Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1218408 > unrolled thread

[GIT PULL 0/2] perf/urgent fixes

Back to article view | Back to linux.kernel

Contents

  [GIT PULL 0/2] perf/urgent fixes Arnaldo Carvalho de Melo <acme@kernel.org> - 2015-09-03 18:10 +0200
    Re: [GIT PULL 0/2] perf/urgent fixes Ingo Molnar <mingo@kernel.org> - 2015-09-04 11:10 +0200

#1218408 — [GIT PULL 0/2] perf/urgent fixes

Hi Ingo,

	Please consider pulling,

- Arnaldo

The following changes since commit 5b923564ccf43f92969c9e0fd199c8c5db657039:

  Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent (2015-09-02 09:22:53 +0200)

are available in the git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-urgent-for-mingo

for you to fetch changes up to 53ff6bc37be449f546158a39c528d7814dfb15a1:

  perf tools: Fix use of wrong event when processing exit events (2015-09-02 17:46:26 -0300)

----------------------------------------------------------------
perf/urgent fixes:

- In some cases where perf_event.fork.{pid,tid} should be used we were instead
  using perf_event.comm.{pid,tid}, which is not a problem for for the 'pid'
  case, that sits in the same place in these union_perf_event members, but
  comm.tid sits where fork.ppid is, oops.

  These cases were considered as (potentially) problematic:

   - 'perf script' with !sample_id_all, i.e. only non old kernels without
      perf_event_attr.sample_id_all.

   - intel_pt could be affected when decoding without timestamps, as the exit
     event is only used to flush out data which anyway gets flushed at the
     end of the session.

   - intel_bts also uses the exit event to flush data which would probably not
     cause errors as it would get flushed at the end of the session instead.

  Fix it. (Adrian Hunter)

- Due to relaxing the compiler checks for bison generated files, we missed
  updating one parse_events_add_pmu() caller when this function had its
  prototype changed, fix it. (Jiri Olsa)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

----------------------------------------------------------------
Adrian Hunter (1):
      perf tools: Fix use of wrong event when processing exit events

Jiri Olsa (1):
      perf tools: Fix parse_events_add_pmu caller

 tools/perf/builtin-script.c    | 4 ++--
 tools/perf/util/intel-bts.c    | 2 +-
 tools/perf/util/intel-pt.c     | 2 +-
 tools/perf/util/parse-events.y | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [next] | [standalone]

#1218777

* Arnaldo Carvalho de Melo <acme@kernel.org> wrote:

> Hi Ingo,
> 
> 	Please consider pulling,
> 
> - Arnaldo
> 
> The following changes since commit 5b923564ccf43f92969c9e0fd199c8c5db657039:
> 
>   Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent (2015-09-02 09:22:53 +0200)
> 
> are available in the git repository at:
> 
>   git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-urgent-for-mingo
> 
> for you to fetch changes up to 53ff6bc37be449f546158a39c528d7814dfb15a1:
> 
>   perf tools: Fix use of wrong event when processing exit events (2015-09-02 17:46:26 -0300)
> 
> ----------------------------------------------------------------
> perf/urgent fixes:
> 
> - In some cases where perf_event.fork.{pid,tid} should be used we were instead
>   using perf_event.comm.{pid,tid}, which is not a problem for for the 'pid'
>   case, that sits in the same place in these union_perf_event members, but
>   comm.tid sits where fork.ppid is, oops.
> 
>   These cases were considered as (potentially) problematic:
> 
>    - 'perf script' with !sample_id_all, i.e. only non old kernels without
>       perf_event_attr.sample_id_all.
> 
>    - intel_pt could be affected when decoding without timestamps, as the exit
>      event is only used to flush out data which anyway gets flushed at the
>      end of the session.
> 
>    - intel_bts also uses the exit event to flush data which would probably not
>      cause errors as it would get flushed at the end of the session instead.
> 
>   Fix it. (Adrian Hunter)
> 
> - Due to relaxing the compiler checks for bison generated files, we missed
>   updating one parse_events_add_pmu() caller when this function had its
>   prototype changed, fix it. (Jiri Olsa)
> 
> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
> 
> ----------------------------------------------------------------
> Adrian Hunter (1):
>       perf tools: Fix use of wrong event when processing exit events
> 
> Jiri Olsa (1):
>       perf tools: Fix parse_events_add_pmu caller
> 
>  tools/perf/builtin-script.c    | 4 ++--
>  tools/perf/util/intel-bts.c    | 2 +-
>  tools/perf/util/intel-pt.c     | 2 +-
>  tools/perf/util/parse-events.y | 2 +-
>  4 files changed, 5 insertions(+), 5 deletions(-)

Pulled, thanks a lot Arnaldo!

	Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web