sched: Teach dequeue_task() about special task states

Since special task states must not suffer spurious wakeups, and the
proposed delayed dequeue can cause exactly these (under some boundary
conditions), propagate this knowledge into dequeue_task() such that it
can do the right thing.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Tested-by: Valentin Schneider <vschneid@redhat.com>
Link: https://lkml.kernel.org/r/20240727105030.110439521@infradead.org

Author: Peter Zijlstra

kernel/sched/core.c

@@ -6530,11 +6530,16 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		if (signal_pending_state(prev_state, prev)) {
 			WRITE_ONCE(prev->__state, TASK_RUNNING);
 		} else {
+			int flags = DEQUEUE_NOCLOCK;
+
 			prev->sched_contributes_to_load =
 				(prev_state & TASK_UNINTERRUPTIBLE) &&
 				!(prev_state & TASK_NOLOAD) &&
 				!(prev_state & TASK_FROZEN);
 
+			if (unlikely(is_special_task_state(prev_state)))
+				flags |= DEQUEUE_SPECIAL;
+
 			/*
 			 * __schedule()			ttwu()
 			 *   prev_state = prev->state;    if (p->on_rq && ...)
@@ -6546,7 +6551,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 			 *
 			 * After this, schedule() must not care about p->state any more.
 			 */
-			block_task(rq, prev, DEQUEUE_NOCLOCK);
+			block_task(rq, prev, flags);
 		}
 		switch_count = &prev->nvcsw;
 	}

kernel/sched/sched.h

@@ -2248,10 +2248,11 @@ extern const u32		sched_prio_to_wmult[40];
  *
  */
 
-#define DEQUEUE_SLEEP		0x01
+#define DEQUEUE_SLEEP		0x01 /* Matches ENQUEUE_WAKEUP */
 #define DEQUEUE_SAVE		0x02 /* Matches ENQUEUE_RESTORE */
 #define DEQUEUE_MOVE		0x04 /* Matches ENQUEUE_MOVE */
 #define DEQUEUE_NOCLOCK		0x08 /* Matches ENQUEUE_NOCLOCK */
+#define DEQUEUE_SPECIAL		0x10
 #define DEQUEUE_MIGRATING	0x100 /* Matches ENQUEUE_MIGRATING */
 #define DEQUEUE_DELAYED		0x200 /* Matches ENQUEUE_DELAYED */