perf_counter: optimize perf_counter_task_tick()
perf_counter_task_tick() does way too much work to find out
there's nothing to do. Provide an easy short-circuit for the
normal case where there are no counters on the system.
[ Impact: micro-optimization ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
LKML-Reference: <20090508170028.750619201@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 60e55f0..fdb0d24 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -39,6 +39,7 @@
static int perf_reserved_percpu __read_mostly;
static int perf_overcommit __read_mostly = 1;
+static atomic_t nr_counters __read_mostly;
static atomic_t nr_mmap_tracking __read_mostly;
static atomic_t nr_munmap_tracking __read_mostly;
static atomic_t nr_comm_tracking __read_mostly;
@@ -1076,8 +1077,14 @@
void perf_counter_task_tick(struct task_struct *curr, int cpu)
{
- struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
- struct perf_counter_context *ctx = &curr->perf_counter_ctx;
+ struct perf_cpu_context *cpuctx;
+ struct perf_counter_context *ctx;
+
+ if (!atomic_read(&nr_counters))
+ return;
+
+ cpuctx = &per_cpu(perf_cpu_context, cpu);
+ ctx = &curr->perf_counter_ctx;
perf_counter_cpu_sched_out(cpuctx);
perf_counter_task_sched_out(curr, cpu);
@@ -1197,6 +1204,7 @@
{
perf_pending_sync(counter);
+ atomic_dec(&nr_counters);
if (counter->hw_event.mmap)
atomic_dec(&nr_mmap_tracking);
if (counter->hw_event.munmap)
@@ -2861,6 +2869,7 @@
counter->pmu = pmu;
+ atomic_inc(&nr_counters);
if (counter->hw_event.mmap)
atomic_inc(&nr_mmap_tracking);
if (counter->hw_event.munmap)