- put the sync wakeup feature back in, based on Mike Kravetz's patch.

fs/pipe.c

@@ -119,7 +119,7 @@ pipe_read(struct file *filp, char *buf, size_t count, loff_t *ppos)
 		 * writers synchronously that there is more
 		 * room.
 		 */
-		wake_up_interruptible(PIPE_WAIT(*inode));
+		wake_up_interruptible_sync(PIPE_WAIT(*inode));
  		kill_fasync(PIPE_FASYNC_WRITERS(*inode), SIGIO, POLL_OUT);
 		if (!PIPE_EMPTY(*inode))
 			BUG();
@@ -219,7 +219,7 @@ pipe_write(struct file *filp, const char *buf, size_t count, loff_t *ppos)
 			 * is going to give up this CPU, so it doesnt have
 			 * to do idle reschedules.
 			 */
-			wake_up_interruptible(PIPE_WAIT(*inode));
+			wake_up_interruptible_sync(PIPE_WAIT(*inode));
  			kill_fasync(PIPE_FASYNC_READERS(*inode), SIGIO, POLL_IN);
 			PIPE_WAITING_WRITERS(*inode)++;
 			pipe_wait(inode);

include/linux/sched.h

@@ -491,6 +491,7 @@ extern unsigned long prof_len;
 extern unsigned long prof_shift;
 
 extern void FASTCALL(__wake_up(wait_queue_head_t *q, unsigned int mode, int nr));
+extern void FASTCALL(__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr));
 extern void FASTCALL(sleep_on(wait_queue_head_t *q));
 extern long FASTCALL(sleep_on_timeout(wait_queue_head_t *q,
 				      signed long timeout));
@@ -507,6 +508,11 @@ extern void FASTCALL(sched_exit(task_t * p));
 #define wake_up_interruptible(x)	__wake_up((x),TASK_INTERRUPTIBLE, 1)
 #define wake_up_interruptible_nr(x, nr)	__wake_up((x),TASK_INTERRUPTIBLE, nr)
 #define wake_up_interruptible_all(x)	__wake_up((x),TASK_INTERRUPTIBLE, 0)
+#ifdef CONFIG_SMP
+#define wake_up_interruptible_sync(x)   __wake_up_sync((x),TASK_INTERRUPTIBLE, 1)
+#else
+#define wake_up_interruptible_sync(x)   __wake_up((x),TASK_INTERRUPTIBLE, 1)
+#endif
 asmlinkage long sys_wait4(pid_t pid,unsigned int * stat_addr, int options, struct rusage * ru);
 
 extern int in_group_p(gid_t);

kernel/ksyms.c

@@ -457,6 +457,9 @@ EXPORT_SYMBOL(iomem_resource);
 /* process management */
 EXPORT_SYMBOL(complete_and_exit);
 EXPORT_SYMBOL(__wake_up);
+#if CONFIG_SMP
+EXPORT_SYMBOL_GPL(__wake_up_sync); /* internal use only */
+#endif
 EXPORT_SYMBOL(wake_up_process);
 EXPORT_SYMBOL(sleep_on);
 EXPORT_SYMBOL(sleep_on_timeout);

kernel/sched.c

@@ -321,31 +321,43 @@ void kick_if_running(task_t * p)
  * "current->state = TASK_RUNNING" to mark yourself runnable
  * without the overhead of this.
  */
-static int try_to_wake_up(task_t * p)
+static int try_to_wake_up(task_t * p, int sync)
 {
 	unsigned long flags;
 	int success = 0;
 	long old_state;
 	runqueue_t *rq;
 
+repeat_lock_task:
 	rq = task_rq_lock(p, &flags);
 	old_state = p->state;
-	p->state = TASK_RUNNING;
 	if (!p->array) {
+		if (unlikely(sync && (rq->curr != p))) {
+			if (p->thread_info->cpu != smp_processor_id()) {
+				p->thread_info->cpu = smp_processor_id();
+				task_rq_unlock(rq, &flags);
+				goto repeat_lock_task;
+			}
+		}
 		if (old_state == TASK_UNINTERRUPTIBLE)
 			rq->nr_uninterruptible--;
 		activate_task(p, rq);
+		/*
+		 * If sync is set, a resched_task() is a NOOP
+		 */
 		if (p->prio < rq->curr->prio)
 			resched_task(rq->curr);
 		success = 1;
 	}
+	p->state = TASK_RUNNING;
 	task_rq_unlock(rq, &flags);
+
 	return success;
 }
 
 int wake_up_process(task_t * p)
 {
-	return try_to_wake_up(p);
+	return try_to_wake_up(p, 0);
 }
 
 void wake_up_forked_process(task_t * p)
@@ -874,7 +886,7 @@ asmlinkage void preempt_schedule(void)
  * started to run but is not in state TASK_RUNNING.  try_to_wake_up() returns
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
-static inline void __wake_up_common(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+static inline void __wake_up_common(wait_queue_head_t *q, unsigned int mode, int nr_exclusive, int sync)
 {
 	struct list_head *tmp;
 	unsigned int state;
@@ -885,7 +897,7 @@ static inline void __wake_up_common(wait_queue_head_t *q, unsigned int mode, int
 		curr = list_entry(tmp, wait_queue_t, task_list);
 		p = curr->task;
 		state = p->state;
-		if ((state & mode) && try_to_wake_up(p) &&
+		if ((state & mode) && try_to_wake_up(p, sync) &&
 			((curr->flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive))
 				break;
 	}
@@ -899,17 +911,36 @@ void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
 		return;
 
 	spin_lock_irqsave(&q->lock, flags);
-	__wake_up_common(q, mode, nr_exclusive);
+	__wake_up_common(q, mode, nr_exclusive, 0);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+
+#if CONFIG_SMP
+
+void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+{
+	unsigned long flags;
+
+	if (unlikely(!q))
+		return;
+
+	spin_lock_irqsave(&q->lock, flags);
+	if (likely(nr_exclusive))
+		__wake_up_common(q, mode, nr_exclusive, 1);
+	else
+		__wake_up_common(q, mode, nr_exclusive, 0);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 
+#endif
+ 
 void complete(struct completion *x)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&x->wait.lock, flags);
 	x->done++;
-	__wake_up_common(&x->wait, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, 1);
+	__wake_up_common(&x->wait, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, 1, 0);
 	spin_unlock_irqrestore(&x->wait.lock, flags);
 }