Merge tag 'for-6.1/block-2022-10-03' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull requests via Christoph:
      - handle number of queue changes in the TCP and RDMA drivers
        (Daniel Wagner)
      - allow changing the number of queues in nvmet (Daniel Wagner)
      - also consider host_iface when checking ip options (Daniel
        Wagner)
      - don't map pages which can't come from HIGHMEM (Fabio M. De
        Francesco)
      - avoid unnecessary flush bios in nvmet (Guixin Liu)
      - shrink and better pack the nvme_iod structure (Keith Busch)
      - add comment for unaligned "fake" nqn (Linjun Bao)
      - print actual source IP address through sysfs "address" attr
        (Martin Belanger)
      - various cleanups (Jackie Liu, Wolfram Sang, Genjian Zhang)
      - handle effects after freeing the request (Keith Busch)
      - copy firmware_rev on each init (Keith Busch)
      - restrict management ioctls to admin (Keith Busch)
      - ensure subsystem reset is single threaded (Keith Busch)
      - report the actual number of tagset maps in nvme-pci (Keith
        Busch)
      - small fabrics authentication fixups (Christoph Hellwig)
      - add common code for tagset allocation and freeing (Christoph
        Hellwig)
      - stop using the request_queue in nvmet (Christoph Hellwig)
      - set min_align_mask before calculating max_hw_sectors (Rishabh
        Bhatnagar)
      - send a rediscover uevent when a persistent discovery controller
        reconnects (Sagi Grimberg)
      - misc nvmet-tcp fixes (Varun Prakash, zhenwei pi)

 - MD pull request via Song:
      - Various raid5 fix and clean up, by Logan Gunthorpe and David
        Sloan.
      - Raid10 performance optimization, by Yu Kuai.

 - sbitmap wakeup hang fixes (Hugh, Keith, Jan, Yu)

 - IO scheduler switching quisce fix (Keith)

 - s390/dasd block driver updates (Stefan)

 - support for recovery for the ublk driver (ZiyangZhang)

 - rnbd drivers fixes and updates (Guoqing, Santosh, ye, Christoph)

 - blk-mq and null_blk map fixes (Bart)

 - various bcache fixes (Coly, Jilin, Jules)

 - nbd signal hang fix (Shigeru)

 - block writeback throttling fix (Yu)

 - optimize the passthrough mapping handling (me)

 - prepare block cgroups to being gendisk based (Christoph)

 - get rid of an old PSI hack in the block layer, moving it to the
   callers instead where it belongs (Christoph)

 - blk-throttle fixes and cleanups (Yu)

 - misc fixes and cleanups (Liu Shixin, Liu Song, Miaohe, Pankaj,
   Ping-Xiang, Wolfram, Saurabh, Li Jinlin, Li Lei, Lin, Li zeming,
   Miaohe, Bart, Coly, Gaosheng

* tag 'for-6.1/block-2022-10-03' of git://git.kernel.dk/linux: (162 commits)
  sbitmap: fix lockup while swapping
  block: add rationale for not using blk_mq_plug() when applicable
  block: adapt blk_mq_plug() to not plug for writes that require a zone lock
  s390/dasd: use blk_mq_alloc_disk
  blk-cgroup: don't update the blkg lookup hint in blkg_conf_prep
  nvmet: don't look at the request_queue in nvmet_bdev_set_limits
  nvmet: don't look at the request_queue in nvmet_bdev_zone_mgmt_emulate_all
  blk-mq: use quiesced elevator switch when reinitializing queues
  block: replace blk_queue_nowait with bdev_nowait
  nvme: remove nvme_ctrl_init_connect_q
  nvme-loop: use the tagset alloc/free helpers
  nvme-loop: store the generic nvme_ctrl in set->driver_data
  nvme-loop: initialize sqsize later
  nvme-fc: use the tagset alloc/free helpers
  nvme-fc: store the generic nvme_ctrl in set->driver_data
  nvme-fc: keep ctrl->sqsize in sync with opts->queue_size
  nvme-rdma: use the tagset alloc/free helpers
  nvme-rdma: store the generic nvme_ctrl in set->driver_data
  nvme-tcp: use the tagset alloc/free helpers
  nvme-tcp: store the generic nvme_ctrl in set->driver_data
  ...

12 files changed, 263 insertions, 174 deletions

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 2acda9cea0f9..aebb7ef10e63 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -107,7 +107,7 @@
  *
  * BTREE NODES:
  *
- * Our unit of allocation is a bucket, and we we can't arbitrarily allocate and
+ * Our unit of allocation is a bucket, and we can't arbitrarily allocate and
  * free smaller than a bucket - so, that's how big our btree nodes are.
  *
  * (If buckets are really big we'll only use part of the bucket for a btree node
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 94d38e8a59b3..2bba4d6aaaa2 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -1264,7 +1264,7 @@ static void __btree_sort(struct btree_keys *b, struct btree_iter *iter,
 		 *
 		 * Don't worry event 'out' is allocated from mempool, it can
 		 * still be swapped here. Because state->pool is a page mempool
-		 * creaated by by mempool_init_page_pool(), which allocates
+		 * created by mempool_init_page_pool(), which allocates
 		 * pages by alloc_pages() indeed.
 		 */
 
diff --git a/drivers/md/bcache/stats.h b/drivers/md/bcache/stats.h
index ca4f435f7216..bd3afc856d53 100644
--- a/drivers/md/bcache/stats.h
+++ b/drivers/md/bcache/stats.h
@@ -54,7 +54,6 @@ void bch_cache_accounting_destroy(struct cache_accounting *acc);
 
 void bch_mark_cache_accounting(struct cache_set *c, struct bcache_device *d,
 			       bool hit, bool bypass);
-void bch_mark_cache_readahead(struct cache_set *c, struct bcache_device *d);
 void bch_mark_cache_miss_collision(struct cache_set *c,
 				   struct bcache_device *d);
 void bch_mark_sectors_bypassed(struct cache_set *c,
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 3f0ff3aab6f2..0285b676e983 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -157,6 +157,53 @@ static void __update_writeback_rate(struct cached_dev *dc)
 	dc->writeback_rate_target = target;
 }
 
+static bool idle_counter_exceeded(struct cache_set *c)
+{
+	int counter, dev_nr;
+
+	/*
+	 * If c->idle_counter is overflow (idel for really long time),
+	 * reset as 0 and not set maximum rate this time for code
+	 * simplicity.
+	 */
+	counter = atomic_inc_return(&c->idle_counter);
+	if (counter <= 0) {
+		atomic_set(&c->idle_counter, 0);
+		return false;
+	}
+
+	dev_nr = atomic_read(&c->attached_dev_nr);
+	if (dev_nr == 0)
+		return false;
+
+	/*
+	 * c->idle_counter is increased by writeback thread of all
+	 * attached backing devices, in order to represent a rough
+	 * time period, counter should be divided by dev_nr.
+	 * Otherwise the idle time cannot be larger with more backing
+	 * device attached.
+	 * The following calculation equals to checking
+	 *	(counter / dev_nr) < (dev_nr * 6)
+	 */
+	if (counter < (dev_nr * dev_nr * 6))
+		return false;
+
+	return true;
+}
+
+/*
+ * Idle_counter is increased every time when update_writeback_rate() is
+ * called. If all backing devices attached to the same cache set have
+ * identical dc->writeback_rate_update_seconds values, it is about 6
+ * rounds of update_writeback_rate() on each backing device before
+ * c->at_max_writeback_rate is set to 1, and then max wrteback rate set
+ * to each dc->writeback_rate.rate.
+ * In order to avoid extra locking cost for counting exact dirty cached
+ * devices number, c->attached_dev_nr is used to calculate the idle
+ * throushold. It might be bigger if not all cached device are in write-
+ * back mode, but it still works well with limited extra rounds of
+ * update_writeback_rate().
+ */
 static bool set_at_max_writeback_rate(struct cache_set *c,
 				       struct cached_dev *dc)
 {
@@ -167,21 +214,8 @@ static bool set_at_max_writeback_rate(struct cache_set *c,
 	/* Don't set max writeback rate if gc is running */
 	if (!c->gc_mark_valid)
 		return false;
-	/*
-	 * Idle_counter is increased everytime when update_writeback_rate() is
-	 * called. If all backing devices attached to the same cache set have
-	 * identical dc->writeback_rate_update_seconds values, it is about 6
-	 * rounds of update_writeback_rate() on each backing device before
-	 * c->at_max_writeback_rate is set to 1, and then max wrteback rate set
-	 * to each dc->writeback_rate.rate.
-	 * In order to avoid extra locking cost for counting exact dirty cached
-	 * devices number, c->attached_dev_nr is used to calculate the idle
-	 * throushold. It might be bigger if not all cached device are in write-
-	 * back mode, but it still works well with limited extra rounds of
-	 * update_writeback_rate().
-	 */
-	if (atomic_inc_return(&c->idle_counter) <
-	    atomic_read(&c->attached_dev_nr) * 6)
+
+	if (!idle_counter_exceeded(c))
 		return false;
 
 	if (atomic_read(&c->at_max_writeback_rate) != 1)
@@ -195,13 +229,10 @@ static bool set_at_max_writeback_rate(struct cache_set *c,
 	dc->writeback_rate_change = 0;
 
 	/*
-	 * Check c->idle_counter and c->at_max_writeback_rate agagain in case
-	 * new I/O arrives during before set_at_max_writeback_rate() returns.
-	 * Then the writeback rate is set to 1, and its new value should be
-	 * decided via __update_writeback_rate().
+	 * In case new I/O arrives during before
+	 * set_at_max_writeback_rate() returns.
 	 */
-	if ((atomic_read(&c->idle_counter) <
-	     atomic_read(&c->attached_dev_nr) * 6) ||
+	if (!idle_counter_exceeded(c) ||
 	    !atomic_read(&c->at_max_writeback_rate))
 		return false;
 
@@ -801,10 +832,9 @@ static int bch_writeback_thread(void *arg)
 		}
 	}
 
-	if (dc->writeback_write_wq) {
-		flush_workqueue(dc->writeback_write_wq);
+	if (dc->writeback_write_wq)
 		destroy_workqueue(dc->writeback_write_wq);
-	}
+
 	cached_dev_put(dc);
 	wait_for_kthread_stop();
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 332f96b58252..d8034ff0cb24 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1856,9 +1856,7 @@ static bool dm_table_supports_write_zeroes(struct dm_table *t)
 static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev,
 				     sector_t start, sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return !blk_queue_nowait(q);
+	return !bdev_nowait(dev->bdev);
 }
 
 static bool dm_table_supports_nowait(struct dm_table *t)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 729be2c5296c..a467b492d4ad 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5845,7 +5845,7 @@ int md_run(struct mddev *mddev)
 			}
 		}
 		sysfs_notify_dirent_safe(rdev->sysfs_state);
-		nowait = nowait && blk_queue_nowait(bdev_get_queue(rdev->bdev));
+		nowait = nowait && bdev_nowait(rdev->bdev);
 	}
 
 	if (!bioset_initialized(&mddev->bio_set)) {
@@ -6982,7 +6982,7 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
 	 * If the new disk does not support REQ_NOWAIT,
 	 * disable on the whole MD.
 	 */
-	if (!blk_queue_nowait(bdev_get_queue(rdev->bdev))) {
+	if (!bdev_nowait(rdev->bdev)) {
 		pr_info("%s: Disabling nowait because %pg does not support nowait\n",
 			mdname(mddev), rdev->bdev);
 		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->queue);
@@ -8156,7 +8156,6 @@ static void *md_seq_start(struct seq_file *seq, loff_t *pos)
 	list_for_each(tmp,&all_mddevs)
 		if (!l--) {
 			mddev = list_entry(tmp, struct mddev, all_mddevs);
-			mddev_get(mddev);
 			if (!mddev_get(mddev))
 				continue;
 			spin_unlock(&all_mddevs_lock);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 78addfe4a0c9..857c49399c28 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -47,7 +47,7 @@ static void dump_zones(struct mddev *mddev)
 		int len = 0;
 
 		for (k = 0; k < conf->strip_zone[j].nb_dev; k++)
-			len += snprintf(line+len, 200-len, "%s%pg", k?"/":"",
+			len += scnprintf(line+len, 200-len, "%s%pg", k?"/":"",
 				conf->devlist[j * raid_disks + k]->bdev);
 		pr_debug("md: zone%d=[%s]\n", j, line);
 
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 64d6e4cd8a3a..3aa8b6e11d58 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -79,6 +79,21 @@ static void end_reshape(struct r10conf *conf);
 
 #include "raid1-10.c"
 
+#define NULL_CMD
+#define cmd_before(conf, cmd) \
+	do { \
+		write_sequnlock_irq(&(conf)->resync_lock); \
+		cmd; \
+	} while (0)
+#define cmd_after(conf) write_seqlock_irq(&(conf)->resync_lock)
+
+#define wait_event_barrier_cmd(conf, cond, cmd) \
+	wait_event_cmd((conf)->wait_barrier, cond, cmd_before(conf, cmd), \
+		       cmd_after(conf))
+
+#define wait_event_barrier(conf, cond) \
+	wait_event_barrier_cmd(conf, cond, NULL_CMD)
+
 /*
  * for resync bio, r10bio pointer can be retrieved from the per-bio
  * 'struct resync_pages'.
@@ -274,6 +289,12 @@ static void put_buf(struct r10bio *r10_bio)
 	lower_barrier(conf);
 }
 
+static void wake_up_barrier(struct r10conf *conf)
+{
+	if (wq_has_sleeper(&conf->wait_barrier))
+		wake_up(&conf->wait_barrier);
+}
+
 static void reschedule_retry(struct r10bio *r10_bio)
 {
 	unsigned long flags;
@@ -930,78 +951,101 @@ static void flush_pending_writes(struct r10conf *conf)
 
 static void raise_barrier(struct r10conf *conf, int force)
 {
+	write_seqlock_irq(&conf->resync_lock);
 	BUG_ON(force && !conf->barrier);
-	spin_lock_irq(&conf->resync_lock);
 
 	/* Wait until no block IO is waiting (unless 'force') */
-	wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting,
-			    conf->resync_lock);
+	wait_event_barrier(conf, force || !conf->nr_waiting);
 
 	/* block any new IO from starting */
-	conf->barrier++;
+	WRITE_ONCE(conf->barrier, conf->barrier + 1);
 
 	/* Now wait for all pending IO to complete */
-	wait_event_lock_irq(conf->wait_barrier,
-			    !atomic_read(&conf->nr_pending) && conf->barrier < RESYNC_DEPTH,
-			    conf->resync_lock);
+	wait_event_barrier(conf, !atomic_read(&conf->nr_pending) &&
+				 conf->barrier < RESYNC_DEPTH);
 
-	spin_unlock_irq(&conf->resync_lock);
+	write_sequnlock_irq(&conf->resync_lock);
 }
 
 static void lower_barrier(struct r10conf *conf)
 {
 	unsigned long flags;
-	spin_lock_irqsave(&conf->resync_lock, flags);
-	conf->barrier--;
-	spin_unlock_irqrestore(&conf->resync_lock, flags);
+
+	write_seqlock_irqsave(&conf->resync_lock, flags);
+	WRITE_ONCE(conf->barrier, conf->barrier - 1);
+	write_sequnlock_irqrestore(&conf->resync_lock, flags);
 	wake_up(&conf->wait_barrier);
 }
 
+static bool stop_waiting_barrier(struct r10conf *conf)
+{
+	struct bio_list *bio_list = current->bio_list;
+
+	/* barrier is dropped */
+	if (!conf->barrier)
+		return true;
+
+	/*
+	 * If there are already pending requests (preventing the barrier from
+	 * rising completely), and the pre-process bio queue isn't empty, then
+	 * don't wait, as we need to empty that queue to get the nr_pending
+	 * count down.
+	 */
+	if (atomic_read(&conf->nr_pending) && bio_list &&
+	    (!bio_list_empty(&bio_list[0]) || !bio_list_empty(&bio_list[1])))
+		return true;
+
+	/* move on if recovery thread is blocked by us */
+	if (conf->mddev->thread->tsk == current &&
+	    test_bit(MD_RECOVERY_RUNNING, &conf->mddev->recovery) &&
+	    conf->nr_queued > 0)
+		return true;
+
+	return false;
+}
+
+static bool wait_barrier_nolock(struct r10conf *conf)
+{
+	unsigned int seq = read_seqbegin(&conf->resync_lock);
+
+	if (READ_ONCE(conf->barrier))
+		return false;
+
+	atomic_inc(&conf->nr_pending);
+	if (!read_seqretry(&conf->resync_lock, seq))
+		return true;
+
+	if (atomic_dec_and_test(&conf->nr_pending))
+		wake_up_barrier(conf);
+
+	return false;
+}
+
 static bool wait_barrier(struct r10conf *conf, bool nowait)
 {
 	bool ret = true;
 
-	spin_lock_irq(&conf->resync_lock);
+	if (wait_barrier_nolock(conf))
+		return true;
+
+	write_seqlock_irq(&conf->resync_lock);
 	if (conf->barrier) {
-		struct bio_list *bio_list = current->bio_list;
-		conf->nr_waiting++;
-		/* Wait for the barrier to drop.
-		 * However if there are already pending
-		 * requests (preventing the barrier from
-		 * rising completely), and the
-		 * pre-process bio queue isn't empty,
-		 * then don't wait, as we need to empty
-		 * that queue to get the nr_pending
-		 * count down.
-		 */
 		/* Return false when nowait flag is set */
 		if (nowait) {
 			ret = false;
 		} else {
+			conf->nr_waiting++;
 			raid10_log(conf->mddev, "wait barrier");
-			wait_event_lock_irq(conf->wait_barrier,
-					    !conf->barrier ||
-					    (atomic_read(&conf->nr_pending) &&
-					     bio_list &&
-					     (!bio_list_empty(&bio_list[0]) ||
-					      !bio_list_empty(&bio_list[1]))) ||
-					     /* move on if recovery thread is
-					      * blocked by us
-					      */
-					     (conf->mddev->thread->tsk == current &&
-					      test_bit(MD_RECOVERY_RUNNING,
-						       &conf->mddev->recovery) &&
-					      conf->nr_queued > 0),
-					    conf->resync_lock);
+			wait_event_barrier(conf, stop_waiting_barrier(conf));
+			conf->nr_waiting--;
 		}
-		conf->nr_waiting--;
 		if (!conf->nr_waiting)
 			wake_up(&conf->wait_barrier);
 	}
 	/* Only increment nr_pending when we wait */
 	if (ret)
 		atomic_inc(&conf->nr_pending);
-	spin_unlock_irq(&conf->resync_lock);
+	write_sequnlock_irq(&conf->resync_lock);
 	return ret;
 }
 
@@ -1009,7 +1053,7 @@ static void allow_barrier(struct r10conf *conf)
 {
 	if ((atomic_dec_and_test(&conf->nr_pending)) ||
 			(conf->array_freeze_pending))
-		wake_up(&conf->wait_barrier);
+		wake_up_barrier(conf);
 }
 
 static void freeze_array(struct r10conf *conf, int extra)
@@ -1026,27 +1070,24 @@ static void freeze_array(struct r10conf *conf, int extra)
 	 * must match the number of pending IOs (nr_pending) before
 	 * we continue.
 	 */
-	spin_lock_irq(&conf->resync_lock);
+	write_seqlock_irq(&conf->resync_lock);
 	conf->array_freeze_pending++;
-	conf->barrier++;
+	WRITE_ONCE(conf->barrier, conf->barrier + 1);
 	conf->nr_waiting++;
-	wait_event_lock_irq_cmd(conf->wait_barrier,
-				atomic_read(&conf->nr_pending) == conf->nr_queued+extra,
-				conf->resync_lock,
-				flush_pending_writes(conf));
-
+	wait_event_barrier_cmd(conf, atomic_read(&conf->nr_pending) ==
+			conf->nr_queued + extra, flush_pending_writes(conf));
 	conf->array_freeze_pending--;
-	spin_unlock_irq(&conf->resync_lock);
+	write_sequnlock_irq(&conf->resync_lock);
 }
 
 static void unfreeze_array(struct r10conf *conf)
 {
 	/* reverse the effect of the freeze */
-	spin_lock_irq(&conf->resync_lock);
-	conf->barrier--;
+	write_seqlock_irq(&conf->resync_lock);
+	WRITE_ONCE(conf->barrier, conf->barrier - 1);
 	conf->nr_waiting--;
 	wake_up(&conf->wait_barrier);
-	spin_unlock_irq(&conf->resync_lock);
+	write_sequnlock_irq(&conf->resync_lock);
 }
 
 static sector_t choose_data_offset(struct r10bio *r10_bio,
@@ -1885,7 +1926,7 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
 	__make_request(mddev, bio, sectors);
 
 	/* In case raid10d snuck in to freeze_array */
-	wake_up(&conf->wait_barrier);
+	wake_up_barrier(conf);
 	return true;
 }
 
@@ -1980,7 +2021,7 @@ static int enough(struct r10conf *conf, int ignore)
  * Otherwise, it must be degraded:
  *	- recovery is interrupted.
  *	- &mddev->degraded is bumped.
-
+ *
  * @rdev is marked as &Faulty excluding case when array is failed and
  * &mddev->fail_last_dev is off.
  */
@@ -4032,7 +4073,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 	INIT_LIST_HEAD(&conf->retry_list);
 	INIT_LIST_HEAD(&conf->bio_end_io_list);
 
-	spin_lock_init(&conf->resync_lock);
+	seqlock_init(&conf->resync_lock);
 	init_waitqueue_head(&conf->wait_barrier);
 	atomic_set(&conf->nr_pending, 0);
 
@@ -4351,7 +4392,7 @@ static void *raid10_takeover_raid0(struct mddev *mddev, sector_t size, int devs)
 				rdev->new_raid_disk = rdev->raid_disk * 2;
 				rdev->sectors = size;
 			}
-		conf->barrier = 1;
+		WRITE_ONCE(conf->barrier, 1);
 	}
 
 	return conf;
diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h
index 5c0804d8bb1f..8c072ce0bc54 100644
--- a/drivers/md/raid10.h
+++ b/drivers/md/raid10.h
@@ -76,7 +76,7 @@ struct r10conf {
 	/* queue pending writes and submit them on unplug */
 	struct bio_list		pending_bio_list;
 
-	spinlock_t		resync_lock;
+	seqlock_t		resync_lock;
 	atomic_t		nr_pending;
 	int			nr_waiting;
 	int			nr_queued;
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index f4e1cc1ece43..79c73330020b 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -125,7 +125,7 @@ struct r5l_log {
 					 * reclaimed.  if it's 0, reclaim spaces
 					 * used by io_units which are in
 					 * IO_UNIT_STRIPE_END state (eg, reclaim
-					 * dones't wait for specific io_unit
+					 * doesn't wait for specific io_unit
 					 * switching to IO_UNIT_STRIPE_END
 					 * state) */
 	wait_queue_head_t iounit_wait;
@@ -1327,9 +1327,9 @@ static void r5l_write_super_and_discard_space(struct r5l_log *log,
 	 * superblock is updated to new log tail. Updating superblock (either
 	 * directly call md_update_sb() or depend on md thread) must hold
 	 * reconfig mutex. On the other hand, raid5_quiesce is called with
-	 * reconfig_mutex hold. The first step of raid5_quiesce() is waitting
-	 * for all IO finish, hence waitting for reclaim thread, while reclaim
-	 * thread is calling this function and waitting for reconfig mutex. So
+	 * reconfig_mutex hold. The first step of raid5_quiesce() is waiting
+	 * for all IO finish, hence waiting for reclaim thread, while reclaim
+	 * thread is calling this function and waiting for reconfig mutex. So
 	 * there is a deadlock. We workaround this issue with a trylock.
 	 * FIXME: we could miss discard if we can't take reconfig mutex
 	 */
@@ -1923,7 +1923,8 @@ r5c_recovery_alloc_stripe(
 {
 	struct stripe_head *sh;
 
-	sh = raid5_get_active_stripe(conf, stripe_sect, 0, noblock, 0);
+	sh = raid5_get_active_stripe(conf, NULL, stripe_sect,
+				     noblock ? R5_GAS_NOBLOCK : 0);
 	if (!sh)
 		return NULL;  /* no more stripe available */
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 31a0cbf63384..7b820b81d8c2 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -36,6 +36,7 @@
  */
 
 #include <linux/blkdev.h>
+#include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/async_tx.h>
@@ -789,87 +790,80 @@ struct stripe_request_ctx {
  */
 static bool is_inactive_blocked(struct r5conf *conf, int hash)
 {
-	int active = atomic_read(&conf->active_stripes);
-
 	if (list_empty(conf->inactive_list + hash))
 		return false;
 
 	if (!test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state))
 		return true;
 
-	return active < (conf->max_nr_stripes * 3 / 4);
+	return (atomic_read(&conf->active_stripes) <
+		(conf->max_nr_stripes * 3 / 4));
 }
 
-static struct stripe_head *__raid5_get_active_stripe(struct r5conf *conf,
+struct stripe_head *raid5_get_active_stripe(struct r5conf *conf,
 		struct stripe_request_ctx *ctx, sector_t sector,
-		bool previous, bool noblock, bool noquiesce)
+		unsigned int flags)
 {
 	struct stripe_head *sh;
 	int hash = stripe_hash_locks_hash(conf, sector);
+	int previous = !!(flags & R5_GAS_PREVIOUS);
 
 	pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
 
 	spin_lock_irq(conf->hash_locks + hash);
 
-retry:
-	if (!noquiesce && conf->quiesce) {
-		/*
-		 * Must release the reference to batch_last before waiting,
-		 * on quiesce, otherwise the batch_last will hold a reference
-		 * to a stripe and raid5_quiesce() will deadlock waiting for
-		 * active_stripes to go to zero.
-		 */
-		if (ctx && ctx->batch_last) {
-			raid5_release_stripe(ctx->batch_last);
-			ctx->batch_last = NULL;
-		}
-
-		wait_event_lock_irq(conf->wait_for_quiescent, !conf->quiesce,
-				    *(conf->hash_locks + hash));
-	}
+	for (;;) {
+		if (!(flags & R5_GAS_NOQUIESCE) && conf->quiesce) {
+			/*
+			 * Must release the reference to batch_last before
+			 * waiting, on quiesce, otherwise the batch_last will
+			 * hold a reference to a stripe and raid5_quiesce()
+			 * will deadlock waiting for active_stripes to go to
+			 * zero.
+			 */
+			if (ctx && ctx->batch_last) {
+				raid5_release_stripe(ctx->batch_last);
+				ctx->batch_last = NULL;
+			}
 
-	sh = find_get_stripe(conf, sector, conf->generation - previous, hash);
-	if (sh)
-		goto out;
+			wait_event_lock_irq(conf->wait_for_quiescent,
+					    !conf->quiesce,
+					    *(conf->hash_locks + hash));
+		}
 
-	if (test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state))
-		goto wait_for_stripe;
+		sh = find_get_stripe(conf, sector, conf->generation - previous,
+				     hash);
+		if (sh)
+			break;
 
-	sh = get_free_stripe(conf, hash);
-	if (sh) {
-		r5c_check_stripe_cache_usage(conf);
-		init_stripe(sh, sector, previous);
-		atomic_inc(&sh->count);
-		goto out;
-	}
+		if (!test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) {
+			sh = get_free_stripe(conf, hash);
+			if (sh) {
+				r5c_check_stripe_cache_usage(conf);
+				init_stripe(sh, sector, previous);
+				atomic_inc(&sh->count);
+				break;
+			}
 
-	if (!test_bit(R5_DID_ALLOC, &conf->cache_state))
-		set_bit(R5_ALLOC_MORE, &conf->cache_state);
+			if (!test_bit(R5_DID_ALLOC, &conf->cache_state))
+				set_bit(R5_ALLOC_MORE, &conf->cache_state);
+		}
 
-wait_for_stripe:
-	if (noblock)
-		goto out;
+		if (flags & R5_GAS_NOBLOCK)
+			break;
 
-	set_bit(R5_INACTIVE_BLOCKED, &conf->cache_state);
-	r5l_wake_reclaim(conf->log, 0);
-	wait_event_lock_irq(conf->wait_for_stripe,
-			    is_inactive_blocked(conf, hash),
-			    *(conf->hash_locks + hash));
-	clear_bit(R5_INACTIVE_BLOCKED, &conf->cache_state);
-	goto retry;
+		set_bit(R5_INACTIVE_BLOCKED, &conf->cache_state);
+		r5l_wake_reclaim(conf->log, 0);
+		wait_event_lock_irq(conf->wait_for_stripe,
+				    is_inactive_blocked(conf, hash),
+				    *(conf->hash_locks + hash));
+		clear_bit(R5_INACTIVE_BLOCKED, &conf->cache_state);
+	}
 
-out:
 	spin_unlock_irq(conf->hash_locks + hash);
 	return sh;
 }
 
-struct stripe_head *raid5_get_active_stripe(struct r5conf *conf,
-		sector_t sector, bool previous, bool noblock, bool noquiesce)
-{
-	return __raid5_get_active_stripe(conf, NULL, sector, previous, noblock,
-					 noquiesce);
-}
-
 static bool is_full_stripe_write(struct stripe_head *sh)
 {
 	BUG_ON(sh->overwrite_disks > (sh->disks - sh->raid_conf->max_degraded));
@@ -4047,7 +4041,7 @@ static void handle_stripe_fill(struct stripe_head *sh,
 		 * back cache (prexor with orig_page, and then xor with
 		 * page) in the read path
 		 */
-		if (s->injournal && s->failed) {
+		if (s->to_read && s->injournal && s->failed) {
 			if (test_bit(STRIPE_R5C_CACHING, &sh->state))
 				r5c_make_stripe_write_out(sh);
 			goto out;
@@ -4636,7 +4630,8 @@ static void handle_stripe_expansion(struct r5conf *conf, struct stripe_head *sh)
 			sector_t bn = raid5_compute_blocknr(sh, i, 1);
 			sector_t s = raid5_compute_sector(conf, bn, 0,
 							  &dd_idx, NULL);
-			sh2 = raid5_get_active_stripe(conf, s, 0, 1, 1);
+			sh2 = raid5_get_active_stripe(conf, NULL, s,
+				R5_GAS_NOBLOCK | R5_GAS_NOQUIESCE);
 			if (sh2 == NULL)
 				/* so far only the early blocks of this stripe
 				 * have been requested.  When later blocks
@@ -5273,7 +5268,9 @@ static void handle_stripe(struct stripe_head *sh)
 	/* Finish reconstruct operations initiated by the expansion process */
 	if (sh->reconstruct_state == reconstruct_state_result) {
 		struct stripe_head *sh_src
-			= raid5_get_active_stripe(conf, sh->sector, 1, 1, 1);
+			= raid5_get_active_stripe(conf, NULL, sh->sector,
+					R5_GAS_PREVIOUS | R5_GAS_NOBLOCK |
+					R5_GAS_NOQUIESCE);
 		if (sh_src && test_bit(STRIPE_EXPAND_SOURCE, &sh_src->state)) {
 			/* sh cannot be written until sh_src has been read.
 			 * so arrange for sh to be delayed a little
@@ -5542,7 +5539,6 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 
 	if (is_badblock(rdev, sector, bio_sectors(raid_bio), &first_bad,
 			&bad_sectors)) {
-		bio_put(raid_bio);
 		rdev_dec_pending(rdev, mddev);
 		return 0;
 	}
@@ -5823,7 +5819,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 		DEFINE_WAIT(w);
 		int d;
 	again:
-		sh = raid5_get_active_stripe(conf, logical_sector, 0, 0, 0);
+		sh = raid5_get_active_stripe(conf, NULL, logical_sector, 0);
 		prepare_to_wait(&conf->wait_for_overlap, &w,
 				TASK_UNINTERRUPTIBLE);
 		set_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags);
@@ -5978,7 +5974,7 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 	enum stripe_result ret;
 	struct stripe_head *sh;
 	sector_t new_sector;
-	int previous = 0;
+	int previous = 0, flags = 0;
 	int seq, dd_idx;
 
 	seq = read_seqcount_begin(&conf->gen_lock);
@@ -6012,8 +6008,11 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 	pr_debug("raid456: %s, sector %llu logical %llu\n", __func__,
 		 new_sector, logical_sector);
 
-	sh = __raid5_get_active_stripe(conf, ctx, new_sector, previous,
-				       (bi->bi_opf & REQ_RAHEAD), 0);
+	if (previous)
+		flags |= R5_GAS_PREVIOUS;
+	if (bi->bi_opf & REQ_RAHEAD)
+		flags |= R5_GAS_NOBLOCK;
+	sh = raid5_get_active_stripe(conf, ctx, new_sector, flags);
 	if (unlikely(!sh)) {
 		/* cannot get stripe, just give-up */
 		bi->bi_status = BLK_STS_IOERR;
@@ -6362,7 +6361,8 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 	for (i = 0; i < reshape_sectors; i += RAID5_STRIPE_SECTORS(conf)) {
 		int j;
 		int skipped_disk = 0;
-		sh = raid5_get_active_stripe(conf, stripe_addr+i, 0, 0, 1);
+		sh = raid5_get_active_stripe(conf, NULL, stripe_addr+i,
+					     R5_GAS_NOQUIESCE);
 		set_bit(STRIPE_EXPANDING, &sh->state);
 		atomic_inc(&conf->reshape_stripes);
 		/* If any of this stripe is beyond the end of the old
@@ -6411,7 +6411,8 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 	if (last_sector >= mddev->dev_sectors)
 		last_sector = mddev->dev_sectors - 1;
 	while (first_sector <= last_sector) {
-		sh = raid5_get_active_stripe(conf, first_sector, 1, 0, 1);
+		sh = raid5_get_active_stripe(conf, NULL, first_sector,
+				R5_GAS_PREVIOUS | R5_GAS_NOQUIESCE);
 		set_bit(STRIPE_EXPAND_SOURCE, &sh->state);
 		set_bit(STRIPE_HANDLE, &sh->state);
 		raid5_release_stripe(sh);
@@ -6531,9 +6532,10 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n
 
 	md_bitmap_cond_end_sync(mddev->bitmap, sector_nr, false);
 
-	sh = raid5_get_active_stripe(conf, sector_nr, 0, 1, 0);
+	sh = raid5_get_active_stripe(conf, NULL, sector_nr,
+				     R5_GAS_NOBLOCK);
 	if (sh == NULL) {
-		sh = raid5_get_active_stripe(conf, sector_nr, 0, 0, 0);
+		sh = raid5_get_active_stripe(conf, NULL, sector_nr, 0);
 		/* make sure we don't swamp the stripe cache if someone else
 		 * is trying to get access
 		 */
@@ -6596,8 +6598,8 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio,
 			/* already done this stripe */
 			continue;
 
-		sh = raid5_get_active_stripe(conf, sector, 0, 1, 1);
-
+		sh = raid5_get_active_stripe(conf, NULL, sector,
+				R5_GAS_NOBLOCK | R5_GAS_NOQUIESCE);
 		if (!sh) {
 			/* failed to get a stripe - must wait */
 			conf->retry_read_aligned = raid_bio;
@@ -6781,7 +6783,18 @@ static void raid5d(struct md_thread *thread)
 			spin_unlock_irq(&conf->device_lock);
 			md_check_recovery(mddev);
 			spin_lock_irq(&conf->device_lock);
+
+			/*
+			 * Waiting on MD_SB_CHANGE_PENDING below may deadlock
+			 * seeing md_check_recovery() is needed to clear
+			 * the flag when using mdmon.
+			 */
+			continue;
 		}
+
+		wait_event_lock_irq(mddev->sb_wait,
+			!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
+			conf->device_lock);
 	}
 	pr_debug("%d stripes handled\n", handled);
 
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index a5082bed83c8..e873938a6125 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -803,16 +803,24 @@ raid5_get_dev_page(struct stripe_head *sh, int disk_idx)
 }
 #endif
 
-extern void md_raid5_kick_device(struct r5conf *conf);
-extern int raid5_set_cache_size(struct mddev *mddev, int size);
-extern sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous);
-extern void raid5_release_stripe(struct stripe_head *sh);
-extern sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector,
-				     int previous, int *dd_idx,
-				     struct stripe_head *sh);
-extern struct stripe_head *
-raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
-			bool previous, bool noblock, bool noquiesce);
-extern int raid5_calc_degraded(struct r5conf *conf);
-extern int r5c_journal_mode_set(struct mddev *mddev, int journal_mode);
+void md_raid5_kick_device(struct r5conf *conf);
+int raid5_set_cache_size(struct mddev *mddev, int size);
+sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous);
+void raid5_release_stripe(struct stripe_head *sh);
+sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector,
+		int previous, int *dd_idx, struct stripe_head *sh);
+
+struct stripe_request_ctx;
+/* get stripe from previous generation (when reshaping) */
+#define R5_GAS_PREVIOUS		(1 << 0)
+/* do not block waiting for a free stripe */
+#define R5_GAS_NOBLOCK		(1 << 1)
+/* do not block waiting for quiesce to be released */
+#define R5_GAS_NOQUIESCE	(1 << 2)
+struct stripe_head *raid5_get_active_stripe(struct r5conf *conf,
+		struct stripe_request_ctx *ctx, sector_t sector,
+		unsigned int flags);
+
+int raid5_calc_degraded(struct r5conf *conf);
+int r5c_journal_mode_set(struct mddev *mddev, int journal_mode);
 #endif