lkml.org 
[lkml]   [2010]   [May]   [7]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    Patch in this message
    /
    Date
    From
    Subject[tip:perf/core] perf: Fix exit() vs PERF_FORMAT_GROUP
    Commit-ID:  4fd38e4595e2f6c9d27732c042a0e16b2753049c
    Gitweb: http://git.kernel.org/tip/4fd38e4595e2f6c9d27732c042a0e16b2753049c
    Author: Peter Zijlstra <a.p.zijlstra@chello.nl>
    AuthorDate: Thu, 6 May 2010 17:31:38 +0200
    Committer: Ingo Molnar <mingo@elte.hu>
    CommitDate: Fri, 7 May 2010 11:30:17 +0200

    perf: Fix exit() vs PERF_FORMAT_GROUP

    Both Stephane and Corey reported that PERF_FORMAT_GROUP didn't work
    as expected if the task the counters were attached to quit before
    the read() call.

    The cause is that we unconditionally destroy the grouping when we
    remove counters from their context. Fix this by only doing this when
    we free the counter itself.

    Reported-by: Corey Ashford <cjashfor@linux.vnet.ibm.com>
    Reported-by: Stephane Eranian <eranian@google.com>
    Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
    LKML-Reference: <1273160566.5605.404.camel@twins>
    Signed-off-by: Ingo Molnar <mingo@elte.hu>
    ---
    include/linux/perf_event.h | 1 +
    kernel/perf_event.c | 5 +++++
    2 files changed, 6 insertions(+), 0 deletions(-)

    diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
    index c8e3754..bf8f3c0 100644
    --- a/include/linux/perf_event.h
    +++ b/include/linux/perf_event.h
    @@ -522,6 +522,7 @@ struct pmu {
    * enum perf_event_active_state - the states of a event
    */
    enum perf_event_active_state {
    + PERF_EVENT_STATE_FREE = -3,
    PERF_EVENT_STATE_ERROR = -2,
    PERF_EVENT_STATE_OFF = -1,
    PERF_EVENT_STATE_INACTIVE = 0,
    diff --git a/kernel/perf_event.c b/kernel/perf_event.c
    index 3d1552d..f13c3db 100644
    --- a/kernel/perf_event.c
    +++ b/kernel/perf_event.c
    @@ -341,6 +341,9 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
    if (event->state > PERF_EVENT_STATE_OFF)
    event->state = PERF_EVENT_STATE_OFF;

    + if (event->state > PERF_EVENT_STATE_FREE)
    + return;
    +
    /*
    * If this was a group event with sibling events then
    * upgrade the siblings to singleton events by adding them
    @@ -1856,6 +1859,8 @@ int perf_event_release_kernel(struct perf_event *event)
    {
    struct perf_event_context *ctx = event->ctx;

    + event->state = PERF_EVENT_STATE_FREE;
    +
    WARN_ON_ONCE(ctx->parent_ctx);
    mutex_lock(&ctx->mutex);
    perf_event_remove_from_context(event);

    \
     
     \ /
      Last update: 2010-05-07 20:45    [W:0.032 / U:30.420 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site