perf: Fix move_group() order

Jiri reported triggering the new WARN_ON_ONCE in event_sched_out over
the weekend:

  event_sched_out.isra.79+0x2b9/0x2d0
  group_sched_out+0x69/0xc0
  ctx_sched_out+0x106/0x130
  task_ctx_sched_out+0x37/0x70
  __perf_install_in_context+0x70/0x1a0
  remote_function+0x48/0x60
  generic_exec_single+0x15b/0x1d0
  smp_call_function_single+0x67/0xa0
  task_function_call+0x53/0x80
  perf_install_in_context+0x8b/0x110

I think the below should cure this; if we install a group leader it
will iterate the (still intact) group list and find its siblings and
try and install those too -- even though those still have the old
event->ctx -- in the new ctx.

Upon installing the first group sibling we'd try and schedule out the
group and trigger the above warn.

Fix this by installing the group leader last, installing siblings
would have no effect, they're not reachable through the group lists
and therefore we don't schedule them.

Also delay resetting the state until we're absolutely sure the events
are quiescent.

Reported-by: Jiri Olsa <jolsa@redhat.com>
Reported-by: vincent.weaver@maine.edu
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20150126162639.GA21418@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/events/core.c

@@ -7645,16 +7645,9 @@ SYSCALL_DEFINE5(perf_event_open,
 
 		perf_remove_from_context(group_leader, false);
 
-		/*
-		 * Removing from the context ends up with disabled
-		 * event. What we want here is event in the initial
-		 * startup state, ready to be add into new context.
-		 */
-		perf_event__state_init(group_leader);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
 			perf_remove_from_context(sibling, false);
-			perf_event__state_init(sibling);
 			put_ctx(gctx);
 		}
 	} else {
@@ -7670,13 +7663,31 @@ SYSCALL_DEFINE5(perf_event_open,
 		 */
 		synchronize_rcu();
 
-		perf_install_in_context(ctx, group_leader, group_leader->cpu);
-		get_ctx(ctx);
+		/*
+		 * Install the group siblings before the group leader.
+		 *
+		 * Because a group leader will try and install the entire group
+		 * (through the sibling list, which is still in-tact), we can
+		 * end up with siblings installed in the wrong context.
+		 *
+		 * By installing siblings first we NO-OP because they're not
+		 * reachable through the group lists.
+		 */
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
+			perf_event__state_init(sibling);
 			perf_install_in_context(ctx, sibling, sibling->cpu);
 			get_ctx(ctx);
 		}
+
+		/*
+		 * Removing from the context ends up with disabled
+		 * event. What we want here is event in the initial
+		 * startup state, ready to be add into new context.
+		 */
+		perf_event__state_init(group_leader);
+		perf_install_in_context(ctx, group_leader, group_leader->cpu);
+		get_ctx(ctx);
 	}
 
 	perf_install_in_context(ctx, event, event->cpu);
@@ -7806,8 +7817,35 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 		list_add(&event->migrate_entry, &events);
 	}
 
+	/*
+	 * Wait for the events to quiesce before re-instating them.
+	 */
 	synchronize_rcu();
 
+	/*
+	 * Re-instate events in 2 passes.
+	 *
+	 * Skip over group leaders and only install siblings on this first
+	 * pass, siblings will not get enabled without a leader, however a
+	 * leader will enable its siblings, even if those are still on the old
+	 * context.
+	 */
+	list_for_each_entry_safe(event, tmp, &events, migrate_entry) {
+		if (event->group_leader == event)
+			continue;
+
+		list_del(&event->migrate_entry);
+		if (event->state >= PERF_EVENT_STATE_OFF)
+			event->state = PERF_EVENT_STATE_INACTIVE;
+		account_event_cpu(event, dst_cpu);
+		perf_install_in_context(dst_ctx, event, dst_cpu);
+		get_ctx(dst_ctx);
+	}
+
+	/*
+	 * Once all the siblings are setup properly, install the group leaders
+	 * to make it go.
+	 */
 	list_for_each_entry_safe(event, tmp, &events, migrate_entry) {
 		list_del(&event->migrate_entry);
 		if (event->state >= PERF_EVENT_STATE_OFF)