sched: Fix trace_sched_switch(.prev_state)

JIRA: https://issues.redhat.com/browse/RHEL-110301

commit 8feb053
Author: Peter Zijlstra <[email protected]>
Date:   Wed Mar 19 22:23:23 2025 +0100

    sched: Fix trace_sched_switch(.prev_state)

    Gabriele noted that in case of signal_pending_state(), the tracepoint
    sees a stale task-state.

    Fixes: fa2c325 ("sched/tracing: Don't re-read p->state when emitting sched_switch event")
    Reported-by: Gabriele Monaco <[email protected]>
    Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
    Cc: Valentin Schneider <[email protected]>

Signed-off-by: Phil Auld <[email protected]>

Author: auldp

kernel/sched/core.c

@@ -6495,12 +6495,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  * Otherwise marks the task's __state as RUNNING
  */
 static bool try_to_block_task(struct rq *rq, struct task_struct *p,
-			      unsigned long task_state)
+			      unsigned long *task_state_p)
 {
+	unsigned long task_state = *task_state_p;
 	int flags = DEQUEUE_NOCLOCK;
 
 	if (signal_pending_state(task_state, p)) {
 		WRITE_ONCE(p->__state, TASK_RUNNING);
+		*task_state_p = TASK_RUNNING;
 		return false;
 	}
 
@@ -6637,7 +6639,7 @@ static void __sched notrace __schedule(int sched_mode)
 			goto picked;
 		}
 	} else if (!preempt && prev_state) {
-		try_to_block_task(rq, prev, prev_state);
+		try_to_block_task(rq, prev, &prev_state);
 		switch_count = &prev->nvcsw;
 	}