt_runtime_us can result in an unstable - system when the runtime is so small the system has difficulty making - forward progress (NOTE: the migration thread and kstopmachine both - are real-time processes). - 1. Overview =========== @@ -187,7 +169,7 @@ get their allocated time. Implementing SCHED_EDF might take a while to complete. Priority Inheritance is the biggest challenge as the current linux PI infrastructure is geared towards -the limited static priority levels 0-99. With deadline scheduling you need to +the limited static priority levels 0-139. With deadline scheduling you need to do deadline inheritance (since priority is inversely proportional to the deadline delta (deadline - now). diff --git a/trunk/Documentation/sysctl/kernel.txt b/trunk/Documentation/sysctl/kernel.txt index 322a00bb99d9..f11ca7979fa6 100644 --- a/trunk/Documentation/sysctl/kernel.txt +++ b/trunk/Documentation/sysctl/kernel.txt @@ -32,7 +32,6 @@ show up in /proc/sys/kernel: - kstack_depth_to_print [ X86 only ] - l2cr [ PPC only ] - modprobe ==> Documentation/debugging-modules.txt -- modules_disabled - msgmax - msgmnb - msgmni @@ -185,16 +184,6 @@ kernel stack. ============================================================== -modules_disabled: - -A toggle value indicating if modules are allowed to be loaded -in an otherwise modular kernel. This toggle defaults to off -(0), but can be set true (1). Once true, modules can be -neither loaded nor unloaded, and the toggle cannot be set back -to false. - -============================================================== - osrelease, ostype & version: # cat osrelease diff --git a/trunk/Documentation/trace/events.txt b/trunk/Documentation/trace/events.txt deleted file mode 100644 index f157d7594ea7..000000000000 --- a/trunk/Documentation/trace/events.txt +++ /dev/null @@ -1,90 +0,0 @@ - Event Tracing - - Documentation written by Theodore Ts'o - Updated by Li Zefan - -1. Introduction -=============== - -Tracepoints (see Documentation/trace/tracepoints.txt) can be used -without creating custom kernel modules to register probe functions -using the event tracing infrastructure. - -Not all tracepoints can be traced using the event tracing system; -the kernel developer must provide code snippets which define how the -tracing information is saved into the tracing buffer, and how the -tracing information should be printed. - -2. Using Event Tracing -====================== - -2.1 Via the 'set_event' interface ---------------------------------- - -The events which are available for tracing can be found in the file -/debug/tracing/available_events. - -To enable a particular event, such as 'sched_wakeup', simply echo it -to /debug/tracing/set_event. For example: - - # echo sched_wakeup >> /debug/tracing/set_event - -[ Note: '>>' is necessary, otherwise it will firstly disable - all the events. ] - -To disable an event, echo the event name to the set_event file prefixed -with an exclamation point: - - # echo '!sched_wakeup' >> /debug/tracing/set_event - -To disable all events, echo an empty line to the set_event file: - - # echo > /debug/tracing/set_event - -To enable all events, echo '*:*' or '*:' to the set_event file: - - # echo *:* > /debug/tracing/set_event - -The events are organized into subsystems, such as ext4, irq, sched, -etc., and a full event name looks like this: :. The -subsystem name is optional, but it is displayed in the available_events -file. All of the events in a subsystem can be specified via the syntax -":*"; for example, to enable all irq events, you can use the -command: - - # echo 'irq:*' > /debug/tracing/set_event - -2.2 Via the 'enable' toggle ---------------------------- - -The events available are also listed in /debug/tracing/events/ hierarchy -of directories. - -To enable event 'sched_wakeup': - - # echo 1 > /debug/tracing/events/sched/sched_wakeup/enable - -To disable it: - - # echo 0 > /debug/tracing/events/sched/sched_wakeup/enable - -To enable all events in sched subsystem: - - # echo 1 > /debug/tracing/events/sched/enable - -To eanble all events: - - # echo 1 > /debug/tracing/events/enable - -When reading one of these enable files, there are four results: - - 0 - all events this file affects are disabled - 1 - all events this file affects are enabled - X - there is a mixture of events enabled and disabled - ? - this file does not affect any event - -3. Defining an event-enabled tracepoint -======================================= - -See The example provided in samples/trace_events - diff --git a/trunk/Documentation/trace/ftrace.txt b/trunk/Documentation/trace/ftrace.txt index 2a82d8602944..fd9a3e693813 100644 --- a/trunk/Documentation/trace/ftrace.txt +++ b/trunk/Documentation/trace/ftrace.txt @@ -179,7 +179,7 @@ Here is the list of current tracers that may be configured. Function call tracer to trace all kernel functions. - "function_graph" + "function_graph_tracer" Similar to the function tracer except that the function tracer probes the functions on their entry @@ -518,18 +518,9 @@ priority with zero (0) being the highest priority and the nice values starting at 100 (nice -20). Below is a quick chart to map the kernel priority to user land priorities. - Kernel Space User Space - =============================================================== - 0(high) to 98(low) user RT priority 99(high) to 1(low) - with SCHED_RR or SCHED_FIFO - --------------------------------------------------------------- - 99 sched_priority is not used in scheduling - decisions(it must be specified as 0) - --------------------------------------------------------------- - 100(high) to 139(low) user nice -20(high) to 19(low) - --------------------------------------------------------------- - 140 idle task priority - --------------------------------------------------------------- + Kernel priority: 0 to 99 ==> user RT priority 99 to 0 + Kernel priority: 100 to 139 ==> user nice -20 to 19 + Kernel priority: 140 ==> idle task priority The task states are: diff --git a/trunk/Documentation/trace/power.txt b/trunk/Documentation/trace/power.txt deleted file mode 100644 index cd805e16dc27..000000000000 --- a/trunk/Documentation/trace/power.txt +++ /dev/null @@ -1,17 +0,0 @@ -The power tracer collects detailed information about C-state and P-state -transitions, instead of just looking at the high-level "average" -information. - -There is a helper script found in scrips/tracing/power.pl in the kernel -sources which can be used to parse this information and create a -Scalable Vector Graphics (SVG) picture from the trace data. - -To use this tracer: - - echo 0 > /sys/kernel/debug/tracing/tracing_enabled - echo power > /sys/kernel/debug/tracing/current_tracer - echo 1 > /sys/kernel/debug/tracing/tracing_enabled - sleep 1 - echo 0 > /sys/kernel/debug/tracing/tracing_enabled - cat /sys/kernel/debug/tracing/trace | \ - perl scripts/tracing/power.pl > out.sv diff --git a/trunk/Documentation/x86/boot.txt b/trunk/Documentation/x86/boot.txt index 8da3a795083f..e0203662f9e9 100644 --- a/trunk/Documentation/x86/boot.txt +++ b/trunk/Documentation/x86/boot.txt @@ -50,10 +50,6 @@ Protocol 2.08: (Kernel 2.6.26) Added crc32 checksum and ELF format Protocol 2.09: (Kernel 2.6.26) Added a field of 64-bit physical pointer to single linked list of struct setup_data. -Protocol 2.10: (Kernel 2.6.31) Added a protocol for relaxed alignment - beyond the kernel_alignment added, new init_size and - pref_address fields. Added extended boot loader IDs. - **** MEMORY LAYOUT The traditional memory map for the kernel loader, used for Image or @@ -172,13 +168,12 @@ Offset Proto Name Meaning 021C/4 2.00+ ramdisk_size initrd size (set by boot loader) 0220/4 2.00+ bootsect_kludge DO NOT USE - for bootsect.S use only 0224/2 2.01+ heap_end_ptr Free memory after setup end -0226/1 2.02+(3 ext_loader_ver Extended boot loader version -0227/1 2.02+(3 ext_loader_type Extended boot loader ID +0226/2 N/A pad1 Unused 0228/4 2.02+ cmd_line_ptr 32-bit pointer to the kernel command line 022C/4 2.03+ ramdisk_max Highest legal initrd address 0230/4 2.05+ kernel_alignment Physical addr alignment required for kernel 0234/1 2.05+ relocatable_kernel Whether kernel is relocatable or not -0235/1 2.10+ min_alignment Minimum alignment, as a power of two +0235/1 N/A pad2 Unused 0236/2 N/A pad3 Unused 0238/4 2.06+ cmdline_size Maximum size of the kernel command line 023C/4 2.07+ hardware_subarch Hardware subarchitecture @@ -187,8 +182,6 @@ Offset Proto Name Meaning 024C/4 2.08+ payload_length Length of kernel payload 0250/8 2.09+ setup_data 64-bit physical pointer to linked list of struct setup_data -0258/8 2.10+ pref_address Preferred loading address -0260/4 2.10+ init_size Linear memory required during initialization (1) For backwards compatibility, if the setup_sects field contains 0, the real value is 4. @@ -197,8 +190,6 @@ Offset Proto Name Meaning field are unusable, which means the size of a bzImage kernel cannot be determined. -(3) Ignored, but safe to set, for boot protocols 2.02-2.09. - If the "HdrS" (0x53726448) magic number is not found at offset 0x202, the boot protocol version is "old". Loading an old kernel, the following parameters should be assumed: @@ -352,32 +343,18 @@ Protocol: 2.00+ 0xTV here, where T is an identifier for the boot loader and V is a version number. Otherwise, enter 0xFF here. - For boot loader IDs above T = 0xD, write T = 0xE to this field and - write the extended ID minus 0x10 to the ext_loader_type field. - Similarly, the ext_loader_ver field can be used to provide more than - four bits for the bootloader version. - - For example, for T = 0x15, V = 0x234, write: - - type_of_loader <- 0xE4 - ext_loader_type <- 0x05 - ext_loader_ver <- 0x23 - Assigned boot loader ids: 0 LILO (0x00 reserved for pre-2.00 bootloader) 1 Loadlin 2 bootsect-loader (0x20, all other values reserved) - 3 Syslinux - 4 Etherboot/gPXE + 3 SYSLINUX + 4 EtherBoot 5 ELILO 7 GRUB - 8 U-Boot + 8 U-BOOT 9 Xen A Gujin B Qemu - C Arcturus Networks uCbootloader - E Extended (see ext_loader_type) - F Special (0xFF = undefined) Please contact if you need a bootloader ID value assigned. @@ -476,35 +453,6 @@ Protocol: 2.01+ Set this field to the offset (from the beginning of the real-mode code) of the end of the setup stack/heap, minus 0x0200. -Field name: ext_loader_ver -Type: write (optional) -Offset/size: 0x226/1 -Protocol: 2.02+ - - This field is used as an extension of the version number in the - type_of_loader field. The total version number is considered to be - (type_of_loader & 0x0f) + (ext_loader_ver << 4). - - The use of this field is boot loader specific. If not written, it - is zero. - - Kernels prior to 2.6.31 did not recognize this field, but it is safe - to write for protocol version 2.02 or higher. - -Field name: ext_loader_type -Type: write (obligatory if (type_of_loader & 0xf0) == 0xe0) -Offset/size: 0x227/1 -Protocol: 2.02+ - - This field is used as an extension of the type number in - type_of_loader field. If the type in type_of_loader is 0xE, then - the actual type is (ext_loader_type + 0x10). - - This field is ignored if the type in type_of_loader is not 0xE. - - Kernels prior to 2.6.31 did not recognize this field, but it is safe - to write for protocol version 2.02 or higher. - Field name: cmd_line_ptr Type: write (obligatory) Offset/size: 0x228/4 @@ -534,19 +482,11 @@ Protocol: 2.03+ 0x37FFFFFF, you can start your ramdisk at 0x37FE0000.) Field name: kernel_alignment -Type: read/modify (reloc) +Type: read (reloc) Offset/size: 0x230/4 -Protocol: 2.05+ (read), 2.10+ (modify) - - Alignment unit required by the kernel (if relocatable_kernel is - true.) A relocatable kernel that is loaded at an alignment - incompatible with the value in this field will be realigned during - kernel initialization. +Protocol: 2.05+ - Starting with protocol version 2.10, this reflects the kernel - alignment preferred for optimal performance; it is possible for the - loader to modify this field to permit a lesser alignment. See the - min_alignment and pref_address field below. + Alignment unit required by the kernel (if relocatable_kernel is true.) Field name: relocatable_kernel Type: read (reloc) @@ -558,22 +498,6 @@ Protocol: 2.05+ After loading, the boot loader must set the code32_start field to point to the loaded code, or to a boot loader hook. -Field name: min_alignment -Type: read (reloc) -Offset/size: 0x235/1 -Protocol: 2.10+ - - This field, if nonzero, indicates as a power of two the minimum - alignment required, as opposed to preferred, by the kernel to boot. - If a boot loader makes use of this field, it should update the - kernel_alignment field with the alignment unit desired; typically: - - kernel_alignment = 1 << min_alignment - - There may be a considerable performance cost with an excessively - misaligned kernel. Therefore, a loader should typically try each - power-of-two alignment from kernel_alignment down to this alignment. - Field name: cmdline_size Type: read Offset/size: 0x238/4 @@ -658,36 +582,6 @@ Protocol: 2.09+ sure to consider the case where the linked list already contains entries. -Field name: pref_address -Type: read (reloc) -Offset/size: 0x258/8 -Protocol: 2.10+ - - This field, if nonzero, represents a preferred load address for the - kernel. A relocating bootloader should attempt to load at this - address if possible. - - A non-relocatable kernel will unconditionally move itself and to run - at this address. - -Field name: init_size -Type: read -Offset/size: 0x25c/4 - - This field indicates the amount of linear contiguous memory starting - at the kernel runtime start address that the kernel needs before it - is capable of examining its memory map. This is not the same thing - as the total amount of memory the kernel needs to boot, but it can - be used by a relocating boot loader to help select a safe load - address for the kernel. - - The kernel runtime start address is determined by the following algorithm: - - if (relocatable_kernel) - runtime_start = align_up(load_address, kernel_alignment) - else - runtime_start = pref_address - **** THE IMAGE CHECKSUM diff --git a/trunk/Documentation/x86/x86_64/boot-options.txt b/trunk/Documentation/x86/x86_64/boot-options.txt index 2db5893d6c97..34c13040a718 100644 --- a/trunk/Documentation/x86/x86_64/boot-options.txt +++ b/trunk/Documentation/x86/x86_64/boot-options.txt @@ -150,6 +150,11 @@ NUMA Otherwise, the remaining system RAM is allocated to an additional node. + numa=hotadd=percent + Only allow hotadd memory to preallocate page structures upto + percent of already available memory. + numa=hotadd=0 will disable hotadd memory. + ACPI acpi=off Don't enable ACPI diff --git a/trunk/Documentation/x86/x86_64/mm.txt b/trunk/Documentation/x86/x86_64/mm.txt index d6498e3cd713..29b52b14d0b4 100644 --- a/trunk/Documentation/x86/x86_64/mm.txt +++ b/trunk/Documentation/x86/x86_64/mm.txt @@ -6,11 +6,10 @@ 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 -ffff880000000000 - ffffc7ffffffffff (=64 TB) direct mapping of all phys. memory -ffffc80000000000 - ffffc8ffffffffff (=40 bits) hole -ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space -ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole -ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB) +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) ... unused hole ... ffffffff80000000 - ffffffffa0000000 (=512 MB) kernel text mapping, from phys 0 ffffffffa0000000 - fffffffffff00000 (=1536 MB) module mapping space diff --git a/trunk/MAINTAINERS b/trunk/MAINTAINERS index ccdb57524e3c..cf4abddfc8a4 100644 --- a/trunk/MAINTAINERS +++ b/trunk/MAINTAINERS @@ -71,7 +71,7 @@ P: Person M: Mail patches to L: Mailing list that is relevant to this area W: Web-page with status/info -T: SCM tree type and location. Type is one of: git, hg, quilt, stgit. +T: SCM tree type and location. Type is one of: git, hg, quilt. S: Status, one of the following: Supported: Someone is actually paid to look after this. @@ -159,8 +159,7 @@ F: drivers/net/r8169.c 8250/16?50 (AND CLONE UARTS) SERIAL DRIVER L: linux-serial@vger.kernel.org W: http://serial.sourceforge.net -M: alan@lxorguk.ukuu.org.uk -S: Odd Fixes +S: Orphan F: drivers/serial/8250* F: include/linux/serial_8250.h @@ -1979,16 +1978,6 @@ F: Documentation/edac.txt F: drivers/edac/edac_* F: include/linux/edac.h -EDAC-AMD64 -P: Doug Thompson -M: dougthompson@xmission.com -P: Borislav Petkov -M: borislav.petkov@amd.com -L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers) -W: bluesmoke.sourceforge.net -S: Supported -F: drivers/edac/amd64_edac* - EDAC-E752X P: Mark Gross M: mark.gross@intel.com @@ -5640,7 +5629,6 @@ P: Alan Cox M: alan@lxorguk.ukuu.org.uk L: linux-kernel@vger.kernel.org S: Maintained -T: stgit http://zeniv.linux.org.uk/~alan/ttydev/ TULIP NETWORK DRIVERS P: Grant Grundler diff --git a/trunk/arch/alpha/kernel/sys_dp264.c b/trunk/arch/alpha/kernel/sys_dp264.c index 5bd5259324b7..9c9d1fd4155f 100644 --- a/trunk/arch/alpha/kernel/sys_dp264.c +++ b/trunk/arch/alpha/kernel/sys_dp264.c @@ -176,26 +176,22 @@ cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity) } } -static int +static void dp264_set_affinity(unsigned int irq, const struct cpumask *affinity) { spin_lock(&dp264_irq_lock); cpu_set_irq_affinity(irq, *affinity); tsunami_update_irq_hw(cached_irq_mask); spin_unlock(&dp264_irq_lock); - - return 0; } -static int +static void clipper_set_affinity(unsigned int irq, const struct cpumask *affinity) { spin_lock(&dp264_irq_lock); cpu_set_irq_affinity(irq - 16, *affinity); tsunami_update_irq_hw(cached_irq_mask); spin_unlock(&dp264_irq_lock); - - return 0; } static struct hw_interrupt_type dp264_irq_type = { diff --git a/trunk/arch/alpha/kernel/sys_titan.c b/trunk/arch/alpha/kernel/sys_titan.c index 8dd239ebdb9e..27f840a4ad3d 100644 --- a/trunk/arch/alpha/kernel/sys_titan.c +++ b/trunk/arch/alpha/kernel/sys_titan.c @@ -157,15 +157,13 @@ titan_cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity) } -static int +static void titan_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) { spin_lock(&titan_irq_lock); titan_cpu_set_irq_affinity(irq - 16, *affinity); titan_update_irq_hw(titan_cached_irq_mask); spin_unlock(&titan_irq_lock); - - return 0; } static void diff --git a/trunk/arch/arm/common/gic.c b/trunk/arch/arm/common/gic.c index 664c7b8b1ba8..3e1714c6523f 100644 --- a/trunk/arch/arm/common/gic.c +++ b/trunk/arch/arm/common/gic.c @@ -109,7 +109,7 @@ static void gic_unmask_irq(unsigned int irq) } #ifdef CONFIG_SMP -static int gic_set_cpu(unsigned int irq, const struct cpumask *mask_val) +static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val) { void __iomem *reg = gic_dist_base(irq) + GIC_DIST_TARGET + (gic_irq(irq) & ~3); unsigned int shift = (irq % 4) * 8; @@ -122,8 +122,6 @@ static int gic_set_cpu(unsigned int irq, const struct cpumask *mask_val) val |= 1 << (cpu + shift); writel(val, reg); spin_unlock(&irq_controller_lock); - - return 0; } #endif diff --git a/trunk/arch/arm/plat-mxc/include/mach/imx-uart.h b/trunk/arch/arm/plat-mxc/include/mach/imx-uart.h index f9bd17dd8dd7..599217b2e13f 100644 --- a/trunk/arch/arm/plat-mxc/include/mach/imx-uart.h +++ b/trunk/arch/arm/plat-mxc/include/mach/imx-uart.h @@ -20,16 +20,11 @@ #define ASMARM_ARCH_UART_H #define IMXUART_HAVE_RTSCTS (1<<0) -#define IMXUART_IRDA (1<<1) struct imxuart_platform_data { int (*init)(struct platform_device *pdev); int (*exit)(struct platform_device *pdev); unsigned int flags; - void (*irda_enable)(int enable); - unsigned int irda_inv_rx:1; - unsigned int irda_inv_tx:1; - unsigned short transceiver_delay; }; #endif diff --git a/trunk/arch/arm/plat-omap/mailbox.c b/trunk/arch/arm/plat-omap/mailbox.c index 40424edae939..0abfbaa59871 100644 --- a/trunk/arch/arm/plat-omap/mailbox.c +++ b/trunk/arch/arm/plat-omap/mailbox.c @@ -147,40 +147,24 @@ static int __mbox_msg_send(struct omap_mbox *mbox, mbox_msg_t msg, void *arg) return ret; } -struct omap_msg_tx_data { - mbox_msg_t msg; - void *arg; -}; - -static void omap_msg_tx_end_io(struct request *rq, int error) -{ - kfree(rq->special); - __blk_put_request(rq->q, rq); -} - int omap_mbox_msg_send(struct omap_mbox *mbox, mbox_msg_t msg, void* arg) { - struct omap_msg_tx_data *tx_data; struct request *rq; struct request_queue *q = mbox->txq->queue; - - tx_data = kmalloc(sizeof(*tx_data), GFP_ATOMIC); - if (unlikely(!tx_data)) - return -ENOMEM; + int ret = 0; rq = blk_get_request(q, WRITE, GFP_ATOMIC); if (unlikely(!rq)) { - kfree(tx_data); - return -ENOMEM; + ret = -ENOMEM; + goto fail; } - tx_data->msg = msg; - tx_data->arg = arg; - rq->end_io = omap_msg_tx_end_io; - blk_insert_request(q, rq, 0, tx_data); + rq->data = (void *)msg; + blk_insert_request(q, rq, 0, arg); schedule_work(&mbox->txq->work); - return 0; + fail: + return ret; } EXPORT_SYMBOL(omap_mbox_msg_send); @@ -194,28 +178,22 @@ static void mbox_tx_work(struct work_struct *work) struct request_queue *q = mbox->txq->queue; while (1) { - struct omap_msg_tx_data *tx_data; - spin_lock(q->queue_lock); - rq = blk_fetch_request(q); + rq = elv_next_request(q); spin_unlock(q->queue_lock); if (!rq) break; - tx_data = rq->special; - - ret = __mbox_msg_send(mbox, tx_data->msg, tx_data->arg); + ret = __mbox_msg_send(mbox, (mbox_msg_t) rq->data, rq->special); if (ret) { enable_mbox_irq(mbox, IRQ_TX); - spin_lock(q->queue_lock); - blk_requeue_request(q, rq); - spin_unlock(q->queue_lock); return; } spin_lock(q->queue_lock); - __blk_end_request_all(rq, 0); + if (__blk_end_request(rq, 0, 0)) + BUG(); spin_unlock(q->queue_lock); } } @@ -240,13 +218,16 @@ static void mbox_rx_work(struct work_struct *work) while (1) { spin_lock_irqsave(q->queue_lock, flags); - rq = blk_fetch_request(q); + rq = elv_next_request(q); spin_unlock_irqrestore(q->queue_lock, flags); if (!rq) break; - msg = (mbox_msg_t)rq->special; - blk_end_request_all(rq, 0); + msg = (mbox_msg_t) rq->data; + + if (blk_end_request(rq, 0, 0)) + BUG(); + mbox->rxq->callback((void *)msg); } } @@ -283,6 +264,7 @@ static void __mbox_rx_interrupt(struct omap_mbox *mbox) goto nomem; msg = mbox_fifo_read(mbox); + rq->data = (void *)msg; if (unlikely(mbox_seq_test(mbox, msg))) { pr_info("mbox: Illegal seq bit!(%08x)\n", msg); @@ -290,7 +272,7 @@ static void __mbox_rx_interrupt(struct omap_mbox *mbox) mbox->err_notify(); } - blk_insert_request(q, rq, 0, (void *)msg); + blk_insert_request(q, rq, 0, NULL); if (mbox->ops->type == OMAP_MBOX_TYPE1) break; } @@ -347,15 +329,16 @@ omap_mbox_read(struct device *dev, struct device_attribute *attr, char *buf) while (1) { spin_lock_irqsave(q->queue_lock, flags); - rq = blk_fetch_request(q); + rq = elv_next_request(q); spin_unlock_irqrestore(q->queue_lock, flags); if (!rq) break; - *p = (mbox_msg_t)rq->special; + *p = (mbox_msg_t) rq->data; - blk_end_request_all(rq, 0); + if (blk_end_request(rq, 0, 0)) + BUG(); if (unlikely(mbox_seq_test(mbox, *p))) { pr_info("mbox: Illegal seq bit!(%08x) ignored\n", *p); diff --git a/trunk/arch/cris/arch-v32/kernel/irq.c b/trunk/arch/cris/arch-v32/kernel/irq.c index d70b445f4a8f..df3925cb1c7f 100644 --- a/trunk/arch/cris/arch-v32/kernel/irq.c +++ b/trunk/arch/cris/arch-v32/kernel/irq.c @@ -325,14 +325,12 @@ static void end_crisv32_irq(unsigned int irq) { } -int set_affinity_crisv32_irq(unsigned int irq, const struct cpumask *dest) +void set_affinity_crisv32_irq(unsigned int irq, const struct cpumask *dest) { unsigned long flags; spin_lock_irqsave(&irq_lock, flags); irq_allocations[irq - FIRST_IRQ].mask = *dest; spin_unlock_irqrestore(&irq_lock, flags); - - return 0; } static struct irq_chip crisv32_irq_type = { diff --git a/trunk/arch/frv/Kconfig b/trunk/arch/frv/Kconfig index 8a5bd7a9c6f5..9d1552a9ee2c 100644 --- a/trunk/arch/frv/Kconfig +++ b/trunk/arch/frv/Kconfig @@ -6,7 +6,6 @@ config FRV bool default y select HAVE_IDE - select HAVE_ARCH_TRACEHOOK config ZONE_DMA bool diff --git a/trunk/arch/frv/include/asm/bitops.h b/trunk/arch/frv/include/asm/bitops.h index 50ae91b29674..287f6f697ce2 100644 --- a/trunk/arch/frv/include/asm/bitops.h +++ b/trunk/arch/frv/include/asm/bitops.h @@ -112,7 +112,7 @@ extern unsigned long atomic_test_and_XOR_mask(unsigned long mask, volatile unsig #define atomic_clear_mask(mask, v) atomic_test_and_ANDNOT_mask((mask), (v)) #define atomic_set_mask(mask, v) atomic_test_and_OR_mask((mask), (v)) -static inline int test_and_clear_bit(unsigned long nr, volatile void *addr) +static inline int test_and_clear_bit(int nr, volatile void *addr) { volatile unsigned long *ptr = addr; unsigned long mask = 1UL << (nr & 31); @@ -120,7 +120,7 @@ static inline int test_and_clear_bit(unsigned long nr, volatile void *addr) return (atomic_test_and_ANDNOT_mask(mask, ptr) & mask) != 0; } -static inline int test_and_set_bit(unsigned long nr, volatile void *addr) +static inline int test_and_set_bit(int nr, volatile void *addr) { volatile unsigned long *ptr = addr; unsigned long mask = 1UL << (nr & 31); @@ -128,7 +128,7 @@ static inline int test_and_set_bit(unsigned long nr, volatile void *addr) return (atomic_test_and_OR_mask(mask, ptr) & mask) != 0; } -static inline int test_and_change_bit(unsigned long nr, volatile void *addr) +static inline int test_and_change_bit(int nr, volatile void *addr) { volatile unsigned long *ptr = addr; unsigned long mask = 1UL << (nr & 31); @@ -136,22 +136,22 @@ static inline int test_and_change_bit(unsigned long nr, volatile void *addr) return (atomic_test_and_XOR_mask(mask, ptr) & mask) != 0; } -static inline void clear_bit(unsigned long nr, volatile void *addr) +static inline void clear_bit(int nr, volatile void *addr) { test_and_clear_bit(nr, addr); } -static inline void set_bit(unsigned long nr, volatile void *addr) +static inline void set_bit(int nr, volatile void *addr) { test_and_set_bit(nr, addr); } -static inline void change_bit(unsigned long nr, volatile void *addr) +static inline void change_bit(int nr, volatile void * addr) { test_and_change_bit(nr, addr); } -static inline void __clear_bit(unsigned long nr, volatile void *addr) +static inline void __clear_bit(int nr, volatile void * addr) { volatile unsigned long *a = addr; int mask; @@ -161,7 +161,7 @@ static inline void __clear_bit(unsigned long nr, volatile void *addr) *a &= ~mask; } -static inline void __set_bit(unsigned long nr, volatile void *addr) +static inline void __set_bit(int nr, volatile void * addr) { volatile unsigned long *a = addr; int mask; @@ -171,7 +171,7 @@ static inline void __set_bit(unsigned long nr, volatile void *addr) *a |= mask; } -static inline void __change_bit(unsigned long nr, volatile void *addr) +static inline void __change_bit(int nr, volatile void *addr) { volatile unsigned long *a = addr; int mask; @@ -181,7 +181,7 @@ static inline void __change_bit(unsigned long nr, volatile void *addr) *a ^= mask; } -static inline int __test_and_clear_bit(unsigned long nr, volatile void *addr) +static inline int __test_and_clear_bit(int nr, volatile void * addr) { volatile unsigned long *a = addr; int mask, retval; @@ -193,7 +193,7 @@ static inline int __test_and_clear_bit(unsigned long nr, volatile void *addr) return retval; } -static inline int __test_and_set_bit(unsigned long nr, volatile void *addr) +static inline int __test_and_set_bit(int nr, volatile void * addr) { volatile unsigned long *a = addr; int mask, retval; @@ -205,7 +205,7 @@ static inline int __test_and_set_bit(unsigned long nr, volatile void *addr) return retval; } -static inline int __test_and_change_bit(unsigned long nr, volatile void *addr) +static inline int __test_and_change_bit(int nr, volatile void * addr) { volatile unsigned long *a = addr; int mask, retval; @@ -220,13 +220,12 @@ static inline int __test_and_change_bit(unsigned long nr, volatile void *addr) /* * This routine doesn't need to be atomic. */ -static inline int -__constant_test_bit(unsigned long nr, const volatile void *addr) +static inline int __constant_test_bit(int nr, const volatile void * addr) { return ((1UL << (nr & 31)) & (((const volatile unsigned int *) addr)[nr >> 5])) != 0; } -static inline int __test_bit(unsigned long nr, const volatile void *addr) +static inline int __test_bit(int nr, const volatile void * addr) { int * a = (int *) addr; int mask; diff --git a/trunk/arch/frv/include/asm/elf.h b/trunk/arch/frv/include/asm/elf.h index 7bbf6e47f8c8..7279ec07d62e 100644 --- a/trunk/arch/frv/include/asm/elf.h +++ b/trunk/arch/frv/include/asm/elf.h @@ -116,7 +116,6 @@ do { \ } while(0) #define USE_ELF_CORE_DUMP -#define CORE_DUMP_USE_REGSET #define ELF_FDPIC_CORE_EFLAGS EF_FRV_FDPIC #define ELF_EXEC_PAGESIZE 16384 diff --git a/trunk/arch/frv/include/asm/pci.h b/trunk/arch/frv/include/asm/pci.h index cc685e60b0f9..585d9b49949a 100644 --- a/trunk/arch/frv/include/asm/pci.h +++ b/trunk/arch/frv/include/asm/pci.h @@ -87,7 +87,8 @@ static inline void pci_dma_sync_single(struct pci_dev *hwdev, dma_addr_t dma_handle, size_t size, int direction) { - BUG_ON(direction == PCI_DMA_NONE); + if (direction == PCI_DMA_NONE) + BUG(); frv_cache_wback_inv((unsigned long)bus_to_virt(dma_handle), (unsigned long)bus_to_virt(dma_handle) + size); @@ -104,7 +105,9 @@ static inline void pci_dma_sync_sg(struct pci_dev *hwdev, int nelems, int direction) { int i; - BUG_ON(direction == PCI_DMA_NONE); + + if (direction == PCI_DMA_NONE) + BUG(); for (i = 0; i < nelems; i++) frv_cache_wback_inv(sg_dma_address(&sg[i]), diff --git a/trunk/arch/frv/include/asm/ptrace.h b/trunk/arch/frv/include/asm/ptrace.h index a54b535c9e49..cf6934012b64 100644 --- a/trunk/arch/frv/include/asm/ptrace.h +++ b/trunk/arch/frv/include/asm/ptrace.h @@ -65,8 +65,6 @@ #ifdef __KERNEL__ #ifndef __ASSEMBLY__ -struct task_struct; - /* * we dedicate GR28 to keeping a pointer to the current exception frame * - gr28 is destroyed on entry to the kernel from userspace @@ -75,18 +73,11 @@ register struct pt_regs *__frame asm("gr28"); #define user_mode(regs) (!((regs)->psr & PSR_S)) #define instruction_pointer(regs) ((regs)->pc) -#define user_stack_pointer(regs) ((regs)->sp) extern unsigned long user_stack(const struct pt_regs *); extern void show_regs(struct pt_regs *); #define profile_pc(regs) ((regs)->pc) - -#define task_pt_regs(task) ((task)->thread.frame0) - -#define arch_has_single_step() (1) -extern void user_enable_single_step(struct task_struct *); -extern void user_disable_single_step(struct task_struct *); +#endif #endif /* !__ASSEMBLY__ */ -#endif /* __KERNEL__ */ #endif /* _ASM_PTRACE_H */ diff --git a/trunk/arch/frv/include/asm/syscall.h b/trunk/arch/frv/include/asm/syscall.h deleted file mode 100644 index 70689eb29b98..000000000000 --- a/trunk/arch/frv/include/asm/syscall.h +++ /dev/null @@ -1,123 +0,0 @@ -/* syscall parameter access functions - * - * Copyright (C) 2009 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. - */ - -#ifndef _ASM_SYSCALL_H -#define _ASM_SYSCALL_H - -#include -#include - -/* - * Get the system call number or -1 - */ -static inline long syscall_get_nr(struct task_struct *task, - struct pt_regs *regs) -{ - return regs->syscallno; -} - -/* - * Restore the clobbered GR8 register - * (1st syscall arg was overwritten with syscall return or error) - */ -static inline void syscall_rollback(struct task_struct *task, - struct pt_regs *regs) -{ - regs->gr8 = regs->orig_gr8; -} - -/* - * See if the syscall return value is an error, returning it if it is and 0 if - * not - */ -static inline long syscall_get_error(struct task_struct *task, - struct pt_regs *regs) -{ - return IS_ERR_VALUE(regs->gr8) ? regs->gr8 : 0; -} - -/* - * Get the syscall return value - */ -static inline long syscall_get_return_value(struct task_struct *task, - struct pt_regs *regs) -{ - return regs->gr8; -} - -/* - * Set the syscall return value - */ -static inline void syscall_set_return_value(struct task_struct *task, - struct pt_regs *regs, - int error, long val) -{ - if (error) - regs->gr8 = -error; - else - regs->gr8 = val; -} - -/* - * Retrieve the system call arguments - */ -static inline void syscall_get_arguments(struct task_struct *task, - struct pt_regs *regs, - unsigned int i, unsigned int n, - unsigned long *args) -{ - /* - * Do this simply for now. If we need to start supporting - * fetching arguments from arbitrary indices, this will need some - * extra logic. Presently there are no in-tree users that depend - * on this behaviour. - */ - BUG_ON(i); - - /* Argument pattern is: GR8, GR9, GR10, GR11, GR12, GR13 */ - switch (n) { - case 6: args[5] = regs->gr13; - case 5: args[4] = regs->gr12; - case 4: args[3] = regs->gr11; - case 3: args[2] = regs->gr10; - case 2: args[1] = regs->gr9; - case 1: args[0] = regs->gr8; - break; - default: - BUG(); - } -} - -/* - * Alter the system call arguments - */ -static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, - unsigned int i, unsigned int n, - const unsigned long *args) -{ - /* Same note as above applies */ - BUG_ON(i); - - switch (n) { - case 6: regs->gr13 = args[5]; - case 5: regs->gr12 = args[4]; - case 4: regs->gr11 = args[3]; - case 3: regs->gr10 = args[2]; - case 2: regs->gr9 = args[1]; - case 1: regs->gr8 = args[0]; - break; - default: - BUG(); - } -} - -#endif /* _ASM_SYSCALL_H */ diff --git a/trunk/arch/frv/include/asm/thread_info.h b/trunk/arch/frv/include/asm/thread_info.h index e8a5ed7be021..bb53ab753ffb 100644 --- a/trunk/arch/frv/include/asm/thread_info.h +++ b/trunk/arch/frv/include/asm/thread_info.h @@ -109,20 +109,20 @@ register struct thread_info *__current_thread_info asm("gr15"); * - other flags in MSW */ #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ -#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ -#define TIF_SIGPENDING 2 /* signal pending */ -#define TIF_NEED_RESCHED 3 /* rescheduling necessary */ -#define TIF_SINGLESTEP 4 /* restore singlestep on return to user mode */ +#define TIF_SIGPENDING 1 /* signal pending */ +#define TIF_NEED_RESCHED 2 /* rescheduling necessary */ +#define TIF_SINGLESTEP 3 /* restore singlestep on return to user mode */ +#define TIF_IRET 4 /* return with iret */ #define TIF_RESTORE_SIGMASK 5 /* restore signal mask in do_signal() */ #define TIF_POLLING_NRFLAG 16 /* true if poll_idle() is polling TIF_NEED_RESCHED */ #define TIF_MEMDIE 17 /* OOM killer killed process */ #define TIF_FREEZE 18 /* freezing for suspend */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) -#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) +#define _TIF_IRET (1 << TIF_IRET) #define _TIF_RESTORE_SIGMASK (1 << TIF_RESTORE_SIGMASK) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_FREEZE (1 << TIF_FREEZE) diff --git a/trunk/arch/frv/kernel/entry.S b/trunk/arch/frv/kernel/entry.S index 356e0e327a89..1da523b3298e 100644 --- a/trunk/arch/frv/kernel/entry.S +++ b/trunk/arch/frv/kernel/entry.S @@ -886,6 +886,7 @@ system_call: bnc icc0,#0,__syscall_badsys ldi @(gr15,#TI_FLAGS),gr4 + ori gr4,#_TIF_SYSCALL_TRACE,gr4 andicc gr4,#_TIF_SYSCALL_TRACE,gr0,icc0 bne icc0,#0,__syscall_trace_entry @@ -1149,10 +1150,11 @@ __entry_work_notifysig: # perform syscall entry tracing __syscall_trace_entry: LEDS 0x6320 - call syscall_trace_entry + setlos.p #0,gr8 + call do_syscall_trace - lddi.p @(gr28,#REG_GR(8)) ,gr8 - ori gr8,#0,gr7 ; syscall_trace_entry() returned new syscallno + ldi @(gr28,#REG_SYSCALLNO),gr7 + lddi @(gr28,#REG_GR(8)) ,gr8 lddi @(gr28,#REG_GR(10)),gr10 lddi.p @(gr28,#REG_GR(12)),gr12 @@ -1167,10 +1169,11 @@ __syscall_exit_work: beq icc0,#1,__entry_work_pending movsg psr,gr23 - andi gr23,#~PSR_PIL,gr23 ; could let syscall_trace_exit() call schedule() + andi gr23,#~PSR_PIL,gr23 ; could let do_syscall_trace() call schedule() movgs gr23,psr - call syscall_trace_exit + setlos.p #1,gr8 + call do_syscall_trace bra __entry_resume_userspace __syscall_badsys: diff --git a/trunk/arch/frv/kernel/ptrace.c b/trunk/arch/frv/kernel/ptrace.c index 60eeed3694c0..5e7d401d21e7 100644 --- a/trunk/arch/frv/kernel/ptrace.c +++ b/trunk/arch/frv/kernel/ptrace.c @@ -19,9 +19,6 @@ #include #include #include -#include -#include -#include #include #include @@ -35,169 +32,6 @@ * in exit.c or in signal.c. */ -/* - * retrieve the contents of FRV userspace general registers - */ -static int genregs_get(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) -{ - const struct user_int_regs *iregs = &target->thread.user->i; - int ret; - - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - iregs, 0, sizeof(*iregs)); - if (ret < 0) - return ret; - - return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, - sizeof(*iregs), -1); -} - -/* - * update the contents of the FRV userspace general registers - */ -static int genregs_set(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - struct user_int_regs *iregs = &target->thread.user->i; - unsigned int offs_gr0, offs_gr1; - int ret; - - /* not allowed to set PSR or __status */ - if (pos < offsetof(struct user_int_regs, psr) + sizeof(long) && - pos + count > offsetof(struct user_int_regs, psr)) - return -EIO; - - if (pos < offsetof(struct user_int_regs, __status) + sizeof(long) && - pos + count > offsetof(struct user_int_regs, __status)) - return -EIO; - - /* set the control regs */ - offs_gr0 = offsetof(struct user_int_regs, gr[0]); - offs_gr1 = offsetof(struct user_int_regs, gr[1]); - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - iregs, 0, offs_gr0); - if (ret < 0) - return ret; - - /* skip GR0/TBR */ - ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, - offs_gr0, offs_gr1); - if (ret < 0) - return ret; - - /* set the general regs */ - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &iregs->gr[1], offs_gr1, sizeof(*iregs)); - if (ret < 0) - return ret; - - return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, - sizeof(*iregs), -1); -} - -/* - * retrieve the contents of FRV userspace FP/Media registers - */ -static int fpmregs_get(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) -{ - const struct user_fpmedia_regs *fpregs = &target->thread.user->f; - int ret; - - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - fpregs, 0, sizeof(*fpregs)); - if (ret < 0) - return ret; - - return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, - sizeof(*fpregs), -1); -} - -/* - * update the contents of the FRV userspace FP/Media registers - */ -static int fpmregs_set(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - struct user_fpmedia_regs *fpregs = &target->thread.user->f; - int ret; - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - fpregs, 0, sizeof(*fpregs)); - if (ret < 0) - return ret; - - return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, - sizeof(*fpregs), -1); -} - -/* - * determine if the FP/Media registers have actually been used - */ -static int fpmregs_active(struct task_struct *target, - const struct user_regset *regset) -{ - return tsk_used_math(target) ? regset->n : 0; -} - -/* - * Define the register sets available on the FRV under Linux - */ -enum frv_regset { - REGSET_GENERAL, - REGSET_FPMEDIA, -}; - -static const struct user_regset frv_regsets[] = { - /* - * General register format is: - * PSR, ISR, CCR, CCCR, LR, LCR, PC, (STATUS), SYSCALLNO, ORIG_G8 - * GNER0-1, IACC0, TBR, GR1-63 - */ - [REGSET_GENERAL] = { - .core_note_type = NT_PRSTATUS, - .n = ELF_NGREG, - .size = sizeof(long), - .align = sizeof(long), - .get = genregs_get, - .set = genregs_set, - }, - /* - * FPU/Media register format is: - * FR0-63, FNER0-1, MSR0-1, ACC0-7, ACCG0-8, FSR - */ - [REGSET_FPMEDIA] = { - .core_note_type = NT_PRFPREG, - .n = sizeof(struct user_fpmedia_regs) / sizeof(long), - .size = sizeof(long), - .align = sizeof(long), - .get = fpmregs_get, - .set = fpmregs_set, - .active = fpmregs_active, - }, -}; - -static const struct user_regset_view user_frv_native_view = { - .name = "frv", - .e_machine = EM_FRV, - .regsets = frv_regsets, - .n = ARRAY_SIZE(frv_regsets), -}; - -const struct user_regset_view *task_user_regset_view(struct task_struct *task) -{ - return &user_frv_native_view; -} - /* * Get contents of register REGNO in task TASK. */ @@ -235,23 +69,40 @@ static inline int put_reg(struct task_struct *task, int regno, } /* - * Called by kernel/ptrace.c when detaching.. - * - * Control h/w single stepping + * check that an address falls within the bounds of the target process's memory + * mappings */ -void user_enable_single_step(struct task_struct *child) +static inline int is_user_addr_valid(struct task_struct *child, + unsigned long start, unsigned long len) { - child->thread.frame0->__status |= REG__STATUS_STEP; +#ifdef CONFIG_MMU + if (start >= PAGE_OFFSET || len > PAGE_OFFSET - start) + return -EIO; + return 0; +#else + struct vm_area_struct *vma; + + vma = find_vma(child->mm, start); + if (vma && start >= vma->vm_start && start + len <= vma->vm_end) + return 0; + + return -EIO; +#endif } -void user_disable_single_step(struct task_struct *child) +/* + * Called by kernel/ptrace.c when detaching.. + * + * Control h/w single stepping + */ +void ptrace_disable(struct task_struct *child) { child->thread.frame0->__status &= ~REG__STATUS_STEP; } -void ptrace_disable(struct task_struct *child) +void ptrace_enable(struct task_struct *child) { - user_disable_single_step(child); + child->thread.frame0->__status |= REG__STATUS_STEP; } long arch_ptrace(struct task_struct *child, long request, long addr, long data) @@ -260,6 +111,15 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) int ret; switch (request) { + /* when I and D space are separate, these will need to be fixed. */ + case PTRACE_PEEKTEXT: /* read word at location addr. */ + case PTRACE_PEEKDATA: + ret = -EIO; + if (is_user_addr_valid(child, addr, sizeof(tmp)) < 0) + break; + ret = generic_ptrace_peekdata(child, addr, data); + break; + /* read the word at location addr in the USER area. */ case PTRACE_PEEKUSR: { tmp = 0; @@ -303,6 +163,15 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) break; } + /* when I and D space are separate, this will have to be fixed. */ + case PTRACE_POKETEXT: /* write the word at location addr. */ + case PTRACE_POKEDATA: + ret = -EIO; + if (is_user_addr_valid(child, addr, sizeof(tmp)) < 0) + break; + ret = generic_ptrace_pokedata(child, addr, data); + break; + case PTRACE_POKEUSR: /* write the word at location addr in the USER area */ ret = -EIO; if ((addr & 3) || addr < 0) @@ -310,7 +179,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) ret = 0; switch (addr >> 2) { - case 0 ... PT__END - 1: + case 0 ... PT__END-1: ret = put_reg(child, addr >> 2, data); break; @@ -320,29 +189,95 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) } break; - case PTRACE_GETREGS: /* Get all integer regs from the child. */ - return copy_regset_to_user(child, &user_frv_native_view, - REGSET_GENERAL, - 0, sizeof(child->thread.user->i), - (void __user *)data); - - case PTRACE_SETREGS: /* Set all integer regs in the child. */ - return copy_regset_from_user(child, &user_frv_native_view, - REGSET_GENERAL, - 0, sizeof(child->thread.user->i), - (const void __user *)data); - - case PTRACE_GETFPREGS: /* Get the child FP/Media state. */ - return copy_regset_to_user(child, &user_frv_native_view, - REGSET_FPMEDIA, - 0, sizeof(child->thread.user->f), - (void __user *)data); - - case PTRACE_SETFPREGS: /* Set the child FP/Media state. */ - return copy_regset_from_user(child, &user_frv_native_view, - REGSET_FPMEDIA, - 0, sizeof(child->thread.user->f), - (const void __user *)data); + case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */ + case PTRACE_CONT: /* restart after signal. */ + ret = -EIO; + if (!valid_signal(data)) + break; + if (request == PTRACE_SYSCALL) + set_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + else + clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + child->exit_code = data; + ptrace_disable(child); + wake_up_process(child); + ret = 0; + break; + + /* make the child exit. Best I can do is send it a sigkill. + * perhaps it should be put in the status that it wants to + * exit. + */ + case PTRACE_KILL: + ret = 0; + if (child->exit_state == EXIT_ZOMBIE) /* already dead */ + break; + child->exit_code = SIGKILL; + clear_tsk_thread_flag(child, TIF_SINGLESTEP); + ptrace_disable(child); + wake_up_process(child); + break; + + case PTRACE_SINGLESTEP: /* set the trap flag. */ + ret = -EIO; + if (!valid_signal(data)) + break; + clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + ptrace_enable(child); + child->exit_code = data; + wake_up_process(child); + ret = 0; + break; + + case PTRACE_DETACH: /* detach a process that was attached. */ + ret = ptrace_detach(child, data); + break; + + case PTRACE_GETREGS: { /* Get all integer regs from the child. */ + int i; + for (i = 0; i < PT__GPEND; i++) { + tmp = get_reg(child, i); + if (put_user(tmp, (unsigned long *) data)) { + ret = -EFAULT; + break; + } + data += sizeof(long); + } + ret = 0; + break; + } + + case PTRACE_SETREGS: { /* Set all integer regs in the child. */ + int i; + for (i = 0; i < PT__GPEND; i++) { + if (get_user(tmp, (unsigned long *) data)) { + ret = -EFAULT; + break; + } + put_reg(child, i, tmp); + data += sizeof(long); + } + ret = 0; + break; + } + + case PTRACE_GETFPREGS: { /* Get the child FP/Media state. */ + ret = 0; + if (copy_to_user((void *) data, + &child->thread.user->f, + sizeof(child->thread.user->f))) + ret = -EFAULT; + break; + } + + case PTRACE_SETFPREGS: { /* Set the child FP/Media state. */ + ret = 0; + if (copy_from_user(&child->thread.user->f, + (void *) data, + sizeof(child->thread.user->f))) + ret = -EFAULT; + break; + } case PTRACE_GETFDPIC: tmp = 0; @@ -365,36 +300,414 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) break; default: - ret = ptrace_request(child, request, addr, data); + ret = -EIO; break; } return ret; } -/* - * handle tracing of system call entry - * - return the revised system call number or ULONG_MAX to cause ENOSYS - */ -asmlinkage unsigned long syscall_trace_entry(void) +int __nongprelbss kstrace; + +static const struct { + const char *name; + unsigned argmask; +} __syscall_name_table[NR_syscalls] = { + [0] = { "restart_syscall" }, + [1] = { "exit", 0x000001 }, + [2] = { "fork", 0xffffff }, + [3] = { "read", 0x000141 }, + [4] = { "write", 0x000141 }, + [5] = { "open", 0x000235 }, + [6] = { "close", 0x000001 }, + [7] = { "waitpid", 0x000141 }, + [8] = { "creat", 0x000025 }, + [9] = { "link", 0x000055 }, + [10] = { "unlink", 0x000005 }, + [11] = { "execve", 0x000445 }, + [12] = { "chdir", 0x000005 }, + [13] = { "time", 0x000004 }, + [14] = { "mknod", 0x000325 }, + [15] = { "chmod", 0x000025 }, + [16] = { "lchown", 0x000025 }, + [17] = { "break" }, + [18] = { "oldstat", 0x000045 }, + [19] = { "lseek", 0x000131 }, + [20] = { "getpid", 0xffffff }, + [21] = { "mount", 0x043555 }, + [22] = { "umount", 0x000005 }, + [23] = { "setuid", 0x000001 }, + [24] = { "getuid", 0xffffff }, + [25] = { "stime", 0x000004 }, + [26] = { "ptrace", 0x004413 }, + [27] = { "alarm", 0x000001 }, + [28] = { "oldfstat", 0x000041 }, + [29] = { "pause", 0xffffff }, + [30] = { "utime", 0x000045 }, + [31] = { "stty" }, + [32] = { "gtty" }, + [33] = { "access", 0x000025 }, + [34] = { "nice", 0x000001 }, + [35] = { "ftime" }, + [36] = { "sync", 0xffffff }, + [37] = { "kill", 0x000011 }, + [38] = { "rename", 0x000055 }, + [39] = { "mkdir", 0x000025 }, + [40] = { "rmdir", 0x000005 }, + [41] = { "dup", 0x000001 }, + [42] = { "pipe", 0x000004 }, + [43] = { "times", 0x000004 }, + [44] = { "prof" }, + [45] = { "brk", 0x000004 }, + [46] = { "setgid", 0x000001 }, + [47] = { "getgid", 0xffffff }, + [48] = { "signal", 0x000041 }, + [49] = { "geteuid", 0xffffff }, + [50] = { "getegid", 0xffffff }, + [51] = { "acct", 0x000005 }, + [52] = { "umount2", 0x000035 }, + [53] = { "lock" }, + [54] = { "ioctl", 0x000331 }, + [55] = { "fcntl", 0x000331 }, + [56] = { "mpx" }, + [57] = { "setpgid", 0x000011 }, + [58] = { "ulimit" }, + [60] = { "umask", 0x000002 }, + [61] = { "chroot", 0x000005 }, + [62] = { "ustat", 0x000043 }, + [63] = { "dup2", 0x000011 }, + [64] = { "getppid", 0xffffff }, + [65] = { "getpgrp", 0xffffff }, + [66] = { "setsid", 0xffffff }, + [67] = { "sigaction" }, + [68] = { "sgetmask" }, + [69] = { "ssetmask" }, + [70] = { "setreuid" }, + [71] = { "setregid" }, + [72] = { "sigsuspend" }, + [73] = { "sigpending" }, + [74] = { "sethostname" }, + [75] = { "setrlimit" }, + [76] = { "getrlimit" }, + [77] = { "getrusage" }, + [78] = { "gettimeofday" }, + [79] = { "settimeofday" }, + [80] = { "getgroups" }, + [81] = { "setgroups" }, + [82] = { "select" }, + [83] = { "symlink" }, + [84] = { "oldlstat" }, + [85] = { "readlink" }, + [86] = { "uselib" }, + [87] = { "swapon" }, + [88] = { "reboot" }, + [89] = { "readdir" }, + [91] = { "munmap", 0x000034 }, + [92] = { "truncate" }, + [93] = { "ftruncate" }, + [94] = { "fchmod" }, + [95] = { "fchown" }, + [96] = { "getpriority" }, + [97] = { "setpriority" }, + [99] = { "statfs" }, + [100] = { "fstatfs" }, + [102] = { "socketcall" }, + [103] = { "syslog" }, + [104] = { "setitimer" }, + [105] = { "getitimer" }, + [106] = { "stat" }, + [107] = { "lstat" }, + [108] = { "fstat" }, + [111] = { "vhangup" }, + [114] = { "wait4" }, + [115] = { "swapoff" }, + [116] = { "sysinfo" }, + [117] = { "ipc" }, + [118] = { "fsync" }, + [119] = { "sigreturn" }, + [120] = { "clone" }, + [121] = { "setdomainname" }, + [122] = { "uname" }, + [123] = { "modify_ldt" }, + [123] = { "cacheflush" }, + [124] = { "adjtimex" }, + [125] = { "mprotect" }, + [126] = { "sigprocmask" }, + [127] = { "create_module" }, + [128] = { "init_module" }, + [129] = { "delete_module" }, + [130] = { "get_kernel_syms" }, + [131] = { "quotactl" }, + [132] = { "getpgid" }, + [133] = { "fchdir" }, + [134] = { "bdflush" }, + [135] = { "sysfs" }, + [136] = { "personality" }, + [137] = { "afs_syscall" }, + [138] = { "setfsuid" }, + [139] = { "setfsgid" }, + [140] = { "_llseek", 0x014331 }, + [141] = { "getdents" }, + [142] = { "_newselect", 0x000141 }, + [143] = { "flock" }, + [144] = { "msync" }, + [145] = { "readv" }, + [146] = { "writev" }, + [147] = { "getsid", 0x000001 }, + [148] = { "fdatasync", 0x000001 }, + [149] = { "_sysctl", 0x000004 }, + [150] = { "mlock" }, + [151] = { "munlock" }, + [152] = { "mlockall" }, + [153] = { "munlockall" }, + [154] = { "sched_setparam" }, + [155] = { "sched_getparam" }, + [156] = { "sched_setscheduler" }, + [157] = { "sched_getscheduler" }, + [158] = { "sched_yield" }, + [159] = { "sched_get_priority_max" }, + [160] = { "sched_get_priority_min" }, + [161] = { "sched_rr_get_interval" }, + [162] = { "nanosleep", 0x000044 }, + [163] = { "mremap" }, + [164] = { "setresuid" }, + [165] = { "getresuid" }, + [166] = { "vm86" }, + [167] = { "query_module" }, + [168] = { "poll" }, + [169] = { "nfsservctl" }, + [170] = { "setresgid" }, + [171] = { "getresgid" }, + [172] = { "prctl", 0x333331 }, + [173] = { "rt_sigreturn", 0xffffff }, + [174] = { "rt_sigaction", 0x001441 }, + [175] = { "rt_sigprocmask", 0x001441 }, + [176] = { "rt_sigpending", 0x000014 }, + [177] = { "rt_sigtimedwait", 0x001444 }, + [178] = { "rt_sigqueueinfo", 0x000411 }, + [179] = { "rt_sigsuspend", 0x000014 }, + [180] = { "pread", 0x003341 }, + [181] = { "pwrite", 0x003341 }, + [182] = { "chown", 0x000115 }, + [183] = { "getcwd" }, + [184] = { "capget" }, + [185] = { "capset" }, + [186] = { "sigaltstack" }, + [187] = { "sendfile" }, + [188] = { "getpmsg" }, + [189] = { "putpmsg" }, + [190] = { "vfork", 0xffffff }, + [191] = { "ugetrlimit" }, + [192] = { "mmap2", 0x313314 }, + [193] = { "truncate64" }, + [194] = { "ftruncate64" }, + [195] = { "stat64", 0x000045 }, + [196] = { "lstat64", 0x000045 }, + [197] = { "fstat64", 0x000041 }, + [198] = { "lchown32" }, + [199] = { "getuid32", 0xffffff }, + [200] = { "getgid32", 0xffffff }, + [201] = { "geteuid32", 0xffffff }, + [202] = { "getegid32", 0xffffff }, + [203] = { "setreuid32" }, + [204] = { "setregid32" }, + [205] = { "getgroups32" }, + [206] = { "setgroups32" }, + [207] = { "fchown32" }, + [208] = { "setresuid32" }, + [209] = { "getresuid32" }, + [210] = { "setresgid32" }, + [211] = { "getresgid32" }, + [212] = { "chown32" }, + [213] = { "setuid32" }, + [214] = { "setgid32" }, + [215] = { "setfsuid32" }, + [216] = { "setfsgid32" }, + [217] = { "pivot_root" }, + [218] = { "mincore" }, + [219] = { "madvise" }, + [220] = { "getdents64" }, + [221] = { "fcntl64" }, + [223] = { "security" }, + [224] = { "gettid" }, + [225] = { "readahead" }, + [226] = { "setxattr" }, + [227] = { "lsetxattr" }, + [228] = { "fsetxattr" }, + [229] = { "getxattr" }, + [230] = { "lgetxattr" }, + [231] = { "fgetxattr" }, + [232] = { "listxattr" }, + [233] = { "llistxattr" }, + [234] = { "flistxattr" }, + [235] = { "removexattr" }, + [236] = { "lremovexattr" }, + [237] = { "fremovexattr" }, + [238] = { "tkill" }, + [239] = { "sendfile64" }, + [240] = { "futex" }, + [241] = { "sched_setaffinity" }, + [242] = { "sched_getaffinity" }, + [243] = { "set_thread_area" }, + [244] = { "get_thread_area" }, + [245] = { "io_setup" }, + [246] = { "io_destroy" }, + [247] = { "io_getevents" }, + [248] = { "io_submit" }, + [249] = { "io_cancel" }, + [250] = { "fadvise64" }, + [252] = { "exit_group", 0x000001 }, + [253] = { "lookup_dcookie" }, + [254] = { "epoll_create" }, + [255] = { "epoll_ctl" }, + [256] = { "epoll_wait" }, + [257] = { "remap_file_pages" }, + [258] = { "set_tid_address" }, + [259] = { "timer_create" }, + [260] = { "timer_settime" }, + [261] = { "timer_gettime" }, + [262] = { "timer_getoverrun" }, + [263] = { "timer_delete" }, + [264] = { "clock_settime" }, + [265] = { "clock_gettime" }, + [266] = { "clock_getres" }, + [267] = { "clock_nanosleep" }, + [268] = { "statfs64" }, + [269] = { "fstatfs64" }, + [270] = { "tgkill" }, + [271] = { "utimes" }, + [272] = { "fadvise64_64" }, + [273] = { "vserver" }, + [274] = { "mbind" }, + [275] = { "get_mempolicy" }, + [276] = { "set_mempolicy" }, + [277] = { "mq_open" }, + [278] = { "mq_unlink" }, + [279] = { "mq_timedsend" }, + [280] = { "mq_timedreceive" }, + [281] = { "mq_notify" }, + [282] = { "mq_getsetattr" }, + [283] = { "sys_kexec_load" }, +}; + +asmlinkage void do_syscall_trace(int leaving) { - __frame->__status |= REG__STATUS_SYSC_ENTRY; - if (tracehook_report_syscall_entry(__frame)) { - /* tracing decided this syscall should not happen, so - * We'll return a bogus call number to get an ENOSYS - * error, but leave the original number in - * __frame->syscallno - */ - return ULONG_MAX; +#if 0 + unsigned long *argp; + const char *name; + unsigned argmask; + char buffer[16]; + + if (!kstrace) + return; + + if (!current->mm) + return; + + if (__frame->gr7 == __NR_close) + return; + +#if 0 + if (__frame->gr7 != __NR_mmap2 && + __frame->gr7 != __NR_vfork && + __frame->gr7 != __NR_execve && + __frame->gr7 != __NR_exit) + return; +#endif + + argmask = 0; + name = NULL; + if (__frame->gr7 < NR_syscalls) { + name = __syscall_name_table[__frame->gr7].name; + argmask = __syscall_name_table[__frame->gr7].argmask; + } + if (!name) { + sprintf(buffer, "sys_%lx", __frame->gr7); + name = buffer; } - return __frame->syscallno; -} + if (!leaving) { + if (!argmask) { + printk(KERN_CRIT "[%d] %s(%lx,%lx,%lx,%lx,%lx,%lx)\n", + current->pid, + name, + __frame->gr8, + __frame->gr9, + __frame->gr10, + __frame->gr11, + __frame->gr12, + __frame->gr13); + } + else if (argmask == 0xffffff) { + printk(KERN_CRIT "[%d] %s()\n", + current->pid, + name); + } + else { + printk(KERN_CRIT "[%d] %s(", + current->pid, + name); + + argp = &__frame->gr8; + + do { + switch (argmask & 0xf) { + case 1: + printk("%ld", (long) *argp); + break; + case 2: + printk("%lo", *argp); + break; + case 3: + printk("%lx", *argp); + break; + case 4: + printk("%p", (void *) *argp); + break; + case 5: + printk("\"%s\"", (char *) *argp); + break; + } + + argp++; + argmask >>= 4; + if (argmask) + printk(","); + + } while (argmask); + + printk(")\n"); + } + } + else { + if ((int)__frame->gr8 > -4096 && (int)__frame->gr8 < 4096) + printk(KERN_CRIT "[%d] %s() = %ld\n", current->pid, name, __frame->gr8); + else + printk(KERN_CRIT "[%d] %s() = %lx\n", current->pid, name, __frame->gr8); + } + return; +#endif -/* - * handle tracing of system call exit - */ -asmlinkage void syscall_trace_exit(void) -{ - __frame->__status |= REG__STATUS_SYSC_EXIT; - tracehook_report_syscall_exit(__frame, 0); + if (!test_thread_flag(TIF_SYSCALL_TRACE)) + return; + + if (!(current->ptrace & PT_PTRACED)) + return; + + /* we need to indicate entry or exit to strace */ + if (leaving) + __frame->__status |= REG__STATUS_SYSC_EXIT; + else + __frame->__status |= REG__STATUS_SYSC_ENTRY; + + ptrace_notify(SIGTRAP); + + /* + * this isn't the same as continuing with a signal, but it will do + * for normal use. strace only continues with a signal if the + * stopping signal is not SIGTRAP. -brl + */ + if (current->exit_code) { + send_sig(current->exit_code, current, 1); + current->exit_code = 0; + } } diff --git a/trunk/arch/frv/kernel/signal.c b/trunk/arch/frv/kernel/signal.c index 4a7a62c6e783..3bdb368292a8 100644 --- a/trunk/arch/frv/kernel/signal.c +++ b/trunk/arch/frv/kernel/signal.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include #include @@ -517,9 +516,6 @@ static void do_signal(void) * clear the TIF_RESTORE_SIGMASK flag */ if (test_thread_flag(TIF_RESTORE_SIGMASK)) clear_thread_flag(TIF_RESTORE_SIGMASK); - - tracehook_signal_handler(signr, &info, &ka, __frame, - test_thread_flag(TIF_SINGLESTEP)); } return; @@ -568,10 +564,4 @@ asmlinkage void do_notify_resume(__u32 thread_info_flags) if (thread_info_flags & (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK)) do_signal(); - /* deal with notification on about to resume userspace execution */ - if (thread_info_flags & _TIF_NOTIFY_RESUME) { - clear_thread_flag(TIF_NOTIFY_RESUME); - tracehook_notify_resume(__frame); - } - } /* end do_notify_resume() */ diff --git a/trunk/arch/frv/kernel/uaccess.c b/trunk/arch/frv/kernel/uaccess.c index 374f88d6cc00..9fb771a20df3 100644 --- a/trunk/arch/frv/kernel/uaccess.c +++ b/trunk/arch/frv/kernel/uaccess.c @@ -23,7 +23,8 @@ long strncpy_from_user(char *dst, const char __user *src, long count) char *p, ch; long err = -EFAULT; - BUG_ON(count < 0); + if (count < 0) + BUG(); p = dst; @@ -75,7 +76,8 @@ long strnlen_user(const char __user *src, long count) long err = 0; char ch; - BUG_ON(count < 0); + if (count < 0) + BUG(); #ifndef CONFIG_MMU if ((unsigned long) src < memory_start) diff --git a/trunk/arch/frv/mb93090-mb00/pci-dma-nommu.c b/trunk/arch/frv/mb93090-mb00/pci-dma-nommu.c index 4e1ba0b15443..52ff9aec799d 100644 --- a/trunk/arch/frv/mb93090-mb00/pci-dma-nommu.c +++ b/trunk/arch/frv/mb93090-mb00/pci-dma-nommu.c @@ -116,7 +116,8 @@ EXPORT_SYMBOL(dma_free_coherent); dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size, enum dma_data_direction direction) { - BUG_ON(direction == DMA_NONE); + if (direction == DMA_NONE) + BUG(); frv_cache_wback_inv((unsigned long) ptr, (unsigned long) ptr + size); @@ -150,7 +151,8 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, frv_cache_wback_inv(sg_dma_address(&sg[i]), sg_dma_address(&sg[i]) + sg_dma_len(&sg[i])); - BUG_ON(direction == DMA_NONE); + if (direction == DMA_NONE) + BUG(); return nents; } diff --git a/trunk/arch/frv/mb93090-mb00/pci-dma.c b/trunk/arch/frv/mb93090-mb00/pci-dma.c index 45954f0813dc..3ddedebc4eb3 100644 --- a/trunk/arch/frv/mb93090-mb00/pci-dma.c +++ b/trunk/arch/frv/mb93090-mb00/pci-dma.c @@ -48,7 +48,8 @@ EXPORT_SYMBOL(dma_free_coherent); dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size, enum dma_data_direction direction) { - BUG_ON(direction == DMA_NONE); + if (direction == DMA_NONE) + BUG(); frv_cache_wback_inv((unsigned long) ptr, (unsigned long) ptr + size); @@ -80,7 +81,8 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, void *vaddr; int i; - BUG_ON(direction == DMA_NONE); + if (direction == DMA_NONE) + BUG(); dampr2 = __get_DAMPR(2); diff --git a/trunk/arch/ia64/hp/sim/hpsim_irq.c b/trunk/arch/ia64/hp/sim/hpsim_irq.c index acb5047ab573..cc0a3182db3c 100644 --- a/trunk/arch/ia64/hp/sim/hpsim_irq.c +++ b/trunk/arch/ia64/hp/sim/hpsim_irq.c @@ -21,10 +21,9 @@ hpsim_irq_noop (unsigned int irq) { } -static int +static void hpsim_set_affinity_noop(unsigned int a, const struct cpumask *b) { - return 0; } static struct hw_interrupt_type irq_type_hp_sim = { diff --git a/trunk/arch/ia64/include/asm/kvm_host.h b/trunk/arch/ia64/include/asm/kvm_host.h index 5f43697aed30..4542651e6acb 100644 --- a/trunk/arch/ia64/include/asm/kvm_host.h +++ b/trunk/arch/ia64/include/asm/kvm_host.h @@ -371,7 +371,6 @@ struct kvm_vcpu_arch { int last_run_cpu; int vmm_tr_slot; int vm_tr_slot; - int sn_rtc_tr_slot; #define KVM_MP_STATE_RUNNABLE 0 #define KVM_MP_STATE_UNINITIALIZED 1 @@ -466,7 +465,6 @@ struct kvm_arch { unsigned long vmm_init_rr; int online_vcpus; - int is_sn2; struct kvm_ioapic *vioapic; struct kvm_vm_stat stat; @@ -474,7 +472,6 @@ struct kvm_arch { struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; - int iommu_flags; struct hlist_head irq_ack_notifier_list; unsigned long irq_sources_bitmap; @@ -581,8 +578,6 @@ struct kvm_vmm_info{ kvm_vmm_entry *vmm_entry; kvm_tramp_entry *tramp_entry; unsigned long vmm_ivt; - unsigned long patch_mov_ar; - unsigned long patch_mov_ar_sn2; }; int kvm_highest_pending_irq(struct kvm_vcpu *vcpu); @@ -590,6 +585,7 @@ 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); +static inline void kvm_inject_nmi(struct kvm_vcpu *vcpu) {} #endif /* __ASSEMBLY__*/ #endif diff --git a/trunk/arch/ia64/include/asm/pgtable.h b/trunk/arch/ia64/include/asm/pgtable.h index 0a9cc73d35c7..7a9bff47564f 100644 --- a/trunk/arch/ia64/include/asm/pgtable.h +++ b/trunk/arch/ia64/include/asm/pgtable.h @@ -146,8 +146,6 @@ #define PAGE_GATE __pgprot(__ACCESS_BITS | _PAGE_PL_0 | _PAGE_AR_X_RX) #define PAGE_KERNEL __pgprot(__DIRTY_BITS | _PAGE_PL_0 | _PAGE_AR_RWX) #define PAGE_KERNELRX __pgprot(__ACCESS_BITS | _PAGE_PL_0 | _PAGE_AR_RX) -#define PAGE_KERNEL_UC __pgprot(__DIRTY_BITS | _PAGE_PL_0 | _PAGE_AR_RWX | \ - _PAGE_MA_UC) # ifndef __ASSEMBLY__ diff --git a/trunk/arch/ia64/kernel/acpi.c b/trunk/arch/ia64/kernel/acpi.c index baec6f00f7f3..5510317db37b 100644 --- a/trunk/arch/ia64/kernel/acpi.c +++ b/trunk/arch/ia64/kernel/acpi.c @@ -636,7 +636,7 @@ void __init acpi_numa_arch_fixup(void) * success: return IRQ number (>=0) * failure: return < 0 */ -int acpi_register_gsi(struct device *dev, u32 gsi, int triggering, int polarity) +int acpi_register_gsi(u32 gsi, int triggering, int polarity) { if (acpi_irq_model == ACPI_IRQ_MODEL_PLATFORM) return gsi; @@ -678,8 +678,7 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table) fadt = (struct acpi_table_fadt *)fadt_header; - acpi_register_gsi(NULL, fadt->sci_interrupt, ACPI_LEVEL_SENSITIVE, - ACPI_ACTIVE_LOW); + acpi_register_gsi(fadt->sci_interrupt, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW); return 0; } diff --git a/trunk/arch/ia64/kernel/iosapic.c b/trunk/arch/ia64/kernel/iosapic.c index f92cef47bf86..166e0d839fa0 100644 --- a/trunk/arch/ia64/kernel/iosapic.c +++ b/trunk/arch/ia64/kernel/iosapic.c @@ -329,7 +329,7 @@ unmask_irq (unsigned int irq) } -static int +static void iosapic_set_affinity(unsigned int irq, const struct cpumask *mask) { #ifdef CONFIG_SMP @@ -343,15 +343,15 @@ iosapic_set_affinity(unsigned int irq, const struct cpumask *mask) cpu = cpumask_first_and(cpu_online_mask, mask); if (cpu >= nr_cpu_ids) - return -1; + return; if (irq_prepare_move(irq, cpu)) - return -1; + return; dest = cpu_physical_id(cpu); if (!iosapic_intr_info[irq].count) - return -1; /* not an IOSAPIC interrupt */ + return; /* not an IOSAPIC interrupt */ set_irq_affinity_info(irq, dest, redir); @@ -376,9 +376,7 @@ iosapic_set_affinity(unsigned int irq, const struct cpumask *mask) iosapic_write(iosapic, IOSAPIC_RTE_HIGH(rte_index), high32); iosapic_write(iosapic, IOSAPIC_RTE_LOW(rte_index), low32); } - #endif - return 0; } /* diff --git a/trunk/arch/ia64/kernel/irq_ia64.c b/trunk/arch/ia64/kernel/irq_ia64.c index b448197728be..acc4d19ae62a 100644 --- a/trunk/arch/ia64/kernel/irq_ia64.c +++ b/trunk/arch/ia64/kernel/irq_ia64.c @@ -610,9 +610,6 @@ static struct irqaction ipi_irqaction = { .name = "IPI" }; -/* - * KVM uses this interrupt to force a cpu out of guest mode - */ static struct irqaction resched_irqaction = { .handler = dummy_handler, .flags = IRQF_DISABLED, diff --git a/trunk/arch/ia64/kernel/msi_ia64.c b/trunk/arch/ia64/kernel/msi_ia64.c index 0f8ade9331ba..2b15e233f7fe 100644 --- a/trunk/arch/ia64/kernel/msi_ia64.c +++ b/trunk/arch/ia64/kernel/msi_ia64.c @@ -12,7 +12,7 @@ static struct irq_chip ia64_msi_chip; #ifdef CONFIG_SMP -static int ia64_set_msi_irq_affinity(unsigned int irq, +static void ia64_set_msi_irq_affinity(unsigned int irq, const cpumask_t *cpu_mask) { struct msi_msg msg; @@ -20,10 +20,10 @@ static int ia64_set_msi_irq_affinity(unsigned int irq, int cpu = first_cpu(*cpu_mask); if (!cpu_online(cpu)) - return -1; + return; if (irq_prepare_move(irq, cpu)) - return -1; + return; read_msi_msg(irq, &msg); @@ -39,8 +39,6 @@ static int ia64_set_msi_irq_affinity(unsigned int irq, write_msi_msg(irq, &msg); cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu)); - - return 0; } #endif /* CONFIG_SMP */ @@ -132,17 +130,17 @@ void arch_teardown_msi_irq(unsigned int irq) #ifdef CONFIG_DMAR #ifdef CONFIG_SMP -static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask) +static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask) { struct irq_cfg *cfg = irq_cfg + irq; struct msi_msg msg; int cpu = cpumask_first(mask); if (!cpu_online(cpu)) - return -1; + return; if (irq_prepare_move(irq, cpu)) - return -1; + return; dmar_msi_read(irq, &msg); @@ -153,8 +151,6 @@ static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask) dmar_msi_write(irq, &msg); cpumask_copy(irq_desc[irq].affinity, mask); - - return 0; } #endif /* CONFIG_SMP */ diff --git a/trunk/arch/ia64/kvm/Kconfig b/trunk/arch/ia64/kvm/Kconfig index 64d520937874..0a2d6b86075a 100644 --- a/trunk/arch/ia64/kvm/Kconfig +++ b/trunk/arch/ia64/kvm/Kconfig @@ -23,7 +23,7 @@ if VIRTUALIZATION config KVM tristate "Kernel-based Virtual Machine (KVM) support" - depends on HAVE_KVM && MODULES && EXPERIMENTAL + depends on HAVE_KVM && EXPERIMENTAL # for device assignment: depends on PCI select PREEMPT_NOTIFIERS diff --git a/trunk/arch/ia64/kvm/kvm-ia64.c b/trunk/arch/ia64/kvm/kvm-ia64.c index 80c57b0a21c4..d20a5db4c4dd 100644 --- a/trunk/arch/ia64/kvm/kvm-ia64.c +++ b/trunk/arch/ia64/kvm/kvm-ia64.c @@ -41,9 +41,6 @@ #include #include #include -#include -#include -#include #include "misc.h" #include "vti.h" @@ -68,16 +65,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; -static unsigned long kvm_get_itc(struct kvm_vcpu *vcpu) -{ -#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC) - if (vcpu->kvm->arch.is_sn2) - return rtc_time(); - else -#endif - return ia64_getreg(_IA64_REG_AR_ITC); -} - static void kvm_flush_icache(unsigned long start, unsigned long len) { int l; @@ -132,7 +119,8 @@ void kvm_arch_hardware_enable(void *garbage) unsigned long saved_psr; int slot; - pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base), PAGE_KERNEL)); + 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); local_irq_restore(saved_psr); @@ -295,18 +283,6 @@ static int handle_sal_call(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } -static int __apic_accept_irq(struct kvm_vcpu *vcpu, uint64_t vector) -{ - struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd); - - if (!test_and_set_bit(vector, &vpd->irr[0])) { - vcpu->arch.irq_new_pending = 1; - kvm_vcpu_kick(vcpu); - return 1; - } - return 0; -} - /* * offset: address offset to IPI space. * value: deliver value. @@ -316,20 +292,20 @@ static void vcpu_deliver_ipi(struct kvm_vcpu *vcpu, uint64_t dm, { switch (dm) { case SAPIC_FIXED: + kvm_apic_set_irq(vcpu, vector, 0); break; case SAPIC_NMI: - vector = 2; + kvm_apic_set_irq(vcpu, 2, 0); break; case SAPIC_EXTINT: - vector = 0; + kvm_apic_set_irq(vcpu, 0, 0); break; case SAPIC_INIT: case SAPIC_PMI: default: printk(KERN_ERR"kvm: Unimplemented Deliver reserved IPI!\n"); - return; + break; } - __apic_accept_irq(vcpu, vector); } static struct kvm_vcpu *lid_to_vcpu(struct kvm *kvm, unsigned long id, @@ -437,23 +413,6 @@ static int handle_switch_rr6(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int kvm_sn2_setup_mappings(struct kvm_vcpu *vcpu) -{ - unsigned long pte, rtc_phys_addr, map_addr; - int slot; - - map_addr = KVM_VMM_BASE + (1UL << KVM_VMM_SHIFT); - rtc_phys_addr = LOCAL_MMR_OFFSET | SH_RTC; - pte = pte_val(mk_pte_phys(rtc_phys_addr, PAGE_KERNEL_UC)); - slot = ia64_itr_entry(0x3, map_addr, pte, PAGE_SHIFT); - vcpu->arch.sn_rtc_tr_slot = slot; - if (slot < 0) { - printk(KERN_ERR "Mayday mayday! RTC mapping failed!\n"); - slot = 0; - } - return slot; -} - int kvm_emulate_halt(struct kvm_vcpu *vcpu) { @@ -467,7 +426,7 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) if (irqchip_in_kernel(vcpu->kvm)) { - vcpu_now_itc = kvm_get_itc(vcpu) + vcpu->arch.itc_offset; + 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; @@ -488,10 +447,10 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) hrtimer_cancel(p_ht); vcpu->arch.ht_active = 0; - if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests) || - kvm_cpu_has_pending_timer(vcpu)) + if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests)) if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) - vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; + vcpu->arch.mp_state = + KVM_MP_STATE_RUNNABLE; if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE) return -EINTR; @@ -592,35 +551,22 @@ static int kvm_insert_vmm_mapping(struct kvm_vcpu *vcpu) if (r < 0) goto out; vcpu->arch.vm_tr_slot = r; - -#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC) - if (kvm->arch.is_sn2) { - r = kvm_sn2_setup_mappings(vcpu); - if (r < 0) - goto out; - } -#endif - r = 0; out: return r; + } static void kvm_purge_vmm_mapping(struct kvm_vcpu *vcpu) { - struct kvm *kvm = vcpu->kvm; + ia64_ptr_entry(0x3, vcpu->arch.vmm_tr_slot); ia64_ptr_entry(0x3, vcpu->arch.vm_tr_slot); -#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC) - if (kvm->arch.is_sn2) - ia64_ptr_entry(0x3, vcpu->arch.sn_rtc_tr_slot); -#endif + } static int kvm_vcpu_pre_transition(struct kvm_vcpu *vcpu) { - unsigned long psr; - int r; int cpu = smp_processor_id(); if (vcpu->arch.last_run_cpu != cpu || @@ -632,27 +578,36 @@ static int kvm_vcpu_pre_transition(struct kvm_vcpu *vcpu) vcpu->arch.host_rr6 = ia64_get_rr(RR6); vti_set_rr6(vcpu->arch.vmm_rr); - local_irq_save(psr); - r = kvm_insert_vmm_mapping(vcpu); - local_irq_restore(psr); - return r; + 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 __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int vti_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { union context *host_ctx, *guest_ctx; int r; - /* - * down_read() may sleep and return with interrupts enabled - */ - down_read(&vcpu->kvm->slots_lock); + /*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: if (signal_pending(current)) { @@ -661,31 +616,26 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } + /* + * down_read() may sleep and return with interrupts enabled + */ + down_read(&vcpu->kvm->slots_lock); + preempt_disable(); local_irq_disable(); - /*Get host and guest context with guest address space.*/ - host_ctx = kvm_get_host_context(vcpu); - guest_ctx = kvm_get_guest_context(vcpu); - - clear_bit(KVM_REQ_KICK, &vcpu->requests); - - r = kvm_vcpu_pre_transition(vcpu); - if (r < 0) - goto vcpu_run_fail; - - up_read(&vcpu->kvm->slots_lock); + vcpu->guest_mode = 1; kvm_guest_enter(); - - /* - * Transition to the guest - */ - kvm_vmm_info->tramp_entry(host_ctx, guest_ctx); - - kvm_vcpu_post_transition(vcpu); + 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; - set_bit(KVM_REQ_KICK, &vcpu->requests); + vcpu->guest_mode = 0; local_irq_enable(); /* @@ -696,10 +646,9 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) */ barrier(); kvm_guest_exit(); + up_read(&vcpu->kvm->slots_lock); preempt_enable(); - down_read(&vcpu->kvm->slots_lock); - r = kvm_handle_exit(kvm_run, vcpu); if (r > 0) { @@ -708,20 +657,12 @@ 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 again; } return r; - -vcpu_run_fail: - local_irq_enable(); - preempt_enable(); - kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; - goto out; } static void kvm_set_mmio_data(struct kvm_vcpu *vcpu) @@ -847,9 +788,6 @@ struct kvm *kvm_arch_create_vm(void) if (IS_ERR(kvm)) return ERR_PTR(-ENOMEM); - - kvm->arch.is_sn2 = ia64_platform_is("sn2"); - kvm_init_vm(kvm); kvm->arch.online_vcpus = 0; @@ -946,7 +884,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) RESTORE_REGS(saved_gp); vcpu->arch.irq_new_pending = 1; - vcpu->arch.itc_offset = regs->saved_itc - kvm_get_itc(vcpu); + vcpu->arch.itc_offset = regs->saved_itc - ia64_getreg(_IA64_REG_AR_ITC); set_bit(KVM_REQ_RESUME, &vcpu->requests); vcpu_put(vcpu); @@ -1105,6 +1043,10 @@ static void kvm_free_vmm_area(void) } } +static void vti_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ +} + static int vti_init_vpd(struct kvm_vcpu *vcpu) { int i; @@ -1223,7 +1165,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) regs->cr_iip = PALE_RESET_ENTRY; /*Initialize itc offset for vcpus*/ - itc_offset = 0UL - kvm_get_itc(vcpu); + itc_offset = 0UL - ia64_getreg(_IA64_REG_AR_ITC); for (i = 0; i < kvm->arch.online_vcpus; i++) { v = (struct kvm_vcpu *)((char *)vcpu + sizeof(struct kvm_vcpu_data) * i); @@ -1295,7 +1237,6 @@ static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id) local_irq_save(psr); r = kvm_insert_vmm_mapping(vcpu); - local_irq_restore(psr); if (r) goto fail; r = kvm_vcpu_init(vcpu, vcpu->kvm, id); @@ -1313,11 +1254,13 @@ static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id) goto uninit; kvm_purge_vmm_mapping(vcpu); + local_irq_restore(psr); return 0; uninit: kvm_vcpu_uninit(vcpu); fail: + local_irq_restore(psr); return r; } @@ -1348,6 +1291,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->kvm = kvm; cpu = get_cpu(); + vti_vcpu_load(vcpu, cpu); r = vti_vcpu_setup(vcpu, id); put_cpu(); @@ -1483,7 +1427,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) } for (i = 0; i < 4; i++) regs->insvc[i] = vcpu->arch.insvc[i]; - regs->saved_itc = vcpu->arch.itc_offset + kvm_get_itc(vcpu); + regs->saved_itc = vcpu->arch.itc_offset + ia64_getreg(_IA64_REG_AR_ITC); SAVE_REGS(xtp); SAVE_REGS(metaphysical_rr0); SAVE_REGS(metaphysical_rr4); @@ -1630,7 +1574,6 @@ int kvm_arch_set_memory_region(struct kvm *kvm, void kvm_arch_flush_shadow(struct kvm *kvm) { - kvm_flush_remote_tlbs(kvm); } long kvm_arch_dev_ioctl(struct file *filp, @@ -1673,37 +1616,8 @@ static int vti_cpu_has_kvm_support(void) return 0; } - -/* - * On SN2, the ITC isn't stable, so copy in fast path code to use the - * SN2 RTC, replacing the ITC based default verion. - */ -static void kvm_patch_vmm(struct kvm_vmm_info *vmm_info, - struct module *module) -{ - unsigned long new_ar, new_ar_sn2; - unsigned long module_base; - - if (!ia64_platform_is("sn2")) - return; - - module_base = (unsigned long)module->module_core; - - new_ar = kvm_vmm_base + vmm_info->patch_mov_ar - module_base; - new_ar_sn2 = kvm_vmm_base + vmm_info->patch_mov_ar_sn2 - module_base; - - printk(KERN_INFO "kvm: Patching ITC emulation to use SGI SN2 RTC " - "as source\n"); - - /* - * Copy the SN2 version of mov_ar into place. They are both - * the same size, so 6 bundles is sufficient (6 * 0x10). - */ - memcpy((void *)new_ar, (void *)new_ar_sn2, 0x60); -} - static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info, - struct module *module) + struct module *module) { unsigned long module_base; unsigned long vmm_size; @@ -1725,7 +1639,6 @@ static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info, return -EFAULT; memcpy((void *)kvm_vmm_base, (void *)module_base, vmm_size); - kvm_patch_vmm(vmm_info, module); kvm_flush_icache(kvm_vmm_base, vmm_size); /*Recalculate kvm_vmm_info based on new VMM*/ @@ -1879,24 +1792,38 @@ 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 me; - int cpu = vcpu->cpu; + int ipi_pcpu = vcpu->cpu; + int cpu = get_cpu(); if (waitqueue_active(&vcpu->wq)) wake_up_interruptible(&vcpu->wq); - me = get_cpu(); - if (cpu != me && (unsigned) cpu < nr_cpu_ids && cpu_online(cpu)) - if (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests)) - smp_send_reschedule(cpu); + if (vcpu->guest_mode && cpu != ipi_pcpu) + smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0); put_cpu(); } -int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq) +int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig) { - return __apic_accept_irq(vcpu, irq->vector); + + 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; + kvm_vcpu_kick(vcpu); + return 1; + } + return 0; } int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest) @@ -1909,18 +1836,20 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda) return 0; } -int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) +struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector, + unsigned long bitmap) { - return vcpu1->arch.xtp - vcpu2->arch.xtp; -} + struct kvm_vcpu *lvcpu = kvm->vcpus[0]; + int i; -int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, - int short_hand, int dest, int dest_mode) -{ - struct kvm_lapic *target = vcpu->arch.apic; - return (dest_mode == 0) ? - kvm_apic_match_physical_addr(target, dest) : - kvm_apic_match_logical_addr(target, dest); + for (i = 1; i < kvm->arch.online_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) @@ -1959,12 +1888,6 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) return 0; } -int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) -{ - /* do real check here */ - return 1; -} - int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { return vcpu->arch.timer_fired; @@ -1995,7 +1918,6 @@ static int vcpu_reset(struct kvm_vcpu *vcpu) long psr; local_irq_save(psr); r = kvm_insert_vmm_mapping(vcpu); - local_irq_restore(psr); if (r) goto fail; @@ -2008,6 +1930,7 @@ static int vcpu_reset(struct kvm_vcpu *vcpu) kvm_purge_vmm_mapping(vcpu); r = 0; fail: + local_irq_restore(psr); return r; } diff --git a/trunk/arch/ia64/kvm/kvm_fw.c b/trunk/arch/ia64/kvm/kvm_fw.c index e4b82319881d..a8ae52ed5635 100644 --- a/trunk/arch/ia64/kvm/kvm_fw.c +++ b/trunk/arch/ia64/kvm/kvm_fw.c @@ -21,9 +21,6 @@ #include #include -#include -#include -#include #include "vti.h" #include "misc.h" @@ -191,35 +188,12 @@ static struct ia64_pal_retval pal_freq_base(struct kvm_vcpu *vcpu) return result; } -/* - * On the SGI SN2, the ITC isn't stable. Emulation backed by the SN2 - * RTC is used instead. This function patches the ratios from SAL - * to match the RTC before providing them to the guest. - */ -static void sn2_patch_itc_freq_ratios(struct ia64_pal_retval *result) -{ - struct pal_freq_ratio *ratio; - unsigned long sal_freq, sal_drift, factor; - - result->status = ia64_sal_freq_base(SAL_FREQ_BASE_PLATFORM, - &sal_freq, &sal_drift); - ratio = (struct pal_freq_ratio *)&result->v2; - factor = ((sal_freq * 3) + (sn_rtc_cycles_per_second / 2)) / - sn_rtc_cycles_per_second; - - ratio->num = 3; - ratio->den = factor; -} - 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); - - if (vcpu->kvm->arch.is_sn2) - sn2_patch_itc_freq_ratios(&result); - return result; } diff --git a/trunk/arch/ia64/kvm/lapic.h b/trunk/arch/ia64/kvm/lapic.h index ee541cebcd78..6d6cbcb14893 100644 --- a/trunk/arch/ia64/kvm/lapic.h +++ b/trunk/arch/ia64/kvm/lapic.h @@ -20,10 +20,6 @@ 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_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, - int short_hand, int dest, int dest_mode); -int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); -int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq); -#define kvm_apic_present(x) (true) +int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig); #endif diff --git a/trunk/arch/ia64/kvm/optvfault.S b/trunk/arch/ia64/kvm/optvfault.S index f793be3effff..32254ce9a1bd 100644 --- a/trunk/arch/ia64/kvm/optvfault.S +++ b/trunk/arch/ia64/kvm/optvfault.S @@ -11,7 +11,6 @@ #include #include -#include #include "vti.h" #include "asm-offsets.h" @@ -141,35 +140,6 @@ GLOBAL_ENTRY(kvm_asm_mov_from_ar) ;; END(kvm_asm_mov_from_ar) -/* - * Special SGI SN2 optimized version of mov_from_ar using the SN2 RTC - * clock as it's source for emulating the ITC. This version will be - * copied on top of the original version if the host is determined to - * be an SN2. - */ -GLOBAL_ENTRY(kvm_asm_mov_from_ar_sn2) - add r18=VMM_VCPU_ITC_OFS_OFFSET, r21 - movl r19 = (KVM_VMM_BASE+(1<cpl == 0) { /* Allow hypercalls only when cpl = 0. */ if (iim == DOMN_PAL_REQUEST) { - local_irq_save(psr); set_pal_call_data(v); vmm_transition(v); get_pal_call_result(v); vcpu_increment_iip(v); - local_irq_restore(psr); return; } else if (iim == DOMN_SAL_REQUEST) { - local_irq_save(psr); set_sal_call_data(v); vmm_transition(v); get_sal_call_result(v); vcpu_increment_iip(v); - local_irq_restore(psr); return; } } diff --git a/trunk/arch/ia64/kvm/vcpu.c b/trunk/arch/ia64/kvm/vcpu.c index a2c6c15e4761..a18ee17b9192 100644 --- a/trunk/arch/ia64/kvm/vcpu.c +++ b/trunk/arch/ia64/kvm/vcpu.c @@ -788,29 +788,13 @@ void vcpu_set_fpreg(struct kvm_vcpu *vcpu, unsigned long reg, setfpreg(reg, val, regs); /* FIXME: handle NATs later*/ } -/* - * The Altix RTC is mapped specially here for the vmm module - */ -#define SN_RTC_BASE (u64 *)(KVM_VMM_BASE+(1UL<arch.is_sn2) - return (*SN_RTC_BASE); - else -#endif - return ia64_getreg(_IA64_REG_AR_ITC); -} - /************************************************************************ * lsapic timer ***********************************************************************/ u64 vcpu_get_itc(struct kvm_vcpu *vcpu) { unsigned long guest_itc; - guest_itc = VMX(vcpu, itc_offset) + kvm_get_itc(vcpu); + 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; @@ -825,7 +809,7 @@ static void vcpu_set_itc(struct kvm_vcpu *vcpu, u64 val) struct kvm_vcpu *v; struct kvm *kvm; int i; - long itc_offset = val - kvm_get_itc(vcpu); + long itc_offset = val - ia64_getreg(_IA64_REG_AR_ITC); unsigned long vitv = VCPU(vcpu, itv); kvm = (struct kvm *)KVM_VM_BASE; diff --git a/trunk/arch/ia64/kvm/vmm.c b/trunk/arch/ia64/kvm/vmm.c index f4b4c899bb6c..9eee5c04bacc 100644 --- a/trunk/arch/ia64/kvm/vmm.c +++ b/trunk/arch/ia64/kvm/vmm.c @@ -30,19 +30,15 @@ MODULE_AUTHOR("Intel"); MODULE_LICENSE("GPL"); extern char kvm_ia64_ivt; -extern char kvm_asm_mov_from_ar; -extern char kvm_asm_mov_from_ar_sn2; extern fpswa_interface_t *vmm_fpswa_interface; long vmm_sanity = 1; struct kvm_vmm_info vmm_info = { - .module = THIS_MODULE, - .vmm_entry = vmm_entry, - .tramp_entry = vmm_trampoline, - .vmm_ivt = (unsigned long)&kvm_ia64_ivt, - .patch_mov_ar = (unsigned long)&kvm_asm_mov_from_ar, - .patch_mov_ar_sn2 = (unsigned long)&kvm_asm_mov_from_ar_sn2, + .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) diff --git a/trunk/arch/ia64/kvm/vmm_ivt.S b/trunk/arch/ia64/kvm/vmm_ivt.S index 40920c630649..3ef1a017a318 100644 --- a/trunk/arch/ia64/kvm/vmm_ivt.S +++ b/trunk/arch/ia64/kvm/vmm_ivt.S @@ -95,7 +95,7 @@ GLOBAL_ENTRY(kvm_vmm_panic) ;; srlz.i // guarantee that interruption collection is on ;; - (p15) ssm psr.i // restore psr. + //(p15) ssm psr.i // restore psr.i addl r14=@gprel(ia64_leave_hypervisor),gp ;; KVM_SAVE_REST @@ -249,7 +249,7 @@ ENTRY(kvm_break_fault) ;; srlz.i // guarantee that interruption collection is on ;; - (p15)ssm psr.i // restore psr.i + //(p15)ssm psr.i // restore psr.i addl r14=@gprel(ia64_leave_hypervisor),gp ;; KVM_SAVE_REST @@ -439,7 +439,7 @@ kvm_dispatch_vexirq: ;; srlz.i // guarantee that interruption collection is on ;; - (p15) ssm psr.i // restore psr.i + //(p15) ssm psr.i // restore psr.i adds r3=8,r2 // set up second base pointer ;; KVM_SAVE_REST @@ -819,7 +819,7 @@ ENTRY(kvm_dtlb_miss_dispatch) ;; srlz.i // guarantee that interruption collection is on ;; - (p15) ssm psr.i // restore psr.i + //(p15) ssm psr.i // restore psr.i addl r14=@gprel(ia64_leave_hypervisor_prepare),gp ;; KVM_SAVE_REST @@ -842,7 +842,7 @@ ENTRY(kvm_itlb_miss_dispatch) ;; srlz.i // guarantee that interruption collection is on ;; - (p15) ssm psr.i // restore psr.i + //(p15) ssm psr.i // restore psr.i addl r14=@gprel(ia64_leave_hypervisor),gp ;; KVM_SAVE_REST @@ -871,7 +871,7 @@ ENTRY(kvm_dispatch_reflection) ;; srlz.i // guarantee that interruption collection is on ;; - (p15) ssm psr.i // restore psr.i + //(p15) ssm psr.i // restore psr.i addl r14=@gprel(ia64_leave_hypervisor),gp ;; KVM_SAVE_REST @@ -898,7 +898,7 @@ ENTRY(kvm_dispatch_virtualization_fault) ;; srlz.i // guarantee that interruption collection is on ;; - (p15) ssm psr.i // restore psr.i + //(p15) ssm psr.i // restore psr.i addl r14=@gprel(ia64_leave_hypervisor_prepare),gp ;; KVM_SAVE_REST @@ -920,7 +920,7 @@ ENTRY(kvm_dispatch_interrupt) ;; srlz.i ;; - (p15) ssm psr.i + //(p15) ssm psr.i addl r14=@gprel(ia64_leave_hypervisor),gp ;; KVM_SAVE_REST @@ -1333,7 +1333,7 @@ hostret = r24 ;; (p7) srlz.i ;; -(p6) ssm psr.i +//(p6) ssm psr.i ;; mov rp=rpsave mov ar.pfs=pfssave diff --git a/trunk/arch/ia64/kvm/vtlb.c b/trunk/arch/ia64/kvm/vtlb.c index 4290a429bf7c..2c2501f13159 100644 --- a/trunk/arch/ia64/kvm/vtlb.c +++ b/trunk/arch/ia64/kvm/vtlb.c @@ -254,8 +254,7 @@ u64 guest_vhpt_lookup(u64 iha, u64 *pte) "(p7) st8 [%2]=r9;;" "ssm psr.ic;;" "srlz.d;;" - "ssm psr.i;;" - "srlz.d;;" + /* "ssm psr.i;;" Once interrupts in vmm open, need fix*/ : "=r"(ret) : "r"(iha), "r"(pte):"memory"); return ret; diff --git a/trunk/arch/ia64/sn/kernel/irq.c b/trunk/arch/ia64/sn/kernel/irq.c index 764f26abac05..66fd705e82c0 100644 --- a/trunk/arch/ia64/sn/kernel/irq.c +++ b/trunk/arch/ia64/sn/kernel/irq.c @@ -227,7 +227,7 @@ struct sn_irq_info *sn_retarget_vector(struct sn_irq_info *sn_irq_info, return new_irq_info; } -static int sn_set_affinity_irq(unsigned int irq, const struct cpumask *mask) +static void sn_set_affinity_irq(unsigned int irq, const struct cpumask *mask) { struct sn_irq_info *sn_irq_info, *sn_irq_info_safe; nasid_t nasid; @@ -239,8 +239,6 @@ static int sn_set_affinity_irq(unsigned int irq, const struct cpumask *mask) list_for_each_entry_safe(sn_irq_info, sn_irq_info_safe, sn_irq_lh[irq], list) (void)sn_retarget_vector(sn_irq_info, nasid, slice); - - return 0; } #ifdef CONFIG_SMP diff --git a/trunk/arch/ia64/sn/kernel/msi_sn.c b/trunk/arch/ia64/sn/kernel/msi_sn.c index fbbfb9701201..81e428943d73 100644 --- a/trunk/arch/ia64/sn/kernel/msi_sn.c +++ b/trunk/arch/ia64/sn/kernel/msi_sn.c @@ -151,7 +151,7 @@ int sn_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *entry) } #ifdef CONFIG_SMP -static int sn_set_msi_irq_affinity(unsigned int irq, +static void sn_set_msi_irq_affinity(unsigned int irq, const struct cpumask *cpu_mask) { struct msi_msg msg; @@ -168,7 +168,7 @@ static int sn_set_msi_irq_affinity(unsigned int irq, cpu = cpumask_first(cpu_mask); sn_irq_info = sn_msi_info[irq].sn_irq_info; if (sn_irq_info == NULL || sn_irq_info->irq_int_bit >= 0) - return -1; + return; /* * Release XIO resources for the old MSI PCI address @@ -189,7 +189,7 @@ static int sn_set_msi_irq_affinity(unsigned int irq, new_irq_info = sn_retarget_vector(sn_irq_info, nasid, slice); sn_msi_info[irq].sn_irq_info = new_irq_info; if (new_irq_info == NULL) - return -1; + return; /* * Map the xio address into bus space @@ -206,8 +206,6 @@ static int sn_set_msi_irq_affinity(unsigned int irq, write_msi_msg(irq, &msg); cpumask_copy(irq_desc[irq].affinity, cpu_mask); - - return 0; } #endif /* CONFIG_SMP */ diff --git a/trunk/arch/mips/cavium-octeon/octeon-irq.c b/trunk/arch/mips/cavium-octeon/octeon-irq.c index d3a0c8154bec..1c19af8daa62 100644 --- a/trunk/arch/mips/cavium-octeon/octeon-irq.c +++ b/trunk/arch/mips/cavium-octeon/octeon-irq.c @@ -177,7 +177,7 @@ static void octeon_irq_ciu0_disable(unsigned int irq) } #ifdef CONFIG_SMP -static int octeon_irq_ciu0_set_affinity(unsigned int irq, const struct cpumask *dest) +static void octeon_irq_ciu0_set_affinity(unsigned int irq, const struct cpumask *dest) { int cpu; int bit = irq - OCTEON_IRQ_WORKQ0; /* Bit 0-63 of EN0 */ @@ -199,8 +199,6 @@ static int octeon_irq_ciu0_set_affinity(unsigned int irq, const struct cpumask * */ cvmx_read_csr(CVMX_CIU_INTX_EN0(cvmx_get_core_num() * 2)); write_unlock(&octeon_irq_ciu0_rwlock); - - return 0; } #endif @@ -294,7 +292,7 @@ static void octeon_irq_ciu1_disable(unsigned int irq) } #ifdef CONFIG_SMP -static int octeon_irq_ciu1_set_affinity(unsigned int irq, const struct cpumask *dest) +static void octeon_irq_ciu1_set_affinity(unsigned int irq, const struct cpumask *dest) { int cpu; int bit = irq - OCTEON_IRQ_WDOG0; /* Bit 0-63 of EN1 */ @@ -317,8 +315,6 @@ static int octeon_irq_ciu1_set_affinity(unsigned int irq, const struct cpumask * */ cvmx_read_csr(CVMX_CIU_INTX_EN1(cvmx_get_core_num() * 2 + 1)); write_unlock(&octeon_irq_ciu1_rwlock); - - return 0; } #endif diff --git a/trunk/arch/mips/include/asm/irq.h b/trunk/arch/mips/include/asm/irq.h index 4f1eed107b08..3214ade02d10 100644 --- a/trunk/arch/mips/include/asm/irq.h +++ b/trunk/arch/mips/include/asm/irq.h @@ -49,7 +49,7 @@ static inline void smtc_im_ack_irq(unsigned int irq) #ifdef CONFIG_MIPS_MT_SMTC_IRQAFF #include -extern int plat_set_irq_affinity(unsigned int irq, +extern void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity); extern void smtc_forward_irq(unsigned int irq); diff --git a/trunk/arch/mips/kernel/irq-gic.c b/trunk/arch/mips/kernel/irq-gic.c index 3f43c2e3aa5a..87deb8f6c458 100644 --- a/trunk/arch/mips/kernel/irq-gic.c +++ b/trunk/arch/mips/kernel/irq-gic.c @@ -155,7 +155,7 @@ static void gic_unmask_irq(unsigned int irq) static DEFINE_SPINLOCK(gic_lock); -static int gic_set_affinity(unsigned int irq, const struct cpumask *cpumask) +static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask) { cpumask_t tmp = CPU_MASK_NONE; unsigned long flags; @@ -166,7 +166,7 @@ static int gic_set_affinity(unsigned int irq, const struct cpumask *cpumask) cpumask_and(&tmp, cpumask, cpu_online_mask); if (cpus_empty(tmp)) - return -1; + return; /* Assumption : cpumask refers to a single CPU */ spin_lock_irqsave(&gic_lock, flags); @@ -190,7 +190,6 @@ static int gic_set_affinity(unsigned int irq, const struct cpumask *cpumask) cpumask_copy(irq_desc[irq].affinity, cpumask); spin_unlock_irqrestore(&gic_lock, flags); - return 0; } #endif diff --git a/trunk/arch/mips/mti-malta/malta-smtc.c b/trunk/arch/mips/mti-malta/malta-smtc.c index 499ffe5475df..5ba31888fefb 100644 --- a/trunk/arch/mips/mti-malta/malta-smtc.c +++ b/trunk/arch/mips/mti-malta/malta-smtc.c @@ -114,7 +114,7 @@ struct plat_smp_ops msmtc_smp_ops = { */ -int plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) +void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) { cpumask_t tmask; int cpu = 0; @@ -156,7 +156,5 @@ int plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) /* Do any generic SMTC IRQ affinity setup */ smtc_set_irq_affinity(irq, tmask); - - return 0; } #endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */ diff --git a/trunk/arch/mips/sibyte/bcm1480/irq.c b/trunk/arch/mips/sibyte/bcm1480/irq.c index 690de06bde90..c147c4b35d3f 100644 --- a/trunk/arch/mips/sibyte/bcm1480/irq.c +++ b/trunk/arch/mips/sibyte/bcm1480/irq.c @@ -50,7 +50,7 @@ static void enable_bcm1480_irq(unsigned int irq); static void disable_bcm1480_irq(unsigned int irq); static void ack_bcm1480_irq(unsigned int irq); #ifdef CONFIG_SMP -static int bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask); +static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask); #endif #ifdef CONFIG_PCI @@ -109,7 +109,7 @@ void bcm1480_unmask_irq(int cpu, int irq) } #ifdef CONFIG_SMP -static int bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask) +static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask) { int i = 0, old_cpu, cpu, int_on, k; u64 cur_ints; @@ -118,7 +118,7 @@ static int bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask) if (cpumask_weight(mask) != 1) { printk("attempted to set irq affinity for irq %d to multiple CPUs\n", irq); - return -1; + return; } i = cpumask_first(mask); @@ -152,8 +152,6 @@ static int bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask) } } spin_unlock_irqrestore(&bcm1480_imr_lock, flags); - - return 0; } #endif diff --git a/trunk/arch/mips/sibyte/sb1250/irq.c b/trunk/arch/mips/sibyte/sb1250/irq.c index 409dec798863..38cb998ade22 100644 --- a/trunk/arch/mips/sibyte/sb1250/irq.c +++ b/trunk/arch/mips/sibyte/sb1250/irq.c @@ -50,7 +50,7 @@ static void enable_sb1250_irq(unsigned int irq); static void disable_sb1250_irq(unsigned int irq); static void ack_sb1250_irq(unsigned int irq); #ifdef CONFIG_SMP -static int sb1250_set_affinity(unsigned int irq, const struct cpumask *mask); +static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask); #endif #ifdef CONFIG_SIBYTE_HAS_LDT @@ -103,7 +103,7 @@ void sb1250_unmask_irq(int cpu, int irq) } #ifdef CONFIG_SMP -static int sb1250_set_affinity(unsigned int irq, const struct cpumask *mask) +static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask) { int i = 0, old_cpu, cpu, int_on; u64 cur_ints; @@ -113,7 +113,7 @@ static int sb1250_set_affinity(unsigned int irq, const struct cpumask *mask) if (cpumask_weight(mask) > 1) { printk("attempted to set irq affinity for irq %d to multiple CPUs\n", irq); - return -1; + return; } /* Convert logical CPU to physical CPU */ @@ -143,8 +143,6 @@ static int sb1250_set_affinity(unsigned int irq, const struct cpumask *mask) R_IMR_INTERRUPT_MASK)); } spin_unlock_irqrestore(&sb1250_imr_lock, flags); - - return 0; } #endif diff --git a/trunk/arch/mn10300/Kconfig b/trunk/arch/mn10300/Kconfig index 89faacad5d17..355926730e8d 100644 --- a/trunk/arch/mn10300/Kconfig +++ b/trunk/arch/mn10300/Kconfig @@ -8,7 +8,6 @@ mainmenu "Linux Kernel Configuration" config MN10300 def_bool y select HAVE_OPROFILE - select HAVE_ARCH_TRACEHOOK config AM33 def_bool y diff --git a/trunk/arch/mn10300/include/asm/elf.h b/trunk/arch/mn10300/include/asm/elf.h index 49105462e6fc..bf09f8bb392e 100644 --- a/trunk/arch/mn10300/include/asm/elf.h +++ b/trunk/arch/mn10300/include/asm/elf.h @@ -34,7 +34,7 @@ */ typedef unsigned long elf_greg_t; -#define ELF_NGREG ((sizeof(struct pt_regs) / sizeof(elf_greg_t)) - 1) +#define ELF_NGREG (sizeof (struct pt_regs) / sizeof(elf_greg_t)) typedef elf_greg_t elf_gregset_t[ELF_NGREG]; #define ELF_NFPREG 32 @@ -76,7 +76,6 @@ do { \ } while (0) #define USE_ELF_CORE_DUMP -#define CORE_DUMP_USE_REGSET #define ELF_EXEC_PAGESIZE 4096 /* diff --git a/trunk/arch/mn10300/include/asm/processor.h b/trunk/arch/mn10300/include/asm/processor.h index f7d4b0d285e8..73239271873d 100644 --- a/trunk/arch/mn10300/include/asm/processor.h +++ b/trunk/arch/mn10300/include/asm/processor.h @@ -143,7 +143,13 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); unsigned long get_wchan(struct task_struct *p); -#define task_pt_regs(task) ((task)->thread.uregs) +#define task_pt_regs(task) \ +({ \ + struct pt_regs *__regs__; \ + __regs__ = (struct pt_regs *) (KSTK_TOP(task_stack_page(task)) - 8); \ + __regs__ - 1; \ +}) + #define KSTK_EIP(task) (task_pt_regs(task)->pc) #define KSTK_ESP(task) (task_pt_regs(task)->sp) diff --git a/trunk/arch/mn10300/include/asm/ptrace.h b/trunk/arch/mn10300/include/asm/ptrace.h index 921942ed1b03..7b06cc623d8b 100644 --- a/trunk/arch/mn10300/include/asm/ptrace.h +++ b/trunk/arch/mn10300/include/asm/ptrace.h @@ -91,17 +91,9 @@ extern struct pt_regs *__frame; /* current frame pointer */ #if defined(__KERNEL__) #if !defined(__ASSEMBLY__) -struct task_struct; - #define user_mode(regs) (((regs)->epsw & EPSW_nSL) == EPSW_nSL) #define instruction_pointer(regs) ((regs)->pc) -#define user_stack_pointer(regs) ((regs)->sp) extern void show_regs(struct pt_regs *); - -#define arch_has_single_step() (1) -extern void user_enable_single_step(struct task_struct *); -extern void user_disable_single_step(struct task_struct *); - #endif /* !__ASSEMBLY */ #define profile_pc(regs) ((regs)->pc) diff --git a/trunk/arch/mn10300/kernel/entry.S b/trunk/arch/mn10300/kernel/entry.S index 7408a27199f3..3dc3e462f92a 100644 --- a/trunk/arch/mn10300/kernel/entry.S +++ b/trunk/arch/mn10300/kernel/entry.S @@ -76,7 +76,7 @@ ENTRY(system_call) cmp nr_syscalls,d0 bcc syscall_badsys btst _TIF_SYSCALL_TRACE,(TI_flags,a2) - bne syscall_entry_trace + bne syscall_trace_entry syscall_call: add d0,d0,a1 add a1,a1 @@ -104,10 +104,11 @@ restore_all: syscall_exit_work: btst _TIF_SYSCALL_TRACE,d2 beq work_pending - __sti # could let syscall_trace_exit() call + __sti # could let do_syscall_trace() call # schedule() instead mov fp,d0 - call syscall_trace_exit[],0 # do_syscall_trace(regs) + mov 1,d1 + call do_syscall_trace[],0 # do_syscall_trace(regs,entryexit) jmp resume_userspace ALIGN @@ -137,11 +138,13 @@ work_notifysig: jmp resume_userspace # perform syscall entry tracing -syscall_entry_trace: +syscall_trace_entry: mov -ENOSYS,d0 mov d0,(REG_D0,fp) mov fp,d0 - call syscall_trace_entry[],0 # returns the syscall number to actually use + clr d1 + call do_syscall_trace[],0 + mov (REG_ORIG_D0,fp),d0 mov (REG_D1,fp),d1 cmp nr_syscalls,d0 bcs syscall_call diff --git a/trunk/arch/mn10300/kernel/ptrace.c b/trunk/arch/mn10300/kernel/ptrace.c index e143339ad28e..d6d6cdc75c52 100644 --- a/trunk/arch/mn10300/kernel/ptrace.c +++ b/trunk/arch/mn10300/kernel/ptrace.c @@ -17,9 +17,6 @@ #include #include #include -#include -#include -#include #include #include #include @@ -67,6 +64,12 @@ static inline int get_stack_long(struct task_struct *task, int offset) ((unsigned long) task->thread.uregs + offset); } +/* + * this routine will put a word on the processes privileged stack. + * the offset is how far from the base addr as stored in the TSS. + * this routine assumes that all the privileged stacks are in our + * data space. + */ static inline int put_stack_long(struct task_struct *task, int offset, unsigned long data) { @@ -77,233 +80,94 @@ int put_stack_long(struct task_struct *task, int offset, unsigned long data) return 0; } -/* - * retrieve the contents of MN10300 userspace general registers - */ -static int genregs_get(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) +static inline unsigned long get_fpregs(struct fpu_state_struct *buf, + struct task_struct *tsk) { - const struct pt_regs *regs = task_pt_regs(target); - int ret; - - /* we need to skip regs->next */ - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - regs, 0, PT_ORIG_D0 * sizeof(long)); - if (ret < 0) - return ret; - - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - ®s->orig_d0, PT_ORIG_D0 * sizeof(long), - NR_PTREGS * sizeof(long)); - if (ret < 0) - return ret; - - return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, - NR_PTREGS * sizeof(long), -1); + return __copy_to_user(buf, &tsk->thread.fpu_state, + sizeof(struct fpu_state_struct)); } -/* - * update the contents of the MN10300 userspace general registers - */ -static int genregs_set(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) +static inline unsigned long set_fpregs(struct task_struct *tsk, + struct fpu_state_struct *buf) { - struct pt_regs *regs = task_pt_regs(target); - unsigned long tmp; - int ret; - - /* we need to skip regs->next */ - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - regs, 0, PT_ORIG_D0 * sizeof(long)); - if (ret < 0) - return ret; - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - ®s->orig_d0, PT_ORIG_D0 * sizeof(long), - PT_EPSW * sizeof(long)); - if (ret < 0) - return ret; - - /* we need to mask off changes to EPSW */ - tmp = regs->epsw; - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &tmp, PT_EPSW * sizeof(long), - PT_PC * sizeof(long)); - tmp &= EPSW_FLAG_V | EPSW_FLAG_C | EPSW_FLAG_N | EPSW_FLAG_Z; - tmp |= regs->epsw & ~(EPSW_FLAG_V | EPSW_FLAG_C | EPSW_FLAG_N | - EPSW_FLAG_Z); - regs->epsw = tmp; - - if (ret < 0) - return ret; - - /* and finally load the PC */ - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - ®s->pc, PT_PC * sizeof(long), - NR_PTREGS * sizeof(long)); - - if (ret < 0) - return ret; - - return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, - NR_PTREGS * sizeof(long), -1); + return __copy_from_user(&tsk->thread.fpu_state, buf, + sizeof(struct fpu_state_struct)); } -/* - * retrieve the contents of MN10300 userspace FPU registers - */ -static int fpuregs_get(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) +static inline void fpsave_init(struct task_struct *task) { - const struct fpu_state_struct *fpregs = &target->thread.fpu_state; - int ret; - - unlazy_fpu(target); - - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - fpregs, 0, sizeof(*fpregs)); - if (ret < 0) - return ret; - - return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, - sizeof(*fpregs), -1); + memset(&task->thread.fpu_state, 0, sizeof(struct fpu_state_struct)); } /* - * update the contents of the MN10300 userspace FPU registers + * make sure the single step bit is not set */ -static int fpuregs_set(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - struct fpu_state_struct fpu_state = target->thread.fpu_state; - int ret; - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &fpu_state, 0, sizeof(fpu_state)); - if (ret < 0) - return ret; - - fpu_kill_state(target); - target->thread.fpu_state = fpu_state; - set_using_fpu(target); - - return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, - sizeof(fpu_state), -1); -} - -/* - * determine if the FPU registers have actually been used - */ -static int fpuregs_active(struct task_struct *target, - const struct user_regset *regset) -{ - return is_using_fpu(target) ? regset->n : 0; -} - -/* - * Define the register sets available on the MN10300 under Linux - */ -enum mn10300_regset { - REGSET_GENERAL, - REGSET_FPU, -}; - -static const struct user_regset mn10300_regsets[] = { - /* - * General register format is: - * A3, A2, D3, D2, MCVF, MCRL, MCRH, MDRQ - * E1, E0, E7...E2, SP, LAR, LIR, MDR - * A1, A0, D1, D0, ORIG_D0, EPSW, PC - */ - [REGSET_GENERAL] = { - .core_note_type = NT_PRSTATUS, - .n = ELF_NGREG, - .size = sizeof(long), - .align = sizeof(long), - .get = genregs_get, - .set = genregs_set, - }, - /* - * FPU register format is: - * FS0-31, FPCR - */ - [REGSET_FPU] = { - .core_note_type = NT_PRFPREG, - .n = sizeof(struct fpu_state_struct) / sizeof(long), - .size = sizeof(long), - .align = sizeof(long), - .get = fpuregs_get, - .set = fpuregs_set, - .active = fpuregs_active, - }, -}; - -static const struct user_regset_view user_mn10300_native_view = { - .name = "mn10300", - .e_machine = EM_MN10300, - .regsets = mn10300_regsets, - .n = ARRAY_SIZE(mn10300_regsets), -}; - -const struct user_regset_view *task_user_regset_view(struct task_struct *task) -{ - return &user_mn10300_native_view; -} - -/* - * set the single-step bit - */ -void user_enable_single_step(struct task_struct *child) +void ptrace_disable(struct task_struct *child) { #ifndef CONFIG_MN10300_USING_JTAG struct user *dummy = NULL; long tmp; tmp = get_stack_long(child, (unsigned long) &dummy->regs.epsw); - tmp |= EPSW_T; + tmp &= ~EPSW_T; put_stack_long(child, (unsigned long) &dummy->regs.epsw, tmp); #endif } /* - * make sure the single-step bit is not set + * set the single step bit */ -void user_disable_single_step(struct task_struct *child) +void ptrace_enable(struct task_struct *child) { #ifndef CONFIG_MN10300_USING_JTAG struct user *dummy = NULL; long tmp; tmp = get_stack_long(child, (unsigned long) &dummy->regs.epsw); - tmp &= ~EPSW_T; + tmp |= EPSW_T; put_stack_long(child, (unsigned long) &dummy->regs.epsw, tmp); #endif } -void ptrace_disable(struct task_struct *child) -{ - user_disable_single_step(child); -} - /* * handle the arch-specific side of process tracing */ long arch_ptrace(struct task_struct *child, long request, long addr, long data) { - unsigned long tmp; - int ret; + struct fpu_state_struct fpu_state; + int i, ret; switch (request) { + /* read the word at location addr. */ + case PTRACE_PEEKTEXT: { + unsigned long tmp; + int copied; + + copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0); + ret = -EIO; + if (copied != sizeof(tmp)) + break; + ret = put_user(tmp, (unsigned long *) data); + break; + } + + /* read the word at location addr. */ + case PTRACE_PEEKDATA: { + unsigned long tmp; + int copied; + + copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0); + ret = -EIO; + if (copied != sizeof(tmp)) + break; + ret = put_user(tmp, (unsigned long *) data); + break; + } + /* read the word at location addr in the USER area. */ - case PTRACE_PEEKUSR: + case PTRACE_PEEKUSR: { + unsigned long tmp; + ret = -EIO; if ((addr & 3) || addr < 0 || addr > sizeof(struct user) - 3) @@ -315,6 +179,17 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) ptrace_regid_to_frame[addr]); ret = put_user(tmp, (unsigned long *) data); break; + } + + /* write the word at location addr. */ + case PTRACE_POKETEXT: + case PTRACE_POKEDATA: + if (access_process_vm(child, addr, &data, sizeof(data), 1) == + sizeof(data)) + ret = 0; + else + ret = -EIO; + break; /* write the word at location addr in the USER area */ case PTRACE_POKEUSR: @@ -329,32 +204,132 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) data); break; - case PTRACE_GETREGS: /* Get all integer regs from the child. */ - return copy_regset_to_user(child, &user_mn10300_native_view, - REGSET_GENERAL, - 0, NR_PTREGS * sizeof(long), - (void __user *)data); - - case PTRACE_SETREGS: /* Set all integer regs in the child. */ - return copy_regset_from_user(child, &user_mn10300_native_view, - REGSET_GENERAL, - 0, NR_PTREGS * sizeof(long), - (const void __user *)data); - - case PTRACE_GETFPREGS: /* Get the child FPU state. */ - return copy_regset_to_user(child, &user_mn10300_native_view, - REGSET_FPU, - 0, sizeof(struct fpu_state_struct), - (void __user *)data); - - case PTRACE_SETFPREGS: /* Set the child FPU state. */ - return copy_regset_from_user(child, &user_mn10300_native_view, - REGSET_FPU, - 0, sizeof(struct fpu_state_struct), - (const void __user *)data); + /* continue and stop at next (return from) syscall */ + case PTRACE_SYSCALL: + /* restart after signal. */ + case PTRACE_CONT: + ret = -EIO; + if ((unsigned long) data > _NSIG) + break; + if (request == PTRACE_SYSCALL) + set_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + else + clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + child->exit_code = data; + ptrace_disable(child); + wake_up_process(child); + ret = 0; + break; + + /* + * make the child exit + * - the best I can do is send it a sigkill + * - perhaps it should be put in the status that it wants to + * exit + */ + case PTRACE_KILL: + ret = 0; + if (child->exit_state == EXIT_ZOMBIE) /* already dead */ + break; + child->exit_code = SIGKILL; + clear_tsk_thread_flag(child, TIF_SINGLESTEP); + ptrace_disable(child); + wake_up_process(child); + break; + + case PTRACE_SINGLESTEP: /* set the trap flag. */ +#ifndef CONFIG_MN10300_USING_JTAG + ret = -EIO; + if ((unsigned long) data > _NSIG) + break; + clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + ptrace_enable(child); + child->exit_code = data; + wake_up_process(child); + ret = 0; +#else + ret = -EINVAL; +#endif + break; + + case PTRACE_DETACH: /* detach a process that was attached. */ + ret = ptrace_detach(child, data); + break; + + /* Get all gp regs from the child. */ + case PTRACE_GETREGS: { + unsigned long tmp; + + if (!access_ok(VERIFY_WRITE, (unsigned *) data, NR_PTREGS << 2)) { + ret = -EIO; + break; + } + + for (i = 0; i < NR_PTREGS << 2; i += 4) { + tmp = get_stack_long(child, ptrace_regid_to_frame[i]); + __put_user(tmp, (unsigned long *) data); + data += sizeof(tmp); + } + ret = 0; + break; + } + + case PTRACE_SETREGS: { /* Set all gp regs in the child. */ + unsigned long tmp; + + if (!access_ok(VERIFY_READ, (unsigned long *)data, + sizeof(struct pt_regs))) { + ret = -EIO; + break; + } + + for (i = 0; i < NR_PTREGS << 2; i += 4) { + __get_user(tmp, (unsigned long *) data); + put_stack_long(child, ptrace_regid_to_frame[i], tmp); + data += sizeof(tmp); + } + ret = 0; + break; + } + + case PTRACE_GETFPREGS: { /* Get the child FPU state. */ + if (is_using_fpu(child)) { + unlazy_fpu(child); + fpu_state = child->thread.fpu_state; + } else { + memset(&fpu_state, 0, sizeof(fpu_state)); + } + + ret = -EIO; + if (copy_to_user((void *) data, &fpu_state, + sizeof(fpu_state)) == 0) + ret = 0; + break; + } + + case PTRACE_SETFPREGS: { /* Set the child FPU state. */ + ret = -EFAULT; + if (copy_from_user(&fpu_state, (const void *) data, + sizeof(fpu_state)) == 0) { + fpu_kill_state(child); + child->thread.fpu_state = fpu_state; + set_using_fpu(child); + ret = 0; + } + break; + } + + case PTRACE_SETOPTIONS: { + if (data & PTRACE_O_TRACESYSGOOD) + child->ptrace |= PT_TRACESYSGOOD; + else + child->ptrace &= ~PT_TRACESYSGOOD; + ret = 0; + break; + } default: - ret = ptrace_request(child, request, addr, data); + ret = -EIO; break; } @@ -362,26 +337,43 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) } /* - * handle tracing of system call entry - * - return the revised system call number or ULONG_MAX to cause ENOSYS + * notification of system call entry/exit + * - triggered by current->work.syscall_trace */ -asmlinkage unsigned long syscall_trace_entry(struct pt_regs *regs) +asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit) { - if (tracehook_report_syscall_entry(regs)) - /* tracing decided this syscall should not happen, so - * We'll return a bogus call number to get an ENOSYS - * error, but leave the original number in - * regs->orig_d0 - */ - return ULONG_MAX; +#if 0 + /* just in case... */ + printk(KERN_DEBUG "[%d] syscall_%lu(%lx,%lx,%lx,%lx) = %lx\n", + current->pid, + regs->orig_d0, + regs->a0, + regs->d1, + regs->a3, + regs->a2, + regs->d0); + return; +#endif - return regs->orig_d0; -} + if (!test_thread_flag(TIF_SYSCALL_TRACE) && + !test_thread_flag(TIF_SINGLESTEP)) + return; + if (!(current->ptrace & PT_PTRACED)) + return; -/* - * handle tracing of system call exit - */ -asmlinkage void syscall_trace_exit(struct pt_regs *regs) -{ - tracehook_report_syscall_exit(regs, 0); + /* the 0x80 provides a way for the tracing parent to distinguish + between a syscall stop and SIGTRAP delivery */ + ptrace_notify(SIGTRAP | + ((current->ptrace & PT_TRACESYSGOOD) && + !test_thread_flag(TIF_SINGLESTEP) ? 0x80 : 0)); + + /* + * this isn't the same as continuing with a signal, but it will do + * for normal use. strace only continues with a signal if the + * stopping signal is not SIGTRAP. -brl + */ + if (current->exit_code) { + send_sig(current->exit_code, current, 1); + current->exit_code = 0; + } } diff --git a/trunk/arch/mn10300/kernel/signal.c b/trunk/arch/mn10300/kernel/signal.c index 9f7572a0f578..841ca9955a18 100644 --- a/trunk/arch/mn10300/kernel/signal.c +++ b/trunk/arch/mn10300/kernel/signal.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include @@ -512,9 +511,6 @@ static void do_signal(struct pt_regs *regs) * clear the TIF_RESTORE_SIGMASK flag */ if (test_thread_flag(TIF_RESTORE_SIGMASK)) clear_thread_flag(TIF_RESTORE_SIGMASK); - - tracehook_signal_handler(signr, &info, &ka, regs, - test_thread_flag(TIF_SINGLESTEP)); } return; @@ -565,9 +561,4 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags) /* deal with pending signal delivery */ if (thread_info_flags & (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK)) do_signal(regs); - - if (thread_info_flags & _TIF_NOTIFY_RESUME) { - clear_thread_flag(TIF_NOTIFY_RESUME); - tracehook_notify_resume(__frame); - } } diff --git a/trunk/arch/mn10300/mm/tlb-mn10300.S b/trunk/arch/mn10300/mm/tlb-mn10300.S index 7095147dcb8b..789208094e98 100644 --- a/trunk/arch/mn10300/mm/tlb-mn10300.S +++ b/trunk/arch/mn10300/mm/tlb-mn10300.S @@ -165,6 +165,24 @@ ENTRY(itlb_aerror) ENTRY(dtlb_aerror) and ~EPSW_NMID,epsw add -4,sp + mov d1,(sp) + + movhu (MMUFCR_DFC),d1 # is it the initial valid write + # to this page? + and MMUFCR_xFC_INITWR,d1 + beq dtlb_pagefault # jump if not + + mov (DPTEL),d1 # set the dirty bit + # (don't replace with BSET!) + or _PAGE_DIRTY,d1 + mov d1,(DPTEL) + mov (sp),d1 + add 4,sp + rti + + ALIGN +dtlb_pagefault: + mov (sp),d1 SAVE_ALL add -4,sp # need to pass three params diff --git a/trunk/arch/parisc/kernel/irq.c b/trunk/arch/parisc/kernel/irq.c index 8007f1e65729..4ea4229d765c 100644 --- a/trunk/arch/parisc/kernel/irq.c +++ b/trunk/arch/parisc/kernel/irq.c @@ -130,17 +130,15 @@ int cpu_check_affinity(unsigned int irq, const struct cpumask *dest) return cpu_dest; } -static int cpu_set_affinity_irq(unsigned int irq, const struct cpumask *dest) +static void cpu_set_affinity_irq(unsigned int irq, const struct cpumask *dest) { int cpu_dest; cpu_dest = cpu_check_affinity(irq, dest); if (cpu_dest < 0) - return -1; + return; cpumask_copy(&irq_desc[irq].affinity, dest); - - return 0; } #endif diff --git a/trunk/arch/powerpc/kvm/powerpc.c b/trunk/arch/powerpc/kvm/powerpc.c index 2cf915e51e7e..9057335fdc61 100644 --- a/trunk/arch/powerpc/kvm/powerpc.c +++ b/trunk/arch/powerpc/kvm/powerpc.c @@ -41,12 +41,6 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *v) return !!(v->arch.pending_exceptions); } -int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) -{ - /* do real check here */ - return 1; -} - int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) { return !(v->arch.msr & MSR_WE); diff --git a/trunk/arch/powerpc/platforms/pseries/xics.c b/trunk/arch/powerpc/platforms/pseries/xics.c index be3581a8c294..80b513449f4c 100644 --- a/trunk/arch/powerpc/platforms/pseries/xics.c +++ b/trunk/arch/powerpc/platforms/pseries/xics.c @@ -333,7 +333,7 @@ static void xics_eoi_lpar(unsigned int virq) lpar_xirr_info_set((0xff << 24) | irq); } -static int xics_set_affinity(unsigned int virq, const struct cpumask *cpumask) +static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask) { unsigned int irq; int status; @@ -342,14 +342,14 @@ static int xics_set_affinity(unsigned int virq, const struct cpumask *cpumask) irq = (unsigned int)irq_map[virq].hwirq; if (irq == XICS_IPI || irq == XICS_IRQ_SPURIOUS) - return -1; + return; status = rtas_call(ibm_get_xive, 1, 3, xics_status, irq); if (status) { printk(KERN_ERR "%s: ibm,get-xive irq=%u returns %d\n", __func__, irq, status); - return -1; + return; } /* @@ -363,7 +363,7 @@ static int xics_set_affinity(unsigned int virq, const struct cpumask *cpumask) printk(KERN_WARNING "%s: No online cpus in the mask %s for irq %d\n", __func__, cpulist, virq); - return -1; + return; } status = rtas_call(ibm_set_xive, 3, 1, NULL, @@ -372,10 +372,8 @@ static int xics_set_affinity(unsigned int virq, const struct cpumask *cpumask) if (status) { printk(KERN_ERR "%s: ibm,set-xive irq=%u returns %d\n", __func__, irq, status); - return -1; + return; } - - return 0; } static struct irq_chip xics_pic_direct = { diff --git a/trunk/arch/powerpc/sysdev/axonram.c b/trunk/arch/powerpc/sysdev/axonram.c index a4779912a5ca..9e105cbc5e5f 100644 --- a/trunk/arch/powerpc/sysdev/axonram.c +++ b/trunk/arch/powerpc/sysdev/axonram.c @@ -250,7 +250,7 @@ axon_ram_probe(struct of_device *device, const struct of_device_id *device_id) set_capacity(bank->disk, bank->size >> AXON_RAM_SECTOR_SHIFT); blk_queue_make_request(bank->disk->queue, axon_ram_make_request); - blk_queue_logical_block_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE); + blk_queue_hardsect_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE); add_disk(bank->disk); bank->irq_id = irq_of_parse_and_map(device->node, 0); diff --git a/trunk/arch/powerpc/sysdev/mpic.c b/trunk/arch/powerpc/sysdev/mpic.c index 352d8c3ef526..0efc12d1a3d7 100644 --- a/trunk/arch/powerpc/sysdev/mpic.c +++ b/trunk/arch/powerpc/sysdev/mpic.c @@ -807,7 +807,7 @@ static void mpic_end_ipi(unsigned int irq) #endif /* CONFIG_SMP */ -int mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask) +void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask) { struct mpic *mpic = mpic_from_irq(irq); unsigned int src = mpic_irq_to_hw(irq); @@ -824,8 +824,6 @@ int mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask) mpic_irq_write(src, MPIC_INFO(IRQ_DESTINATION), mpic_physmask(cpus_addr(tmp)[0])); } - - return 0; } static unsigned int mpic_type_to_vecpri(struct mpic *mpic, unsigned int type) diff --git a/trunk/arch/powerpc/sysdev/mpic.h b/trunk/arch/powerpc/sysdev/mpic.h index eff433c322a0..3cef2af10f42 100644 --- a/trunk/arch/powerpc/sysdev/mpic.h +++ b/trunk/arch/powerpc/sysdev/mpic.h @@ -36,6 +36,6 @@ static inline int mpic_pasemi_msi_init(struct mpic *mpic) extern int mpic_set_irq_type(unsigned int virq, unsigned int flow_type); extern void mpic_set_vector(unsigned int virq, unsigned int vector); -extern int mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask); +extern void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask); #endif /* _POWERPC_SYSDEV_MPIC_H */ diff --git a/trunk/arch/s390/include/asm/kvm_host.h b/trunk/arch/s390/include/asm/kvm_host.h index a27d0d5a6f86..54ea39f96ecd 100644 --- a/trunk/arch/s390/include/asm/kvm_host.h +++ b/trunk/arch/s390/include/asm/kvm_host.h @@ -13,8 +13,6 @@ #ifndef ASM_KVM_HOST_H #define ASM_KVM_HOST_H -#include -#include #include #include #include @@ -212,8 +210,7 @@ struct kvm_vcpu_arch { s390_fp_regs guest_fpregs; unsigned int guest_acrs[NUM_ACRS]; struct kvm_s390_local_interrupt local_int; - struct hrtimer ckc_timer; - struct tasklet_struct tasklet; + struct timer_list ckc_timer; union { cpuid_t cpu_id; u64 stidp_data; diff --git a/trunk/arch/s390/kvm/intercept.c b/trunk/arch/s390/kvm/intercept.c index 98997ccba501..9d19803111ba 100644 --- a/trunk/arch/s390/kvm/intercept.c +++ b/trunk/arch/s390/kvm/intercept.c @@ -154,25 +154,17 @@ static int handle_stop(struct kvm_vcpu *vcpu) static int handle_validity(struct kvm_vcpu *vcpu) { int viwhy = vcpu->arch.sie_block->ipb >> 16; - int rc; - vcpu->stat.exit_validity++; - if ((viwhy == 0x37) && (vcpu->arch.sie_block->prefix - <= vcpu->kvm->arch.guest_memsize - 2*PAGE_SIZE)){ - rc = fault_in_pages_writeable((char __user *) - vcpu->kvm->arch.guest_origin + - vcpu->arch.sie_block->prefix, - 2*PAGE_SIZE); - if (rc) - /* user will receive sigsegv, exit to user */ - rc = -ENOTSUPP; - } else - rc = -ENOTSUPP; - - if (rc) - VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d", - viwhy); - return rc; + 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) diff --git a/trunk/arch/s390/kvm/interrupt.c b/trunk/arch/s390/kvm/interrupt.c index f04f5301b1b4..0189356fe209 100644 --- a/trunk/arch/s390/kvm/interrupt.c +++ b/trunk/arch/s390/kvm/interrupt.c @@ -12,8 +12,6 @@ #include #include -#include -#include #include #include #include "kvm-s390.h" @@ -301,13 +299,13 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) } if ((!rc) && atomic_read(&fi->active)) { - spin_lock(&fi->lock); + spin_lock_bh(&fi->lock); list_for_each_entry(inti, &fi->list, list) if (__interrupt_is_deliverable(vcpu, inti)) { rc = 1; break; } - spin_unlock(&fi->lock); + spin_unlock_bh(&fi->lock); } if ((!rc) && (vcpu->arch.sie_block->ckc < @@ -320,12 +318,6 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) return rc; } -int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) -{ - /* do real check here */ - return 1; -} - int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { return 0; @@ -363,12 +355,14 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) return 0; } - sltime = ((vcpu->arch.sie_block->ckc - now)*125)>>9; + sltime = (vcpu->arch.sie_block->ckc - now) / (0xf4240000ul / HZ) + 1; - hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL); - VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime); + vcpu->arch.ckc_timer.expires = jiffies + sltime; + + add_timer(&vcpu->arch.ckc_timer); + VCPU_EVENT(vcpu, 5, "enabled wait timer:%llx jiffies", sltime); no_timer: - spin_lock(&vcpu->arch.local_int.float_int->lock); + spin_lock_bh(&vcpu->arch.local_int.float_int->lock); spin_lock_bh(&vcpu->arch.local_int.lock); add_wait_queue(&vcpu->arch.local_int.wq, &wait); while (list_empty(&vcpu->arch.local_int.list) && @@ -377,46 +371,33 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) !signal_pending(current)) { set_current_state(TASK_INTERRUPTIBLE); spin_unlock_bh(&vcpu->arch.local_int.lock); - spin_unlock(&vcpu->arch.local_int.float_int->lock); + spin_unlock_bh(&vcpu->arch.local_int.float_int->lock); vcpu_put(vcpu); schedule(); vcpu_load(vcpu); - spin_lock(&vcpu->arch.local_int.float_int->lock); + 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(&vcpu->arch.local_int.float_int->lock); - hrtimer_try_to_cancel(&vcpu->arch.ckc_timer); + spin_unlock_bh(&vcpu->arch.local_int.float_int->lock); + del_timer(&vcpu->arch.ckc_timer); return 0; } -void kvm_s390_tasklet(unsigned long parm) +void kvm_s390_idle_wakeup(unsigned long data) { - struct kvm_vcpu *vcpu = (struct kvm_vcpu *) parm; + struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data; - spin_lock(&vcpu->arch.local_int.lock); + 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(&vcpu->arch.local_int.lock); + spin_unlock_bh(&vcpu->arch.local_int.lock); } -/* - * low level hrtimer wake routine. Because this runs in hardirq context - * we schedule a tasklet to do the real work. - */ -enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer) -{ - struct kvm_vcpu *vcpu; - - vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer); - tasklet_schedule(&vcpu->arch.tasklet); - - return HRTIMER_NORESTART; -} void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) { @@ -455,7 +436,7 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) if (atomic_read(&fi->active)) { do { deliver = 0; - spin_lock(&fi->lock); + 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); @@ -466,7 +447,7 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) } if (list_empty(&fi->list)) atomic_set(&fi->active, 0); - spin_unlock(&fi->lock); + spin_unlock_bh(&fi->lock); if (deliver) { __do_deliver_interrupt(vcpu, inti); kfree(inti); @@ -531,7 +512,7 @@ int kvm_s390_inject_vm(struct kvm *kvm, mutex_lock(&kvm->lock); fi = &kvm->arch.float_int; - spin_lock(&fi->lock); + 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); @@ -548,7 +529,7 @@ int kvm_s390_inject_vm(struct kvm *kvm, if (waitqueue_active(&li->wq)) wake_up_interruptible(&li->wq); spin_unlock_bh(&li->lock); - spin_unlock(&fi->lock); + spin_unlock_bh(&fi->lock); mutex_unlock(&kvm->lock); return 0; } diff --git a/trunk/arch/s390/kvm/kvm-s390.c b/trunk/arch/s390/kvm/kvm-s390.c index 10bccd1f8aee..f4d56e9939c9 100644 --- a/trunk/arch/s390/kvm/kvm-s390.c +++ b/trunk/arch/s390/kvm/kvm-s390.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include @@ -196,10 +195,6 @@ struct kvm *kvm_arch_create_vm(void) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { VCPU_EVENT(vcpu, 3, "%s", "free cpu"); - if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda == - (__u64) vcpu->arch.sie_block) - vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0; - smp_mb(); free_page((unsigned long)(vcpu->arch.sie_block)); kvm_vcpu_uninit(vcpu); kfree(vcpu); @@ -288,10 +283,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->gmsor = vcpu->kvm->arch.guest_origin; vcpu->arch.sie_block->ecb = 2; vcpu->arch.sie_block->eca = 0xC1002001U; - hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); - tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet, - (unsigned long) vcpu); - vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup; + 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 = 0xff; return 0; @@ -314,21 +307,19 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.sie_block->icpua = id; BUG_ON(!kvm->arch.sca); - if (!kvm->arch.sca->cpu[id].sda) - kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block; - else - BUG_ON(!kvm->vcpus[id]); /* vcpu does already exist */ + 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(&kvm->arch.float_int.lock); + 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(&kvm->arch.float_int.lock); + spin_unlock_bh(&kvm->arch.float_int.lock); rc = kvm_vcpu_init(vcpu, kvm, id); if (rc) @@ -487,12 +478,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu_load(vcpu); - /* verify, that memory has been registered */ - if (!vcpu->kvm->arch.guest_memsize) { - vcpu_put(vcpu); - return -EINVAL; - } - if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); @@ -672,8 +657,6 @@ int kvm_arch_set_memory_region(struct kvm *kvm, struct kvm_memory_slot old, int user_alloc) { - int i; - /* 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. @@ -681,7 +664,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm, vmas. It is okay to mmap() and munmap() stuff in this slot after doing this call at any time */ - if (mem->slot || kvm->arch.guest_memsize) + if (mem->slot) return -EINVAL; if (mem->guest_phys_addr) @@ -693,39 +676,15 @@ int kvm_arch_set_memory_region(struct kvm *kvm, if (mem->memory_size & (PAGE_SIZE - 1)) return -EINVAL; - if (!user_alloc) - return -EINVAL; - - /* lock all vcpus */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (!kvm->vcpus[i]) - continue; - if (!mutex_trylock(&kvm->vcpus[i]->mutex)) - goto fail_out; - } - kvm->arch.guest_origin = mem->userspace_addr; kvm->arch.guest_memsize = mem->memory_size; - /* update sie control blocks, and unlock all vcpus */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm->vcpus[i]->arch.sie_block->gmsor = - kvm->arch.guest_origin; - kvm->vcpus[i]->arch.sie_block->gmslm = - kvm->arch.guest_memsize + - kvm->arch.guest_origin + - VIRTIODESCSPACE - 1ul; - mutex_unlock(&kvm->vcpus[i]->mutex); - } - } + /* 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; - -fail_out: - for (; i >= 0; i--) - mutex_unlock(&kvm->vcpus[i]->mutex); - return -EINVAL; } void kvm_arch_flush_shadow(struct kvm *kvm) diff --git a/trunk/arch/s390/kvm/kvm-s390.h b/trunk/arch/s390/kvm/kvm-s390.h index 748fee872323..00bbe69b78da 100644 --- a/trunk/arch/s390/kvm/kvm-s390.h +++ b/trunk/arch/s390/kvm/kvm-s390.h @@ -14,7 +14,6 @@ #ifndef ARCH_S390_KVM_S390_H #define ARCH_S390_KVM_S390_H -#include #include #include @@ -42,8 +41,7 @@ static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu) } int kvm_s390_handle_wait(struct kvm_vcpu *vcpu); -enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer); -void kvm_s390_tasklet(unsigned long parm); +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); diff --git a/trunk/arch/s390/kvm/priv.c b/trunk/arch/s390/kvm/priv.c index 93ecd06e1a74..4b88834b8dd8 100644 --- a/trunk/arch/s390/kvm/priv.c +++ b/trunk/arch/s390/kvm/priv.c @@ -204,11 +204,11 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) int cpus = 0; int n; - spin_lock(&fi->lock); + spin_lock_bh(&fi->lock); for (n = 0; n < KVM_MAX_VCPUS; n++) if (fi->local_int[n]) cpus++; - spin_unlock(&fi->lock); + spin_unlock_bh(&fi->lock); /* deal with other level 3 hypervisors */ if (stsi(mem, 3, 2, 2) == -ENOSYS) diff --git a/trunk/arch/s390/kvm/sigp.c b/trunk/arch/s390/kvm/sigp.c index 36678835034d..f27dbedf0866 100644 --- a/trunk/arch/s390/kvm/sigp.c +++ b/trunk/arch/s390/kvm/sigp.c @@ -52,7 +52,7 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, if (cpu_addr >= KVM_MAX_VCPUS) return 3; /* not operational */ - spin_lock(&fi->lock); + 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) @@ -64,7 +64,7 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, *reg |= SIGP_STAT_STOPPED; rc = 1; /* status stored */ } - spin_unlock(&fi->lock); + spin_unlock_bh(&fi->lock); VCPU_EVENT(vcpu, 4, "sensed status of cpu %x rc %x", cpu_addr, rc); return rc; @@ -86,7 +86,7 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) inti->type = KVM_S390_INT_EMERGENCY; - spin_lock(&fi->lock); + spin_lock_bh(&fi->lock); li = fi->local_int[cpu_addr]; if (li == NULL) { rc = 3; /* not operational */ @@ -102,7 +102,7 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) spin_unlock_bh(&li->lock); rc = 0; /* order accepted */ unlock: - spin_unlock(&fi->lock); + spin_unlock_bh(&fi->lock); VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr); return rc; } @@ -123,7 +123,7 @@ static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int store) inti->type = KVM_S390_SIGP_STOP; - spin_lock(&fi->lock); + spin_lock_bh(&fi->lock); li = fi->local_int[cpu_addr]; if (li == NULL) { rc = 3; /* not operational */ @@ -142,7 +142,7 @@ static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int store) spin_unlock_bh(&li->lock); rc = 0; /* order accepted */ unlock: - spin_unlock(&fi->lock); + spin_unlock_bh(&fi->lock); VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", cpu_addr); return rc; } @@ -188,7 +188,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, if (!inti) return 2; /* busy */ - spin_lock(&fi->lock); + spin_lock_bh(&fi->lock); li = fi->local_int[cpu_addr]; if ((cpu_addr >= KVM_MAX_VCPUS) || (li == NULL)) { @@ -220,7 +220,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, out_li: spin_unlock_bh(&li->lock); out_fi: - spin_unlock(&fi->lock); + spin_unlock_bh(&fi->lock); return rc; } diff --git a/trunk/arch/sh/Kconfig b/trunk/arch/sh/Kconfig index 586cd045e2db..e7390dd0283d 100644 --- a/trunk/arch/sh/Kconfig +++ b/trunk/arch/sh/Kconfig @@ -15,7 +15,6 @@ config SUPERH select HAVE_IOREMAP_PROT if MMU select HAVE_ARCH_TRACEHOOK select HAVE_DMA_API_DEBUG - select RTC_LIB help The SuperH is a RISC processor targeted for use in embedded systems and consumer electronics; it was also used in the Sega Dreamcast @@ -75,18 +74,14 @@ config GENERIC_IOMAP bool config GENERIC_TIME - def_bool y + def_bool n config GENERIC_CLOCKEVENTS - def_bool y + def_bool n config GENERIC_CLOCKEVENTS_BROADCAST bool -config GENERIC_CMOS_UPDATE - def_bool y - depends on SH_SH03 || SH_DREAMCAST - config GENERIC_LOCKBREAK def_bool y depends on SMP && PREEMPT @@ -117,12 +112,6 @@ config SYS_SUPPORTS_PCI config SYS_SUPPORTS_CMT bool -config SYS_SUPPORTS_MTU2 - bool - -config SYS_SUPPORTS_TMU - bool - config STACKTRACE_SUPPORT def_bool y @@ -168,14 +157,13 @@ config CPU_SH3 bool select CPU_HAS_INTEVT select CPU_HAS_SR_RB - select SYS_SUPPORTS_TMU config CPU_SH4 bool select CPU_HAS_INTEVT select CPU_HAS_SR_RB + select CPU_HAS_PTEA if !CPU_SH4A || CPU_SHX2 select CPU_HAS_FPU if !CPU_SH4AL_DSP - select SYS_SUPPORTS_TMU config CPU_SH4A bool @@ -189,7 +177,6 @@ config CPU_SH4AL_DSP config CPU_SH5 bool select CPU_HAS_FPU - select SYS_SUPPORTS_TMU config CPU_SHX2 bool @@ -223,32 +210,27 @@ config CPU_SUBTYPE_SH7201 bool "Support SH7201 processor" select CPU_SH2A select CPU_HAS_FPU - select SYS_SUPPORTS_MTU2 config CPU_SUBTYPE_SH7203 bool "Support SH7203 processor" select CPU_SH2A select CPU_HAS_FPU select SYS_SUPPORTS_CMT - select SYS_SUPPORTS_MTU2 config CPU_SUBTYPE_SH7206 bool "Support SH7206 processor" select CPU_SH2A select SYS_SUPPORTS_CMT - select SYS_SUPPORTS_MTU2 config CPU_SUBTYPE_SH7263 bool "Support SH7263 processor" select CPU_SH2A select CPU_HAS_FPU select SYS_SUPPORTS_CMT - select SYS_SUPPORTS_MTU2 config CPU_SUBTYPE_MXG bool "Support MX-G processor" select CPU_SH2A - select SYS_SUPPORTS_MTU2 help Select MX-G if running on an R8A03022BG part. @@ -301,7 +283,6 @@ config CPU_SUBTYPE_SH7720 bool "Support SH7720 processor" select CPU_SH3 select CPU_HAS_DSP - select SYS_SUPPORTS_CMT help Select SH7720 if you have a SH3-DSP SH7720 CPU. @@ -309,7 +290,6 @@ config CPU_SUBTYPE_SH7721 bool "Support SH7721 processor" select CPU_SH3 select CPU_HAS_DSP - select SYS_SUPPORTS_CMT help Select SH7721 if you have a SH3-DSP SH7721 CPU. @@ -367,16 +347,6 @@ config CPU_SUBTYPE_SH7723 help Select SH7723 if you have an SH-MobileR2 CPU. -config CPU_SUBTYPE_SH7724 - bool "Support SH7724 processor" - select CPU_SH4A - select CPU_SHX2 - select ARCH_SHMOBILE - select ARCH_SPARSEMEM_ENABLE - select SYS_SUPPORTS_CMT - help - Select SH7724 if you have an SH-MobileR2R CPU. - config CPU_SUBTYPE_SH7763 bool "Support SH7763 processor" select CPU_SH4A @@ -472,26 +442,48 @@ source "arch/sh/boards/Kconfig" menu "Timer and clock configuration" -config SH_TIMER_TMU - bool "TMU timer driver" - depends on SYS_SUPPORTS_TMU +config SH_TMU + bool "TMU timer support" + depends on CPU_SH3 || CPU_SH4 default y + select GENERIC_TIME + select GENERIC_CLOCKEVENTS help - This enables the build of the TMU timer driver. + This enables the use of the TMU as the system timer. -config SH_TIMER_CMT - bool "CMT timer driver" - depends on SYS_SUPPORTS_CMT +config SH_CMT + bool "CMT timer support" + depends on SYS_SUPPORTS_CMT && CPU_SH2 default y help - This enables build of the CMT timer driver. + This enables the use of the CMT as the system timer. -config SH_TIMER_MTU2 - bool "MTU2 timer driver" - depends on SYS_SUPPORTS_MTU2 +# +# Support for the new-style CMT driver. This will replace SH_CMT +# once its other dependencies are merged. +# +config SH_TIMER_CMT + bool "CMT clockevents driver" + depends on SYS_SUPPORTS_CMT && !SH_CMT + select GENERIC_CLOCKEVENTS + +config SH_MTU2 + bool "MTU2 timer support" + depends on CPU_SH2A default y help - This enables build of the MTU2 timer driver. + This enables the use of the MTU2 as the system timer. + +config SH_TIMER_IRQ + int + default "28" if CPU_SUBTYPE_SH7780 || CPU_SUBTYPE_SH7785 || \ + CPU_SUBTYPE_SH7763 + default "86" if CPU_SUBTYPE_SH7619 + default "140" if CPU_SUBTYPE_SH7206 + default "142" if CPU_SUBTYPE_SH7203 && SH_CMT + default "153" if CPU_SUBTYPE_SH7203 && SH_MTU2 + default "238" if CPU_SUBTYPE_MXG + default "16" config SH_PCLK_FREQ int "Peripheral clock frequency (in Hz)" @@ -502,7 +494,7 @@ config SH_PCLK_FREQ CPU_SUBTYPE_SH7760 || CPU_SUBTYPE_SH7705 || \ CPU_SUBTYPE_SH7203 || CPU_SUBTYPE_SH7206 || \ CPU_SUBTYPE_SH7263 || CPU_SUBTYPE_MXG || \ - CPU_SUBTYPE_SH7786 || CPU_SUBTYPE_SH7724 + CPU_SUBTYPE_SH7786 default "60000000" if CPU_SUBTYPE_SH7751 || CPU_SUBTYPE_SH7751R default "66000000" if CPU_SUBTYPE_SH4_202 default "50000000" @@ -511,13 +503,6 @@ config SH_PCLK_FREQ This is necessary for determining the reference clock value on platforms lacking an RTC. -config SH_CLK_CPG - def_bool y - -config SH_CLK_CPG_LEGACY - depends on SH_CLK_CPG - def_bool y if !CPU_SUBTYPE_SH7785 && !ARCH_SHMOBILE - config SH_CLK_MD int "CPU Mode Pin Setting" depends on CPU_SH2 @@ -678,54 +663,27 @@ config GUSA_RB LLSC, this should be more efficient than the other alternative of disabling interrupts around the atomic sequence. -config SPARSE_IRQ - bool "Support sparse irq numbering" - depends on EXPERIMENTAL - help - This enables support for sparse irqs. This is useful in general - as most CPUs have a fairly sparse array of IRQ vectors, which - the irq_desc then maps directly on to. Systems with a high - number of off-chip IRQs will want to treat this as - experimental until they have been independently verified. - - If you don't know what to do here, say N. - endmenu menu "Boot options" config ZERO_PAGE_OFFSET - hex - default "0x00010000" if PAGE_SIZE_64KB || SH_RTS7751R2D || \ - SH_7751_SOLUTION_ENGINE - default "0x00004000" if PAGE_SIZE_16KB || SH_SH03 + hex "Zero page offset" + default "0x00004000" if SH_SH03 + default "0x00010000" if PAGE_SIZE_64KB default "0x00002000" if PAGE_SIZE_8KB default "0x00001000" help This sets the default offset of zero page. config BOOT_LINK_OFFSET - hex - default "0x00210000" if SH_SHMIN - default "0x00400000" if SH_CAYMAN - default "0x00810000" if SH_7780_SOLUTION_ENGINE - default "0x009e0000" if SH_TITAN - default "0x01800000" if SH_SDK7780 - default "0x02000000" if SH_EDOSK7760 + hex "Link address offset for booting" default "0x00800000" help This option allows you to set the link address offset of the zImage. This can be useful if you are on a board which has a small amount of memory. -config ENTRY_OFFSET - hex - default "0x00001000" if PAGE_SIZE_4KB - default "0x00002000" if PAGE_SIZE_8KB - default "0x00004000" if PAGE_SIZE_16KB - default "0x00010000" if PAGE_SIZE_64KB - default "0x00000000" - config UBC_WAKEUP bool "Wakeup UBC on startup" depends on CPU_SH4 && !CPU_SH4A diff --git a/trunk/arch/sh/Kconfig.cpu b/trunk/arch/sh/Kconfig.cpu index cd6e3ea598d5..c7d704381a6d 100644 --- a/trunk/arch/sh/Kconfig.cpu +++ b/trunk/arch/sh/Kconfig.cpu @@ -76,6 +76,11 @@ config SPECULATIVE_EXECUTION If unsure, say N. +config SH64_USER_MISALIGNED_FIXUP + def_bool y + prompt "Fixup misaligned loads/stores occurring in user mode" + depends on SUPERH64 + config SH64_ID2815_WORKAROUND bool "Include workaround for SH5-101 cut2 silicon defect ID2815" depends on CPU_SUBTYPE_SH5_101 @@ -96,6 +101,9 @@ config CPU_HAS_SR_RB See for further information on SR.RB and register banking in the kernel in general. +config CPU_HAS_PTEA + bool + config CPU_HAS_PTEAEX bool diff --git a/trunk/arch/sh/Kconfig.debug b/trunk/arch/sh/Kconfig.debug index 8179cc9be9a4..0d62681f72a0 100644 --- a/trunk/arch/sh/Kconfig.debug +++ b/trunk/arch/sh/Kconfig.debug @@ -38,10 +38,10 @@ config EARLY_SCIF_CONSOLE_PORT default "0xffe00000" if CPU_SUBTYPE_SH7780 || CPU_SUBTYPE_SH7763 || \ CPU_SUBTYPE_SH7722 || CPU_SUBTYPE_SH7366 || \ CPU_SUBTYPE_SH7343 + default "0xffe80000" if CPU_SH4 default "0xffea0000" if CPU_SUBTYPE_SH7785 default "0xfffe8000" if CPU_SUBTYPE_SH7203 default "0xfffe9800" if CPU_SUBTYPE_SH7206 || CPU_SUBTYPE_SH7263 - default "0xffe80000" if CPU_SH4 default "0x00000000" config EARLY_PRINTK @@ -92,7 +92,7 @@ config 4KSTACKS config IRQSTACKS bool "Use separate kernel stacks when processing interrupts" - depends on DEBUG_KERNEL && SUPERH32 && BROKEN + depends on DEBUG_KERNEL && SUPERH32 help If you say Y here the kernel will use separate kernel stacks for handling hard and soft interrupts. This can help avoid @@ -122,8 +122,27 @@ config SH_NO_BSS_INIT For all other cases, say N. If this option seems perplexing, or you aren't sure, say N. +config MORE_COMPILE_OPTIONS + bool "Add any additional compile options" + help + If you want to add additional CFLAGS to the kernel build, enable this + option and then enter what you would like to add in the next question. + Note however that -g is already appended with the selection of KGDB. + +config COMPILE_OPTIONS + string "Additional compile arguments" + depends on MORE_COMPILE_OPTIONS + config SH64_SR_WATCH bool "Debug: set SR.WATCH to enable hardware watchpoints and trace" depends on SUPERH64 +config POOR_MANS_STRACE + bool "Debug: enable rudimentary strace facility" + depends on SUPERH64 + help + This option allows system calls to be traced to the console. It also + aids in detecting kernel stack underflow. It is useful for debugging + early-userland problems (e.g. init incurring fatal exceptions.) + endmenu diff --git a/trunk/arch/sh/Makefile b/trunk/arch/sh/Makefile index 75d049b03f7e..bece1f7535f2 100644 --- a/trunk/arch/sh/Makefile +++ b/trunk/arch/sh/Makefile @@ -70,6 +70,9 @@ cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -ml cflags-y += $(call cc-option,-mno-fdpic) cflags-y += $(isaflags-y) -ffreestanding +cflags-$(CONFIG_MORE_COMPILE_OPTIONS) += \ + $(shell echo $(CONFIG_COMPILE_OPTIONS) | sed -e 's/"//g') + OBJCOPYFLAGS := -O binary -R .note -R .note.gnu.build-id -R .comment \ -R .stab -R .stabstr -S @@ -82,6 +85,7 @@ defaultimage-$(CONFIG_SH_7206_SOLUTION_ENGINE) := vmlinux defaultimage-$(CONFIG_SH_7619_SOLUTION_ENGINE) := vmlinux # Set some sensible Kbuild defaults +KBUILD_DEFCONFIG := shx3_defconfig KBUILD_IMAGE := $(defaultimage-y) # @@ -89,38 +93,26 @@ KBUILD_IMAGE := $(defaultimage-y) # error messages during linking. # ifdef CONFIG_SUPERH32 -UTS_MACHINE := sh -BITS := 32 -LDFLAGS_vmlinux += -e _stext -KBUILD_DEFCONFIG := shx3_defconfig +UTS_MACHINE := sh +LDFLAGS_vmlinux += -e _stext else -UTS_MACHINE := sh64 -BITS := 64 -LDFLAGS_vmlinux += --defsym phys_stext=_stext-$(CONFIG_PAGE_OFFSET) \ - --defsym phys_stext_shmedia=phys_stext+1 \ - -e phys_stext_shmedia -KBUILD_DEFCONFIG := cayman_defconfig -endif - -ifneq ($(SUBARCH),$(ARCH)) - ifeq ($(CROSS_COMPILE),) - CROSS_COMPILE := $(call cc-cross-prefix, $(UTS_MACHINE)-linux- $(UTS_MACHINE)-linux-gnu- $(UTS_MACHINE)-unknown-linux-gnu-) - endif +UTS_MACHINE := sh64 +LDFLAGS_vmlinux += --defsym phys_stext=_stext-$(CONFIG_PAGE_OFFSET) \ + --defsym phys_stext_shmedia=phys_stext+1 \ + -e phys_stext_shmedia endif ifdef CONFIG_CPU_LITTLE_ENDIAN -ld-bfd := elf32-$(UTS_MACHINE)-linux -LDFLAGS_vmlinux += --defsym 'jiffies=jiffies_64' --oformat $(ld-bfd) +LDFLAGS_vmlinux += --defsym 'jiffies=jiffies_64' LDFLAGS += -EL else -ld-bfd := elf32-$(UTS_MACHINE)big-linux -LDFLAGS_vmlinux += --defsym 'jiffies=jiffies_64+4' --oformat $(ld-bfd) +LDFLAGS_vmlinux += --defsym 'jiffies=jiffies_64+4' LDFLAGS += -EB endif -export ld-bfd BITS - -head-y := arch/sh/kernel/init_task.o arch/sh/kernel/head_$(BITS).o +head-y := arch/sh/kernel/init_task.o +head-$(CONFIG_SUPERH32) += arch/sh/kernel/head_32.o +head-$(CONFIG_SUPERH64) += arch/sh/kernel/head_64.o core-y += arch/sh/kernel/ arch/sh/mm/ arch/sh/boards/ core-$(CONFIG_SH_FPU_EMU) += arch/sh/math-emu/ @@ -201,11 +193,10 @@ zImage uImage uImage.srec vmlinux.srec: vmlinux compressed: zImage -archprepare: maketools +archprepare: maketools arch/sh/lib64/syscalltab.h archclean: $(Q)$(MAKE) $(clean)=$(boot) - $(Q)$(MAKE) $(clean)=arch/sh/kernel/vsyscall define archhelp @echo '* zImage - Compressed kernel image' @@ -214,4 +205,34 @@ define archhelp @echo ' uImage.srec - Create an S-record for U-Boot' endef -CLEAN_FILES += include/asm-sh/machtypes.h +define filechk_gen-syscalltab + (set -e; \ + echo "/*"; \ + echo " * DO NOT MODIFY."; \ + echo " *"; \ + echo " * This file was generated by arch/sh/Makefile"; \ + echo " * Any changes will be reverted at build time."; \ + echo " */"; \ + echo ""; \ + echo "#ifndef __SYSCALLTAB_H"; \ + echo "#define __SYSCALLTAB_H"; \ + echo ""; \ + echo "#include "; \ + echo ""; \ + echo "struct syscall_info {"; \ + echo " const char *name;"; \ + echo "} syscall_info_table[] = {"; \ + sed -e '/^.*\.long /!d;s// { "/;s/\(\([^/]*\)\/\)\{1\}.*/\2/; \ + s/[ \t]*$$//g;s/$$/" },/;s/\("\)sys_/\1/g'; \ + echo "};"; \ + echo ""; \ + echo "#define NUM_SYSCALL_INFO_ENTRIES ARRAY_SIZE(syscall_info_table)";\ + echo ""; \ + echo "#endif /* __SYSCALLTAB_H */" ) +endef + +arch/sh/lib64/syscalltab.h: arch/sh/kernel/syscalls_64.S + $(call filechk,gen-syscalltab) + +CLEAN_FILES += arch/sh/lib64/syscalltab.h \ + include/asm-sh/machtypes.h diff --git a/trunk/arch/sh/boards/Kconfig b/trunk/arch/sh/boards/Kconfig index 1c91b1f565d5..dcc1af8a2cfe 100644 --- a/trunk/arch/sh/boards/Kconfig +++ b/trunk/arch/sh/boards/Kconfig @@ -46,15 +46,6 @@ config SH_7722_SOLUTION_ENGINE Select 7722 SolutionEngine if configuring for a Hitachi SH772 evaluation board. -config SH_7724_SOLUTION_ENGINE - bool "SolutionEngine7724" - select SOLUTION_ENGINE - depends on CPU_SUBTYPE_SH7724 - select ARCH_REQUIRE_GPIOLIB - help - Select 7724 SolutionEngine if configuring for a Hitachi SH7724 - evaluation board. - config SH_7751_SOLUTION_ENGINE bool "SolutionEngine7751" select SOLUTION_ENGINE @@ -130,7 +121,7 @@ config SH_RTS7751R2D bool "RTS7751R2D" depends on CPU_SUBTYPE_SH7751R select SYS_SUPPORTS_PCI - select IO_TRAPPED if MMU + select IO_TRAPPED help Select RTS7751R2D if configuring for a Renesas Technology Sales SH-Graphics board. @@ -154,13 +145,13 @@ config SH_HIGHLANDER bool "Highlander" depends on CPU_SUBTYPE_SH7780 || CPU_SUBTYPE_SH7785 select SYS_SUPPORTS_PCI - select IO_TRAPPED if MMU + select IO_TRAPPED config SH_SH7785LCR bool "SH7785LCR" depends on CPU_SUBTYPE_SH7785 select SYS_SUPPORTS_PCI - select IO_TRAPPED if MMU + select IO_TRAPPED config SH_SH7785LCR_29BIT_PHYSMAPS bool "SH7785LCR 29bit physmaps" diff --git a/trunk/arch/sh/boards/board-ap325rxa.c b/trunk/arch/sh/boards/board-ap325rxa.c index 1c4d83ef2a47..f2a29641b6a3 100644 --- a/trunk/arch/sh/boards/board-ap325rxa.c +++ b/trunk/arch/sh/boards/board-ap325rxa.c @@ -535,18 +535,6 @@ static int __init ap325rxa_devices_setup(void) } device_initcall(ap325rxa_devices_setup); -/* Return the board specific boot mode pin configuration */ -static int ap325rxa_mode_pins(void) -{ - /* MD0=0, MD1=0, MD2=0: Clock Mode 0 - * MD3=0: 16-bit Area0 Bus Width - * MD5=1: Little Endian - * TSTMD=1, MD8=1: Test Mode Disabled - */ - return MODE_PIN5 | MODE_PIN8; -} - static struct sh_machine_vector mv_ap325rxa __initmv = { .mv_name = "AP-325RXA", - .mv_mode_pins = ap325rxa_mode_pins, }; diff --git a/trunk/arch/sh/boards/board-sh7785lcr.c b/trunk/arch/sh/boards/board-sh7785lcr.c index 7be56fb06c1f..6f94f17adc46 100644 --- a/trunk/arch/sh/boards/board-sh7785lcr.c +++ b/trunk/arch/sh/boards/board-sh7785lcr.c @@ -2,12 +2,12 @@ * Renesas Technology Corp. R0P7785LC0011RL Support. * * Copyright (C) 2008 Yoshihiro Shimoda - * Copyright (C) 2009 Paul Mundt * * 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. */ + #include #include #include @@ -19,12 +19,8 @@ #include #include #include -#include -#include -#include #include -#include -#include +#include /* * NOTE: This board has 2 physical memory maps. @@ -277,20 +273,6 @@ void __init init_sh7785lcr_IRQ(void) plat_irq_setup_pins(IRQ_MODE_IRQ3210); } -static int sh7785lcr_clk_init(void) -{ - struct clk *clk; - int ret; - - clk = clk_get(NULL, "extal"); - if (!clk || IS_ERR(clk)) - return PTR_ERR(clk); - ret = clk_set_rate(clk, 33333333); - clk_put(clk); - - return ret; -} - static void sh7785lcr_power_off(void) { unsigned char *p; @@ -321,34 +303,12 @@ static void __init sh7785lcr_setup(char **cmdline_p) writel(0x000307c2, sm501_reg); } -/* Return the board specific boot mode pin configuration */ -static int sh7785lcr_mode_pins(void) -{ - int value = 0; - - /* These are the factory default settings of S1 and S2. - * If you change these dip switches then you will need to - * adjust the values below as well. - */ - value |= MODE_PIN4; /* Clock Mode 16 */ - value |= MODE_PIN5; /* 32-bit Area0 bus width */ - value |= MODE_PIN6; /* 32-bit Area0 bus width */ - value |= MODE_PIN7; /* Area 0 SRAM interface [fixed] */ - value |= MODE_PIN8; /* Little Endian */ - value |= MODE_PIN9; /* Master Mode */ - value |= MODE_PIN14; /* No PLL step-up */ - - return value; -} - /* * The Machine Vector */ static struct sh_machine_vector mv_sh7785lcr __initmv = { .mv_name = "SH7785LCR", .mv_setup = sh7785lcr_setup, - .mv_clk_init = sh7785lcr_clk_init, .mv_init_irq = init_sh7785lcr_IRQ, - .mv_mode_pins = sh7785lcr_mode_pins, }; diff --git a/trunk/arch/sh/boards/mach-cayman/Makefile b/trunk/arch/sh/boards/mach-cayman/Makefile index 00fa3eaecb1b..cafe1ac3b29c 100644 --- a/trunk/arch/sh/boards/mach-cayman/Makefile +++ b/trunk/arch/sh/boards/mach-cayman/Makefile @@ -1,4 +1,4 @@ # # Makefile for the Hitachi Cayman specific parts of the kernel # -obj-y := setup.o irq.o panic.o +obj-y := setup.o irq.o diff --git a/trunk/arch/sh/boards/mach-cayman/irq.c b/trunk/arch/sh/boards/mach-cayman/irq.c index 33f770856319..da62ad516994 100644 --- a/trunk/arch/sh/boards/mach-cayman/irq.c +++ b/trunk/arch/sh/boards/mach-cayman/irq.c @@ -142,11 +142,26 @@ int cayman_irq_demux(int evt) return irq; } +#if defined(CONFIG_PROC_FS) && defined(CONFIG_SYSCTL) +int cayman_irq_describe(char* p, int irq) +{ + if (irq < NR_INTC_IRQS) { + return intc_irq_describe(p, irq); + } else if (irq < NR_INTC_IRQS + 8) { + return sprintf(p, "(SMSC %d)", irq - NR_INTC_IRQS); + } else if ((irq >= NR_INTC_IRQS + 24) && (irq < NR_INTC_IRQS + 32)) { + return sprintf(p, "(PCI2 %d)", irq - (NR_INTC_IRQS + 24)); + } + + return 0; +} +#endif + void init_cayman_irq(void) { int i; - epld_virt = (unsigned long)ioremap_nocache(EPLD_BASE, 1024); + epld_virt = onchip_remap(EPLD_BASE, 1024, "EPLD"); if (!epld_virt) { printk(KERN_ERR "Cayman IRQ: Unable to remap EPLD\n"); return; diff --git a/trunk/arch/sh/boards/mach-cayman/panic.c b/trunk/arch/sh/boards/mach-cayman/panic.c deleted file mode 100644 index d1e67306d07c..000000000000 --- a/trunk/arch/sh/boards/mach-cayman/panic.c +++ /dev/null @@ -1,49 +0,0 @@ -/* - * Copyright (C) 2003 Richard Curnow, SuperH UK Limited - * - * 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. - */ - -#include -#include -#include - -/* THIS IS A PHYSICAL ADDRESS */ -#define HDSP2534_ADDR (0x04002100) - -static void poor_mans_delay(void) -{ - int i; - - for (i = 0; i < 2500000; i++) - cpu_relax(); -} - -static void show_value(unsigned long x) -{ - int i; - unsigned nibble; - for (i = 0; i < 8; i++) { - nibble = ((x >> (i * 4)) & 0xf); - - __raw_writeb(nibble + ((nibble > 9) ? 55 : 48), - HDSP2534_ADDR + 0xe0 + ((7 - i) << 2)); - } -} - -void -panic_handler(unsigned long panicPC, unsigned long panicSSR, - unsigned long panicEXPEVT) -{ - while (1) { - /* This piece of code displays the PC on the LED display */ - show_value(panicPC); - poor_mans_delay(); - show_value(panicSSR); - poor_mans_delay(); - show_value(panicEXPEVT); - poor_mans_delay(); - } -} diff --git a/trunk/arch/sh/boards/mach-cayman/setup.c b/trunk/arch/sh/boards/mach-cayman/setup.c index 7e8216ac31bd..e7f9cc5f2ff1 100644 --- a/trunk/arch/sh/boards/mach-cayman/setup.c +++ b/trunk/arch/sh/boards/mach-cayman/setup.c @@ -102,7 +102,7 @@ static int __init smsc_superio_setup(void) { unsigned char devid, devrev; - smsc_superio_virt = (unsigned long)ioremap_nocache(SMSC_SUPERIO_BASE, 1024); + smsc_superio_virt = onchip_remap(SMSC_SUPERIO_BASE, 1024, "SMSC SuperIO"); if (!smsc_superio_virt) { panic("Unable to remap SMSC SuperIO\n"); } diff --git a/trunk/arch/sh/boards/mach-dreamcast/setup.c b/trunk/arch/sh/boards/mach-dreamcast/setup.c index ebe99227d4e6..d1bee4884cd6 100644 --- a/trunk/arch/sh/boards/mach-dreamcast/setup.c +++ b/trunk/arch/sh/boards/mach-dreamcast/setup.c @@ -30,6 +30,7 @@ extern struct irq_chip systemasic_int; extern void aica_time_init(void); +extern int gapspci_init(void); extern int systemasic_irq_demux(int); static void __init dreamcast_setup(char **cmdline_p) @@ -50,6 +51,11 @@ static void __init dreamcast_setup(char **cmdline_p) handle_level_irq); board_time_init = aica_time_init; + +#ifdef CONFIG_PCI + if (gapspci_init() < 0) + printk(KERN_WARNING "GAPSPCI was not detected.\n"); +#endif } static struct sh_machine_vector mv_dreamcast __initmv = { diff --git a/trunk/arch/sh/boards/mach-migor/setup.c b/trunk/arch/sh/boards/mach-migor/setup.c index 6ed401cd3156..1ee1de0bc1c3 100644 --- a/trunk/arch/sh/boards/mach-migor/setup.c +++ b/trunk/arch/sh/boards/mach-migor/setup.c @@ -584,22 +584,3 @@ static int __init migor_devices_setup(void) return platform_add_devices(migor_devices, ARRAY_SIZE(migor_devices)); } __initcall(migor_devices_setup); - -/* Return the board specific boot mode pin configuration */ -static int migor_mode_pins(void) -{ - /* MD0=1, MD1=1, MD2=0: Clock Mode 3 - * MD3=0: 16-bit Area0 Bus Width - * MD5=1: Little Endian - * TSTMD=1, MD8=0: Test Mode Disabled - */ - return MODE_PIN0 | MODE_PIN1 | MODE_PIN5; -} - -/* - * The Machine Vector - */ -static struct sh_machine_vector mv_migor __initmv = { - .mv_name = "Migo-R", - .mv_mode_pins = migor_mode_pins, -}; diff --git a/trunk/arch/sh/boards/mach-r2d/setup.c b/trunk/arch/sh/boards/mach-r2d/setup.c index a625ecb93e47..c585be00956e 100644 --- a/trunk/arch/sh/boards/mach-r2d/setup.c +++ b/trunk/arch/sh/boards/mach-r2d/setup.c @@ -10,9 +10,6 @@ */ #include #include -#include -#include -#include #include #include #include @@ -184,50 +181,6 @@ static struct platform_device sm501_device = { .resource = sm501_resources, }; -static struct mtd_partition r2d_partitions[] = { - { - .name = "U-Boot", - .offset = 0x00000000, - .size = 0x00040000, - .mask_flags = MTD_WRITEABLE, - }, { - .name = "Environment", - .offset = MTDPART_OFS_NXTBLK, - .size = 0x00040000, - .mask_flags = MTD_WRITEABLE, - }, { - .name = "Kernel", - .offset = MTDPART_OFS_NXTBLK, - .size = 0x001c0000, - }, { - .name = "Flash_FS", - .offset = MTDPART_OFS_NXTBLK, - .size = MTDPART_SIZ_FULL, - } -}; - -static struct physmap_flash_data flash_data = { - .width = 2, - .nr_parts = ARRAY_SIZE(r2d_partitions), - .parts = r2d_partitions, -}; - -static struct resource flash_resource = { - .start = 0x00000000, - .end = 0x02000000, - .flags = IORESOURCE_MEM, -}; - -static struct platform_device flash_device = { - .name = "physmap-flash", - .id = -1, - .resource = &flash_resource, - .num_resources = 1, - .dev = { - .platform_data = &flash_data, - }, -}; - static struct platform_device *rts7751r2d_devices[] __initdata = { &sm501_device, &heartbeat_device, @@ -250,9 +203,6 @@ static int __init rts7751r2d_devices_setup(void) if (register_trapped_io(&cf_trapped_io) == 0) platform_device_register(&cf_ide_device); - if (mach_is_r2d_plus()) - platform_device_register(&flash_device); - spi_register_board_info(spi_bus, ARRAY_SIZE(spi_bus)); return platform_add_devices(rts7751r2d_devices, diff --git a/trunk/arch/sh/boards/mach-se/7724/Makefile b/trunk/arch/sh/boards/mach-se/7724/Makefile deleted file mode 100644 index 349cbd6ce82d..000000000000 --- a/trunk/arch/sh/boards/mach-se/7724/Makefile +++ /dev/null @@ -1,10 +0,0 @@ -# -# Makefile for the HITACHI UL SolutionEngine 7724 specific parts of the kernel -# -# 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. -# -# - -obj-y := setup.o irq.o \ No newline at end of file diff --git a/trunk/arch/sh/boards/mach-se/7724/irq.c b/trunk/arch/sh/boards/mach-se/7724/irq.c deleted file mode 100644 index f76cf3b49f23..000000000000 --- a/trunk/arch/sh/boards/mach-se/7724/irq.c +++ /dev/null @@ -1,139 +0,0 @@ -/* - * linux/arch/sh/boards/se/7724/irq.c - * - * Copyright (C) 2009 Renesas Solutions Corp. - * - * Kuninori Morimoto - * - * Based on linux/arch/sh/boards/se/7722/irq.c - * Copyright (C) 2007 Nobuhiro Iwamatsu - * - * Hitachi UL SolutionEngine 7724 Support. - * - * 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. - */ -#include -#include -#include -#include -#include -#include - -struct fpga_irq { - unsigned long sraddr; - unsigned long mraddr; - unsigned short mask; - unsigned int base; -}; - -static unsigned int fpga2irq(unsigned int irq) -{ - if (irq >= IRQ0_BASE && - irq <= IRQ0_END) - return IRQ0_IRQ; - else if (irq >= IRQ1_BASE && - irq <= IRQ1_END) - return IRQ1_IRQ; - else - return IRQ2_IRQ; -} - -static struct fpga_irq get_fpga_irq(unsigned int irq) -{ - struct fpga_irq set; - - switch (irq) { - case IRQ0_IRQ: - set.sraddr = IRQ0_SR; - set.mraddr = IRQ0_MR; - set.mask = IRQ0_MASK; - set.base = IRQ0_BASE; - break; - case IRQ1_IRQ: - set.sraddr = IRQ1_SR; - set.mraddr = IRQ1_MR; - set.mask = IRQ1_MASK; - set.base = IRQ1_BASE; - break; - default: - set.sraddr = IRQ2_SR; - set.mraddr = IRQ2_MR; - set.mask = IRQ2_MASK; - set.base = IRQ2_BASE; - break; - } - - return set; -} - -static void disable_se7724_irq(unsigned int irq) -{ - struct fpga_irq set = get_fpga_irq(fpga2irq(irq)); - unsigned int bit = irq - set.base; - ctrl_outw(ctrl_inw(set.mraddr) | 0x0001 << bit, set.mraddr); -} - -static void enable_se7724_irq(unsigned int irq) -{ - struct fpga_irq set = get_fpga_irq(fpga2irq(irq)); - unsigned int bit = irq - set.base; - ctrl_outw(ctrl_inw(set.mraddr) & ~(0x0001 << bit), set.mraddr); -} - -static struct irq_chip se7724_irq_chip __read_mostly = { - .name = "SE7724-FPGA", - .mask = disable_se7724_irq, - .unmask = enable_se7724_irq, - .mask_ack = disable_se7724_irq, -}; - -static void se7724_irq_demux(unsigned int irq, struct irq_desc *desc) -{ - struct fpga_irq set = get_fpga_irq(irq); - unsigned short intv = ctrl_inw(set.sraddr); - struct irq_desc *ext_desc; - unsigned int ext_irq = set.base; - - intv &= set.mask; - - while (intv) { - if (intv & 0x0001) { - ext_desc = irq_desc + ext_irq; - handle_level_irq(ext_irq, ext_desc); - } - intv >>= 1; - ext_irq++; - } -} - -/* - * Initialize IRQ setting - */ -void __init init_se7724_IRQ(void) -{ - int i; - - ctrl_outw(0xffff, IRQ0_MR); /* mask all */ - ctrl_outw(0xffff, IRQ1_MR); /* mask all */ - ctrl_outw(0xffff, IRQ2_MR); /* mask all */ - ctrl_outw(0x0000, IRQ0_SR); /* clear irq */ - ctrl_outw(0x0000, IRQ1_SR); /* clear irq */ - ctrl_outw(0x0000, IRQ2_SR); /* clear irq */ - ctrl_outw(0x002a, IRQ_MODE); /* set irq type */ - - for (i = 0; i < SE7724_FPGA_IRQ_NR; i++) - set_irq_chip_and_handler_name(SE7724_FPGA_IRQ_BASE + i, - &se7724_irq_chip, - handle_level_irq, "level"); - - set_irq_chained_handler(IRQ0_IRQ, se7724_irq_demux); - set_irq_type(IRQ0_IRQ, IRQ_TYPE_LEVEL_LOW); - - set_irq_chained_handler(IRQ1_IRQ, se7724_irq_demux); - set_irq_type(IRQ1_IRQ, IRQ_TYPE_LEVEL_LOW); - - set_irq_chained_handler(IRQ2_IRQ, se7724_irq_demux); - set_irq_type(IRQ2_IRQ, IRQ_TYPE_LEVEL_LOW); -} diff --git a/trunk/arch/sh/boards/mach-se/7724/setup.c b/trunk/arch/sh/boards/mach-se/7724/setup.c deleted file mode 100644 index 9cd04bd558b8..000000000000 --- a/trunk/arch/sh/boards/mach-se/7724/setup.c +++ /dev/null @@ -1,448 +0,0 @@ -/* - * linux/arch/sh/boards/se/7724/setup.c - * - * Copyright (C) 2009 Renesas Solutions Corp. - * - * Kuninori Morimoto - * - * 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. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include