linux-stable.git/tools/perf/util/session.c, branch linux-3.12.y

perf session: Do not fail on processing out of order event

2015-01-26T13:39:09+00:00

commit f61ff6c06dc8f32c7036013ad802c899ec590607 upstream.

Linus reported perf report command being interrupted due to processing
of 'out of order' event, with following error:

  Timestamp below last timeslice flush
  0x5733a8 [0x28]: failed to process type: 3

I could reproduce the issue and in my case it was caused by one CPU
(mmap) being behind during record and userspace mmap reader seeing the
data after other CPUs data were already stored.

This is expected under some circumstances because we need to limit the
number of events that we queue for reordering when we receive a
PERF_RECORD_FINISHED_ROUND or when we force flush due to memory
pressure.

Reported-by: Linus Torvalds 
Signed-off-by: Jiri Olsa 
Acked-by: Ingo Molnar 
Cc: Andi Kleen 
Cc: Corey Ashford 
Cc: David Ahern 
Cc: Frederic Weisbecker 
Cc: Ingo Molnar 
Cc: Linus Torvalds 
Cc: Matt Fleming 
Cc: Namhyung Kim 
Cc: Paul Mackerras 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lkml.kernel.org/r/1417016371-30249-1-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo 
[zhangzhiqiang: backport to 3.10:
 - adjust context
 - commit f61ff6c06d struct events_stats was defined in tools/perf/util/event.h
   while 3.10 stable defined in tools/perf/util/hist.h.
 - 3.10 stable there is no pr_oe_time() which used for debug.
 - After the above adjustments, becomes same to the original patch:
   https://github.com/torvalds/linux/commit/f61ff6c06dc8f32c7036013ad802c899ec590607
]
Signed-off-by: Zhiqiang Zhang 
Signed-off-by: Jiri Slaby

perf kvm: Fix kvm report without guestmount.

2014-02-06T19:22:18+00:00

commit ad85ace07a05062ef6b59c35a5e80b6eaee1eee6 upstream.

Currently, if we use perf kvm --guestkallsyms --guestmodules report, we
can not get the perf information from perf data file. All sample are
shown as unknown.

Reproducing steps:
	# perf kvm --guestkallsyms /tmp/kallsyms --guestmodules /tmp/modules record -a sleep 1
	[ perf record: Woken up 1 times to write data ]
	[ perf record: Captured and wrote 0.624 MB perf.data.guest (~27260 samples) ]
	# perf kvm --guestkallsyms /tmp/kallsyms --guestmodules /tmp/modules report |grep %
	   100.00%  [guest/6471]  [unknown]         [g] 0xffffffff8164f330

This bug was introduced by 207b57926 (perf kvm: Fix regression with guest machine creation).
In original code, it uses perf_session__find_machine(), it means we deliver symbol to machine
which has the same pid, if no machine found, deliver it to *default* guest. But if we use
perf_session__findnew_machine() here, if no machine was found, new machine with pid will be built
and added. Then the default guest which with pid == 0 will never get a symbol.

And because the new machine initialized here has no kernel map created, the symbol delivered to
it will be marked as "unknown".

This patch here is to revert commit 207b57926 and fix the SEGFAULT bug in another way.

Verification steps:
	# ./perf kvm --guestkallsyms /home/kallsyms --guestmodules /home/modules record -a sleep 1
	[ perf record: Woken up 1 times to write data ]
	[ perf record: Captured and wrote 0.651 MB perf.data.guest (~28437 samples) ]
	# ./perf kvm --guestkallsyms /home/kallsyms --guestmodules /home/modules report |grep %
	    22.64%    :6471  [guest.kernel.kallsyms]  [g] update_rq_clock.part.70
	    19.99%    :6471  [guest.kernel.kallsyms]  [g] d_free
	    18.46%    :6471  [guest.kernel.kallsyms]  [g] bio_phys_segments
	    16.25%    :6471  [guest.kernel.kallsyms]  [g] dequeue_task
	    12.78%    :6471  [guest.kernel.kallsyms]  [g] __switch_to
	     7.91%    :6471  [guest.kernel.kallsyms]  [g] scheduler_tick
	     1.75%    :6471  [guest.kernel.kallsyms]  [g] native_apic_mem_write
	     0.21%    :6471  [guest.kernel.kallsyms]  [g] apic_timer_interrupt

Signed-off-by: Dongsheng Yang 
Acked-by: David Ahern 
Cc: David Ahern 
Link: http://lkml.kernel.org/r/1387564907-3045-1-git-send-email-yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Greg Kroah-Hartman

perf session: Fix infinite loop on invalid perf.data file

2013-10-04T18:17:46+00:00

perf-record updates the header in the perf.data file at termination.
Without this update perf-report (and other processing built-ins) it
caused an infinite loop when perf report (or something like) called.

This is because the algorithm in __perf_session__process_events()
depends on the data_size which is read from file header.  Use file size
directly instead in this case to do the best-effort processing.

Signed-off-by: Namhyung Kim 
Tested-by: David Ahern 
Tested-by: Sonny Rao 
Acked-by: Ingo Molnar 
Cc: David Ahern 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Paul Mackerras 
Cc: Peter Zijlstra 
Cc: Sonny Rao 
Link: http://lkml.kernel.org/r/1380529188-27193-1-git-send-email-namhyung@kernel.org
Signed-off-by: David Ahern 
[ Reworded warning as per Ingo Molnar suggestion, replaces 'perf.data'
  with session->filename, to precisely identify the data file involved ]
Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Add default handler for mmap2 events

2013-10-04T18:16:04+00:00

Commands that do not implement an mmap2 handler should at least not die
with a segfault when processing files with MMAP2 events.

Signed-off-by: David Ahern 
Link: http://lkml.kernel.org/r/1379900700-5186-5-git-send-email-dsahern@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo

perf session: Check for SIGINT in more loops

2013-09-19T14:32:17+00:00

When processing big files we were not checking if session_done was set
by the SIGINT signal handler, for instance in 'perf report'. Fix it.

Cc: Adrian Hunter 
Cc: David Ahern 
Cc: Frederic Weisbecker 
Cc: Jiri Olsa 
Cc: Mike Galbraith 
Cc: Paul Mackerras 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lkml.kernel.org/n/tip-pyad42lgrtq7xhg2dpsoauq7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Add attr->mmap2 support

2013-09-11T13:09:32+00:00

This patch adds support for the new PERF_RECORD_MMAP2 record type
exposed by the kernel. This is an extended PERF_RECORD_MMAP record.

It adds for each file-backed mapping the device major, minor number and
the inode number and generation.

This triplet uniquely identifies the source of a file-backed mapping. It
can be used to detect identical virtual mappings between processes, for
instance.

The patch will prefer MMAP2 over MMAP.

Signed-off-by: Stephane Eranian 
Cc: Andi Kleen 
Cc: David Ahern 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Link: http://lkml.kernel.org/r/1377079825-19057-3-git-send-email-eranian@google.com
[ Cope with 314add6 "Change machine__findnew_thread() to set thread pid",
  fix 'perf test' regression test entry affected,
  use perf_missing_features.mmap2 to fallback to not using .mmap2 in older kernels,
  so that new tools can work with kernels where this feature is not present ]
Signed-off-by: Arnaldo Carvalho de Melo

perf trace: Handle perf.data files with no tracepoints

2013-09-09T18:50:44+00:00

Before:

  perf trace -i perf.data
  Segmentation fault (core dumped)
  #

After:

 # perf trace -i perf.data
 Data file does not have raw_syscalls:sys_enter events
 #

When there are no tracepoints in a perf.data file the struct pevent
that contains the list of tracepoints that will be used to lookup the
tracepoint id by name will not be populated, causing a NULL deref.

And we don't need to do all that dance to look at pevents for an entry
with a slighly different name to then lookup the tracepoint by its id on
the evlist, just use the perf_evlist__find_tracepoint_by_name() routine,
that will find the tracepoint, if present.

Cc: Adrian Hunter 
Cc: David Ahern 
Cc: Frederic Weisbecker 
Cc: Jiri Olsa 
Cc: Mike Galbraith 
Cc: Paul Mackerras 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lkml.kernel.org/n/tip-egcm21k1e6gcyxpcgjxtmsq3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf session: Separate progress bar update when processing events

2013-09-05T19:19:02+00:00

Currently when processing events in the __perf_session__process_events
function we update a progress bar based on the file_size. During the
same processing we update the progress bar from within
flush_sample_queue which is based on number of samples count.

Having 2 different based updates is causing the progress bar to jump
heavily back and forth giving not much usefull info.

Fixing this by keeping only __perf_session__process_events based
progress bar update. And turning on flush_sample_queue progress bar
update only for final flushing.

This reduces the number of time the progress bar update function is
called and it significantly reduces the loading time for TUI, where the
progress bar update takes quite a lot of time.

Signed-off-by: Jiri Olsa 
Cc: Corey Ashford 
Cc: David Ahern 
Cc: Frederic Weisbecker 
Cc: Ingo Molnar 
Cc: Namhyung Kim 
Cc: Paul Mackerras 
Cc: Peter Zijlstra 
Link: http://lkml.kernel.org/r/20130905091449.GC1100@krava.brq.redhat.com
Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Fix symbol offset computation for some dsos

2013-09-02T17:58:21+00:00

For some dsos (e.g., libc, libpthread, kernel modules) the symbol offset
is huge. e.g.,

qemu-kvm 17238/17242 [007] 762235.640311:
    ffffffff816288a1 __schedule+0x451 ([kernel.kallsyms])
    ffffffff81629609 schedule+0x29 ([kernel.kallsyms])
    ffffffffa00a6ded kvm_vcpu_block+0xffffffffa00a106d (/lib/modules/3.11.0-rc1+/kernel/arch/x86/kvm/kvm.ko)
    ffffffffa00bae6b kvm_arch_vcpu_ioctl_run+0xffffffffa00a118b (/lib/modules/3.11.0-rc1+/kernel/arch/x86/kvm/kvm.ko)
    ffffffffa00a4d7a kvm_vcpu_ioctl+0xffffffffa00a141a (/lib/modules/3.11.0-rc1+/kernel/arch/x86/kvm/kvm.ko)
    ffffffff811a7bdb do_vfs_ioctl+0x8b ([kernel.kallsyms])
    ffffffff811a80c1 sys_ioctl+0x91 ([kernel.kallsyms])
    ffffffff81633182 system_call+0x72 ([kernel.kallsyms])
        7f882a97af27 __GI___ioctl+0x7f882a891007 (/lib64/libc-2.14.90.so)
           100000002 [unknown] ([unknown])

It seems to be maps with a non-0 start. Taking that into account the
offsets are correct:

qemu-kvm 17238/17242 [007] 762235.640311:
    ffffffff816288a1 __schedule+0x451 ([kernel.kallsyms])
    ffffffff81629609 schedule+0x29 ([kernel.kallsyms])
    ffffffffa00a6ded kvm_vcpu_block+0x6d (/lib/modules/3.11.0-rc1+/kernel/arch/x86/kvm/kvm.ko)
    ffffffffa00bae6b kvm_arch_vcpu_ioctl_run+0x18b (/lib/modules/3.11.0-rc1+/kernel/arch/x86/kvm/kvm.ko)
    ffffffffa00a4d7a kvm_vcpu_ioctl+0x41a (/lib/modules/3.11.0-rc1+/kernel/arch/x86/kvm/kvm.ko)
    ffffffff811a7bdb do_vfs_ioctl+0x8b ([kernel.kallsyms])
    ffffffff811a80c1 sys_ioctl+0x91 ([kernel.kallsyms])
    ffffffff81633182 system_call+0x72 ([kernel.kallsyms])
        7f882a97af27 __GI___ioctl+0x7 (/lib64/libc-2.14.90.so)
           100000002 [unknown] ([unknown])

Signed-off-by: David Ahern 
Link: http://lkml.kernel.org/r/1375026512-45826-1-git-send-email-dsahern@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Add support for PERF_SAMPLE_IDENTIFIER

2013-08-29T19:09:31+00:00

Enable parsing of samples with sample format bit PERF_SAMPLE_IDENTIFIER.
In addition, if the kernel supports it, prefer it to selecting
PERF_SAMPLE_ID thereby allowing non-matching sample types.

Signed-off-by: Adrian Hunter 
Cc: David Ahern 
Cc: Frederic Weisbecker 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Mike Galbraith 
Cc: Namhyung Kim 
Cc: Paul Mackerras 
Cc: Peter Zijlstra 
Cc: Stephane Eranian 
Link: http://lkml.kernel.org/r/1377591794-30553-8-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo