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

Commit-ID: eb3182ef0405ff2f6668fd3e5ff9883f60ce8801 Gitweb: https://git.kernel.org/tip/eb3182ef0405ff2f6668fd3e5ff9883f60ce8801 Author: Dapeng Mi dapeng1.mi@linux.intel.com AuthorDate: Wed, 15 Oct 2025 13:18:28 +08:00 Committer: Ingo Molnar mingo@kernel.org CommitterDate: Mon, 03 Nov 2025 11:04:19 +01:00

perf/core: Fix system hang caused by cpu-clock usage

cpu-clock usage by the async-profiler tool can trigger a system hang, which got bisected back to the following commit by Octavia Togami:

18dbcbfabfff ("perf: Fix the POLL_HUP delivery breakage") causes this issue

The root cause of the hang is that cpu-clock is a special type of SW event which relies on hrtimers. The __perf_event_overflow() callback is invoked from the hrtimer handler for cpu-clock events, and __perf_event_overflow() tries to call cpu_clock_event_stop() to stop the event, which calls htimer_cancel() to cancel the hrtimer.

But that's a recursion into the hrtimer code from a hrtimer handler, which (unsurprisingly) deadlocks.

To fix this bug, use hrtimer_try_to_cancel() instead, and set the PERF_HES_STOPPED flag, which causes perf_swevent_hrtimer() to stop the event once it sees the PERF_HES_STOPPED flag.

[ mingo: Fixed the comments and improved the changelog. ]

Closes: https://lore.kernel.org/all/CAHPNGSQpXEopYreir+uDDEbtXTBvBvi8c6fYXJvceqtgTPa... Fixes: 18dbcbfabfff ("perf: Fix the POLL_HUP delivery breakage") Reported-by: Octavia Togami octavia.togami@gmail.com Suggested-by: Peter Zijlstra peterz@infradead.org Signed-off-by: Dapeng Mi dapeng1.mi@linux.intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Tested-by: Octavia Togami octavia.togami@gmail.com Cc: stable@vger.kernel.org Link: https://github.com/lucko/spark/issues/530 Link: https://patch.msgid.link/20251015051828.12809-1-dapeng1.mi@linux.intel.com --- kernel/events/core.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c index 177e57c..1fd347d 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 +11820,20 @@ 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() + * Careful: this function can be triggered in the hrtimer handler, + * for cpu-clock events, so hrtimer_cancel() would cause a + * deadlock. + * + * So use hrtimer_try_to_cancel() to try to stop the hrtimer, + * and the cpu-clock handler also sets the PERF_HES_STOPPED flag, + * which guarantees that perf_swevent_hrtimer() will stop the + * hrtimer once it sees 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 +11877,14 @@ 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 +11958,14 @@ 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);