[PATCH 5.10.y 1/3] perf: Fix cgroup state vs ERROR

From: Peter Zijlstra <[email protected]>

[ Upstream commit 61988e36dc5457cdff7ae7927e8d9ad1419ee998 ]

While chasing down a missing perf_cgroup_event_disable() elsewhere,
Leo Yan found that both perf_put_aux_event() and
perf_remove_sibling_event() were also missing one.

Specifically, the rule is that events that switch to OFF,ERROR need to
call perf_cgroup_event_disable().

Unify the disable paths to ensure this.

Fixes: ab43762ef010 ("perf: Allow normal events to output AUX data")
Fixes: 9f0c4fa111dc ("perf/core: Add a new PERF_EV_CAP_SIBLING event capability")
Reported-by: Leo Yan <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Stable-dep-of: 42c5ca1f0a28 ("perf/core: Fix group leader use-after-free after sibling detach")
Signed-off-by: Sasha Levin <[email protected]>
---
 kernel/events/core.c | 56 ++++++++++++++++++++++++--------------------
 1 file changed, 30 insertions(+), 26 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index c9cd1f622a1fc..756152374a3b9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2145,14 +2145,13 @@ perf_aux_output_match(struct perf_event *event, struct perf_event *aux_event)
 }
 
 static void put_event(struct perf_event *event);
-static void event_sched_out(struct perf_event *event,
-			    struct perf_cpu_context *cpuctx,
-			    struct perf_event_context *ctx);
+static void __event_disable(struct perf_event *event,
+			    struct perf_event_context *ctx,
+			    enum perf_event_state state);
 
 static void perf_put_aux_event(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
-	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	struct perf_event *iter;
 
 	/*
@@ -2181,8 +2180,7 @@ static void perf_put_aux_event(struct perf_event *event)
 		 * state so that we don't try to schedule it again. Note
 		 * that perf_event_enable() will clear the ERROR status.
 		 */
-		event_sched_out(iter, cpuctx, ctx);
-		perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+		__event_disable(iter, ctx, PERF_EVENT_STATE_ERROR);
 	}
 }
 
@@ -2236,21 +2234,6 @@ static inline struct list_head *get_event_list(struct perf_event *event)
 	return event->attr.pinned ? &ctx->pinned_active : &ctx->flexible_active;
 }
 
-/*
- * Events that have PERF_EV_CAP_SIBLING require being part of a group and
- * cannot exist on their own, schedule them out and move them into the ERROR
- * state. Also see _perf_event_enable(), it will not be able to recover
- * this ERROR state.
- */
-static inline void perf_remove_sibling_event(struct perf_event *event)
-{
-	struct perf_event_context *ctx = event->ctx;
-	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
-
-	event_sched_out(event, cpuctx, ctx);
-	perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
-}
-
 static void perf_group_detach(struct perf_event *event)
 {
 	struct perf_event *leader = event->group_leader;
@@ -2286,8 +2269,15 @@ static void perf_group_detach(struct perf_event *event)
 	 */
 	list_for_each_entry_safe(sibling, tmp, &event->sibling_list, sibling_list) {
 
+		/*
+		 * Events that have PERF_EV_CAP_SIBLING require being part of
+		 * a group and cannot exist on their own, schedule them out
+		 * and move them into the ERROR state. Also see
+		 * _perf_event_enable(), it will not be able to recover this
+		 * ERROR state.
+		 */
 		if (sibling->event_caps & PERF_EV_CAP_SIBLING)
-			perf_remove_sibling_event(sibling);
+			__event_disable(sibling, ctx, PERF_EVENT_STATE_ERROR);
 
 		sibling->group_leader = sibling;
 		list_del_init(&sibling->sibling_list);
@@ -2494,6 +2484,15 @@ static void perf_remove_from_context(struct perf_event *event, unsigned long fla
 	}
 }
 
+static void __event_disable(struct perf_event *event,
+			    struct perf_event_context *ctx,
+			    enum perf_event_state state)
+{
+	event_sched_out(event, __get_cpu_context(ctx), ctx);
+	perf_cgroup_event_disable(event, ctx);
+	perf_event_set_state(event, state);
+}
+
 /*
  * Cross CPU call to disable a performance event
  */
@@ -2510,13 +2509,18 @@ static void __perf_event_disable(struct perf_event *event,
 		update_cgrp_time_from_event(event);
 	}
 
+	/*
+	 * When disabling a group leader, the whole group becomes ineligible
+	 * to run, so schedule out the full group.
+	 */
 	if (event == event->group_leader)
 		group_sched_out(event, cpuctx, ctx);
-	else
-		event_sched_out(event, cpuctx, ctx);
 
-	perf_event_set_state(event, PERF_EVENT_STATE_OFF);
-	perf_cgroup_event_disable(event, ctx);
+	/*
+	 * But only mark the leader OFF; the siblings will remain
+	 * INACTIVE.
+	 */
+	__event_disable(event, ctx, PERF_EVENT_STATE_OFF);
 }
 
 /*
-- 
2.53.0