linux.git/tools/perf/builtin-stat.c, branch for-next

perf stat: Support inherit events during fork() for bperf

2024-11-02T06:31:08+00:00

bperf has a nice ability to share PMUs, but it still does not support
inherit events during fork(), resulting in some deviations in its stat
results compared with perf.

perf stat result:
$ ./perf stat -e cycles,instructions -- ./perf test -w sqrtloop
   Performance counter stats for './perf test -w sqrtloop':

       2,316,038,116      cycles
       2,859,350,725      instructions

         1.009603637 seconds time elapsed

         1.004196000 seconds user
         0.003950000 seconds sys

bperf stat result:
$ ./perf stat --bpf-counters -e cycles,instructions -- \
      ./perf test -w sqrtloop

   Performance counter stats for './perf test -w sqrtloop':

          18,762,093      cycles
          23,487,766      instructions

         1.008913769 seconds time elapsed

         1.003248000 seconds user
         0.004069000 seconds sys

In order to support event inheritance, two new bpf programs are added
to monitor the fork and exit of tasks respectively. When a task is
created, add it to the filter map to enable counting, and reuse the
`accum_key` of its parent task to count together with the parent task.
When a task exits, remove it from the filter map to disable counting.

After support:
$ ./perf stat --bpf-counters -e cycles,instructions -- \
      ./perf test -w sqrtloop

 Performance counter stats for './perf test -w sqrtloop':

     2,316,252,189      cycles
     2,859,946,547      instructions

       1.009422314 seconds time elapsed

       1.003597000 seconds user
       0.004270000 seconds sys

Signed-off-by: Tengda Wu 
Cc: song@kernel.org
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20241021110201.325617-2-wutengda@huaweicloud.com
Signed-off-by: Namhyung Kim

perf tools: Add fallback for exclude_guest

2024-10-22T16:51:22+00:00

Commit 7b100989b4f6bce70 ("perf evlist: Remove __evlist__add_default")
changed to parse "cycles:P" event instead of creating a new cycles
event for perf record.  But it also changed the way how modifiers are
handled so it doesn't set the exclude_guest bit by default.

It seems Apple M1 PMU requires exclude_guest set and returns EOPNOTSUPP
if not.  Let's add a fallback so that it can work with default events.

Also update perf stat hybrid tests to handle possible u or H modifiers.

Reviewed-by: Ian Rogers 
Reviewed-by: James Clark 
Reviewed-by: Ravi Bangoria 
Acked-by: Kan Liang 
Cc: James Clark 
Cc: Atish Patra 
Cc: Mingwei Zhang 
Cc: Kajol Jain 
Cc: Thomas Richter 
Cc: Palmer Dabbelt 
Link: https://lore.kernel.org/r/20241016062359.264929-2-namhyung@kernel.org
Fixes: 7b100989b4f6bce70 ("perf evlist: Remove __evlist__add_default")
Signed-off-by: Namhyung Kim

perf stat: Disable metric thresholds for CSV and JSON metric-only mode

2024-10-17T19:44:26+00:00

These modes don't use the threshold, so don't compute it saving time
and potentially reducing events.

Signed-off-by: Ian Rogers 
Cc: Yicong Yang 
Cc: Weilin Wang 
Cc: Will Deacon 
Cc: James Clark 
Cc: Mike Leach 
Cc: Leo Yan 
Cc: Sumanth Korikkar 
Cc: Thomas Richter 
Cc: Tim Chen 
Cc: John Garry 
Link: https://lore.kernel.org/r/20241017175356.783793-8-irogers@google.com
Signed-off-by: Namhyung Kim

perf tool_pmu: Rename enum perf_tool_event to tool_pmu_event

2024-10-11T06:40:32+00:00

To better reflect the events listed are from the tool PMU. Rename the
enum values from PERF_TOOL_* to TOOL_PMU__EVENT_*.

Signed-off-by: Ian Rogers 
Acked-by: Namhyung Kim 
Link: https://lore.kernel.org/r/20241002032016.333748-6-irogers@google.com
Signed-off-by: Namhyung Kim

perf tool_pmu: Factor tool events into their own PMU

2024-10-11T06:40:32+00:00

Rather than treat tool events as a special kind of event, create a
tool only PMU where the events/aliases match the existing
duration_time, user_time and system_time events. Remove special
parsing and printing support for the tool events, but add function
calls for when PMU functions are called on a tool_pmu.

Move the tool PMU code in evsel into tool_pmu.c to better encapsulate
the tool event behavior in that file.

Signed-off-by: Ian Rogers 
Acked-by: Namhyung Kim 
Link: https://lore.kernel.org/r/20241002032016.333748-5-irogers@google.com
Signed-off-by: Namhyung Kim

perf stat: Fix affinity memory leaks on error path

2024-10-02T21:58:03+00:00

Missed cleanup when an error occurs.

Fixes: 49de179577e7 ("perf stat: No need to setup affinities when starting a workload")
Signed-off-by: Ian Rogers 
Link: https://lore.kernel.org/r/20241001052327.7052-2-irogers@google.com
Signed-off-by: Namhyung Kim

perf stat: Remove evlist__add_default_attrs use strings

2024-09-26T20:26:11+00:00

add_default_atttributes would add evsels by having pre-created
perf_event_attr, however, this needed fixing for hybrid as the
extended PMU type was necessary for each core PMU. The logic for this
was in an arch specific x86 function and wasn't present for ARM,
meaning that default events weren't being opened on all PMUs on
ARM. Change the creation of the default events to use parse_events and
strings as that will open the events on all PMUs.

Rather than try to detect events on PMUs before parsing, parse the
event but skip its output in stat-display.

The previous order of hardware events was: cycles,
stalled-cycles-frontend, stalled-cycles-backend, instructions. As
instructions is a more fundamental concept the order is changed to:
instructions, cycles, stalled-cycles-frontend, stalled-cycles-backend.

Closes: https://lore.kernel.org/lkml/CAP-5=fVABSBZnsmtRn1uF-k-G1GWM-L5SgiinhPTfHbQsKXb_g@mail.gmail.com/
Acked-by: Namhyung Kim 
Signed-off-by: Ian Rogers 
[Don't display unsupported default events except 'cycles']
Acked-by: Kan Liang 
Signed-off-by: James Clark 
Cc: Yang Jihong 
Cc: Dominique Martinet 
Cc: Colin Ian King 
Cc: Howard Chu 
Cc: Ze Gao 
Cc: Yicong Yang 
Cc: Weilin Wang 
Cc: Will Deacon 
Cc: Mike Leach 
Cc: Jing Zhang 
Cc: Yang Li 
Cc: Leo Yan 
Cc: ak@linux.intel.com
Cc: Athira Rajeev 
Cc: linux-arm-kernel@lists.infradead.org
Cc: Sun Haiyong 
Cc: John Garry 
Link: https://lore.kernel.org/r/20240926144851.245903-4-james.clark@linaro.org
Signed-off-by: Namhyung Kim

perf stat: Stop repeating when ref_perf_stat() returns -1

2024-09-25T22:58:42+00:00

Exit when run_perf_stat() returns an error to avoid continuously
repeating the same error message. It's not expected that COUNTER_FATAL
or internal errors are recoverable so there's no point in retrying.

This fixes the following flood of error messages for permission issues,
for example when perf_event_paranoid==3:
  perf stat -r 1044 -- false

  Error:
  Access to performance monitoring and observability operations is limited.
  ...
  Error:
  Access to performance monitoring and observability operations is limited.
  ...
  (repeating for 1044 times).

Signed-off-by: Levi Yun 
Reviewed-by: James Clark 
Cc: nd@arm.com
Cc: howardchu95@gmail.com
Link: https://lore.kernel.org/r/20240925132022.2650180-3-yeoreum.yun@arm.com
Signed-off-by: Namhyung Kim

perf stat: Close cork_fd when create_perf_stat_counter() failed

2024-09-25T22:58:42+00:00

When create_perf_stat_counter() failed, it doesn't close workload.cork_fd
open in evlist__prepare_workload(). This could make too many open file
error while __run_perf_stat() repeats.

Introduce evlist__cancel_workload to close workload.cork_fd and
wait workload.child_pid until exit to clear child process
when create_perf_stat_counter() is failed.

Signed-off-by: Levi Yun 
Reviewed-by: James Clark 
Reviewed-by: Andi Kleen 
Cc: nd@arm.com
Cc: howardchu95@gmail.com
Link: https://lore.kernel.org/r/20240925132022.2650180-2-yeoreum.yun@arm.com
Signed-off-by: Namhyung Kim

perf evsel: Add accessor for tool_event

2024-09-11T14:28:27+00:00

Currently tool events use a dedicated variable within the evsel. Later
changes will move this to the unused struct perf_event_attr config for
these events. Add an accessor to allow the later change to be well
typed and avoid changing all uses.

Signed-off-by: Ian Rogers 
Link: https://lore.kernel.org/r/20240907050830.6752-4-irogers@google.com
Cc: Ravi Bangoria 
Cc: Sandipan Das 
Cc: Mark Rutland 
Cc: Yang Jihong 
Cc: Dominique Martinet 
Cc: Clément Le Goffic 
Cc: Colin Ian King 
Cc: Howard Chu 
Cc: Ze Gao 
Cc: Yicong Yang 
Cc: Changbin Du 
Cc: Junhao He 
Cc: Peter Zijlstra 
Cc: Adrian Hunter 
Cc: Weilin Wang 
Cc: Arnaldo Carvalho de Melo 
Cc: Jiri Olsa 
Cc: Namhyung Kim 
Cc: Will Deacon 
Cc: James Clark 
Cc: Mike Leach 
Cc: Jing Zhang 
Cc: Leo Yan 
Cc: Oliver Upton 
Cc: Benjamin Gray 
Cc: Andi Kleen 
Cc: Alexander Shishkin 
Cc: Kan Liang 
Cc: Athira Jajeev 
Cc: linux-arm-kernel@lists.infradead.org
Cc: Sun Haiyong 
Cc: Tiezhu Yang 
Cc: Xu Yang 
Cc: John Garry 
Cc: Ingo Molnar 
Cc: Veronika Molnarova 
Cc: Dr. David Alan Gilbert 
Cc: linux-kernel@vger.kernel.org
Cc: linux-perf-users@vger.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo