Merge tag 'for-5.13/drivers-2021-04-27' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:

 - MD changes via Song:
        - raid5 POWER fix
        - raid1 failure fix
        - UAF fix for md cluster
        - mddev_find_or_alloc() clean up
        - Fix NULL pointer deref with external bitmap
        - Performance improvement for raid10 discard requests
        - Fix missing information of /proc/mdstat

 - rsxx const qualifier removal (Arnd)

 - Expose allocated brd pages (Calvin)

 - rnbd via Gioh Kim:
        - Change maintainer
        - Change domain address of maintainers' email
        - Add polling IO mode and document update
        - Fix memory leak and some bug detected by static code analysis
          tools
        - Code refactoring

 - Series of floppy cleanups/fixes (Denis)

 - s390 dasd fixes (Julian)

 - kerneldoc fixes (Lee)

 - null_blk double free (Lv)

 - null_blk virtual boundary addition (Max)

 - Remove xsysace driver (Michal)

 - umem driver removal (Davidlohr)

 - ataflop fixes (Dan)

 - Revalidate disk removal (Christoph)

 - Bounce buffer cleanups (Christoph)

 - Mark lightnvm as deprecated (Christoph)

 - mtip32xx init cleanups (Shixin)

 - Various fixes (Tian, Gustavo, Coly, Yang, Zhang, Zhiqiang)

* tag 'for-5.13/drivers-2021-04-27' of git://git.kernel.dk/linux-block: (143 commits)
  async_xor: increase src_offs when dropping destination page
  drivers/block/null_blk/main: Fix a double free in null_init.
  md/raid1: properly indicate failure when ending a failed write request
  md-cluster: fix use-after-free issue when removing rdev
  nvme: introduce generic per-namespace chardev
  nvme: cleanup nvme_configure_apst
  nvme: do not try to reconfigure APST when the controller is not live
  nvme: add 'kato' sysfs attribute
  nvme: sanitize KATO setting
  nvmet: avoid queuing keep-alive timer if it is disabled
  brd: expose number of allocated pages in debugfs
  ataflop: fix off by one in ataflop_probe()
  ataflop: potential out of bounds in do_format()
  drbd: Fix fall-through warnings for Clang
  block/rnbd: Use strscpy instead of strlcpy
  block/rnbd-clt-sysfs: Remove copy buffer overlap in rnbd_clt_get_path_name
  block/rnbd-clt: Remove max_segment_size
  block/rnbd-clt: Generate kobject_uevent when the rnbd device state changes
  block/rnbd-srv: Remove unused arguments of rnbd_srv_rdma_ev
  Documentation/ABI/rnbd-clt: Add description for nr_poll_queues
  ...

18 files changed, 541 insertions, 196 deletions

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 8c371d5eef8e..097577ae3c47 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -482,8 +482,7 @@ void bch_bucket_free(struct cache_set *c, struct bkey *k)
 	unsigned int i;
 
 	for (i = 0; i < KEY_PTRS(k); i++)
-		__bch_bucket_free(PTR_CACHE(c, k, i),
-				  PTR_BUCKET(c, k, i));
+		__bch_bucket_free(c->cache, PTR_BUCKET(c, k, i));
 }
 
 int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
@@ -674,7 +673,7 @@ bool bch_alloc_sectors(struct cache_set *c,
 		SET_PTR_OFFSET(&b->key, i, PTR_OFFSET(&b->key, i) + sectors);
 
 		atomic_long_add(sectors,
-				&PTR_CACHE(c, &b->key, i)->sectors_written);
+				&c->cache->sectors_written);
 	}
 
 	if (b->sectors_free < c->cache->sb.block_size)
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 848dd4db1659..0a4551e165ab 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -804,13 +804,6 @@ static inline sector_t bucket_remainder(struct cache_set *c, sector_t s)
 	return s & (c->cache->sb.bucket_size - 1);
 }
 
-static inline struct cache *PTR_CACHE(struct cache_set *c,
-				      const struct bkey *k,
-				      unsigned int ptr)
-{
-	return c->cache;
-}
-
 static inline size_t PTR_BUCKET_NR(struct cache_set *c,
 				   const struct bkey *k,
 				   unsigned int ptr)
@@ -822,7 +815,7 @@ static inline struct bucket *PTR_BUCKET(struct cache_set *c,
 					const struct bkey *k,
 					unsigned int ptr)
 {
-	return PTR_CACHE(c, k, ptr)->buckets + PTR_BUCKET_NR(c, k, ptr);
+	return c->cache->buckets + PTR_BUCKET_NR(c, k, ptr);
 }
 
 static inline uint8_t gen_after(uint8_t a, uint8_t b)
@@ -841,7 +834,7 @@ static inline uint8_t ptr_stale(struct cache_set *c, const struct bkey *k,
 static inline bool ptr_available(struct cache_set *c, const struct bkey *k,
 				 unsigned int i)
 {
-	return (PTR_DEV(k, i) < MAX_CACHES_PER_SET) && PTR_CACHE(c, k, i);
+	return (PTR_DEV(k, i) < MAX_CACHES_PER_SET) && c->cache;
 }
 
 /* Btree key macros */
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index fe6dce125aba..183a58c89377 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -426,7 +426,7 @@ void __bch_btree_node_write(struct btree *b, struct closure *parent)
 	do_btree_node_write(b);
 
 	atomic_long_add(set_blocks(i, block_bytes(b->c->cache)) * b->c->cache->sb.block_size,
-			&PTR_CACHE(b->c, &b->key, 0)->btree_sectors_written);
+			&b->c->cache->btree_sectors_written);
 
 	b->written += set_blocks(i, block_bytes(b->c->cache));
 }
@@ -1161,7 +1161,7 @@ static void make_btree_freeing_key(struct btree *b, struct bkey *k)
 
 	for (i = 0; i < KEY_PTRS(k); i++)
 		SET_PTR_GEN(k, i,
-			    bch_inc_gen(PTR_CACHE(b->c, &b->key, i),
+			    bch_inc_gen(b->c->cache,
 					PTR_BUCKET(b->c, &b->key, i)));
 
 	mutex_unlock(&b->c->bucket_lock);
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 63e809f38e3f..116edda845c3 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -50,7 +50,7 @@ void bch_btree_verify(struct btree *b)
 	v->keys.ops = b->keys.ops;
 
 	bio = bch_bbio_alloc(b->c);
-	bio_set_dev(bio, PTR_CACHE(b->c, &b->key, 0)->bdev);
+	bio_set_dev(bio, b->c->cache->bdev);
 	bio->bi_iter.bi_sector	= PTR_OFFSET(&b->key, 0);
 	bio->bi_iter.bi_size	= KEY_SIZE(&v->key) << 9;
 	bio->bi_opf		= REQ_OP_READ | REQ_META;
diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c
index f4658a1f37b8..d626ffcbecb9 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -50,7 +50,7 @@ static bool __ptr_invalid(struct cache_set *c, const struct bkey *k)
 
 	for (i = 0; i < KEY_PTRS(k); i++)
 		if (ptr_available(c, k, i)) {
-			struct cache *ca = PTR_CACHE(c, k, i);
+			struct cache *ca = c->cache;
 			size_t bucket = PTR_BUCKET_NR(c, k, i);
 			size_t r = bucket_remainder(c, PTR_OFFSET(k, i));
 
@@ -71,7 +71,7 @@ static const char *bch_ptr_status(struct cache_set *c, const struct bkey *k)
 
 	for (i = 0; i < KEY_PTRS(k); i++)
 		if (ptr_available(c, k, i)) {
-			struct cache *ca = PTR_CACHE(c, k, i);
+			struct cache *ca = c->cache;
 			size_t bucket = PTR_BUCKET_NR(c, k, i);
 			size_t r = bucket_remainder(c, PTR_OFFSET(k, i));
 
diff --git a/drivers/md/bcache/features.c b/drivers/md/bcache/features.c
index d636b7b2d070..6d2b7b84a7b7 100644
--- a/drivers/md/bcache/features.c
+++ b/drivers/md/bcache/features.c
@@ -19,7 +19,7 @@ struct feature {
 static struct feature feature_list[] = {
 	{BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE,
 		"large_bucket"},
-	{0, 0, 0 },
+	{0, 0, NULL },
 };
 
 #define compose_feature_string(type)				\
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index dad71a6b7889..e4388fe3ab7e 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -36,7 +36,7 @@ void __bch_submit_bbio(struct bio *bio, struct cache_set *c)
 	struct bbio *b = container_of(bio, struct bbio, bio);
 
 	bio->bi_iter.bi_sector	= PTR_OFFSET(&b->key, 0);
-	bio_set_dev(bio, PTR_CACHE(c, &b->key, 0)->bdev);
+	bio_set_dev(bio, c->cache->bdev);
 
 	b->submit_time_us = local_clock_us();
 	closure_bio_submit(c, bio, bio->bi_private);
@@ -137,7 +137,7 @@ void bch_bbio_count_io_errors(struct cache_set *c, struct bio *bio,
 			      blk_status_t error, const char *m)
 {
 	struct bbio *b = container_of(bio, struct bbio, bio);
-	struct cache *ca = PTR_CACHE(c, &b->key, 0);
+	struct cache *ca = c->cache;
 	int is_read = (bio_data_dir(bio) == READ ? 1 : 0);
 
 	unsigned int threshold = op_is_write(bio_op(bio))
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index c6613e817333..61bd79babf7a 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -111,7 +111,7 @@ reread:		left = ca->sb.bucket_size - offset;
 			 * Check from the oldest jset for last_seq. If
 			 * i->j.seq < j->last_seq, it means the oldest jset
 			 * in list is expired and useless, remove it from
-			 * this list. Otherwise, j is a condidate jset for
+			 * this list. Otherwise, j is a candidate jset for
 			 * further following checks.
 			 */
 			while (!list_empty(list)) {
@@ -498,7 +498,7 @@ static void btree_flush_write(struct cache_set *c)
 		 * - If there are matched nodes recorded in btree_nodes[],
 		 *   they are clean now (this is why and how the oldest
 		 *   journal entry can be reclaimed). These selected nodes
-		 *   will be ignored and skipped in the folowing for-loop.
+		 *   will be ignored and skipped in the following for-loop.
 		 */
 		if (((btree_current_write(b)->journal - fifo_front_p) &
 		     mask) != 0) {
@@ -768,7 +768,7 @@ static void journal_write_unlocked(struct closure *cl)
 	w->data->csum		= csum_set(w->data);
 
 	for (i = 0; i < KEY_PTRS(k); i++) {
-		ca = PTR_CACHE(c, k, i);
+		ca = c->cache;
 		bio = &ca->journal.bio;
 
 		atomic_long_add(sectors, &ca->meta_sectors_written);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 03e1fe4de53d..2b6d6e9cd680 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1052,6 +1052,7 @@ static int cached_dev_status_update(void *arg)
 
 int bch_cached_dev_run(struct cached_dev *dc)
 {
+	int ret = 0;
 	struct bcache_device *d = &dc->disk;
 	char *buf = kmemdup_nul(dc->sb.label, SB_LABEL_SIZE, GFP_KERNEL);
 	char *env[] = {
@@ -1064,19 +1065,15 @@ int bch_cached_dev_run(struct cached_dev *dc)
 	if (dc->io_disable) {
 		pr_err("I/O disabled on cached dev %s\n",
 		       dc->backing_dev_name);
-		kfree(env[1]);
-		kfree(env[2]);
-		kfree(buf);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
 	if (atomic_xchg(&dc->running, 1)) {
-		kfree(env[1]);
-		kfree(env[2]);
-		kfree(buf);
 		pr_info("cached dev %s is running already\n",
 		       dc->backing_dev_name);
-		return -EBUSY;
+		ret = -EBUSY;
+		goto out;
 	}
 
 	if (!d->c &&
@@ -1097,15 +1094,13 @@ int bch_cached_dev_run(struct cached_dev *dc)
 	 * only class / kset properties are persistent
 	 */
 	kobject_uevent_env(&disk_to_dev(d->disk)->kobj, KOBJ_CHANGE, env);
-	kfree(env[1]);
-	kfree(env[2]);
-	kfree(buf);
 
 	if (sysfs_create_link(&d->kobj, &disk_to_dev(d->disk)->kobj, "dev") ||
 	    sysfs_create_link(&disk_to_dev(d->disk)->kobj,
 			      &d->kobj, "bcache")) {
 		pr_err("Couldn't create bcache dev <-> disk sysfs symlinks\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out;
 	}
 
 	dc->status_update_thread = kthread_run(cached_dev_status_update,
@@ -1114,7 +1109,11 @@ int bch_cached_dev_run(struct cached_dev *dc)
 		pr_warn("failed to create bcache_status_update kthread, continue to run without monitoring backing device status\n");
 	}
 
-	return 0;
+out:
+	kfree(env[1]);
+	kfree(env[2]);
+	kfree(buf);
+	return ret;
 }
 
 /*
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index c029f7443190..bca4a7c97da7 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -27,7 +27,7 @@ struct closure;
 
 #else /* DEBUG */
 
-#define EBUG_ON(cond)			do { if (cond); } while (0)
+#define EBUG_ON(cond)		do { if (cond) do {} while (0); } while (0)
 #define atomic_dec_bug(v)	atomic_dec(v)
 #define atomic_inc_bug(v, i)	atomic_inc(v)
 
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 82d4e0880a99..8120da278161 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -110,13 +110,13 @@ static void __update_writeback_rate(struct cached_dev *dc)
 		int64_t fps;
 
 		if (c->gc_stats.in_use <= BCH_WRITEBACK_FRAGMENT_THRESHOLD_MID) {
-			fp_term = dc->writeback_rate_fp_term_low *
+			fp_term = (int64_t)dc->writeback_rate_fp_term_low *
 			(c->gc_stats.in_use - BCH_WRITEBACK_FRAGMENT_THRESHOLD_LOW);
 		} else if (c->gc_stats.in_use <= BCH_WRITEBACK_FRAGMENT_THRESHOLD_HIGH) {
-			fp_term = dc->writeback_rate_fp_term_mid *
+			fp_term = (int64_t)dc->writeback_rate_fp_term_mid *
 			(c->gc_stats.in_use - BCH_WRITEBACK_FRAGMENT_THRESHOLD_MID);
 		} else {
-			fp_term = dc->writeback_rate_fp_term_high *
+			fp_term = (int64_t)dc->writeback_rate_fp_term_high *
 			(c->gc_stats.in_use - BCH_WRITEBACK_FRAGMENT_THRESHOLD_HIGH);
 		}
 		fps = div_s64(dirty, dirty_buckets) * fp_term;
@@ -416,7 +416,7 @@ static void read_dirty_endio(struct bio *bio)
 	struct dirty_io *io = w->private;
 
 	/* is_read = 1 */
-	bch_count_io_errors(PTR_CACHE(io->dc->disk.c, &w->key, 0),
+	bch_count_io_errors(io->dc->disk.c->cache,
 			    bio->bi_status, 1,
 			    "reading dirty data from cache");
 
@@ -510,8 +510,7 @@ static void read_dirty(struct cached_dev *dc)
 			dirty_init(w);
 			bio_set_op_attrs(&io->bio, REQ_OP_READ, 0);
 			io->bio.bi_iter.bi_sector = PTR_OFFSET(&w->key, 0);
-			bio_set_dev(&io->bio,
-				    PTR_CACHE(dc->disk.c, &w->key, 0)->bdev);
+			bio_set_dev(&io->bio, dc->disk.c->cache->bdev);
 			io->bio.bi_end_io	= read_dirty_endio;
 
 			if (bch_bio_alloc_pages(&io->bio, GFP_KERNEL))
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index 200c5d0f08bf..ea3130e11680 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -1722,6 +1722,8 @@ void md_bitmap_flush(struct mddev *mddev)
 	md_bitmap_daemon_work(mddev);
 	bitmap->daemon_lastrun -= sleep;
 	md_bitmap_daemon_work(mddev);
+	if (mddev->bitmap_info.external)
+		md_super_wait(mddev);
 	md_bitmap_update_sb(bitmap);
 }
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 21da0c48f6c2..49f897fbb89b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -734,78 +734,94 @@ void mddev_init(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(mddev_init);
 
+static struct mddev *mddev_find_locked(dev_t unit)
+{
+	struct mddev *mddev;
+
+	list_for_each_entry(mddev, &all_mddevs, all_mddevs)
+		if (mddev->unit == unit)
+			return mddev;
+
+	return NULL;
+}
+
+/* find an unused unit number */
+static dev_t mddev_alloc_unit(void)
+{
+	static int next_minor = 512;
+	int start = next_minor;
+	bool is_free = 0;
+	dev_t dev = 0;
+
+	while (!is_free) {
+		dev = MKDEV(MD_MAJOR, next_minor);
+		next_minor++;
+		if (next_minor > MINORMASK)
+			next_minor = 0;
+		if (next_minor == start)
+			return 0;		/* Oh dear, all in use. */
+		is_free = !mddev_find_locked(dev);
+	}
+
+	return dev;
+}
+
 static struct mddev *mddev_find(dev_t unit)
 {
-	struct mddev *mddev, *new = NULL;
+	struct mddev *mddev;
 
-	if (unit && MAJOR(unit) != MD_MAJOR)
-		unit &= ~((1<<MdpMinorShift)-1);
+	if (MAJOR(unit) != MD_MAJOR)
+		unit &= ~((1 << MdpMinorShift) - 1);
 
- retry:
 	spin_lock(&all_mddevs_lock);
+	mddev = mddev_find_locked(unit);
+	if (mddev)
+		mddev_get(mddev);
+	spin_unlock(&all_mddevs_lock);
 
-	if (unit) {
-		list_for_each_entry(mddev, &all_mddevs, all_mddevs)
-			if (mddev->unit == unit) {
-				mddev_get(mddev);
-				spin_unlock(&all_mddevs_lock);
-				kfree(new);
-				return mddev;
-			}
+	return mddev;
+}
 
-		if (new) {
-			list_add(&new->all_mddevs, &all_mddevs);
-			spin_unlock(&all_mddevs_lock);
-			new->hold_active = UNTIL_IOCTL;
-			return new;
-		}
-	} else if (new) {
-		/* find an unused unit number */
-		static int next_minor = 512;
-		int start = next_minor;
-		int is_free = 0;
-		int dev = 0;
-		while (!is_free) {
-			dev = MKDEV(MD_MAJOR, next_minor);
-			next_minor++;
-			if (next_minor > MINORMASK)
-				next_minor = 0;
-			if (next_minor == start) {
-				/* Oh dear, all in use. */
-				spin_unlock(&all_mddevs_lock);
-				kfree(new);
-				return NULL;
-			}
+static struct mddev *mddev_alloc(dev_t unit)
+{
+	struct mddev *new;
+	int error;
 
-			is_free = 1;
-			list_for_each_entry(mddev, &all_mddevs, all_mddevs)
-				if (mddev->unit == dev) {
-					is_free = 0;
-					break;
-				}
-		}
-		new->unit = dev;
-		new->md_minor = MINOR(dev);
-		new->hold_active = UNTIL_STOP;
-		list_add(&new->all_mddevs, &all_mddevs);
-		spin_unlock(&all_mddevs_lock);
-		return new;
-	}
-	spin_unlock(&all_mddevs_lock);
+	if (unit && MAJOR(unit) != MD_MAJOR)
+		unit &= ~((1 << MdpMinorShift) - 1);
 
 	new = kzalloc(sizeof(*new), GFP_KERNEL);
 	if (!new)
-		return NULL;
-
-	new->unit = unit;
-	if (MAJOR(unit) == MD_MAJOR)
-		new->md_minor = MINOR(unit);
-	else
-		new->md_minor = MINOR(unit) >> MdpMinorShift;
-
+		return ERR_PTR(-ENOMEM);
 	mddev_init(new);
 
-	goto retry;
+	spin_lock(&all_mddevs_lock);
+	if (unit) {
+		error = -EEXIST;
+		if (mddev_find_locked(unit))
+			goto out_free_new;
+		new->unit = unit;
+		if (MAJOR(unit) == MD_MAJOR)
+			new->md_minor = MINOR(unit);
+		else
+			new->md_minor = MINOR(unit) >> MdpMinorShift;
+		new->hold_active = UNTIL_IOCTL;
+	} else {
+		error = -ENODEV;
+		new->unit = mddev_alloc_unit();
+		if (!new->unit)
+			goto out_free_new;
+		new->md_minor = MINOR(new->unit);
+		new->hold_active = UNTIL_STOP;
+	}
+
+	list_add(&new->all_mddevs, &all_mddevs);
+	spin_unlock(&all_mddevs_lock);
+	return new;
+out_free_new:
+	spin_unlock(&all_mddevs_lock);
+	kfree(new);
+	return ERR_PTR(error);
 }
 
 static struct attribute_group md_redundancy_group;
@@ -5644,29 +5660,29 @@ static int md_alloc(dev_t dev, char *name)
 	 * writing to /sys/module/md_mod/parameters/new_array.
 	 */
 	static DEFINE_MUTEX(disks_mutex);
-	struct mddev *mddev = mddev_find(dev);
+	struct mddev *mddev;
 	struct gendisk *disk;
 	int partitioned;
 	int shift;
 	int unit;
-	int error;
+	int error ;
 
-	if (!mddev)
-		return -ENODEV;
-
-	partitioned = (MAJOR(mddev->unit) != MD_MAJOR);
-	shift = partitioned ? MdpMinorShift : 0;
-	unit = MINOR(mddev->unit) >> shift;
-
-	/* wait for any previous instance of this device to be
-	 * completely removed (mddev_delayed_delete).
+	/*
+	 * Wait for any previous instance of this device to be completely
+	 * removed (mddev_delayed_delete).
 	 */
 	flush_workqueue(md_misc_wq);
 
 	mutex_lock(&disks_mutex);
-	error = -EEXIST;
-	if (mddev->gendisk)
-		goto abort;
+	mddev = mddev_alloc(dev);
+	if (IS_ERR(mddev)) {
+		mutex_unlock(&disks_mutex);
+		return PTR_ERR(mddev);
+	}
+
+	partitioned = (MAJOR(mddev->unit) != MD_MAJOR);
+	shift = partitioned ? MdpMinorShift : 0;
+	unit = MINOR(mddev->unit) >> shift;
 
 	if (name && !dev) {
 		/* Need to ensure that 'name' is not a duplicate.
@@ -5678,6 +5694,7 @@ static int md_alloc(dev_t dev, char *name)
 			if (mddev2->gendisk &&
 			    strcmp(mddev2->gendisk->disk_name, name) == 0) {
 				spin_unlock(&all_mddevs_lock);
+				error = -EEXIST;
 				goto abort;
 			}
 		spin_unlock(&all_mddevs_lock);
@@ -6524,11 +6541,9 @@ static void autorun_devices(int part)
 
 		md_probe(dev);
 		mddev = mddev_find(dev);
-		if (!mddev || !mddev->gendisk) {
-			if (mddev)
-				mddev_put(mddev);
+		if (!mddev)
 			break;
-		}
+
 		if (mddev_lock(mddev))
 			pr_warn("md: %s locked, cannot run\n", mdname(mddev));
 		else if (mddev->raid_disks || mddev->major_version
@@ -7821,8 +7836,7 @@ static int md_open(struct block_device *bdev, fmode_t mode)
 		/* Wait until bdev->bd_disk is definitely gone */
 		if (work_pending(&mddev->del_work))
 			flush_workqueue(md_misc_wq);
-		/* Then retry the open from the top */
-		return -ERESTARTSYS;
+		return -EBUSY;
 	}
 	BUG_ON(mddev != bdev->bd_disk->private_data);
 
@@ -8153,7 +8167,11 @@ static void *md_seq_start(struct seq_file *seq, loff_t *pos)
 	loff_t l = *pos;
 	struct mddev *mddev;
 
-	if (l >= 0x10000)
+	if (l == 0x10000) {
+		++*pos;
+		return (void *)2;
+	}
+	if (l > 0x10000)
 		return NULL;
 	if (!l--)
 		/* header */
@@ -8575,6 +8593,26 @@ void md_write_end(struct mddev *mddev)
 
 EXPORT_SYMBOL(md_write_end);
 
+/* This is used by raid0 and raid10 */
+void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
+			struct bio *bio, sector_t start, sector_t size)
+{
+	struct bio *discard_bio = NULL;
+
+	if (__blkdev_issue_discard(rdev->bdev, start, size, GFP_NOIO, 0,
+			&discard_bio) || !discard_bio)
+		return;
+
+	bio_chain(discard_bio, bio);
+	bio_clone_blkg_association(discard_bio, bio);
+	if (mddev->gendisk)
+		trace_block_bio_remap(discard_bio,
+				disk_devt(mddev->gendisk),
+				bio->bi_iter.bi_sector);
+	submit_bio_noacct(discard_bio);
+}
+EXPORT_SYMBOL_GPL(md_submit_discard_bio);
+
 /* md_allow_write(mddev)
  * Calling this ensures that the array is marked 'active' so that writes
  * may proceed without blocking.  It is important to call this before
@@ -9251,11 +9289,11 @@ void md_check_recovery(struct mddev *mddev)
 		}
 
 		if (mddev_is_clustered(mddev)) {
-			struct md_rdev *rdev;
+			struct md_rdev *rdev, *tmp;
 			/* kick the device if another node issued a
 			 * remove disk.
 			 */
-			rdev_for_each(rdev, mddev) {
+			rdev_for_each_safe(rdev, tmp, mddev) {
 				if (test_and_clear_bit(ClusterRemove, &rdev->flags) &&
 						rdev->raid_disk < 0)
 					md_kick_rdev_from_array(rdev);
@@ -9569,7 +9607,7 @@ err_wq:
 static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct mdp_superblock_1 *sb = page_address(rdev->sb_page);
-	struct md_rdev *rdev2;
+	struct md_rdev *rdev2, *tmp;
 	int role, ret;
 	char b[BDEVNAME_SIZE];
 
@@ -9586,7 +9624,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 	}
 
 	/* Check for change of roles in the active devices */
-	rdev_for_each(rdev2, mddev) {
+	rdev_for_each_safe(rdev2, tmp, mddev) {
 		if (test_bit(Faulty, &rdev2->flags))
 			continue;
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index bcbba1b5ec4a..fb7eab58cfd5 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -713,6 +713,8 @@ extern void md_write_end(struct mddev *mddev);
 extern void md_done_sync(struct mddev *mddev, int blocks, int ok);
 extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
 extern void md_finish_reshape(struct mddev *mddev);
+void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
+			struct bio *bio, sector_t start, sector_t size);
 
 extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 67f157f2525d..e5d7411cba9b 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -477,7 +477,6 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 
 	for (disk = 0; disk < zone->nb_dev; disk++) {
 		sector_t dev_start, dev_end;
-		struct bio *discard_bio = NULL;
 		struct md_rdev *rdev;
 
 		if (disk < start_disk_index)
@@ -500,18 +499,9 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 
 		rdev = conf->devlist[(zone - conf->strip_zone) *
 			conf->strip_zone[0].nb_dev + disk];
-		if (__blkdev_issue_discard(rdev->bdev,
+		md_submit_discard_bio(mddev, rdev, bio,
 			dev_start + zone->dev_start + rdev->data_offset,
-			dev_end - dev_start, GFP_NOIO, 0, &discard_bio) ||
-		    !discard_bio)
-			continue;
-		bio_chain(discard_bio, bio);
-		bio_clone_blkg_association(discard_bio, bio);
-		if (mddev->gendisk)
-			trace_block_bio_remap(discard_bio,
-				disk_devt(mddev->gendisk),
-				bio->bi_iter.bi_sector);
-		submit_bio_noacct(discard_bio);
+			dev_end - dev_start);
 	}
 	bio_endio(bio);
 }
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index d2378765dc15..ced076ba560e 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -478,6 +478,8 @@ static void raid1_end_write_request(struct bio *bio)
 		if (!test_bit(Faulty, &rdev->flags))
 			set_bit(R1BIO_WriteError, &r1_bio->state);
 		else {
+			/* Fail the request */
+			set_bit(R1BIO_Degraded, &r1_bio->state);
 			/* Finished with this branch */
 			r1_bio->bios[mirror] = NULL;
 			to_put = bio;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index a9ae7d113492..13f5e6b2a73d 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -91,7 +91,7 @@ static inline struct r10bio *get_resync_r10bio(struct bio *bio)
 static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
 {
 	struct r10conf *conf = data;
-	int size = offsetof(struct r10bio, devs[conf->copies]);
+	int size = offsetof(struct r10bio, devs[conf->geo.raid_disks]);
 
 	/* allocate a r10bio with room for raid_disks entries in the
 	 * bios array */
@@ -238,7 +238,7 @@ static void put_all_bios(struct r10conf *conf, struct r10bio *r10_bio)
 {
 	int i;
 
-	for (i = 0; i < conf->copies; i++) {
+	for (i = 0; i < conf->geo.raid_disks; i++) {
 		struct bio **bio = & r10_bio->devs[i].bio;
 		if (!BIO_SPECIAL(*bio))
 			bio_put(*bio);
@@ -327,7 +327,7 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio,
 	int slot;
 	int repl = 0;
 
-	for (slot = 0; slot < conf->copies; slot++) {
+	for (slot = 0; slot < conf->geo.raid_disks; slot++) {
 		if (r10_bio->devs[slot].bio == bio)
 			break;
 		if (r10_bio->devs[slot].repl_bio == bio) {
@@ -336,7 +336,6 @@ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio,
 		}
 	}
 
-	BUG_ON(slot == conf->copies);
 	update_head_pos(slot, r10_bio);
 
 	if (slotp)
@@ -1274,12 +1273,77 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	}
 }
 
+static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio)
+{
+	int i;
+	struct r10conf *conf = mddev->private;
+	struct md_rdev *blocked_rdev;
+
+retry_wait:
+	blocked_rdev = NULL;
+	rcu_read_lock();
+	for (i = 0; i < conf->copies; i++) {
+		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		struct md_rdev *rrdev = rcu_dereference(
+			conf->mirrors[i].replacement);
+		if (rdev == rrdev)
+			rrdev = NULL;
+		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+			atomic_inc(&rdev->nr_pending);
+			blocked_rdev = rdev;
+			break;
+		}
+		if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) {
+			atomic_inc(&rrdev->nr_pending);
+			blocked_rdev = rrdev;
+			break;
+		}
+
+		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
+			sector_t first_bad;
+			sector_t dev_sector = r10_bio->devs[i].addr;
+			int bad_sectors;
+			int is_bad;
+
+			/*
+			 * Discard request doesn't care the write result
+			 * so it doesn't need to wait blocked disk here.
+			 */
+			if (!r10_bio->sectors)
+				continue;
+
+			is_bad = is_badblock(rdev, dev_sector, r10_bio->sectors,
+					     &first_bad, &bad_sectors);
+			if (is_bad < 0) {
+				/*
+				 * Mustn't write here until the bad block
+				 * is acknowledged
+				 */
+				atomic_inc(&rdev->nr_pending);
+				set_bit(BlockedBadBlocks, &rdev->flags);
+				blocked_rdev = rdev;
+				break;
+			}
+		}
+	}
+	rcu_read_unlock();
+
+	if (unlikely(blocked_rdev)) {
+		/* Have to wait for this device to get unblocked, then retry */
+		allow_barrier(conf);
+		raid10_log(conf->mddev, "%s wait rdev %d blocked",
+				__func__, blocked_rdev->raid_disk);
+		md_wait_for_blocked_rdev(blocked_rdev, mddev);
+		wait_barrier(conf);
+		goto retry_wait;
+	}
+}
+
 static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 				 struct r10bio *r10_bio)
 {
 	struct r10conf *conf = mddev->private;
 	int i;
-	struct md_rdev *blocked_rdev;
 	sector_t sectors;
 	int max_sectors;
 
@@ -1337,8 +1401,9 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 
 	r10_bio->read_slot = -1; /* make sure repl_bio gets freed */
 	raid10_find_phys(conf, r10_bio);
-retry_write:
-	blocked_rdev = NULL;
+
+	wait_blocked_dev(mddev, r10_bio);
+
 	rcu_read_lock();
 	max_sectors = r10_bio->sectors;
 
@@ -1349,16 +1414,6 @@ retry_write:
 			conf->mirrors[d].replacement);
 		if (rdev == rrdev)
 			rrdev = NULL;
-		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
-			atomic_inc(&rdev->nr_pending);
-			blocked_rdev = rdev;
-			break;
-		}
-		if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) {
-			atomic_inc(&rrdev->nr_pending);
-			blocked_rdev = rrdev;
-			break;
-		}
 		if (rdev && (test_bit(Faulty, &rdev->flags)))
 			rdev = NULL;
 		if (rrdev && (test_bit(Faulty, &rrdev->flags)))
@@ -1379,15 +1434,6 @@ retry_write:
 
 			is_bad = is_badblock(rdev, dev_sector, max_sectors,
 					     &first_bad, &bad_sectors);
-			if (is_bad < 0) {
-				/* Mustn't write here until the bad block
-				 * is acknowledged
-				 */
-				atomic_inc(&rdev->nr_pending);
-				set_bit(BlockedBadBlocks, &rdev->flags);
-				blocked_rdev = rdev;
-				break;
-			}
 			if (is_bad && first_bad <= dev_sector) {
 				/* Cannot write here at all */
 				bad_sectors -= (dev_sector - first_bad);
@@ -1423,35 +1469,6 @@ retry_write:
 	}
 	rcu_read_unlock();
 
-	if (unlikely(blocked_rdev)) {
-		/* Have to wait for this device to get unblocked, then retry */
-		int j;
-		int d;
-
-		for (j = 0; j < i; j++) {
-			if (r10_bio->devs[j].bio) {
-				d = r10_bio->devs[j].devnum;
-				rdev_dec_pending(conf->mirrors[d].rdev, mddev);
-			}
-			if (r10_bio->devs[j].repl_bio) {
-				struct md_rdev *rdev;
-				d = r10_bio->devs[j].devnum;
-				rdev = conf->mirrors[d].replacement;
-				if (!rdev) {
-					/* Race with remove_disk */
-					smp_mb();
-					rdev = conf->mirrors[d].rdev;
-				}
-				rdev_dec_pending(rdev, mddev);
-			}
-		}
-		allow_barrier(conf);
-		raid10_log(conf->mddev, "wait rdev %d blocked", blocked_rdev->raid_disk);
-		md_wait_for_blocked_rdev(blocked_rdev, mddev);
-		wait_barrier(conf);
-		goto retry_write;
-	}
-
 	if (max_sectors < r10_bio->sectors)
 		r10_bio->sectors = max_sectors;
 
@@ -1492,7 +1509,8 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
 	r10_bio->sector = bio->bi_iter.bi_sector;
 	r10_bio->state = 0;
 	r10_bio->read_slot = -1;
-	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->copies);
+	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) *
+			conf->geo.raid_disks);
 
 	if (bio_data_dir(bio) == READ)
 		raid10_read_request(mddev, bio, r10_bio);
@@ -1500,6 +1518,304 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
 		raid10_write_request(mddev, bio, r10_bio);
 }
 
+static void raid_end_discard_bio(struct r10bio *r10bio)
+{
+	struct r10conf *conf = r10bio->mddev->private;
+	struct r10bio *first_r10bio;
+
+	while (atomic_dec_and_test(&r10bio->remaining)) {
+
+		allow_barrier(conf);
+
+		if (!test_bit(R10BIO_Discard, &r10bio->state)) {
+			first_r10bio = (struct r10bio *)r10bio->master_bio;
+			free_r10bio(r10bio);
+			r10bio = first_r10bio;
+		} else {
+			md_write_end(r10bio->mddev);
+			bio_endio(r10bio->master_bio);
+			free_r10bio(r10bio);
+			break;
+		}
+	}
+}
+
+static void raid10_end_discard_request(struct bio *bio)
+{
+	struct r10bio *r10_bio = bio->bi_private;
+	struct r10conf *conf = r10_bio->mddev->private;
+	struct md_rdev *rdev = NULL;
+	int dev;
+	int slot, repl;
+
+	/*
+	 * We don't care the return value of discard bio
+	 */
+	if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
+		set_bit(R10BIO_Uptodate, &r10_bio->state);
+
+	dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
+	if (repl)
+		rdev = conf->mirrors[dev].replacement;
+	if (!rdev) {
+		/*
+		 * raid10_remove_disk uses smp_mb to make sure rdev is set to
+		 * replacement before setting replacement to NULL. It can read
+		 * rdev first without barrier protect even replacment is NULL
+		 */
+		smp_rmb();
+		rdev = conf->mirrors[dev].rdev;
+	}
+
+	raid_end_discard_bio(r10_bio);
+	rdev_dec_pending(rdev, conf->mddev);
+}
+
+/*
+ * There are some limitations to handle discard bio
+ * 1st, the discard size is bigger than stripe_size*2.
+ * 2st, if the discard bio spans reshape progress, we use the old way to
+ * handle discard bio
+ */
+static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
+{
+	struct r10conf *conf = mddev->private;
+	struct geom *geo = &conf->geo;
+	int far_copies = geo->far_copies;
+	bool first_copy = true;
+	struct r10bio *r10_bio, *first_r10bio;
+	struct bio *split;
+	int disk;
+	sector_t chunk;
+	unsigned int stripe_size;
+	unsigned int stripe_data_disks;
+	sector_t split_size;
+	sector_t bio_start, bio_end;
+	sector_t first_stripe_index, last_stripe_index;
+	sector_t start_disk_offset;
+	unsigned int start_disk_index;
+	sector_t end_disk_offset;
+	unsigned int end_disk_index;
+	unsigned int remainder;
+
+	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+		return -EAGAIN;
+
+	wait_barrier(conf);
+
+	/*
+	 * Check reshape again to avoid reshape happens after checking
+	 * MD_RECOVERY_RESHAPE and before wait_barrier
+	 */
+	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+		goto out;
+
+	if (geo->near_copies)
+		stripe_data_disks = geo->raid_disks / geo->near_copies +
+					geo->raid_disks % geo->near_copies;
+	else
+		stripe_data_disks = geo->raid_disks;
+
+	stripe_size = stripe_data_disks << geo->chunk_shift;
+
+	bio_start = bio->bi_iter.bi_sector;
+	bio_end = bio_end_sector(bio);
+
+	/*
+	 * Maybe one discard bio is smaller than strip size or across one
+	 * stripe and discard region is larger than one stripe size. For far
+	 * offset layout, if the discard region is not aligned with stripe
+	 * size, there is hole when we submit discard bio to member disk.
+	 * For simplicity, we only handle discard bio which discard region
+	 * is bigger than stripe_size * 2
+	 */
+	if (bio_sectors(bio) < stripe_size*2)
+		goto out;
+
+	/*
+	 * Keep bio aligned with strip size.
+	 */
+	div_u64_rem(bio_start, stripe_size, &remainder);
+	if (remainder) {
+		split_size = stripe_size - remainder;
+		split = bio_split(bio, split_size, GFP_NOIO, &conf->bio_split);
+		bio_chain(split, bio);
+		allow_barrier(conf);
+		/* Resend the fist split part */
+		submit_bio_noacct(split);
+		wait_barrier(conf);
+	}
+	div_u64_rem(bio_end, stripe_size, &remainder);
+	if (remainder) {
+		split_size = bio_sectors(bio) - remainder;
+		split = bio_split(bio, split_size, GFP_NOIO, &conf->bio_split);
+		bio_chain(split, bio);
+		allow_barrier(conf);
+		/* Resend the second split part */
+		submit_bio_noacct(bio);
+		bio = split;
+		wait_barrier(conf);
+	}
+
+	bio_start = bio->bi_iter.bi_sector;
+	bio_end = bio_end_sector(bio);
+
+	/*
+	 * Raid10 uses chunk as the unit to store data. It's similar like raid0.
+	 * One stripe contains the chunks from all member disk (one chunk from
+	 * one disk at the same HBA address). For layout detail, see 'man md 4'
+	 */
+	chunk = bio_start >> geo->chunk_shift;
+	chunk *= geo->near_copies;
+	first_stripe_index = chunk;
+	start_disk_index = sector_div(first_stripe_index, geo->raid_disks);
+	if (geo->far_offset)
+		first_stripe_index *= geo->far_copies;
+	start_disk_offset = (bio_start & geo->chunk_mask) +
+				(first_stripe_index << geo->chunk_shift);
+
+	chunk = bio_end >> geo->chunk_shift;
+	chunk *= geo->near_copies;
+	last_stripe_index = chunk;
+	end_disk_index = sector_div(last_stripe_index, geo->raid_disks);
+	if (geo->far_offset)
+		last_stripe_index *= geo->far_copies;
+	end_disk_offset = (bio_end & geo->chunk_mask) +
+				(last_stripe_index << geo->chunk_shift);
+
+retry_discard:
+	r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO);
+	r10_bio->mddev = mddev;
+	r10_bio->state = 0;
+	r10_bio->sectors = 0;
+	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * geo->raid_disks);
+	wait_blocked_dev(mddev, r10_bio);
+
+	/*
+	 * For far layout it needs more than one r10bio to cover all regions.
+	 * Inspired by raid10_sync_request, we can use the first r10bio->master_bio
+	 * to record the discard bio. Other r10bio->master_bio record the first
+	 * r10bio. The first r10bio only release after all other r10bios finish.
+	 * The discard bio returns only first r10bio finishes
+	 */
+	if (first_copy) {
+		r10_bio->master_bio = bio;
+		set_bit(R10BIO_Discard, &r10_bio->state);
+		first_copy = false;
+		first_r10bio = r10_bio;
+	} else
+		r10_bio->master_bio = (struct bio *)first_r10bio;
+
+	rcu_read_lock();
+	for (disk = 0; disk < geo->raid_disks; disk++) {
+		struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev);
+		struct md_rdev *rrdev = rcu_dereference(
+			conf->mirrors[disk].replacement);
+
+		r10_bio->devs[disk].bio = NULL;
+		r10_bio->devs[disk].repl_bio = NULL;
+
+		if (rdev && (test_bit(Faulty, &rdev->flags)))
+			rdev = NULL;
+		if (rrdev && (test_bit(Faulty, &rrdev->flags)))
+			rrdev = NULL;
+		if (!rdev && !rrdev)
+			continue;
+
+		if (rdev) {
+			r10_bio->devs[disk].bio = bio;
+			atomic_inc(&rdev->nr_pending);
+		}
+		if (rrdev) {
+			r10_bio->devs[disk].repl_bio = bio;
+			atomic_inc(&rrdev->nr_pending);
+		}
+	}
+	rcu_read_unlock();
+
+	atomic_set(&r10_bio->remaining, 1);
+	for (disk = 0; disk < geo->raid_disks; disk++) {
+		sector_t dev_start, dev_end;
+		struct bio *mbio, *rbio = NULL;
+		struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev);
+		struct md_rdev *rrdev = rcu_dereference(
+			conf->mirrors[disk].replacement);
+
+		/*
+		 * Now start to calculate the start and end address for each disk.
+		 * The space between dev_start and dev_end is the discard region.
+		 *
+		 * For dev_start, it needs to consider three conditions:
+		 * 1st, the disk is before start_disk, you can imagine the disk in
+		 * the next stripe. So the dev_start is the start address of next
+		 * stripe.
+		 * 2st, the disk is after start_disk, it means the disk is at the
+		 * same stripe of first disk
+		 * 3st, the first disk itself, we can use start_disk_offset directly
+		 */
+		if (disk < start_disk_index)
+			dev_start = (first_stripe_index + 1) * mddev->chunk_sectors;
+		else if (disk > start_disk_index)
+			dev_start = first_stripe_index * mddev->chunk_sectors;
+		else
+			dev_start = start_disk_offset;
+
+		if (disk < end_disk_index)
+			dev_end = (last_stripe_index + 1) * mddev->chunk_sectors;
+		else if (disk > end_disk_index)
+			dev_end = last_stripe_index * mddev->chunk_sectors;
+		else
+			dev_end = end_disk_offset;
+
+		/*
+		 * It only handles discard bio which size is >= stripe size, so
+		 * dev_end > dev_start all the time
+		 */
+		if (r10_bio->devs[disk].bio) {
+			mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
+			mbio->bi_end_io = raid10_end_discard_request;
+			mbio->bi_private = r10_bio;
+			r10_bio->devs[disk].bio = mbio;
+			r10_bio->devs[disk].devnum = disk;
+			atomic_inc(&r10_bio->remaining);
+			md_submit_discard_bio(mddev, rdev, mbio,
+					dev_start + choose_data_offset(r10_bio, rdev),
+					dev_end - dev_start);
+			bio_endio(mbio);
+		}
+		if (r10_bio->devs[disk].repl_bio) {
+			rbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
+			rbio->bi_end_io = raid10_end_discard_request;
+			rbio->bi_private = r10_bio;
+			r10_bio->devs[disk].repl_bio = rbio;
+			r10_bio->devs[disk].devnum = disk;
+			atomic_inc(&r10_bio->remaining);
+			md_submit_discard_bio(mddev, rrdev, rbio,
+					dev_start + choose_data_offset(r10_bio, rrdev),
+					dev_end - dev_start);
+			bio_endio(rbio);
+		}
+	}
+
+	if (!geo->far_offset && --far_copies) {
+		first_stripe_index += geo->stride >> geo->chunk_shift;
+		start_disk_offset += geo->stride;
+		last_stripe_index += geo->stride >> geo->chunk_shift;
+		end_disk_offset += geo->stride;
+		atomic_inc(&first_r10bio->remaining);
+		raid_end_discard_bio(r10_bio);
+		wait_barrier(conf);
+		goto retry_discard;
+	}
+
+	raid_end_discard_bio(r10_bio);
+
+	return 0;
+out:
+	allow_barrier(conf);
+	return -EAGAIN;
+}
+
 static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
 {
 	struct r10conf *conf = mddev->private;
@@ -1514,6 +1830,10 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
 	if (!md_write_start(mddev, bio))
 		return false;
 
+	if (unlikely(bio_op(bio) == REQ_OP_DISCARD))
+		if (!raid10_handle_discard(mddev, bio))
+			return true;
+
 	/*
 	 * If this request crosses a chunk boundary, we need to split
 	 * it.
@@ -3753,7 +4073,7 @@ static int raid10_run(struct mddev *mddev)
 
 	if (mddev->queue) {
 		blk_queue_max_discard_sectors(mddev->queue,
-					      mddev->chunk_sectors);
+					      UINT_MAX);
 		blk_queue_max_write_same_sectors(mddev->queue, 0);
 		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
 		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h
index 79cd2b7d3128..1461fd55311b 100644
--- a/drivers/md/raid10.h
+++ b/drivers/md/raid10.h
@@ -179,5 +179,6 @@ enum r10bio_state {
 	R10BIO_Previous,
 /* failfast devices did receive failfast requests. */
 	R10BIO_FailFast,
+	R10BIO_Discard,
 };
 #endif