]> git.itanic.dy.fi Git - linux-stable/commit
perf test shell stat_bpf_counters: Fix test on Intel
authorNamhyung Kim <namhyung@kernel.org>
Fri, 25 Aug 2023 16:41:51 +0000 (09:41 -0700)
committerArnaldo Carvalho de Melo <acme@redhat.com>
Tue, 29 Aug 2023 17:16:14 +0000 (14:16 -0300)
commit68ca249c964f520af7f8763e22f12bd26b57b870
tree328c667f8ac6bbc095dc168901de24ad06cc3b53
parent11f5710d96afcd569a7c8e00395b714bbea3ce5d
perf test shell stat_bpf_counters: Fix test on Intel

As of now, bpf counters (bperf) don't support event groups.  But the
default perf stat includes topdown metrics if supported (on recent Intel
machines) which require groups.  That makes perf stat exiting.

  $ sudo perf stat --bpf-counter true
  bpf managed perf events do not yet support groups.

Actually the test explicitly uses cycles event only, but it missed to
pass the option when it checks the availability of the command.

Fixes: 2c0cb9f56020d2ea ("perf test: Add a shell test for 'perf stat --bpf-counters' new option")
Reviewed-by: Song Liu <song@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: bpf@vger.kernel.org
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230825164152.165610-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
tools/perf/tests/shell/stat_bpf_counters.sh