diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block index 44f52a4f5903359eda2f2ffafff2d3341e437e62..cbbd3e0699453391a461bff35431df5f0ee0d53e 100644 --- a/Documentation/ABI/testing/sysfs-block +++ b/Documentation/ABI/testing/sysfs-block @@ -60,3 +60,62 @@ 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/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss b/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss new file mode 100644 index 0000000000000000000000000000000000000000..0a92a7c93a62067f4526fe581f4604c3eb9f5ee0 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss @@ -0,0 +1,33 @@ +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/Documentation/ABI/testing/sysfs-devices-cache_disable b/Documentation/ABI/testing/sysfs-devices-cache_disable new file mode 100644 index 0000000000000000000000000000000000000000..175bb4f705124a82c023d2abecdf1d309c86fe17 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-cache_disable @@ -0,0 +1,18 @@ +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/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index d9aa43d78bcc9fc92e582a62cadb18cd9b27f4f0..25fb8bcf32a276f280d44aa53a4f2712a14257f4 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -704,12 +704,24 @@ 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/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile index b1eb661e6302a3e5aeae0a58d3cda169f46f66a2..9632444f6c6270b87894e2381f95985ed3126d7a 100644 --- a/Documentation/DocBook/Makefile +++ b/Documentation/DocBook/Makefile @@ -13,7 +13,8 @@ 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 + alsa-driver-api.xml writing-an-alsa-driver.xml \ + tracepoint.xml ### # The build process is as follows (targets): diff --git a/Documentation/DocBook/tracepoint.tmpl b/Documentation/DocBook/tracepoint.tmpl new file mode 100644 index 0000000000000000000000000000000000000000..b0756d0fd57910a44d2f2d29fdb4edf87dac21ca --- /dev/null +++ b/Documentation/DocBook/tracepoint.tmpl @@ -0,0 +1,89 @@ + + + + + + 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/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt index 068848240a8bdf135ba706da5c3d01a43609397a..02cced183b2d63f81428b3d6a21064397c7a7533 100644 --- a/Documentation/RCU/trace.txt +++ b/Documentation/RCU/trace.txt @@ -192,23 +192,24 @@ rcu/rcuhier (which displays the struct rcu_node hierarchy). The output of "cat rcu/rcudata" looks as follows: rcu: - 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: + 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 rcu_bh: - 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 + 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 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. @@ -253,12 +254,6 @@ 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 @@ -305,6 +300,9 @@ 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: @@ -411,3 +409,63 @@ 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/Documentation/Smack.txt b/Documentation/Smack.txt index 629c92e99783ecb7934ee00cf42c4a9f8556004f..34614b4c708eba850acad3ac15f7e59add026f3e 100644 --- a/Documentation/Smack.txt +++ b/Documentation/Smack.txt @@ -184,8 +184,9 @@ 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 or the "/" (slash) character. Smack labels -cannot begin with a '-', which is reserved for special options. +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. There are some predefined labels: @@ -523,3 +524,18 @@ 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/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt index 6fab97ea7e6b0ecd4b3973cd0787257f14647617..8d2158a1c6aaf433e8063650309be1667954f062 100644 --- a/Documentation/block/biodoc.txt +++ b/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/PCI/PCI-DMA-mapping.txt for a discussion +Note: Please refer to Documentation/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/Documentation/filesystems/gfs2-glocks.txt b/Documentation/filesystems/gfs2-glocks.txt index 4dae9a3840bf9953ed5f12be7aae10625d6a5b99..0494f78d87e40c225eb1dc1a1489acd891210761 100644 --- a/Documentation/filesystems/gfs2-glocks.txt +++ b/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/Documentation/filesystems/gfs2.txt b/Documentation/filesystems/gfs2.txt index 593004b6bbabaeee282b1041835f580cf12baa2e..5e3ab8f3beff15f0597368de302f5361fad8b504 100644 --- a/Documentation/filesystems/gfs2.txt +++ b/Documentation/filesystems/gfs2.txt @@ -11,18 +11,15 @@ 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. Different lock -modules can plug into GFS and each file system selects the appropriate -lock module at mount time. Lock modules include: +GFS uses interchangable inter-node locking mechanisms, the currently +supported mechanisms are: 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/ -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 +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 @@ -31,13 +28,19 @@ needed, simply: $ mkfs -t gfs2 -p lock_nolock -j 1 /dev/block_device $ mount -t gfs2 /dev/block_device /dir -GFS2 is not on-disk compatible with previous versions of GFS. +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. The following man pages can be found at the URL above: - gfs2_fsck to repair a filesystem + fsck.gfs2 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/Documentation/futex-requeue-pi.txt b/Documentation/futex-requeue-pi.txt new file mode 100644 index 0000000000000000000000000000000000000000..9dc1ff4fd53692dc88a3da952ecd85715faa11e3 --- /dev/null +++ b/Documentation/futex-requeue-pi.txt @@ -0,0 +1,131 @@ +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/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface index 2f10ce6a879f7276f635cd1ac51c03d8c004d8c1..004ee161721e9b3bd1aa213c174a594174b187c8 100644 --- a/Documentation/hwmon/sysfs-interface +++ b/Documentation/hwmon/sysfs-interface @@ -150,6 +150,11 @@ fan[1-*]_min Fan minimum value Unit: revolution/min (RPM) RW +fan[1-*]_max Fan maximum value + Unit: revolution/min (RPM) + Only rarely supported by the hardware. + RW + fan[1-*]_input Fan input value. Unit: revolution/min (RPM) RO @@ -390,6 +395,7 @@ OR in[0-*]_min_alarm in[0-*]_max_alarm fan[1-*]_min_alarm +fan[1-*]_max_alarm temp[1-*]_min_alarm temp[1-*]_max_alarm temp[1-*]_crit_alarm diff --git a/Documentation/input/multi-touch-protocol.txt b/Documentation/input/multi-touch-protocol.txt index 9f09557aea39c5e80b6b9810ab170fddd32b1c91..a12ea3b586e6e15ecb66322c78bf5d6cb3e03f79 100644 --- a/Documentation/input/multi-touch-protocol.txt +++ b/Documentation/input/multi-touch-protocol.txt @@ -18,8 +18,12 @@ Usage Anonymous finger details are sent sequentially as separate packets of ABS events. Only the ABS_MT events are recognized as part of a finger packet. The end of a packet is marked by calling the input_mt_sync() -function, which generates a SYN_MT_REPORT event. The end of multi-touch -transfer is marked by calling the usual input_sync() function. +function, which generates a SYN_MT_REPORT event. This instructs the +receiver to accept the data for the current finger and prepare to receive +another. The end of a multi-touch transfer is marked by calling the usual +input_sync() function. This instructs the receiver to act upon events +accumulated since last EV_SYN/SYN_REPORT and prepare to receive a new +set of events/packets. A set of ABS_MT events with the desired properties is defined. The events are divided into categories, to allow for partial implementation. The @@ -27,11 +31,26 @@ minimum set consists of ABS_MT_TOUCH_MAJOR, ABS_MT_POSITION_X and ABS_MT_POSITION_Y, which allows for multiple fingers to be tracked. If the device supports it, the ABS_MT_WIDTH_MAJOR may be used to provide the size of the approaching finger. Anisotropy and direction may be specified with -ABS_MT_TOUCH_MINOR, ABS_MT_WIDTH_MINOR and ABS_MT_ORIENTATION. Devices with -more granular information may specify general shapes as blobs, i.e., as a -sequence of rectangular shapes grouped together by an -ABS_MT_BLOB_ID. Finally, the ABS_MT_TOOL_TYPE may be used to specify -whether the touching tool is a finger or a pen or something else. +ABS_MT_TOUCH_MINOR, ABS_MT_WIDTH_MINOR and ABS_MT_ORIENTATION. The +ABS_MT_TOOL_TYPE may be used to specify whether the touching tool is a +finger or a pen or something else. Devices with more granular information +may specify general shapes as blobs, i.e., as a sequence of rectangular +shapes grouped together by an ABS_MT_BLOB_ID. Finally, for the few devices +that currently support it, the ABS_MT_TRACKING_ID event may be used to +report finger tracking from hardware [5]. + +Here is what a minimal event sequence for a two-finger touch would look +like: + + ABS_MT_TOUCH_MAJOR + ABS_MT_POSITION_X + ABS_MT_POSITION_Y + SYN_MT_REPORT + ABS_MT_TOUCH_MAJOR + ABS_MT_POSITION_X + ABS_MT_POSITION_Y + SYN_MT_REPORT + SYN_REPORT Event Semantics @@ -44,24 +63,24 @@ ABS_MT_TOUCH_MAJOR The length of the major axis of the contact. The length should be given in surface units. If the surface has an X times Y resolution, the largest -possible value of ABS_MT_TOUCH_MAJOR is sqrt(X^2 + Y^2), the diagonal. +possible value of ABS_MT_TOUCH_MAJOR is sqrt(X^2 + Y^2), the diagonal [4]. ABS_MT_TOUCH_MINOR The length, in surface units, of the minor axis of the contact. If the -contact is circular, this event can be omitted. +contact is circular, this event can be omitted [4]. ABS_MT_WIDTH_MAJOR The length, in surface units, of the major axis of the approaching tool. This should be understood as the size of the tool itself. The orientation of the contact and the approaching tool are assumed to be the -same. +same [4]. ABS_MT_WIDTH_MINOR The length, in surface units, of the minor axis of the approaching -tool. Omit if circular. +tool. Omit if circular [4]. The above four values can be used to derive additional information about the contact. The ratio ABS_MT_TOUCH_MAJOR / ABS_MT_WIDTH_MAJOR approximates @@ -70,14 +89,17 @@ different characteristic widths [1]. ABS_MT_ORIENTATION -The orientation of the ellipse. The value should describe half a revolution -clockwise around the touch center. The scale of the value is arbitrary, but -zero should be returned for an ellipse aligned along the Y axis of the -surface. As an example, an index finger placed straight onto the axis could -return zero orientation, something negative when twisted to the left, and -something positive when twisted to the right. This value can be omitted if -the touching object is circular, or if the information is not available in -the kernel driver. +The orientation of the ellipse. The value should describe a signed quarter +of a revolution clockwise around the touch center. The signed value range +is arbitrary, but zero should be returned for a finger aligned along the Y +axis of the surface, a negative value when finger is turned to the left, and +a positive value when finger turned to the right. When completely aligned with +the X axis, the range max should be returned. Orientation can be omitted +if the touching object is circular, or if the information is not available +in the kernel driver. Partial orientation support is possible if the device +can distinguish between the two axis, but not (uniquely) any values in +between. In such cases, the range of ABS_MT_ORIENTATION should be [0, 1] +[4]. ABS_MT_POSITION_X @@ -98,8 +120,35 @@ ABS_MT_BLOB_ID The BLOB_ID groups several packets together into one arbitrarily shaped contact. This is a low-level anonymous grouping, and should not be confused -with the high-level contactID, explained below. Most kernel drivers will -not have this capability, and can safely omit the event. +with the high-level trackingID [5]. Most kernel drivers will not have blob +capability, and can safely omit the event. + +ABS_MT_TRACKING_ID + +The TRACKING_ID identifies an initiated contact throughout its life cycle +[5]. There are currently only a few devices that support it, so this event +should normally be omitted. + + +Event Computation +----------------- + +The flora of different hardware unavoidably leads to some devices fitting +better to the MT protocol than others. To simplify and unify the mapping, +this section gives recipes for how to compute certain events. + +For devices reporting contacts as rectangular shapes, signed orientation +cannot be obtained. Assuming X and Y are the lengths of the sides of the +touching rectangle, here is a simple formula that retains the most +information possible: + + ABS_MT_TOUCH_MAJOR := max(X, Y) + ABS_MT_TOUCH_MINOR := min(X, Y) + ABS_MT_ORIENTATION := bool(X > Y) + +The range of ABS_MT_ORIENTATION should be set to [0, 1], to indicate that +the device can distinguish between a finger along the Y axis (0) and a +finger along the X axis (1). Finger Tracking @@ -109,14 +158,18 @@ The kernel driver should generate an arbitrary enumeration of the set of anonymous contacts currently on the surface. The order in which the packets appear in the event stream is not important. -The process of finger tracking, i.e., to assign a unique contactID to each +The process of finger tracking, i.e., to assign a unique trackingID to each initiated contact on the surface, is left to user space; preferably the -multi-touch X driver [3]. In that driver, the contactID stays the same and +multi-touch X driver [3]. In that driver, the trackingID stays the same and unique until the contact vanishes (when the finger leaves the surface). The problem of assigning a set of anonymous fingers to a set of identified fingers is a euclidian bipartite matching problem at each event update, and relies on a sufficiently rapid update rate. +There are a few devices that support trackingID in hardware. User space can +make use of these native identifiers to reduce bandwidth and cpu usage. + + Notes ----- @@ -136,5 +189,7 @@ could be used to derive tilt. time of writing (April 2009), the MT protocol is not yet merged, and the prototype implements finger matching, basic mouse support and two-finger scrolling. The project aims at improving the quality of current multi-touch -functionality available in the synaptics X driver, and in addition +functionality available in the Synaptics X driver, and in addition implement more advanced gestures. +[4] See the section on event computation. +[5] See the section on finger tracking. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 779160afa351b67003fd49993514c215167fddad..f93c6336e6891a5b048eb787364e8150f326ebb5 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -56,7 +56,6 @@ 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. @@ -329,11 +328,6 @@ 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: , @@ -653,6 +647,13 @@ 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] @@ -759,12 +760,25 @@ 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] 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. gamecon.map[2|3]= [HW,JOY] Multisystem joystick and NES/SNES/PSX pad @@ -921,6 +935,12 @@ 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. @@ -1061,15 +1081,6 @@ 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) @@ -1079,6 +1090,10 @@ and is between 256 and 4096 characters. It is defined in the file Configure the RouterBoard 532 series on-chip Ethernet adapter MAC address. + kmemleak= [KNL] Boot-time kmemleak enable/disable + Valid arguments: on, off + Default: on + kstack=N [X86] Print N words from the kernel stack in oops dumps. @@ -1582,6 +1597,9 @@ 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. @@ -1667,6 +1685,14 @@ 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/Documentation/kmemleak.txt b/Documentation/kmemleak.txt new file mode 100644 index 0000000000000000000000000000000000000000..0112da3b9ab87f731006993c76e1a7fdc4eddcaa --- /dev/null +++ b/Documentation/kmemleak.txt @@ -0,0 +1,142 @@ +Kernel Memory Leak Detector +=========================== + +Introduction +------------ + +Kmemleak provides a way of detecting possible kernel memory leaks in a +way similar to a tracing garbage collector +(http://en.wikipedia.org/wiki/Garbage_collection_%28computer_science%29#Tracing_garbage_collectors), +with the difference that the orphan objects are not freed but only +reported via /sys/kernel/debug/kmemleak. A similar method is used by the +Valgrind tool (memcheck --leak-check) to detect the memory leaks in +user-space applications. + +Usage +----- + +CONFIG_DEBUG_KMEMLEAK in "Kernel hacking" has to be enabled. A kernel +thread scans the memory every 10 minutes (by default) and prints any new +unreferenced objects found. To trigger an intermediate scan and display +all the possible memory leaks: + + # mount -t debugfs nodev /sys/kernel/debug/ + # cat /sys/kernel/debug/kmemleak + +Note that the orphan objects are listed in the order they were allocated +and one object at the beginning of the list may cause other subsequent +objects to be reported as orphan. + +Memory scanning parameters can be modified at run-time by writing to the +/sys/kernel/debug/kmemleak file. The following parameters are supported: + + off - disable kmemleak (irreversible) + stack=on - enable the task stacks scanning + stack=off - disable the tasks stacks scanning + scan=on - start the automatic memory scanning thread + scan=off - stop the automatic memory scanning thread + scan= - set the automatic memory scanning period in seconds (0 + to disable it) + +Kmemleak can also be disabled at boot-time by passing "kmemleak=off" on +the kernel command line. + +Basic Algorithm +--------------- + +The memory allocations via kmalloc, vmalloc, kmem_cache_alloc and +friends are traced and the pointers, together with additional +information like size and stack trace, are stored in a prio search tree. +The corresponding freeing function calls are tracked and the pointers +removed from the kmemleak data structures. + +An allocated block of memory is considered orphan if no pointer to its +start address or to any location inside the block can be found by +scanning the memory (including saved registers). This means that there +might be no way for the kernel to pass the address of the allocated +block to a freeing function and therefore the block is considered a +memory leak. + +The scanning algorithm steps: + + 1. mark all objects as white (remaining white objects will later be + considered orphan) + 2. scan the memory starting with the data section and stacks, checking + the values against the addresses stored in the prio search tree. If + a pointer to a white object is found, the object is added to the + gray list + 3. scan the gray objects for matching addresses (some white objects + can become gray and added at the end of the gray list) until the + gray set is finished + 4. the remaining white objects are considered orphan and reported via + /sys/kernel/debug/kmemleak + +Some allocated memory blocks have pointers stored in the kernel's +internal data structures and they cannot be detected as orphans. To +avoid this, kmemleak can also store the number of values pointing to an +address inside the block address range that need to be found so that the +block is not considered a leak. One example is __vmalloc(). + +Kmemleak API +------------ + +See the include/linux/kmemleak.h header for the functions prototype. + +kmemleak_init - initialize kmemleak +kmemleak_alloc - notify of a memory block allocation +kmemleak_free - notify of a memory block freeing +kmemleak_not_leak - mark an object as not a leak +kmemleak_ignore - do not scan or report an object as leak +kmemleak_scan_area - add scan areas inside a memory block +kmemleak_no_scan - do not scan a memory block +kmemleak_erase - erase an old value in a pointer variable +kmemleak_alloc_recursive - as kmemleak_alloc but checks the recursiveness +kmemleak_free_recursive - as kmemleak_free but checks the recursiveness + +Dealing with false positives/negatives +-------------------------------------- + +The false negatives are real memory leaks (orphan objects) but not +reported by kmemleak because values found during the memory scanning +point to such objects. To reduce the number of false negatives, kmemleak +provides the kmemleak_ignore, kmemleak_scan_area, kmemleak_no_scan and +kmemleak_erase functions (see above). The task stacks also increase the +amount of false negatives and their scanning is not enabled by default. + +The false positives are objects wrongly reported as being memory leaks +(orphan). For objects known not to be leaks, kmemleak provides the +kmemleak_not_leak function. The kmemleak_ignore could also be used if +the memory block is known not to contain other pointers and it will no +longer be scanned. + +Some of the reported leaks are only transient, especially on SMP +systems, because of pointers temporarily stored in CPU registers or +stacks. Kmemleak defines MSECS_MIN_AGE (defaulting to 1000) representing +the minimum age of an object to be reported as a memory leak. + +Limitations and Drawbacks +------------------------- + +The main drawback is the reduced performance of memory allocation and +freeing. To avoid other penalties, the memory scanning is only performed +when the /sys/kernel/debug/kmemleak file is read. Anyway, this tool is +intended for debugging purposes where the performance might not be the +most important requirement. + +To keep the algorithm simple, kmemleak scans for values pointing to any +address inside a block's address range. This may lead to an increased +number of false negatives. However, it is likely that a real memory leak +will eventually become visible. + +Another source of false negatives is the data stored in non-pointer +values. In a future version, kmemleak could only scan the pointer +members in the allocated structures. This feature would solve many of +the false negative cases described above. + +The tool can report false positives. These are cases where an allocated +block doesn't need to be freed (some cases in the init_call functions), +the pointer is calculated by other methods than the usual container_of +macro or the pointer is stored in a location not scanned by kmemleak. + +Page allocations and ioremap are not tracked. Only the ARM and x86 +architectures are currently supported. diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index f5b7127f54acb6af1d9f997a40e099b60c0b7571..7f5809eddee62eaf524103eeda485f5e553d5a01 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -31,6 +31,7 @@ Contents: - Locking functions. - Interrupt disabling functions. + - Sleep and wake-up functions. - Miscellaneous functions. (*) Inter-CPU locking barrier effects. @@ -1217,6 +1218,132 @@ 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 ----------------------- @@ -1366,7 +1493,7 @@ 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, three +work correctly, even if it's in an SMP kernel. There are, however, four circumstances in which reordering definitely _could_ be a problem: (*) Interprocessor interaction. diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt index 5ba4d3fc625a424b341bfa5b5853473eaf80fe6a..1df7f9cdab0576227671703c6fec1fc780ec596b 100644 --- a/Documentation/scheduler/sched-rt-group.txt +++ b/Documentation/scheduler/sched-rt-group.txt @@ -4,6 +4,7 @@ CONTENTS ======== +0. WARNING 1. Overview 1.1 The problem 1.2 The solution @@ -14,6 +15,23 @@ 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 =========== @@ -169,7 +187,7 @@ 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 0-139. With deadline scheduling you need to +the limited static priority levels 0-99. With deadline scheduling you need to do deadline inheritance (since priority is inversely proportional to the deadline delta (deadline - now). diff --git a/Documentation/sound/alsa/Procfile.txt b/Documentation/sound/alsa/Procfile.txt index bba2dbb79d81c10d71bbc5b0879f6d3745d1543d..cfac20cf9e33fa150a6cf69f4e6d624e8116caa9 100644 --- a/Documentation/sound/alsa/Procfile.txt +++ b/Documentation/sound/alsa/Procfile.txt @@ -104,6 +104,11 @@ card*/pcm*/xrun_debug When this value is greater than 1, the driver will show the stack trace additionally. This may help the debugging. + Since 2.6.30, this option also enables the hwptr check using + jiffies. This detects spontaneous invalid pointer callback + values, but can be lead to too much corrections for a (mostly + buggy) hardware that doesn't give smooth pointer updates. + card*/pcm*/sub*/info The general information of this PCM sub-stream. diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index f11ca7979fa67b5bbf08339cf473d110ecf92f7d..322a00bb99d97f703130de7f349f2dbc9b6fa24e 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -32,6 +32,7 @@ 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 @@ -184,6 +185,16 @@ 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/Documentation/trace/events.txt b/Documentation/trace/events.txt new file mode 100644 index 0000000000000000000000000000000000000000..f157d7594ea7c2bdf991b25f84b5580acec505e3 --- /dev/null +++ b/Documentation/trace/events.txt @@ -0,0 +1,90 @@ + 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/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index fd9a3e69381351aeeaa6712d07c5170aa7dca1a4..2a82d8602944abca930635cff44f37c52238529d 100644 --- a/Documentation/trace/ftrace.txt +++ b/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_tracer" + "function_graph" Similar to the function tracer except that the function tracer probes the functions on their entry @@ -518,9 +518,18 @@ 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 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 + 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 + --------------------------------------------------------------- The task states are: diff --git a/Documentation/trace/power.txt b/Documentation/trace/power.txt new file mode 100644 index 0000000000000000000000000000000000000000..cd805e16dc2712d1058e0170fd6872efa5b3e340 --- /dev/null +++ b/Documentation/trace/power.txt @@ -0,0 +1,17 @@ +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/Documentation/x86/boot.txt b/Documentation/x86/boot.txt index e0203662f9e9f8a1a907060437f3fcdf907e2667..8da3a795083fec448cb7e13831b0c10180ff0b6e 100644 --- a/Documentation/x86/boot.txt +++ b/Documentation/x86/boot.txt @@ -50,6 +50,10 @@ 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 @@ -168,12 +172,13 @@ 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 -0226/2 N/A pad1 Unused +0226/1 2.02+(3 ext_loader_ver Extended boot loader version +0227/1 2.02+(3 ext_loader_type Extended boot loader ID 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 N/A pad2 Unused +0235/1 2.10+ min_alignment Minimum alignment, as a power of two 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 @@ -182,6 +187,8 @@ 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. @@ -190,6 +197,8 @@ 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: @@ -343,18 +352,32 @@ 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 + 3 Syslinux + 4 Etherboot/gPXE 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. @@ -453,6 +476,35 @@ 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 @@ -482,11 +534,19 @@ Protocol: 2.03+ 0x37FFFFFF, you can start your ramdisk at 0x37FE0000.) Field name: kernel_alignment -Type: read (reloc) +Type: read/modify (reloc) Offset/size: 0x230/4 -Protocol: 2.05+ +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. - Alignment unit required by the kernel (if relocatable_kernel is true.) + 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. Field name: relocatable_kernel Type: read (reloc) @@ -498,6 +558,22 @@ 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 @@ -582,6 +658,36 @@ 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/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt index 34c13040a718f6febbccadc1f32bc24f4a060664..2db5893d6c97234ded88dbc8b52daaa8defc3af4 100644 --- a/Documentation/x86/x86_64/boot-options.txt +++ b/Documentation/x86/x86_64/boot-options.txt @@ -150,11 +150,6 @@ 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/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt index 29b52b14d0b43950fa79f3948b1fbe4789396fbf..d6498e3cd7133c7d88279c26d8618aa5fc3d10ad 100644 --- a/Documentation/x86/x86_64/mm.txt +++ b/Documentation/x86/x86_64/mm.txt @@ -6,10 +6,11 @@ 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 - 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) +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) ... unused hole ... ffffffff80000000 - ffffffffa0000000 (=512 MB) kernel text mapping, from phys 0 ffffffffa0000000 - fffffffffff00000 (=1536 MB) module mapping space diff --git a/MAINTAINERS b/MAINTAINERS index 5ee166e27b9fcae30c166023c297a7d6a4d3b74b..c944d618dc83d1a45c63b038e8f12429dde38a8c 100644 --- a/MAINTAINERS +++ b/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. +T: SCM tree type and location. Type is one of: git, hg, quilt, stgit. S: Status, one of the following: Supported: Someone is actually paid to look after this. @@ -159,7 +159,8 @@ F: drivers/net/r8169.c 8250/16?50 (AND CLONE UARTS) SERIAL DRIVER L: linux-serial@vger.kernel.org W: http://serial.sourceforge.net -S: Orphan +M: alan@lxorguk.ukuu.org.uk +S: Odd Fixes F: drivers/serial/8250* F: include/linux/serial_8250.h @@ -434,7 +435,7 @@ F: arch/alpha/ AMD GEODE CS5536 USB DEVICE CONTROLLER DRIVER P: Thomas Dahlmann -M: thomas.dahlmann@amd.com +M: dahlmann.thomas@arcor.de L: linux-geode@lists.infradead.org (moderated for non-subscribers) S: Supported F: drivers/usb/gadget/amd5536udc.* @@ -624,6 +625,7 @@ M: paulius.zaleckas@teltonika.lt L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only) T: git git://gitorious.org/linux-gemini/mainline.git S: Maintained +F: arch/arm/mach-gemini/ ARM/EBSA110 MACHINE SUPPORT P: Russell King @@ -650,6 +652,7 @@ P: Paulius Zaleckas M: paulius.zaleckas@teltonika.lt L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only) S: Maintained +F: arch/arm/mm/*-fa* ARM/FOOTBRIDGE ARCHITECTURE P: Russell King @@ -1540,6 +1543,13 @@ W: http://www.fi.muni.cz/~kas/cosa/ S: Maintained F: drivers/net/wan/cosa* +CPMAC ETHERNET DRIVER +P: Florian Fainelli +M: florian@openwrt.org +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/cpmac.c + CPU FREQUENCY DRIVERS P: Dave Jones M: davej@redhat.com @@ -1792,10 +1802,10 @@ F: drivers/char/epca* F: drivers/char/digi* DIRECTORY NOTIFICATION (DNOTIFY) -P: Stephen Rothwell -M: sfr@canb.auug.org.au +P: Eric Paris +M: eparis@parisplace.org L: linux-kernel@vger.kernel.org -S: Supported +S: Maintained F: Documentation/filesystems/dnotify.txt F: fs/notify/dnotify/ F: include/linux/dnotify.h @@ -1969,10 +1979,20 @@ 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 -P: Doug Thompson M: mark.gross@intel.com +P: Doug Thompson M: dougthompson@xmission.com L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers) W: bluesmoke.sourceforge.net @@ -2249,7 +2269,7 @@ P: Li Yang M: leoli@freescale.com P: Zhang Wei M: zw@zh-kernel.org -L: linuxppc-embedded@ozlabs.org +L: linuxppc-dev@ozlabs.org L: linux-kernel@vger.kernel.org S: Maintained F: drivers/dma/fsldma.* @@ -2838,6 +2858,8 @@ P: John McCutchan M: john@johnmccutchan.com P: Robert Love M: rlove@rlove.org +P: Eric Paris +M: eparis@parisplace.org L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/filesystems/inotify.txt @@ -3350,6 +3372,12 @@ F: Documentation/trace/kmemtrace.txt F: include/trace/kmemtrace.h F: kernel/trace/kmemtrace.c +KMEMLEAK +P: Catalin Marinas +M: catalin.marinas@arm.com +L: linux-kernel@vger.kernel.org +S: Maintained + KPROBES P: Ananth N Mavinakayanahalli M: ananth@in.ibm.com @@ -4383,6 +4411,16 @@ S: Maintained F: include/linux/delayacct.h F: kernel/delayacct.c +PERFORMANCE COUNTER SUBSYSTEM +P: Peter Zijlstra +M: a.p.zijlstra@chello.nl +P: Paul Mackerras +M: paulus@samba.org +P: Ingo Molnar +M: mingo@elte.hu +L: linux-kernel@vger.kernel.org +S: Supported + PERSONALITY HANDLING P: Christoph Hellwig M: hch@infradead.org @@ -5620,6 +5658,7 @@ 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/Makefile b/Makefile index 739fd34a72a2422f14937ccd084f77d52edc0fc1..03373bb703ca9cd4d8cde6403502357815b7e531 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 30 -EXTRAVERSION = -rc7 +EXTRAVERSION = NAME = Man-Eating Seals of Antiquity # *DOCUMENTATION* @@ -533,7 +533,7 @@ endif include $(srctree)/arch/$(SRCARCH)/Makefile -ifneq (CONFIG_FRAME_WARN,0) +ifneq ($(CONFIG_FRAME_WARN),0) KBUILD_CFLAGS += $(call cc-option,-Wframe-larger-than=${CONFIG_FRAME_WARN}) endif diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 42ee05981e7173d39ac6e047dabce5b46075669b..9a3334ae282e38345d177e060acc2021fdeda084 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -371,8 +371,6 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, char __user *, path, int retval = -EINVAL; char *name; - lock_kernel(); - name = getname(path); retval = PTR_ERR(name); if (IS_ERR(name)) @@ -392,7 +390,6 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, char __user *, path, } putname(name); out: - unlock_kernel(); return retval; } diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c index 9c9d1fd4155fc5e736c98d89e68d034cd8f2b9ef..5bd5259324b7c8827adb237facd7bf120edd4ca2 100644 --- a/arch/alpha/kernel/sys_dp264.c +++ b/arch/alpha/kernel/sys_dp264.c @@ -176,22 +176,26 @@ cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity) } } -static void +static int 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 void +static int 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/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c index 27f840a4ad3d7ec0949ac92a55ef5c7c1a3b9280..8dd239ebdb9e2cc3489c3d128402a9da37033a29 100644 --- a/arch/alpha/kernel/sys_titan.c +++ b/arch/alpha/kernel/sys_titan.c @@ -157,13 +157,15 @@ titan_cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity) } -static void +static int 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/arch/arm/common/gic.c b/arch/arm/common/gic.c index 3e1714c6523f06f4ab0572886edba151f21ffb8c..664c7b8b1ba87d7d5268c661808636a27b4f610c 100644 --- a/arch/arm/common/gic.c +++ b/arch/arm/common/gic.c @@ -109,7 +109,7 @@ static void gic_unmask_irq(unsigned int irq) } #ifdef CONFIG_SMP -static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val) +static int 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; @@ -122,6 +122,8 @@ static void 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/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 6116e4893c0ade4bc478996a82c316ce5c99a64e..15f8a092b700acc82754f9f9011524b068cb0db8 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -114,3 +114,16 @@ .align 3; \ .long 9999b,9001f; \ .previous + +/* + * SMP data memory barrier + */ + .macro smp_dmb +#ifdef CONFIG_SMP +#if __LINUX_ARM_ARCH__ >= 7 + dmb +#elif __LINUX_ARM_ARCH__ == 6 + mcr p15, 0, r0, c7, c10, 5 @ dmb +#endif +#endif + .endm diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index ee99723b3a6c4899283a76ba26c7140c08a146dd..16b52f397983f7ead8079769a772265cab71657f 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -44,11 +44,29 @@ static inline void atomic_set(atomic_t *v, int i) : "cc"); } +static inline void atomic_add(int i, atomic_t *v) +{ + unsigned long tmp; + int result; + + __asm__ __volatile__("@ atomic_add\n" +"1: ldrex %0, [%2]\n" +" add %0, %0, %3\n" +" strex %1, %0, [%2]\n" +" teq %1, #0\n" +" bne 1b" + : "=&r" (result), "=&r" (tmp) + : "r" (&v->counter), "Ir" (i) + : "cc"); +} + static inline int atomic_add_return(int i, atomic_t *v) { unsigned long tmp; int result; + smp_mb(); + __asm__ __volatile__("@ atomic_add_return\n" "1: ldrex %0, [%2]\n" " add %0, %0, %3\n" @@ -59,14 +77,34 @@ static inline int atomic_add_return(int i, atomic_t *v) : "r" (&v->counter), "Ir" (i) : "cc"); + smp_mb(); + return result; } +static inline void atomic_sub(int i, atomic_t *v) +{ + unsigned long tmp; + int result; + + __asm__ __volatile__("@ atomic_sub\n" +"1: ldrex %0, [%2]\n" +" sub %0, %0, %3\n" +" strex %1, %0, [%2]\n" +" teq %1, #0\n" +" bne 1b" + : "=&r" (result), "=&r" (tmp) + : "r" (&v->counter), "Ir" (i) + : "cc"); +} + static inline int atomic_sub_return(int i, atomic_t *v) { unsigned long tmp; int result; + smp_mb(); + __asm__ __volatile__("@ atomic_sub_return\n" "1: ldrex %0, [%2]\n" " sub %0, %0, %3\n" @@ -77,6 +115,8 @@ static inline int atomic_sub_return(int i, atomic_t *v) : "r" (&v->counter), "Ir" (i) : "cc"); + smp_mb(); + return result; } @@ -84,6 +124,8 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new) { unsigned long oldval, res; + smp_mb(); + do { __asm__ __volatile__("@ atomic_cmpxchg\n" "ldrex %1, [%2]\n" @@ -95,6 +137,8 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new) : "cc"); } while (res); + smp_mb(); + return oldval; } @@ -135,6 +179,7 @@ static inline int atomic_add_return(int i, atomic_t *v) return val; } +#define atomic_add(i, v) (void) atomic_add_return(i, v) static inline int atomic_sub_return(int i, atomic_t *v) { @@ -148,6 +193,7 @@ static inline int atomic_sub_return(int i, atomic_t *v) return val; } +#define atomic_sub(i, v) (void) atomic_sub_return(i, v) static inline int atomic_cmpxchg(atomic_t *v, int old, int new) { @@ -187,10 +233,8 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) } #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) -#define atomic_add(i, v) (void) atomic_add_return(i, v) -#define atomic_inc(v) (void) atomic_add_return(1, v) -#define atomic_sub(i, v) (void) atomic_sub_return(i, v) -#define atomic_dec(v) (void) atomic_sub_return(1, v) +#define atomic_inc(v) atomic_add(1, v) +#define atomic_dec(v) atomic_sub(1, v) #define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0) #define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0) @@ -200,11 +244,10 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) #define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0) -/* Atomic operations are already serializing on ARM */ -#define smp_mb__before_atomic_dec() barrier() -#define smp_mb__after_atomic_dec() barrier() -#define smp_mb__before_atomic_inc() barrier() -#define smp_mb__after_atomic_inc() barrier() +#define smp_mb__before_atomic_dec() smp_mb() +#define smp_mb__after_atomic_dec() smp_mb() +#define smp_mb__before_atomic_inc() smp_mb() +#define smp_mb__after_atomic_inc() smp_mb() #include #endif diff --git a/arch/arm/include/asm/cache.h b/arch/arm/include/asm/cache.h index cb7a9e97fd7ef7807161f509e0260a6fa94233cc..feaa75f0013eafcfcf5323954ade694bc40e343f 100644 --- a/arch/arm/include/asm/cache.h +++ b/arch/arm/include/asm/cache.h @@ -7,4 +7,20 @@ #define L1_CACHE_SHIFT 5 #define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) +/* + * Memory returned by kmalloc() may be used for DMA, so we must make + * sure that all such allocations are cache aligned. Otherwise, + * unrelated code may cause parts of the buffer to be read into the + * cache before the transfer is done, causing old data to be seen by + * the CPU. + */ +#define ARCH_KMALLOC_MINALIGN L1_CACHE_BYTES + +/* + * With EABI on ARMv5 and above we must have 64-bit aligned slab pointers. + */ +#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5) +#define ARCH_SLAB_MINALIGN 8 +#endif + #endif diff --git a/arch/arm/include/asm/flat.h b/arch/arm/include/asm/flat.h index 1d77e51907f6ddb70f5aa8123583827bffaa676c..59426a4595c9cb90bcb765843f89295bd20f6797 100644 --- a/arch/arm/include/asm/flat.h +++ b/arch/arm/include/asm/flat.h @@ -5,9 +5,6 @@ #ifndef __ARM_FLAT_H__ #define __ARM_FLAT_H__ -/* An odd number of words will be pushed after this alignment, so - deliberately misalign the value. */ -#define flat_stack_align(sp) sp = (void *)(((unsigned long)(sp) - 4) | 4) #define flat_argvp_envp_on_stack() 1 #define flat_old_ram_flag(flags) (flags) #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h index e6eb8a67b8071a49153e8f7daa03e733e8c710cf..7b522770f29dc6e967f3c719817925ebf753c6e1 100644 --- a/arch/arm/include/asm/page.h +++ b/arch/arm/include/asm/page.h @@ -202,13 +202,6 @@ typedef struct page *pgtable_t; (((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \ VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -/* - * With EABI on ARMv5 and above we must have 64-bit aligned slab pointers. - */ -#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5) -#define ARCH_SLAB_MINALIGN 8 -#endif - #include #endif diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h index bd4dc8ed53d59ebbfb1ac4d6fa547a93874278f7..d65b2f5bf41f60cfd21163ef0e5b92e76bc58db8 100644 --- a/arch/arm/include/asm/system.h +++ b/arch/arm/include/asm/system.h @@ -248,6 +248,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size unsigned int tmp; #endif + smp_mb(); + switch (size) { #if __LINUX_ARM_ARCH__ >= 6 case 1: @@ -307,6 +309,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size __bad_xchg(ptr, size), ret = 0; break; } + smp_mb(); return ret; } @@ -316,6 +319,12 @@ extern void enable_hlt(void); #include +#if __LINUX_ARM_ARCH__ < 6 + +#ifdef CONFIG_SMP +#error "SMP is not supported on this platform" +#endif + /* * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make * them available. @@ -329,6 +338,173 @@ extern void enable_hlt(void); #include #endif +#else /* __LINUX_ARM_ARCH__ >= 6 */ + +extern void __bad_cmpxchg(volatile void *ptr, int size); + +/* + * cmpxchg only support 32-bits operands on ARMv6. + */ + +static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, + unsigned long new, int size) +{ + unsigned long oldval, res; + + switch (size) { +#ifdef CONFIG_CPU_32v6K + case 1: + do { + asm volatile("@ __cmpxchg1\n" + " ldrexb %1, [%2]\n" + " mov %0, #0\n" + " teq %1, %3\n" + " strexbeq %0, %4, [%2]\n" + : "=&r" (res), "=&r" (oldval) + : "r" (ptr), "Ir" (old), "r" (new) + : "memory", "cc"); + } while (res); + break; + case 2: + do { + asm volatile("@ __cmpxchg1\n" + " ldrexh %1, [%2]\n" + " mov %0, #0\n" + " teq %1, %3\n" + " strexheq %0, %4, [%2]\n" + : "=&r" (res), "=&r" (oldval) + : "r" (ptr), "Ir" (old), "r" (new) + : "memory", "cc"); + } while (res); + break; +#endif /* CONFIG_CPU_32v6K */ + case 4: + do { + asm volatile("@ __cmpxchg4\n" + " ldrex %1, [%2]\n" + " mov %0, #0\n" + " teq %1, %3\n" + " strexeq %0, %4, [%2]\n" + : "=&r" (res), "=&r" (oldval) + : "r" (ptr), "Ir" (old), "r" (new) + : "memory", "cc"); + } while (res); + break; + default: + __bad_cmpxchg(ptr, size); + oldval = 0; + } + + return oldval; +} + +static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old, + unsigned long new, int size) +{ + unsigned long ret; + + smp_mb(); + ret = __cmpxchg(ptr, old, new, size); + smp_mb(); + + return ret; +} + +#define cmpxchg(ptr,o,n) \ + ((__typeof__(*(ptr)))__cmpxchg_mb((ptr), \ + (unsigned long)(o), \ + (unsigned long)(n), \ + sizeof(*(ptr)))) + +static inline unsigned long __cmpxchg_local(volatile void *ptr, + unsigned long old, + unsigned long new, int size) +{ + unsigned long ret; + + switch (size) { +#ifndef CONFIG_CPU_32v6K + case 1: + case 2: + ret = __cmpxchg_local_generic(ptr, old, new, size); + break; +#endif /* !CONFIG_CPU_32v6K */ + default: + ret = __cmpxchg(ptr, old, new, size); + } + + return ret; +} + +#define cmpxchg_local(ptr,o,n) \ + ((__typeof__(*(ptr)))__cmpxchg_local((ptr), \ + (unsigned long)(o), \ + (unsigned long)(n), \ + sizeof(*(ptr)))) + +#ifdef CONFIG_CPU_32v6K + +/* + * Note : ARMv7-M (currently unsupported by Linux) does not support + * ldrexd/strexd. If ARMv7-M is ever supported by the Linux kernel, it should + * not be allowed to use __cmpxchg64. + */ +static inline unsigned long long __cmpxchg64(volatile void *ptr, + unsigned long long old, + unsigned long long new) +{ + register unsigned long long oldval asm("r0"); + register unsigned long long __old asm("r2") = old; + register unsigned long long __new asm("r4") = new; + unsigned long res; + + do { + asm volatile( + " @ __cmpxchg8\n" + " ldrexd %1, %H1, [%2]\n" + " mov %0, #0\n" + " teq %1, %3\n" + " teqeq %H1, %H3\n" + " strexdeq %0, %4, %H4, [%2]\n" + : "=&r" (res), "=&r" (oldval) + : "r" (ptr), "Ir" (__old), "r" (__new) + : "memory", "cc"); + } while (res); + + return oldval; +} + +static inline unsigned long long __cmpxchg64_mb(volatile void *ptr, + unsigned long long old, + unsigned long long new) +{ + unsigned long long ret; + + smp_mb(); + ret = __cmpxchg64(ptr, old, new); + smp_mb(); + + return ret; +} + +#define cmpxchg64(ptr,o,n) \ + ((__typeof__(*(ptr)))__cmpxchg64_mb((ptr), \ + (unsigned long long)(o), \ + (unsigned long long)(n))) + +#define cmpxchg64_local(ptr,o,n) \ + ((__typeof__(*(ptr)))__cmpxchg64((ptr), \ + (unsigned long long)(o), \ + (unsigned long long)(n))) + +#else /* !CONFIG_CPU_32v6K */ + +#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n)) + +#endif /* CONFIG_CPU_32v6K */ + +#endif /* __LINUX_ARM_ARCH__ >= 6 */ + #endif /* __ASSEMBLY__ */ #define arch_align_stack(x) (x) diff --git a/arch/arm/kernel/elf.c b/arch/arm/kernel/elf.c index d4a0da1e48f40988bb7f92ce34664d86adb74a32..950391f194c4a9198927b4977fa49d52e08c80de 100644 --- a/arch/arm/kernel/elf.c +++ b/arch/arm/kernel/elf.c @@ -78,6 +78,15 @@ int arm_elf_read_implies_exec(const struct elf32_hdr *x, int executable_stack) return 1; if (cpu_architecture() < CPU_ARCH_ARMv6) return 1; +#if !defined(CONFIG_AEABI) || defined(CONFIG_OABI_COMPAT) + /* + * If we have support for OABI programs, we can never allow NX + * support - our signal syscall restart mechanism relies upon + * being able to execute code placed on the user stack. + */ + return 1; +#else return 0; +#endif } EXPORT_SYMBOL(arm_elf_read_implies_exec); diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index d662a2f1fd85e20ec7fc1af48461689f86fe6745..83b1da6b7baaa44cbfd220876503b9d755c1acd3 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -815,10 +815,7 @@ __kuser_helper_start: */ __kuser_memory_barrier: @ 0xffff0fa0 - -#if __LINUX_ARM_ARCH__ >= 6 && defined(CONFIG_SMP) - mcr p15, 0, r0, c7, c10, 5 @ dmb -#endif + smp_dmb usr_ret lr .align 5 diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h index 2e787d40d59992c96bb6d546c2d31cc7a485c251..c7f2627385e719749a08241fcd0732e0d4e15996 100644 --- a/arch/arm/lib/bitops.h +++ b/arch/arm/lib/bitops.h @@ -18,12 +18,14 @@ mov r2, #1 add r1, r1, r0, lsr #3 @ Get byte offset mov r3, r2, lsl r3 @ create mask + smp_dmb 1: ldrexb r2, [r1] ands r0, r2, r3 @ save old value of bit \instr r2, r2, r3 @ toggle bit strexb ip, r2, [r1] cmp ip, #0 bne 1b + smp_dmb cmp r0, #0 movne r0, #1 2: mov pc, lr diff --git a/arch/arm/mach-gemini/include/mach/hardware.h b/arch/arm/mach-gemini/include/mach/hardware.h index de6752674c056d7248afbff274f739f9d3f44356..213a4fcfeb1cc451f0c7775b36493c9c57070412 100644 --- a/arch/arm/mach-gemini/include/mach/hardware.h +++ b/arch/arm/mach-gemini/include/mach/hardware.h @@ -15,10 +15,9 @@ /* * Memory Map definitions */ -/* FIXME: Does it really swap SRAM like this? */ #ifdef CONFIG_GEMINI_MEM_SWAP # define GEMINI_DRAM_BASE 0x00000000 -# define GEMINI_SRAM_BASE 0x20000000 +# define GEMINI_SRAM_BASE 0x70000000 #else # define GEMINI_SRAM_BASE 0x00000000 # define GEMINI_DRAM_BASE 0x10000000 diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c index eeb00240d7841656df8f742e5c38fefb79dfe126..be1ca28fed3fb9eceb03394338eaaf5166821a06 100644 --- a/arch/arm/mach-kirkwood/common.c +++ b/arch/arm/mach-kirkwood/common.c @@ -144,6 +144,9 @@ static struct platform_device kirkwood_ge00 = { .id = 0, .num_resources = 1, .resource = kirkwood_ge00_resources, + .dev = { + .coherent_dma_mask = 0xffffffff, + }, }; void __init kirkwood_ge00_init(struct mv643xx_eth_platform_data *eth_data) @@ -202,6 +205,9 @@ static struct platform_device kirkwood_ge01 = { .id = 1, .num_resources = 1, .resource = kirkwood_ge01_resources, + .dev = { + .coherent_dma_mask = 0xffffffff, + }, }; void __init kirkwood_ge01_init(struct mv643xx_eth_platform_data *eth_data) @@ -386,12 +392,10 @@ static struct mv64xxx_i2c_pdata kirkwood_i2c_pdata = { static struct resource kirkwood_i2c_resources[] = { { - .name = "i2c", .start = I2C_PHYS_BASE, .end = I2C_PHYS_BASE + 0x1f, .flags = IORESOURCE_MEM, }, { - .name = "i2c", .start = IRQ_KIRKWOOD_TWSI, .end = IRQ_KIRKWOOD_TWSI, .flags = IORESOURCE_IRQ, diff --git a/arch/arm/mach-kirkwood/ts219-setup.c b/arch/arm/mach-kirkwood/ts219-setup.c index dda5743cf3e023b84fc2d04dd1248d1e06c73d35..01aa213c0a6ffda67086c8c3aaac24dbfd4b5113 100644 --- a/arch/arm/mach-kirkwood/ts219-setup.c +++ b/arch/arm/mach-kirkwood/ts219-setup.c @@ -142,6 +142,8 @@ static unsigned int qnap_ts219_mpp_config[] __initdata = { MPP1_SPI_MOSI, MPP2_SPI_SCK, MPP3_SPI_MISO, + MPP4_SATA1_ACTn, + MPP5_SATA0_ACTn, MPP8_TW_SDA, MPP9_TW_SCK, MPP10_UART0_TXD, @@ -150,10 +152,6 @@ static unsigned int qnap_ts219_mpp_config[] __initdata = { MPP14_UART1_RXD, /* PIC controller */ MPP15_GPIO, /* USB Copy button */ MPP16_GPIO, /* Reset button */ - MPP20_SATA1_ACTn, - MPP21_SATA0_ACTn, - MPP22_SATA1_PRESENTn, - MPP23_SATA0_PRESENTn, 0 }; diff --git a/arch/arm/mach-loki/common.c b/arch/arm/mach-loki/common.c index c0d2d9d12e743bccb39644c713a0e6661c538078..818f19d7ab1f6af7ef050d5a167e14b85b3df921 100644 --- a/arch/arm/mach-loki/common.c +++ b/arch/arm/mach-loki/common.c @@ -82,6 +82,9 @@ static struct platform_device loki_ge0 = { .id = 0, .num_resources = 1, .resource = loki_ge0_resources, + .dev = { + .coherent_dma_mask = 0xffffffff, + }, }; void __init loki_ge0_init(struct mv643xx_eth_platform_data *eth_data) @@ -136,6 +139,9 @@ static struct platform_device loki_ge1 = { .id = 1, .num_resources = 1, .resource = loki_ge1_resources, + .dev = { + .coherent_dma_mask = 0xffffffff, + }, }; void __init loki_ge1_init(struct mv643xx_eth_platform_data *eth_data) diff --git a/arch/arm/mach-mmp/include/mach/mfp-pxa168.h b/arch/arm/mach-mmp/include/mach/mfp-pxa168.h index d0bdb6e3682bdcc8e21862f5be8000e574e36b9e..2e914649b9e44075d5af3b17d147c793b5134375 100644 --- a/arch/arm/mach-mmp/include/mach/mfp-pxa168.h +++ b/arch/arm/mach-mmp/include/mach/mfp-pxa168.h @@ -3,6 +3,11 @@ #include +#define MFP_DRIVE_VERY_SLOW (0x0 << 13) +#define MFP_DRIVE_SLOW (0x1 << 13) +#define MFP_DRIVE_MEDIUM (0x2 << 13) +#define MFP_DRIVE_FAST (0x3 << 13) + /* GPIO */ #define GPIO0_GPIO MFP_CFG(GPIO0, AF5) #define GPIO1_GPIO MFP_CFG(GPIO1, AF5) diff --git a/arch/arm/mach-mmp/include/mach/mfp-pxa910.h b/arch/arm/mach-mmp/include/mach/mfp-pxa910.h index 48a1cbc7c56b0bdd15bcc9d289301dcdcaf8134f..d97de36c50adbf75016a047f8b87f86f1385c313 100644 --- a/arch/arm/mach-mmp/include/mach/mfp-pxa910.h +++ b/arch/arm/mach-mmp/include/mach/mfp-pxa910.h @@ -3,6 +3,11 @@ #include +#define MFP_DRIVE_VERY_SLOW (0x0 << 13) +#define MFP_DRIVE_SLOW (0x2 << 13) +#define MFP_DRIVE_MEDIUM (0x4 << 13) +#define MFP_DRIVE_FAST (0x8 << 13) + /* UART2 */ #define GPIO47_UART2_RXD MFP_CFG(GPIO47, AF6) #define GPIO48_UART2_TXD MFP_CFG(GPIO48, AF6) diff --git a/arch/arm/mach-mmp/include/mach/mfp.h b/arch/arm/mach-mmp/include/mach/mfp.h index 277ea4cd0f9f5ca1d49674cb70ad235d108fc603..62e510e80a58099bfefb363253a2fdae92537837 100644 --- a/arch/arm/mach-mmp/include/mach/mfp.h +++ b/arch/arm/mach-mmp/include/mach/mfp.h @@ -12,16 +12,13 @@ * possible, we make the following compromise: * * 1. SLEEP_OE_N will always be programmed to '1' (by MFP_LPM_FLOAT) - * 2. DRIVE strength definitions redefined to include the reserved bit10 + * 2. DRIVE strength definitions redefined to include the reserved bit + * - the reserved bit differs between pxa168 and pxa910, and the + * MFP_DRIVE_* macros are individually defined in mfp-pxa{168,910}.h * 3. Override MFP_CFG() and MFP_CFG_DRV() * 4. Drop the use of MFP_CFG_LPM() and MFP_CFG_X() */ -#define MFP_DRIVE_VERY_SLOW (0x0 << 13) -#define MFP_DRIVE_SLOW (0x2 << 13) -#define MFP_DRIVE_MEDIUM (0x4 << 13) -#define MFP_DRIVE_FAST (0x8 << 13) - #undef MFP_CFG #undef MFP_CFG_DRV #undef MFP_CFG_LPM diff --git a/arch/arm/mach-mmp/time.c b/arch/arm/mach-mmp/time.c index b03a6eda7419278c79f8d1c9617ba456d19297bb..a8400bb891e7017f21661830b7da4bfca7af9d7f 100644 --- a/arch/arm/mach-mmp/time.c +++ b/arch/arm/mach-mmp/time.c @@ -136,7 +136,7 @@ static struct clock_event_device ckevt = { .set_mode = timer_set_mode, }; -static cycle_t clksrc_read(void) +static cycle_t clksrc_read(struct clocksource *cs) { return timer_read(); } diff --git a/arch/arm/mach-mv78xx0/common.c b/arch/arm/mach-mv78xx0/common.c index 9ba595083dab9ac8a175998d7dc59de529f2d091..1b22e4af8791ff16cd238c7852d68a9aa4f12740 100644 --- a/arch/arm/mach-mv78xx0/common.c +++ b/arch/arm/mach-mv78xx0/common.c @@ -321,6 +321,9 @@ static struct platform_device mv78xx0_ge00 = { .id = 0, .num_resources = 1, .resource = mv78xx0_ge00_resources, + .dev = { + .coherent_dma_mask = 0xffffffff, + }, }; void __init mv78xx0_ge00_init(struct mv643xx_eth_platform_data *eth_data) @@ -375,6 +378,9 @@ static struct platform_device mv78xx0_ge01 = { .id = 1, .num_resources = 1, .resource = mv78xx0_ge01_resources, + .dev = { + .coherent_dma_mask = 0xffffffff, + }, }; void __init mv78xx0_ge01_init(struct mv643xx_eth_platform_data *eth_data) @@ -429,6 +435,9 @@ static struct platform_device mv78xx0_ge10 = { .id = 2, .num_resources = 1, .resource = mv78xx0_ge10_resources, + .dev = { + .coherent_dma_mask = 0xffffffff, + }, }; void __init mv78xx0_ge10_init(struct mv643xx_eth_platform_data *eth_data) @@ -496,6 +505,9 @@ static struct platform_device mv78xx0_ge11 = { .id = 3, .num_resources = 1, .resource = mv78xx0_ge11_resources, + .dev = { + .coherent_dma_mask = 0xffffffff, + }, }; void __init mv78xx0_ge11_init(struct mv643xx_eth_platform_data *eth_data) @@ -532,12 +544,10 @@ static struct mv64xxx_i2c_pdata mv78xx0_i2c_0_pdata = { static struct resource mv78xx0_i2c_0_resources[] = { { - .name = "i2c 0 base", .start = I2C_0_PHYS_BASE, .end = I2C_0_PHYS_BASE + 0x1f, .flags = IORESOURCE_MEM, }, { - .name = "i2c 0 irq", .start = IRQ_MV78XX0_I2C_0, .end = IRQ_MV78XX0_I2C_0, .flags = IORESOURCE_IRQ, @@ -567,12 +577,10 @@ static struct mv64xxx_i2c_pdata mv78xx0_i2c_1_pdata = { static struct resource mv78xx0_i2c_1_resources[] = { { - .name = "i2c 1 base", .start = I2C_1_PHYS_BASE, .end = I2C_1_PHYS_BASE + 0x1f, .flags = IORESOURCE_MEM, }, { - .name = "i2c 1 irq", .start = IRQ_MV78XX0_I2C_1, .end = IRQ_MV78XX0_I2C_1, .flags = IORESOURCE_IRQ, diff --git a/arch/arm/mach-mx2/clock_imx21.c b/arch/arm/mach-mx2/clock_imx21.c index 999d013e06e352e62e45cc232fc28b755b573ebd..e4b08ca804eaeded273ff239227e498d753528d8 100644 --- a/arch/arm/mach-mx2/clock_imx21.c +++ b/arch/arm/mach-mx2/clock_imx21.c @@ -890,7 +890,7 @@ static struct clk clko_clk = { .con_id = n, \ .clk = &c, \ }, -static struct clk_lookup lookups[] __initdata = { +static struct clk_lookup lookups[] = { /* It's unlikely that any driver wants one of them directly: _REGISTER_CLOCK(NULL, "ckih", ckih_clk) _REGISTER_CLOCK(NULL, "ckil", ckil_clk) diff --git a/arch/arm/mach-mx2/clock_imx27.c b/arch/arm/mach-mx2/clock_imx27.c index 3f7280c490f0754c29dc92f78a3e599f169deb37..2c971442f3f2ad3b2c2331fadbe704045570d808 100644 --- a/arch/arm/mach-mx2/clock_imx27.c +++ b/arch/arm/mach-mx2/clock_imx27.c @@ -621,7 +621,7 @@ DEFINE_CLOCK1(csi_clk, 0, 0, 0, parent, &csi_clk1, &per4_clk); .clk = &c, \ }, -static struct clk_lookup lookups[] __initdata = { +static struct clk_lookup lookups[] = { _REGISTER_CLOCK("imx-uart.0", NULL, uart1_clk) _REGISTER_CLOCK("imx-uart.1", NULL, uart2_clk) _REGISTER_CLOCK("imx-uart.2", NULL, uart3_clk) diff --git a/arch/arm/mach-mx3/clock-imx35.c b/arch/arm/mach-mx3/clock-imx35.c index 53a112d4e04aa2d1f6ccc022abe40c306ef0454b..3c1e06f56dd6ca60764d3f9ec349f1e1e926c8f3 100644 --- a/arch/arm/mach-mx3/clock-imx35.c +++ b/arch/arm/mach-mx3/clock-imx35.c @@ -404,7 +404,7 @@ DEFINE_CLOCK(gpu2d_clk, 0, CCM_CGR3, 4, NULL, NULL); .clk = &c, \ }, -static struct clk_lookup lookups[] __initdata = { +static struct clk_lookup lookups[] = { _REGISTER_CLOCK(NULL, "asrc", asrc_clk) _REGISTER_CLOCK(NULL, "ata", ata_clk) _REGISTER_CLOCK(NULL, "audmux", audmux_clk) diff --git a/arch/arm/mach-mx3/clock.c b/arch/arm/mach-mx3/clock.c index 9957a11533a4471fc7a03837417bf740e8765ae9..a68fcf981edf124678efa99695cf7efe6cd2cbc4 100644 --- a/arch/arm/mach-mx3/clock.c +++ b/arch/arm/mach-mx3/clock.c @@ -516,7 +516,7 @@ DEFINE_CLOCK(ipg_clk, 0, NULL, 0, ipg_get_rate, NULL, &ahb_clk); .clk = &c, \ }, -static struct clk_lookup lookups[] __initdata = { +static struct clk_lookup lookups[] = { _REGISTER_CLOCK(NULL, "emi", emi_clk) _REGISTER_CLOCK(NULL, "cspi", cspi1_clk) _REGISTER_CLOCK(NULL, "cspi", cspi2_clk) diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c index 6af99ddabdfb92e0159ba96252654549dc04b9ce..b1c7778d9f96ebef4700e3887138802edc625282 100644 --- a/arch/arm/mach-orion5x/common.c +++ b/arch/arm/mach-orion5x/common.c @@ -188,6 +188,9 @@ static struct platform_device orion5x_eth = { .id = 0, .num_resources = 1, .resource = orion5x_eth_resources, + .dev = { + .coherent_dma_mask = 0xffffffff, + }, }; void __init orion5x_eth_init(struct mv643xx_eth_platform_data *eth_data) @@ -248,12 +251,10 @@ static struct mv64xxx_i2c_pdata orion5x_i2c_pdata = { static struct resource orion5x_i2c_resources[] = { { - .name = "i2c base", .start = I2C_PHYS_BASE, .end = I2C_PHYS_BASE + 0x1f, .flags = IORESOURCE_MEM, }, { - .name = "i2c irq", .start = IRQ_ORION5X_I2C, .end = IRQ_ORION5X_I2C, .flags = IORESOURCE_IRQ, diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c index d245e59c51b1c5f7afc6d4691d7bac68577510c9..29970f703f3cc6d33ddc19635f1b56a6df3d9777 100644 --- a/arch/arm/mach-pxa/devices.c +++ b/arch/arm/mach-pxa/devices.c @@ -72,7 +72,10 @@ void __init pxa_set_mci_info(struct pxamci_platform_data *info) } -static struct pxa2xx_udc_mach_info pxa_udc_info; +static struct pxa2xx_udc_mach_info pxa_udc_info = { + .gpio_pullup = -1, + .gpio_vbus = -1, +}; void __init pxa_set_udc_info(struct pxa2xx_udc_mach_info *info) { diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c index 92ba16e1b6fc6e042cf8c2aedb684f58cbdb1a6e..7db966dc29ce50f2e7815e26723794c8e1da639c 100644 --- a/arch/arm/mach-pxa/ezx.c +++ b/arch/arm/mach-pxa/ezx.c @@ -111,9 +111,9 @@ static unsigned long ezx_pin_config[] __initdata = { GPIO25_SSP1_TXD, GPIO26_SSP1_RXD, GPIO24_GPIO, /* pcap chip select */ - GPIO1_GPIO, /* pcap interrupt */ - GPIO4_GPIO, /* WDI_AP */ - GPIO55_GPIO, /* SYS_RESTART */ + GPIO1_GPIO | WAKEUP_ON_EDGE_RISE, /* pcap interrupt */ + GPIO4_GPIO | MFP_LPM_DRIVE_HIGH, /* WDI_AP */ + GPIO55_GPIO | MFP_LPM_DRIVE_HIGH, /* SYS_RESTART */ /* MMC */ GPIO32_MMC_CLK, @@ -144,20 +144,20 @@ static unsigned long ezx_pin_config[] __initdata = { #if defined(CONFIG_MACH_EZX_A780) || defined(CONFIG_MACH_EZX_E680) static unsigned long gen1_pin_config[] __initdata = { /* flip / lockswitch */ - GPIO12_GPIO, + GPIO12_GPIO | WAKEUP_ON_EDGE_BOTH, /* bluetooth (bcm2035) */ - GPIO14_GPIO | WAKEUP_ON_LEVEL_HIGH, /* HOSTWAKE */ + GPIO14_GPIO | WAKEUP_ON_EDGE_RISE, /* HOSTWAKE */ GPIO48_GPIO, /* RESET */ GPIO28_GPIO, /* WAKEUP */ /* Neptune handshake */ - GPIO0_GPIO | WAKEUP_ON_LEVEL_HIGH, /* BP_RDY */ - GPIO57_GPIO, /* AP_RDY */ - GPIO13_GPIO | WAKEUP_ON_LEVEL_HIGH, /* WDI */ - GPIO3_GPIO | WAKEUP_ON_LEVEL_HIGH, /* WDI2 */ - GPIO82_GPIO, /* RESET */ - GPIO99_GPIO, /* TC_MM_EN */ + GPIO0_GPIO | WAKEUP_ON_EDGE_FALL, /* BP_RDY */ + GPIO57_GPIO | MFP_LPM_DRIVE_HIGH, /* AP_RDY */ + GPIO13_GPIO | WAKEUP_ON_EDGE_BOTH, /* WDI */ + GPIO3_GPIO | WAKEUP_ON_EDGE_BOTH, /* WDI2 */ + GPIO82_GPIO | MFP_LPM_DRIVE_HIGH, /* RESET */ + GPIO99_GPIO | MFP_LPM_DRIVE_HIGH, /* TC_MM_EN */ /* sound */ GPIO52_SSP3_SCLK, @@ -199,21 +199,21 @@ static unsigned long gen1_pin_config[] __initdata = { defined(CONFIG_MACH_EZX_E2) || defined(CONFIG_MACH_EZX_E6) static unsigned long gen2_pin_config[] __initdata = { /* flip / lockswitch */ - GPIO15_GPIO, + GPIO15_GPIO | WAKEUP_ON_EDGE_BOTH, /* EOC */ - GPIO10_GPIO, + GPIO10_GPIO | WAKEUP_ON_EDGE_RISE, /* bluetooth (bcm2045) */ - GPIO13_GPIO | WAKEUP_ON_LEVEL_HIGH, /* HOSTWAKE */ + GPIO13_GPIO | WAKEUP_ON_EDGE_RISE, /* HOSTWAKE */ GPIO37_GPIO, /* RESET */ GPIO57_GPIO, /* WAKEUP */ /* Neptune handshake */ - GPIO0_GPIO | WAKEUP_ON_LEVEL_HIGH, /* BP_RDY */ - GPIO96_GPIO, /* AP_RDY */ - GPIO3_GPIO | WAKEUP_ON_LEVEL_HIGH, /* WDI */ - GPIO116_GPIO, /* RESET */ + GPIO0_GPIO | WAKEUP_ON_EDGE_FALL, /* BP_RDY */ + GPIO96_GPIO | MFP_LPM_DRIVE_HIGH, /* AP_RDY */ + GPIO3_GPIO | WAKEUP_ON_EDGE_FALL, /* WDI */ + GPIO116_GPIO | MFP_LPM_DRIVE_HIGH, /* RESET */ GPIO41_GPIO, /* BP_FLASH */ /* sound */ diff --git a/arch/arm/mach-pxa/imote2.c b/arch/arm/mach-pxa/imote2.c index 2121309b2474dc545e379cac27697c8d374b0bad..2b27336c29f1b6ec517a63fd0881f8e964ff507d 100644 --- a/arch/arm/mach-pxa/imote2.c +++ b/arch/arm/mach-pxa/imote2.c @@ -412,7 +412,7 @@ static struct platform_device imote2_flash_device = { */ static struct i2c_board_info __initdata imote2_i2c_board_info[] = { { /* UCAM sensor board */ - .type = "max1238", + .type = "max1239", .addr = 0x35, }, { /* ITS400 Sensor board only */ .type = "max1363", diff --git a/arch/arm/mach-pxa/include/mach/reset.h b/arch/arm/mach-pxa/include/mach/reset.h index 31e6a7b6ad80d27f055b9ce49da0b7e036e06755..b6c10556fbc7931ab2382fee61fa73e9c8291081 100644 --- a/arch/arm/mach-pxa/include/mach/reset.h +++ b/arch/arm/mach-pxa/include/mach/reset.h @@ -13,8 +13,9 @@ extern void clear_reset_status(unsigned int mask); /** * init_gpio_reset() - register GPIO as reset generator * @gpio: gpio nr - * @output: set gpio as out/low instead of input during normal work + * @output: set gpio as output instead of input during normal work + * @level: output level */ -extern int init_gpio_reset(int gpio, int output); +extern int init_gpio_reset(int gpio, int output, int level); #endif /* __ASM_ARCH_RESET_H */ diff --git a/arch/arm/mach-pxa/mfp-pxa2xx.c b/arch/arm/mach-pxa/mfp-pxa2xx.c index 7ffb91d64c39733e39e6cc9d8518f2ae5f67a379..cf6b720c055f5f5c51136c918975a4f736f6c9ed 100644 --- a/arch/arm/mach-pxa/mfp-pxa2xx.c +++ b/arch/arm/mach-pxa/mfp-pxa2xx.c @@ -322,6 +322,7 @@ static inline void pxa27x_mfp_init(void) {} #ifdef CONFIG_PM static unsigned long saved_gafr[2][4]; static unsigned long saved_gpdr[4]; +static unsigned long saved_pgsr[4]; static int pxa2xx_mfp_suspend(struct sys_device *d, pm_message_t state) { @@ -332,6 +333,7 @@ static int pxa2xx_mfp_suspend(struct sys_device *d, pm_message_t state) saved_gafr[0][i] = GAFR_L(i); saved_gafr[1][i] = GAFR_U(i); saved_gpdr[i] = GPDR(i * 32); + saved_pgsr[i] = PGSR(i); GPDR(i * 32) = gpdr_lpm[i]; } @@ -346,6 +348,7 @@ static int pxa2xx_mfp_resume(struct sys_device *d) GAFR_L(i) = saved_gafr[0][i]; GAFR_U(i) = saved_gafr[1][i]; GPDR(i * 32) = saved_gpdr[i]; + PGSR(i) = saved_pgsr[i]; } PSSR = PSSR_RDH | PSSR_PH; return 0; @@ -374,6 +377,9 @@ static int __init pxa2xx_mfp_init(void) if (cpu_is_pxa27x()) pxa27x_mfp_init(); + /* clear RDH bit to enable GPIO receivers after reset/sleep exit */ + PSSR = PSSR_RDH; + /* initialize gafr_run[], pgsr_lpm[] from existing values */ for (i = 0; i <= gpio_to_bank(pxa_last_gpio); i++) gpdr_lpm[i] = GPDR(i * 32); diff --git a/arch/arm/mach-pxa/palmld.c b/arch/arm/mach-pxa/palmld.c index 1cec1806f002e270bbdf146cc14d56e5b6f17608..471a853e548b9bd861280b4a9ede88c4d1156be5 100644 --- a/arch/arm/mach-pxa/palmld.c +++ b/arch/arm/mach-pxa/palmld.c @@ -62,6 +62,8 @@ static unsigned long palmld_pin_config[] __initdata = { GPIO29_AC97_SDATA_IN_0, GPIO30_AC97_SDATA_OUT, GPIO31_AC97_SYNC, + GPIO89_AC97_SYSCLK, + GPIO95_AC97_nRESET, /* IrDA */ GPIO108_GPIO, /* ir disable */ diff --git a/arch/arm/mach-pxa/palmt5.c b/arch/arm/mach-pxa/palmt5.c index 30662363907b88da99e5d2f7c979849d657f6134..05bf979b78a668d3a4a9c256944bdbaeb7dc1de3 100644 --- a/arch/arm/mach-pxa/palmt5.c +++ b/arch/arm/mach-pxa/palmt5.c @@ -64,6 +64,7 @@ static unsigned long palmt5_pin_config[] __initdata = { GPIO29_AC97_SDATA_IN_0, GPIO30_AC97_SDATA_OUT, GPIO31_AC97_SYNC, + GPIO89_AC97_SYSCLK, GPIO95_AC97_nRESET, /* IrDA */ diff --git a/arch/arm/mach-pxa/palmtx.c b/arch/arm/mach-pxa/palmtx.c index e2d44b1a8a9b9111c3daeb2f06ba6c682dc224e8..e99a893c58a78b2589fefae2345b019cab98b92f 100644 --- a/arch/arm/mach-pxa/palmtx.c +++ b/arch/arm/mach-pxa/palmtx.c @@ -65,6 +65,7 @@ static unsigned long palmtx_pin_config[] __initdata = { GPIO29_AC97_SDATA_IN_0, GPIO30_AC97_SDATA_OUT, GPIO31_AC97_SYNC, + GPIO89_AC97_SYSCLK, GPIO95_AC97_nRESET, /* IrDA */ diff --git a/arch/arm/mach-pxa/reset.c b/arch/arm/mach-pxa/reset.c index df29d45fb4e72db6cabbe06332018071fbe1774d..01e9d643394a9d28160a98ccaee118761d8fb75f 100644 --- a/arch/arm/mach-pxa/reset.c +++ b/arch/arm/mach-pxa/reset.c @@ -20,7 +20,7 @@ static void do_hw_reset(void); static int reset_gpio = -1; -int init_gpio_reset(int gpio, int output) +int init_gpio_reset(int gpio, int output, int level) { int rc; @@ -31,7 +31,7 @@ int init_gpio_reset(int gpio, int output) } if (output) - rc = gpio_direction_output(gpio, 0); + rc = gpio_direction_output(gpio, level); else rc = gpio_direction_input(gpio); if (rc) { diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index c18e34acafcb427563f874a2a59804a952a3b2b5..5a45fe340a1057729a7e7a31442af85da9426595 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -531,9 +531,15 @@ static int spitz_ohci_init(struct device *dev) return gpio_direction_output(SPITZ_GPIO_USB_HOST, 1); } +static void spitz_ohci_exit(struct device *dev) +{ + gpio_free(SPITZ_GPIO_USB_HOST); +} + static struct pxaohci_platform_data spitz_ohci_platform_data = { .port_mode = PMM_NPS_MODE, .init = spitz_ohci_init, + .exit = spitz_ohci_exit, .flags = ENABLE_PORT_ALL | NO_OC_PROTECTION, .power_budget = 150, }; @@ -731,7 +737,7 @@ static void spitz_restart(char mode, const char *cmd) static void __init common_init(void) { - init_gpio_reset(SPITZ_GPIO_ON_RESET, 1); + init_gpio_reset(SPITZ_GPIO_ON_RESET, 1, 0); pm_power_off = spitz_poweroff; arm_pm_restart = spitz_restart; diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c index afac5b6d3d78e50212afbca1df72579f57de00e4..a0bd46ef5d30de6fb09cda7fc96371a344c95207 100644 --- a/arch/arm/mach-pxa/tosa.c +++ b/arch/arm/mach-pxa/tosa.c @@ -897,7 +897,7 @@ static void __init tosa_init(void) gpio_set_wake(MFP_PIN_GPIO1, 1); /* We can't pass to gpio-keys since it will drop the Reset altfunc */ - init_gpio_reset(TOSA_GPIO_ON_RESET, 0); + init_gpio_reset(TOSA_GPIO_ON_RESET, 0, 0); pm_power_off = tosa_poweroff; arm_pm_restart = tosa_restart; diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 3397f1e64d76378d676d7c7e9f517bde86cff9ad..a08d9d2380d3e357dedbf743111e0eac45721b09 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -184,23 +184,37 @@ __v7_setup: stmia r12, {r0-r5, r7, r9, r11, lr} bl v7_flush_dcache_all ldmia r12, {r0-r5, r7, r9, r11, lr} + + mrc p15, 0, r0, c0, c0, 0 @ read main ID register + and r10, r0, #0xff000000 @ ARM? + teq r10, #0x41000000 + bne 2f + and r5, r0, #0x00f00000 @ variant + and r6, r0, #0x0000000f @ revision + orr r0, r6, r5, lsr #20-4 @ combine variant and revision + #ifdef CONFIG_ARM_ERRATA_430973 - mrc p15, 0, r10, c1, c0, 1 @ read aux control register - orr r10, r10, #(1 << 6) @ set IBE to 1 - mcr p15, 0, r10, c1, c0, 1 @ write aux control register + teq r5, #0x00100000 @ only present in r1p* + mrceq p15, 0, r10, c1, c0, 1 @ read aux control register + orreq r10, r10, #(1 << 6) @ set IBE to 1 + mcreq p15, 0, r10, c1, c0, 1 @ write aux control register #endif #ifdef CONFIG_ARM_ERRATA_458693 - mrc p15, 0, r10, c1, c0, 1 @ read aux control register - orr r10, r10, #(1 << 5) @ set L1NEON to 1 - orr r10, r10, #(1 << 9) @ set PLDNOP to 1 - mcr p15, 0, r10, c1, c0, 1 @ write aux control register + teq r0, #0x20 @ only present in r2p0 + mrceq p15, 0, r10, c1, c0, 1 @ read aux control register + orreq r10, r10, #(1 << 5) @ set L1NEON to 1 + orreq r10, r10, #(1 << 9) @ set PLDNOP to 1 + mcreq p15, 0, r10, c1, c0, 1 @ write aux control register #endif #ifdef CONFIG_ARM_ERRATA_460075 - mrc p15, 1, r10, c9, c0, 2 @ read L2 cache aux ctrl register - orr r10, r10, #(1 << 22) @ set the Write Allocate disable bit - mcr p15, 1, r10, c9, c0, 2 @ write the L2 cache aux ctrl register + teq r0, #0x20 @ only present in r2p0 + mrceq p15, 1, r10, c9, c0, 2 @ read L2 cache aux ctrl register + tsteq r10, #1 << 22 + orreq r10, r10, #(1 << 22) @ set the Write Allocate disable bit + mcreq p15, 1, r10, c9, c0, 2 @ write the L2 cache aux ctrl register #endif - mov r10, #0 + +2: mov r10, #0 #ifdef HARVARD_CACHE mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate #endif diff --git a/arch/arm/plat-mxc/include/mach/imx-uart.h b/arch/arm/plat-mxc/include/mach/imx-uart.h index 599217b2e13f94cea800c55653e6497c9d2ff3ad..f9bd17dd8dd71af1fd6d6c05f7c7781b51daea26 100644 --- a/arch/arm/plat-mxc/include/mach/imx-uart.h +++ b/arch/arm/plat-mxc/include/mach/imx-uart.h @@ -20,11 +20,16 @@ #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/arch/arm/plat-omap/mailbox.c b/arch/arm/plat-omap/mailbox.c index 0abfbaa59871313c5ce3857457c3407f6ca4bafc..40424edae93912067cabd21a8ce7c4c304a91428 100644 --- a/arch/arm/plat-omap/mailbox.c +++ b/arch/arm/plat-omap/mailbox.c @@ -147,24 +147,40 @@ 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; - int ret = 0; + + tx_data = kmalloc(sizeof(*tx_data), GFP_ATOMIC); + if (unlikely(!tx_data)) + return -ENOMEM; rq = blk_get_request(q, WRITE, GFP_ATOMIC); if (unlikely(!rq)) { - ret = -ENOMEM; - goto fail; + kfree(tx_data); + return -ENOMEM; } - rq->data = (void *)msg; - blk_insert_request(q, rq, 0, arg); + tx_data->msg = msg; + tx_data->arg = arg; + rq->end_io = omap_msg_tx_end_io; + blk_insert_request(q, rq, 0, tx_data); schedule_work(&mbox->txq->work); - fail: - return ret; + return 0; } EXPORT_SYMBOL(omap_mbox_msg_send); @@ -178,22 +194,28 @@ 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 = elv_next_request(q); + rq = blk_fetch_request(q); spin_unlock(q->queue_lock); if (!rq) break; - ret = __mbox_msg_send(mbox, (mbox_msg_t) rq->data, rq->special); + tx_data = rq->special; + + ret = __mbox_msg_send(mbox, tx_data->msg, tx_data->arg); 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); - if (__blk_end_request(rq, 0, 0)) - BUG(); + __blk_end_request_all(rq, 0); spin_unlock(q->queue_lock); } } @@ -218,16 +240,13 @@ static void mbox_rx_work(struct work_struct *work) while (1) { spin_lock_irqsave(q->queue_lock, flags); - rq = elv_next_request(q); + rq = blk_fetch_request(q); spin_unlock_irqrestore(q->queue_lock, flags); if (!rq) break; - msg = (mbox_msg_t) rq->data; - - if (blk_end_request(rq, 0, 0)) - BUG(); - + msg = (mbox_msg_t)rq->special; + blk_end_request_all(rq, 0); mbox->rxq->callback((void *)msg); } } @@ -264,7 +283,6 @@ 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); @@ -272,7 +290,7 @@ static void __mbox_rx_interrupt(struct omap_mbox *mbox) mbox->err_notify(); } - blk_insert_request(q, rq, 0, NULL); + blk_insert_request(q, rq, 0, (void *)msg); if (mbox->ops->type == OMAP_MBOX_TYPE1) break; } @@ -329,16 +347,15 @@ omap_mbox_read(struct device *dev, struct device_attribute *attr, char *buf) while (1) { spin_lock_irqsave(q->queue_lock, flags); - rq = elv_next_request(q); + rq = blk_fetch_request(q); spin_unlock_irqrestore(q->queue_lock, flags); if (!rq) break; - *p = (mbox_msg_t) rq->data; + *p = (mbox_msg_t)rq->special; - if (blk_end_request(rq, 0, 0)) - BUG(); + blk_end_request_all(rq, 0); if (unlikely(mbox_seq_test(mbox, *p))) { pr_info("mbox: Illegal seq bit!(%08x) ignored\n", *p); diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types index 945e0d237a1dfc6c3016090972813d7d32ba128e..fec64678a63aae2f6bd3b9200a0175599d90b64a 100644 --- a/arch/arm/tools/mach-types +++ b/arch/arm/tools/mach-types @@ -12,7 +12,7 @@ # # http://www.arm.linux.org.uk/developer/machines/?action=new # -# Last update: Mon Mar 23 20:09:01 2009 +# Last update: Fri May 29 10:14:20 2009 # # machine_is_xxx CONFIG_xxxx MACH_TYPE_xxx number # @@ -916,7 +916,7 @@ nxdb500 MACH_NXDB500 NXDB500 905 apf9328 MACH_APF9328 APF9328 906 omap_wipoq MACH_OMAP_WIPOQ OMAP_WIPOQ 907 omap_twip MACH_OMAP_TWIP OMAP_TWIP 908 -palmt650 MACH_PALMT650 PALMT650 909 +treo650 MACH_TREO650 TREO650 909 acumen MACH_ACUMEN ACUMEN 910 xp100 MACH_XP100 XP100 911 fs2410 MACH_FS2410 FS2410 912 @@ -1232,7 +1232,7 @@ ql202b MACH_QL202B QL202B 1226 vpac270 MACH_VPAC270 VPAC270 1227 rd129 MACH_RD129 RD129 1228 htcwizard MACH_HTCWIZARD HTCWIZARD 1229 -xscale_treo680 MACH_XSCALE_TREO680 XSCALE_TREO680 1230 +treo680 MACH_TREO680 TREO680 1230 tecon_tmezon MACH_TECON_TMEZON TECON_TMEZON 1231 zylonite MACH_ZYLONITE ZYLONITE 1233 gene1270 MACH_GENE1270 GENE1270 1234 @@ -1418,10 +1418,10 @@ looxc550 MACH_LOOXC550 LOOXC550 1417 cnty_titan MACH_CNTY_TITAN CNTY_TITAN 1418 app3xx MACH_APP3XX APP3XX 1419 sideoatsgrama MACH_SIDEOATSGRAMA SIDEOATSGRAMA 1420 -palmtreo700p MACH_PALMTREO700P PALMTREO700P 1421 -palmtreo700w MACH_PALMTREO700W PALMTREO700W 1422 -palmtreo750 MACH_PALMTREO750 PALMTREO750 1423 -palmtreo755p MACH_PALMTREO755P PALMTREO755P 1424 +treo700p MACH_TREO700P TREO700P 1421 +treo700w MACH_TREO700W TREO700W 1422 +treo750 MACH_TREO750 TREO750 1423 +treo755p MACH_TREO755P TREO755P 1424 ezreganut9200 MACH_EZREGANUT9200 EZREGANUT9200 1425 sarge MACH_SARGE SARGE 1426 a696 MACH_A696 A696 1427 @@ -1721,7 +1721,7 @@ sapphire MACH_SAPPHIRE SAPPHIRE 1729 csb637xo MACH_CSB637XO CSB637XO 1730 evisiong MACH_EVISIONG EVISIONG 1731 stmp37xx MACH_STMP37XX STMP37XX 1732 -stmp378x MACH_STMP38XX STMP38XX 1733 +stmp378x MACH_STMP378X STMP378X 1733 tnt MACH_TNT TNT 1734 tbxt MACH_TBXT TBXT 1735 playmate MACH_PLAYMATE PLAYMATE 1736 @@ -1817,7 +1817,7 @@ smdkc100 MACH_SMDKC100 SMDKC100 1826 tavorevb MACH_TAVOREVB TAVOREVB 1827 saar MACH_SAAR SAAR 1828 deister_eyecam MACH_DEISTER_EYECAM DEISTER_EYECAM 1829 -at91sam9m10ek MACH_AT91SAM9M10EK AT91SAM9M10EK 1830 +at91sam9m10g45ek MACH_AT91SAM9M10G45EK AT91SAM9M10G45EK 1830 linkstation_produo MACH_LINKSTATION_PRODUO LINKSTATION_PRODUO 1831 hit_b0 MACH_HIT_B0 HIT_B0 1832 adx_rmu MACH_ADX_RMU ADX_RMU 1833 @@ -2132,3 +2132,116 @@ apollo MACH_APOLLO APOLLO 2141 at91cap9stk MACH_AT91CAP9STK AT91CAP9STK 2142 spc300 MACH_SPC300 SPC300 2143 eko MACH_EKO EKO 2144 +ccw9m2443 MACH_CCW9M2443 CCW9M2443 2145 +ccw9m2443js MACH_CCW9M2443JS CCW9M2443JS 2146 +m2m_router_device MACH_M2M_ROUTER_DEVICE M2M_ROUTER_DEVICE 2147 +str9104nas MACH_STAR9104NAS STAR9104NAS 2148 +pca100 MACH_PCA100 PCA100 2149 +z3_dm365_mod_01 MACH_Z3_DM365_MOD_01 Z3_DM365_MOD_01 2150 +hipox MACH_HIPOX HIPOX 2151 +omap3_piteds MACH_OMAP3_PITEDS OMAP3_PITEDS 2152 +bm150r MACH_BM150R BM150R 2153 +tbone MACH_TBONE TBONE 2154 +merlin MACH_MERLIN MERLIN 2155 +falcon MACH_FALCON FALCON 2156 +davinci_da850_evm MACH_DAVINCI_DA850_EVM DAVINCI_DA850_EVM 2157 +s5p6440 MACH_S5P6440 S5P6440 2158 +at91sam9g10ek MACH_AT91SAM9G10EK AT91SAM9G10EK 2159 +omap_4430sdp MACH_OMAP_4430SDP OMAP_4430SDP 2160 +lpc313x MACH_LPC313X LPC313X 2161 +magx_zn5 MACH_MAGX_ZN5 MAGX_ZN5 2162 +magx_em30 MACH_MAGX_EM30 MAGX_EM30 2163 +magx_ve66 MACH_MAGX_VE66 MAGX_VE66 2164 +meesc MACH_MEESC MEESC 2165 +otc570 MACH_OTC570 OTC570 2166 +bcu2412 MACH_BCU2412 BCU2412 2167 +beacon MACH_BEACON BEACON 2168 +actia_tgw MACH_ACTIA_TGW ACTIA_TGW 2169 +e4430 MACH_E4430 E4430 2170 +ql300 MACH_QL300 QL300 2171 +btmavb101 MACH_BTMAVB101 BTMAVB101 2172 +btmawb101 MACH_BTMAWB101 BTMAWB101 2173 +sq201 MACH_SQ201 SQ201 2174 +quatro45xx MACH_QUATRO45XX QUATRO45XX 2175 +openpad MACH_OPENPAD OPENPAD 2176 +tx25 MACH_TX25 TX25 2177 +omap3_torpedo MACH_OMAP3_TORPEDO OMAP3_TORPEDO 2178 +htcraphael_k MACH_HTCRAPHAEL_K HTCRAPHAEL_K 2179 +lal43 MACH_LAL43 LAL43 2181 +htcraphael_cdma500 MACH_HTCRAPHAEL_CDMA500 HTCRAPHAEL_CDMA500 2182 +anw6410 MACH_ANW6410 ANW6410 2183 +htcprophet MACH_HTCPROPHET HTCPROPHET 2185 +cfa_10022 MACH_CFA_10022 CFA_10022 2186 +imx27_visstrim_m10 MACH_IMX27_VISSTRIM_M10 IMX27_VISSTRIM_M10 2187 +px2imx27 MACH_PX2IMX27 PX2IMX27 2188 +stm3210e_eval MACH_STM3210E_EVAL STM3210E_EVAL 2189 +dvs10 MACH_DVS10 DVS10 2190 +portuxg20 MACH_PORTUXG20 PORTUXG20 2191 +arm_spv MACH_ARM_SPV ARM_SPV 2192 +smdkc110 MACH_SMDKC110 SMDKC110 2193 +cabespresso MACH_CABESPRESSO CABESPRESSO 2194 +hmc800 MACH_HMC800 HMC800 2195 +sholes MACH_SHOLES SHOLES 2196 +btmxc31 MACH_BTMXC31 BTMXC31 2197 +dt501 MACH_DT501 DT501 2198 +ktx MACH_KTX KTX 2199 +omap3517evm MACH_OMAP3517EVM OMAP3517EVM 2200 +netspace_v2 MACH_NETSPACE_V2 NETSPACE_V2 2201 +netspace_max_v2 MACH_NETSPACE_MAX_V2 NETSPACE_MAX_V2 2202 +d2net_v2 MACH_D2NET_V2 D2NET_V2 2203 +net2big_v2 MACH_NET2BIG_V2 NET2BIG_V2 2204 +net4big_v2 MACH_NET4BIG_V2 NET4BIG_V2 2205 +net5big_v2 MACH_NET5BIG_V2 NET5BIG_V2 2206 +endb2443 MACH_ENDB2443 ENDB2443 2207 +inetspace_v2 MACH_INETSPACE_V2 INETSPACE_V2 2208 +tros MACH_TROS TROS 2209 +pelco_homer MACH_PELCO_HOMER PELCO_HOMER 2210 +ofsp8 MACH_OFSP8 OFSP8 2211 +at91sam9g45ekes MACH_AT91SAM9G45EKES AT91SAM9G45EKES 2212 +guf_cupid MACH_GUF_CUPID GUF_CUPID 2213 +eab1r MACH_EAB1R EAB1R 2214 +desirec MACH_DESIREC DESIREC 2215 +cordoba MACH_CORDOBA CORDOBA 2216 +irvine MACH_IRVINE IRVINE 2217 +sff772 MACH_SFF772 SFF772 2218 +pelco_milano MACH_PELCO_MILANO PELCO_MILANO 2219 +pc7302 MACH_PC7302 PC7302 2220 +bip6000 MACH_BIP6000 BIP6000 2221 +silvermoon MACH_SILVERMOON SILVERMOON 2222 +vc0830 MACH_VC0830 VC0830 2223 +dt430 MACH_DT430 DT430 2224 +ji42pf MACH_JI42PF JI42PF 2225 +gnet_ksm MACH_GNET_KSM GNET_KSM 2226 +gnet_sgm MACH_GNET_SGM GNET_SGM 2227 +gnet_sgr MACH_GNET_SGR GNET_SGR 2228 +omap3_icetekevm MACH_OMAP3_ICETEKEVM OMAP3_ICETEKEVM 2229 +pnp MACH_PNP PNP 2230 +ctera_2bay_k MACH_CTERA_2BAY_K CTERA_2BAY_K 2231 +ctera_2bay_u MACH_CTERA_2BAY_U CTERA_2BAY_U 2232 +sas_c MACH_SAS_C SAS_C 2233 +vma2315 MACH_VMA2315 VMA2315 2234 +vcs MACH_VCS VCS 2235 +spear600 MACH_SPEAR600 SPEAR600 2236 +spear300 MACH_SPEAR300 SPEAR300 2237 +spear1300 MACH_SPEAR1300 SPEAR1300 2238 +lilly1131 MACH_LILLY1131 LILLY1131 2239 +arvoo_ax301 MACH_ARVOO_AX301 ARVOO_AX301 2240 +mapphone MACH_MAPPHONE MAPPHONE 2241 +legend MACH_LEGEND LEGEND 2242 +salsa MACH_SALSA SALSA 2243 +lounge MACH_LOUNGE LOUNGE 2244 +vision MACH_VISION VISION 2245 +vmb20 MACH_VMB20 VMB20 2246 +hy2410 MACH_HY2410 HY2410 2247 +hy9315 MACH_HY9315 HY9315 2248 +bullwinkle MACH_BULLWINKLE BULLWINKLE 2249 +arm_ultimator2 MACH_ARM_ULTIMATOR2 ARM_ULTIMATOR2 2250 +vs_v210 MACH_VS_V210 VS_V210 2252 +vs_v212 MACH_VS_V212 VS_V212 2253 +hmt MACH_HMT HMT 2254 +suen3 MACH_SUEN3 SUEN3 2255 +vesper MACH_VESPER VESPER 2256 +str9 MACH_STR9 STR9 2257 +omap3_wl_ff MACH_OMAP3_WL_FF OMAP3_WL_FF 2258 +simcom MACH_SIMCOM SIMCOM 2259 +mcwebio MACH_MCWEBIO MCWEBIO 2260 diff --git a/arch/blackfin/include/asm/flat.h b/arch/blackfin/include/asm/flat.h index e70074e05f4ef095e33beb1cf28ede8ae817f980..733a178d782d0dd8e77e2c619f7b67d3271d2500 100644 --- a/arch/blackfin/include/asm/flat.h +++ b/arch/blackfin/include/asm/flat.h @@ -10,7 +10,6 @@ #include -#define flat_stack_align(sp) /* nothing needed */ #define flat_argvp_envp_on_stack() 0 #define flat_old_ram_flag(flags) (flags) diff --git a/arch/cris/arch-v32/kernel/irq.c b/arch/cris/arch-v32/kernel/irq.c index df3925cb1c7fbbcab86f8445491d0e77ebf684a9..d70b445f4a8f0fc82922e848ae4f0bbbae6a1fb5 100644 --- a/arch/cris/arch-v32/kernel/irq.c +++ b/arch/cris/arch-v32/kernel/irq.c @@ -325,12 +325,14 @@ static void end_crisv32_irq(unsigned int irq) { } -void set_affinity_crisv32_irq(unsigned int irq, const struct cpumask *dest) +int 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/arch/frv/Kconfig b/arch/frv/Kconfig index 9d1552a9ee2c88ddb40bc7d70dea316f725d2843..8a5bd7a9c6f533b452b21de81127c476b1826765 100644 --- a/arch/frv/Kconfig +++ b/arch/frv/Kconfig @@ -6,6 +6,7 @@ config FRV bool default y select HAVE_IDE + select HAVE_ARCH_TRACEHOOK config ZONE_DMA bool diff --git a/arch/frv/include/asm/bitops.h b/arch/frv/include/asm/bitops.h index 287f6f697ce276d55b498cea168a67e402e6b5bf..50ae91b29674584743e5935aa49e0717fb260b34 100644 --- a/arch/frv/include/asm/bitops.h +++ b/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(int nr, volatile void *addr) +static inline int test_and_clear_bit(unsigned long 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(int nr, volatile void *addr) return (atomic_test_and_ANDNOT_mask(mask, ptr) & mask) != 0; } -static inline int test_and_set_bit(int nr, volatile void *addr) +static inline int test_and_set_bit(unsigned long 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(int nr, volatile void *addr) return (atomic_test_and_OR_mask(mask, ptr) & mask) != 0; } -static inline int test_and_change_bit(int nr, volatile void *addr) +static inline int test_and_change_bit(unsigned long 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(int nr, volatile void *addr) return (atomic_test_and_XOR_mask(mask, ptr) & mask) != 0; } -static inline void clear_bit(int nr, volatile void *addr) +static inline void clear_bit(unsigned long nr, volatile void *addr) { test_and_clear_bit(nr, addr); } -static inline void set_bit(int nr, volatile void *addr) +static inline void set_bit(unsigned long nr, volatile void *addr) { test_and_set_bit(nr, addr); } -static inline void change_bit(int nr, volatile void * addr) +static inline void change_bit(unsigned long nr, volatile void *addr) { test_and_change_bit(nr, addr); } -static inline void __clear_bit(int nr, volatile void * addr) +static inline void __clear_bit(unsigned long nr, volatile void *addr) { volatile unsigned long *a = addr; int mask; @@ -161,7 +161,7 @@ static inline void __clear_bit(int nr, volatile void * addr) *a &= ~mask; } -static inline void __set_bit(int nr, volatile void * addr) +static inline void __set_bit(unsigned long nr, volatile void *addr) { volatile unsigned long *a = addr; int mask; @@ -171,7 +171,7 @@ static inline void __set_bit(int nr, volatile void * addr) *a |= mask; } -static inline void __change_bit(int nr, volatile void *addr) +static inline void __change_bit(unsigned long nr, volatile void *addr) { volatile unsigned long *a = addr; int mask; @@ -181,7 +181,7 @@ static inline void __change_bit(int nr, volatile void *addr) *a ^= mask; } -static inline int __test_and_clear_bit(int nr, volatile void * addr) +static inline int __test_and_clear_bit(unsigned long nr, volatile void *addr) { volatile unsigned long *a = addr; int mask, retval; @@ -193,7 +193,7 @@ static inline int __test_and_clear_bit(int nr, volatile void * addr) return retval; } -static inline int __test_and_set_bit(int nr, volatile void * addr) +static inline int __test_and_set_bit(unsigned long nr, volatile void *addr) { volatile unsigned long *a = addr; int mask, retval; @@ -205,7 +205,7 @@ static inline int __test_and_set_bit(int nr, volatile void * addr) return retval; } -static inline int __test_and_change_bit(int nr, volatile void * addr) +static inline int __test_and_change_bit(unsigned long nr, volatile void *addr) { volatile unsigned long *a = addr; int mask, retval; @@ -220,12 +220,13 @@ static inline int __test_and_change_bit(int nr, volatile void * addr) /* * This routine doesn't need to be atomic. */ -static inline int __constant_test_bit(int nr, const volatile void * addr) +static inline int +__constant_test_bit(unsigned long nr, const volatile void *addr) { return ((1UL << (nr & 31)) & (((const volatile unsigned int *) addr)[nr >> 5])) != 0; } -static inline int __test_bit(int nr, const volatile void * addr) +static inline int __test_bit(unsigned long nr, const volatile void *addr) { int * a = (int *) addr; int mask; diff --git a/arch/frv/include/asm/elf.h b/arch/frv/include/asm/elf.h index 7279ec07d62e32007f91a01bfe58a20014283a4d..7bbf6e47f8c8a5cb216c9b8f5e0b8be3b902c5bb 100644 --- a/arch/frv/include/asm/elf.h +++ b/arch/frv/include/asm/elf.h @@ -116,6 +116,7 @@ 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/arch/frv/include/asm/pci.h b/arch/frv/include/asm/pci.h index 585d9b49949a7537d9d1f89221f93c047cfedacf..cc685e60b0f9ce92c06372cd695346a3b3ba6b17 100644 --- a/arch/frv/include/asm/pci.h +++ b/arch/frv/include/asm/pci.h @@ -87,8 +87,7 @@ static inline void pci_dma_sync_single(struct pci_dev *hwdev, dma_addr_t dma_handle, size_t size, int direction) { - if (direction == PCI_DMA_NONE) - BUG(); + BUG_ON(direction == PCI_DMA_NONE); frv_cache_wback_inv((unsigned long)bus_to_virt(dma_handle), (unsigned long)bus_to_virt(dma_handle) + size); @@ -105,9 +104,7 @@ static inline void pci_dma_sync_sg(struct pci_dev *hwdev, int nelems, int direction) { int i; - - if (direction == PCI_DMA_NONE) - BUG(); + BUG_ON(direction == PCI_DMA_NONE); for (i = 0; i < nelems; i++) frv_cache_wback_inv(sg_dma_address(&sg[i]), diff --git a/arch/frv/include/asm/ptrace.h b/arch/frv/include/asm/ptrace.h index cf6934012b64dc70736e26073470e143b2ed11ab..a54b535c9e493f2ba18fa0974993d5859e18bf0a 100644 --- a/arch/frv/include/asm/ptrace.h +++ b/arch/frv/include/asm/ptrace.h @@ -65,6 +65,8 @@ #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 @@ -73,11 +75,18 @@ 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) -#endif + +#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 /* !__ASSEMBLY__ */ +#endif /* __KERNEL__ */ #endif /* _ASM_PTRACE_H */ diff --git a/arch/frv/include/asm/syscall.h b/arch/frv/include/asm/syscall.h new file mode 100644 index 0000000000000000000000000000000000000000..70689eb29b98848eb2abf269cf82ad6a7f1b8895 --- /dev/null +++ b/arch/frv/include/asm/syscall.h @@ -0,0 +1,123 @@ +/* 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/arch/frv/include/asm/thread_info.h b/arch/frv/include/asm/thread_info.h index bb53ab753ffbf7b3a62e9e105583b4339d9768ce..e8a5ed7be0212791674996fd16afeb4f38a6b751 100644 --- a/arch/frv/include/asm/thread_info.h +++ b/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_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_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_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/arch/frv/kernel/entry.S b/arch/frv/kernel/entry.S index 1da523b3298e03a36c8e27e23bf9d20f10615e67..356e0e327a8923f87d366776f06e5b916852bf56 100644 --- a/arch/frv/kernel/entry.S +++ b/arch/frv/kernel/entry.S @@ -886,7 +886,6 @@ 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 @@ -1150,11 +1149,10 @@ __entry_work_notifysig: # perform syscall entry tracing __syscall_trace_entry: LEDS 0x6320 - setlos.p #0,gr8 - call do_syscall_trace + call syscall_trace_entry - ldi @(gr28,#REG_SYSCALLNO),gr7 - lddi @(gr28,#REG_GR(8)) ,gr8 + lddi.p @(gr28,#REG_GR(8)) ,gr8 + ori gr8,#0,gr7 ; syscall_trace_entry() returned new syscallno lddi @(gr28,#REG_GR(10)),gr10 lddi.p @(gr28,#REG_GR(12)),gr12 @@ -1169,11 +1167,10 @@ __syscall_exit_work: beq icc0,#1,__entry_work_pending movsg psr,gr23 - andi gr23,#~PSR_PIL,gr23 ; could let do_syscall_trace() call schedule() + andi gr23,#~PSR_PIL,gr23 ; could let syscall_trace_exit() call schedule() movgs gr23,psr - setlos.p #1,gr8 - call do_syscall_trace + call syscall_trace_exit bra __entry_resume_userspace __syscall_badsys: diff --git a/arch/frv/kernel/ptrace.c b/arch/frv/kernel/ptrace.c index 5e7d401d21e7d6455883f118213a040e97754fbf..60eeed3694c0764d2d0b9d7d3a0c2cffe14b9a89 100644 --- a/arch/frv/kernel/ptrace.c +++ b/arch/frv/kernel/ptrace.c @@ -19,6 +19,9 @@ #include #include #include +#include +#include +#include #include #include @@ -32,6 +35,169 @@ * 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. */ @@ -68,41 +234,24 @@ static inline int put_reg(struct task_struct *task, int regno, } } -/* - * check that an address falls within the bounds of the target process's memory - * mappings - */ -static inline int is_user_addr_valid(struct task_struct *child, - unsigned long start, unsigned long len) -{ -#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 -} - /* * Called by kernel/ptrace.c when detaching.. * * Control h/w single stepping */ -void ptrace_disable(struct task_struct *child) +void user_enable_single_step(struct task_struct *child) +{ + child->thread.frame0->__status |= REG__STATUS_STEP; +} + +void user_disable_single_step(struct task_struct *child) { child->thread.frame0->__status &= ~REG__STATUS_STEP; } -void ptrace_enable(struct task_struct *child) +void ptrace_disable(struct task_struct *child) { - child->thread.frame0->__status |= REG__STATUS_STEP; + user_disable_single_step(child); } long arch_ptrace(struct task_struct *child, long request, long addr, long data) @@ -111,15 +260,6 @@ 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; @@ -163,15 +303,6 @@ 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) @@ -179,7 +310,7 @@ 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; @@ -189,95 +320,29 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) } break; - 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_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_GETFDPIC: tmp = 0; @@ -300,414 +365,36 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) break; default: - ret = -EIO; + ret = ptrace_request(child, request, addr, data); break; } return ret; } -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) +/* + * 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) { -#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; - } - - 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); + __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; } - return; -#endif - - 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); + return __frame->syscallno; +} - /* - * 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; - } +/* + * handle tracing of system call exit + */ +asmlinkage void syscall_trace_exit(void) +{ + __frame->__status |= REG__STATUS_SYSC_EXIT; + tracehook_report_syscall_exit(__frame, 0); } diff --git a/arch/frv/kernel/signal.c b/arch/frv/kernel/signal.c index 3bdb368292a8c8a53f9c00b3aa39dc169420b095..4a7a62c6e7833ed91a9087b3762cb3d0ba24df5f 100644 --- a/arch/frv/kernel/signal.c +++ b/arch/frv/kernel/signal.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -516,6 +517,9 @@ 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; @@ -564,4 +568,10 @@ 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/arch/frv/kernel/uaccess.c b/arch/frv/kernel/uaccess.c index 9fb771a20df3cf831f4779aba7859e4c865928de..374f88d6cc00d0c32fffd03f5c7b3a8b1af395ee 100644 --- a/arch/frv/kernel/uaccess.c +++ b/arch/frv/kernel/uaccess.c @@ -23,8 +23,7 @@ long strncpy_from_user(char *dst, const char __user *src, long count) char *p, ch; long err = -EFAULT; - if (count < 0) - BUG(); + BUG_ON(count < 0); p = dst; @@ -76,8 +75,7 @@ long strnlen_user(const char __user *src, long count) long err = 0; char ch; - if (count < 0) - BUG(); + BUG_ON(count < 0); #ifndef CONFIG_MMU if ((unsigned long) src < memory_start) diff --git a/arch/frv/mb93090-mb00/pci-dma-nommu.c b/arch/frv/mb93090-mb00/pci-dma-nommu.c index 52ff9aec799d29c84a649aa128ccb985b60cd68c..4e1ba0b15443a86ac4f5fd12bb34b552c392a768 100644 --- a/arch/frv/mb93090-mb00/pci-dma-nommu.c +++ b/arch/frv/mb93090-mb00/pci-dma-nommu.c @@ -116,8 +116,7 @@ EXPORT_SYMBOL(dma_free_coherent); dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size, enum dma_data_direction direction) { - if (direction == DMA_NONE) - BUG(); + BUG_ON(direction == DMA_NONE); frv_cache_wback_inv((unsigned long) ptr, (unsigned long) ptr + size); @@ -151,8 +150,7 @@ 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])); - if (direction == DMA_NONE) - BUG(); + BUG_ON(direction == DMA_NONE); return nents; } diff --git a/arch/frv/mb93090-mb00/pci-dma.c b/arch/frv/mb93090-mb00/pci-dma.c index 3ddedebc4eb3db1a1bbc25a7a10dd2e1fd1e66e5..45954f0813dc9e75a5e15f06e5cdb13776170c30 100644 --- a/arch/frv/mb93090-mb00/pci-dma.c +++ b/arch/frv/mb93090-mb00/pci-dma.c @@ -48,8 +48,7 @@ EXPORT_SYMBOL(dma_free_coherent); dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size, enum dma_data_direction direction) { - if (direction == DMA_NONE) - BUG(); + BUG_ON(direction == DMA_NONE); frv_cache_wback_inv((unsigned long) ptr, (unsigned long) ptr + size); @@ -81,8 +80,7 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, void *vaddr; int i; - if (direction == DMA_NONE) - BUG(); + BUG_ON(direction == DMA_NONE); dampr2 = __get_DAMPR(2); diff --git a/arch/h8300/include/asm/flat.h b/arch/h8300/include/asm/flat.h index 2a873508a9a101b359483ebbf086f84aa769f0f0..bd12b31b90e60b3df56b0d8080e4bd86df98ce79 100644 --- a/arch/h8300/include/asm/flat.h +++ b/arch/h8300/include/asm/flat.h @@ -5,7 +5,6 @@ #ifndef __H8300_FLAT_H__ #define __H8300_FLAT_H__ -#define flat_stack_align(sp) /* nothing needed */ #define flat_argvp_envp_on_stack() 1 #define flat_old_ram_flag(flags) 1 #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) diff --git a/arch/ia64/hp/sim/hpsim_irq.c b/arch/ia64/hp/sim/hpsim_irq.c index cc0a3182db3c0158d246f658065a0f0f5d426a5f..acb5047ab57341d9818160f361db47c7e6e59313 100644 --- a/arch/ia64/hp/sim/hpsim_irq.c +++ b/arch/ia64/hp/sim/hpsim_irq.c @@ -21,9 +21,10 @@ hpsim_irq_noop (unsigned int irq) { } -static void +static int 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/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h index 4542651e6acb1e82f3f4665ebca0705a9e6161aa..5f43697aed3018f5d821a10d641642de88473c32 100644 --- a/arch/ia64/include/asm/kvm_host.h +++ b/arch/ia64/include/asm/kvm_host.h @@ -371,6 +371,7 @@ 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 @@ -465,6 +466,7 @@ struct kvm_arch { unsigned long vmm_init_rr; int online_vcpus; + int is_sn2; struct kvm_ioapic *vioapic; struct kvm_vm_stat stat; @@ -472,6 +474,7 @@ 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; @@ -578,6 +581,8 @@ 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); @@ -585,7 +590,6 @@ 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/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index 7a9bff47564f10c3165123e378ce226e90d55f2b..0a9cc73d35c78fac88f4733511021849a0b2a248 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -146,6 +146,8 @@ #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/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 5510317db37b2a439711bb3fa97d6af0c7cd00bf..baec6f00f7f3feee71c5110b01f12b5c8b3f4fda 100644 --- a/arch/ia64/kernel/acpi.c +++ b/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(u32 gsi, int triggering, int polarity) +int acpi_register_gsi(struct device *dev, u32 gsi, int triggering, int polarity) { if (acpi_irq_model == ACPI_IRQ_MODEL_PLATFORM) return gsi; @@ -678,7 +678,8 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table) fadt = (struct acpi_table_fadt *)fadt_header; - acpi_register_gsi(fadt->sci_interrupt, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW); + acpi_register_gsi(NULL, fadt->sci_interrupt, ACPI_LEVEL_SENSITIVE, + ACPI_ACTIVE_LOW); return 0; } diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index 166e0d839fa04d753fa3709bfe62544eee32e9ec..f92cef47bf862ed8cd3943875585535e0c412763 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -329,7 +329,7 @@ unmask_irq (unsigned int irq) } -static void +static int 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; + return -1; if (irq_prepare_move(irq, cpu)) - return; + return -1; dest = cpu_physical_id(cpu); if (!iosapic_intr_info[irq].count) - return; /* not an IOSAPIC interrupt */ + return -1; /* not an IOSAPIC interrupt */ set_irq_affinity_info(irq, dest, redir); @@ -376,7 +376,9 @@ 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/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index acc4d19ae62ad17fd956f914a0829a6bda3b8589..b448197728be5cc22b91fd92f2c49d2cee0f455f 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -610,6 +610,9 @@ 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/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c index 2b15e233f7fef6b016f50367c90f9c91ba096b63..0f8ade9331badf4acaf29818dcad0dc67b31fd5e 100644 --- a/arch/ia64/kernel/msi_ia64.c +++ b/arch/ia64/kernel/msi_ia64.c @@ -12,7 +12,7 @@ static struct irq_chip ia64_msi_chip; #ifdef CONFIG_SMP -static void ia64_set_msi_irq_affinity(unsigned int irq, +static int ia64_set_msi_irq_affinity(unsigned int irq, const cpumask_t *cpu_mask) { struct msi_msg msg; @@ -20,10 +20,10 @@ static void ia64_set_msi_irq_affinity(unsigned int irq, int cpu = first_cpu(*cpu_mask); if (!cpu_online(cpu)) - return; + return -1; if (irq_prepare_move(irq, cpu)) - return; + return -1; read_msi_msg(irq, &msg); @@ -39,6 +39,8 @@ static void 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 */ @@ -130,17 +132,17 @@ void arch_teardown_msi_irq(unsigned int irq) #ifdef CONFIG_DMAR #ifdef CONFIG_SMP -static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask) +static int 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; + return -1; if (irq_prepare_move(irq, cpu)) - return; + return -1; dmar_msi_read(irq, &msg); @@ -151,6 +153,8 @@ static void 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/arch/ia64/kvm/Kconfig b/arch/ia64/kvm/Kconfig index 0a2d6b86075a66ce45908ee6fc66f2cd981b4c8c..64d5209378749ff7175f8218fdbb546ee6310315 100644 --- a/arch/ia64/kvm/Kconfig +++ b/arch/ia64/kvm/Kconfig @@ -23,7 +23,7 @@ if VIRTUALIZATION config KVM tristate "Kernel-based Virtual Machine (KVM) support" - depends on HAVE_KVM && EXPERIMENTAL + depends on HAVE_KVM && MODULES && EXPERIMENTAL # for device assignment: depends on PCI select PREEMPT_NOTIFIERS diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index d20a5db4c4dde90674debfd2eb370b4434870b89..80c57b0a21c479ee593fb095bc8429089eced2f5 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -41,6 +41,9 @@ #include #include #include +#include +#include +#include #include "misc.h" #include "vti.h" @@ -65,6 +68,16 @@ 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; @@ -119,8 +132,7 @@ 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); @@ -283,6 +295,18 @@ 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. @@ -292,20 +316,20 @@ 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: - kvm_apic_set_irq(vcpu, 2, 0); + vector = 2; break; case SAPIC_EXTINT: - kvm_apic_set_irq(vcpu, 0, 0); + vector = 0; break; case SAPIC_INIT: case SAPIC_PMI: default: printk(KERN_ERR"kvm: Unimplemented Deliver reserved IPI!\n"); - break; + return; } + __apic_accept_irq(vcpu, vector); } static struct kvm_vcpu *lid_to_vcpu(struct kvm *kvm, unsigned long id, @@ -413,6 +437,23 @@ 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) { @@ -426,7 +467,7 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) if (irqchip_in_kernel(vcpu->kvm)) { - vcpu_now_itc = ia64_getreg(_IA64_REG_AR_ITC) + vcpu->arch.itc_offset; + vcpu_now_itc = kvm_get_itc(vcpu) + vcpu->arch.itc_offset; if (time_after(vcpu_now_itc, vpd->itm)) { vcpu->arch.timer_check = 1; @@ -447,10 +488,10 @@ 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)) + if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests) || + kvm_cpu_has_pending_timer(vcpu)) 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; @@ -551,22 +592,35 @@ 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 || @@ -578,36 +632,27 @@ 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); - return kvm_insert_vmm_mapping(vcpu); + local_irq_save(psr); + r = kvm_insert_vmm_mapping(vcpu); + local_irq_restore(psr); + return r; } + static void kvm_vcpu_post_transition(struct kvm_vcpu *vcpu) { kvm_purge_vmm_mapping(vcpu); vti_set_rr6(vcpu->arch.host_rr6); } -static int vti_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { union context *host_ctx, *guest_ctx; int r; - /*Get host and guest context with guest address space.*/ - host_ctx = kvm_get_host_context(vcpu); - guest_ctx = kvm_get_guest_context(vcpu); - - r = kvm_vcpu_pre_transition(vcpu); - if (r < 0) - goto out; - kvm_vmm_info->tramp_entry(host_ctx, guest_ctx); - kvm_vcpu_post_transition(vcpu); - r = 0; -out: - return r; -} - -static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - int r; + /* + * down_read() may sleep and return with interrupts enabled + */ + down_read(&vcpu->kvm->slots_lock); again: if (signal_pending(current)) { @@ -616,26 +661,31 @@ again: goto out; } - /* - * down_read() may sleep and return with interrupts enabled - */ - down_read(&vcpu->kvm->slots_lock); - preempt_disable(); local_irq_disable(); - vcpu->guest_mode = 1; + /*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); kvm_guest_enter(); - r = vti_vcpu_run(vcpu, kvm_run); - if (r < 0) { - local_irq_enable(); - preempt_enable(); - kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; - goto out; - } + + /* + * Transition to the guest + */ + kvm_vmm_info->tramp_entry(host_ctx, guest_ctx); + + kvm_vcpu_post_transition(vcpu); vcpu->arch.launched = 1; - vcpu->guest_mode = 0; + set_bit(KVM_REQ_KICK, &vcpu->requests); local_irq_enable(); /* @@ -646,9 +696,10 @@ again: */ 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) { @@ -657,12 +708,20 @@ again: } 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) @@ -788,6 +847,9 @@ 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; @@ -884,7 +946,7 @@ 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 - ia64_getreg(_IA64_REG_AR_ITC); + vcpu->arch.itc_offset = regs->saved_itc - kvm_get_itc(vcpu); set_bit(KVM_REQ_RESUME, &vcpu->requests); vcpu_put(vcpu); @@ -1043,10 +1105,6 @@ 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; @@ -1165,7 +1223,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) regs->cr_iip = PALE_RESET_ENTRY; /*Initialize itc offset for vcpus*/ - itc_offset = 0UL - ia64_getreg(_IA64_REG_AR_ITC); + itc_offset = 0UL - kvm_get_itc(vcpu); for (i = 0; i < kvm->arch.online_vcpus; i++) { v = (struct kvm_vcpu *)((char *)vcpu + sizeof(struct kvm_vcpu_data) * i); @@ -1237,6 +1295,7 @@ 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); @@ -1254,13 +1313,11 @@ 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; } @@ -1291,7 +1348,6 @@ 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(); @@ -1427,7 +1483,7 @@ 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 + ia64_getreg(_IA64_REG_AR_ITC); + regs->saved_itc = vcpu->arch.itc_offset + kvm_get_itc(vcpu); SAVE_REGS(xtp); SAVE_REGS(metaphysical_rr0); SAVE_REGS(metaphysical_rr4); @@ -1574,6 +1630,7 @@ 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, @@ -1616,8 +1673,37 @@ out: 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; @@ -1639,6 +1725,7 @@ 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*/ @@ -1792,38 +1879,24 @@ void kvm_arch_hardware_unsetup(void) { } -static void vcpu_kick_intr(void *info) -{ -#ifdef DEBUG - struct kvm_vcpu *vcpu = (struct kvm_vcpu *)info; - printk(KERN_DEBUG"vcpu_kick_intr %p \n", vcpu); -#endif -} - void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { - int ipi_pcpu = vcpu->cpu; - int cpu = get_cpu(); + int me; + int cpu = vcpu->cpu; if (waitqueue_active(&vcpu->wq)) wake_up_interruptible(&vcpu->wq); - if (vcpu->guest_mode && cpu != ipi_pcpu) - smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0); + 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); put_cpu(); } -int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig) +int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq) { - - 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; + return __apic_accept_irq(vcpu, irq->vector); } int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest) @@ -1836,20 +1909,18 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda) return 0; } -struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector, - unsigned long bitmap) +int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) { - struct kvm_vcpu *lvcpu = kvm->vcpus[0]; - int i; - - 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 vcpu1->arch.xtp - vcpu2->arch.xtp; +} - return lvcpu; +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); } static int find_highest_bits(int *dat) @@ -1888,6 +1959,12 @@ 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; @@ -1918,6 +1995,7 @@ 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; @@ -1930,7 +2008,6 @@ 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/arch/ia64/kvm/kvm_fw.c b/arch/ia64/kvm/kvm_fw.c index a8ae52ed56358e3e3d1b81edf095ebfceaa36a3b..e4b82319881db227044550b3330f1eea69770f50 100644 --- a/arch/ia64/kvm/kvm_fw.c +++ b/arch/ia64/kvm/kvm_fw.c @@ -21,6 +21,9 @@ #include #include +#include +#include +#include #include "vti.h" #include "misc.h" @@ -188,12 +191,35 @@ static struct ia64_pal_retval pal_freq_base(struct kvm_vcpu *vcpu) return result; } -static struct ia64_pal_retval pal_freq_ratios(struct kvm_vcpu *vcpu) +/* + * 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/arch/ia64/kvm/lapic.h b/arch/ia64/kvm/lapic.h index 6d6cbcb14893c281952f82365779cf925cf7f0e0..ee541cebcd78aa7442aff169308a17e0259bc8c4 100644 --- a/arch/ia64/kvm/lapic.h +++ b/arch/ia64/kvm/lapic.h @@ -20,6 +20,10 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu); int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest); int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda); -int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig); +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) #endif diff --git a/arch/ia64/kvm/optvfault.S b/arch/ia64/kvm/optvfault.S index 32254ce9a1bda61a25f3edce6143206a7d651aa1..f793be3effff5a773c3f5586994b374d1a5d2f82 100644 --- a/arch/ia64/kvm/optvfault.S +++ b/arch/ia64/kvm/optvfault.S @@ -11,6 +11,7 @@ #include #include +#include #include "vti.h" #include "asm-offsets.h" @@ -140,6 +141,35 @@ 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/arch/ia64/kvm/vcpu.c b/arch/ia64/kvm/vcpu.c index a18ee17b9192e01f3c3f1683817be3ae775e1ca7..a2c6c15e4761871ffe98f5bba8b52b6b70691056 100644 --- a/arch/ia64/kvm/vcpu.c +++ b/arch/ia64/kvm/vcpu.c @@ -788,13 +788,29 @@ 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) + ia64_getreg(_IA64_REG_AR_ITC); + guest_itc = VMX(vcpu, itc_offset) + kvm_get_itc(vcpu); if (guest_itc >= VMX(vcpu, last_itc)) { VMX(vcpu, last_itc) = guest_itc; @@ -809,7 +825,7 @@ static void vcpu_set_itc(struct kvm_vcpu *vcpu, u64 val) struct kvm_vcpu *v; struct kvm *kvm; int i; - long itc_offset = val - ia64_getreg(_IA64_REG_AR_ITC); + long itc_offset = val - kvm_get_itc(vcpu); unsigned long vitv = VCPU(vcpu, itv); kvm = (struct kvm *)KVM_VM_BASE; diff --git a/arch/ia64/kvm/vmm.c b/arch/ia64/kvm/vmm.c index 9eee5c04baccceaaf646d72922d3403cf313e2d5..f4b4c899bb6ce9d77d42d7a796931cb13e47ab03 100644 --- a/arch/ia64/kvm/vmm.c +++ b/arch/ia64/kvm/vmm.c @@ -30,15 +30,19 @@ 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, + .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, }; static int __init kvm_vmm_init(void) diff --git a/arch/ia64/kvm/vmm_ivt.S b/arch/ia64/kvm/vmm_ivt.S index 3ef1a017a3189e76e713767f56d7c3a9e95fdb3c..40920c630649c3affa7556c355fea302b614f2a3 100644 --- a/arch/ia64/kvm/vmm_ivt.S +++ b/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.i + (p15) ssm psr.i // restore psr. 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/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c index 2c2501f131597c6389e82e6c4e3e62eb6ecf7f80..4290a429bf7c9b48f0cd9ff049d60626e23af689 100644 --- a/arch/ia64/kvm/vtlb.c +++ b/arch/ia64/kvm/vtlb.c @@ -254,7 +254,8 @@ u64 guest_vhpt_lookup(u64 iha, u64 *pte) "(p7) st8 [%2]=r9;;" "ssm psr.ic;;" "srlz.d;;" - /* "ssm psr.i;;" Once interrupts in vmm open, need fix*/ + "ssm psr.i;;" + "srlz.d;;" : "=r"(ret) : "r"(iha), "r"(pte):"memory"); return ret; diff --git a/arch/ia64/sn/kernel/irq.c b/arch/ia64/sn/kernel/irq.c index 66fd705e82c09ee1e1905356cf447526461c086a..764f26abac05df5e9d7659ff7254da6fde398301 100644 --- a/arch/ia64/sn/kernel/irq.c +++ b/arch/ia64/sn/kernel/irq.c @@ -227,7 +227,7 @@ finish_up: return new_irq_info; } -static void sn_set_affinity_irq(unsigned int irq, const struct cpumask *mask) +static int 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; @@ -239,6 +239,8 @@ static void 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/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c index 81e428943d7374d01e0aef8530e39c7ecd892b30..fbbfb970120128a29df68c549895187ea3e3013e 100644 --- a/arch/ia64/sn/kernel/msi_sn.c +++ b/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 void sn_set_msi_irq_affinity(unsigned int irq, +static int sn_set_msi_irq_affinity(unsigned int irq, const struct cpumask *cpu_mask) { struct msi_msg msg; @@ -168,7 +168,7 @@ static void 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; + return -1; /* * Release XIO resources for the old MSI PCI address @@ -189,7 +189,7 @@ static void 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; + return -1; /* * Map the xio address into bus space @@ -206,6 +206,8 @@ static void 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/arch/m32r/include/asm/flat.h b/arch/m32r/include/asm/flat.h index d851cf0c4aa5ecff7902da7a54fdab618eccdad4..5d711c4688fb9f8162fd017a7e35451ad4c41da6 100644 --- a/arch/m32r/include/asm/flat.h +++ b/arch/m32r/include/asm/flat.h @@ -12,7 +12,6 @@ #ifndef __ASM_M32R_FLAT_H #define __ASM_M32R_FLAT_H -#define flat_stack_align(sp) (*sp += (*sp & 3 ? (4 - (*sp & 3)): 0)) #define flat_argvp_envp_on_stack() 0 #define flat_old_ram_flag(flags) (flags) #define flat_set_persistent(relval, p) 0 diff --git a/arch/m68k/include/asm/flat.h b/arch/m68k/include/asm/flat.h index 814b5174a8e0ffb623aa96e65f9b2a1b52a4ddad..a0e290793978b35dd89586eba50c4e1f7950f1ca 100644 --- a/arch/m68k/include/asm/flat.h +++ b/arch/m68k/include/asm/flat.h @@ -5,7 +5,6 @@ #ifndef __M68KNOMMU_FLAT_H__ #define __M68KNOMMU_FLAT_H__ -#define flat_stack_align(sp) /* nothing needed */ #define flat_argvp_envp_on_stack() 1 #define flat_old_ram_flag(flags) (flags) #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) diff --git a/arch/m68k/include/asm/m520xsim.h b/arch/m68k/include/asm/m520xsim.h index 49d016e6391a3417289bca0b79d1380e66e0ac76..83bbcfd6e8f2b9d17aaff1eb908ee568967eb268 100644 --- a/arch/m68k/include/asm/m520xsim.h +++ b/arch/m68k/include/asm/m520xsim.h @@ -59,5 +59,14 @@ #define MCFPIT_IMR MCFINTC_IMRL #define MCFPIT_IMR_IBIT (1 << MCFINT_PIT1) +/* + * Reset Controll Unit. + */ +#define MCF_RCR 0xFC0A0000 +#define MCF_RSR 0xFC0A0001 + +#define MCF_RCR_SWRESET 0x80 /* Software reset bit */ +#define MCF_RCR_FRCSTOUT 0x40 /* Force external reset */ + /****************************************************************************/ #endif /* m520xsim_h */ diff --git a/arch/m68k/include/asm/m523xsim.h b/arch/m68k/include/asm/m523xsim.h index bf397313e93f11b380b6dc13120751df9a3d1699..55183b5df1b8716bd500c12013cbae45c86b8e52 100644 --- a/arch/m68k/include/asm/m523xsim.h +++ b/arch/m68k/include/asm/m523xsim.h @@ -41,5 +41,14 @@ #define MCFSIM_DACR1 0x50 /* SDRAM base address 1 */ #define MCFSIM_DMR1 0x54 /* SDRAM address mask 1 */ +/* + * Reset Controll Unit (relative to IPSBAR). + */ +#define MCF_RCR 0x110000 +#define MCF_RSR 0x110001 + +#define MCF_RCR_SWRESET 0x80 /* Software reset bit */ +#define MCF_RCR_FRCSTOUT 0x40 /* Force external reset */ + /****************************************************************************/ #endif /* m523xsim_h */ diff --git a/arch/m68k/include/asm/m527xsim.h b/arch/m68k/include/asm/m527xsim.h index 1f63ab3fb3e671fd3b44ee731664c1a9c6709c86..95f4f8ee8f7c4131dca96d35cf87ea082d6e110d 100644 --- a/arch/m68k/include/asm/m527xsim.h +++ b/arch/m68k/include/asm/m527xsim.h @@ -70,5 +70,14 @@ #define UART2_ENABLE_MASK 0x3f00 #endif +/* + * Reset Controll Unit (relative to IPSBAR). + */ +#define MCF_RCR 0x110000 +#define MCF_RSR 0x110001 + +#define MCF_RCR_SWRESET 0x80 /* Software reset bit */ +#define MCF_RCR_FRCSTOUT 0x40 /* Force external reset */ + /****************************************************************************/ #endif /* m527xsim_h */ diff --git a/arch/m68k/include/asm/m528xsim.h b/arch/m68k/include/asm/m528xsim.h index 28bf783a5d6df7302d03371ae7ad6528750eb064..d79c49f8134ab05583aa8ef91f88ca60b161d71c 100644 --- a/arch/m68k/include/asm/m528xsim.h +++ b/arch/m68k/include/asm/m528xsim.h @@ -56,6 +56,14 @@ #define MCF5282_INTC0_ICR17 (volatile u8 *) (MCF_IPSBAR + 0x0C51) +/* + * Reset Control Unit (relative to IPSBAR). + */ +#define MCF_RCR 0x110000 +#define MCF_RSR 0x110001 + +#define MCF_RCR_SWRESET 0x80 /* Software reset bit */ +#define MCF_RCR_FRCSTOUT 0x40 /* Force external reset */ /********************************************************************* * diff --git a/arch/m68k/include/asm/m532xsim.h b/arch/m68k/include/asm/m532xsim.h index ce603451b55e33c4d7290b61cdd26fcf722ef2a0..eb7fd444894748ccadc262093b09712ecebcfd77 100644 --- a/arch/m68k/include/asm/m532xsim.h +++ b/arch/m68k/include/asm/m532xsim.h @@ -125,6 +125,18 @@ #define ACR_CM_OFF_IMP (3<<5) #define ACR_WPROTECT (1<<2) +/********************************************************************* + * + * Reset Controller Module + * + *********************************************************************/ + +#define MCF_RCR 0xFC0A0000 +#define MCF_RSR 0xFC0A0001 + +#define MCF_RCR_SWRESET 0x80 /* Software reset bit */ +#define MCF_RCR_FRCSTOUT 0x40 /* Force external reset */ + /********************************************************************* * * Inter-IC (I2C) Module diff --git a/arch/m68k/include/asm/processor_no.h b/arch/m68k/include/asm/processor_no.h index 91cba18acdd32a5f14c220aee136649e88262947..7a1e0ba35f5adaf90111835ca718b832e1da5810 100644 --- a/arch/m68k/include/asm/processor_no.h +++ b/arch/m68k/include/asm/processor_no.h @@ -72,10 +72,10 @@ struct thread_struct { unsigned char fpstate[FPSTATESIZE]; /* floating point state */ }; -#define INIT_THREAD { \ - sizeof(init_stack) + (unsigned long) init_stack, 0, \ - PS_S, __KERNEL_DS, \ - {0, 0}, 0, {0,}, {0, 0, 0}, {0,}, \ +#define INIT_THREAD { \ + .ksp = sizeof(init_stack) + (unsigned long) init_stack, \ + .sr = PS_S, \ + .fs = __KERNEL_DS, \ } /* diff --git a/arch/m68k/include/asm/swab.h b/arch/m68k/include/asm/swab.h index 9e3054ea59e933005f6f2fa475e39273c9635bf5..5b754aace744959af8918e2b94ab3f7351c1ed1c 100644 --- a/arch/m68k/include/asm/swab.h +++ b/arch/m68k/include/asm/swab.h @@ -1,7 +1,7 @@ #ifndef _M68K_SWAB_H #define _M68K_SWAB_H -#include +#include #include #define __SWAB_64_THRU_32__ diff --git a/arch/m68k/include/asm/system_no.h b/arch/m68k/include/asm/system_no.h index 4496c0aa83792da36f621da71936da4b09a5fbfb..3c0718d74398b3b7ce0b29bfb66b3f1895474db8 100644 --- a/arch/m68k/include/asm/system_no.h +++ b/arch/m68k/include/asm/system_no.h @@ -203,113 +203,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz #include #endif -#if defined( CONFIG_M68328 ) || defined( CONFIG_M68EZ328 ) || \ - defined (CONFIG_M68360) || defined( CONFIG_M68VZ328 ) -#define HARD_RESET_NOW() ({ \ - local_irq_disable(); \ - asm(" \ - moveal #0x10c00000, %a0; \ - moveb #0, 0xFFFFF300; \ - moveal 0(%a0), %sp; \ - moveal 4(%a0), %a0; \ - jmp (%a0); \ - "); \ -}) -#endif - -#ifdef CONFIG_COLDFIRE -#if defined(CONFIG_M5272) && defined(CONFIG_NETtel) -/* - * Need to account for broken early mask of 5272 silicon. So don't - * jump through the original start address. Jump strait into the - * known start of the FLASH code. - */ -#define HARD_RESET_NOW() ({ \ - asm(" \ - movew #0x2700, %sr; \ - jmp 0xf0000400; \ - "); \ -}) -#elif defined(CONFIG_NETtel) || \ - defined(CONFIG_SECUREEDGEMP3) || defined(CONFIG_CLEOPATRA) -#define HARD_RESET_NOW() ({ \ - asm(" \ - movew #0x2700, %sr; \ - moveal #0x10000044, %a0; \ - movel #0xffffffff, (%a0); \ - moveal #0x10000001, %a0; \ - moveb #0x00, (%a0); \ - moveal #0xf0000004, %a0; \ - moveal (%a0), %a0; \ - jmp (%a0); \ - "); \ -}) -#elif defined(CONFIG_M5272) -/* - * Retrieve the boot address in flash using CSBR0 and CSOR0 - * find the reset vector at flash_address + 4 (e.g. 0x400) - * remap it in the flash's current location (e.g. 0xf0000400) - * and jump there. - */ -#define HARD_RESET_NOW() ({ \ - asm(" \ - movew #0x2700, %%sr; \ - move.l %0+0x40,%%d0; \ - and.l %0+0x44,%%d0; \ - andi.l #0xfffff000,%%d0; \ - mov.l %%d0,%%a0; \ - or.l 4(%%a0),%%d0; \ - mov.l %%d0,%%a0; \ - jmp (%%a0);" \ - : /* No output */ \ - : "o" (*(char *)MCF_MBAR) ); \ -}) -#elif defined(CONFIG_M528x) -/* - * The MCF528x has a bit (SOFTRST) in memory (Reset Control Register RCR), - * that when set, resets the MCF528x. - */ -#define HARD_RESET_NOW() \ -({ \ - unsigned char volatile *reset; \ - asm("move.w #0x2700, %sr"); \ - reset = ((volatile unsigned char *)(MCF_IPSBAR + 0x110000)); \ - while(1) \ - *reset |= (0x01 << 7);\ -}) -#elif defined(CONFIG_M523x) -#define HARD_RESET_NOW() ({ \ - asm(" \ - movew #0x2700, %sr; \ - movel #0x01000000, %sp; \ - moveal #0x40110000, %a0; \ - moveb #0x80, (%a0); \ - "); \ -}) -#elif defined(CONFIG_M520x) - /* - * The MCF5208 has a bit (SOFTRST) in memory (Reset Control Register - * RCR), that when set, resets the MCF5208. - */ -#define HARD_RESET_NOW() \ -({ \ - unsigned char volatile *reset; \ - asm("move.w #0x2700, %sr"); \ - reset = ((volatile unsigned char *)(MCF_IPSBAR + 0xA0000)); \ - while(1) \ - *reset |= 0x80; \ -}) -#else -#define HARD_RESET_NOW() ({ \ - asm(" \ - movew #0x2700, %sr; \ - moveal #0x4, %a0; \ - moveal (%a0), %a0; \ - jmp (%a0); \ - "); \ -}) -#endif -#endif #define arch_align_stack(x) (x) diff --git a/arch/m68knommu/kernel/entry.S b/arch/m68knommu/kernel/entry.S index f4782d2dce8f7369fbdaeddd916dc61c57a2afa9..f56faa5c9cd91a06e2c24e153c3fd54fa72a183e 100644 --- a/arch/m68knommu/kernel/entry.S +++ b/arch/m68knommu/kernel/entry.S @@ -26,7 +26,6 @@ #include #include -#include #include #include #include diff --git a/arch/m68knommu/kernel/setup.c b/arch/m68knommu/kernel/setup.c index 5985f198902113d6ce971e975983fa09019db051..5c2bb3eeaaa2ec98ecdead8e7a2f03a3d9d51e34 100644 --- a/arch/m68knommu/kernel/setup.c +++ b/arch/m68knommu/kernel/setup.c @@ -166,15 +166,13 @@ void __init setup_arch(char **cmdline_p) printk(KERN_INFO "Motorola M5235EVB support (C)2005 Syn-tech Systems, Inc. (Jate Sujjavanich)\n"); #endif -#ifdef DEBUG - printk(KERN_DEBUG "KERNEL -> TEXT=0x%06x-0x%06x DATA=0x%06x-0x%06x " - "BSS=0x%06x-0x%06x\n", (int) &_stext, (int) &_etext, - (int) &_sdata, (int) &_edata, - (int) &_sbss, (int) &_ebss); - printk(KERN_DEBUG "MEMORY -> ROMFS=0x%06x-0x%06x MEM=0x%06x-0x%06x\n ", - (int) &_ebss, (int) memory_start, - (int) memory_start, (int) memory_end); -#endif + pr_debug("KERNEL -> TEXT=0x%06x-0x%06x DATA=0x%06x-0x%06x " + "BSS=0x%06x-0x%06x\n", (int) &_stext, (int) &_etext, + (int) &_sdata, (int) &_edata, + (int) &_sbss, (int) &_ebss); + pr_debug("MEMORY -> ROMFS=0x%06x-0x%06x MEM=0x%06x-0x%06x\n ", + (int) &_ebss, (int) memory_start, + (int) memory_start, (int) memory_end); /* Keep a copy of command line */ *cmdline_p = &command_line[0]; diff --git a/arch/m68knommu/mm/init.c b/arch/m68knommu/mm/init.c index 7befc0c357e0850a1635032c26c1632bd580c38c..b1703c67a4f195f54203e8cbeed93c3441b8d9a8 100644 --- a/arch/m68knommu/mm/init.c +++ b/arch/m68knommu/mm/init.c @@ -126,9 +126,7 @@ void __init mem_init(void) unsigned long start_mem = memory_start; /* DAVIDM - these must start at end of kernel */ unsigned long end_mem = memory_end; /* DAVIDM - this must not include kernel stack at top */ -#ifdef DEBUG - printk(KERN_DEBUG "Mem_init: start=%lx, end=%lx\n", start_mem, end_mem); -#endif + pr_debug("Mem_init: start=%lx, end=%lx\n", start_mem, end_mem); end_mem &= PAGE_MASK; high_memory = (void *) end_mem; diff --git a/arch/m68knommu/platform/5206/config.c b/arch/m68knommu/platform/5206/config.c index 53a5920c2b71ad68185ae2fe5ef08c6647c5af86..f6f79874e9af7a33da56676167b403d85844434e 100644 --- a/arch/m68knommu/platform/5206/config.c +++ b/arch/m68knommu/platform/5206/config.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -21,10 +20,6 @@ /***************************************************************************/ -void coldfire_reset(void); - -/***************************************************************************/ - static struct mcf_platform_uart m5206_uart_platform[] = { { .mapbase = MCF_MBAR + MCFUART_BASE1, @@ -109,10 +104,21 @@ void mcf_settimericr(unsigned int timer, unsigned int level) /***************************************************************************/ +void m5206_cpu_reset(void) +{ + local_irq_disable(); + /* Set watchdog to soft reset, and enabled */ + __raw_writeb(0xc0, MCF_MBAR + MCFSIM_SYPCR); + for (;;) + /* wait for watchdog to timeout */; +} + +/***************************************************************************/ + void __init config_BSP(char *commandp, int size) { mcf_setimr(MCFSIM_IMR_MASKALL); - mach_reset = coldfire_reset; + mach_reset = m5206_cpu_reset; } /***************************************************************************/ diff --git a/arch/m68knommu/platform/5206e/config.c b/arch/m68knommu/platform/5206e/config.c index db902540bf2c980fb8f2e4e89c1915dddbf5dc88..65887799db81271c044f043a05a2d2cbc619666f 100644 --- a/arch/m68knommu/platform/5206e/config.c +++ b/arch/m68knommu/platform/5206e/config.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include @@ -21,10 +20,6 @@ /***************************************************************************/ -void coldfire_reset(void); - -/***************************************************************************/ - static struct mcf_platform_uart m5206e_uart_platform[] = { { .mapbase = MCF_MBAR + MCFUART_BASE1, @@ -109,6 +104,17 @@ void mcf_settimericr(unsigned int timer, unsigned int level) /***************************************************************************/ +void m5206e_cpu_reset(void) +{ + local_irq_disable(); + /* Set watchdog to soft reset, and enabled */ + __raw_writeb(0xc0, MCF_MBAR + MCFSIM_SYPCR); + for (;;) + /* wait for watchdog to timeout */; +} + +/***************************************************************************/ + void __init config_BSP(char *commandp, int size) { mcf_setimr(MCFSIM_IMR_MASKALL); @@ -119,7 +125,7 @@ void __init config_BSP(char *commandp, int size) commandp[size-1] = 0; #endif /* CONFIG_NETtel */ - mach_reset = coldfire_reset; + mach_reset = m5206e_cpu_reset; } /***************************************************************************/ diff --git a/arch/m68knommu/platform/520x/config.c b/arch/m68knommu/platform/520x/config.c index 855fc6a79d72fc1b00af368b65002b27d8eca0f0..1c43a8aec69b90ddd892698301d3478c026bb98a 100644 --- a/arch/m68knommu/platform/520x/config.c +++ b/arch/m68knommu/platform/520x/config.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -23,10 +22,6 @@ /***************************************************************************/ -void coldfire_reset(void); - -/***************************************************************************/ - static struct mcf_platform_uart m520x_uart_platform[] = { { .mapbase = MCF_MBAR + MCFUART_BASE1, @@ -169,9 +164,17 @@ void mcf_autovector(unsigned int vec) /***************************************************************************/ +static void m520x_cpu_reset(void) +{ + local_irq_disable(); + __raw_writeb(MCF_RCR_SWRESET, MCF_RCR); +} + +/***************************************************************************/ + void __init config_BSP(char *commandp, int size) { - mach_reset = coldfire_reset; + mach_reset = m520x_cpu_reset; m520x_uarts_init(); m520x_fec_init(); } diff --git a/arch/m68knommu/platform/523x/config.c b/arch/m68knommu/platform/523x/config.c index 74133f27b30c4ce290fc4a9d21da49afc541fb9d..961fefebca14ebcf3c6e5954b6fbebfe65ecd092 100644 --- a/arch/m68knommu/platform/523x/config.c +++ b/arch/m68knommu/platform/523x/config.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include @@ -24,10 +23,6 @@ /***************************************************************************/ -void coldfire_reset(void); - -/***************************************************************************/ - static struct mcf_platform_uart m523x_uart_platform[] = { { .mapbase = MCF_MBAR + MCFUART_BASE1, @@ -145,13 +140,20 @@ void mcf_autovector(unsigned int vec) { /* Everything is auto-vectored on the 523x */ } +/***************************************************************************/ + +static void m523x_cpu_reset(void) +{ + local_irq_disable(); + __raw_writeb(MCF_RCR_SWRESET, MCF_IPSBAR + MCF_RCR); +} /***************************************************************************/ void __init config_BSP(char *commandp, int size) { mcf_disableall(); - mach_reset = coldfire_reset; + mach_reset = m523x_cpu_reset; m523x_uarts_init(); m523x_fec_init(); } diff --git a/arch/m68knommu/platform/5249/config.c b/arch/m68knommu/platform/5249/config.c index 9eab19d01eb1098f615694a577395fe77a693a31..93d998825925074addca47dee661c49dc8cec9be 100644 --- a/arch/m68knommu/platform/5249/config.c +++ b/arch/m68knommu/platform/5249/config.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include @@ -20,10 +19,6 @@ /***************************************************************************/ -void coldfire_reset(void); - -/***************************************************************************/ - static struct mcf_platform_uart m5249_uart_platform[] = { { .mapbase = MCF_MBAR + MCFUART_BASE1, @@ -106,10 +101,21 @@ void mcf_settimericr(unsigned int timer, unsigned int level) /***************************************************************************/ +void m5249_cpu_reset(void) +{ + local_irq_disable(); + /* Set watchdog to soft reset, and enabled */ + __raw_writeb(0xc0, MCF_MBAR + MCFSIM_SYPCR); + for (;;) + /* wait for watchdog to timeout */; +} + +/***************************************************************************/ + void __init config_BSP(char *commandp, int size) { mcf_setimr(MCFSIM_IMR_MASKALL); - mach_reset = coldfire_reset; + mach_reset = m5249_cpu_reset; } /***************************************************************************/ diff --git a/arch/m68knommu/platform/5272/config.c b/arch/m68knommu/platform/5272/config.c index e049245f4092a77e114bfabc6a8647d042759f81..5f95fcde05fd8a8a1e951b32594415bb27453154 100644 --- a/arch/m68knommu/platform/5272/config.c +++ b/arch/m68knommu/platform/5272/config.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -21,8 +20,6 @@ /***************************************************************************/ -void coldfire_reset(void); - extern unsigned int mcf_timervector; extern unsigned int mcf_profilevector; extern unsigned int mcf_timerlevel; @@ -170,6 +167,19 @@ void mcf_settimericr(int timer, int level) /***************************************************************************/ +static void m5272_cpu_reset(void) +{ + local_irq_disable(); + /* Set watchdog to reset, and enabled */ + __raw_writew(0, MCF_MBAR + MCFSIM_WIRR); + __raw_writew(1, MCF_MBAR + MCFSIM_WRRR); + __raw_writew(0, MCF_MBAR + MCFSIM_WCR); + for (;;) + /* wait for watchdog to timeout */; +} + +/***************************************************************************/ + void __init config_BSP(char *commandp, int size) { #if defined (CONFIG_MOD5272) @@ -194,7 +204,7 @@ void __init config_BSP(char *commandp, int size) mcf_timervector = 69; mcf_profilevector = 70; - mach_reset = coldfire_reset; + mach_reset = m5272_cpu_reset; } /***************************************************************************/ diff --git a/arch/m68knommu/platform/527x/config.c b/arch/m68knommu/platform/527x/config.c index 428b15922ef59113eebb6a322675098c731d0038..f746439cfd3ef9db0080b0d85f9d4f803c8b8d61 100644 --- a/arch/m68knommu/platform/527x/config.c +++ b/arch/m68knommu/platform/527x/config.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include @@ -24,10 +23,6 @@ /***************************************************************************/ -void coldfire_reset(void); - -/***************************************************************************/ - static struct mcf_platform_uart m527x_uart_platform[] = { { .mapbase = MCF_MBAR + MCFUART_BASE1, @@ -227,10 +222,18 @@ void mcf_autovector(unsigned int vec) /***************************************************************************/ +static void m527x_cpu_reset(void) +{ + local_irq_disable(); + __raw_writeb(MCF_RCR_SWRESET, MCF_IPSBAR + MCF_RCR); +} + +/***************************************************************************/ + void __init config_BSP(char *commandp, int size) { mcf_disableall(); - mach_reset = coldfire_reset; + mach_reset = m527x_cpu_reset; m527x_uarts_init(); m527x_fec_init(); } diff --git a/arch/m68knommu/platform/528x/config.c b/arch/m68knommu/platform/528x/config.c index bee526f4d1af7c94bf65fe11aaec08be3c0f8c85..a1d1a61c4fe667188fc1979df0630d7f5c7a547f 100644 --- a/arch/m68knommu/platform/528x/config.c +++ b/arch/m68knommu/platform/528x/config.c @@ -31,10 +31,6 @@ /***************************************************************************/ -void coldfire_reset(void); - -/***************************************************************************/ - static struct mcf_platform_uart m528x_uart_platform[] = { { .mapbase = MCF_MBAR + MCFUART_BASE1, @@ -171,6 +167,14 @@ void mcf_autovector(unsigned int vec) /***************************************************************************/ +static void m528x_cpu_reset(void) +{ + local_irq_disable(); + __raw_writeb(MCF_RCR_SWRESET, MCF_IPSBAR + MCF_RCR); +} + +/***************************************************************************/ + #ifdef CONFIG_WILDFIRE void wildfire_halt(void) { @@ -214,6 +218,7 @@ void __init config_BSP(char *commandp, int size) static int __init init_BSP(void) { + mach_reset = m528x_cpu_reset; m528x_uarts_init(); m528x_fec_init(); platform_add_devices(m528x_devices, ARRAY_SIZE(m528x_devices)); diff --git a/arch/m68knommu/platform/5307/config.c b/arch/m68knommu/platform/5307/config.c index 44803bf70a6e0988868f3bd6a8815e1a35e2312c..39da9e9ff674ef87a315a166f168fb979c250833 100644 --- a/arch/m68knommu/platform/5307/config.c +++ b/arch/m68knommu/platform/5307/config.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -22,8 +21,6 @@ /***************************************************************************/ -void coldfire_reset(void); - extern unsigned int mcf_timervector; extern unsigned int mcf_profilevector; extern unsigned int mcf_timerlevel; @@ -119,6 +116,17 @@ void mcf_settimericr(unsigned int timer, unsigned int level) /***************************************************************************/ +void m5307_cpu_reset(void) +{ + local_irq_disable(); + /* Set watchdog to soft reset, and enabled */ + __raw_writeb(0xc0, MCF_MBAR + MCFSIM_SYPCR); + for (;;) + /* wait for watchdog to timeout */; +} + +/***************************************************************************/ + void __init config_BSP(char *commandp, int size) { mcf_setimr(MCFSIM_IMR_MASKALL); @@ -134,7 +142,7 @@ void __init config_BSP(char *commandp, int size) mcf_timerlevel = 6; #endif - mach_reset = coldfire_reset; + mach_reset = m5307_cpu_reset; #ifdef CONFIG_BDM_DISABLE /* diff --git a/arch/m68knommu/platform/532x/config.c b/arch/m68knommu/platform/532x/config.c index 591f2f801134b495f1dfbf9f49a4868e20319c7b..cdb761971f7a7e8ca479766aeb2271d0688c52bf 100644 --- a/arch/m68knommu/platform/532x/config.c +++ b/arch/m68knommu/platform/532x/config.c @@ -31,8 +31,6 @@ /***************************************************************************/ -void coldfire_reset(void); - extern unsigned int mcf_timervector; extern unsigned int mcf_profilevector; extern unsigned int mcf_timerlevel; @@ -164,6 +162,14 @@ void mcf_settimericr(unsigned int timer, unsigned int level) /***************************************************************************/ +static void m532x_cpu_reset(void) +{ + local_irq_disable(); + __raw_writeb(MCF_RCR_SWRESET, MCF_RCR); +} + +/***************************************************************************/ + void __init config_BSP(char *commandp, int size) { mcf_setimr(MCFSIM_IMR_MASKALL); @@ -181,7 +187,7 @@ void __init config_BSP(char *commandp, int size) mcf_timervector = 64+32; mcf_profilevector = 64+33; - mach_reset = coldfire_reset; + mach_reset = m532x_cpu_reset; #ifdef CONFIG_BDM_DISABLE /* diff --git a/arch/m68knommu/platform/5407/config.c b/arch/m68knommu/platform/5407/config.c index 0ee8c1a200c87d5a4cad4e5e76421526fe947f1e..b41d942bf8d07e3bf0079bc53a1e0432b41daa93 100644 --- a/arch/m68knommu/platform/5407/config.c +++ b/arch/m68knommu/platform/5407/config.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -21,8 +20,6 @@ /***************************************************************************/ -void coldfire_reset(void); - extern unsigned int mcf_timervector; extern unsigned int mcf_profilevector; extern unsigned int mcf_timerlevel; @@ -110,6 +107,17 @@ void mcf_settimericr(unsigned int timer, unsigned int level) /***************************************************************************/ +void m5407_cpu_reset(void) +{ + local_irq_disable(); + /* set watchdog to soft reset, and enabled */ + __raw_writeb(0xc0, MCF_MBAR + MCFSIM_SYPCR); + for (;;) + /* wait for watchdog to timeout */; +} + +/***************************************************************************/ + void __init config_BSP(char *commandp, int size) { mcf_setimr(MCFSIM_IMR_MASKALL); @@ -121,7 +129,7 @@ void __init config_BSP(char *commandp, int size) mcf_timerlevel = 6; #endif - mach_reset = coldfire_reset; + mach_reset = m5407_cpu_reset; } /***************************************************************************/ diff --git a/arch/m68knommu/platform/coldfire/vectors.c b/arch/m68knommu/platform/coldfire/vectors.c index 6cf894620234c317e48dc68fd7956dd7f19460f3..bdca0297fa9a1f6fc261df8cd12c9f9d487ee25f 100644 --- a/arch/m68knommu/platform/coldfire/vectors.c +++ b/arch/m68knommu/platform/coldfire/vectors.c @@ -96,10 +96,3 @@ void ack_vector(unsigned int irq) } /***************************************************************************/ - -void coldfire_reset(void) -{ - HARD_RESET_NOW(); -} - -/***************************************************************************/ diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 09b1287a92ce468de161de8700135109a49ac09b..25f3b0a11ca8f3c37556fff8db1619fb4c240ede 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -72,6 +72,7 @@ config MIPS_COBALT select IRQ_CPU select IRQ_GT641XX select PCI_GT64XXX_PCI0 + select PCI select SYS_HAS_CPU_NEVADA select SYS_HAS_EARLY_PRINTK select SYS_SUPPORTS_32BIT_KERNEL @@ -593,7 +594,7 @@ config WR_PPMC board, which is based on GT64120 bridge chip. config CAVIUM_OCTEON_SIMULATOR - bool "Support for the Cavium Networks Octeon Simulator" + bool "Cavium Networks Octeon Simulator" select CEVT_R4K select 64BIT_PHYS_ADDR select DMA_COHERENT @@ -607,7 +608,7 @@ config CAVIUM_OCTEON_SIMULATOR hardware. config CAVIUM_OCTEON_REFERENCE_BOARD - bool "Support for the Cavium Networks Octeon reference board" + bool "Cavium Networks Octeon reference board" select CEVT_R4K select 64BIT_PHYS_ADDR select DMA_COHERENT diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index 1c19af8daa62a3f992f20ecb1a281a527bfec3cd..d3a0c8154beca80cd7cb40bc3d783fa247891941 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -177,7 +177,7 @@ static void octeon_irq_ciu0_disable(unsigned int irq) } #ifdef CONFIG_SMP -static void octeon_irq_ciu0_set_affinity(unsigned int irq, const struct cpumask *dest) +static int 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 */ @@ -199,6 +199,8 @@ static void 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 @@ -292,7 +294,7 @@ static void octeon_irq_ciu1_disable(unsigned int irq) } #ifdef CONFIG_SMP -static void octeon_irq_ciu1_set_affinity(unsigned int irq, const struct cpumask *dest) +static int 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 */ @@ -315,6 +317,8 @@ static void 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/arch/mips/include/asm/cpu-info.h b/arch/mips/include/asm/cpu-info.h index 744cd8fb107f8777d824312f42d9abb1cef57d68..126044308dec310fac7f66a28bca08ade3964f94 100644 --- a/arch/mips/include/asm/cpu-info.h +++ b/arch/mips/include/asm/cpu-info.h @@ -39,8 +39,8 @@ struct cache_desc { #define MIPS_CACHE_PINDEX 0x00000020 /* Physically indexed cache */ struct cpuinfo_mips { - unsigned long udelay_val; - unsigned long asid_cache; + unsigned int udelay_val; + unsigned int asid_cache; /* * Capability and feature descriptor structure for MIPS CPU diff --git a/arch/mips/include/asm/delay.h b/arch/mips/include/asm/delay.h index b0bccd2c4ed503bb4f10ae8bc4aac057522e3ba0..a07e51b2be1356c5425923dc1710954283ad19d1 100644 --- a/arch/mips/include/asm/delay.h +++ b/arch/mips/include/asm/delay.h @@ -11,94 +11,12 @@ #ifndef _ASM_DELAY_H #define _ASM_DELAY_H -#include -#include +extern void __delay(unsigned int loops); +extern void __ndelay(unsigned int ns); +extern void __udelay(unsigned int us); -#include -#include - -static inline void __delay(unsigned long loops) -{ - if (sizeof(long) == 4) - __asm__ __volatile__ ( - " .set noreorder \n" - " .align 3 \n" - "1: bnez %0, 1b \n" - " subu %0, 1 \n" - " .set reorder \n" - : "=r" (loops) - : "0" (loops)); - else if (sizeof(long) == 8 && !DADDI_WAR) - __asm__ __volatile__ ( - " .set noreorder \n" - " .align 3 \n" - "1: bnez %0, 1b \n" - " dsubu %0, 1 \n" - " .set reorder \n" - : "=r" (loops) - : "0" (loops)); - else if (sizeof(long) == 8 && DADDI_WAR) - __asm__ __volatile__ ( - " .set noreorder \n" - " .align 3 \n" - "1: bnez %0, 1b \n" - " dsubu %0, %2 \n" - " .set reorder \n" - : "=r" (loops) - : "0" (loops), "r" (1)); -} - - -/* - * Division by multiplication: you don't have to worry about - * loss of precision. - * - * Use only for very small delays ( < 1 msec). Should probably use a - * lookup table, really, as the multiplications take much too long with - * short delays. This is a "reasonable" implementation, though (and the - * first constant multiplications gets optimized away if the delay is - * a constant) - */ - -static inline void __udelay(unsigned long usecs, unsigned long lpj) -{ - unsigned long hi, lo; - - /* - * The rates of 128 is rounded wrongly by the catchall case - * for 64-bit. Excessive precission? Probably ... - */ -#if defined(CONFIG_64BIT) && (HZ == 128) - usecs *= 0x0008637bd05af6c7UL; /* 2**64 / (1000000 / HZ) */ -#elif defined(CONFIG_64BIT) - usecs *= (0x8000000000000000UL / (500000 / HZ)); -#else /* 32-bit junk follows here */ - usecs *= (unsigned long) (((0x8000000000000000ULL / (500000 / HZ)) + - 0x80000000ULL) >> 32); -#endif - - if (sizeof(long) == 4) - __asm__("multu\t%2, %3" - : "=h" (usecs), "=l" (lo) - : "r" (usecs), "r" (lpj) - : GCC_REG_ACCUM); - else if (sizeof(long) == 8 && !R4000_WAR) - __asm__("dmultu\t%2, %3" - : "=h" (usecs), "=l" (lo) - : "r" (usecs), "r" (lpj) - : GCC_REG_ACCUM); - else if (sizeof(long) == 8 && R4000_WAR) - __asm__("dmultu\t%3, %4\n\tmfhi\t%0" - : "=r" (usecs), "=h" (hi), "=l" (lo) - : "r" (usecs), "r" (lpj) - : GCC_REG_ACCUM); - - __delay(usecs); -} - -#define __udelay_val cpu_data[raw_smp_processor_id()].udelay_val - -#define udelay(usecs) __udelay((usecs), __udelay_val) +#define ndelay(ns) __udelay(ns) +#define udelay(us) __udelay(us) /* make sure "usecs *= ..." in udelay do not overflow. */ #if HZ >= 1000 diff --git a/arch/mips/include/asm/ioctl.h b/arch/mips/include/asm/ioctl.h index 85067e248a839e544d6c386a309a9bbe9273abfb..916163401b2cfd4b55c26fa4b8adef1beef0c290 100644 --- a/arch/mips/include/asm/ioctl.h +++ b/arch/mips/include/asm/ioctl.h @@ -60,12 +60,16 @@ ((nr) << _IOC_NRSHIFT) | \ ((size) << _IOC_SIZESHIFT)) +#ifdef __KERNEL__ /* provoke compile error for invalid uses of size argument */ extern unsigned int __invalid_size_argument_for_IOC; #define _IOC_TYPECHECK(t) \ ((sizeof(t) == sizeof(t[1]) && \ sizeof(t) < (1 << _IOC_SIZEBITS)) ? \ sizeof(t) : __invalid_size_argument_for_IOC) +#else +#define _IOC_TYPECHECK(t) (sizeof(t)) +#endif /* used to create numbers */ #define _IO(type, nr) _IOC(_IOC_NONE, (type), (nr), 0) diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index 3214ade02d105988937576c8425f444b08783b0e..4f1eed107b08217f8f2991ed17f92c424b6c437f 100644 --- a/arch/mips/include/asm/irq.h +++ b/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 void plat_set_irq_affinity(unsigned int irq, +extern int plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity); extern void smtc_forward_irq(unsigned int irq); diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c index 87deb8f6c45885e5c356df3ac4ddf1e58a6ac81c..3f43c2e3aa5a59ede8eab7ecdaee7762ea6afb68 100644 --- a/arch/mips/kernel/irq-gic.c +++ b/arch/mips/kernel/irq-gic.c @@ -155,7 +155,7 @@ static void gic_unmask_irq(unsigned int irq) static DEFINE_SPINLOCK(gic_lock); -static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask) +static int gic_set_affinity(unsigned int irq, const struct cpumask *cpumask) { cpumask_t tmp = CPU_MASK_NONE; unsigned long flags; @@ -166,7 +166,7 @@ static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask) cpumask_and(&tmp, cpumask, cpu_online_mask); if (cpus_empty(tmp)) - return; + return -1; /* Assumption : cpumask refers to a single CPU */ spin_lock_irqsave(&gic_lock, flags); @@ -190,6 +190,7 @@ static void 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/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index 26760cad8b6972c4ad956a8cad81355c9d15ade7..e0a4ac18fa07e72f62d38089aa9d3ba9f472c51f 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -42,7 +42,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, fmt, __cpu_name[n], (version >> 4) & 0x0f, version & 0x0f, (fp_vers >> 4) & 0x0f, fp_vers & 0x0f); - seq_printf(m, "BogoMIPS\t\t: %lu.%02lu\n", + seq_printf(m, "BogoMIPS\t\t: %u.%02u\n", cpu_data[n].udelay_val / (500000/HZ), (cpu_data[n].udelay_val / (5000/HZ)) % 100); seq_printf(m, "wait instruction\t: %s\n", cpu_wait ? "yes" : "no"); diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile index c13c7ad2cdaeb218d9b4cc09e89ec468a6f9cfe1..2adead5a8a376e54a8f9c58dade0c4e817fd82c7 100644 --- a/arch/mips/lib/Makefile +++ b/arch/mips/lib/Makefile @@ -2,8 +2,8 @@ # Makefile for MIPS-specific library files.. # -lib-y += csum_partial.o memcpy.o memcpy-inatomic.o memset.o strlen_user.o \ - strncpy_user.o strnlen_user.o uncached.o +lib-y += csum_partial.o delay.o memcpy.o memcpy-inatomic.o memset.o \ + strlen_user.o strncpy_user.o strnlen_user.o uncached.o obj-y += iomap.o obj-$(CONFIG_PCI) += iomap-pci.o diff --git a/arch/mips/lib/delay.c b/arch/mips/lib/delay.c new file mode 100644 index 0000000000000000000000000000000000000000..f69c6b569eb3b7c42b4ea756e56f847e7bd75fe2 --- /dev/null +++ b/arch/mips/lib/delay.c @@ -0,0 +1,56 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1994 by Waldorf Electronics + * Copyright (C) 1995 - 2000, 01, 03 by Ralf Baechle + * Copyright (C) 1999, 2000 Silicon Graphics, Inc. + * Copyright (C) 2007 Maciej W. Rozycki + */ +#include +#include +#include + +#include +#include + +inline void __delay(unsigned int loops) +{ + __asm__ __volatile__ ( + " .set noreorder \n" + " .align 3 \n" + "1: bnez %0, 1b \n" + " subu %0, 1 \n" + " .set reorder \n" + : "=r" (loops) + : "0" (loops)); +} +EXPORT_SYMBOL(__delay); + +/* + * Division by multiplication: you don't have to worry about + * loss of precision. + * + * Use only for very small delays ( < 1 msec). Should probably use a + * lookup table, really, as the multiplications take much too long with + * short delays. This is a "reasonable" implementation, though (and the + * first constant multiplications gets optimized away if the delay is + * a constant) + */ + +void __udelay(unsigned long us) +{ + unsigned int lpj = current_cpu_data.udelay_val; + + __delay((us * 0x000010c7 * HZ * lpj) >> 32); +} +EXPORT_SYMBOL(__udelay); + +void __ndelay(unsigned long ns) +{ + unsigned int lpj = current_cpu_data.udelay_val; + + __delay((us * 0x00000005 * HZ * lpj) >> 32); +} +EXPORT_SYMBOL(__ndelay); diff --git a/arch/mips/mti-malta/malta-smtc.c b/arch/mips/mti-malta/malta-smtc.c index 5ba31888fefbbecacd123e7033ef8ddcb6c30944..499ffe5475dff4fe8254990499d13d6f5ff4a266 100644 --- a/arch/mips/mti-malta/malta-smtc.c +++ b/arch/mips/mti-malta/malta-smtc.c @@ -114,7 +114,7 @@ struct plat_smp_ops msmtc_smp_ops = { */ -void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) +int plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) { cpumask_t tmask; int cpu = 0; @@ -156,5 +156,7 @@ void 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/arch/mips/sibyte/bcm1480/irq.c b/arch/mips/sibyte/bcm1480/irq.c index c147c4b35d3fc6f9e1f48b81866eb36d7f882594..690de06bde902f38a49b8d1e1765ae3fd2251b48 100644 --- a/arch/mips/sibyte/bcm1480/irq.c +++ b/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 void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask); +static int 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 void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask) +static int 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 void 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; + return -1; } i = cpumask_first(mask); @@ -152,6 +152,8 @@ static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask) } } spin_unlock_irqrestore(&bcm1480_imr_lock, flags); + + return 0; } #endif diff --git a/arch/mips/sibyte/cfe/setup.c b/arch/mips/sibyte/cfe/setup.c index 3de30f79db3f33dcbf945bca58389456af40e1f3..eb5396cf81bb1b725c79ec2360c890dca8214cac 100644 --- a/arch/mips/sibyte/cfe/setup.c +++ b/arch/mips/sibyte/cfe/setup.c @@ -288,13 +288,7 @@ void __init prom_init(void) */ cfe_cons_handle = cfe_getstdhandle(CFE_STDHANDLE_CONSOLE); if (cfe_getenv("LINUX_CMDLINE", arcs_cmdline, CL_SIZE) < 0) { - if (argc < 0) { - /* - * It's OK for direct boot to not provide a - * command line - */ - strcpy(arcs_cmdline, "root=/dev/ram0 "); - } else { + if (argc >= 0) { /* The loader should have set the command line */ /* too early for panic to do any good */ printk("LINUX_CMDLINE not defined in cfe."); diff --git a/arch/mips/sibyte/sb1250/irq.c b/arch/mips/sibyte/sb1250/irq.c index 38cb998ade22053b8963377b70d6f7dad7fb6b94..409dec798863194f364eb378666c9e7471fd0227 100644 --- a/arch/mips/sibyte/sb1250/irq.c +++ b/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 void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask); +static int 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 void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask) +static int 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 void 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; + return -1; } /* Convert logical CPU to physical CPU */ @@ -143,6 +143,8 @@ static void 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/arch/mn10300/Kconfig b/arch/mn10300/Kconfig index 355926730e8d9f49387138fb2cf1cc5b9b3b8898..89faacad5d17d71871d75453fdf55d107f15985e 100644 --- a/arch/mn10300/Kconfig +++ b/arch/mn10300/Kconfig @@ -8,6 +8,7 @@ mainmenu "Linux Kernel Configuration" config MN10300 def_bool y select HAVE_OPROFILE + select HAVE_ARCH_TRACEHOOK config AM33 def_bool y diff --git a/arch/mn10300/include/asm/elf.h b/arch/mn10300/include/asm/elf.h index bf09f8bb392eef17bf41441050b5adb6e9920d0b..49105462e6fc9c5fb095fa35ad25b55493ba15a6 100644 --- a/arch/mn10300/include/asm/elf.h +++ b/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)) +#define ELF_NGREG ((sizeof(struct pt_regs) / sizeof(elf_greg_t)) - 1) typedef elf_greg_t elf_gregset_t[ELF_NGREG]; #define ELF_NFPREG 32 @@ -76,6 +76,7 @@ do { \ } while (0) #define USE_ELF_CORE_DUMP +#define CORE_DUMP_USE_REGSET #define ELF_EXEC_PAGESIZE 4096 /* diff --git a/arch/mn10300/include/asm/processor.h b/arch/mn10300/include/asm/processor.h index 73239271873da304c88fe396eda7074686c3185a..f7d4b0d285e8dddb835781ac071898ff5d34dfe9 100644 --- a/arch/mn10300/include/asm/processor.h +++ b/arch/mn10300/include/asm/processor.h @@ -143,13 +143,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); unsigned long get_wchan(struct task_struct *p); -#define task_pt_regs(task) \ -({ \ - struct pt_regs *__regs__; \ - __regs__ = (struct pt_regs *) (KSTK_TOP(task_stack_page(task)) - 8); \ - __regs__ - 1; \ -}) - +#define task_pt_regs(task) ((task)->thread.uregs) #define KSTK_EIP(task) (task_pt_regs(task)->pc) #define KSTK_ESP(task) (task_pt_regs(task)->sp) diff --git a/arch/mn10300/include/asm/ptrace.h b/arch/mn10300/include/asm/ptrace.h index 7b06cc623d8b074a3a23511673e2c170bb033840..921942ed1b03508a582e6e226ed33acf50c8fa5b 100644 --- a/arch/mn10300/include/asm/ptrace.h +++ b/arch/mn10300/include/asm/ptrace.h @@ -91,9 +91,17 @@ 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/arch/mn10300/kernel/entry.S b/arch/mn10300/kernel/entry.S index 3dc3e462f92a4e39b496f4d78f7bc1adc6e64e85..7408a27199f342fd26679db7a326aa0b07885f53 100644 --- a/arch/mn10300/kernel/entry.S +++ b/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_trace_entry + bne syscall_entry_trace syscall_call: add d0,d0,a1 add a1,a1 @@ -104,11 +104,10 @@ restore_all: syscall_exit_work: btst _TIF_SYSCALL_TRACE,d2 beq work_pending - __sti # could let do_syscall_trace() call + __sti # could let syscall_trace_exit() call # schedule() instead mov fp,d0 - mov 1,d1 - call do_syscall_trace[],0 # do_syscall_trace(regs,entryexit) + call syscall_trace_exit[],0 # do_syscall_trace(regs) jmp resume_userspace ALIGN @@ -138,13 +137,11 @@ work_notifysig: jmp resume_userspace # perform syscall entry tracing -syscall_trace_entry: +syscall_entry_trace: mov -ENOSYS,d0 mov d0,(REG_D0,fp) mov fp,d0 - clr d1 - call do_syscall_trace[],0 - mov (REG_ORIG_D0,fp),d0 + call syscall_trace_entry[],0 # returns the syscall number to actually use mov (REG_D1,fp),d1 cmp nr_syscalls,d0 bcs syscall_call diff --git a/arch/mn10300/kernel/ptrace.c b/arch/mn10300/kernel/ptrace.c index d6d6cdc75c523b66e6218d493311aac2afc5f017..e143339ad28e00869d9b23c1d882d994cdd89d62 100644 --- a/arch/mn10300/kernel/ptrace.c +++ b/arch/mn10300/kernel/ptrace.c @@ -17,6 +17,9 @@ #include #include #include +#include +#include +#include #include #include #include @@ -64,12 +67,6 @@ 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) { @@ -80,94 +77,233 @@ int put_stack_long(struct task_struct *task, int offset, unsigned long data) return 0; } -static inline unsigned long get_fpregs(struct fpu_state_struct *buf, - struct task_struct *tsk) +/* + * 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) { - return __copy_to_user(buf, &tsk->thread.fpu_state, - sizeof(struct fpu_state_struct)); + 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); } -static inline unsigned long set_fpregs(struct task_struct *tsk, - struct fpu_state_struct *buf) +/* + * 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) { - return __copy_from_user(&tsk->thread.fpu_state, buf, - sizeof(struct fpu_state_struct)); + 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); } -static inline void fpsave_init(struct task_struct *task) +/* + * 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) { - memset(&task->thread.fpu_state, 0, sizeof(struct fpu_state_struct)); + 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); } /* - * make sure the single step bit is not set + * update the contents of the MN10300 userspace FPU registers */ -void ptrace_disable(struct task_struct *child) +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) { #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 } /* - * set the single step bit + * make sure the single-step bit is not set */ -void ptrace_enable(struct task_struct *child) +void user_disable_single_step(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) { - struct fpu_state_struct fpu_state; - int i, ret; + unsigned long tmp; + int 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: { - unsigned long tmp; - + case PTRACE_PEEKUSR: ret = -EIO; if ((addr & 3) || addr < 0 || addr > sizeof(struct user) - 3) @@ -179,17 +315,6 @@ 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: @@ -204,132 +329,32 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) data); break; - /* 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; - } + 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); default: - ret = -EIO; + ret = ptrace_request(child, request, addr, data); break; } @@ -337,43 +362,26 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) } /* - * notification of system call entry/exit - * - triggered by current->work.syscall_trace + * handle tracing of system call entry + * - return the revised system call number or ULONG_MAX to cause ENOSYS */ -asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit) +asmlinkage unsigned long syscall_trace_entry(struct pt_regs *regs) { -#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 - - if (!test_thread_flag(TIF_SYSCALL_TRACE) && - !test_thread_flag(TIF_SINGLESTEP)) - return; - if (!(current->ptrace & PT_PTRACED)) - return; + 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; - /* 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)); + return regs->orig_d0; +} - /* - * 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; - } +/* + * handle tracing of system call exit + */ +asmlinkage void syscall_trace_exit(struct pt_regs *regs) +{ + tracehook_report_syscall_exit(regs, 0); } diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c index 841ca9955a1813836ef2d07d0b7dfbc03e335347..9f7572a0f5784a30d9ff16bbcfa407d10fc8a066 100644 --- a/arch/mn10300/kernel/signal.c +++ b/arch/mn10300/kernel/signal.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -511,6 +512,9 @@ 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; @@ -561,4 +565,9 @@ 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/arch/mn10300/mm/tlb-mn10300.S b/arch/mn10300/mm/tlb-mn10300.S index 789208094e985ec6a02f25c666492b5735c58bb9..7095147dcb8ba2f83bbad869b7b2e4366dd4a6a5 100644 --- a/arch/mn10300/mm/tlb-mn10300.S +++ b/arch/mn10300/mm/tlb-mn10300.S @@ -165,24 +165,6 @@ 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/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c index 4ea4229d765ccc0657148d4f2268931ea3d6b8f9..8007f1e6572986559789a2520603a77336c72214 100644 --- a/arch/parisc/kernel/irq.c +++ b/arch/parisc/kernel/irq.c @@ -130,15 +130,17 @@ int cpu_check_affinity(unsigned int irq, const struct cpumask *dest) return cpu_dest; } -static void cpu_set_affinity_irq(unsigned int irq, const struct cpumask *dest) +static int 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; + return -1; cpumask_copy(&irq_desc[irq].affinity, dest); + + return 0; } #endif diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index 5339bb44cce9053823e4083dfe301e3c77c1a1f1..ea8870a34482a27daf52c512687cfdfd5658f486 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.28-rc3 -# Tue Nov 11 19:36:51 2008 +# Linux kernel version: 2.6.30-rc7 +# Mon May 25 14:53:25 2009 # # CONFIG_PPC64 is not set @@ -14,6 +14,7 @@ CONFIG_6xx=y # CONFIG_40x is not set # CONFIG_44x is not set # CONFIG_E200 is not set +CONFIG_PPC_BOOK3S=y CONFIG_PPC_FPU=y CONFIG_ALTIVEC=y CONFIG_PPC_STD_MMU=y @@ -43,7 +44,7 @@ CONFIG_GENERIC_FIND_NEXT_BIT=y CONFIG_PPC=y CONFIG_EARLY_PRINTK=y CONFIG_GENERIC_NVRAM=y -CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y +CONFIG_SCHED_OMIT_FRAME_POINTER=y CONFIG_ARCH_MAY_HAVE_PC_FDC=y CONFIG_PPC_OF=y CONFIG_OF=y @@ -52,12 +53,14 @@ CONFIG_OF=y CONFIG_AUDIT_ARCH=y CONFIG_GENERIC_BUG=y CONFIG_SYS_SUPPORTS_APM_EMULATION=y +CONFIG_DTC=y # CONFIG_DEFAULT_UIMAGE is not set CONFIG_HIBERNATE_32=y CONFIG_ARCH_HIBERNATION_POSSIBLE=y CONFIG_ARCH_SUSPEND_POSSIBLE=y # CONFIG_PPC_DCR_NATIVE is not set # CONFIG_PPC_DCR_MMIO is not set +CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # @@ -72,14 +75,24 @@ CONFIG_SWAP=y CONFIG_SYSVIPC=y CONFIG_SYSVIPC_SYSCTL=y CONFIG_POSIX_MQUEUE=y +CONFIG_POSIX_MQUEUE_SYSCTL=y # CONFIG_BSD_PROCESS_ACCT is not set # CONFIG_TASKSTATS is not set # CONFIG_AUDIT is not set + +# +# RCU Subsystem +# +CONFIG_CLASSIC_RCU=y +# CONFIG_TREE_RCU is not set +# CONFIG_PREEMPT_RCU is not set +# CONFIG_TREE_RCU_TRACE is not set +# CONFIG_PREEMPT_RCU_TRACE is not set CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_CGROUPS is not set # CONFIG_GROUP_SCHED is not set +# CONFIG_CGROUPS is not set CONFIG_SYSFS_DEPRECATED=y CONFIG_SYSFS_DEPRECATED_V2=y # CONFIG_RELAY is not set @@ -88,23 +101,27 @@ CONFIG_NAMESPACES=y # CONFIG_IPC_NS is not set # CONFIG_USER_NS is not set # CONFIG_PID_NS is not set +# CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="" +CONFIG_RD_GZIP=y +CONFIG_RD_BZIP2=y +CONFIG_RD_LZMA=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set CONFIG_SYSCTL=y +CONFIG_ANON_INODES=y # CONFIG_EMBEDDED is not set CONFIG_SYSCTL_SYSCALL=y CONFIG_KALLSYMS=y CONFIG_KALLSYMS_ALL=y # CONFIG_KALLSYMS_EXTRA_PASS is not set +# CONFIG_STRIP_ASM_SYMS is not set CONFIG_HOTPLUG=y CONFIG_PRINTK=y CONFIG_BUG=y CONFIG_ELF_CORE=y -# CONFIG_COMPAT_BRK is not set CONFIG_BASE_FULL=y CONFIG_FUTEX=y -CONFIG_ANON_INODES=y CONFIG_EPOLL=y CONFIG_SIGNALFD=y CONFIG_TIMERFD=y @@ -114,10 +131,12 @@ CONFIG_AIO=y CONFIG_VM_EVENT_COUNTERS=y CONFIG_PCI_QUIRKS=y CONFIG_SLUB_DEBUG=y +# CONFIG_COMPAT_BRK is not set # CONFIG_SLAB is not set CONFIG_SLUB=y # CONFIG_SLOB is not set CONFIG_PROFILING=y +CONFIG_TRACEPOINTS=y # CONFIG_MARKERS is not set CONFIG_OPROFILE=y CONFIG_HAVE_OPROFILE=y @@ -127,10 +146,10 @@ CONFIG_HAVE_IOREMAP_PROT=y CONFIG_HAVE_KPROBES=y CONFIG_HAVE_KRETPROBES=y CONFIG_HAVE_ARCH_TRACEHOOK=y +# CONFIG_SLOW_WORK is not set # CONFIG_HAVE_GENERIC_DMA_COHERENT is not set CONFIG_SLABINFO=y CONFIG_RT_MUTEXES=y -# CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 CONFIG_MODULES=y # CONFIG_MODULE_FORCE_LOAD is not set @@ -138,11 +157,8 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_MODVERSIONS is not set # CONFIG_MODULE_SRCVERSION_ALL is not set -CONFIG_KMOD=y CONFIG_BLOCK=y CONFIG_LBD=y -# CONFIG_BLK_DEV_IO_TRACE is not set -CONFIG_LSF=y CONFIG_BLK_DEV_BSG=y # CONFIG_BLK_DEV_INTEGRITY is not set @@ -158,14 +174,11 @@ CONFIG_DEFAULT_AS=y # CONFIG_DEFAULT_CFQ is not set # CONFIG_DEFAULT_NOOP is not set CONFIG_DEFAULT_IOSCHED="anticipatory" -CONFIG_CLASSIC_RCU=y CONFIG_FREEZER=y # # Platform support # -CONFIG_PPC_MULTIPLATFORM=y -CONFIG_CLASSIC32=y # CONFIG_PPC_CHRP is not set # CONFIG_MPC5121_ADS is not set # CONFIG_MPC5121_GENERIC is not set @@ -178,7 +191,9 @@ CONFIG_PPC_PMAC=y # CONFIG_PPC_83xx is not set # CONFIG_PPC_86xx is not set # CONFIG_EMBEDDED6xx is not set +# CONFIG_AMIGAONE is not set CONFIG_PPC_NATIVE=y +CONFIG_PPC_OF_BOOT_TRAMPOLINE=y # CONFIG_IPIC is not set CONFIG_MPIC=y # CONFIG_MPIC_WEIRD is not set @@ -212,11 +227,12 @@ CONFIG_CPU_FREQ_PMAC=y CONFIG_PPC601_SYNC_FIX=y # CONFIG_TAU is not set # CONFIG_FSL_ULI1575 is not set +# CONFIG_SIMPLE_GPIO is not set # # Kernel options # -# CONFIG_HIGHMEM is not set +CONFIG_HIGHMEM=y CONFIG_TICK_ONESHOT=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y @@ -239,6 +255,7 @@ CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y CONFIG_ARCH_HAS_WALK_MEMORY=y CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y # CONFIG_KEXEC is not set +# CONFIG_CRASH_DUMP is not set CONFIG_ARCH_FLATMEM_ENABLE=y CONFIG_ARCH_POPULATES_NODE_MAP=y CONFIG_SELECT_MEMORY_MODEL=y @@ -250,12 +267,17 @@ CONFIG_FLAT_NODE_MEM_MAP=y CONFIG_PAGEFLAGS_EXTENDED=y CONFIG_SPLIT_PTLOCK_CPUS=4 # CONFIG_MIGRATION is not set -# CONFIG_RESOURCES_64BIT is not set # CONFIG_PHYS_ADDR_T_64BIT is not set CONFIG_ZONE_DMA_FLAG=1 CONFIG_BOUNCE=y CONFIG_VIRT_TO_BUS=y CONFIG_UNEVICTABLE_LRU=y +CONFIG_HAVE_MLOCK=y +CONFIG_HAVE_MLOCKED_PAGE_BIT=y +CONFIG_PPC_4K_PAGES=y +# CONFIG_PPC_16K_PAGES is not set +# CONFIG_PPC_64K_PAGES is not set +# CONFIG_PPC_256K_PAGES is not set CONFIG_FORCE_MAX_ZONEORDER=11 CONFIG_PROC_DEVICETREE=y # CONFIG_CMDLINE_BOOL is not set @@ -288,6 +310,8 @@ CONFIG_ARCH_SUPPORTS_MSI=y # CONFIG_PCI_MSI is not set # CONFIG_PCI_LEGACY is not set # CONFIG_PCI_DEBUG is not set +# CONFIG_PCI_STUB is not set +# CONFIG_PCI_IOV is not set CONFIG_PCCARD=m # CONFIG_PCMCIA_DEBUG is not set CONFIG_PCMCIA=m @@ -397,6 +421,8 @@ CONFIG_NETFILTER_XTABLES=m CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m # CONFIG_NETFILTER_XT_TARGET_CONNMARK is not set # CONFIG_NETFILTER_XT_TARGET_DSCP is not set +CONFIG_NETFILTER_XT_TARGET_HL=m +# CONFIG_NETFILTER_XT_TARGET_LED is not set CONFIG_NETFILTER_XT_TARGET_MARK=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m @@ -405,6 +431,7 @@ CONFIG_NETFILTER_XT_TARGET_RATEEST=m CONFIG_NETFILTER_XT_TARGET_TRACE=m CONFIG_NETFILTER_XT_TARGET_TCPMSS=m CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m +# CONFIG_NETFILTER_XT_MATCH_CLUSTER is not set CONFIG_NETFILTER_XT_MATCH_COMMENT=m # CONFIG_NETFILTER_XT_MATCH_CONNBYTES is not set CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m @@ -415,6 +442,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m CONFIG_NETFILTER_XT_MATCH_ESP=m # CONFIG_NETFILTER_XT_MATCH_HASHLIMIT is not set CONFIG_NETFILTER_XT_MATCH_HELPER=m +CONFIG_NETFILTER_XT_MATCH_HL=m CONFIG_NETFILTER_XT_MATCH_IPRANGE=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m CONFIG_NETFILTER_XT_MATCH_LIMIT=m @@ -478,17 +506,15 @@ CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_IP_DCCP=m CONFIG_INET_DCCP_DIAG=m -CONFIG_IP_DCCP_ACKVEC=y # # DCCP CCIDs Configuration (EXPERIMENTAL) # -CONFIG_IP_DCCP_CCID2=m # CONFIG_IP_DCCP_CCID2_DEBUG is not set -CONFIG_IP_DCCP_CCID3=m +CONFIG_IP_DCCP_CCID3=y # CONFIG_IP_DCCP_CCID3_DEBUG is not set CONFIG_IP_DCCP_CCID3_RTO=100 -CONFIG_IP_DCCP_TFRC_LIB=m +CONFIG_IP_DCCP_TFRC_LIB=y # # DCCP Kernel Hacking @@ -508,13 +534,16 @@ CONFIG_IP_DCCP_TFRC_LIB=m # CONFIG_LAPB is not set # CONFIG_ECONET is not set # CONFIG_WAN_ROUTER is not set +# CONFIG_PHONET is not set # CONFIG_NET_SCHED is not set CONFIG_NET_CLS_ROUTE=y +# CONFIG_DCB is not set # # Network testing # # CONFIG_NET_PKTGEN is not set +# CONFIG_NET_DROP_MONITOR is not set # CONFIG_HAMRADIO is not set # CONFIG_CAN is not set CONFIG_IRDA=m @@ -577,8 +606,6 @@ CONFIG_BT_HIDP=m # # Bluetooth device drivers # -CONFIG_BT_HCIUSB=m -# CONFIG_BT_HCIUSB_SCO is not set # CONFIG_BT_HCIBTUSB is not set # CONFIG_BT_HCIUART is not set CONFIG_BT_HCIBCM203X=m @@ -590,31 +617,27 @@ CONFIG_BT_HCIBFUSB=m # CONFIG_BT_HCIBTUART is not set # CONFIG_BT_HCIVHCI is not set # CONFIG_AF_RXRPC is not set -# CONFIG_PHONET is not set CONFIG_WIRELESS=y CONFIG_CFG80211=m -CONFIG_NL80211=y +# CONFIG_CFG80211_REG_DEBUG is not set CONFIG_WIRELESS_OLD_REGULATORY=y CONFIG_WIRELESS_EXT=y CONFIG_WIRELESS_EXT_SYSFS=y +# CONFIG_LIB80211 is not set CONFIG_MAC80211=m # # Rate control algorithm selection # -CONFIG_MAC80211_RC_PID=y -# CONFIG_MAC80211_RC_MINSTREL is not set -CONFIG_MAC80211_RC_DEFAULT_PID=y -# CONFIG_MAC80211_RC_DEFAULT_MINSTREL is not set -CONFIG_MAC80211_RC_DEFAULT="pid" +CONFIG_MAC80211_RC_MINSTREL=y +# CONFIG_MAC80211_RC_DEFAULT_PID is not set +CONFIG_MAC80211_RC_DEFAULT_MINSTREL=y +CONFIG_MAC80211_RC_DEFAULT="minstrel" # CONFIG_MAC80211_MESH is not set CONFIG_MAC80211_LEDS=y +# CONFIG_MAC80211_DEBUGFS is not set # CONFIG_MAC80211_DEBUG_MENU is not set -CONFIG_IEEE80211=m -# CONFIG_IEEE80211_DEBUG is not set -CONFIG_IEEE80211_CRYPT_WEP=m -CONFIG_IEEE80211_CRYPT_CCMP=m -CONFIG_IEEE80211_CRYPT_TKIP=m +# CONFIG_WIMAX is not set # CONFIG_RFKILL is not set # CONFIG_NET_9P is not set @@ -662,17 +685,27 @@ CONFIG_BLK_DEV_RAM_SIZE=4096 # CONFIG_BLK_DEV_HD is not set CONFIG_MISC_DEVICES=y # CONFIG_PHANTOM is not set -# CONFIG_EEPROM_93CX6 is not set # CONFIG_SGI_IOC4 is not set # CONFIG_TIFM_CORE is not set +# CONFIG_ICS932S401 is not set # CONFIG_ENCLOSURE_SERVICES is not set # CONFIG_HP_ILO is not set +# CONFIG_ISL29003 is not set +# CONFIG_C2PORT is not set + +# +# EEPROM support +# +# CONFIG_EEPROM_AT24 is not set +# CONFIG_EEPROM_LEGACY is not set +# CONFIG_EEPROM_93CX6 is not set CONFIG_HAVE_IDE=y CONFIG_IDE=y # # Please see Documentation/ide/ide.txt for help/info on IDE drives # +CONFIG_IDE_XFER_MODE=y CONFIG_IDE_TIMINGS=y CONFIG_IDE_ATAPI=y # CONFIG_BLK_DEV_IDE_SATA is not set @@ -684,7 +717,6 @@ CONFIG_BLK_DEV_IDECS=m CONFIG_BLK_DEV_IDECD=y CONFIG_BLK_DEV_IDECD_VERBOSE_ERRORS=y # CONFIG_BLK_DEV_IDETAPE is not set -CONFIG_BLK_DEV_IDESCSI=y # CONFIG_IDE_TASK_IOCTL is not set CONFIG_IDE_PROC_FS=y @@ -714,6 +746,7 @@ CONFIG_BLK_DEV_IDEDMA_PCI=y # CONFIG_BLK_DEV_JMICRON is not set # CONFIG_BLK_DEV_SC1200 is not set # CONFIG_BLK_DEV_PIIX is not set +# CONFIG_BLK_DEV_IT8172 is not set # CONFIG_BLK_DEV_IT8213 is not set # CONFIG_BLK_DEV_IT821X is not set # CONFIG_BLK_DEV_NS87415 is not set @@ -728,7 +761,6 @@ CONFIG_BLK_DEV_SL82C105=y # CONFIG_BLK_DEV_TC86C001 is not set CONFIG_BLK_DEV_IDE_PMAC=y CONFIG_BLK_DEV_IDE_PMAC_ATA100FIRST=y -CONFIG_BLK_DEV_IDEDMA_PMAC=y CONFIG_BLK_DEV_IDEDMA=y # @@ -772,6 +804,7 @@ CONFIG_SCSI_FC_ATTRS=y # CONFIG_SCSI_SRP_ATTRS is not set CONFIG_SCSI_LOWLEVEL=y # CONFIG_ISCSI_TCP is not set +# CONFIG_SCSI_CXGB3_ISCSI is not set # CONFIG_BLK_DEV_3W_XXXX_RAID is not set # CONFIG_SCSI_3W_9XXX is not set # CONFIG_SCSI_ACARD is not set @@ -791,8 +824,12 @@ CONFIG_SCSI_AIC7XXX_OLD=m # CONFIG_MEGARAID_NEWGEN is not set # CONFIG_MEGARAID_LEGACY is not set # CONFIG_MEGARAID_SAS is not set +# CONFIG_SCSI_MPT2SAS is not set # CONFIG_SCSI_HPTIOP is not set # CONFIG_SCSI_BUSLOGIC is not set +# CONFIG_LIBFC is not set +# CONFIG_LIBFCOE is not set +# CONFIG_FCOE is not set # CONFIG_SCSI_DMX3191D is not set # CONFIG_SCSI_EATA is not set # CONFIG_SCSI_FUTURE_DOMAIN is not set @@ -822,6 +859,7 @@ CONFIG_SCSI_MAC53C94=y # CONFIG_SCSI_SRP is not set # CONFIG_SCSI_LOWLEVEL_PCMCIA is not set # CONFIG_SCSI_DH is not set +# CONFIG_SCSI_OSD_INITIATOR is not set # CONFIG_ATA is not set CONFIG_MD=y CONFIG_BLK_DEV_MD=m @@ -881,6 +919,7 @@ CONFIG_THERM_ADT746X=m # CONFIG_ANSLCD is not set CONFIG_PMAC_RACKMETER=m CONFIG_NETDEVICES=y +CONFIG_COMPAT_NET_DEV_OPS=y CONFIG_DUMMY=m # CONFIG_BONDING is not set # CONFIG_MACVLAN is not set @@ -898,6 +937,8 @@ CONFIG_BMAC=y CONFIG_SUNGEM=y # CONFIG_CASSINI is not set # CONFIG_NET_VENDOR_3COM is not set +# CONFIG_ETHOC is not set +# CONFIG_DNET is not set # CONFIG_NET_TULIP is not set # CONFIG_HP100 is not set # CONFIG_IBM_NEW_EMAC_ZMII is not set @@ -913,7 +954,6 @@ CONFIG_PCNET32=y # CONFIG_ADAPTEC_STARFIRE is not set # CONFIG_B44 is not set # CONFIG_FORCEDETH is not set -# CONFIG_EEPRO100 is not set # CONFIG_E100 is not set # CONFIG_FEALNX is not set # CONFIG_NATSEMI is not set @@ -923,6 +963,7 @@ CONFIG_PCNET32=y # CONFIG_R6040 is not set # CONFIG_SIS900 is not set # CONFIG_EPIC100 is not set +# CONFIG_SMSC9420 is not set # CONFIG_SUNDANCE is not set # CONFIG_TLAN is not set # CONFIG_VIA_RHINE is not set @@ -935,6 +976,7 @@ CONFIG_NETDEV_1000=y # CONFIG_E1000E is not set # CONFIG_IP1000 is not set # CONFIG_IGB is not set +# CONFIG_IGBVF is not set # CONFIG_NS83820 is not set # CONFIG_HAMACHI is not set # CONFIG_YELLOWFIN is not set @@ -945,18 +987,20 @@ CONFIG_NETDEV_1000=y # CONFIG_VIA_VELOCITY is not set # CONFIG_TIGON3 is not set # CONFIG_BNX2 is not set -# CONFIG_MV643XX_ETH is not set # CONFIG_QLA3XXX is not set # CONFIG_ATL1 is not set # CONFIG_ATL1E is not set +# CONFIG_ATL1C is not set # CONFIG_JME is not set CONFIG_NETDEV_10000=y # CONFIG_CHELSIO_T1 is not set +CONFIG_CHELSIO_T3_DEPENDS=y # CONFIG_CHELSIO_T3 is not set # CONFIG_ENIC is not set # CONFIG_IXGBE is not set # CONFIG_IXGB is not set # CONFIG_S2IO is not set +# CONFIG_VXGE is not set # CONFIG_MYRI10GE is not set # CONFIG_NETXEN_NIC is not set # CONFIG_NIU is not set @@ -966,6 +1010,7 @@ CONFIG_NETDEV_10000=y # CONFIG_BNX2X is not set # CONFIG_QLGE is not set # CONFIG_SFC is not set +# CONFIG_BE2NET is not set # CONFIG_TR is not set # @@ -974,20 +1019,11 @@ CONFIG_NETDEV_10000=y # CONFIG_WLAN_PRE80211 is not set CONFIG_WLAN_80211=y # CONFIG_PCMCIA_RAYCS is not set -# CONFIG_IPW2100 is not set -# CONFIG_IPW2200 is not set # CONFIG_LIBERTAS is not set # CONFIG_LIBERTAS_THINFIRM is not set # CONFIG_AIRO is not set -CONFIG_HERMES=m -CONFIG_APPLE_AIRPORT=m -# CONFIG_PLX_HERMES is not set -# CONFIG_TMD_HERMES is not set -# CONFIG_NORTEL_HERMES is not set -CONFIG_PCI_HERMES=m -CONFIG_PCMCIA_HERMES=m -# CONFIG_PCMCIA_SPECTRUM is not set # CONFIG_ATMEL is not set +# CONFIG_AT76C50X_USB is not set # CONFIG_AIRO_CS is not set # CONFIG_PCMCIA_WL3501 is not set CONFIG_PRISM54=m @@ -997,15 +1033,17 @@ CONFIG_PRISM54=m # CONFIG_RTL8187 is not set # CONFIG_ADM8211 is not set # CONFIG_MAC80211_HWSIM is not set +# CONFIG_MWL8K is not set CONFIG_P54_COMMON=m # CONFIG_P54_USB is not set # CONFIG_P54_PCI is not set +CONFIG_P54_LEDS=y # CONFIG_ATH5K is not set # CONFIG_ATH9K is not set -# CONFIG_IWLCORE is not set -# CONFIG_IWLWIFI_LEDS is not set -# CONFIG_IWLAGN is not set -# CONFIG_IWL3945 is not set +# CONFIG_AR9170_USB is not set +# CONFIG_IPW2100 is not set +# CONFIG_IPW2200 is not set +# CONFIG_IWLWIFI is not set # CONFIG_HOSTAP is not set CONFIG_B43=m CONFIG_B43_PCI_AUTOSELECT=y @@ -1025,6 +1063,19 @@ CONFIG_B43LEGACY_DMA_AND_PIO_MODE=y # CONFIG_B43LEGACY_PIO_MODE is not set # CONFIG_ZD1211RW is not set # CONFIG_RT2X00 is not set +CONFIG_HERMES=m +CONFIG_HERMES_CACHE_FW_ON_INIT=y +CONFIG_APPLE_AIRPORT=m +# CONFIG_PLX_HERMES is not set +# CONFIG_TMD_HERMES is not set +# CONFIG_NORTEL_HERMES is not set +CONFIG_PCI_HERMES=m +CONFIG_PCMCIA_HERMES=m +# CONFIG_PCMCIA_SPECTRUM is not set + +# +# Enable WiMAX (Networking options) to see the WiMAX drivers +# # # USB Network Adapters @@ -1036,6 +1087,7 @@ CONFIG_B43LEGACY_DMA_AND_PIO_MODE=y CONFIG_USB_USBNET=m CONFIG_USB_NET_AX8817X=m CONFIG_USB_NET_CDCETHER=m +# CONFIG_USB_NET_CDC_EEM is not set # CONFIG_USB_NET_DM9601 is not set # CONFIG_USB_NET_SMSC95XX is not set # CONFIG_USB_NET_GL620A is not set @@ -1099,7 +1151,7 @@ CONFIG_INPUT_KEYBOARD=y CONFIG_INPUT_MOUSE=y # CONFIG_MOUSE_PS2 is not set # CONFIG_MOUSE_SERIAL is not set -# CONFIG_MOUSE_APPLETOUCH is not set +CONFIG_MOUSE_APPLETOUCH=y # CONFIG_MOUSE_BCM5974 is not set # CONFIG_MOUSE_VSXXXAA is not set # CONFIG_INPUT_JOYSTICK is not set @@ -1150,10 +1202,13 @@ CONFIG_SERIAL_PMACZILOG_TTYS=y # CONFIG_SERIAL_JSM is not set # CONFIG_SERIAL_OF_PLATFORM is not set CONFIG_UNIX98_PTYS=y +# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set CONFIG_LEGACY_PTYS=y CONFIG_LEGACY_PTY_COUNT=256 +# CONFIG_HVC_UDBG is not set # CONFIG_IPMI_HANDLER is not set CONFIG_HW_RANDOM=m +# CONFIG_HW_RANDOM_TIMERIOMEM is not set CONFIG_NVRAM=y CONFIG_GEN_RTC=y # CONFIG_GEN_RTC_X is not set @@ -1232,12 +1287,9 @@ CONFIG_I2C_POWERMAC=y # Miscellaneous I2C Chip support # # CONFIG_DS1682 is not set -# CONFIG_EEPROM_AT24 is not set -# CONFIG_EEPROM_LEGACY is not set # CONFIG_SENSORS_PCF8574 is not set # CONFIG_PCF8575 is not set # CONFIG_SENSORS_PCA9539 is not set -# CONFIG_SENSORS_PCF8591 is not set # CONFIG_SENSORS_MAX6875 is not set # CONFIG_SENSORS_TSL2550 is not set # CONFIG_I2C_DEBUG_CORE is not set @@ -1259,11 +1311,11 @@ CONFIG_BATTERY_PMU=y # CONFIG_THERMAL is not set # CONFIG_THERMAL_HWMON is not set # CONFIG_WATCHDOG is not set +CONFIG_SSB_POSSIBLE=y # # Sonics Silicon Backplane # -CONFIG_SSB_POSSIBLE=y CONFIG_SSB=m CONFIG_SSB_SPROM=y CONFIG_SSB_PCIHOST_POSSIBLE=y @@ -1281,18 +1333,13 @@ CONFIG_SSB_DRIVER_PCICORE=y # CONFIG_MFD_CORE is not set # CONFIG_MFD_SM501 is not set # CONFIG_HTC_PASIC3 is not set +# CONFIG_TWL4030_CORE is not set # CONFIG_MFD_TMIO is not set # CONFIG_PMIC_DA903X is not set # CONFIG_MFD_WM8400 is not set # CONFIG_MFD_WM8350_I2C is not set - -# -# Voltage and Current regulators -# +# CONFIG_MFD_PCF50633 is not set # CONFIG_REGULATOR is not set -# CONFIG_REGULATOR_FIXED_VOLTAGE is not set -# CONFIG_REGULATOR_VIRTUAL_CONSUMER is not set -# CONFIG_REGULATOR_BQ24022 is not set # # Multimedia devices @@ -1390,6 +1437,7 @@ CONFIG_FB_ATY_BACKLIGHT=y # CONFIG_FB_KYRO is not set CONFIG_FB_3DFX=y # CONFIG_FB_3DFX_ACCEL is not set +CONFIG_FB_3DFX_I2C=y # CONFIG_FB_VOODOO1 is not set # CONFIG_FB_VT8623 is not set # CONFIG_FB_TRIDENT is not set @@ -1399,12 +1447,14 @@ CONFIG_FB_3DFX=y # CONFIG_FB_IBM_GXT4500 is not set # CONFIG_FB_VIRTUAL is not set # CONFIG_FB_METRONOME is not set +# CONFIG_FB_MB862XX is not set +# CONFIG_FB_BROADSHEET is not set CONFIG_BACKLIGHT_LCD_SUPPORT=y CONFIG_LCD_CLASS_DEVICE=m # CONFIG_LCD_ILI9320 is not set # CONFIG_LCD_PLATFORM is not set CONFIG_BACKLIGHT_CLASS_DEVICE=y -# CONFIG_BACKLIGHT_CORGI is not set +CONFIG_BACKLIGHT_GENERIC=y # # Display device support @@ -1444,11 +1494,13 @@ CONFIG_SND_MIXER_OSS=m CONFIG_SND_PCM_OSS=m CONFIG_SND_PCM_OSS_PLUGINS=y CONFIG_SND_SEQUENCER_OSS=y +# CONFIG_SND_HRTIMER is not set # CONFIG_SND_DYNAMIC_MINORS is not set CONFIG_SND_SUPPORT_OLD_API=y CONFIG_SND_VERBOSE_PROCFS=y # CONFIG_SND_VERBOSE_PRINTK is not set # CONFIG_SND_DEBUG is not set +CONFIG_SND_VMASTER=y CONFIG_SND_DRIVERS=y CONFIG_SND_DUMMY=m # CONFIG_SND_VIRMIDI is not set @@ -1486,6 +1538,8 @@ CONFIG_SND_PCI=y # CONFIG_SND_INDIGO is not set # CONFIG_SND_INDIGOIO is not set # CONFIG_SND_INDIGODJ is not set +# CONFIG_SND_INDIGOIOX is not set +# CONFIG_SND_INDIGODJX is not set # CONFIG_SND_EMU10K1 is not set # CONFIG_SND_EMU10K1X is not set # CONFIG_SND_ENS1370 is not set @@ -1551,28 +1605,31 @@ CONFIG_USB_HID=y # # Special HID drivers # -CONFIG_HID_COMPAT=y CONFIG_HID_A4TECH=y CONFIG_HID_APPLE=y CONFIG_HID_BELKIN=y -CONFIG_HID_BRIGHT=y CONFIG_HID_CHERRY=y CONFIG_HID_CHICONY=y CONFIG_HID_CYPRESS=y -CONFIG_HID_DELL=y +# CONFIG_DRAGONRISE_FF is not set CONFIG_HID_EZKEY=y +CONFIG_HID_KYE=y CONFIG_HID_GYRATION=y +CONFIG_HID_KENSINGTON=y CONFIG_HID_LOGITECH=y # CONFIG_LOGITECH_FF is not set # CONFIG_LOGIRUMBLEPAD2_FF is not set CONFIG_HID_MICROSOFT=y CONFIG_HID_MONTEREY=y +CONFIG_HID_NTRIG=y CONFIG_HID_PANTHERLORD=y # CONFIG_PANTHERLORD_FF is not set CONFIG_HID_PETALYNX=y CONFIG_HID_SAMSUNG=y CONFIG_HID_SONY=y CONFIG_HID_SUNPLUS=y +# CONFIG_GREENASIA_FF is not set +CONFIG_HID_TOPSEED=y # CONFIG_THRUSTMASTER_FF is not set # CONFIG_ZEROPLUS_FF is not set CONFIG_USB_SUPPORT=y @@ -1603,6 +1660,7 @@ CONFIG_USB_EHCI_HCD=m CONFIG_USB_EHCI_ROOT_HUB_TT=y # CONFIG_USB_EHCI_TT_NEWSCHED is not set # CONFIG_USB_EHCI_HCD_PPC_OF is not set +# CONFIG_USB_OXU210HP_HCD is not set # CONFIG_USB_ISP116X_HCD is not set # CONFIG_USB_ISP1760_HCD is not set CONFIG_USB_OHCI_HCD=y @@ -1625,24 +1683,23 @@ CONFIG_USB_PRINTER=m # CONFIG_USB_TMC is not set # -# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' +# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may # # -# may also be needed; see USB_STORAGE Help for more information +# also be needed; see USB_STORAGE Help for more info # CONFIG_USB_STORAGE=m # CONFIG_USB_STORAGE_DEBUG is not set # CONFIG_USB_STORAGE_DATAFAB is not set # CONFIG_USB_STORAGE_FREECOM is not set # CONFIG_USB_STORAGE_ISD200 is not set -# CONFIG_USB_STORAGE_DPCM is not set # CONFIG_USB_STORAGE_USBAT is not set # CONFIG_USB_STORAGE_SDDR09 is not set # CONFIG_USB_STORAGE_SDDR55 is not set # CONFIG_USB_STORAGE_JUMPSHOT is not set # CONFIG_USB_STORAGE_ALAUDA is not set -CONFIG_USB_STORAGE_ONETOUCH=y +CONFIG_USB_STORAGE_ONETOUCH=m # CONFIG_USB_STORAGE_KARMA is not set # CONFIG_USB_STORAGE_CYPRESS_ATACB is not set # CONFIG_USB_LIBUSUAL is not set @@ -1665,7 +1722,7 @@ CONFIG_USB_EZUSB=y # CONFIG_USB_SERIAL_CH341 is not set # CONFIG_USB_SERIAL_WHITEHEAT is not set # CONFIG_USB_SERIAL_DIGI_ACCELEPORT is not set -# CONFIG_USB_SERIAL_CP2101 is not set +# CONFIG_USB_SERIAL_CP210X is not set # CONFIG_USB_SERIAL_CYPRESS_M8 is not set # CONFIG_USB_SERIAL_EMPEG is not set # CONFIG_USB_SERIAL_FTDI_SIO is not set @@ -1701,15 +1758,19 @@ CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y # CONFIG_USB_SERIAL_NAVMAN is not set # CONFIG_USB_SERIAL_PL2303 is not set # CONFIG_USB_SERIAL_OTI6858 is not set +# CONFIG_USB_SERIAL_QUALCOMM is not set # CONFIG_USB_SERIAL_SPCP8X5 is not set # CONFIG_USB_SERIAL_HP4X is not set # CONFIG_USB_SERIAL_SAFE is not set +# CONFIG_USB_SERIAL_SIEMENS_MPI is not set # CONFIG_USB_SERIAL_SIERRAWIRELESS is not set +# CONFIG_USB_SERIAL_SYMBOL is not set # CONFIG_USB_SERIAL_TI is not set # CONFIG_USB_SERIAL_CYBERJACK is not set # CONFIG_USB_SERIAL_XIRCOM is not set # CONFIG_USB_SERIAL_OPTION is not set # CONFIG_USB_SERIAL_OMNINET is not set +# CONFIG_USB_SERIAL_OPTICON is not set # CONFIG_USB_SERIAL_DEBUG is not set # @@ -1726,7 +1787,6 @@ CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y # CONFIG_USB_LED is not set # CONFIG_USB_CYPRESS_CY7C63 is not set # CONFIG_USB_CYTHERM is not set -# CONFIG_USB_PHIDGET is not set # CONFIG_USB_IDMOUSE is not set # CONFIG_USB_FTDI_ELAN is not set CONFIG_USB_APPLEDISPLAY=m @@ -1738,6 +1798,11 @@ CONFIG_USB_APPLEDISPLAY=m # CONFIG_USB_ISIGHTFW is not set # CONFIG_USB_VST is not set # CONFIG_USB_GADGET is not set + +# +# OTG and related infrastructure +# +# CONFIG_NOP_USB_XCEIV is not set # CONFIG_UWB is not set # CONFIG_MMC is not set # CONFIG_MEMSTICK is not set @@ -1748,7 +1813,9 @@ CONFIG_LEDS_CLASS=y # LED drivers # # CONFIG_LEDS_PCA9532 is not set +# CONFIG_LEDS_LP5521 is not set # CONFIG_LEDS_PCA955X is not set +# CONFIG_LEDS_BD2802 is not set # # LED Triggers @@ -1759,11 +1826,16 @@ CONFIG_LEDS_TRIGGER_IDE_DISK=y # CONFIG_LEDS_TRIGGER_HEARTBEAT is not set # CONFIG_LEDS_TRIGGER_BACKLIGHT is not set CONFIG_LEDS_TRIGGER_DEFAULT_ON=y + +# +# iptables trigger is under Netfilter config (LED target) +# # CONFIG_ACCESSIBILITY is not set # CONFIG_INFINIBAND is not set # CONFIG_EDAC is not set # CONFIG_RTC_CLASS is not set # CONFIG_DMADEVICES is not set +# CONFIG_AUXDISPLAY is not set # CONFIG_UIO is not set # CONFIG_STAGING is not set @@ -1774,6 +1846,7 @@ CONFIG_EXT2_FS=y # CONFIG_EXT2_FS_XATTR is not set # CONFIG_EXT2_FS_XIP is not set CONFIG_EXT3_FS=y +# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set CONFIG_EXT3_FS_XATTR=y CONFIG_EXT3_FS_POSIX_ACL=y # CONFIG_EXT3_FS_SECURITY is not set @@ -1783,7 +1856,9 @@ CONFIG_EXT4_FS_XATTR=y # CONFIG_EXT4_FS_POSIX_ACL is not set # CONFIG_EXT4_FS_SECURITY is not set CONFIG_JBD=y +# CONFIG_JBD_DEBUG is not set CONFIG_JBD2=y +# CONFIG_JBD2_DEBUG is not set CONFIG_FS_MBCACHE=y # CONFIG_REISERFS_FS is not set # CONFIG_JFS_FS is not set @@ -1792,6 +1867,7 @@ CONFIG_FILE_LOCKING=y # CONFIG_XFS_FS is not set # CONFIG_GFS2_FS is not set # CONFIG_OCFS2_FS is not set +# CONFIG_BTRFS_FS is not set CONFIG_DNOTIFY=y CONFIG_INOTIFY=y CONFIG_INOTIFY_USER=y @@ -1800,6 +1876,11 @@ CONFIG_INOTIFY_USER=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m +# +# Caches +# +# CONFIG_FSCACHE is not set + # # CD-ROM/DVD Filesystems # @@ -1831,10 +1912,7 @@ CONFIG_TMPFS=y # CONFIG_TMPFS_POSIX_ACL is not set # CONFIG_HUGETLB_PAGE is not set # CONFIG_CONFIGFS_FS is not set - -# -# Miscellaneous filesystems -# +CONFIG_MISC_FILESYSTEMS=y # CONFIG_ADFS_FS is not set # CONFIG_AFFS_FS is not set CONFIG_HFS_FS=m @@ -1843,6 +1921,7 @@ CONFIG_HFSPLUS_FS=m # CONFIG_BFS_FS is not set # CONFIG_EFS_FS is not set # CONFIG_CRAMFS is not set +# CONFIG_SQUASHFS is not set # CONFIG_VXFS_FS is not set # CONFIG_MINIX_FS is not set # CONFIG_OMFS_FS is not set @@ -1851,6 +1930,7 @@ CONFIG_HFSPLUS_FS=m # CONFIG_ROMFS_FS is not set # CONFIG_SYSV_FS is not set # CONFIG_UFS_FS is not set +# CONFIG_NILFS2_FS is not set CONFIG_NETWORK_FILESYSTEMS=y CONFIG_NFS_FS=y CONFIG_NFS_V3=y @@ -1868,7 +1948,6 @@ CONFIG_NFS_ACL_SUPPORT=y CONFIG_NFS_COMMON=y CONFIG_SUNRPC=y CONFIG_SUNRPC_GSS=y -# CONFIG_SUNRPC_REGISTER_V4 is not set CONFIG_RPCSEC_GSS_KRB5=y # CONFIG_RPCSEC_GSS_SPKM3 is not set CONFIG_SMB_FS=m @@ -1940,11 +2019,13 @@ CONFIG_NLS_ISO8859_1=m # CONFIG_NLS_KOI8_U is not set CONFIG_NLS_UTF8=m # CONFIG_DLM is not set +CONFIG_BINARY_PRINTF=y # # Library routines # CONFIG_BITREVERSE=y +CONFIG_GENERIC_FIND_LAST_BIT=y CONFIG_CRC_CCITT=y CONFIG_CRC16=y CONFIG_CRC_T10DIF=y @@ -1954,15 +2035,18 @@ CONFIG_CRC32=y CONFIG_LIBCRC32C=m CONFIG_ZLIB_INFLATE=y CONFIG_ZLIB_DEFLATE=y +CONFIG_DECOMPRESS_GZIP=y +CONFIG_DECOMPRESS_BZIP2=y +CONFIG_DECOMPRESS_LZMA=y CONFIG_TEXTSEARCH=y CONFIG_TEXTSEARCH_KMP=m CONFIG_TEXTSEARCH_BM=m CONFIG_TEXTSEARCH_FSM=m -CONFIG_PLIST=y CONFIG_HAS_IOMEM=y CONFIG_HAS_IOPORT=y CONFIG_HAS_DMA=y CONFIG_HAVE_LMB=y +CONFIG_NLATTR=y # # Kernel hacking @@ -1973,13 +2057,16 @@ CONFIG_ENABLE_MUST_CHECK=y CONFIG_FRAME_WARN=1024 CONFIG_MAGIC_SYSRQ=y # CONFIG_UNUSED_SYMBOLS is not set -# CONFIG_DEBUG_FS is not set +CONFIG_DEBUG_FS=y # CONFIG_HEADERS_CHECK is not set CONFIG_DEBUG_KERNEL=y # CONFIG_DEBUG_SHIRQ is not set CONFIG_DETECT_SOFTLOCKUP=y # CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0 +CONFIG_DETECT_HUNG_TASK=y +# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set +CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0 CONFIG_SCHED_DEBUG=y CONFIG_SCHEDSTATS=y # CONFIG_TIMER_STATS is not set @@ -1994,6 +2081,7 @@ CONFIG_SCHEDSTATS=y # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set CONFIG_STACKTRACE=y # CONFIG_DEBUG_KOBJECT is not set +# CONFIG_DEBUG_HIGHMEM is not set CONFIG_DEBUG_BUGVERBOSE=y # CONFIG_DEBUG_INFO is not set # CONFIG_DEBUG_VM is not set @@ -2001,6 +2089,7 @@ CONFIG_DEBUG_BUGVERBOSE=y CONFIG_DEBUG_MEMORY_INIT=y # CONFIG_DEBUG_LIST is not set # CONFIG_DEBUG_SG is not set +# CONFIG_DEBUG_NOTIFIERS is not set # CONFIG_BOOT_PRINTK_DELAY is not set # CONFIG_RCU_TORTURE_TEST is not set # CONFIG_RCU_CPU_STALL_DETECTOR is not set @@ -2009,7 +2098,14 @@ CONFIG_DEBUG_MEMORY_INIT=y # CONFIG_FAULT_INJECTION is not set CONFIG_LATENCYTOP=y CONFIG_SYSCTL_SYSCALL_CHECK=y +CONFIG_NOP_TRACER=y CONFIG_HAVE_FUNCTION_TRACER=y +CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y +CONFIG_HAVE_DYNAMIC_FTRACE=y +CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y +CONFIG_RING_BUFFER=y +CONFIG_TRACING=y +CONFIG_TRACING_SUPPORT=y # # Tracers @@ -2017,12 +2113,19 @@ CONFIG_HAVE_FUNCTION_TRACER=y # CONFIG_FUNCTION_TRACER is not set # CONFIG_SCHED_TRACER is not set # CONFIG_CONTEXT_SWITCH_TRACER is not set +# CONFIG_EVENT_TRACER is not set # CONFIG_BOOT_TRACER is not set +# CONFIG_TRACE_BRANCH_PROFILING is not set # CONFIG_STACK_TRACER is not set -# CONFIG_DYNAMIC_PRINTK_DEBUG is not set +# CONFIG_KMEMTRACE is not set +# CONFIG_WORKQUEUE_TRACER is not set +# CONFIG_BLK_DEV_IO_TRACE is not set +# CONFIG_FTRACE_STARTUP_TEST is not set +# CONFIG_DYNAMIC_DEBUG is not set # CONFIG_SAMPLES is not set CONFIG_HAVE_ARCH_KGDB=y # CONFIG_KGDB is not set +CONFIG_PRINT_STACK_DEPTH=64 # CONFIG_DEBUG_STACKOVERFLOW is not set # CONFIG_DEBUG_STACK_USAGE is not set # CONFIG_CODE_PATCHING_SELFTEST is not set @@ -2033,6 +2136,7 @@ CONFIG_XMON_DEFAULT=y CONFIG_XMON_DISASSEMBLY=y CONFIG_DEBUGGER=y CONFIG_IRQSTACKS=y +# CONFIG_VIRQ_DEBUG is not set # CONFIG_BDI_SWITCH is not set CONFIG_BOOTX_TEXT=y # CONFIG_PPC_EARLY_DEBUG is not set @@ -2051,13 +2155,20 @@ CONFIG_CRYPTO=y # # CONFIG_CRYPTO_FIPS is not set CONFIG_CRYPTO_ALGAPI=y +CONFIG_CRYPTO_ALGAPI2=y CONFIG_CRYPTO_AEAD=y +CONFIG_CRYPTO_AEAD2=y CONFIG_CRYPTO_BLKCIPHER=y +CONFIG_CRYPTO_BLKCIPHER2=y CONFIG_CRYPTO_HASH=y -CONFIG_CRYPTO_RNG=y +CONFIG_CRYPTO_HASH2=y +CONFIG_CRYPTO_RNG2=y +CONFIG_CRYPTO_PCOMP=y CONFIG_CRYPTO_MANAGER=y +CONFIG_CRYPTO_MANAGER2=y # CONFIG_CRYPTO_GF128MUL is not set CONFIG_CRYPTO_NULL=m +CONFIG_CRYPTO_WORKQUEUE=y # CONFIG_CRYPTO_CRYPTD is not set CONFIG_CRYPTO_AUTHENC=y # CONFIG_CRYPTO_TEST is not set @@ -2127,6 +2238,7 @@ CONFIG_CRYPTO_TWOFISH_COMMON=m # Compression # CONFIG_CRYPTO_DEFLATE=m +# CONFIG_CRYPTO_ZLIB is not set # CONFIG_CRYPTO_LZO is not set # diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index b7e034b0a6ddbd4bb9d491106e08b791ef3fac22..53512374e1c9daea22bd71d6d153b69d1b0e0d42 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -131,5 +131,41 @@ static inline int irqs_disabled_flags(unsigned long flags) */ struct irq_chip; +#ifdef CONFIG_PERF_COUNTERS +static inline unsigned long test_perf_counter_pending(void) +{ + unsigned long x; + + asm volatile("lbz %0,%1(13)" + : "=r" (x) + : "i" (offsetof(struct paca_struct, perf_counter_pending))); + return x; +} + +static inline void set_perf_counter_pending(void) +{ + asm volatile("stb %0,%1(13)" : : + "r" (1), + "i" (offsetof(struct paca_struct, perf_counter_pending))); +} + +static inline void clear_perf_counter_pending(void) +{ + asm volatile("stb %0,%1(13)" : : + "r" (0), + "i" (offsetof(struct paca_struct, perf_counter_pending))); +} + +#else + +static inline unsigned long test_perf_counter_pending(void) +{ + return 0; +} + +static inline void set_perf_counter_pending(void) {} +static inline void clear_perf_counter_pending(void) {} +#endif /* CONFIG_PERF_COUNTERS */ + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_HW_IRQ_H */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 0ea1985bdb8b51de64becad0c2a40414c4ac4bae..c8a3cbfe02ffaea0bca9be6d35a9fa8ef218bf18 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -105,6 +105,7 @@ struct paca_struct { u8 soft_enabled; /* irq soft-enable flag */ u8 hard_enabled; /* set if irqs are enabled in MSR */ u8 io_sync; /* writel() needs spin_unlock sync */ + u8 perf_counter_pending; /* PM interrupt while soft-disabled */ /* Stuff for accurate time accounting */ u64 user_time; /* accumulated usermode TB ticks */ diff --git a/arch/powerpc/include/asm/perf_counter.h b/arch/powerpc/include/asm/perf_counter.h new file mode 100644 index 0000000000000000000000000000000000000000..cc7c887705b875e9ec3e5ecb7537b36af7f3d0c9 --- /dev/null +++ b/arch/powerpc/include/asm/perf_counter.h @@ -0,0 +1,98 @@ +/* + * Performance counter support - PowerPC-specific definitions. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include + +#define MAX_HWCOUNTERS 8 +#define MAX_EVENT_ALTERNATIVES 8 +#define MAX_LIMITED_HWCOUNTERS 2 + +/* + * This struct provides the constants and functions needed to + * describe the PMU on a particular POWER-family CPU. + */ +struct power_pmu { + int n_counter; + int max_alternatives; + u64 add_fields; + u64 test_adder; + int (*compute_mmcr)(u64 events[], int n_ev, + unsigned int hwc[], u64 mmcr[]); + int (*get_constraint)(u64 event, u64 *mskp, u64 *valp); + int (*get_alternatives)(u64 event, unsigned int flags, + u64 alt[]); + void (*disable_pmc)(unsigned int pmc, u64 mmcr[]); + int (*limited_pmc_event)(u64 event); + u32 flags; + int n_generic; + int *generic_events; + int (*cache_events)[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; +}; + +extern struct power_pmu *ppmu; + +/* + * Values for power_pmu.flags + */ +#define PPMU_LIMITED_PMC5_6 1 /* PMC5/6 have limited function */ +#define PPMU_ALT_SIPR 2 /* uses alternate posn for SIPR/HV */ + +/* + * Values for flags to get_alternatives() + */ +#define PPMU_LIMITED_PMC_OK 1 /* can put this on a limited PMC */ +#define PPMU_LIMITED_PMC_REQD 2 /* have to put this on a limited PMC */ +#define PPMU_ONLY_COUNT_RUN 4 /* only counting in run state */ + +struct pt_regs; +extern unsigned long perf_misc_flags(struct pt_regs *regs); +#define perf_misc_flags(regs) perf_misc_flags(regs) + +extern unsigned long perf_instruction_pointer(struct pt_regs *regs); + +/* + * The power_pmu.get_constraint function returns a 64-bit value and + * a 64-bit mask that express the constraints between this event and + * other events. + * + * The value and mask are divided up into (non-overlapping) bitfields + * of three different types: + * + * Select field: this expresses the constraint that some set of bits + * in MMCR* needs to be set to a specific value for this event. For a + * select field, the mask contains 1s in every bit of the field, and + * the value contains a unique value for each possible setting of the + * MMCR* bits. The constraint checking code will ensure that two events + * that set the same field in their masks have the same value in their + * value dwords. + * + * Add field: this expresses the constraint that there can be at most + * N events in a particular class. A field of k bits can be used for + * N <= 2^(k-1) - 1. The mask has the most significant bit of the field + * set (and the other bits 0), and the value has only the least significant + * bit of the field set. In addition, the 'add_fields' and 'test_adder' + * in the struct power_pmu for this processor come into play. The + * add_fields value contains 1 in the LSB of the field, and the + * test_adder contains 2^(k-1) - 1 - N in the field. + * + * NAND field: this expresses the constraint that you may not have events + * in all of a set of classes. (For example, on PPC970, you can't select + * events from the FPU, ISU and IDU simultaneously, although any two are + * possible.) For N classes, the field is N+1 bits wide, and each class + * is assigned one bit from the least-significant N bits. The mask has + * only the most-significant bit set, and the value has only the bit + * for the event's class set. The test_adder has the least significant + * bit set in the field. + * + * If an event is not subject to the constraint expressed by a particular + * field, then it will have 0 in both the mask and value for that field. + */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index e8018d540e87db3f3c0f5bf44b7453dc57dbe9d9..fb359b0a6937de645c8101709ac4ade7fd9df446 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -492,11 +492,13 @@ #define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */ #define SPRN_MMCR1 798 #define SPRN_MMCRA 0x312 +#define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ #define MMCRA_SIHV 0x10000000UL /* state of MSR HV when SIAR set */ #define MMCRA_SIPR 0x08000000UL /* state of MSR PR when SIAR set */ #define MMCRA_SLOT 0x07000000UL /* SLOT bits (37-39) */ #define MMCRA_SLOT_SHIFT 24 #define MMCRA_SAMPLE_ENABLE 0x00000001UL /* enable sampling */ +#define POWER6_MMCRA_SDSYNC 0x0000080000000000ULL /* SDAR/SIAR synced */ #define POWER6_MMCRA_SIHV 0x0000040000000000ULL #define POWER6_MMCRA_SIPR 0x0000020000000000ULL #define POWER6_MMCRA_THRM 0x00000020UL diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index d98a30dfd41ca2e11c8f7212097182ab6caaeaa2..a0b92de51c7edfa594941f134de592c77eb49b3e 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -322,6 +322,6 @@ SYSCALL_SPU(epoll_create1) SYSCALL_SPU(dup3) SYSCALL_SPU(pipe2) SYSCALL(inotify_init1) -SYSCALL(ni_syscall) +SYSCALL_SPU(perf_counter_open) COMPAT_SYS_SPU(preadv) COMPAT_SYS_SPU(pwritev) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 3f06f8ec81c513639e96194ca7b40262e35cf0ca..4badac2d11d1a7f3c8989ffb5be20dd4cd131a57 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -341,6 +341,7 @@ #define __NR_dup3 316 #define __NR_pipe2 317 #define __NR_inotify_init1 318 +#define __NR_perf_counter_open 319 #define __NR_preadv 320 #define __NR_pwritev 321 diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 65cf36502aa60142d6229c0dbab1b119bb62c9f8..a7def5f90cadbe2392b7ecfd6aa65f80570b1014 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -95,6 +95,9 @@ obj64-$(CONFIG_AUDIT) += compat_audit.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o +obj-$(CONFIG_PERF_COUNTERS) += perf_counter.o power4-pmu.o ppc970-pmu.o \ + power5-pmu.o power5+-pmu.o power6-pmu.o \ + power7-pmu.o obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index ce90c570cd8ee1f40a4042720572c89724f6f694..561b6465231105073ef991300d6aab206e1e0531 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -129,6 +129,7 @@ int main(void) DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr)); DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled)); DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled)); + DEFINE(PACAPERFPEND, offsetof(struct paca_struct, perf_counter_pending)); DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id)); #ifdef CONFIG_PPC_MM_SLICES DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct, diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index abfc3233047900ac675559928adc73b52466f75b..43e073477c34adeac616067a62b4302dbc66d6d6 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -526,6 +526,15 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES) 2: TRACE_AND_RESTORE_IRQ(r5); +#ifdef CONFIG_PERF_COUNTERS + /* check paca->perf_counter_pending if we're enabling ints */ + lbz r3,PACAPERFPEND(r13) + and. r3,r3,r5 + beq 27f + bl .perf_counter_do_pending +27: +#endif /* CONFIG_PERF_COUNTERS */ + /* extract EE bit and use it to restore paca->hard_enabled */ ld r3,_MSR(r1) rldicl r4,r3,49,63 /* r0 = (r3 >> 15) & 1 */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 8564a412e7a66f28b0403007f7a6615d23167816..f7f376ea7b178792fa12927b0578230e9bc61915 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -53,6 +53,7 @@ #include #include #include +#include #include #include @@ -137,6 +138,11 @@ notrace void raw_local_irq_restore(unsigned long en) } #endif /* CONFIG_PPC_STD_MMU_64 */ + if (test_perf_counter_pending()) { + clear_perf_counter_pending(); + perf_counter_do_pending(); + } + /* * if (get_paca()->hard_enabled) return; * But again we need to take care that gcc gets hard_enabled directly diff --git a/arch/powerpc/kernel/perf_counter.c b/arch/powerpc/kernel/perf_counter.c new file mode 100644 index 0000000000000000000000000000000000000000..bb202388170e7d3807edfb81bb1deed418d051c7 --- /dev/null +++ b/arch/powerpc/kernel/perf_counter.c @@ -0,0 +1,1263 @@ +/* + * Performance counter support - powerpc architecture code + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct cpu_hw_counters { + int n_counters; + int n_percpu; + int disabled; + int n_added; + int n_limited; + u8 pmcs_enabled; + struct perf_counter *counter[MAX_HWCOUNTERS]; + u64 events[MAX_HWCOUNTERS]; + unsigned int flags[MAX_HWCOUNTERS]; + u64 mmcr[3]; + struct perf_counter *limited_counter[MAX_LIMITED_HWCOUNTERS]; + u8 limited_hwidx[MAX_LIMITED_HWCOUNTERS]; +}; +DEFINE_PER_CPU(struct cpu_hw_counters, cpu_hw_counters); + +struct power_pmu *ppmu; + +/* + * Normally, to ignore kernel events we set the FCS (freeze counters + * in supervisor mode) bit in MMCR0, but if the kernel runs with the + * hypervisor bit set in the MSR, or if we are running on a processor + * where the hypervisor bit is forced to 1 (as on Apple G5 processors), + * then we need to use the FCHV bit to ignore kernel events. + */ +static unsigned int freeze_counters_kernel = MMCR0_FCS; + +static void perf_counter_interrupt(struct pt_regs *regs); + +void perf_counter_print_debug(void) +{ +} + +/* + * Read one performance monitor counter (PMC). + */ +static unsigned long read_pmc(int idx) +{ + unsigned long val; + + switch (idx) { + case 1: + val = mfspr(SPRN_PMC1); + break; + case 2: + val = mfspr(SPRN_PMC2); + break; + case 3: + val = mfspr(SPRN_PMC3); + break; + case 4: + val = mfspr(SPRN_PMC4); + break; + case 5: + val = mfspr(SPRN_PMC5); + break; + case 6: + val = mfspr(SPRN_PMC6); + break; + case 7: + val = mfspr(SPRN_PMC7); + break; + case 8: + val = mfspr(SPRN_PMC8); + break; + default: + printk(KERN_ERR "oops trying to read PMC%d\n", idx); + val = 0; + } + return val; +} + +/* + * Write one PMC. + */ +static void write_pmc(int idx, unsigned long val) +{ + switch (idx) { + case 1: + mtspr(SPRN_PMC1, val); + break; + case 2: + mtspr(SPRN_PMC2, val); + break; + case 3: + mtspr(SPRN_PMC3, val); + break; + case 4: + mtspr(SPRN_PMC4, val); + break; + case 5: + mtspr(SPRN_PMC5, val); + break; + case 6: + mtspr(SPRN_PMC6, val); + break; + case 7: + mtspr(SPRN_PMC7, val); + break; + case 8: + mtspr(SPRN_PMC8, val); + break; + default: + printk(KERN_ERR "oops trying to write PMC%d\n", idx); + } +} + +/* + * Check if a set of events can all go on the PMU at once. + * If they can't, this will look at alternative codes for the events + * and see if any combination of alternative codes is feasible. + * The feasible set is returned in event[]. + */ +static int power_check_constraints(u64 event[], unsigned int cflags[], + int n_ev) +{ + u64 mask, value, nv; + u64 alternatives[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; + u64 amasks[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; + u64 avalues[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES]; + u64 smasks[MAX_HWCOUNTERS], svalues[MAX_HWCOUNTERS]; + int n_alt[MAX_HWCOUNTERS], choice[MAX_HWCOUNTERS]; + int i, j; + u64 addf = ppmu->add_fields; + u64 tadd = ppmu->test_adder; + + if (n_ev > ppmu->n_counter) + return -1; + + /* First see if the events will go on as-is */ + for (i = 0; i < n_ev; ++i) { + if ((cflags[i] & PPMU_LIMITED_PMC_REQD) + && !ppmu->limited_pmc_event(event[i])) { + ppmu->get_alternatives(event[i], cflags[i], + alternatives[i]); + event[i] = alternatives[i][0]; + } + if (ppmu->get_constraint(event[i], &amasks[i][0], + &avalues[i][0])) + return -1; + } + value = mask = 0; + for (i = 0; i < n_ev; ++i) { + nv = (value | avalues[i][0]) + (value & avalues[i][0] & addf); + if ((((nv + tadd) ^ value) & mask) != 0 || + (((nv + tadd) ^ avalues[i][0]) & amasks[i][0]) != 0) + break; + value = nv; + mask |= amasks[i][0]; + } + if (i == n_ev) + return 0; /* all OK */ + + /* doesn't work, gather alternatives... */ + if (!ppmu->get_alternatives) + return -1; + for (i = 0; i < n_ev; ++i) { + choice[i] = 0; + n_alt[i] = ppmu->get_alternatives(event[i], cflags[i], + alternatives[i]); + for (j = 1; j < n_alt[i]; ++j) + ppmu->get_constraint(alternatives[i][j], + &amasks[i][j], &avalues[i][j]); + } + + /* enumerate all possibilities and see if any will work */ + i = 0; + j = -1; + value = mask = nv = 0; + while (i < n_ev) { + if (j >= 0) { + /* we're backtracking, restore context */ + value = svalues[i]; + mask = smasks[i]; + j = choice[i]; + } + /* + * See if any alternative k for event i, + * where k > j, will satisfy the constraints. + */ + while (++j < n_alt[i]) { + nv = (value | avalues[i][j]) + + (value & avalues[i][j] & addf); + if ((((nv + tadd) ^ value) & mask) == 0 && + (((nv + tadd) ^ avalues[i][j]) + & amasks[i][j]) == 0) + break; + } + if (j >= n_alt[i]) { + /* + * No feasible alternative, backtrack + * to event i-1 and continue enumerating its + * alternatives from where we got up to. + */ + if (--i < 0) + return -1; + } else { + /* + * Found a feasible alternative for event i, + * remember where we got up to with this event, + * go on to the next event, and start with + * the first alternative for it. + */ + choice[i] = j; + svalues[i] = value; + smasks[i] = mask; + value = nv; + mask |= amasks[i][j]; + ++i; + j = -1; + } + } + + /* OK, we have a feasible combination, tell the caller the solution */ + for (i = 0; i < n_ev; ++i) + event[i] = alternatives[i][choice[i]]; + return 0; +} + +/* + * Check if newly-added counters have consistent settings for + * exclude_{user,kernel,hv} with each other and any previously + * added counters. + */ +static int check_excludes(struct perf_counter **ctrs, unsigned int cflags[], + int n_prev, int n_new) +{ + int eu = 0, ek = 0, eh = 0; + int i, n, first; + struct perf_counter *counter; + + n = n_prev + n_new; + if (n <= 1) + return 0; + + first = 1; + for (i = 0; i < n; ++i) { + if (cflags[i] & PPMU_LIMITED_PMC_OK) { + cflags[i] &= ~PPMU_LIMITED_PMC_REQD; + continue; + } + counter = ctrs[i]; + if (first) { + eu = counter->attr.exclude_user; + ek = counter->attr.exclude_kernel; + eh = counter->attr.exclude_hv; + first = 0; + } else if (counter->attr.exclude_user != eu || + counter->attr.exclude_kernel != ek || + counter->attr.exclude_hv != eh) { + return -EAGAIN; + } + } + + if (eu || ek || eh) + for (i = 0; i < n; ++i) + if (cflags[i] & PPMU_LIMITED_PMC_OK) + cflags[i] |= PPMU_LIMITED_PMC_REQD; + + return 0; +} + +static void power_pmu_read(struct perf_counter *counter) +{ + long val, delta, prev; + + if (!counter->hw.idx) + return; + /* + * Performance monitor interrupts come even when interrupts + * are soft-disabled, as long as interrupts are hard-enabled. + * Therefore we treat them like NMIs. + */ + do { + prev = atomic64_read(&counter->hw.prev_count); + barrier(); + val = read_pmc(counter->hw.idx); + } while (atomic64_cmpxchg(&counter->hw.prev_count, prev, val) != prev); + + /* The counters are only 32 bits wide */ + delta = (val - prev) & 0xfffffffful; + atomic64_add(delta, &counter->count); + atomic64_sub(delta, &counter->hw.period_left); +} + +/* + * On some machines, PMC5 and PMC6 can't be written, don't respect + * the freeze conditions, and don't generate interrupts. This tells + * us if `counter' is using such a PMC. + */ +static int is_limited_pmc(int pmcnum) +{ + return (ppmu->flags & PPMU_LIMITED_PMC5_6) + && (pmcnum == 5 || pmcnum == 6); +} + +static void freeze_limited_counters(struct cpu_hw_counters *cpuhw, + unsigned long pmc5, unsigned long pmc6) +{ + struct perf_counter *counter; + u64 val, prev, delta; + int i; + + for (i = 0; i < cpuhw->n_limited; ++i) { + counter = cpuhw->limited_counter[i]; + if (!counter->hw.idx) + continue; + val = (counter->hw.idx == 5) ? pmc5 : pmc6; + prev = atomic64_read(&counter->hw.prev_count); + counter->hw.idx = 0; + delta = (val - prev) & 0xfffffffful; + atomic64_add(delta, &counter->count); + } +} + +static void thaw_limited_counters(struct cpu_hw_counters *cpuhw, + unsigned long pmc5, unsigned long pmc6) +{ + struct perf_counter *counter; + u64 val; + int i; + + for (i = 0; i < cpuhw->n_limited; ++i) { + counter = cpuhw->limited_counter[i]; + counter->hw.idx = cpuhw->limited_hwidx[i]; + val = (counter->hw.idx == 5) ? pmc5 : pmc6; + atomic64_set(&counter->hw.prev_count, val); + perf_counter_update_userpage(counter); + } +} + +/* + * Since limited counters don't respect the freeze conditions, we + * have to read them immediately after freezing or unfreezing the + * other counters. We try to keep the values from the limited + * counters as consistent as possible by keeping the delay (in + * cycles and instructions) between freezing/unfreezing and reading + * the limited counters as small and consistent as possible. + * Therefore, if any limited counters are in use, we read them + * both, and always in the same order, to minimize variability, + * and do it inside the same asm that writes MMCR0. + */ +static void write_mmcr0(struct cpu_hw_counters *cpuhw, unsigned long mmcr0) +{ + unsigned long pmc5, pmc6; + + if (!cpuhw->n_limited) { + mtspr(SPRN_MMCR0, mmcr0); + return; + } + + /* + * Write MMCR0, then read PMC5 and PMC6 immediately. + * To ensure we don't get a performance monitor interrupt + * between writing MMCR0 and freezing/thawing the limited + * counters, we first write MMCR0 with the counter overflow + * interrupt enable bits turned off. + */ + asm volatile("mtspr %3,%2; mfspr %0,%4; mfspr %1,%5" + : "=&r" (pmc5), "=&r" (pmc6) + : "r" (mmcr0 & ~(MMCR0_PMC1CE | MMCR0_PMCjCE)), + "i" (SPRN_MMCR0), + "i" (SPRN_PMC5), "i" (SPRN_PMC6)); + + if (mmcr0 & MMCR0_FC) + freeze_limited_counters(cpuhw, pmc5, pmc6); + else + thaw_limited_counters(cpuhw, pmc5, pmc6); + + /* + * Write the full MMCR0 including the counter overflow interrupt + * enable bits, if necessary. + */ + if (mmcr0 & (MMCR0_PMC1CE | MMCR0_PMCjCE)) + mtspr(SPRN_MMCR0, mmcr0); +} + +/* + * Disable all counters to prevent PMU interrupts and to allow + * counters to be added or removed. + */ +void hw_perf_disable(void) +{ + struct cpu_hw_counters *cpuhw; + unsigned long ret; + unsigned long flags; + + local_irq_save(flags); + cpuhw = &__get_cpu_var(cpu_hw_counters); + + ret = cpuhw->disabled; + if (!ret) { + cpuhw->disabled = 1; + cpuhw->n_added = 0; + + /* + * Check if we ever enabled the PMU on this cpu. + */ + if (!cpuhw->pmcs_enabled) { + if (ppc_md.enable_pmcs) + ppc_md.enable_pmcs(); + cpuhw->pmcs_enabled = 1; + } + + /* + * Disable instruction sampling if it was enabled + */ + if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) { + mtspr(SPRN_MMCRA, + cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE); + mb(); + } + + /* + * Set the 'freeze counters' bit. + * The barrier is to make sure the mtspr has been + * executed and the PMU has frozen the counters + * before we return. + */ + write_mmcr0(cpuhw, mfspr(SPRN_MMCR0) | MMCR0_FC); + mb(); + } + local_irq_restore(flags); +} + +/* + * Re-enable all counters if disable == 0. + * If we were previously disabled and counters were added, then + * put the new config on the PMU. + */ +void hw_perf_enable(void) +{ + struct perf_counter *counter; + struct cpu_hw_counters *cpuhw; + unsigned long flags; + long i; + unsigned long val; + s64 left; + unsigned int hwc_index[MAX_HWCOUNTERS]; + int n_lim; + int idx; + + local_irq_save(flags); + cpuhw = &__get_cpu_var(cpu_hw_counters); + if (!cpuhw->disabled) { + local_irq_restore(flags); + return; + } + cpuhw->disabled = 0; + + /* + * If we didn't change anything, or only removed counters, + * no need to recalculate MMCR* settings and reset the PMCs. + * Just reenable the PMU with the current MMCR* settings + * (possibly updated for removal of counters). + */ + if (!cpuhw->n_added) { + mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE); + mtspr(SPRN_MMCR1, cpuhw->mmcr[1]); + if (cpuhw->n_counters == 0) + get_lppaca()->pmcregs_in_use = 0; + goto out_enable; + } + + /* + * Compute MMCR* values for the new set of counters + */ + if (ppmu->compute_mmcr(cpuhw->events, cpuhw->n_counters, hwc_index, + cpuhw->mmcr)) { + /* shouldn't ever get here */ + printk(KERN_ERR "oops compute_mmcr failed\n"); + goto out; + } + + /* + * Add in MMCR0 freeze bits corresponding to the + * attr.exclude_* bits for the first counter. + * We have already checked that all counters have the + * same values for these bits as the first counter. + */ + counter = cpuhw->counter[0]; + if (counter->attr.exclude_user) + cpuhw->mmcr[0] |= MMCR0_FCP; + if (counter->attr.exclude_kernel) + cpuhw->mmcr[0] |= freeze_counters_kernel; + if (counter->attr.exclude_hv) + cpuhw->mmcr[0] |= MMCR0_FCHV; + + /* + * Write the new configuration to MMCR* with the freeze + * bit set and set the hardware counters to their initial values. + * Then unfreeze the counters. + */ + get_lppaca()->pmcregs_in_use = 1; + mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE); + mtspr(SPRN_MMCR1, cpuhw->mmcr[1]); + mtspr(SPRN_MMCR0, (cpuhw->mmcr[0] & ~(MMCR0_PMC1CE | MMCR0_PMCjCE)) + | MMCR0_FC); + + /* + * Read off any pre-existing counters that need to move + * to another PMC. + */ + for (i = 0; i < cpuhw->n_counters; ++i) { + counter = cpuhw->counter[i]; + if (counter->hw.idx && counter->hw.idx != hwc_index[i] + 1) { + power_pmu_read(counter); + write_pmc(counter->hw.idx, 0); + counter->hw.idx = 0; + } + } + + /* + * Initialize the PMCs for all the new and moved counters. + */ + cpuhw->n_limited = n_lim = 0; + for (i = 0; i < cpuhw->n_counters; ++i) { + counter = cpuhw->counter[i]; + if (counter->hw.idx) + continue; + idx = hwc_index[i] + 1; + if (is_limited_pmc(idx)) { + cpuhw->limited_counter[n_lim] = counter; + cpuhw->limited_hwidx[n_lim] = idx; + ++n_lim; + continue; + } + val = 0; + if (counter->hw.sample_period) { + left = atomic64_read(&counter->hw.period_left); + if (left < 0x80000000L) + val = 0x80000000L - left; + } + atomic64_set(&counter->hw.prev_count, val); + counter->hw.idx = idx; + write_pmc(idx, val); + perf_counter_update_userpage(counter); + } + cpuhw->n_limited = n_lim; + cpuhw->mmcr[0] |= MMCR0_PMXE | MMCR0_FCECE; + + out_enable: + mb(); + write_mmcr0(cpuhw, cpuhw->mmcr[0]); + + /* + * Enable instruction sampling if necessary + */ + if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) { + mb(); + mtspr(SPRN_MMCRA, cpuhw->mmcr[2]); + } + + out: + local_irq_restore(flags); +} + +static int collect_events(struct perf_counter *group, int max_count, + struct perf_counter *ctrs[], u64 *events, + unsigned int *flags) +{ + int n = 0; + struct perf_counter *counter; + + if (!is_software_counter(group)) { + if (n >= max_count) + return -1; + ctrs[n] = group; + flags[n] = group->hw.counter_base; + events[n++] = group->hw.config; + } + list_for_each_entry(counter, &group->sibling_list, list_entry) { + if (!is_software_counter(counter) && + counter->state != PERF_COUNTER_STATE_OFF) { + if (n >= max_count) + return -1; + ctrs[n] = counter; + flags[n] = counter->hw.counter_base; + events[n++] = counter->hw.config; + } + } + return n; +} + +static void counter_sched_in(struct perf_counter *counter, int cpu) +{ + counter->state = PERF_COUNTER_STATE_ACTIVE; + counter->oncpu = cpu; + counter->tstamp_running += counter->ctx->time - counter->tstamp_stopped; + if (is_software_counter(counter)) + counter->pmu->enable(counter); +} + +/* + * Called to enable a whole group of counters. + * Returns 1 if the group was enabled, or -EAGAIN if it could not be. + * Assumes the caller has disabled interrupts and has + * frozen the PMU with hw_perf_save_disable. + */ +int hw_perf_group_sched_in(struct perf_counter *group_leader, + struct perf_cpu_context *cpuctx, + struct perf_counter_context *ctx, int cpu) +{ + struct cpu_hw_counters *cpuhw; + long i, n, n0; + struct perf_counter *sub; + + cpuhw = &__get_cpu_var(cpu_hw_counters); + n0 = cpuhw->n_counters; + n = collect_events(group_leader, ppmu->n_counter - n0, + &cpuhw->counter[n0], &cpuhw->events[n0], + &cpuhw->flags[n0]); + if (n < 0) + return -EAGAIN; + if (check_excludes(cpuhw->counter, cpuhw->flags, n0, n)) + return -EAGAIN; + i = power_check_constraints(cpuhw->events, cpuhw->flags, n + n0); + if (i < 0) + return -EAGAIN; + cpuhw->n_counters = n0 + n; + cpuhw->n_added += n; + + /* + * OK, this group can go on; update counter states etc., + * and enable any software counters + */ + for (i = n0; i < n0 + n; ++i) + cpuhw->counter[i]->hw.config = cpuhw->events[i]; + cpuctx->active_oncpu += n; + n = 1; + counter_sched_in(group_leader, cpu); + list_for_each_entry(sub, &group_leader->sibling_list, list_entry) { + if (sub->state != PERF_COUNTER_STATE_OFF) { + counter_sched_in(sub, cpu); + ++n; + } + } + ctx->nr_active += n; + + return 1; +} + +/* + * Add a counter to the PMU. + * If all counters are not already frozen, then we disable and + * re-enable the PMU in order to get hw_perf_enable to do the + * actual work of reconfiguring the PMU. + */ +static int power_pmu_enable(struct perf_counter *counter) +{ + struct cpu_hw_counters *cpuhw; + unsigned long flags; + int n0; + int ret = -EAGAIN; + + local_irq_save(flags); + perf_disable(); + + /* + * Add the counter to the list (if there is room) + * and check whether the total set is still feasible. + */ + cpuhw = &__get_cpu_var(cpu_hw_counters); + n0 = cpuhw->n_counters; + if (n0 >= ppmu->n_counter) + goto out; + cpuhw->counter[n0] = counter; + cpuhw->events[n0] = counter->hw.config; + cpuhw->flags[n0] = counter->hw.counter_base; + if (check_excludes(cpuhw->counter, cpuhw->flags, n0, 1)) + goto out; + if (power_check_constraints(cpuhw->events, cpuhw->flags, n0 + 1)) + goto out; + + counter->hw.config = cpuhw->events[n0]; + ++cpuhw->n_counters; + ++cpuhw->n_added; + + ret = 0; + out: + perf_enable(); + local_irq_restore(flags); + return ret; +} + +/* + * Remove a counter from the PMU. + */ +static void power_pmu_disable(struct perf_counter *counter) +{ + struct cpu_hw_counters *cpuhw; + long i; + unsigned long flags; + + local_irq_save(flags); + perf_disable(); + + power_pmu_read(counter); + + cpuhw = &__get_cpu_var(cpu_hw_counters); + for (i = 0; i < cpuhw->n_counters; ++i) { + if (counter == cpuhw->counter[i]) { + while (++i < cpuhw->n_counters) + cpuhw->counter[i-1] = cpuhw->counter[i]; + --cpuhw->n_counters; + ppmu->disable_pmc(counter->hw.idx - 1, cpuhw->mmcr); + if (counter->hw.idx) { + write_pmc(counter->hw.idx, 0); + counter->hw.idx = 0; + } + perf_counter_update_userpage(counter); + break; + } + } + for (i = 0; i < cpuhw->n_limited; ++i) + if (counter == cpuhw->limited_counter[i]) + break; + if (i < cpuhw->n_limited) { + while (++i < cpuhw->n_limited) { + cpuhw->limited_counter[i-1] = cpuhw->limited_counter[i]; + cpuhw->limited_hwidx[i-1] = cpuhw->limited_hwidx[i]; + } + --cpuhw->n_limited; + } + if (cpuhw->n_counters == 0) { + /* disable exceptions if no counters are running */ + cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE); + } + + perf_enable(); + local_irq_restore(flags); +} + +/* + * Re-enable interrupts on a counter after they were throttled + * because they were coming too fast. + */ +static void power_pmu_unthrottle(struct perf_counter *counter) +{ + s64 val, left; + unsigned long flags; + + if (!counter->hw.idx || !counter->hw.sample_period) + return; + local_irq_save(flags); + perf_disable(); + power_pmu_read(counter); + left = counter->hw.sample_period; + counter->hw.last_period = left; + val = 0; + if (left < 0x80000000L) + val = 0x80000000L - left; + write_pmc(counter->hw.idx, val); + atomic64_set(&counter->hw.prev_count, val); + atomic64_set(&counter->hw.period_left, left); + perf_counter_update_userpage(counter); + perf_enable(); + local_irq_restore(flags); +} + +struct pmu power_pmu = { + .enable = power_pmu_enable, + .disable = power_pmu_disable, + .read = power_pmu_read, + .unthrottle = power_pmu_unthrottle, +}; + +/* + * Return 1 if we might be able to put counter on a limited PMC, + * or 0 if not. + * A counter can only go on a limited PMC if it counts something + * that a limited PMC can count, doesn't require interrupts, and + * doesn't exclude any processor mode. + */ +static int can_go_on_limited_pmc(struct perf_counter *counter, u64 ev, + unsigned int flags) +{ + int n; + u64 alt[MAX_EVENT_ALTERNATIVES]; + + if (counter->attr.exclude_user + || counter->attr.exclude_kernel + || counter->attr.exclude_hv + || counter->attr.sample_period) + return 0; + + if (ppmu->limited_pmc_event(ev)) + return 1; + + /* + * The requested event isn't on a limited PMC already; + * see if any alternative code goes on a limited PMC. + */ + if (!ppmu->get_alternatives) + return 0; + + flags |= PPMU_LIMITED_PMC_OK | PPMU_LIMITED_PMC_REQD; + n = ppmu->get_alternatives(ev, flags, alt); + + return n > 0; +} + +/* + * Find an alternative event that goes on a normal PMC, if possible, + * and return the event code, or 0 if there is no such alternative. + * (Note: event code 0 is "don't count" on all machines.) + */ +static u64 normal_pmc_alternative(u64 ev, unsigned long flags) +{ + u64 alt[MAX_EVENT_ALTERNATIVES]; + int n; + + flags &= ~(PPMU_LIMITED_PMC_OK | PPMU_LIMITED_PMC_REQD); + n = ppmu->get_alternatives(ev, flags, alt); + if (!n) + return 0; + return alt[0]; +} + +/* Number of perf_counters counting hardware events */ +static atomic_t num_counters; +/* Used to avoid races in calling reserve/release_pmc_hardware */ +static DEFINE_MUTEX(pmc_reserve_mutex); + +/* + * Release the PMU if this is the last perf_counter. + */ +static void hw_perf_counter_destroy(struct perf_counter *counter) +{ + if (!atomic_add_unless(&num_counters, -1, 1)) { + mutex_lock(&pmc_reserve_mutex); + if (atomic_dec_return(&num_counters) == 0) + release_pmc_hardware(); + mutex_unlock(&pmc_reserve_mutex); + } +} + +/* + * Translate a generic cache event config to a raw event code. + */ +static int hw_perf_cache_event(u64 config, u64 *eventp) +{ + unsigned long type, op, result; + int ev; + + if (!ppmu->cache_events) + return -EINVAL; + + /* unpack config */ + type = config & 0xff; + op = (config >> 8) & 0xff; + result = (config >> 16) & 0xff; + + if (type >= PERF_COUNT_HW_CACHE_MAX || + op >= PERF_COUNT_HW_CACHE_OP_MAX || + result >= PERF_COUNT_HW_CACHE_RESULT_MAX) + return -EINVAL; + + ev = (*ppmu->cache_events)[type][op][result]; + if (ev == 0) + return -EOPNOTSUPP; + if (ev == -1) + return -EINVAL; + *eventp = ev; + return 0; +} + +const struct pmu *hw_perf_counter_init(struct perf_counter *counter) +{ + u64 ev; + unsigned long flags; + struct perf_counter *ctrs[MAX_HWCOUNTERS]; + u64 events[MAX_HWCOUNTERS]; + unsigned int cflags[MAX_HWCOUNTERS]; + int n; + int err; + + if (!ppmu) + return ERR_PTR(-ENXIO); + switch (counter->attr.type) { + case PERF_TYPE_HARDWARE: + ev = counter->attr.config; + if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0) + return ERR_PTR(-EOPNOTSUPP); + ev = ppmu->generic_events[ev]; + break; + case PERF_TYPE_HW_CACHE: + err = hw_perf_cache_event(counter->attr.config, &ev); + if (err) + return ERR_PTR(err); + break; + case PERF_TYPE_RAW: + ev = counter->attr.config; + break; + } + counter->hw.config_base = ev; + counter->hw.idx = 0; + + /* + * If we are not running on a hypervisor, force the + * exclude_hv bit to 0 so that we don't care what + * the user set it to. + */ + if (!firmware_has_feature(FW_FEATURE_LPAR)) + counter->attr.exclude_hv = 0; + + /* + * If this is a per-task counter, then we can use + * PM_RUN_* events interchangeably with their non RUN_* + * equivalents, e.g. PM_RUN_CYC instead of PM_CYC. + * XXX we should check if the task is an idle task. + */ + flags = 0; + if (counter->ctx->task) + flags |= PPMU_ONLY_COUNT_RUN; + + /* + * If this machine has limited counters, check whether this + * event could go on a limited counter. + */ + if (ppmu->flags & PPMU_LIMITED_PMC5_6) { + if (can_go_on_limited_pmc(counter, ev, flags)) { + flags |= PPMU_LIMITED_PMC_OK; + } else if (ppmu->limited_pmc_event(ev)) { + /* + * The requested event is on a limited PMC, + * but we can't use a limited PMC; see if any + * alternative goes on a normal PMC. + */ + ev = normal_pmc_alternative(ev, flags); + if (!ev) + return ERR_PTR(-EINVAL); + } + } + + /* + * If this is in a group, check if it can go on with all the + * other hardware counters in the group. We assume the counter + * hasn't been linked into its leader's sibling list at this point. + */ + n = 0; + if (counter->group_leader != counter) { + n = collect_events(counter->group_leader, ppmu->n_counter - 1, + ctrs, events, cflags); + if (n < 0) + return ERR_PTR(-EINVAL); + } + events[n] = ev; + ctrs[n] = counter; + cflags[n] = flags; + if (check_excludes(ctrs, cflags, n, 1)) + return ERR_PTR(-EINVAL); + if (power_check_constraints(events, cflags, n + 1)) + return ERR_PTR(-EINVAL); + + counter->hw.config = events[n]; + counter->hw.counter_base = cflags[n]; + counter->hw.last_period = counter->hw.sample_period; + atomic64_set(&counter->hw.period_left, counter->hw.last_period); + + /* + * See if we need to reserve the PMU. + * If no counters are currently in use, then we have to take a + * mutex to ensure that we don't race with another task doing + * reserve_pmc_hardware or release_pmc_hardware. + */ + err = 0; + if (!atomic_inc_not_zero(&num_counters)) { + mutex_lock(&pmc_reserve_mutex); + if (atomic_read(&num_counters) == 0 && + reserve_pmc_hardware(perf_counter_interrupt)) + err = -EBUSY; + else + atomic_inc(&num_counters); + mutex_unlock(&pmc_reserve_mutex); + } + counter->destroy = hw_perf_counter_destroy; + + if (err) + return ERR_PTR(err); + return &power_pmu; +} + +/* + * A counter has overflowed; update its count and record + * things if requested. Note that interrupts are hard-disabled + * here so there is no possibility of being interrupted. + */ +static void record_and_restart(struct perf_counter *counter, long val, + struct pt_regs *regs, int nmi) +{ + u64 period = counter->hw.sample_period; + s64 prev, delta, left; + int record = 0; + u64 addr, mmcra, sdsync; + + /* we don't have to worry about interrupts here */ + prev = atomic64_read(&counter->hw.prev_count); + delta = (val - prev) & 0xfffffffful; + atomic64_add(delta, &counter->count); + + /* + * See if the total period for this counter has expired, + * and update for the next period. + */ + val = 0; + left = atomic64_read(&counter->hw.period_left) - delta; + if (period) { + if (left <= 0) { + left += period; + if (left <= 0) + left = period; + record = 1; + } + if (left < 0x80000000L) + val = 0x80000000L - left; + } + + /* + * Finally record data if requested. + */ + if (record) { + struct perf_sample_data data = { + .regs = regs, + .addr = 0, + .period = counter->hw.last_period, + }; + + if (counter->attr.sample_type & PERF_SAMPLE_ADDR) { + /* + * The user wants a data address recorded. + * If we're not doing instruction sampling, + * give them the SDAR (sampled data address). + * If we are doing instruction sampling, then only + * give them the SDAR if it corresponds to the + * instruction pointed to by SIAR; this is indicated + * by the [POWER6_]MMCRA_SDSYNC bit in MMCRA. + */ + mmcra = regs->dsisr; + sdsync = (ppmu->flags & PPMU_ALT_SIPR) ? + POWER6_MMCRA_SDSYNC : MMCRA_SDSYNC; + if (!(mmcra & MMCRA_SAMPLE_ENABLE) || (mmcra & sdsync)) + data.addr = mfspr(SPRN_SDAR); + } + if (perf_counter_overflow(counter, nmi, &data)) { + /* + * Interrupts are coming too fast - throttle them + * by setting the counter to 0, so it will be + * at least 2^30 cycles until the next interrupt + * (assuming each counter counts at most 2 counts + * per cycle). + */ + val = 0; + left = ~0ULL >> 1; + } + } + + write_pmc(counter->hw.idx, val); + atomic64_set(&counter->hw.prev_count, val); + atomic64_set(&counter->hw.period_left, left); + perf_counter_update_userpage(counter); +} + +/* + * Called from generic code to get the misc flags (i.e. processor mode) + * for an event. + */ +unsigned long perf_misc_flags(struct pt_regs *regs) +{ + unsigned long mmcra; + + if (TRAP(regs) != 0xf00) { + /* not a PMU interrupt */ + return user_mode(regs) ? PERF_EVENT_MISC_USER : + PERF_EVENT_MISC_KERNEL; + } + + mmcra = regs->dsisr; + if (ppmu->flags & PPMU_ALT_SIPR) { + if (mmcra & POWER6_MMCRA_SIHV) + return PERF_EVENT_MISC_HYPERVISOR; + return (mmcra & POWER6_MMCRA_SIPR) ? PERF_EVENT_MISC_USER : + PERF_EVENT_MISC_KERNEL; + } + if (mmcra & MMCRA_SIHV) + return PERF_EVENT_MISC_HYPERVISOR; + return (mmcra & MMCRA_SIPR) ? PERF_EVENT_MISC_USER : + PERF_EVENT_MISC_KERNEL; +} + +/* + * Called from generic code to get the instruction pointer + * for an event. + */ +unsigned long perf_instruction_pointer(struct pt_regs *regs) +{ + unsigned long mmcra; + unsigned long ip; + unsigned long slot; + + if (TRAP(regs) != 0xf00) + return regs->nip; /* not a PMU interrupt */ + + ip = mfspr(SPRN_SIAR); + mmcra = regs->dsisr; + if ((mmcra & MMCRA_SAMPLE_ENABLE) && !(ppmu->flags & PPMU_ALT_SIPR)) { + slot = (mmcra & MMCRA_SLOT) >> MMCRA_SLOT_SHIFT; + if (slot > 1) + ip += 4 * (slot - 1); + } + return ip; +} + +/* + * Performance monitor interrupt stuff + */ +static void perf_counter_interrupt(struct pt_regs *regs) +{ + int i; + struct cpu_hw_counters *cpuhw = &__get_cpu_var(cpu_hw_counters); + struct perf_counter *counter; + long val; + int found = 0; + int nmi; + + if (cpuhw->n_limited) + freeze_limited_counters(cpuhw, mfspr(SPRN_PMC5), + mfspr(SPRN_PMC6)); + + /* + * Overload regs->dsisr to store MMCRA so we only need to read it once. + */ + regs->dsisr = mfspr(SPRN_MMCRA); + + /* + * If interrupts were soft-disabled when this PMU interrupt + * occurred, treat it as an NMI. + */ + nmi = !regs->softe; + if (nmi) + nmi_enter(); + else + irq_enter(); + + for (i = 0; i < cpuhw->n_counters; ++i) { + counter = cpuhw->counter[i]; + if (!counter->hw.idx || is_limited_pmc(counter->hw.idx)) + continue; + val = read_pmc(counter->hw.idx); + if ((int)val < 0) { + /* counter has overflowed */ + found = 1; + record_and_restart(counter, val, regs, nmi); + } + } + + /* + * In case we didn't find and reset the counter that caused + * the interrupt, scan all counters and reset any that are + * negative, to avoid getting continual interrupts. + * Any that we processed in the previous loop will not be negative. + */ + if (!found) { + for (i = 0; i < ppmu->n_counter; ++i) { + if (is_limited_pmc(i + 1)) + continue; + val = read_pmc(i + 1); + if ((int)val < 0) + write_pmc(i + 1, 0); + } + } + + /* + * Reset MMCR0 to its normal value. This will set PMXE and + * clear FC (freeze counters) and PMAO (perf mon alert occurred) + * and thus allow interrupts to occur again. + * XXX might want to use MSR.PM to keep the counters frozen until + * we get back out of this interrupt. + */ + write_mmcr0(cpuhw, cpuhw->mmcr[0]); + + if (nmi) + nmi_exit(); + else + irq_exit(); +} + +void hw_perf_counter_setup(int cpu) +{ + struct cpu_hw_counters *cpuhw = &per_cpu(cpu_hw_counters, cpu); + + memset(cpuhw, 0, sizeof(*cpuhw)); + cpuhw->mmcr[0] = MMCR0_FC; +} + +extern struct power_pmu power4_pmu; +extern struct power_pmu ppc970_pmu; +extern struct power_pmu power5_pmu; +extern struct power_pmu power5p_pmu; +extern struct power_pmu power6_pmu; +extern struct power_pmu power7_pmu; + +static int init_perf_counters(void) +{ + unsigned long pvr; + + /* XXX should get this from cputable */ + pvr = mfspr(SPRN_PVR); + switch (PVR_VER(pvr)) { + case PV_POWER4: + case PV_POWER4p: + ppmu = &power4_pmu; + break; + case PV_970: + case PV_970FX: + case PV_970MP: + ppmu = &ppc970_pmu; + break; + case PV_POWER5: + ppmu = &power5_pmu; + break; + case PV_POWER5p: + ppmu = &power5p_pmu; + break; + case 0x3e: + ppmu = &power6_pmu; + break; + case 0x3f: + ppmu = &power7_pmu; + break; + } + + /* + * Use FCHV to ignore kernel events if MSR.HV is set. + */ + if (mfmsr() & MSR_HV) + freeze_counters_kernel = MMCR0_FCHV; + + return 0; +} + +arch_initcall(init_perf_counters); diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c new file mode 100644 index 0000000000000000000000000000000000000000..07bd308a5fa748247f3ea0472d5d973eb6576523 --- /dev/null +++ b/arch/powerpc/kernel/power4-pmu.c @@ -0,0 +1,598 @@ +/* + * Performance counter support for POWER4 (GP) and POWER4+ (GQ) processors. + * + * Copyright 2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include + +/* + * Bits in event code for POWER4 + */ +#define PM_PMC_SH 12 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0xf +#define PM_UNIT_SH 8 /* TTMMUX number and setting - unit select */ +#define PM_UNIT_MSK 0xf +#define PM_LOWER_SH 6 +#define PM_LOWER_MSK 1 +#define PM_LOWER_MSKS 0x40 +#define PM_BYTE_SH 4 /* Byte number of event bus to use */ +#define PM_BYTE_MSK 3 +#define PM_PMCSEL_MSK 7 + +/* + * Unit code values + */ +#define PM_FPU 1 +#define PM_ISU1 2 +#define PM_IFU 3 +#define PM_IDU0 4 +#define PM_ISU1_ALT 6 +#define PM_ISU2 7 +#define PM_IFU_ALT 8 +#define PM_LSU0 9 +#define PM_LSU1 0xc +#define PM_GPS 0xf + +/* + * Bits in MMCR0 for POWER4 + */ +#define MMCR0_PMC1SEL_SH 8 +#define MMCR0_PMC2SEL_SH 1 +#define MMCR_PMCSEL_MSK 0x1f + +/* + * Bits in MMCR1 for POWER4 + */ +#define MMCR1_TTM0SEL_SH 62 +#define MMCR1_TTC0SEL_SH 61 +#define MMCR1_TTM1SEL_SH 59 +#define MMCR1_TTC1SEL_SH 58 +#define MMCR1_TTM2SEL_SH 56 +#define MMCR1_TTC2SEL_SH 55 +#define MMCR1_TTM3SEL_SH 53 +#define MMCR1_TTC3SEL_SH 52 +#define MMCR1_TTMSEL_MSK 3 +#define MMCR1_TD_CP_DBG0SEL_SH 50 +#define MMCR1_TD_CP_DBG1SEL_SH 48 +#define MMCR1_TD_CP_DBG2SEL_SH 46 +#define MMCR1_TD_CP_DBG3SEL_SH 44 +#define MMCR1_DEBUG0SEL_SH 43 +#define MMCR1_DEBUG1SEL_SH 42 +#define MMCR1_DEBUG2SEL_SH 41 +#define MMCR1_DEBUG3SEL_SH 40 +#define MMCR1_PMC1_ADDER_SEL_SH 39 +#define MMCR1_PMC2_ADDER_SEL_SH 38 +#define MMCR1_PMC6_ADDER_SEL_SH 37 +#define MMCR1_PMC5_ADDER_SEL_SH 36 +#define MMCR1_PMC8_ADDER_SEL_SH 35 +#define MMCR1_PMC7_ADDER_SEL_SH 34 +#define MMCR1_PMC3_ADDER_SEL_SH 33 +#define MMCR1_PMC4_ADDER_SEL_SH 32 +#define MMCR1_PMC3SEL_SH 27 +#define MMCR1_PMC4SEL_SH 22 +#define MMCR1_PMC5SEL_SH 17 +#define MMCR1_PMC6SEL_SH 12 +#define MMCR1_PMC7SEL_SH 7 +#define MMCR1_PMC8SEL_SH 2 /* note bit 0 is in MMCRA for GP */ + +static short mmcr1_adder_bits[8] = { + MMCR1_PMC1_ADDER_SEL_SH, + MMCR1_PMC2_ADDER_SEL_SH, + MMCR1_PMC3_ADDER_SEL_SH, + MMCR1_PMC4_ADDER_SEL_SH, + MMCR1_PMC5_ADDER_SEL_SH, + MMCR1_PMC6_ADDER_SEL_SH, + MMCR1_PMC7_ADDER_SEL_SH, + MMCR1_PMC8_ADDER_SEL_SH +}; + +/* + * Bits in MMCRA + */ +#define MMCRA_PMC8SEL0_SH 17 /* PMC8SEL bit 0 for GP */ + +/* + * Layout of constraint bits: + * 6666555555555544444444443333333333222222222211111111110000000000 + * 3210987654321098765432109876543210987654321098765432109876543210 + * |[ >[ >[ >|||[ >[ >< >< >< >< ><><><><><><><><> + * | UC1 UC2 UC3 ||| PS1 PS2 B0 B1 B2 B3 P1P2P3P4P5P6P7P8 + * \SMPL ||\TTC3SEL + * |\TTC_IFU_SEL + * \TTM2SEL0 + * + * SMPL - SAMPLE_ENABLE constraint + * 56: SAMPLE_ENABLE value 0x0100_0000_0000_0000 + * + * UC1 - unit constraint 1: can't have all three of FPU/ISU1/IDU0|ISU2 + * 55: UC1 error 0x0080_0000_0000_0000 + * 54: FPU events needed 0x0040_0000_0000_0000 + * 53: ISU1 events needed 0x0020_0000_0000_0000 + * 52: IDU0|ISU2 events needed 0x0010_0000_0000_0000 + * + * UC2 - unit constraint 2: can't have all three of FPU/IFU/LSU0 + * 51: UC2 error 0x0008_0000_0000_0000 + * 50: FPU events needed 0x0004_0000_0000_0000 + * 49: IFU events needed 0x0002_0000_0000_0000 + * 48: LSU0 events needed 0x0001_0000_0000_0000 + * + * UC3 - unit constraint 3: can't have all four of LSU0/IFU/IDU0|ISU2/ISU1 + * 47: UC3 error 0x8000_0000_0000 + * 46: LSU0 events needed 0x4000_0000_0000 + * 45: IFU events needed 0x2000_0000_0000 + * 44: IDU0|ISU2 events needed 0x1000_0000_0000 + * 43: ISU1 events needed 0x0800_0000_0000 + * + * TTM2SEL0 + * 42: 0 = IDU0 events needed + * 1 = ISU2 events needed 0x0400_0000_0000 + * + * TTC_IFU_SEL + * 41: 0 = IFU.U events needed + * 1 = IFU.L events needed 0x0200_0000_0000 + * + * TTC3SEL + * 40: 0 = LSU1.U events needed + * 1 = LSU1.L events needed 0x0100_0000_0000 + * + * PS1 + * 39: PS1 error 0x0080_0000_0000 + * 36-38: count of events needing PMC1/2/5/6 0x0070_0000_0000 + * + * PS2 + * 35: PS2 error 0x0008_0000_0000 + * 32-34: count of events needing PMC3/4/7/8 0x0007_0000_0000 + * + * B0 + * 28-31: Byte 0 event source 0xf000_0000 + * 1 = FPU + * 2 = ISU1 + * 3 = IFU + * 4 = IDU0 + * 7 = ISU2 + * 9 = LSU0 + * c = LSU1 + * f = GPS + * + * B1, B2, B3 + * 24-27, 20-23, 16-19: Byte 1, 2, 3 event sources + * + * P8 + * 15: P8 error 0x8000 + * 14-15: Count of events needing PMC8 + * + * P1..P7 + * 0-13: Count of events needing PMC1..PMC7 + * + * Note: this doesn't allow events using IFU.U to be combined with events + * using IFU.L, though that is feasible (using TTM0 and TTM2). However + * there are no listed events for IFU.L (they are debug events not + * verified for performance monitoring) so this shouldn't cause a + * problem. + */ + +static struct unitinfo { + u64 value, mask; + int unit; + int lowerbit; +} p4_unitinfo[16] = { + [PM_FPU] = { 0x44000000000000ull, 0x88000000000000ull, PM_FPU, 0 }, + [PM_ISU1] = { 0x20080000000000ull, 0x88000000000000ull, PM_ISU1, 0 }, + [PM_ISU1_ALT] = + { 0x20080000000000ull, 0x88000000000000ull, PM_ISU1, 0 }, + [PM_IFU] = { 0x02200000000000ull, 0x08820000000000ull, PM_IFU, 41 }, + [PM_IFU_ALT] = + { 0x02200000000000ull, 0x08820000000000ull, PM_IFU, 41 }, + [PM_IDU0] = { 0x10100000000000ull, 0x80840000000000ull, PM_IDU0, 1 }, + [PM_ISU2] = { 0x10140000000000ull, 0x80840000000000ull, PM_ISU2, 0 }, + [PM_LSU0] = { 0x01400000000000ull, 0x08800000000000ull, PM_LSU0, 0 }, + [PM_LSU1] = { 0x00000000000000ull, 0x00010000000000ull, PM_LSU1, 40 }, + [PM_GPS] = { 0x00000000000000ull, 0x00000000000000ull, PM_GPS, 0 } +}; + +static unsigned char direct_marked_event[8] = { + (1<<2) | (1<<3), /* PMC1: PM_MRK_GRP_DISP, PM_MRK_ST_CMPL */ + (1<<3) | (1<<5), /* PMC2: PM_THRESH_TIMEO, PM_MRK_BRU_FIN */ + (1<<3), /* PMC3: PM_MRK_ST_CMPL_INT */ + (1<<4) | (1<<5), /* PMC4: PM_MRK_GRP_CMPL, PM_MRK_CRU_FIN */ + (1<<4) | (1<<5), /* PMC5: PM_MRK_GRP_TIMEO */ + (1<<3) | (1<<4) | (1<<5), + /* PMC6: PM_MRK_ST_GPS, PM_MRK_FXU_FIN, PM_MRK_GRP_ISSUED */ + (1<<4) | (1<<5), /* PMC7: PM_MRK_FPU_FIN, PM_MRK_INST_FIN */ + (1<<4), /* PMC8: PM_MRK_LSU_FIN */ +}; + +/* + * Returns 1 if event counts things relating to marked instructions + * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not. + */ +static int p4_marked_instr_event(u64 event) +{ + int pmc, psel, unit, byte, bit; + unsigned int mask; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + psel = event & PM_PMCSEL_MSK; + if (pmc) { + if (direct_marked_event[pmc - 1] & (1 << psel)) + return 1; + if (psel == 0) /* add events */ + bit = (pmc <= 4)? pmc - 1: 8 - pmc; + else if (psel == 6) /* decode events */ + bit = 4; + else + return 0; + } else + bit = psel; + + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + mask = 0; + switch (unit) { + case PM_LSU1: + if (event & PM_LOWER_MSKS) + mask = 1 << 28; /* byte 7 bit 4 */ + else + mask = 6 << 24; /* byte 3 bits 1 and 2 */ + break; + case PM_LSU0: + /* byte 3, bit 3; byte 2 bits 0,2,3,4,5; byte 1 */ + mask = 0x083dff00; + } + return (mask >> (byte * 8 + bit)) & 1; +} + +static int p4_get_constraint(u64 event, u64 *maskp, u64 *valp) +{ + int pmc, byte, unit, lower, sh; + u64 mask = 0, value = 0; + int grp = -1; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 8) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + grp = ((pmc - 1) >> 1) & 1; + } + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + if (unit) { + lower = (event >> PM_LOWER_SH) & PM_LOWER_MSK; + + /* + * Bus events on bytes 0 and 2 can be counted + * on PMC1/2/5/6; bytes 1 and 3 on PMC3/4/7/8. + */ + if (!pmc) + grp = byte & 1; + + if (!p4_unitinfo[unit].unit) + return -1; + mask |= p4_unitinfo[unit].mask; + value |= p4_unitinfo[unit].value; + sh = p4_unitinfo[unit].lowerbit; + if (sh > 1) + value |= (u64)lower << sh; + else if (lower != sh) + return -1; + unit = p4_unitinfo[unit].unit; + + /* Set byte lane select field */ + mask |= 0xfULL << (28 - 4 * byte); + value |= (u64)unit << (28 - 4 * byte); + } + if (grp == 0) { + /* increment PMC1/2/5/6 field */ + mask |= 0x8000000000ull; + value |= 0x1000000000ull; + } else { + /* increment PMC3/4/7/8 field */ + mask |= 0x800000000ull; + value |= 0x100000000ull; + } + + /* Marked instruction events need sample_enable set */ + if (p4_marked_instr_event(event)) { + mask |= 1ull << 56; + value |= 1ull << 56; + } + + /* PMCSEL=6 decode events on byte 2 need sample_enable clear */ + if (pmc && (event & PM_PMCSEL_MSK) == 6 && byte == 2) + mask |= 1ull << 56; + + *maskp = mask; + *valp = value; + return 0; +} + +static unsigned int ppc_inst_cmpl[] = { + 0x1001, 0x4001, 0x6001, 0x7001, 0x8001 +}; + +static int p4_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int i, j, na; + + alt[0] = event; + na = 1; + + /* 2 possibilities for PM_GRP_DISP_REJECT */ + if (event == 0x8003 || event == 0x0224) { + alt[1] = event ^ (0x8003 ^ 0x0224); + return 2; + } + + /* 2 possibilities for PM_ST_MISS_L1 */ + if (event == 0x0c13 || event == 0x0c23) { + alt[1] = event ^ (0x0c13 ^ 0x0c23); + return 2; + } + + /* several possibilities for PM_INST_CMPL */ + for (i = 0; i < ARRAY_SIZE(ppc_inst_cmpl); ++i) { + if (event == ppc_inst_cmpl[i]) { + for (j = 0; j < ARRAY_SIZE(ppc_inst_cmpl); ++j) + if (j != i) + alt[na++] = ppc_inst_cmpl[j]; + break; + } + } + + return na; +} + +static int p4_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr0 = 0, mmcr1 = 0, mmcra = 0; + unsigned int pmc, unit, byte, psel, lower; + unsigned int ttm, grp; + unsigned int pmc_inuse = 0; + unsigned int pmc_grp_use[2]; + unsigned char busbyte[4]; + unsigned char unituse[16]; + unsigned int unitlower = 0; + int i; + + if (n_ev > 8) + return -1; + + /* First pass to count resource use */ + pmc_grp_use[0] = pmc_grp_use[1] = 0; + memset(busbyte, 0, sizeof(busbyte)); + memset(unituse, 0, sizeof(unituse)); + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + pmc_inuse |= 1 << (pmc - 1); + /* count 1/2/5/6 vs 3/4/7/8 use */ + ++pmc_grp_use[((pmc - 1) >> 1) & 1]; + } + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + lower = (event[i] >> PM_LOWER_SH) & PM_LOWER_MSK; + if (unit) { + if (!pmc) + ++pmc_grp_use[byte & 1]; + if (unit == 6 || unit == 8) + /* map alt ISU1/IFU codes: 6->2, 8->3 */ + unit = (unit >> 1) - 1; + if (busbyte[byte] && busbyte[byte] != unit) + return -1; + busbyte[byte] = unit; + lower <<= unit; + if (unituse[unit] && lower != (unitlower & lower)) + return -1; + unituse[unit] = 1; + unitlower |= lower; + } + } + if (pmc_grp_use[0] > 4 || pmc_grp_use[1] > 4) + return -1; + + /* + * Assign resources and set multiplexer selects. + * + * Units 1,2,3 are on TTM0, 4,6,7 on TTM1, 8,10 on TTM2. + * Each TTMx can only select one unit, but since + * units 2 and 6 are both ISU1, and 3 and 8 are both IFU, + * we have some choices. + */ + if (unituse[2] & (unituse[1] | (unituse[3] & unituse[9]))) { + unituse[6] = 1; /* Move 2 to 6 */ + unituse[2] = 0; + } + if (unituse[3] & (unituse[1] | unituse[2])) { + unituse[8] = 1; /* Move 3 to 8 */ + unituse[3] = 0; + unitlower = (unitlower & ~8) | ((unitlower & 8) << 5); + } + /* Check only one unit per TTMx */ + if (unituse[1] + unituse[2] + unituse[3] > 1 || + unituse[4] + unituse[6] + unituse[7] > 1 || + unituse[8] + unituse[9] > 1 || + (unituse[5] | unituse[10] | unituse[11] | + unituse[13] | unituse[14])) + return -1; + + /* Set TTMxSEL fields. Note, units 1-3 => TTM0SEL codes 0-2 */ + mmcr1 |= (u64)(unituse[3] * 2 + unituse[2]) << MMCR1_TTM0SEL_SH; + mmcr1 |= (u64)(unituse[7] * 3 + unituse[6] * 2) << MMCR1_TTM1SEL_SH; + mmcr1 |= (u64)unituse[9] << MMCR1_TTM2SEL_SH; + + /* Set TTCxSEL fields. */ + if (unitlower & 0xe) + mmcr1 |= 1ull << MMCR1_TTC0SEL_SH; + if (unitlower & 0xf0) + mmcr1 |= 1ull << MMCR1_TTC1SEL_SH; + if (unitlower & 0xf00) + mmcr1 |= 1ull << MMCR1_TTC2SEL_SH; + if (unitlower & 0x7000) + mmcr1 |= 1ull << MMCR1_TTC3SEL_SH; + + /* Set byte lane select fields. */ + for (byte = 0; byte < 4; ++byte) { + unit = busbyte[byte]; + if (!unit) + continue; + if (unit == 0xf) { + /* special case for GPS */ + mmcr1 |= 1ull << (MMCR1_DEBUG0SEL_SH - byte); + } else { + if (!unituse[unit]) + ttm = unit - 1; /* 2->1, 3->2 */ + else + ttm = unit >> 2; + mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2*byte); + } + } + + /* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + psel = event[i] & PM_PMCSEL_MSK; + if (!pmc) { + /* Bus event or 00xxx direct event (off or cycles) */ + if (unit) + psel |= 0x10 | ((byte & 2) << 2); + for (pmc = 0; pmc < 8; ++pmc) { + if (pmc_inuse & (1 << pmc)) + continue; + grp = (pmc >> 1) & 1; + if (unit) { + if (grp == (byte & 1)) + break; + } else if (pmc_grp_use[grp] < 4) { + ++pmc_grp_use[grp]; + break; + } + } + pmc_inuse |= 1 << pmc; + } else { + /* Direct event */ + --pmc; + if (psel == 0 && (byte & 2)) + /* add events on higher-numbered bus */ + mmcr1 |= 1ull << mmcr1_adder_bits[pmc]; + else if (psel == 6 && byte == 3) + /* seem to need to set sample_enable here */ + mmcra |= MMCRA_SAMPLE_ENABLE; + psel |= 8; + } + if (pmc <= 1) + mmcr0 |= psel << (MMCR0_PMC1SEL_SH - 7 * pmc); + else + mmcr1 |= psel << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2)); + if (pmc == 7) /* PMC8 */ + mmcra |= (psel & 1) << MMCRA_PMC8SEL0_SH; + hwc[i] = pmc; + if (p4_marked_instr_event(event[i])) + mmcra |= MMCRA_SAMPLE_ENABLE; + } + + if (pmc_inuse & 1) + mmcr0 |= MMCR0_PMC1CE; + if (pmc_inuse & 0xfe) + mmcr0 |= MMCR0_PMCjCE; + + mmcra |= 0x2000; /* mark only one IOP per PPC instruction */ + + /* Return MMCRx values */ + mmcr[0] = mmcr0; + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + return 0; +} + +static void p4_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + /* + * Setting the PMCxSEL field to 0 disables PMC x. + * (Note that pmc is 0-based here, not 1-based.) + */ + if (pmc <= 1) { + mmcr[0] &= ~(0x1fUL << (MMCR0_PMC1SEL_SH - 7 * pmc)); + } else { + mmcr[1] &= ~(0x1fUL << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2))); + if (pmc == 7) + mmcr[2] &= ~(1UL << MMCRA_PMC8SEL0_SH); + } +} + +static int p4_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 7, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x1001, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x8c10, /* PM_LD_REF_L1 */ + [PERF_COUNT_HW_CACHE_MISSES] = 0x3c10, /* PM_LD_MISS_L1 */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x330, /* PM_BR_ISSUED */ + [PERF_COUNT_HW_BRANCH_MISSES] = 0x331, /* PM_BR_MPRED_CR */ +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int power4_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x8c10, 0x3c10 }, + [C(OP_WRITE)] = { 0x7c10, 0xc13 }, + [C(OP_PREFETCH)] = { 0xc35, 0 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { 0, 0 }, + [C(OP_PREFETCH)] = { 0xc34, 0 }, + }, + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x904 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x900 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x330, 0x331 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +struct power_pmu power4_pmu = { + .n_counter = 8, + .max_alternatives = 5, + .add_fields = 0x0000001100005555ull, + .test_adder = 0x0011083300000000ull, + .compute_mmcr = p4_compute_mmcr, + .get_constraint = p4_get_constraint, + .get_alternatives = p4_get_alternatives, + .disable_pmc = p4_disable_pmc, + .n_generic = ARRAY_SIZE(p4_generic_events), + .generic_events = p4_generic_events, + .cache_events = &power4_cache_events, +}; diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c new file mode 100644 index 0000000000000000000000000000000000000000..41e5d2d958d4c89a13df1840731dfd0b82eab49d --- /dev/null +++ b/arch/powerpc/kernel/power5+-pmu.c @@ -0,0 +1,671 @@ +/* + * Performance counter support for POWER5+/++ (not POWER5) processors. + * + * Copyright 2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include + +/* + * Bits in event code for POWER5+ (POWER5 GS) and POWER5++ (POWER5 GS DD3) + */ +#define PM_PMC_SH 20 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0xf +#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH) +#define PM_UNIT_SH 16 /* TTMMUX number and setting - unit select */ +#define PM_UNIT_MSK 0xf +#define PM_BYTE_SH 12 /* Byte number of event bus to use */ +#define PM_BYTE_MSK 7 +#define PM_GRS_SH 8 /* Storage subsystem mux select */ +#define PM_GRS_MSK 7 +#define PM_BUSEVENT_MSK 0x80 /* Set if event uses event bus */ +#define PM_PMCSEL_MSK 0x7f + +/* Values in PM_UNIT field */ +#define PM_FPU 0 +#define PM_ISU0 1 +#define PM_IFU 2 +#define PM_ISU1 3 +#define PM_IDU 4 +#define PM_ISU0_ALT 6 +#define PM_GRS 7 +#define PM_LSU0 8 +#define PM_LSU1 0xc +#define PM_LASTUNIT 0xc + +/* + * Bits in MMCR1 for POWER5+ + */ +#define MMCR1_TTM0SEL_SH 62 +#define MMCR1_TTM1SEL_SH 60 +#define MMCR1_TTM2SEL_SH 58 +#define MMCR1_TTM3SEL_SH 56 +#define MMCR1_TTMSEL_MSK 3 +#define MMCR1_TD_CP_DBG0SEL_SH 54 +#define MMCR1_TD_CP_DBG1SEL_SH 52 +#define MMCR1_TD_CP_DBG2SEL_SH 50 +#define MMCR1_TD_CP_DBG3SEL_SH 48 +#define MMCR1_GRS_L2SEL_SH 46 +#define MMCR1_GRS_L2SEL_MSK 3 +#define MMCR1_GRS_L3SEL_SH 44 +#define MMCR1_GRS_L3SEL_MSK 3 +#define MMCR1_GRS_MCSEL_SH 41 +#define MMCR1_GRS_MCSEL_MSK 7 +#define MMCR1_GRS_FABSEL_SH 39 +#define MMCR1_GRS_FABSEL_MSK 3 +#define MMCR1_PMC1_ADDER_SEL_SH 35 +#define MMCR1_PMC2_ADDER_SEL_SH 34 +#define MMCR1_PMC3_ADDER_SEL_SH 33 +#define MMCR1_PMC4_ADDER_SEL_SH 32 +#define MMCR1_PMC1SEL_SH 25 +#define MMCR1_PMC2SEL_SH 17 +#define MMCR1_PMC3SEL_SH 9 +#define MMCR1_PMC4SEL_SH 1 +#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8) +#define MMCR1_PMCSEL_MSK 0x7f + +/* + * Bits in MMCRA + */ + +/* + * Layout of constraint bits: + * 6666555555555544444444443333333333222222222211111111110000000000 + * 3210987654321098765432109876543210987654321098765432109876543210 + * [ ><><>< ><> <><>[ > < >< >< >< ><><><><><><> + * NC G0G1G2 G3 T0T1 UC B0 B1 B2 B3 P6P5P4P3P2P1 + * + * NC - number of counters + * 51: NC error 0x0008_0000_0000_0000 + * 48-50: number of events needing PMC1-4 0x0007_0000_0000_0000 + * + * G0..G3 - GRS mux constraints + * 46-47: GRS_L2SEL value + * 44-45: GRS_L3SEL value + * 41-44: GRS_MCSEL value + * 39-40: GRS_FABSEL value + * Note that these match up with their bit positions in MMCR1 + * + * T0 - TTM0 constraint + * 36-37: TTM0SEL value (0=FPU, 2=IFU, 3=ISU1) 0x30_0000_0000 + * + * T1 - TTM1 constraint + * 34-35: TTM1SEL value (0=IDU, 3=GRS) 0x0c_0000_0000 + * + * UC - unit constraint: can't have all three of FPU|IFU|ISU1, ISU0, IDU|GRS + * 33: UC3 error 0x02_0000_0000 + * 32: FPU|IFU|ISU1 events needed 0x01_0000_0000 + * 31: ISU0 events needed 0x01_8000_0000 + * 30: IDU|GRS events needed 0x00_4000_0000 + * + * B0 + * 24-27: Byte 0 event source 0x0f00_0000 + * Encoding as for the event code + * + * B1, B2, B3 + * 20-23, 16-19, 12-15: Byte 1, 2, 3 event sources + * + * P6 + * 11: P6 error 0x800 + * 10-11: Count of events needing PMC6 + * + * P1..P5 + * 0-9: Count of events needing PMC1..PMC5 + */ + +static const int grsel_shift[8] = { + MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, + MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, + MMCR1_GRS_MCSEL_SH, MMCR1_GRS_FABSEL_SH +}; + +/* Masks and values for using events from the various units */ +static u64 unit_cons[PM_LASTUNIT+1][2] = { + [PM_FPU] = { 0x3200000000ull, 0x0100000000ull }, + [PM_ISU0] = { 0x0200000000ull, 0x0080000000ull }, + [PM_ISU1] = { 0x3200000000ull, 0x3100000000ull }, + [PM_IFU] = { 0x3200000000ull, 0x2100000000ull }, + [PM_IDU] = { 0x0e00000000ull, 0x0040000000ull }, + [PM_GRS] = { 0x0e00000000ull, 0x0c40000000ull }, +}; + +static int power5p_get_constraint(u64 event, u64 *maskp, u64 *valp) +{ + int pmc, byte, unit, sh; + int bit, fmask; + u64 mask = 0, value = 0; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 6) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + if (pmc >= 5 && !(event == 0x500009 || event == 0x600005)) + return -1; + } + if (event & PM_BUSEVENT_MSK) { + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + if (unit > PM_LASTUNIT) + return -1; + if (unit == PM_ISU0_ALT) + unit = PM_ISU0; + mask |= unit_cons[unit][0]; + value |= unit_cons[unit][1]; + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + if (byte >= 4) { + if (unit != PM_LSU1) + return -1; + /* Map LSU1 low word (bytes 4-7) to unit LSU1+1 */ + ++unit; + byte &= 3; + } + if (unit == PM_GRS) { + bit = event & 7; + fmask = (bit == 6)? 7: 3; + sh = grsel_shift[bit]; + mask |= (u64)fmask << sh; + value |= (u64)((event >> PM_GRS_SH) & fmask) << sh; + } + /* Set byte lane select field */ + mask |= 0xfULL << (24 - 4 * byte); + value |= (u64)unit << (24 - 4 * byte); + } + if (pmc < 5) { + /* need a counter from PMC1-4 set */ + mask |= 0x8000000000000ull; + value |= 0x1000000000000ull; + } + *maskp = mask; + *valp = value; + return 0; +} + +static int power5p_limited_pmc_event(u64 event) +{ + int pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + + return pmc == 5 || pmc == 6; +} + +#define MAX_ALT 3 /* at most 3 alternatives for any event */ + +static const unsigned int event_alternatives[][MAX_ALT] = { + { 0x100c0, 0x40001f }, /* PM_GCT_FULL_CYC */ + { 0x120e4, 0x400002 }, /* PM_GRP_DISP_REJECT */ + { 0x230e2, 0x323087 }, /* PM_BR_PRED_CR */ + { 0x230e3, 0x223087, 0x3230a0 }, /* PM_BR_PRED_TA */ + { 0x410c7, 0x441084 }, /* PM_THRD_L2MISS_BOTH_CYC */ + { 0x800c4, 0xc20e0 }, /* PM_DTLB_MISS */ + { 0xc50c6, 0xc60e0 }, /* PM_MRK_DTLB_MISS */ + { 0x100005, 0x600005 }, /* PM_RUN_CYC */ + { 0x100009, 0x200009 }, /* PM_INST_CMPL */ + { 0x200015, 0x300015 }, /* PM_LSU_LMQ_SRQ_EMPTY_CYC */ + { 0x300009, 0x400009 }, /* PM_INST_DISP */ +}; + +/* + * Scan the alternatives table for a match and return the + * index into the alternatives table if found, else -1. + */ +static int find_alternative(unsigned int event) +{ + int i, j; + + for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) { + if (event < event_alternatives[i][0]) + break; + for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j) + if (event == event_alternatives[i][j]) + return i; + } + return -1; +} + +static const unsigned char bytedecode_alternatives[4][4] = { + /* PMC 1 */ { 0x21, 0x23, 0x25, 0x27 }, + /* PMC 2 */ { 0x07, 0x17, 0x0e, 0x1e }, + /* PMC 3 */ { 0x20, 0x22, 0x24, 0x26 }, + /* PMC 4 */ { 0x07, 0x17, 0x0e, 0x1e } +}; + +/* + * Some direct events for decodes of event bus byte 3 have alternative + * PMCSEL values on other counters. This returns the alternative + * event code for those that do, or -1 otherwise. This also handles + * alternative PCMSEL values for add events. + */ +static s64 find_alternative_bdecode(u64 event) +{ + int pmc, altpmc, pp, j; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc == 0 || pmc > 4) + return -1; + altpmc = 5 - pmc; /* 1 <-> 4, 2 <-> 3 */ + pp = event & PM_PMCSEL_MSK; + for (j = 0; j < 4; ++j) { + if (bytedecode_alternatives[pmc - 1][j] == pp) { + return (event & ~(PM_PMC_MSKS | PM_PMCSEL_MSK)) | + (altpmc << PM_PMC_SH) | + bytedecode_alternatives[altpmc - 1][j]; + } + } + + /* new decode alternatives for power5+ */ + if (pmc == 1 && (pp == 0x0d || pp == 0x0e)) + return event + (2 << PM_PMC_SH) + (0x2e - 0x0d); + if (pmc == 3 && (pp == 0x2e || pp == 0x2f)) + return event - (2 << PM_PMC_SH) - (0x2e - 0x0d); + + /* alternative add event encodings */ + if (pp == 0x10 || pp == 0x28) + return ((event ^ (0x10 ^ 0x28)) & ~PM_PMC_MSKS) | + (altpmc << PM_PMC_SH); + + return -1; +} + +static int power5p_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int i, j, nalt = 1; + int nlim; + s64 ae; + + alt[0] = event; + nalt = 1; + nlim = power5p_limited_pmc_event(event); + i = find_alternative(event); + if (i >= 0) { + for (j = 0; j < MAX_ALT; ++j) { + ae = event_alternatives[i][j]; + if (ae && ae != event) + alt[nalt++] = ae; + nlim += power5p_limited_pmc_event(ae); + } + } else { + ae = find_alternative_bdecode(event); + if (ae > 0) + alt[nalt++] = ae; + } + + if (flags & PPMU_ONLY_COUNT_RUN) { + /* + * We're only counting in RUN state, + * so PM_CYC is equivalent to PM_RUN_CYC + * and PM_INST_CMPL === PM_RUN_INST_CMPL. + * This doesn't include alternatives that don't provide + * any extra flexibility in assigning PMCs (e.g. + * 0x100005 for PM_RUN_CYC vs. 0xf for PM_CYC). + * Note that even with these additional alternatives + * we never end up with more than 3 alternatives for any event. + */ + j = nalt; + for (i = 0; i < nalt; ++i) { + switch (alt[i]) { + case 0xf: /* PM_CYC */ + alt[j++] = 0x600005; /* PM_RUN_CYC */ + ++nlim; + break; + case 0x600005: /* PM_RUN_CYC */ + alt[j++] = 0xf; + break; + case 0x100009: /* PM_INST_CMPL */ + alt[j++] = 0x500009; /* PM_RUN_INST_CMPL */ + ++nlim; + break; + case 0x500009: /* PM_RUN_INST_CMPL */ + alt[j++] = 0x100009; /* PM_INST_CMPL */ + alt[j++] = 0x200009; + break; + } + } + nalt = j; + } + + if (!(flags & PPMU_LIMITED_PMC_OK) && nlim) { + /* remove the limited PMC events */ + j = 0; + for (i = 0; i < nalt; ++i) { + if (!power5p_limited_pmc_event(alt[i])) { + alt[j] = alt[i]; + ++j; + } + } + nalt = j; + } else if ((flags & PPMU_LIMITED_PMC_REQD) && nlim < nalt) { + /* remove all but the limited PMC events */ + j = 0; + for (i = 0; i < nalt; ++i) { + if (power5p_limited_pmc_event(alt[i])) { + alt[j] = alt[i]; + ++j; + } + } + nalt = j; + } + + return nalt; +} + +/* + * Map of which direct events on which PMCs are marked instruction events. + * Indexed by PMCSEL value, bit i (LE) set if PMC i is a marked event. + * Bit 0 is set if it is marked for all PMCs. + * The 0x80 bit indicates a byte decode PMCSEL value. + */ +static unsigned char direct_event_is_marked[0x28] = { + 0, /* 00 */ + 0x1f, /* 01 PM_IOPS_CMPL */ + 0x2, /* 02 PM_MRK_GRP_DISP */ + 0xe, /* 03 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */ + 0, /* 04 */ + 0x1c, /* 05 PM_MRK_BRU_FIN, PM_MRK_INST_FIN, PM_MRK_CRU_FIN */ + 0x80, /* 06 */ + 0x80, /* 07 */ + 0, 0, 0,/* 08 - 0a */ + 0x18, /* 0b PM_THRESH_TIMEO, PM_MRK_GRP_TIMEO */ + 0, /* 0c */ + 0x80, /* 0d */ + 0x80, /* 0e */ + 0, /* 0f */ + 0, /* 10 */ + 0x14, /* 11 PM_MRK_GRP_BR_REDIR, PM_MRK_GRP_IC_MISS */ + 0, /* 12 */ + 0x10, /* 13 PM_MRK_GRP_CMPL */ + 0x1f, /* 14 PM_GRP_MRK, PM_MRK_{FXU,FPU,LSU}_FIN */ + 0x2, /* 15 PM_MRK_GRP_ISSUED */ + 0x80, /* 16 */ + 0x80, /* 17 */ + 0, 0, 0, 0, 0, + 0x80, /* 1d */ + 0x80, /* 1e */ + 0, /* 1f */ + 0x80, /* 20 */ + 0x80, /* 21 */ + 0x80, /* 22 */ + 0x80, /* 23 */ + 0x80, /* 24 */ + 0x80, /* 25 */ + 0x80, /* 26 */ + 0x80, /* 27 */ +}; + +/* + * Returns 1 if event counts things relating to marked instructions + * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not. + */ +static int power5p_marked_instr_event(u64 event) +{ + int pmc, psel; + int bit, byte, unit; + u32 mask; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + psel = event & PM_PMCSEL_MSK; + if (pmc >= 5) + return 0; + + bit = -1; + if (psel < sizeof(direct_event_is_marked)) { + if (direct_event_is_marked[psel] & (1 << pmc)) + return 1; + if (direct_event_is_marked[psel] & 0x80) + bit = 4; + else if (psel == 0x08) + bit = pmc - 1; + else if (psel == 0x10) + bit = 4 - pmc; + else if (psel == 0x1b && (pmc == 1 || pmc == 3)) + bit = 4; + } else if ((psel & 0x48) == 0x40) { + bit = psel & 7; + } else if (psel == 0x28) { + bit = pmc - 1; + } else if (pmc == 3 && (psel == 0x2e || psel == 0x2f)) { + bit = 4; + } + + if (!(event & PM_BUSEVENT_MSK) || bit == -1) + return 0; + + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + if (unit == PM_LSU0) { + /* byte 1 bits 0-7, byte 2 bits 0,2-4,6 */ + mask = 0x5dff00; + } else if (unit == PM_LSU1 && byte >= 4) { + byte -= 4; + /* byte 5 bits 6-7, byte 6 bits 0,4, byte 7 bits 0-4,6 */ + mask = 0x5f11c000; + } else + return 0; + + return (mask >> (byte * 8 + bit)) & 1; +} + +static int power5p_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr1 = 0; + u64 mmcra = 0; + unsigned int pmc, unit, byte, psel; + unsigned int ttm; + int i, isbus, bit, grsel; + unsigned int pmc_inuse = 0; + unsigned char busbyte[4]; + unsigned char unituse[16]; + int ttmuse; + + if (n_ev > 6) + return -1; + + /* First pass to count resource use */ + memset(busbyte, 0, sizeof(busbyte)); + memset(unituse, 0, sizeof(unituse)); + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 6) + return -1; + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + pmc_inuse |= 1 << (pmc - 1); + } + if (event[i] & PM_BUSEVENT_MSK) { + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + if (unit > PM_LASTUNIT) + return -1; + if (unit == PM_ISU0_ALT) + unit = PM_ISU0; + if (byte >= 4) { + if (unit != PM_LSU1) + return -1; + ++unit; + byte &= 3; + } + if (busbyte[byte] && busbyte[byte] != unit) + return -1; + busbyte[byte] = unit; + unituse[unit] = 1; + } + } + + /* + * Assign resources and set multiplexer selects. + * + * PM_ISU0 can go either on TTM0 or TTM1, but that's the only + * choice we have to deal with. + */ + if (unituse[PM_ISU0] & + (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_ISU1])) { + unituse[PM_ISU0_ALT] = 1; /* move ISU to TTM1 */ + unituse[PM_ISU0] = 0; + } + /* Set TTM[01]SEL fields. */ + ttmuse = 0; + for (i = PM_FPU; i <= PM_ISU1; ++i) { + if (!unituse[i]) + continue; + if (ttmuse++) + return -1; + mmcr1 |= (u64)i << MMCR1_TTM0SEL_SH; + } + ttmuse = 0; + for (; i <= PM_GRS; ++i) { + if (!unituse[i]) + continue; + if (ttmuse++) + return -1; + mmcr1 |= (u64)(i & 3) << MMCR1_TTM1SEL_SH; + } + if (ttmuse > 1) + return -1; + + /* Set byte lane select fields, TTM[23]SEL and GRS_*SEL. */ + for (byte = 0; byte < 4; ++byte) { + unit = busbyte[byte]; + if (!unit) + continue; + if (unit == PM_ISU0 && unituse[PM_ISU0_ALT]) { + /* get ISU0 through TTM1 rather than TTM0 */ + unit = PM_ISU0_ALT; + } else if (unit == PM_LSU1 + 1) { + /* select lower word of LSU1 for this byte */ + mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte); + } + ttm = unit >> 2; + mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte); + } + + /* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + psel = event[i] & PM_PMCSEL_MSK; + isbus = event[i] & PM_BUSEVENT_MSK; + if (!pmc) { + /* Bus event or any-PMC direct event */ + for (pmc = 0; pmc < 4; ++pmc) { + if (!(pmc_inuse & (1 << pmc))) + break; + } + if (pmc >= 4) + return -1; + pmc_inuse |= 1 << pmc; + } else if (pmc <= 4) { + /* Direct event */ + --pmc; + if (isbus && (byte & 2) && + (psel == 8 || psel == 0x10 || psel == 0x28)) + /* add events on higher-numbered bus */ + mmcr1 |= 1ull << (MMCR1_PMC1_ADDER_SEL_SH - pmc); + } else { + /* Instructions or run cycles on PMC5/6 */ + --pmc; + } + if (isbus && unit == PM_GRS) { + bit = psel & 7; + grsel = (event[i] >> PM_GRS_SH) & PM_GRS_MSK; + mmcr1 |= (u64)grsel << grsel_shift[bit]; + } + if (power5p_marked_instr_event(event[i])) + mmcra |= MMCRA_SAMPLE_ENABLE; + if ((psel & 0x58) == 0x40 && (byte & 1) != ((pmc >> 1) & 1)) + /* select alternate byte lane */ + psel |= 0x10; + if (pmc <= 3) + mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc); + hwc[i] = pmc; + } + + /* Return MMCRx values */ + mmcr[0] = 0; + if (pmc_inuse & 1) + mmcr[0] = MMCR0_PMC1CE; + if (pmc_inuse & 0x3e) + mmcr[0] |= MMCR0_PMCjCE; + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + return 0; +} + +static void power5p_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + if (pmc <= 3) + mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc)); +} + +static int power5p_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 0xf, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x100009, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x1c10a8, /* LD_REF_L1 */ + [PERF_COUNT_HW_CACHE_MISSES] = 0x3c1088, /* LD_MISS_L1 */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x230e4, /* BR_ISSUED */ + [PERF_COUNT_HW_BRANCH_MISSES] = 0x230e5, /* BR_MPRED_CR */ +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x1c10a8, 0x3c1088 }, + [C(OP_WRITE)] = { 0x2c10a8, 0xc10c3 }, + [C(OP_PREFETCH)] = { 0xc70e7, -1 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { 0, 0 }, + [C(OP_PREFETCH)] = { 0xc50c3, 0 }, + }, + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0xc20e4, 0x800c4 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x800c0 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x230e4, 0x230e5 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +struct power_pmu power5p_pmu = { + .n_counter = 6, + .max_alternatives = MAX_ALT, + .add_fields = 0x7000000000055ull, + .test_adder = 0x3000040000000ull, + .compute_mmcr = power5p_compute_mmcr, + .get_constraint = power5p_get_constraint, + .get_alternatives = power5p_get_alternatives, + .disable_pmc = power5p_disable_pmc, + .limited_pmc_event = power5p_limited_pmc_event, + .flags = PPMU_LIMITED_PMC5_6, + .n_generic = ARRAY_SIZE(power5p_generic_events), + .generic_events = power5p_generic_events, + .cache_events = &power5p_cache_events, +}; diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c new file mode 100644 index 0000000000000000000000000000000000000000..05600b66221ae0e491c9b947bfdbe649983ab18f --- /dev/null +++ b/arch/powerpc/kernel/power5-pmu.c @@ -0,0 +1,611 @@ +/* + * Performance counter support for POWER5 (not POWER5++) processors. + * + * Copyright 2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include + +/* + * Bits in event code for POWER5 (not POWER5++) + */ +#define PM_PMC_SH 20 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0xf +#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH) +#define PM_UNIT_SH 16 /* TTMMUX number and setting - unit select */ +#define PM_UNIT_MSK 0xf +#define PM_BYTE_SH 12 /* Byte number of event bus to use */ +#define PM_BYTE_MSK 7 +#define PM_GRS_SH 8 /* Storage subsystem mux select */ +#define PM_GRS_MSK 7 +#define PM_BUSEVENT_MSK 0x80 /* Set if event uses event bus */ +#define PM_PMCSEL_MSK 0x7f + +/* Values in PM_UNIT field */ +#define PM_FPU 0 +#define PM_ISU0 1 +#define PM_IFU 2 +#define PM_ISU1 3 +#define PM_IDU 4 +#define PM_ISU0_ALT 6 +#define PM_GRS 7 +#define PM_LSU0 8 +#define PM_LSU1 0xc +#define PM_LASTUNIT 0xc + +/* + * Bits in MMCR1 for POWER5 + */ +#define MMCR1_TTM0SEL_SH 62 +#define MMCR1_TTM1SEL_SH 60 +#define MMCR1_TTM2SEL_SH 58 +#define MMCR1_TTM3SEL_SH 56 +#define MMCR1_TTMSEL_MSK 3 +#define MMCR1_TD_CP_DBG0SEL_SH 54 +#define MMCR1_TD_CP_DBG1SEL_SH 52 +#define MMCR1_TD_CP_DBG2SEL_SH 50 +#define MMCR1_TD_CP_DBG3SEL_SH 48 +#define MMCR1_GRS_L2SEL_SH 46 +#define MMCR1_GRS_L2SEL_MSK 3 +#define MMCR1_GRS_L3SEL_SH 44 +#define MMCR1_GRS_L3SEL_MSK 3 +#define MMCR1_GRS_MCSEL_SH 41 +#define MMCR1_GRS_MCSEL_MSK 7 +#define MMCR1_GRS_FABSEL_SH 39 +#define MMCR1_GRS_FABSEL_MSK 3 +#define MMCR1_PMC1_ADDER_SEL_SH 35 +#define MMCR1_PMC2_ADDER_SEL_SH 34 +#define MMCR1_PMC3_ADDER_SEL_SH 33 +#define MMCR1_PMC4_ADDER_SEL_SH 32 +#define MMCR1_PMC1SEL_SH 25 +#define MMCR1_PMC2SEL_SH 17 +#define MMCR1_PMC3SEL_SH 9 +#define MMCR1_PMC4SEL_SH 1 +#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8) +#define MMCR1_PMCSEL_MSK 0x7f + +/* + * Bits in MMCRA + */ + +/* + * Layout of constraint bits: + * 6666555555555544444444443333333333222222222211111111110000000000 + * 3210987654321098765432109876543210987654321098765432109876543210 + * <><>[ ><><>< ><> [ >[ >[ >< >< >< >< ><><><><><><> + * T0T1 NC G0G1G2 G3 UC PS1PS2 B0 B1 B2 B3 P6P5P4P3P2P1 + * + * T0 - TTM0 constraint + * 54-55: TTM0SEL value (0=FPU, 2=IFU, 3=ISU1) 0xc0_0000_0000_0000 + * + * T1 - TTM1 constraint + * 52-53: TTM1SEL value (0=IDU, 3=GRS) 0x30_0000_0000_0000 + * + * NC - number of counters + * 51: NC error 0x0008_0000_0000_0000 + * 48-50: number of events needing PMC1-4 0x0007_0000_0000_0000 + * + * G0..G3 - GRS mux constraints + * 46-47: GRS_L2SEL value + * 44-45: GRS_L3SEL value + * 41-44: GRS_MCSEL value + * 39-40: GRS_FABSEL value + * Note that these match up with their bit positions in MMCR1 + * + * UC - unit constraint: can't have all three of FPU|IFU|ISU1, ISU0, IDU|GRS + * 37: UC3 error 0x20_0000_0000 + * 36: FPU|IFU|ISU1 events needed 0x10_0000_0000 + * 35: ISU0 events needed 0x08_0000_0000 + * 34: IDU|GRS events needed 0x04_0000_0000 + * + * PS1 + * 33: PS1 error 0x2_0000_0000 + * 31-32: count of events needing PMC1/2 0x1_8000_0000 + * + * PS2 + * 30: PS2 error 0x4000_0000 + * 28-29: count of events needing PMC3/4 0x3000_0000 + * + * B0 + * 24-27: Byte 0 event source 0x0f00_0000 + * Encoding as for the event code + * + * B1, B2, B3 + * 20-23, 16-19, 12-15: Byte 1, 2, 3 event sources + * + * P1..P6 + * 0-11: Count of events needing PMC1..PMC6 + */ + +static const int grsel_shift[8] = { + MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, MMCR1_GRS_L2SEL_SH, + MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, MMCR1_GRS_L3SEL_SH, + MMCR1_GRS_MCSEL_SH, MMCR1_GRS_FABSEL_SH +}; + +/* Masks and values for using events from the various units */ +static u64 unit_cons[PM_LASTUNIT+1][2] = { + [PM_FPU] = { 0xc0002000000000ull, 0x00001000000000ull }, + [PM_ISU0] = { 0x00002000000000ull, 0x00000800000000ull }, + [PM_ISU1] = { 0xc0002000000000ull, 0xc0001000000000ull }, + [PM_IFU] = { 0xc0002000000000ull, 0x80001000000000ull }, + [PM_IDU] = { 0x30002000000000ull, 0x00000400000000ull }, + [PM_GRS] = { 0x30002000000000ull, 0x30000400000000ull }, +}; + +static int power5_get_constraint(u64 event, u64 *maskp, u64 *valp) +{ + int pmc, byte, unit, sh; + int bit, fmask; + u64 mask = 0, value = 0; + int grp = -1; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 6) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + if (pmc <= 4) + grp = (pmc - 1) >> 1; + else if (event != 0x500009 && event != 0x600005) + return -1; + } + if (event & PM_BUSEVENT_MSK) { + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + if (unit > PM_LASTUNIT) + return -1; + if (unit == PM_ISU0_ALT) + unit = PM_ISU0; + mask |= unit_cons[unit][0]; + value |= unit_cons[unit][1]; + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + if (byte >= 4) { + if (unit != PM_LSU1) + return -1; + /* Map LSU1 low word (bytes 4-7) to unit LSU1+1 */ + ++unit; + byte &= 3; + } + if (unit == PM_GRS) { + bit = event & 7; + fmask = (bit == 6)? 7: 3; + sh = grsel_shift[bit]; + mask |= (u64)fmask << sh; + value |= (u64)((event >> PM_GRS_SH) & fmask) << sh; + } + /* + * Bus events on bytes 0 and 2 can be counted + * on PMC1/2; bytes 1 and 3 on PMC3/4. + */ + if (!pmc) + grp = byte & 1; + /* Set byte lane select field */ + mask |= 0xfULL << (24 - 4 * byte); + value |= (u64)unit << (24 - 4 * byte); + } + if (grp == 0) { + /* increment PMC1/2 field */ + mask |= 0x200000000ull; + value |= 0x080000000ull; + } else if (grp == 1) { + /* increment PMC3/4 field */ + mask |= 0x40000000ull; + value |= 0x10000000ull; + } + if (pmc < 5) { + /* need a counter from PMC1-4 set */ + mask |= 0x8000000000000ull; + value |= 0x1000000000000ull; + } + *maskp = mask; + *valp = value; + return 0; +} + +#define MAX_ALT 3 /* at most 3 alternatives for any event */ + +static const unsigned int event_alternatives[][MAX_ALT] = { + { 0x120e4, 0x400002 }, /* PM_GRP_DISP_REJECT */ + { 0x410c7, 0x441084 }, /* PM_THRD_L2MISS_BOTH_CYC */ + { 0x100005, 0x600005 }, /* PM_RUN_CYC */ + { 0x100009, 0x200009, 0x500009 }, /* PM_INST_CMPL */ + { 0x300009, 0x400009 }, /* PM_INST_DISP */ +}; + +/* + * Scan the alternatives table for a match and return the + * index into the alternatives table if found, else -1. + */ +static int find_alternative(u64 event) +{ + int i, j; + + for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) { + if (event < event_alternatives[i][0]) + break; + for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j) + if (event == event_alternatives[i][j]) + return i; + } + return -1; +} + +static const unsigned char bytedecode_alternatives[4][4] = { + /* PMC 1 */ { 0x21, 0x23, 0x25, 0x27 }, + /* PMC 2 */ { 0x07, 0x17, 0x0e, 0x1e }, + /* PMC 3 */ { 0x20, 0x22, 0x24, 0x26 }, + /* PMC 4 */ { 0x07, 0x17, 0x0e, 0x1e } +}; + +/* + * Some direct events for decodes of event bus byte 3 have alternative + * PMCSEL values on other counters. This returns the alternative + * event code for those that do, or -1 otherwise. + */ +static s64 find_alternative_bdecode(u64 event) +{ + int pmc, altpmc, pp, j; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc == 0 || pmc > 4) + return -1; + altpmc = 5 - pmc; /* 1 <-> 4, 2 <-> 3 */ + pp = event & PM_PMCSEL_MSK; + for (j = 0; j < 4; ++j) { + if (bytedecode_alternatives[pmc - 1][j] == pp) { + return (event & ~(PM_PMC_MSKS | PM_PMCSEL_MSK)) | + (altpmc << PM_PMC_SH) | + bytedecode_alternatives[altpmc - 1][j]; + } + } + return -1; +} + +static int power5_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int i, j, nalt = 1; + s64 ae; + + alt[0] = event; + nalt = 1; + i = find_alternative(event); + if (i >= 0) { + for (j = 0; j < MAX_ALT; ++j) { + ae = event_alternatives[i][j]; + if (ae && ae != event) + alt[nalt++] = ae; + } + } else { + ae = find_alternative_bdecode(event); + if (ae > 0) + alt[nalt++] = ae; + } + return nalt; +} + +/* + * Map of which direct events on which PMCs are marked instruction events. + * Indexed by PMCSEL value, bit i (LE) set if PMC i is a marked event. + * Bit 0 is set if it is marked for all PMCs. + * The 0x80 bit indicates a byte decode PMCSEL value. + */ +static unsigned char direct_event_is_marked[0x28] = { + 0, /* 00 */ + 0x1f, /* 01 PM_IOPS_CMPL */ + 0x2, /* 02 PM_MRK_GRP_DISP */ + 0xe, /* 03 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */ + 0, /* 04 */ + 0x1c, /* 05 PM_MRK_BRU_FIN, PM_MRK_INST_FIN, PM_MRK_CRU_FIN */ + 0x80, /* 06 */ + 0x80, /* 07 */ + 0, 0, 0,/* 08 - 0a */ + 0x18, /* 0b PM_THRESH_TIMEO, PM_MRK_GRP_TIMEO */ + 0, /* 0c */ + 0x80, /* 0d */ + 0x80, /* 0e */ + 0, /* 0f */ + 0, /* 10 */ + 0x14, /* 11 PM_MRK_GRP_BR_REDIR, PM_MRK_GRP_IC_MISS */ + 0, /* 12 */ + 0x10, /* 13 PM_MRK_GRP_CMPL */ + 0x1f, /* 14 PM_GRP_MRK, PM_MRK_{FXU,FPU,LSU}_FIN */ + 0x2, /* 15 PM_MRK_GRP_ISSUED */ + 0x80, /* 16 */ + 0x80, /* 17 */ + 0, 0, 0, 0, 0, + 0x80, /* 1d */ + 0x80, /* 1e */ + 0, /* 1f */ + 0x80, /* 20 */ + 0x80, /* 21 */ + 0x80, /* 22 */ + 0x80, /* 23 */ + 0x80, /* 24 */ + 0x80, /* 25 */ + 0x80, /* 26 */ + 0x80, /* 27 */ +}; + +/* + * Returns 1 if event counts things relating to marked instructions + * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not. + */ +static int power5_marked_instr_event(u64 event) +{ + int pmc, psel; + int bit, byte, unit; + u32 mask; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + psel = event & PM_PMCSEL_MSK; + if (pmc >= 5) + return 0; + + bit = -1; + if (psel < sizeof(direct_event_is_marked)) { + if (direct_event_is_marked[psel] & (1 << pmc)) + return 1; + if (direct_event_is_marked[psel] & 0x80) + bit = 4; + else if (psel == 0x08) + bit = pmc - 1; + else if (psel == 0x10) + bit = 4 - pmc; + else if (psel == 0x1b && (pmc == 1 || pmc == 3)) + bit = 4; + } else if ((psel & 0x58) == 0x40) + bit = psel & 7; + + if (!(event & PM_BUSEVENT_MSK)) + return 0; + + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + if (unit == PM_LSU0) { + /* byte 1 bits 0-7, byte 2 bits 0,2-4,6 */ + mask = 0x5dff00; + } else if (unit == PM_LSU1 && byte >= 4) { + byte -= 4; + /* byte 4 bits 1,3,5,7, byte 5 bits 6-7, byte 7 bits 0-4,6 */ + mask = 0x5f00c0aa; + } else + return 0; + + return (mask >> (byte * 8 + bit)) & 1; +} + +static int power5_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr1 = 0; + u64 mmcra = 0; + unsigned int pmc, unit, byte, psel; + unsigned int ttm, grp; + int i, isbus, bit, grsel; + unsigned int pmc_inuse = 0; + unsigned int pmc_grp_use[2]; + unsigned char busbyte[4]; + unsigned char unituse[16]; + int ttmuse; + + if (n_ev > 6) + return -1; + + /* First pass to count resource use */ + pmc_grp_use[0] = pmc_grp_use[1] = 0; + memset(busbyte, 0, sizeof(busbyte)); + memset(unituse, 0, sizeof(unituse)); + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 6) + return -1; + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + pmc_inuse |= 1 << (pmc - 1); + /* count 1/2 vs 3/4 use */ + if (pmc <= 4) + ++pmc_grp_use[(pmc - 1) >> 1]; + } + if (event[i] & PM_BUSEVENT_MSK) { + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + if (unit > PM_LASTUNIT) + return -1; + if (unit == PM_ISU0_ALT) + unit = PM_ISU0; + if (byte >= 4) { + if (unit != PM_LSU1) + return -1; + ++unit; + byte &= 3; + } + if (!pmc) + ++pmc_grp_use[byte & 1]; + if (busbyte[byte] && busbyte[byte] != unit) + return -1; + busbyte[byte] = unit; + unituse[unit] = 1; + } + } + if (pmc_grp_use[0] > 2 || pmc_grp_use[1] > 2) + return -1; + + /* + * Assign resources and set multiplexer selects. + * + * PM_ISU0 can go either on TTM0 or TTM1, but that's the only + * choice we have to deal with. + */ + if (unituse[PM_ISU0] & + (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_ISU1])) { + unituse[PM_ISU0_ALT] = 1; /* move ISU to TTM1 */ + unituse[PM_ISU0] = 0; + } + /* Set TTM[01]SEL fields. */ + ttmuse = 0; + for (i = PM_FPU; i <= PM_ISU1; ++i) { + if (!unituse[i]) + continue; + if (ttmuse++) + return -1; + mmcr1 |= (u64)i << MMCR1_TTM0SEL_SH; + } + ttmuse = 0; + for (; i <= PM_GRS; ++i) { + if (!unituse[i]) + continue; + if (ttmuse++) + return -1; + mmcr1 |= (u64)(i & 3) << MMCR1_TTM1SEL_SH; + } + if (ttmuse > 1) + return -1; + + /* Set byte lane select fields, TTM[23]SEL and GRS_*SEL. */ + for (byte = 0; byte < 4; ++byte) { + unit = busbyte[byte]; + if (!unit) + continue; + if (unit == PM_ISU0 && unituse[PM_ISU0_ALT]) { + /* get ISU0 through TTM1 rather than TTM0 */ + unit = PM_ISU0_ALT; + } else if (unit == PM_LSU1 + 1) { + /* select lower word of LSU1 for this byte */ + mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte); + } + ttm = unit >> 2; + mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte); + } + + /* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + psel = event[i] & PM_PMCSEL_MSK; + isbus = event[i] & PM_BUSEVENT_MSK; + if (!pmc) { + /* Bus event or any-PMC direct event */ + for (pmc = 0; pmc < 4; ++pmc) { + if (pmc_inuse & (1 << pmc)) + continue; + grp = (pmc >> 1) & 1; + if (isbus) { + if (grp == (byte & 1)) + break; + } else if (pmc_grp_use[grp] < 2) { + ++pmc_grp_use[grp]; + break; + } + } + pmc_inuse |= 1 << pmc; + } else if (pmc <= 4) { + /* Direct event */ + --pmc; + if ((psel == 8 || psel == 0x10) && isbus && (byte & 2)) + /* add events on higher-numbered bus */ + mmcr1 |= 1ull << (MMCR1_PMC1_ADDER_SEL_SH - pmc); + } else { + /* Instructions or run cycles on PMC5/6 */ + --pmc; + } + if (isbus && unit == PM_GRS) { + bit = psel & 7; + grsel = (event[i] >> PM_GRS_SH) & PM_GRS_MSK; + mmcr1 |= (u64)grsel << grsel_shift[bit]; + } + if (power5_marked_instr_event(event[i])) + mmcra |= MMCRA_SAMPLE_ENABLE; + if (pmc <= 3) + mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc); + hwc[i] = pmc; + } + + /* Return MMCRx values */ + mmcr[0] = 0; + if (pmc_inuse & 1) + mmcr[0] = MMCR0_PMC1CE; + if (pmc_inuse & 0x3e) + mmcr[0] |= MMCR0_PMCjCE; + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + return 0; +} + +static void power5_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + if (pmc <= 3) + mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc)); +} + +static int power5_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 0xf, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x100009, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x4c1090, /* LD_REF_L1 */ + [PERF_COUNT_HW_CACHE_MISSES] = 0x3c1088, /* LD_MISS_L1 */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x230e4, /* BR_ISSUED */ + [PERF_COUNT_HW_BRANCH_MISSES] = 0x230e5, /* BR_MPRED_CR */ +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x4c1090, 0x3c1088 }, + [C(OP_WRITE)] = { 0x3c1090, 0xc10c3 }, + [C(OP_PREFETCH)] = { 0xc70e7, 0 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x3c309b }, + [C(OP_WRITE)] = { 0, 0 }, + [C(OP_PREFETCH)] = { 0xc50c3, 0 }, + }, + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x2c4090, 0x800c4 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x800c0 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x230e4, 0x230e5 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +struct power_pmu power5_pmu = { + .n_counter = 6, + .max_alternatives = MAX_ALT, + .add_fields = 0x7000090000555ull, + .test_adder = 0x3000490000000ull, + .compute_mmcr = power5_compute_mmcr, + .get_constraint = power5_get_constraint, + .get_alternatives = power5_get_alternatives, + .disable_pmc = power5_disable_pmc, + .n_generic = ARRAY_SIZE(power5_generic_events), + .generic_events = power5_generic_events, + .cache_events = &power5_cache_events, +}; diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c new file mode 100644 index 0000000000000000000000000000000000000000..46f74bebcfd92e8f30d4dc3187c1437baec22e76 --- /dev/null +++ b/arch/powerpc/kernel/power6-pmu.c @@ -0,0 +1,532 @@ +/* + * Performance counter support for POWER6 processors. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include + +/* + * Bits in event code for POWER6 + */ +#define PM_PMC_SH 20 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0x7 +#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH) +#define PM_UNIT_SH 16 /* Unit event comes (TTMxSEL encoding) */ +#define PM_UNIT_MSK 0xf +#define PM_UNIT_MSKS (PM_UNIT_MSK << PM_UNIT_SH) +#define PM_LLAV 0x8000 /* Load lookahead match value */ +#define PM_LLA 0x4000 /* Load lookahead match enable */ +#define PM_BYTE_SH 12 /* Byte of event bus to use */ +#define PM_BYTE_MSK 3 +#define PM_SUBUNIT_SH 8 /* Subunit event comes from (NEST_SEL enc.) */ +#define PM_SUBUNIT_MSK 7 +#define PM_SUBUNIT_MSKS (PM_SUBUNIT_MSK << PM_SUBUNIT_SH) +#define PM_PMCSEL_MSK 0xff /* PMCxSEL value */ +#define PM_BUSEVENT_MSK 0xf3700 + +/* + * Bits in MMCR1 for POWER6 + */ +#define MMCR1_TTM0SEL_SH 60 +#define MMCR1_TTMSEL_SH(n) (MMCR1_TTM0SEL_SH - (n) * 4) +#define MMCR1_TTMSEL_MSK 0xf +#define MMCR1_TTMSEL(m, n) (((m) >> MMCR1_TTMSEL_SH(n)) & MMCR1_TTMSEL_MSK) +#define MMCR1_NESTSEL_SH 45 +#define MMCR1_NESTSEL_MSK 0x7 +#define MMCR1_NESTSEL(m) (((m) >> MMCR1_NESTSEL_SH) & MMCR1_NESTSEL_MSK) +#define MMCR1_PMC1_LLA ((u64)1 << 44) +#define MMCR1_PMC1_LLA_VALUE ((u64)1 << 39) +#define MMCR1_PMC1_ADDR_SEL ((u64)1 << 35) +#define MMCR1_PMC1SEL_SH 24 +#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8) +#define MMCR1_PMCSEL_MSK 0xff + +/* + * Map of which direct events on which PMCs are marked instruction events. + * Indexed by PMCSEL value >> 1. + * Bottom 4 bits are a map of which PMCs are interesting, + * top 4 bits say what sort of event: + * 0 = direct marked event, + * 1 = byte decode event, + * 4 = add/and event (PMC1 -> bits 0 & 4), + * 5 = add/and event (PMC1 -> bits 1 & 5), + * 6 = add/and event (PMC1 -> bits 2 & 6), + * 7 = add/and event (PMC1 -> bits 3 & 7). + */ +static unsigned char direct_event_is_marked[0x60 >> 1] = { + 0, /* 00 */ + 0, /* 02 */ + 0, /* 04 */ + 0x07, /* 06 PM_MRK_ST_CMPL, PM_MRK_ST_GPS, PM_MRK_ST_CMPL_INT */ + 0x04, /* 08 PM_MRK_DFU_FIN */ + 0x06, /* 0a PM_MRK_IFU_FIN, PM_MRK_INST_FIN */ + 0, /* 0c */ + 0, /* 0e */ + 0x02, /* 10 PM_MRK_INST_DISP */ + 0x08, /* 12 PM_MRK_LSU_DERAT_MISS */ + 0, /* 14 */ + 0, /* 16 */ + 0x0c, /* 18 PM_THRESH_TIMEO, PM_MRK_INST_FIN */ + 0x0f, /* 1a PM_MRK_INST_DISP, PM_MRK_{FXU,FPU,LSU}_FIN */ + 0x01, /* 1c PM_MRK_INST_ISSUED */ + 0, /* 1e */ + 0, /* 20 */ + 0, /* 22 */ + 0, /* 24 */ + 0, /* 26 */ + 0x15, /* 28 PM_MRK_DATA_FROM_L2MISS, PM_MRK_DATA_FROM_L3MISS */ + 0, /* 2a */ + 0, /* 2c */ + 0, /* 2e */ + 0x4f, /* 30 */ + 0x7f, /* 32 */ + 0x4f, /* 34 */ + 0x5f, /* 36 */ + 0x6f, /* 38 */ + 0x4f, /* 3a */ + 0, /* 3c */ + 0x08, /* 3e PM_MRK_INST_TIMEO */ + 0x1f, /* 40 */ + 0x1f, /* 42 */ + 0x1f, /* 44 */ + 0x1f, /* 46 */ + 0x1f, /* 48 */ + 0x1f, /* 4a */ + 0x1f, /* 4c */ + 0x1f, /* 4e */ + 0, /* 50 */ + 0x05, /* 52 PM_MRK_BR_TAKEN, PM_MRK_BR_MPRED */ + 0x1c, /* 54 PM_MRK_PTEG_FROM_L3MISS, PM_MRK_PTEG_FROM_L2MISS */ + 0x02, /* 56 PM_MRK_LD_MISS_L1 */ + 0, /* 58 */ + 0, /* 5a */ + 0, /* 5c */ + 0, /* 5e */ +}; + +/* + * Masks showing for each unit which bits are marked events. + * These masks are in LE order, i.e. 0x00000001 is byte 0, bit 0. + */ +static u32 marked_bus_events[16] = { + 0x01000000, /* direct events set 1: byte 3 bit 0 */ + 0x00010000, /* direct events set 2: byte 2 bit 0 */ + 0, 0, 0, 0, /* IDU, IFU, nest: nothing */ + 0x00000088, /* VMX set 1: byte 0 bits 3, 7 */ + 0x000000c0, /* VMX set 2: byte 0 bits 4-7 */ + 0x04010000, /* LSU set 1: byte 2 bit 0, byte 3 bit 2 */ + 0xff010000u, /* LSU set 2: byte 2 bit 0, all of byte 3 */ + 0, /* LSU set 3 */ + 0x00000010, /* VMX set 3: byte 0 bit 4 */ + 0, /* BFP set 1 */ + 0x00000022, /* BFP set 2: byte 0 bits 1, 5 */ + 0, 0 +}; + +/* + * Returns 1 if event counts things relating to marked instructions + * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not. + */ +static int power6_marked_instr_event(u64 event) +{ + int pmc, psel, ptype; + int bit, byte, unit; + u32 mask; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + psel = (event & PM_PMCSEL_MSK) >> 1; /* drop edge/level bit */ + if (pmc >= 5) + return 0; + + bit = -1; + if (psel < sizeof(direct_event_is_marked)) { + ptype = direct_event_is_marked[psel]; + if (pmc == 0 || !(ptype & (1 << (pmc - 1)))) + return 0; + ptype >>= 4; + if (ptype == 0) + return 1; + if (ptype == 1) + bit = 0; + else + bit = ptype ^ (pmc - 1); + } else if ((psel & 0x48) == 0x40) + bit = psel & 7; + + if (!(event & PM_BUSEVENT_MSK) || bit == -1) + return 0; + + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + mask = marked_bus_events[unit]; + return (mask >> (byte * 8 + bit)) & 1; +} + +/* + * Assign PMC numbers and compute MMCR1 value for a set of events + */ +static int p6_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr1 = 0; + u64 mmcra = 0; + int i; + unsigned int pmc, ev, b, u, s, psel; + unsigned int ttmset = 0; + unsigned int pmc_inuse = 0; + + if (n_ev > 6) + return -1; + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc_inuse & (1 << (pmc - 1))) + return -1; /* collision! */ + pmc_inuse |= 1 << (pmc - 1); + } + } + for (i = 0; i < n_ev; ++i) { + ev = event[i]; + pmc = (ev >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + --pmc; + } else { + /* can go on any PMC; find a free one */ + for (pmc = 0; pmc < 4; ++pmc) + if (!(pmc_inuse & (1 << pmc))) + break; + if (pmc >= 4) + return -1; + pmc_inuse |= 1 << pmc; + } + hwc[i] = pmc; + psel = ev & PM_PMCSEL_MSK; + if (ev & PM_BUSEVENT_MSK) { + /* this event uses the event bus */ + b = (ev >> PM_BYTE_SH) & PM_BYTE_MSK; + u = (ev >> PM_UNIT_SH) & PM_UNIT_MSK; + /* check for conflict on this byte of event bus */ + if ((ttmset & (1 << b)) && MMCR1_TTMSEL(mmcr1, b) != u) + return -1; + mmcr1 |= (u64)u << MMCR1_TTMSEL_SH(b); + ttmset |= 1 << b; + if (u == 5) { + /* Nest events have a further mux */ + s = (ev >> PM_SUBUNIT_SH) & PM_SUBUNIT_MSK; + if ((ttmset & 0x10) && + MMCR1_NESTSEL(mmcr1) != s) + return -1; + ttmset |= 0x10; + mmcr1 |= (u64)s << MMCR1_NESTSEL_SH; + } + if (0x30 <= psel && psel <= 0x3d) { + /* these need the PMCx_ADDR_SEL bits */ + if (b >= 2) + mmcr1 |= MMCR1_PMC1_ADDR_SEL >> pmc; + } + /* bus select values are different for PMC3/4 */ + if (pmc >= 2 && (psel & 0x90) == 0x80) + psel ^= 0x20; + } + if (ev & PM_LLA) { + mmcr1 |= MMCR1_PMC1_LLA >> pmc; + if (ev & PM_LLAV) + mmcr1 |= MMCR1_PMC1_LLA_VALUE >> pmc; + } + if (power6_marked_instr_event(event[i])) + mmcra |= MMCRA_SAMPLE_ENABLE; + if (pmc < 4) + mmcr1 |= (u64)psel << MMCR1_PMCSEL_SH(pmc); + } + mmcr[0] = 0; + if (pmc_inuse & 1) + mmcr[0] = MMCR0_PMC1CE; + if (pmc_inuse & 0xe) + mmcr[0] |= MMCR0_PMCjCE; + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + return 0; +} + +/* + * Layout of constraint bits: + * + * 0-1 add field: number of uses of PMC1 (max 1) + * 2-3, 4-5, 6-7, 8-9, 10-11: ditto for PMC2, 3, 4, 5, 6 + * 12-15 add field: number of uses of PMC1-4 (max 4) + * 16-19 select field: unit on byte 0 of event bus + * 20-23, 24-27, 28-31 ditto for bytes 1, 2, 3 + * 32-34 select field: nest (subunit) event selector + */ +static int p6_get_constraint(u64 event, u64 *maskp, u64 *valp) +{ + int pmc, byte, sh, subunit; + u64 mask = 0, value = 0; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 4 && !(event == 0x500009 || event == 0x600005)) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + } + if (event & PM_BUSEVENT_MSK) { + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + sh = byte * 4 + (16 - PM_UNIT_SH); + mask |= PM_UNIT_MSKS << sh; + value |= (u64)(event & PM_UNIT_MSKS) << sh; + if ((event & PM_UNIT_MSKS) == (5 << PM_UNIT_SH)) { + subunit = (event >> PM_SUBUNIT_SH) & PM_SUBUNIT_MSK; + mask |= (u64)PM_SUBUNIT_MSK << 32; + value |= (u64)subunit << 32; + } + } + if (pmc <= 4) { + mask |= 0x8000; /* add field for count of PMC1-4 uses */ + value |= 0x1000; + } + *maskp = mask; + *valp = value; + return 0; +} + +static int p6_limited_pmc_event(u64 event) +{ + int pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + + return pmc == 5 || pmc == 6; +} + +#define MAX_ALT 4 /* at most 4 alternatives for any event */ + +static const unsigned int event_alternatives[][MAX_ALT] = { + { 0x0130e8, 0x2000f6, 0x3000fc }, /* PM_PTEG_RELOAD_VALID */ + { 0x080080, 0x10000d, 0x30000c, 0x4000f0 }, /* PM_LD_MISS_L1 */ + { 0x080088, 0x200054, 0x3000f0 }, /* PM_ST_MISS_L1 */ + { 0x10000a, 0x2000f4, 0x600005 }, /* PM_RUN_CYC */ + { 0x10000b, 0x2000f5 }, /* PM_RUN_COUNT */ + { 0x10000e, 0x400010 }, /* PM_PURR */ + { 0x100010, 0x4000f8 }, /* PM_FLUSH */ + { 0x10001a, 0x200010 }, /* PM_MRK_INST_DISP */ + { 0x100026, 0x3000f8 }, /* PM_TB_BIT_TRANS */ + { 0x100054, 0x2000f0 }, /* PM_ST_FIN */ + { 0x100056, 0x2000fc }, /* PM_L1_ICACHE_MISS */ + { 0x1000f0, 0x40000a }, /* PM_INST_IMC_MATCH_CMPL */ + { 0x1000f8, 0x200008 }, /* PM_GCT_EMPTY_CYC */ + { 0x1000fc, 0x400006 }, /* PM_LSU_DERAT_MISS_CYC */ + { 0x20000e, 0x400007 }, /* PM_LSU_DERAT_MISS */ + { 0x200012, 0x300012 }, /* PM_INST_DISP */ + { 0x2000f2, 0x3000f2 }, /* PM_INST_DISP */ + { 0x2000f8, 0x300010 }, /* PM_EXT_INT */ + { 0x2000fe, 0x300056 }, /* PM_DATA_FROM_L2MISS */ + { 0x2d0030, 0x30001a }, /* PM_MRK_FPU_FIN */ + { 0x30000a, 0x400018 }, /* PM_MRK_INST_FIN */ + { 0x3000f6, 0x40000e }, /* PM_L1_DCACHE_RELOAD_VALID */ + { 0x3000fe, 0x400056 }, /* PM_DATA_FROM_L3MISS */ +}; + +/* + * This could be made more efficient with a binary search on + * a presorted list, if necessary + */ +static int find_alternatives_list(u64 event) +{ + int i, j; + unsigned int alt; + + for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) { + if (event < event_alternatives[i][0]) + return -1; + for (j = 0; j < MAX_ALT; ++j) { + alt = event_alternatives[i][j]; + if (!alt || event < alt) + break; + if (event == alt) + return i; + } + } + return -1; +} + +static int p6_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int i, j, nlim; + unsigned int psel, pmc; + unsigned int nalt = 1; + u64 aevent; + + alt[0] = event; + nlim = p6_limited_pmc_event(event); + + /* check the alternatives table */ + i = find_alternatives_list(event); + if (i >= 0) { + /* copy out alternatives from list */ + for (j = 0; j < MAX_ALT; ++j) { + aevent = event_alternatives[i][j]; + if (!aevent) + break; + if (aevent != event) + alt[nalt++] = aevent; + nlim += p6_limited_pmc_event(aevent); + } + + } else { + /* Check for alternative ways of computing sum events */ + /* PMCSEL 0x32 counter N == PMCSEL 0x34 counter 5-N */ + psel = event & (PM_PMCSEL_MSK & ~1); /* ignore edge bit */ + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc && (psel == 0x32 || psel == 0x34)) + alt[nalt++] = ((event ^ 0x6) & ~PM_PMC_MSKS) | + ((5 - pmc) << PM_PMC_SH); + + /* PMCSEL 0x38 counter N == PMCSEL 0x3a counter N+/-2 */ + if (pmc && (psel == 0x38 || psel == 0x3a)) + alt[nalt++] = ((event ^ 0x2) & ~PM_PMC_MSKS) | + ((pmc > 2? pmc - 2: pmc + 2) << PM_PMC_SH); + } + + if (flags & PPMU_ONLY_COUNT_RUN) { + /* + * We're only counting in RUN state, + * so PM_CYC is equivalent to PM_RUN_CYC, + * PM_INST_CMPL === PM_RUN_INST_CMPL, PM_PURR === PM_RUN_PURR. + * This doesn't include alternatives that don't provide + * any extra flexibility in assigning PMCs (e.g. + * 0x10000a for PM_RUN_CYC vs. 0x1e for PM_CYC). + * Note that even with these additional alternatives + * we never end up with more than 4 alternatives for any event. + */ + j = nalt; + for (i = 0; i < nalt; ++i) { + switch (alt[i]) { + case 0x1e: /* PM_CYC */ + alt[j++] = 0x600005; /* PM_RUN_CYC */ + ++nlim; + break; + case 0x10000a: /* PM_RUN_CYC */ + alt[j++] = 0x1e; /* PM_CYC */ + break; + case 2: /* PM_INST_CMPL */ + alt[j++] = 0x500009; /* PM_RUN_INST_CMPL */ + ++nlim; + break; + case 0x500009: /* PM_RUN_INST_CMPL */ + alt[j++] = 2; /* PM_INST_CMPL */ + break; + case 0x10000e: /* PM_PURR */ + alt[j++] = 0x4000f4; /* PM_RUN_PURR */ + break; + case 0x4000f4: /* PM_RUN_PURR */ + alt[j++] = 0x10000e; /* PM_PURR */ + break; + } + } + nalt = j; + } + + if (!(flags & PPMU_LIMITED_PMC_OK) && nlim) { + /* remove the limited PMC events */ + j = 0; + for (i = 0; i < nalt; ++i) { + if (!p6_limited_pmc_event(alt[i])) { + alt[j] = alt[i]; + ++j; + } + } + nalt = j; + } else if ((flags & PPMU_LIMITED_PMC_REQD) && nlim < nalt) { + /* remove all but the limited PMC events */ + j = 0; + for (i = 0; i < nalt; ++i) { + if (p6_limited_pmc_event(alt[i])) { + alt[j] = alt[i]; + ++j; + } + } + nalt = j; + } + + return nalt; +} + +static void p6_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + /* Set PMCxSEL to 0 to disable PMCx */ + if (pmc <= 3) + mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc)); +} + +static int power6_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 0x1e, + [PERF_COUNT_HW_INSTRUCTIONS] = 2, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x280030, /* LD_REF_L1 */ + [PERF_COUNT_HW_CACHE_MISSES] = 0x30000c, /* LD_MISS_L1 */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x410a0, /* BR_PRED */ + [PERF_COUNT_HW_BRANCH_MISSES] = 0x400052, /* BR_MPRED */ +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + * The "DTLB" and "ITLB" events relate to the DERAT and IERAT. + */ +static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x80082, 0x80080 }, + [C(OP_WRITE)] = { 0x80086, 0x80088 }, + [C(OP_PREFETCH)] = { 0x810a4, 0 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x100056 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0x4008c, 0 }, + }, + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x150730, 0x250532 }, + [C(OP_WRITE)] = { 0x250432, 0x150432 }, + [C(OP_PREFETCH)] = { 0x810a6, 0 }, + }, + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x20000e }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x420ce }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x430e6, 0x400052 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +struct power_pmu power6_pmu = { + .n_counter = 6, + .max_alternatives = MAX_ALT, + .add_fields = 0x1555, + .test_adder = 0x3000, + .compute_mmcr = p6_compute_mmcr, + .get_constraint = p6_get_constraint, + .get_alternatives = p6_get_alternatives, + .disable_pmc = p6_disable_pmc, + .limited_pmc_event = p6_limited_pmc_event, + .flags = PPMU_LIMITED_PMC5_6 | PPMU_ALT_SIPR, + .n_generic = ARRAY_SIZE(power6_generic_events), + .generic_events = power6_generic_events, + .cache_events = &power6_cache_events, +}; diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c new file mode 100644 index 0000000000000000000000000000000000000000..b3f7d1216bae8b8299735a8e3b03f267ddafcd5d --- /dev/null +++ b/arch/powerpc/kernel/power7-pmu.c @@ -0,0 +1,357 @@ +/* + * Performance counter support for POWER7 processors. + * + * Copyright 2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include + +/* + * Bits in event code for POWER7 + */ +#define PM_PMC_SH 16 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0xf +#define PM_PMC_MSKS (PM_PMC_MSK << PM_PMC_SH) +#define PM_UNIT_SH 12 /* TTMMUX number and setting - unit select */ +#define PM_UNIT_MSK 0xf +#define PM_COMBINE_SH 11 /* Combined event bit */ +#define PM_COMBINE_MSK 1 +#define PM_COMBINE_MSKS 0x800 +#define PM_L2SEL_SH 8 /* L2 event select */ +#define PM_L2SEL_MSK 7 +#define PM_PMCSEL_MSK 0xff + +/* + * Bits in MMCR1 for POWER7 + */ +#define MMCR1_TTM0SEL_SH 60 +#define MMCR1_TTM1SEL_SH 56 +#define MMCR1_TTM2SEL_SH 52 +#define MMCR1_TTM3SEL_SH 48 +#define MMCR1_TTMSEL_MSK 0xf +#define MMCR1_L2SEL_SH 45 +#define MMCR1_L2SEL_MSK 7 +#define MMCR1_PMC1_COMBINE_SH 35 +#define MMCR1_PMC2_COMBINE_SH 34 +#define MMCR1_PMC3_COMBINE_SH 33 +#define MMCR1_PMC4_COMBINE_SH 32 +#define MMCR1_PMC1SEL_SH 24 +#define MMCR1_PMC2SEL_SH 16 +#define MMCR1_PMC3SEL_SH 8 +#define MMCR1_PMC4SEL_SH 0 +#define MMCR1_PMCSEL_SH(n) (MMCR1_PMC1SEL_SH - (n) * 8) +#define MMCR1_PMCSEL_MSK 0xff + +/* + * Bits in MMCRA + */ + +/* + * Layout of constraint bits: + * 6666555555555544444444443333333333222222222211111111110000000000 + * 3210987654321098765432109876543210987654321098765432109876543210 + * [ ><><><><><><> + * NC P6P5P4P3P2P1 + * + * NC - number of counters + * 15: NC error 0x8000 + * 12-14: number of events needing PMC1-4 0x7000 + * + * P6 + * 11: P6 error 0x800 + * 10-11: Count of events needing PMC6 + * + * P1..P5 + * 0-9: Count of events needing PMC1..PMC5 + */ + +static int power7_get_constraint(u64 event, u64 *maskp, u64 *valp) +{ + int pmc, sh; + u64 mask = 0, value = 0; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 6) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + if (pmc >= 5 && !(event == 0x500fa || event == 0x600f4)) + return -1; + } + if (pmc < 5) { + /* need a counter from PMC1-4 set */ + mask |= 0x8000; + value |= 0x1000; + } + *maskp = mask; + *valp = value; + return 0; +} + +#define MAX_ALT 2 /* at most 2 alternatives for any event */ + +static const unsigned int event_alternatives[][MAX_ALT] = { + { 0x200f2, 0x300f2 }, /* PM_INST_DISP */ + { 0x200f4, 0x600f4 }, /* PM_RUN_CYC */ + { 0x400fa, 0x500fa }, /* PM_RUN_INST_CMPL */ +}; + +/* + * Scan the alternatives table for a match and return the + * index into the alternatives table if found, else -1. + */ +static int find_alternative(u64 event) +{ + int i, j; + + for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) { + if (event < event_alternatives[i][0]) + break; + for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j) + if (event == event_alternatives[i][j]) + return i; + } + return -1; +} + +static s64 find_alternative_decode(u64 event) +{ + int pmc, psel; + + /* this only handles the 4x decode events */ + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + psel = event & PM_PMCSEL_MSK; + if ((pmc == 2 || pmc == 4) && (psel & ~7) == 0x40) + return event - (1 << PM_PMC_SH) + 8; + if ((pmc == 1 || pmc == 3) && (psel & ~7) == 0x48) + return event + (1 << PM_PMC_SH) - 8; + return -1; +} + +static int power7_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int i, j, nalt = 1; + s64 ae; + + alt[0] = event; + nalt = 1; + i = find_alternative(event); + if (i >= 0) { + for (j = 0; j < MAX_ALT; ++j) { + ae = event_alternatives[i][j]; + if (ae && ae != event) + alt[nalt++] = ae; + } + } else { + ae = find_alternative_decode(event); + if (ae > 0) + alt[nalt++] = ae; + } + + if (flags & PPMU_ONLY_COUNT_RUN) { + /* + * We're only counting in RUN state, + * so PM_CYC is equivalent to PM_RUN_CYC + * and PM_INST_CMPL === PM_RUN_INST_CMPL. + * This doesn't include alternatives that don't provide + * any extra flexibility in assigning PMCs. + */ + j = nalt; + for (i = 0; i < nalt; ++i) { + switch (alt[i]) { + case 0x1e: /* PM_CYC */ + alt[j++] = 0x600f4; /* PM_RUN_CYC */ + break; + case 0x600f4: /* PM_RUN_CYC */ + alt[j++] = 0x1e; + break; + case 0x2: /* PM_PPC_CMPL */ + alt[j++] = 0x500fa; /* PM_RUN_INST_CMPL */ + break; + case 0x500fa: /* PM_RUN_INST_CMPL */ + alt[j++] = 0x2; /* PM_PPC_CMPL */ + break; + } + } + nalt = j; + } + + return nalt; +} + +/* + * Returns 1 if event counts things relating to marked instructions + * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not. + */ +static int power7_marked_instr_event(u64 event) +{ + int pmc, psel; + int unit; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + psel = event & PM_PMCSEL_MSK & ~1; /* trim off edge/level bit */ + if (pmc >= 5) + return 0; + + switch (psel >> 4) { + case 2: + return pmc == 2 || pmc == 4; + case 3: + if (psel == 0x3c) + return pmc == 1; + if (psel == 0x3e) + return pmc != 2; + return 1; + case 4: + case 5: + return unit == 0xd; + case 6: + if (psel == 0x64) + return pmc >= 3; + case 8: + return unit == 0xd; + } + return 0; +} + +static int power7_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr1 = 0; + u64 mmcra = 0; + unsigned int pmc, unit, combine, l2sel, psel; + unsigned int pmc_inuse = 0; + int i; + + /* First pass to count resource use */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 6) + return -1; + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + pmc_inuse |= 1 << (pmc - 1); + } + } + + /* Second pass: assign PMCs, set all MMCR1 fields */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + combine = (event[i] >> PM_COMBINE_SH) & PM_COMBINE_MSK; + l2sel = (event[i] >> PM_L2SEL_SH) & PM_L2SEL_MSK; + psel = event[i] & PM_PMCSEL_MSK; + if (!pmc) { + /* Bus event or any-PMC direct event */ + for (pmc = 0; pmc < 4; ++pmc) { + if (!(pmc_inuse & (1 << pmc))) + break; + } + if (pmc >= 4) + return -1; + pmc_inuse |= 1 << pmc; + } else { + /* Direct or decoded event */ + --pmc; + } + if (pmc <= 3) { + mmcr1 |= (u64) unit << (MMCR1_TTM0SEL_SH - 4 * pmc); + mmcr1 |= (u64) combine << (MMCR1_PMC1_COMBINE_SH - pmc); + mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc); + if (unit == 6) /* L2 events */ + mmcr1 |= (u64) l2sel << MMCR1_L2SEL_SH; + } + if (power7_marked_instr_event(event[i])) + mmcra |= MMCRA_SAMPLE_ENABLE; + hwc[i] = pmc; + } + + /* Return MMCRx values */ + mmcr[0] = 0; + if (pmc_inuse & 1) + mmcr[0] = MMCR0_PMC1CE; + if (pmc_inuse & 0x3e) + mmcr[0] |= MMCR0_PMCjCE; + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + return 0; +} + +static void power7_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + if (pmc <= 3) + mmcr[1] &= ~(0xffULL << MMCR1_PMCSEL_SH(pmc)); +} + +static int power7_generic_events[] = { + [PERF_COUNT_CPU_CYCLES] = 0x1e, + [PERF_COUNT_INSTRUCTIONS] = 2, + [PERF_COUNT_CACHE_REFERENCES] = 0xc880, /* LD_REF_L1_LSU */ + [PERF_COUNT_CACHE_MISSES] = 0x400f0, /* LD_MISS_L1 */ + [PERF_COUNT_BRANCH_INSTRUCTIONS] = 0x10068, /* BRU_FIN */ + [PERF_COUNT_BRANCH_MISSES] = 0x400f6, /* BR_MPRED */ +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x400f0, 0xc880 }, + [C(OP_WRITE)] = { 0, 0x300f0 }, + [C(OP_PREFETCH)] = { 0xd8b8, 0 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x200fc }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0x408a, 0 }, + }, + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x6080, 0x6084 }, + [C(OP_WRITE)] = { 0x6082, 0x6086 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x300fc }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x400fc }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x10068, 0x400f6 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +struct power_pmu power7_pmu = { + .n_counter = 6, + .max_alternatives = MAX_ALT + 1, + .add_fields = 0x1555ull, + .test_adder = 0x3000ull, + .compute_mmcr = power7_compute_mmcr, + .get_constraint = power7_get_constraint, + .get_alternatives = power7_get_alternatives, + .disable_pmc = power7_disable_pmc, + .n_generic = ARRAY_SIZE(power7_generic_events), + .generic_events = power7_generic_events, + .cache_events = &power7_cache_events, +}; diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c new file mode 100644 index 0000000000000000000000000000000000000000..ba0a357a89f405f8e70d6cd7255928e40b906d86 --- /dev/null +++ b/arch/powerpc/kernel/ppc970-pmu.c @@ -0,0 +1,482 @@ +/* + * Performance counter support for PPC970-family processors. + * + * Copyright 2008-2009 Paul Mackerras, IBM Corporation. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include +#include +#include + +/* + * Bits in event code for PPC970 + */ +#define PM_PMC_SH 12 /* PMC number (1-based) for direct events */ +#define PM_PMC_MSK 0xf +#define PM_UNIT_SH 8 /* TTMMUX number and setting - unit select */ +#define PM_UNIT_MSK 0xf +#define PM_SPCSEL_SH 6 +#define PM_SPCSEL_MSK 3 +#define PM_BYTE_SH 4 /* Byte number of event bus to use */ +#define PM_BYTE_MSK 3 +#define PM_PMCSEL_MSK 0xf + +/* Values in PM_UNIT field */ +#define PM_NONE 0 +#define PM_FPU 1 +#define PM_VPU 2 +#define PM_ISU 3 +#define PM_IFU 4 +#define PM_IDU 5 +#define PM_STS 6 +#define PM_LSU0 7 +#define PM_LSU1U 8 +#define PM_LSU1L 9 +#define PM_LASTUNIT 9 + +/* + * Bits in MMCR0 for PPC970 + */ +#define MMCR0_PMC1SEL_SH 8 +#define MMCR0_PMC2SEL_SH 1 +#define MMCR_PMCSEL_MSK 0x1f + +/* + * Bits in MMCR1 for PPC970 + */ +#define MMCR1_TTM0SEL_SH 62 +#define MMCR1_TTM1SEL_SH 59 +#define MMCR1_TTM3SEL_SH 53 +#define MMCR1_TTMSEL_MSK 3 +#define MMCR1_TD_CP_DBG0SEL_SH 50 +#define MMCR1_TD_CP_DBG1SEL_SH 48 +#define MMCR1_TD_CP_DBG2SEL_SH 46 +#define MMCR1_TD_CP_DBG3SEL_SH 44 +#define MMCR1_PMC1_ADDER_SEL_SH 39 +#define MMCR1_PMC2_ADDER_SEL_SH 38 +#define MMCR1_PMC6_ADDER_SEL_SH 37 +#define MMCR1_PMC5_ADDER_SEL_SH 36 +#define MMCR1_PMC8_ADDER_SEL_SH 35 +#define MMCR1_PMC7_ADDER_SEL_SH 34 +#define MMCR1_PMC3_ADDER_SEL_SH 33 +#define MMCR1_PMC4_ADDER_SEL_SH 32 +#define MMCR1_PMC3SEL_SH 27 +#define MMCR1_PMC4SEL_SH 22 +#define MMCR1_PMC5SEL_SH 17 +#define MMCR1_PMC6SEL_SH 12 +#define MMCR1_PMC7SEL_SH 7 +#define MMCR1_PMC8SEL_SH 2 + +static short mmcr1_adder_bits[8] = { + MMCR1_PMC1_ADDER_SEL_SH, + MMCR1_PMC2_ADDER_SEL_SH, + MMCR1_PMC3_ADDER_SEL_SH, + MMCR1_PMC4_ADDER_SEL_SH, + MMCR1_PMC5_ADDER_SEL_SH, + MMCR1_PMC6_ADDER_SEL_SH, + MMCR1_PMC7_ADDER_SEL_SH, + MMCR1_PMC8_ADDER_SEL_SH +}; + +/* + * Bits in MMCRA + */ + +/* + * Layout of constraint bits: + * 6666555555555544444444443333333333222222222211111111110000000000 + * 3210987654321098765432109876543210987654321098765432109876543210 + * <><><>[ >[ >[ >< >< >< >< ><><><><><><><><> + * SPT0T1 UC PS1 PS2 B0 B1 B2 B3 P1P2P3P4P5P6P7P8 + * + * SP - SPCSEL constraint + * 48-49: SPCSEL value 0x3_0000_0000_0000 + * + * T0 - TTM0 constraint + * 46-47: TTM0SEL value (0=FPU, 2=IFU, 3=VPU) 0xC000_0000_0000 + * + * T1 - TTM1 constraint + * 44-45: TTM1SEL value (0=IDU, 3=STS) 0x3000_0000_0000 + * + * UC - unit constraint: can't have all three of FPU|IFU|VPU, ISU, IDU|STS + * 43: UC3 error 0x0800_0000_0000 + * 42: FPU|IFU|VPU events needed 0x0400_0000_0000 + * 41: ISU events needed 0x0200_0000_0000 + * 40: IDU|STS events needed 0x0100_0000_0000 + * + * PS1 + * 39: PS1 error 0x0080_0000_0000 + * 36-38: count of events needing PMC1/2/5/6 0x0070_0000_0000 + * + * PS2 + * 35: PS2 error 0x0008_0000_0000 + * 32-34: count of events needing PMC3/4/7/8 0x0007_0000_0000 + * + * B0 + * 28-31: Byte 0 event source 0xf000_0000 + * Encoding as for the event code + * + * B1, B2, B3 + * 24-27, 20-23, 16-19: Byte 1, 2, 3 event sources + * + * P1 + * 15: P1 error 0x8000 + * 14-15: Count of events needing PMC1 + * + * P2..P8 + * 0-13: Count of events needing PMC2..PMC8 + */ + +static unsigned char direct_marked_event[8] = { + (1<<2) | (1<<3), /* PMC1: PM_MRK_GRP_DISP, PM_MRK_ST_CMPL */ + (1<<3) | (1<<5), /* PMC2: PM_THRESH_TIMEO, PM_MRK_BRU_FIN */ + (1<<3) | (1<<5), /* PMC3: PM_MRK_ST_CMPL_INT, PM_MRK_VMX_FIN */ + (1<<4) | (1<<5), /* PMC4: PM_MRK_GRP_CMPL, PM_MRK_CRU_FIN */ + (1<<4) | (1<<5), /* PMC5: PM_GRP_MRK, PM_MRK_GRP_TIMEO */ + (1<<3) | (1<<4) | (1<<5), + /* PMC6: PM_MRK_ST_STS, PM_MRK_FXU_FIN, PM_MRK_GRP_ISSUED */ + (1<<4) | (1<<5), /* PMC7: PM_MRK_FPU_FIN, PM_MRK_INST_FIN */ + (1<<4) /* PMC8: PM_MRK_LSU_FIN */ +}; + +/* + * Returns 1 if event counts things relating to marked instructions + * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not. + */ +static int p970_marked_instr_event(u64 event) +{ + int pmc, psel, unit, byte, bit; + unsigned int mask; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + psel = event & PM_PMCSEL_MSK; + if (pmc) { + if (direct_marked_event[pmc - 1] & (1 << psel)) + return 1; + if (psel == 0) /* add events */ + bit = (pmc <= 4)? pmc - 1: 8 - pmc; + else if (psel == 7 || psel == 13) /* decode events */ + bit = 4; + else + return 0; + } else + bit = psel; + + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + mask = 0; + switch (unit) { + case PM_VPU: + mask = 0x4c; /* byte 0 bits 2,3,6 */ + case PM_LSU0: + /* byte 2 bits 0,2,3,4,6; all of byte 1 */ + mask = 0x085dff00; + case PM_LSU1L: + mask = 0x50 << 24; /* byte 3 bits 4,6 */ + break; + } + return (mask >> (byte * 8 + bit)) & 1; +} + +/* Masks and values for using events from the various units */ +static u64 unit_cons[PM_LASTUNIT+1][2] = { + [PM_FPU] = { 0xc80000000000ull, 0x040000000000ull }, + [PM_VPU] = { 0xc80000000000ull, 0xc40000000000ull }, + [PM_ISU] = { 0x080000000000ull, 0x020000000000ull }, + [PM_IFU] = { 0xc80000000000ull, 0x840000000000ull }, + [PM_IDU] = { 0x380000000000ull, 0x010000000000ull }, + [PM_STS] = { 0x380000000000ull, 0x310000000000ull }, +}; + +static int p970_get_constraint(u64 event, u64 *maskp, u64 *valp) +{ + int pmc, byte, unit, sh, spcsel; + u64 mask = 0, value = 0; + int grp = -1; + + pmc = (event >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc > 8) + return -1; + sh = (pmc - 1) * 2; + mask |= 2 << sh; + value |= 1 << sh; + grp = ((pmc - 1) >> 1) & 1; + } + unit = (event >> PM_UNIT_SH) & PM_UNIT_MSK; + if (unit) { + if (unit > PM_LASTUNIT) + return -1; + mask |= unit_cons[unit][0]; + value |= unit_cons[unit][1]; + byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK; + /* + * Bus events on bytes 0 and 2 can be counted + * on PMC1/2/5/6; bytes 1 and 3 on PMC3/4/7/8. + */ + if (!pmc) + grp = byte & 1; + /* Set byte lane select field */ + mask |= 0xfULL << (28 - 4 * byte); + value |= (u64)unit << (28 - 4 * byte); + } + if (grp == 0) { + /* increment PMC1/2/5/6 field */ + mask |= 0x8000000000ull; + value |= 0x1000000000ull; + } else if (grp == 1) { + /* increment PMC3/4/7/8 field */ + mask |= 0x800000000ull; + value |= 0x100000000ull; + } + spcsel = (event >> PM_SPCSEL_SH) & PM_SPCSEL_MSK; + if (spcsel) { + mask |= 3ull << 48; + value |= (u64)spcsel << 48; + } + *maskp = mask; + *valp = value; + return 0; +} + +static int p970_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + alt[0] = event; + + /* 2 alternatives for LSU empty */ + if (event == 0x2002 || event == 0x3002) { + alt[1] = event ^ 0x1000; + return 2; + } + + return 1; +} + +static int p970_compute_mmcr(u64 event[], int n_ev, + unsigned int hwc[], u64 mmcr[]) +{ + u64 mmcr0 = 0, mmcr1 = 0, mmcra = 0; + unsigned int pmc, unit, byte, psel; + unsigned int ttm, grp; + unsigned int pmc_inuse = 0; + unsigned int pmc_grp_use[2]; + unsigned char busbyte[4]; + unsigned char unituse[16]; + unsigned char unitmap[] = { 0, 0<<3, 3<<3, 1<<3, 2<<3, 0|4, 3|4 }; + unsigned char ttmuse[2]; + unsigned char pmcsel[8]; + int i; + int spcsel; + + if (n_ev > 8) + return -1; + + /* First pass to count resource use */ + pmc_grp_use[0] = pmc_grp_use[1] = 0; + memset(busbyte, 0, sizeof(busbyte)); + memset(unituse, 0, sizeof(unituse)); + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + if (pmc) { + if (pmc_inuse & (1 << (pmc - 1))) + return -1; + pmc_inuse |= 1 << (pmc - 1); + /* count 1/2/5/6 vs 3/4/7/8 use */ + ++pmc_grp_use[((pmc - 1) >> 1) & 1]; + } + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + if (unit) { + if (unit > PM_LASTUNIT) + return -1; + if (!pmc) + ++pmc_grp_use[byte & 1]; + if (busbyte[byte] && busbyte[byte] != unit) + return -1; + busbyte[byte] = unit; + unituse[unit] = 1; + } + } + if (pmc_grp_use[0] > 4 || pmc_grp_use[1] > 4) + return -1; + + /* + * Assign resources and set multiplexer selects. + * + * PM_ISU can go either on TTM0 or TTM1, but that's the only + * choice we have to deal with. + */ + if (unituse[PM_ISU] & + (unituse[PM_FPU] | unituse[PM_IFU] | unituse[PM_VPU])) + unitmap[PM_ISU] = 2 | 4; /* move ISU to TTM1 */ + /* Set TTM[01]SEL fields. */ + ttmuse[0] = ttmuse[1] = 0; + for (i = PM_FPU; i <= PM_STS; ++i) { + if (!unituse[i]) + continue; + ttm = unitmap[i]; + ++ttmuse[(ttm >> 2) & 1]; + mmcr1 |= (u64)(ttm & ~4) << MMCR1_TTM1SEL_SH; + } + /* Check only one unit per TTMx */ + if (ttmuse[0] > 1 || ttmuse[1] > 1) + return -1; + + /* Set byte lane select fields and TTM3SEL. */ + for (byte = 0; byte < 4; ++byte) { + unit = busbyte[byte]; + if (!unit) + continue; + if (unit <= PM_STS) + ttm = (unitmap[unit] >> 2) & 1; + else if (unit == PM_LSU0) + ttm = 2; + else { + ttm = 3; + if (unit == PM_LSU1L && byte >= 2) + mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte); + } + mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte); + } + + /* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */ + memset(pmcsel, 0x8, sizeof(pmcsel)); /* 8 means don't count */ + for (i = 0; i < n_ev; ++i) { + pmc = (event[i] >> PM_PMC_SH) & PM_PMC_MSK; + unit = (event[i] >> PM_UNIT_SH) & PM_UNIT_MSK; + byte = (event[i] >> PM_BYTE_SH) & PM_BYTE_MSK; + psel = event[i] & PM_PMCSEL_MSK; + if (!pmc) { + /* Bus event or any-PMC direct event */ + if (unit) + psel |= 0x10 | ((byte & 2) << 2); + else + psel |= 8; + for (pmc = 0; pmc < 8; ++pmc) { + if (pmc_inuse & (1 << pmc)) + continue; + grp = (pmc >> 1) & 1; + if (unit) { + if (grp == (byte & 1)) + break; + } else if (pmc_grp_use[grp] < 4) { + ++pmc_grp_use[grp]; + break; + } + } + pmc_inuse |= 1 << pmc; + } else { + /* Direct event */ + --pmc; + if (psel == 0 && (byte & 2)) + /* add events on higher-numbered bus */ + mmcr1 |= 1ull << mmcr1_adder_bits[pmc]; + } + pmcsel[pmc] = psel; + hwc[i] = pmc; + spcsel = (event[i] >> PM_SPCSEL_SH) & PM_SPCSEL_MSK; + mmcr1 |= spcsel; + if (p970_marked_instr_event(event[i])) + mmcra |= MMCRA_SAMPLE_ENABLE; + } + for (pmc = 0; pmc < 2; ++pmc) + mmcr0 |= pmcsel[pmc] << (MMCR0_PMC1SEL_SH - 7 * pmc); + for (; pmc < 8; ++pmc) + mmcr1 |= (u64)pmcsel[pmc] << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2)); + if (pmc_inuse & 1) + mmcr0 |= MMCR0_PMC1CE; + if (pmc_inuse & 0xfe) + mmcr0 |= MMCR0_PMCjCE; + + mmcra |= 0x2000; /* mark only one IOP per PPC instruction */ + + /* Return MMCRx values */ + mmcr[0] = mmcr0; + mmcr[1] = mmcr1; + mmcr[2] = mmcra; + return 0; +} + +static void p970_disable_pmc(unsigned int pmc, u64 mmcr[]) +{ + int shift, i; + + if (pmc <= 1) { + shift = MMCR0_PMC1SEL_SH - 7 * pmc; + i = 0; + } else { + shift = MMCR1_PMC3SEL_SH - 5 * (pmc - 2); + i = 1; + } + /* + * Setting the PMCxSEL field to 0x08 disables PMC x. + */ + mmcr[i] = (mmcr[i] & ~(0x1fUL << shift)) | (0x08UL << shift); +} + +static int ppc970_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = 7, + [PERF_COUNT_HW_INSTRUCTIONS] = 1, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x8810, /* PM_LD_REF_L1 */ + [PERF_COUNT_HW_CACHE_MISSES] = 0x3810, /* PM_LD_MISS_L1 */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x431, /* PM_BR_ISSUED */ + [PERF_COUNT_HW_BRANCH_MISSES] = 0x327, /* PM_GRP_BR_MPRED */ +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x8810, 0x3810 }, + [C(OP_WRITE)] = { 0x7810, 0x813 }, + [C(OP_PREFETCH)] = { 0x731, 0 }, + }, + [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { 0, 0 }, + }, + [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0 }, + [C(OP_WRITE)] = { 0, 0 }, + [C(OP_PREFETCH)] = { 0x733, 0 }, + }, + [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x704 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0, 0x700 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, + [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */ + [C(OP_READ)] = { 0x431, 0x327 }, + [C(OP_WRITE)] = { -1, -1 }, + [C(OP_PREFETCH)] = { -1, -1 }, + }, +}; + +struct power_pmu ppc970_pmu = { + .n_counter = 8, + .max_alternatives = 2, + .add_fields = 0x001100005555ull, + .test_adder = 0x013300000000ull, + .compute_mmcr = p970_compute_mmcr, + .get_constraint = p970_get_constraint, + .get_alternatives = p970_get_alternatives, + .disable_pmc = p970_disable_pmc, + .n_generic = ARRAY_SIZE(ppc970_generic_events), + .generic_events = ppc970_generic_events, + .cache_events = &ppc970_cache_events, +}; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 9057335fdc616ce607f76b2dc7e099965ce49e5e..2cf915e51e7e9e7c7ad6202e0d287187b8a313ed 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -41,6 +41,12 @@ 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/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 76993941cac95a12f7c95972eb55f9e0b00fe769..5beffc8f481e7c6d725b63c82f3aebeed2bde9c2 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -170,6 +171,8 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, die("Weird page fault", regs, SIGSEGV); } + perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address); + /* When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the * kernel and should generate an OOPS. Unfortunately, in the case of an @@ -309,6 +312,8 @@ good_area: } if (ret & VM_FAULT_MAJOR) { current->maj_flt++; + perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, + regs, address); #ifdef CONFIG_PPC_SMLPAR if (firmware_has_feature(FW_FEATURE_CMO)) { preempt_disable(); @@ -316,8 +321,11 @@ good_area: preempt_enable(); } #endif - } else + } else { current->min_flt++; + perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, + regs, address); + } up_read(&mm->mmap_sem); return 0; diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 25f8a9c2ba1a601aa09cfc5829472fcf0c1c4f72..cca6b4fc719a2a3eb3b7d774c5c2c4d2329e8c8d 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -1,6 +1,7 @@ config PPC64 bool "64-bit kernel" default n + select HAVE_PERF_COUNTERS help This option selects whether a 32-bit or a 64-bit kernel will be built. diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c index 80b513449f4c44d3c98915efe233c01caa382f4d..be3581a8c294c8de4d083b1b2c5710381a35c2d9 100644 --- a/arch/powerpc/platforms/pseries/xics.c +++ b/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 void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask) +static int xics_set_affinity(unsigned int virq, const struct cpumask *cpumask) { unsigned int irq; int status; @@ -342,14 +342,14 @@ static void 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; + return -1; 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; + return -1; } /* @@ -363,7 +363,7 @@ static void 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; + return -1; } status = rtas_call(ibm_set_xive, 3, 1, NULL, @@ -372,8 +372,10 @@ static void 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; + return -1; } + + return 0; } static struct irq_chip xics_pic_direct = { diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index 9e105cbc5e5f4c3fb3f10654485d009cb37bb111..a4779912a5caa4d45eacedd3b584d33a2537fafd 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/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_hardsect_size(bank->disk->queue, AXON_RAM_SECTOR_SIZE); + blk_queue_logical_block_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/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index bbee441ae867c2e2d420de7775b815ed8c551428..9c3af5045495bb67c0259998a39dd641c65e47ea 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -807,7 +807,7 @@ static void mpic_end_ipi(unsigned int irq) #endif /* CONFIG_SMP */ -void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask) +int 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); @@ -824,6 +824,8 @@ void 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/arch/powerpc/sysdev/mpic.h b/arch/powerpc/sysdev/mpic.h index 3cef2af10f4254daea1ff69769117ffb1f8a23b3..eff433c322a0c55632b7d413acfddc18ed5cbaa8 100644 --- a/arch/powerpc/sysdev/mpic.h +++ b/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 void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask); +extern int mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask); #endif /* _POWERPC_SYSDEV_MPIC_H */ diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 54ea39f96ecdf17f04a078f51a1c20d45003897b..a27d0d5a6f8689fa81f558686cad2f378487be42 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -13,6 +13,8 @@ #ifndef ASM_KVM_HOST_H #define ASM_KVM_HOST_H +#include +#include #include #include #include @@ -210,7 +212,8 @@ struct kvm_vcpu_arch { s390_fp_regs guest_fpregs; unsigned int guest_acrs[NUM_ACRS]; struct kvm_s390_local_interrupt local_int; - struct timer_list ckc_timer; + struct hrtimer ckc_timer; + struct tasklet_struct tasklet; union { cpuid_t cpu_id; u64 stidp_data; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 9d19803111bab26d8021d3aaf2f0f028092f8c8b..98997ccba50151dbf7965831b062e5f74c44fb93 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -154,17 +154,25 @@ 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) { - 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; + 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; } static int handle_instruction(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 0189356fe2098cb3f6ddd61434da623b8a7c9cfa..f04f5301b1b42fdd06207c93a84bd6568594cd72 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -12,6 +12,8 @@ #include #include +#include +#include #include #include #include "kvm-s390.h" @@ -299,13 +301,13 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) } if ((!rc) && atomic_read(&fi->active)) { - spin_lock_bh(&fi->lock); + spin_lock(&fi->lock); list_for_each_entry(inti, &fi->list, list) if (__interrupt_is_deliverable(vcpu, inti)) { rc = 1; break; } - spin_unlock_bh(&fi->lock); + spin_unlock(&fi->lock); } if ((!rc) && (vcpu->arch.sie_block->ckc < @@ -318,6 +320,12 @@ 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; @@ -355,14 +363,12 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) return 0; } - sltime = (vcpu->arch.sie_block->ckc - now) / (0xf4240000ul / HZ) + 1; + sltime = ((vcpu->arch.sie_block->ckc - now)*125)>>9; - vcpu->arch.ckc_timer.expires = jiffies + sltime; - - add_timer(&vcpu->arch.ckc_timer); - VCPU_EVENT(vcpu, 5, "enabled wait timer:%llx jiffies", sltime); + 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); no_timer: - spin_lock_bh(&vcpu->arch.local_int.float_int->lock); + spin_lock(&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) && @@ -371,33 +377,46 @@ no_timer: !signal_pending(current)) { set_current_state(TASK_INTERRUPTIBLE); spin_unlock_bh(&vcpu->arch.local_int.lock); - spin_unlock_bh(&vcpu->arch.local_int.float_int->lock); + spin_unlock(&vcpu->arch.local_int.float_int->lock); vcpu_put(vcpu); schedule(); vcpu_load(vcpu); - spin_lock_bh(&vcpu->arch.local_int.float_int->lock); + spin_lock(&vcpu->arch.local_int.float_int->lock); spin_lock_bh(&vcpu->arch.local_int.lock); } __unset_cpu_idle(vcpu); __set_current_state(TASK_RUNNING); remove_wait_queue(&vcpu->wq, &wait); spin_unlock_bh(&vcpu->arch.local_int.lock); - spin_unlock_bh(&vcpu->arch.local_int.float_int->lock); - del_timer(&vcpu->arch.ckc_timer); + spin_unlock(&vcpu->arch.local_int.float_int->lock); + hrtimer_try_to_cancel(&vcpu->arch.ckc_timer); return 0; } -void kvm_s390_idle_wakeup(unsigned long data) +void kvm_s390_tasklet(unsigned long parm) { - struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data; + struct kvm_vcpu *vcpu = (struct kvm_vcpu *) parm; - spin_lock_bh(&vcpu->arch.local_int.lock); + spin_lock(&vcpu->arch.local_int.lock); vcpu->arch.local_int.timer_due = 1; if (waitqueue_active(&vcpu->arch.local_int.wq)) wake_up_interruptible(&vcpu->arch.local_int.wq); - spin_unlock_bh(&vcpu->arch.local_int.lock); + spin_unlock(&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) { @@ -436,7 +455,7 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) if (atomic_read(&fi->active)) { do { deliver = 0; - spin_lock_bh(&fi->lock); + spin_lock(&fi->lock); list_for_each_entry_safe(inti, n, &fi->list, list) { if (__interrupt_is_deliverable(vcpu, inti)) { list_del(&inti->list); @@ -447,7 +466,7 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) } if (list_empty(&fi->list)) atomic_set(&fi->active, 0); - spin_unlock_bh(&fi->lock); + spin_unlock(&fi->lock); if (deliver) { __do_deliver_interrupt(vcpu, inti); kfree(inti); @@ -512,7 +531,7 @@ int kvm_s390_inject_vm(struct kvm *kvm, mutex_lock(&kvm->lock); fi = &kvm->arch.float_int; - spin_lock_bh(&fi->lock); + spin_lock(&fi->lock); list_add_tail(&inti->list, &fi->list); atomic_set(&fi->active, 1); sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS); @@ -529,7 +548,7 @@ 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_bh(&fi->lock); + spin_unlock(&fi->lock); mutex_unlock(&kvm->lock); return 0; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f4d56e9939c90949c1e886eaabf6cc7d35cab858..10bccd1f8aee58a33220bfbc07aa3b3452b1b3e7 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -195,6 +196,10 @@ out_nokvm: 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); @@ -283,8 +288,10 @@ 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; - setup_timer(&vcpu->arch.ckc_timer, kvm_s390_idle_wakeup, - (unsigned long) vcpu); + 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; get_cpu_id(&vcpu->arch.cpu_id); vcpu->arch.cpu_id.version = 0xff; return 0; @@ -307,19 +314,21 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.sie_block->icpua = id; BUG_ON(!kvm->arch.sca); - BUG_ON(kvm->arch.sca->cpu[id].sda); - kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block; + 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 */ vcpu->arch.sie_block->scaoh = (__u32)(((__u64)kvm->arch.sca) >> 32); vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca; spin_lock_init(&vcpu->arch.local_int.lock); INIT_LIST_HEAD(&vcpu->arch.local_int.list); vcpu->arch.local_int.float_int = &kvm->arch.float_int; - spin_lock_bh(&kvm->arch.float_int.lock); + spin_lock(&kvm->arch.float_int.lock); kvm->arch.float_int.local_int[id] = &vcpu->arch.local_int; init_waitqueue_head(&vcpu->arch.local_int.wq); vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags; - spin_unlock_bh(&kvm->arch.float_int.lock); + spin_unlock(&kvm->arch.float_int.lock); rc = kvm_vcpu_init(vcpu, kvm, id); if (rc) @@ -478,6 +487,12 @@ 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); @@ -657,6 +672,8 @@ 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. @@ -664,7 +681,7 @@ 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) + if (mem->slot || kvm->arch.guest_memsize) return -EINVAL; if (mem->guest_phys_addr) @@ -676,15 +693,39 @@ 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; - /* 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. */ + /* 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); + } + } 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/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 00bbe69b78da97757b8da8840d0f55977a7aca8c..748fee872323f3cd996bfda466e01cd54fc8e169 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -14,6 +14,7 @@ #ifndef ARCH_S390_KVM_S390_H #define ARCH_S390_KVM_S390_H +#include #include #include @@ -41,7 +42,8 @@ static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu) } int kvm_s390_handle_wait(struct kvm_vcpu *vcpu); -void kvm_s390_idle_wakeup(unsigned long data); +enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer); +void kvm_s390_tasklet(unsigned long parm); 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/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 4b88834b8dd8bd4be94de20d5bf248b8f195bcd6..93ecd06e1a749fc866177c5bd5c6bcdd6ae82e81 100644 --- a/arch/s390/kvm/priv.c +++ b/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_bh(&fi->lock); + spin_lock(&fi->lock); for (n = 0; n < KVM_MAX_VCPUS; n++) if (fi->local_int[n]) cpus++; - spin_unlock_bh(&fi->lock); + spin_unlock(&fi->lock); /* deal with other level 3 hypervisors */ if (stsi(mem, 3, 2, 2) == -ENOSYS) diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index f27dbedf086600280964164b207851c5f2f98dd2..36678835034d9f49a748f448fd943073e9974564 100644 --- a/arch/s390/kvm/sigp.c +++ b/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_bh(&fi->lock); + spin_lock(&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_bh(&fi->lock); + spin_unlock(&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_bh(&fi->lock); + spin_lock(&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_bh(&fi->lock); + spin_unlock(&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_bh(&fi->lock); + spin_lock(&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_bh(&fi->lock); + spin_unlock(&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_bh(&fi->lock); + spin_lock(&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_bh(&fi->lock); + spin_unlock(&fi->lock); return rc; } diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index e7390dd0283dde02275de43a88f726c36bfff47e..586cd045e2db213df61a3a9a46a3aaf2ecd08b8d 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -15,6 +15,7 @@ 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 @@ -74,14 +75,18 @@ config GENERIC_IOMAP bool config GENERIC_TIME - def_bool n + def_bool y config GENERIC_CLOCKEVENTS - def_bool n + def_bool y 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 @@ -112,6 +117,12 @@ 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 @@ -157,13 +168,14 @@ 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 @@ -177,6 +189,7 @@ config CPU_SH4AL_DSP config CPU_SH5 bool select CPU_HAS_FPU + select SYS_SUPPORTS_TMU config CPU_SHX2 bool @@ -210,27 +223,32 @@ 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. @@ -283,6 +301,7 @@ 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. @@ -290,6 +309,7 @@ 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. @@ -347,6 +367,16 @@ 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 @@ -442,48 +472,26 @@ source "arch/sh/boards/Kconfig" menu "Timer and clock configuration" -config SH_TMU - bool "TMU timer support" - depends on CPU_SH3 || CPU_SH4 +config SH_TIMER_TMU + bool "TMU timer driver" + depends on SYS_SUPPORTS_TMU default y - select GENERIC_TIME - select GENERIC_CLOCKEVENTS help - This enables the use of the TMU as the system timer. + This enables the build of the TMU timer driver. -config SH_CMT - bool "CMT timer support" - depends on SYS_SUPPORTS_CMT && CPU_SH2 +config SH_TIMER_CMT + bool "CMT timer driver" + depends on SYS_SUPPORTS_CMT default y help - This enables the use of the CMT as the system timer. + This enables build of the CMT timer driver. -# -# 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 +config SH_TIMER_MTU2 + bool "MTU2 timer driver" + depends on SYS_SUPPORTS_MTU2 default y help - 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" + This enables build of the MTU2 timer driver. config SH_PCLK_FREQ int "Peripheral clock frequency (in Hz)" @@ -494,7 +502,7 @@ 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_SH7786 || CPU_SUBTYPE_SH7724 default "60000000" if CPU_SUBTYPE_SH7751 || CPU_SUBTYPE_SH7751R default "66000000" if CPU_SUBTYPE_SH4_202 default "50000000" @@ -503,6 +511,13 @@ 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 @@ -663,27 +678,54 @@ 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 "Zero page offset" - default "0x00004000" if SH_SH03 - default "0x00010000" if PAGE_SIZE_64KB + hex + default "0x00010000" if PAGE_SIZE_64KB || SH_RTS7751R2D || \ + SH_7751_SOLUTION_ENGINE + default "0x00004000" if PAGE_SIZE_16KB || SH_SH03 default "0x00002000" if PAGE_SIZE_8KB default "0x00001000" help This sets the default offset of zero page. config BOOT_LINK_OFFSET - hex "Link address offset for booting" + 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 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/arch/sh/Kconfig.cpu b/arch/sh/Kconfig.cpu index c7d704381a6d5425548751ed4874580a0e3c1ab9..cd6e3ea598d5b8d028720fb806ddb82a39b2e863 100644 --- a/arch/sh/Kconfig.cpu +++ b/arch/sh/Kconfig.cpu @@ -76,11 +76,6 @@ 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 @@ -101,9 +96,6 @@ 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/arch/sh/Kconfig.debug b/arch/sh/Kconfig.debug index 0d62681f72a092830134b0d5a80186fede6e59e0..8179cc9be9a4a343ab5af583cbfe52792067aa07 100644 --- a/arch/sh/Kconfig.debug +++ b/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 + depends on DEBUG_KERNEL && SUPERH32 && BROKEN help If you say Y here the kernel will use separate kernel stacks for handling hard and soft interrupts. This can help avoid @@ -122,27 +122,8 @@ 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/arch/sh/Makefile b/arch/sh/Makefile index bece1f7535f2008c9f3199753e2241f1f73f9fb2..75d049b03f7e04231de0525ba6b57e3779fe2984 100644 --- a/arch/sh/Makefile +++ b/arch/sh/Makefile @@ -70,9 +70,6 @@ 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 $(CONFIG_COMPILE_OPTIONS) | sed -e 's/"//g') - OBJCOPYFLAGS := -O binary -R .note -R .note.gnu.build-id -R .comment \ -R .stab -R .stabstr -S @@ -85,7 +82,6 @@ defaultimage-$(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) # @@ -93,26 +89,38 @@ KBUILD_IMAGE := $(defaultimage-y) # error messages during linking. # ifdef CONFIG_SUPERH32 -UTS_MACHINE := sh -LDFLAGS_vmlinux += -e _stext +UTS_MACHINE := sh +BITS := 32 +LDFLAGS_vmlinux += -e _stext +KBUILD_DEFCONFIG := shx3_defconfig else -UTS_MACHINE := sh64 -LDFLAGS_vmlinux += --defsym phys_stext=_stext-$(CONFIG_PAGE_OFFSET) \ - --defsym phys_stext_shmedia=phys_stext+1 \ - -e phys_stext_shmedia +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- $(UTS_MACHINE)-unknown-linux-gnu-) + endif endif ifdef CONFIG_CPU_LITTLE_ENDIAN -LDFLAGS_vmlinux += --defsym 'jiffies=jiffies_64' +ld-bfd := elf32-$(UTS_MACHINE)-linux +LDFLAGS_vmlinux += --defsym 'jiffies=jiffies_64' --oformat $(ld-bfd) LDFLAGS += -EL else -LDFLAGS_vmlinux += --defsym 'jiffies=jiffies_64+4' +ld-bfd := elf32-$(UTS_MACHINE)big-linux +LDFLAGS_vmlinux += --defsym 'jiffies=jiffies_64+4' --oformat $(ld-bfd) LDFLAGS += -EB endif -head-y := arch/sh/kernel/init_task.o -head-$(CONFIG_SUPERH32) += arch/sh/kernel/head_32.o -head-$(CONFIG_SUPERH64) += arch/sh/kernel/head_64.o +export ld-bfd BITS + +head-y := arch/sh/kernel/init_task.o arch/sh/kernel/head_$(BITS).o core-y += arch/sh/kernel/ arch/sh/mm/ arch/sh/boards/ core-$(CONFIG_SH_FPU_EMU) += arch/sh/math-emu/ @@ -193,10 +201,11 @@ zImage uImage uImage.srec vmlinux.srec: vmlinux compressed: zImage -archprepare: maketools arch/sh/lib64/syscalltab.h +archprepare: maketools archclean: $(Q)$(MAKE) $(clean)=$(boot) + $(Q)$(MAKE) $(clean)=arch/sh/kernel/vsyscall define archhelp @echo '* zImage - Compressed kernel image' @@ -205,34 +214,4 @@ define archhelp @echo ' uImage.srec - Create an S-record for U-Boot' endef -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 +CLEAN_FILES += include/asm-sh/machtypes.h diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig index dcc1af8a2cfe6428c00f0b4f400ffb27cb675ca1..1c91b1f565d5444bf4775439aff906e822fa5cb6 100644 --- a/arch/sh/boards/Kconfig +++ b/arch/sh/boards/Kconfig @@ -46,6 +46,15 @@ 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 @@ -121,7 +130,7 @@ config SH_RTS7751R2D bool "RTS7751R2D" depends on CPU_SUBTYPE_SH7751R select SYS_SUPPORTS_PCI - select IO_TRAPPED + select IO_TRAPPED if MMU help Select RTS7751R2D if configuring for a Renesas Technology Sales SH-Graphics board. @@ -145,13 +154,13 @@ config SH_HIGHLANDER bool "Highlander" depends on CPU_SUBTYPE_SH7780 || CPU_SUBTYPE_SH7785 select SYS_SUPPORTS_PCI - select IO_TRAPPED + select IO_TRAPPED if MMU config SH_SH7785LCR bool "SH7785LCR" depends on CPU_SUBTYPE_SH7785 select SYS_SUPPORTS_PCI - select IO_TRAPPED + select IO_TRAPPED if MMU config SH_SH7785LCR_29BIT_PHYSMAPS bool "SH7785LCR 29bit physmaps" diff --git a/arch/sh/boards/board-ap325rxa.c b/arch/sh/boards/board-ap325rxa.c index f2a29641b6a326cc857c8334383717dffc70aba7..1c4d83ef2a4724e10da98bd42d58941d4a03ba15 100644 --- a/arch/sh/boards/board-ap325rxa.c +++ b/arch/sh/boards/board-ap325rxa.c @@ -535,6 +535,18 @@ 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/arch/sh/boards/board-sh7785lcr.c b/arch/sh/boards/board-sh7785lcr.c index 6f94f17adc467dd00d13aaa20ef5891b2ee064ed..7be56fb06c1f0a7aecbd95ee47f0fa805535518e 100644 --- a/arch/sh/boards/board-sh7785lcr.c +++ b/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 @@ -19,8 +19,12 @@ #include #include #include -#include +#include +#include #include +#include +#include +#include /* * NOTE: This board has 2 physical memory maps. @@ -273,6 +277,20 @@ 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; @@ -303,12 +321,34 @@ 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/arch/sh/boards/mach-cayman/Makefile b/arch/sh/boards/mach-cayman/Makefile index cafe1ac3b29c288570e0ac5cd14743b35174e7fe..00fa3eaecb1be7a5e8bcad1ea3bb850095a0149c 100644 --- a/arch/sh/boards/mach-cayman/Makefile +++ b/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 +obj-y := setup.o irq.o panic.o diff --git a/arch/sh/boards/mach-cayman/irq.c b/arch/sh/boards/mach-cayman/irq.c index da62ad516994bc74aecd4823502d682c21ee5660..33f77085631937fef9d1489590980016dd0f2d15 100644 --- a/arch/sh/boards/mach-cayman/irq.c +++ b/arch/sh/boards/mach-cayman/irq.c @@ -142,26 +142,11 @@ 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 = onchip_remap(EPLD_BASE, 1024, "EPLD"); + epld_virt = (unsigned long)ioremap_nocache(EPLD_BASE, 1024); if (!epld_virt) { printk(KERN_ERR "Cayman IRQ: Unable to remap EPLD\n"); return; diff --git a/arch/sh/boards/mach-cayman/panic.c b/arch/sh/boards/mach-cayman/panic.c new file mode 100644 index 0000000000000000000000000000000000000000..d1e67306d07c068654b046fd58bbc5f46847f4c3 --- /dev/null +++ b/arch/sh/boards/mach-cayman/panic.c @@ -0,0 +1,49 @@ +/* + * 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/arch/sh/boards/mach-cayman/setup.c b/arch/sh/boards/mach-cayman/setup.c index e7f9cc5f2ff11e7d350dbb067d412d4b39089fbd..7e8216ac31bda3cf263faad31ab3105e7afd0b0f 100644 --- a/arch/sh/boards/mach-cayman/setup.c +++ b/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 = onchip_remap(SMSC_SUPERIO_BASE, 1024, "SMSC SuperIO"); + smsc_superio_virt = (unsigned long)ioremap_nocache(SMSC_SUPERIO_BASE, 1024); if (!smsc_superio_virt) { panic("Unable to remap SMSC SuperIO\n"); } diff --git a/arch/sh/boards/mach-dreamcast/setup.c b/arch/sh/boards/mach-dreamcast/setup.c index d1bee4884cd667da313e0105e490cd2b5a5e6750..ebe99227d4e6674704b96e4c03c7e699401b6194 100644 --- a/arch/sh/boards/mach-dreamcast/setup.c +++ b/arch/sh/boards/mach-dreamcast/setup.c @@ -30,7 +30,6 @@ 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) @@ -51,11 +50,6 @@ 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/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c index 1ee1de0bc1c3c93ab627a34ddb4acec3409f94f7..6ed401cd3156af429569bf197c99fc1cbfe861e6 100644 --- a/arch/sh/boards/mach-migor/setup.c +++ b/arch/sh/boards/mach-migor/setup.c @@ -584,3 +584,22 @@ 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/arch/sh/boards/mach-r2d/setup.c b/arch/sh/boards/mach-r2d/setup.c index c585be00956ea9a8d541656081ac80a2f86ae3f4..a625ecb93e47ee55a6300c87986c17445ad9f0a3 100644 --- a/arch/sh/boards/mach-r2d/setup.c +++ b/arch/sh/boards/mach-r2d/setup.c @@ -10,6 +10,9 @@ */ #include #include +#include +#include +#include #include #include #include @@ -181,6 +184,50 @@ 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, @@ -203,6 +250,9 @@ 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/arch/sh/boards/mach-se/7724/Makefile b/arch/sh/boards/mach-se/7724/Makefile new file mode 100644 index 0000000000000000000000000000000000000000..349cbd6ce82d9574637a08072abf8249771997d5 --- /dev/null +++ b/arch/sh/boards/mach-se/7724/Makefile @@ -0,0 +1,10 @@ +# +# 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/arch/sh/boards/mach-se/7724/irq.c b/arch/sh/boards/mach-se/7724/irq.c new file mode 100644 index 0000000000000000000000000000000000000000..f76cf3b49f2375f458b105aa78517373f971c0ce --- /dev/null +++ b/arch/sh/boards/mach-se/7724/irq.c @@ -0,0 +1,139 @@ +/* + * 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/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c new file mode 100644 index 0000000000000000000000000000000000000000..9cd04bd558b88930583774a29837d5aa8424518d --- /dev/null +++ b/arch/sh/boards/mach-se/7724/setup.c @@ -0,0 +1,448 @@ +/* + * 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
); if section is defined, else just show +# the command. + +[macros] +(?su)[\\]?(?Plinkperf):(?P\S*?)\[(?P.*?)\]= + +[attributes] +asterisk=* +plus=+ +caret=^ +startsb=[ +endsb=] +tilde=~ + +ifdef::backend-docbook[] +[linkperf-inlinemacro] +{0%{target}} +{0#} +{0#{target}{0}} +{0#} +endif::backend-docbook[] + +ifdef::backend-docbook[] +ifndef::perf-asciidoc-no-roff[] +# "unbreak" docbook-xsl v1.68 for manpages. v1.69 works with or without this. +# v1.72 breaks with this because it replaces dots not in roff requests. +[listingblock] +{title} + +ifdef::doctype-manpage[] + .ft C +endif::doctype-manpage[] +| +ifdef::doctype-manpage[] + .ft +endif::doctype-manpage[] + +{title#} +endif::perf-asciidoc-no-roff[] + +ifdef::perf-asciidoc-no-roff[] +ifdef::doctype-manpage[] +# The following two small workarounds insert a simple paragraph after screen +[listingblock] +{title} + +| + +{title#} + +[verseblock] +{title} +{title%} +{title#} +| + +{title#} +{title%} +endif::doctype-manpage[] +endif::perf-asciidoc-no-roff[] +endif::backend-docbook[] + +ifdef::doctype-manpage[] +ifdef::backend-docbook[] +[header] +template::[header-declarations] + + +{mantitle} +{manvolnum} +perf +{perf_version} +perf Manual + + + {manname} + {manpurpose} + +endif::backend-docbook[] +endif::doctype-manpage[] + +ifdef::backend-xhtml11[] +[linkperf-inlinemacro] +{target}{0?({0})} +endif::backend-xhtml11[] diff --git a/tools/perf/Documentation/manpage-1.72.xsl b/tools/perf/Documentation/manpage-1.72.xsl new file mode 100644 index 0000000000000000000000000000000000000000..b4d315cb8c4792c25cfad7892e056356543e85e1 --- /dev/null +++ b/tools/perf/Documentation/manpage-1.72.xsl @@ -0,0 +1,14 @@ + + + + + + +▓ +⌂ + + diff --git a/tools/perf/Documentation/manpage-base.xsl b/tools/perf/Documentation/manpage-base.xsl new file mode 100644 index 0000000000000000000000000000000000000000..a264fa616093cf4e28a1080dd76747b008859e19 --- /dev/null +++ b/tools/perf/Documentation/manpage-base.xsl @@ -0,0 +1,35 @@ + + + + + + + + + + + + + + sp + + + + + + + + br + + + diff --git a/tools/perf/Documentation/manpage-bold-literal.xsl b/tools/perf/Documentation/manpage-bold-literal.xsl new file mode 100644 index 0000000000000000000000000000000000000000..608eb5df628141eeeb67e101e732263c34257b61 --- /dev/null +++ b/tools/perf/Documentation/manpage-bold-literal.xsl @@ -0,0 +1,17 @@ + + + + + + + fB + + + fR + + + diff --git a/tools/perf/Documentation/manpage-normal.xsl b/tools/perf/Documentation/manpage-normal.xsl new file mode 100644 index 0000000000000000000000000000000000000000..a48f5b11f3dcc9227131d3a5caf1de4f857f0b28 --- /dev/null +++ b/tools/perf/Documentation/manpage-normal.xsl @@ -0,0 +1,13 @@ + + + + + + +\ +. + + diff --git a/tools/perf/Documentation/manpage-suppress-sp.xsl b/tools/perf/Documentation/manpage-suppress-sp.xsl new file mode 100644 index 0000000000000000000000000000000000000000..a63c7632a87d47ea1afb65f2ca1286685823d250 --- /dev/null +++ b/tools/perf/Documentation/manpage-suppress-sp.xsl @@ -0,0 +1,21 @@ + + + + + + + + + + + + + + + diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt new file mode 100644 index 0000000000000000000000000000000000000000..c9dcade068312d843904107d51beb9d9497f2c4a --- /dev/null +++ b/tools/perf/Documentation/perf-annotate.txt @@ -0,0 +1,29 @@ +perf-annotate(1) +============== + +NAME +---- +perf-annotate - Read perf.data (created by perf record) and display annotated code + +SYNOPSIS +-------- +[verse] +'perf annotate' [-i | --input=file] symbol_name + +DESCRIPTION +----------- +This command reads the input file and displays an annotated version of the +code. If the object file has debug symbols then the source code will be +displayed alongside assembly code. + +If there is no debug info in the object, then annotated assembly is displayed. + +OPTIONS +------- +-i:: +--input=:: + Input file name. (default: perf.data) + +SEE ALSO +-------- +linkperf:perf-record[1] diff --git a/tools/perf/Documentation/perf-help.txt b/tools/perf/Documentation/perf-help.txt new file mode 100644 index 0000000000000000000000000000000000000000..514391818d1f1a133189f8a140cbdea71779396e --- /dev/null +++ b/tools/perf/Documentation/perf-help.txt @@ -0,0 +1,38 @@ +perf-help(1) +============ + +NAME +---- +perf-help - display help information about perf + +SYNOPSIS +-------- +'perf help' [-a|--all] [COMMAND] + +DESCRIPTION +----------- + +With no options and no COMMAND given, the synopsis of the 'perf' +command and a list of the most commonly used perf commands are printed +on the standard output. + +If the option '--all' or '-a' is given, then all available commands are +printed on the standard output. + +If a perf command is named, a manual page for that command is brought +up. The 'man' program is used by default for this purpose, but this +can be overridden by other options or configuration variables. + +Note that `perf --help ...` is identical to `perf help ...` because the +former is internally converted into the latter. + +OPTIONS +------- +-a:: +--all:: + Prints all the available commands on the standard output. This + option supersedes any other option. + +PERF +---- +Part of the linkperf:perf[1] suite diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt new file mode 100644 index 0000000000000000000000000000000000000000..8290b94226687f8f3d4b8700419519879bedbd78 --- /dev/null +++ b/tools/perf/Documentation/perf-list.txt @@ -0,0 +1,25 @@ +perf-list(1) +============ + +NAME +---- +perf-list - List all symbolic event types + +SYNOPSIS +-------- +[verse] +'perf list' + +DESCRIPTION +----------- +This command displays the symbolic event types which can be selected in the +various perf commands with the -e option. + +OPTIONS +------- +None + +SEE ALSO +-------- +linkperf:perf-stat[1], linkperf:perf-top[1], +linkperf:perf-record[1] diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt new file mode 100644 index 0000000000000000000000000000000000000000..1dbc1eeb4c01259552e17372f3e6f279195b22d9 --- /dev/null +++ b/tools/perf/Documentation/perf-record.txt @@ -0,0 +1,42 @@ +perf-record(1) +============== + +NAME +---- +perf-record - Run a command and record its profile into perf.data + +SYNOPSIS +-------- +[verse] +'perf record' [-e | --event=EVENT] [-l] [-a] +'perf record' [-e | --event=EVENT] [-l] [-a] -- [] + +DESCRIPTION +----------- +This command runs a command and gathers a performance counter profile +from it, into perf.data - without displaying anything. + +This file can then be inspected later on, using 'perf report'. + + +OPTIONS +------- +...:: + Any command you can specify in a shell. + +-e:: +--event=:: + Select the PMU event. Selection can be a symbolic event name + (use 'perf list' to list all events) or a raw PMU + event (eventsel+umask) in the form of rNNN where NNN is a + hexadecimal event descriptor. + +-a:: + system-wide collection + +-l:: + scale counter values + +SEE ALSO +-------- +linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt new file mode 100644 index 0000000000000000000000000000000000000000..52d3fc6846a976e9947b7176a520273e639dfe6d --- /dev/null +++ b/tools/perf/Documentation/perf-report.txt @@ -0,0 +1,26 @@ +perf-report(1) +============== + +NAME +---- +perf-report - Read perf.data (created by perf record) and display the profile + +SYNOPSIS +-------- +[verse] +'perf report' [-i | --input=file] + +DESCRIPTION +----------- +This command displays the performance counter profile information recorded +via perf report. + +OPTIONS +------- +-i:: +--input=:: + Input file name. (default: perf.data) + +SEE ALSO +-------- +linkperf:perf-stat[1] diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt new file mode 100644 index 0000000000000000000000000000000000000000..c368a72721d785b3836fe5c1e2a37bdcfc3082f5 --- /dev/null +++ b/tools/perf/Documentation/perf-stat.txt @@ -0,0 +1,66 @@ +perf-stat(1) +============ + +NAME +---- +perf-stat - Run a command and gather performance counter statistics + +SYNOPSIS +-------- +[verse] +'perf stat' [-e | --event=EVENT] [-l] [-a] +'perf stat' [-e | --event=EVENT] [-l] [-a] -- [] + +DESCRIPTION +----------- +This command runs a command and gathers performance counter statistics +from it. + + +OPTIONS +------- +...:: + Any command you can specify in a shell. + + +-e:: +--event=:: + Select the PMU event. Selection can be a symbolic event name + (use 'perf list' to list all events) or a raw PMU + event (eventsel+umask) in the form of rNNN where NNN is a + hexadecimal event descriptor. + +-i:: +--inherit:: + child tasks inherit counters +-p:: +--pid=:: + stat events on existing pid + +-a:: + system-wide collection + +-l:: + scale counter values + +EXAMPLES +-------- + +$ perf stat -- make -j + + Performance counter stats for 'make -j': + + 8117.370256 task clock ticks # 11.281 CPU utilization factor + 678 context switches # 0.000 M/sec + 133 CPU migrations # 0.000 M/sec + 235724 pagefaults # 0.029 M/sec + 24821162526 CPU cycles # 3057.784 M/sec + 18687303457 instructions # 2302.138 M/sec + 172158895 cache references # 21.209 M/sec + 27075259 cache misses # 3.335 M/sec + + Wall-clock time elapsed: 719.554352 msecs + +SEE ALSO +-------- +linkperf:perf-top[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt new file mode 100644 index 0000000000000000000000000000000000000000..539d0128972508b754dc367b70d73f87641bd0b0 --- /dev/null +++ b/tools/perf/Documentation/perf-top.txt @@ -0,0 +1,39 @@ +perf-top(1) +=========== + +NAME +---- +perf-top - Run a command and profile it + +SYNOPSIS +-------- +[verse] +'perf top' [-e | --event=EVENT] [-l] [-a] + +DESCRIPTION +----------- +This command runs a command and gathers a performance counter profile +from it. + + +OPTIONS +------- +...:: + Any command you can specify in a shell. + +-e:: +--event=:: + Select the PMU event. Selection can be a symbolic event name + (use 'perf list' to list all events) or a raw PMU + event (eventsel+umask) in the form of rNNN where NNN is a + hexadecimal event descriptor. + +-a:: + system-wide collection + +-l:: + scale counter values + +SEE ALSO +-------- +linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt new file mode 100644 index 0000000000000000000000000000000000000000..69c832557199d1a1bd1fb82a25e10a557acc49b7 --- /dev/null +++ b/tools/perf/Documentation/perf.txt @@ -0,0 +1,24 @@ +perf(1) +======= + +NAME +---- +perf - Performance analysis tools for Linux + +SYNOPSIS +-------- +[verse] +'perf' [--version] [--help] COMMAND [ARGS] + +DESCRIPTION +----------- +Performance counters for Linux are are a new kernel-based subsystem +that provide a framework for all things performance analysis. It +covers hardware level (CPU/PMU, Performance Monitoring Unit) features +and software features (software counters, tracepoints) as well. + +SEE ALSO +-------- +linkperf:perf-stat[1], linkperf:perf-top[1], +linkperf:perf-record[1], linkperf:perf-report[1], +linkperf:perf-list[1] diff --git a/tools/perf/Makefile b/tools/perf/Makefile new file mode 100644 index 0000000000000000000000000000000000000000..0cbd5d6874ec353b84a0d2da43189b22f38e1e43 --- /dev/null +++ b/tools/perf/Makefile @@ -0,0 +1,929 @@ +# The default target of this Makefile is... +all:: + +# Define V=1 to have a more verbose compile. +# +# Define SNPRINTF_RETURNS_BOGUS if your are on a system which snprintf() +# or vsnprintf() return -1 instead of number of characters which would +# have been written to the final string if enough space had been available. +# +# Define FREAD_READS_DIRECTORIES if your are on a system which succeeds +# when attempting to read from an fopen'ed directory. +# +# Define NO_OPENSSL environment variable if you do not have OpenSSL. +# This also implies MOZILLA_SHA1. +# +# Define CURLDIR=/foo/bar if your curl header and library files are in +# /foo/bar/include and /foo/bar/lib directories. +# +# Define EXPATDIR=/foo/bar if your expat header and library files are in +# /foo/bar/include and /foo/bar/lib directories. +# +# Define NO_D_INO_IN_DIRENT if you don't have d_ino in your struct dirent. +# +# Define NO_D_TYPE_IN_DIRENT if your platform defines DT_UNKNOWN but lacks +# d_type in struct dirent (latest Cygwin -- will be fixed soonish). +# +# Define NO_C99_FORMAT if your formatted IO functions (printf/scanf et.al.) +# do not support the 'size specifiers' introduced by C99, namely ll, hh, +# j, z, t. (representing long long int, char, intmax_t, size_t, ptrdiff_t). +# some C compilers supported these specifiers prior to C99 as an extension. +# +# Define NO_STRCASESTR if you don't have strcasestr. +# +# Define NO_MEMMEM if you don't have memmem. +# +# Define NO_STRTOUMAX if you don't have strtoumax in the C library. +# If your compiler also does not support long long or does not have +# strtoull, define NO_STRTOULL. +# +# Define NO_SETENV if you don't have setenv in the C library. +# +# Define NO_UNSETENV if you don't have unsetenv in the C library. +# +# Define NO_MKDTEMP if you don't have mkdtemp in the C library. +# +# Define NO_SYS_SELECT_H if you don't have sys/select.h. +# +# Define NO_SYMLINK_HEAD if you never want .perf/HEAD to be a symbolic link. +# Enable it on Windows. By default, symrefs are still used. +# +# Define NO_SVN_TESTS if you want to skip time-consuming SVN interoperability +# tests. These tests take up a significant amount of the total test time +# but are not needed unless you plan to talk to SVN repos. +# +# Define NO_FINK if you are building on Darwin/Mac OS X, have Fink +# installed in /sw, but don't want PERF to link against any libraries +# installed there. If defined you may specify your own (or Fink's) +# include directories and library directories by defining CFLAGS +# and LDFLAGS appropriately. +# +# Define NO_DARWIN_PORTS if you are building on Darwin/Mac OS X, +# have DarwinPorts installed in /opt/local, but don't want PERF to +# link against any libraries installed there. If defined you may +# specify your own (or DarwinPort's) include directories and +# library directories by defining CFLAGS and LDFLAGS appropriately. +# +# Define PPC_SHA1 environment variable when running make to make use of +# a bundled SHA1 routine optimized for PowerPC. +# +# Define ARM_SHA1 environment variable when running make to make use of +# a bundled SHA1 routine optimized for ARM. +# +# Define MOZILLA_SHA1 environment variable when running make to make use of +# a bundled SHA1 routine coming from Mozilla. It is GPL'd and should be fast +# on non-x86 architectures (e.g. PowerPC), while the OpenSSL version (default +# choice) has very fast version optimized for i586. +# +# Define NEEDS_SSL_WITH_CRYPTO if you need -lcrypto with -lssl (Darwin). +# +# Define NEEDS_LIBICONV if linking with libc is not enough (Darwin). +# +# Define NEEDS_SOCKET if linking with libc is not enough (SunOS, +# Patrick Mauritz). +# +# Define NO_MMAP if you want to avoid mmap. +# +# Define NO_PTHREADS if you do not have or do not want to use Pthreads. +# +# Define NO_PREAD if you have a problem with pread() system call (e.g. +# cygwin.dll before v1.5.22). +# +# Define NO_FAST_WORKING_DIRECTORY if accessing objects in pack files is +# generally faster on your platform than accessing the working directory. +# +# Define NO_TRUSTABLE_FILEMODE if your filesystem may claim to support +# the executable mode bit, but doesn't really do so. +# +# Define NO_IPV6 if you lack IPv6 support and getaddrinfo(). +# +# Define NO_SOCKADDR_STORAGE if your platform does not have struct +# sockaddr_storage. +# +# Define NO_ICONV if your libc does not properly support iconv. +# +# Define OLD_ICONV if your library has an old iconv(), where the second +# (input buffer pointer) parameter is declared with type (const char **). +# +# Define NO_DEFLATE_BOUND if your zlib does not have deflateBound. +# +# Define NO_R_TO_GCC_LINKER if your gcc does not like "-R/path/lib" +# that tells runtime paths to dynamic libraries; +# "-Wl,-rpath=/path/lib" is used instead. +# +# Define USE_NSEC below if you want perf to care about sub-second file mtimes +# and ctimes. Note that you need recent glibc (at least 2.2.4) for this, and +# it will BREAK YOUR LOCAL DIFFS! show-diff and anything using it will likely +# randomly break unless your underlying filesystem supports those sub-second +# times (my ext3 doesn't). +# +# Define USE_ST_TIMESPEC if your "struct stat" uses "st_ctimespec" instead of +# "st_ctim" +# +# Define NO_NSEC if your "struct stat" does not have "st_ctim.tv_nsec" +# available. This automatically turns USE_NSEC off. +# +# Define USE_STDEV below if you want perf to care about the underlying device +# change being considered an inode change from the update-index perspective. +# +# Define NO_ST_BLOCKS_IN_STRUCT_STAT if your platform does not have st_blocks +# field that counts the on-disk footprint in 512-byte blocks. +# +# Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8 +# +# Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72. +# +# Define NO_PERL_MAKEMAKER if you cannot use Makefiles generated by perl's +# MakeMaker (e.g. using ActiveState under Cygwin). +# +# Define NO_PERL if you do not want Perl scripts or libraries at all. +# +# Define INTERNAL_QSORT to use Git's implementation of qsort(), which +# is a simplified version of the merge sort used in glibc. This is +# recommended if Git triggers O(n^2) behavior in your platform's qsort(). +# +# Define NO_EXTERNAL_GREP if you don't want "perf grep" to ever call +# your external grep (e.g., if your system lacks grep, if its grep is +# broken, or spawning external process is slower than built-in grep perf has). + +PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE + @$(SHELL_PATH) util/PERF-VERSION-GEN +-include PERF-VERSION-FILE + +uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not') +uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not') +uname_O := $(shell sh -c 'uname -o 2>/dev/null || echo not') +uname_R := $(shell sh -c 'uname -r 2>/dev/null || echo not') +uname_P := $(shell sh -c 'uname -p 2>/dev/null || echo not') +uname_V := $(shell sh -c 'uname -v 2>/dev/null || echo not') + +# CFLAGS and LDFLAGS are for the users to override from the command line. + +CFLAGS = -ggdb3 -Wall -Werror -Wstrict-prototypes -Wmissing-declarations -Wmissing-prototypes -std=gnu99 -Wdeclaration-after-statement -O6 +LDFLAGS = -lpthread -lrt -lelf +ALL_CFLAGS = $(CFLAGS) +ALL_LDFLAGS = $(LDFLAGS) +STRIP ?= strip + +# Among the variables below, these: +# perfexecdir +# template_dir +# mandir +# infodir +# htmldir +# ETC_PERFCONFIG (but not sysconfdir) +# can be specified as a relative path some/where/else; +# this is interpreted as relative to $(prefix) and "perf" at +# runtime figures out where they are based on the path to the executable. +# This can help installing the suite in a relocatable way. + +prefix = $(HOME) +bindir_relative = bin +bindir = $(prefix)/$(bindir_relative) +mandir = share/man +infodir = share/info +perfexecdir = libexec/perf-core +sharedir = $(prefix)/share +template_dir = share/perf-core/templates +htmldir = share/doc/perf-doc +ifeq ($(prefix),/usr) +sysconfdir = /etc +ETC_PERFCONFIG = $(sysconfdir)/perfconfig +else +sysconfdir = $(prefix)/etc +ETC_PERFCONFIG = etc/perfconfig +endif +lib = lib +# DESTDIR= + +export prefix bindir sharedir sysconfdir + +CC = gcc +AR = ar +RM = rm -f +TAR = tar +FIND = find +INSTALL = install +RPMBUILD = rpmbuild +PTHREAD_LIBS = -lpthread + +# sparse is architecture-neutral, which means that we need to tell it +# explicitly what architecture to check for. Fix this up for yours.. +SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ + + + +### --- END CONFIGURATION SECTION --- + +# Those must not be GNU-specific; they are shared with perl/ which may +# be built by a different compiler. (Note that this is an artifact now +# but it still might be nice to keep that distinction.) +BASIC_CFLAGS = +BASIC_LDFLAGS = + +# Guard against environment variables +BUILTIN_OBJS = +BUILT_INS = +COMPAT_CFLAGS = +COMPAT_OBJS = +LIB_H = +LIB_OBJS = +SCRIPT_PERL = +SCRIPT_SH = +TEST_PROGRAMS = + +# +# No scripts right now: +# + +# SCRIPT_SH += perf-am.sh + +# +# No Perl scripts right now: +# + +# SCRIPT_PERL += perf-add--interactive.perl + +SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) \ + $(patsubst %.perl,%,$(SCRIPT_PERL)) + +# Empty... +EXTRA_PROGRAMS = + +# ... and all the rest that could be moved out of bindir to perfexecdir +PROGRAMS += $(EXTRA_PROGRAMS) + +# +# Single 'perf' binary right now: +# +PROGRAMS += perf + +# List built-in command $C whose implementation cmd_$C() is not in +# builtin-$C.o but is linked in as part of some other command. +# +# None right now: +# +# BUILT_INS += perf-init $X + +# what 'all' will build and 'install' will install, in perfexecdir +ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS) + +# what 'all' will build but not install in perfexecdir +OTHER_PROGRAMS = perf$X + +# Set paths to tools early so that they can be used for version tests. +ifndef SHELL_PATH + SHELL_PATH = /bin/sh +endif +ifndef PERL_PATH + PERL_PATH = /usr/bin/perl +endif + +export PERL_PATH + +LIB_FILE=libperf.a + +LIB_H += ../../include/linux/perf_counter.h +LIB_H += perf.h +LIB_H += util/list.h +LIB_H += util/rbtree.h +LIB_H += util/levenshtein.h +LIB_H += util/parse-options.h +LIB_H += util/parse-events.h +LIB_H += util/quote.h +LIB_H += util/util.h +LIB_H += util/help.h +LIB_H += util/strbuf.h +LIB_H += util/string.h +LIB_H += util/run-command.h +LIB_H += util/sigchain.h +LIB_H += util/symbol.h +LIB_H += util/color.h + +LIB_OBJS += util/abspath.o +LIB_OBJS += util/alias.o +LIB_OBJS += util/config.o +LIB_OBJS += util/ctype.o +LIB_OBJS += util/environment.o +LIB_OBJS += util/exec_cmd.o +LIB_OBJS += util/help.o +LIB_OBJS += util/levenshtein.o +LIB_OBJS += util/parse-options.o +LIB_OBJS += util/parse-events.o +LIB_OBJS += util/path.o +LIB_OBJS += util/rbtree.o +LIB_OBJS += util/run-command.o +LIB_OBJS += util/quote.o +LIB_OBJS += util/strbuf.o +LIB_OBJS += util/string.o +LIB_OBJS += util/usage.o +LIB_OBJS += util/wrapper.o +LIB_OBJS += util/sigchain.o +LIB_OBJS += util/symbol.o +LIB_OBJS += util/color.o +LIB_OBJS += util/pager.o + +BUILTIN_OBJS += builtin-annotate.o +BUILTIN_OBJS += builtin-help.o +BUILTIN_OBJS += builtin-list.o +BUILTIN_OBJS += builtin-record.o +BUILTIN_OBJS += builtin-report.o +BUILTIN_OBJS += builtin-stat.o +BUILTIN_OBJS += builtin-top.o + +PERFLIBS = $(LIB_FILE) +EXTLIBS = + +# +# Platform specific tweaks +# + +# We choose to avoid "if .. else if .. else .. endif endif" +# because maintaining the nesting to match is a pain. If +# we had "elif" things would have been much nicer... + +-include config.mak.autogen +-include config.mak + +ifeq ($(uname_S),Darwin) + ifndef NO_FINK + ifeq ($(shell test -d /sw/lib && echo y),y) + BASIC_CFLAGS += -I/sw/include + BASIC_LDFLAGS += -L/sw/lib + endif + endif + ifndef NO_DARWIN_PORTS + ifeq ($(shell test -d /opt/local/lib && echo y),y) + BASIC_CFLAGS += -I/opt/local/include + BASIC_LDFLAGS += -L/opt/local/lib + endif + endif + PTHREAD_LIBS = +endif + +ifndef CC_LD_DYNPATH + ifdef NO_R_TO_GCC_LINKER + # Some gcc does not accept and pass -R to the linker to specify + # the runtime dynamic library path. + CC_LD_DYNPATH = -Wl,-rpath, + else + CC_LD_DYNPATH = -R + endif +endif + +ifdef ZLIB_PATH + BASIC_CFLAGS += -I$(ZLIB_PATH)/include + EXTLIBS += -L$(ZLIB_PATH)/$(lib) $(CC_LD_DYNPATH)$(ZLIB_PATH)/$(lib) +endif +EXTLIBS += -lz + +ifdef NEEDS_SOCKET + EXTLIBS += -lsocket +endif +ifdef NEEDS_NSL + EXTLIBS += -lnsl +endif +ifdef NO_D_TYPE_IN_DIRENT + BASIC_CFLAGS += -DNO_D_TYPE_IN_DIRENT +endif +ifdef NO_D_INO_IN_DIRENT + BASIC_CFLAGS += -DNO_D_INO_IN_DIRENT +endif +ifdef NO_ST_BLOCKS_IN_STRUCT_STAT + BASIC_CFLAGS += -DNO_ST_BLOCKS_IN_STRUCT_STAT +endif +ifdef USE_NSEC + BASIC_CFLAGS += -DUSE_NSEC +endif +ifdef USE_ST_TIMESPEC + BASIC_CFLAGS += -DUSE_ST_TIMESPEC +endif +ifdef NO_NSEC + BASIC_CFLAGS += -DNO_NSEC +endif +ifdef NO_C99_FORMAT + BASIC_CFLAGS += -DNO_C99_FORMAT +endif +ifdef SNPRINTF_RETURNS_BOGUS + COMPAT_CFLAGS += -DSNPRINTF_RETURNS_BOGUS + COMPAT_OBJS += compat/snprintf.o +endif +ifdef FREAD_READS_DIRECTORIES + COMPAT_CFLAGS += -DFREAD_READS_DIRECTORIES + COMPAT_OBJS += compat/fopen.o +endif +ifdef NO_SYMLINK_HEAD + BASIC_CFLAGS += -DNO_SYMLINK_HEAD +endif +ifdef NO_STRCASESTR + COMPAT_CFLAGS += -DNO_STRCASESTR + COMPAT_OBJS += compat/strcasestr.o +endif +ifdef NO_STRTOUMAX + COMPAT_CFLAGS += -DNO_STRTOUMAX + COMPAT_OBJS += compat/strtoumax.o +endif +ifdef NO_STRTOULL + COMPAT_CFLAGS += -DNO_STRTOULL +endif +ifdef NO_SETENV + COMPAT_CFLAGS += -DNO_SETENV + COMPAT_OBJS += compat/setenv.o +endif +ifdef NO_MKDTEMP + COMPAT_CFLAGS += -DNO_MKDTEMP + COMPAT_OBJS += compat/mkdtemp.o +endif +ifdef NO_UNSETENV + COMPAT_CFLAGS += -DNO_UNSETENV + COMPAT_OBJS += compat/unsetenv.o +endif +ifdef NO_SYS_SELECT_H + BASIC_CFLAGS += -DNO_SYS_SELECT_H +endif +ifdef NO_MMAP + COMPAT_CFLAGS += -DNO_MMAP + COMPAT_OBJS += compat/mmap.o +else + ifdef USE_WIN32_MMAP + COMPAT_CFLAGS += -DUSE_WIN32_MMAP + COMPAT_OBJS += compat/win32mmap.o + endif +endif +ifdef NO_PREAD + COMPAT_CFLAGS += -DNO_PREAD + COMPAT_OBJS += compat/pread.o +endif +ifdef NO_FAST_WORKING_DIRECTORY + BASIC_CFLAGS += -DNO_FAST_WORKING_DIRECTORY +endif +ifdef NO_TRUSTABLE_FILEMODE + BASIC_CFLAGS += -DNO_TRUSTABLE_FILEMODE +endif +ifdef NO_IPV6 + BASIC_CFLAGS += -DNO_IPV6 +endif +ifdef NO_UINTMAX_T + BASIC_CFLAGS += -Duintmax_t=uint32_t +endif +ifdef NO_SOCKADDR_STORAGE +ifdef NO_IPV6 + BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in +else + BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in6 +endif +endif +ifdef NO_INET_NTOP + LIB_OBJS += compat/inet_ntop.o +endif +ifdef NO_INET_PTON + LIB_OBJS += compat/inet_pton.o +endif + +ifdef NO_ICONV + BASIC_CFLAGS += -DNO_ICONV +endif + +ifdef OLD_ICONV + BASIC_CFLAGS += -DOLD_ICONV +endif + +ifdef NO_DEFLATE_BOUND + BASIC_CFLAGS += -DNO_DEFLATE_BOUND +endif + +ifdef PPC_SHA1 + SHA1_HEADER = "ppc/sha1.h" + LIB_OBJS += ppc/sha1.o ppc/sha1ppc.o +else +ifdef ARM_SHA1 + SHA1_HEADER = "arm/sha1.h" + LIB_OBJS += arm/sha1.o arm/sha1_arm.o +else +ifdef MOZILLA_SHA1 + SHA1_HEADER = "mozilla-sha1/sha1.h" + LIB_OBJS += mozilla-sha1/sha1.o +else + SHA1_HEADER = + EXTLIBS += $(LIB_4_CRYPTO) +endif +endif +endif +ifdef NO_PERL_MAKEMAKER + export NO_PERL_MAKEMAKER +endif +ifdef NO_HSTRERROR + COMPAT_CFLAGS += -DNO_HSTRERROR + COMPAT_OBJS += compat/hstrerror.o +endif +ifdef NO_MEMMEM + COMPAT_CFLAGS += -DNO_MEMMEM + COMPAT_OBJS += compat/memmem.o +endif +ifdef INTERNAL_QSORT + COMPAT_CFLAGS += -DINTERNAL_QSORT + COMPAT_OBJS += compat/qsort.o +endif +ifdef RUNTIME_PREFIX + COMPAT_CFLAGS += -DRUNTIME_PREFIX +endif + +ifdef DIR_HAS_BSD_GROUP_SEMANTICS + COMPAT_CFLAGS += -DDIR_HAS_BSD_GROUP_SEMANTICS +endif +ifdef NO_EXTERNAL_GREP + BASIC_CFLAGS += -DNO_EXTERNAL_GREP +endif + +ifeq ($(PERL_PATH),) +NO_PERL=NoThanks +endif + +QUIET_SUBDIR0 = +$(MAKE) -C # space to separate -C and subdir +QUIET_SUBDIR1 = + +ifneq ($(findstring $(MAKEFLAGS),w),w) +PRINT_DIR = --no-print-directory +else # "make -w" +NO_SUBDIR = : +endif + +ifneq ($(findstring $(MAKEFLAGS),s),s) +ifndef V + QUIET_CC = @echo ' ' CC $@; + QUIET_AR = @echo ' ' AR $@; + QUIET_LINK = @echo ' ' LINK $@; + QUIET_BUILT_IN = @echo ' ' BUILTIN $@; + QUIET_GEN = @echo ' ' GEN $@; + QUIET_SUBDIR0 = +@subdir= + QUIET_SUBDIR1 = ;$(NO_SUBDIR) echo ' ' SUBDIR $$subdir; \ + $(MAKE) $(PRINT_DIR) -C $$subdir + export V + export QUIET_GEN + export QUIET_BUILT_IN +endif +endif + +ifdef ASCIIDOC8 + export ASCIIDOC8 +endif + +# Shell quote (do not use $(call) to accommodate ancient setups); + +SHA1_HEADER_SQ = $(subst ','\'',$(SHA1_HEADER)) +ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG)) + +DESTDIR_SQ = $(subst ','\'',$(DESTDIR)) +bindir_SQ = $(subst ','\'',$(bindir)) +bindir_relative_SQ = $(subst ','\'',$(bindir_relative)) +mandir_SQ = $(subst ','\'',$(mandir)) +infodir_SQ = $(subst ','\'',$(infodir)) +perfexecdir_SQ = $(subst ','\'',$(perfexecdir)) +template_dir_SQ = $(subst ','\'',$(template_dir)) +htmldir_SQ = $(subst ','\'',$(htmldir)) +prefix_SQ = $(subst ','\'',$(prefix)) + +SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) +PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH)) + +LIBS = $(PERFLIBS) $(EXTLIBS) + +BASIC_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' \ + $(COMPAT_CFLAGS) +LIB_OBJS += $(COMPAT_OBJS) + +ALL_CFLAGS += $(BASIC_CFLAGS) +ALL_LDFLAGS += $(BASIC_LDFLAGS) + +export TAR INSTALL DESTDIR SHELL_PATH + + +### Build rules + +SHELL = $(SHELL_PATH) + +all:: shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) PERF-BUILD-OPTIONS +ifneq (,$X) + $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), test '$p' -ef '$p$X' || $(RM) '$p';) +endif + +all:: + +please_set_SHELL_PATH_to_a_more_modern_shell: + @$$(:) + +shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell + +strip: $(PROGRAMS) perf$X + $(STRIP) $(STRIP_OPTS) $(PROGRAMS) perf$X + +perf.o: perf.c common-cmds.h PERF-CFLAGS + $(QUIET_CC)$(CC) -DPERF_VERSION='"$(PERF_VERSION)"' \ + '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ + $(ALL_CFLAGS) -c $(filter %.c,$^) + +perf$X: perf.o $(BUILTIN_OBJS) $(PERFLIBS) + $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ perf.o \ + $(BUILTIN_OBJS) $(ALL_LDFLAGS) $(LIBS) + +builtin-help.o: builtin-help.c common-cmds.h PERF-CFLAGS + $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \ + '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ + '-DPERF_MAN_PATH="$(mandir_SQ)"' \ + '-DPERF_INFO_PATH="$(infodir_SQ)"' $< + +$(BUILT_INS): perf$X + $(QUIET_BUILT_IN)$(RM) $@ && \ + ln perf$X $@ 2>/dev/null || \ + ln -s perf$X $@ 2>/dev/null || \ + cp perf$X $@ + +common-cmds.h: util/generate-cmdlist.sh command-list.txt + +common-cmds.h: $(wildcard Documentation/perf-*.txt) + $(QUIET_GEN)util/generate-cmdlist.sh > $@+ && mv $@+ $@ + +$(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh + $(QUIET_GEN)$(RM) $@ $@+ && \ + sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \ + -e 's|@SHELL_PATH@|$(SHELL_PATH_SQ)|' \ + -e 's|@@PERL@@|$(PERL_PATH_SQ)|g' \ + -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \ + -e 's/@@NO_CURL@@/$(NO_CURL)/g' \ + $@.sh >$@+ && \ + chmod +x $@+ && \ + mv $@+ $@ + +configure: configure.ac + $(QUIET_GEN)$(RM) $@ $<+ && \ + sed -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \ + $< > $<+ && \ + autoconf -o $@ $<+ && \ + $(RM) $<+ + +# These can record PERF_VERSION +perf.o perf.spec \ + $(patsubst %.sh,%,$(SCRIPT_SH)) \ + $(patsubst %.perl,%,$(SCRIPT_PERL)) \ + : PERF-VERSION-FILE + +%.o: %.c PERF-CFLAGS + $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) $< +%.s: %.c PERF-CFLAGS + $(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $< +%.o: %.S + $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) $< + +util/exec_cmd.o: util/exec_cmd.c PERF-CFLAGS + $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) \ + '-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \ + '-DBINDIR="$(bindir_relative_SQ)"' \ + '-DPREFIX="$(prefix_SQ)"' \ + $< + +builtin-init-db.o: builtin-init-db.c PERF-CFLAGS + $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) -DDEFAULT_PERF_TEMPLATE_DIR='"$(template_dir_SQ)"' $< + +util/config.o: util/config.c PERF-CFLAGS + $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + +perf-%$X: %.o $(PERFLIBS) + $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) + +$(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H) +$(patsubst perf-%$X,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h) +builtin-revert.o wt-status.o: wt-status.h + +$(LIB_FILE): $(LIB_OBJS) + $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS) + +doc: + $(MAKE) -C Documentation all + +man: + $(MAKE) -C Documentation man + +html: + $(MAKE) -C Documentation html + +info: + $(MAKE) -C Documentation info + +pdf: + $(MAKE) -C Documentation pdf + +TAGS: + $(RM) TAGS + $(FIND) . -name '*.[hcS]' -print | xargs etags -a + +tags: + $(RM) tags + $(FIND) . -name '*.[hcS]' -print | xargs ctags -a + +cscope: + $(RM) cscope* + $(FIND) . -name '*.[hcS]' -print | xargs cscope -b + +### Detect prefix changes +TRACK_CFLAGS = $(subst ','\'',$(ALL_CFLAGS)):\ + $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ) + +PERF-CFLAGS: .FORCE-PERF-CFLAGS + @FLAGS='$(TRACK_CFLAGS)'; \ + if test x"$$FLAGS" != x"`cat PERF-CFLAGS 2>/dev/null`" ; then \ + echo 1>&2 " * new build flags or prefix"; \ + echo "$$FLAGS" >PERF-CFLAGS; \ + fi + +# We need to apply sq twice, once to protect from the shell +# that runs PERF-BUILD-OPTIONS, and then again to protect it +# and the first level quoting from the shell that runs "echo". +PERF-BUILD-OPTIONS: .FORCE-PERF-BUILD-OPTIONS + @echo SHELL_PATH=\''$(subst ','\'',$(SHELL_PATH_SQ))'\' >$@ + @echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@ + @echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@ + @echo NO_PERL=\''$(subst ','\'',$(subst ','\'',$(NO_PERL)))'\' >>$@ + +### Testing rules + +# +# None right now: +# +# TEST_PROGRAMS += test-something$X + +all:: $(TEST_PROGRAMS) + +# GNU make supports exporting all variables by "export" without parameters. +# However, the environment gets quite big, and some programs have problems +# with that. + +export NO_SVN_TESTS + +check: common-cmds.h + if sparse; \ + then \ + for i in *.c */*.c; \ + do \ + sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; \ + done; \ + else \ + echo 2>&1 "Did you mean 'make test'?"; \ + exit 1; \ + fi + +remove-dashes: + ./fixup-builtins $(BUILT_INS) $(PROGRAMS) $(SCRIPTS) + +### Installation rules + +ifneq ($(filter /%,$(firstword $(template_dir))),) +template_instdir = $(template_dir) +else +template_instdir = $(prefix)/$(template_dir) +endif +export template_instdir + +ifneq ($(filter /%,$(firstword $(perfexecdir))),) +perfexec_instdir = $(perfexecdir) +else +perfexec_instdir = $(prefix)/$(perfexecdir) +endif +perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir)) +export perfexec_instdir + +install: all + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)' + $(INSTALL) perf$X '$(DESTDIR_SQ)$(bindir_SQ)' +ifdef BUILT_INS + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' + $(INSTALL) $(BUILT_INS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' +ifneq (,$X) + $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), $(RM) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$p';) +endif +endif + +install-doc: + $(MAKE) -C Documentation install + +install-man: + $(MAKE) -C Documentation install-man + +install-html: + $(MAKE) -C Documentation install-html + +install-info: + $(MAKE) -C Documentation install-info + +install-pdf: + $(MAKE) -C Documentation install-pdf + +quick-install-doc: + $(MAKE) -C Documentation quick-install + +quick-install-man: + $(MAKE) -C Documentation quick-install-man + +quick-install-html: + $(MAKE) -C Documentation quick-install-html + + +### Maintainer's dist rules +# +# None right now +# +# +# perf.spec: perf.spec.in +# sed -e 's/@@VERSION@@/$(PERF_VERSION)/g' < $< > $@+ +# mv $@+ $@ +# +# PERF_TARNAME=perf-$(PERF_VERSION) +# dist: perf.spec perf-archive$(X) configure +# ./perf-archive --format=tar \ +# --prefix=$(PERF_TARNAME)/ HEAD^{tree} > $(PERF_TARNAME).tar +# @mkdir -p $(PERF_TARNAME) +# @cp perf.spec configure $(PERF_TARNAME) +# @echo $(PERF_VERSION) > $(PERF_TARNAME)/version +# $(TAR) rf $(PERF_TARNAME).tar \ +# $(PERF_TARNAME)/perf.spec \ +# $(PERF_TARNAME)/configure \ +# $(PERF_TARNAME)/version +# @$(RM) -r $(PERF_TARNAME) +# gzip -f -9 $(PERF_TARNAME).tar +# +# htmldocs = perf-htmldocs-$(PERF_VERSION) +# manpages = perf-manpages-$(PERF_VERSION) +# dist-doc: +# $(RM) -r .doc-tmp-dir +# mkdir .doc-tmp-dir +# $(MAKE) -C Documentation WEBDOC_DEST=../.doc-tmp-dir install-webdoc +# cd .doc-tmp-dir && $(TAR) cf ../$(htmldocs).tar . +# gzip -n -9 -f $(htmldocs).tar +# : +# $(RM) -r .doc-tmp-dir +# mkdir -p .doc-tmp-dir/man1 .doc-tmp-dir/man5 .doc-tmp-dir/man7 +# $(MAKE) -C Documentation DESTDIR=./ \ +# man1dir=../.doc-tmp-dir/man1 \ +# man5dir=../.doc-tmp-dir/man5 \ +# man7dir=../.doc-tmp-dir/man7 \ +# install +# cd .doc-tmp-dir && $(TAR) cf ../$(manpages).tar . +# gzip -n -9 -f $(manpages).tar +# $(RM) -r .doc-tmp-dir +# +# rpm: dist +# $(RPMBUILD) -ta $(PERF_TARNAME).tar.gz + +### Cleaning rules + +distclean: clean +# $(RM) configure + +clean: + $(RM) *.o */*.o $(LIB_FILE) + $(RM) $(ALL_PROGRAMS) $(BUILT_INS) perf$X + $(RM) $(TEST_PROGRAMS) + $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo common-cmds.h TAGS tags cscope* + $(RM) -r autom4te.cache + $(RM) config.log config.mak.autogen config.mak.append config.status config.cache + $(RM) -r $(PERF_TARNAME) .doc-tmp-dir + $(RM) $(PERF_TARNAME).tar.gz perf-core_$(PERF_VERSION)-*.tar.gz + $(RM) $(htmldocs).tar.gz $(manpages).tar.gz + $(MAKE) -C Documentation/ clean + $(RM) PERF-VERSION-FILE PERF-CFLAGS PERF-BUILD-OPTIONS + +.PHONY: all install clean strip +.PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell +.PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS +.PHONY: .FORCE-PERF-BUILD-OPTIONS + +### Make sure built-ins do not have dups and listed in perf.c +# +check-builtins:: + ./check-builtins.sh + +### Test suite coverage testing +# +# None right now +# +# .PHONY: coverage coverage-clean coverage-build coverage-report +# +# coverage: +# $(MAKE) coverage-build +# $(MAKE) coverage-report +# +# coverage-clean: +# rm -f *.gcda *.gcno +# +# COVERAGE_CFLAGS = $(CFLAGS) -O0 -ftest-coverage -fprofile-arcs +# COVERAGE_LDFLAGS = $(CFLAGS) -O0 -lgcov +# +# coverage-build: coverage-clean +# $(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" all +# $(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" \ +# -j1 test +# +# coverage-report: +# gcov -b *.c */*.c +# grep '^function.*called 0 ' *.c.gcov */*.c.gcov \ +# | sed -e 's/\([^:]*\)\.gcov: *function \([^ ]*\) called.*/\1: \2/' \ +# | tee coverage-untested-functions diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c new file mode 100644 index 0000000000000000000000000000000000000000..b1ed5f766cb3fbbdefd0d5fc1e7c039e0765b555 --- /dev/null +++ b/tools/perf/builtin-annotate.c @@ -0,0 +1,1356 @@ +/* + * builtin-annotate.c + * + * Builtin annotate command: Analyze the perf.data input file, + * look up and read DSOs and symbol information and display + * a histogram of results, along various sorting keys. + */ +#include "builtin.h" + +#include "util/util.h" + +#include "util/color.h" +#include "util/list.h" +#include "util/cache.h" +#include "util/rbtree.h" +#include "util/symbol.h" +#include "util/string.h" + +#include "perf.h" + +#include "util/parse-options.h" +#include "util/parse-events.h" + +#define SHOW_KERNEL 1 +#define SHOW_USER 2 +#define SHOW_HV 4 + +static char const *input_name = "perf.data"; +static char *vmlinux = "vmlinux"; + +static char default_sort_order[] = "comm,symbol"; +static char *sort_order = default_sort_order; + +static int input; +static int show_mask = SHOW_KERNEL | SHOW_USER | SHOW_HV; + +static int dump_trace = 0; +#define dprintf(x...) do { if (dump_trace) printf(x); } while (0) + +static int verbose; + +static unsigned long page_size; +static unsigned long mmap_window = 32; + +struct ip_event { + struct perf_event_header header; + __u64 ip; + __u32 pid, tid; +}; + +struct mmap_event { + struct perf_event_header header; + __u32 pid, tid; + __u64 start; + __u64 len; + __u64 pgoff; + char filename[PATH_MAX]; +}; + +struct comm_event { + struct perf_event_header header; + __u32 pid, tid; + char comm[16]; +}; + +struct fork_event { + struct perf_event_header header; + __u32 pid, ppid; +}; + +struct period_event { + struct perf_event_header header; + __u64 time; + __u64 id; + __u64 sample_period; +}; + +typedef union event_union { + struct perf_event_header header; + struct ip_event ip; + struct mmap_event mmap; + struct comm_event comm; + struct fork_event fork; + struct period_event period; +} event_t; + +static LIST_HEAD(dsos); +static struct dso *kernel_dso; +static struct dso *vdso; + + +static void dsos__add(struct dso *dso) +{ + list_add_tail(&dso->node, &dsos); +} + +static struct dso *dsos__find(const char *name) +{ + struct dso *pos; + + list_for_each_entry(pos, &dsos, node) + if (strcmp(pos->name, name) == 0) + return pos; + return NULL; +} + +static struct dso *dsos__findnew(const char *name) +{ + struct dso *dso = dsos__find(name); + int nr; + + if (dso) + return dso; + + dso = dso__new(name, 0); + if (!dso) + goto out_delete_dso; + + nr = dso__load(dso, NULL, verbose); + if (nr < 0) { + if (verbose) + fprintf(stderr, "Failed to open: %s\n", name); + goto out_delete_dso; + } + if (!nr && verbose) { + fprintf(stderr, + "No symbols found in: %s, maybe install a debug package?\n", + name); + } + + dsos__add(dso); + + return dso; + +out_delete_dso: + dso__delete(dso); + return NULL; +} + +static void dsos__fprintf(FILE *fp) +{ + struct dso *pos; + + list_for_each_entry(pos, &dsos, node) + dso__fprintf(pos, fp); +} + +static struct symbol *vdso__find_symbol(struct dso *dso, __u64 ip) +{ + return dso__find_symbol(kernel_dso, ip); +} + +static int load_kernel(void) +{ + int err; + + kernel_dso = dso__new("[kernel]", 0); + if (!kernel_dso) + return -1; + + err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose); + if (err) { + dso__delete(kernel_dso); + kernel_dso = NULL; + } else + dsos__add(kernel_dso); + + vdso = dso__new("[vdso]", 0); + if (!vdso) + return -1; + + vdso->find_symbol = vdso__find_symbol; + + dsos__add(vdso); + + return err; +} + +struct map { + struct list_head node; + __u64 start; + __u64 end; + __u64 pgoff; + __u64 (*map_ip)(struct map *, __u64); + struct dso *dso; +}; + +static __u64 map__map_ip(struct map *map, __u64 ip) +{ + return ip - map->start + map->pgoff; +} + +static __u64 vdso__map_ip(struct map *map, __u64 ip) +{ + return ip; +} + +static struct map *map__new(struct mmap_event *event) +{ + struct map *self = malloc(sizeof(*self)); + + if (self != NULL) { + const char *filename = event->filename; + + self->start = event->start; + self->end = event->start + event->len; + self->pgoff = event->pgoff; + + self->dso = dsos__findnew(filename); + if (self->dso == NULL) + goto out_delete; + + if (self->dso == vdso) + self->map_ip = vdso__map_ip; + else + self->map_ip = map__map_ip; + } + return self; +out_delete: + free(self); + return NULL; +} + +static struct map *map__clone(struct map *self) +{ + struct map *map = malloc(sizeof(*self)); + + if (!map) + return NULL; + + memcpy(map, self, sizeof(*self)); + + return map; +} + +static int map__overlap(struct map *l, struct map *r) +{ + if (l->start > r->start) { + struct map *t = l; + l = r; + r = t; + } + + if (l->end > r->start) + return 1; + + return 0; +} + +static size_t map__fprintf(struct map *self, FILE *fp) +{ + return fprintf(fp, " %Lx-%Lx %Lx %s\n", + self->start, self->end, self->pgoff, self->dso->name); +} + + +struct thread { + struct rb_node rb_node; + struct list_head maps; + pid_t pid; + char *comm; +}; + +static struct thread *thread__new(pid_t pid) +{ + struct thread *self = malloc(sizeof(*self)); + + if (self != NULL) { + self->pid = pid; + self->comm = malloc(32); + if (self->comm) + snprintf(self->comm, 32, ":%d", self->pid); + INIT_LIST_HEAD(&self->maps); + } + + return self; +} + +static int thread__set_comm(struct thread *self, const char *comm) +{ + if (self->comm) + free(self->comm); + self->comm = strdup(comm); + return self->comm ? 0 : -ENOMEM; +} + +static size_t thread__fprintf(struct thread *self, FILE *fp) +{ + struct map *pos; + size_t ret = fprintf(fp, "Thread %d %s\n", self->pid, self->comm); + + list_for_each_entry(pos, &self->maps, node) + ret += map__fprintf(pos, fp); + + return ret; +} + + +static struct rb_root threads; +static struct thread *last_match; + +static struct thread *threads__findnew(pid_t pid) +{ + struct rb_node **p = &threads.rb_node; + struct rb_node *parent = NULL; + struct thread *th; + + /* + * Font-end cache - PID lookups come in blocks, + * so most of the time we dont have to look up + * the full rbtree: + */ + if (last_match && last_match->pid == pid) + return last_match; + + while (*p != NULL) { + parent = *p; + th = rb_entry(parent, struct thread, rb_node); + + if (th->pid == pid) { + last_match = th; + return th; + } + + if (pid < th->pid) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + th = thread__new(pid); + if (th != NULL) { + rb_link_node(&th->rb_node, parent, p); + rb_insert_color(&th->rb_node, &threads); + last_match = th; + } + + return th; +} + +static void thread__insert_map(struct thread *self, struct map *map) +{ + struct map *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, &self->maps, node) { + if (map__overlap(pos, map)) { + list_del_init(&pos->node); + /* XXX leaks dsos */ + free(pos); + } + } + + list_add_tail(&map->node, &self->maps); +} + +static int thread__fork(struct thread *self, struct thread *parent) +{ + struct map *map; + + if (self->comm) + free(self->comm); + self->comm = strdup(parent->comm); + if (!self->comm) + return -ENOMEM; + + list_for_each_entry(map, &parent->maps, node) { + struct map *new = map__clone(map); + if (!new) + return -ENOMEM; + thread__insert_map(self, new); + } + + return 0; +} + +static struct map *thread__find_map(struct thread *self, __u64 ip) +{ + struct map *pos; + + if (self == NULL) + return NULL; + + list_for_each_entry(pos, &self->maps, node) + if (ip >= pos->start && ip <= pos->end) + return pos; + + return NULL; +} + +static size_t threads__fprintf(FILE *fp) +{ + size_t ret = 0; + struct rb_node *nd; + + for (nd = rb_first(&threads); nd; nd = rb_next(nd)) { + struct thread *pos = rb_entry(nd, struct thread, rb_node); + + ret += thread__fprintf(pos, fp); + } + + return ret; +} + +/* + * histogram, sorted on item, collects counts + */ + +static struct rb_root hist; + +struct hist_entry { + struct rb_node rb_node; + + struct thread *thread; + struct map *map; + struct dso *dso; + struct symbol *sym; + __u64 ip; + char level; + + uint32_t count; +}; + +/* + * configurable sorting bits + */ + +struct sort_entry { + struct list_head list; + + char *header; + + int64_t (*cmp)(struct hist_entry *, struct hist_entry *); + int64_t (*collapse)(struct hist_entry *, struct hist_entry *); + size_t (*print)(FILE *fp, struct hist_entry *); +}; + +/* --sort pid */ + +static int64_t +sort__thread_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->thread->pid - left->thread->pid; +} + +static size_t +sort__thread_print(FILE *fp, struct hist_entry *self) +{ + return fprintf(fp, "%16s:%5d", self->thread->comm ?: "", self->thread->pid); +} + +static struct sort_entry sort_thread = { + .header = " Command: Pid", + .cmp = sort__thread_cmp, + .print = sort__thread_print, +}; + +/* --sort comm */ + +static int64_t +sort__comm_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->thread->pid - left->thread->pid; +} + +static int64_t +sort__comm_collapse(struct hist_entry *left, struct hist_entry *right) +{ + char *comm_l = left->thread->comm; + char *comm_r = right->thread->comm; + + if (!comm_l || !comm_r) { + if (!comm_l && !comm_r) + return 0; + else if (!comm_l) + return -1; + else + return 1; + } + + return strcmp(comm_l, comm_r); +} + +static size_t +sort__comm_print(FILE *fp, struct hist_entry *self) +{ + return fprintf(fp, "%16s", self->thread->comm); +} + +static struct sort_entry sort_comm = { + .header = " Command", + .cmp = sort__comm_cmp, + .collapse = sort__comm_collapse, + .print = sort__comm_print, +}; + +/* --sort dso */ + +static int64_t +sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct dso *dso_l = left->dso; + struct dso *dso_r = right->dso; + + if (!dso_l || !dso_r) { + if (!dso_l && !dso_r) + return 0; + else if (!dso_l) + return -1; + else + return 1; + } + + return strcmp(dso_l->name, dso_r->name); +} + +static size_t +sort__dso_print(FILE *fp, struct hist_entry *self) +{ + if (self->dso) + return fprintf(fp, "%-25s", self->dso->name); + + return fprintf(fp, "%016llx ", (__u64)self->ip); +} + +static struct sort_entry sort_dso = { + .header = "Shared Object ", + .cmp = sort__dso_cmp, + .print = sort__dso_print, +}; + +/* --sort symbol */ + +static int64_t +sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) +{ + __u64 ip_l, ip_r; + + if (left->sym == right->sym) + return 0; + + ip_l = left->sym ? left->sym->start : left->ip; + ip_r = right->sym ? right->sym->start : right->ip; + + return (int64_t)(ip_r - ip_l); +} + +static size_t +sort__sym_print(FILE *fp, struct hist_entry *self) +{ + size_t ret = 0; + + if (verbose) + ret += fprintf(fp, "%#018llx ", (__u64)self->ip); + + if (self->sym) { + ret += fprintf(fp, "[%c] %s", + self->dso == kernel_dso ? 'k' : '.', self->sym->name); + } else { + ret += fprintf(fp, "%#016llx", (__u64)self->ip); + } + + return ret; +} + +static struct sort_entry sort_sym = { + .header = "Symbol", + .cmp = sort__sym_cmp, + .print = sort__sym_print, +}; + +static int sort__need_collapse = 0; + +struct sort_dimension { + char *name; + struct sort_entry *entry; + int taken; +}; + +static struct sort_dimension sort_dimensions[] = { + { .name = "pid", .entry = &sort_thread, }, + { .name = "comm", .entry = &sort_comm, }, + { .name = "dso", .entry = &sort_dso, }, + { .name = "symbol", .entry = &sort_sym, }, +}; + +static LIST_HEAD(hist_entry__sort_list); + +static int sort_dimension__add(char *tok) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) { + struct sort_dimension *sd = &sort_dimensions[i]; + + if (sd->taken) + continue; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + if (sd->entry->collapse) + sort__need_collapse = 1; + + list_add_tail(&sd->entry->list, &hist_entry__sort_list); + sd->taken = 1; + + return 0; + } + + return -ESRCH; +} + +static int64_t +hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct sort_entry *se; + int64_t cmp = 0; + + list_for_each_entry(se, &hist_entry__sort_list, list) { + cmp = se->cmp(left, right); + if (cmp) + break; + } + + return cmp; +} + +static int64_t +hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) +{ + struct sort_entry *se; + int64_t cmp = 0; + + list_for_each_entry(se, &hist_entry__sort_list, list) { + int64_t (*f)(struct hist_entry *, struct hist_entry *); + + f = se->collapse ?: se->cmp; + + cmp = f(left, right); + if (cmp) + break; + } + + return cmp; +} + +/* + * collect histogram counts + */ +static void hist_hit(struct hist_entry *he, __u64 ip) +{ + unsigned int sym_size, offset; + struct symbol *sym = he->sym; + + he->count++; + + if (!sym || !sym->hist) + return; + + sym_size = sym->end - sym->start; + offset = ip - sym->start; + + if (offset >= sym_size) + return; + + sym->hist_sum++; + sym->hist[offset]++; + + if (verbose >= 3) + printf("%p %s: count++ [ip: %p, %08Lx] => %Ld\n", + (void *)(unsigned long)he->sym->start, + he->sym->name, + (void *)(unsigned long)ip, ip - he->sym->start, + sym->hist[offset]); +} + +static int +hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, + struct symbol *sym, __u64 ip, char level) +{ + struct rb_node **p = &hist.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *he; + struct hist_entry entry = { + .thread = thread, + .map = map, + .dso = dso, + .sym = sym, + .ip = ip, + .level = level, + .count = 1, + }; + int cmp; + + while (*p != NULL) { + parent = *p; + he = rb_entry(parent, struct hist_entry, rb_node); + + cmp = hist_entry__cmp(&entry, he); + + if (!cmp) { + hist_hit(he, ip); + + return 0; + } + + if (cmp < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + he = malloc(sizeof(*he)); + if (!he) + return -ENOMEM; + *he = entry; + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &hist); + + return 0; +} + +static void hist_entry__free(struct hist_entry *he) +{ + free(he); +} + +/* + * collapse the histogram + */ + +static struct rb_root collapse_hists; + +static void collapse__insert_entry(struct hist_entry *he) +{ + struct rb_node **p = &collapse_hists.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + int64_t cmp; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + + cmp = hist_entry__collapse(iter, he); + + if (!cmp) { + iter->count += he->count; + hist_entry__free(he); + return; + } + + if (cmp < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &collapse_hists); +} + +static void collapse__resort(void) +{ + struct rb_node *next; + struct hist_entry *n; + + if (!sort__need_collapse) + return; + + next = rb_first(&hist); + while (next) { + n = rb_entry(next, struct hist_entry, rb_node); + next = rb_next(&n->rb_node); + + rb_erase(&n->rb_node, &hist); + collapse__insert_entry(n); + } +} + +/* + * reverse the map, sort on count. + */ + +static struct rb_root output_hists; + +static void output__insert_entry(struct hist_entry *he) +{ + struct rb_node **p = &output_hists.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + + if (he->count > iter->count) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &output_hists); +} + +static void output__resort(void) +{ + struct rb_node *next; + struct hist_entry *n; + struct rb_root *tree = &hist; + + if (sort__need_collapse) + tree = &collapse_hists; + + next = rb_first(tree); + + while (next) { + n = rb_entry(next, struct hist_entry, rb_node); + next = rb_next(&n->rb_node); + + rb_erase(&n->rb_node, tree); + output__insert_entry(n); + } +} + +static void register_idle_thread(void) +{ + struct thread *thread = threads__findnew(0); + + if (thread == NULL || + thread__set_comm(thread, "[idle]")) { + fprintf(stderr, "problem inserting idle task.\n"); + exit(-1); + } +} + +static unsigned long total = 0, + total_mmap = 0, + total_comm = 0, + total_fork = 0, + total_unknown = 0; + +static int +process_overflow_event(event_t *event, unsigned long offset, unsigned long head) +{ + char level; + int show = 0; + struct dso *dso = NULL; + struct thread *thread = threads__findnew(event->ip.pid); + __u64 ip = event->ip.ip; + struct map *map = NULL; + + dprintf("%p [%p]: PERF_EVENT (IP, %d): %d: %p\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->header.misc, + event->ip.pid, + (void *)(long)ip); + + dprintf(" ... thread: %s:%d\n", thread->comm, thread->pid); + + if (thread == NULL) { + fprintf(stderr, "problem processing %d event, skipping it.\n", + event->header.type); + return -1; + } + + if (event->header.misc & PERF_EVENT_MISC_KERNEL) { + show = SHOW_KERNEL; + level = 'k'; + + dso = kernel_dso; + + dprintf(" ...... dso: %s\n", dso->name); + + } else if (event->header.misc & PERF_EVENT_MISC_USER) { + + show = SHOW_USER; + level = '.'; + + map = thread__find_map(thread, ip); + if (map != NULL) { + ip = map->map_ip(map, ip); + dso = map->dso; + } else { + /* + * If this is outside of all known maps, + * and is a negative address, try to look it + * up in the kernel dso, as it might be a + * vsyscall (which executes in user-mode): + */ + if ((long long)ip < 0) + dso = kernel_dso; + } + dprintf(" ...... dso: %s\n", dso ? dso->name : ""); + + } else { + show = SHOW_HV; + level = 'H'; + dprintf(" ...... dso: [hypervisor]\n"); + } + + if (show & show_mask) { + struct symbol *sym = NULL; + + if (dso) + sym = dso->find_symbol(dso, ip); + + if (hist_entry__add(thread, map, dso, sym, ip, level)) { + fprintf(stderr, + "problem incrementing symbol count, skipping event\n"); + return -1; + } + } + total++; + + return 0; +} + +static int +process_mmap_event(event_t *event, unsigned long offset, unsigned long head) +{ + struct thread *thread = threads__findnew(event->mmap.pid); + struct map *map = map__new(&event->mmap); + + dprintf("%p [%p]: PERF_EVENT_MMAP %d: [%p(%p) @ %p]: %s\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->mmap.pid, + (void *)(long)event->mmap.start, + (void *)(long)event->mmap.len, + (void *)(long)event->mmap.pgoff, + event->mmap.filename); + + if (thread == NULL || map == NULL) { + dprintf("problem processing PERF_EVENT_MMAP, skipping event.\n"); + return 0; + } + + thread__insert_map(thread, map); + total_mmap++; + + return 0; +} + +static int +process_comm_event(event_t *event, unsigned long offset, unsigned long head) +{ + struct thread *thread = threads__findnew(event->comm.pid); + + dprintf("%p [%p]: PERF_EVENT_COMM: %s:%d\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->comm.comm, event->comm.pid); + + if (thread == NULL || + thread__set_comm(thread, event->comm.comm)) { + dprintf("problem processing PERF_EVENT_COMM, skipping event.\n"); + return -1; + } + total_comm++; + + return 0; +} + +static int +process_fork_event(event_t *event, unsigned long offset, unsigned long head) +{ + struct thread *thread = threads__findnew(event->fork.pid); + struct thread *parent = threads__findnew(event->fork.ppid); + + dprintf("%p [%p]: PERF_EVENT_FORK: %d:%d\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->fork.pid, event->fork.ppid); + + if (!thread || !parent || thread__fork(thread, parent)) { + dprintf("problem processing PERF_EVENT_FORK, skipping event.\n"); + return -1; + } + total_fork++; + + return 0; +} + +static int +process_period_event(event_t *event, unsigned long offset, unsigned long head) +{ + dprintf("%p [%p]: PERF_EVENT_PERIOD: time:%Ld, id:%Ld: period:%Ld\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->period.time, + event->period.id, + event->period.sample_period); + + return 0; +} + +static int +process_event(event_t *event, unsigned long offset, unsigned long head) +{ + if (event->header.misc & PERF_EVENT_MISC_OVERFLOW) + return process_overflow_event(event, offset, head); + + switch (event->header.type) { + case PERF_EVENT_MMAP: + return process_mmap_event(event, offset, head); + + case PERF_EVENT_COMM: + return process_comm_event(event, offset, head); + + case PERF_EVENT_FORK: + return process_fork_event(event, offset, head); + + case PERF_EVENT_PERIOD: + return process_period_event(event, offset, head); + /* + * We dont process them right now but they are fine: + */ + + case PERF_EVENT_THROTTLE: + case PERF_EVENT_UNTHROTTLE: + return 0; + + default: + return -1; + } + + return 0; +} + +static int +parse_line(FILE *file, struct symbol *sym, __u64 start, __u64 len) +{ + char *line = NULL, *tmp, *tmp2; + unsigned int offset; + size_t line_len; + __u64 line_ip; + int ret; + char *c; + + if (getline(&line, &line_len, file) < 0) + return -1; + if (!line) + return -1; + + c = strchr(line, '\n'); + if (c) + *c = 0; + + line_ip = -1; + offset = 0; + ret = -2; + + /* + * Strip leading spaces: + */ + tmp = line; + while (*tmp) { + if (*tmp != ' ') + break; + tmp++; + } + + if (*tmp) { + /* + * Parse hexa addresses followed by ':' + */ + line_ip = strtoull(tmp, &tmp2, 16); + if (*tmp2 != ':') + line_ip = -1; + } + + if (line_ip != -1) { + unsigned int hits = 0; + double percent = 0.0; + char *color = PERF_COLOR_NORMAL; + + offset = line_ip - start; + if (offset < len) + hits = sym->hist[offset]; + + if (sym->hist_sum) + percent = 100.0 * hits / sym->hist_sum; + + /* + * We color high-overhead entries in red, mid-overhead + * entries in green - and keep the low overhead places + * normal: + */ + if (percent >= 5.0) + color = PERF_COLOR_RED; + else { + if (percent > 0.5) + color = PERF_COLOR_GREEN; + } + + color_fprintf(stdout, color, " %7.2f", percent); + printf(" : "); + color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", line); + } else { + if (!*line) + printf(" :\n"); + else + printf(" : %s\n", line); + } + + return 0; +} + +static void annotate_sym(struct dso *dso, struct symbol *sym) +{ + char *filename = dso->name; + __u64 start, end, len; + char command[PATH_MAX*2]; + FILE *file; + + if (!filename) + return; + if (dso == kernel_dso) + filename = vmlinux; + + printf("\n------------------------------------------------\n"); + printf(" Percent | Source code & Disassembly of %s\n", filename); + printf("------------------------------------------------\n"); + + if (verbose >= 2) + printf("annotating [%p] %30s : [%p] %30s\n", dso, dso->name, sym, sym->name); + + start = sym->obj_start; + if (!start) + start = sym->start; + + end = start + sym->end - sym->start + 1; + len = sym->end - sym->start; + + sprintf(command, "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s", (__u64)start, (__u64)end, filename); + + if (verbose >= 3) + printf("doing: %s\n", command); + + file = popen(command, "r"); + if (!file) + return; + + while (!feof(file)) { + if (parse_line(file, sym, start, len) < 0) + break; + } + + pclose(file); +} + +static void find_annotations(void) +{ + struct rb_node *nd; + struct dso *dso; + int count = 0; + + list_for_each_entry(dso, &dsos, node) { + + for (nd = rb_first(&dso->syms); nd; nd = rb_next(nd)) { + struct symbol *sym = rb_entry(nd, struct symbol, rb_node); + + if (sym->hist) { + annotate_sym(dso, sym); + count++; + } + } + } + + if (!count) + printf(" Error: symbol '%s' not present amongst the samples.\n", sym_hist_filter); +} + +static int __cmd_annotate(void) +{ + int ret, rc = EXIT_FAILURE; + unsigned long offset = 0; + unsigned long head = 0; + struct stat stat; + event_t *event; + uint32_t size; + char *buf; + + register_idle_thread(); + + input = open(input_name, O_RDONLY); + if (input < 0) { + perror("failed to open file"); + exit(-1); + } + + ret = fstat(input, &stat); + if (ret < 0) { + perror("failed to stat file"); + exit(-1); + } + + if (!stat.st_size) { + fprintf(stderr, "zero-sized file, nothing to do!\n"); + exit(0); + } + + if (load_kernel() < 0) { + perror("failed to load kernel symbols"); + return EXIT_FAILURE; + } + +remap: + buf = (char *)mmap(NULL, page_size * mmap_window, PROT_READ, + MAP_SHARED, input, offset); + if (buf == MAP_FAILED) { + perror("failed to mmap file"); + exit(-1); + } + +more: + event = (event_t *)(buf + head); + + size = event->header.size; + if (!size) + size = 8; + + if (head + event->header.size >= page_size * mmap_window) { + unsigned long shift = page_size * (head / page_size); + int ret; + + ret = munmap(buf, page_size * mmap_window); + assert(ret == 0); + + offset += shift; + head -= shift; + goto remap; + } + + size = event->header.size; + + dprintf("%p [%p]: event: %d\n", + (void *)(offset + head), + (void *)(long)event->header.size, + event->header.type); + + if (!size || process_event(event, offset, head) < 0) { + + dprintf("%p [%p]: skipping unknown header type: %d\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->header.type); + + total_unknown++; + + /* + * assume we lost track of the stream, check alignment, and + * increment a single u64 in the hope to catch on again 'soon'. + */ + + if (unlikely(head & 7)) + head &= ~7ULL; + + size = 8; + } + + head += size; + + if (offset + head < stat.st_size) + goto more; + + rc = EXIT_SUCCESS; + close(input); + + dprintf(" IP events: %10ld\n", total); + dprintf(" mmap events: %10ld\n", total_mmap); + dprintf(" comm events: %10ld\n", total_comm); + dprintf(" fork events: %10ld\n", total_fork); + dprintf(" unknown events: %10ld\n", total_unknown); + + if (dump_trace) + return 0; + + if (verbose >= 3) + threads__fprintf(stdout); + + if (verbose >= 2) + dsos__fprintf(stdout); + + collapse__resort(); + output__resort(); + + find_annotations(); + + return rc; +} + +static const char * const annotate_usage[] = { + "perf annotate [] ", + NULL +}; + +static const struct option options[] = { + OPT_STRING('i', "input", &input_name, "file", + "input file name"), + OPT_STRING('s', "symbol", &sym_hist_filter, "symbol", + "symbol to annotate"), + OPT_BOOLEAN('v', "verbose", &verbose, + "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, + "dump raw trace in ASCII"), + OPT_STRING('k', "vmlinux", &vmlinux, "file", "vmlinux pathname"), + OPT_END() +}; + +static void setup_sorting(void) +{ + char *tmp, *tok, *str = strdup(sort_order); + + for (tok = strtok_r(str, ", ", &tmp); + tok; tok = strtok_r(NULL, ", ", &tmp)) { + if (sort_dimension__add(tok) < 0) { + error("Unknown --sort key: `%s'", tok); + usage_with_options(annotate_usage, options); + } + } + + free(str); +} + +int cmd_annotate(int argc, const char **argv, const char *prefix) +{ + symbol__init(); + + page_size = getpagesize(); + + argc = parse_options(argc, argv, options, annotate_usage, 0); + + setup_sorting(); + + if (argc) { + /* + * Special case: if there's an argument left then assume tha + * it's a symbol filter: + */ + if (argc > 1) + usage_with_options(annotate_usage, options); + + sym_hist_filter = argv[0]; + } + + if (!sym_hist_filter) + usage_with_options(annotate_usage, options); + + setup_pager(); + + return __cmd_annotate(); +} diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c new file mode 100644 index 0000000000000000000000000000000000000000..0f32dc3f3c4c7a45b5d18bf8fac59aabedb8069f --- /dev/null +++ b/tools/perf/builtin-help.c @@ -0,0 +1,461 @@ +/* + * builtin-help.c + * + * Builtin help command + */ +#include "util/cache.h" +#include "builtin.h" +#include "util/exec_cmd.h" +#include "common-cmds.h" +#include "util/parse-options.h" +#include "util/run-command.h" +#include "util/help.h" + +static struct man_viewer_list { + struct man_viewer_list *next; + char name[FLEX_ARRAY]; +} *man_viewer_list; + +static struct man_viewer_info_list { + struct man_viewer_info_list *next; + const char *info; + char name[FLEX_ARRAY]; +} *man_viewer_info_list; + +enum help_format { + HELP_FORMAT_MAN, + HELP_FORMAT_INFO, + HELP_FORMAT_WEB, +}; + +static int show_all = 0; +static enum help_format help_format = HELP_FORMAT_MAN; +static struct option builtin_help_options[] = { + OPT_BOOLEAN('a', "all", &show_all, "print all available commands"), + OPT_SET_INT('m', "man", &help_format, "show man page", HELP_FORMAT_MAN), + OPT_SET_INT('w', "web", &help_format, "show manual in web browser", + HELP_FORMAT_WEB), + OPT_SET_INT('i', "info", &help_format, "show info page", + HELP_FORMAT_INFO), + OPT_END(), +}; + +static const char * const builtin_help_usage[] = { + "perf help [--all] [--man|--web|--info] [command]", + NULL +}; + +static enum help_format parse_help_format(const char *format) +{ + if (!strcmp(format, "man")) + return HELP_FORMAT_MAN; + if (!strcmp(format, "info")) + return HELP_FORMAT_INFO; + if (!strcmp(format, "web") || !strcmp(format, "html")) + return HELP_FORMAT_WEB; + die("unrecognized help format '%s'", format); +} + +static const char *get_man_viewer_info(const char *name) +{ + struct man_viewer_info_list *viewer; + + for (viewer = man_viewer_info_list; viewer; viewer = viewer->next) + { + if (!strcasecmp(name, viewer->name)) + return viewer->info; + } + return NULL; +} + +static int check_emacsclient_version(void) +{ + struct strbuf buffer = STRBUF_INIT; + struct child_process ec_process; + const char *argv_ec[] = { "emacsclient", "--version", NULL }; + int version; + + /* emacsclient prints its version number on stderr */ + memset(&ec_process, 0, sizeof(ec_process)); + ec_process.argv = argv_ec; + ec_process.err = -1; + ec_process.stdout_to_stderr = 1; + if (start_command(&ec_process)) { + fprintf(stderr, "Failed to start emacsclient.\n"); + return -1; + } + strbuf_read(&buffer, ec_process.err, 20); + close(ec_process.err); + + /* + * Don't bother checking return value, because "emacsclient --version" + * seems to always exits with code 1. + */ + finish_command(&ec_process); + + if (prefixcmp(buffer.buf, "emacsclient")) { + fprintf(stderr, "Failed to parse emacsclient version.\n"); + strbuf_release(&buffer); + return -1; + } + + strbuf_remove(&buffer, 0, strlen("emacsclient")); + version = atoi(buffer.buf); + + if (version < 22) { + fprintf(stderr, + "emacsclient version '%d' too old (< 22).\n", + version); + strbuf_release(&buffer); + return -1; + } + + strbuf_release(&buffer); + return 0; +} + +static void exec_woman_emacs(const char* path, const char *page) +{ + if (!check_emacsclient_version()) { + /* This works only with emacsclient version >= 22. */ + struct strbuf man_page = STRBUF_INIT; + + if (!path) + path = "emacsclient"; + strbuf_addf(&man_page, "(woman \"%s\")", page); + execlp(path, "emacsclient", "-e", man_page.buf, NULL); + warning("failed to exec '%s': %s", path, strerror(errno)); + } +} + +static void exec_man_konqueror(const char* path, const char *page) +{ + const char *display = getenv("DISPLAY"); + if (display && *display) { + struct strbuf man_page = STRBUF_INIT; + const char *filename = "kfmclient"; + + /* It's simpler to launch konqueror using kfmclient. */ + if (path) { + const char *file = strrchr(path, '/'); + if (file && !strcmp(file + 1, "konqueror")) { + char *new = strdup(path); + char *dest = strrchr(new, '/'); + + /* strlen("konqueror") == strlen("kfmclient") */ + strcpy(dest + 1, "kfmclient"); + path = new; + } + if (file) + filename = file; + } else + path = "kfmclient"; + strbuf_addf(&man_page, "man:%s(1)", page); + execlp(path, filename, "newTab", man_page.buf, NULL); + warning("failed to exec '%s': %s", path, strerror(errno)); + } +} + +static void exec_man_man(const char* path, const char *page) +{ + if (!path) + path = "man"; + execlp(path, "man", page, NULL); + warning("failed to exec '%s': %s", path, strerror(errno)); +} + +static void exec_man_cmd(const char *cmd, const char *page) +{ + struct strbuf shell_cmd = STRBUF_INIT; + strbuf_addf(&shell_cmd, "%s %s", cmd, page); + execl("/bin/sh", "sh", "-c", shell_cmd.buf, NULL); + warning("failed to exec '%s': %s", cmd, strerror(errno)); +} + +static void add_man_viewer(const char *name) +{ + struct man_viewer_list **p = &man_viewer_list; + size_t len = strlen(name); + + while (*p) + p = &((*p)->next); + *p = calloc(1, (sizeof(**p) + len + 1)); + strncpy((*p)->name, name, len); +} + +static int supported_man_viewer(const char *name, size_t len) +{ + return (!strncasecmp("man", name, len) || + !strncasecmp("woman", name, len) || + !strncasecmp("konqueror", name, len)); +} + +static void do_add_man_viewer_info(const char *name, + size_t len, + const char *value) +{ + struct man_viewer_info_list *new = calloc(1, sizeof(*new) + len + 1); + + strncpy(new->name, name, len); + new->info = strdup(value); + new->next = man_viewer_info_list; + man_viewer_info_list = new; +} + +static int add_man_viewer_path(const char *name, + size_t len, + const char *value) +{ + if (supported_man_viewer(name, len)) + do_add_man_viewer_info(name, len, value); + else + warning("'%s': path for unsupported man viewer.\n" + "Please consider using 'man..cmd' instead.", + name); + + return 0; +} + +static int add_man_viewer_cmd(const char *name, + size_t len, + const char *value) +{ + if (supported_man_viewer(name, len)) + warning("'%s': cmd for supported man viewer.\n" + "Please consider using 'man..path' instead.", + name); + else + do_add_man_viewer_info(name, len, value); + + return 0; +} + +static int add_man_viewer_info(const char *var, const char *value) +{ + const char *name = var + 4; + const char *subkey = strrchr(name, '.'); + + if (!subkey) + return error("Config with no key for man viewer: %s", name); + + if (!strcmp(subkey, ".path")) { + if (!value) + return config_error_nonbool(var); + return add_man_viewer_path(name, subkey - name, value); + } + if (!strcmp(subkey, ".cmd")) { + if (!value) + return config_error_nonbool(var); + return add_man_viewer_cmd(name, subkey - name, value); + } + + warning("'%s': unsupported man viewer sub key.", subkey); + return 0; +} + +static int perf_help_config(const char *var, const char *value, void *cb) +{ + if (!strcmp(var, "help.format")) { + if (!value) + return config_error_nonbool(var); + help_format = parse_help_format(value); + return 0; + } + if (!strcmp(var, "man.viewer")) { + if (!value) + return config_error_nonbool(var); + add_man_viewer(value); + return 0; + } + if (!prefixcmp(var, "man.")) + return add_man_viewer_info(var, value); + + return perf_default_config(var, value, cb); +} + +static struct cmdnames main_cmds, other_cmds; + +void list_common_cmds_help(void) +{ + int i, longest = 0; + + for (i = 0; i < ARRAY_SIZE(common_cmds); i++) { + if (longest < strlen(common_cmds[i].name)) + longest = strlen(common_cmds[i].name); + } + + puts(" The most commonly used perf commands are:"); + for (i = 0; i < ARRAY_SIZE(common_cmds); i++) { + printf(" %s ", common_cmds[i].name); + mput_char(' ', longest - strlen(common_cmds[i].name)); + puts(common_cmds[i].help); + } +} + +static int is_perf_command(const char *s) +{ + return is_in_cmdlist(&main_cmds, s) || + is_in_cmdlist(&other_cmds, s); +} + +static const char *prepend(const char *prefix, const char *cmd) +{ + size_t pre_len = strlen(prefix); + size_t cmd_len = strlen(cmd); + char *p = malloc(pre_len + cmd_len + 1); + memcpy(p, prefix, pre_len); + strcpy(p + pre_len, cmd); + return p; +} + +static const char *cmd_to_page(const char *perf_cmd) +{ + if (!perf_cmd) + return "perf"; + else if (!prefixcmp(perf_cmd, "perf")) + return perf_cmd; + else if (is_perf_command(perf_cmd)) + return prepend("perf-", perf_cmd); + else + return prepend("perf-", perf_cmd); +} + +static void setup_man_path(void) +{ + struct strbuf new_path = STRBUF_INIT; + const char *old_path = getenv("MANPATH"); + + /* We should always put ':' after our path. If there is no + * old_path, the ':' at the end will let 'man' to try + * system-wide paths after ours to find the manual page. If + * there is old_path, we need ':' as delimiter. */ + strbuf_addstr(&new_path, system_path(PERF_MAN_PATH)); + strbuf_addch(&new_path, ':'); + if (old_path) + strbuf_addstr(&new_path, old_path); + + setenv("MANPATH", new_path.buf, 1); + + strbuf_release(&new_path); +} + +static void exec_viewer(const char *name, const char *page) +{ + const char *info = get_man_viewer_info(name); + + if (!strcasecmp(name, "man")) + exec_man_man(info, page); + else if (!strcasecmp(name, "woman")) + exec_woman_emacs(info, page); + else if (!strcasecmp(name, "konqueror")) + exec_man_konqueror(info, page); + else if (info) + exec_man_cmd(info, page); + else + warning("'%s': unknown man viewer.", name); +} + +static void show_man_page(const char *perf_cmd) +{ + struct man_viewer_list *viewer; + const char *page = cmd_to_page(perf_cmd); + const char *fallback = getenv("PERF_MAN_VIEWER"); + + setup_man_path(); + for (viewer = man_viewer_list; viewer; viewer = viewer->next) + { + exec_viewer(viewer->name, page); /* will return when unable */ + } + if (fallback) + exec_viewer(fallback, page); + exec_viewer("man", page); + die("no man viewer handled the request"); +} + +static void show_info_page(const char *perf_cmd) +{ + const char *page = cmd_to_page(perf_cmd); + setenv("INFOPATH", system_path(PERF_INFO_PATH), 1); + execlp("info", "info", "perfman", page, NULL); +} + +static void get_html_page_path(struct strbuf *page_path, const char *page) +{ + struct stat st; + const char *html_path = system_path(PERF_HTML_PATH); + + /* Check that we have a perf documentation directory. */ + if (stat(mkpath("%s/perf.html", html_path), &st) + || !S_ISREG(st.st_mode)) + die("'%s': not a documentation directory.", html_path); + + strbuf_init(page_path, 0); + strbuf_addf(page_path, "%s/%s.html", html_path, page); +} + +/* + * If open_html is not defined in a platform-specific way (see for + * example compat/mingw.h), we use the script web--browse to display + * HTML. + */ +#ifndef open_html +static void open_html(const char *path) +{ + execl_perf_cmd("web--browse", "-c", "help.browser", path, NULL); +} +#endif + +static void show_html_page(const char *perf_cmd) +{ + const char *page = cmd_to_page(perf_cmd); + struct strbuf page_path; /* it leaks but we exec bellow */ + + get_html_page_path(&page_path, page); + + open_html(page_path.buf); +} + +int cmd_help(int argc, const char **argv, const char *prefix) +{ + const char *alias; + load_command_list("perf-", &main_cmds, &other_cmds); + + perf_config(perf_help_config, NULL); + + argc = parse_options(argc, argv, builtin_help_options, + builtin_help_usage, 0); + + if (show_all) { + printf("\n usage: %s\n\n", perf_usage_string); + list_commands("perf commands", &main_cmds, &other_cmds); + printf(" %s\n\n", perf_more_info_string); + return 0; + } + + if (!argv[0]) { + printf("\n usage: %s\n\n", perf_usage_string); + list_common_cmds_help(); + printf("\n %s\n\n", perf_more_info_string); + return 0; + } + + alias = alias_lookup(argv[0]); + if (alias && !is_perf_command(argv[0])) { + printf("`perf %s' is aliased to `%s'\n", argv[0], alias); + return 0; + } + + switch (help_format) { + case HELP_FORMAT_MAN: + show_man_page(argv[0]); + break; + case HELP_FORMAT_INFO: + show_info_page(argv[0]); + break; + case HELP_FORMAT_WEB: + show_html_page(argv[0]); + break; + } + + return 0; +} diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c new file mode 100644 index 0000000000000000000000000000000000000000..fe60e37c96efc85e60e83d59d1cdb7127fe198c8 --- /dev/null +++ b/tools/perf/builtin-list.c @@ -0,0 +1,20 @@ +/* + * builtin-list.c + * + * Builtin list command: list all event types + * + * Copyright (C) 2009, Thomas Gleixner + * Copyright (C) 2008-2009, Red Hat Inc, Ingo Molnar + */ +#include "builtin.h" + +#include "perf.h" + +#include "util/parse-options.h" +#include "util/parse-events.h" + +int cmd_list(int argc, const char **argv, const char *prefix) +{ + print_events(); + return 0; +} diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c new file mode 100644 index 0000000000000000000000000000000000000000..29259e74dcfa7b4b9d89202ed0987d2312b0eec5 --- /dev/null +++ b/tools/perf/builtin-record.c @@ -0,0 +1,582 @@ +/* + * builtin-record.c + * + * Builtin record command: Record the profile of a workload + * (or a CPU, or a PID) into the perf.data output file - for + * later analysis via perf report. + */ +#include "builtin.h" + +#include "perf.h" + +#include "util/util.h" +#include "util/parse-options.h" +#include "util/parse-events.h" +#include "util/string.h" + +#include +#include + +#define ALIGN(x, a) __ALIGN_MASK(x, (typeof(x))(a)-1) +#define __ALIGN_MASK(x, mask) (((x)+(mask))&~(mask)) + +static int fd[MAX_NR_CPUS][MAX_COUNTERS]; + +static long default_interval = 100000; + +static int nr_cpus = 0; +static unsigned int page_size; +static unsigned int mmap_pages = 128; +static int freq = 0; +static int output; +static const char *output_name = "perf.data"; +static int group = 0; +static unsigned int realtime_prio = 0; +static int system_wide = 0; +static pid_t target_pid = -1; +static int inherit = 1; +static int force = 0; +static int append_file = 0; +static int verbose = 0; + +static long samples; +static struct timeval last_read; +static struct timeval this_read; + +static __u64 bytes_written; + +static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS]; + +static int nr_poll; +static int nr_cpu; + +struct mmap_event { + struct perf_event_header header; + __u32 pid; + __u32 tid; + __u64 start; + __u64 len; + __u64 pgoff; + char filename[PATH_MAX]; +}; + +struct comm_event { + struct perf_event_header header; + __u32 pid; + __u32 tid; + char comm[16]; +}; + + +struct mmap_data { + int counter; + void *base; + unsigned int mask; + unsigned int prev; +}; + +static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS]; + +static unsigned int mmap_read_head(struct mmap_data *md) +{ + struct perf_counter_mmap_page *pc = md->base; + int head; + + head = pc->data_head; + rmb(); + + return head; +} + +static void mmap_read(struct mmap_data *md) +{ + unsigned int head = mmap_read_head(md); + unsigned int old = md->prev; + unsigned char *data = md->base + page_size; + unsigned long size; + void *buf; + int diff; + + gettimeofday(&this_read, NULL); + + /* + * If we're further behind than half the buffer, there's a chance + * the writer will bite our tail and mess up the samples under us. + * + * If we somehow ended up ahead of the head, we got messed up. + * + * In either case, truncate and restart at head. + */ + diff = head - old; + if (diff > md->mask / 2 || diff < 0) { + struct timeval iv; + unsigned long msecs; + + timersub(&this_read, &last_read, &iv); + msecs = iv.tv_sec*1000 + iv.tv_usec/1000; + + fprintf(stderr, "WARNING: failed to keep up with mmap data." + " Last read %lu msecs ago.\n", msecs); + + /* + * head points to a known good entry, start there. + */ + old = head; + } + + last_read = this_read; + + if (old != head) + samples++; + + size = head - old; + + if ((old & md->mask) + size != (head & md->mask)) { + buf = &data[old & md->mask]; + size = md->mask + 1 - (old & md->mask); + old += size; + + while (size) { + int ret = write(output, buf, size); + + if (ret < 0) + die("failed to write"); + + size -= ret; + buf += ret; + + bytes_written += ret; + } + } + + buf = &data[old & md->mask]; + size = head - old; + old += size; + + while (size) { + int ret = write(output, buf, size); + + if (ret < 0) + die("failed to write"); + + size -= ret; + buf += ret; + + bytes_written += ret; + } + + md->prev = old; +} + +static volatile int done = 0; +static volatile int signr = -1; + +static void sig_handler(int sig) +{ + done = 1; + signr = sig; +} + +static void sig_atexit(void) +{ + if (signr == -1) + return; + + signal(signr, SIG_DFL); + kill(getpid(), signr); +} + +static void pid_synthesize_comm_event(pid_t pid, int full) +{ + struct comm_event comm_ev; + char filename[PATH_MAX]; + char bf[BUFSIZ]; + int fd, ret; + size_t size; + char *field, *sep; + DIR *tasks; + struct dirent dirent, *next; + + snprintf(filename, sizeof(filename), "/proc/%d/stat", pid); + + fd = open(filename, O_RDONLY); + if (fd < 0) { + fprintf(stderr, "couldn't open %s\n", filename); + exit(EXIT_FAILURE); + } + if (read(fd, bf, sizeof(bf)) < 0) { + fprintf(stderr, "couldn't read %s\n", filename); + exit(EXIT_FAILURE); + } + close(fd); + + /* 9027 (cat) R 6747 9027 6747 34816 9027 ... */ + memset(&comm_ev, 0, sizeof(comm_ev)); + field = strchr(bf, '('); + if (field == NULL) + goto out_failure; + sep = strchr(++field, ')'); + if (sep == NULL) + goto out_failure; + size = sep - field; + memcpy(comm_ev.comm, field, size++); + + comm_ev.pid = pid; + comm_ev.header.type = PERF_EVENT_COMM; + size = ALIGN(size, sizeof(__u64)); + comm_ev.header.size = sizeof(comm_ev) - (sizeof(comm_ev.comm) - size); + + if (!full) { + comm_ev.tid = pid; + + ret = write(output, &comm_ev, comm_ev.header.size); + if (ret < 0) { + perror("failed to write"); + exit(-1); + } + return; + } + + snprintf(filename, sizeof(filename), "/proc/%d/task", pid); + + tasks = opendir(filename); + while (!readdir_r(tasks, &dirent, &next) && next) { + char *end; + pid = strtol(dirent.d_name, &end, 10); + if (*end) + continue; + + comm_ev.tid = pid; + + ret = write(output, &comm_ev, comm_ev.header.size); + if (ret < 0) { + perror("failed to write"); + exit(-1); + } + } + closedir(tasks); + return; + +out_failure: + fprintf(stderr, "couldn't get COMM and pgid, malformed %s\n", + filename); + exit(EXIT_FAILURE); +} + +static void pid_synthesize_mmap_samples(pid_t pid) +{ + char filename[PATH_MAX]; + FILE *fp; + + snprintf(filename, sizeof(filename), "/proc/%d/maps", pid); + + fp = fopen(filename, "r"); + if (fp == NULL) { + fprintf(stderr, "couldn't open %s\n", filename); + exit(EXIT_FAILURE); + } + while (1) { + char bf[BUFSIZ], *pbf = bf; + struct mmap_event mmap_ev = { + .header.type = PERF_EVENT_MMAP, + }; + int n; + size_t size; + if (fgets(bf, sizeof(bf), fp) == NULL) + break; + + /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ + n = hex2u64(pbf, &mmap_ev.start); + if (n < 0) + continue; + pbf += n + 1; + n = hex2u64(pbf, &mmap_ev.len); + if (n < 0) + continue; + pbf += n + 3; + if (*pbf == 'x') { /* vm_exec */ + char *execname = strrchr(bf, ' '); + + if (execname == NULL || execname[1] != '/') + continue; + + execname += 1; + size = strlen(execname); + execname[size - 1] = '\0'; /* Remove \n */ + memcpy(mmap_ev.filename, execname, size); + size = ALIGN(size, sizeof(__u64)); + mmap_ev.len -= mmap_ev.start; + mmap_ev.header.size = (sizeof(mmap_ev) - + (sizeof(mmap_ev.filename) - size)); + mmap_ev.pid = pid; + mmap_ev.tid = pid; + + if (write(output, &mmap_ev, mmap_ev.header.size) < 0) { + perror("failed to write"); + exit(-1); + } + } + } + + fclose(fp); +} + +static void synthesize_samples(void) +{ + DIR *proc; + struct dirent dirent, *next; + + proc = opendir("/proc"); + + while (!readdir_r(proc, &dirent, &next) && next) { + char *end; + pid_t pid; + + pid = strtol(dirent.d_name, &end, 10); + if (*end) /* only interested in proper numerical dirents */ + continue; + + pid_synthesize_comm_event(pid, 1); + pid_synthesize_mmap_samples(pid); + } + + closedir(proc); +} + +static int group_fd; + +static void create_counter(int counter, int cpu, pid_t pid) +{ + struct perf_counter_attr *attr = attrs + counter; + int track = 1; + + attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; + if (freq) { + attr->sample_type |= PERF_SAMPLE_PERIOD; + attr->freq = 1; + attr->sample_freq = freq; + } + attr->mmap = track; + attr->comm = track; + attr->inherit = (cpu < 0) && inherit; + attr->disabled = 1; + + track = 0; /* only the first counter needs these */ + +try_again: + fd[nr_cpu][counter] = sys_perf_counter_open(attr, pid, cpu, group_fd, 0); + + if (fd[nr_cpu][counter] < 0) { + int err = errno; + + if (err == EPERM) + die("Permission error - are you root?\n"); + + /* + * If it's cycles then fall back to hrtimer + * based cpu-clock-tick sw counter, which + * is always available even if no PMU support: + */ + if (attr->type == PERF_TYPE_HARDWARE + && attr->config == PERF_COUNT_HW_CPU_CYCLES) { + + if (verbose) + warning(" ... trying to fall back to cpu-clock-ticks\n"); + attr->type = PERF_TYPE_SOFTWARE; + attr->config = PERF_COUNT_SW_CPU_CLOCK; + goto try_again; + } + printf("\n"); + error("perfcounter syscall returned with %d (%s)\n", + fd[nr_cpu][counter], strerror(err)); + die("No CONFIG_PERF_COUNTERS=y kernel support configured?\n"); + exit(-1); + } + + assert(fd[nr_cpu][counter] >= 0); + fcntl(fd[nr_cpu][counter], F_SETFL, O_NONBLOCK); + + /* + * First counter acts as the group leader: + */ + if (group && group_fd == -1) + group_fd = fd[nr_cpu][counter]; + + event_array[nr_poll].fd = fd[nr_cpu][counter]; + event_array[nr_poll].events = POLLIN; + nr_poll++; + + mmap_array[nr_cpu][counter].counter = counter; + mmap_array[nr_cpu][counter].prev = 0; + mmap_array[nr_cpu][counter].mask = mmap_pages*page_size - 1; + mmap_array[nr_cpu][counter].base = mmap(NULL, (mmap_pages+1)*page_size, + PROT_READ, MAP_SHARED, fd[nr_cpu][counter], 0); + if (mmap_array[nr_cpu][counter].base == MAP_FAILED) { + error("failed to mmap with %d (%s)\n", errno, strerror(errno)); + exit(-1); + } + + ioctl(fd[nr_cpu][counter], PERF_COUNTER_IOC_ENABLE); +} + +static void open_counters(int cpu, pid_t pid) +{ + int counter; + + if (pid > 0) { + pid_synthesize_comm_event(pid, 0); + pid_synthesize_mmap_samples(pid); + } + + group_fd = -1; + for (counter = 0; counter < nr_counters; counter++) + create_counter(counter, cpu, pid); + + nr_cpu++; +} + +static int __cmd_record(int argc, const char **argv) +{ + int i, counter; + struct stat st; + pid_t pid; + int flags; + int ret; + + page_size = sysconf(_SC_PAGE_SIZE); + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + assert(nr_cpus <= MAX_NR_CPUS); + assert(nr_cpus >= 0); + + if (!stat(output_name, &st) && !force && !append_file) { + fprintf(stderr, "Error, output file %s exists, use -A to append or -f to overwrite.\n", + output_name); + exit(-1); + } + + flags = O_CREAT|O_RDWR; + if (append_file) + flags |= O_APPEND; + else + flags |= O_TRUNC; + + output = open(output_name, flags, S_IRUSR|S_IWUSR); + if (output < 0) { + perror("failed to create output file"); + exit(-1); + } + + if (!system_wide) { + open_counters(-1, target_pid != -1 ? target_pid : getpid()); + } else for (i = 0; i < nr_cpus; i++) + open_counters(i, target_pid); + + atexit(sig_atexit); + signal(SIGCHLD, sig_handler); + signal(SIGINT, sig_handler); + + if (target_pid == -1 && argc) { + pid = fork(); + if (pid < 0) + perror("failed to fork"); + + if (!pid) { + if (execvp(argv[0], (char **)argv)) { + perror(argv[0]); + exit(-1); + } + } + } + + if (realtime_prio) { + struct sched_param param; + + param.sched_priority = realtime_prio; + if (sched_setscheduler(0, SCHED_FIFO, ¶m)) { + printf("Could not set realtime priority.\n"); + exit(-1); + } + } + + if (system_wide) + synthesize_samples(); + + while (!done) { + int hits = samples; + + for (i = 0; i < nr_cpu; i++) { + for (counter = 0; counter < nr_counters; counter++) + mmap_read(&mmap_array[i][counter]); + } + + if (hits == samples) + ret = poll(event_array, nr_poll, 100); + } + + /* + * Approximate RIP event size: 24 bytes. + */ + fprintf(stderr, + "[ perf record: Captured and wrote %.3f MB %s (~%lld samples) ]\n", + (double)bytes_written / 1024.0 / 1024.0, + output_name, + bytes_written / 24); + + return 0; +} + +static const char * const record_usage[] = { + "perf record [] []", + "perf record [] -- []", + NULL +}; + +static const struct option options[] = { + OPT_CALLBACK('e', "event", NULL, "event", + "event selector. use 'perf list' to list available events", + parse_events), + OPT_INTEGER('p', "pid", &target_pid, + "record events on existing pid"), + OPT_INTEGER('r', "realtime", &realtime_prio, + "collect data with this RT SCHED_FIFO priority"), + OPT_BOOLEAN('a', "all-cpus", &system_wide, + "system-wide collection from all CPUs"), + OPT_BOOLEAN('A', "append", &append_file, + "append to the output file to do incremental profiling"), + OPT_BOOLEAN('f', "force", &force, + "overwrite existing data file"), + OPT_LONG('c', "count", &default_interval, + "event period to sample"), + OPT_STRING('o', "output", &output_name, "file", + "output file name"), + OPT_BOOLEAN('i', "inherit", &inherit, + "child tasks inherit counters"), + OPT_INTEGER('F', "freq", &freq, + "profile at this frequency"), + OPT_INTEGER('m', "mmap-pages", &mmap_pages, + "number of mmap data pages"), + OPT_BOOLEAN('v', "verbose", &verbose, + "be more verbose (show counter open errors, etc)"), + OPT_END() +}; + +int cmd_record(int argc, const char **argv, const char *prefix) +{ + int counter; + + argc = parse_options(argc, argv, options, record_usage, 0); + if (!argc && target_pid == -1 && !system_wide) + usage_with_options(record_usage, options); + + if (!nr_counters) + nr_counters = 1; + + for (counter = 0; counter < nr_counters; counter++) { + if (attrs[counter].sample_period) + continue; + + attrs[counter].sample_period = default_interval; + } + + return __cmd_record(argc, argv); +} diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c new file mode 100644 index 0000000000000000000000000000000000000000..82fa93b4db9996d3af08d72b71934053107d70ef --- /dev/null +++ b/tools/perf/builtin-report.c @@ -0,0 +1,1316 @@ +/* + * builtin-report.c + * + * Builtin report command: Analyze the perf.data input file, + * look up and read DSOs and symbol information and display + * a histogram of results, along various sorting keys. + */ +#include "builtin.h" + +#include "util/util.h" + +#include "util/color.h" +#include "util/list.h" +#include "util/cache.h" +#include "util/rbtree.h" +#include "util/symbol.h" +#include "util/string.h" + +#include "perf.h" + +#include "util/parse-options.h" +#include "util/parse-events.h" + +#define SHOW_KERNEL 1 +#define SHOW_USER 2 +#define SHOW_HV 4 + +static char const *input_name = "perf.data"; +static char *vmlinux = NULL; + +static char default_sort_order[] = "comm,dso"; +static char *sort_order = default_sort_order; + +static int input; +static int show_mask = SHOW_KERNEL | SHOW_USER | SHOW_HV; + +static int dump_trace = 0; +#define dprintf(x...) do { if (dump_trace) printf(x); } while (0) + +static int verbose; +static int full_paths; + +static unsigned long page_size; +static unsigned long mmap_window = 32; + +struct ip_event { + struct perf_event_header header; + __u64 ip; + __u32 pid, tid; + __u64 period; +}; + +struct mmap_event { + struct perf_event_header header; + __u32 pid, tid; + __u64 start; + __u64 len; + __u64 pgoff; + char filename[PATH_MAX]; +}; + +struct comm_event { + struct perf_event_header header; + __u32 pid, tid; + char comm[16]; +}; + +struct fork_event { + struct perf_event_header header; + __u32 pid, ppid; +}; + +struct period_event { + struct perf_event_header header; + __u64 time; + __u64 id; + __u64 sample_period; +}; + +typedef union event_union { + struct perf_event_header header; + struct ip_event ip; + struct mmap_event mmap; + struct comm_event comm; + struct fork_event fork; + struct period_event period; +} event_t; + +static LIST_HEAD(dsos); +static struct dso *kernel_dso; +static struct dso *vdso; + +static void dsos__add(struct dso *dso) +{ + list_add_tail(&dso->node, &dsos); +} + +static struct dso *dsos__find(const char *name) +{ + struct dso *pos; + + list_for_each_entry(pos, &dsos, node) + if (strcmp(pos->name, name) == 0) + return pos; + return NULL; +} + +static struct dso *dsos__findnew(const char *name) +{ + struct dso *dso = dsos__find(name); + int nr; + + if (dso) + return dso; + + dso = dso__new(name, 0); + if (!dso) + goto out_delete_dso; + + nr = dso__load(dso, NULL, verbose); + if (nr < 0) { + if (verbose) + fprintf(stderr, "Failed to open: %s\n", name); + goto out_delete_dso; + } + if (!nr && verbose) { + fprintf(stderr, + "No symbols found in: %s, maybe install a debug package?\n", + name); + } + + dsos__add(dso); + + return dso; + +out_delete_dso: + dso__delete(dso); + return NULL; +} + +static void dsos__fprintf(FILE *fp) +{ + struct dso *pos; + + list_for_each_entry(pos, &dsos, node) + dso__fprintf(pos, fp); +} + +static struct symbol *vdso__find_symbol(struct dso *dso, __u64 ip) +{ + return dso__find_symbol(kernel_dso, ip); +} + +static int load_kernel(void) +{ + int err; + + kernel_dso = dso__new("[kernel]", 0); + if (!kernel_dso) + return -1; + + err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose); + if (err) { + dso__delete(kernel_dso); + kernel_dso = NULL; + } else + dsos__add(kernel_dso); + + vdso = dso__new("[vdso]", 0); + if (!vdso) + return -1; + + vdso->find_symbol = vdso__find_symbol; + + dsos__add(vdso); + + return err; +} + +static char __cwd[PATH_MAX]; +static char *cwd = __cwd; +static int cwdlen; + +static int strcommon(const char *pathname) +{ + int n = 0; + + while (pathname[n] == cwd[n] && n < cwdlen) + ++n; + + return n; +} + +struct map { + struct list_head node; + __u64 start; + __u64 end; + __u64 pgoff; + __u64 (*map_ip)(struct map *, __u64); + struct dso *dso; +}; + +static __u64 map__map_ip(struct map *map, __u64 ip) +{ + return ip - map->start + map->pgoff; +} + +static __u64 vdso__map_ip(struct map *map, __u64 ip) +{ + return ip; +} + +static inline int is_anon_memory(const char *filename) +{ + return strcmp(filename, "//anon") == 0; +} + +static struct map *map__new(struct mmap_event *event) +{ + struct map *self = malloc(sizeof(*self)); + + if (self != NULL) { + const char *filename = event->filename; + char newfilename[PATH_MAX]; + int anon; + + if (cwd) { + int n = strcommon(filename); + + if (n == cwdlen) { + snprintf(newfilename, sizeof(newfilename), + ".%s", filename + n); + filename = newfilename; + } + } + + anon = is_anon_memory(filename); + + if (anon) { + snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", event->pid); + filename = newfilename; + } + + self->start = event->start; + self->end = event->start + event->len; + self->pgoff = event->pgoff; + + self->dso = dsos__findnew(filename); + if (self->dso == NULL) + goto out_delete; + + if (self->dso == vdso || anon) + self->map_ip = vdso__map_ip; + else + self->map_ip = map__map_ip; + } + return self; +out_delete: + free(self); + return NULL; +} + +static struct map *map__clone(struct map *self) +{ + struct map *map = malloc(sizeof(*self)); + + if (!map) + return NULL; + + memcpy(map, self, sizeof(*self)); + + return map; +} + +static int map__overlap(struct map *l, struct map *r) +{ + if (l->start > r->start) { + struct map *t = l; + l = r; + r = t; + } + + if (l->end > r->start) + return 1; + + return 0; +} + +static size_t map__fprintf(struct map *self, FILE *fp) +{ + return fprintf(fp, " %Lx-%Lx %Lx %s\n", + self->start, self->end, self->pgoff, self->dso->name); +} + + +struct thread { + struct rb_node rb_node; + struct list_head maps; + pid_t pid; + char *comm; +}; + +static struct thread *thread__new(pid_t pid) +{ + struct thread *self = malloc(sizeof(*self)); + + if (self != NULL) { + self->pid = pid; + self->comm = malloc(32); + if (self->comm) + snprintf(self->comm, 32, ":%d", self->pid); + INIT_LIST_HEAD(&self->maps); + } + + return self; +} + +static int thread__set_comm(struct thread *self, const char *comm) +{ + if (self->comm) + free(self->comm); + self->comm = strdup(comm); + return self->comm ? 0 : -ENOMEM; +} + +static size_t thread__fprintf(struct thread *self, FILE *fp) +{ + struct map *pos; + size_t ret = fprintf(fp, "Thread %d %s\n", self->pid, self->comm); + + list_for_each_entry(pos, &self->maps, node) + ret += map__fprintf(pos, fp); + + return ret; +} + + +static struct rb_root threads; +static struct thread *last_match; + +static struct thread *threads__findnew(pid_t pid) +{ + struct rb_node **p = &threads.rb_node; + struct rb_node *parent = NULL; + struct thread *th; + + /* + * Font-end cache - PID lookups come in blocks, + * so most of the time we dont have to look up + * the full rbtree: + */ + if (last_match && last_match->pid == pid) + return last_match; + + while (*p != NULL) { + parent = *p; + th = rb_entry(parent, struct thread, rb_node); + + if (th->pid == pid) { + last_match = th; + return th; + } + + if (pid < th->pid) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + th = thread__new(pid); + if (th != NULL) { + rb_link_node(&th->rb_node, parent, p); + rb_insert_color(&th->rb_node, &threads); + last_match = th; + } + + return th; +} + +static void thread__insert_map(struct thread *self, struct map *map) +{ + struct map *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, &self->maps, node) { + if (map__overlap(pos, map)) { + list_del_init(&pos->node); + /* XXX leaks dsos */ + free(pos); + } + } + + list_add_tail(&map->node, &self->maps); +} + +static int thread__fork(struct thread *self, struct thread *parent) +{ + struct map *map; + + if (self->comm) + free(self->comm); + self->comm = strdup(parent->comm); + if (!self->comm) + return -ENOMEM; + + list_for_each_entry(map, &parent->maps, node) { + struct map *new = map__clone(map); + if (!new) + return -ENOMEM; + thread__insert_map(self, new); + } + + return 0; +} + +static struct map *thread__find_map(struct thread *self, __u64 ip) +{ + struct map *pos; + + if (self == NULL) + return NULL; + + list_for_each_entry(pos, &self->maps, node) + if (ip >= pos->start && ip <= pos->end) + return pos; + + return NULL; +} + +static size_t threads__fprintf(FILE *fp) +{ + size_t ret = 0; + struct rb_node *nd; + + for (nd = rb_first(&threads); nd; nd = rb_next(nd)) { + struct thread *pos = rb_entry(nd, struct thread, rb_node); + + ret += thread__fprintf(pos, fp); + } + + return ret; +} + +/* + * histogram, sorted on item, collects counts + */ + +static struct rb_root hist; + +struct hist_entry { + struct rb_node rb_node; + + struct thread *thread; + struct map *map; + struct dso *dso; + struct symbol *sym; + __u64 ip; + char level; + + __u64 count; +}; + +/* + * configurable sorting bits + */ + +struct sort_entry { + struct list_head list; + + char *header; + + int64_t (*cmp)(struct hist_entry *, struct hist_entry *); + int64_t (*collapse)(struct hist_entry *, struct hist_entry *); + size_t (*print)(FILE *fp, struct hist_entry *); +}; + +/* --sort pid */ + +static int64_t +sort__thread_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->thread->pid - left->thread->pid; +} + +static size_t +sort__thread_print(FILE *fp, struct hist_entry *self) +{ + return fprintf(fp, "%16s:%5d", self->thread->comm ?: "", self->thread->pid); +} + +static struct sort_entry sort_thread = { + .header = " Command: Pid", + .cmp = sort__thread_cmp, + .print = sort__thread_print, +}; + +/* --sort comm */ + +static int64_t +sort__comm_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->thread->pid - left->thread->pid; +} + +static int64_t +sort__comm_collapse(struct hist_entry *left, struct hist_entry *right) +{ + char *comm_l = left->thread->comm; + char *comm_r = right->thread->comm; + + if (!comm_l || !comm_r) { + if (!comm_l && !comm_r) + return 0; + else if (!comm_l) + return -1; + else + return 1; + } + + return strcmp(comm_l, comm_r); +} + +static size_t +sort__comm_print(FILE *fp, struct hist_entry *self) +{ + return fprintf(fp, "%16s", self->thread->comm); +} + +static struct sort_entry sort_comm = { + .header = " Command", + .cmp = sort__comm_cmp, + .collapse = sort__comm_collapse, + .print = sort__comm_print, +}; + +/* --sort dso */ + +static int64_t +sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct dso *dso_l = left->dso; + struct dso *dso_r = right->dso; + + if (!dso_l || !dso_r) { + if (!dso_l && !dso_r) + return 0; + else if (!dso_l) + return -1; + else + return 1; + } + + return strcmp(dso_l->name, dso_r->name); +} + +static size_t +sort__dso_print(FILE *fp, struct hist_entry *self) +{ + if (self->dso) + return fprintf(fp, "%-25s", self->dso->name); + + return fprintf(fp, "%016llx ", (__u64)self->ip); +} + +static struct sort_entry sort_dso = { + .header = "Shared Object ", + .cmp = sort__dso_cmp, + .print = sort__dso_print, +}; + +/* --sort symbol */ + +static int64_t +sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) +{ + __u64 ip_l, ip_r; + + if (left->sym == right->sym) + return 0; + + ip_l = left->sym ? left->sym->start : left->ip; + ip_r = right->sym ? right->sym->start : right->ip; + + return (int64_t)(ip_r - ip_l); +} + +static size_t +sort__sym_print(FILE *fp, struct hist_entry *self) +{ + size_t ret = 0; + + if (verbose) + ret += fprintf(fp, "%#018llx ", (__u64)self->ip); + + if (self->sym) { + ret += fprintf(fp, "[%c] %s", + self->dso == kernel_dso ? 'k' : '.', self->sym->name); + } else { + ret += fprintf(fp, "%#016llx", (__u64)self->ip); + } + + return ret; +} + +static struct sort_entry sort_sym = { + .header = "Symbol", + .cmp = sort__sym_cmp, + .print = sort__sym_print, +}; + +static int sort__need_collapse = 0; + +struct sort_dimension { + char *name; + struct sort_entry *entry; + int taken; +}; + +static struct sort_dimension sort_dimensions[] = { + { .name = "pid", .entry = &sort_thread, }, + { .name = "comm", .entry = &sort_comm, }, + { .name = "dso", .entry = &sort_dso, }, + { .name = "symbol", .entry = &sort_sym, }, +}; + +static LIST_HEAD(hist_entry__sort_list); + +static int sort_dimension__add(char *tok) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) { + struct sort_dimension *sd = &sort_dimensions[i]; + + if (sd->taken) + continue; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + if (sd->entry->collapse) + sort__need_collapse = 1; + + list_add_tail(&sd->entry->list, &hist_entry__sort_list); + sd->taken = 1; + + return 0; + } + + return -ESRCH; +} + +static int64_t +hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct sort_entry *se; + int64_t cmp = 0; + + list_for_each_entry(se, &hist_entry__sort_list, list) { + cmp = se->cmp(left, right); + if (cmp) + break; + } + + return cmp; +} + +static int64_t +hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) +{ + struct sort_entry *se; + int64_t cmp = 0; + + list_for_each_entry(se, &hist_entry__sort_list, list) { + int64_t (*f)(struct hist_entry *, struct hist_entry *); + + f = se->collapse ?: se->cmp; + + cmp = f(left, right); + if (cmp) + break; + } + + return cmp; +} + +static size_t +hist_entry__fprintf(FILE *fp, struct hist_entry *self, __u64 total_samples) +{ + struct sort_entry *se; + size_t ret; + + if (total_samples) { + double percent = self->count * 100.0 / total_samples; + char *color = PERF_COLOR_NORMAL; + + /* + * We color high-overhead entries in red, mid-overhead + * entries in green - and keep the low overhead places + * normal: + */ + if (percent >= 5.0) { + color = PERF_COLOR_RED; + } else { + if (percent >= 0.5) + color = PERF_COLOR_GREEN; + } + + ret = color_fprintf(fp, color, " %6.2f%%", + (self->count * 100.0) / total_samples); + } else + ret = fprintf(fp, "%12Ld ", self->count); + + list_for_each_entry(se, &hist_entry__sort_list, list) { + fprintf(fp, " "); + ret += se->print(fp, self); + } + + ret += fprintf(fp, "\n"); + + return ret; +} + +/* + * collect histogram counts + */ + +static int +hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, + struct symbol *sym, __u64 ip, char level, __u64 count) +{ + struct rb_node **p = &hist.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *he; + struct hist_entry entry = { + .thread = thread, + .map = map, + .dso = dso, + .sym = sym, + .ip = ip, + .level = level, + .count = count, + }; + int cmp; + + while (*p != NULL) { + parent = *p; + he = rb_entry(parent, struct hist_entry, rb_node); + + cmp = hist_entry__cmp(&entry, he); + + if (!cmp) { + he->count += count; + return 0; + } + + if (cmp < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + he = malloc(sizeof(*he)); + if (!he) + return -ENOMEM; + *he = entry; + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &hist); + + return 0; +} + +static void hist_entry__free(struct hist_entry *he) +{ + free(he); +} + +/* + * collapse the histogram + */ + +static struct rb_root collapse_hists; + +static void collapse__insert_entry(struct hist_entry *he) +{ + struct rb_node **p = &collapse_hists.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + int64_t cmp; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + + cmp = hist_entry__collapse(iter, he); + + if (!cmp) { + iter->count += he->count; + hist_entry__free(he); + return; + } + + if (cmp < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &collapse_hists); +} + +static void collapse__resort(void) +{ + struct rb_node *next; + struct hist_entry *n; + + if (!sort__need_collapse) + return; + + next = rb_first(&hist); + while (next) { + n = rb_entry(next, struct hist_entry, rb_node); + next = rb_next(&n->rb_node); + + rb_erase(&n->rb_node, &hist); + collapse__insert_entry(n); + } +} + +/* + * reverse the map, sort on count. + */ + +static struct rb_root output_hists; + +static void output__insert_entry(struct hist_entry *he) +{ + struct rb_node **p = &output_hists.rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + + if (he->count > iter->count) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, &output_hists); +} + +static void output__resort(void) +{ + struct rb_node *next; + struct hist_entry *n; + struct rb_root *tree = &hist; + + if (sort__need_collapse) + tree = &collapse_hists; + + next = rb_first(tree); + + while (next) { + n = rb_entry(next, struct hist_entry, rb_node); + next = rb_next(&n->rb_node); + + rb_erase(&n->rb_node, tree); + output__insert_entry(n); + } +} + +static size_t output__fprintf(FILE *fp, __u64 total_samples) +{ + struct hist_entry *pos; + struct sort_entry *se; + struct rb_node *nd; + size_t ret = 0; + + fprintf(fp, "\n"); + fprintf(fp, "#\n"); + fprintf(fp, "# (%Ld samples)\n", (__u64)total_samples); + fprintf(fp, "#\n"); + + fprintf(fp, "# Overhead"); + list_for_each_entry(se, &hist_entry__sort_list, list) + fprintf(fp, " %s", se->header); + fprintf(fp, "\n"); + + fprintf(fp, "# ........"); + list_for_each_entry(se, &hist_entry__sort_list, list) { + int i; + + fprintf(fp, " "); + for (i = 0; i < strlen(se->header); i++) + fprintf(fp, "."); + } + fprintf(fp, "\n"); + + fprintf(fp, "#\n"); + + for (nd = rb_first(&output_hists); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct hist_entry, rb_node); + ret += hist_entry__fprintf(fp, pos, total_samples); + } + + if (!strcmp(sort_order, default_sort_order)) { + fprintf(fp, "#\n"); + fprintf(fp, "# (For more details, try: perf report --sort comm,dso,symbol)\n"); + fprintf(fp, "#\n"); + } + fprintf(fp, "\n"); + + return ret; +} + +static void register_idle_thread(void) +{ + struct thread *thread = threads__findnew(0); + + if (thread == NULL || + thread__set_comm(thread, "[idle]")) { + fprintf(stderr, "problem inserting idle task.\n"); + exit(-1); + } +} + +static unsigned long total = 0, + total_mmap = 0, + total_comm = 0, + total_fork = 0, + total_unknown = 0; + +static int +process_overflow_event(event_t *event, unsigned long offset, unsigned long head) +{ + char level; + int show = 0; + struct dso *dso = NULL; + struct thread *thread = threads__findnew(event->ip.pid); + __u64 ip = event->ip.ip; + __u64 period = 1; + struct map *map = NULL; + + if (event->header.type & PERF_SAMPLE_PERIOD) + period = event->ip.period; + + dprintf("%p [%p]: PERF_EVENT (IP, %d): %d: %p period: %Ld\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->header.misc, + event->ip.pid, + (void *)(long)ip, + (long long)period); + + dprintf(" ... thread: %s:%d\n", thread->comm, thread->pid); + + if (thread == NULL) { + fprintf(stderr, "problem processing %d event, skipping it.\n", + event->header.type); + return -1; + } + + if (event->header.misc & PERF_EVENT_MISC_KERNEL) { + show = SHOW_KERNEL; + level = 'k'; + + dso = kernel_dso; + + dprintf(" ...... dso: %s\n", dso->name); + + } else if (event->header.misc & PERF_EVENT_MISC_USER) { + + show = SHOW_USER; + level = '.'; + + map = thread__find_map(thread, ip); + if (map != NULL) { + ip = map->map_ip(map, ip); + dso = map->dso; + } else { + /* + * If this is outside of all known maps, + * and is a negative address, try to look it + * up in the kernel dso, as it might be a + * vsyscall (which executes in user-mode): + */ + if ((long long)ip < 0) + dso = kernel_dso; + } + dprintf(" ...... dso: %s\n", dso ? dso->name : ""); + + } else { + show = SHOW_HV; + level = 'H'; + dprintf(" ...... dso: [hypervisor]\n"); + } + + if (show & show_mask) { + struct symbol *sym = NULL; + + if (dso) + sym = dso->find_symbol(dso, ip); + + if (hist_entry__add(thread, map, dso, sym, ip, level, period)) { + fprintf(stderr, + "problem incrementing symbol count, skipping event\n"); + return -1; + } + } + total += period; + + return 0; +} + +static int +process_mmap_event(event_t *event, unsigned long offset, unsigned long head) +{ + struct thread *thread = threads__findnew(event->mmap.pid); + struct map *map = map__new(&event->mmap); + + dprintf("%p [%p]: PERF_EVENT_MMAP %d: [%p(%p) @ %p]: %s\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->mmap.pid, + (void *)(long)event->mmap.start, + (void *)(long)event->mmap.len, + (void *)(long)event->mmap.pgoff, + event->mmap.filename); + + if (thread == NULL || map == NULL) { + dprintf("problem processing PERF_EVENT_MMAP, skipping event.\n"); + return 0; + } + + thread__insert_map(thread, map); + total_mmap++; + + return 0; +} + +static int +process_comm_event(event_t *event, unsigned long offset, unsigned long head) +{ + struct thread *thread = threads__findnew(event->comm.pid); + + dprintf("%p [%p]: PERF_EVENT_COMM: %s:%d\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->comm.comm, event->comm.pid); + + if (thread == NULL || + thread__set_comm(thread, event->comm.comm)) { + dprintf("problem processing PERF_EVENT_COMM, skipping event.\n"); + return -1; + } + total_comm++; + + return 0; +} + +static int +process_fork_event(event_t *event, unsigned long offset, unsigned long head) +{ + struct thread *thread = threads__findnew(event->fork.pid); + struct thread *parent = threads__findnew(event->fork.ppid); + + dprintf("%p [%p]: PERF_EVENT_FORK: %d:%d\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->fork.pid, event->fork.ppid); + + if (!thread || !parent || thread__fork(thread, parent)) { + dprintf("problem processing PERF_EVENT_FORK, skipping event.\n"); + return -1; + } + total_fork++; + + return 0; +} + +static int +process_period_event(event_t *event, unsigned long offset, unsigned long head) +{ + dprintf("%p [%p]: PERF_EVENT_PERIOD: time:%Ld, id:%Ld: period:%Ld\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->period.time, + event->period.id, + event->period.sample_period); + + return 0; +} + +static int +process_event(event_t *event, unsigned long offset, unsigned long head) +{ + if (event->header.misc & PERF_EVENT_MISC_OVERFLOW) + return process_overflow_event(event, offset, head); + + switch (event->header.type) { + case PERF_EVENT_MMAP: + return process_mmap_event(event, offset, head); + + case PERF_EVENT_COMM: + return process_comm_event(event, offset, head); + + case PERF_EVENT_FORK: + return process_fork_event(event, offset, head); + + case PERF_EVENT_PERIOD: + return process_period_event(event, offset, head); + /* + * We dont process them right now but they are fine: + */ + + case PERF_EVENT_THROTTLE: + case PERF_EVENT_UNTHROTTLE: + return 0; + + default: + return -1; + } + + return 0; +} + +static int __cmd_report(void) +{ + int ret, rc = EXIT_FAILURE; + unsigned long offset = 0; + unsigned long head = 0; + struct stat stat; + event_t *event; + uint32_t size; + char *buf; + + register_idle_thread(); + + input = open(input_name, O_RDONLY); + if (input < 0) { + fprintf(stderr, " failed to open file: %s", input_name); + if (!strcmp(input_name, "perf.data")) + fprintf(stderr, " (try 'perf record' first)"); + fprintf(stderr, "\n"); + exit(-1); + } + + ret = fstat(input, &stat); + if (ret < 0) { + perror("failed to stat file"); + exit(-1); + } + + if (!stat.st_size) { + fprintf(stderr, "zero-sized file, nothing to do!\n"); + exit(0); + } + + if (load_kernel() < 0) { + perror("failed to load kernel symbols"); + return EXIT_FAILURE; + } + + if (!full_paths) { + if (getcwd(__cwd, sizeof(__cwd)) == NULL) { + perror("failed to get the current directory"); + return EXIT_FAILURE; + } + cwdlen = strlen(cwd); + } else { + cwd = NULL; + cwdlen = 0; + } +remap: + buf = (char *)mmap(NULL, page_size * mmap_window, PROT_READ, + MAP_SHARED, input, offset); + if (buf == MAP_FAILED) { + perror("failed to mmap file"); + exit(-1); + } + +more: + event = (event_t *)(buf + head); + + size = event->header.size; + if (!size) + size = 8; + + if (head + event->header.size >= page_size * mmap_window) { + unsigned long shift = page_size * (head / page_size); + int ret; + + ret = munmap(buf, page_size * mmap_window); + assert(ret == 0); + + offset += shift; + head -= shift; + goto remap; + } + + size = event->header.size; + + dprintf("%p [%p]: event: %d\n", + (void *)(offset + head), + (void *)(long)event->header.size, + event->header.type); + + if (!size || process_event(event, offset, head) < 0) { + + dprintf("%p [%p]: skipping unknown header type: %d\n", + (void *)(offset + head), + (void *)(long)(event->header.size), + event->header.type); + + total_unknown++; + + /* + * assume we lost track of the stream, check alignment, and + * increment a single u64 in the hope to catch on again 'soon'. + */ + + if (unlikely(head & 7)) + head &= ~7ULL; + + size = 8; + } + + head += size; + + if (offset + head < stat.st_size) + goto more; + + rc = EXIT_SUCCESS; + close(input); + + dprintf(" IP events: %10ld\n", total); + dprintf(" mmap events: %10ld\n", total_mmap); + dprintf(" comm events: %10ld\n", total_comm); + dprintf(" fork events: %10ld\n", total_fork); + dprintf(" unknown events: %10ld\n", total_unknown); + + if (dump_trace) + return 0; + + if (verbose >= 3) + threads__fprintf(stdout); + + if (verbose >= 2) + dsos__fprintf(stdout); + + collapse__resort(); + output__resort(); + output__fprintf(stdout, total); + + return rc; +} + +static const char * const report_usage[] = { + "perf report [] ", + NULL +}; + +static const struct option options[] = { + OPT_STRING('i', "input", &input_name, "file", + "input file name"), + OPT_BOOLEAN('v', "verbose", &verbose, + "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, + "dump raw trace in ASCII"), + OPT_STRING('k', "vmlinux", &vmlinux, "file", "vmlinux pathname"), + OPT_STRING('s', "sort", &sort_order, "key[,key2...]", + "sort by key(s): pid, comm, dso, symbol. Default: pid,symbol"), + OPT_BOOLEAN('P', "full-paths", &full_paths, + "Don't shorten the pathnames taking into account the cwd"), + OPT_END() +}; + +static void setup_sorting(void) +{ + char *tmp, *tok, *str = strdup(sort_order); + + for (tok = strtok_r(str, ", ", &tmp); + tok; tok = strtok_r(NULL, ", ", &tmp)) { + if (sort_dimension__add(tok) < 0) { + error("Unknown --sort key: `%s'", tok); + usage_with_options(report_usage, options); + } + } + + free(str); +} + +int cmd_report(int argc, const char **argv, const char *prefix) +{ + symbol__init(); + + page_size = getpagesize(); + + argc = parse_options(argc, argv, options, report_usage, 0); + + setup_sorting(); + + /* + * Any (unrecognized) arguments left? + */ + if (argc) + usage_with_options(report_usage, options); + + setup_pager(); + + return __cmd_report(); +} diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c new file mode 100644 index 0000000000000000000000000000000000000000..c43e4a97dc4283d9b4b5d7cdf4803d1e139de8a1 --- /dev/null +++ b/tools/perf/builtin-stat.c @@ -0,0 +1,367 @@ +/* + * builtin-stat.c + * + * Builtin stat command: Give a precise performance counters summary + * overview about any workload, CPU or specific PID. + * + * Sample output: + + $ perf stat ~/hackbench 10 + Time: 0.104 + + Performance counter stats for '/home/mingo/hackbench': + + 1255.538611 task clock ticks # 10.143 CPU utilization factor + 54011 context switches # 0.043 M/sec + 385 CPU migrations # 0.000 M/sec + 17755 pagefaults # 0.014 M/sec + 3808323185 CPU cycles # 3033.219 M/sec + 1575111190 instructions # 1254.530 M/sec + 17367895 cache references # 13.833 M/sec + 7674421 cache misses # 6.112 M/sec + + Wall-clock time elapsed: 123.786620 msecs + + * + * Copyright (C) 2008, Red Hat Inc, Ingo Molnar + * + * Improvements and fixes by: + * + * Arjan van de Ven + * Yanmin Zhang + * Wu Fengguang + * Mike Galbraith + * Paul Mackerras + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include "perf.h" +#include "builtin.h" +#include "util/util.h" +#include "util/parse-options.h" +#include "util/parse-events.h" + +#include + +static struct perf_counter_attr default_attrs[MAX_COUNTERS] = { + + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES}, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS }, + + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES}, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES }, + +}; + +static int system_wide = 0; +static int inherit = 1; +static int verbose = 0; + +static int fd[MAX_NR_CPUS][MAX_COUNTERS]; + +static int target_pid = -1; +static int nr_cpus = 0; +static unsigned int page_size; + +static int scale = 1; + +static const unsigned int default_count[] = { + 1000000, + 1000000, + 10000, + 10000, + 1000000, + 10000, +}; + +static __u64 event_res[MAX_COUNTERS][3]; +static __u64 event_scaled[MAX_COUNTERS]; + +static __u64 runtime_nsecs; +static __u64 walltime_nsecs; +static __u64 runtime_cycles; + +static void create_perf_stat_counter(int counter) +{ + struct perf_counter_attr *attr = attrs + counter; + + if (scale) + attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING; + + if (system_wide) { + int cpu; + for (cpu = 0; cpu < nr_cpus; cpu ++) { + fd[cpu][counter] = sys_perf_counter_open(attr, -1, cpu, -1, 0); + if (fd[cpu][counter] < 0 && verbose) { + printf("Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n", counter, fd[cpu][counter], strerror(errno)); + } + } + } else { + attr->inherit = inherit; + attr->disabled = 1; + + fd[0][counter] = sys_perf_counter_open(attr, 0, -1, -1, 0); + if (fd[0][counter] < 0 && verbose) { + printf("Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n", counter, fd[0][counter], strerror(errno)); + } + } +} + +/* + * Does the counter have nsecs as a unit? + */ +static inline int nsec_counter(int counter) +{ + if (attrs[counter].type != PERF_TYPE_SOFTWARE) + return 0; + + if (attrs[counter].config == PERF_COUNT_SW_CPU_CLOCK) + return 1; + + if (attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK) + return 1; + + return 0; +} + +/* + * Read out the results of a single counter: + */ +static void read_counter(int counter) +{ + __u64 *count, single_count[3]; + ssize_t res; + int cpu, nv; + int scaled; + + count = event_res[counter]; + + count[0] = count[1] = count[2] = 0; + + nv = scale ? 3 : 1; + for (cpu = 0; cpu < nr_cpus; cpu ++) { + if (fd[cpu][counter] < 0) + continue; + + res = read(fd[cpu][counter], single_count, nv * sizeof(__u64)); + assert(res == nv * sizeof(__u64)); + + count[0] += single_count[0]; + if (scale) { + count[1] += single_count[1]; + count[2] += single_count[2]; + } + } + + scaled = 0; + if (scale) { + if (count[2] == 0) { + event_scaled[counter] = -1; + count[0] = 0; + return; + } + + if (count[2] < count[1]) { + event_scaled[counter] = 1; + count[0] = (unsigned long long) + ((double)count[0] * count[1] / count[2] + 0.5); + } + } + /* + * Save the full runtime - to allow normalization during printout: + */ + if (attrs[counter].type == PERF_TYPE_SOFTWARE && + attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK) + runtime_nsecs = count[0]; + if (attrs[counter].type == PERF_TYPE_HARDWARE && + attrs[counter].config == PERF_COUNT_HW_CPU_CYCLES) + runtime_cycles = count[0]; +} + +/* + * Print out the results of a single counter: + */ +static void print_counter(int counter) +{ + __u64 *count; + int scaled; + + count = event_res[counter]; + scaled = event_scaled[counter]; + + if (scaled == -1) { + fprintf(stderr, " %14s %-20s\n", + "", event_name(counter)); + return; + } + + if (nsec_counter(counter)) { + double msecs = (double)count[0] / 1000000; + + fprintf(stderr, " %14.6f %-20s", + msecs, event_name(counter)); + if (attrs[counter].type == PERF_TYPE_SOFTWARE && + attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK) { + + if (walltime_nsecs) + fprintf(stderr, " # %11.3f CPU utilization factor", + (double)count[0] / (double)walltime_nsecs); + } + } else { + fprintf(stderr, " %14Ld %-20s", + count[0], event_name(counter)); + if (runtime_nsecs) + fprintf(stderr, " # %11.3f M/sec", + (double)count[0]/runtime_nsecs*1000.0); + if (runtime_cycles && + attrs[counter].type == PERF_TYPE_HARDWARE && + attrs[counter].config == PERF_COUNT_HW_INSTRUCTIONS) { + + fprintf(stderr, " # %1.3f per cycle", + (double)count[0] / (double)runtime_cycles); + } + } + if (scaled) + fprintf(stderr, " (scaled from %.2f%%)", + (double) count[2] / count[1] * 100); + fprintf(stderr, "\n"); +} + +static int do_perf_stat(int argc, const char **argv) +{ + unsigned long long t0, t1; + int counter; + int status; + int pid; + int i; + + if (!system_wide) + nr_cpus = 1; + + for (counter = 0; counter < nr_counters; counter++) + create_perf_stat_counter(counter); + + /* + * Enable counters and exec the command: + */ + t0 = rdclock(); + prctl(PR_TASK_PERF_COUNTERS_ENABLE); + + if ((pid = fork()) < 0) + perror("failed to fork"); + + if (!pid) { + if (execvp(argv[0], (char **)argv)) { + perror(argv[0]); + exit(-1); + } + } + + while (wait(&status) >= 0) + ; + + prctl(PR_TASK_PERF_COUNTERS_DISABLE); + t1 = rdclock(); + + walltime_nsecs = t1 - t0; + + fflush(stdout); + + fprintf(stderr, "\n"); + fprintf(stderr, " Performance counter stats for \'%s", argv[0]); + + for (i = 1; i < argc; i++) + fprintf(stderr, " %s", argv[i]); + + fprintf(stderr, "\':\n"); + fprintf(stderr, "\n"); + + for (counter = 0; counter < nr_counters; counter++) + read_counter(counter); + + for (counter = 0; counter < nr_counters; counter++) + print_counter(counter); + + + fprintf(stderr, "\n"); + fprintf(stderr, " Wall-clock time elapsed: %12.6f msecs\n", + (double)(t1-t0)/1e6); + fprintf(stderr, "\n"); + + return 0; +} + +static volatile int signr = -1; + +static void skip_signal(int signo) +{ + signr = signo; +} + +static void sig_atexit(void) +{ + if (signr == -1) + return; + + signal(signr, SIG_DFL); + kill(getpid(), signr); +} + +static const char * const stat_usage[] = { + "perf stat [] ", + NULL +}; + +static const struct option options[] = { + OPT_CALLBACK('e', "event", NULL, "event", + "event selector. use 'perf list' to list available events", + parse_events), + OPT_BOOLEAN('i', "inherit", &inherit, + "child tasks inherit counters"), + OPT_INTEGER('p', "pid", &target_pid, + "stat events on existing pid"), + OPT_BOOLEAN('a', "all-cpus", &system_wide, + "system-wide collection from all CPUs"), + OPT_BOOLEAN('S', "scale", &scale, + "scale/normalize counters"), + OPT_BOOLEAN('v', "verbose", &verbose, + "be more verbose (show counter open errors, etc)"), + OPT_END() +}; + +int cmd_stat(int argc, const char **argv, const char *prefix) +{ + page_size = sysconf(_SC_PAGE_SIZE); + + memcpy(attrs, default_attrs, sizeof(attrs)); + + argc = parse_options(argc, argv, options, stat_usage, 0); + if (!argc) + usage_with_options(stat_usage, options); + + if (!nr_counters) + nr_counters = 8; + + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + assert(nr_cpus <= MAX_NR_CPUS); + assert(nr_cpus >= 0); + + /* + * We dont want to block the signals - that would cause + * child tasks to inherit that and Ctrl-C would not work. + * What we want is for Ctrl-C to work in the exec()-ed + * task, but being ignored by perf stat itself: + */ + atexit(sig_atexit); + signal(SIGINT, skip_signal); + signal(SIGALRM, skip_signal); + signal(SIGABRT, skip_signal); + + return do_perf_stat(argc, argv); +} diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c new file mode 100644 index 0000000000000000000000000000000000000000..fe338d3c5d7ec3a82931f7e34b2b9837295bd60c --- /dev/null +++ b/tools/perf/builtin-top.c @@ -0,0 +1,736 @@ +/* + * builtin-top.c + * + * Builtin top command: Display a continuously updated profile of + * any workload, CPU or specific PID. + * + * Copyright (C) 2008, Red Hat Inc, Ingo Molnar + * + * Improvements and fixes by: + * + * Arjan van de Ven + * Yanmin Zhang + * Wu Fengguang + * Mike Galbraith + * Paul Mackerras + * + * Released under the GPL v2. (and only v2, not any later version) + */ +#include "builtin.h" + +#include "perf.h" + +#include "util/symbol.h" +#include "util/color.h" +#include "util/util.h" +#include "util/rbtree.h" +#include "util/parse-options.h" +#include "util/parse-events.h" + +#include +#include + +#include + +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +static int fd[MAX_NR_CPUS][MAX_COUNTERS]; + +static int system_wide = 0; + +static int default_interval = 100000; + +static __u64 count_filter = 5; +static int print_entries = 15; + +static int target_pid = -1; +static int profile_cpu = -1; +static int nr_cpus = 0; +static unsigned int realtime_prio = 0; +static int group = 0; +static unsigned int page_size; +static unsigned int mmap_pages = 16; +static int freq = 0; +static int verbose = 0; + +static char *sym_filter; +static unsigned long filter_start; +static unsigned long filter_end; + +static int delay_secs = 2; +static int zero; +static int dump_symtab; + +/* + * Symbols + */ + +static __u64 min_ip; +static __u64 max_ip = -1ll; + +struct sym_entry { + struct rb_node rb_node; + struct list_head node; + unsigned long count[MAX_COUNTERS]; + unsigned long snap_count; + double weight; + int skip; +}; + +struct sym_entry *sym_filter_entry; + +struct dso *kernel_dso; + +/* + * Symbols will be added here in record_ip and will get out + * after decayed. + */ +static LIST_HEAD(active_symbols); +static pthread_mutex_t active_symbols_lock = PTHREAD_MUTEX_INITIALIZER; + +/* + * Ordering weight: count-1 * count-2 * ... / count-n + */ +static double sym_weight(const struct sym_entry *sym) +{ + double weight = sym->snap_count; + int counter; + + for (counter = 1; counter < nr_counters-1; counter++) + weight *= sym->count[counter]; + + weight /= (sym->count[counter] + 1); + + return weight; +} + +static long samples; +static long userspace_samples; +static const char CONSOLE_CLEAR[] = ""; + +static void __list_insert_active_sym(struct sym_entry *syme) +{ + list_add(&syme->node, &active_symbols); +} + +static void list_remove_active_sym(struct sym_entry *syme) +{ + pthread_mutex_lock(&active_symbols_lock); + list_del_init(&syme->node); + pthread_mutex_unlock(&active_symbols_lock); +} + +static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se) +{ + struct rb_node **p = &tree->rb_node; + struct rb_node *parent = NULL; + struct sym_entry *iter; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct sym_entry, rb_node); + + if (se->weight > iter->weight) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&se->rb_node, parent, p); + rb_insert_color(&se->rb_node, tree); +} + +static void print_sym_table(void) +{ + int printed = 0, j; + int counter; + float samples_per_sec = samples/delay_secs; + float ksamples_per_sec = (samples-userspace_samples)/delay_secs; + float sum_ksamples = 0.0; + struct sym_entry *syme, *n; + struct rb_root tmp = RB_ROOT; + struct rb_node *nd; + + samples = userspace_samples = 0; + + /* Sort the active symbols */ + pthread_mutex_lock(&active_symbols_lock); + syme = list_entry(active_symbols.next, struct sym_entry, node); + pthread_mutex_unlock(&active_symbols_lock); + + list_for_each_entry_safe_from(syme, n, &active_symbols, node) { + syme->snap_count = syme->count[0]; + if (syme->snap_count != 0) { + syme->weight = sym_weight(syme); + rb_insert_active_sym(&tmp, syme); + sum_ksamples += syme->snap_count; + + for (j = 0; j < nr_counters; j++) + syme->count[j] = zero ? 0 : syme->count[j] * 7 / 8; + } else + list_remove_active_sym(syme); + } + + puts(CONSOLE_CLEAR); + + printf( +"------------------------------------------------------------------------------\n"); + printf( " PerfTop:%8.0f irqs/sec kernel:%4.1f%% [", + samples_per_sec, + 100.0 - (100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec))); + + if (nr_counters == 1) { + printf("%Ld", attrs[0].sample_period); + if (freq) + printf("Hz "); + else + printf(" "); + } + + for (counter = 0; counter < nr_counters; counter++) { + if (counter) + printf("/"); + + printf("%s", event_name(counter)); + } + + printf( "], "); + + if (target_pid != -1) + printf(" (target_pid: %d", target_pid); + else + printf(" (all"); + + if (profile_cpu != -1) + printf(", cpu: %d)\n", profile_cpu); + else { + if (target_pid != -1) + printf(")\n"); + else + printf(", %d CPUs)\n", nr_cpus); + } + + printf("------------------------------------------------------------------------------\n\n"); + + if (nr_counters == 1) + printf(" samples pcnt"); + else + printf(" weight samples pcnt"); + + printf(" RIP kernel function\n" + " ______ _______ _____ ________________ _______________\n\n" + ); + + for (nd = rb_first(&tmp); nd; nd = rb_next(nd)) { + struct sym_entry *syme = rb_entry(nd, struct sym_entry, rb_node); + struct symbol *sym = (struct symbol *)(syme + 1); + char *color = PERF_COLOR_NORMAL; + double pcnt; + + if (++printed > print_entries || syme->snap_count < count_filter) + continue; + + pcnt = 100.0 - (100.0 * ((sum_ksamples - syme->snap_count) / + sum_ksamples)); + + /* + * We color high-overhead entries in red, mid-overhead + * entries in green - and keep the low overhead places + * normal: + */ + if (pcnt >= 5.0) { + color = PERF_COLOR_RED; + } else { + if (pcnt >= 0.5) + color = PERF_COLOR_GREEN; + } + + if (nr_counters == 1) + printf("%20.2f - ", syme->weight); + else + printf("%9.1f %10ld - ", syme->weight, syme->snap_count); + + color_fprintf(stdout, color, "%4.1f%%", pcnt); + printf(" - %016llx : %s\n", sym->start, sym->name); + } +} + +static void *display_thread(void *arg) +{ + struct pollfd stdin_poll = { .fd = 0, .events = POLLIN }; + int delay_msecs = delay_secs * 1000; + + printf("PerfTop refresh period: %d seconds\n", delay_secs); + + do { + print_sym_table(); + } while (!poll(&stdin_poll, 1, delay_msecs) == 1); + + printf("key pressed - exiting.\n"); + exit(0); + + return NULL; +} + +static int symbol_filter(struct dso *self, struct symbol *sym) +{ + static int filter_match; + struct sym_entry *syme; + const char *name = sym->name; + + if (!strcmp(name, "_text") || + !strcmp(name, "_etext") || + !strcmp(name, "_sinittext") || + !strncmp("init_module", name, 11) || + !strncmp("cleanup_module", name, 14) || + strstr(name, "_text_start") || + strstr(name, "_text_end")) + return 1; + + syme = dso__sym_priv(self, sym); + /* Tag samples to be skipped. */ + if (!strcmp("default_idle", name) || + !strcmp("cpu_idle", name) || + !strcmp("enter_idle", name) || + !strcmp("exit_idle", name) || + !strcmp("mwait_idle", name)) + syme->skip = 1; + + if (filter_match == 1) { + filter_end = sym->start; + filter_match = -1; + if (filter_end - filter_start > 10000) { + fprintf(stderr, + "hm, too large filter symbol <%s> - skipping.\n", + sym_filter); + fprintf(stderr, "symbol filter start: %016lx\n", + filter_start); + fprintf(stderr, " end: %016lx\n", + filter_end); + filter_end = filter_start = 0; + sym_filter = NULL; + sleep(1); + } + } + + if (filter_match == 0 && sym_filter && !strcmp(name, sym_filter)) { + filter_match = 1; + filter_start = sym->start; + } + + + return 0; +} + +static int parse_symbols(void) +{ + struct rb_node *node; + struct symbol *sym; + + kernel_dso = dso__new("[kernel]", sizeof(struct sym_entry)); + if (kernel_dso == NULL) + return -1; + + if (dso__load_kernel(kernel_dso, NULL, symbol_filter, 1) != 0) + goto out_delete_dso; + + node = rb_first(&kernel_dso->syms); + sym = rb_entry(node, struct symbol, rb_node); + min_ip = sym->start; + + node = rb_last(&kernel_dso->syms); + sym = rb_entry(node, struct symbol, rb_node); + max_ip = sym->end; + + if (dump_symtab) + dso__fprintf(kernel_dso, stderr); + + return 0; + +out_delete_dso: + dso__delete(kernel_dso); + kernel_dso = NULL; + return -1; +} + +#define TRACE_COUNT 3 + +/* + * Binary search in the histogram table and record the hit: + */ +static void record_ip(__u64 ip, int counter) +{ + struct symbol *sym = dso__find_symbol(kernel_dso, ip); + + if (sym != NULL) { + struct sym_entry *syme = dso__sym_priv(kernel_dso, sym); + + if (!syme->skip) { + syme->count[counter]++; + pthread_mutex_lock(&active_symbols_lock); + if (list_empty(&syme->node) || !syme->node.next) + __list_insert_active_sym(syme); + pthread_mutex_unlock(&active_symbols_lock); + return; + } + } + + samples--; +} + +static void process_event(__u64 ip, int counter) +{ + samples++; + + if (ip < min_ip || ip > max_ip) { + userspace_samples++; + return; + } + + record_ip(ip, counter); +} + +struct mmap_data { + int counter; + void *base; + unsigned int mask; + unsigned int prev; +}; + +static unsigned int mmap_read_head(struct mmap_data *md) +{ + struct perf_counter_mmap_page *pc = md->base; + int head; + + head = pc->data_head; + rmb(); + + return head; +} + +struct timeval last_read, this_read; + +static void mmap_read_counter(struct mmap_data *md) +{ + unsigned int head = mmap_read_head(md); + unsigned int old = md->prev; + unsigned char *data = md->base + page_size; + int diff; + + gettimeofday(&this_read, NULL); + + /* + * If we're further behind than half the buffer, there's a chance + * the writer will bite our tail and mess up the samples under us. + * + * If we somehow ended up ahead of the head, we got messed up. + * + * In either case, truncate and restart at head. + */ + diff = head - old; + if (diff > md->mask / 2 || diff < 0) { + struct timeval iv; + unsigned long msecs; + + timersub(&this_read, &last_read, &iv); + msecs = iv.tv_sec*1000 + iv.tv_usec/1000; + + fprintf(stderr, "WARNING: failed to keep up with mmap data." + " Last read %lu msecs ago.\n", msecs); + + /* + * head points to a known good entry, start there. + */ + old = head; + } + + last_read = this_read; + + for (; old != head;) { + struct ip_event { + struct perf_event_header header; + __u64 ip; + __u32 pid, target_pid; + }; + struct mmap_event { + struct perf_event_header header; + __u32 pid, target_pid; + __u64 start; + __u64 len; + __u64 pgoff; + char filename[PATH_MAX]; + }; + + typedef union event_union { + struct perf_event_header header; + struct ip_event ip; + struct mmap_event mmap; + } event_t; + + event_t *event = (event_t *)&data[old & md->mask]; + + event_t event_copy; + + size_t size = event->header.size; + + /* + * Event straddles the mmap boundary -- header should always + * be inside due to u64 alignment of output. + */ + if ((old & md->mask) + size != ((old + size) & md->mask)) { + unsigned int offset = old; + unsigned int len = min(sizeof(*event), size), cpy; + void *dst = &event_copy; + + do { + cpy = min(md->mask + 1 - (offset & md->mask), len); + memcpy(dst, &data[offset & md->mask], cpy); + offset += cpy; + dst += cpy; + len -= cpy; + } while (len); + + event = &event_copy; + } + + old += size; + + if (event->header.misc & PERF_EVENT_MISC_OVERFLOW) { + if (event->header.type & PERF_SAMPLE_IP) + process_event(event->ip.ip, md->counter); + } + } + + md->prev = old; +} + +static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS]; +static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS]; + +static void mmap_read(void) +{ + int i, counter; + + for (i = 0; i < nr_cpus; i++) { + for (counter = 0; counter < nr_counters; counter++) + mmap_read_counter(&mmap_array[i][counter]); + } +} + +int nr_poll; +int group_fd; + +static void start_counter(int i, int counter) +{ + struct perf_counter_attr *attr; + unsigned int cpu; + + cpu = profile_cpu; + if (target_pid == -1 && profile_cpu == -1) + cpu = i; + + attr = attrs + counter; + + attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; + attr->freq = freq; + +try_again: + fd[i][counter] = sys_perf_counter_open(attr, target_pid, cpu, group_fd, 0); + + if (fd[i][counter] < 0) { + int err = errno; + + if (err == EPERM) + die("No permission - are you root?\n"); + /* + * If it's cycles then fall back to hrtimer + * based cpu-clock-tick sw counter, which + * is always available even if no PMU support: + */ + if (attr->type == PERF_TYPE_HARDWARE + && attr->config == PERF_COUNT_HW_CPU_CYCLES) { + + if (verbose) + warning(" ... trying to fall back to cpu-clock-ticks\n"); + + attr->type = PERF_TYPE_SOFTWARE; + attr->config = PERF_COUNT_SW_CPU_CLOCK; + goto try_again; + } + printf("\n"); + error("perfcounter syscall returned with %d (%s)\n", + fd[i][counter], strerror(err)); + die("No CONFIG_PERF_COUNTERS=y kernel support configured?\n"); + exit(-1); + } + assert(fd[i][counter] >= 0); + fcntl(fd[i][counter], F_SETFL, O_NONBLOCK); + + /* + * First counter acts as the group leader: + */ + if (group && group_fd == -1) + group_fd = fd[i][counter]; + + event_array[nr_poll].fd = fd[i][counter]; + event_array[nr_poll].events = POLLIN; + nr_poll++; + + mmap_array[i][counter].counter = counter; + mmap_array[i][counter].prev = 0; + mmap_array[i][counter].mask = mmap_pages*page_size - 1; + mmap_array[i][counter].base = mmap(NULL, (mmap_pages+1)*page_size, + PROT_READ, MAP_SHARED, fd[i][counter], 0); + if (mmap_array[i][counter].base == MAP_FAILED) + die("failed to mmap with %d (%s)\n", errno, strerror(errno)); +} + +static int __cmd_top(void) +{ + pthread_t thread; + int i, counter; + int ret; + + for (i = 0; i < nr_cpus; i++) { + group_fd = -1; + for (counter = 0; counter < nr_counters; counter++) + start_counter(i, counter); + } + + /* Wait for a minimal set of events before starting the snapshot */ + poll(event_array, nr_poll, 100); + + mmap_read(); + + if (pthread_create(&thread, NULL, display_thread, NULL)) { + printf("Could not create display thread.\n"); + exit(-1); + } + + if (realtime_prio) { + struct sched_param param; + + param.sched_priority = realtime_prio; + if (sched_setscheduler(0, SCHED_FIFO, ¶m)) { + printf("Could not set realtime priority.\n"); + exit(-1); + } + } + + while (1) { + int hits = samples; + + mmap_read(); + + if (hits == samples) + ret = poll(event_array, nr_poll, 100); + } + + return 0; +} + +static const char * const top_usage[] = { + "perf top []", + NULL +}; + +static const struct option options[] = { + OPT_CALLBACK('e', "event", NULL, "event", + "event selector. use 'perf list' to list available events", + parse_events), + OPT_INTEGER('c', "count", &default_interval, + "event period to sample"), + OPT_INTEGER('p', "pid", &target_pid, + "profile events on existing pid"), + OPT_BOOLEAN('a', "all-cpus", &system_wide, + "system-wide collection from all CPUs"), + OPT_INTEGER('C', "CPU", &profile_cpu, + "CPU to profile on"), + OPT_INTEGER('m', "mmap-pages", &mmap_pages, + "number of mmap data pages"), + OPT_INTEGER('r', "realtime", &realtime_prio, + "collect data with this RT SCHED_FIFO priority"), + OPT_INTEGER('d', "delay", &delay_secs, + "number of seconds to delay between refreshes"), + OPT_BOOLEAN('D', "dump-symtab", &dump_symtab, + "dump the symbol table used for profiling"), + OPT_INTEGER('f', "count-filter", &count_filter, + "only display functions with more events than this"), + OPT_BOOLEAN('g', "group", &group, + "put the counters into a counter group"), + OPT_STRING('s', "sym-filter", &sym_filter, "pattern", + "only display symbols matchig this pattern"), + OPT_BOOLEAN('z', "zero", &group, + "zero history across updates"), + OPT_INTEGER('F', "freq", &freq, + "profile at this frequency"), + OPT_INTEGER('E', "entries", &print_entries, + "display this many functions"), + OPT_BOOLEAN('v', "verbose", &verbose, + "be more verbose (show counter open errors, etc)"), + OPT_END() +}; + +int cmd_top(int argc, const char **argv, const char *prefix) +{ + int counter; + + page_size = sysconf(_SC_PAGE_SIZE); + + argc = parse_options(argc, argv, options, top_usage, 0); + if (argc) + usage_with_options(top_usage, options); + + if (freq) { + default_interval = freq; + freq = 1; + } + + /* CPU and PID are mutually exclusive */ + if (target_pid != -1 && profile_cpu != -1) { + printf("WARNING: PID switch overriding CPU\n"); + sleep(1); + profile_cpu = -1; + } + + if (!nr_counters) + nr_counters = 1; + + if (delay_secs < 1) + delay_secs = 1; + + parse_symbols(); + + /* + * Fill in the ones not specifically initialized via -c: + */ + for (counter = 0; counter < nr_counters; counter++) { + if (attrs[counter].sample_period) + continue; + + attrs[counter].sample_period = default_interval; + } + + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + assert(nr_cpus <= MAX_NR_CPUS); + assert(nr_cpus >= 0); + + if (target_pid != -1 || profile_cpu != -1) + nr_cpus = 1; + + return __cmd_top(); +} diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h new file mode 100644 index 0000000000000000000000000000000000000000..51d168230ee746f4bf6f1a6f886c500b36350ebb --- /dev/null +++ b/tools/perf/builtin.h @@ -0,0 +1,26 @@ +#ifndef BUILTIN_H +#define BUILTIN_H + +#include "util/util.h" +#include "util/strbuf.h" + +extern const char perf_version_string[]; +extern const char perf_usage_string[]; +extern const char perf_more_info_string[]; + +extern void list_common_cmds_help(void); +extern const char *help_unknown_cmd(const char *cmd); +extern void prune_packed_objects(int); +extern int read_line_with_nul(char *buf, int size, FILE *file); +extern int check_pager_config(const char *cmd); + +extern int cmd_annotate(int argc, const char **argv, const char *prefix); +extern int cmd_help(int argc, const char **argv, const char *prefix); +extern int cmd_record(int argc, const char **argv, const char *prefix); +extern int cmd_report(int argc, const char **argv, const char *prefix); +extern int cmd_stat(int argc, const char **argv, const char *prefix); +extern int cmd_top(int argc, const char **argv, const char *prefix); +extern int cmd_version(int argc, const char **argv, const char *prefix); +extern int cmd_list(int argc, const char **argv, const char *prefix); + +#endif diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt new file mode 100644 index 0000000000000000000000000000000000000000..eebce30afbc094ec3acbf1464e6bc76dcd5ec882 --- /dev/null +++ b/tools/perf/command-list.txt @@ -0,0 +1,10 @@ +# +# List of known perf commands. +# command name category [deprecated] [common] +# +perf-annotate mainporcelain common +perf-list mainporcelain common +perf-record mainporcelain common +perf-report mainporcelain common +perf-stat mainporcelain common +perf-top mainporcelain common diff --git a/tools/perf/design.txt b/tools/perf/design.txt new file mode 100644 index 0000000000000000000000000000000000000000..860e116d979c834e0bdd68825a4cb83b8adf25da --- /dev/null +++ b/tools/perf/design.txt @@ -0,0 +1,442 @@ + +Performance Counters for Linux +------------------------------ + +Performance counters are special hardware registers available on most modern +CPUs. These registers count the number of certain types of hw events: such +as instructions executed, cachemisses suffered, or branches mis-predicted - +without slowing down the kernel or applications. These registers can also +trigger interrupts when a threshold number of events have passed - and can +thus be used to profile the code that runs on that CPU. + +The Linux Performance Counter subsystem provides an abstraction of these +hardware capabilities. It provides per task and per CPU counters, counter +groups, and it provides event capabilities on top of those. It +provides "virtual" 64-bit counters, regardless of the width of the +underlying hardware counters. + +Performance counters are accessed via special file descriptors. +There's one file descriptor per virtual counter used. + +The special file descriptor is opened via the perf_counter_open() +system call: + + int sys_perf_counter_open(struct perf_counter_hw_event *hw_event_uptr, + pid_t pid, int cpu, int group_fd, + unsigned long flags); + +The syscall returns the new fd. The fd can be used via the normal +VFS system calls: read() can be used to read the counter, fcntl() +can be used to set the blocking mode, etc. + +Multiple counters can be kept open at a time, and the counters +can be poll()ed. + +When creating a new counter fd, 'perf_counter_hw_event' is: + +struct perf_counter_hw_event { + /* + * The MSB of the config word signifies if the rest contains cpu + * specific (raw) counter configuration data, if unset, the next + * 7 bits are an event type and the rest of the bits are the event + * identifier. + */ + __u64 config; + + __u64 irq_period; + __u32 record_type; + __u32 read_format; + + __u64 disabled : 1, /* off by default */ + inherit : 1, /* children inherit it */ + pinned : 1, /* must always be on PMU */ + exclusive : 1, /* only group on PMU */ + exclude_user : 1, /* don't count user */ + exclude_kernel : 1, /* ditto kernel */ + exclude_hv : 1, /* ditto hypervisor */ + exclude_idle : 1, /* don't count when idle */ + mmap : 1, /* include mmap data */ + munmap : 1, /* include munmap data */ + comm : 1, /* include comm data */ + + __reserved_1 : 52; + + __u32 extra_config_len; + __u32 wakeup_events; /* wakeup every n events */ + + __u64 __reserved_2; + __u64 __reserved_3; +}; + +The 'config' field specifies what the counter should count. It +is divided into 3 bit-fields: + +raw_type: 1 bit (most significant bit) 0x8000_0000_0000_0000 +type: 7 bits (next most significant) 0x7f00_0000_0000_0000 +event_id: 56 bits (least significant) 0x00ff_ffff_ffff_ffff + +If 'raw_type' is 1, then the counter will count a hardware event +specified by the remaining 63 bits of event_config. The encoding is +machine-specific. + +If 'raw_type' is 0, then the 'type' field says what kind of counter +this is, with the following encoding: + +enum perf_event_types { + PERF_TYPE_HARDWARE = 0, + PERF_TYPE_SOFTWARE = 1, + PERF_TYPE_TRACEPOINT = 2, +}; + +A counter of PERF_TYPE_HARDWARE will count the hardware event +specified by 'event_id': + +/* + * Generalized performance counter event types, used by the hw_event.event_id + * parameter of the sys_perf_counter_open() syscall: + */ +enum hw_event_ids { + /* + * Common hardware events, generalized by the kernel: + */ + PERF_COUNT_HW_CPU_CYCLES = 0, + PERF_COUNT_HW_INSTRUCTIONS = 1, + PERF_COUNT_HW_CACHE_REFERENCES = 2, + PERF_COUNT_HW_CACHE_MISSES = 3, + PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4, + PERF_COUNT_HW_BRANCH_MISSES = 5, + PERF_COUNT_HW_BUS_CYCLES = 6, +}; + +These are standardized types of events that work relatively uniformly +on all CPUs that implement Performance Counters support under Linux, +although there may be variations (e.g., different CPUs might count +cache references and misses at different levels of the cache hierarchy). +If a CPU is not able to count the selected event, then the system call +will return -EINVAL. + +More hw_event_types are supported as well, but they are CPU-specific +and accessed as raw events. For example, to count "External bus +cycles while bus lock signal asserted" events on Intel Core CPUs, pass +in a 0x4064 event_id value and set hw_event.raw_type to 1. + +A counter of type PERF_TYPE_SOFTWARE will count one of the available +software events, selected by 'event_id': + +/* + * Special "software" counters provided by the kernel, even if the hardware + * does not support performance counters. These counters measure various + * physical and sw events of the kernel (and allow the profiling of them as + * well): + */ +enum sw_event_ids { + PERF_COUNT_SW_CPU_CLOCK = 0, + PERF_COUNT_SW_TASK_CLOCK = 1, + PERF_COUNT_SW_PAGE_FAULTS = 2, + PERF_COUNT_SW_CONTEXT_SWITCHES = 3, + PERF_COUNT_SW_CPU_MIGRATIONS = 4, + PERF_COUNT_SW_PAGE_FAULTS_MIN = 5, + PERF_COUNT_SW_PAGE_FAULTS_MAJ = 6, +}; + +Counters of the type PERF_TYPE_TRACEPOINT are available when the ftrace event +tracer is available, and event_id values can be obtained from +/debug/tracing/events/*/*/id + + +Counters come in two flavours: counting counters and sampling +counters. A "counting" counter is one that is used for counting the +number of events that occur, and is characterised by having +irq_period = 0. + + +A read() on a counter returns the current value of the counter and possible +additional values as specified by 'read_format', each value is a u64 (8 bytes) +in size. + +/* + * Bits that can be set in hw_event.read_format to request that + * reads on the counter should return the indicated quantities, + * in increasing order of bit value, after the counter value. + */ +enum perf_counter_read_format { + PERF_FORMAT_TOTAL_TIME_ENABLED = 1, + PERF_FORMAT_TOTAL_TIME_RUNNING = 2, +}; + +Using these additional values one can establish the overcommit ratio for a +particular counter allowing one to take the round-robin scheduling effect +into account. + + +A "sampling" counter is one that is set up to generate an interrupt +every N events, where N is given by 'irq_period'. A sampling counter +has irq_period > 0. The record_type controls what data is recorded on each +interrupt: + +/* + * Bits that can be set in hw_event.record_type to request information + * in the overflow packets. + */ +enum perf_counter_record_format { + PERF_RECORD_IP = 1U << 0, + PERF_RECORD_TID = 1U << 1, + PERF_RECORD_TIME = 1U << 2, + PERF_RECORD_ADDR = 1U << 3, + PERF_RECORD_GROUP = 1U << 4, + PERF_RECORD_CALLCHAIN = 1U << 5, +}; + +Such (and other) events will be recorded in a ring-buffer, which is +available to user-space using mmap() (see below). + +The 'disabled' bit specifies whether the counter starts out disabled +or enabled. If it is initially disabled, it can be enabled by ioctl +or prctl (see below). + +The 'inherit' bit, if set, specifies that this counter should count +events on descendant tasks as well as the task specified. This only +applies to new descendents, not to any existing descendents at the +time the counter is created (nor to any new descendents of existing +descendents). + +The 'pinned' bit, if set, specifies that the counter should always be +on the CPU if at all possible. It only applies to hardware counters +and only to group leaders. If a pinned counter cannot be put onto the +CPU (e.g. because there are not enough hardware counters or because of +a conflict with some other event), then the counter goes into an +'error' state, where reads return end-of-file (i.e. read() returns 0) +until the counter is subsequently enabled or disabled. + +The 'exclusive' bit, if set, specifies that when this counter's group +is on the CPU, it should be the only group using the CPU's counters. +In future, this will allow sophisticated monitoring programs to supply +extra configuration information via 'extra_config_len' to exploit +advanced features of the CPU's Performance Monitor Unit (PMU) that are +not otherwise accessible and that might disrupt other hardware +counters. + +The 'exclude_user', 'exclude_kernel' and 'exclude_hv' bits provide a +way to request that counting of events be restricted to times when the +CPU is in user, kernel and/or hypervisor mode. + +The 'mmap' and 'munmap' bits allow recording of PROT_EXEC mmap/munmap +operations, these can be used to relate userspace IP addresses to actual +code, even after the mapping (or even the whole process) is gone, +these events are recorded in the ring-buffer (see below). + +The 'comm' bit allows tracking of process comm data on process creation. +This too is recorded in the ring-buffer (see below). + +The 'pid' parameter to the perf_counter_open() system call allows the +counter to be specific to a task: + + pid == 0: if the pid parameter is zero, the counter is attached to the + current task. + + pid > 0: the counter is attached to a specific task (if the current task + has sufficient privilege to do so) + + pid < 0: all tasks are counted (per cpu counters) + +The 'cpu' parameter allows a counter to be made specific to a CPU: + + cpu >= 0: the counter is restricted to a specific CPU + cpu == -1: the counter counts on all CPUs + +(Note: the combination of 'pid == -1' and 'cpu == -1' is not valid.) + +A 'pid > 0' and 'cpu == -1' counter is a per task counter that counts +events of that task and 'follows' that task to whatever CPU the task +gets schedule to. Per task counters can be created by any user, for +their own tasks. + +A 'pid == -1' and 'cpu == x' counter is a per CPU counter that counts +all events on CPU-x. Per CPU counters need CAP_SYS_ADMIN privilege. + +The 'flags' parameter is currently unused and must be zero. + +The 'group_fd' parameter allows counter "groups" to be set up. A +counter group has one counter which is the group "leader". The leader +is created first, with group_fd = -1 in the perf_counter_open call +that creates it. The rest of the group members are created +subsequently, with group_fd giving the fd of the group leader. +(A single counter on its own is created with group_fd = -1 and is +considered to be a group with only 1 member.) + +A counter group is scheduled onto the CPU as a unit, that is, it will +only be put onto the CPU if all of the counters in the group can be +put onto the CPU. This means that the values of the member counters +can be meaningfully compared, added, divided (to get ratios), etc., +with each other, since they have counted events for the same set of +executed instructions. + + +Like stated, asynchronous events, like counter overflow or PROT_EXEC mmap +tracking are logged into a ring-buffer. This ring-buffer is created and +accessed through mmap(). + +The mmap size should be 1+2^n pages, where the first page is a meta-data page +(struct perf_counter_mmap_page) that contains various bits of information such +as where the ring-buffer head is. + +/* + * Structure of the page that can be mapped via mmap + */ +struct perf_counter_mmap_page { + __u32 version; /* version number of this structure */ + __u32 compat_version; /* lowest version this is compat with */ + + /* + * Bits needed to read the hw counters in user-space. + * + * u32 seq; + * s64 count; + * + * do { + * seq = pc->lock; + * + * barrier() + * if (pc->index) { + * count = pmc_read(pc->index - 1); + * count += pc->offset; + * } else + * goto regular_read; + * + * barrier(); + * } while (pc->lock != seq); + * + * NOTE: for obvious reason this only works on self-monitoring + * processes. + */ + __u32 lock; /* seqlock for synchronization */ + __u32 index; /* hardware counter identifier */ + __s64 offset; /* add to hardware counter value */ + + /* + * Control data for the mmap() data buffer. + * + * User-space reading this value should issue an rmb(), on SMP capable + * platforms, after reading this value -- see perf_counter_wakeup(). + */ + __u32 data_head; /* head in the data section */ +}; + +NOTE: the hw-counter userspace bits are arch specific and are currently only + implemented on powerpc. + +The following 2^n pages are the ring-buffer which contains events of the form: + +#define PERF_EVENT_MISC_KERNEL (1 << 0) +#define PERF_EVENT_MISC_USER (1 << 1) +#define PERF_EVENT_MISC_OVERFLOW (1 << 2) + +struct perf_event_header { + __u32 type; + __u16 misc; + __u16 size; +}; + +enum perf_event_type { + + /* + * The MMAP events record the PROT_EXEC mappings so that we can + * correlate userspace IPs to code. They have the following structure: + * + * struct { + * struct perf_event_header header; + * + * u32 pid, tid; + * u64 addr; + * u64 len; + * u64 pgoff; + * char filename[]; + * }; + */ + PERF_EVENT_MMAP = 1, + PERF_EVENT_MUNMAP = 2, + + /* + * struct { + * struct perf_event_header header; + * + * u32 pid, tid; + * char comm[]; + * }; + */ + PERF_EVENT_COMM = 3, + + /* + * When header.misc & PERF_EVENT_MISC_OVERFLOW the event_type field + * will be PERF_RECORD_* + * + * struct { + * struct perf_event_header header; + * + * { u64 ip; } && PERF_RECORD_IP + * { u32 pid, tid; } && PERF_RECORD_TID + * { u64 time; } && PERF_RECORD_TIME + * { u64 addr; } && PERF_RECORD_ADDR + * + * { u64 nr; + * { u64 event, val; } cnt[nr]; } && PERF_RECORD_GROUP + * + * { u16 nr, + * hv, + * kernel, + * user; + * u64 ips[nr]; } && PERF_RECORD_CALLCHAIN + * }; + */ +}; + +NOTE: PERF_RECORD_CALLCHAIN is arch specific and currently only implemented + on x86. + +Notification of new events is possible through poll()/select()/epoll() and +fcntl() managing signals. + +Normally a notification is generated for every page filled, however one can +additionally set perf_counter_hw_event.wakeup_events to generate one every +so many counter overflow events. + +Future work will include a splice() interface to the ring-buffer. + + +Counters can be enabled and disabled in two ways: via ioctl and via +prctl. When a counter is disabled, it doesn't count or generate +events but does continue to exist and maintain its count value. + +An individual counter or counter group can be enabled with + + ioctl(fd, PERF_COUNTER_IOC_ENABLE); + +or disabled with + + ioctl(fd, PERF_COUNTER_IOC_DISABLE); + +Enabling or disabling the leader of a group enables or disables the +whole group; that is, while the group leader is disabled, none of the +counters in the group will count. Enabling or disabling a member of a +group other than the leader only affects that counter - disabling an +non-leader stops that counter from counting but doesn't affect any +other counter. + +Additionally, non-inherited overflow counters can use + + ioctl(fd, PERF_COUNTER_IOC_REFRESH, nr); + +to enable a counter for 'nr' events, after which it gets disabled again. + +A process can enable or disable all the counter groups that are +attached to it, using prctl: + + prctl(PR_TASK_PERF_COUNTERS_ENABLE); + + prctl(PR_TASK_PERF_COUNTERS_DISABLE); + +This applies to all counters on the current process, whether created +by this process or by another, and doesn't affect any counters that +this process has created on other processes. It only enables or +disables the group leaders, not any other members in the groups. + diff --git a/tools/perf/perf.c b/tools/perf/perf.c new file mode 100644 index 0000000000000000000000000000000000000000..4eb725933703b6e8c41c558e46f11d705cc9d41f --- /dev/null +++ b/tools/perf/perf.c @@ -0,0 +1,428 @@ +/* + * perf.c + * + * Performance analysis utility. + * + * This is the main hub from which the sub-commands (perf stat, + * perf top, perf record, perf report, etc.) are started. + */ +#include "builtin.h" + +#include "util/exec_cmd.h" +#include "util/cache.h" +#include "util/quote.h" +#include "util/run-command.h" + +const char perf_usage_string[] = + "perf [--version] [--help] COMMAND [ARGS]"; + +const char perf_more_info_string[] = + "See 'perf help COMMAND' for more information on a specific command."; + +static int use_pager = -1; +struct pager_config { + const char *cmd; + int val; +}; + +static int pager_command_config(const char *var, const char *value, void *data) +{ + struct pager_config *c = data; + if (!prefixcmp(var, "pager.") && !strcmp(var + 6, c->cmd)) + c->val = perf_config_bool(var, value); + return 0; +} + +/* returns 0 for "no pager", 1 for "use pager", and -1 for "not specified" */ +int check_pager_config(const char *cmd) +{ + struct pager_config c; + c.cmd = cmd; + c.val = -1; + perf_config(pager_command_config, &c); + return c.val; +} + +static void commit_pager_choice(void) { + switch (use_pager) { + case 0: + setenv("PERF_PAGER", "cat", 1); + break; + case 1: + /* setup_pager(); */ + break; + default: + break; + } +} + +static int handle_options(const char*** argv, int* argc, int* envchanged) +{ + int handled = 0; + + while (*argc > 0) { + const char *cmd = (*argv)[0]; + if (cmd[0] != '-') + break; + + /* + * For legacy reasons, the "version" and "help" + * commands can be written with "--" prepended + * to make them look like flags. + */ + if (!strcmp(cmd, "--help") || !strcmp(cmd, "--version")) + break; + + /* + * Check remaining flags. + */ + if (!prefixcmp(cmd, "--exec-path")) { + cmd += 11; + if (*cmd == '=') + perf_set_argv_exec_path(cmd + 1); + else { + puts(perf_exec_path()); + exit(0); + } + } else if (!strcmp(cmd, "--html-path")) { + puts(system_path(PERF_HTML_PATH)); + exit(0); + } else if (!strcmp(cmd, "-p") || !strcmp(cmd, "--paginate")) { + use_pager = 1; + } else if (!strcmp(cmd, "--no-pager")) { + use_pager = 0; + if (envchanged) + *envchanged = 1; + } else if (!strcmp(cmd, "--perf-dir")) { + if (*argc < 2) { + fprintf(stderr, "No directory given for --perf-dir.\n" ); + usage(perf_usage_string); + } + setenv(PERF_DIR_ENVIRONMENT, (*argv)[1], 1); + if (envchanged) + *envchanged = 1; + (*argv)++; + (*argc)--; + handled++; + } else if (!prefixcmp(cmd, "--perf-dir=")) { + setenv(PERF_DIR_ENVIRONMENT, cmd + 10, 1); + if (envchanged) + *envchanged = 1; + } else if (!strcmp(cmd, "--work-tree")) { + if (*argc < 2) { + fprintf(stderr, "No directory given for --work-tree.\n" ); + usage(perf_usage_string); + } + setenv(PERF_WORK_TREE_ENVIRONMENT, (*argv)[1], 1); + if (envchanged) + *envchanged = 1; + (*argv)++; + (*argc)--; + } else if (!prefixcmp(cmd, "--work-tree=")) { + setenv(PERF_WORK_TREE_ENVIRONMENT, cmd + 12, 1); + if (envchanged) + *envchanged = 1; + } else { + fprintf(stderr, "Unknown option: %s\n", cmd); + usage(perf_usage_string); + } + + (*argv)++; + (*argc)--; + handled++; + } + return handled; +} + +static int handle_alias(int *argcp, const char ***argv) +{ + int envchanged = 0, ret = 0, saved_errno = errno; + int count, option_count; + const char** new_argv; + const char *alias_command; + char *alias_string; + + alias_command = (*argv)[0]; + alias_string = alias_lookup(alias_command); + if (alias_string) { + if (alias_string[0] == '!') { + if (*argcp > 1) { + struct strbuf buf; + + strbuf_init(&buf, PATH_MAX); + strbuf_addstr(&buf, alias_string); + sq_quote_argv(&buf, (*argv) + 1, PATH_MAX); + free(alias_string); + alias_string = buf.buf; + } + ret = system(alias_string + 1); + if (ret >= 0 && WIFEXITED(ret) && + WEXITSTATUS(ret) != 127) + exit(WEXITSTATUS(ret)); + die("Failed to run '%s' when expanding alias '%s'", + alias_string + 1, alias_command); + } + count = split_cmdline(alias_string, &new_argv); + if (count < 0) + die("Bad alias.%s string", alias_command); + option_count = handle_options(&new_argv, &count, &envchanged); + if (envchanged) + die("alias '%s' changes environment variables\n" + "You can use '!perf' in the alias to do this.", + alias_command); + memmove(new_argv - option_count, new_argv, + count * sizeof(char *)); + new_argv -= option_count; + + if (count < 1) + die("empty alias for %s", alias_command); + + if (!strcmp(alias_command, new_argv[0])) + die("recursive alias: %s", alias_command); + + new_argv = realloc(new_argv, sizeof(char*) * + (count + *argcp + 1)); + /* insert after command name */ + memcpy(new_argv + count, *argv + 1, sizeof(char*) * *argcp); + new_argv[count+*argcp] = NULL; + + *argv = new_argv; + *argcp += count - 1; + + ret = 1; + } + + errno = saved_errno; + + return ret; +} + +const char perf_version_string[] = PERF_VERSION; + +#define RUN_SETUP (1<<0) +#define USE_PAGER (1<<1) +/* + * require working tree to be present -- anything uses this needs + * RUN_SETUP for reading from the configuration file. + */ +#define NEED_WORK_TREE (1<<2) + +struct cmd_struct { + const char *cmd; + int (*fn)(int, const char **, const char *); + int option; +}; + +static int run_builtin(struct cmd_struct *p, int argc, const char **argv) +{ + int status; + struct stat st; + const char *prefix; + + prefix = NULL; + if (p->option & RUN_SETUP) + prefix = NULL; /* setup_perf_directory(); */ + + if (use_pager == -1 && p->option & RUN_SETUP) + use_pager = check_pager_config(p->cmd); + if (use_pager == -1 && p->option & USE_PAGER) + use_pager = 1; + commit_pager_choice(); + + if (p->option & NEED_WORK_TREE) + /* setup_work_tree() */; + + status = p->fn(argc, argv, prefix); + if (status) + return status & 0xff; + + /* Somebody closed stdout? */ + if (fstat(fileno(stdout), &st)) + return 0; + /* Ignore write errors for pipes and sockets.. */ + if (S_ISFIFO(st.st_mode) || S_ISSOCK(st.st_mode)) + return 0; + + /* Check for ENOSPC and EIO errors.. */ + if (fflush(stdout)) + die("write failure on standard output: %s", strerror(errno)); + if (ferror(stdout)) + die("unknown write failure on standard output"); + if (fclose(stdout)) + die("close failed on standard output: %s", strerror(errno)); + return 0; +} + +static void handle_internal_command(int argc, const char **argv) +{ + const char *cmd = argv[0]; + static struct cmd_struct commands[] = { + { "help", cmd_help, 0 }, + { "list", cmd_list, 0 }, + { "record", cmd_record, 0 }, + { "report", cmd_report, 0 }, + { "stat", cmd_stat, 0 }, + { "top", cmd_top, 0 }, + { "annotate", cmd_annotate, 0 }, + { "version", cmd_version, 0 }, + }; + int i; + static const char ext[] = STRIP_EXTENSION; + + if (sizeof(ext) > 1) { + i = strlen(argv[0]) - strlen(ext); + if (i > 0 && !strcmp(argv[0] + i, ext)) { + char *argv0 = strdup(argv[0]); + argv[0] = cmd = argv0; + argv0[i] = '\0'; + } + } + + /* Turn "perf cmd --help" into "perf help cmd" */ + if (argc > 1 && !strcmp(argv[1], "--help")) { + argv[1] = argv[0]; + argv[0] = cmd = "help"; + } + + for (i = 0; i < ARRAY_SIZE(commands); i++) { + struct cmd_struct *p = commands+i; + if (strcmp(p->cmd, cmd)) + continue; + exit(run_builtin(p, argc, argv)); + } +} + +static void execv_dashed_external(const char **argv) +{ + struct strbuf cmd = STRBUF_INIT; + const char *tmp; + int status; + + strbuf_addf(&cmd, "perf-%s", argv[0]); + + /* + * argv[0] must be the perf command, but the argv array + * belongs to the caller, and may be reused in + * subsequent loop iterations. Save argv[0] and + * restore it on error. + */ + tmp = argv[0]; + argv[0] = cmd.buf; + + /* + * if we fail because the command is not found, it is + * OK to return. Otherwise, we just pass along the status code. + */ + status = run_command_v_opt(argv, 0); + if (status != -ERR_RUN_COMMAND_EXEC) { + if (IS_RUN_COMMAND_ERR(status)) + die("unable to run '%s'", argv[0]); + exit(-status); + } + errno = ENOENT; /* as if we called execvp */ + + argv[0] = tmp; + + strbuf_release(&cmd); +} + +static int run_argv(int *argcp, const char ***argv) +{ + int done_alias = 0; + + while (1) { + /* See if it's an internal command */ + handle_internal_command(*argcp, *argv); + + /* .. then try the external ones */ + execv_dashed_external(*argv); + + /* It could be an alias -- this works around the insanity + * of overriding "perf log" with "perf show" by having + * alias.log = show + */ + if (done_alias || !handle_alias(argcp, argv)) + break; + done_alias = 1; + } + + return done_alias; +} + + +int main(int argc, const char **argv) +{ + const char *cmd; + + cmd = perf_extract_argv0_path(argv[0]); + if (!cmd) + cmd = "perf-help"; + + /* + * "perf-xxxx" is the same as "perf xxxx", but we obviously: + * + * - cannot take flags in between the "perf" and the "xxxx". + * - cannot execute it externally (since it would just do + * the same thing over again) + * + * So we just directly call the internal command handler, and + * die if that one cannot handle it. + */ + if (!prefixcmp(cmd, "perf-")) { + cmd += 5; + argv[0] = cmd; + handle_internal_command(argc, argv); + die("cannot handle %s internally", cmd); + } + + /* Look for flags.. */ + argv++; + argc--; + handle_options(&argv, &argc, NULL); + commit_pager_choice(); + if (argc > 0) { + if (!prefixcmp(argv[0], "--")) + argv[0] += 2; + } else { + /* The user didn't specify a command; give them help */ + printf("\n usage: %s\n\n", perf_usage_string); + list_common_cmds_help(); + printf("\n %s\n\n", perf_more_info_string); + exit(1); + } + cmd = argv[0]; + + /* + * We use PATH to find perf commands, but we prepend some higher + * precidence paths: the "--exec-path" option, the PERF_EXEC_PATH + * environment, and the $(perfexecdir) from the Makefile at build + * time. + */ + setup_path(); + + while (1) { + static int done_help = 0; + static int was_alias = 0; + + was_alias = run_argv(&argc, &argv); + if (errno != ENOENT) + break; + + if (was_alias) { + fprintf(stderr, "Expansion of alias '%s' failed; " + "'%s' is not a perf-command\n", + cmd, argv[0]); + exit(1); + } + if (!done_help) { + cmd = argv[0] = help_unknown_cmd(cmd); + done_help = 1; + } else + break; + } + + fprintf(stderr, "Failed to run command '%s': %s\n", + cmd, strerror(errno)); + + return 1; +} diff --git a/tools/perf/perf.h b/tools/perf/perf.h new file mode 100644 index 0000000000000000000000000000000000000000..af0a5046d743a22b718b0360b392cc4107fdc6ef --- /dev/null +++ b/tools/perf/perf.h @@ -0,0 +1,67 @@ +#ifndef _PERF_PERF_H +#define _PERF_PERF_H + +#if defined(__x86_64__) || defined(__i386__) +#include "../../arch/x86/include/asm/unistd.h" +#define rmb() asm volatile("lfence" ::: "memory") +#define cpu_relax() asm volatile("rep; nop" ::: "memory"); +#endif + +#ifdef __powerpc__ +#include "../../arch/powerpc/include/asm/unistd.h" +#define rmb() asm volatile ("sync" ::: "memory") +#define cpu_relax() asm volatile ("" ::: "memory"); +#endif + +#include +#include +#include +#include + +#include "../../include/linux/perf_counter.h" + +/* + * prctl(PR_TASK_PERF_COUNTERS_DISABLE) will (cheaply) disable all + * counters in the current task. + */ +#define PR_TASK_PERF_COUNTERS_DISABLE 31 +#define PR_TASK_PERF_COUNTERS_ENABLE 32 + +#ifndef NSEC_PER_SEC +# define NSEC_PER_SEC 1000000000ULL +#endif + +static inline unsigned long long rdclock(void) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC, &ts); + return ts.tv_sec * 1000000000ULL + ts.tv_nsec; +} + +/* + * Pick up some kernel type conventions: + */ +#define __user +#define asmlinkage + +#define unlikely(x) __builtin_expect(!!(x), 0) +#define min(x, y) ({ \ + typeof(x) _min1 = (x); \ + typeof(y) _min2 = (y); \ + (void) (&_min1 == &_min2); \ + _min1 < _min2 ? _min1 : _min2; }) + +static inline int +sys_perf_counter_open(struct perf_counter_attr *attr_uptr, + pid_t pid, int cpu, int group_fd, + unsigned long flags) +{ + return syscall(__NR_perf_counter_open, attr_uptr, pid, cpu, + group_fd, flags); +} + +#define MAX_COUNTERS 256 +#define MAX_NR_CPUS 256 + +#endif diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN new file mode 100755 index 0000000000000000000000000000000000000000..c561d1538c039df208f6d7bbdf96d3030c06ef4d --- /dev/null +++ b/tools/perf/util/PERF-VERSION-GEN @@ -0,0 +1,42 @@ +#!/bin/sh + +GVF=PERF-VERSION-FILE +DEF_VER=v0.0.1.PERF + +LF=' +' + +# First see if there is a version file (included in release tarballs), +# then try git-describe, then default. +if test -f version +then + VN=$(cat version) || VN="$DEF_VER" +elif test -d .git -o -f .git && + VN=$(git describe --abbrev=4 HEAD 2>/dev/null) && + case "$VN" in + *$LF*) (exit 1) ;; + v[0-9]*) + git update-index -q --refresh + test -z "$(git diff-index --name-only HEAD --)" || + VN="$VN-dirty" ;; + esac +then + VN=$(echo "$VN" | sed -e 's/-/./g'); +else + VN="$DEF_VER" +fi + +VN=$(expr "$VN" : v*'\(.*\)') + +if test -r $GVF +then + VC=$(sed -e 's/^PERF_VERSION = //' <$GVF) +else + VC=unset +fi +test "$VN" = "$VC" || { + echo >&2 "PERF_VERSION = $VN" + echo "PERF_VERSION = $VN" >$GVF +} + + diff --git a/tools/perf/util/abspath.c b/tools/perf/util/abspath.c new file mode 100644 index 0000000000000000000000000000000000000000..61d33b81fc979ad66f9843872ac94720f3398f33 --- /dev/null +++ b/tools/perf/util/abspath.c @@ -0,0 +1,117 @@ +#include "cache.h" + +/* + * Do not use this for inspecting *tracked* content. When path is a + * symlink to a directory, we do not want to say it is a directory when + * dealing with tracked content in the working tree. + */ +static int is_directory(const char *path) +{ + struct stat st; + return (!stat(path, &st) && S_ISDIR(st.st_mode)); +} + +/* We allow "recursive" symbolic links. Only within reason, though. */ +#define MAXDEPTH 5 + +const char *make_absolute_path(const char *path) +{ + static char bufs[2][PATH_MAX + 1], *buf = bufs[0], *next_buf = bufs[1]; + char cwd[1024] = ""; + int buf_index = 1, len; + + int depth = MAXDEPTH; + char *last_elem = NULL; + struct stat st; + + if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX) + die ("Too long path: %.*s", 60, path); + + while (depth--) { + if (!is_directory(buf)) { + char *last_slash = strrchr(buf, '/'); + if (last_slash) { + *last_slash = '\0'; + last_elem = xstrdup(last_slash + 1); + } else { + last_elem = xstrdup(buf); + *buf = '\0'; + } + } + + if (*buf) { + if (!*cwd && !getcwd(cwd, sizeof(cwd))) + die ("Could not get current working directory"); + + if (chdir(buf)) + die ("Could not switch to '%s'", buf); + } + if (!getcwd(buf, PATH_MAX)) + die ("Could not get current working directory"); + + if (last_elem) { + int len = strlen(buf); + if (len + strlen(last_elem) + 2 > PATH_MAX) + die ("Too long path name: '%s/%s'", + buf, last_elem); + buf[len] = '/'; + strcpy(buf + len + 1, last_elem); + free(last_elem); + last_elem = NULL; + } + + if (!lstat(buf, &st) && S_ISLNK(st.st_mode)) { + len = readlink(buf, next_buf, PATH_MAX); + if (len < 0) + die ("Invalid symlink: %s", buf); + if (PATH_MAX <= len) + die("symbolic link too long: %s", buf); + next_buf[len] = '\0'; + buf = next_buf; + buf_index = 1 - buf_index; + next_buf = bufs[buf_index]; + } else + break; + } + + if (*cwd && chdir(cwd)) + die ("Could not change back to '%s'", cwd); + + return buf; +} + +static const char *get_pwd_cwd(void) +{ + static char cwd[PATH_MAX + 1]; + char *pwd; + struct stat cwd_stat, pwd_stat; + if (getcwd(cwd, PATH_MAX) == NULL) + return NULL; + pwd = getenv("PWD"); + if (pwd && strcmp(pwd, cwd)) { + stat(cwd, &cwd_stat); + if (!stat(pwd, &pwd_stat) && + pwd_stat.st_dev == cwd_stat.st_dev && + pwd_stat.st_ino == cwd_stat.st_ino) { + strlcpy(cwd, pwd, PATH_MAX); + } + } + return cwd; +} + +const char *make_nonrelative_path(const char *path) +{ + static char buf[PATH_MAX + 1]; + + if (is_absolute_path(path)) { + if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX) + die("Too long path: %.*s", 60, path); + } else { + const char *cwd = get_pwd_cwd(); + if (!cwd) + die("Cannot determine the current working directory"); + if (snprintf(buf, PATH_MAX, "%s/%s", cwd, path) >= PATH_MAX) + die("Too long path: %.*s", 60, path); + } + return buf; +} diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c new file mode 100644 index 0000000000000000000000000000000000000000..9b3dd2b428df8c4e95ed0dce7e281419744cf14e --- /dev/null +++ b/tools/perf/util/alias.c @@ -0,0 +1,77 @@ +#include "cache.h" + +static const char *alias_key; +static char *alias_val; + +static int alias_lookup_cb(const char *k, const char *v, void *cb) +{ + if (!prefixcmp(k, "alias.") && !strcmp(k+6, alias_key)) { + if (!v) + return config_error_nonbool(k); + alias_val = strdup(v); + return 0; + } + return 0; +} + +char *alias_lookup(const char *alias) +{ + alias_key = alias; + alias_val = NULL; + perf_config(alias_lookup_cb, NULL); + return alias_val; +} + +int split_cmdline(char *cmdline, const char ***argv) +{ + int src, dst, count = 0, size = 16; + char quoted = 0; + + *argv = malloc(sizeof(char*) * size); + + /* split alias_string */ + (*argv)[count++] = cmdline; + for (src = dst = 0; cmdline[src];) { + char c = cmdline[src]; + if (!quoted && isspace(c)) { + cmdline[dst++] = 0; + while (cmdline[++src] + && isspace(cmdline[src])) + ; /* skip */ + if (count >= size) { + size += 16; + *argv = realloc(*argv, sizeof(char*) * size); + } + (*argv)[count++] = cmdline + dst; + } else if (!quoted && (c == '\'' || c == '"')) { + quoted = c; + src++; + } else if (c == quoted) { + quoted = 0; + src++; + } else { + if (c == '\\' && quoted != '\'') { + src++; + c = cmdline[src]; + if (!c) { + free(*argv); + *argv = NULL; + return error("cmdline ends with \\"); + } + } + cmdline[dst++] = c; + src++; + } + } + + cmdline[dst] = 0; + + if (quoted) { + free(*argv); + *argv = NULL; + return error("unclosed quote"); + } + + return count; +} + diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h new file mode 100644 index 0000000000000000000000000000000000000000..393d6146d13b38743641adb819c2552a56716043 --- /dev/null +++ b/tools/perf/util/cache.h @@ -0,0 +1,119 @@ +#ifndef CACHE_H +#define CACHE_H + +#include "util.h" +#include "strbuf.h" + +#define PERF_DIR_ENVIRONMENT "PERF_DIR" +#define PERF_WORK_TREE_ENVIRONMENT "PERF_WORK_TREE" +#define DEFAULT_PERF_DIR_ENVIRONMENT ".perf" +#define DB_ENVIRONMENT "PERF_OBJECT_DIRECTORY" +#define INDEX_ENVIRONMENT "PERF_INDEX_FILE" +#define GRAFT_ENVIRONMENT "PERF_GRAFT_FILE" +#define TEMPLATE_DIR_ENVIRONMENT "PERF_TEMPLATE_DIR" +#define CONFIG_ENVIRONMENT "PERF_CONFIG" +#define EXEC_PATH_ENVIRONMENT "PERF_EXEC_PATH" +#define CEILING_DIRECTORIES_ENVIRONMENT "PERF_CEILING_DIRECTORIES" +#define PERFATTRIBUTES_FILE ".perfattributes" +#define INFOATTRIBUTES_FILE "info/attributes" +#define ATTRIBUTE_MACRO_PREFIX "[attr]" + +typedef int (*config_fn_t)(const char *, const char *, void *); +extern int perf_default_config(const char *, const char *, void *); +extern int perf_config_from_file(config_fn_t fn, const char *, void *); +extern int perf_config(config_fn_t fn, void *); +extern int perf_parse_ulong(const char *, unsigned long *); +extern int perf_config_int(const char *, const char *); +extern unsigned long perf_config_ulong(const char *, const char *); +extern int perf_config_bool_or_int(const char *, const char *, int *); +extern int perf_config_bool(const char *, const char *); +extern int perf_config_string(const char **, const char *, const char *); +extern int perf_config_set(const char *, const char *); +extern int perf_config_set_multivar(const char *, const char *, const char *, int); +extern int perf_config_rename_section(const char *, const char *); +extern const char *perf_etc_perfconfig(void); +extern int check_repository_format_version(const char *var, const char *value, void *cb); +extern int perf_config_system(void); +extern int perf_config_global(void); +extern int config_error_nonbool(const char *); +extern const char *config_exclusive_filename; + +#define MAX_PERFNAME (1000) +extern char perf_default_email[MAX_PERFNAME]; +extern char perf_default_name[MAX_PERFNAME]; +extern int user_ident_explicitly_given; + +extern const char *perf_log_output_encoding; +extern const char *perf_mailmap_file; + +/* IO helper functions */ +extern void maybe_flush_or_die(FILE *, const char *); +extern int copy_fd(int ifd, int ofd); +extern int copy_file(const char *dst, const char *src, int mode); +extern ssize_t read_in_full(int fd, void *buf, size_t count); +extern ssize_t write_in_full(int fd, const void *buf, size_t count); +extern void write_or_die(int fd, const void *buf, size_t count); +extern int write_or_whine(int fd, const void *buf, size_t count, const char *msg); +extern int write_or_whine_pipe(int fd, const void *buf, size_t count, const char *msg); +extern void fsync_or_die(int fd, const char *); + +/* pager.c */ +extern void setup_pager(void); +extern const char *pager_program; +extern int pager_in_use(void); +extern int pager_use_color; + +extern const char *editor_program; +extern const char *excludes_file; + +char *alias_lookup(const char *alias); +int split_cmdline(char *cmdline, const char ***argv); + +#define alloc_nr(x) (((x)+16)*3/2) + +/* + * Realloc the buffer pointed at by variable 'x' so that it can hold + * at least 'nr' entries; the number of entries currently allocated + * is 'alloc', using the standard growing factor alloc_nr() macro. + * + * DO NOT USE any expression with side-effect for 'x' or 'alloc'. + */ +#define ALLOC_GROW(x, nr, alloc) \ + do { \ + if ((nr) > alloc) { \ + if (alloc_nr(alloc) < (nr)) \ + alloc = (nr); \ + else \ + alloc = alloc_nr(alloc); \ + x = xrealloc((x), alloc * sizeof(*(x))); \ + } \ + } while(0) + + +static inline int is_absolute_path(const char *path) +{ + return path[0] == '/'; +} + +const char *make_absolute_path(const char *path); +const char *make_nonrelative_path(const char *path); +const char *make_relative_path(const char *abs, const char *base); +int normalize_path_copy(char *dst, const char *src); +int longest_ancestor_length(const char *path, const char *prefix_list); +char *strip_path_suffix(const char *path, const char *suffix); + +extern char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2))); +extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2))); +/* perf_mkstemp() - create tmp file honoring TMPDIR variable */ +extern int perf_mkstemp(char *path, size_t len, const char *template); + +extern char *mksnpath(char *buf, size_t n, const char *fmt, ...) + __attribute__((format (printf, 3, 4))); +extern char *perf_snpath(char *buf, size_t n, const char *fmt, ...) + __attribute__((format (printf, 3, 4))); +extern char *perf_pathdup(const char *fmt, ...) + __attribute__((format (printf, 1, 2))); + +extern size_t strlcpy(char *dest, const char *src, size_t size); + +#endif /* CACHE_H */ diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c new file mode 100644 index 0000000000000000000000000000000000000000..9a8c20ccc53e28dd99ab6bd2f27f548fe85532fe --- /dev/null +++ b/tools/perf/util/color.c @@ -0,0 +1,241 @@ +#include "cache.h" +#include "color.h" + +int perf_use_color_default = -1; + +static int parse_color(const char *name, int len) +{ + static const char * const color_names[] = { + "normal", "black", "red", "green", "yellow", + "blue", "magenta", "cyan", "white" + }; + char *end; + int i; + for (i = 0; i < ARRAY_SIZE(color_names); i++) { + const char *str = color_names[i]; + if (!strncasecmp(name, str, len) && !str[len]) + return i - 1; + } + i = strtol(name, &end, 10); + if (end - name == len && i >= -1 && i <= 255) + return i; + return -2; +} + +static int parse_attr(const char *name, int len) +{ + static const int attr_values[] = { 1, 2, 4, 5, 7 }; + static const char * const attr_names[] = { + "bold", "dim", "ul", "blink", "reverse" + }; + int i; + for (i = 0; i < ARRAY_SIZE(attr_names); i++) { + const char *str = attr_names[i]; + if (!strncasecmp(name, str, len) && !str[len]) + return attr_values[i]; + } + return -1; +} + +void color_parse(const char *value, const char *var, char *dst) +{ + color_parse_mem(value, strlen(value), var, dst); +} + +void color_parse_mem(const char *value, int value_len, const char *var, + char *dst) +{ + const char *ptr = value; + int len = value_len; + int attr = -1; + int fg = -2; + int bg = -2; + + if (!strncasecmp(value, "reset", len)) { + strcpy(dst, PERF_COLOR_RESET); + return; + } + + /* [fg [bg]] [attr] */ + while (len > 0) { + const char *word = ptr; + int val, wordlen = 0; + + while (len > 0 && !isspace(word[wordlen])) { + wordlen++; + len--; + } + + ptr = word + wordlen; + while (len > 0 && isspace(*ptr)) { + ptr++; + len--; + } + + val = parse_color(word, wordlen); + if (val >= -1) { + if (fg == -2) { + fg = val; + continue; + } + if (bg == -2) { + bg = val; + continue; + } + goto bad; + } + val = parse_attr(word, wordlen); + if (val < 0 || attr != -1) + goto bad; + attr = val; + } + + if (attr >= 0 || fg >= 0 || bg >= 0) { + int sep = 0; + + *dst++ = '\033'; + *dst++ = '['; + if (attr >= 0) { + *dst++ = '0' + attr; + sep++; + } + if (fg >= 0) { + if (sep++) + *dst++ = ';'; + if (fg < 8) { + *dst++ = '3'; + *dst++ = '0' + fg; + } else { + dst += sprintf(dst, "38;5;%d", fg); + } + } + if (bg >= 0) { + if (sep++) + *dst++ = ';'; + if (bg < 8) { + *dst++ = '4'; + *dst++ = '0' + bg; + } else { + dst += sprintf(dst, "48;5;%d", bg); + } + } + *dst++ = 'm'; + } + *dst = 0; + return; +bad: + die("bad color value '%.*s' for variable '%s'", value_len, value, var); +} + +int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty) +{ + if (value) { + if (!strcasecmp(value, "never")) + return 0; + if (!strcasecmp(value, "always")) + return 1; + if (!strcasecmp(value, "auto")) + goto auto_color; + } + + /* Missing or explicit false to turn off colorization */ + if (!perf_config_bool(var, value)) + return 0; + + /* any normal truth value defaults to 'auto' */ + auto_color: + if (stdout_is_tty < 0) + stdout_is_tty = isatty(1); + if (stdout_is_tty || (pager_in_use() && pager_use_color)) { + char *term = getenv("TERM"); + if (term && strcmp(term, "dumb")) + return 1; + } + return 0; +} + +int perf_color_default_config(const char *var, const char *value, void *cb) +{ + if (!strcmp(var, "color.ui")) { + perf_use_color_default = perf_config_colorbool(var, value, -1); + return 0; + } + + return perf_default_config(var, value, cb); +} + +static int color_vfprintf(FILE *fp, const char *color, const char *fmt, + va_list args, const char *trail) +{ + int r = 0; + + /* + * Auto-detect: + */ + if (perf_use_color_default < 0) { + if (isatty(1) || pager_in_use()) + perf_use_color_default = 1; + else + perf_use_color_default = 0; + } + + if (perf_use_color_default && *color) + r += fprintf(fp, "%s", color); + r += vfprintf(fp, fmt, args); + if (perf_use_color_default && *color) + r += fprintf(fp, "%s", PERF_COLOR_RESET); + if (trail) + r += fprintf(fp, "%s", trail); + return r; +} + + + +int color_fprintf(FILE *fp, const char *color, const char *fmt, ...) +{ + va_list args; + int r; + + va_start(args, fmt); + r = color_vfprintf(fp, color, fmt, args, NULL); + va_end(args); + return r; +} + +int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...) +{ + va_list args; + int r; + va_start(args, fmt); + r = color_vfprintf(fp, color, fmt, args, "\n"); + va_end(args); + return r; +} + +/* + * This function splits the buffer by newlines and colors the lines individually. + * + * Returns 0 on success. + */ +int color_fwrite_lines(FILE *fp, const char *color, + size_t count, const char *buf) +{ + if (!*color) + return fwrite(buf, count, 1, fp) != 1; + while (count) { + char *p = memchr(buf, '\n', count); + if (p != buf && (fputs(color, fp) < 0 || + fwrite(buf, p ? p - buf : count, 1, fp) != 1 || + fputs(PERF_COLOR_RESET, fp) < 0)) + return -1; + if (!p) + return 0; + if (fputc('\n', fp) < 0) + return -1; + count -= p + 1 - buf; + buf = p + 1; + } + return 0; +} + + diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h new file mode 100644 index 0000000000000000000000000000000000000000..5abfd379582b40428f62807b5aefa81a239a49d2 --- /dev/null +++ b/tools/perf/util/color.h @@ -0,0 +1,36 @@ +#ifndef COLOR_H +#define COLOR_H + +/* "\033[1;38;5;2xx;48;5;2xxm\0" is 23 bytes */ +#define COLOR_MAXLEN 24 + +#define PERF_COLOR_NORMAL "" +#define PERF_COLOR_RESET "\033[m" +#define PERF_COLOR_BOLD "\033[1m" +#define PERF_COLOR_RED "\033[31m" +#define PERF_COLOR_GREEN "\033[32m" +#define PERF_COLOR_YELLOW "\033[33m" +#define PERF_COLOR_BLUE "\033[34m" +#define PERF_COLOR_MAGENTA "\033[35m" +#define PERF_COLOR_CYAN "\033[36m" +#define PERF_COLOR_BG_RED "\033[41m" + +/* + * This variable stores the value of color.ui + */ +extern int perf_use_color_default; + + +/* + * Use this instead of perf_default_config if you need the value of color.ui. + */ +int perf_color_default_config(const char *var, const char *value, void *cb); + +int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty); +void color_parse(const char *value, const char *var, char *dst); +void color_parse_mem(const char *value, int len, const char *var, char *dst); +int color_fprintf(FILE *fp, const char *color, const char *fmt, ...); +int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...); +int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf); + +#endif /* COLOR_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c new file mode 100644 index 0000000000000000000000000000000000000000..3dd13faa6a27f9e1378184bd3349c2a3cf51f073 --- /dev/null +++ b/tools/perf/util/config.c @@ -0,0 +1,873 @@ +/* + * GIT - The information manager from hell + * + * Copyright (C) Linus Torvalds, 2005 + * Copyright (C) Johannes Schindelin, 2005 + * + */ +#include "util.h" +#include "cache.h" +#include "exec_cmd.h" + +#define MAXNAME (256) + +static FILE *config_file; +static const char *config_file_name; +static int config_linenr; +static int config_file_eof; + +const char *config_exclusive_filename = NULL; + +static int get_next_char(void) +{ + int c; + FILE *f; + + c = '\n'; + if ((f = config_file) != NULL) { + c = fgetc(f); + if (c == '\r') { + /* DOS like systems */ + c = fgetc(f); + if (c != '\n') { + ungetc(c, f); + c = '\r'; + } + } + if (c == '\n') + config_linenr++; + if (c == EOF) { + config_file_eof = 1; + c = '\n'; + } + } + return c; +} + +static char *parse_value(void) +{ + static char value[1024]; + int quote = 0, comment = 0, len = 0, space = 0; + + for (;;) { + int c = get_next_char(); + if (len >= sizeof(value) - 1) + return NULL; + if (c == '\n') { + if (quote) + return NULL; + value[len] = 0; + return value; + } + if (comment) + continue; + if (isspace(c) && !quote) { + space = 1; + continue; + } + if (!quote) { + if (c == ';' || c == '#') { + comment = 1; + continue; + } + } + if (space) { + if (len) + value[len++] = ' '; + space = 0; + } + if (c == '\\') { + c = get_next_char(); + switch (c) { + case '\n': + continue; + case 't': + c = '\t'; + break; + case 'b': + c = '\b'; + break; + case 'n': + c = '\n'; + break; + /* Some characters escape as themselves */ + case '\\': case '"': + break; + /* Reject unknown escape sequences */ + default: + return NULL; + } + value[len++] = c; + continue; + } + if (c == '"') { + quote = 1-quote; + continue; + } + value[len++] = c; + } +} + +static inline int iskeychar(int c) +{ + return isalnum(c) || c == '-'; +} + +static int get_value(config_fn_t fn, void *data, char *name, unsigned int len) +{ + int c; + char *value; + + /* Get the full name */ + for (;;) { + c = get_next_char(); + if (config_file_eof) + break; + if (!iskeychar(c)) + break; + name[len++] = tolower(c); + if (len >= MAXNAME) + return -1; + } + name[len] = 0; + while (c == ' ' || c == '\t') + c = get_next_char(); + + value = NULL; + if (c != '\n') { + if (c != '=') + return -1; + value = parse_value(); + if (!value) + return -1; + } + return fn(name, value, data); +} + +static int get_extended_base_var(char *name, int baselen, int c) +{ + do { + if (c == '\n') + return -1; + c = get_next_char(); + } while (isspace(c)); + + /* We require the format to be '[base "extension"]' */ + if (c != '"') + return -1; + name[baselen++] = '.'; + + for (;;) { + int c = get_next_char(); + if (c == '\n') + return -1; + if (c == '"') + break; + if (c == '\\') { + c = get_next_char(); + if (c == '\n') + return -1; + } + name[baselen++] = c; + if (baselen > MAXNAME / 2) + return -1; + } + + /* Final ']' */ + if (get_next_char() != ']') + return -1; + return baselen; +} + +static int get_base_var(char *name) +{ + int baselen = 0; + + for (;;) { + int c = get_next_char(); + if (config_file_eof) + return -1; + if (c == ']') + return baselen; + if (isspace(c)) + return get_extended_base_var(name, baselen, c); + if (!iskeychar(c) && c != '.') + return -1; + if (baselen > MAXNAME / 2) + return -1; + name[baselen++] = tolower(c); + } +} + +static int perf_parse_file(config_fn_t fn, void *data) +{ + int comment = 0; + int baselen = 0; + static char var[MAXNAME]; + + /* U+FEFF Byte Order Mark in UTF8 */ + static const unsigned char *utf8_bom = (unsigned char *) "\xef\xbb\xbf"; + const unsigned char *bomptr = utf8_bom; + + for (;;) { + int c = get_next_char(); + if (bomptr && *bomptr) { + /* We are at the file beginning; skip UTF8-encoded BOM + * if present. Sane editors won't put this in on their + * own, but e.g. Windows Notepad will do it happily. */ + if ((unsigned char) c == *bomptr) { + bomptr++; + continue; + } else { + /* Do not tolerate partial BOM. */ + if (bomptr != utf8_bom) + break; + /* No BOM at file beginning. Cool. */ + bomptr = NULL; + } + } + if (c == '\n') { + if (config_file_eof) + return 0; + comment = 0; + continue; + } + if (comment || isspace(c)) + continue; + if (c == '#' || c == ';') { + comment = 1; + continue; + } + if (c == '[') { + baselen = get_base_var(var); + if (baselen <= 0) + break; + var[baselen++] = '.'; + var[baselen] = 0; + continue; + } + if (!isalpha(c)) + break; + var[baselen] = tolower(c); + if (get_value(fn, data, var, baselen+1) < 0) + break; + } + die("bad config file line %d in %s", config_linenr, config_file_name); +} + +static int parse_unit_factor(const char *end, unsigned long *val) +{ + if (!*end) + return 1; + else if (!strcasecmp(end, "k")) { + *val *= 1024; + return 1; + } + else if (!strcasecmp(end, "m")) { + *val *= 1024 * 1024; + return 1; + } + else if (!strcasecmp(end, "g")) { + *val *= 1024 * 1024 * 1024; + return 1; + } + return 0; +} + +static int perf_parse_long(const char *value, long *ret) +{ + if (value && *value) { + char *end; + long val = strtol(value, &end, 0); + unsigned long factor = 1; + if (!parse_unit_factor(end, &factor)) + return 0; + *ret = val * factor; + return 1; + } + return 0; +} + +int perf_parse_ulong(const char *value, unsigned long *ret) +{ + if (value && *value) { + char *end; + unsigned long val = strtoul(value, &end, 0); + if (!parse_unit_factor(end, &val)) + return 0; + *ret = val; + return 1; + } + return 0; +} + +static void die_bad_config(const char *name) +{ + if (config_file_name) + die("bad config value for '%s' in %s", name, config_file_name); + die("bad config value for '%s'", name); +} + +int perf_config_int(const char *name, const char *value) +{ + long ret = 0; + if (!perf_parse_long(value, &ret)) + die_bad_config(name); + return ret; +} + +unsigned long perf_config_ulong(const char *name, const char *value) +{ + unsigned long ret; + if (!perf_parse_ulong(value, &ret)) + die_bad_config(name); + return ret; +} + +int perf_config_bool_or_int(const char *name, const char *value, int *is_bool) +{ + *is_bool = 1; + if (!value) + return 1; + if (!*value) + return 0; + if (!strcasecmp(value, "true") || !strcasecmp(value, "yes") || !strcasecmp(value, "on")) + return 1; + if (!strcasecmp(value, "false") || !strcasecmp(value, "no") || !strcasecmp(value, "off")) + return 0; + *is_bool = 0; + return perf_config_int(name, value); +} + +int perf_config_bool(const char *name, const char *value) +{ + int discard; + return !!perf_config_bool_or_int(name, value, &discard); +} + +int perf_config_string(const char **dest, const char *var, const char *value) +{ + if (!value) + return config_error_nonbool(var); + *dest = strdup(value); + return 0; +} + +static int perf_default_core_config(const char *var, const char *value) +{ + /* Add other config variables here and to Documentation/config.txt. */ + return 0; +} + +int perf_default_config(const char *var, const char *value, void *dummy) +{ + if (!prefixcmp(var, "core.")) + return perf_default_core_config(var, value); + + /* Add other config variables here and to Documentation/config.txt. */ + return 0; +} + +int perf_config_from_file(config_fn_t fn, const char *filename, void *data) +{ + int ret; + FILE *f = fopen(filename, "r"); + + ret = -1; + if (f) { + config_file = f; + config_file_name = filename; + config_linenr = 1; + config_file_eof = 0; + ret = perf_parse_file(fn, data); + fclose(f); + config_file_name = NULL; + } + return ret; +} + +const char *perf_etc_perfconfig(void) +{ + static const char *system_wide; + if (!system_wide) + system_wide = system_path(ETC_PERFCONFIG); + return system_wide; +} + +static int perf_env_bool(const char *k, int def) +{ + const char *v = getenv(k); + return v ? perf_config_bool(k, v) : def; +} + +int perf_config_system(void) +{ + return !perf_env_bool("PERF_CONFIG_NOSYSTEM", 0); +} + +int perf_config_global(void) +{ + return !perf_env_bool("PERF_CONFIG_NOGLOBAL", 0); +} + +int perf_config(config_fn_t fn, void *data) +{ + int ret = 0, found = 0; + char *repo_config = NULL; + const char *home = NULL; + + /* Setting $PERF_CONFIG makes perf read _only_ the given config file. */ + if (config_exclusive_filename) + return perf_config_from_file(fn, config_exclusive_filename, data); + if (perf_config_system() && !access(perf_etc_perfconfig(), R_OK)) { + ret += perf_config_from_file(fn, perf_etc_perfconfig(), + data); + found += 1; + } + + home = getenv("HOME"); + if (perf_config_global() && home) { + char *user_config = strdup(mkpath("%s/.perfconfig", home)); + if (!access(user_config, R_OK)) { + ret += perf_config_from_file(fn, user_config, data); + found += 1; + } + free(user_config); + } + + repo_config = perf_pathdup("config"); + if (!access(repo_config, R_OK)) { + ret += perf_config_from_file(fn, repo_config, data); + found += 1; + } + free(repo_config); + if (found == 0) + return -1; + return ret; +} + +/* + * Find all the stuff for perf_config_set() below. + */ + +#define MAX_MATCHES 512 + +static struct { + int baselen; + char* key; + int do_not_match; + regex_t* value_regex; + int multi_replace; + size_t offset[MAX_MATCHES]; + enum { START, SECTION_SEEN, SECTION_END_SEEN, KEY_SEEN } state; + int seen; +} store; + +static int matches(const char* key, const char* value) +{ + return !strcmp(key, store.key) && + (store.value_regex == NULL || + (store.do_not_match ^ + !regexec(store.value_regex, value, 0, NULL, 0))); +} + +static int store_aux(const char* key, const char* value, void *cb) +{ + const char *ep; + size_t section_len; + + switch (store.state) { + case KEY_SEEN: + if (matches(key, value)) { + if (store.seen == 1 && store.multi_replace == 0) { + warning("%s has multiple values", key); + } else if (store.seen >= MAX_MATCHES) { + error("too many matches for %s", key); + return 1; + } + + store.offset[store.seen] = ftell(config_file); + store.seen++; + } + break; + case SECTION_SEEN: + /* + * What we are looking for is in store.key (both + * section and var), and its section part is baselen + * long. We found key (again, both section and var). + * We would want to know if this key is in the same + * section as what we are looking for. We already + * know we are in the same section as what should + * hold store.key. + */ + ep = strrchr(key, '.'); + section_len = ep - key; + + if ((section_len != store.baselen) || + memcmp(key, store.key, section_len+1)) { + store.state = SECTION_END_SEEN; + break; + } + + /* + * Do not increment matches: this is no match, but we + * just made sure we are in the desired section. + */ + store.offset[store.seen] = ftell(config_file); + /* fallthru */ + case SECTION_END_SEEN: + case START: + if (matches(key, value)) { + store.offset[store.seen] = ftell(config_file); + store.state = KEY_SEEN; + store.seen++; + } else { + if (strrchr(key, '.') - key == store.baselen && + !strncmp(key, store.key, store.baselen)) { + store.state = SECTION_SEEN; + store.offset[store.seen] = ftell(config_file); + } + } + } + return 0; +} + +static int store_write_section(int fd, const char* key) +{ + const char *dot; + int i, success; + struct strbuf sb = STRBUF_INIT; + + dot = memchr(key, '.', store.baselen); + if (dot) { + strbuf_addf(&sb, "[%.*s \"", (int)(dot - key), key); + for (i = dot - key + 1; i < store.baselen; i++) { + if (key[i] == '"' || key[i] == '\\') + strbuf_addch(&sb, '\\'); + strbuf_addch(&sb, key[i]); + } + strbuf_addstr(&sb, "\"]\n"); + } else { + strbuf_addf(&sb, "[%.*s]\n", store.baselen, key); + } + + success = write_in_full(fd, sb.buf, sb.len) == sb.len; + strbuf_release(&sb); + + return success; +} + +static int store_write_pair(int fd, const char* key, const char* value) +{ + int i, success; + int length = strlen(key + store.baselen + 1); + const char *quote = ""; + struct strbuf sb = STRBUF_INIT; + + /* + * Check to see if the value needs to be surrounded with a dq pair. + * Note that problematic characters are always backslash-quoted; this + * check is about not losing leading or trailing SP and strings that + * follow beginning-of-comment characters (i.e. ';' and '#') by the + * configuration parser. + */ + if (value[0] == ' ') + quote = "\""; + for (i = 0; value[i]; i++) + if (value[i] == ';' || value[i] == '#') + quote = "\""; + if (i && value[i - 1] == ' ') + quote = "\""; + + strbuf_addf(&sb, "\t%.*s = %s", + length, key + store.baselen + 1, quote); + + for (i = 0; value[i]; i++) + switch (value[i]) { + case '\n': + strbuf_addstr(&sb, "\\n"); + break; + case '\t': + strbuf_addstr(&sb, "\\t"); + break; + case '"': + case '\\': + strbuf_addch(&sb, '\\'); + default: + strbuf_addch(&sb, value[i]); + break; + } + strbuf_addf(&sb, "%s\n", quote); + + success = write_in_full(fd, sb.buf, sb.len) == sb.len; + strbuf_release(&sb); + + return success; +} + +static ssize_t find_beginning_of_line(const char* contents, size_t size, + size_t offset_, int* found_bracket) +{ + size_t equal_offset = size, bracket_offset = size; + ssize_t offset; + +contline: + for (offset = offset_-2; offset > 0 + && contents[offset] != '\n'; offset--) + switch (contents[offset]) { + case '=': equal_offset = offset; break; + case ']': bracket_offset = offset; break; + } + if (offset > 0 && contents[offset-1] == '\\') { + offset_ = offset; + goto contline; + } + if (bracket_offset < equal_offset) { + *found_bracket = 1; + offset = bracket_offset+1; + } else + offset++; + + return offset; +} + +int perf_config_set(const char* key, const char* value) +{ + return perf_config_set_multivar(key, value, NULL, 0); +} + +/* + * If value==NULL, unset in (remove from) config, + * if value_regex!=NULL, disregard key/value pairs where value does not match. + * if multi_replace==0, nothing, or only one matching key/value is replaced, + * else all matching key/values (regardless how many) are removed, + * before the new pair is written. + * + * Returns 0 on success. + * + * This function does this: + * + * - it locks the config file by creating ".perf/config.lock" + * + * - it then parses the config using store_aux() as validator to find + * the position on the key/value pair to replace. If it is to be unset, + * it must be found exactly once. + * + * - the config file is mmap()ed and the part before the match (if any) is + * written to the lock file, then the changed part and the rest. + * + * - the config file is removed and the lock file rename()d to it. + * + */ +int perf_config_set_multivar(const char* key, const char* value, + const char* value_regex, int multi_replace) +{ + int i, dot; + int fd = -1, in_fd; + int ret = 0; + char* config_filename; + const char* last_dot = strrchr(key, '.'); + + if (config_exclusive_filename) + config_filename = strdup(config_exclusive_filename); + else + config_filename = perf_pathdup("config"); + + /* + * Since "key" actually contains the section name and the real + * key name separated by a dot, we have to know where the dot is. + */ + + if (last_dot == NULL) { + error("key does not contain a section: %s", key); + ret = 2; + goto out_free; + } + store.baselen = last_dot - key; + + store.multi_replace = multi_replace; + + /* + * Validate the key and while at it, lower case it for matching. + */ + store.key = malloc(strlen(key) + 1); + dot = 0; + for (i = 0; key[i]; i++) { + unsigned char c = key[i]; + if (c == '.') + dot = 1; + /* Leave the extended basename untouched.. */ + if (!dot || i > store.baselen) { + if (!iskeychar(c) || (i == store.baselen+1 && !isalpha(c))) { + error("invalid key: %s", key); + free(store.key); + ret = 1; + goto out_free; + } + c = tolower(c); + } else if (c == '\n') { + error("invalid key (newline): %s", key); + free(store.key); + ret = 1; + goto out_free; + } + store.key[i] = c; + } + store.key[i] = 0; + + /* + * If .perf/config does not exist yet, write a minimal version. + */ + in_fd = open(config_filename, O_RDONLY); + if ( in_fd < 0 ) { + free(store.key); + + if ( ENOENT != errno ) { + error("opening %s: %s", config_filename, + strerror(errno)); + ret = 3; /* same as "invalid config file" */ + goto out_free; + } + /* if nothing to unset, error out */ + if (value == NULL) { + ret = 5; + goto out_free; + } + + store.key = (char*)key; + if (!store_write_section(fd, key) || + !store_write_pair(fd, key, value)) + goto write_err_out; + } else { + struct stat st; + char* contents; + size_t contents_sz, copy_begin, copy_end; + int i, new_line = 0; + + if (value_regex == NULL) + store.value_regex = NULL; + else { + if (value_regex[0] == '!') { + store.do_not_match = 1; + value_regex++; + } else + store.do_not_match = 0; + + store.value_regex = (regex_t*)malloc(sizeof(regex_t)); + if (regcomp(store.value_regex, value_regex, + REG_EXTENDED)) { + error("invalid pattern: %s", value_regex); + free(store.value_regex); + ret = 6; + goto out_free; + } + } + + store.offset[0] = 0; + store.state = START; + store.seen = 0; + + /* + * After this, store.offset will contain the *end* offset + * of the last match, or remain at 0 if no match was found. + * As a side effect, we make sure to transform only a valid + * existing config file. + */ + if (perf_config_from_file(store_aux, config_filename, NULL)) { + error("invalid config file %s", config_filename); + free(store.key); + if (store.value_regex != NULL) { + regfree(store.value_regex); + free(store.value_regex); + } + ret = 3; + goto out_free; + } + + free(store.key); + if (store.value_regex != NULL) { + regfree(store.value_regex); + free(store.value_regex); + } + + /* if nothing to unset, or too many matches, error out */ + if ((store.seen == 0 && value == NULL) || + (store.seen > 1 && multi_replace == 0)) { + ret = 5; + goto out_free; + } + + fstat(in_fd, &st); + contents_sz = xsize_t(st.st_size); + contents = mmap(NULL, contents_sz, PROT_READ, + MAP_PRIVATE, in_fd, 0); + close(in_fd); + + if (store.seen == 0) + store.seen = 1; + + for (i = 0, copy_begin = 0; i < store.seen; i++) { + if (store.offset[i] == 0) { + store.offset[i] = copy_end = contents_sz; + } else if (store.state != KEY_SEEN) { + copy_end = store.offset[i]; + } else + copy_end = find_beginning_of_line( + contents, contents_sz, + store.offset[i]-2, &new_line); + + if (copy_end > 0 && contents[copy_end-1] != '\n') + new_line = 1; + + /* write the first part of the config */ + if (copy_end > copy_begin) { + if (write_in_full(fd, contents + copy_begin, + copy_end - copy_begin) < + copy_end - copy_begin) + goto write_err_out; + if (new_line && + write_in_full(fd, "\n", 1) != 1) + goto write_err_out; + } + copy_begin = store.offset[i]; + } + + /* write the pair (value == NULL means unset) */ + if (value != NULL) { + if (store.state == START) { + if (!store_write_section(fd, key)) + goto write_err_out; + } + if (!store_write_pair(fd, key, value)) + goto write_err_out; + } + + /* write the rest of the config */ + if (copy_begin < contents_sz) + if (write_in_full(fd, contents + copy_begin, + contents_sz - copy_begin) < + contents_sz - copy_begin) + goto write_err_out; + + munmap(contents, contents_sz); + } + + ret = 0; + +out_free: + free(config_filename); + return ret; + +write_err_out: + goto out_free; + +} + +/* + * Call this to report error for your variable that should not + * get a boolean value (i.e. "[my] var" means "true"). + */ +int config_error_nonbool(const char *var) +{ + return error("Missing value for '%s'", var); +} diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c new file mode 100644 index 0000000000000000000000000000000000000000..b90ec004f29c30c4b6a6ea5339599d7a8db0fb8c --- /dev/null +++ b/tools/perf/util/ctype.c @@ -0,0 +1,26 @@ +/* + * Sane locale-independent, ASCII ctype. + * + * No surprises, and works with signed and unsigned chars. + */ +#include "cache.h" + +enum { + S = GIT_SPACE, + A = GIT_ALPHA, + D = GIT_DIGIT, + G = GIT_GLOB_SPECIAL, /* *, ?, [, \\ */ + R = GIT_REGEX_SPECIAL, /* $, (, ), +, ., ^, {, | * */ +}; + +unsigned char sane_ctype[256] = { + 0, 0, 0, 0, 0, 0, 0, 0, 0, S, S, 0, 0, S, 0, 0, /* 0.. 15 */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 16.. 31 */ + S, 0, 0, 0, R, 0, 0, 0, R, R, G, R, 0, 0, R, 0, /* 32.. 47 */ + D, D, D, D, D, D, D, D, D, D, 0, 0, 0, 0, 0, G, /* 48.. 63 */ + 0, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A, /* 64.. 79 */ + A, A, A, A, A, A, A, A, A, A, A, G, G, 0, R, 0, /* 80.. 95 */ + 0, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A, /* 96..111 */ + A, A, A, A, A, A, A, A, A, A, A, R, R, 0, 0, 0, /* 112..127 */ + /* Nothing in the 128.. range */ +}; diff --git a/tools/perf/util/environment.c b/tools/perf/util/environment.c new file mode 100644 index 0000000000000000000000000000000000000000..275b0ee345f5eab4b1dcaebc18d5068698d9e437 --- /dev/null +++ b/tools/perf/util/environment.c @@ -0,0 +1,9 @@ +/* + * We put all the perf config variables in this same object + * file, so that programs can link against the config parser + * without having to link against all the rest of perf. + */ +#include "cache.h" + +const char *pager_program; +int pager_use_color = 1; diff --git a/tools/perf/util/exec_cmd.c b/tools/perf/util/exec_cmd.c new file mode 100644 index 0000000000000000000000000000000000000000..d39292263153021ac44a6f9b4e2779ce63478094 --- /dev/null +++ b/tools/perf/util/exec_cmd.c @@ -0,0 +1,165 @@ +#include "cache.h" +#include "exec_cmd.h" +#include "quote.h" +#define MAX_ARGS 32 + +extern char **environ; +static const char *argv_exec_path; +static const char *argv0_path; + +const char *system_path(const char *path) +{ +#ifdef RUNTIME_PREFIX + static const char *prefix; +#else + static const char *prefix = PREFIX; +#endif + struct strbuf d = STRBUF_INIT; + + if (is_absolute_path(path)) + return path; + +#ifdef RUNTIME_PREFIX + assert(argv0_path); + assert(is_absolute_path(argv0_path)); + + if (!prefix && + !(prefix = strip_path_suffix(argv0_path, PERF_EXEC_PATH)) && + !(prefix = strip_path_suffix(argv0_path, BINDIR)) && + !(prefix = strip_path_suffix(argv0_path, "perf"))) { + prefix = PREFIX; + fprintf(stderr, "RUNTIME_PREFIX requested, " + "but prefix computation failed. " + "Using static fallback '%s'.\n", prefix); + } +#endif + + strbuf_addf(&d, "%s/%s", prefix, path); + path = strbuf_detach(&d, NULL); + return path; +} + +const char *perf_extract_argv0_path(const char *argv0) +{ + const char *slash; + + if (!argv0 || !*argv0) + return NULL; + slash = argv0 + strlen(argv0); + + while (argv0 <= slash && !is_dir_sep(*slash)) + slash--; + + if (slash >= argv0) { + argv0_path = strndup(argv0, slash - argv0); + return slash + 1; + } + + return argv0; +} + +void perf_set_argv_exec_path(const char *exec_path) +{ + argv_exec_path = exec_path; + /* + * Propagate this setting to external programs. + */ + setenv(EXEC_PATH_ENVIRONMENT, exec_path, 1); +} + + +/* Returns the highest-priority, location to look for perf programs. */ +const char *perf_exec_path(void) +{ + const char *env; + + if (argv_exec_path) + return argv_exec_path; + + env = getenv(EXEC_PATH_ENVIRONMENT); + if (env && *env) { + return env; + } + + return system_path(PERF_EXEC_PATH); +} + +static void add_path(struct strbuf *out, const char *path) +{ + if (path && *path) { + if (is_absolute_path(path)) + strbuf_addstr(out, path); + else + strbuf_addstr(out, make_nonrelative_path(path)); + + strbuf_addch(out, PATH_SEP); + } +} + +void setup_path(void) +{ + const char *old_path = getenv("PATH"); + struct strbuf new_path = STRBUF_INIT; + + add_path(&new_path, perf_exec_path()); + add_path(&new_path, argv0_path); + + if (old_path) + strbuf_addstr(&new_path, old_path); + else + strbuf_addstr(&new_path, "/usr/local/bin:/usr/bin:/bin"); + + setenv("PATH", new_path.buf, 1); + + strbuf_release(&new_path); +} + +const char **prepare_perf_cmd(const char **argv) +{ + int argc; + const char **nargv; + + for (argc = 0; argv[argc]; argc++) + ; /* just counting */ + nargv = malloc(sizeof(*nargv) * (argc + 2)); + + nargv[0] = "perf"; + for (argc = 0; argv[argc]; argc++) + nargv[argc + 1] = argv[argc]; + nargv[argc + 1] = NULL; + return nargv; +} + +int execv_perf_cmd(const char **argv) { + const char **nargv = prepare_perf_cmd(argv); + + /* execvp() can only ever return if it fails */ + execvp("perf", (char **)nargv); + + free(nargv); + return -1; +} + + +int execl_perf_cmd(const char *cmd,...) +{ + int argc; + const char *argv[MAX_ARGS + 1]; + const char *arg; + va_list param; + + va_start(param, cmd); + argv[0] = cmd; + argc = 1; + while (argc < MAX_ARGS) { + arg = argv[argc++] = va_arg(param, char *); + if (!arg) + break; + } + va_end(param); + if (MAX_ARGS <= argc) + return error("too many args to run %s", cmd); + + argv[argc] = NULL; + return execv_perf_cmd(argv); +} diff --git a/tools/perf/util/exec_cmd.h b/tools/perf/util/exec_cmd.h new file mode 100644 index 0000000000000000000000000000000000000000..effe25eb15456dcad9bc6233eb19f38193af2623 --- /dev/null +++ b/tools/perf/util/exec_cmd.h @@ -0,0 +1,13 @@ +#ifndef PERF_EXEC_CMD_H +#define PERF_EXEC_CMD_H + +extern void perf_set_argv_exec_path(const char *exec_path); +extern const char *perf_extract_argv0_path(const char *path); +extern const char *perf_exec_path(void); +extern void setup_path(void); +extern const char **prepare_perf_cmd(const char **argv); +extern int execv_perf_cmd(const char **argv); /* NULL terminated */ +extern int execl_perf_cmd(const char *cmd, ...); +extern const char *system_path(const char *path); + +#endif /* PERF_EXEC_CMD_H */ diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh new file mode 100755 index 0000000000000000000000000000000000000000..f06f6fd148f8e63b810a7095e403e6630f1ca7f8 --- /dev/null +++ b/tools/perf/util/generate-cmdlist.sh @@ -0,0 +1,24 @@ +#!/bin/sh + +echo "/* Automatically generated by $0 */ +struct cmdname_help +{ + char name[16]; + char help[80]; +}; + +static struct cmdname_help common_cmds[] = {" + +sed -n -e 's/^perf-\([^ ]*\)[ ].* common.*/\1/p' command-list.txt | +sort | +while read cmd +do + sed -n ' + /^NAME/,/perf-'"$cmd"'/H + ${ + x + s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/ + p + }' "Documentation/perf-$cmd.txt" +done +echo "};" diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c new file mode 100644 index 0000000000000000000000000000000000000000..6653f7dd1d784f96fcd8161cafc7fb78895dc6e4 --- /dev/null +++ b/tools/perf/util/help.c @@ -0,0 +1,367 @@ +#include "cache.h" +#include "../builtin.h" +#include "exec_cmd.h" +#include "levenshtein.h" +#include "help.h" + +/* most GUI terminals set COLUMNS (although some don't export it) */ +static int term_columns(void) +{ + char *col_string = getenv("COLUMNS"); + int n_cols; + + if (col_string && (n_cols = atoi(col_string)) > 0) + return n_cols; + +#ifdef TIOCGWINSZ + { + struct winsize ws; + if (!ioctl(1, TIOCGWINSZ, &ws)) { + if (ws.ws_col) + return ws.ws_col; + } + } +#endif + + return 80; +} + +void add_cmdname(struct cmdnames *cmds, const char *name, int len) +{ + struct cmdname *ent = malloc(sizeof(*ent) + len + 1); + + ent->len = len; + memcpy(ent->name, name, len); + ent->name[len] = 0; + + ALLOC_GROW(cmds->names, cmds->cnt + 1, cmds->alloc); + cmds->names[cmds->cnt++] = ent; +} + +static void clean_cmdnames(struct cmdnames *cmds) +{ + int i; + for (i = 0; i < cmds->cnt; ++i) + free(cmds->names[i]); + free(cmds->names); + cmds->cnt = 0; + cmds->alloc = 0; +} + +static int cmdname_compare(const void *a_, const void *b_) +{ + struct cmdname *a = *(struct cmdname **)a_; + struct cmdname *b = *(struct cmdname **)b_; + return strcmp(a->name, b->name); +} + +static void uniq(struct cmdnames *cmds) +{ + int i, j; + + if (!cmds->cnt) + return; + + for (i = j = 1; i < cmds->cnt; i++) + if (strcmp(cmds->names[i]->name, cmds->names[i-1]->name)) + cmds->names[j++] = cmds->names[i]; + + cmds->cnt = j; +} + +void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes) +{ + int ci, cj, ei; + int cmp; + + ci = cj = ei = 0; + while (ci < cmds->cnt && ei < excludes->cnt) { + cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name); + if (cmp < 0) + cmds->names[cj++] = cmds->names[ci++]; + else if (cmp == 0) + ci++, ei++; + else if (cmp > 0) + ei++; + } + + while (ci < cmds->cnt) + cmds->names[cj++] = cmds->names[ci++]; + + cmds->cnt = cj; +} + +static void pretty_print_string_list(struct cmdnames *cmds, int longest) +{ + int cols = 1, rows; + int space = longest + 1; /* min 1 SP between words */ + int max_cols = term_columns() - 1; /* don't print *on* the edge */ + int i, j; + + if (space < max_cols) + cols = max_cols / space; + rows = (cmds->cnt + cols - 1) / cols; + + for (i = 0; i < rows; i++) { + printf(" "); + + for (j = 0; j < cols; j++) { + int n = j * rows + i; + int size = space; + if (n >= cmds->cnt) + break; + if (j == cols-1 || n + rows >= cmds->cnt) + size = 1; + printf("%-*s", size, cmds->names[n]->name); + } + putchar('\n'); + } +} + +static int is_executable(const char *name) +{ + struct stat st; + + if (stat(name, &st) || /* stat, not lstat */ + !S_ISREG(st.st_mode)) + return 0; + +#ifdef __MINGW32__ + /* cannot trust the executable bit, peek into the file instead */ + char buf[3] = { 0 }; + int n; + int fd = open(name, O_RDONLY); + st.st_mode &= ~S_IXUSR; + if (fd >= 0) { + n = read(fd, buf, 2); + if (n == 2) + /* DOS executables start with "MZ" */ + if (!strcmp(buf, "#!") || !strcmp(buf, "MZ")) + st.st_mode |= S_IXUSR; + close(fd); + } +#endif + return st.st_mode & S_IXUSR; +} + +static void list_commands_in_dir(struct cmdnames *cmds, + const char *path, + const char *prefix) +{ + int prefix_len; + DIR *dir = opendir(path); + struct dirent *de; + struct strbuf buf = STRBUF_INIT; + int len; + + if (!dir) + return; + if (!prefix) + prefix = "perf-"; + prefix_len = strlen(prefix); + + strbuf_addf(&buf, "%s/", path); + len = buf.len; + + while ((de = readdir(dir)) != NULL) { + int entlen; + + if (prefixcmp(de->d_name, prefix)) + continue; + + strbuf_setlen(&buf, len); + strbuf_addstr(&buf, de->d_name); + if (!is_executable(buf.buf)) + continue; + + entlen = strlen(de->d_name) - prefix_len; + if (has_extension(de->d_name, ".exe")) + entlen -= 4; + + add_cmdname(cmds, de->d_name + prefix_len, entlen); + } + closedir(dir); + strbuf_release(&buf); +} + +void load_command_list(const char *prefix, + struct cmdnames *main_cmds, + struct cmdnames *other_cmds) +{ + const char *env_path = getenv("PATH"); + const char *exec_path = perf_exec_path(); + + if (exec_path) { + list_commands_in_dir(main_cmds, exec_path, prefix); + qsort(main_cmds->names, main_cmds->cnt, + sizeof(*main_cmds->names), cmdname_compare); + uniq(main_cmds); + } + + if (env_path) { + char *paths, *path, *colon; + path = paths = strdup(env_path); + while (1) { + if ((colon = strchr(path, PATH_SEP))) + *colon = 0; + if (!exec_path || strcmp(path, exec_path)) + list_commands_in_dir(other_cmds, path, prefix); + + if (!colon) + break; + path = colon + 1; + } + free(paths); + + qsort(other_cmds->names, other_cmds->cnt, + sizeof(*other_cmds->names), cmdname_compare); + uniq(other_cmds); + } + exclude_cmds(other_cmds, main_cmds); +} + +void list_commands(const char *title, struct cmdnames *main_cmds, + struct cmdnames *other_cmds) +{ + int i, longest = 0; + + for (i = 0; i < main_cmds->cnt; i++) + if (longest < main_cmds->names[i]->len) + longest = main_cmds->names[i]->len; + for (i = 0; i < other_cmds->cnt; i++) + if (longest < other_cmds->names[i]->len) + longest = other_cmds->names[i]->len; + + if (main_cmds->cnt) { + const char *exec_path = perf_exec_path(); + printf("available %s in '%s'\n", title, exec_path); + printf("----------------"); + mput_char('-', strlen(title) + strlen(exec_path)); + putchar('\n'); + pretty_print_string_list(main_cmds, longest); + putchar('\n'); + } + + if (other_cmds->cnt) { + printf("%s available from elsewhere on your $PATH\n", title); + printf("---------------------------------------"); + mput_char('-', strlen(title)); + putchar('\n'); + pretty_print_string_list(other_cmds, longest); + putchar('\n'); + } +} + +int is_in_cmdlist(struct cmdnames *c, const char *s) +{ + int i; + for (i = 0; i < c->cnt; i++) + if (!strcmp(s, c->names[i]->name)) + return 1; + return 0; +} + +static int autocorrect; +static struct cmdnames aliases; + +static int perf_unknown_cmd_config(const char *var, const char *value, void *cb) +{ + if (!strcmp(var, "help.autocorrect")) + autocorrect = perf_config_int(var,value); + /* Also use aliases for command lookup */ + if (!prefixcmp(var, "alias.")) + add_cmdname(&aliases, var + 6, strlen(var + 6)); + + return perf_default_config(var, value, cb); +} + +static int levenshtein_compare(const void *p1, const void *p2) +{ + const struct cmdname *const *c1 = p1, *const *c2 = p2; + const char *s1 = (*c1)->name, *s2 = (*c2)->name; + int l1 = (*c1)->len; + int l2 = (*c2)->len; + return l1 != l2 ? l1 - l2 : strcmp(s1, s2); +} + +static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old) +{ + int i; + ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc); + + for (i = 0; i < old->cnt; i++) + cmds->names[cmds->cnt++] = old->names[i]; + free(old->names); + old->cnt = 0; + old->names = NULL; +} + +const char *help_unknown_cmd(const char *cmd) +{ + int i, n = 0, best_similarity = 0; + struct cmdnames main_cmds, other_cmds; + + memset(&main_cmds, 0, sizeof(main_cmds)); + memset(&other_cmds, 0, sizeof(main_cmds)); + memset(&aliases, 0, sizeof(aliases)); + + perf_config(perf_unknown_cmd_config, NULL); + + load_command_list("perf-", &main_cmds, &other_cmds); + + add_cmd_list(&main_cmds, &aliases); + add_cmd_list(&main_cmds, &other_cmds); + qsort(main_cmds.names, main_cmds.cnt, + sizeof(main_cmds.names), cmdname_compare); + uniq(&main_cmds); + + if (main_cmds.cnt) { + /* This reuses cmdname->len for similarity index */ + for (i = 0; i < main_cmds.cnt; ++i) + main_cmds.names[i]->len = + levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4); + + qsort(main_cmds.names, main_cmds.cnt, + sizeof(*main_cmds.names), levenshtein_compare); + + best_similarity = main_cmds.names[0]->len; + n = 1; + while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len) + ++n; + } + + if (autocorrect && n == 1) { + const char *assumed = main_cmds.names[0]->name; + + main_cmds.names[0] = NULL; + clean_cmdnames(&main_cmds); + fprintf(stderr, "WARNING: You called a Git program named '%s', " + "which does not exist.\n" + "Continuing under the assumption that you meant '%s'\n", + cmd, assumed); + if (autocorrect > 0) { + fprintf(stderr, "in %0.1f seconds automatically...\n", + (float)autocorrect/10.0); + poll(NULL, 0, autocorrect * 100); + } + return assumed; + } + + fprintf(stderr, "perf: '%s' is not a perf-command. See 'perf --help'.\n", cmd); + + if (main_cmds.cnt && best_similarity < 6) { + fprintf(stderr, "\nDid you mean %s?\n", + n < 2 ? "this": "one of these"); + + for (i = 0; i < n; i++) + fprintf(stderr, "\t%s\n", main_cmds.names[i]->name); + } + + exit(1); +} + +int cmd_version(int argc, const char **argv, const char *prefix) +{ + printf("perf version %s\n", perf_version_string); + return 0; +} diff --git a/tools/perf/util/help.h b/tools/perf/util/help.h new file mode 100644 index 0000000000000000000000000000000000000000..56bc15406ffc55115fa1c827e0d1d5a7e74c516d --- /dev/null +++ b/tools/perf/util/help.h @@ -0,0 +1,29 @@ +#ifndef HELP_H +#define HELP_H + +struct cmdnames { + int alloc; + int cnt; + struct cmdname { + size_t len; /* also used for similarity index in help.c */ + char name[FLEX_ARRAY]; + } **names; +}; + +static inline void mput_char(char c, unsigned int num) +{ + while(num--) + putchar(c); +} + +void load_command_list(const char *prefix, + struct cmdnames *main_cmds, + struct cmdnames *other_cmds); +void add_cmdname(struct cmdnames *cmds, const char *name, int len); +/* Here we require that excludes is a sorted list. */ +void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes); +int is_in_cmdlist(struct cmdnames *c, const char *s); +void list_commands(const char *title, struct cmdnames *main_cmds, + struct cmdnames *other_cmds); + +#endif /* HELP_H */ diff --git a/tools/perf/util/levenshtein.c b/tools/perf/util/levenshtein.c new file mode 100644 index 0000000000000000000000000000000000000000..e521d1516df6eac70c6c2b3d9f925dd9708f4907 --- /dev/null +++ b/tools/perf/util/levenshtein.c @@ -0,0 +1,84 @@ +#include "cache.h" +#include "levenshtein.h" + +/* + * This function implements the Damerau-Levenshtein algorithm to + * calculate a distance between strings. + * + * Basically, it says how many letters need to be swapped, substituted, + * deleted from, or added to string1, at least, to get string2. + * + * The idea is to build a distance matrix for the substrings of both + * strings. To avoid a large space complexity, only the last three rows + * are kept in memory (if swaps had the same or higher cost as one deletion + * plus one insertion, only two rows would be needed). + * + * At any stage, "i + 1" denotes the length of the current substring of + * string1 that the distance is calculated for. + * + * row2 holds the current row, row1 the previous row (i.e. for the substring + * of string1 of length "i"), and row0 the row before that. + * + * In other words, at the start of the big loop, row2[j + 1] contains the + * Damerau-Levenshtein distance between the substring of string1 of length + * "i" and the substring of string2 of length "j + 1". + * + * All the big loop does is determine the partial minimum-cost paths. + * + * It does so by calculating the costs of the path ending in characters + * i (in string1) and j (in string2), respectively, given that the last + * operation is a substition, a swap, a deletion, or an insertion. + * + * This implementation allows the costs to be weighted: + * + * - w (as in "sWap") + * - s (as in "Substitution") + * - a (for insertion, AKA "Add") + * - d (as in "Deletion") + * + * Note that this algorithm calculates a distance _iff_ d == a. + */ +int levenshtein(const char *string1, const char *string2, + int w, int s, int a, int d) +{ + int len1 = strlen(string1), len2 = strlen(string2); + int *row0 = malloc(sizeof(int) * (len2 + 1)); + int *row1 = malloc(sizeof(int) * (len2 + 1)); + int *row2 = malloc(sizeof(int) * (len2 + 1)); + int i, j; + + for (j = 0; j <= len2; j++) + row1[j] = j * a; + for (i = 0; i < len1; i++) { + int *dummy; + + row2[0] = (i + 1) * d; + for (j = 0; j < len2; j++) { + /* substitution */ + row2[j + 1] = row1[j] + s * (string1[i] != string2[j]); + /* swap */ + if (i > 0 && j > 0 && string1[i - 1] == string2[j] && + string1[i] == string2[j - 1] && + row2[j + 1] > row0[j - 1] + w) + row2[j + 1] = row0[j - 1] + w; + /* deletion */ + if (row2[j + 1] > row1[j + 1] + d) + row2[j + 1] = row1[j + 1] + d; + /* insertion */ + if (row2[j + 1] > row2[j] + a) + row2[j + 1] = row2[j] + a; + } + + dummy = row0; + row0 = row1; + row1 = row2; + row2 = dummy; + } + + i = row1[len2]; + free(row0); + free(row1); + free(row2); + + return i; +} diff --git a/tools/perf/util/levenshtein.h b/tools/perf/util/levenshtein.h new file mode 100644 index 0000000000000000000000000000000000000000..0173abeef52c8dc3930a5c36420ff073ba8ddc87 --- /dev/null +++ b/tools/perf/util/levenshtein.h @@ -0,0 +1,8 @@ +#ifndef LEVENSHTEIN_H +#define LEVENSHTEIN_H + +int levenshtein(const char *string1, const char *string2, + int swap_penalty, int substition_penalty, + int insertion_penalty, int deletion_penalty); + +#endif diff --git a/tools/perf/util/list.h b/tools/perf/util/list.h new file mode 100644 index 0000000000000000000000000000000000000000..e2548e8072cfb4f8bc57cdd643a12d7dca1639fe --- /dev/null +++ b/tools/perf/util/list.h @@ -0,0 +1,603 @@ +#ifndef _LINUX_LIST_H +#define _LINUX_LIST_H +/* + Copyright (C) Cast of dozens, comes from the Linux kernel + + This program is free software; you can redistribute it and/or modify it + under the terms of version 2 of the GNU General Public License as + published by the Free Software Foundation. +*/ + +#include + +/* + * These are non-NULL pointers that will result in page faults + * under normal circumstances, used to verify that nobody uses + * non-initialized list entries. + */ +#define LIST_POISON1 ((void *)0x00100100) +#define LIST_POISON2 ((void *)0x00200200) + +/** + * container_of - cast a member of a structure out to the containing structure + * @ptr: the pointer to the member. + * @type: the type of the container struct this is embedded in. + * @member: the name of the member within the struct. + * + */ +#define container_of(ptr, type, member) ({ \ + const typeof( ((type *)0)->member ) *__mptr = (ptr); \ + (type *)( (char *)__mptr - offsetof(type,member) );}) + +/* + * Simple doubly linked list implementation. + * + * Some of the internal functions ("__xxx") are useful when + * manipulating whole lists rather than single entries, as + * sometimes we already know the next/prev entries and we can + * generate better code by using them directly rather than + * using the generic single-entry routines. + */ + +struct list_head { + struct list_head *next, *prev; +}; + +#define LIST_HEAD_INIT(name) { &(name), &(name) } + +#define LIST_HEAD(name) \ + struct list_head name = LIST_HEAD_INIT(name) + +static inline void INIT_LIST_HEAD(struct list_head *list) +{ + list->next = list; + list->prev = list; +} + +/* + * Insert a new entry between two known consecutive entries. + * + * This is only for internal list manipulation where we know + * the prev/next entries already! + */ +static inline void __list_add(struct list_head *new, + struct list_head *prev, + struct list_head *next) +{ + next->prev = new; + new->next = next; + new->prev = prev; + prev->next = new; +} + +/** + * list_add - add a new entry + * @new: new entry to be added + * @head: list head to add it after + * + * Insert a new entry after the specified head. + * This is good for implementing stacks. + */ +static inline void list_add(struct list_head *new, struct list_head *head) +{ + __list_add(new, head, head->next); +} + +/** + * list_add_tail - add a new entry + * @new: new entry to be added + * @head: list head to add it before + * + * Insert a new entry before the specified head. + * This is useful for implementing queues. + */ +static inline void list_add_tail(struct list_head *new, struct list_head *head) +{ + __list_add(new, head->prev, head); +} + +/* + * Delete a list entry by making the prev/next entries + * point to each other. + * + * This is only for internal list manipulation where we know + * the prev/next entries already! + */ +static inline void __list_del(struct list_head * prev, struct list_head * next) +{ + next->prev = prev; + prev->next = next; +} + +/** + * list_del - deletes entry from list. + * @entry: the element to delete from the list. + * Note: list_empty on entry does not return true after this, the entry is + * in an undefined state. + */ +static inline void list_del(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); + entry->next = LIST_POISON1; + entry->prev = LIST_POISON2; +} + +/** + * list_del_range - deletes range of entries from list. + * @beging: first element in the range to delete from the list. + * @beging: first element in the range to delete from the list. + * Note: list_empty on the range of entries does not return true after this, + * the entries is in an undefined state. + */ +static inline void list_del_range(struct list_head *begin, + struct list_head *end) +{ + begin->prev->next = end->next; + end->next->prev = begin->prev; +} + +/** + * list_replace - replace old entry by new one + * @old : the element to be replaced + * @new : the new element to insert + * Note: if 'old' was empty, it will be overwritten. + */ +static inline void list_replace(struct list_head *old, + struct list_head *new) +{ + new->next = old->next; + new->next->prev = new; + new->prev = old->prev; + new->prev->next = new; +} + +static inline void list_replace_init(struct list_head *old, + struct list_head *new) +{ + list_replace(old, new); + INIT_LIST_HEAD(old); +} + +/** + * list_del_init - deletes entry from list and reinitialize it. + * @entry: the element to delete from the list. + */ +static inline void list_del_init(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); + INIT_LIST_HEAD(entry); +} + +/** + * list_move - delete from one list and add as another's head + * @list: the entry to move + * @head: the head that will precede our entry + */ +static inline void list_move(struct list_head *list, struct list_head *head) +{ + __list_del(list->prev, list->next); + list_add(list, head); +} + +/** + * list_move_tail - delete from one list and add as another's tail + * @list: the entry to move + * @head: the head that will follow our entry + */ +static inline void list_move_tail(struct list_head *list, + struct list_head *head) +{ + __list_del(list->prev, list->next); + list_add_tail(list, head); +} + +/** + * list_is_last - tests whether @list is the last entry in list @head + * @list: the entry to test + * @head: the head of the list + */ +static inline int list_is_last(const struct list_head *list, + const struct list_head *head) +{ + return list->next == head; +} + +/** + * list_empty - tests whether a list is empty + * @head: the list to test. + */ +static inline int list_empty(const struct list_head *head) +{ + return head->next == head; +} + +/** + * list_empty_careful - tests whether a list is empty and not being modified + * @head: the list to test + * + * Description: + * tests whether a list is empty _and_ checks that no other CPU might be + * in the process of modifying either member (next or prev) + * + * NOTE: using list_empty_careful() without synchronization + * can only be safe if the only activity that can happen + * to the list entry is list_del_init(). Eg. it cannot be used + * if another CPU could re-list_add() it. + */ +static inline int list_empty_careful(const struct list_head *head) +{ + struct list_head *next = head->next; + return (next == head) && (next == head->prev); +} + +static inline void __list_splice(struct list_head *list, + struct list_head *head) +{ + struct list_head *first = list->next; + struct list_head *last = list->prev; + struct list_head *at = head->next; + + first->prev = head; + head->next = first; + + last->next = at; + at->prev = last; +} + +/** + * list_splice - join two lists + * @list: the new list to add. + * @head: the place to add it in the first list. + */ +static inline void list_splice(struct list_head *list, struct list_head *head) +{ + if (!list_empty(list)) + __list_splice(list, head); +} + +/** + * list_splice_init - join two lists and reinitialise the emptied list. + * @list: the new list to add. + * @head: the place to add it in the first list. + * + * The list at @list is reinitialised + */ +static inline void list_splice_init(struct list_head *list, + struct list_head *head) +{ + if (!list_empty(list)) { + __list_splice(list, head); + INIT_LIST_HEAD(list); + } +} + +/** + * list_entry - get the struct for this entry + * @ptr: the &struct list_head pointer. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_struct within the struct. + */ +#define list_entry(ptr, type, member) \ + container_of(ptr, type, member) + +/** + * list_first_entry - get the first element from a list + * @ptr: the list head to take the element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_struct within the struct. + * + * Note, that list is expected to be not empty. + */ +#define list_first_entry(ptr, type, member) \ + list_entry((ptr)->next, type, member) + +/** + * list_for_each - iterate over a list + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + */ +#define list_for_each(pos, head) \ + for (pos = (head)->next; pos != (head); \ + pos = pos->next) + +/** + * __list_for_each - iterate over a list + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + * + * This variant differs from list_for_each() in that it's the + * simplest possible list iteration code, no prefetching is done. + * Use this for code that knows the list to be very short (empty + * or 1 entry) most of the time. + */ +#define __list_for_each(pos, head) \ + for (pos = (head)->next; pos != (head); pos = pos->next) + +/** + * list_for_each_prev - iterate over a list backwards + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + */ +#define list_for_each_prev(pos, head) \ + for (pos = (head)->prev; pos != (head); \ + pos = pos->prev) + +/** + * list_for_each_safe - iterate over a list safe against removal of list entry + * @pos: the &struct list_head to use as a loop cursor. + * @n: another &struct list_head to use as temporary storage + * @head: the head for your list. + */ +#define list_for_each_safe(pos, n, head) \ + for (pos = (head)->next, n = pos->next; pos != (head); \ + pos = n, n = pos->next) + +/** + * list_for_each_entry - iterate over list of given type + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + */ +#define list_for_each_entry(pos, head, member) \ + for (pos = list_entry((head)->next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = list_entry(pos->member.next, typeof(*pos), member)) + +/** + * list_for_each_entry_reverse - iterate backwards over list of given type. + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + */ +#define list_for_each_entry_reverse(pos, head, member) \ + for (pos = list_entry((head)->prev, typeof(*pos), member); \ + &pos->member != (head); \ + pos = list_entry(pos->member.prev, typeof(*pos), member)) + +/** + * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue + * @pos: the type * to use as a start point + * @head: the head of the list + * @member: the name of the list_struct within the struct. + * + * Prepares a pos entry for use as a start point in list_for_each_entry_continue. + */ +#define list_prepare_entry(pos, head, member) \ + ((pos) ? : list_entry(head, typeof(*pos), member)) + +/** + * list_for_each_entry_continue - continue iteration over list of given type + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * Continue to iterate over list of given type, continuing after + * the current position. + */ +#define list_for_each_entry_continue(pos, head, member) \ + for (pos = list_entry(pos->member.next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = list_entry(pos->member.next, typeof(*pos), member)) + +/** + * list_for_each_entry_from - iterate over list of given type from the current point + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * Iterate over list of given type, continuing from current position. + */ +#define list_for_each_entry_from(pos, head, member) \ + for (; &pos->member != (head); \ + pos = list_entry(pos->member.next, typeof(*pos), member)) + +/** + * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + */ +#define list_for_each_entry_safe(pos, n, head, member) \ + for (pos = list_entry((head)->next, typeof(*pos), member), \ + n = list_entry(pos->member.next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = n, n = list_entry(n->member.next, typeof(*n), member)) + +/** + * list_for_each_entry_safe_continue + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * Iterate over list of given type, continuing after current point, + * safe against removal of list entry. + */ +#define list_for_each_entry_safe_continue(pos, n, head, member) \ + for (pos = list_entry(pos->member.next, typeof(*pos), member), \ + n = list_entry(pos->member.next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = n, n = list_entry(n->member.next, typeof(*n), member)) + +/** + * list_for_each_entry_safe_from + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * Iterate over list of given type from current point, safe against + * removal of list entry. + */ +#define list_for_each_entry_safe_from(pos, n, head, member) \ + for (n = list_entry(pos->member.next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = n, n = list_entry(n->member.next, typeof(*n), member)) + +/** + * list_for_each_entry_safe_reverse + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * Iterate backwards over list of given type, safe against removal + * of list entry. + */ +#define list_for_each_entry_safe_reverse(pos, n, head, member) \ + for (pos = list_entry((head)->prev, typeof(*pos), member), \ + n = list_entry(pos->member.prev, typeof(*pos), member); \ + &pos->member != (head); \ + pos = n, n = list_entry(n->member.prev, typeof(*n), member)) + +/* + * Double linked lists with a single pointer list head. + * Mostly useful for hash tables where the two pointer list head is + * too wasteful. + * You lose the ability to access the tail in O(1). + */ + +struct hlist_head { + struct hlist_node *first; +}; + +struct hlist_node { + struct hlist_node *next, **pprev; +}; + +#define HLIST_HEAD_INIT { .first = NULL } +#define HLIST_HEAD(name) struct hlist_head name = { .first = NULL } +#define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL) +static inline void INIT_HLIST_NODE(struct hlist_node *h) +{ + h->next = NULL; + h->pprev = NULL; +} + +static inline int hlist_unhashed(const struct hlist_node *h) +{ + return !h->pprev; +} + +static inline int hlist_empty(const struct hlist_head *h) +{ + return !h->first; +} + +static inline void __hlist_del(struct hlist_node *n) +{ + struct hlist_node *next = n->next; + struct hlist_node **pprev = n->pprev; + *pprev = next; + if (next) + next->pprev = pprev; +} + +static inline void hlist_del(struct hlist_node *n) +{ + __hlist_del(n); + n->next = LIST_POISON1; + n->pprev = LIST_POISON2; +} + +static inline void hlist_del_init(struct hlist_node *n) +{ + if (!hlist_unhashed(n)) { + __hlist_del(n); + INIT_HLIST_NODE(n); + } +} + +static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) +{ + struct hlist_node *first = h->first; + n->next = first; + if (first) + first->pprev = &n->next; + h->first = n; + n->pprev = &h->first; +} + +/* next must be != NULL */ +static inline void hlist_add_before(struct hlist_node *n, + struct hlist_node *next) +{ + n->pprev = next->pprev; + n->next = next; + next->pprev = &n->next; + *(n->pprev) = n; +} + +static inline void hlist_add_after(struct hlist_node *n, + struct hlist_node *next) +{ + next->next = n->next; + n->next = next; + next->pprev = &n->next; + + if(next->next) + next->next->pprev = &next->next; +} + +#define hlist_entry(ptr, type, member) container_of(ptr,type,member) + +#define hlist_for_each(pos, head) \ + for (pos = (head)->first; pos; \ + pos = pos->next) + +#define hlist_for_each_safe(pos, n, head) \ + for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ + pos = n) + +/** + * hlist_for_each_entry - iterate over list of given type + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_for_each_entry(tpos, pos, head, member) \ + for (pos = (head)->first; \ + pos && \ + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ + pos = pos->next) + +/** + * hlist_for_each_entry_continue - iterate over a hlist continuing after current point + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_for_each_entry_continue(tpos, pos, member) \ + for (pos = (pos)->next; \ + pos && \ + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ + pos = pos->next) + +/** + * hlist_for_each_entry_from - iterate over a hlist continuing from current point + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_for_each_entry_from(tpos, pos, member) \ + for (; pos && \ + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ + pos = pos->next) + +/** + * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @n: another &struct hlist_node to use as temporary storage + * @head: the head for your list. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_for_each_entry_safe(tpos, pos, n, head, member) \ + for (pos = (head)->first; \ + pos && ({ n = pos->next; 1; }) && \ + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ + pos = n) + +#endif diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c new file mode 100644 index 0000000000000000000000000000000000000000..a28bccae5458b3015fdbcfe0e458746d5b2db23b --- /dev/null +++ b/tools/perf/util/pager.c @@ -0,0 +1,99 @@ +#include "cache.h" +#include "run-command.h" +#include "sigchain.h" + +/* + * This is split up from the rest of git so that we can do + * something different on Windows. + */ + +static int spawned_pager; + +#ifndef __MINGW32__ +static void pager_preexec(void) +{ + /* + * Work around bug in "less" by not starting it until we + * have real input + */ + fd_set in; + + FD_ZERO(&in); + FD_SET(0, &in); + select(1, &in, NULL, &in, NULL); + + setenv("LESS", "FRSX", 0); +} +#endif + +static const char *pager_argv[] = { "sh", "-c", NULL, NULL }; +static struct child_process pager_process; + +static void wait_for_pager(void) +{ + fflush(stdout); + fflush(stderr); + /* signal EOF to pager */ + close(1); + close(2); + finish_command(&pager_process); +} + +static void wait_for_pager_signal(int signo) +{ + wait_for_pager(); + sigchain_pop(signo); + raise(signo); +} + +void setup_pager(void) +{ + const char *pager = getenv("PERF_PAGER"); + + if (!isatty(1)) + return; + if (!pager) { + if (!pager_program) + perf_config(perf_default_config, NULL); + pager = pager_program; + } + if (!pager) + pager = getenv("PAGER"); + if (!pager) + pager = "less"; + else if (!*pager || !strcmp(pager, "cat")) + return; + + spawned_pager = 1; /* means we are emitting to terminal */ + + /* spawn the pager */ + pager_argv[2] = pager; + pager_process.argv = pager_argv; + pager_process.in = -1; +#ifndef __MINGW32__ + pager_process.preexec_cb = pager_preexec; +#endif + if (start_command(&pager_process)) + return; + + /* original process continues, but writes to the pipe */ + dup2(pager_process.in, 1); + if (isatty(2)) + dup2(pager_process.in, 2); + close(pager_process.in); + + /* this makes sure that the parent terminates after the pager */ + sigchain_push_common(wait_for_pager_signal); + atexit(wait_for_pager); +} + +int pager_in_use(void) +{ + const char *env; + + if (spawned_pager) + return 1; + + env = getenv("PERF_PAGER_IN_USE"); + return env ? perf_config_bool("PERF_PAGER_IN_USE", env) : 0; +} diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c new file mode 100644 index 0000000000000000000000000000000000000000..9d5f1ca50e6fe4fc8466f3d97f8051a1e39253f2 --- /dev/null +++ b/tools/perf/util/parse-events.c @@ -0,0 +1,316 @@ + +#include "../perf.h" +#include "util.h" +#include "parse-options.h" +#include "parse-events.h" +#include "exec_cmd.h" +#include "string.h" + +extern char *strcasestr(const char *haystack, const char *needle); + +int nr_counters; + +struct perf_counter_attr attrs[MAX_COUNTERS]; + +struct event_symbol { + __u8 type; + __u64 config; + char *symbol; +}; + +#define C(x, y) .type = PERF_TYPE_##x, .config = PERF_COUNT_##y +#define CR(x, y) .type = PERF_TYPE_##x, .config = y + +static struct event_symbol event_symbols[] = { + { C(HARDWARE, HW_CPU_CYCLES), "cpu-cycles", }, + { C(HARDWARE, HW_CPU_CYCLES), "cycles", }, + { C(HARDWARE, HW_INSTRUCTIONS), "instructions", }, + { C(HARDWARE, HW_CACHE_REFERENCES), "cache-references", }, + { C(HARDWARE, HW_CACHE_MISSES), "cache-misses", }, + { C(HARDWARE, HW_BRANCH_INSTRUCTIONS),"branch-instructions", }, + { C(HARDWARE, HW_BRANCH_INSTRUCTIONS),"branches", }, + { C(HARDWARE, HW_BRANCH_MISSES), "branch-misses", }, + { C(HARDWARE, HW_BUS_CYCLES), "bus-cycles", }, + + { C(SOFTWARE, SW_CPU_CLOCK), "cpu-clock", }, + { C(SOFTWARE, SW_TASK_CLOCK), "task-clock", }, + { C(SOFTWARE, SW_PAGE_FAULTS), "page-faults", }, + { C(SOFTWARE, SW_PAGE_FAULTS), "faults", }, + { C(SOFTWARE, SW_PAGE_FAULTS_MIN), "minor-faults", }, + { C(SOFTWARE, SW_PAGE_FAULTS_MAJ), "major-faults", }, + { C(SOFTWARE, SW_CONTEXT_SWITCHES), "context-switches", }, + { C(SOFTWARE, SW_CONTEXT_SWITCHES), "cs", }, + { C(SOFTWARE, SW_CPU_MIGRATIONS), "cpu-migrations", }, + { C(SOFTWARE, SW_CPU_MIGRATIONS), "migrations", }, +}; + +#define __PERF_COUNTER_FIELD(config, name) \ + ((config & PERF_COUNTER_##name##_MASK) >> PERF_COUNTER_##name##_SHIFT) + +#define PERF_COUNTER_RAW(config) __PERF_COUNTER_FIELD(config, RAW) +#define PERF_COUNTER_CONFIG(config) __PERF_COUNTER_FIELD(config, CONFIG) +#define PERF_COUNTER_TYPE(config) __PERF_COUNTER_FIELD(config, TYPE) +#define PERF_COUNTER_ID(config) __PERF_COUNTER_FIELD(config, EVENT) + +static char *hw_event_names[] = { + "cycles", + "instructions", + "cache-references", + "cache-misses", + "branches", + "branch-misses", + "bus-cycles", +}; + +static char *sw_event_names[] = { + "cpu-clock-ticks", + "task-clock-ticks", + "page-faults", + "context-switches", + "CPU-migrations", + "minor-faults", + "major-faults", +}; + +#define MAX_ALIASES 8 + +static char *hw_cache [][MAX_ALIASES] = { + { "L1-data" , "l1-d", "l1d", "l1" }, + { "L1-instruction" , "l1-i", "l1i" }, + { "L2" , "l2" }, + { "Data-TLB" , "dtlb", "d-tlb" }, + { "Instruction-TLB" , "itlb", "i-tlb" }, + { "Branch" , "bpu" , "btb", "bpc" }, +}; + +static char *hw_cache_op [][MAX_ALIASES] = { + { "Load" , "read" }, + { "Store" , "write" }, + { "Prefetch" , "speculative-read", "speculative-load" }, +}; + +static char *hw_cache_result [][MAX_ALIASES] = { + { "Reference" , "ops", "access" }, + { "Miss" }, +}; + +char *event_name(int counter) +{ + __u64 config = attrs[counter].config; + int type = attrs[counter].type; + static char buf[32]; + + if (attrs[counter].type == PERF_TYPE_RAW) { + sprintf(buf, "raw 0x%llx", config); + return buf; + } + + switch (type) { + case PERF_TYPE_HARDWARE: + if (config < PERF_COUNT_HW_MAX) + return hw_event_names[config]; + return "unknown-hardware"; + + case PERF_TYPE_HW_CACHE: { + __u8 cache_type, cache_op, cache_result; + static char name[100]; + + cache_type = (config >> 0) & 0xff; + if (cache_type > PERF_COUNT_HW_CACHE_MAX) + return "unknown-ext-hardware-cache-type"; + + cache_op = (config >> 8) & 0xff; + if (cache_op > PERF_COUNT_HW_CACHE_OP_MAX) + return "unknown-ext-hardware-cache-op"; + + cache_result = (config >> 16) & 0xff; + if (cache_result > PERF_COUNT_HW_CACHE_RESULT_MAX) + return "unknown-ext-hardware-cache-result"; + + sprintf(name, "%s-Cache-%s-%ses", + hw_cache[cache_type][0], + hw_cache_op[cache_op][0], + hw_cache_result[cache_result][0]); + + return name; + } + + case PERF_TYPE_SOFTWARE: + if (config < PERF_COUNT_SW_MAX) + return sw_event_names[config]; + return "unknown-software"; + + default: + break; + } + + return "unknown"; +} + +static int parse_aliases(const char *str, char *names[][MAX_ALIASES], int size) +{ + int i, j; + + for (i = 0; i < size; i++) { + for (j = 0; j < MAX_ALIASES; j++) { + if (!names[i][j]) + break; + if (strcasestr(str, names[i][j])) + return i; + } + } + + return -1; +} + +static int parse_generic_hw_symbols(const char *str, struct perf_counter_attr *attr) +{ + int cache_type = -1, cache_op = 0, cache_result = 0; + + cache_type = parse_aliases(str, hw_cache, PERF_COUNT_HW_CACHE_MAX); + /* + * No fallback - if we cannot get a clear cache type + * then bail out: + */ + if (cache_type == -1) + return -EINVAL; + + cache_op = parse_aliases(str, hw_cache_op, PERF_COUNT_HW_CACHE_OP_MAX); + /* + * Fall back to reads: + */ + if (cache_op == -1) + cache_op = PERF_COUNT_HW_CACHE_OP_READ; + + cache_result = parse_aliases(str, hw_cache_result, + PERF_COUNT_HW_CACHE_RESULT_MAX); + /* + * Fall back to accesses: + */ + if (cache_result == -1) + cache_result = PERF_COUNT_HW_CACHE_RESULT_ACCESS; + + attr->config = cache_type | (cache_op << 8) | (cache_result << 16); + attr->type = PERF_TYPE_HW_CACHE; + + return 0; +} + +/* + * Each event can have multiple symbolic names. + * Symbolic names are (almost) exactly matched. + */ +static int parse_event_symbols(const char *str, struct perf_counter_attr *attr) +{ + __u64 config, id; + int type; + unsigned int i; + const char *sep, *pstr; + + if (str[0] == 'r' && hex2u64(str + 1, &config) > 0) { + attr->type = PERF_TYPE_RAW; + attr->config = config; + + return 0; + } + + pstr = str; + sep = strchr(pstr, ':'); + if (sep) { + type = atoi(pstr); + pstr = sep + 1; + id = atoi(pstr); + sep = strchr(pstr, ':'); + if (sep) { + pstr = sep + 1; + if (strchr(pstr, 'k')) + attr->exclude_user = 1; + if (strchr(pstr, 'u')) + attr->exclude_kernel = 1; + } + attr->type = type; + attr->config = id; + + return 0; + } + + for (i = 0; i < ARRAY_SIZE(event_symbols); i++) { + if (!strncmp(str, event_symbols[i].symbol, + strlen(event_symbols[i].symbol))) { + + attr->type = event_symbols[i].type; + attr->config = event_symbols[i].config; + + return 0; + } + } + + return parse_generic_hw_symbols(str, attr); +} + +int parse_events(const struct option *opt, const char *str, int unset) +{ + struct perf_counter_attr attr; + int ret; + + memset(&attr, 0, sizeof(attr)); +again: + if (nr_counters == MAX_COUNTERS) + return -1; + + ret = parse_event_symbols(str, &attr); + if (ret < 0) + return ret; + + attrs[nr_counters] = attr; + nr_counters++; + + str = strstr(str, ","); + if (str) { + str++; + goto again; + } + + return 0; +} + +static const char * const event_type_descriptors[] = { + "", + "Hardware event", + "Software event", + "Tracepoint event", + "Hardware cache event", +}; + +/* + * Print the help text for the event symbols: + */ +void print_events(void) +{ + struct event_symbol *syms = event_symbols; + unsigned int i, type, prev_type = -1; + + fprintf(stderr, "\n"); + fprintf(stderr, "List of pre-defined events (to be used in -e):\n"); + + for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) { + type = syms->type + 1; + if (type > ARRAY_SIZE(event_type_descriptors)) + type = 0; + + if (type != prev_type) + fprintf(stderr, "\n"); + + fprintf(stderr, " %-30s [%s]\n", syms->symbol, + event_type_descriptors[type]); + + prev_type = type; + } + + fprintf(stderr, "\n"); + fprintf(stderr, " %-30s [raw hardware event descriptor]\n", + "rNNN"); + fprintf(stderr, "\n"); + + exit(129); +} diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h new file mode 100644 index 0000000000000000000000000000000000000000..e3d552908e60015517316d2d91cba6324c8fbc2f --- /dev/null +++ b/tools/perf/util/parse-events.h @@ -0,0 +1,17 @@ + +/* + * Parse symbolic events/counts passed in as options: + */ + +extern int nr_counters; + +extern struct perf_counter_attr attrs[MAX_COUNTERS]; + +extern char *event_name(int ctr); + +extern int parse_events(const struct option *opt, const char *str, int unset); + +#define EVENTS_HELP_MAX (128*1024) + +extern void print_events(void); + diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c new file mode 100644 index 0000000000000000000000000000000000000000..b3affb1658d2a1646aea5680a941c9701df27e1b --- /dev/null +++ b/tools/perf/util/parse-options.c @@ -0,0 +1,508 @@ +#include "util.h" +#include "parse-options.h" +#include "cache.h" + +#define OPT_SHORT 1 +#define OPT_UNSET 2 + +static int opterror(const struct option *opt, const char *reason, int flags) +{ + if (flags & OPT_SHORT) + return error("switch `%c' %s", opt->short_name, reason); + if (flags & OPT_UNSET) + return error("option `no-%s' %s", opt->long_name, reason); + return error("option `%s' %s", opt->long_name, reason); +} + +static int get_arg(struct parse_opt_ctx_t *p, const struct option *opt, + int flags, const char **arg) +{ + if (p->opt) { + *arg = p->opt; + p->opt = NULL; + } else if (p->argc == 1 && (opt->flags & PARSE_OPT_LASTARG_DEFAULT)) { + *arg = (const char *)opt->defval; + } else if (p->argc > 1) { + p->argc--; + *arg = *++p->argv; + } else + return opterror(opt, "requires a value", flags); + return 0; +} + +static int get_value(struct parse_opt_ctx_t *p, + const struct option *opt, int flags) +{ + const char *s, *arg = NULL; + const int unset = flags & OPT_UNSET; + + if (unset && p->opt) + return opterror(opt, "takes no value", flags); + if (unset && (opt->flags & PARSE_OPT_NONEG)) + return opterror(opt, "isn't available", flags); + + if (!(flags & OPT_SHORT) && p->opt) { + switch (opt->type) { + case OPTION_CALLBACK: + if (!(opt->flags & PARSE_OPT_NOARG)) + break; + /* FALLTHROUGH */ + case OPTION_BOOLEAN: + case OPTION_BIT: + case OPTION_SET_INT: + case OPTION_SET_PTR: + return opterror(opt, "takes no value", flags); + default: + break; + } + } + + switch (opt->type) { + case OPTION_BIT: + if (unset) + *(int *)opt->value &= ~opt->defval; + else + *(int *)opt->value |= opt->defval; + return 0; + + case OPTION_BOOLEAN: + *(int *)opt->value = unset ? 0 : *(int *)opt->value + 1; + return 0; + + case OPTION_SET_INT: + *(int *)opt->value = unset ? 0 : opt->defval; + return 0; + + case OPTION_SET_PTR: + *(void **)opt->value = unset ? NULL : (void *)opt->defval; + return 0; + + case OPTION_STRING: + if (unset) + *(const char **)opt->value = NULL; + else if (opt->flags & PARSE_OPT_OPTARG && !p->opt) + *(const char **)opt->value = (const char *)opt->defval; + else + return get_arg(p, opt, flags, (const char **)opt->value); + return 0; + + case OPTION_CALLBACK: + if (unset) + return (*opt->callback)(opt, NULL, 1) ? (-1) : 0; + if (opt->flags & PARSE_OPT_NOARG) + return (*opt->callback)(opt, NULL, 0) ? (-1) : 0; + if (opt->flags & PARSE_OPT_OPTARG && !p->opt) + return (*opt->callback)(opt, NULL, 0) ? (-1) : 0; + if (get_arg(p, opt, flags, &arg)) + return -1; + return (*opt->callback)(opt, arg, 0) ? (-1) : 0; + + case OPTION_INTEGER: + if (unset) { + *(int *)opt->value = 0; + return 0; + } + if (opt->flags & PARSE_OPT_OPTARG && !p->opt) { + *(int *)opt->value = opt->defval; + return 0; + } + if (get_arg(p, opt, flags, &arg)) + return -1; + *(int *)opt->value = strtol(arg, (char **)&s, 10); + if (*s) + return opterror(opt, "expects a numerical value", flags); + return 0; + + case OPTION_LONG: + if (unset) { + *(long *)opt->value = 0; + return 0; + } + if (opt->flags & PARSE_OPT_OPTARG && !p->opt) { + *(long *)opt->value = opt->defval; + return 0; + } + if (get_arg(p, opt, flags, &arg)) + return -1; + *(long *)opt->value = strtol(arg, (char **)&s, 10); + if (*s) + return opterror(opt, "expects a numerical value", flags); + return 0; + + default: + die("should not happen, someone must be hit on the forehead"); + } +} + +static int parse_short_opt(struct parse_opt_ctx_t *p, const struct option *options) +{ + for (; options->type != OPTION_END; options++) { + if (options->short_name == *p->opt) { + p->opt = p->opt[1] ? p->opt + 1 : NULL; + return get_value(p, options, OPT_SHORT); + } + } + return -2; +} + +static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg, + const struct option *options) +{ + const char *arg_end = strchr(arg, '='); + const struct option *abbrev_option = NULL, *ambiguous_option = NULL; + int abbrev_flags = 0, ambiguous_flags = 0; + + if (!arg_end) + arg_end = arg + strlen(arg); + + for (; options->type != OPTION_END; options++) { + const char *rest; + int flags = 0; + + if (!options->long_name) + continue; + + rest = skip_prefix(arg, options->long_name); + if (options->type == OPTION_ARGUMENT) { + if (!rest) + continue; + if (*rest == '=') + return opterror(options, "takes no value", flags); + if (*rest) + continue; + p->out[p->cpidx++] = arg - 2; + return 0; + } + if (!rest) { + /* abbreviated? */ + if (!strncmp(options->long_name, arg, arg_end - arg)) { +is_abbreviated: + if (abbrev_option) { + /* + * If this is abbreviated, it is + * ambiguous. So when there is no + * exact match later, we need to + * error out. + */ + ambiguous_option = abbrev_option; + ambiguous_flags = abbrev_flags; + } + if (!(flags & OPT_UNSET) && *arg_end) + p->opt = arg_end + 1; + abbrev_option = options; + abbrev_flags = flags; + continue; + } + /* negated and abbreviated very much? */ + if (!prefixcmp("no-", arg)) { + flags |= OPT_UNSET; + goto is_abbreviated; + } + /* negated? */ + if (strncmp(arg, "no-", 3)) + continue; + flags |= OPT_UNSET; + rest = skip_prefix(arg + 3, options->long_name); + /* abbreviated and negated? */ + if (!rest && !prefixcmp(options->long_name, arg + 3)) + goto is_abbreviated; + if (!rest) + continue; + } + if (*rest) { + if (*rest != '=') + continue; + p->opt = rest + 1; + } + return get_value(p, options, flags); + } + + if (ambiguous_option) + return error("Ambiguous option: %s " + "(could be --%s%s or --%s%s)", + arg, + (ambiguous_flags & OPT_UNSET) ? "no-" : "", + ambiguous_option->long_name, + (abbrev_flags & OPT_UNSET) ? "no-" : "", + abbrev_option->long_name); + if (abbrev_option) + return get_value(p, abbrev_option, abbrev_flags); + return -2; +} + +static void check_typos(const char *arg, const struct option *options) +{ + if (strlen(arg) < 3) + return; + + if (!prefixcmp(arg, "no-")) { + error ("did you mean `--%s` (with two dashes ?)", arg); + exit(129); + } + + for (; options->type != OPTION_END; options++) { + if (!options->long_name) + continue; + if (!prefixcmp(options->long_name, arg)) { + error ("did you mean `--%s` (with two dashes ?)", arg); + exit(129); + } + } +} + +void parse_options_start(struct parse_opt_ctx_t *ctx, + int argc, const char **argv, int flags) +{ + memset(ctx, 0, sizeof(*ctx)); + ctx->argc = argc - 1; + ctx->argv = argv + 1; + ctx->out = argv; + ctx->cpidx = ((flags & PARSE_OPT_KEEP_ARGV0) != 0); + ctx->flags = flags; + if ((flags & PARSE_OPT_KEEP_UNKNOWN) && + (flags & PARSE_OPT_STOP_AT_NON_OPTION)) + die("STOP_AT_NON_OPTION and KEEP_UNKNOWN don't go together"); +} + +static int usage_with_options_internal(const char * const *, + const struct option *, int); + +int parse_options_step(struct parse_opt_ctx_t *ctx, + const struct option *options, + const char * const usagestr[]) +{ + int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP); + + /* we must reset ->opt, unknown short option leave it dangling */ + ctx->opt = NULL; + + for (; ctx->argc; ctx->argc--, ctx->argv++) { + const char *arg = ctx->argv[0]; + + if (*arg != '-' || !arg[1]) { + if (ctx->flags & PARSE_OPT_STOP_AT_NON_OPTION) + break; + ctx->out[ctx->cpidx++] = ctx->argv[0]; + continue; + } + + if (arg[1] != '-') { + ctx->opt = arg + 1; + if (internal_help && *ctx->opt == 'h') + return parse_options_usage(usagestr, options); + switch (parse_short_opt(ctx, options)) { + case -1: + return parse_options_usage(usagestr, options); + case -2: + goto unknown; + } + if (ctx->opt) + check_typos(arg + 1, options); + while (ctx->opt) { + if (internal_help && *ctx->opt == 'h') + return parse_options_usage(usagestr, options); + switch (parse_short_opt(ctx, options)) { + case -1: + return parse_options_usage(usagestr, options); + case -2: + /* fake a short option thing to hide the fact that we may have + * started to parse aggregated stuff + * + * This is leaky, too bad. + */ + ctx->argv[0] = strdup(ctx->opt - 1); + *(char *)ctx->argv[0] = '-'; + goto unknown; + } + } + continue; + } + + if (!arg[2]) { /* "--" */ + if (!(ctx->flags & PARSE_OPT_KEEP_DASHDASH)) { + ctx->argc--; + ctx->argv++; + } + break; + } + + if (internal_help && !strcmp(arg + 2, "help-all")) + return usage_with_options_internal(usagestr, options, 1); + if (internal_help && !strcmp(arg + 2, "help")) + return parse_options_usage(usagestr, options); + switch (parse_long_opt(ctx, arg + 2, options)) { + case -1: + return parse_options_usage(usagestr, options); + case -2: + goto unknown; + } + continue; +unknown: + if (!(ctx->flags & PARSE_OPT_KEEP_UNKNOWN)) + return PARSE_OPT_UNKNOWN; + ctx->out[ctx->cpidx++] = ctx->argv[0]; + ctx->opt = NULL; + } + return PARSE_OPT_DONE; +} + +int parse_options_end(struct parse_opt_ctx_t *ctx) +{ + memmove(ctx->out + ctx->cpidx, ctx->argv, ctx->argc * sizeof(*ctx->out)); + ctx->out[ctx->cpidx + ctx->argc] = NULL; + return ctx->cpidx + ctx->argc; +} + +int parse_options(int argc, const char **argv, const struct option *options, + const char * const usagestr[], int flags) +{ + struct parse_opt_ctx_t ctx; + + parse_options_start(&ctx, argc, argv, flags); + switch (parse_options_step(&ctx, options, usagestr)) { + case PARSE_OPT_HELP: + exit(129); + case PARSE_OPT_DONE: + break; + default: /* PARSE_OPT_UNKNOWN */ + if (ctx.argv[0][1] == '-') { + error("unknown option `%s'", ctx.argv[0] + 2); + } else { + error("unknown switch `%c'", *ctx.opt); + } + usage_with_options(usagestr, options); + } + + return parse_options_end(&ctx); +} + +#define USAGE_OPTS_WIDTH 24 +#define USAGE_GAP 2 + +int usage_with_options_internal(const char * const *usagestr, + const struct option *opts, int full) +{ + if (!usagestr) + return PARSE_OPT_HELP; + + fprintf(stderr, "\n usage: %s\n", *usagestr++); + while (*usagestr && **usagestr) + fprintf(stderr, " or: %s\n", *usagestr++); + while (*usagestr) { + fprintf(stderr, "%s%s\n", + **usagestr ? " " : "", + *usagestr); + usagestr++; + } + + if (opts->type != OPTION_GROUP) + fputc('\n', stderr); + + for (; opts->type != OPTION_END; opts++) { + size_t pos; + int pad; + + if (opts->type == OPTION_GROUP) { + fputc('\n', stderr); + if (*opts->help) + fprintf(stderr, "%s\n", opts->help); + continue; + } + if (!full && (opts->flags & PARSE_OPT_HIDDEN)) + continue; + + pos = fprintf(stderr, " "); + if (opts->short_name) + pos += fprintf(stderr, "-%c", opts->short_name); + if (opts->long_name && opts->short_name) + pos += fprintf(stderr, ", "); + if (opts->long_name) + pos += fprintf(stderr, "--%s", opts->long_name); + + switch (opts->type) { + case OPTION_ARGUMENT: + break; + case OPTION_INTEGER: + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=]"); + else + pos += fprintf(stderr, "[]"); + else + pos += fprintf(stderr, " "); + break; + case OPTION_CALLBACK: + if (opts->flags & PARSE_OPT_NOARG) + break; + /* FALLTHROUGH */ + case OPTION_STRING: + if (opts->argh) { + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=<%s>]", opts->argh); + else + pos += fprintf(stderr, "[<%s>]", opts->argh); + else + pos += fprintf(stderr, " <%s>", opts->argh); + } else { + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=...]"); + else + pos += fprintf(stderr, "[...]"); + else + pos += fprintf(stderr, " ..."); + } + break; + default: /* OPTION_{BIT,BOOLEAN,SET_INT,SET_PTR} */ + break; + } + + if (pos <= USAGE_OPTS_WIDTH) + pad = USAGE_OPTS_WIDTH - pos; + else { + fputc('\n', stderr); + pad = USAGE_OPTS_WIDTH; + } + fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help); + } + fputc('\n', stderr); + + return PARSE_OPT_HELP; +} + +void usage_with_options(const char * const *usagestr, + const struct option *opts) +{ + usage_with_options_internal(usagestr, opts, 0); + exit(129); +} + +int parse_options_usage(const char * const *usagestr, + const struct option *opts) +{ + return usage_with_options_internal(usagestr, opts, 0); +} + + +int parse_opt_verbosity_cb(const struct option *opt, const char *arg, + int unset) +{ + int *target = opt->value; + + if (unset) + /* --no-quiet, --no-verbose */ + *target = 0; + else if (opt->short_name == 'v') { + if (*target >= 0) + (*target)++; + else + *target = 1; + } else { + if (*target <= 0) + (*target)--; + else + *target = -1; + } + return 0; +} diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h new file mode 100644 index 0000000000000000000000000000000000000000..a1039a6ce0ebabdc561fc1b061e3e2ead566cc83 --- /dev/null +++ b/tools/perf/util/parse-options.h @@ -0,0 +1,174 @@ +#ifndef PARSE_OPTIONS_H +#define PARSE_OPTIONS_H + +enum parse_opt_type { + /* special types */ + OPTION_END, + OPTION_ARGUMENT, + OPTION_GROUP, + /* options with no arguments */ + OPTION_BIT, + OPTION_BOOLEAN, /* _INCR would have been a better name */ + OPTION_SET_INT, + OPTION_SET_PTR, + /* options with arguments (usually) */ + OPTION_STRING, + OPTION_INTEGER, + OPTION_LONG, + OPTION_CALLBACK, +}; + +enum parse_opt_flags { + PARSE_OPT_KEEP_DASHDASH = 1, + PARSE_OPT_STOP_AT_NON_OPTION = 2, + PARSE_OPT_KEEP_ARGV0 = 4, + PARSE_OPT_KEEP_UNKNOWN = 8, + PARSE_OPT_NO_INTERNAL_HELP = 16, +}; + +enum parse_opt_option_flags { + PARSE_OPT_OPTARG = 1, + PARSE_OPT_NOARG = 2, + PARSE_OPT_NONEG = 4, + PARSE_OPT_HIDDEN = 8, + PARSE_OPT_LASTARG_DEFAULT = 16, +}; + +struct option; +typedef int parse_opt_cb(const struct option *, const char *arg, int unset); + +/* + * `type`:: + * holds the type of the option, you must have an OPTION_END last in your + * array. + * + * `short_name`:: + * the character to use as a short option name, '\0' if none. + * + * `long_name`:: + * the long option name, without the leading dashes, NULL if none. + * + * `value`:: + * stores pointers to the values to be filled. + * + * `argh`:: + * token to explain the kind of argument this option wants. Keep it + * homogenous across the repository. + * + * `help`:: + * the short help associated to what the option does. + * Must never be NULL (except for OPTION_END). + * OPTION_GROUP uses this pointer to store the group header. + * + * `flags`:: + * mask of parse_opt_option_flags. + * PARSE_OPT_OPTARG: says that the argument is optionnal (not for BOOLEANs) + * PARSE_OPT_NOARG: says that this option takes no argument, for CALLBACKs + * PARSE_OPT_NONEG: says that this option cannot be negated + * PARSE_OPT_HIDDEN this option is skipped in the default usage, showed in + * the long one. + * + * `callback`:: + * pointer to the callback to use for OPTION_CALLBACK. + * + * `defval`:: + * default value to fill (*->value) with for PARSE_OPT_OPTARG. + * OPTION_{BIT,SET_INT,SET_PTR} store the {mask,integer,pointer} to put in + * the value when met. + * CALLBACKS can use it like they want. + */ +struct option { + enum parse_opt_type type; + int short_name; + const char *long_name; + void *value; + const char *argh; + const char *help; + + int flags; + parse_opt_cb *callback; + intptr_t defval; +}; + +#define OPT_END() { OPTION_END } +#define OPT_ARGUMENT(l, h) { OPTION_ARGUMENT, 0, (l), NULL, NULL, (h) } +#define OPT_GROUP(h) { OPTION_GROUP, 0, NULL, NULL, NULL, (h) } +#define OPT_BIT(s, l, v, h, b) { OPTION_BIT, (s), (l), (v), NULL, (h), 0, NULL, (b) } +#define OPT_BOOLEAN(s, l, v, h) { OPTION_BOOLEAN, (s), (l), (v), NULL, (h) } +#define OPT_SET_INT(s, l, v, h, i) { OPTION_SET_INT, (s), (l), (v), NULL, (h), 0, NULL, (i) } +#define OPT_SET_PTR(s, l, v, h, p) { OPTION_SET_PTR, (s), (l), (v), NULL, (h), 0, NULL, (p) } +#define OPT_INTEGER(s, l, v, h) { OPTION_INTEGER, (s), (l), (v), NULL, (h) } +#define OPT_LONG(s, l, v, h) { OPTION_LONG, (s), (l), (v), NULL, (h) } +#define OPT_STRING(s, l, v, a, h) { OPTION_STRING, (s), (l), (v), (a), (h) } +#define OPT_DATE(s, l, v, h) \ + { OPTION_CALLBACK, (s), (l), (v), "time",(h), 0, \ + parse_opt_approxidate_cb } +#define OPT_CALLBACK(s, l, v, a, h, f) \ + { OPTION_CALLBACK, (s), (l), (v), (a), (h), 0, (f) } + +/* parse_options() will filter out the processed options and leave the + * non-option argments in argv[]. + * Returns the number of arguments left in argv[]. + */ +extern int parse_options(int argc, const char **argv, + const struct option *options, + const char * const usagestr[], int flags); + +extern NORETURN void usage_with_options(const char * const *usagestr, + const struct option *options); + +/*----- incremantal advanced APIs -----*/ + +enum { + PARSE_OPT_HELP = -1, + PARSE_OPT_DONE, + PARSE_OPT_UNKNOWN, +}; + +/* + * It's okay for the caller to consume argv/argc in the usual way. + * Other fields of that structure are private to parse-options and should not + * be modified in any way. + */ +struct parse_opt_ctx_t { + const char **argv; + const char **out; + int argc, cpidx; + const char *opt; + int flags; +}; + +extern int parse_options_usage(const char * const *usagestr, + const struct option *opts); + +extern void parse_options_start(struct parse_opt_ctx_t *ctx, + int argc, const char **argv, int flags); + +extern int parse_options_step(struct parse_opt_ctx_t *ctx, + const struct option *options, + const char * const usagestr[]); + +extern int parse_options_end(struct parse_opt_ctx_t *ctx); + + +/*----- some often used options -----*/ +extern int parse_opt_abbrev_cb(const struct option *, const char *, int); +extern int parse_opt_approxidate_cb(const struct option *, const char *, int); +extern int parse_opt_verbosity_cb(const struct option *, const char *, int); + +#define OPT__VERBOSE(var) OPT_BOOLEAN('v', "verbose", (var), "be verbose") +#define OPT__QUIET(var) OPT_BOOLEAN('q', "quiet", (var), "be quiet") +#define OPT__VERBOSITY(var) \ + { OPTION_CALLBACK, 'v', "verbose", (var), NULL, "be more verbose", \ + PARSE_OPT_NOARG, &parse_opt_verbosity_cb, 0 }, \ + { OPTION_CALLBACK, 'q', "quiet", (var), NULL, "be more quiet", \ + PARSE_OPT_NOARG, &parse_opt_verbosity_cb, 0 } +#define OPT__DRY_RUN(var) OPT_BOOLEAN('n', "dry-run", (var), "dry run") +#define OPT__ABBREV(var) \ + { OPTION_CALLBACK, 0, "abbrev", (var), "n", \ + "use digits to display SHA-1s", \ + PARSE_OPT_OPTARG, &parse_opt_abbrev_cb, 0 } + +extern const char *parse_options_fix_filename(const char *prefix, const char *file); + +#endif diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c new file mode 100644 index 0000000000000000000000000000000000000000..a501a40dd2cbeec12cc2d9b4ced0f5b3ea09842e --- /dev/null +++ b/tools/perf/util/path.c @@ -0,0 +1,353 @@ +/* + * I'm tired of doing "vsnprintf()" etc just to open a + * file, so here's a "return static buffer with printf" + * interface for paths. + * + * It's obviously not thread-safe. Sue me. But it's quite + * useful for doing things like + * + * f = open(mkpath("%s/%s.perf", base, name), O_RDONLY); + * + * which is what it's designed for. + */ +#include "cache.h" + +static char bad_path[] = "/bad-path/"; +/* + * Two hacks: + */ + +static char *get_perf_dir(void) +{ + return "."; +} + +size_t strlcpy(char *dest, const char *src, size_t size) +{ + size_t ret = strlen(src); + + if (size) { + size_t len = (ret >= size) ? size - 1 : ret; + memcpy(dest, src, len); + dest[len] = '\0'; + } + return ret; +} + + +static char *get_pathname(void) +{ + static char pathname_array[4][PATH_MAX]; + static int index; + return pathname_array[3 & ++index]; +} + +static char *cleanup_path(char *path) +{ + /* Clean it up */ + if (!memcmp(path, "./", 2)) { + path += 2; + while (*path == '/') + path++; + } + return path; +} + +char *mksnpath(char *buf, size_t n, const char *fmt, ...) +{ + va_list args; + unsigned len; + + va_start(args, fmt); + len = vsnprintf(buf, n, fmt, args); + va_end(args); + if (len >= n) { + strlcpy(buf, bad_path, n); + return buf; + } + return cleanup_path(buf); +} + +static char *perf_vsnpath(char *buf, size_t n, const char *fmt, va_list args) +{ + const char *perf_dir = get_perf_dir(); + size_t len; + + len = strlen(perf_dir); + if (n < len + 1) + goto bad; + memcpy(buf, perf_dir, len); + if (len && !is_dir_sep(perf_dir[len-1])) + buf[len++] = '/'; + len += vsnprintf(buf + len, n - len, fmt, args); + if (len >= n) + goto bad; + return cleanup_path(buf); +bad: + strlcpy(buf, bad_path, n); + return buf; +} + +char *perf_snpath(char *buf, size_t n, const char *fmt, ...) +{ + va_list args; + va_start(args, fmt); + (void)perf_vsnpath(buf, n, fmt, args); + va_end(args); + return buf; +} + +char *perf_pathdup(const char *fmt, ...) +{ + char path[PATH_MAX]; + va_list args; + va_start(args, fmt); + (void)perf_vsnpath(path, sizeof(path), fmt, args); + va_end(args); + return xstrdup(path); +} + +char *mkpath(const char *fmt, ...) +{ + va_list args; + unsigned len; + char *pathname = get_pathname(); + + va_start(args, fmt); + len = vsnprintf(pathname, PATH_MAX, fmt, args); + va_end(args); + if (len >= PATH_MAX) + return bad_path; + return cleanup_path(pathname); +} + +char *perf_path(const char *fmt, ...) +{ + const char *perf_dir = get_perf_dir(); + char *pathname = get_pathname(); + va_list args; + unsigned len; + + len = strlen(perf_dir); + if (len > PATH_MAX-100) + return bad_path; + memcpy(pathname, perf_dir, len); + if (len && perf_dir[len-1] != '/') + pathname[len++] = '/'; + va_start(args, fmt); + len += vsnprintf(pathname + len, PATH_MAX - len, fmt, args); + va_end(args); + if (len >= PATH_MAX) + return bad_path; + return cleanup_path(pathname); +} + + +/* perf_mkstemp() - create tmp file honoring TMPDIR variable */ +int perf_mkstemp(char *path, size_t len, const char *template) +{ + const char *tmp; + size_t n; + + tmp = getenv("TMPDIR"); + if (!tmp) + tmp = "/tmp"; + n = snprintf(path, len, "%s/%s", tmp, template); + if (len <= n) { + errno = ENAMETOOLONG; + return -1; + } + return mkstemp(path); +} + + +const char *make_relative_path(const char *abs, const char *base) +{ + static char buf[PATH_MAX + 1]; + int baselen; + if (!base) + return abs; + baselen = strlen(base); + if (prefixcmp(abs, base)) + return abs; + if (abs[baselen] == '/') + baselen++; + else if (base[baselen - 1] != '/') + return abs; + strcpy(buf, abs + baselen); + return buf; +} + +/* + * It is okay if dst == src, but they should not overlap otherwise. + * + * Performs the following normalizations on src, storing the result in dst: + * - Ensures that components are separated by '/' (Windows only) + * - Squashes sequences of '/'. + * - Removes "." components. + * - Removes ".." components, and the components the precede them. + * Returns failure (non-zero) if a ".." component appears as first path + * component anytime during the normalization. Otherwise, returns success (0). + * + * Note that this function is purely textual. It does not follow symlinks, + * verify the existence of the path, or make any system calls. + */ +int normalize_path_copy(char *dst, const char *src) +{ + char *dst0; + + if (has_dos_drive_prefix(src)) { + *dst++ = *src++; + *dst++ = *src++; + } + dst0 = dst; + + if (is_dir_sep(*src)) { + *dst++ = '/'; + while (is_dir_sep(*src)) + src++; + } + + for (;;) { + char c = *src; + + /* + * A path component that begins with . could be + * special: + * (1) "." and ends -- ignore and terminate. + * (2) "./" -- ignore them, eat slash and continue. + * (3) ".." and ends -- strip one and terminate. + * (4) "../" -- strip one, eat slash and continue. + */ + if (c == '.') { + if (!src[1]) { + /* (1) */ + src++; + } else if (is_dir_sep(src[1])) { + /* (2) */ + src += 2; + while (is_dir_sep(*src)) + src++; + continue; + } else if (src[1] == '.') { + if (!src[2]) { + /* (3) */ + src += 2; + goto up_one; + } else if (is_dir_sep(src[2])) { + /* (4) */ + src += 3; + while (is_dir_sep(*src)) + src++; + goto up_one; + } + } + } + + /* copy up to the next '/', and eat all '/' */ + while ((c = *src++) != '\0' && !is_dir_sep(c)) + *dst++ = c; + if (is_dir_sep(c)) { + *dst++ = '/'; + while (is_dir_sep(c)) + c = *src++; + src--; + } else if (!c) + break; + continue; + + up_one: + /* + * dst0..dst is prefix portion, and dst[-1] is '/'; + * go up one level. + */ + dst--; /* go to trailing '/' */ + if (dst <= dst0) + return -1; + /* Windows: dst[-1] cannot be backslash anymore */ + while (dst0 < dst && dst[-1] != '/') + dst--; + } + *dst = '\0'; + return 0; +} + +/* + * path = Canonical absolute path + * prefix_list = Colon-separated list of absolute paths + * + * Determines, for each path in prefix_list, whether the "prefix" really + * is an ancestor directory of path. Returns the length of the longest + * ancestor directory, excluding any trailing slashes, or -1 if no prefix + * is an ancestor. (Note that this means 0 is returned if prefix_list is + * "/".) "/foo" is not considered an ancestor of "/foobar". Directories + * are not considered to be their own ancestors. path must be in a + * canonical form: empty components, or "." or ".." components are not + * allowed. prefix_list may be null, which is like "". + */ +int longest_ancestor_length(const char *path, const char *prefix_list) +{ + char buf[PATH_MAX+1]; + const char *ceil, *colon; + int len, max_len = -1; + + if (prefix_list == NULL || !strcmp(path, "/")) + return -1; + + for (colon = ceil = prefix_list; *colon; ceil = colon+1) { + for (colon = ceil; *colon && *colon != PATH_SEP; colon++); + len = colon - ceil; + if (len == 0 || len > PATH_MAX || !is_absolute_path(ceil)) + continue; + strlcpy(buf, ceil, len+1); + if (normalize_path_copy(buf, buf) < 0) + continue; + len = strlen(buf); + if (len > 0 && buf[len-1] == '/') + buf[--len] = '\0'; + + if (!strncmp(path, buf, len) && + path[len] == '/' && + len > max_len) { + max_len = len; + } + } + + return max_len; +} + +/* strip arbitrary amount of directory separators at end of path */ +static inline int chomp_trailing_dir_sep(const char *path, int len) +{ + while (len && is_dir_sep(path[len - 1])) + len--; + return len; +} + +/* + * If path ends with suffix (complete path components), returns the + * part before suffix (sans trailing directory separators). + * Otherwise returns NULL. + */ +char *strip_path_suffix(const char *path, const char *suffix) +{ + int path_len = strlen(path), suffix_len = strlen(suffix); + + while (suffix_len) { + if (!path_len) + return NULL; + + if (is_dir_sep(path[path_len - 1])) { + if (!is_dir_sep(suffix[suffix_len - 1])) + return NULL; + path_len = chomp_trailing_dir_sep(path, path_len); + suffix_len = chomp_trailing_dir_sep(suffix, suffix_len); + } + else if (path[--path_len] != suffix[--suffix_len]) + return NULL; + } + + if (path_len && !is_dir_sep(path[path_len - 1])) + return NULL; + return xstrndup(path, chomp_trailing_dir_sep(path, path_len)); +} diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c new file mode 100644 index 0000000000000000000000000000000000000000..f18c5212bc92b8a89437a65fbdd83c0928266110 --- /dev/null +++ b/tools/perf/util/quote.c @@ -0,0 +1,481 @@ +#include "cache.h" +#include "quote.h" + +int quote_path_fully = 1; + +/* Help to copy the thing properly quoted for the shell safety. + * any single quote is replaced with '\'', any exclamation point + * is replaced with '\!', and the whole thing is enclosed in a + * + * E.g. + * original sq_quote result + * name ==> name ==> 'name' + * a b ==> a b ==> 'a b' + * a'b ==> a'\''b ==> 'a'\''b' + * a!b ==> a'\!'b ==> 'a'\!'b' + */ +static inline int need_bs_quote(char c) +{ + return (c == '\'' || c == '!'); +} + +void sq_quote_buf(struct strbuf *dst, const char *src) +{ + char *to_free = NULL; + + if (dst->buf == src) + to_free = strbuf_detach(dst, NULL); + + strbuf_addch(dst, '\''); + while (*src) { + size_t len = strcspn(src, "'!"); + strbuf_add(dst, src, len); + src += len; + while (need_bs_quote(*src)) { + strbuf_addstr(dst, "'\\"); + strbuf_addch(dst, *src++); + strbuf_addch(dst, '\''); + } + } + strbuf_addch(dst, '\''); + free(to_free); +} + +void sq_quote_print(FILE *stream, const char *src) +{ + char c; + + fputc('\'', stream); + while ((c = *src++)) { + if (need_bs_quote(c)) { + fputs("'\\", stream); + fputc(c, stream); + fputc('\'', stream); + } else { + fputc(c, stream); + } + } + fputc('\'', stream); +} + +void sq_quote_argv(struct strbuf *dst, const char** argv, size_t maxlen) +{ + int i; + + /* Copy into destination buffer. */ + strbuf_grow(dst, 255); + for (i = 0; argv[i]; ++i) { + strbuf_addch(dst, ' '); + sq_quote_buf(dst, argv[i]); + if (maxlen && dst->len > maxlen) + die("Too many or long arguments"); + } +} + +char *sq_dequote_step(char *arg, char **next) +{ + char *dst = arg; + char *src = arg; + char c; + + if (*src != '\'') + return NULL; + for (;;) { + c = *++src; + if (!c) + return NULL; + if (c != '\'') { + *dst++ = c; + continue; + } + /* We stepped out of sq */ + switch (*++src) { + case '\0': + *dst = 0; + if (next) + *next = NULL; + return arg; + case '\\': + c = *++src; + if (need_bs_quote(c) && *++src == '\'') { + *dst++ = c; + continue; + } + /* Fallthrough */ + default: + if (!next || !isspace(*src)) + return NULL; + do { + c = *++src; + } while (isspace(c)); + *dst = 0; + *next = src; + return arg; + } + } +} + +char *sq_dequote(char *arg) +{ + return sq_dequote_step(arg, NULL); +} + +int sq_dequote_to_argv(char *arg, const char ***argv, int *nr, int *alloc) +{ + char *next = arg; + + if (!*arg) + return 0; + do { + char *dequoted = sq_dequote_step(next, &next); + if (!dequoted) + return -1; + ALLOC_GROW(*argv, *nr + 1, *alloc); + (*argv)[(*nr)++] = dequoted; + } while (next); + + return 0; +} + +/* 1 means: quote as octal + * 0 means: quote as octal if (quote_path_fully) + * -1 means: never quote + * c: quote as "\\c" + */ +#define X8(x) x, x, x, x, x, x, x, x +#define X16(x) X8(x), X8(x) +static signed char const sq_lookup[256] = { + /* 0 1 2 3 4 5 6 7 */ + /* 0x00 */ 1, 1, 1, 1, 1, 1, 1, 'a', + /* 0x08 */ 'b', 't', 'n', 'v', 'f', 'r', 1, 1, + /* 0x10 */ X16(1), + /* 0x20 */ -1, -1, '"', -1, -1, -1, -1, -1, + /* 0x28 */ X16(-1), X16(-1), X16(-1), + /* 0x58 */ -1, -1, -1, -1,'\\', -1, -1, -1, + /* 0x60 */ X16(-1), X8(-1), + /* 0x78 */ -1, -1, -1, -1, -1, -1, -1, 1, + /* 0x80 */ /* set to 0 */ +}; + +static inline int sq_must_quote(char c) +{ + return sq_lookup[(unsigned char)c] + quote_path_fully > 0; +} + +/* returns the longest prefix not needing a quote up to maxlen if positive. + This stops at the first \0 because it's marked as a character needing an + escape */ +static size_t next_quote_pos(const char *s, ssize_t maxlen) +{ + size_t len; + if (maxlen < 0) { + for (len = 0; !sq_must_quote(s[len]); len++); + } else { + for (len = 0; len < maxlen && !sq_must_quote(s[len]); len++); + } + return len; +} + +/* + * C-style name quoting. + * + * (1) if sb and fp are both NULL, inspect the input name and counts the + * number of bytes that are needed to hold c_style quoted version of name, + * counting the double quotes around it but not terminating NUL, and + * returns it. + * However, if name does not need c_style quoting, it returns 0. + * + * (2) if sb or fp are not NULL, it emits the c_style quoted version + * of name, enclosed with double quotes if asked and needed only. + * Return value is the same as in (1). + */ +static size_t quote_c_style_counted(const char *name, ssize_t maxlen, + struct strbuf *sb, FILE *fp, int no_dq) +{ +#undef EMIT +#define EMIT(c) \ + do { \ + if (sb) strbuf_addch(sb, (c)); \ + if (fp) fputc((c), fp); \ + count++; \ + } while (0) +#define EMITBUF(s, l) \ + do { \ + int __ret; \ + if (sb) strbuf_add(sb, (s), (l)); \ + if (fp) __ret = fwrite((s), (l), 1, fp); \ + count += (l); \ + } while (0) + + size_t len, count = 0; + const char *p = name; + + for (;;) { + int ch; + + len = next_quote_pos(p, maxlen); + if (len == maxlen || !p[len]) + break; + + if (!no_dq && p == name) + EMIT('"'); + + EMITBUF(p, len); + EMIT('\\'); + p += len; + ch = (unsigned char)*p++; + if (sq_lookup[ch] >= ' ') { + EMIT(sq_lookup[ch]); + } else { + EMIT(((ch >> 6) & 03) + '0'); + EMIT(((ch >> 3) & 07) + '0'); + EMIT(((ch >> 0) & 07) + '0'); + } + } + + EMITBUF(p, len); + if (p == name) /* no ending quote needed */ + return 0; + + if (!no_dq) + EMIT('"'); + return count; +} + +size_t quote_c_style(const char *name, struct strbuf *sb, FILE *fp, int nodq) +{ + return quote_c_style_counted(name, -1, sb, fp, nodq); +} + +void quote_two_c_style(struct strbuf *sb, const char *prefix, const char *path, int nodq) +{ + if (quote_c_style(prefix, NULL, NULL, 0) || + quote_c_style(path, NULL, NULL, 0)) { + if (!nodq) + strbuf_addch(sb, '"'); + quote_c_style(prefix, sb, NULL, 1); + quote_c_style(path, sb, NULL, 1); + if (!nodq) + strbuf_addch(sb, '"'); + } else { + strbuf_addstr(sb, prefix); + strbuf_addstr(sb, path); + } +} + +void write_name_quoted(const char *name, FILE *fp, int terminator) +{ + if (terminator) { + quote_c_style(name, NULL, fp, 0); + } else { + fputs(name, fp); + } + fputc(terminator, fp); +} + +extern void write_name_quotedpfx(const char *pfx, size_t pfxlen, + const char *name, FILE *fp, int terminator) +{ + int needquote = 0; + + if (terminator) { + needquote = next_quote_pos(pfx, pfxlen) < pfxlen + || name[next_quote_pos(name, -1)]; + } + if (needquote) { + fputc('"', fp); + quote_c_style_counted(pfx, pfxlen, NULL, fp, 1); + quote_c_style(name, NULL, fp, 1); + fputc('"', fp); + } else { + int ret; + + ret = fwrite(pfx, pfxlen, 1, fp); + fputs(name, fp); + } + fputc(terminator, fp); +} + +/* quote path as relative to the given prefix */ +char *quote_path_relative(const char *in, int len, + struct strbuf *out, const char *prefix) +{ + int needquote; + + if (len < 0) + len = strlen(in); + + /* "../" prefix itself does not need quoting, but "in" might. */ + needquote = next_quote_pos(in, len) < len; + strbuf_setlen(out, 0); + strbuf_grow(out, len); + + if (needquote) + strbuf_addch(out, '"'); + if (prefix) { + int off = 0; + while (prefix[off] && off < len && prefix[off] == in[off]) + if (prefix[off] == '/') { + prefix += off + 1; + in += off + 1; + len -= off + 1; + off = 0; + } else + off++; + + for (; *prefix; prefix++) + if (*prefix == '/') + strbuf_addstr(out, "../"); + } + + quote_c_style_counted (in, len, out, NULL, 1); + + if (needquote) + strbuf_addch(out, '"'); + if (!out->len) + strbuf_addstr(out, "./"); + + return out->buf; +} + +/* + * C-style name unquoting. + * + * Quoted should point at the opening double quote. + * + Returns 0 if it was able to unquote the string properly, and appends the + * result in the strbuf `sb'. + * + Returns -1 in case of error, and doesn't touch the strbuf. Though note + * that this function will allocate memory in the strbuf, so calling + * strbuf_release is mandatory whichever result unquote_c_style returns. + * + * Updates endp pointer to point at one past the ending double quote if given. + */ +int unquote_c_style(struct strbuf *sb, const char *quoted, const char **endp) +{ + size_t oldlen = sb->len, len; + int ch, ac; + + if (*quoted++ != '"') + return -1; + + for (;;) { + len = strcspn(quoted, "\"\\"); + strbuf_add(sb, quoted, len); + quoted += len; + + switch (*quoted++) { + case '"': + if (endp) + *endp = quoted; + return 0; + case '\\': + break; + default: + goto error; + } + + switch ((ch = *quoted++)) { + case 'a': ch = '\a'; break; + case 'b': ch = '\b'; break; + case 'f': ch = '\f'; break; + case 'n': ch = '\n'; break; + case 'r': ch = '\r'; break; + case 't': ch = '\t'; break; + case 'v': ch = '\v'; break; + + case '\\': case '"': + break; /* verbatim */ + + /* octal values with first digit over 4 overflow */ + case '0': case '1': case '2': case '3': + ac = ((ch - '0') << 6); + if ((ch = *quoted++) < '0' || '7' < ch) + goto error; + ac |= ((ch - '0') << 3); + if ((ch = *quoted++) < '0' || '7' < ch) + goto error; + ac |= (ch - '0'); + ch = ac; + break; + default: + goto error; + } + strbuf_addch(sb, ch); + } + + error: + strbuf_setlen(sb, oldlen); + return -1; +} + +/* quoting as a string literal for other languages */ + +void perl_quote_print(FILE *stream, const char *src) +{ + const char sq = '\''; + const char bq = '\\'; + char c; + + fputc(sq, stream); + while ((c = *src++)) { + if (c == sq || c == bq) + fputc(bq, stream); + fputc(c, stream); + } + fputc(sq, stream); +} + +void python_quote_print(FILE *stream, const char *src) +{ + const char sq = '\''; + const char bq = '\\'; + const char nl = '\n'; + char c; + + fputc(sq, stream); + while ((c = *src++)) { + if (c == nl) { + fputc(bq, stream); + fputc('n', stream); + continue; + } + if (c == sq || c == bq) + fputc(bq, stream); + fputc(c, stream); + } + fputc(sq, stream); +} + +void tcl_quote_print(FILE *stream, const char *src) +{ + char c; + + fputc('"', stream); + while ((c = *src++)) { + switch (c) { + case '[': case ']': + case '{': case '}': + case '$': case '\\': case '"': + fputc('\\', stream); + default: + fputc(c, stream); + break; + case '\f': + fputs("\\f", stream); + break; + case '\r': + fputs("\\r", stream); + break; + case '\n': + fputs("\\n", stream); + break; + case '\t': + fputs("\\t", stream); + break; + case '\v': + fputs("\\v", stream); + break; + } + } + fputc('"', stream); +} diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h new file mode 100644 index 0000000000000000000000000000000000000000..5dfad89816db124e9b18abc7d2964997a55a329b --- /dev/null +++ b/tools/perf/util/quote.h @@ -0,0 +1,68 @@ +#ifndef QUOTE_H +#define QUOTE_H + +#include +#include + +/* Help to copy the thing properly quoted for the shell safety. + * any single quote is replaced with '\'', any exclamation point + * is replaced with '\!', and the whole thing is enclosed in a + * single quote pair. + * + * For example, if you are passing the result to system() as an + * argument: + * + * sprintf(cmd, "foobar %s %s", sq_quote(arg0), sq_quote(arg1)) + * + * would be appropriate. If the system() is going to call ssh to + * run the command on the other side: + * + * sprintf(cmd, "git-diff-tree %s %s", sq_quote(arg0), sq_quote(arg1)); + * sprintf(rcmd, "ssh %s %s", sq_util/quote.host), sq_quote(cmd)); + * + * Note that the above examples leak memory! Remember to free result from + * sq_quote() in a real application. + * + * sq_quote_buf() writes to an existing buffer of specified size; it + * will return the number of characters that would have been written + * excluding the final null regardless of the buffer size. + */ + +extern void sq_quote_print(FILE *stream, const char *src); + +extern void sq_quote_buf(struct strbuf *, const char *src); +extern void sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen); + +/* This unwraps what sq_quote() produces in place, but returns + * NULL if the input does not look like what sq_quote would have + * produced. + */ +extern char *sq_dequote(char *); + +/* + * Same as the above, but can be used to unwrap many arguments in the + * same string separated by space. "next" is changed to point to the + * next argument that should be passed as first parameter. When there + * is no more argument to be dequoted, "next" is updated to point to NULL. + */ +extern char *sq_dequote_step(char *arg, char **next); +extern int sq_dequote_to_argv(char *arg, const char ***argv, int *nr, int *alloc); + +extern int unquote_c_style(struct strbuf *, const char *quoted, const char **endp); +extern size_t quote_c_style(const char *name, struct strbuf *, FILE *, int no_dq); +extern void quote_two_c_style(struct strbuf *, const char *, const char *, int); + +extern void write_name_quoted(const char *name, FILE *, int terminator); +extern void write_name_quotedpfx(const char *pfx, size_t pfxlen, + const char *name, FILE *, int terminator); + +/* quote path as relative to the given prefix */ +char *quote_path_relative(const char *in, int len, + struct strbuf *out, const char *prefix); + +/* quoting as a string literal for other languages */ +extern void perl_quote_print(FILE *stream, const char *src); +extern void python_quote_print(FILE *stream, const char *src); +extern void tcl_quote_print(FILE *stream, const char *src); + +#endif diff --git a/tools/perf/util/rbtree.c b/tools/perf/util/rbtree.c new file mode 100644 index 0000000000000000000000000000000000000000..b15ba9c7cb3f2500d43c1182c1d91a8f1302b6b7 --- /dev/null +++ b/tools/perf/util/rbtree.c @@ -0,0 +1,383 @@ +/* + Red Black Trees + (C) 1999 Andrea Arcangeli + (C) 2002 David Woodhouse + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + + linux/lib/rbtree.c +*/ + +#include "rbtree.h" + +static void __rb_rotate_left(struct rb_node *node, struct rb_root *root) +{ + struct rb_node *right = node->rb_right; + struct rb_node *parent = rb_parent(node); + + if ((node->rb_right = right->rb_left)) + rb_set_parent(right->rb_left, node); + right->rb_left = node; + + rb_set_parent(right, parent); + + if (parent) + { + if (node == parent->rb_left) + parent->rb_left = right; + else + parent->rb_right = right; + } + else + root->rb_node = right; + rb_set_parent(node, right); +} + +static void __rb_rotate_right(struct rb_node *node, struct rb_root *root) +{ + struct rb_node *left = node->rb_left; + struct rb_node *parent = rb_parent(node); + + if ((node->rb_left = left->rb_right)) + rb_set_parent(left->rb_right, node); + left->rb_right = node; + + rb_set_parent(left, parent); + + if (parent) + { + if (node == parent->rb_right) + parent->rb_right = left; + else + parent->rb_left = left; + } + else + root->rb_node = left; + rb_set_parent(node, left); +} + +void rb_insert_color(struct rb_node *node, struct rb_root *root) +{ + struct rb_node *parent, *gparent; + + while ((parent = rb_parent(node)) && rb_is_red(parent)) + { + gparent = rb_parent(parent); + + if (parent == gparent->rb_left) + { + { + register struct rb_node *uncle = gparent->rb_right; + if (uncle && rb_is_red(uncle)) + { + rb_set_black(uncle); + rb_set_black(parent); + rb_set_red(gparent); + node = gparent; + continue; + } + } + + if (parent->rb_right == node) + { + register struct rb_node *tmp; + __rb_rotate_left(parent, root); + tmp = parent; + parent = node; + node = tmp; + } + + rb_set_black(parent); + rb_set_red(gparent); + __rb_rotate_right(gparent, root); + } else { + { + register struct rb_node *uncle = gparent->rb_left; + if (uncle && rb_is_red(uncle)) + { + rb_set_black(uncle); + rb_set_black(parent); + rb_set_red(gparent); + node = gparent; + continue; + } + } + + if (parent->rb_left == node) + { + register struct rb_node *tmp; + __rb_rotate_right(parent, root); + tmp = parent; + parent = node; + node = tmp; + } + + rb_set_black(parent); + rb_set_red(gparent); + __rb_rotate_left(gparent, root); + } + } + + rb_set_black(root->rb_node); +} + +static void __rb_erase_color(struct rb_node *node, struct rb_node *parent, + struct rb_root *root) +{ + struct rb_node *other; + + while ((!node || rb_is_black(node)) && node != root->rb_node) + { + if (parent->rb_left == node) + { + other = parent->rb_right; + if (rb_is_red(other)) + { + rb_set_black(other); + rb_set_red(parent); + __rb_rotate_left(parent, root); + other = parent->rb_right; + } + if ((!other->rb_left || rb_is_black(other->rb_left)) && + (!other->rb_right || rb_is_black(other->rb_right))) + { + rb_set_red(other); + node = parent; + parent = rb_parent(node); + } + else + { + if (!other->rb_right || rb_is_black(other->rb_right)) + { + rb_set_black(other->rb_left); + rb_set_red(other); + __rb_rotate_right(other, root); + other = parent->rb_right; + } + rb_set_color(other, rb_color(parent)); + rb_set_black(parent); + rb_set_black(other->rb_right); + __rb_rotate_left(parent, root); + node = root->rb_node; + break; + } + } + else + { + other = parent->rb_left; + if (rb_is_red(other)) + { + rb_set_black(other); + rb_set_red(parent); + __rb_rotate_right(parent, root); + other = parent->rb_left; + } + if ((!other->rb_left || rb_is_black(other->rb_left)) && + (!other->rb_right || rb_is_black(other->rb_right))) + { + rb_set_red(other); + node = parent; + parent = rb_parent(node); + } + else + { + if (!other->rb_left || rb_is_black(other->rb_left)) + { + rb_set_black(other->rb_right); + rb_set_red(other); + __rb_rotate_left(other, root); + other = parent->rb_left; + } + rb_set_color(other, rb_color(parent)); + rb_set_black(parent); + rb_set_black(other->rb_left); + __rb_rotate_right(parent, root); + node = root->rb_node; + break; + } + } + } + if (node) + rb_set_black(node); +} + +void rb_erase(struct rb_node *node, struct rb_root *root) +{ + struct rb_node *child, *parent; + int color; + + if (!node->rb_left) + child = node->rb_right; + else if (!node->rb_right) + child = node->rb_left; + else + { + struct rb_node *old = node, *left; + + node = node->rb_right; + while ((left = node->rb_left) != NULL) + node = left; + child = node->rb_right; + parent = rb_parent(node); + color = rb_color(node); + + if (child) + rb_set_parent(child, parent); + if (parent == old) { + parent->rb_right = child; + parent = node; + } else + parent->rb_left = child; + + node->rb_parent_color = old->rb_parent_color; + node->rb_right = old->rb_right; + node->rb_left = old->rb_left; + + if (rb_parent(old)) + { + if (rb_parent(old)->rb_left == old) + rb_parent(old)->rb_left = node; + else + rb_parent(old)->rb_right = node; + } else + root->rb_node = node; + + rb_set_parent(old->rb_left, node); + if (old->rb_right) + rb_set_parent(old->rb_right, node); + goto color; + } + + parent = rb_parent(node); + color = rb_color(node); + + if (child) + rb_set_parent(child, parent); + if (parent) + { + if (parent->rb_left == node) + parent->rb_left = child; + else + parent->rb_right = child; + } + else + root->rb_node = child; + + color: + if (color == RB_BLACK) + __rb_erase_color(child, parent, root); +} + +/* + * This function returns the first node (in sort order) of the tree. + */ +struct rb_node *rb_first(const struct rb_root *root) +{ + struct rb_node *n; + + n = root->rb_node; + if (!n) + return NULL; + while (n->rb_left) + n = n->rb_left; + return n; +} + +struct rb_node *rb_last(const struct rb_root *root) +{ + struct rb_node *n; + + n = root->rb_node; + if (!n) + return NULL; + while (n->rb_right) + n = n->rb_right; + return n; +} + +struct rb_node *rb_next(const struct rb_node *node) +{ + struct rb_node *parent; + + if (rb_parent(node) == node) + return NULL; + + /* If we have a right-hand child, go down and then left as far + as we can. */ + if (node->rb_right) { + node = node->rb_right; + while (node->rb_left) + node=node->rb_left; + return (struct rb_node *)node; + } + + /* No right-hand children. Everything down and left is + smaller than us, so any 'next' node must be in the general + direction of our parent. Go up the tree; any time the + ancestor is a right-hand child of its parent, keep going + up. First time it's a left-hand child of its parent, said + parent is our 'next' node. */ + while ((parent = rb_parent(node)) && node == parent->rb_right) + node = parent; + + return parent; +} + +struct rb_node *rb_prev(const struct rb_node *node) +{ + struct rb_node *parent; + + if (rb_parent(node) == node) + return NULL; + + /* If we have a left-hand child, go down and then right as far + as we can. */ + if (node->rb_left) { + node = node->rb_left; + while (node->rb_right) + node=node->rb_right; + return (struct rb_node *)node; + } + + /* No left-hand children. Go up till we find an ancestor which + is a right-hand child of its parent */ + while ((parent = rb_parent(node)) && node == parent->rb_left) + node = parent; + + return parent; +} + +void rb_replace_node(struct rb_node *victim, struct rb_node *new, + struct rb_root *root) +{ + struct rb_node *parent = rb_parent(victim); + + /* Set the surrounding nodes to point to the replacement */ + if (parent) { + if (victim == parent->rb_left) + parent->rb_left = new; + else + parent->rb_right = new; + } else { + root->rb_node = new; + } + if (victim->rb_left) + rb_set_parent(victim->rb_left, new); + if (victim->rb_right) + rb_set_parent(victim->rb_right, new); + + /* Copy the pointers/colour from the victim to the replacement */ + *new = *victim; +} diff --git a/tools/perf/util/rbtree.h b/tools/perf/util/rbtree.h new file mode 100644 index 0000000000000000000000000000000000000000..6bdc488a47fbabbbad379e6a83c7e21fbe8dcc6b --- /dev/null +++ b/tools/perf/util/rbtree.h @@ -0,0 +1,171 @@ +/* + Red Black Trees + (C) 1999 Andrea Arcangeli + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + + linux/include/linux/rbtree.h + + To use rbtrees you'll have to implement your own insert and search cores. + This will avoid us to use callbacks and to drop drammatically performances. + I know it's not the cleaner way, but in C (not in C++) to get + performances and genericity... + + Some example of insert and search follows here. The search is a plain + normal search over an ordered tree. The insert instead must be implemented + int two steps: as first thing the code must insert the element in + order as a red leaf in the tree, then the support library function + rb_insert_color() must be called. Such function will do the + not trivial work to rebalance the rbtree if necessary. + +----------------------------------------------------------------------- +static inline struct page * rb_search_page_cache(struct inode * inode, + unsigned long offset) +{ + struct rb_node * n = inode->i_rb_page_cache.rb_node; + struct page * page; + + while (n) + { + page = rb_entry(n, struct page, rb_page_cache); + + if (offset < page->offset) + n = n->rb_left; + else if (offset > page->offset) + n = n->rb_right; + else + return page; + } + return NULL; +} + +static inline struct page * __rb_insert_page_cache(struct inode * inode, + unsigned long offset, + struct rb_node * node) +{ + struct rb_node ** p = &inode->i_rb_page_cache.rb_node; + struct rb_node * parent = NULL; + struct page * page; + + while (*p) + { + parent = *p; + page = rb_entry(parent, struct page, rb_page_cache); + + if (offset < page->offset) + p = &(*p)->rb_left; + else if (offset > page->offset) + p = &(*p)->rb_right; + else + return page; + } + + rb_link_node(node, parent, p); + + return NULL; +} + +static inline struct page * rb_insert_page_cache(struct inode * inode, + unsigned long offset, + struct rb_node * node) +{ + struct page * ret; + if ((ret = __rb_insert_page_cache(inode, offset, node))) + goto out; + rb_insert_color(node, &inode->i_rb_page_cache); + out: + return ret; +} +----------------------------------------------------------------------- +*/ + +#ifndef _LINUX_RBTREE_H +#define _LINUX_RBTREE_H + +#include + +/** + * container_of - cast a member of a structure out to the containing structure + * @ptr: the pointer to the member. + * @type: the type of the container struct this is embedded in. + * @member: the name of the member within the struct. + * + */ +#define container_of(ptr, type, member) ({ \ + const typeof( ((type *)0)->member ) *__mptr = (ptr); \ + (type *)( (char *)__mptr - offsetof(type,member) );}) + +struct rb_node +{ + unsigned long rb_parent_color; +#define RB_RED 0 +#define RB_BLACK 1 + struct rb_node *rb_right; + struct rb_node *rb_left; +} __attribute__((aligned(sizeof(long)))); + /* The alignment might seem pointless, but allegedly CRIS needs it */ + +struct rb_root +{ + struct rb_node *rb_node; +}; + + +#define rb_parent(r) ((struct rb_node *)((r)->rb_parent_color & ~3)) +#define rb_color(r) ((r)->rb_parent_color & 1) +#define rb_is_red(r) (!rb_color(r)) +#define rb_is_black(r) rb_color(r) +#define rb_set_red(r) do { (r)->rb_parent_color &= ~1; } while (0) +#define rb_set_black(r) do { (r)->rb_parent_color |= 1; } while (0) + +static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) +{ + rb->rb_parent_color = (rb->rb_parent_color & 3) | (unsigned long)p; +} +static inline void rb_set_color(struct rb_node *rb, int color) +{ + rb->rb_parent_color = (rb->rb_parent_color & ~1) | color; +} + +#define RB_ROOT (struct rb_root) { NULL, } +#define rb_entry(ptr, type, member) container_of(ptr, type, member) + +#define RB_EMPTY_ROOT(root) ((root)->rb_node == NULL) +#define RB_EMPTY_NODE(node) (rb_parent(node) == node) +#define RB_CLEAR_NODE(node) (rb_set_parent(node, node)) + +extern void rb_insert_color(struct rb_node *, struct rb_root *); +extern void rb_erase(struct rb_node *, struct rb_root *); + +/* Find logical next and previous nodes in a tree */ +extern struct rb_node *rb_next(const struct rb_node *); +extern struct rb_node *rb_prev(const struct rb_node *); +extern struct rb_node *rb_first(const struct rb_root *); +extern struct rb_node *rb_last(const struct rb_root *); + +/* Fast replacement of a single node without remove/rebalance/add/rebalance */ +extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, + struct rb_root *root); + +static inline void rb_link_node(struct rb_node * node, struct rb_node * parent, + struct rb_node ** rb_link) +{ + node->rb_parent_color = (unsigned long )parent; + node->rb_left = node->rb_right = NULL; + + *rb_link = node; +} + +#endif /* _LINUX_RBTREE_H */ diff --git a/tools/perf/util/run-command.c b/tools/perf/util/run-command.c new file mode 100644 index 0000000000000000000000000000000000000000..b2f5e854f40adf807eab34876a2b475bff31cf19 --- /dev/null +++ b/tools/perf/util/run-command.c @@ -0,0 +1,395 @@ +#include "cache.h" +#include "run-command.h" +#include "exec_cmd.h" + +static inline void close_pair(int fd[2]) +{ + close(fd[0]); + close(fd[1]); +} + +static inline void dup_devnull(int to) +{ + int fd = open("/dev/null", O_RDWR); + dup2(fd, to); + close(fd); +} + +int start_command(struct child_process *cmd) +{ + int need_in, need_out, need_err; + int fdin[2], fdout[2], fderr[2]; + + /* + * In case of errors we must keep the promise to close FDs + * that have been passed in via ->in and ->out. + */ + + need_in = !cmd->no_stdin && cmd->in < 0; + if (need_in) { + if (pipe(fdin) < 0) { + if (cmd->out > 0) + close(cmd->out); + return -ERR_RUN_COMMAND_PIPE; + } + cmd->in = fdin[1]; + } + + need_out = !cmd->no_stdout + && !cmd->stdout_to_stderr + && cmd->out < 0; + if (need_out) { + if (pipe(fdout) < 0) { + if (need_in) + close_pair(fdin); + else if (cmd->in) + close(cmd->in); + return -ERR_RUN_COMMAND_PIPE; + } + cmd->out = fdout[0]; + } + + need_err = !cmd->no_stderr && cmd->err < 0; + if (need_err) { + if (pipe(fderr) < 0) { + if (need_in) + close_pair(fdin); + else if (cmd->in) + close(cmd->in); + if (need_out) + close_pair(fdout); + else if (cmd->out) + close(cmd->out); + return -ERR_RUN_COMMAND_PIPE; + } + cmd->err = fderr[0]; + } + +#ifndef __MINGW32__ + fflush(NULL); + cmd->pid = fork(); + if (!cmd->pid) { + if (cmd->no_stdin) + dup_devnull(0); + else if (need_in) { + dup2(fdin[0], 0); + close_pair(fdin); + } else if (cmd->in) { + dup2(cmd->in, 0); + close(cmd->in); + } + + if (cmd->no_stderr) + dup_devnull(2); + else if (need_err) { + dup2(fderr[1], 2); + close_pair(fderr); + } + + if (cmd->no_stdout) + dup_devnull(1); + else if (cmd->stdout_to_stderr) + dup2(2, 1); + else if (need_out) { + dup2(fdout[1], 1); + close_pair(fdout); + } else if (cmd->out > 1) { + dup2(cmd->out, 1); + close(cmd->out); + } + + if (cmd->dir && chdir(cmd->dir)) + die("exec %s: cd to %s failed (%s)", cmd->argv[0], + cmd->dir, strerror(errno)); + if (cmd->env) { + for (; *cmd->env; cmd->env++) { + if (strchr(*cmd->env, '=')) + putenv((char*)*cmd->env); + else + unsetenv(*cmd->env); + } + } + if (cmd->preexec_cb) + cmd->preexec_cb(); + if (cmd->perf_cmd) { + execv_perf_cmd(cmd->argv); + } else { + execvp(cmd->argv[0], (char *const*) cmd->argv); + } + exit(127); + } +#else + int s0 = -1, s1 = -1, s2 = -1; /* backups of stdin, stdout, stderr */ + const char **sargv = cmd->argv; + char **env = environ; + + if (cmd->no_stdin) { + s0 = dup(0); + dup_devnull(0); + } else if (need_in) { + s0 = dup(0); + dup2(fdin[0], 0); + } else if (cmd->in) { + s0 = dup(0); + dup2(cmd->in, 0); + } + + if (cmd->no_stderr) { + s2 = dup(2); + dup_devnull(2); + } else if (need_err) { + s2 = dup(2); + dup2(fderr[1], 2); + } + + if (cmd->no_stdout) { + s1 = dup(1); + dup_devnull(1); + } else if (cmd->stdout_to_stderr) { + s1 = dup(1); + dup2(2, 1); + } else if (need_out) { + s1 = dup(1); + dup2(fdout[1], 1); + } else if (cmd->out > 1) { + s1 = dup(1); + dup2(cmd->out, 1); + } + + if (cmd->dir) + die("chdir in start_command() not implemented"); + if (cmd->env) { + env = copy_environ(); + for (; *cmd->env; cmd->env++) + env = env_setenv(env, *cmd->env); + } + + if (cmd->perf_cmd) { + cmd->argv = prepare_perf_cmd(cmd->argv); + } + + cmd->pid = mingw_spawnvpe(cmd->argv[0], cmd->argv, env); + + if (cmd->env) + free_environ(env); + if (cmd->perf_cmd) + free(cmd->argv); + + cmd->argv = sargv; + if (s0 >= 0) + dup2(s0, 0), close(s0); + if (s1 >= 0) + dup2(s1, 1), close(s1); + if (s2 >= 0) + dup2(s2, 2), close(s2); +#endif + + if (cmd->pid < 0) { + int err = errno; + if (need_in) + close_pair(fdin); + else if (cmd->in) + close(cmd->in); + if (need_out) + close_pair(fdout); + else if (cmd->out) + close(cmd->out); + if (need_err) + close_pair(fderr); + return err == ENOENT ? + -ERR_RUN_COMMAND_EXEC : + -ERR_RUN_COMMAND_FORK; + } + + if (need_in) + close(fdin[0]); + else if (cmd->in) + close(cmd->in); + + if (need_out) + close(fdout[1]); + else if (cmd->out) + close(cmd->out); + + if (need_err) + close(fderr[1]); + + return 0; +} + +static int wait_or_whine(pid_t pid) +{ + for (;;) { + int status, code; + pid_t waiting = waitpid(pid, &status, 0); + + if (waiting < 0) { + if (errno == EINTR) + continue; + error("waitpid failed (%s)", strerror(errno)); + return -ERR_RUN_COMMAND_WAITPID; + } + if (waiting != pid) + return -ERR_RUN_COMMAND_WAITPID_WRONG_PID; + if (WIFSIGNALED(status)) + return -ERR_RUN_COMMAND_WAITPID_SIGNAL; + + if (!WIFEXITED(status)) + return -ERR_RUN_COMMAND_WAITPID_NOEXIT; + code = WEXITSTATUS(status); + switch (code) { + case 127: + return -ERR_RUN_COMMAND_EXEC; + case 0: + return 0; + default: + return -code; + } + } +} + +int finish_command(struct child_process *cmd) +{ + return wait_or_whine(cmd->pid); +} + +int run_command(struct child_process *cmd) +{ + int code = start_command(cmd); + if (code) + return code; + return finish_command(cmd); +} + +static void prepare_run_command_v_opt(struct child_process *cmd, + const char **argv, + int opt) +{ + memset(cmd, 0, sizeof(*cmd)); + cmd->argv = argv; + cmd->no_stdin = opt & RUN_COMMAND_NO_STDIN ? 1 : 0; + cmd->perf_cmd = opt & RUN_PERF_CMD ? 1 : 0; + cmd->stdout_to_stderr = opt & RUN_COMMAND_STDOUT_TO_STDERR ? 1 : 0; +} + +int run_command_v_opt(const char **argv, int opt) +{ + struct child_process cmd; + prepare_run_command_v_opt(&cmd, argv, opt); + return run_command(&cmd); +} + +int run_command_v_opt_cd_env(const char **argv, int opt, const char *dir, const char *const *env) +{ + struct child_process cmd; + prepare_run_command_v_opt(&cmd, argv, opt); + cmd.dir = dir; + cmd.env = env; + return run_command(&cmd); +} + +#ifdef __MINGW32__ +static __stdcall unsigned run_thread(void *data) +{ + struct async *async = data; + return async->proc(async->fd_for_proc, async->data); +} +#endif + +int start_async(struct async *async) +{ + int pipe_out[2]; + + if (pipe(pipe_out) < 0) + return error("cannot create pipe: %s", strerror(errno)); + async->out = pipe_out[0]; + +#ifndef __MINGW32__ + /* Flush stdio before fork() to avoid cloning buffers */ + fflush(NULL); + + async->pid = fork(); + if (async->pid < 0) { + error("fork (async) failed: %s", strerror(errno)); + close_pair(pipe_out); + return -1; + } + if (!async->pid) { + close(pipe_out[0]); + exit(!!async->proc(pipe_out[1], async->data)); + } + close(pipe_out[1]); +#else + async->fd_for_proc = pipe_out[1]; + async->tid = (HANDLE) _beginthreadex(NULL, 0, run_thread, async, 0, NULL); + if (!async->tid) { + error("cannot create thread: %s", strerror(errno)); + close_pair(pipe_out); + return -1; + } +#endif + return 0; +} + +int finish_async(struct async *async) +{ +#ifndef __MINGW32__ + int ret = 0; + + if (wait_or_whine(async->pid)) + ret = error("waitpid (async) failed"); +#else + DWORD ret = 0; + if (WaitForSingleObject(async->tid, INFINITE) != WAIT_OBJECT_0) + ret = error("waiting for thread failed: %lu", GetLastError()); + else if (!GetExitCodeThread(async->tid, &ret)) + ret = error("cannot get thread exit code: %lu", GetLastError()); + CloseHandle(async->tid); +#endif + return ret; +} + +int run_hook(const char *index_file, const char *name, ...) +{ + struct child_process hook; + const char **argv = NULL, *env[2]; + char index[PATH_MAX]; + va_list args; + int ret; + size_t i = 0, alloc = 0; + + if (access(perf_path("hooks/%s", name), X_OK) < 0) + return 0; + + va_start(args, name); + ALLOC_GROW(argv, i + 1, alloc); + argv[i++] = perf_path("hooks/%s", name); + while (argv[i-1]) { + ALLOC_GROW(argv, i + 1, alloc); + argv[i++] = va_arg(args, const char *); + } + va_end(args); + + memset(&hook, 0, sizeof(hook)); + hook.argv = argv; + hook.no_stdin = 1; + hook.stdout_to_stderr = 1; + if (index_file) { + snprintf(index, sizeof(index), "PERF_INDEX_FILE=%s", index_file); + env[0] = index; + env[1] = NULL; + hook.env = env; + } + + ret = start_command(&hook); + free(argv); + if (ret) { + warning("Could not spawn %s", argv[0]); + return ret; + } + ret = finish_command(&hook); + if (ret == -ERR_RUN_COMMAND_WAITPID_SIGNAL) + warning("%s exited due to uncaught signal", argv[0]); + + return ret; +} diff --git a/tools/perf/util/run-command.h b/tools/perf/util/run-command.h new file mode 100644 index 0000000000000000000000000000000000000000..328289f236695fc909375378090f2783965d5582 --- /dev/null +++ b/tools/perf/util/run-command.h @@ -0,0 +1,93 @@ +#ifndef RUN_COMMAND_H +#define RUN_COMMAND_H + +enum { + ERR_RUN_COMMAND_FORK = 10000, + ERR_RUN_COMMAND_EXEC, + ERR_RUN_COMMAND_PIPE, + ERR_RUN_COMMAND_WAITPID, + ERR_RUN_COMMAND_WAITPID_WRONG_PID, + ERR_RUN_COMMAND_WAITPID_SIGNAL, + ERR_RUN_COMMAND_WAITPID_NOEXIT, +}; +#define IS_RUN_COMMAND_ERR(x) (-(x) >= ERR_RUN_COMMAND_FORK) + +struct child_process { + const char **argv; + pid_t pid; + /* + * Using .in, .out, .err: + * - Specify 0 for no redirections (child inherits stdin, stdout, + * stderr from parent). + * - Specify -1 to have a pipe allocated as follows: + * .in: returns the writable pipe end; parent writes to it, + * the readable pipe end becomes child's stdin + * .out, .err: returns the readable pipe end; parent reads from + * it, the writable pipe end becomes child's stdout/stderr + * The caller of start_command() must close the returned FDs + * after it has completed reading from/writing to it! + * - Specify > 0 to set a channel to a particular FD as follows: + * .in: a readable FD, becomes child's stdin + * .out: a writable FD, becomes child's stdout/stderr + * .err > 0 not supported + * The specified FD is closed by start_command(), even in case + * of errors! + */ + int in; + int out; + int err; + const char *dir; + const char *const *env; + unsigned no_stdin:1; + unsigned no_stdout:1; + unsigned no_stderr:1; + unsigned perf_cmd:1; /* if this is to be perf sub-command */ + unsigned stdout_to_stderr:1; + void (*preexec_cb)(void); +}; + +int start_command(struct child_process *); +int finish_command(struct child_process *); +int run_command(struct child_process *); + +extern int run_hook(const char *index_file, const char *name, ...); + +#define RUN_COMMAND_NO_STDIN 1 +#define RUN_PERF_CMD 2 /*If this is to be perf sub-command */ +#define RUN_COMMAND_STDOUT_TO_STDERR 4 +int run_command_v_opt(const char **argv, int opt); + +/* + * env (the environment) is to be formatted like environ: "VAR=VALUE". + * To unset an environment variable use just "VAR". + */ +int run_command_v_opt_cd_env(const char **argv, int opt, const char *dir, const char *const *env); + +/* + * The purpose of the following functions is to feed a pipe by running + * a function asynchronously and providing output that the caller reads. + * + * It is expected that no synchronization and mutual exclusion between + * the caller and the feed function is necessary so that the function + * can run in a thread without interfering with the caller. + */ +struct async { + /* + * proc writes to fd and closes it; + * returns 0 on success, non-zero on failure + */ + int (*proc)(int fd, void *data); + void *data; + int out; /* caller reads from here and closes it */ +#ifndef __MINGW32__ + pid_t pid; +#else + HANDLE tid; + int fd_for_proc; +#endif +}; + +int start_async(struct async *async); +int finish_async(struct async *async); + +#endif diff --git a/tools/perf/util/sigchain.c b/tools/perf/util/sigchain.c new file mode 100644 index 0000000000000000000000000000000000000000..1118b99e57d3308f333c56f487329a8fef75a7df --- /dev/null +++ b/tools/perf/util/sigchain.c @@ -0,0 +1,52 @@ +#include "sigchain.h" +#include "cache.h" + +#define SIGCHAIN_MAX_SIGNALS 32 + +struct sigchain_signal { + sigchain_fun *old; + int n; + int alloc; +}; +static struct sigchain_signal signals[SIGCHAIN_MAX_SIGNALS]; + +static void check_signum(int sig) +{ + if (sig < 1 || sig >= SIGCHAIN_MAX_SIGNALS) + die("BUG: signal out of range: %d", sig); +} + +int sigchain_push(int sig, sigchain_fun f) +{ + struct sigchain_signal *s = signals + sig; + check_signum(sig); + + ALLOC_GROW(s->old, s->n + 1, s->alloc); + s->old[s->n] = signal(sig, f); + if (s->old[s->n] == SIG_ERR) + return -1; + s->n++; + return 0; +} + +int sigchain_pop(int sig) +{ + struct sigchain_signal *s = signals + sig; + check_signum(sig); + if (s->n < 1) + return 0; + + if (signal(sig, s->old[s->n - 1]) == SIG_ERR) + return -1; + s->n--; + return 0; +} + +void sigchain_push_common(sigchain_fun f) +{ + sigchain_push(SIGINT, f); + sigchain_push(SIGHUP, f); + sigchain_push(SIGTERM, f); + sigchain_push(SIGQUIT, f); + sigchain_push(SIGPIPE, f); +} diff --git a/tools/perf/util/sigchain.h b/tools/perf/util/sigchain.h new file mode 100644 index 0000000000000000000000000000000000000000..618083bce0c66a551fd4d894b31520a67b25bac9 --- /dev/null +++ b/tools/perf/util/sigchain.h @@ -0,0 +1,11 @@ +#ifndef SIGCHAIN_H +#define SIGCHAIN_H + +typedef void (*sigchain_fun)(int); + +int sigchain_push(int sig, sigchain_fun f); +int sigchain_pop(int sig); + +void sigchain_push_common(sigchain_fun f); + +#endif /* SIGCHAIN_H */ diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c new file mode 100644 index 0000000000000000000000000000000000000000..eaba0930680233a6f682c2d7710a2eb7fa9daac8 --- /dev/null +++ b/tools/perf/util/strbuf.c @@ -0,0 +1,359 @@ +#include "cache.h" + +int prefixcmp(const char *str, const char *prefix) +{ + for (; ; str++, prefix++) + if (!*prefix) + return 0; + else if (*str != *prefix) + return (unsigned char)*prefix - (unsigned char)*str; +} + +/* + * Used as the default ->buf value, so that people can always assume + * buf is non NULL and ->buf is NUL terminated even for a freshly + * initialized strbuf. + */ +char strbuf_slopbuf[1]; + +void strbuf_init(struct strbuf *sb, size_t hint) +{ + sb->alloc = sb->len = 0; + sb->buf = strbuf_slopbuf; + if (hint) + strbuf_grow(sb, hint); +} + +void strbuf_release(struct strbuf *sb) +{ + if (sb->alloc) { + free(sb->buf); + strbuf_init(sb, 0); + } +} + +char *strbuf_detach(struct strbuf *sb, size_t *sz) +{ + char *res = sb->alloc ? sb->buf : NULL; + if (sz) + *sz = sb->len; + strbuf_init(sb, 0); + return res; +} + +void strbuf_attach(struct strbuf *sb, void *buf, size_t len, size_t alloc) +{ + strbuf_release(sb); + sb->buf = buf; + sb->len = len; + sb->alloc = alloc; + strbuf_grow(sb, 0); + sb->buf[sb->len] = '\0'; +} + +void strbuf_grow(struct strbuf *sb, size_t extra) +{ + if (sb->len + extra + 1 <= sb->len) + die("you want to use way too much memory"); + if (!sb->alloc) + sb->buf = NULL; + ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc); +} + +void strbuf_trim(struct strbuf *sb) +{ + char *b = sb->buf; + while (sb->len > 0 && isspace((unsigned char)sb->buf[sb->len - 1])) + sb->len--; + while (sb->len > 0 && isspace(*b)) { + b++; + sb->len--; + } + memmove(sb->buf, b, sb->len); + sb->buf[sb->len] = '\0'; +} +void strbuf_rtrim(struct strbuf *sb) +{ + while (sb->len > 0 && isspace((unsigned char)sb->buf[sb->len - 1])) + sb->len--; + sb->buf[sb->len] = '\0'; +} + +void strbuf_ltrim(struct strbuf *sb) +{ + char *b = sb->buf; + while (sb->len > 0 && isspace(*b)) { + b++; + sb->len--; + } + memmove(sb->buf, b, sb->len); + sb->buf[sb->len] = '\0'; +} + +void strbuf_tolower(struct strbuf *sb) +{ + int i; + for (i = 0; i < sb->len; i++) + sb->buf[i] = tolower(sb->buf[i]); +} + +struct strbuf **strbuf_split(const struct strbuf *sb, int delim) +{ + int alloc = 2, pos = 0; + char *n, *p; + struct strbuf **ret; + struct strbuf *t; + + ret = calloc(alloc, sizeof(struct strbuf *)); + p = n = sb->buf; + while (n < sb->buf + sb->len) { + int len; + n = memchr(n, delim, sb->len - (n - sb->buf)); + if (pos + 1 >= alloc) { + alloc = alloc * 2; + ret = realloc(ret, sizeof(struct strbuf *) * alloc); + } + if (!n) + n = sb->buf + sb->len - 1; + len = n - p + 1; + t = malloc(sizeof(struct strbuf)); + strbuf_init(t, len); + strbuf_add(t, p, len); + ret[pos] = t; + ret[++pos] = NULL; + p = ++n; + } + return ret; +} + +void strbuf_list_free(struct strbuf **sbs) +{ + struct strbuf **s = sbs; + + while (*s) { + strbuf_release(*s); + free(*s++); + } + free(sbs); +} + +int strbuf_cmp(const struct strbuf *a, const struct strbuf *b) +{ + int len = a->len < b->len ? a->len: b->len; + int cmp = memcmp(a->buf, b->buf, len); + if (cmp) + return cmp; + return a->len < b->len ? -1: a->len != b->len; +} + +void strbuf_splice(struct strbuf *sb, size_t pos, size_t len, + const void *data, size_t dlen) +{ + if (pos + len < pos) + die("you want to use way too much memory"); + if (pos > sb->len) + die("`pos' is too far after the end of the buffer"); + if (pos + len > sb->len) + die("`pos + len' is too far after the end of the buffer"); + + if (dlen >= len) + strbuf_grow(sb, dlen - len); + memmove(sb->buf + pos + dlen, + sb->buf + pos + len, + sb->len - pos - len); + memcpy(sb->buf + pos, data, dlen); + strbuf_setlen(sb, sb->len + dlen - len); +} + +void strbuf_insert(struct strbuf *sb, size_t pos, const void *data, size_t len) +{ + strbuf_splice(sb, pos, 0, data, len); +} + +void strbuf_remove(struct strbuf *sb, size_t pos, size_t len) +{ + strbuf_splice(sb, pos, len, NULL, 0); +} + +void strbuf_add(struct strbuf *sb, const void *data, size_t len) +{ + strbuf_grow(sb, len); + memcpy(sb->buf + sb->len, data, len); + strbuf_setlen(sb, sb->len + len); +} + +void strbuf_adddup(struct strbuf *sb, size_t pos, size_t len) +{ + strbuf_grow(sb, len); + memcpy(sb->buf + sb->len, sb->buf + pos, len); + strbuf_setlen(sb, sb->len + len); +} + +void strbuf_addf(struct strbuf *sb, const char *fmt, ...) +{ + int len; + va_list ap; + + if (!strbuf_avail(sb)) + strbuf_grow(sb, 64); + va_start(ap, fmt); + len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); + va_end(ap); + if (len < 0) + die("your vsnprintf is broken"); + if (len > strbuf_avail(sb)) { + strbuf_grow(sb, len); + va_start(ap, fmt); + len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); + va_end(ap); + if (len > strbuf_avail(sb)) { + die("this should not happen, your snprintf is broken"); + } + } + strbuf_setlen(sb, sb->len + len); +} + +void strbuf_expand(struct strbuf *sb, const char *format, expand_fn_t fn, + void *context) +{ + for (;;) { + const char *percent; + size_t consumed; + + percent = strchrnul(format, '%'); + strbuf_add(sb, format, percent - format); + if (!*percent) + break; + format = percent + 1; + + consumed = fn(sb, format, context); + if (consumed) + format += consumed; + else + strbuf_addch(sb, '%'); + } +} + +size_t strbuf_expand_dict_cb(struct strbuf *sb, const char *placeholder, + void *context) +{ + struct strbuf_expand_dict_entry *e = context; + size_t len; + + for (; e->placeholder && (len = strlen(e->placeholder)); e++) { + if (!strncmp(placeholder, e->placeholder, len)) { + if (e->value) + strbuf_addstr(sb, e->value); + return len; + } + } + return 0; +} + +size_t strbuf_fread(struct strbuf *sb, size_t size, FILE *f) +{ + size_t res; + size_t oldalloc = sb->alloc; + + strbuf_grow(sb, size); + res = fread(sb->buf + sb->len, 1, size, f); + if (res > 0) + strbuf_setlen(sb, sb->len + res); + else if (res < 0 && oldalloc == 0) + strbuf_release(sb); + return res; +} + +ssize_t strbuf_read(struct strbuf *sb, int fd, size_t hint) +{ + size_t oldlen = sb->len; + size_t oldalloc = sb->alloc; + + strbuf_grow(sb, hint ? hint : 8192); + for (;;) { + ssize_t cnt; + + cnt = read(fd, sb->buf + sb->len, sb->alloc - sb->len - 1); + if (cnt < 0) { + if (oldalloc == 0) + strbuf_release(sb); + else + strbuf_setlen(sb, oldlen); + return -1; + } + if (!cnt) + break; + sb->len += cnt; + strbuf_grow(sb, 8192); + } + + sb->buf[sb->len] = '\0'; + return sb->len - oldlen; +} + +#define STRBUF_MAXLINK (2*PATH_MAX) + +int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint) +{ + size_t oldalloc = sb->alloc; + + if (hint < 32) + hint = 32; + + while (hint < STRBUF_MAXLINK) { + int len; + + strbuf_grow(sb, hint); + len = readlink(path, sb->buf, hint); + if (len < 0) { + if (errno != ERANGE) + break; + } else if (len < hint) { + strbuf_setlen(sb, len); + return 0; + } + + /* .. the buffer was too small - try again */ + hint *= 2; + } + if (oldalloc == 0) + strbuf_release(sb); + return -1; +} + +int strbuf_getline(struct strbuf *sb, FILE *fp, int term) +{ + int ch; + + strbuf_grow(sb, 0); + if (feof(fp)) + return EOF; + + strbuf_reset(sb); + while ((ch = fgetc(fp)) != EOF) { + if (ch == term) + break; + strbuf_grow(sb, 1); + sb->buf[sb->len++] = ch; + } + if (ch == EOF && sb->len == 0) + return EOF; + + sb->buf[sb->len] = '\0'; + return 0; +} + +int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint) +{ + int fd, len; + + fd = open(path, O_RDONLY); + if (fd < 0) + return -1; + len = strbuf_read(sb, fd, hint); + close(fd); + if (len < 0) + return -1; + + return len; +} diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h new file mode 100644 index 0000000000000000000000000000000000000000..9ee908a3ec5d4d5329385bc10cdd676f703c0c1f --- /dev/null +++ b/tools/perf/util/strbuf.h @@ -0,0 +1,137 @@ +#ifndef STRBUF_H +#define STRBUF_H + +/* + * Strbuf's can be use in many ways: as a byte array, or to store arbitrary + * long, overflow safe strings. + * + * Strbufs has some invariants that are very important to keep in mind: + * + * 1. the ->buf member is always malloc-ed, hence strbuf's can be used to + * build complex strings/buffers whose final size isn't easily known. + * + * It is NOT legal to copy the ->buf pointer away. + * `strbuf_detach' is the operation that detachs a buffer from its shell + * while keeping the shell valid wrt its invariants. + * + * 2. the ->buf member is a byte array that has at least ->len + 1 bytes + * allocated. The extra byte is used to store a '\0', allowing the ->buf + * member to be a valid C-string. Every strbuf function ensure this + * invariant is preserved. + * + * Note that it is OK to "play" with the buffer directly if you work it + * that way: + * + * strbuf_grow(sb, SOME_SIZE); + * ... Here, the memory array starting at sb->buf, and of length + * ... strbuf_avail(sb) is all yours, and you are sure that + * ... strbuf_avail(sb) is at least SOME_SIZE. + * strbuf_setlen(sb, sb->len + SOME_OTHER_SIZE); + * + * Of course, SOME_OTHER_SIZE must be smaller or equal to strbuf_avail(sb). + * + * Doing so is safe, though if it has to be done in many places, adding the + * missing API to the strbuf module is the way to go. + * + * XXX: do _not_ assume that the area that is yours is of size ->alloc - 1 + * even if it's true in the current implementation. Alloc is somehow a + * "private" member that should not be messed with. + */ + +#include + +extern char strbuf_slopbuf[]; +struct strbuf { + size_t alloc; + size_t len; + char *buf; +}; + +#define STRBUF_INIT { 0, 0, strbuf_slopbuf } + +/*----- strbuf life cycle -----*/ +extern void strbuf_init(struct strbuf *, size_t); +extern void strbuf_release(struct strbuf *); +extern char *strbuf_detach(struct strbuf *, size_t *); +extern void strbuf_attach(struct strbuf *, void *, size_t, size_t); +static inline void strbuf_swap(struct strbuf *a, struct strbuf *b) { + struct strbuf tmp = *a; + *a = *b; + *b = tmp; +} + +/*----- strbuf size related -----*/ +static inline size_t strbuf_avail(const struct strbuf *sb) { + return sb->alloc ? sb->alloc - sb->len - 1 : 0; +} + +extern void strbuf_grow(struct strbuf *, size_t); + +static inline void strbuf_setlen(struct strbuf *sb, size_t len) { + if (!sb->alloc) + strbuf_grow(sb, 0); + assert(len < sb->alloc); + sb->len = len; + sb->buf[len] = '\0'; +} +#define strbuf_reset(sb) strbuf_setlen(sb, 0) + +/*----- content related -----*/ +extern void strbuf_trim(struct strbuf *); +extern void strbuf_rtrim(struct strbuf *); +extern void strbuf_ltrim(struct strbuf *); +extern int strbuf_cmp(const struct strbuf *, const struct strbuf *); +extern void strbuf_tolower(struct strbuf *); + +extern struct strbuf **strbuf_split(const struct strbuf *, int delim); +extern void strbuf_list_free(struct strbuf **); + +/*----- add data in your buffer -----*/ +static inline void strbuf_addch(struct strbuf *sb, int c) { + strbuf_grow(sb, 1); + sb->buf[sb->len++] = c; + sb->buf[sb->len] = '\0'; +} + +extern void strbuf_insert(struct strbuf *, size_t pos, const void *, size_t); +extern void strbuf_remove(struct strbuf *, size_t pos, size_t len); + +/* splice pos..pos+len with given data */ +extern void strbuf_splice(struct strbuf *, size_t pos, size_t len, + const void *, size_t); + +extern void strbuf_add(struct strbuf *, const void *, size_t); +static inline void strbuf_addstr(struct strbuf *sb, const char *s) { + strbuf_add(sb, s, strlen(s)); +} +static inline void strbuf_addbuf(struct strbuf *sb, const struct strbuf *sb2) { + strbuf_add(sb, sb2->buf, sb2->len); +} +extern void strbuf_adddup(struct strbuf *sb, size_t pos, size_t len); + +typedef size_t (*expand_fn_t) (struct strbuf *sb, const char *placeholder, void *context); +extern void strbuf_expand(struct strbuf *sb, const char *format, expand_fn_t fn, void *context); +struct strbuf_expand_dict_entry { + const char *placeholder; + const char *value; +}; +extern size_t strbuf_expand_dict_cb(struct strbuf *sb, const char *placeholder, void *context); + +__attribute__((format(printf,2,3))) +extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...); + +extern size_t strbuf_fread(struct strbuf *, size_t, FILE *); +/* XXX: if read fails, any partial read is undone */ +extern ssize_t strbuf_read(struct strbuf *, int fd, size_t hint); +extern int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint); +extern int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint); + +extern int strbuf_getline(struct strbuf *, FILE *, int); + +extern void stripspace(struct strbuf *buf, int skip_comments); +extern int launch_editor(const char *path, struct strbuf *buffer, const char *const *env); + +extern int strbuf_branchname(struct strbuf *sb, const char *name); +extern int strbuf_check_branch_ref(struct strbuf *sb, const char *name); + +#endif /* STRBUF_H */ diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c new file mode 100644 index 0000000000000000000000000000000000000000..ec33c0c7f4e2de2e3b6e7cc4dc4fc5910a2f3296 --- /dev/null +++ b/tools/perf/util/string.c @@ -0,0 +1,34 @@ +#include "string.h" + +static int hex(char ch) +{ + if ((ch >= '0') && (ch <= '9')) + return ch - '0'; + if ((ch >= 'a') && (ch <= 'f')) + return ch - 'a' + 10; + if ((ch >= 'A') && (ch <= 'F')) + return ch - 'A' + 10; + return -1; +} + +/* + * While we find nice hex chars, build a long_val. + * Return number of chars processed. + */ +int hex2u64(const char *ptr, __u64 *long_val) +{ + const char *p = ptr; + *long_val = 0; + + while (*p) { + const int hex_val = hex(*p); + + if (hex_val < 0) + break; + + *long_val = (*long_val << 4) | hex_val; + p++; + } + + return p - ptr; +} diff --git a/tools/perf/util/string.h b/tools/perf/util/string.h new file mode 100644 index 0000000000000000000000000000000000000000..72812c1c9a7a2cabd3e54c6066cc22db287ed376 --- /dev/null +++ b/tools/perf/util/string.h @@ -0,0 +1,8 @@ +#ifndef _PERF_STRING_H_ +#define _PERF_STRING_H_ + +#include + +int hex2u64(const char *ptr, __u64 *val); + +#endif diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c new file mode 100644 index 0000000000000000000000000000000000000000..49a55f81371218b4250845c5a073dbb2e27100d9 --- /dev/null +++ b/tools/perf/util/symbol.c @@ -0,0 +1,641 @@ +#include "util.h" +#include "../perf.h" +#include "string.h" +#include "symbol.h" + +#include +#include +#include + +const char *sym_hist_filter; + +static struct symbol *symbol__new(__u64 start, __u64 len, + const char *name, unsigned int priv_size, + __u64 obj_start, int verbose) +{ + size_t namelen = strlen(name) + 1; + struct symbol *self = calloc(1, priv_size + sizeof(*self) + namelen); + + if (!self) + return NULL; + + if (verbose >= 2) + printf("new symbol: %016Lx [%08lx]: %s, hist: %p, obj_start: %p\n", + (__u64)start, (unsigned long)len, name, self->hist, (void *)(unsigned long)obj_start); + + self->obj_start= obj_start; + self->hist = NULL; + self->hist_sum = 0; + + if (sym_hist_filter && !strcmp(name, sym_hist_filter)) + self->hist = calloc(sizeof(__u64), len); + + if (priv_size) { + memset(self, 0, priv_size); + self = ((void *)self) + priv_size; + } + self->start = start; + self->end = start + len - 1; + memcpy(self->name, name, namelen); + + return self; +} + +static void symbol__delete(struct symbol *self, unsigned int priv_size) +{ + free(((void *)self) - priv_size); +} + +static size_t symbol__fprintf(struct symbol *self, FILE *fp) +{ + return fprintf(fp, " %llx-%llx %s\n", + self->start, self->end, self->name); +} + +struct dso *dso__new(const char *name, unsigned int sym_priv_size) +{ + struct dso *self = malloc(sizeof(*self) + strlen(name) + 1); + + if (self != NULL) { + strcpy(self->name, name); + self->syms = RB_ROOT; + self->sym_priv_size = sym_priv_size; + self->find_symbol = dso__find_symbol; + } + + return self; +} + +static void dso__delete_symbols(struct dso *self) +{ + struct symbol *pos; + struct rb_node *next = rb_first(&self->syms); + + while (next) { + pos = rb_entry(next, struct symbol, rb_node); + next = rb_next(&pos->rb_node); + rb_erase(&pos->rb_node, &self->syms); + symbol__delete(pos, self->sym_priv_size); + } +} + +void dso__delete(struct dso *self) +{ + dso__delete_symbols(self); + free(self); +} + +static void dso__insert_symbol(struct dso *self, struct symbol *sym) +{ + struct rb_node **p = &self->syms.rb_node; + struct rb_node *parent = NULL; + const __u64 ip = sym->start; + struct symbol *s; + + while (*p != NULL) { + parent = *p; + s = rb_entry(parent, struct symbol, rb_node); + if (ip < s->start) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&sym->rb_node, parent, p); + rb_insert_color(&sym->rb_node, &self->syms); +} + +struct symbol *dso__find_symbol(struct dso *self, __u64 ip) +{ + struct rb_node *n; + + if (self == NULL) + return NULL; + + n = self->syms.rb_node; + + while (n) { + struct symbol *s = rb_entry(n, struct symbol, rb_node); + + if (ip < s->start) + n = n->rb_left; + else if (ip > s->end) + n = n->rb_right; + else + return s; + } + + return NULL; +} + +size_t dso__fprintf(struct dso *self, FILE *fp) +{ + size_t ret = fprintf(fp, "dso: %s\n", self->name); + + struct rb_node *nd; + for (nd = rb_first(&self->syms); nd; nd = rb_next(nd)) { + struct symbol *pos = rb_entry(nd, struct symbol, rb_node); + ret += symbol__fprintf(pos, fp); + } + + return ret; +} + +static int dso__load_kallsyms(struct dso *self, symbol_filter_t filter, int verbose) +{ + struct rb_node *nd, *prevnd; + char *line = NULL; + size_t n; + FILE *file = fopen("/proc/kallsyms", "r"); + + if (file == NULL) + goto out_failure; + + while (!feof(file)) { + __u64 start; + struct symbol *sym; + int line_len, len; + char symbol_type; + + line_len = getline(&line, &n, file); + if (line_len < 0) + break; + + if (!line) + goto out_failure; + + line[--line_len] = '\0'; /* \n */ + + len = hex2u64(line, &start); + + len++; + if (len + 2 >= line_len) + continue; + + symbol_type = toupper(line[len]); + /* + * We're interested only in code ('T'ext) + */ + if (symbol_type != 'T' && symbol_type != 'W') + continue; + /* + * Well fix up the end later, when we have all sorted. + */ + sym = symbol__new(start, 0xdead, line + len + 2, + self->sym_priv_size, 0, verbose); + + if (sym == NULL) + goto out_delete_line; + + if (filter && filter(self, sym)) + symbol__delete(sym, self->sym_priv_size); + else + dso__insert_symbol(self, sym); + } + + /* + * Now that we have all sorted out, just set the ->end of all + * symbols + */ + prevnd = rb_first(&self->syms); + + if (prevnd == NULL) + goto out_delete_line; + + for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) { + struct symbol *prev = rb_entry(prevnd, struct symbol, rb_node), + *curr = rb_entry(nd, struct symbol, rb_node); + + prev->end = curr->start - 1; + prevnd = nd; + } + + free(line); + fclose(file); + + return 0; + +out_delete_line: + free(line); +out_failure: + return -1; +} + +static int dso__load_perf_map(struct dso *self, symbol_filter_t filter, int verbose) +{ + char *line = NULL; + size_t n; + FILE *file; + int nr_syms = 0; + + file = fopen(self->name, "r"); + if (file == NULL) + goto out_failure; + + while (!feof(file)) { + __u64 start, size; + struct symbol *sym; + int line_len, len; + + line_len = getline(&line, &n, file); + if (line_len < 0) + break; + + if (!line) + goto out_failure; + + line[--line_len] = '\0'; /* \n */ + + len = hex2u64(line, &start); + + len++; + if (len + 2 >= line_len) + continue; + + len += hex2u64(line + len, &size); + + len++; + if (len + 2 >= line_len) + continue; + + sym = symbol__new(start, size, line + len, + self->sym_priv_size, start, verbose); + + if (sym == NULL) + goto out_delete_line; + + if (filter && filter(self, sym)) + symbol__delete(sym, self->sym_priv_size); + else { + dso__insert_symbol(self, sym); + nr_syms++; + } + } + + free(line); + fclose(file); + + return nr_syms; + +out_delete_line: + free(line); +out_failure: + return -1; +} + +/** + * elf_symtab__for_each_symbol - iterate thru all the symbols + * + * @self: struct elf_symtab instance to iterate + * @index: uint32_t index + * @sym: GElf_Sym iterator + */ +#define elf_symtab__for_each_symbol(syms, nr_syms, index, sym) \ + for (index = 0, gelf_getsym(syms, index, &sym);\ + index < nr_syms; \ + index++, gelf_getsym(syms, index, &sym)) + +static inline uint8_t elf_sym__type(const GElf_Sym *sym) +{ + return GELF_ST_TYPE(sym->st_info); +} + +static inline int elf_sym__is_function(const GElf_Sym *sym) +{ + return elf_sym__type(sym) == STT_FUNC && + sym->st_name != 0 && + sym->st_shndx != SHN_UNDEF && + sym->st_size != 0; +} + +static inline const char *elf_sym__name(const GElf_Sym *sym, + const Elf_Data *symstrs) +{ + return symstrs->d_buf + sym->st_name; +} + +static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, + GElf_Shdr *shp, const char *name, + size_t *index) +{ + Elf_Scn *sec = NULL; + size_t cnt = 1; + + while ((sec = elf_nextscn(elf, sec)) != NULL) { + char *str; + + gelf_getshdr(sec, shp); + str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name); + if (!strcmp(name, str)) { + if (index) + *index = cnt; + break; + } + ++cnt; + } + + return sec; +} + +#define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \ + for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \ + idx < nr_entries; \ + ++idx, pos = gelf_getrel(reldata, idx, &pos_mem)) + +#define elf_section__for_each_rela(reldata, pos, pos_mem, idx, nr_entries) \ + for (idx = 0, pos = gelf_getrela(reldata, 0, &pos_mem); \ + idx < nr_entries; \ + ++idx, pos = gelf_getrela(reldata, idx, &pos_mem)) + +static int dso__synthesize_plt_symbols(struct dso *self, Elf *elf, + GElf_Ehdr *ehdr, Elf_Scn *scn_dynsym, + GElf_Shdr *shdr_dynsym, + size_t dynsym_idx, int verbose) +{ + uint32_t nr_rel_entries, idx; + GElf_Sym sym; + __u64 plt_offset; + GElf_Shdr shdr_plt; + struct symbol *f; + GElf_Shdr shdr_rel_plt; + Elf_Data *reldata, *syms, *symstrs; + Elf_Scn *scn_plt_rel, *scn_symstrs; + char sympltname[1024]; + int nr = 0, symidx; + + scn_plt_rel = elf_section_by_name(elf, ehdr, &shdr_rel_plt, + ".rela.plt", NULL); + if (scn_plt_rel == NULL) { + scn_plt_rel = elf_section_by_name(elf, ehdr, &shdr_rel_plt, + ".rel.plt", NULL); + if (scn_plt_rel == NULL) + return 0; + } + + if (shdr_rel_plt.sh_link != dynsym_idx) + return 0; + + if (elf_section_by_name(elf, ehdr, &shdr_plt, ".plt", NULL) == NULL) + return 0; + + /* + * Fetch the relocation section to find the indexes to the GOT + * and the symbols in the .dynsym they refer to. + */ + reldata = elf_getdata(scn_plt_rel, NULL); + if (reldata == NULL) + return -1; + + syms = elf_getdata(scn_dynsym, NULL); + if (syms == NULL) + return -1; + + scn_symstrs = elf_getscn(elf, shdr_dynsym->sh_link); + if (scn_symstrs == NULL) + return -1; + + symstrs = elf_getdata(scn_symstrs, NULL); + if (symstrs == NULL) + return -1; + + nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize; + plt_offset = shdr_plt.sh_offset; + + if (shdr_rel_plt.sh_type == SHT_RELA) { + GElf_Rela pos_mem, *pos; + + elf_section__for_each_rela(reldata, pos, pos_mem, idx, + nr_rel_entries) { + symidx = GELF_R_SYM(pos->r_info); + plt_offset += shdr_plt.sh_entsize; + gelf_getsym(syms, symidx, &sym); + snprintf(sympltname, sizeof(sympltname), + "%s@plt", elf_sym__name(&sym, symstrs)); + + f = symbol__new(plt_offset, shdr_plt.sh_entsize, + sympltname, self->sym_priv_size, 0, verbose); + if (!f) + return -1; + + dso__insert_symbol(self, f); + ++nr; + } + } else if (shdr_rel_plt.sh_type == SHT_REL) { + GElf_Rel pos_mem, *pos; + elf_section__for_each_rel(reldata, pos, pos_mem, idx, + nr_rel_entries) { + symidx = GELF_R_SYM(pos->r_info); + plt_offset += shdr_plt.sh_entsize; + gelf_getsym(syms, symidx, &sym); + snprintf(sympltname, sizeof(sympltname), + "%s@plt", elf_sym__name(&sym, symstrs)); + + f = symbol__new(plt_offset, shdr_plt.sh_entsize, + sympltname, self->sym_priv_size, 0, verbose); + if (!f) + return -1; + + dso__insert_symbol(self, f); + ++nr; + } + } else { + /* + * TODO: There are still one more shdr_rel_plt.sh_type + * I have to investigate, but probably should be ignored. + */ + } + + return nr; +} + +static int dso__load_sym(struct dso *self, int fd, const char *name, + symbol_filter_t filter, int verbose) +{ + Elf_Data *symstrs; + uint32_t nr_syms; + int err = -1; + uint32_t index; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + Elf_Data *syms; + GElf_Sym sym; + Elf_Scn *sec, *sec_dynsym; + Elf *elf; + size_t dynsym_idx; + int nr = 0; + + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (elf == NULL) { + if (verbose) + fprintf(stderr, "%s: cannot read %s ELF file.\n", + __func__, name); + goto out_close; + } + + if (gelf_getehdr(elf, &ehdr) == NULL) { + if (verbose) + fprintf(stderr, "%s: cannot get elf header.\n", __func__); + goto out_elf_end; + } + + /* + * We need to check if we have a .dynsym, so that we can handle the + * .plt, synthesizing its symbols, that aren't on the symtabs (be it + * .dynsym or .symtab) + */ + sec_dynsym = elf_section_by_name(elf, &ehdr, &shdr, + ".dynsym", &dynsym_idx); + if (sec_dynsym != NULL) { + nr = dso__synthesize_plt_symbols(self, elf, &ehdr, + sec_dynsym, &shdr, + dynsym_idx, verbose); + if (nr < 0) + goto out_elf_end; + } + + /* + * But if we have a full .symtab (that is a superset of .dynsym) we + * should add the symbols not in the .dynsyn + */ + sec = elf_section_by_name(elf, &ehdr, &shdr, ".symtab", NULL); + if (sec == NULL) { + if (sec_dynsym == NULL) + goto out_elf_end; + + sec = sec_dynsym; + gelf_getshdr(sec, &shdr); + } + + syms = elf_getdata(sec, NULL); + if (syms == NULL) + goto out_elf_end; + + sec = elf_getscn(elf, shdr.sh_link); + if (sec == NULL) + goto out_elf_end; + + symstrs = elf_getdata(sec, NULL); + if (symstrs == NULL) + goto out_elf_end; + + nr_syms = shdr.sh_size / shdr.sh_entsize; + + memset(&sym, 0, sizeof(sym)); + + elf_symtab__for_each_symbol(syms, nr_syms, index, sym) { + struct symbol *f; + __u64 obj_start; + + if (!elf_sym__is_function(&sym)) + continue; + + sec = elf_getscn(elf, sym.st_shndx); + if (!sec) + goto out_elf_end; + + gelf_getshdr(sec, &shdr); + obj_start = sym.st_value; + + sym.st_value -= shdr.sh_addr - shdr.sh_offset; + + f = symbol__new(sym.st_value, sym.st_size, + elf_sym__name(&sym, symstrs), + self->sym_priv_size, obj_start, verbose); + if (!f) + goto out_elf_end; + + if (filter && filter(self, f)) + symbol__delete(f, self->sym_priv_size); + else { + dso__insert_symbol(self, f); + nr++; + } + } + + err = nr; +out_elf_end: + elf_end(elf); +out_close: + return err; +} + +int dso__load(struct dso *self, symbol_filter_t filter, int verbose) +{ + int size = strlen(self->name) + sizeof("/usr/lib/debug%s.debug"); + char *name = malloc(size); + int variant = 0; + int ret = -1; + int fd; + + if (!name) + return -1; + + if (strncmp(self->name, "/tmp/perf-", 10) == 0) + return dso__load_perf_map(self, filter, verbose); + +more: + do { + switch (variant) { + case 0: /* Fedora */ + snprintf(name, size, "/usr/lib/debug%s.debug", self->name); + break; + case 1: /* Ubuntu */ + snprintf(name, size, "/usr/lib/debug%s", self->name); + break; + case 2: /* Sane people */ + snprintf(name, size, "%s", self->name); + break; + + default: + goto out; + } + variant++; + + fd = open(name, O_RDONLY); + } while (fd < 0); + + ret = dso__load_sym(self, fd, name, filter, verbose); + close(fd); + + /* + * Some people seem to have debuginfo files _WITHOUT_ debug info!?!? + */ + if (!ret) + goto more; + +out: + free(name); + return ret; +} + +static int dso__load_vmlinux(struct dso *self, const char *vmlinux, + symbol_filter_t filter, int verbose) +{ + int err, fd = open(vmlinux, O_RDONLY); + + if (fd < 0) + return -1; + + err = dso__load_sym(self, fd, vmlinux, filter, verbose); + close(fd); + + return err; +} + +int dso__load_kernel(struct dso *self, const char *vmlinux, + symbol_filter_t filter, int verbose) +{ + int err = -1; + + if (vmlinux) + err = dso__load_vmlinux(self, vmlinux, filter, verbose); + + if (err) + err = dso__load_kallsyms(self, filter, verbose); + + return err; +} + +void symbol__init(void) +{ + elf_version(EV_CURRENT); +} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h new file mode 100644 index 0000000000000000000000000000000000000000..0d1292bd82706ec4f567caf492b6a3e23da98e7f --- /dev/null +++ b/tools/perf/util/symbol.h @@ -0,0 +1,47 @@ +#ifndef _PERF_SYMBOL_ +#define _PERF_SYMBOL_ 1 + +#include +#include "list.h" +#include "rbtree.h" + +struct symbol { + struct rb_node rb_node; + __u64 start; + __u64 end; + __u64 obj_start; + __u64 hist_sum; + __u64 *hist; + char name[0]; +}; + +struct dso { + struct list_head node; + struct rb_root syms; + unsigned int sym_priv_size; + struct symbol *(*find_symbol)(struct dso *, __u64 ip); + char name[0]; +}; + +const char *sym_hist_filter; + +typedef int (*symbol_filter_t)(struct dso *self, struct symbol *sym); + +struct dso *dso__new(const char *name, unsigned int sym_priv_size); +void dso__delete(struct dso *self); + +static inline void *dso__sym_priv(struct dso *self, struct symbol *sym) +{ + return ((void *)sym) - self->sym_priv_size; +} + +struct symbol *dso__find_symbol(struct dso *self, __u64 ip); + +int dso__load_kernel(struct dso *self, const char *vmlinux, + symbol_filter_t filter, int verbose); +int dso__load(struct dso *self, symbol_filter_t filter, int verbose); + +size_t dso__fprintf(struct dso *self, FILE *fp); + +void symbol__init(void); +#endif /* _PERF_SYMBOL_ */ diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c new file mode 100644 index 0000000000000000000000000000000000000000..e16bf9a707e89ff249e2785bf4e4996cf076e143 --- /dev/null +++ b/tools/perf/util/usage.c @@ -0,0 +1,80 @@ +/* + * GIT - The information manager from hell + * + * Copyright (C) Linus Torvalds, 2005 + */ +#include "util.h" + +static void report(const char *prefix, const char *err, va_list params) +{ + char msg[1024]; + vsnprintf(msg, sizeof(msg), err, params); + fprintf(stderr, " %s%s\n", prefix, msg); +} + +static NORETURN void usage_builtin(const char *err) +{ + fprintf(stderr, "\n Usage: %s\n", err); + exit(129); +} + +static NORETURN void die_builtin(const char *err, va_list params) +{ + report(" Fatal: ", err, params); + exit(128); +} + +static void error_builtin(const char *err, va_list params) +{ + report(" Error: ", err, params); +} + +static void warn_builtin(const char *warn, va_list params) +{ + report(" Warning: ", warn, params); +} + +/* If we are in a dlopen()ed .so write to a global variable would segfault + * (ugh), so keep things static. */ +static void (*usage_routine)(const char *err) NORETURN = usage_builtin; +static void (*die_routine)(const char *err, va_list params) NORETURN = die_builtin; +static void (*error_routine)(const char *err, va_list params) = error_builtin; +static void (*warn_routine)(const char *err, va_list params) = warn_builtin; + +void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN) +{ + die_routine = routine; +} + +void usage(const char *err) +{ + usage_routine(err); +} + +void die(const char *err, ...) +{ + va_list params; + + va_start(params, err); + die_routine(err, params); + va_end(params); +} + +int error(const char *err, ...) +{ + va_list params; + + va_start(params, err); + error_routine(err, params); + va_end(params); + return -1; +} + +void warning(const char *warn, ...) +{ + va_list params; + + va_start(params, warn); + warn_routine(warn, params); + va_end(params); +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h new file mode 100644 index 0000000000000000000000000000000000000000..76590a16c2717aa0ecd25a821db7463078e8fb71 --- /dev/null +++ b/tools/perf/util/util.h @@ -0,0 +1,410 @@ +#ifndef GIT_COMPAT_UTIL_H +#define GIT_COMPAT_UTIL_H + +#define _FILE_OFFSET_BITS 64 + +#ifndef FLEX_ARRAY +/* + * See if our compiler is known to support flexible array members. + */ +#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) +# define FLEX_ARRAY /* empty */ +#elif defined(__GNUC__) +# if (__GNUC__ >= 3) +# define FLEX_ARRAY /* empty */ +# else +# define FLEX_ARRAY 0 /* older GNU extension */ +# endif +#endif + +/* + * Otherwise, default to safer but a bit wasteful traditional style + */ +#ifndef FLEX_ARRAY +# define FLEX_ARRAY 1 +#endif +#endif + +#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0])) + +#ifdef __GNUC__ +#define TYPEOF(x) (__typeof__(x)) +#else +#define TYPEOF(x) +#endif + +#define MSB(x, bits) ((x) & TYPEOF(x)(~0ULL << (sizeof(x) * 8 - (bits)))) +#define HAS_MULTI_BITS(i) ((i) & ((i) - 1)) /* checks if an integer has more than 1 bit set */ + +/* Approximation of the length of the decimal representation of this type. */ +#define decimal_length(x) ((int)(sizeof(x) * 2.56 + 0.5) + 1) + +#if !defined(__APPLE__) && !defined(__FreeBSD__) && !defined(__USLC__) && !defined(_M_UNIX) +#define _XOPEN_SOURCE 600 /* glibc2 and AIX 5.3L need 500, OpenBSD needs 600 for S_ISLNK() */ +#define _XOPEN_SOURCE_EXTENDED 1 /* AIX 5.3L needs this */ +#endif +#define _ALL_SOURCE 1 +#define _GNU_SOURCE 1 +#define _BSD_SOURCE 1 + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#ifndef __MINGW32__ +#include +#include +#include +#include +#ifndef NO_SYS_SELECT_H +#include +#endif +#include +#include +#include +#include +#include +#include +#if defined(__CYGWIN__) +#undef _XOPEN_SOURCE +#include +#define _XOPEN_SOURCE 600 +#include "compat/cygwin.h" +#else +#undef _ALL_SOURCE /* AIX 5.3L defines a struct list with _ALL_SOURCE. */ +#include +#define _ALL_SOURCE 1 +#endif +#else /* __MINGW32__ */ +/* pull in Windows compatibility stuff */ +#include "compat/mingw.h" +#endif /* __MINGW32__ */ + +#ifndef NO_ICONV +#include +#endif + +#ifndef NO_OPENSSL +#include +#include +#endif + +/* On most systems would have given us this, but + * not on some systems (e.g. GNU/Hurd). + */ +#ifndef PATH_MAX +#define PATH_MAX 4096 +#endif + +#ifndef PRIuMAX +#define PRIuMAX "llu" +#endif + +#ifndef PRIu32 +#define PRIu32 "u" +#endif + +#ifndef PRIx32 +#define PRIx32 "x" +#endif + +#ifndef PATH_SEP +#define PATH_SEP ':' +#endif + +#ifndef STRIP_EXTENSION +#define STRIP_EXTENSION "" +#endif + +#ifndef has_dos_drive_prefix +#define has_dos_drive_prefix(path) 0 +#endif + +#ifndef is_dir_sep +#define is_dir_sep(c) ((c) == '/') +#endif + +#ifdef __GNUC__ +#define NORETURN __attribute__((__noreturn__)) +#else +#define NORETURN +#ifndef __attribute__ +#define __attribute__(x) +#endif +#endif + +/* General helper functions */ +extern void usage(const char *err) NORETURN; +extern void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2))); +extern int error(const char *err, ...) __attribute__((format (printf, 1, 2))); +extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2))); + +extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN); + +extern int prefixcmp(const char *str, const char *prefix); +extern time_t tm_to_time_t(const struct tm *tm); + +static inline const char *skip_prefix(const char *str, const char *prefix) +{ + size_t len = strlen(prefix); + return strncmp(str, prefix, len) ? NULL : str + len; +} + +#if defined(NO_MMAP) || defined(USE_WIN32_MMAP) + +#ifndef PROT_READ +#define PROT_READ 1 +#define PROT_WRITE 2 +#define MAP_PRIVATE 1 +#define MAP_FAILED ((void*)-1) +#endif + +#define mmap git_mmap +#define munmap git_munmap +extern void *git_mmap(void *start, size_t length, int prot, int flags, int fd, off_t offset); +extern int git_munmap(void *start, size_t length); + +#else /* NO_MMAP || USE_WIN32_MMAP */ + +#include + +#endif /* NO_MMAP || USE_WIN32_MMAP */ + +#ifdef NO_MMAP + +/* This value must be multiple of (pagesize * 2) */ +#define DEFAULT_PACKED_GIT_WINDOW_SIZE (1 * 1024 * 1024) + +#else /* NO_MMAP */ + +/* This value must be multiple of (pagesize * 2) */ +#define DEFAULT_PACKED_GIT_WINDOW_SIZE \ + (sizeof(void*) >= 8 \ + ? 1 * 1024 * 1024 * 1024 \ + : 32 * 1024 * 1024) + +#endif /* NO_MMAP */ + +#ifdef NO_ST_BLOCKS_IN_STRUCT_STAT +#define on_disk_bytes(st) ((st).st_size) +#else +#define on_disk_bytes(st) ((st).st_blocks * 512) +#endif + +#define DEFAULT_PACKED_GIT_LIMIT \ + ((1024L * 1024L) * (sizeof(void*) >= 8 ? 8192 : 256)) + +#ifdef NO_PREAD +#define pread git_pread +extern ssize_t git_pread(int fd, void *buf, size_t count, off_t offset); +#endif +/* + * Forward decl that will remind us if its twin in cache.h changes. + * This function is used in compat/pread.c. But we can't include + * cache.h there. + */ +extern ssize_t read_in_full(int fd, void *buf, size_t count); + +#ifdef NO_SETENV +#define setenv gitsetenv +extern int gitsetenv(const char *, const char *, int); +#endif + +#ifdef NO_MKDTEMP +#define mkdtemp gitmkdtemp +extern char *gitmkdtemp(char *); +#endif + +#ifdef NO_UNSETENV +#define unsetenv gitunsetenv +extern void gitunsetenv(const char *); +#endif + +#ifdef NO_STRCASESTR +#define strcasestr gitstrcasestr +extern char *gitstrcasestr(const char *haystack, const char *needle); +#endif + +#ifdef NO_STRLCPY +#define strlcpy gitstrlcpy +extern size_t gitstrlcpy(char *, const char *, size_t); +#endif + +#ifdef NO_STRTOUMAX +#define strtoumax gitstrtoumax +extern uintmax_t gitstrtoumax(const char *, char **, int); +#endif + +#ifdef NO_HSTRERROR +#define hstrerror githstrerror +extern const char *githstrerror(int herror); +#endif + +#ifdef NO_MEMMEM +#define memmem gitmemmem +void *gitmemmem(const void *haystack, size_t haystacklen, + const void *needle, size_t needlelen); +#endif + +#ifdef FREAD_READS_DIRECTORIES +#ifdef fopen +#undef fopen +#endif +#define fopen(a,b) git_fopen(a,b) +extern FILE *git_fopen(const char*, const char*); +#endif + +#ifdef SNPRINTF_RETURNS_BOGUS +#define snprintf git_snprintf +extern int git_snprintf(char *str, size_t maxsize, + const char *format, ...); +#define vsnprintf git_vsnprintf +extern int git_vsnprintf(char *str, size_t maxsize, + const char *format, va_list ap); +#endif + +#ifdef __GLIBC_PREREQ +#if __GLIBC_PREREQ(2, 1) +#define HAVE_STRCHRNUL +#endif +#endif + +#ifndef HAVE_STRCHRNUL +#define strchrnul gitstrchrnul +static inline char *gitstrchrnul(const char *s, int c) +{ + while (*s && *s != c) + s++; + return (char *)s; +} +#endif + +/* + * Wrappers: + */ +extern char *xstrdup(const char *str); +extern void *xmalloc(size_t size); +extern void *xmemdupz(const void *data, size_t len); +extern char *xstrndup(const char *str, size_t len); +extern void *xrealloc(void *ptr, size_t size); +extern void *xcalloc(size_t nmemb, size_t size); +extern void *xmmap(void *start, size_t length, int prot, int flags, int fd, off_t offset); +extern ssize_t xread(int fd, void *buf, size_t len); +extern ssize_t xwrite(int fd, const void *buf, size_t len); +extern int xdup(int fd); +extern FILE *xfdopen(int fd, const char *mode); +extern int xmkstemp(char *template); + +static inline size_t xsize_t(off_t len) +{ + return (size_t)len; +} + +static inline int has_extension(const char *filename, const char *ext) +{ + size_t len = strlen(filename); + size_t extlen = strlen(ext); + return len > extlen && !memcmp(filename + len - extlen, ext, extlen); +} + +/* Sane ctype - no locale, and works with signed chars */ +#undef isascii +#undef isspace +#undef isdigit +#undef isalpha +#undef isalnum +#undef tolower +#undef toupper +extern unsigned char sane_ctype[256]; +#define GIT_SPACE 0x01 +#define GIT_DIGIT 0x02 +#define GIT_ALPHA 0x04 +#define GIT_GLOB_SPECIAL 0x08 +#define GIT_REGEX_SPECIAL 0x10 +#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0) +#define isascii(x) (((x) & ~0x7f) == 0) +#define isspace(x) sane_istest(x,GIT_SPACE) +#define isdigit(x) sane_istest(x,GIT_DIGIT) +#define isalpha(x) sane_istest(x,GIT_ALPHA) +#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT) +#define is_glob_special(x) sane_istest(x,GIT_GLOB_SPECIAL) +#define is_regex_special(x) sane_istest(x,GIT_GLOB_SPECIAL | GIT_REGEX_SPECIAL) +#define tolower(x) sane_case((unsigned char)(x), 0x20) +#define toupper(x) sane_case((unsigned char)(x), 0) + +static inline int sane_case(int x, int high) +{ + if (sane_istest(x, GIT_ALPHA)) + x = (x & ~0x20) | high; + return x; +} + +static inline int strtoul_ui(char const *s, int base, unsigned int *result) +{ + unsigned long ul; + char *p; + + errno = 0; + ul = strtoul(s, &p, base); + if (errno || *p || p == s || (unsigned int) ul != ul) + return -1; + *result = ul; + return 0; +} + +static inline int strtol_i(char const *s, int base, int *result) +{ + long ul; + char *p; + + errno = 0; + ul = strtol(s, &p, base); + if (errno || *p || p == s || (int) ul != ul) + return -1; + *result = ul; + return 0; +} + +#ifdef INTERNAL_QSORT +void git_qsort(void *base, size_t nmemb, size_t size, + int(*compar)(const void *, const void *)); +#define qsort git_qsort +#endif + +#ifndef DIR_HAS_BSD_GROUP_SEMANTICS +# define FORCE_DIR_SET_GID S_ISGID +#else +# define FORCE_DIR_SET_GID 0 +#endif + +#ifdef NO_NSEC +#undef USE_NSEC +#define ST_CTIME_NSEC(st) 0 +#define ST_MTIME_NSEC(st) 0 +#else +#ifdef USE_ST_TIMESPEC +#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctimespec.tv_nsec)) +#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtimespec.tv_nsec)) +#else +#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctim.tv_nsec)) +#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtim.tv_nsec)) +#endif +#endif + +#endif diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c new file mode 100644 index 0000000000000000000000000000000000000000..6350d65f6d9e5f8a2faca0dd40ff790bd4cda8b9 --- /dev/null +++ b/tools/perf/util/wrapper.c @@ -0,0 +1,206 @@ +/* + * Various trivial helper wrappers around standard functions + */ +#include "cache.h" + +/* + * There's no pack memory to release - but stay close to the Git + * version so wrap this away: + */ +static inline void release_pack_memory(size_t size, int flag) +{ +} + +char *xstrdup(const char *str) +{ + char *ret = strdup(str); + if (!ret) { + release_pack_memory(strlen(str) + 1, -1); + ret = strdup(str); + if (!ret) + die("Out of memory, strdup failed"); + } + return ret; +} + +void *xmalloc(size_t size) +{ + void *ret = malloc(size); + if (!ret && !size) + ret = malloc(1); + if (!ret) { + release_pack_memory(size, -1); + ret = malloc(size); + if (!ret && !size) + ret = malloc(1); + if (!ret) + die("Out of memory, malloc failed"); + } +#ifdef XMALLOC_POISON + memset(ret, 0xA5, size); +#endif + return ret; +} + +/* + * xmemdupz() allocates (len + 1) bytes of memory, duplicates "len" bytes of + * "data" to the allocated memory, zero terminates the allocated memory, + * and returns a pointer to the allocated memory. If the allocation fails, + * the program dies. + */ +void *xmemdupz(const void *data, size_t len) +{ + char *p = xmalloc(len + 1); + memcpy(p, data, len); + p[len] = '\0'; + return p; +} + +char *xstrndup(const char *str, size_t len) +{ + char *p = memchr(str, '\0', len); + return xmemdupz(str, p ? p - str : len); +} + +void *xrealloc(void *ptr, size_t size) +{ + void *ret = realloc(ptr, size); + if (!ret && !size) + ret = realloc(ptr, 1); + if (!ret) { + release_pack_memory(size, -1); + ret = realloc(ptr, size); + if (!ret && !size) + ret = realloc(ptr, 1); + if (!ret) + die("Out of memory, realloc failed"); + } + return ret; +} + +void *xcalloc(size_t nmemb, size_t size) +{ + void *ret = calloc(nmemb, size); + if (!ret && (!nmemb || !size)) + ret = calloc(1, 1); + if (!ret) { + release_pack_memory(nmemb * size, -1); + ret = calloc(nmemb, size); + if (!ret && (!nmemb || !size)) + ret = calloc(1, 1); + if (!ret) + die("Out of memory, calloc failed"); + } + return ret; +} + +void *xmmap(void *start, size_t length, + int prot, int flags, int fd, off_t offset) +{ + void *ret = mmap(start, length, prot, flags, fd, offset); + if (ret == MAP_FAILED) { + if (!length) + return NULL; + release_pack_memory(length, fd); + ret = mmap(start, length, prot, flags, fd, offset); + if (ret == MAP_FAILED) + die("Out of memory? mmap failed: %s", strerror(errno)); + } + return ret; +} + +/* + * xread() is the same a read(), but it automatically restarts read() + * operations with a recoverable error (EAGAIN and EINTR). xread() + * DOES NOT GUARANTEE that "len" bytes is read even if the data is available. + */ +ssize_t xread(int fd, void *buf, size_t len) +{ + ssize_t nr; + while (1) { + nr = read(fd, buf, len); + if ((nr < 0) && (errno == EAGAIN || errno == EINTR)) + continue; + return nr; + } +} + +/* + * xwrite() is the same a write(), but it automatically restarts write() + * operations with a recoverable error (EAGAIN and EINTR). xwrite() DOES NOT + * GUARANTEE that "len" bytes is written even if the operation is successful. + */ +ssize_t xwrite(int fd, const void *buf, size_t len) +{ + ssize_t nr; + while (1) { + nr = write(fd, buf, len); + if ((nr < 0) && (errno == EAGAIN || errno == EINTR)) + continue; + return nr; + } +} + +ssize_t read_in_full(int fd, void *buf, size_t count) +{ + char *p = buf; + ssize_t total = 0; + + while (count > 0) { + ssize_t loaded = xread(fd, p, count); + if (loaded <= 0) + return total ? total : loaded; + count -= loaded; + p += loaded; + total += loaded; + } + + return total; +} + +ssize_t write_in_full(int fd, const void *buf, size_t count) +{ + const char *p = buf; + ssize_t total = 0; + + while (count > 0) { + ssize_t written = xwrite(fd, p, count); + if (written < 0) + return -1; + if (!written) { + errno = ENOSPC; + return -1; + } + count -= written; + p += written; + total += written; + } + + return total; +} + +int xdup(int fd) +{ + int ret = dup(fd); + if (ret < 0) + die("dup failed: %s", strerror(errno)); + return ret; +} + +FILE *xfdopen(int fd, const char *mode) +{ + FILE *stream = fdopen(fd, mode); + if (stream == NULL) + die("Out of memory? fdopen failed: %s", strerror(errno)); + return stream; +} + +int xmkstemp(char *template) +{ + int fd; + + fd = mkstemp(template); + if (fd < 0) + die("Unable to create temporary file: %s", strerror(errno)); + return fd; +} diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index c3b99def9cbc3c1eff063248a064d7ee3fc8c84e..1eddae94bab331bee8eb01b5e71fd6df8e0d7604 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -85,7 +85,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx) { - union ioapic_redir_entry *pent; + union kvm_ioapic_redirect_entry *pent; int injected = -1; pent = &ioapic->redirtbl[idx]; @@ -142,149 +142,40 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) } } -static int ioapic_inj_irq(struct kvm_ioapic *ioapic, - struct kvm_vcpu *vcpu, - u8 vector, u8 trig_mode, u8 delivery_mode) -{ - ioapic_debug("irq %d trig %d deliv %d\n", vector, trig_mode, - delivery_mode); - - ASSERT((delivery_mode == IOAPIC_FIXED) || - (delivery_mode == IOAPIC_LOWEST_PRIORITY)); - - return kvm_apic_set_irq(vcpu, vector, trig_mode); -} - -static void ioapic_inj_nmi(struct kvm_vcpu *vcpu) -{ - kvm_inject_nmi(vcpu); - kvm_vcpu_kick(vcpu); -} - -u32 kvm_ioapic_get_delivery_bitmask(struct kvm_ioapic *ioapic, u8 dest, - u8 dest_mode) -{ - u32 mask = 0; - int i; - struct kvm *kvm = ioapic->kvm; - struct kvm_vcpu *vcpu; - - ioapic_debug("dest %d dest_mode %d\n", dest, dest_mode); - - if (dest_mode == 0) { /* Physical mode. */ - if (dest == 0xFF) { /* Broadcast. */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) - if (kvm->vcpus[i] && kvm->vcpus[i]->arch.apic) - mask |= 1 << i; - return mask; - } - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = kvm->vcpus[i]; - if (!vcpu) - continue; - if (kvm_apic_match_physical_addr(vcpu->arch.apic, dest)) { - if (vcpu->arch.apic) - mask = 1 << i; - break; - } - } - } else if (dest != 0) /* Logical mode, MDA non-zero. */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = kvm->vcpus[i]; - if (!vcpu) - continue; - if (vcpu->arch.apic && - kvm_apic_match_logical_addr(vcpu->arch.apic, dest)) - mask |= 1 << vcpu->vcpu_id; - } - ioapic_debug("mask %x\n", mask); - return mask; -} - static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) { - u8 dest = ioapic->redirtbl[irq].fields.dest_id; - u8 dest_mode = ioapic->redirtbl[irq].fields.dest_mode; - u8 delivery_mode = ioapic->redirtbl[irq].fields.delivery_mode; - u8 vector = ioapic->redirtbl[irq].fields.vector; - u8 trig_mode = ioapic->redirtbl[irq].fields.trig_mode; - u32 deliver_bitmask; - struct kvm_vcpu *vcpu; - int vcpu_id, r = -1; + union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq]; + struct kvm_lapic_irq irqe; ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x " "vector=%x trig_mode=%x\n", - dest, dest_mode, delivery_mode, vector, trig_mode); - - deliver_bitmask = kvm_ioapic_get_delivery_bitmask(ioapic, dest, - dest_mode); - if (!deliver_bitmask) { - ioapic_debug("no target on destination\n"); - return 0; - } + entry->fields.dest, entry->fields.dest_mode, + entry->fields.delivery_mode, entry->fields.vector, + entry->fields.trig_mode); + + irqe.dest_id = entry->fields.dest_id; + irqe.vector = entry->fields.vector; + irqe.dest_mode = entry->fields.dest_mode; + irqe.trig_mode = entry->fields.trig_mode; + irqe.delivery_mode = entry->fields.delivery_mode << 8; + irqe.level = 1; + irqe.shorthand = 0; - switch (delivery_mode) { - case IOAPIC_LOWEST_PRIORITY: - vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, vector, - deliver_bitmask); #ifdef CONFIG_X86 - if (irq == 0) - vcpu = ioapic->kvm->vcpus[0]; -#endif - if (vcpu != NULL) - r = ioapic_inj_irq(ioapic, vcpu, vector, - trig_mode, delivery_mode); - else - ioapic_debug("null lowest prio vcpu: " - "mask=%x vector=%x delivery_mode=%x\n", - deliver_bitmask, vector, IOAPIC_LOWEST_PRIORITY); - break; - case IOAPIC_FIXED: -#ifdef CONFIG_X86 - if (irq == 0) - deliver_bitmask = 1; -#endif - for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) { - if (!(deliver_bitmask & (1 << vcpu_id))) - continue; - deliver_bitmask &= ~(1 << vcpu_id); - vcpu = ioapic->kvm->vcpus[vcpu_id]; - if (vcpu) { - if (r < 0) - r = 0; - r += ioapic_inj_irq(ioapic, vcpu, vector, - trig_mode, delivery_mode); - } - } - break; - case IOAPIC_NMI: - for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) { - if (!(deliver_bitmask & (1 << vcpu_id))) - continue; - deliver_bitmask &= ~(1 << vcpu_id); - vcpu = ioapic->kvm->vcpus[vcpu_id]; - if (vcpu) { - ioapic_inj_nmi(vcpu); - r = 1; - } - else - ioapic_debug("NMI to vcpu %d failed\n", - vcpu->vcpu_id); - } - break; - default: - printk(KERN_WARNING "Unsupported delivery mode %d\n", - delivery_mode); - break; + /* Always delivery PIT interrupt to vcpu 0 */ + if (irq == 0) { + irqe.dest_mode = 0; /* Physical mode. */ + irqe.dest_id = ioapic->kvm->vcpus[0]->vcpu_id; } - return r; +#endif + return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe); } int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) { u32 old_irr = ioapic->irr; u32 mask = 1 << irq; - union ioapic_redir_entry entry; + union kvm_ioapic_redirect_entry entry; int ret = 1; if (irq >= 0 && irq < IOAPIC_NUM_PINS) { @@ -305,7 +196,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int pin, int trigger_mode) { - union ioapic_redir_entry *ent; + union kvm_ioapic_redirect_entry *ent; ent = &ioapic->redirtbl[pin]; diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index a34bd5e6436bddf086f4e7dca13bdce09776fa64..7080b713c160310788f6f61baa446fda9bf29a23 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -40,22 +40,7 @@ struct kvm_ioapic { u32 id; u32 irr; u32 pad; - union ioapic_redir_entry { - u64 bits; - struct { - u8 vector; - u8 delivery_mode:3; - u8 dest_mode:1; - u8 delivery_status:1; - u8 polarity:1; - u8 remote_irr:1; - u8 trig_mode:1; - u8 mask:1; - u8 reserve:7; - u8 reserved[4]; - u8 dest_id; - } fields; - } redirtbl[IOAPIC_NUM_PINS]; + union kvm_ioapic_redirect_entry redirtbl[IOAPIC_NUM_PINS]; struct kvm_io_device dev; struct kvm *kvm; void (*ack_notifier)(void *opaque, int irq); @@ -79,13 +64,13 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm) return kvm->arch.vioapic; } -struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector, - unsigned long bitmap); +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); void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode); int kvm_ioapic_init(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level); void kvm_ioapic_reset(struct kvm_ioapic *ioapic); -u32 kvm_ioapic_get_delivery_bitmask(struct kvm_ioapic *ioapic, u8 dest, - u8 dest_mode); - +int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, + struct kvm_lapic_irq *irq); #endif diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index 4c403750360082f0e53d3e5459c17d78797ab9e0..15147583abd164d64de465eb7fce9d0c27a41ef8 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -39,11 +39,16 @@ int kvm_iommu_map_pages(struct kvm *kvm, pfn_t pfn; int i, r = 0; struct iommu_domain *domain = kvm->arch.iommu_domain; + int flags; /* check if iommu exists and in use */ if (!domain) return 0; + flags = IOMMU_READ | IOMMU_WRITE; + if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY) + flags |= IOMMU_CACHE; + for (i = 0; i < npages; i++) { /* check if already mapped */ if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) @@ -53,8 +58,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, r = iommu_map_range(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn), - PAGE_SIZE, - IOMMU_READ | IOMMU_WRITE); + PAGE_SIZE, flags); if (r) { printk(KERN_ERR "kvm_iommu_map_address:" "iommu failed to map pfn=%lx\n", pfn); @@ -88,7 +92,7 @@ int kvm_assign_device(struct kvm *kvm, { struct pci_dev *pdev = NULL; struct iommu_domain *domain = kvm->arch.iommu_domain; - int r; + int r, last_flags; /* check if iommu exists and in use */ if (!domain) @@ -107,12 +111,29 @@ int kvm_assign_device(struct kvm *kvm, return r; } + last_flags = kvm->arch.iommu_flags; + if (iommu_domain_has_cap(kvm->arch.iommu_domain, + IOMMU_CAP_CACHE_COHERENCY)) + kvm->arch.iommu_flags |= KVM_IOMMU_CACHE_COHERENCY; + + /* Check if need to update IOMMU page table for guest memory */ + if ((last_flags ^ kvm->arch.iommu_flags) == + KVM_IOMMU_CACHE_COHERENCY) { + kvm_iommu_unmap_memslots(kvm); + r = kvm_iommu_map_memslots(kvm); + if (r) + goto out_unmap; + } + printk(KERN_DEBUG "assign device: host bdf = %x:%x:%x\n", assigned_dev->host_busnr, PCI_SLOT(assigned_dev->host_devfn), PCI_FUNC(assigned_dev->host_devfn)); return 0; +out_unmap: + kvm_iommu_unmap_memslots(kvm); + return r; } int kvm_deassign_device(struct kvm *kvm, diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 864ac5483baade3fce7085c3c51f23e493426914..a8bd466d00ccf1af71ab09e229197c2366fcdef5 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -22,6 +22,9 @@ #include #include +#ifdef CONFIG_IA64 +#include +#endif #include "irq.h" @@ -43,57 +46,73 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level); } -static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level) +inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq) { - int vcpu_id, r = -1; - struct kvm_vcpu *vcpu; - struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); - int dest_id = (e->msi.address_lo & MSI_ADDR_DEST_ID_MASK) - >> MSI_ADDR_DEST_ID_SHIFT; - int vector = (e->msi.data & MSI_DATA_VECTOR_MASK) - >> MSI_DATA_VECTOR_SHIFT; - int dest_mode = test_bit(MSI_ADDR_DEST_MODE_SHIFT, - (unsigned long *)&e->msi.address_lo); - int trig_mode = test_bit(MSI_DATA_TRIGGER_SHIFT, - (unsigned long *)&e->msi.data); - int delivery_mode = test_bit(MSI_DATA_DELIVERY_MODE_SHIFT, - (unsigned long *)&e->msi.data); - u32 deliver_bitmask; - - BUG_ON(!ioapic); - - deliver_bitmask = kvm_ioapic_get_delivery_bitmask(ioapic, - dest_id, dest_mode); - /* IOAPIC delivery mode value is the same as MSI here */ - switch (delivery_mode) { - case IOAPIC_LOWEST_PRIORITY: - vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, vector, - deliver_bitmask); - if (vcpu != NULL) - r = kvm_apic_set_irq(vcpu, vector, trig_mode); - else - printk(KERN_INFO "kvm: null lowest priority vcpu!\n"); - break; - case IOAPIC_FIXED: - for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) { - if (!(deliver_bitmask & (1 << vcpu_id))) - continue; - deliver_bitmask &= ~(1 << vcpu_id); - vcpu = ioapic->kvm->vcpus[vcpu_id]; - if (vcpu) { - if (r < 0) - r = 0; - r += kvm_apic_set_irq(vcpu, vector, trig_mode); - } +#ifdef CONFIG_IA64 + return irq->delivery_mode == + (IOSAPIC_LOWEST_PRIORITY << IOSAPIC_DELIVERY_SHIFT); +#else + return irq->delivery_mode == APIC_DM_LOWEST; +#endif +} + +int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, + struct kvm_lapic_irq *irq) +{ + int i, r = -1; + struct kvm_vcpu *vcpu, *lowest = NULL; + + if (irq->dest_mode == 0 && irq->dest_id == 0xff && + kvm_is_dm_lowest_prio(irq)) + printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); + + for (i = 0; i < KVM_MAX_VCPUS; i++) { + vcpu = kvm->vcpus[i]; + + if (!vcpu || !kvm_apic_present(vcpu)) + continue; + + if (!kvm_apic_match_dest(vcpu, src, irq->shorthand, + irq->dest_id, irq->dest_mode)) + continue; + + if (!kvm_is_dm_lowest_prio(irq)) { + if (r < 0) + r = 0; + r += kvm_apic_set_irq(vcpu, irq); + } else { + if (!lowest) + lowest = vcpu; + else if (kvm_apic_compare_prio(vcpu, lowest) < 0) + lowest = vcpu; } - break; - default: - break; } + + if (lowest) + r = kvm_apic_set_irq(lowest, irq); + return r; } +static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int level) +{ + struct kvm_lapic_irq irq; + + irq.dest_id = (e->msi.address_lo & + MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT; + irq.vector = (e->msi.data & + MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT; + irq.dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo; + irq.trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data; + irq.delivery_mode = e->msi.data & 0x700; + irq.level = 1; + irq.shorthand = 0; + + /* TODO Deal with RH bit of MSI message address */ + return kvm_irq_delivery_to_apic(kvm, NULL, &irq); +} + /* This should be called with the kvm->lock mutex held * Return value: * < 0 Interrupt was ignored (masked or not delivered for other reasons) @@ -252,7 +271,7 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e, delta = 8; break; case KVM_IRQCHIP_IOAPIC: - e->set = kvm_set_ioapic_irq; + e->set = kvm_set_ioapic_irq; break; default: goto out; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 1ecbe2391c8b11157c86ab2083f4ed856d38d813..764554350ed86f41b26f45eb840ad02138a55081 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -41,6 +41,8 @@ #include #include #include +#include +#include #include #include @@ -60,9 +62,6 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); -static int msi2intx = 1; -module_param(msi2intx, bool, 0); - DEFINE_SPINLOCK(kvm_lock); LIST_HEAD(vm_list); @@ -95,38 +94,96 @@ static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *h return NULL; } +static int find_index_from_host_irq(struct kvm_assigned_dev_kernel + *assigned_dev, int irq) +{ + int i, index; + struct msix_entry *host_msix_entries; + + host_msix_entries = assigned_dev->host_msix_entries; + + index = -1; + for (i = 0; i < assigned_dev->entries_nr; i++) + if (irq == host_msix_entries[i].vector) { + index = i; + break; + } + if (index < 0) { + printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n"); + return 0; + } + + return index; +} + static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) { struct kvm_assigned_dev_kernel *assigned_dev; + struct kvm *kvm; + int irq, i; assigned_dev = container_of(work, struct kvm_assigned_dev_kernel, interrupt_work); + kvm = assigned_dev->kvm; /* This is taken to safely inject irq inside the guest. When * the interrupt injection (or the ioapic code) uses a * finer-grained lock, update this */ - mutex_lock(&assigned_dev->kvm->lock); - kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, - assigned_dev->guest_irq, 1); - - if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI) { - enable_irq(assigned_dev->host_irq); - assigned_dev->host_irq_disabled = false; + mutex_lock(&kvm->lock); + spin_lock_irq(&assigned_dev->assigned_dev_lock); + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + struct kvm_guest_msix_entry *guest_entries = + assigned_dev->guest_msix_entries; + for (i = 0; i < assigned_dev->entries_nr; i++) { + if (!(guest_entries[i].flags & + KVM_ASSIGNED_MSIX_PENDING)) + continue; + guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING; + kvm_set_irq(assigned_dev->kvm, + assigned_dev->irq_source_id, + guest_entries[i].vector, 1); + irq = assigned_dev->host_msix_entries[i].vector; + if (irq != 0) + enable_irq(irq); + assigned_dev->host_irq_disabled = false; + } + } else { + kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, + assigned_dev->guest_irq, 1); + if (assigned_dev->irq_requested_type & + KVM_DEV_IRQ_GUEST_MSI) { + enable_irq(assigned_dev->host_irq); + assigned_dev->host_irq_disabled = false; + } } + + spin_unlock_irq(&assigned_dev->assigned_dev_lock); mutex_unlock(&assigned_dev->kvm->lock); } static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) { + unsigned long flags; struct kvm_assigned_dev_kernel *assigned_dev = (struct kvm_assigned_dev_kernel *) dev_id; + spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags); + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + int index = find_index_from_host_irq(assigned_dev, irq); + if (index < 0) + goto out; + assigned_dev->guest_msix_entries[index].flags |= + KVM_ASSIGNED_MSIX_PENDING; + } + schedule_work(&assigned_dev->interrupt_work); disable_irq_nosync(irq); assigned_dev->host_irq_disabled = true; +out: + spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags); return IRQ_HANDLED; } @@ -134,6 +191,7 @@ static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) { struct kvm_assigned_dev_kernel *dev; + unsigned long flags; if (kian->gsi == -1) return; @@ -146,28 +204,30 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) /* The guest irq may be shared so this ack may be * from another device. */ + spin_lock_irqsave(&dev->assigned_dev_lock, flags); if (dev->host_irq_disabled) { enable_irq(dev->host_irq); dev->host_irq_disabled = false; } + spin_unlock_irqrestore(&dev->assigned_dev_lock, flags); } -/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */ -static void kvm_free_assigned_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) +static void deassign_guest_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) { - if (!irqchip_in_kernel(kvm)) - return; - kvm_unregister_irq_ack_notifier(&assigned_dev->ack_notifier); + assigned_dev->ack_notifier.gsi = -1; if (assigned_dev->irq_source_id != -1) kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id); assigned_dev->irq_source_id = -1; + assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK); +} - if (!assigned_dev->irq_requested_type) - return; - +/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */ +static void deassign_host_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) +{ /* * In kvm_free_device_irq, cancel_work_sync return true if: * 1. work is scheduled, and then cancelled. @@ -184,17 +244,64 @@ static void kvm_free_assigned_irq(struct kvm *kvm, * now, the kvm state is still legal for probably we also have to wait * interrupt_work done. */ - disable_irq_nosync(assigned_dev->host_irq); - cancel_work_sync(&assigned_dev->interrupt_work); + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + int i; + for (i = 0; i < assigned_dev->entries_nr; i++) + disable_irq_nosync(assigned_dev-> + host_msix_entries[i].vector); + + cancel_work_sync(&assigned_dev->interrupt_work); + + for (i = 0; i < assigned_dev->entries_nr; i++) + free_irq(assigned_dev->host_msix_entries[i].vector, + (void *)assigned_dev); + + assigned_dev->entries_nr = 0; + kfree(assigned_dev->host_msix_entries); + kfree(assigned_dev->guest_msix_entries); + pci_disable_msix(assigned_dev->dev); + } else { + /* Deal with MSI and INTx */ + disable_irq_nosync(assigned_dev->host_irq); + cancel_work_sync(&assigned_dev->interrupt_work); - free_irq(assigned_dev->host_irq, (void *)assigned_dev); + free_irq(assigned_dev->host_irq, (void *)assigned_dev); - if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) - pci_disable_msi(assigned_dev->dev); + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI) + pci_disable_msi(assigned_dev->dev); + } - assigned_dev->irq_requested_type = 0; + assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK); } +static int kvm_deassign_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev, + unsigned long irq_requested_type) +{ + unsigned long guest_irq_type, host_irq_type; + + if (!irqchip_in_kernel(kvm)) + return -EINVAL; + /* no irq assignment to deassign */ + if (!assigned_dev->irq_requested_type) + return -ENXIO; + + host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK; + guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK; + + if (host_irq_type) + deassign_host_irq(kvm, assigned_dev); + if (guest_irq_type) + deassign_guest_irq(kvm, assigned_dev); + + return 0; +} + +static void kvm_free_assigned_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) +{ + kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type); +} static void kvm_free_assigned_device(struct kvm *kvm, struct kvm_assigned_dev_kernel @@ -226,190 +333,244 @@ void kvm_free_all_assigned_devices(struct kvm *kvm) } } -static int assigned_device_update_intx(struct kvm *kvm, - struct kvm_assigned_dev_kernel *adev, - struct kvm_assigned_irq *airq) +static int assigned_device_enable_host_intx(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) { - adev->guest_irq = airq->guest_irq; - adev->ack_notifier.gsi = airq->guest_irq; + dev->host_irq = dev->dev->irq; + /* Even though this is PCI, we don't want to use shared + * interrupts. Sharing host devices with guest-assigned devices + * on the same interrupt line is not a happy situation: there + * are going to be long delays in accepting, acking, etc. + */ + if (request_irq(dev->host_irq, kvm_assigned_dev_intr, + 0, "kvm_assigned_intx_device", (void *)dev)) + return -EIO; + return 0; +} - if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_INTX) - return 0; +#ifdef __KVM_HAVE_MSI +static int assigned_device_enable_host_msi(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) +{ + int r; - if (irqchip_in_kernel(kvm)) { - if (!msi2intx && - (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)) { - free_irq(adev->host_irq, (void *)adev); - pci_disable_msi(adev->dev); - } + if (!dev->dev->msi_enabled) { + r = pci_enable_msi(dev->dev); + if (r) + return r; + } - if (!capable(CAP_SYS_RAWIO)) - return -EPERM; + dev->host_irq = dev->dev->irq; + if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0, + "kvm_assigned_msi_device", (void *)dev)) { + pci_disable_msi(dev->dev); + return -EIO; + } - if (airq->host_irq) - adev->host_irq = airq->host_irq; - else - adev->host_irq = adev->dev->irq; + return 0; +} +#endif - /* Even though this is PCI, we don't want to use shared - * interrupts. Sharing host devices with guest-assigned devices - * on the same interrupt line is not a happy situation: there - * are going to be long delays in accepting, acking, etc. - */ - if (request_irq(adev->host_irq, kvm_assigned_dev_intr, - 0, "kvm_assigned_intx_device", (void *)adev)) - return -EIO; +#ifdef __KVM_HAVE_MSIX +static int assigned_device_enable_host_msix(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) +{ + int i, r = -EINVAL; + + /* host_msix_entries and guest_msix_entries should have been + * initialized */ + if (dev->entries_nr == 0) + return r; + + r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr); + if (r) + return r; + + for (i = 0; i < dev->entries_nr; i++) { + r = request_irq(dev->host_msix_entries[i].vector, + kvm_assigned_dev_intr, 0, + "kvm_assigned_msix_device", + (void *)dev); + /* FIXME: free requested_irq's on failure */ + if (r) + return r; } - adev->irq_requested_type = KVM_ASSIGNED_DEV_GUEST_INTX | - KVM_ASSIGNED_DEV_HOST_INTX; return 0; } -#ifdef CONFIG_X86 -static int assigned_device_update_msi(struct kvm *kvm, - struct kvm_assigned_dev_kernel *adev, - struct kvm_assigned_irq *airq) +#endif + +static int assigned_device_enable_guest_intx(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) { - int r; + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = irq->guest_irq; + return 0; +} - adev->guest_irq = airq->guest_irq; - if (airq->flags & KVM_DEV_IRQ_ASSIGN_ENABLE_MSI) { - /* x86 don't care upper address of guest msi message addr */ - adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_MSI; - adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_INTX; - adev->ack_notifier.gsi = -1; - } else if (msi2intx) { - adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_INTX; - adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_MSI; - adev->ack_notifier.gsi = airq->guest_irq; - } else { - /* - * Guest require to disable device MSI, we disable MSI and - * re-enable INTx by default again. Notice it's only for - * non-msi2intx. - */ - assigned_device_update_intx(kvm, adev, airq); - return 0; +#ifdef __KVM_HAVE_MSI +static int assigned_device_enable_guest_msi(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) +{ + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = -1; + return 0; +} +#endif +#ifdef __KVM_HAVE_MSIX +static int assigned_device_enable_guest_msix(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) +{ + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = -1; + return 0; +} +#endif + +static int assign_host_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + __u32 host_irq_type) +{ + int r = -EEXIST; + + if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK) + return r; + + switch (host_irq_type) { + case KVM_DEV_IRQ_HOST_INTX: + r = assigned_device_enable_host_intx(kvm, dev); + break; +#ifdef __KVM_HAVE_MSI + case KVM_DEV_IRQ_HOST_MSI: + r = assigned_device_enable_host_msi(kvm, dev); + break; +#endif +#ifdef __KVM_HAVE_MSIX + case KVM_DEV_IRQ_HOST_MSIX: + r = assigned_device_enable_host_msix(kvm, dev); + break; +#endif + default: + r = -EINVAL; } - if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) - return 0; + if (!r) + dev->irq_requested_type |= host_irq_type; - if (irqchip_in_kernel(kvm)) { - if (!msi2intx) { - if (adev->irq_requested_type & - KVM_ASSIGNED_DEV_HOST_INTX) - free_irq(adev->host_irq, (void *)adev); + return r; +} - r = pci_enable_msi(adev->dev); - if (r) - return r; - } +static int assign_guest_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq, + unsigned long guest_irq_type) +{ + int id; + int r = -EEXIST; + + if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK) + return r; - adev->host_irq = adev->dev->irq; - if (request_irq(adev->host_irq, kvm_assigned_dev_intr, 0, - "kvm_assigned_msi_device", (void *)adev)) - return -EIO; + id = kvm_request_irq_source_id(kvm); + if (id < 0) + return id; + + dev->irq_source_id = id; + + switch (guest_irq_type) { + case KVM_DEV_IRQ_GUEST_INTX: + r = assigned_device_enable_guest_intx(kvm, dev, irq); + break; +#ifdef __KVM_HAVE_MSI + case KVM_DEV_IRQ_GUEST_MSI: + r = assigned_device_enable_guest_msi(kvm, dev, irq); + break; +#endif +#ifdef __KVM_HAVE_MSIX + case KVM_DEV_IRQ_GUEST_MSIX: + r = assigned_device_enable_guest_msix(kvm, dev, irq); + break; +#endif + default: + r = -EINVAL; } - if (!msi2intx) - adev->irq_requested_type = KVM_ASSIGNED_DEV_GUEST_MSI; + if (!r) { + dev->irq_requested_type |= guest_irq_type; + kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier); + } else + kvm_free_irq_source_id(kvm, dev->irq_source_id); - adev->irq_requested_type |= KVM_ASSIGNED_DEV_HOST_MSI; - return 0; + return r; } -#endif +/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */ static int kvm_vm_ioctl_assign_irq(struct kvm *kvm, - struct kvm_assigned_irq - *assigned_irq) + struct kvm_assigned_irq *assigned_irq) { - int r = 0; + int r = -EINVAL; struct kvm_assigned_dev_kernel *match; - u32 current_flags = 0, changed_flags; + unsigned long host_irq_type, guest_irq_type; - mutex_lock(&kvm->lock); + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + if (!irqchip_in_kernel(kvm)) + return r; + + mutex_lock(&kvm->lock); + r = -ENODEV; match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, assigned_irq->assigned_dev_id); - if (!match) { - mutex_unlock(&kvm->lock); - return -EINVAL; - } - - if (!match->irq_requested_type) { - INIT_WORK(&match->interrupt_work, - kvm_assigned_dev_interrupt_work_handler); - if (irqchip_in_kernel(kvm)) { - /* Register ack nofitier */ - match->ack_notifier.gsi = -1; - match->ack_notifier.irq_acked = - kvm_assigned_dev_ack_irq; - kvm_register_irq_ack_notifier(kvm, - &match->ack_notifier); - - /* Request IRQ source ID */ - r = kvm_request_irq_source_id(kvm); - if (r < 0) - goto out_release; - else - match->irq_source_id = r; - -#ifdef CONFIG_X86 - /* Determine host device irq type, we can know the - * result from dev->msi_enabled */ - if (msi2intx) - pci_enable_msi(match->dev); -#endif - } - } + if (!match) + goto out; - if ((match->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) && - (match->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI)) - current_flags |= KVM_DEV_IRQ_ASSIGN_ENABLE_MSI; + host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK); + guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK); - changed_flags = assigned_irq->flags ^ current_flags; + r = -EINVAL; + /* can only assign one type at a time */ + if (hweight_long(host_irq_type) > 1) + goto out; + if (hweight_long(guest_irq_type) > 1) + goto out; + if (host_irq_type == 0 && guest_irq_type == 0) + goto out; - if ((changed_flags & KVM_DEV_IRQ_ASSIGN_MSI_ACTION) || - (msi2intx && match->dev->msi_enabled)) { -#ifdef CONFIG_X86 - r = assigned_device_update_msi(kvm, match, assigned_irq); - if (r) { - printk(KERN_WARNING "kvm: failed to enable " - "MSI device!\n"); - goto out_release; - } -#else - r = -ENOTTY; -#endif - } else if (assigned_irq->host_irq == 0 && match->dev->irq == 0) { - /* Host device IRQ 0 means don't support INTx */ - if (!msi2intx) { - printk(KERN_WARNING - "kvm: wait device to enable MSI!\n"); - r = 0; - } else { - printk(KERN_WARNING - "kvm: failed to enable MSI device!\n"); - r = -ENOTTY; - goto out_release; - } - } else { - /* Non-sharing INTx mode */ - r = assigned_device_update_intx(kvm, match, assigned_irq); - if (r) { - printk(KERN_WARNING "kvm: failed to enable " - "INTx device!\n"); - goto out_release; - } - } + r = 0; + if (host_irq_type) + r = assign_host_irq(kvm, match, host_irq_type); + if (r) + goto out; + if (guest_irq_type) + r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type); +out: mutex_unlock(&kvm->lock); return r; -out_release: +} + +static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm, + struct kvm_assigned_irq + *assigned_irq) +{ + int r = -ENODEV; + struct kvm_assigned_dev_kernel *match; + + mutex_lock(&kvm->lock); + + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_irq->assigned_dev_id); + if (!match) + goto out; + + r = kvm_deassign_irq(kvm, match, assigned_irq->flags); +out: mutex_unlock(&kvm->lock); - kvm_free_assigned_device(kvm, match); return r; } @@ -427,7 +588,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, assigned_dev->assigned_dev_id); if (match) { /* device already assigned */ - r = -EINVAL; + r = -EEXIST; goto out; } @@ -464,8 +625,12 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, match->host_devfn = assigned_dev->devfn; match->flags = assigned_dev->flags; match->dev = dev; + spin_lock_init(&match->assigned_dev_lock); match->irq_source_id = -1; match->kvm = kvm; + match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq; + INIT_WORK(&match->interrupt_work, + kvm_assigned_dev_interrupt_work_handler); list_add(&match->list, &kvm->arch.assigned_dev_head); @@ -878,6 +1043,8 @@ static void kvm_destroy_vm(struct kvm *kvm) #endif #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); +#else + kvm_arch_flush_shadow(kvm); #endif kvm_arch_destroy_vm(kvm); mmdrop(mm); @@ -919,9 +1086,8 @@ int __kvm_set_memory_region(struct kvm *kvm, { int r; gfn_t base_gfn; - unsigned long npages; - int largepages; - unsigned long i; + unsigned long npages, ugfn; + unsigned long largepages, i; struct kvm_memory_slot *memslot; struct kvm_memory_slot old, new; @@ -1010,6 +1176,14 @@ int __kvm_set_memory_region(struct kvm *kvm, new.lpage_info[0].write_count = 1; if ((base_gfn+npages) % KVM_PAGES_PER_HPAGE) new.lpage_info[largepages-1].write_count = 1; + ugfn = new.userspace_addr >> PAGE_SHIFT; + /* + * If the gfn and userspace address are not aligned wrt each + * other, disable large page support for this slot + */ + if ((base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE - 1)) + for (i = 0; i < largepages; ++i) + new.lpage_info[i].write_count = 1; } /* Allocate page dirty bitmap if needed */ @@ -1043,8 +1217,10 @@ int __kvm_set_memory_region(struct kvm *kvm, kvm_free_physmem_slot(&old, npages ? &new : NULL); /* Slot deletion case: we have to update the current slot */ + spin_lock(&kvm->mmu_lock); if (!npages) *memslot = old; + spin_unlock(&kvm->mmu_lock); #ifdef CONFIG_DMAR /* map the pages in iommu page table */ r = kvm_iommu_map_pages(kvm, base_gfn, npages); @@ -1454,12 +1630,14 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) for (;;) { prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); - if (kvm_cpu_has_interrupt(vcpu) || - kvm_cpu_has_pending_timer(vcpu) || - kvm_arch_vcpu_runnable(vcpu)) { + if ((kvm_arch_interrupt_allowed(vcpu) && + kvm_cpu_has_interrupt(vcpu)) || + kvm_arch_vcpu_runnable(vcpu)) { set_bit(KVM_REQ_UNHALT, &vcpu->requests); break; } + if (kvm_cpu_has_pending_timer(vcpu)) + break; if (signal_pending(current)) break; @@ -1593,6 +1771,88 @@ static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) return 0; } +#ifdef __KVM_HAVE_MSIX +static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm, + struct kvm_assigned_msix_nr *entry_nr) +{ + int r = 0; + struct kvm_assigned_dev_kernel *adev; + + mutex_lock(&kvm->lock); + + adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + entry_nr->assigned_dev_id); + if (!adev) { + r = -EINVAL; + goto msix_nr_out; + } + + if (adev->entries_nr == 0) { + adev->entries_nr = entry_nr->entry_nr; + if (adev->entries_nr == 0 || + adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) { + r = -EINVAL; + goto msix_nr_out; + } + + adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) * + entry_nr->entry_nr, + GFP_KERNEL); + if (!adev->host_msix_entries) { + r = -ENOMEM; + goto msix_nr_out; + } + adev->guest_msix_entries = kzalloc( + sizeof(struct kvm_guest_msix_entry) * + entry_nr->entry_nr, GFP_KERNEL); + if (!adev->guest_msix_entries) { + kfree(adev->host_msix_entries); + r = -ENOMEM; + goto msix_nr_out; + } + } else /* Not allowed set MSI-X number twice */ + r = -EINVAL; +msix_nr_out: + mutex_unlock(&kvm->lock); + return r; +} + +static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm, + struct kvm_assigned_msix_entry *entry) +{ + int r = 0, i; + struct kvm_assigned_dev_kernel *adev; + + mutex_lock(&kvm->lock); + + adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + entry->assigned_dev_id); + + if (!adev) { + r = -EINVAL; + goto msix_entry_out; + } + + for (i = 0; i < adev->entries_nr; i++) + if (adev->guest_msix_entries[i].vector == 0 || + adev->guest_msix_entries[i].entry == entry->entry) { + adev->guest_msix_entries[i].entry = entry->entry; + adev->guest_msix_entries[i].vector = entry->gsi; + adev->host_msix_entries[i].entry = entry->entry; + break; + } + if (i == adev->entries_nr) { + r = -ENOSPC; + goto msix_entry_out; + } + +msix_entry_out: + mutex_unlock(&kvm->lock); + + return r; +} +#endif + static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -1864,6 +2124,11 @@ static long kvm_vm_ioctl(struct file *filp, break; } case KVM_ASSIGN_IRQ: { + r = -EOPNOTSUPP; + break; + } +#ifdef KVM_CAP_ASSIGN_DEV_IRQ + case KVM_ASSIGN_DEV_IRQ: { struct kvm_assigned_irq assigned_irq; r = -EFAULT; @@ -1874,6 +2139,18 @@ static long kvm_vm_ioctl(struct file *filp, goto out; break; } + case KVM_DEASSIGN_DEV_IRQ: { + struct kvm_assigned_irq assigned_irq; + + r = -EFAULT; + if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) + goto out; + r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq); + if (r) + goto out; + break; + } +#endif #endif #ifdef KVM_CAP_DEVICE_DEASSIGNMENT case KVM_DEASSIGN_PCI_DEVICE: { @@ -1917,7 +2194,29 @@ static long kvm_vm_ioctl(struct file *filp, vfree(entries); break; } +#ifdef __KVM_HAVE_MSIX + case KVM_ASSIGN_SET_MSIX_NR: { + struct kvm_assigned_msix_nr entry_nr; + r = -EFAULT; + if (copy_from_user(&entry_nr, argp, sizeof entry_nr)) + goto out; + r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr); + if (r) + goto out; + break; + } + case KVM_ASSIGN_SET_MSIX_ENTRY: { + struct kvm_assigned_msix_entry entry; + r = -EFAULT; + if (copy_from_user(&entry, argp, sizeof entry)) + goto out; + r = kvm_vm_ioctl_set_msix_entry(kvm, &entry); + if (r) + goto out; + break; + } #endif +#endif /* KVM_CAP_IRQ_ROUTING */ default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); } @@ -2112,15 +2411,15 @@ EXPORT_SYMBOL_GPL(kvm_handle_fault_on_reboot); static int kvm_reboot(struct notifier_block *notifier, unsigned long val, void *v) { - if (val == SYS_RESTART) { - /* - * Some (well, at least mine) BIOSes hang on reboot if - * in vmx root mode. - */ - printk(KERN_INFO "kvm: exiting hardware virtualization\n"); - kvm_rebooting = true; - on_each_cpu(hardware_disable, NULL, 1); - } + /* + * Some (well, at least mine) BIOSes hang on reboot if + * in vmx root mode. + * + * And Intel TXT required VMX off for all cpu when system shutdown. + */ + printk(KERN_INFO "kvm: exiting hardware virtualization\n"); + kvm_rebooting = true; + on_each_cpu(hardware_disable, NULL, 1); return NOTIFY_OK; } @@ -2301,7 +2600,7 @@ int kvm_init(void *opaque, unsigned int vcpu_size, bad_pfn = page_to_pfn(bad_page); - if (!alloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) { + if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) { r = -ENOMEM; goto out_free_0; } @@ -2353,9 +2652,6 @@ int kvm_init(void *opaque, unsigned int vcpu_size, kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out; -#ifndef CONFIG_X86 - msi2intx = 0; -#endif return 0;