[tip: perf/urgent] x86/perf: Make sure to program the counter value for stopped events on migration

[tip-bot2 for Peter Zijlstra]

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

Commit-ID:     f1cac6ac62d28a9a57b17f51ac5795bf250c12d3
Gitweb:        https://git.kernel.org/tip/f1cac6ac62d28a9a57b17f51ac5795bf250c12d3
Author:        Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate:    Wed, 11 Mar 2026 21:29:14 +01:00
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Thu, 12 Mar 2026 11:29:15 +01:00

x86/perf: Make sure to program the counter value for stopped events on migration

Both Mi Dapeng and Ian Rogers noted that not everything that sets HES_STOPPED
is required to EF_UPDATE. Specifically the 'step 1' loop of rescheduling
explicitly does EF_UPDATE to ensure the counter value is read.

However, then 'step 2' simply leaves the new counter uninitialized when
HES_STOPPED, even though, as noted above, the thing that stopped them might not
be aware it needs to EF_RELOAD -- since it didn't EF_UPDATE on stop.

One such location that is affected is throttling, throttle does pmu->stop(, 0);
and unthrottle does pmu->start(, 0); possibly restarting an uninitialized counter.

Fixes: a4eaf7f14675 ("perf: Rework the PMU methods")
Reported-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
Reported-by: Ian Rogers <irogers@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
Link: https://patch.msgid.link/20260311204035.GX606826@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
---
 arch/x86/events/core.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 54b4c31..810ab21 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1374,8 +1374,10 @@ static void x86_pmu_enable(struct pmu *pmu)
 
 			cpuc->events[hwc->idx] = event;
 
-			if (hwc->state & PERF_HES_ARCH)
+			if (hwc->state & PERF_HES_ARCH) {
+				static_call(x86_pmu_set_period)(event);
 				continue;
+			}
 
 			/*
 			 * if cpuc->enabled = 0, then no wrmsr as