[PATCH 16/24] sched: Teach dequeue_task() about special task states

[Peter Zijlstra]

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@xxxxxxxxxxxxx>
---
 kernel/sched/core.c  |    7 ++++++-
 kernel/sched/sched.h |    3 ++-
 2 files changed, 8 insertions(+), 2 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6521,11 +6521,16 @@ static void __sched notrace __schedule(u
 		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 && ...)
@@ -6537,7 +6542,7 @@ static void __sched notrace __schedule(u
 			 *
 			 * 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;
 	}
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2254,10 +2254,11 @@ 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 */