perf_event: Fix event group handling in __perf_event_sched_*()

Paul Mackerras says:

 "Actually, looking at this more closely, it has to be a group
 leader anyway since it's at the top level of ctx->group_list.  In
 fact I see four places where we do:

  list_for_each_entry(event, &ctx->group_list, group_entry) {
	if (event == event->group_leader)
		...

 or the equivalent, three of which appear to have been introduced
 by afedadf2 ("perf_counter: Optimize sched in/out of counters")
 back in May by Peter Z.

 As far as I can see the if () is superfluous in each case (a
 singleton event will be a group of 1 and will have its
 group_leader pointing to itself)."

 [ See: http://marc.info/?l=linux-kernel&m=125361238901442&w=2 ]

And Peter Zijlstra points out this is a bugfix:

 "The intent was to call event_sched_{in,out}() for single event
  groups because that's cheaper than group_sched_{in,out}(),
  however..

  - as you noticed, I got the condition wrong, it should have read:

      list_empty(&event->sibling_list)

  - it failed to call group_can_go_on() which deals with ->exclusive.

  - it also doesn't call hw_perf_group_sched_in() which might break
    power."

 [ See: http://marc.info/?l=linux-kernel&m=125369523318583&w=2 ]

Changelog v1->v2:

 - Fix the title name according to Peter Zijlstra's suggestion

 - Remove the comments and WARN_ON_ONCE() as Peter Zijlstra's
   suggestion

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <4ABC5A55.7000208@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 0f86feb..e50543d 100644 (file)
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1030,14 +1030,10 @@ void __perf_event_sched_out(struct perf_event_context *ctx,
        update_context_time(ctx);
 
        perf_disable();
-       if (ctx->nr_active) {
-               list_for_each_entry(event, &ctx->group_list, group_entry) {
-                       if (event != event->group_leader)
-                               event_sched_out(event, cpuctx, ctx);
-                       else
-                               group_sched_out(event, cpuctx, ctx);
-               }
-       }
+       if (ctx->nr_active)
+               list_for_each_entry(event, &ctx->group_list, group_entry)
+                       group_sched_out(event, cpuctx, ctx);
+
        perf_enable();
  out:
        spin_unlock(&ctx->lock);
@@ -1258,12 +1254,8 @@ __perf_event_sched_in(struct perf_event_context *ctx,
                if (event->cpu != -1 && event->cpu != cpu)
                        continue;
 
-               if (event != event->group_leader)
-                       event_sched_in(event, cpuctx, ctx, cpu);
-               else {
-                       if (group_can_go_on(event, cpuctx, 1))
-                               group_sched_in(event, cpuctx, ctx, cpu);
-               }
+               if (group_can_go_on(event, cpuctx, 1))
+                       group_sched_in(event, cpuctx, ctx, cpu);
 
                /*
                 * If this pinned group hasn't been scheduled,
@@ -1291,15 +1283,9 @@ __perf_event_sched_in(struct perf_event_context *ctx,
                if (event->cpu != -1 && event->cpu != cpu)
                        continue;
 
-               if (event != event->group_leader) {
-                       if (event_sched_in(event, cpuctx, ctx, cpu))
+               if (group_can_go_on(event, cpuctx, can_add_hw))
+                       if (group_sched_in(event, cpuctx, ctx, cpu))
                                can_add_hw = 0;
-               } else {
-                       if (group_can_go_on(event, cpuctx, can_add_hw)) {
-                               if (group_sched_in(event, cpuctx, ctx, cpu))
-                                       can_add_hw = 0;
-                       }
-               }
        }
        perf_enable();
  out: