From 8c9ed8e14c342ec5e7f27e7e498f62409a10eb29 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Fri, 25 Sep 2009 13:51:17 +0800 Subject: 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 Acked-by: Peter Zijlstra Cc: Paul Mackerras LKML-Reference: <4ABC5A55.7000208@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 30 ++++++++---------------------- 1 file changed, 8 insertions(+), 22 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 0f86feb6db0c..e50543db642a 100644 --- 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: -- cgit v1.2.3 From 27f9994c50e95f3a5a81fe4c7491a9f9cffe6ec0 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Fri, 25 Sep 2009 13:54:01 +0800 Subject: perf_event: Clean up perf_event_init_task() While at it: we can traverse ctx->group_list to get all group leader, it should be safe since we hold ctx->mutex. Changlog v1->v2: - remove WARN_ON_ONCE() according to Peter Zijlstra's suggestion Signed-off-by: Xiao Guangrong Acked-by: Peter Zijlstra Cc: Paul Mackerras LKML-Reference: <4ABC5AF9.6060808@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index e50543db642a..e491fb087939 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4767,9 +4767,7 @@ int perf_event_init_task(struct task_struct *child) * We dont have to disable NMIs - we are only looking at * the list, not manipulating it: */ - list_for_each_entry_rcu(event, &parent_ctx->event_list, event_entry) { - if (event != event->group_leader) - continue; + list_for_each_entry(event, &parent_ctx->group_list, group_entry) { if (!event->attr.inherit) { inherited_all = 0; -- cgit v1.2.3