perf: Fix the POLL_HUP delivery breakage

JIRA: https://issues.redhat.com/browse/RHEL-78198

upstream
========
commit 18dbcbf
Author: Kan Liang <kan.liang@linux.intel.com>
Date: Mon Aug 11 11:26:44 2025 -0700

description
===========
The event_limit can be set by the PERF_EVENT_IOC_REFRESH to limit the
number of events. When the event_limit reaches 0, the POLL_HUP signal
should be sent. But it's missed.

The corresponding counter should be stopped when the event_limit reaches
0. It was implemented in the ARCH-specific code. However, since the
commit 9734e25 ("perf: Fix the throttle logic for a group"), all
the ARCH-specific code has been moved to the generic code. The code to
handle the event_limit was lost.

Add the event->pmu->stop(event, 0); back.

Fixes: 9734e25 ("perf: Fix the throttle logic for a group")
Closes: https://lore.kernel.org/lkml/aICYAqM5EQUlTqtX@li-2b55cdcc-350b-11b2-a85c-a78bff51fc11.ibm.com/
    Reported-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
    Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
    Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
    Tested-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
    Link: https://lkml.kernel.org/r/20250811182644.1305952-1-kan.liang@linux.intel.com

Signed-off-by: Michael Petlan <mpetlan@redhat.com>

Author: rfmvh

kernel/events/core.c

@@ -10336,6 +10336,7 @@ static int __perf_event_overflow(struct perf_event *event,
 		ret = 1;
 		event->pending_kill = POLL_HUP;
 		perf_event_disable_inatomic(event);
+		event->pmu->stop(event, 0);
 	}
 
 	if (event->attr.sigtrap) {