summaryrefslogtreecommitdiffstats
path: root/kernel/perf_event.c
diff options
context:
space:
mode:
authorPeter Zijlstra <a.p.zijlstra@chello.nl>2009-11-16 12:45:14 +0100
committerIngo Molnar <mingo@elte.hu>2009-11-16 13:27:45 +0100
commit559fdc3c1b624edb1933a875022fe7e27934d11c (patch)
treeb722805dbebd9584ffb981e2be84385ee0e22c67 /kernel/perf_event.c
parent7255fe2a42c612f2b8fe4c347f0a5f0c97d85a46 (diff)
downloadop-kernel-dev-559fdc3c1b624edb1933a875022fe7e27934d11c.zip
op-kernel-dev-559fdc3c1b624edb1933a875022fe7e27934d11c.tar.gz
perf_event: Optimize perf_output_lock()
The purpose of perf_output_{un,}lock() is to: 1) avoid publishing incomplete data [ possible when publishing a head that is ahead of an entry that is still being written ] 2) guarantee fwd progress [ a simple refcount on pending writers doesn't need to drop to 0, making it so would end up implementing something like forced quiecent states of RCU ] To satisfy the above without undue complexity it serializes between CPUs, this means that a pending writer can only be the same cpu in a nested context, and since (under normal operation) a cpu always makes progress we're good -- if the head is only published when the bottom most writer completes. Now we don't need to disable IRQs in order to serialize between CPUs, disabling preemption ought to be sufficient, esp since we already deal with nesting due to NMIs. This avoids potentially expensive (and needless) local IRQ disable/enable ops. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1258373161.26714.254.camel@laptop> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'kernel/perf_event.c')
-rw-r--r--kernel/perf_event.c21
1 files changed, 11 insertions, 10 deletions
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 6f4ed3b..3256e36 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -2674,20 +2674,21 @@ static void perf_output_wakeup(struct perf_output_handle *handle)
static void perf_output_lock(struct perf_output_handle *handle)
{
struct perf_mmap_data *data = handle->data;
- int cpu;
+ int cur, cpu = get_cpu();
handle->locked = 0;
- local_irq_save(handle->flags);
- cpu = smp_processor_id();
-
- if (in_nmi() && atomic_read(&data->lock) == cpu)
- return;
+ for (;;) {
+ cur = atomic_cmpxchg(&data->lock, -1, cpu);
+ if (cur == -1) {
+ handle->locked = 1;
+ break;
+ }
+ if (cur == cpu)
+ break;
- while (atomic_cmpxchg(&data->lock, -1, cpu) != -1)
cpu_relax();
-
- handle->locked = 1;
+ }
}
static void perf_output_unlock(struct perf_output_handle *handle)
@@ -2733,7 +2734,7 @@ again:
if (atomic_xchg(&data->wakeup, 0))
perf_output_wakeup(handle);
out:
- local_irq_restore(handle->flags);
+ put_cpu();
}
void perf_output_copy(struct perf_output_handle *handle,
OpenPOWER on IntegriCloud