Messages in this thread Patch in this message | | | Date | Sat, 21 Nov 2009 13:41:56 GMT | From | tip-bot for Peter Zijlstra <> | Subject | [tip:perf/core] perf: Optimize perf_event_comm_ctx() |
| |
Commit-ID: f6595f3a9680c86b6332f881a7ae2cbbcfdc8619 Gitweb: http://git.kernel.org/tip/f6595f3a9680c86b6332f881a7ae2cbbcfdc8619 Author: Peter Zijlstra <a.p.zijlstra@chello.nl> AuthorDate: Fri, 20 Nov 2009 22:19:47 +0100 Committer: Ingo Molnar <mingo@elte.hu> CommitDate: Sat, 21 Nov 2009 14:11:36 +0100
perf: Optimize perf_event_comm_ctx()
Remove a rcu_read_{,un}lock() pair and a few conditionals.
We can remove the rcu_read_lock() by increasing the scope of one in the calling function.
We can do away with the system_state check if the machine still boots after this patch (seems to be the case).
We can do away with the list_empty() check because the bare list_for_each_entry_rcu() reduces to that now that we've removed everything else.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <20091120212508.527608793@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu> --- kernel/perf_event.c | 7 +------ 1 files changed, 1 insertions(+), 6 deletions(-)
diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 2afb305..4deefaa 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -3374,15 +3374,10 @@ static void perf_event_comm_ctx(struct perf_event_context *ctx, { struct perf_event *event; - if (system_state != SYSTEM_RUNNING || list_empty(&ctx->event_list)) - return; - - rcu_read_lock(); list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { if (perf_event_comm_match(event)) perf_event_comm_output(event, comm_event); } - rcu_read_unlock(); } static void perf_event_comm_event(struct perf_comm_event *comm_event) @@ -3401,11 +3396,11 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) comm_event->event_id.header.size = sizeof(comm_event->event_id) + size; + rcu_read_lock(); cpuctx = &get_cpu_var(perf_cpu_context); perf_event_comm_ctx(&cpuctx->ctx, comm_event); put_cpu_var(perf_cpu_context); - rcu_read_lock(); /* * doesn't really matter which of the child contexts the * events ends up in.
| |