[tip: perf/urgent] perf: Fix system hang caused by cpu-clock

[tip-bot2 for Dapeng Mi]

The following commit has been merged into the perf/urgent branch of tip:

Commit-ID:     e33076f34f7a449c0e1808f15d88b2dd9a85979a
Gitweb:        https://git.kernel.org/tip/e33076f34f7a449c0e1808f15d88b2dd9a85979a
Author:        Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
AuthorDate:    Wed, 15 Oct 2025 13:18:28 +08:00
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Mon, 03 Nov 2025 10:26:09 +01:00

perf: Fix system hang caused by cpu-clock

A system hang issue caused by cpu-clock is reported and bisection
indicates the commit 18dbcbfabfff ("perf: Fix the POLL_HUP delivery
 breakage") causes this issue.

The root cause of the hang issue is that cpu-clock is a specific SW
event which relies on the hrtimer. The __perf_event_overflow()
is invoked from the hrtimer handler for cpu-clock event, and
__perf_event_overflow() tries to call event stop callback
(cpu_clock_event_stop()) to stop the event, and cpu_clock_event_stop()
calls htimer_cancel() to cancel the hrtimer. But unfortunately the
hrtimer callback is currently executing and then traps into deadlock.

To avoid this deadlock, use hrtimer_try_to_cancel() instead of
hrtimer_cancel() to cancel the hrtimer, and set PERF_HES_STOPPED flag
for the stopping events. perf_swevent_hrtimer() would stop the event
hrtimer once it detects the PERF_HES_STOPPED flag.

Closes: https://lore.kernel.org/all/CAHPNGSQpXEopYreir+uDDEbtXTBvBvi8c6fYXJvceqtgTPao3Q@xxxxxxxxxxxxxx/
Fixes: 18dbcbfabfff ("perf: Fix the POLL_HUP delivery breakage")
Reported-by: Octavia Togami <octavia.togami@xxxxxxxxx>
Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Tested-by: Octavia Togami <octavia.togami@xxxxxxxxx>
Link: https://patch.msgid.link/20251015051828.12809-1-dapeng1.mi@xxxxxxxxxxxxxxx
---
 kernel/events/core.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 177e57c..6e4af97 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11773,7 +11773,8 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 
 	event = container_of(hrtimer, struct perf_event, hw.hrtimer);
 
-	if (event->state != PERF_EVENT_STATE_ACTIVE)
+	if (event->state != PERF_EVENT_STATE_ACTIVE ||
+	    event->hw.state & PERF_HES_STOPPED)
 		return HRTIMER_NORESTART;
 
 	event->pmu->read(event);
@@ -11819,15 +11820,18 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 
 	/*
-	 * The throttle can be triggered in the hrtimer handler.
-	 * The HRTIMER_NORESTART should be used to stop the timer,
-	 * rather than hrtimer_cancel(). See perf_swevent_hrtimer()
+	 * The event stop can be triggered in the hrtimer handler.
+	 * So use hrtimer_try_to_cancel() instead of hrtimer_cancel()
+	 * to stop the hrtimer() to avoid trapping into a dead loop.
+	 * Simultaneously the event would be set PERF_HES_STOPPED flag,
+	 * perf_swevent_hrtimer() would stop the event hrtimer once it
+	 * detects the PERF_HES_STOPPED flag.
 	 */
 	if (is_sampling_event(event) && (hwc->interrupts != MAX_INTERRUPTS)) {
 		ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
 		local64_set(&hwc->period_left, ktime_to_ns(remaining));
 
-		hrtimer_cancel(&hwc->hrtimer);
+		hrtimer_try_to_cancel(&hwc->hrtimer);
 	}
 }
 
@@ -11871,12 +11875,14 @@ static void cpu_clock_event_update(struct perf_event *event)
 
 static void cpu_clock_event_start(struct perf_event *event, int flags)
 {
+	event->hw.state = 0;
 	local64_set(&event->hw.prev_count, local_clock());
 	perf_swevent_start_hrtimer(event);
 }
 
 static void cpu_clock_event_stop(struct perf_event *event, int flags)
 {
+	event->hw.state = PERF_HES_STOPPED;
 	perf_swevent_cancel_hrtimer(event);
 	if (flags & PERF_EF_UPDATE)
 		cpu_clock_event_update(event);
@@ -11950,12 +11956,14 @@ static void task_clock_event_update(struct perf_event *event, u64 now)
 
 static void task_clock_event_start(struct perf_event *event, int flags)
 {
+	event->hw.state = 0;
 	local64_set(&event->hw.prev_count, event->ctx->time);
 	perf_swevent_start_hrtimer(event);
 }
 
 static void task_clock_event_stop(struct perf_event *event, int flags)
 {
+	event->hw.state = PERF_HES_STOPPED;
 	perf_swevent_cancel_hrtimer(event);
 	if (flags & PERF_EF_UPDATE)
 		task_clock_event_update(event, event->ctx->time);