lkml.org 
[lkml]   [2009]   [Jun]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
Subject[Announce] Performance Counters for Linux, v8
We are pleased to announce version 8 of the performance counters 
subsystem for Linux.

This new subsystem adds a new system call (sys_perf_counter_open())
and it provides the new 'perf' tool that makes use of these new
kernel capabilities.

This subsystem and this tool is new in that it tries a new approach
at integrating all things performance analysis under one roof.

There have been many changes since -v7 - see the shortlog below for
details.

There are a lot of new contributors to this code. Many thanks go to:
Peter Zijlstra, Paul Mackerras, Robert Richter, Arnaldo Carvalho de
Melo, Mike Galbraith, Thomas Gleixner, Wu Fengguang, Jaswinder Singh
Rajput, Yong Wang, Frederic Weisbecker, Yinghai Lu, Luis Henriques,
Eric Paris, Arjan van de Ven, Tim Blechmann, Steven Whitehouse,
Jaswinder Singh, H. Peter Anvin, Hidetoshi Seto, Erdem Aktas and
Andrew Morton.

The biggest change in -v8 is a re-focusig of our effort towards
building tools to help various user-space development workflows. The
latest code and perfcounter-tools deal with all sorts of user-space
profiling usage models, they are very fast and are able to look up
DSO symbols regardless of where they are loaded - and try to be easy
to use and easy to configure.

Per-application and system-wide profiling modes are supported - plus
a number of intermediate modes are supported as well via the use of
inherited counters that traverse into child-task hierarchies
automatically and transparently.

With perfcounters there is no daemon needed: if a perfcounters
kernel is booted on a supported CPU (all AMD models and Core2 /
Corei7 / Atom Intel CPUs - both 64-bit and 32-bit user-space is
supported) then profiling can be done straight away.

Profiling sessions are recorded into local files, which can then be
analyzed. There's a number of high-level-overview tools 'perf stat'
and 'perf top' which help one get a quick impression about what to
profile and in what way.

New in -v8 is the 'perf' utility which has merged all the
perfcounters utilities and which exposes all the functionality of
the kernel subsystem, in one uniform and unified way:

mercury:~/tip/tools/perf> perf

usage: perf [--version] [--help] COMMAND [ARGS]

The most commonly used perf commands are:
annotate Read perf.data (created by perf record) and display annotated code
list List all symbolic event types
record Run a command and record its profile into perf.data
report Read perf.data (created by perf record) and display the profile
stat Run a command and gather performance counter statistics
top Run a command and profile it

See 'perf help COMMAND' for more information on a specific command.

There's also a new "record + report" separated profilig workflow
supported: use "perf record ./my-app" to record its profile, then
use "perf report" and all its --sort options to get various
high-level and low level details. Oprofile users will find this
workflow familar.

On the lowest level, 'perf annotate' will annotate the source code
alongside profiling information and assembly code:

$ perf annotate decode_tree_entry

------------------------------------------------
Percent | Source code & Disassembly of /home/mingo/git/git
------------------------------------------------
:
: /home/mingo/git/git: file format elf64-x86-64
:
:
: Disassembly of section .text:
:
: 00000000004a0da0 <decode_tree_entry>:
: *modep = mode;
: return str;
: }
:
: static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size)
: {
3.82 : 4a0da0: 41 54 push %r12
: const char *path;
: unsigned int mode, len;
:
: if (size < 24 || buf[size - 21])
0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx
: *modep = mode;
: return str;
: }
:
: static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size)
: {
0.00 : 4a0da6: 49 89 fc mov %rdi,%r12
0.00 : 4a0da9: 55 push %rbp
3.37 : 4a0daa: 53 push %rbx
: const char *path;
: unsigned int mode, len;
:
: if (size < 24 || buf[size - 21])
0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80>
0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1)
3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80>
: static const char *get_mode(const char *str, unsigned int *modep)
: {
: unsigned char c;
: unsigned int mode = 0;
:
: if (*str == ' ')
1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax
0.39 : 4a0db7: 3c 20 cmp $0x20,%al
0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80>
: return NULL;
:
: while ((c = *str++) != ' ') {
0.06 : 4a0dbb: 89 c2 mov %eax,%edx
: if (c < '0' || c > '7')
1.99 : 4a0dbd: 31 ed xor %ebp,%ebp
: unsigned int mode = 0;
:
: if (*str == ' ')
: return NULL;
:
: while ((c = *str++) != ' ') {
1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx
: if (c < '0' || c > '7')
0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax
0.17 : 4a0dc6: 3c 07 cmp $0x7,%al
0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37>
0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80>
0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax)
16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax
0.14 : 4a0dd3: 3c 07 cmp $0x7,%al
0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80>
: return NULL;
: mode = (mode << 3) + (c - '0');
3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax
: unsigned int mode = 0;
:
: if (*str == ' ')
: return NULL;
:
: while ((c = *str++) != ' ') {
0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx
16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx
: if (c < '0' || c > '7')
: return NULL;
: mode = (mode << 3) + (c - '0');


Those who already use Git will (hopefully) find 'perf' intuitive, as
we've picked up a number of internal libraries from Git to build
this tool so the look-and-feel will be familar. It's very
extensible, new subcommands can be added easily - while there's just
a single new binary in the system.

'perf report' supports multi-key histograms and a rich set of views
of the same performance data - per task or per dso, or a finegrained
per symbol view (and all permutations of these keys).

Most of the user-visible action in -v8 was in the tooling, but the
kernel side code has been revamped all around as well:

- Sampling support for inherited counters

- Performance optimizations to lazy-switch PMU contexts

- Enhanced PowerPC and x86 support.

- Generic tracepoints can be used via perfcounters too

- Fixed-frequency, auto-sampling counters. (they can be used via
the '-F' option in perf record and perf top.)

- Generic "hardware cache" event enumeration method - for those
who want more than just a handful of essential hardware
counters.

- Automatic "fool-proof" event-throttling code to protect against
accidentally too short sampling periods.

- The 'raw events' configuration space has been extended -
every event type that oprofile is able to handle can be
specified via raw perfcounter events as well.

- ... and lots of other changes.

To try/test/check this code, the latest perfcounters tree can be
pulled/cloned from:

git pull \
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git \
perfcounters/core

Or the following patch can be applied to the latest
(v2.6.30-rc8-git3) upstream -git Linux kernel:

http://redhat.com/~mingo/perfcounters/perfcounters-v8-v2.6.30-rc8-git3.patch

The 'perf' utility can be built by pulling that tree and by doing:

cd tools/perf/
make
make install

( The combo patch is too large to be posted to lkml - and all the
v7->v8 patches have been posted to lkml already. )

As usual, test feedback, patche, comments and suggestions are
welcome!

Ingo

------------------>
Andrew Morton (1):
mutex: add atomic_dec_and_mutex_lock(), fix

Arjan van de Ven (2):
perf_counter tools: Warning fixes on 32-bit
perf_counter tools: Initialize a stack variable before use

Arnaldo Carvalho de Melo (26):
perf record: Allow specifying a pid to record
perf_counter: First part of 'perf report' conversion to C + elfutils
perf_counter: Implement dso__load using libelf
perf_counter: Use rb_trees in perf report
perf_counter: Add our private copy of list.h
perf_counter: Use rb_tree for symhists and threads in report
perf report: Fix kernel symbol resolution
perf: Don't assume /proc/kallsyms is ordered
perf report: Sort output by symbol usage
perf report: Use hex2long instead of sscanf
perf report: Only load text symbols from kallsyms
perf report: Show the IP only in --verbose mode
perf_counter tools: Move symbol resolution classes from report to libperf
perf_counter tools: struct symbol priv area
perf_counter tools: Consolidate dso methods to load kernel symbols
perf_counter tools: Optionally pass a symbol filter to the dso load routines
perf_counter tools: Convert builtin-top to use libperf symbol routines
perf_counter tools: Shorten the DSO names using cwd
perf_counter tools: Add locking to perf top
perf_counter tools: Add string.[ch]
perf_counter tools: Use hex2u64 in more places
perf_counter tools: Add missing rb_erase in dso__delete_symbols
perf_counter tools: Cover PLT symbols too
perf_counter tools: Fix off-by-one bug in symbol__new
perf report: Fix rbtree bug
perf report: Add -vvv to print the list of threads and its mmaps

Erdem Aktas (1):
perf_counter tools: fix buffer overwrite problem for perf top command

Eric Paris (2):
mutex: add atomic_dec_and_mutex_lock()
mutex: add atomic_dec_and_mutex_lock()

Frederic Weisbecker (3):
perf_counter: Sleep before refresh using poll in perf top
perf_counter tools: Fix warn_unused_result warnings
perf top: Fix zero or negative refresh delay

H. Peter Anvin (1):
mutex: drop "inline" from mutex_lock() inside kernel/mutex.c

Hidetoshi Seto (1):
x86: smarten /proc/interrupts output for new counters

Ingo Molnar (183):
performance counters: documentation
performance counters: x86 support
x86, perfcounters: read out MSR_CORE_PERF_GLOBAL_STATUS with counters disabled
perfcounters: select ANON_INODES
perfcounters, x86: simplify disable/enable of counters
perfcounters, x86: clean up debug code
perfcounters: consolidate global-disable codepaths
perf counters: restructure the API
perf counters: add support for group counters
perf counters: group counter, fixes
perf counters: hw driver API
perf counters: implement PERF_COUNT_CPU_CLOCK
perf counters: consolidate hw_perf save/restore APIs
perf counters: implement PERF_COUNT_TASK_CLOCK
perf counters: add prctl interface to disable/enable counters
perf counters: clean up state transitions
perf counters: update docs
x86: implement atomic64_t on 32-bit
perfcounters: restructure x86 counter math
perfcounters: implement "counter inheritance"
perfcounters: fix task clock counter
perfcounters: add context switch counter
perfcounters: add task migrations counter
perfcounters: add nr-of-faults counter
perfcounters: fix non-intel-perfmon CPUs
perfcounters, x86: fix sw counters on non-PMC CPUs
perfcounters: fix lapic initialization
perfcounters: release CPU context when exiting task counters
perfcounters: flush on setuid exec
perfcounters: use hw_event.disable flag
perfcounters: remove warnings
perfcounters: tweak group scheduling
x86, perfcounters: rename intel_arch_perfmon.h => perf_counter.h
x86, perfcounters: prepare for fixed-mode PMCs
perfcounters: add fixed-mode PMC enumeration
x86, perfcounters: refactor code for fixed-function PMCs
perfcounters: hw ops rename
perfcounters: fix task clock counter
perfcounters: pull inherited counters
perfcounters: fix init context lock
perfcounters: enable lowlevel pmc code to schedule counters
x86, perfcounters: print out the ->used bitmask
perfcounters: remove ->nr_inherited
perfcounters: generalize the counter scheduler
perfcounters: add PERF_COUNT_BUS_CYCLES
x86, perfcounters: add support for fixed-function pmcs
perfcounters: include asm/perf_counter.h only if CONFIG_PERF_COUNTERS=y
perfcounters: fix "perf counters kills oprofile" bug, v2
perfcounters: remove duplicate definition of LOCAL_PERF_VECTOR
perfcounters: fix acpi_idle_do_entry() workaround
perfcounters: fix reserved bits sizing
perf_counter: fix crash on perfmon v1 systems
perf_counter: create Documentation/perf_counter/ and move perfcounters.txt there
perf_counter: add sample user-space to Documentation/perf_counter/
perf_counter tools: tidy up in-kernel dependencies
perf_counter tools: fix build warning in kerneltop.c
perf_counter tools: increase cpu-cycles again
x86, perfcounters: add atomic64_xchg()
perf_counter: fix off task->comm by one
perf_counter tools: include PID in perf-report output, tweak user/kernel printut
perf_counter: copy in Git's top Makefile
perf_counter tools: add in basic glue from Git
perf_counter tools: clean up after introduction of the Git command framework
perf_counter tools: separate kerneltop into 'perf top' and 'perf stat'
perf_counter tools: add help texts
perf_counter tools: add 'perf record' command
perf_counter tools: fix --version
perf_counter tools: add 'perf help'
perf_counter tools: fix 'make install'
perfcounters, sched: remove __task_delta_exec()
perf_counter tools: move helper library to util/*
perf_counter: add/update copyrights
perf_counter tools: add perf-report to the Makefile
perf_counter tools: perf stat: make -l default-on
perf_counter tools: fix infinite loop in perf-report on zeroed event records
perf_counter tools: fix x86 syscall numbers
perf_counter: round-robin per-CPU counters too
perf_counter: initialize the per-cpu context earlier
perf_counter: convert perf_resource_mutex to a spinlock
perf_counter: fix fixed-purpose counter support on v2 Intel-PERFMON
perf_counter tools: remove debug code from builtin-stat.c
perf_counter: x86: Fix throttling
perf_counter: x86: Disallow interval of 1
perf_counter: x86: Protect against infinite loops in intel_pmu_handle_irq()
perf_counter: Remove ACPI quirk
perf stat: handle Ctrl-C
perf_counter: fix threaded task exit
perf_counter, x86: fix zero irq_period counters
perf_counter, x86: speed up the scheduling fast-path
perf_counter: fix counter freeing logic
perf_counter: fix counter inheritance race
perf_counter: Fix context removal deadlock
perf_counter: fix !PERF_COUNTERS build failure
perf_counter tools: increase limits
perf_counter: Increase mmap limit
perf_counter tools: increase limits, fix
perf_counter: Move child perfcounter init to after scheduler init
perf stat: flip around ':k' and ':u' flags
Revert "perf_counter, x86: speed up the scheduling fast-path"
perf_counter: fix warning & lockup
perf_counter, x86: Fix APIC NMI programming
perf_counter, x86: Make NMI lockups more robust
perf_counter: Initialize ->oncpu properly
perf record: Straighten out argv types
perf stat: Remove unused variable
perf record: Convert to Git option parsing
perf_counter tools: Librarize event string parsing
perf stat: Convert to Git option parsing
perf top: Convert to Git option parsing
perf_counter tools: remove the standalone perf-report utility
perf record: Convert to Git option parsing
perf report: Add help/manpage
perf report: add --dump-raw-trace option
perf report: add counter for unknown events
perf report: add more debugging
perf report: Only load text symbols from kallsyms, fix
perf_counter tools: Introduce stricter C code checking
perf_counter tools: Rename output.perf to perf.data
perf_counter tools: Add built-in pager support
perf report: Remove <ctype.h> include
pref_counter: tools: report: Add header printout & prettify
pref_counter: tools: report: Robustify in case of weird events
perf_counter: Fix perf_counter_init_task() on !CONFIG_PERF_COUNTERS
perf_counter tools: report: Add help text for --sort
perf_counter tools: Clean up builtin-stat.c's do_perfstat()
perf_counter tools: Split display into reading and printing
perf_counter tools: Also display time-normalized stat results
perf_counter: Fix cpuctx->task_ctx races
perf_counter: Robustify counter-free logic
perf_counter tools: Print 'CPU utilization factor' in builtin-stat
perf_counter tools: Fix 'make install'
perf_counter tools: Generate per command manpages (and pdf/html, etc.)
perf_counter tools: Fix unknown command help text
perf_counter: Tidy up style details
perf report: Clean up the default output
perf report: Fix column width/alignment of dsos
perf record: Add --append option
perf record: Increase mmap buffering default
perf report: Print more info instead of <unknown> entries
perf_counter tools: Make source code headers more coherent
perf record: Print out the number of events captured
perf report: Print -D to stdout
perf report: Improve sort key recognition
perf report: Handle vDSO symbols properly
perf_counter tools: Clean up old kerneltop references
perf record: Refine capture printout
perf report: Display 100% correctly
perf stat: Print out all arguments
perf report: Add front-entry cache for lookups
perf help: Fix bug when there's no perf-* command around
perf_counter tools: Optimize harder
perf_counter tools: Work around warnings in older GCCs
perf_counter: Fix throttling lock-up
perf report: Clean up event processing
perf report: Split out event processing helpers
perf report: Handle all known event types
perf top: Reduce default filter threshold
perf record/report: Fix PID/COMM handling
perf_counter tools: Build with native optimization
perf_counter tools: Print out symbol parsing errors only if --verbose
perf report: Print out the total number of events
perf_counter tools: Add color terminal output support
perf_counter tools: Dont output in color on !tty
perf report: Bail out if there are unrecognized options/arguments
perf stat: Update help text
perf record: Split out counter creation into a helper function
perf record, top: Implement --freq
perf report: Display user/kernel differentiator
perf_counter tools: Clarify events/samples naming
perf_counter tools: Remove -march=native
perf_counter tools: Sample and display frequency adjustment changes
perf record: Set frequency correctly
perf_counter: Separate out attr->type from attr->config
perf_counter: Implement generalized cache event types
perf_counter tools: Fix cache-event printout
perf_counter tools: Uniform help printouts
perf_counter tools: Tidy up manpage details
perf_counter tools: Prepare for 'perf annotate'
perf_counter tools: Add 'perf annotate' feature
perf_counter tools: Move from Documentation/perf_counter/ to tools/perf/
perf_counter tools: Fix error condition in parse_aliases()
perf annotate: Automatically pick up vmlinux in the local directory
perf annotate: Fix command line help text

Jaswinder Singh (1):
x86: perf_counter.c intel_perfmon_event_map and max_intel_perfmon_events should be static

Jaswinder Singh Rajput (7):
x86: perf_counter remove unwanted hw_perf_enable_all
x86: irqinit_32.c fix compilation warning
x86: prepare perf_counter to add more cpus
x86: AMD Support for perf_counter
x86: decent declarations in perf_counter.c
x86: use pr_info in perf_counter.c
x86: perf_counter cleanup

Luis Henriques (2):
perf_counter: fix alignment in /proc/interrupts
locking, rtmutex.c: Documentation cleanup

Mike Galbraith (23):
perfcounters: throttle on too high IRQ rates
perfcounters: ratelimit performance counter interrupts
perfcounters fix section mismatch warning in perf_counter.c::perf_counters_lapic_init()
perfcounters: fix refcounting bug
perfcounters: fix "perf counters kill oprofile" bug
perf_counters: account NMI interrupts
perfcounters: fix use after free in perf_release()
perf_counter tools: kerneltop: add real-time data acquisition thread
perf_counter tools: kerneltop: display per function percentage along with event count
perf_counter tools: fix build error
perf_counter, x86: clean up throttling printk
perf top: fix segfault
perf top: Reduce display overhead
perf top: Remove leftover NMI/IRQ bits
perf top: fix typo in -d option
perf record: Fix the profiling of existing pid or whole box
perf_counter tools: Document '--' option parsing terminator
perf_counter tools: Fix top symbol table dump typo
perf_counter tools: Fix top symbol table max_ip typo
perf_counter tools: Guard against record damaging existing files
perf_counter tools: Make .gitignore reflect perf_counter tools files
perf_counter tools: Cleanup Makefile
perf_counter tools: Fix uninitialized variable in perf-report.c

Paul Mackerras (62):
perf_counter: Fix return value from dummy hw_perf_counter_init
perf_counter: Fix the cpu_clock software counter
perf_counter: Add optional hw_perf_group_sched_in arch function
perf_counter: Add dummy perf_counter_print_debug function
powerpc/perf_counter: Add perf_counter system call on powerpc
powerpc: Provide a way to defer perf counter work until interrupts are enabled
powerpc/perf_counter: Add generic support for POWER-family PMU hardware
powerpc/perf_counter: Add support for PPC970 family
powerpc/perf_counter: Add support for POWER6
perf_counter: Always schedule all software counters in
powerpc/perf_counter: Make sure PMU gets enabled properly
perf_counter: Add support for pinned and exclusive counter groups
perf_counter: Add counter enable/disable ioctls
perf_counters: make software counters work as per-cpu counters
perf_counters: allow users to count user, kernel and/or hypervisor events
perfcounters: fix refcounting bug, take 2
perfcounters: make context switch and migration software counters work again
perfcounters/powerpc: Make exclude_kernel bit work on Apple G5 processors
perfcounters/powerpc: Add support for POWER5 processors
perfcounters: fix a few minor cleanliness issues
perfcounters: provide expansion room in the ABI
perfcounters/powerpc: fix oops with multiple counters in a group
perfcounters/powerpc: add support for POWER5+ processors
perfcounters/powerpc: add support for POWER4 processors
perf_counter: abstract wakeup flag setting in core to fix powerpc build
perf_counter: powerpc: clean up perc_counter_interrupt
perf_counter: fix type/event_id layout on big-endian systems
perf_counter: add an mmap method to allow userspace to read hardware counters
perf_counter tools: remove glib dependency and fix bugs in kerneltop.c
perf_counter: update documentation
perf_counter: record time running and time enabled for each counter
perf_counter: powerpc: only reserve PMU hardware when we need it
perf_counter: make it possible for hw_perf_counter_init to return error codes
perf_counter tools: optionally scale counter values in perfstat mode
perf_counter: fix powerpc build
perf_counter: powerpc: set sample enable bit for marked instruction events
perf_counter: add MAINTAINERS entry
perf_counter: powerpc: add nmi_enter/nmi_exit calls
perf_counter: powerpc: allow use of limited-function counters
perf_counter: update copyright notice
perf_counter: Put whole group on when enabling group leader
perf_counter: don't count scheduler ticks as context switches
perf_counter: call atomic64_set for counter->count
perf_counter: call hw_perf_save_disable/restore around group_sched_in
perf_counter: powerpc: use u64 for event codes internally
perf_counter: allow arch to supply event misc flags and instruction pointer
perf_counter: powerpc: supply more precise information on counter overflow events
perf_counter: powerpc: initialize cpuhw pointer before use
perf_counter: Dynamically allocate tasks' perf_counter_context struct
perf_counter: Optimize context switch between identical inherited contexts
perf_counter: powerpc: Implement interrupt throttling
perf_counter: Fix race in attaching counters to tasks and exiting
perf_counter: Don't swap contexts containing locked mutex
perf_counter: Provide functions for locking and pinning the context for a task
perf_counter: Allow software counters to count while task is not running
perf_counter: Initialize per-cpu context earlier on cpu up
perf_counter: Fix cpu migration counter
perf_counter: Remove unused prev_state field
perf_counter: powerpc: Fix event alternative code generation on POWER5/5+
perf_counter: powerpc: Fix race causing "oops trying to read PMC0" errors
perf_counter: powerpc: Use new identifier names in powerpc-specific code
perf_counter: Fix lockup with interrupting counters

Peter Zijlstra (169):
perfcounters: IRQ and NMI support on AMD CPUs
perfcounters: IRQ and NMI support on AMD CPUs, fix
x86: perf_counter cleanup
perf_counter: x86: fix 32-bit irq_period assumption
perf_counter: use list_move_tail()
perf_counter: add comment to barrier
perf_counter: x86: use ULL postfix for 64bit constants
perf_counter: software counter event infrastructure
perf_counter: provide pagefault software events
perf_counter: provide major/minor page fault software events
perf_counter: hrtimer based sampling for software time events
perf_counter: add an event_list
perf_counter: fix hrtimer sampling
perf_counter: fix uninitialized usage of event_list
perf_counter: generic context switch event
perf_counter: fix up counter free paths
perf_counter: hook up the tracepoint events
perf_counter: revamp syscall input ABI
perf_counter: unify irq output code
perf_counter: remove the event config bitfields
perf_counter: avoid recursion
perf_counter: new output ABI - part 1
perf_counter tools: update to new syscall ABI
perf_counter tools: use mmap() output
perf_counter tools: remove glib dependency and fix bugs in kerneltop.c, fix poll()
perf_counter: fix perf_poll()
perf_counter: more elaborate write API
perf_counter: output objects
perf_counter: sanity check on the output API
perf_counter: optionally provide the pid/tid of the sampled task
perf_counter: kerneltop: mmap_pages argument
perf_counter: kerneltop: output event support
perf_counter: allow and require one-page mmap on counting counters
perf_counter: unify and fix delayed counter wakeup
perf_counter: fix update_userpage()
perf_counter: kerneltop: simplify data_head read
perf_counter: executable mmap() information
perf_counter: kerneltop: parse the mmap data stream
perf_counter: x86: proper error propagation for the x86 hw_perf_counter_init()
perf_counter: small cleanup of the output routines
perf_counter: re-arrange the perf_event_type
perf_counter tools: kerneltop: update event_types
perf_counter: provide generic callchain bits
perf_counter: x86: callchain support
perf_counter: pmc arbitration
perf_counter: move the event overflow output bits to record_type
perf_counter: per event wakeups
perf_counter: kerneltop: update to new ABI
perf_counter: add more context information
perf_counter: update mmap() counter read
perf_counter: update mmap() counter read, take 2
perf_counter: add more context information
perf_counter: SIGIO support
perf_counter: generalize pending infrastructure
perf_counter: x86: self-IPI for pending work
perf_counter: theres more to overflow than writing events
perf_counter: fix the mlock accounting
perf_counter: PERF_RECORD_TIME
perf_counter: counter overflow limit
perf_counter: comment the perf_event_type stuff
perf_counter: change event definition
perf_counter: rework context time
perf_counter: rework the task clock software counter
perf_counter: remove rq->lock usage
perf_counter: minimize context time updates
perf_counter: fix NMI race in task clock
perf_counter: provide misc bits in the event header
perf_counter: use misc field to widen type
perf_counter: kerneltop: keep up with ABI changes
perf_counter: add some comments
perf_counter: track task-comm data
perf_counter: some simple userspace profiling
perf_counter: move PERF_RECORD_TIME
perf_counter: allow for data addresses to be recorded
perf_counter: optimize mmap/comm tracking
perf_counter: sysctl for system wide perf counters
perf_counter: log full path names
perf_counter tools: fix Documentation/perf_counter build error
perf_counter: fix race in perf_output_*
perf_counter: fix nmi-watchdog interaction
perf_counter: tool: handle 0-length data files
perf_counter: documentation update
perf_counter: x86: fixup nmi_watchdog vs perf_counter boo-boo
perf_counter: uncouple data_head updates from wakeups
perf_counter: add ioctl(PERF_COUNTER_IOC_RESET)
perf_counter: provide an mlock threshold
perf_counter: fix the output lock
perf_counter: inheritable sample counters
perf_counter: tools: update the tools to support process and inherited counters
perf_counter: optimize perf_counter_task_tick()
perf_counter: rework ioctl()s
perf_counter: add PERF_RECORD_CONFIG
perf_counter: add PERF_RECORD_CPU
perf_counter: fix print debug irq disable
perf_counter: x86: More accurate counter update
perf_counter: x86: Allow unpriviliged use of NMIs
perf_counter: Fix perf_output_copy() WARN to account for overflow
perf_counter: x86: Fix up the amd NMI/INT throttle
perf_counter: Rework the perf counter disable/enable
perf_counter: x86: Robustify interrupt handling
perf_counter: remove perf_disable/enable exports
perf_counter: per user mlock gift
perf_counter: frequency based adaptive irq_period
perf top: update to use the new freq interface
perf_counter: frequency based adaptive irq_period, 32-bit fix
perf_counter: Fix inheritance cleanup code
perf_counter: Fix counter inheritance
perf_counter: Solve the rotate_ctx vs inherit race differently
perf_counter: Log irq_period changes
perf_counter: Optimize disable of time based sw counters
perf_counter: Optimize sched in/out of counters
perf_counter: Fix dynamic irq_period logging
perf_counter: Sanitize counter->mutex
perf_counter: Sanitize context locking
perf_counter: Fix userspace build
perf_counter: Simplify context cleanup
perf_counter: Change pctrl() behaviour
perf_counter: Remove perf_counter_context::nr_enabled
perf_counter: Fix perf-$cmd invokation
perf_counter: Remove unused ABI bits
perf_counter: Make pctrl() affect inherited counters too
perf_counter: Propagate inheritance failures down the fork() path
perf_counter: Fix PERF_COUNTER_CONTEXT_SWITCHES for cpu counters
perf_counter: x86: Expose INV and EDGE bits
perf_counter: x86: Remove interrupt throttle
perf_counter: Generic per counter interrupt throttle
perf report: Fix segfault on unknown symbols
perf report: Fix ELF symbol parsing
perf report: More robust error handling
perf_counter: tools: /usr/lib/debug%s.debug support
perf_counter: tools: report: Add vmlinux support
perf_counter: tools: report: Rework histogram code
perf_counter: tools: report: Dynamic sort/print bits
pref_counter: tools: report: Add --sort option
perf_counter: tools: report: Add comm sorting
pref_counter: tools: report: Add dso sorting
perf_counter tools: report: Implement header output for --sort variants
perf_counter: Fix COMM and MMAP events for cpu wide counters
perf_counter: Clean up task_ctx vs interrupts
perf_counter: Ammend cleanup in fork() fail
perf_counter: Use PID namespaces properly
perf_counter: tools: Expand the COMM,MMAP event synthesizer
perf_counter: tools: Better handle existing data files
perf_counter tools: Remove the last nmi bits
x86: Fix atomic_long_xchg() on 64bit
perf_counter: Add unique counter id
perf_counter: Rename various fields
perf_counter: Remove the last nmi/irq bits
perf_counter: x86: Emulate longer sample periods
perf_counter: Change data head from u32 to u64
perf_counter: Add ioctl for changing the sample period/frequency
perf_counter: Rename perf_counter_hw_event => perf_counter_attr
perf_counter tools: Fix up the ABI shakeup
perf report: Separate out idle threads
perf_counter: Add a comm hook for pure fork()s
perf record: Use long arg for counter period
perf report: Fix comm sorting
perf_counter: Fix race in counter initialization
perf report: Simplify symbol output
perf report: Add consistent spacing rules
perf_counter: Add fork event
perf_counter: Remove munmap stuff
perf_counter tools: Use fork and remove munmap events
x86: Set context.vdso before installing the mapping
perf_counter: Generate mmap events for install_special_mapping()
perf report: Deal with maps
perf_counter: Change PERF_SAMPLE_CONFIG into PERF_SAMPLE_ID
perf_counter: Add PERF_SAMPLE_PERIOD
perf_counter: Fix frequency adjustment for < HZ

Robert Richter (30):
perf_counter, x86: remove X86_FEATURE_ARCH_PERFMON flag for AMD cpus
perf_counter, x86: declare perf_max_counters only for CONFIG_PERF_COUNTERS
perf_counter, x86: add default path to cpu detection
perf_counter, x86: rework pmc_amd_save_disable_all() and pmc_amd_restore_all()
perf_counter, x86: protect per-cpu variables with compile barriers only
perfcounters: rename struct hw_perf_counter_ops into struct pmu
perf_counter, x86: rename struct pmc_x86_ops into struct x86_pmu
perf_counter, x86: make interrupt handler model specific
perf_counter, x86: remove get_status() from struct x86_pmu
perf_counter, x86: remove ack_status() from struct x86_pmu
perf_counter, x86: rename __hw_perf_counter_set_period into x86_perf_counter_set_period
perf_counter, x86: rename intel only functions
perf_counter, x86: modify initialization of struct x86_pmu
perf_counter, x86: make x86_pmu data a static struct
perf_counter, x86: move counter parameters to struct x86_pmu
perf_counter, x86: make pmu version generic
perf_counter, x86: make x86_pmu_read() static inline
perf_counter, x86: rename cpuc->active_mask
perf_counter, x86: generic use of cpuc->active
perf_counter, x86: consistent use of type int for counter index
perf_counter, x86: rework counter enable functions
perf_counter, x86: rework counter disable functions
perf_counter, x86: change and remove pmu initialization checks
perf_counter, x86: implement the interrupt handler for AMD cpus
perf_counter, x86: return raw count with x86_perf_counter_update()
perf_counter, x86: introduce max_period variable
perf_counter, x86: remove vendor check in fixed_mode_idx()
perf_counter, x86: remove unused function argument in intel_pmu_get_status()
perf_counter: update 'perf top' documentation
perf_counter, x86: rename bitmasks to ->used_mask and ->active_mask

Steven Whitehouse (1):
perfcounters: export perf_tpcounter_event

Thomas Gleixner (14):
performance counters: core code
perf counters: protect them against CSTATE transitions
perf counters: clean up 'raw' type API
perf counters: expand use of counter->event
signals: split do_tkill
signals: implement sys_rt_tgsigqueueinfo
x86: hookup sys_rt_tgsigqueueinfo
perf_counter tools: remove build generated files
perfcounter tools: move common defines ... to local header file
perfcounter tools: make rdclock an inline function
perfcounter tools: fix pointer mismatch
perfcounter tools: get the syscall number from arch/*/include/asm/unistd.h
perf_counter tools: Add 'perf list' to list available events
perf_counter tools: Add help for perf list

Tim Blechmann (1):
perf_counter: include missing header

Wu Fengguang (9):
perf_counter tools: Merge common code into perfcounters.h
perf_counter tools: Move perfstat supporting code into perfcounters.h
perf_counter tools: support symbolic event names in kerneltop
perf_counter tools: Reuse event_name() in kerneltop
perf_counter tools: move remaining code into kerneltop.c
perf_counter tools: fix comment for sym_weight()
perf_counter tools: fix event_id type
perf_counter tools: cut down default count for cpu-cycles
perf_counter tools: when no command is feed to perfstat, display help and exit

Yinghai Lu (2):
perf_counter: more barrier in blank weak function
x86: make irqinit_32.c more like irqinit_64.c, v2

Yong Wang (4):
perf_counter/x86: Always use NMI for performance-monitoring interrupt
perf_counter/x86: Remove the IRQ (non-NMI) handling bits
perf_counter: Documentation update
perf_counter tools: Fix incorrect printf formats


MAINTAINERS | 10 +
arch/powerpc/include/asm/hw_irq.h | 39 +
arch/powerpc/include/asm/paca.h | 1 +
arch/powerpc/include/asm/perf_counter.h | 95 +
arch/powerpc/include/asm/reg.h | 2 +
arch/powerpc/include/asm/systbl.h | 2 +-
arch/powerpc/include/asm/unistd.h | 1 +
arch/powerpc/kernel/Makefile | 2 +
arch/powerpc/kernel/asm-offsets.c | 1 +
arch/powerpc/kernel/entry_64.S | 9 +
arch/powerpc/kernel/irq.c | 5 +
arch/powerpc/kernel/perf_counter.c | 1214 ++++++
arch/powerpc/kernel/power4-pmu.c | 557 +++
arch/powerpc/kernel/power5+-pmu.c | 630 ++++
arch/powerpc/kernel/power5-pmu.c | 570 +++
arch/powerpc/kernel/power6-pmu.c | 490 +++
arch/powerpc/kernel/ppc970-pmu.c | 441 +++
arch/powerpc/mm/fault.c | 10 +-
arch/powerpc/platforms/Kconfig.cputype | 1 +
arch/x86/Kconfig | 1 +
arch/x86/ia32/ia32entry.S | 4 +-
arch/x86/include/asm/atomic_32.h | 236 ++
arch/x86/include/asm/entry_arch.h | 2 +-
arch/x86/include/asm/hardirq.h | 2 +
arch/x86/include/asm/hw_irq.h | 2 +
arch/x86/include/asm/intel_arch_perfmon.h | 31 -
arch/x86/include/asm/irq_vectors.h | 8 +-
arch/x86/include/asm/perf_counter.h | 100 +
arch/x86/include/asm/unistd_32.h | 2 +
arch/x86/include/asm/unistd_64.h | 5 +-
arch/x86/kernel/apic/apic.c | 3 +
arch/x86/kernel/cpu/Makefile | 12 +-
arch/x86/kernel/cpu/common.c | 2 +
arch/x86/kernel/cpu/perf_counter.c | 1417 +++++++
arch/x86/kernel/cpu/perfctr-watchdog.c | 4 +-
arch/x86/kernel/entry_64.S | 5 +
arch/x86/kernel/irq.c | 10 +
arch/x86/kernel/irqinit_32.c | 59 +-
arch/x86/kernel/irqinit_64.c | 12 +-
arch/x86/kernel/signal.c | 1 -
arch/x86/kernel/syscall_table_32.S | 2 +
arch/x86/kernel/traps.c | 15 +-
arch/x86/mm/fault.c | 12 +-
arch/x86/oprofile/nmi_int.c | 7 +-
arch/x86/oprofile/op_model_ppro.c | 10 +-
arch/x86/vdso/vdso32-setup.c | 6 +-
arch/x86/vdso/vma.c | 7 +-
drivers/char/sysrq.c | 2 +
fs/exec.c | 9 +
include/asm-generic/atomic.h | 2 +-
include/linux/compat.h | 2 +
include/linux/init_task.h | 10 +
include/linux/kernel_stat.h | 5 +
include/linux/mutex.h | 1 +
include/linux/perf_counter.h | 685 ++++
include/linux/prctl.h | 3 +
include/linux/sched.h | 21 +-
include/linux/signal.h | 2 +
include/linux/syscalls.h | 5 +
init/Kconfig | 35 +
kernel/Makefile | 1 +
kernel/compat.c | 11 +
kernel/exit.c | 16 +-
kernel/fork.c | 12 +
kernel/mutex.c | 27 +-
kernel/perf_counter.c | 4160 +++++++++++++++++++++
kernel/rtmutex.c | 8 +-
kernel/sched.c | 57 +-
kernel/signal.c | 56 +-
kernel/sys.c | 7 +
kernel/sys_ni.c | 3 +
kernel/sysctl.c | 27 +
kernel/timer.c | 3 +
mm/mmap.c | 5 +
tools/perf/.gitignore | 16 +
tools/perf/Documentation/Makefile | 300 ++
tools/perf/Documentation/asciidoc.conf | 91 +
tools/perf/Documentation/manpage-1.72.xsl | 14 +
tools/perf/Documentation/manpage-base.xsl | 35 +
tools/perf/Documentation/manpage-bold-literal.xsl | 17 +
tools/perf/Documentation/manpage-normal.xsl | 13 +
tools/perf/Documentation/manpage-suppress-sp.xsl | 21 +
tools/perf/Documentation/perf-annotate.txt | 29 +
tools/perf/Documentation/perf-help.txt | 38 +
tools/perf/Documentation/perf-list.txt | 25 +
tools/perf/Documentation/perf-record.txt | 42 +
tools/perf/Documentation/perf-report.txt | 26 +
tools/perf/Documentation/perf-stat.txt | 66 +
tools/perf/Documentation/perf-top.txt | 39 +
tools/perf/Documentation/perf.txt | 24 +
tools/perf/Makefile | 929 +++++
tools/perf/builtin-annotate.c | 1355 +++++++
tools/perf/builtin-help.c | 461 +++
tools/perf/builtin-list.c | 20 +
tools/perf/builtin-record.c | 544 +++
tools/perf/builtin-report.c | 1291 +++++++
tools/perf/builtin-stat.c | 339 ++
tools/perf/builtin-top.c | 692 ++++
tools/perf/builtin.h | 26 +
tools/perf/command-list.txt | 10 +
tools/perf/design.txt | 442 +++
tools/perf/perf.c | 428 +++
tools/perf/perf.h | 67 +
tools/perf/util/PERF-VERSION-GEN | 42 +
tools/perf/util/abspath.c | 117 +
tools/perf/util/alias.c | 77 +
tools/perf/util/cache.h | 119 +
tools/perf/util/color.c | 241 ++
tools/perf/util/color.h | 36 +
tools/perf/util/config.c | 873 +++++
tools/perf/util/ctype.c | 26 +
tools/perf/util/environment.c | 9 +
tools/perf/util/exec_cmd.c | 165 +
tools/perf/util/exec_cmd.h | 13 +
tools/perf/util/generate-cmdlist.sh | 24 +
tools/perf/util/help.c | 367 ++
tools/perf/util/help.h | 29 +
tools/perf/util/levenshtein.c | 84 +
tools/perf/util/levenshtein.h | 8 +
tools/perf/util/list.h | 603 +++
tools/perf/util/pager.c | 99 +
tools/perf/util/parse-events.c | 316 ++
tools/perf/util/parse-events.h | 17 +
tools/perf/util/parse-options.c | 508 +++
tools/perf/util/parse-options.h | 174 +
tools/perf/util/path.c | 353 ++
tools/perf/util/quote.c | 481 +++
tools/perf/util/quote.h | 68 +
tools/perf/util/rbtree.c | 383 ++
tools/perf/util/rbtree.h | 171 +
tools/perf/util/run-command.c | 395 ++
tools/perf/util/run-command.h | 93 +
tools/perf/util/sigchain.c | 52 +
tools/perf/util/sigchain.h | 11 +
tools/perf/util/strbuf.c | 359 ++
tools/perf/util/strbuf.h | 137 +
tools/perf/util/string.c | 34 +
tools/perf/util/string.h | 8 +
tools/perf/util/symbol.c | 576 +++
tools/perf/util/symbol.h | 47 +
tools/perf/util/usage.c | 80 +
tools/perf/util/util.h | 410 ++
tools/perf/util/wrapper.c | 206 +
143 files changed, 26321 insertions(+), 122 deletions(-)
create mode 100644 arch/powerpc/include/asm/perf_counter.h
create mode 100644 arch/powerpc/kernel/perf_counter.c
create mode 100644 arch/powerpc/kernel/power4-pmu.c
create mode 100644 arch/powerpc/kernel/power5+-pmu.c
create mode 100644 arch/powerpc/kernel/power5-pmu.c
create mode 100644 arch/powerpc/kernel/power6-pmu.c
create mode 100644 arch/powerpc/kernel/ppc970-pmu.c
delete mode 100644 arch/x86/include/asm/intel_arch_perfmon.h
create mode 100644 arch/x86/include/asm/perf_counter.h
create mode 100644 arch/x86/kernel/cpu/perf_counter.c
create mode 100644 include/linux/perf_counter.h
create mode 100644 kernel/perf_counter.c
create mode 100644 tools/perf/.gitignore
create mode 100644 tools/perf/Documentation/Makefile
create mode 100644 tools/perf/Documentation/asciidoc.conf
create mode 100644 tools/perf/Documentation/manpage-1.72.xsl
create mode 100644 tools/perf/Documentation/manpage-base.xsl
create mode 100644 tools/perf/Documentation/manpage-bold-literal.xsl
create mode 100644 tools/perf/Documentation/manpage-normal.xsl
create mode 100644 tools/perf/Documentation/manpage-suppress-sp.xsl
create mode 100644 tools/perf/Documentation/perf-annotate.txt
create mode 100644 tools/perf/Documentation/perf-help.txt
create mode 100644 tools/perf/Documentation/perf-list.txt
create mode 100644 tools/perf/Documentation/perf-record.txt
create mode 100644 tools/perf/Documentation/perf-report.txt
create mode 100644 tools/perf/Documentation/perf-stat.txt
create mode 100644 tools/perf/Documentation/perf-top.txt
create mode 100644 tools/perf/Documentation/perf.txt
create mode 100644 tools/perf/Makefile
create mode 100644 tools/perf/builtin-annotate.c
create mode 100644 tools/perf/builtin-help.c
create mode 100644 tools/perf/builtin-list.c
create mode 100644 tools/perf/builtin-record.c
create mode 100644 tools/perf/builtin-report.c
create mode 100644 tools/perf/builtin-stat.c
create mode 100644 tools/perf/builtin-top.c
create mode 100644 tools/perf/builtin.h
create mode 100644 tools/perf/command-list.txt
create mode 100644 tools/perf/design.txt
create mode 100644 tools/perf/perf.c
create mode 100644 tools/perf/perf.h
create mode 100755 tools/perf/util/PERF-VERSION-GEN
create mode 100644 tools/perf/util/abspath.c
create mode 100644 tools/perf/util/alias.c
create mode 100644 tools/perf/util/cache.h
create mode 100644 tools/perf/util/color.c
create mode 100644 tools/perf/util/color.h
create mode 100644 tools/perf/util/config.c
create mode 100644 tools/perf/util/ctype.c
create mode 100644 tools/perf/util/environment.c
create mode 100644 tools/perf/util/exec_cmd.c
create mode 100644 tools/perf/util/exec_cmd.h
create mode 100755 tools/perf/util/generate-cmdlist.sh
create mode 100644 tools/perf/util/help.c
create mode 100644 tools/perf/util/help.h
create mode 100644 tools/perf/util/levenshtein.c
create mode 100644 tools/perf/util/levenshtein.h
create mode 100644 tools/perf/util/list.h
create mode 100644 tools/perf/util/pager.c
create mode 100644 tools/perf/util/parse-events.c
create mode 100644 tools/perf/util/parse-events.h
create mode 100644 tools/perf/util/parse-options.c
create mode 100644 tools/perf/util/parse-options.h
create mode 100644 tools/perf/util/path.c
create mode 100644 tools/perf/util/quote.c
create mode 100644 tools/perf/util/quote.h
create mode 100644 tools/perf/util/rbtree.c
create mode 100644 tools/perf/util/rbtree.h
create mode 100644 tools/perf/util/run-command.c
create mode 100644 tools/perf/util/run-command.h
create mode 100644 tools/perf/util/sigchain.c
create mode 100644 tools/perf/util/sigchain.h
create mode 100644 tools/perf/util/strbuf.c
create mode 100644 tools/perf/util/strbuf.h
create mode 100644 tools/perf/util/string.c
create mode 100644 tools/perf/util/string.h
create mode 100644 tools/perf/util/symbol.c
create mode 100644 tools/perf/util/symbol.h
create mode 100644 tools/perf/util/usage.c
create mode 100644 tools/perf/util/util.h
create mode 100644 tools/perf/util/wrapper.c



\
 
 \ /
  Last update: 2009-06-06 22:39    [W:0.162 / U:0.528 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site