[PATCH 1/2 v3] wait: add wait_event_lock_irq() interface

@@ -452,7 +452,7 @@ void md_flush_request(struct mddev *mddev, struct bio *bio)
 	spin_lock_irq(&mddev->write_lock);
 	wait_event_lock_irq(mddev->sb_wait,
 			    !mddev->flush_bio,
-			    mddev->write_lock, /*nothing*/);
+			    mddev->write_lock);
 	mddev->flush_bio = bio;
 	spin_unlock_irq(&mddev->write_lock);
 

@@ -551,32 +551,6 @@ struct md_thread {
 
 #define THREAD_WAKEUP  0
 
-#define __wait_event_lock_irq(wq, condition, lock, cmd) 		\
-do {									\
-	wait_queue_t __wait;						\
-	init_waitqueue_entry(&__wait, current);				\
-									\
-	add_wait_queue(&wq, &__wait);					\
-	for (;;) {							\
-		set_current_state(TASK_UNINTERRUPTIBLE);		\
-		if (condition)						\
-			break;						\
-		spin_unlock_irq(&lock);					\
-		cmd;							\
-		schedule();						\
-		spin_lock_irq(&lock);					\
-	}								\
-	current->state = TASK_RUNNING;					\
-	remove_wait_queue(&wq, &__wait);				\
-} while (0)
-
-#define wait_event_lock_irq(wq, condition, lock, cmd) 			\
-do {									\
-	if (condition)	 						\
-		break;							\
-	__wait_event_lock_irq(wq, condition, lock, cmd);		\
-} while (0)
-
 static inline void safe_put_page(struct page *p)
 {
 	if (p) put_page(p);

@@ -822,7 +822,7 @@ static void raise_barrier(struct r1conf *conf)
 
 	/* Wait until no block IO is waiting */
 	wait_event_lock_irq(conf->wait_barrier, !conf->nr_waiting,
-			    conf->resync_lock, );
+			    conf->resync_lock);
 
 	/* block any new IO from starting */
 	conf->barrier++;

@@ -830,7 +830,7 @@ static void raise_barrier(struct r1conf *conf)
 	/* Now wait for all pending IO to complete */
 	wait_event_lock_irq(conf->wait_barrier,
 			    !conf->nr_pending && conf->barrier < RESYNC_DEPTH,
-			    conf->resync_lock, );
+			    conf->resync_lock);
 
 	spin_unlock_irq(&conf->resync_lock);
 }

@@ -864,8 +864,7 @@ static void wait_barrier(struct r1conf *conf)
 				    (conf->nr_pending &&
 				     current->bio_list &&
 				     !bio_list_empty(current->bio_list)),
-				    conf->resync_lock,
-			);
+				    conf->resync_lock);
 		conf->nr_waiting--;
 	}
 	conf->nr_pending++;

@@ -898,10 +897,10 @@ static void freeze_array(struct r1conf *conf)
 	spin_lock_irq(&conf->resync_lock);
 	conf->barrier++;
 	conf->nr_waiting++;
-	wait_event_lock_irq(conf->wait_barrier,
-			    conf->nr_pending == conf->nr_queued+1,
-			    conf->resync_lock,
-			    flush_pending_writes(conf));
+	wait_event_lock_irq_cmd(conf->wait_barrier,
+				conf->nr_pending == conf->nr_queued+1,
+				conf->resync_lock,
+				flush_pending_writes(conf));
 	spin_unlock_irq(&conf->resync_lock);
 }
 static void unfreeze_array(struct r1conf *conf)

@@ -952,7 +952,7 @@ static void raise_barrier(struct r10conf *conf, int force)
 
 	/* Wait until no block IO is waiting (unless 'force') */
 	wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting,
-			    conf->resync_lock, );
+			    conf->resync_lock);
 
 	/* block any new IO from starting */
 	conf->barrier++;

@@ -960,7 +960,7 @@ static void raise_barrier(struct r10conf *conf, int force)
 	/* Now wait for all pending IO to complete */
 	wait_event_lock_irq(conf->wait_barrier,
 			    !conf->nr_pending && conf->barrier < RESYNC_DEPTH,
-			    conf->resync_lock, );
+			    conf->resync_lock);
 
 	spin_unlock_irq(&conf->resync_lock);
 }

@@ -993,8 +993,7 @@ static void wait_barrier(struct r10conf *conf)
 				    (conf->nr_pending &&
 				     current->bio_list &&
 				     !bio_list_empty(current->bio_list)),
-				    conf->resync_lock,
-			);
+				    conf->resync_lock);
 		conf->nr_waiting--;
 	}
 	conf->nr_pending++;

@@ -1027,10 +1026,10 @@ static void freeze_array(struct r10conf *conf)
 	spin_lock_irq(&conf->resync_lock);
 	conf->barrier++;
 	conf->nr_waiting++;
-	wait_event_lock_irq(conf->wait_barrier,
-			    conf->nr_pending == conf->nr_queued+1,
-			    conf->resync_lock,
-			    flush_pending_writes(conf));
+	wait_event_lock_irq_cmd(conf->wait_barrier,
+				conf->nr_pending == conf->nr_queued+1,
+				conf->resync_lock,
+				flush_pending_writes(conf));
 
 	spin_unlock_irq(&conf->resync_lock);
 }

@@ -466,7 +466,7 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
 	do {
 		wait_event_lock_irq(conf->wait_for_stripe,
 				    conf->quiesce == 0 || noquiesce,
-				    conf->device_lock, /* nothing */);
+				    conf->device_lock);
 		sh = __find_stripe(conf, sector, conf->generation - previous);
 		if (!sh) {
 			if (!conf->inactive_blocked)

@@ -480,8 +480,7 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
 						    (atomic_read(&conf->active_stripes)
 						     < (conf->max_nr_stripes *3/4)
 						     || !conf->inactive_blocked),
-						    conf->device_lock,
-						    );
+						    conf->device_lock);
 				conf->inactive_blocked = 0;
 			} else
 				init_stripe(sh, sector, previous);

@@ -1646,8 +1645,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 		spin_lock_irq(&conf->device_lock);
 		wait_event_lock_irq(conf->wait_for_stripe,
 				    !list_empty(&conf->inactive_list),
-				    conf->device_lock,
-				    );
+				    conf->device_lock);
 		osh = get_free_stripe(conf);
 		spin_unlock_irq(&conf->device_lock);
 		atomic_set(&nsh->count, 1);

@@ -4003,7 +4001,7 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 		spin_lock_irq(&conf->device_lock);
 		wait_event_lock_irq(conf->wait_for_stripe,
 				    conf->quiesce == 0,
-				    conf->device_lock, /* nothing */);
+				    conf->device_lock);
 		atomic_inc(&conf->active_aligned_reads);
 		spin_unlock_irq(&conf->device_lock);
 

@@ -6095,7 +6093,7 @@ static void raid5_quiesce(struct mddev *mddev, int state)
 		wait_event_lock_irq(conf->wait_for_stripe,
 				    atomic_read(&conf->active_stripes) == 0 &&
 				    atomic_read(&conf->active_aligned_reads) == 0,
-				    conf->device_lock, /* nothing */);
+				    conf->device_lock);
 		conf->quiesce = 1;
 		spin_unlock_irq(&conf->device_lock);
 		/* allow reshape to continue */

@@ -550,6 +550,170 @@ do {									\
 	__ret;								\
 })
 
+
+#define __wait_event_lock_irq(wq, condition, lock, cmd)			\
+do {									\
+	DEFINE_WAIT(__wait);						\
+									\
+	for (;;) {							\
+		prepare_to_wait(&wq, &__wait, TASK_UNINTERRUPTIBLE);	\
+		if (condition)						\
+			break;						\
+		spin_unlock_irq(&lock);					\
+		cmd;							\
+		schedule();						\
+		spin_lock_irq(&lock);					\
+	}								\
+	finish_wait(&wq, &__wait);					\
+} while (0)
+
+/**
+ * wait_event_lock_irq_cmd - sleep until a condition gets true. The
+ *			     condition is checked under the lock. This
+ *			     is expected to be called with the lock
+ *			     taken.
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @lock: a locked spinlock_t, which will be released before cmd
+ *	  and schedule() and reacquired afterwards.
+ * @cmd: a command which is invoked outside the critical section before
+ *	 sleep
+ *
+ * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
+ * @condition evaluates to true. The @condition is checked each time
+ * the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ *
+ * This is supposed to be called while holding the lock. The lock is
+ * dropped before invoking the cmd and going to sleep and is reacquired
+ * afterwards.
+ */
+#define wait_event_lock_irq_cmd(wq, condition, lock, cmd)		\
+do {									\
+	if (condition)							\
+		break;							\
+	__wait_event_lock_irq(wq, condition, lock, cmd);		\
+} while (0)
+
+/**
+ * wait_event_lock_irq - sleep until a condition gets true. The
+ *			 condition is checked under the lock. This
+ *			 is expected to be called with the lock
+ *			 taken.
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @lock: a locked spinlock_t, which will be released before schedule()
+ *	  and reacquired afterwards.
+ *
+ * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
+ * @condition evaluates to true. The @condition is checked each time
+ * the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ *
+ * This is supposed to be called while holding the lock. The lock is
+ * dropped before going to sleep and is reacquired afterwards.
+ */
+#define wait_event_lock_irq(wq, condition, lock)			\
+do {									\
+	if (condition)							\
+		break;							\
+	__wait_event_lock_irq(wq, condition, lock, );			\
+} while (0)
+
+
+#define __wait_event_interruptible_lock_irq(wq, condition,		\
+					    lock, ret, cmd)		\
+do {									\
+	DEFINE_WAIT(__wait);						\
+									\
+	for (;;) {							\
+		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
+		if (condition)						\
+			break;						\
+		if (signal_pending(current)) {				\
+			ret = -ERESTARTSYS;				\
+			break;						\
+		}							\
+		spin_unlock_irq(&lock);					\
+		cmd;							\
+		schedule();						\
+		spin_lock_irq(&lock);					\
+	}								\
+	finish_wait(&wq, &__wait);					\
+} while (0)
+
+/**
+ * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true.
+ *		The condition is checked under the lock. This is expected to
+ *		be called with the lock taken.
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @lock: a locked spinlock_t, which will be released before cmd and
+ *	  schedule() and reacquired afterwards.
+ * @cmd: a command which is invoked outside the critical section before
+ *	 sleep
+ *
+ * The process is put to sleep (TASK_INTERRUPTIBLE) until the
+ * @condition evaluates to true or a signal is received. The @condition is
+ * checked each time the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ *
+ * This is supposed to be called while holding the lock. The lock is
+ * dropped before invoking the cmd and going to sleep and is reacquired
+ * afterwards.
+ *
+ * The macro will return -ERESTARTSYS if it was interrupted by a signal
+ * and 0 if @condition evaluated to true.
+ */
+#define wait_event_interruptible_lock_irq_cmd(wq, condition, lock, cmd)	\
+({									\
+	int __ret = 0;							\
+									\
+	if (!(condition))						\
+		__wait_event_interruptible_lock_irq(wq, condition,	\
+						    lock, __ret, cmd);	\
+	__ret;								\
+})
+
+/**
+ * wait_event_interruptible_lock_irq - sleep until a condition gets true.
+ *		The condition is checked under the lock. This is expected
+ *		to be called with the lock taken.
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @lock: a locked spinlock_t, which will be released before schedule()
+ *	  and reacquired afterwards.
+ *
+ * The process is put to sleep (TASK_INTERRUPTIBLE) until the
+ * @condition evaluates to true or signal is received. The @condition is
+ * checked each time the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ *
+ * This is supposed to be called while holding the lock. The lock is
+ * dropped before going to sleep and is reacquired afterwards.
+ *
+ * The macro will return -ERESTARTSYS if it was interrupted by a signal
+ * and 0 if @condition evaluated to true.
+ */
+#define wait_event_interruptible_lock_irq(wq, condition, lock)		\
+({									\
+	int __ret = 0;							\
+									\
+	if (!(condition))						\
+		__wait_event_interruptible_lock_irq(wq, condition,	\
+						    lock, __ret, );	\
+	__ret;								\
+})
+
+
 /*
  * These are the old interfaces to sleep waiting for an event.
  * They are racy.  DO NOT use them, use the wait_event* interfaces above.

@@ -463,6 +463,7 @@ out:
  */
 static void loop_add_bio(struct loop_device *lo, struct bio *bio)
 {
+	lo->lo_bio_count++;
 	bio_list_add(&lo->lo_bio_list, bio);
 }
 

@@ -471,6 +472,7 @@ static void loop_add_bio(struct loop_device *lo, struct bio *bio)
  */
 static struct bio *loop_get_bio(struct loop_device *lo)
 {
+	lo->lo_bio_count--;
 	return bio_list_pop(&lo->lo_bio_list);
 }
 

@@ -489,6 +491,10 @@ static void loop_make_request(struct request_queue *q, struct bio *old_bio)
 		goto out;
 	if (unlikely(rw == WRITE && (lo->lo_flags & LO_FLAGS_READ_ONLY)))
 		goto out;
+	if (lo->lo_bio_count >= q->nr_congestion_on)
+		wait_event_lock_irq(lo->lo_req_wait,
+				    lo->lo_bio_count < q->nr_congestion_off,
+				    lo->lo_lock);
 	loop_add_bio(lo, old_bio);
 	wake_up(&lo->lo_event);
 	spin_unlock_irq(&lo->lo_lock);

@@ -546,6 +552,8 @@ static int loop_thread(void *data)
 			continue;
 		spin_lock_irq(&lo->lo_lock);
 		bio = loop_get_bio(lo);
+		if (lo->lo_bio_count < lo->lo_queue->nr_congestion_off)
+			wake_up(&lo->lo_req_wait);
 		spin_unlock_irq(&lo->lo_lock);
 
 		BUG_ON(!bio);

@@ -873,6 +881,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->transfer = transfer_none;
 	lo->ioctl = NULL;
 	lo->lo_sizelimit = 0;
+	lo->lo_bio_count = 0;
 	lo->old_gfp_mask = mapping_gfp_mask(mapping);
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 

@@ -1673,6 +1682,7 @@ static int loop_add(struct loop_device **l, int i)
 	lo->lo_number		= i;
 	lo->lo_thread		= NULL;
 	init_waitqueue_head(&lo->lo_event);
+	init_waitqueue_head(&lo->lo_req_wait);
 	spin_lock_init(&lo->lo_lock);
 	disk->major		= LOOP_MAJOR;
 	disk->first_minor	= i << part_shift;

@@ -53,10 +53,13 @@ struct loop_device {
 
 	spinlock_t		lo_lock;
 	struct bio_list		lo_bio_list;
+	unsigned int		lo_bio_count;
 	int			lo_state;
 	struct mutex		lo_ctl_mutex;
 	struct task_struct	*lo_thread;
 	wait_queue_head_t	lo_event;
+	/* wait queue for incoming requests */
+	wait_queue_head_t	lo_req_wait;
 
 	struct request_queue	*lo_queue;
 	struct gendisk		*lo_disk;

@@ -555,14 +555,13 @@ do {									\
 do {									\
 	DEFINE_WAIT(__wait);						\
 									\
-	cmd;								\
 	for (;;) {							\
 		prepare_to_wait(&wq, &__wait, TASK_UNINTERRUPTIBLE);	\
 		if (condition)						\
 			break;						\
 		spin_unlock_irq(&lock);					\
-		schedule();						\
 		cmd;							\
+		schedule();						\
 		spin_lock_irq(&lock);					\
 	}								\
 	finish_wait(&wq, &__wait);					\

@@ -575,8 +574,8 @@ do {									\
  *			     taken.
  * @wq: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
- * @lock: a locked spinlock_t, which will be released before schedule()
- *	  and cmd reacquired afterwards.
+ * @lock: a locked spinlock_t, which will be released before cmd
+ *	  and schedule() and reacquired afterwards.
  * @cmd: a command which is invoked outside the critical section before
  *	 sleep
  *

@@ -588,7 +587,7 @@ do {									\
  * change the result of the wait condition.
  *
  * This is supposed to be called while holding the lock. The lock is
- * dropped before going to sleep and invoking the cmd and is reacquired
+ * dropped before invoking the cmd and going to sleep and is reacquired
  * afterwards.
  */
 #define wait_event_lock_irq_cmd(wq, condition, lock, cmd)		\

@@ -631,7 +630,6 @@ do {									\
 do {									\
 	DEFINE_WAIT(__wait);						\
 									\
-	cmd;								\
 	for (;;) {							\
 		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
 		if (condition)						\

@@ -641,8 +639,8 @@ do {									\
 			break;						\
 		}							\
 		spin_unlock_irq(&lock);					\
-		schedule();						\
 		cmd;							\
+		schedule();						\
 		spin_lock_irq(&lock);					\
 	}								\
 	finish_wait(&wq, &__wait);					\

@@ -654,8 +652,8 @@ do {									\
  *		be called with the lock taken.
  * @wq: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
- * @lock: a locked spinlock_t, which will be released before schedule()
- *	  and cmd reacquired afterwards.
+ * @lock: a locked spinlock_t, which will be released before cmd and
+ *	  schedule() and reacquired afterwards.
  * @cmd: a command which is invoked outside the critical section before
  *	 sleep
  *

@@ -667,7 +665,7 @@ do {									\
  * change the result of the wait condition.
  *
  * This is supposed to be called while holding the lock. The lock is
- * dropped before going to sleep and invoking the cmd and is reacquired
+ * dropped before invoking the cmd and going to sleep and is reacquired
  * afterwards.
  *
  * The macro will return -ERESTARTSYS if it was interrupted by a signal