perf: Optimize perf_event_mmap_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: <20091120212508.606459548@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/perf_event.c

@@ -3493,15 +3493,10 @@ static void perf_event_mmap_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_mmap_match(event, mmap_event))
 			perf_event_mmap_output(event, mmap_event);
 	}
-	rcu_read_unlock();
 }
 
 static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
@@ -3557,11 +3552,11 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 
 	mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
 
+	rcu_read_lock();
 	cpuctx = &get_cpu_var(perf_cpu_context);
 	perf_event_mmap_ctx(&cpuctx->ctx, mmap_event);
 	put_cpu_var(perf_cpu_context);
 
-	rcu_read_lock();
 	/*
 	 * doesn't really matter which of the child contexts the
 	 * events ends up in.