sched/core: Add {EN,DE}QUEUE_NOCLOCK flags

Currently {en,de}queue_task() do an unconditional update_rq_clock().
However since we want to avoid duplicate updates, so that each
rq->lock section appears atomic in time, we need to be able to skip
these clock updates.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/core.c

@@ -752,17 +752,23 @@ static void set_load_weight(struct task_struct *p)
 
 static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	update_rq_clock(rq);
+	if (!(flags & ENQUEUE_NOCLOCK))
+		update_rq_clock(rq);
+
 	if (!(flags & ENQUEUE_RESTORE))
 		sched_info_queued(rq, p);
+
 	p->sched_class->enqueue_task(rq, p, flags);
 }
 
 static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	update_rq_clock(rq);
+	if (!(flags & DEQUEUE_NOCLOCK))
+		update_rq_clock(rq);
+
 	if (!(flags & DEQUEUE_SAVE))
 		sched_info_dequeued(rq, p);
+
 	p->sched_class->dequeue_task(rq, p, flags);
 }
 

kernel/sched/sched.h

@@ -1331,15 +1331,17 @@ extern const u32 sched_prio_to_wmult[40];
 #define DEQUEUE_SLEEP		0x01
 #define DEQUEUE_SAVE		0x02 /* matches ENQUEUE_RESTORE */
 #define DEQUEUE_MOVE		0x04 /* matches ENQUEUE_MOVE */
+#define DEQUEUE_NOCLOCK		0x08 /* matches ENQUEUE_NOCLOCK */
 
 #define ENQUEUE_WAKEUP		0x01
 #define ENQUEUE_RESTORE		0x02
 #define ENQUEUE_MOVE		0x04
+#define ENQUEUE_NOCLOCK		0x08
 
-#define ENQUEUE_HEAD		0x08
-#define ENQUEUE_REPLENISH	0x10
+#define ENQUEUE_HEAD		0x10
+#define ENQUEUE_REPLENISH	0x20
 #ifdef CONFIG_SMP
-#define ENQUEUE_MIGRATED	0x20
+#define ENQUEUE_MIGRATED	0x40
 #else
 #define ENQUEUE_MIGRATED	0x00
 #endif