perf/ring_buffer: Trigger IO signals for watermark_wakeup

perf_output_wakeup() already marks the perf event fd available for polling.
Trigger IO signals with FASYNC too.

Signed-off-by: Kyle Huey <khuey@kylehuey.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20240413141618.4160-3-khuey@kylehuey.com

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 60ed43d1c29e3e321f931388f15a4feffee2a5f5..4013408ce012362242398c8e5f3b74a01a42b9be 100644 (file)
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -22,6 +22,10 @@ static void perf_output_wakeup(struct perf_output_handle *handle)
        atomic_set(&handle->rb->poll, EPOLLIN);
 
        handle->event->pending_wakeup = 1;
+
+       if (*perf_event_fasync(handle->event) && !handle->event->pending_kill)
+               handle->event->pending_kill = POLL_IN;
+
        irq_work_queue(&handle->event->pending_irq);
 }