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

diff --git a/kernel/events/core.c b/kernel/events/core.c
index fe88d6eea3c2c892190625a097baa4ad7e732ee9..fd89000c9bf59a7355337073b2fbe61917550478 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -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);
 }
 
 /*

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 6a6bc7af0e28d84d44790faef778558e3671e0e0..5f166eb8ee2e5730f02ae85a4d51222ec1aabb4b 100644 (file)
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -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);
        }