Commit 3ba9f93b authored Jun 11, 2021 by Peter Zijlstra

sched,perf,kvm: Fix preemption condition



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@infradead.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20210611082838.285099381@infradead.org

parent b03fbd4f

kernel/events/core.c

+3 −4

Original line number	Diff line number	Diff line
		@@ -8682,13 +8682,12 @@ static void perf_event_switch(struct task_struct *task,
		},
		};

		if (!sched_in && task->state == TASK_RUNNING)
		if (!sched_in && task->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);
		}

		/*

virt/kvm/kvm_main.c

+1 −1

Original line number	Diff line number	Diff line
		@@ -5025,7 +5025,7 @@ static void kvm_sched_out(struct preempt_notifier *pn,
		{
		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);
		}