Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull md updates from Shaohua Li:
 "Mainly fixes bugs and improves performance:

   - Improve scalability for raid1 from Coly

   - Improve raid5-cache read performance, disk efficiency and IO
     pattern from Song and me

   - Fix a race condition of disk hotplug for linear from Coly

   - A few cleanup patches from Ming and Byungchul

   - Fix a memory leak from Neil

   - Fix WRITE SAME IO failure from me

   - Add doc for raid5-cache from me"

* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md: (23 commits)
  md/raid1: fix write behind issues introduced by bio_clone_bioset_partial
  md/raid1: handle flush request correctly
  md/linear: shutup lockdep warnning
  md/raid1: fix a use-after-free bug
  RAID1: avoid unnecessary spin locks in I/O barrier code
  RAID1: a new I/O barrier implementation to remove resync window
  md/raid5: Don't reinvent the wheel but use existing llist API
  md: fast clone bio in bio_clone_mddev()
  md: remove unnecessary check on mddev
  md/raid1: use bio_clone_bioset_partial() in case of write behind
  md: fail if mddev->bio_set can't be created
  block: introduce bio_clone_bioset_partial()
  md: disable WRITE SAME if it fails in underlayer disks
  md/raid5-cache: exclude reclaiming stripes in reclaim check
  md/raid5-cache: stripe reclaim only counts valid stripes
  MD: add doc for raid5-cache
  Documentation: move MD related doc into a separate dir
  md: ensure md devices are freed before module is unloaded.
  md/r5cache: improve journal device efficiency
  md/r5cache: enable chunk_aligned_read with write back cache
  ...

13 files changed, 768 insertions, 335 deletions

diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c
index 685aa2d77e25..b0536cfd8e17 100644
--- a/drivers/md/faulty.c
+++ b/drivers/md/faulty.c
@@ -214,7 +214,7 @@ static void faulty_make_request(struct mddev *mddev, struct bio *bio)
 		}
 	}
 	if (failit) {
-		struct bio *b = bio_clone_mddev(bio, GFP_NOIO, mddev);
+		struct bio *b = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
 
 		b->bi_bdev = conf->rdev->bdev;
 		b->bi_private = bio;
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index f1c7bbac31a5..3e38e0207a3e 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -53,18 +53,26 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
 	return conf->disks + lo;
 }
 
+/*
+ * In linear_congested() conf->raid_disks is used as a copy of
+ * mddev->raid_disks to iterate conf->disks[], because conf->raid_disks
+ * and conf->disks[] are created in linear_conf(), they are always
+ * consitent with each other, but mddev->raid_disks does not.
+ */
 static int linear_congested(struct mddev *mddev, int bits)
 {
 	struct linear_conf *conf;
 	int i, ret = 0;
 
-	conf = mddev->private;
+	rcu_read_lock();
+	conf = rcu_dereference(mddev->private);
 
-	for (i = 0; i < mddev->raid_disks && !ret ; i++) {
+	for (i = 0; i < conf->raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
 		ret |= bdi_congested(q->backing_dev_info, bits);
 	}
 
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -144,6 +152,19 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 			conf->disks[i-1].end_sector +
 			conf->disks[i].rdev->sectors;
 
+	/*
+	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
+	 * keep a copy of mddev->raid_disks in struct linear_conf is,
+	 * mddev->raid_disks may not be consistent with pointers number of
+	 * conf->disks[] when it is updated in linear_add() and used to
+	 * iterate old conf->disks[] earray in linear_congested().
+	 * Here conf->raid_disks is always consitent with number of
+	 * pointers in conf->disks[] array, and mddev->private is updated
+	 * with rcu_assign_pointer() in linear_addr(), such race can be
+	 * avoided.
+	 */
+	conf->raid_disks = raid_disks;
+
 	return conf;
 
 out:
@@ -196,15 +217,24 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 	if (!newconf)
 		return -ENOMEM;
 
+	/* newconf->raid_disks already keeps a copy of * the increased
+	 * value of mddev->raid_disks, WARN_ONCE() is just used to make
+	 * sure of this. It is possible that oldconf is still referenced
+	 * in linear_congested(), therefore kfree_rcu() is used to free
+	 * oldconf until no one uses it anymore.
+	 */
 	mddev_suspend(mddev);
-	oldconf = mddev->private;
+	oldconf = rcu_dereference_protected(mddev->private,
+			lockdep_is_held(&mddev->reconfig_mutex));
 	mddev->raid_disks++;
-	mddev->private = newconf;
+	WARN_ONCE(mddev->raid_disks != newconf->raid_disks,
+		"copied raid_disks doesn't match mddev->raid_disks");
+	rcu_assign_pointer(mddev->private, newconf);
 	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev_resume(mddev);
 	revalidate_disk(mddev->gendisk);
-	kfree(oldconf);
+	kfree_rcu(oldconf, rcu);
 	return 0;
 }
 
@@ -262,6 +292,7 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
 				trace_block_bio_remap(bdev_get_queue(split->bi_bdev),
 						      split, disk_devt(mddev->gendisk),
 						      bio_sector);
+			mddev_check_writesame(mddev, split);
 			generic_make_request(split);
 		}
 	} while (split != bio);
diff --git a/drivers/md/linear.h b/drivers/md/linear.h
index b685ddd7d7f7..8d392e6098b3 100644
--- a/drivers/md/linear.h
+++ b/drivers/md/linear.h
@@ -10,6 +10,7 @@ struct linear_conf
 {
 	struct rcu_head		rcu;
 	sector_t		array_sectors;
+	int			raid_disks; /* a copy of mddev->raid_disks */
 	struct dev_info		disks[0];
 };
 #endif
diff --git a/drivers/md/md.c b/drivers/md/md.c
index ba485dcf1064..985374f20e2e 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -190,16 +190,6 @@ struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
 }
 EXPORT_SYMBOL_GPL(bio_alloc_mddev);
 
-struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask,
-			    struct mddev *mddev)
-{
-	if (!mddev || !mddev->bio_set)
-		return bio_clone(bio, gfp_mask);
-
-	return bio_clone_bioset(bio, gfp_mask, mddev->bio_set);
-}
-EXPORT_SYMBOL_GPL(bio_clone_mddev);
-
 /*
  * We have a system wide 'event count' that is incremented
  * on any 'interesting' event, and readers of /proc/mdstat
@@ -5228,8 +5218,11 @@ int md_run(struct mddev *mddev)
 		sysfs_notify_dirent_safe(rdev->sysfs_state);
 	}
 
-	if (mddev->bio_set == NULL)
+	if (mddev->bio_set == NULL) {
 		mddev->bio_set = bioset_create(BIO_POOL_SIZE, 0);
+		if (!mddev->bio_set)
+			return -ENOMEM;
+	}
 
 	spin_lock(&pers_lock);
 	pers = find_pers(mddev->level, mddev->clevel);
@@ -8980,7 +8973,14 @@ static __exit void md_exit(void)
 
 	for_each_mddev(mddev, tmp) {
 		export_array(mddev);
+		mddev->ctime = 0;
 		mddev->hold_active = 0;
+		/*
+		 * for_each_mddev() will call mddev_put() at the end of each
+		 * iteration.  As the mddev is now fully clear, this will
+		 * schedule the mddev for destruction by a workqueue, and the
+		 * destroy_workqueue() below will wait for that to complete.
+		 */
 	}
 	destroy_workqueue(md_misc_wq);
 	destroy_workqueue(md_wq);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 2a514036a83d..b8859cbf84b6 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -673,8 +673,6 @@ extern void md_rdev_clear(struct md_rdev *rdev);
 
 extern void mddev_suspend(struct mddev *mddev);
 extern void mddev_resume(struct mddev *mddev);
-extern struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask,
-				   struct mddev *mddev);
 extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
 				   struct mddev *mddev);
 
@@ -710,4 +708,11 @@ static inline void mddev_clear_unsupported_flags(struct mddev *mddev,
 {
 	mddev->flags &= ~unsupported_flags;
 }
+
+static inline void mddev_check_writesame(struct mddev *mddev, struct bio *bio)
+{
+	if (bio_op(bio) == REQ_OP_WRITE_SAME &&
+	    !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors)
+		mddev->queue->limits.max_write_same_sectors = 0;
+}
 #endif /* _MD_MD_H */
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index d457afa672d5..79a12b59250b 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -138,6 +138,7 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio)
 	mp_bh->bio.bi_opf |= REQ_FAILFAST_TRANSPORT;
 	mp_bh->bio.bi_end_io = multipath_end_request;
 	mp_bh->bio.bi_private = mp_bh;
+	mddev_check_writesame(mddev, &mp_bh->bio);
 	generic_make_request(&mp_bh->bio);
 	return;
 }
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index d6585239bff2..93347ca7c7a6 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -503,6 +503,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 				trace_block_bio_remap(bdev_get_queue(split->bi_bdev),
 						      split, disk_devt(mddev->gendisk),
 						      bio_sector);
+			mddev_check_writesame(mddev, split);
 			generic_make_request(split);
 		}
 	} while (split != bio);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 830ff2b20346..7453d94eeed7 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -71,9 +71,8 @@
  */
 static int max_queued_requests = 1024;
 
-static void allow_barrier(struct r1conf *conf, sector_t start_next_window,
-			  sector_t bi_sector);
-static void lower_barrier(struct r1conf *conf);
+static void allow_barrier(struct r1conf *conf, sector_t sector_nr);
+static void lower_barrier(struct r1conf *conf, sector_t sector_nr);
 
 #define raid1_log(md, fmt, args...)				\
 	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0)
@@ -100,7 +99,6 @@ static void r1bio_pool_free(void *r1_bio, void *data)
 #define RESYNC_WINDOW_SECTORS (RESYNC_WINDOW >> 9)
 #define CLUSTER_RESYNC_WINDOW (16 * RESYNC_WINDOW)
 #define CLUSTER_RESYNC_WINDOW_SECTORS (CLUSTER_RESYNC_WINDOW >> 9)
-#define NEXT_NORMALIO_DISTANCE (3 * RESYNC_WINDOW_SECTORS)
 
 static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 {
@@ -205,6 +203,7 @@ static void free_r1bio(struct r1bio *r1_bio)
 static void put_buf(struct r1bio *r1_bio)
 {
 	struct r1conf *conf = r1_bio->mddev->private;
+	sector_t sect = r1_bio->sector;
 	int i;
 
 	for (i = 0; i < conf->raid_disks * 2; i++) {
@@ -215,7 +214,7 @@ static void put_buf(struct r1bio *r1_bio)
 
 	mempool_free(r1_bio, conf->r1buf_pool);
 
-	lower_barrier(conf);
+	lower_barrier(conf, sect);
 }
 
 static void reschedule_retry(struct r1bio *r1_bio)
@@ -223,10 +222,12 @@ static void reschedule_retry(struct r1bio *r1_bio)
 	unsigned long flags;
 	struct mddev *mddev = r1_bio->mddev;
 	struct r1conf *conf = mddev->private;
+	int idx;
 
+	idx = sector_to_idx(r1_bio->sector);
 	spin_lock_irqsave(&conf->device_lock, flags);
 	list_add(&r1_bio->retry_list, &conf->retry_list);
-	conf->nr_queued ++;
+	atomic_inc(&conf->nr_queued[idx]);
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
 	wake_up(&conf->wait_barrier);
@@ -243,7 +244,6 @@ static void call_bio_endio(struct r1bio *r1_bio)
 	struct bio *bio = r1_bio->master_bio;
 	int done;
 	struct r1conf *conf = r1_bio->mddev->private;
-	sector_t start_next_window = r1_bio->start_next_window;
 	sector_t bi_sector = bio->bi_iter.bi_sector;
 
 	if (bio->bi_phys_segments) {
@@ -269,7 +269,7 @@ static void call_bio_endio(struct r1bio *r1_bio)
 		 * Wake up any possible resync thread that waits for the device
 		 * to go idle.
 		 */
-		allow_barrier(conf, start_next_window, bi_sector);
+		allow_barrier(conf, bi_sector);
 	}
 }
 
@@ -517,6 +517,25 @@ static void raid1_end_write_request(struct bio *bio)
 		bio_put(to_put);
 }
 
+static sector_t align_to_barrier_unit_end(sector_t start_sector,
+					  sector_t sectors)
+{
+	sector_t len;
+
+	WARN_ON(sectors == 0);
+	/*
+	 * len is the number of sectors from start_sector to end of the
+	 * barrier unit which start_sector belongs to.
+	 */
+	len = round_up(start_sector + 1, BARRIER_UNIT_SECTOR_SIZE) -
+	      start_sector;
+
+	if (len > sectors)
+		len = sectors;
+
+	return len;
+}
+
 /*
  * This routine returns the disk from which the requested read should
  * be done. There is a per-array 'next expected sequential IO' sector
@@ -813,168 +832,228 @@ static void flush_pending_writes(struct r1conf *conf)
  */
 static void raise_barrier(struct r1conf *conf, sector_t sector_nr)
 {
+	int idx = sector_to_idx(sector_nr);
+
 	spin_lock_irq(&conf->resync_lock);
 
 	/* Wait until no block IO is waiting */
-	wait_event_lock_irq(conf->wait_barrier, !conf->nr_waiting,
+	wait_event_lock_irq(conf->wait_barrier,
+			    !atomic_read(&conf->nr_waiting[idx]),
 			    conf->resync_lock);
 
 	/* block any new IO from starting */
-	conf->barrier++;
-	conf->next_resync = sector_nr;
+	atomic_inc(&conf->barrier[idx]);
+	/*
+	 * In raise_barrier() we firstly increase conf->barrier[idx] then
+	 * check conf->nr_pending[idx]. In _wait_barrier() we firstly
+	 * increase conf->nr_pending[idx] then check conf->barrier[idx].
+	 * A memory barrier here to make sure conf->nr_pending[idx] won't
+	 * be fetched before conf->barrier[idx] is increased. Otherwise
+	 * there will be a race between raise_barrier() and _wait_barrier().
+	 */
+	smp_mb__after_atomic();
 
 	/* For these conditions we must wait:
 	 * A: while the array is in frozen state
-	 * B: while barrier >= RESYNC_DEPTH, meaning resync reach
-	 *    the max count which allowed.
-	 * C: next_resync + RESYNC_SECTORS > start_next_window, meaning
-	 *    next resync will reach to the window which normal bios are
-	 *    handling.
-	 * D: while there are any active requests in the current window.
+	 * B: while conf->nr_pending[idx] is not 0, meaning regular I/O
+	 *    existing in corresponding I/O barrier bucket.
+	 * C: while conf->barrier[idx] >= RESYNC_DEPTH, meaning reaches
+	 *    max resync count which allowed on current I/O barrier bucket.
 	 */
 	wait_event_lock_irq(conf->wait_barrier,
 			    !conf->array_frozen &&
-			    conf->barrier < RESYNC_DEPTH &&
-			    conf->current_window_requests == 0 &&
-			    (conf->start_next_window >=
-			     conf->next_resync + RESYNC_SECTORS),
+			     !atomic_read(&conf->nr_pending[idx]) &&
+			     atomic_read(&conf->barrier[idx]) < RESYNC_DEPTH,
 			    conf->resync_lock);
 
-	conf->nr_pending++;
+	atomic_inc(&conf->nr_pending[idx]);
 	spin_unlock_irq(&conf->resync_lock);
 }
 
-static void lower_barrier(struct r1conf *conf)
+static void lower_barrier(struct r1conf *conf, sector_t sector_nr)
 {
-	unsigned long flags;
-	BUG_ON(conf->barrier <= 0);
-	spin_lock_irqsave(&conf->resync_lock, flags);
-	conf->barrier--;
-	conf->nr_pending--;
-	spin_unlock_irqrestore(&conf->resync_lock, flags);
+	int idx = sector_to_idx(sector_nr);
+
+	BUG_ON(atomic_read(&conf->barrier[idx]) <= 0);
+
+	atomic_dec(&conf->barrier[idx]);
+	atomic_dec(&conf->nr_pending[idx]);
 	wake_up(&conf->wait_barrier);
 }
 
-static bool need_to_wait_for_sync(struct r1conf *conf, struct bio *bio)
+static void _wait_barrier(struct r1conf *conf, int idx)
 {
-	bool wait = false;
+	/*
+	 * We need to increase conf->nr_pending[idx] very early here,
+	 * then raise_barrier() can be blocked when it waits for
+	 * conf->nr_pending[idx] to be 0. Then we can avoid holding
+	 * conf->resync_lock when there is no barrier raised in same
+	 * barrier unit bucket. Also if the array is frozen, I/O
+	 * should be blocked until array is unfrozen.
+	 */
+	atomic_inc(&conf->nr_pending[idx]);
+	/*
+	 * In _wait_barrier() we firstly increase conf->nr_pending[idx], then
+	 * check conf->barrier[idx]. In raise_barrier() we firstly increase
+	 * conf->barrier[idx], then check conf->nr_pending[idx]. A memory
+	 * barrier is necessary here to make sure conf->barrier[idx] won't be
+	 * fetched before conf->nr_pending[idx] is increased. Otherwise there
+	 * will be a race between _wait_barrier() and raise_barrier().
+	 */
+	smp_mb__after_atomic();
 
-	if (conf->array_frozen || !bio)
-		wait = true;
-	else if (conf->barrier && bio_data_dir(bio) == WRITE) {
-		if ((conf->mddev->curr_resync_completed
-		     >= bio_end_sector(bio)) ||
-		    (conf->start_next_window + NEXT_NORMALIO_DISTANCE
-		     <= bio->bi_iter.bi_sector))
-			wait = false;
-		else
-			wait = true;
-	}
+	/*
+	 * Don't worry about checking two atomic_t variables at same time
+	 * here. If during we check conf->barrier[idx], the array is
+	 * frozen (conf->array_frozen is 1), and chonf->barrier[idx] is
+	 * 0, it is safe to return and make the I/O continue. Because the
+	 * array is frozen, all I/O returned here will eventually complete
+	 * or be queued, no race will happen. See code comment in
+	 * frozen_array().
+	 */
+	if (!READ_ONCE(conf->array_frozen) &&
+	    !atomic_read(&conf->barrier[idx]))
+		return;
 
-	return wait;
+	/*
+	 * After holding conf->resync_lock, conf->nr_pending[idx]
+	 * should be decreased before waiting for barrier to drop.
+	 * Otherwise, we may encounter a race condition because
+	 * raise_barrer() might be waiting for conf->nr_pending[idx]
+	 * to be 0 at same time.
+	 */
+	spin_lock_irq(&conf->resync_lock);
+	atomic_inc(&conf->nr_waiting[idx]);
+	atomic_dec(&conf->nr_pending[idx]);
+	/*
+	 * In case freeze_array() is waiting for
+	 * get_unqueued_pending() == extra
+	 */
+	wake_up(&conf->wait_barrier);
+	/* Wait for the barrier in same barrier unit bucket to drop. */
+	wait_event_lock_irq(conf->wait_barrier,
+			    !conf->array_frozen &&
+			     !atomic_read(&conf->barrier[idx]),
+			    conf->resync_lock);
+	atomic_inc(&conf->nr_pending[idx]);
+	atomic_dec(&conf->nr_waiting[idx]);
+	spin_unlock_irq(&conf->resync_lock);
 }
 
-static sector_t wait_barrier(struct r1conf *conf, struct bio *bio)
+static void wait_read_barrier(struct r1conf *conf, sector_t sector_nr)
 {
-	sector_t sector = 0;
+	int idx = sector_to_idx(sector_nr);
 
-	spin_lock_irq(&conf->resync_lock);
-	if (need_to_wait_for_sync(conf, bio)) {
-		conf->nr_waiting++;
-		/* Wait for the barrier to drop.
-		 * However if there are already pending
-		 * requests (preventing the barrier from
-		 * rising completely), and the
-		 * per-process bio queue isn't empty,
-		 * then don't wait, as we need to empty
-		 * that queue to allow conf->start_next_window
-		 * to increase.
-		 */
-		raid1_log(conf->mddev, "wait barrier");
-		wait_event_lock_irq(conf->wait_barrier,
-				    !conf->array_frozen &&
-				    (!conf->barrier ||
-				     ((conf->start_next_window <
-				       conf->next_resync + RESYNC_SECTORS) &&
-				      current->bio_list &&
-				      !bio_list_empty(current->bio_list))),
-				    conf->resync_lock);
-		conf->nr_waiting--;
-	}
-
-	if (bio && bio_data_dir(bio) == WRITE) {
-		if (bio->bi_iter.bi_sector >= conf->next_resync) {
-			if (conf->start_next_window == MaxSector)
-				conf->start_next_window =
-					conf->next_resync +
-					NEXT_NORMALIO_DISTANCE;
-
-			if ((conf->start_next_window + NEXT_NORMALIO_DISTANCE)
-			    <= bio->bi_iter.bi_sector)
-				conf->next_window_requests++;
-			else
-				conf->current_window_requests++;
-			sector = conf->start_next_window;
-		}
-	}
+	/*
+	 * Very similar to _wait_barrier(). The difference is, for read
+	 * I/O we don't need wait for sync I/O, but if the whole array
+	 * is frozen, the read I/O still has to wait until the array is
+	 * unfrozen. Since there is no ordering requirement with
+	 * conf->barrier[idx] here, memory barrier is unnecessary as well.
+	 */
+	atomic_inc(&conf->nr_pending[idx]);
 
-	conf->nr_pending++;
+	if (!READ_ONCE(conf->array_frozen))
+		return;
+
+	spin_lock_irq(&conf->resync_lock);
+	atomic_inc(&conf->nr_waiting[idx]);
+	atomic_dec(&conf->nr_pending[idx]);
+	/*
+	 * In case freeze_array() is waiting for
+	 * get_unqueued_pending() == extra
+	 */
+	wake_up(&conf->wait_barrier);
+	/* Wait for array to be unfrozen */
+	wait_event_lock_irq(conf->wait_barrier,
+			    !conf->array_frozen,
+			    conf->resync_lock);
+	atomic_inc(&conf->nr_pending[idx]);
+	atomic_dec(&conf->nr_waiting[idx]);
 	spin_unlock_irq(&conf->resync_lock);
-	return sector;
 }
 
-static void allow_barrier(struct r1conf *conf, sector_t start_next_window,
-			  sector_t bi_sector)
+static void wait_barrier(struct r1conf *conf, sector_t sector_nr)
 {
-	unsigned long flags;
+	int idx = sector_to_idx(sector_nr);
 
-	spin_lock_irqsave(&conf->resync_lock, flags);
-	conf->nr_pending--;
-	if (start_next_window) {
-		if (start_next_window == conf->start_next_window) {
-			if (conf->start_next_window + NEXT_NORMALIO_DISTANCE
-			    <= bi_sector)
-				conf->next_window_requests--;
-			else
-				conf->current_window_requests--;
-		} else
-			conf->current_window_requests--;
-
-		if (!conf->current_window_requests) {
-			if (conf->next_window_requests) {
-				conf->current_window_requests =
-					conf->next_window_requests;
-				conf->next_window_requests = 0;
-				conf->start_next_window +=
-					NEXT_NORMALIO_DISTANCE;
-			} else
-				conf->start_next_window = MaxSector;
-		}
-	}
-	spin_unlock_irqrestore(&conf->resync_lock, flags);
+	_wait_barrier(conf, idx);
+}
+
+static void wait_all_barriers(struct r1conf *conf)
+{
+	int idx;
+
+	for (idx = 0; idx < BARRIER_BUCKETS_NR; idx++)
+		_wait_barrier(conf, idx);
+}
+
+static void _allow_barrier(struct r1conf *conf, int idx)
+{
+	atomic_dec(&conf->nr_pending[idx]);
 	wake_up(&conf->wait_barrier);
 }
 
+static void allow_barrier(struct r1conf *conf, sector_t sector_nr)
+{
+	int idx = sector_to_idx(sector_nr);
+
+	_allow_barrier(conf, idx);
+}
+
+static void allow_all_barriers(struct r1conf *conf)
+{
+	int idx;
+
+	for (idx = 0; idx < BARRIER_BUCKETS_NR; idx++)
+		_allow_barrier(conf, idx);
+}
+
+/* conf->resync_lock should be held */
+static int get_unqueued_pending(struct r1conf *conf)
+{
+	int idx, ret;
+
+	for (ret = 0, idx = 0; idx < BARRIER_BUCKETS_NR; idx++)
+		ret += atomic_read(&conf->nr_pending[idx]) -
+			atomic_read(&conf->nr_queued[idx]);
+
+	return ret;
+}
+
 static void freeze_array(struct r1conf *conf, int extra)
 {
-	/* stop syncio and normal IO and wait for everything to
+	/* Stop sync I/O and normal I/O and wait for everything to
 	 * go quite.
-	 * We wait until nr_pending match nr_queued+extra
-	 * This is called in the context of one normal IO request
-	 * that has failed. Thus any sync request that might be pending
-	 * will be blocked by nr_pending, and we need to wait for
-	 * pending IO requests to complete or be queued for re-try.
-	 * Thus the number queued (nr_queued) plus this request (extra)
-	 * must match the number of pending IOs (nr_pending) before
-	 * we continue.
+	 * This is called in two situations:
+	 * 1) management command handlers (reshape, remove disk, quiesce).
+	 * 2) one normal I/O request failed.
+
+	 * After array_frozen is set to 1, new sync IO will be blocked at
+	 * raise_barrier(), and new normal I/O will blocked at _wait_barrier()
+	 * or wait_read_barrier(). The flying I/Os will either complete or be
+	 * queued. When everything goes quite, there are only queued I/Os left.
+
+	 * Every flying I/O contributes to a conf->nr_pending[idx], idx is the
+	 * barrier bucket index which this I/O request hits. When all sync and
+	 * normal I/O are queued, sum of all conf->nr_pending[] will match sum
+	 * of all conf->nr_queued[]. But normal I/O failure is an exception,
+	 * in handle_read_error(), we may call freeze_array() before trying to
+	 * fix the read error. In this case, the error read I/O is not queued,
+	 * so get_unqueued_pending() == 1.
+	 *
+	 * Therefore before this function returns, we need to wait until
+	 * get_unqueued_pendings(conf) gets equal to extra. For
+	 * normal I/O context, extra is 1, in rested situations extra is 0.
 	 */
 	spin_lock_irq(&conf->resync_lock);
 	conf->array_frozen = 1;
 	raid1_log(conf->mddev, "wait freeze");
-	wait_event_lock_irq_cmd(conf->wait_barrier,
-				conf->nr_pending == conf->nr_queued+extra,
-				conf->resync_lock,
-				flush_pending_writes(conf));
+	wait_event_lock_irq_cmd(
+		conf->wait_barrier,
+		get_unqueued_pending(conf) == extra,
+		conf->resync_lock,
+		flush_pending_writes(conf));
 	spin_unlock_irq(&conf->resync_lock);
 }
 static void unfreeze_array(struct r1conf *conf)
@@ -982,8 +1061,8 @@ static void unfreeze_array(struct r1conf *conf)
 	/* reverse the effect of the freeze */
 	spin_lock_irq(&conf->resync_lock);
 	conf->array_frozen = 0;
-	wake_up(&conf->wait_barrier);
 	spin_unlock_irq(&conf->resync_lock);
+	wake_up(&conf->wait_barrier);
 }
 
 /* duplicate the data pages for behind I/O
@@ -1070,11 +1149,28 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	kfree(plug);
 }
 
-static void raid1_read_request(struct mddev *mddev, struct bio *bio,
-				 struct r1bio *r1_bio)
+static inline struct r1bio *
+alloc_r1bio(struct mddev *mddev, struct bio *bio, sector_t sectors_handled)
+{
+	struct r1conf *conf = mddev->private;
+	struct r1bio *r1_bio;
+
+	r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
+
+	r1_bio->master_bio = bio;
+	r1_bio->sectors = bio_sectors(bio) - sectors_handled;
+	r1_bio->state = 0;
+	r1_bio->mddev = mddev;
+	r1_bio->sector = bio->bi_iter.bi_sector + sectors_handled;
+
+	return r1_bio;
+}
+
+static void raid1_read_request(struct mddev *mddev, struct bio *bio)
 {
 	struct r1conf *conf = mddev->private;
 	struct raid1_info *mirror;
+	struct r1bio *r1_bio;
 	struct bio *read_bio;
 	struct bitmap *bitmap = mddev->bitmap;
 	const int op = bio_op(bio);
@@ -1083,8 +1179,29 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	int max_sectors;
 	int rdisk;
 
-	wait_barrier(conf, bio);
+	/*
+	 * Still need barrier for READ in case that whole
+	 * array is frozen.
+	 */
+	wait_read_barrier(conf, bio->bi_iter.bi_sector);
+
+	r1_bio = alloc_r1bio(mddev, bio, 0);
 
+	/*
+	 * We might need to issue multiple reads to different
+	 * devices if there are bad blocks around, so we keep
+	 * track of the number of reads in bio->bi_phys_segments.
+	 * If this is 0, there is only one r1_bio and no locking
+	 * will be needed when requests complete.  If it is
+	 * non-zero, then it is the number of not-completed requests.
+	 */
+	bio->bi_phys_segments = 0;
+	bio_clear_flag(bio, BIO_SEG_VALID);
+
+	/*
+	 * make_request() can abort the operation when read-ahead is being
+	 * used and no empty request is available.
+	 */
 read_again:
 	rdisk = read_balance(conf, r1_bio, &max_sectors);
 
@@ -1106,9 +1223,8 @@ read_again:
 			   atomic_read(&bitmap->behind_writes) == 0);
 	}
 	r1_bio->read_disk = rdisk;
-	r1_bio->start_next_window = 0;
 
-	read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
+	read_bio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
 	bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector,
 		 max_sectors);
 
@@ -1151,22 +1267,16 @@ read_again:
 		 */
 		reschedule_retry(r1_bio);
 
-		r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
-
-		r1_bio->master_bio = bio;
-		r1_bio->sectors = bio_sectors(bio) - sectors_handled;
-		r1_bio->state = 0;
-		r1_bio->mddev = mddev;
-		r1_bio->sector = bio->bi_iter.bi_sector + sectors_handled;
+		r1_bio = alloc_r1bio(mddev, bio, sectors_handled);
 		goto read_again;
 	} else
 		generic_make_request(read_bio);
 }
 
-static void raid1_write_request(struct mddev *mddev, struct bio *bio,
-				struct r1bio *r1_bio)
+static void raid1_write_request(struct mddev *mddev, struct bio *bio)
 {
 	struct r1conf *conf = mddev->private;
+	struct r1bio *r1_bio;
 	int i, disks;
 	struct bitmap *bitmap = mddev->bitmap;
 	unsigned long flags;
@@ -1176,7 +1286,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	int first_clone;
 	int sectors_handled;
 	int max_sectors;
-	sector_t start_next_window;
 
 	/*
 	 * Register the new request and wait if the reconstruction
@@ -1212,7 +1321,19 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		}
 		finish_wait(&conf->wait_barrier, &w);
 	}
-	start_next_window = wait_barrier(conf, bio);
+	wait_barrier(conf, bio->bi_iter.bi_sector);
+
+	r1_bio = alloc_r1bio(mddev, bio, 0);
+
+	/* We might need to issue multiple writes to different
+	 * devices if there are bad blocks around, so we keep
+	 * track of the number of writes in bio->bi_phys_segments.
+	 * If this is 0, there is only one r1_bio and no locking
+	 * will be needed when requests complete.  If it is
+	 * non-zero, then it is the number of not-completed requests.
+	 */
+	bio->bi_phys_segments = 0;
+	bio_clear_flag(bio, BIO_SEG_VALID);
 
 	if (conf->pending_count >= max_queued_requests) {
 		md_wakeup_thread(mddev->thread);
@@ -1233,7 +1354,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 	disks = conf->raid_disks * 2;
  retry_write:
-	r1_bio->start_next_window = start_next_window;
 	blocked_rdev = NULL;
 	rcu_read_lock();
 	max_sectors = r1_bio->sectors;
@@ -1300,25 +1420,15 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	if (unlikely(blocked_rdev)) {
 		/* Wait for this device to become unblocked */
 		int j;
-		sector_t old = start_next_window;
 
 		for (j = 0; j < i; j++)
 			if (r1_bio->bios[j])
 				rdev_dec_pending(conf->mirrors[j].rdev, mddev);
 		r1_bio->state = 0;
-		allow_barrier(conf, start_next_window, bio->bi_iter.bi_sector);
+		allow_barrier(conf, bio->bi_iter.bi_sector);
 		raid1_log(mddev, "wait rdev %d blocked", blocked_rdev->raid_disk);
 		md_wait_for_blocked_rdev(blocked_rdev, mddev);
-		start_next_window = wait_barrier(conf, bio);
-		/*
-		 * We must make sure the multi r1bios of bio have
-		 * the same value of bi_phys_segments
-		 */
-		if (bio->bi_phys_segments && old &&
-		    old != start_next_window)
-			/* Wait for the former r1bio(s) to complete */
-			wait_event(conf->wait_barrier,
-				   bio->bi_phys_segments == 1);
+		wait_barrier(conf, bio->bi_iter.bi_sector);
 		goto retry_write;
 	}
 
@@ -1341,13 +1451,12 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 	first_clone = 1;
 	for (i = 0; i < disks; i++) {
-		struct bio *mbio;
+		struct bio *mbio = NULL;
+		sector_t offset;
 		if (!r1_bio->bios[i])
 			continue;
 
-		mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		bio_trim(mbio, r1_bio->sector - bio->bi_iter.bi_sector,
-			 max_sectors);
+		offset = r1_bio->sector - bio->bi_iter.bi_sector;
 
 		if (first_clone) {
 			/* do behind I/O ?
@@ -1357,8 +1466,13 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			if (bitmap &&
 			    (atomic_read(&bitmap->behind_writes)
 			     < mddev->bitmap_info.max_write_behind) &&
-			    !waitqueue_active(&bitmap->behind_wait))
+			    !waitqueue_active(&bitmap->behind_wait)) {
+				mbio = bio_clone_bioset_partial(bio, GFP_NOIO,
+								mddev->bio_set,
+								offset << 9,
+								max_sectors << 9);
 				alloc_behind_pages(mbio, r1_bio);
+			}
 
 			bitmap_startwrite(bitmap, r1_bio->sector,
 					  r1_bio->sectors,
@@ -1366,6 +1480,19 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 						   &r1_bio->state));
 			first_clone = 0;
 		}
+
+		if (!mbio) {
+			if (r1_bio->behind_bvecs)
+				mbio = bio_clone_bioset_partial(bio, GFP_NOIO,
+								mddev->bio_set,
+								offset << 9,
+								max_sectors << 9);
+			else {
+				mbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
+				bio_trim(mbio, offset, max_sectors);
+			}
+		}
+
 		if (r1_bio->behind_bvecs) {
 			struct bio_vec *bvec;
 			int j;
@@ -1385,8 +1512,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 				   conf->mirrors[i].rdev->data_offset);
 		mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
 		mbio->bi_end_io	= raid1_end_write_request;
-		mbio->bi_opf = bio_op(bio) |
-			(bio->bi_opf & (REQ_SYNC | REQ_PREFLUSH | REQ_FUA));
+		mbio->bi_opf = bio_op(bio) | (bio->bi_opf & (REQ_SYNC | REQ_FUA));
 		if (test_bit(FailFast, &conf->mirrors[i].rdev->flags) &&
 		    !test_bit(WriteMostly, &conf->mirrors[i].rdev->flags) &&
 		    conf->raid_disks - mddev->degraded > 1)
@@ -1427,12 +1553,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		/* We need another r1_bio.  It has already been counted
 		 * in bio->bi_phys_segments