[dm-devel] [PATCH 3/6] sched,perf,kvm: Fix preemption condition

[Peter Zijlstra]

When ran from the sched-out path (preempt_notifier or perf_event),
p->state is irrelevant to determine preemption. You can get preempted
with !task_is_running() just fine.

The right indicator for preemption is if the task is still on the
runqueue in the sched-out path.

Signed-off-by: Peter Zijlstra (Intel) <peterz at infradead.org>
---
 kernel/events/core.c |    7 +++----
 virt/kvm/kvm_main.c  |    2 +-
 2 files changed, 4 insertions(+), 5 deletions(-)

--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8568,13 +8568,12 @@ static void perf_event_switch(struct tas
 		},
 	};
 
-	if (!sched_in && task->state == TASK_RUNNING)
+	if (!sched_in && current->on_rq) {
 		switch_event.event_id.header.misc |=
 				PERF_RECORD_MISC_SWITCH_OUT_PREEMPT;
+	}
 
-	perf_iterate_sb(perf_event_switch_output,
-		       &switch_event,
-		       NULL);
+	perf_iterate_sb(perf_event_switch_output, &switch_event, NULL);
 }
 
 /*
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4869,7 +4869,7 @@ static void kvm_sched_out(struct preempt
 {
 	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
 
-	if (current->state == TASK_RUNNING) {
+	if (current->on_rq) {
 		WRITE_ONCE(vcpu->preempted, true);
 		WRITE_ONCE(vcpu->ready, true);
 	}