summaryrefslogtreecommitdiffstats
path: root/kernel/perf_event.c
diff options
context:
space:
mode:
authorPeter Zijlstra <a.p.zijlstra@chello.nl>2009-12-17 13:16:32 +0100
committerIngo Molnar <mingo@elte.hu>2009-12-17 13:21:36 +0100
commit5d27c23df09b702868d9a3bff86ec6abd22963ac (patch)
treece29a1253087067b3a0e4239d0936eede870ab0b /kernel/perf_event.c
parentperf events, x86/stacktrace: Fix performance/softlockup by providing a specia... (diff)
downloadlinux-5d27c23df09b702868d9a3bff86ec6abd22963ac.tar.xz
linux-5d27c23df09b702868d9a3bff86ec6abd22963ac.zip
perf events: Dont report side-band events on each cpu for per-task-per-cpu events
Acme noticed that his FORK/MMAP numbers were inflated by about the same factor as his cpu-count. This led to the discovery of a few more sites that need to respect the event->cpu filter. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <20091217121830.215333434@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to '')
-rw-r--r--kernel/perf_event.c32
1 files changed, 18 insertions, 14 deletions
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 8ab86988bd24..03cc061398d1 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1381,6 +1381,9 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
if (event->state != PERF_EVENT_STATE_ACTIVE)
continue;
+ if (event->cpu != -1 && event->cpu != smp_processor_id())
+ continue;
+
hwc = &event->hw;
interrupts = hwc->interrupts;
@@ -3265,6 +3268,9 @@ static void perf_event_task_output(struct perf_event *event,
static int perf_event_task_match(struct perf_event *event)
{
+ if (event->cpu != -1 && event->cpu != smp_processor_id())
+ return 0;
+
if (event->attr.comm || event->attr.mmap || event->attr.task)
return 1;
@@ -3290,12 +3296,11 @@ static void perf_event_task_event(struct perf_task_event *task_event)
rcu_read_lock();
cpuctx = &get_cpu_var(perf_cpu_context);
perf_event_task_ctx(&cpuctx->ctx, task_event);
- put_cpu_var(perf_cpu_context);
-
if (!ctx)
ctx = rcu_dereference(task_event->task->perf_event_ctxp);
if (ctx)
perf_event_task_ctx(ctx, task_event);
+ put_cpu_var(perf_cpu_context);
rcu_read_unlock();
}
@@ -3372,6 +3377,9 @@ static void perf_event_comm_output(struct perf_event *event,
static int perf_event_comm_match(struct perf_event *event)
{
+ if (event->cpu != -1 && event->cpu != smp_processor_id())
+ return 0;
+
if (event->attr.comm)
return 1;
@@ -3408,15 +3416,10 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
rcu_read_lock();
cpuctx = &get_cpu_var(perf_cpu_context);
perf_event_comm_ctx(&cpuctx->ctx, comm_event);
- put_cpu_var(perf_cpu_context);
-
- /*
- * doesn't really matter which of the child contexts the
- * events ends up in.
- */
ctx = rcu_dereference(current->perf_event_ctxp);
if (ctx)
perf_event_comm_ctx(ctx, comm_event);
+ put_cpu_var(perf_cpu_context);
rcu_read_unlock();
}
@@ -3491,6 +3494,9 @@ static void perf_event_mmap_output(struct perf_event *event,
static int perf_event_mmap_match(struct perf_event *event,
struct perf_mmap_event *mmap_event)
{
+ if (event->cpu != -1 && event->cpu != smp_processor_id())
+ return 0;
+
if (event->attr.mmap)
return 1;
@@ -3564,15 +3570,10 @@ got_name:
rcu_read_lock();
cpuctx = &get_cpu_var(perf_cpu_context);
perf_event_mmap_ctx(&cpuctx->ctx, mmap_event);
- put_cpu_var(perf_cpu_context);
-
- /*
- * doesn't really matter which of the child contexts the
- * events ends up in.
- */
ctx = rcu_dereference(current->perf_event_ctxp);
if (ctx)
perf_event_mmap_ctx(ctx, mmap_event);
+ put_cpu_var(perf_cpu_context);
rcu_read_unlock();
kfree(buf);
@@ -3863,6 +3864,9 @@ static int perf_swevent_match(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs)
{
+ if (event->cpu != -1 && event->cpu != smp_processor_id())
+ return 0;
+
if (!perf_swevent_is_counting(event))
return 0;