Commit Graph

117 Commits

Author SHA1 Message Date
Tejun Heo
048c852051 perf: Fix resource leak in failure path of perf_event_open()
perf_event_open() kfrees event after init failure which doesn't
release all resources allocated by perf_event_alloc().  Use
free_event() instead.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@au1.ibm.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: <stable@kernel.org>
LKML-Reference: <4BDBE237.1040809@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-05-01 13:11:25 +02:00
Tejun Heo
336f5899d2 Merge branch 'master' into export-slabh 2010-04-05 11:37:28 +09:00
Frederic Weisbecker
26d80aa782 perf: Always build the stub perf_arch_fetch_caller_regs version
Now that software events use perf_arch_fetch_caller_regs() too, we
need the stub version to be always built in for archs that don't
implement it.

Fixes the following build error in PARISC:

	kernel/built-in.o: In function `perf_event_task_sched_out':
	(.text.perf_event_task_sched_out+0x54): undefined reference to `perf_arch_fetch_caller_regs'

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
2010-04-03 12:22:05 +02:00
Mike Galbraith
8bb39f9aa0 perf: Fix 'perf sched record' deadlock
perf sched record can deadlock a box should the holder of
handle->data->lock take an interrupt, and then attempt to
acquire an rq lock held by a CPU trying to acquire the
same lock. Disable interrupts.

   CPU0                            CPU1
   sched event with rq->lock held
                                   grab handle->data->lock
   spin on handle->data->lock
                                   interrupt
                                   try to grab rq->lock

Reported-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Tested-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <1269598293.6174.8.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-02 19:30:05 +02:00
Frederic Weisbecker
e49a5bd381 perf: Use hot regs with software sched switch/migrate events
Scheduler's task migration events don't work because they always
pass NULL regs perf_sw_event(). The event hence gets filtered
in perf_swevent_add().

Scheduler's context switches events use task_pt_regs() to get
the context when the event occured which is a wrong thing to
do as this won't give us the place in the kernel where we went
to sleep but the place where we left userspace. The result is
even more wrong if we switch from a kernel thread.

Use the hot regs snapshot for both events as they belong to the
non-interrupt/exception based events family. Unlike page faults
or so that provide the regs matching the exact origin of the event,
we need to save the current context.

This makes the task migration event working and fix the context
switch callchains and origin ip.

Example: perf record -a -e cs

Before:

    10.91%      ksoftirqd/0                  0  [k] 0000000000000000
                |
                --- (nil)
                    perf_callchain
                    perf_prepare_sample
                    __perf_event_overflow
                    perf_swevent_overflow
                    perf_swevent_add
                    perf_swevent_ctx_event
                    do_perf_sw_event
                    __perf_sw_event
                    perf_event_task_sched_out
                    schedule
                    run_ksoftirqd
                    kthread
                    kernel_thread_helper

After:

    23.77%  hald-addon-stor  [kernel.kallsyms]  [k] schedule
            |
            --- schedule
               |
               |--60.00%-- schedule_timeout
               |          wait_for_common
               |          wait_for_completion
               |          blk_execute_rq
               |          scsi_execute
               |          scsi_execute_req
               |          sr_test_unit_ready
               |          |
               |          |--66.67%-- sr_media_change
               |          |          media_changed
               |          |          cdrom_media_changed
               |          |          sr_block_media_changed
               |          |          check_disk_change
               |          |          cdrom_open

v2: Always build perf_arch_fetch_caller_regs() now that software
events need that too. They don't need it from modules, unlike trace
events, so we keep the EXPORT_SYMBOL in trace_event_perf.c

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: David Miller <davem@davemloft.net>
2010-04-01 08:26:31 +02:00
Tejun Heo
5a0e3ad6af include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files.  percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.

percpu.h -> slab.h dependency is about to be removed.  Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability.  As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.

  http://userweb.kernel.org/~tj/misc/slabh-sweep.py

The script does the followings.

* Scan files for gfp and slab usages and update includes such that
  only the necessary includes are there.  ie. if only gfp is used,
  gfp.h, if slab is used, slab.h.

* When the script inserts a new include, it looks at the include
  blocks and try to put the new include such that its order conforms
  to its surrounding.  It's put in the include block which contains
  core kernel includes, in the same order that the rest are ordered -
  alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
  doesn't seem to be any matching order.

* If the script can't find a place to put a new include (mostly
  because the file doesn't have fitting include block), it prints out
  an error message indicating which .h file needs to be added to the
  file.

The conversion was done in the following steps.

1. The initial automatic conversion of all .c files updated slightly
   over 4000 files, deleting around 700 includes and adding ~480 gfp.h
   and ~3000 slab.h inclusions.  The script emitted errors for ~400
   files.

2. Each error was manually checked.  Some didn't need the inclusion,
   some needed manual addition while adding it to implementation .h or
   embedding .c file was more appropriate for others.  This step added
   inclusions to around 150 files.

3. The script was run again and the output was compared to the edits
   from #2 to make sure no file was left behind.

4. Several build tests were done and a couple of problems were fixed.
   e.g. lib/decompress_*.c used malloc/free() wrappers around slab
   APIs requiring slab.h to be added manually.

5. The script was run on all .h files but without automatically
   editing them as sprinkling gfp.h and slab.h inclusions around .h
   files could easily lead to inclusion dependency hell.  Most gfp.h
   inclusion directives were ignored as stuff from gfp.h was usually
   wildly available and often used in preprocessor macros.  Each
   slab.h inclusion directive was examined and added manually as
   necessary.

6. percpu.h was updated not to include slab.h.

7. Build test were done on the following configurations and failures
   were fixed.  CONFIG_GCOV_KERNEL was turned off for all tests (as my
   distributed build env didn't work with gcov compiles) and a few
   more options had to be turned off depending on archs to make things
   build (like ipr on powerpc/64 which failed due to missing writeq).

   * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
   * powerpc and powerpc64 SMP allmodconfig
   * sparc and sparc64 SMP allmodconfig
   * ia64 SMP allmodconfig
   * s390 SMP allmodconfig
   * alpha SMP allmodconfig
   * um on x86_64 SMP allmodconfig

8. percpu.h modifications were reverted so that it could be applied as
   a separate patch and serve as bisection point.

Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.

Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-30 22:02:32 +09:00
Frederic Weisbecker
dcd5c1662d perf: Fix unexported generic perf_arch_fetch_caller_regs
perf_arch_fetch_caller_regs() is exported for the overriden x86
version, but not for the generic weak version.

As a general rule, weak functions should not have their symbol
exported in the same file they are defined.

So let's export it on trace_event_perf.c as it is used by trace
events only.

This fixes:

	ERROR: ".perf_arch_fetch_caller_regs" [fs/xfs/xfs.ko] undefined!
	ERROR: ".perf_arch_fetch_caller_regs" [arch/powerpc/platforms/cell/spufs/spufs.ko] undefined!

-v2: And also only build it if trace events are enabled.
-v3: Fix changelog mistake

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1268697902-9518-1-git-send-regression-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-17 12:26:49 +01:00
Paul Mackerras
220b140b52 perf_event: Fix oops triggered by cpu offline/online
Anton Blanchard found that he could reliably make the kernel hit a
BUG_ON in the slab allocator by taking a cpu offline and then online
while a system-wide perf record session was running.

The reason is that when the cpu comes up, we completely reinitialize
the ctx field of the struct perf_cpu_context for the cpu.  If there is
a system-wide perf record session running, then there will be a struct
perf_event that has a reference to the context, so its refcount will
be 2.  (The perf_event has been removed from the context's group_entry
and event_entry lists by perf_event_exit_cpu(), but that doesn't
remove the perf_event's reference to the context and doesn't decrement
the context's refcount.)

When the cpu comes up, perf_event_init_cpu() gets called, and it calls
__perf_event_init_context() on the cpu's context.  That resets the
refcount to 1.  Then when the perf record session finishes and the
perf_event is closed, the refcount gets decremented to 0 and the
context gets kfreed after an RCU grace period.  Since the context
wasn't kmalloced -- it's part of a per-cpu variable -- bad things
happen.

In fact we don't need to completely reinitialize the context when the
cpu comes up.  It's sufficient to initialize the context once at boot,
but we need to do it for all possible cpus.

This moves the context initialization to happen at boot time.  With
this, we don't trash the refcount and the context never gets kfreed,
and we don't hit the BUG_ON.

Reported-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Tested-by: Anton Blanchard <anton@samba.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <stable@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-11 12:43:51 +01:00
Frederic Weisbecker
97d5a22005 perf: Drop the obsolete profile naming for trace events
Drop the obsolete "profile" naming used by perf for trace events.
Perf can now do more than simple events counting, so generalize
the API naming.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Jason Baron <jbaron@redhat.com>
2010-03-10 14:47:18 +01:00
Frederic Weisbecker
c530665c31 perf: Take a hot regs snapshot for trace events
We are taking a wrong regs snapshot when a trace event triggers.
Either we use get_irq_regs(), which gives us the interrupted
registers if we are in an interrupt, or we use task_pt_regs()
which gives us the state before we entered the kernel, assuming
we are lucky enough to be no kernel thread, in which case
task_pt_regs() returns the initial set of regs when the kernel
thread was started.

What we want is different. We need a hot snapshot of the regs,
so that we can get the instruction pointer to record in the
sample, the frame pointer for the callchain, and some other
things.

Let's use the new perf_fetch_caller_regs() for that.

Comparison with perf record -e lock: -R -a -f -g
Before:

        perf  [kernel]                   [k] __do_softirq
               |
               --- __do_softirq
                  |
                  |--55.16%-- __open
                  |
                   --44.84%-- __write_nocancel

After:

            perf  [kernel]           [k] perf_tp_event
               |
               --- perf_tp_event
                  |
                  |--41.07%-- lock_acquire
                  |          |
                  |          |--39.36%-- _raw_spin_lock
                  |          |          |
                  |          |          |--7.81%-- hrtimer_interrupt
                  |          |          |          smp_apic_timer_interrupt
                  |          |          |          apic_timer_interrupt

The old case was producing unreliable callchains. Now having
right frame and instruction pointers, we have the trace we
want.

Also syscalls and kprobe events already have the right regs,
let's use them instead of wasting a retrieval.

v2: Follow the rename perf_save_regs() -> perf_fetch_caller_regs()

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Archs <linux-arch@vger.kernel.org>
2010-03-10 14:40:38 +01:00
Frederic Weisbecker
5331d7b846 perf: Introduce new perf_fetch_caller_regs() for hot regs snapshot
Events that trigger overflows by interrupting a context can
use get_irq_regs() or task_pt_regs() to retrieve the state
when the event triggered. But this is not the case for some
other class of events like trace events as tracepoints are
executed in the same context than the code that triggered
the event.

It means we need a different api to capture the regs there,
namely we need a hot snapshot to get the most important
informations for perf: the instruction pointer to get the
event origin, the frame pointer for the callchain, the code
segment for user_mode() tests (we always use __KERNEL_CS as
trace events always occur from the kernel) and the eflags
for further purposes.

v2: rename perf_save_regs to perf_fetch_caller_regs as per
Masami's suggestion.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Archs <linux-arch@vger.kernel.org>
2010-03-10 14:39:35 +01:00
Peter Zijlstra
d4944a0666 perf: Provide better condition for event rotation
Try to avoid useless rotation and PMU disables.

[ Could be improved by keeping a nr_runnable count to better account
  for the < PERF_STAT_INACTIVE counters ]

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-10 13:22:36 +01:00
Peter Zijlstra
32975a4f11 perf: Optimize perf_disable
Currently we always call hw_perf_disable(), even if its already disabled,
this seems superflous, esp. since it cannot be made NMI safe (see further
patches).

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-10 13:22:25 +01:00
Peter Zijlstra
3f6da39053 perf: Rework and fix the arch CPU-hotplug hooks
Remove the hw_perf_event_*() hotplug hooks in favour of per PMU hotplug
notifiers. This has the advantage of reducing the static weak interface
as well as exposing all hotplug actions to the PMU.

Use this to fix x86 hotplug usage where we did things in ONLINE which
should have been done in UP_PREPARE or STARTING.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
LKML-Reference: <20100305154128.736225361@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-10 13:22:24 +01:00
Peter Zijlstra
dc1d628a67 perf: Provide generic perf_sample_data initialization
This makes it easier to extend perf_sample_data and fixes a bug on arm
and sparc, which failed to set ->raw to NULL, which can cause crashes
when combined with PERF_SAMPLE_RAW.

It also optimizes PowerPC and tracepoint, because the struct
initialization is forced to zero out the whole structure.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Jean Pihet <jpihet@mvista.com>
Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: David S. Miller <davem@davemloft.net>
Cc: Jamie Iles <jamie.iles@picochip.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: stable@kernel.org
LKML-Reference: <20100304140100.315416040@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-10 13:22:23 +01:00
Ingo Molnar
548b841669 Merge commit 'v2.6.34-rc1' into perf/urgent
Conflicts:
	tools/perf/util/probe-event.c

Merge reason: Pick up -rc1 and resolve the conflict as well.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-09 17:11:53 +01:00
Andi Kleen
c9be0a36f9 sysdev: Pass attribute in sysdev_class attributes show/store
Passing the attribute to the low level IO functions allows all kinds
of cleanups, by sharing low level IO code without requiring
an own function for every piece of data.

Also drivers can extend the attributes with own data fields
and use that in the low level function.

Similar to sysdev_attributes and normal attributes.

This is a tree-wide sweep, converting everything in one go.

No functional changes in this patch other than passing the new
argument everywhere.

Tested on x86, the non x86 parts are uncompiled.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-03-07 17:04:47 -08:00
Jiri Slaby
78d7d407b6 kernel core: use helpers for rlimits
Make sure compiler won't do weird things with limits.  E.g.  fetching them
twice may return 2 different values after writable limits are implemented.

I.e.  either use rlimit helpers added in commit 3e10e716ab ("resource:
add helpers for fetching rlimits") or ACCESS_ONCE if not applicable.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: john stultz <johnstul@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 11:26:33 -08:00
Peter Zijlstra
320ebf09cb perf, x86: Restrict the ANY flag
The ANY flag can show SMT data of another task (like 'top'),
so we want to disable it when system-wide profiling is
disabled.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 15:06:46 +01:00
Linus Torvalds
6556a67435 Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (172 commits)
  perf_event, amd: Fix spinlock initialization
  perf_event: Fix preempt warning in perf_clock()
  perf tools: Flush maps on COMM events
  perf_events, x86: Split PMU definitions into separate files
  perf annotate: Handle samples not at objdump output addr boundaries
  perf_events, x86: Remove superflous MSR writes
  perf_events: Simplify code by removing cpu argument to hw_perf_group_sched_in()
  perf_events, x86: AMD event scheduling
  perf_events: Add new start/stop PMU callbacks
  perf_events: Report the MMAP pgoff value in bytes
  perf annotate: Defer allocating sym_priv->hist array
  perf symbols: Improve debugging information about symtab origins
  perf top: Use a macro instead of a constant variable
  perf symbols: Check the right return variable
  perf/scripts: Tag syscall_name helper as not yet available
  perf/scripts: Add perf-trace-python Documentation
  perf/scripts: Remove unnecessary PyTuple resizes
  perf/scripts: Add syscall tracing scripts
  perf/scripts: Add Python scripting engine
  perf/scripts: Remove check-perf-trace from listed scripts
  ...

Fix trivial conflict in tools/perf/util/probe-event.c
2010-02-28 10:20:25 -08:00
Frederic Weisbecker
018cbffe68 Merge commit 'v2.6.33' into perf/core
Merge reason:
	__percpu annotations need the corresponding sparse address
space definition upstream.

Conflicts:
	tools/perf/util/probe-event.c (trivial)
2010-02-27 16:18:46 +01:00
Peter Zijlstra
24691ea964 perf_event: Fix preempt warning in perf_clock()
A recent commit introduced a preemption warning for
perf_clock(), use raw_smp_processor_id() to avoid this, it
really doesn't matter which cpu we use here.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1267198583.22519.684.camel@laptop>
Cc: <stable@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 17:25:00 +01:00
Peter Zijlstra
6e37738a2f perf_events: Simplify code by removing cpu argument to hw_perf_group_sched_in()
Since the cpu argument to hw_perf_group_sched_in() is always
smp_processor_id(), simplify the code a little by removing this argument
and using the current cpu where needed.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: David Miller <davem@davemloft.net>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <1265890918.5396.3.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 10:56:53 +01:00
Stephane Eranian
38331f62c2 perf_events, x86: AMD event scheduling
This patch adds correct AMD NorthBridge event scheduling.

NB events are events measuring L3 cache, Hypertransport traffic. They are
identified by an event code >= 0xe0. They measure events on the
Northbride which is shared by all cores on a package. NB events are
counted on a shared set of counters. When a NB event is programmed in a
counter, the data actually comes from a shared counter. Thus, access to
those counters needs to be synchronized.

We implement the synchronization such that no two cores can be measuring
NB events using the same counters. Thus, we maintain a per-NB allocation
table. The available slot is propagated using the event_constraint
structure.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4b703957.0702d00a.6bf2.7b7d@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 10:56:53 +01:00
Stephane Eranian
d76a0812ac perf_events: Add new start/stop PMU callbacks
In certain situations, the kernel may need to stop and start the same
event rapidly. The current PMU callbacks do not distinguish between stop
and release (i.e., stop + free the resource). Thus, a counter may be
released, then it will be immediately re-acquired. Event scheduling will
again take place with no guarantee to assign the same counter. On some
processors, this may event yield to failure to assign the event back due
to competion between cores.

This patch is adding a new pair of callback to stop and restart a counter
without actually release the underlying counter resource. On stop, the
counter is stopped, its values saved and that's it. On start, the value
is reloaded and counter is restarted (on x86, actual restart is delayed
until perf_enable()).

Signed-off-by: Stephane Eranian <eranian@google.com>
[ added fallback to ->enable/->disable for all other PMUs
  fixed x86_pmu_start() to call x86_pmu.enable()
  merged __x86_pmu_disable into x86_pmu_stop() ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4b703875.0a04d00a.7896.ffffb824@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 10:56:53 +01:00
Peter Zijlstra
3a0304e90a perf_events: Report the MMAP pgoff value in bytes
DaveM reported that currently perf interprets the pgoff value reported by
the MMAP events as a byte range, but the kernel reports it as a page
offset.

Since its broken (and unusable) anyway, change the kernel behaviour (ABI)
to report bytes indeed, avoiding the need for userspace to deal with
PAGE_SIZE things.

Reported-by: David Miller <davem@davemloft.net>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-26 10:56:52 +01:00
Peter Zijlstra
6f93d0a7c8 perf_events: Fix FORK events
Commit 22e19085 ("Honour event state for aux stream data")
introduced a bug where we would drop FORK events.

The thing is that we deliver FORK events to the child process'
event, which at that time will be PERF_EVENT_STATE_INACTIVE
because the child won't be scheduled in (we're in the middle of
fork).

Solve this twice, change the event state filter to exclude only
disabled (STATE_OFF) or worse, and deliver FORK events to the
current (parent).

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Anton Blanchard <anton@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
LKML-Reference: <1266142324.5273.411.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-14 18:10:39 +01:00
Peter Zijlstra
9717e6cd3d perf_events: Optimize perf_event_task_tick()
Pretty much all of the calls do perf_disable/perf_enable cycles, pull
that out to cut back on hardware programming.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-04 09:59:49 +01:00
Mahesh Salgaonkar
cd757645fb perf: Make bp_len type to u64 generic across the arch
Change 'bp_len' type to __u64 to make it work across archs as
the s390 architecture watch point length can be upto 2^64.

reference:
	http://lkml.org/lkml/2010/1/25/212

This is an ABI change that is not backward compatible with
the previous hardware breakpoint info layout integrated in this
development cycle, a rebuilt of perf tools is necessary for
versions based on 2.6.33-rc1 - 2.6.33-rc6 to work with a
kernel based on this patch.

Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: "K. Prasad" <prasad@linux.vnet.ibm.com>
Cc: Maneesh Soni <maneesh@in.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin <schwidefsky@de.ibm.com>
LKML-Reference: <20100130045518.GA20776@in.ibm.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2010-02-04 01:07:12 +01:00
Ingo Molnar
ae7f6711d6 Merge branch 'perf/urgent' into perf/core
Merge reason: We want to queue up a dependent patch. Also update to
              later -rc's.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-29 10:36:22 +01:00
Peter Zijlstra
75c9f3284a perf_events: Fix sample_period transfer on inherit
One problem with frequency driven counters is that we cannot
predict the rate at which they trigger, therefore we have to
start them at period=1, this causes a ramp up effect. However,
if we fail to propagate the stable state on fork each new child
will have to ramp up again. This can lead to significant
artifacts in sample data.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: eranian@google.com
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <1264752266.4283.2121.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-29 09:15:26 +01:00
Peter Zijlstra
abd5071394 perf: Reimplement frequency driven sampling
There was a bug in the old period code that caused intel_pmu_enable_all()
or native_write_msr_safe() to show up quite high in the profiles.

In staring at that code it made my head hurt, so I rewrote it in a
hopefully simpler fashion. Its now fully symetric between tick and
overflow driven adjustments and uses less data to boot.

The only complication is that it basically wants to do a u128 division.
The code approximates that in a rather simple truncate until it fits
fashion, taking care to balance the terms while truncating.

This version does not generate that sampling artefact.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Cc: <stable@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-27 08:39:33 +01:00
Peter Zijlstra
22e190851f perf: Honour event state for aux stream data
Anton reported that perf record kept receiving events even after calling
ioctl(PERF_EVENT_IOC_DISABLE). It turns out that FORK,COMM and MMAP
events didn't respect the disabled state and kept flowing in.

Reported-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Anton Blanchard <anton@samba.org>
LKML-Reference: <1263459187.4244.265.camel@laptop>
CC: stable@kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-21 13:40:40 +01:00
Frederic Weisbecker
329c0e012b perf: Better order flexible and pinned scheduling
When a task gets scheduled in. We don't touch the cpu bound events
so the priority order becomes:

	cpu pinned, cpu flexible, task pinned, task flexible.

So schedule out cpu flexibles when a new task context gets in
and correctly order the groups to schedule in:

	task pinned, cpu flexible, task flexible.

Cpu pinned groups don't need to be touched at this time.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
2010-01-17 13:11:05 +01:00
Frederic Weisbecker
7defb0f879 perf: Don't schedule out/in pinned events on task tick
We don't need to schedule in/out pinned events on task tick,
now that pinned and flexible groups can be scheduled separately.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
2010-01-17 13:09:51 +01:00
Frederic Weisbecker
5b0311e1f2 perf: Allow pinned and flexible groups to be scheduled separately
Tune the scheduling helpers so that we can choose to schedule either
pinned and/or flexible groups from a context.

And while at it, refactor a bit the naming of these helpers to make
these more consistent and flexible.

There is no (intended) change in scheduling behaviour in this
patch.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
2010-01-17 13:08:57 +01:00
Frederic Weisbecker
42cce92f4d perf: Make __perf_event_sched_out static
__perf_event_sched_out doesn't need to be globally available, make
it static.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
2010-01-17 13:08:01 +01:00
Frederic Weisbecker
d6f962b57b perf: Export software-only event group characteristic as a flag
Before scheduling an event group, we first check if a group can go
on. We first check if the group is made of software only events
first, in which case it is enough to know if the group can be
scheduled in.

For that purpose, we iterate through the whole group, which is
wasteful as we could do this check when we add/delete an event to
a group.

So we create a group_flags field in perf event that can host
characteristics from a group of events, starting with a first
PERF_GROUP_SOFTWARE flag that reduces the check on the fast path.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
2010-01-16 12:30:40 +01:00
Frederic Weisbecker
e286417378 perf: Round robin flexible groups of events using list_rotate_left()
This is more proper that doing it through a list_for_each_entry()
that breaks after the first entry.

v2: Don't rotate pinned groups as its not needed to time share
them.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
2010-01-16 12:30:28 +01:00
Frederic Weisbecker
889ff01506 perf/core: Split context's event group list into pinned and non-pinned lists
Split-up struct perf_event_context::group_list into pinned_groups
and flexible_groups (non-pinned).

This first appears to be useless as it duplicates various loops around
the group list handlings.

But it scales better in the fast-path in perf_sched_in(). We don't
anymore iterate twice through the entire list to separate pinned and
non-pinned scheduling. Instead we interate through two distinct lists.

The another desired effect is that it makes easier to define distinct
scheduling rules on both.

Changes in v2:
- Respectively rename pinned_grp_list and
  volatile_grp_list into pinned_groups and flexible_groups as per
  Ingo suggestion.
- Various cleanups

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
2010-01-16 12:27:42 +01:00
Ingo Molnar
61405fea92 Merge branch 'perf/urgent' into perf/core
Merge reason: queue up dependent patch, update to -rc4

Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-13 10:08:50 +01:00
Linus Torvalds
952363c90c Merge branch 'perf-fixes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'perf-fixes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  perf: Fix NULL deref in inheritance code
  perf: Pass appropriate frame pointer to dump_trace()
2009-12-31 11:56:24 -08:00
Peter Zijlstra
05cbaa2853 perf: Fix NULL deref in inheritance code
Liming found a NULL deref when a task has a perf context but no
counters  when it forks.

This can occur in two cases, a race during construction where
the fork hits after installing the context but before the first
counter gets inserted, or more reproducably, a fork after the
last counter is closed (which leaves the context around).

Reported-by: Wang Liming <liming.wang@windriver.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
CC: <stable@kernel.org>
LKML-Reference: <1262185684.7135.222.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-31 13:11:31 +01:00
Li Zefan
07b139c8c8 perf events: Remove CONFIG_EVENT_PROFILE
Quoted from Ingo:

| This reminds me - i think we should eliminate CONFIG_EVENT_PROFILE -
| it's an unnecessary Kconfig complication. If both PERF_EVENTS and
| EVENT_TRACING is enabled we should expose generic tracepoints.
|
| Nor is it limited to event 'profiling', so it has become a misnomer as
| well.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <4B2F1557.2050705@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-28 10:33:06 +01:00
Peter Zijlstra
49f474331e perf events: Remove arg from perf sched hooks
Since we only ever schedule the local cpu, there is no need to pass the
cpu number to the perf sched hooks.

This micro-optimizes things a bit.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-28 09:21:33 +01:00
Roland Dreier
628ff7c1d8 anonfd: Allow making anon files read-only
It seems a couple places such as arch/ia64/kernel/perfmon.c and
drivers/infiniband/core/uverbs_main.c could use anon_inode_getfile()
instead of a private pseudo-fs + alloc_file(), if only there were a way
to get a read-only file.  So provide this by having anon_inode_getfile()
create a read-only file if we pass O_RDONLY in flags.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-12-22 12:27:34 -05:00
Linus Torvalds
eca9dfcd00 Merge branch 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  perf session: Make events_stats u64 to avoid overflow on 32-bit arches
  hw-breakpoints: Fix hardware breakpoints -> perf events dependency
  perf events: Dont report side-band events on each cpu for per-task-per-cpu events
  perf events, x86/stacktrace: Fix performance/softlockup by providing a special frame pointer-only stack walker
  perf events, x86/stacktrace: Make stack walking optional
  perf events: Remove unused perf_counter.h header file
  perf probe: Check new event name
  kprobe-tracer: Check new event/group name
  perf probe: Check whether debugfs path is correct
  perf probe: Fix libdwarf include path for Debian
2009-12-19 09:48:42 -08:00
Peter Zijlstra
5d27c23df0 perf events: Dont report side-band events on each cpu for per-task-per-cpu events
Acme noticed that his FORK/MMAP numbers were inflated by about
the same factor as his cpu-count.

This led to the discovery of a few more sites that need to
respect the event->cpu filter.

Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <20091217121830.215333434@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-17 13:21:36 +01:00
Rusty Russell
f6325e30eb cpumask: use cpu_online in kernel/perf_event.c
Also, we want to check against nr_cpu_ids, not num_possible_cpus().
The latter works, but the correct bounds check is < nr_cpu_ids.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
To: Thomas Gleixner <tglx@linutronix.de>
2009-12-17 11:43:11 +10:30
Linus Torvalds
8aedf8a6ae Merge branch 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (52 commits)
  perf record: Use per-task-per-cpu events for inherited events
  perf record: Properly synchronize child creation
  perf events: Allow per-task-per-cpu counters
  perf diff: Percent calcs should use double values
  perf diff: Change the default sort order to "dso,symbol"
  perf diff: Use perf_session__fprintf_hists just like 'perf record'
  perf report: Fix cut'n'paste error recently introduced
  perf session: Move perf report specific hits out of perf_session__fprintf_hists
  perf tools: Move hist entries printing routines from perf report
  perf report: Generalize perf_session__fprintf_hists()
  perf symbols: Move symbol filtering to event__preprocess_sample()
  perf symbols: Adopt the strlists for dso, comm
  perf symbols: Make symbol_conf global
  perf probe: Fix to show which probe point is not found
  perf probe: Check symbols in symtab/kallsyms
  perf probe: Check build-id of vmlinux
  perf probe: Reject second attempt of adding same-name event
  perf probe: Support event name for --add option
  perf probe: Add glob matching support on --del
  perf probe: Use strlist__for_each macros in probe-event.c
  ...
2009-12-16 12:32:47 -08:00